linux - Debian Package Tracker

general

source: linux (main)
version: 6.19.14-1
maintainer: Debian Kernel Team (archive) (DMD)
uploaders: Bastian Blank [DMD] – Salvatore Bonaccorso [DMD] – maximilian attems [DMD] – Ben Hutchings [DMD]
arch: all
std-ver: 4.2.0
VCS: Git (Browse, QA)

versions [more versions can be listed by madison] [old versions available from snapshot.debian.org]

[pool directory]

o-o-stable: 5.10.223-1
o-o-sec: 5.10.251-1
o-o-p-u: 5.10.223-1
oldstable: 6.1.159-1
old-sec: 6.1.164-1
old-bpo: 6.12.74-2~bpo12+1
old-p-u: 6.1.164-1
stable: 6.12.73-1
stable-sec: 6.12.74-2
stable-bpo: 6.19.11-1~bpo13+1
stable-p-u: 6.12.74-2
testing: 6.19.13-1
unstable: 6.19.14-1
exp: 7.0.1-1~exp1

versioned links

5.10.218-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
5.10.221-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
5.10.223-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
5.10.251-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.1.148-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.1.159-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.1.162-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.1.164-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.43-1~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.57-1~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.63-1~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.63-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.69-1~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.73-1~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.73-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.74-2~bpo12+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.12.74-2: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.16.3-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.16.12-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.17.8-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.17.13-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.5-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.9-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.9-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.10-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.12-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.12-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.13-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.14-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.15-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.18.15-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.6-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.6-2~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.6-2: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.8-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.8-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.10-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.10-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.11-1~bpo13+1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.11-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.12-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.13-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
6.19.14-1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
7.0-1~exp1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]
7.0.1-1~exp1: [.dsc, use dget on this link to retrieve source package] [changelog] [copyright] [rules] [control]

binaries

affs-modules-6.19.14+deb14-m68k-di
affs-modules-6.19.14+deb14-powerpc-di
affs-modules-6.19.14+deb14-powerpc64-di
ata-modules-6.19.14+deb14-alpha-generic-di
ata-modules-6.19.14+deb14-amd64-di
ata-modules-6.19.14+deb14-arm64-di
ata-modules-6.19.14+deb14-armmp-di
ata-modules-6.19.14+deb14-loong64-di
ata-modules-6.19.14+deb14-m68k-di
ata-modules-6.19.14+deb14-parisc-di
ata-modules-6.19.14+deb14-parisc64-di
ata-modules-6.19.14+deb14-powerpc-di
ata-modules-6.19.14+deb14-powerpc64-di
ata-modules-6.19.14+deb14-powerpc64le-di
ata-modules-6.19.14+deb14-riscv64-di
ata-modules-6.19.14+deb14-sparc64-di
base-modules-6.19.14+deb14-alpha-generic-di
base-modules-6.19.14+deb14-amd64-di
base-modules-6.19.14+deb14-arm64-di
base-modules-6.19.14+deb14-armmp-di
base-modules-6.19.14+deb14-loong64-di
base-modules-6.19.14+deb14-m68k-di
base-modules-6.19.14+deb14-parisc-di
base-modules-6.19.14+deb14-parisc64-di
base-modules-6.19.14+deb14-powerpc-di
base-modules-6.19.14+deb14-powerpc64-di
base-modules-6.19.14+deb14-powerpc64le-di
base-modules-6.19.14+deb14-riscv64-di
base-modules-6.19.14+deb14-s390x-di
base-modules-6.19.14+deb14-sh7751r-di
base-modules-6.19.14+deb14-sparc64-di
bpftool (1 bugs: 0, 0, 1, 0)
btrfs-modules-6.19.14+deb14-alpha-generic-di
btrfs-modules-6.19.14+deb14-amd64-di
btrfs-modules-6.19.14+deb14-arm64-di
btrfs-modules-6.19.14+deb14-armmp-di
btrfs-modules-6.19.14+deb14-loong64-di
btrfs-modules-6.19.14+deb14-m68k-di
btrfs-modules-6.19.14+deb14-parisc-di
btrfs-modules-6.19.14+deb14-parisc64-di
btrfs-modules-6.19.14+deb14-powerpc-di
btrfs-modules-6.19.14+deb14-powerpc64-di
btrfs-modules-6.19.14+deb14-powerpc64le-di
btrfs-modules-6.19.14+deb14-riscv64-di
btrfs-modules-6.19.14+deb14-s390x-di
btrfs-modules-6.19.14+deb14-sh7751r-di
btrfs-modules-6.19.14+deb14-sparc64-di
cdrom-core-modules-6.19.14+deb14-alpha-generic-di
cdrom-core-modules-6.19.14+deb14-amd64-di
cdrom-core-modules-6.19.14+deb14-arm64-di
cdrom-core-modules-6.19.14+deb14-armmp-di
cdrom-core-modules-6.19.14+deb14-loong64-di
cdrom-core-modules-6.19.14+deb14-m68k-di
cdrom-core-modules-6.19.14+deb14-parisc-di
cdrom-core-modules-6.19.14+deb14-parisc64-di
cdrom-core-modules-6.19.14+deb14-powerpc-di
cdrom-core-modules-6.19.14+deb14-powerpc64-di
cdrom-core-modules-6.19.14+deb14-powerpc64le-di
cdrom-core-modules-6.19.14+deb14-riscv64-di
cdrom-core-modules-6.19.14+deb14-s390x-di
cdrom-core-modules-6.19.14+deb14-sh7751r-di
cdrom-core-modules-6.19.14+deb14-sparc64-di
crypto-dm-modules-6.19.14+deb14-alpha-generic-di
crypto-dm-modules-6.19.14+deb14-amd64-di
crypto-dm-modules-6.19.14+deb14-arm64-di
crypto-dm-modules-6.19.14+deb14-armmp-di
crypto-dm-modules-6.19.14+deb14-loong64-di
crypto-dm-modules-6.19.14+deb14-parisc-di
crypto-dm-modules-6.19.14+deb14-parisc64-di
crypto-dm-modules-6.19.14+deb14-powerpc-di
crypto-dm-modules-6.19.14+deb14-powerpc64-di
crypto-dm-modules-6.19.14+deb14-powerpc64le-di
crypto-dm-modules-6.19.14+deb14-riscv64-di
crypto-dm-modules-6.19.14+deb14-s390x-di
crypto-dm-modules-6.19.14+deb14-sh7751r-di
crypto-dm-modules-6.19.14+deb14-sparc64-di
crypto-modules-6.19.14+deb14-alpha-generic-di
crypto-modules-6.19.14+deb14-amd64-di
crypto-modules-6.19.14+deb14-arm64-di
crypto-modules-6.19.14+deb14-armmp-di
crypto-modules-6.19.14+deb14-loong64-di
crypto-modules-6.19.14+deb14-m68k-di
crypto-modules-6.19.14+deb14-parisc-di
crypto-modules-6.19.14+deb14-parisc64-di
crypto-modules-6.19.14+deb14-powerpc-di
crypto-modules-6.19.14+deb14-powerpc64-di
crypto-modules-6.19.14+deb14-powerpc64le-di
crypto-modules-6.19.14+deb14-riscv64-di
crypto-modules-6.19.14+deb14-s390x-di
crypto-modules-6.19.14+deb14-sh7751r-di
crypto-modules-6.19.14+deb14-sparc64-di
dasd-extra-modules-6.19.14+deb14-s390x-di
dasd-modules-6.19.14+deb14-s390x-di
drm-core-modules-6.19.14+deb14-alpha-generic-di
drm-core-modules-6.19.14+deb14-amd64-di
drm-core-modules-6.19.14+deb14-armmp-di
drm-core-modules-6.19.14+deb14-loong64-di
drm-core-modules-6.19.14+deb14-powerpc-di
drm-core-modules-6.19.14+deb14-powerpc64-di
drm-core-modules-6.19.14+deb14-powerpc64le-di
drm-core-modules-6.19.14+deb14-riscv64-di
drm-core-modules-6.19.14+deb14-sparc64-di
ext4-modules-6.19.14+deb14-alpha-generic-di
ext4-modules-6.19.14+deb14-amd64-di
ext4-modules-6.19.14+deb14-arm64-di
ext4-modules-6.19.14+deb14-armmp-di
ext4-modules-6.19.14+deb14-loong64-di
ext4-modules-6.19.14+deb14-m68k-di
ext4-modules-6.19.14+deb14-parisc-di
ext4-modules-6.19.14+deb14-parisc64-di
ext4-modules-6.19.14+deb14-powerpc-di
ext4-modules-6.19.14+deb14-powerpc64-di
ext4-modules-6.19.14+deb14-powerpc64le-di
ext4-modules-6.19.14+deb14-riscv64-di
ext4-modules-6.19.14+deb14-s390x-di
ext4-modules-6.19.14+deb14-sh7751r-di
ext4-modules-6.19.14+deb14-sparc64-di
f2fs-modules-6.19.14+deb14-alpha-generic-di
f2fs-modules-6.19.14+deb14-amd64-di
f2fs-modules-6.19.14+deb14-arm64-di
f2fs-modules-6.19.14+deb14-armmp-di
f2fs-modules-6.19.14+deb14-loong64-di
f2fs-modules-6.19.14+deb14-parisc-di
f2fs-modules-6.19.14+deb14-parisc64-di
f2fs-modules-6.19.14+deb14-powerpc-di
f2fs-modules-6.19.14+deb14-powerpc64-di
f2fs-modules-6.19.14+deb14-powerpc64le-di
f2fs-modules-6.19.14+deb14-riscv64-di
f2fs-modules-6.19.14+deb14-s390x-di
f2fs-modules-6.19.14+deb14-sh7751r-di
f2fs-modules-6.19.14+deb14-sparc64-di
fat-modules-6.19.14+deb14-alpha-generic-di
fat-modules-6.19.14+deb14-amd64-di
fat-modules-6.19.14+deb14-arm64-di
fat-modules-6.19.14+deb14-armmp-di
fat-modules-6.19.14+deb14-loong64-di
fat-modules-6.19.14+deb14-m68k-di
fat-modules-6.19.14+deb14-parisc-di
fat-modules-6.19.14+deb14-parisc64-di
fat-modules-6.19.14+deb14-powerpc-di
fat-modules-6.19.14+deb14-powerpc64-di
fat-modules-6.19.14+deb14-powerpc64le-di
fat-modules-6.19.14+deb14-riscv64-di
fat-modules-6.19.14+deb14-s390x-di
fat-modules-6.19.14+deb14-sh7751r-di
fat-modules-6.19.14+deb14-sparc64-di
fb-modules-6.19.14+deb14-alpha-generic-di
fb-modules-6.19.14+deb14-amd64-di
fb-modules-6.19.14+deb14-arm64-di
fb-modules-6.19.14+deb14-armmp-di
fb-modules-6.19.14+deb14-loong64-di
fb-modules-6.19.14+deb14-parisc64-di
fb-modules-6.19.14+deb14-powerpc-di
fb-modules-6.19.14+deb14-powerpc64-di
fb-modules-6.19.14+deb14-powerpc64le-di
fb-modules-6.19.14+deb14-riscv64-di
fb-modules-6.19.14+deb14-sparc64-di
firewire-core-modules-6.19.14+deb14-amd64-di
firewire-core-modules-6.19.14+deb14-loong64-di
firewire-core-modules-6.19.14+deb14-powerpc-di
firewire-core-modules-6.19.14+deb14-powerpc64-di
firewire-core-modules-6.19.14+deb14-powerpc64le-di
firewire-core-modules-6.19.14+deb14-sh7751r-di
hfs-modules-6.19.14+deb14-m68k-di
hfs-modules-6.19.14+deb14-powerpc-di
hfs-modules-6.19.14+deb14-powerpc64-di
hyperv-daemons (1 bugs: 0, 1, 0, 0)
hypervisor-modules-6.19.14+deb14-powerpc64-di
hypervisor-modules-6.19.14+deb14-powerpc64le-di
input-modules-6.19.14+deb14-alpha-generic-di
input-modules-6.19.14+deb14-amd64-di
input-modules-6.19.14+deb14-arm64-di
input-modules-6.19.14+deb14-armmp-di
input-modules-6.19.14+deb14-loong64-di
input-modules-6.19.14+deb14-parisc-di
input-modules-6.19.14+deb14-parisc64-di
input-modules-6.19.14+deb14-powerpc-di
input-modules-6.19.14+deb14-powerpc64-di
input-modules-6.19.14+deb14-powerpc64le-di
input-modules-6.19.14+deb14-riscv64-di
input-modules-6.19.14+deb14-sparc64-di
intel-sdsi
isofs-modules-6.19.14+deb14-alpha-generic-di
isofs-modules-6.19.14+deb14-amd64-di
isofs-modules-6.19.14+deb14-arm64-di
isofs-modules-6.19.14+deb14-armmp-di
isofs-modules-6.19.14+deb14-loong64-di
isofs-modules-6.19.14+deb14-m68k-di
isofs-modules-6.19.14+deb14-parisc-di
isofs-modules-6.19.14+deb14-parisc64-di
isofs-modules-6.19.14+deb14-powerpc-di
isofs-modules-6.19.14+deb14-powerpc64-di
isofs-modules-6.19.14+deb14-powerpc64le-di
isofs-modules-6.19.14+deb14-riscv64-di
isofs-modules-6.19.14+deb14-s390x-di
isofs-modules-6.19.14+deb14-sh7751r-di
isofs-modules-6.19.14+deb14-sparc64-di
jfs-modules-6.19.14+deb14-alpha-generic-di
jfs-modules-6.19.14+deb14-amd64-di
jfs-modules-6.19.14+deb14-arm64-di
jfs-modules-6.19.14+deb14-armmp-di
jfs-modules-6.19.14+deb14-loong64-di
jfs-modules-6.19.14+deb14-parisc-di
jfs-modules-6.19.14+deb14-parisc64-di
jfs-modules-6.19.14+deb14-powerpc-di
jfs-modules-6.19.14+deb14-powerpc64-di
jfs-modules-6.19.14+deb14-powerpc64le-di
jfs-modules-6.19.14+deb14-riscv64-di
jfs-modules-6.19.14+deb14-sh7751r-di
jfs-modules-6.19.14+deb14-sparc64-di
libcpupower-dev
libcpupower1
linux-base-6.19.14+deb14-alpha-generic
linux-base-6.19.14+deb14-alpha-generic-di
linux-base-6.19.14+deb14-alpha-smp
linux-base-6.19.14+deb14-amd64
linux-base-6.19.14+deb14-amd64-di
linux-base-6.19.14+deb14-arm64
linux-base-6.19.14+deb14-arm64-16k
linux-base-6.19.14+deb14-arm64-di
linux-base-6.19.14+deb14-armmp
linux-base-6.19.14+deb14-armmp-di
linux-base-6.19.14+deb14-armmp-lpae
linux-base-6.19.14+deb14-cloud-amd64
linux-base-6.19.14+deb14-cloud-arm64
linux-base-6.19.14+deb14-loong64
linux-base-6.19.14+deb14-loong64-di
linux-base-6.19.14+deb14-m68k
linux-base-6.19.14+deb14-m68k-di
linux-base-6.19.14+deb14-parisc
linux-base-6.19.14+deb14-parisc-di
linux-base-6.19.14+deb14-parisc64
linux-base-6.19.14+deb14-parisc64-di
linux-base-6.19.14+deb14-powerpc
linux-base-6.19.14+deb14-powerpc-di
linux-base-6.19.14+deb14-powerpc-smp
linux-base-6.19.14+deb14-powerpc64
linux-base-6.19.14+deb14-powerpc64-64k
linux-base-6.19.14+deb14-powerpc64-di
linux-base-6.19.14+deb14-powerpc64le
linux-base-6.19.14+deb14-powerpc64le-64k
linux-base-6.19.14+deb14-powerpc64le-di
linux-base-6.19.14+deb14-riscv64
linux-base-6.19.14+deb14-riscv64-di
linux-base-6.19.14+deb14-rt-amd64
linux-base-6.19.14+deb14-rt-arm64
linux-base-6.19.14+deb14-s390x
linux-base-6.19.14+deb14-s390x-di
linux-base-6.19.14+deb14-sh7751r
linux-base-6.19.14+deb14-sh7751r-di
linux-base-6.19.14+deb14-sparc64
linux-base-6.19.14+deb14-sparc64-di
linux-base-6.19.14+deb14-sparc64-smp
linux-base-6.19.14+deb14-test
linux-base-6.19.14+deb14-test-di
linux-base-alpha-generic
linux-base-alpha-smp
linux-base-armmp
linux-base-armmp-lpae
linux-base-loong64
linux-base-m68k
linux-base-parisc
linux-base-parisc64
linux-base-powerpc
linux-base-powerpc-smp
linux-base-powerpc64
linux-base-powerpc64-64k
linux-base-powerpc64le
linux-base-powerpc64le-64k
linux-base-riscv64
linux-base-s390x
linux-base-sh7751r
linux-base-sparc64
linux-base-sparc64-smp
linux-binary-6.19.14+deb14-alpha-generic
linux-binary-6.19.14+deb14-alpha-generic-di
linux-binary-6.19.14+deb14-alpha-smp
linux-binary-6.19.14+deb14-armmp
linux-binary-6.19.14+deb14-armmp-di
linux-binary-6.19.14+deb14-armmp-lpae
linux-binary-6.19.14+deb14-loong64
linux-binary-6.19.14+deb14-loong64-di
linux-binary-6.19.14+deb14-m68k
linux-binary-6.19.14+deb14-m68k-di
linux-binary-6.19.14+deb14-parisc
linux-binary-6.19.14+deb14-parisc-di
linux-binary-6.19.14+deb14-parisc64
linux-binary-6.19.14+deb14-parisc64-di
linux-binary-6.19.14+deb14-powerpc
linux-binary-6.19.14+deb14-powerpc-di
linux-binary-6.19.14+deb14-powerpc-smp
linux-binary-6.19.14+deb14-powerpc64
linux-binary-6.19.14+deb14-powerpc64-64k
linux-binary-6.19.14+deb14-powerpc64-di
linux-binary-6.19.14+deb14-powerpc64le
linux-binary-6.19.14+deb14-powerpc64le-64k
linux-binary-6.19.14+deb14-powerpc64le-di
linux-binary-6.19.14+deb14-riscv64
linux-binary-6.19.14+deb14-riscv64-di
linux-binary-6.19.14+deb14-s390x
linux-binary-6.19.14+deb14-s390x-di
linux-binary-6.19.14+deb14-sh7751r
linux-binary-6.19.14+deb14-sh7751r-di
linux-binary-6.19.14+deb14-sparc64
linux-binary-6.19.14+deb14-sparc64-di
linux-binary-6.19.14+deb14-sparc64-smp
linux-binary-unsigned-6.19.14+deb14-amd64
linux-binary-unsigned-6.19.14+deb14-arm64
linux-binary-unsigned-6.19.14+deb14-arm64-16k
linux-binary-unsigned-6.19.14+deb14-cloud-amd64
linux-binary-unsigned-6.19.14+deb14-cloud-arm64
linux-binary-unsigned-6.19.14+deb14-rt-amd64
linux-binary-unsigned-6.19.14+deb14-rt-arm64
linux-binary-unsigned-6.19.14+deb14-test
linux-bpf-dev
linux-config-6.19
linux-cpupower
linux-doc
linux-doc-6.19
linux-headers-6.19.14+deb14-alpha-generic
linux-headers-6.19.14+deb14-alpha-smp
linux-headers-6.19.14+deb14-amd64
linux-headers-6.19.14+deb14-arm64
linux-headers-6.19.14+deb14-arm64-16k
linux-headers-6.19.14+deb14-armmp
linux-headers-6.19.14+deb14-armmp-lpae
linux-headers-6.19.14+deb14-cloud-amd64
linux-headers-6.19.14+deb14-cloud-arm64
linux-headers-6.19.14+deb14-common
linux-headers-6.19.14+deb14-loong64
linux-headers-6.19.14+deb14-m68k
linux-headers-6.19.14+deb14-parisc
linux-headers-6.19.14+deb14-parisc64
linux-headers-6.19.14+deb14-powerpc
linux-headers-6.19.14+deb14-powerpc-smp
linux-headers-6.19.14+deb14-powerpc64
linux-headers-6.19.14+deb14-powerpc64-64k
linux-headers-6.19.14+deb14-powerpc64le
linux-headers-6.19.14+deb14-powerpc64le-64k
linux-headers-6.19.14+deb14-riscv64
linux-headers-6.19.14+deb14-rt-amd64
linux-headers-6.19.14+deb14-rt-arm64
linux-headers-6.19.14+deb14-s390x
linux-headers-6.19.14+deb14-sh7751r
linux-headers-6.19.14+deb14-sparc64
linux-headers-6.19.14+deb14-sparc64-smp
linux-headers-6.19.14+deb14-test
linux-headers-alpha-generic
linux-headers-alpha-smp
linux-headers-armmp
linux-headers-armmp-lpae
linux-headers-loong64
linux-headers-m68k
linux-headers-parisc
linux-headers-parisc64
linux-headers-powerpc
linux-headers-powerpc-smp
linux-headers-powerpc64
linux-headers-powerpc64-64k
linux-headers-powerpc64le
linux-headers-powerpc64le-64k
linux-headers-riscv64
linux-headers-s390x
linux-headers-sh7751r
linux-headers-sparc64
linux-headers-sparc64-smp
linux-image-6.19.14+deb14-alpha-generic
linux-image-6.19.14+deb14-alpha-generic-dbg
linux-image-6.19.14+deb14-alpha-smp
linux-image-6.19.14+deb14-alpha-smp-dbg
linux-image-6.19.14+deb14-amd64-dbg
linux-image-6.19.14+deb14-arm64-16k-dbg
linux-image-6.19.14+deb14-arm64-dbg
linux-image-6.19.14+deb14-armmp
linux-image-6.19.14+deb14-armmp-dbg
linux-image-6.19.14+deb14-armmp-lpae
linux-image-6.19.14+deb14-armmp-lpae-dbg
linux-image-6.19.14+deb14-cloud-amd64-dbg
linux-image-6.19.14+deb14-cloud-arm64-dbg
linux-image-6.19.14+deb14-loong64
linux-image-6.19.14+deb14-loong64-dbg
linux-image-6.19.14+deb14-m68k
linux-image-6.19.14+deb14-m68k-dbg
linux-image-6.19.14+deb14-parisc
linux-image-6.19.14+deb14-parisc-dbg
linux-image-6.19.14+deb14-parisc64
linux-image-6.19.14+deb14-parisc64-dbg
linux-image-6.19.14+deb14-powerpc
linux-image-6.19.14+deb14-powerpc-dbg
linux-image-6.19.14+deb14-powerpc-smp
linux-image-6.19.14+deb14-powerpc-smp-dbg
linux-image-6.19.14+deb14-powerpc64
linux-image-6.19.14+deb14-powerpc64-64k
linux-image-6.19.14+deb14-powerpc64-64k-dbg
linux-image-6.19.14+deb14-powerpc64-dbg
linux-image-6.19.14+deb14-powerpc64le
linux-image-6.19.14+deb14-powerpc64le-64k
linux-image-6.19.14+deb14-powerpc64le-64k-dbg
linux-image-6.19.14+deb14-powerpc64le-dbg
linux-image-6.19.14+deb14-riscv64
linux-image-6.19.14+deb14-riscv64-dbg
linux-image-6.19.14+deb14-rt-amd64-dbg
linux-image-6.19.14+deb14-rt-arm64-dbg
linux-image-6.19.14+deb14-s390x
linux-image-6.19.14+deb14-s390x-dbg
linux-image-6.19.14+deb14-sh7751r
linux-image-6.19.14+deb14-sh7751r-dbg
linux-image-6.19.14+deb14-sparc64
linux-image-6.19.14+deb14-sparc64-dbg
linux-image-6.19.14+deb14-sparc64-smp
linux-image-6.19.14+deb14-sparc64-smp-dbg
linux-image-6.19.14+deb14-test-dbg
linux-image-alpha-generic
linux-image-alpha-generic-dbg
linux-image-alpha-smp
linux-image-alpha-smp-dbg
linux-image-amd64-signed-template
linux-image-arm64-signed-template
linux-image-armmp
linux-image-armmp-dbg
linux-image-armmp-lpae
linux-image-armmp-lpae-dbg
linux-image-loong64 (1 bugs: 0, 1, 0, 0)
linux-image-loong64-dbg
linux-image-m68k
linux-image-m68k-dbg
linux-image-parisc
linux-image-parisc-dbg
linux-image-parisc64
linux-image-parisc64-dbg
linux-image-powerpc
linux-image-powerpc-dbg
linux-image-powerpc-smp
linux-image-powerpc-smp-dbg
linux-image-powerpc64
linux-image-powerpc64-64k
linux-image-powerpc64-64k-dbg
linux-image-powerpc64-dbg
linux-image-powerpc64le
linux-image-powerpc64le-64k
linux-image-powerpc64le-64k-dbg
linux-image-powerpc64le-dbg
linux-image-riscv64
linux-image-riscv64-dbg
linux-image-s390x
linux-image-s390x-dbg
linux-image-sh7751r
linux-image-sh7751r-dbg
linux-image-sparc64
linux-image-sparc64-dbg
linux-image-sparc64-smp
linux-image-sparc64-smp-dbg
linux-kbuild-6.19.14+deb14
linux-libc-dev (3 bugs: 0, 1, 2, 0)
linux-libc-dev-alpha-cross
linux-libc-dev-amd64-cross
linux-libc-dev-arc-cross
linux-libc-dev-arm64-cross
linux-libc-dev-armel-cross
linux-libc-dev-armhf-cross
linux-libc-dev-hppa-cross
linux-libc-dev-i386-cross
linux-libc-dev-loong64-cross
linux-libc-dev-m68k-cross
linux-libc-dev-mips-cross
linux-libc-dev-mips64-cross
linux-libc-dev-mips64el-cross
linux-libc-dev-mips64r6-cross
linux-libc-dev-mips64r6el-cross
linux-libc-dev-mipsel-cross
linux-libc-dev-mipsn32-cross
linux-libc-dev-mipsn32el-cross
linux-libc-dev-mipsn32r6-cross
linux-libc-dev-mipsn32r6el-cross
linux-libc-dev-mipsr6-cross
linux-libc-dev-mipsr6el-cross
linux-libc-dev-powerpc-cross
linux-libc-dev-ppc64-cross
linux-libc-dev-ppc64el-cross
linux-libc-dev-riscv64-cross
linux-libc-dev-s390x-cross
linux-libc-dev-sh4-cross
linux-libc-dev-sparc64-cross
linux-libc-dev-x32-cross
linux-misc-tools
linux-modules-6.19.14+deb14-alpha-generic
linux-modules-6.19.14+deb14-alpha-smp
linux-modules-6.19.14+deb14-amd64
linux-modules-6.19.14+deb14-arm64
linux-modules-6.19.14+deb14-arm64-16k
linux-modules-6.19.14+deb14-armmp
linux-modules-6.19.14+deb14-armmp-lpae
linux-modules-6.19.14+deb14-cloud-amd64
linux-modules-6.19.14+deb14-cloud-arm64
linux-modules-6.19.14+deb14-loong64
linux-modules-6.19.14+deb14-m68k
linux-modules-6.19.14+deb14-parisc
linux-modules-6.19.14+deb14-parisc64
linux-modules-6.19.14+deb14-powerpc
linux-modules-6.19.14+deb14-powerpc-smp
linux-modules-6.19.14+deb14-powerpc64
linux-modules-6.19.14+deb14-powerpc64-64k
linux-modules-6.19.14+deb14-powerpc64le
linux-modules-6.19.14+deb14-powerpc64le-64k
linux-modules-6.19.14+deb14-riscv64
linux-modules-6.19.14+deb14-rt-amd64
linux-modules-6.19.14+deb14-rt-arm64
linux-modules-6.19.14+deb14-s390x
linux-modules-6.19.14+deb14-sh7751r
linux-modules-6.19.14+deb14-sparc64
linux-modules-6.19.14+deb14-sparc64-smp
linux-modules-6.19.14+deb14-test
linux-perf (4 bugs: 0, 2, 2, 0)
linux-source
linux-source-6.19
loop-modules-6.19.14+deb14-alpha-generic-di
loop-modules-6.19.14+deb14-amd64-di
loop-modules-6.19.14+deb14-arm64-di
loop-modules-6.19.14+deb14-armmp-di
loop-modules-6.19.14+deb14-loong64-di
loop-modules-6.19.14+deb14-m68k-di
loop-modules-6.19.14+deb14-parisc-di
loop-modules-6.19.14+deb14-parisc64-di
loop-modules-6.19.14+deb14-powerpc-di
loop-modules-6.19.14+deb14-powerpc64-di
loop-modules-6.19.14+deb14-powerpc64le-di
loop-modules-6.19.14+deb14-riscv64-di
loop-modules-6.19.14+deb14-s390x-di
loop-modules-6.19.14+deb14-sh7751r-di
md-modules-6.19.14+deb14-alpha-generic-di
md-modules-6.19.14+deb14-amd64-di
md-modules-6.19.14+deb14-arm64-di
md-modules-6.19.14+deb14-armmp-di
md-modules-6.19.14+deb14-loong64-di
md-modules-6.19.14+deb14-m68k-di
md-modules-6.19.14+deb14-parisc-di
md-modules-6.19.14+deb14-parisc64-di
md-modules-6.19.14+deb14-powerpc-di
md-modules-6.19.14+deb14-powerpc64-di
md-modules-6.19.14+deb14-powerpc64le-di
md-modules-6.19.14+deb14-riscv64-di
md-modules-6.19.14+deb14-s390x-di
md-modules-6.19.14+deb14-sh7751r-di
md-modules-6.19.14+deb14-sparc64-di
minix-modules-6.19.14+deb14-sh7751r-di
mmc-core-modules-6.19.14+deb14-amd64-di
mmc-core-modules-6.19.14+deb14-powerpc-di
mmc-core-modules-6.19.14+deb14-powerpc64-di
mmc-core-modules-6.19.14+deb14-riscv64-di
mmc-modules-6.19.14+deb14-amd64-di
mmc-modules-6.19.14+deb14-arm64-di
mmc-modules-6.19.14+deb14-armmp-di
mmc-modules-6.19.14+deb14-riscv64-di
mtd-core-modules-6.19.14+deb14-amd64-di
mtd-core-modules-6.19.14+deb14-loong64-di
mtd-core-modules-6.19.14+deb14-powerpc64-di
mtd-core-modules-6.19.14+deb14-powerpc64le-di
mtd-core-modules-6.19.14+deb14-s390x-di
mtd-modules-6.19.14+deb14-armmp-di
mtd-modules-6.19.14+deb14-loong64-di
mtd-modules-6.19.14+deb14-riscv64-di
multipath-modules-6.19.14+deb14-alpha-generic-di
multipath-modules-6.19.14+deb14-amd64-di
multipath-modules-6.19.14+deb14-arm64-di
multipath-modules-6.19.14+deb14-armmp-di
multipath-modules-6.19.14+deb14-loong64-di
multipath-modules-6.19.14+deb14-parisc-di
multipath-modules-6.19.14+deb14-parisc64-di
multipath-modules-6.19.14+deb14-powerpc-di
multipath-modules-6.19.14+deb14-powerpc64-di
multipath-modules-6.19.14+deb14-powerpc64le-di
multipath-modules-6.19.14+deb14-riscv64-di
multipath-modules-6.19.14+deb14-s390x-di
multipath-modules-6.19.14+deb14-sh7751r-di
multipath-modules-6.19.14+deb14-sparc64-di
nbd-modules-6.19.14+deb14-alpha-generic-di
nbd-modules-6.19.14+deb14-amd64-di
nbd-modules-6.19.14+deb14-arm64-di
nbd-modules-6.19.14+deb14-armmp-di
nbd-modules-6.19.14+deb14-loong64-di
nbd-modules-6.19.14+deb14-m68k-di
nbd-modules-6.19.14+deb14-parisc-di
nbd-modules-6.19.14+deb14-parisc64-di
nbd-modules-6.19.14+deb14-powerpc-di
nbd-modules-6.19.14+deb14-powerpc64-di
nbd-modules-6.19.14+deb14-powerpc64le-di
nbd-modules-6.19.14+deb14-riscv64-di
nbd-modules-6.19.14+deb14-s390x-di
nbd-modules-6.19.14+deb14-sh7751r-di
nbd-modules-6.19.14+deb14-sparc64-di
nic-modules-6.19.14+deb14-alpha-generic-di
nic-modules-6.19.14+deb14-amd64-di
nic-modules-6.19.14+deb14-arm64-di
nic-modules-6.19.14+deb14-armmp-di
nic-modules-6.19.14+deb14-loong64-di
nic-modules-6.19.14+deb14-m68k-di
nic-modules-6.19.14+deb14-parisc-di
nic-modules-6.19.14+deb14-parisc64-di
nic-modules-6.19.14+deb14-powerpc-di
nic-modules-6.19.14+deb14-powerpc64-di
nic-modules-6.19.14+deb14-powerpc64le-di
nic-modules-6.19.14+deb14-riscv64-di
nic-modules-6.19.14+deb14-s390x-di
nic-modules-6.19.14+deb14-sh7751r-di
nic-modules-6.19.14+deb14-sparc64-di
nic-pcmcia-modules-6.19.14+deb14-alpha-generic-di
nic-pcmcia-modules-6.19.14+deb14-amd64-di
nic-pcmcia-modules-6.19.14+deb14-powerpc-di
nic-pcmcia-modules-6.19.14+deb14-powerpc64-di
nic-shared-modules-6.19.14+deb14-alpha-generic-di
nic-shared-modules-6.19.14+deb14-amd64-di
nic-shared-modules-6.19.14+deb14-arm64-di
nic-shared-modules-6.19.14+deb14-armmp-di
nic-shared-modules-6.19.14+deb14-loong64-di
nic-shared-modules-6.19.14+deb14-m68k-di
nic-shared-modules-6.19.14+deb14-parisc-di
nic-shared-modules-6.19.14+deb14-parisc64-di
nic-shared-modules-6.19.14+deb14-powerpc-di
nic-shared-modules-6.19.14+deb14-powerpc64-di
nic-shared-modules-6.19.14+deb14-powerpc64le-di
nic-shared-modules-6.19.14+deb14-riscv64-di
nic-shared-modules-6.19.14+deb14-sh7751r-di
nic-shared-modules-6.19.14+deb14-sparc64-di
nic-usb-modules-6.19.14+deb14-alpha-generic-di
nic-usb-modules-6.19.14+deb14-amd64-di
nic-usb-modules-6.19.14+deb14-arm64-di
nic-usb-modules-6.19.14+deb14-armmp-di
nic-usb-modules-6.19.14+deb14-loong64-di
nic-usb-modules-6.19.14+deb14-parisc-di
nic-usb-modules-6.19.14+deb14-parisc64-di
nic-usb-modules-6.19.14+deb14-powerpc-di
nic-usb-modules-6.19.14+deb14-powerpc64-di
nic-usb-modules-6.19.14+deb14-powerpc64le-di
nic-usb-modules-6.19.14+deb14-riscv64-di
nic-usb-modules-6.19.14+deb14-sh7751r-di
nic-usb-modules-6.19.14+deb14-sparc64-di
nic-wireless-modules-6.19.14+deb14-alpha-generic-di
nic-wireless-modules-6.19.14+deb14-amd64-di
nic-wireless-modules-6.19.14+deb14-arm64-di
nic-wireless-modules-6.19.14+deb14-armmp-di
nic-wireless-modules-6.19.14+deb14-loong64-di
nic-wireless-modules-6.19.14+deb14-powerpc-di
nic-wireless-modules-6.19.14+deb14-powerpc64-di
nic-wireless-modules-6.19.14+deb14-powerpc64le-di
nic-wireless-modules-6.19.14+deb14-riscv64-di
pata-modules-6.19.14+deb14-alpha-generic-di
pata-modules-6.19.14+deb14-amd64-di
pata-modules-6.19.14+deb14-armmp-di
pata-modules-6.19.14+deb14-loong64-di
pata-modules-6.19.14+deb14-m68k-di
pata-modules-6.19.14+deb14-parisc-di
pata-modules-6.19.14+deb14-parisc64-di
pata-modules-6.19.14+deb14-powerpc-di
pata-modules-6.19.14+deb14-powerpc64-di
pata-modules-6.19.14+deb14-riscv64-di
pata-modules-6.19.14+deb14-sh7751r-di
pata-modules-6.19.14+deb14-sparc64-di
pcmcia-modules-6.19.14+deb14-alpha-generic-di
pcmcia-modules-6.19.14+deb14-amd64-di
pcmcia-modules-6.19.14+deb14-powerpc-di
pcmcia-modules-6.19.14+deb14-powerpc64-di
pcmcia-storage-modules-6.19.14+deb14-amd64-di
pcmcia-storage-modules-6.19.14+deb14-powerpc-di
pcmcia-storage-modules-6.19.14+deb14-powerpc64-di
ppp-modules-6.19.14+deb14-alpha-generic-di
ppp-modules-6.19.14+deb14-amd64-di
ppp-modules-6.19.14+deb14-arm64-di
ppp-modules-6.19.14+deb14-armmp-di
ppp-modules-6.19.14+deb14-loong64-di
ppp-modules-6.19.14+deb14-m68k-di
ppp-modules-6.19.14+deb14-parisc-di
ppp-modules-6.19.14+deb14-parisc64-di
ppp-modules-6.19.14+deb14-powerpc-di
ppp-modules-6.19.14+deb14-powerpc64-di
ppp-modules-6.19.14+deb14-powerpc64le-di
ppp-modules-6.19.14+deb14-riscv64-di
ppp-modules-6.19.14+deb14-sh7751r-di
ppp-modules-6.19.14+deb14-sparc64-di
rfkill-modules-6.19.14+deb14-amd64-di
rfkill-modules-6.19.14+deb14-loong64-di
rtla
sata-modules-6.19.14+deb14-alpha-generic-di
sata-modules-6.19.14+deb14-amd64-di
sata-modules-6.19.14+deb14-arm64-di
sata-modules-6.19.14+deb14-armmp-di
sata-modules-6.19.14+deb14-loong64-di
sata-modules-6.19.14+deb14-parisc-di
sata-modules-6.19.14+deb14-parisc64-di
sata-modules-6.19.14+deb14-powerpc-di
sata-modules-6.19.14+deb14-powerpc64-di
sata-modules-6.19.14+deb14-powerpc64le-di
sata-modules-6.19.14+deb14-riscv64-di
sata-modules-6.19.14+deb14-sh7751r-di
sata-modules-6.19.14+deb14-sparc64-di
scsi-core-modules-6.19.14+deb14-alpha-generic-di
scsi-core-modules-6.19.14+deb14-amd64-di
scsi-core-modules-6.19.14+deb14-arm64-di
scsi-core-modules-6.19.14+deb14-armmp-di
scsi-core-modules-6.19.14+deb14-loong64-di
scsi-core-modules-6.19.14+deb14-m68k-di
scsi-core-modules-6.19.14+deb14-parisc-di
scsi-core-modules-6.19.14+deb14-parisc64-di
scsi-core-modules-6.19.14+deb14-powerpc-di
scsi-core-modules-6.19.14+deb14-powerpc64-di
scsi-core-modules-6.19.14+deb14-powerpc64le-di
scsi-core-modules-6.19.14+deb14-riscv64-di
scsi-core-modules-6.19.14+deb14-s390x-di
scsi-core-modules-6.19.14+deb14-sparc64-di
scsi-modules-6.19.14+deb14-alpha-generic-di
scsi-modules-6.19.14+deb14-amd64-di
scsi-modules-6.19.14+deb14-arm64-di
scsi-modules-6.19.14+deb14-armmp-di
scsi-modules-6.19.14+deb14-loong64-di
scsi-modules-6.19.14+deb14-m68k-di
scsi-modules-6.19.14+deb14-parisc-di
scsi-modules-6.19.14+deb14-parisc64-di
scsi-modules-6.19.14+deb14-powerpc-di
scsi-modules-6.19.14+deb14-powerpc64-di
scsi-modules-6.19.14+deb14-powerpc64le-di
scsi-modules-6.19.14+deb14-riscv64-di
scsi-modules-6.19.14+deb14-s390x-di
scsi-modules-6.19.14+deb14-sparc64-di
scsi-nic-modules-6.19.14+deb14-alpha-generic-di
scsi-nic-modules-6.19.14+deb14-amd64-di
scsi-nic-modules-6.19.14+deb14-arm64-di
scsi-nic-modules-6.19.14+deb14-armmp-di
scsi-nic-modules-6.19.14+deb14-loong64-di
scsi-nic-modules-6.19.14+deb14-powerpc-di
scsi-nic-modules-6.19.14+deb14-powerpc64-di
scsi-nic-modules-6.19.14+deb14-powerpc64le-di
scsi-nic-modules-6.19.14+deb14-riscv64-di
serial-modules-6.19.14+deb14-alpha-generic-di
serial-modules-6.19.14+deb14-amd64-di
serial-modules-6.19.14+deb14-loong64-di
serial-modules-6.19.14+deb14-parisc-di
serial-modules-6.19.14+deb14-parisc64-di
serial-modules-6.19.14+deb14-powerpc-di
serial-modules-6.19.14+deb14-powerpc64-di
serial-modules-6.19.14+deb14-powerpc64le-di
sound-modules-6.19.14+deb14-amd64-di
sound-modules-6.19.14+deb14-arm64-di
sound-modules-6.19.14+deb14-armmp-di
sound-modules-6.19.14+deb14-loong64-di
sound-modules-6.19.14+deb14-sh7751r-di
speakup-modules-6.19.14+deb14-amd64-di
speakup-modules-6.19.14+deb14-arm64-di
speakup-modules-6.19.14+deb14-armmp-di
speakup-modules-6.19.14+deb14-loong64-di
speakup-modules-6.19.14+deb14-sh7751r-di
squashfs-modules-6.19.14+deb14-alpha-generic-di
squashfs-modules-6.19.14+deb14-amd64-di
squashfs-modules-6.19.14+deb14-arm64-di
squashfs-modules-6.19.14+deb14-armmp-di
squashfs-modules-6.19.14+deb14-loong64-di
squashfs-modules-6.19.14+deb14-m68k-di
squashfs-modules-6.19.14+deb14-parisc-di
squashfs-modules-6.19.14+deb14-parisc64-di
squashfs-modules-6.19.14+deb14-powerpc-di
squashfs-modules-6.19.14+deb14-powerpc64-di
squashfs-modules-6.19.14+deb14-powerpc64le-di
squashfs-modules-6.19.14+deb14-riscv64-di
squashfs-modules-6.19.14+deb14-sh7751r-di
squashfs-modules-6.19.14+deb14-sparc64-di
udf-modules-6.19.14+deb14-amd64-di
udf-modules-6.19.14+deb14-arm64-di
udf-modules-6.19.14+deb14-armmp-di
udf-modules-6.19.14+deb14-loong64-di
udf-modules-6.19.14+deb14-m68k-di
udf-modules-6.19.14+deb14-powerpc-di
udf-modules-6.19.14+deb14-powerpc64-di
udf-modules-6.19.14+deb14-powerpc64le-di
udf-modules-6.19.14+deb14-riscv64-di
udf-modules-6.19.14+deb14-s390x-di
udf-modules-6.19.14+deb14-sh7751r-di
udf-modules-6.19.14+deb14-sparc64-di
ufs-modules-6.19.14+deb14-sparc64-di
uinput-modules-6.19.14+deb14-amd64-di
uinput-modules-6.19.14+deb14-arm64-di
uinput-modules-6.19.14+deb14-armmp-di
uinput-modules-6.19.14+deb14-loong64-di
uinput-modules-6.19.14+deb14-powerpc-di
uinput-modules-6.19.14+deb14-powerpc64-di
uinput-modules-6.19.14+deb14-powerpc64le-di
usb-modules-6.19.14+deb14-alpha-generic-di
usb-modules-6.19.14+deb14-amd64-di
usb-modules-6.19.14+deb14-arm64-di
usb-modules-6.19.14+deb14-armmp-di
usb-modules-6.19.14+deb14-loong64-di
usb-modules-6.19.14+deb14-parisc-di
usb-modules-6.19.14+deb14-parisc64-di
usb-modules-6.19.14+deb14-powerpc-di
usb-modules-6.19.14+deb14-powerpc64-di
usb-modules-6.19.14+deb14-powerpc64le-di
usb-modules-6.19.14+deb14-riscv64-di
usb-modules-6.19.14+deb14-sparc64-di
usb-serial-modules-6.19.14+deb14-alpha-generic-di
usb-serial-modules-6.19.14+deb14-amd64-di
usb-serial-modules-6.19.14+deb14-arm64-di
usb-serial-modules-6.19.14+deb14-armmp-di
usb-serial-modules-6.19.14+deb14-loong64-di
usb-serial-modules-6.19.14+deb14-parisc-di
usb-serial-modules-6.19.14+deb14-parisc64-di
usb-serial-modules-6.19.14+deb14-powerpc-di
usb-serial-modules-6.19.14+deb14-powerpc64-di
usb-serial-modules-6.19.14+deb14-powerpc64le-di
usb-serial-modules-6.19.14+deb14-riscv64-di
usb-serial-modules-6.19.14+deb14-sh7751r-di
usb-serial-modules-6.19.14+deb14-sparc64-di
usb-storage-modules-6.19.14+deb14-alpha-generic-di
usb-storage-modules-6.19.14+deb14-amd64-di
usb-storage-modules-6.19.14+deb14-arm64-di
usb-storage-modules-6.19.14+deb14-armmp-di
usb-storage-modules-6.19.14+deb14-loong64-di
usb-storage-modules-6.19.14+deb14-parisc-di
usb-storage-modules-6.19.14+deb14-parisc64-di
usb-storage-modules-6.19.14+deb14-powerpc-di
usb-storage-modules-6.19.14+deb14-powerpc64-di
usb-storage-modules-6.19.14+deb14-powerpc64le-di
usb-storage-modules-6.19.14+deb14-riscv64-di
usb-storage-modules-6.19.14+deb14-sh7751r-di
usb-storage-modules-6.19.14+deb14-sparc64-di
usbip
xfs-modules-6.19.14+deb14-alpha-generic-di
xfs-modules-6.19.14+deb14-amd64-di
xfs-modules-6.19.14+deb14-arm64-di
xfs-modules-6.19.14+deb14-loong64-di
xfs-modules-6.19.14+deb14-parisc-di
xfs-modules-6.19.14+deb14-parisc64-di
xfs-modules-6.19.14+deb14-powerpc-di
xfs-modules-6.19.14+deb14-powerpc64-di
xfs-modules-6.19.14+deb14-powerpc64le-di
xfs-modules-6.19.14+deb14-riscv64-di
xfs-modules-6.19.14+deb14-s390x-di
xfs-modules-6.19.14+deb14-sh7751r-di
xfs-modules-6.19.14+deb14-sparc64-di

action needed

lintian reports 8149 errors and 61 warnings high

Lintian reports 8149 errors and 61 warnings about this package. You should make the package lintian clean getting rid of them.

Created: 2026-04-06 Last update: 2026-04-26 20:01

A new upstream version is available: 7.0.1 high

A new upstream version 7.0.1 is available, you should consider packaging it.

Created: 2025-11-27 Last update: 2026-04-26 18:17

570 security issues in trixie high

There are 570 open security issues in trixie.

569 important issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-6238: A buffer overflow vulnerability was found in the NVM Express (NVMe) driver in the Linux kernel. Only privileged user could specify a small meta buffer and let the device perform larger Direct Memory Access (DMA) into the same buffer, overwriting unrelated kernel memory, causing random kernel crashes and memory corruption.
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2019-15213: An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-16089: An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2024-14027: In the Linux kernel, the following vulnerability has been resolved: fs/xattr: missing fdput() in fremovexattr error path In the Linux kernel, the fremovexattr() syscall calls fdget() to acquire a file reference but returns early without calling fdput() when strncpy_from_user() fails on the name argument. In multi-threaded processes where fdget() takes the slow path, this permanently leaks one file reference per call, pinning the struct file and associated kernel objects in memory. An unprivileged local user can exploit this to cause kernel memory exhaustion. The issue was inadvertently fixed by commit a71874379ec8 ("xattr: switch to CLASS(fd)").
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-25740: A memory leak flaw was found in the UBI driver in drivers/mtd/ubi/attach.c in the Linux kernel through 6.7.4 for UBI_IOCATT, because kobj->name is not released.
CVE-2024-52560: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Mark inode as bad as soon as error detected in mi_enum_attr() Extended the `mi_enum_attr()` function interface with an additional parameter, `struct ntfs_inode *ni`, to allow marking the inode as bad as soon as an error is detected.
CVE-2024-56709: In the Linux kernel, the following vulnerability has been resolved: io_uring: check if iowq is killed before queuing task work can be executed after the task has gone through io_uring termination, whether it's the final task_work run or the fallback path. In this case, task work will find ->io_wq being already killed and null'ed, which is a problem if it then tries to forward the request to io_queue_iowq(). Make io_queue_iowq() fail requests in this case. Note that it also checks PF_KTHREAD, because the user can first close a DEFER_TASKRUN ring and shortly after kill the task, in which case ->iowq check would race.
CVE-2024-58015: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: Fix for out-of bound access error Selfgen stats are placed in a buffer using print_array_to_buf_index() function. Array length parameter passed to the function is too big, resulting in possible out-of bound memory error. Decreasing buffer size by one fixes faulty upper bound of passed array. Discovered in coverity scan, CID 1600742 and CID 1600758
CVE-2024-58074: In the Linux kernel, the following vulnerability has been resolved: drm/i915: Grab intel_display from the encoder to avoid potential oopsies Grab the intel_display from 'encoder' rather than 'state' in the encoder hooks to avoid the massive footgun that is intel_sanitize_encoder(), which passes NULL as the 'state' argument to encoder .disable() and .post_disable(). TODO: figure out how to actually fix intel_sanitize_encoder()...
CVE-2024-58093: In the Linux kernel, the following vulnerability has been resolved: PCI/ASPM: Fix link state exit during switch upstream function removal Before 456d8aa37d0f ("PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free"), we would free the ASPM link only after the last function on the bus pertaining to the given link was removed. That was too late. If function 0 is removed before sibling function, link->downstream would point to free'd memory after. After above change, we freed the ASPM parent link state upon any function removal on the bus pertaining to a given link. That is too early. If the link is to a PCIe switch with MFD on the upstream port, then removing functions other than 0 first would free a link which still remains parent_link to the remaining downstream ports. The resulting GPFs are especially frequent during hot-unplug, because pciehp removes devices on the link bus in reverse order. On that switch, function 0 is the virtual P2P bridge to the internal bus. Free exactly when function 0 is removed -- before the parent link is obsolete, but after all subordinate links are gone. [kwilczynski: commit log]
CVE-2024-58094: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before truncation in jfs_truncate_nolock() Added a check for "read-only" mode in the `jfs_truncate_nolock` function to avoid errors related to writing to a read-only filesystem. Call stack: block_write_begin() { jfs_write_failed() { jfs_truncate() { jfs_truncate_nolock() { txEnd() { ... log = JFS_SBI(tblk->sb)->log; // (log == NULL) If the `isReadOnly(ip)` condition is triggered in `jfs_truncate_nolock`, the function execution will stop, and no further data modification will occur. Instead, the `xtTruncate` function will be called with the "COMMIT_WMAP" flag, preventing modifications in "read-only" mode.
CVE-2024-58095: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before txBeginAnon() call Added a read-only check before calling `txBeginAnon` in `extAlloc` and `extRecord`. This prevents modification attempts on a read-only mounted filesystem, avoiding potential errors or crashes. Call trace: txBeginAnon+0xac/0x154 extAlloc+0xe8/0xdec fs/jfs/jfs_extent.c:78 jfs_get_block+0x340/0xb98 fs/jfs/inode.c:248 __block_write_begin_int+0x580/0x166c fs/buffer.c:2128 __block_write_begin fs/buffer.c:2177 [inline] block_write_begin+0x98/0x11c fs/buffer.c:2236 jfs_write_begin+0x44/0x88 fs/jfs/inode.c:299
CVE-2025-21709: In the Linux kernel, the following vulnerability has been resolved: kernel: be more careful about dup_mmap() failures and uprobe registering If a memory allocation fails during dup_mmap(), the maple tree can be left in an unsafe state for other iterators besides the exit path. All the locks are dropped before the exit_mmap() call (in mm/mmap.c), but the incomplete mm_struct can be reached through (at least) the rmap finding the vmas which have a pointer back to the mm_struct. Up to this point, there have been no issues with being able to find an mm_struct that was only partially initialised. Syzbot was able to make the incomplete mm_struct fail with recent forking changes, so it has been proven unsafe to use the mm_struct that hasn't been initialised, as referenced in the link below. Although 8ac662f5da19f ("fork: avoid inappropriate uprobe access to invalid mm") fixed the uprobe access, it does not completely remove the race. This patch sets the MMF_OOM_SKIP to avoid the iteration of the vmas on the oom side (even though this is extremely unlikely to be selected as an oom victim in the race window), and sets MMF_UNSTABLE to avoid other potential users from using a partially initialised mm_struct. When registering vmas for uprobe, skip the vmas in an mm that is marked unstable. Modifying a vma in an unstable mm may cause issues if the mm isn't fully initialised.
CVE-2025-21752: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't use btrfs_set_item_key_safe on RAID stripe-extents Don't use btrfs_set_item_key_safe() to modify the keys in the RAID stripe-tree, as this can lead to corruption of the tree, which is caught by the checks in btrfs_set_item_key_safe(): BTRFS info (device nvme1n1): leaf 49168384 gen 15 total ptrs 194 free space 8329 owner 12 BTRFS info (device nvme1n1): refs 2 lock_owner 1030 current 1030 [ snip ] item 105 key (354549760 230 20480) itemoff 14587 itemsize 16 stride 0 devid 5 physical 67502080 item 106 key (354631680 230 4096) itemoff 14571 itemsize 16 stride 0 devid 1 physical 88559616 item 107 key (354631680 230 32768) itemoff 14555 itemsize 16 stride 0 devid 1 physical 88555520 item 108 key (354717696 230 28672) itemoff 14539 itemsize 16 stride 0 devid 2 physical 67604480 [ snip ] BTRFS critical (device nvme1n1): slot 106 key (354631680 230 32768) new key (354635776 230 4096) ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:2602! Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 1 UID: 0 PID: 1055 Comm: fsstress Not tainted 6.13.0-rc1+ #1464 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 RIP: 0010:btrfs_set_item_key_safe+0xf7/0x270 Code: <snip> RSP: 0018:ffffc90001337ab0 EFLAGS: 00010287 RAX: 0000000000000000 RBX: ffff8881115fd000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000001 RDI: 00000000ffffffff RBP: ffff888110ed6f50 R08: 00000000ffffefff R09: ffffffff8244c500 R10: 00000000ffffefff R11: 00000000ffffffff R12: ffff888100586000 R13: 00000000000000c9 R14: ffffc90001337b1f R15: ffff888110f23b58 FS: 00007f7d75c72740(0000) GS:ffff88813bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fa811652c60 CR3: 0000000111398001 CR4: 0000000000370eb0 Call Trace: <TASK> ? __die_body.cold+0x14/0x1a ? die+0x2e/0x50 ? do_trap+0xca/0x110 ? do_error_trap+0x65/0x80 ? btrfs_set_item_key_safe+0xf7/0x270 ? exc_invalid_op+0x50/0x70 ? btrfs_set_item_key_safe+0xf7/0x270 ? asm_exc_invalid_op+0x1a/0x20 ? btrfs_set_item_key_safe+0xf7/0x270 btrfs_partially_delete_raid_extent+0xc4/0xe0 btrfs_delete_raid_extent+0x227/0x240 __btrfs_free_extent.isra.0+0x57f/0x9c0 ? exc_coproc_segment_overrun+0x40/0x40 __btrfs_run_delayed_refs+0x2fa/0xe80 btrfs_run_delayed_refs+0x81/0xe0 btrfs_commit_transaction+0x2dd/0xbe0 ? preempt_count_add+0x52/0xb0 btrfs_sync_file+0x375/0x4c0 do_fsync+0x39/0x70 __x64_sys_fsync+0x13/0x20 do_syscall_64+0x54/0x110 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f7d7550ef90 Code: <snip> RSP: 002b:00007ffd70237248 EFLAGS: 00000202 ORIG_RAX: 000000000000004a RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007f7d7550ef90 RDX: 000000000000013a RSI: 000000000040eb28 RDI: 0000000000000004 RBP: 000000000000001b R08: 0000000000000078 R09: 00007ffd7023725c R10: 00007f7d75400390 R11: 0000000000000202 R12: 028f5c28f5c28f5c R13: 8f5c28f5c28f5c29 R14: 000000000040b520 R15: 00007f7d75c726c8 </TASK> While the root cause of the tree order corruption isn't clear, using btrfs_duplicate_item() to copy the item and then adjusting both the key and the per-device physical addresses is a safe way to counter this problem.
CVE-2025-21807: In the Linux kernel, the following vulnerability has been resolved: block: fix queue freeze vs limits lock order in sysfs store methods queue_attr_store() always freezes a device queue before calling the attribute store operation. For attributes that control queue limits, the store operation will also lock the queue limits with a call to queue_limits_start_update(). However, some drivers (e.g. SCSI sd) may need to issue commands to a device to obtain limit values from the hardware with the queue limits locked. This creates a potential ABBA deadlock situation if a user attempts to modify a limit (thus freezing the device queue) while the device driver starts a revalidation of the device queue limits. Avoid such deadlock by not freezing the queue before calling the ->store_limit() method in struct queue_sysfs_entry and instead use the queue_limits_commit_update_frozen helper to freeze the queue after taking the limits lock. This also removes taking the sysfs lock for the store_limit method as it doesn't protect anything here, but creates even more nesting. Hopefully it will go away from the actual sysfs methods entirely soon. (commit log adapted from a similar patch from Damien Le Moal)
CVE-2025-21949: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Set hugetlb mmap base address aligned with pmd size With ltp test case "testcases/bin/hugefork02", there is a dmesg error report message such as: kernel BUG at mm/hugetlb.c:5550! Oops - BUG[#1]: CPU: 0 UID: 0 PID: 1517 Comm: hugefork02 Not tainted 6.14.0-rc2+ #241 Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022 pc 90000000004eaf1c ra 9000000000485538 tp 900000010edbc000 sp 900000010edbf940 a0 900000010edbfb00 a1 9000000108d20280 a2 00007fffe9474000 a3 00007ffff3474000 a4 0000000000000000 a5 0000000000000003 a6 00000000003cadd3 a7 0000000000000000 t0 0000000001ffffff t1 0000000001474000 t2 900000010ecd7900 t3 00007fffe9474000 t4 00007fffe9474000 t5 0000000000000040 t6 900000010edbfb00 t7 0000000000000001 t8 0000000000000005 u0 90000000004849d0 s9 900000010edbfa00 s0 9000000108d20280 s1 00007fffe9474000 s2 0000000002000000 s3 9000000108d20280 s4 9000000002b38b10 s5 900000010edbfb00 s6 00007ffff3474000 s7 0000000000000406 s8 900000010edbfa08 ra: 9000000000485538 unmap_vmas+0x130/0x218 ERA: 90000000004eaf1c __unmap_hugepage_range+0x6f4/0x7d0 PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000007 (+FPE +SXE +ASXE -BTE) ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) Process hugefork02 (pid: 1517, threadinfo=00000000a670eaf4, task=000000007a95fc64) Call Trace: [<90000000004eaf1c>] __unmap_hugepage_range+0x6f4/0x7d0 [<9000000000485534>] unmap_vmas+0x12c/0x218 [<9000000000494068>] exit_mmap+0xe0/0x308 [<900000000025fdc4>] mmput+0x74/0x180 [<900000000026a284>] do_exit+0x294/0x898 [<900000000026aa30>] do_group_exit+0x30/0x98 [<900000000027bed4>] get_signal+0x83c/0x868 [<90000000002457b4>] arch_do_signal_or_restart+0x54/0xfa0 [<90000000015795e8>] irqentry_exit_to_user_mode+0xb8/0x138 [<90000000002572d0>] tlb_do_page_fault_1+0x114/0x1b4 The problem is that base address allocated from hugetlbfs is not aligned with pmd size. Here add a checking for hugetlbfs and align base address with pmd size. After this patch the test case "testcases/bin/hugefork02" passes to run. This is similar to the commit 7f24cbc9c4d42db8a3c8484d1 ("mm/mmap: teach generic_get_unmapped_area{_topdown} to handle hugetlb mappings").
CVE-2025-22104: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Use kernel helpers for hex dumps Previously, when the driver was printing hex dumps, the buffer was cast to an 8 byte long and printed using string formatters. If the buffer size was not a multiple of 8 then a read buffer overflow was possible. Therefore, create a new ibmvnic function that loops over a buffer and calls hex_dump_to_buffer instead. This patch address KASAN reports like the one below: ibmvnic 30000003 env3: Login Buffer: ibmvnic 30000003 env3: 01000000af000000 <...> ibmvnic 30000003 env3: 2e6d62692e736261 ibmvnic 30000003 env3: 65050003006d6f63 ================================================================== BUG: KASAN: slab-out-of-bounds in ibmvnic_login+0xacc/0xffc [ibmvnic] Read of size 8 at addr c0000001331a9aa8 by task ip/17681 <...> Allocated by task 17681: <...> ibmvnic_login+0x2f0/0xffc [ibmvnic] ibmvnic_open+0x148/0x308 [ibmvnic] __dev_open+0x1ac/0x304 <...> The buggy address is located 168 bytes inside of allocated 175-byte region [c0000001331a9a00, c0000001331a9aaf) <...> ================================================================= ibmvnic 30000003 env3: 000000000033766e
CVE-2025-22108: In the Linux kernel, the following vulnerability has been resolved: bnxt_en: Mask the bd_cnt field in the TX BD properly The bd_cnt field in the TX BD specifies the total number of BDs for the TX packet. The bd_cnt field has 5 bits and the maximum number supported is 32 with the value 0. CONFIG_MAX_SKB_FRAGS can be modified and the total number of SKB fragments can approach or exceed the maximum supported by the chip. Add a macro to properly mask the bd_cnt field so that the value 32 will be properly masked and set to 0 in the bd_cnd field. Without this patch, the out-of-range bd_cnt value will corrupt the TX BD and may cause TX timeout. The next patch will check for values exceeding 32.
CVE-2025-22109: In the Linux kernel, the following vulnerability has been resolved: ax25: Remove broken autobind Binding AX25 socket by using the autobind feature leads to memory leaks in ax25_connect() and also refcount leaks in ax25_release(). Memory leak was detected with kmemleak: ================================================================ unreferenced object 0xffff8880253cd680 (size 96): backtrace: __kmalloc_node_track_caller_noprof (./include/linux/kmemleak.h:43) kmemdup_noprof (mm/util.c:136) ax25_rt_autobind (net/ax25/ax25_route.c:428) ax25_connect (net/ax25/af_ax25.c:1282) __sys_connect_file (net/socket.c:2045) __sys_connect (net/socket.c:2064) __x64_sys_connect (net/socket.c:2067) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) ================================================================ When socket is bound, refcounts must be incremented the way it is done in ax25_bind() and ax25_setsockopt() (SO_BINDTODEVICE). In case of autobind, the refcounts are not incremented. This bug leads to the following issue reported by Syzkaller: ================================================================ ax25_connect(): syz-executor318 uses autobind, please contact jreuter@yaina.de ------------[ cut here ]------------ refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 0 PID: 5317 at lib/refcount.c:31 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 Modules linked in: CPU: 0 UID: 0 PID: 5317 Comm: syz-executor318 Not tainted 6.14.0-rc4-syzkaller-00278-gece144f151ac #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 ... Call Trace: <TASK> __refcount_dec include/linux/refcount.h:336 [inline] refcount_dec include/linux/refcount.h:351 [inline] ref_tracker_free+0x6af/0x7e0 lib/ref_tracker.c:236 netdev_tracker_free include/linux/netdevice.h:4302 [inline] netdev_put include/linux/netdevice.h:4319 [inline] ax25_release+0x368/0x960 net/ax25/af_ax25.c:1080 __sock_release net/socket.c:647 [inline] sock_close+0xbc/0x240 net/socket.c:1398 __fput+0x3e9/0x9f0 fs/file_table.c:464 __do_sys_close fs/open.c:1580 [inline] __se_sys_close fs/open.c:1565 [inline] __x64_sys_close+0x7f/0x110 fs/open.c:1565 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f ... </TASK> ================================================================ Considering the issues above and the comments left in the code that say: "check if we can remove this feature. It is broken."; "autobinding in this may or may not work"; - it is better to completely remove this feature than to fix it because it is broken and leads to various kinds of memory bugs. Now calling connect() without first binding socket will result in an error (-EINVAL). Userspace software that relies on the autobind feature might get broken. However, this feature does not seem widely used with this specific driver as it was not reliable at any point of time, and it is already broken anyway. E.g. ax25-tools and ax25-apps packages for popular distributions do not use the autobind feature for AF_AX25. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2025-22116: In the Linux kernel, the following vulnerability has been resolved: idpf: check error for register_netdev() on init Current init logic ignores the error code from register_netdev(), which will cause WARN_ON() on attempt to unregister it, if there was one, and there is no info for the user that the creation of the netdev failed. WARNING: CPU: 89 PID: 6902 at net/core/dev.c:11512 unregister_netdevice_many_notify+0x211/0x1a10 ... [ 3707.563641] unregister_netdev+0x1c/0x30 [ 3707.563656] idpf_vport_dealloc+0x5cf/0xce0 [idpf] [ 3707.563684] idpf_deinit_task+0xef/0x160 [idpf] [ 3707.563712] idpf_vc_core_deinit+0x84/0x320 [idpf] [ 3707.563739] idpf_remove+0xbf/0x780 [idpf] [ 3707.563769] pci_device_remove+0xab/0x1e0 [ 3707.563786] device_release_driver_internal+0x371/0x530 [ 3707.563803] driver_detach+0xbf/0x180 [ 3707.563816] bus_remove_driver+0x11b/0x2a0 [ 3707.563829] pci_unregister_driver+0x2a/0x250 Introduce an error check and log the vport number and error code. On removal make sure to check VPORT_REG_NETDEV flag prior to calling unregister and free on the netdev. Add local variables for idx, vport_config and netdev for readability.
CVE-2025-22117: In the Linux kernel, the following vulnerability has been resolved: ice: fix using untrusted value of pkt_len in ice_vc_fdir_parse_raw() Fix using the untrusted value of proto->raw.pkt_len in function ice_vc_fdir_parse_raw() by verifying if it does not exceed the VIRTCHNL_MAX_SIZE_RAW_PACKET value.
CVE-2025-22127: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix potential deadloop in prepare_compress_overwrite() Jan Prusakowski reported a kernel hang issue as below: When running xfstests on linux-next kernel (6.14.0-rc3, 6.12) I encountered a problem in generic/475 test where fsstress process gets blocked in __f2fs_write_data_pages() and the test hangs. The options I used are: MKFS_OPTIONS -- -O compression -O extra_attr -O project_quota -O quota /dev/vdc MOUNT_OPTIONS -- -o acl,user_xattr -o discard,compress_extension=* /dev/vdc /vdc INFO: task kworker/u8:0:11 blocked for more than 122 seconds. Not tainted 6.14.0-rc3-xfstests-lockdep #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u8:0 state:D stack:0 pid:11 tgid:11 ppid:2 task_flags:0x4208160 flags:0x00004000 Workqueue: writeback wb_workfn (flush-253:0) Call Trace: <TASK> __schedule+0x309/0x8e0 schedule+0x3a/0x100 schedule_preempt_disabled+0x15/0x30 __mutex_lock+0x59a/0xdb0 __f2fs_write_data_pages+0x3ac/0x400 do_writepages+0xe8/0x290 __writeback_single_inode+0x5c/0x360 writeback_sb_inodes+0x22f/0x570 wb_writeback+0xb0/0x410 wb_do_writeback+0x47/0x2f0 wb_workfn+0x5a/0x1c0 process_one_work+0x223/0x5b0 worker_thread+0x1d5/0x3c0 kthread+0xfd/0x230 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x1a/0x30 </TASK> The root cause is: once generic/475 starts toload error table to dm device, f2fs_prepare_compress_overwrite() will loop reading compressed cluster pages due to IO error, meanwhile it has held .writepages lock, it can block all other writeback tasks. Let's fix this issue w/ below changes: - add f2fs_handle_page_eio() in prepare_compress_overwrite() to detect IO error. - detect cp_error earler in f2fs_read_multi_pages().
CVE-2025-23131: In the Linux kernel, the following vulnerability has been resolved: dlm: prevent NPD when writing a positive value to event_done do_uevent returns the value written to event_done. In case it is a positive value, new_lockspace would undo all the work, and lockspace would not be set. __dlm_new_lockspace, however, would treat that positive value as a success due to commit 8511a2728ab8 ("dlm: fix use count with multiple joins"). Down the line, device_create_lockspace would pass that NULL lockspace to dlm_find_lockspace_local, leading to a NULL pointer dereference. Treating such positive values as successes prevents the problem. Given this has been broken for so long, this is unlikely to break userspace expectations.
CVE-2025-23132: In the Linux kernel, the following vulnerability has been resolved: f2fs: quota: fix to avoid warning in dquot_writeback_dquots() F2FS-fs (dm-59): checkpoint=enable has some unwritten data. ------------[ cut here ]------------ WARNING: CPU: 6 PID: 8013 at fs/quota/dquot.c:691 dquot_writeback_dquots+0x2fc/0x308 pc : dquot_writeback_dquots+0x2fc/0x308 lr : f2fs_quota_sync+0xcc/0x1c4 Call trace: dquot_writeback_dquots+0x2fc/0x308 f2fs_quota_sync+0xcc/0x1c4 f2fs_write_checkpoint+0x3d4/0x9b0 f2fs_issue_checkpoint+0x1bc/0x2c0 f2fs_sync_fs+0x54/0x150 f2fs_do_sync_file+0x2f8/0x814 __f2fs_ioctl+0x1960/0x3244 f2fs_ioctl+0x54/0xe0 __arm64_sys_ioctl+0xa8/0xe4 invoke_syscall+0x58/0x114 checkpoint and f2fs_remount may race as below, resulting triggering warning in dquot_writeback_dquots(). atomic write remount - do_remount - down_write(&sb->s_umount); - f2fs_remount - ioctl - f2fs_do_sync_file - f2fs_sync_fs - f2fs_write_checkpoint - block_operations - locked = down_read_trylock(&sbi->sb->s_umount) : fail to lock due to the write lock was held by remount - up_write(&sb->s_umount); - f2fs_quota_sync - dquot_writeback_dquots - WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)) : trigger warning because s_umount lock was unlocked by remount If checkpoint comes from mount/umount/remount/freeze/quotactl, caller of checkpoint has already held s_umount lock, calling dquot_writeback_dquots() in the context should be safe. So let's record task to sbi->umount_lock_holder, so that checkpoint can know whether the lock has held in the context or not by checking current w/ it. In addition, in order to not misrepresent caller of checkpoint, we should not allow to trigger async checkpoint for those callers: mount/umount/remount/ freeze/quotactl.
CVE-2025-23135: In the Linux kernel, the following vulnerability has been resolved: RISC-V: KVM: Teardown riscv specific bits after kvm_exit During a module removal, kvm_exit invokes arch specific disable call which disables AIA. However, we invoke aia_exit before kvm_exit resulting in the following warning. KVM kernel module can't be inserted afterwards due to inconsistent state of IRQ. [25469.031389] percpu IRQ 31 still enabled on CPU0! [25469.031732] WARNING: CPU: 3 PID: 943 at kernel/irq/manage.c:2476 __free_percpu_irq+0xa2/0x150 [25469.031804] Modules linked in: kvm(-) [25469.031848] CPU: 3 UID: 0 PID: 943 Comm: rmmod Not tainted 6.14.0-rc5-06947-g91c763118f47-dirty #2 [25469.031905] Hardware name: riscv-virtio,qemu (DT) [25469.031928] epc : __free_percpu_irq+0xa2/0x150 [25469.031976] ra : __free_percpu_irq+0xa2/0x150 [25469.032197] epc : ffffffff8007db1e ra : ffffffff8007db1e sp : ff2000000088bd50 [25469.032241] gp : ffffffff8131cef8 tp : ff60000080b96400 t0 : ff2000000088baf8 [25469.032285] t1 : fffffffffffffffc t2 : 5249207570637265 s0 : ff2000000088bd90 [25469.032329] s1 : ff60000098b21080 a0 : 037d527a15eb4f00 a1 : 037d527a15eb4f00 [25469.032372] a2 : 0000000000000023 a3 : 0000000000000001 a4 : ffffffff8122dbf8 [25469.032410] a5 : 0000000000000fff a6 : 0000000000000000 a7 : ffffffff8122dc10 [25469.032448] s2 : ff60000080c22eb0 s3 : 0000000200000022 s4 : 000000000000001f [25469.032488] s5 : ff60000080c22e00 s6 : ffffffff80c351c0 s7 : 0000000000000000 [25469.032582] s8 : 0000000000000003 s9 : 000055556b7fb490 s10: 00007ffff0e12fa0 [25469.032621] s11: 00007ffff0e13e9a t3 : ffffffff81354ac7 t4 : ffffffff81354ac7 [25469.032664] t5 : ffffffff81354ac8 t6 : ffffffff81354ac7 [25469.032698] status: 0000000200000100 badaddr: ffffffff8007db1e cause: 0000000000000003 [25469.032738] [<ffffffff8007db1e>] __free_percpu_irq+0xa2/0x150 [25469.032797] [<ffffffff8007dbfc>] free_percpu_irq+0x30/0x5e [25469.032856] [<ffffffff013a57dc>] kvm_riscv_aia_exit+0x40/0x42 [kvm] [25469.033947] [<ffffffff013b4e82>] cleanup_module+0x10/0x32 [kvm] [25469.035300] [<ffffffff8009b150>] __riscv_sys_delete_module+0x18e/0x1fc [25469.035374] [<ffffffff8000c1ca>] syscall_handler+0x3a/0x46 [25469.035456] [<ffffffff809ec9a4>] do_trap_ecall_u+0x72/0x134 [25469.035536] [<ffffffff809f5e18>] handle_exception+0x148/0x156 Invoke aia_exit and other arch specific cleanup functions after kvm_exit so that disable gets a chance to be called first before exit.
CVE-2025-37743: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: Avoid memory leak while enabling statistics Driver uses monitor destination rings for extended statistics mode and standalone monitor mode. In extended statistics mode, TLVs are parsed from the buffer received from the monitor destination ring and assigned to the ppdu_info structure to update per-packet statistics. In standalone monitor mode, along with per-packet statistics, the packet data (payload) is captured, and the driver updates per MSDU to mac80211. When the AP interface is enabled, only extended statistics mode is activated. As part of enabling monitor rings for collecting statistics, the driver subscribes to HAL_RX_MPDU_START TLV in the filter configuration. This TLV is received from the monitor destination ring, and kzalloc for the mon_mpdu object occurs, which is not freed, leading to a memory leak. The kzalloc for the mon_mpdu object is only required while enabling the standalone monitor interface. This causes a memory leak while enabling extended statistics mode in the driver. Fix this memory leak by removing the kzalloc for the mon_mpdu object in the HAL_RX_MPDU_START TLV handling. Additionally, remove the standalone monitor mode handlings in the HAL_MON_BUF_ADDR and HAL_RX_MSDU_END TLVs. These TLV tags will be handled properly when enabling standalone monitor mode in the future. Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1 Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
CVE-2025-37746: In the Linux kernel, the following vulnerability has been resolved: perf/dwc_pcie: fix duplicate pci_dev devices During platform_device_register, wrongly using struct device pci_dev as platform_data caused a kmemdup copy of pci_dev. Worse still, accessing the duplicated device leads to list corruption as its mutex content (e.g., list, magic) remains the same as the original.
CVE-2025-37880: In the Linux kernel, the following vulnerability has been resolved: um: work around sched_yield not yielding in time-travel mode sched_yield by a userspace may not actually cause scheduling in time-travel mode as no time has passed. In the case seen it appears to be a badly implemented userspace spinlock in ASAN. Unfortunately, with time-travel it causes an extreme slowdown or even deadlock depending on the kernel configuration (CONFIG_UML_MAX_USERSPACE_ITERATIONS). Work around it by accounting time to the process whenever it executes a sched_yield syscall.
CVE-2025-37906: In the Linux kernel, the following vulnerability has been resolved: ublk: fix race between io_uring_cmd_complete_in_task and ublk_cancel_cmd ublk_cancel_cmd() calls io_uring_cmd_done() to complete uring_cmd, but we may have scheduled task work via io_uring_cmd_complete_in_task() for dispatching request, then kernel crash can be triggered. Fix it by not trying to canceling the command if ublk block request is started.
CVE-2025-38029: In the Linux kernel, the following vulnerability has been resolved: kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range.
CVE-2025-38036: In the Linux kernel, the following vulnerability has been resolved: drm/xe/vf: Perform early GT MMIO initialization to read GMDID VFs need to communicate with the GuC to obtain the GMDID value and existing GuC functions used for that assume that the GT has it's MMIO members already setup. However, due to recent refactoring the gt->mmio is initialized later, and any attempt by the VF to use xe_mmio_read|write() from GuC functions will lead to NPD crash due to unset MMIO register address: [] xe 0000:00:02.1: [drm] Running in SR-IOV VF mode [] xe 0000:00:02.1: [drm] GT0: sending H2G MMIO 0x5507 [] BUG: unable to handle page fault for address: 0000000000190240 Since we are already tweaking the id and type of the primary GT to mimic it's a Media GT before initializing the GuC communication, we can also call xe_gt_mmio_init() to perform early setup of the gt->mmio which will make those GuC functions work again.
CVE-2025-38041: In the Linux kernel, the following vulnerability has been resolved: clk: sunxi-ng: h616: Reparent GPU clock during frequency changes The H616 manual does not state that the GPU PLL supports dynamic frequency configuration, so we must take extra care when changing the frequency. Currently any attempt to do device DVFS on the GPU lead to panfrost various ooops, and GPU hangs. The manual describes the algorithm for changing the PLL frequency, which the CPU PLL notifier code already support, so we reuse that to reparent the GPU clock to GPU1 clock during frequency changes.
CVE-2025-38042: In the Linux kernel, the following vulnerability has been resolved: dmaengine: ti: k3-udma-glue: Drop skip_fdq argument from k3_udma_glue_reset_rx_chn The user of k3_udma_glue_reset_rx_chn() e.g. ti_am65_cpsw_nuss can run on multiple platforms having different DMA architectures. On some platforms there can be one FDQ for all flows in the RX channel while for others there is a separate FDQ for each flow in the RX channel. So far we have been relying on the skip_fdq argument of k3_udma_glue_reset_rx_chn(). Instead of relying on the user to provide this information, infer it based on DMA architecture during k3_udma_glue_request_rx_chn() and save it in an internal flag 'single_fdq'. Use that flag at k3_udma_glue_reset_rx_chn() to deicide if the FDQ needs to be cleared for every flow or just for flow 0. Fixes the below issue on ti_am65_cpsw_nuss driver on AM62-SK. > ip link set eth1 down > ip link set eth0 down > ethtool -L eth0 rx 8 > ip link set eth0 up > modprobe -r ti_am65_cpsw_nuss [ 103.045726] ------------[ cut here ]------------ [ 103.050505] k3_knav_desc_pool size 512000 != avail 64000 [ 103.050703] WARNING: CPU: 1 PID: 450 at drivers/net/ethernet/ti/k3-cppi-desc-pool.c:33 k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.068810] Modules linked in: ti_am65_cpsw_nuss(-) k3_cppi_desc_pool snd_soc_hdmi_codec crct10dif_ce snd_soc_simple_card snd_soc_simple_card_utils display_connector rtc_ti_k3 k3_j72xx_bandgap tidss drm_client_lib snd_soc_davinci_mcas p drm_dma_helper tps6598x phylink snd_soc_ti_udma rti_wdt drm_display_helper snd_soc_tlv320aic3x_i2c typec at24 phy_gmii_sel snd_soc_ti_edma snd_soc_tlv320aic3x sii902x snd_soc_ti_sdma sa2ul omap_mailbox drm_kms_helper authenc cfg80211 r fkill fuse drm drm_panel_orientation_quirks backlight ip_tables x_tables ipv6 [last unloaded: k3_cppi_desc_pool] [ 103.119950] CPU: 1 UID: 0 PID: 450 Comm: modprobe Not tainted 6.13.0-rc7-00001-g9c5e3435fa66 #1011 [ 103.119968] Hardware name: Texas Instruments AM625 SK (DT) [ 103.119974] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 103.119983] pc : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.148007] lr : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.154709] sp : ffff8000826ebbc0 [ 103.158015] x29: ffff8000826ebbc0 x28: ffff0000090b6300 x27: 0000000000000000 [ 103.165145] x26: 0000000000000000 x25: 0000000000000000 x24: ffff0000019df6b0 [ 103.172271] x23: ffff0000019df6b8 x22: ffff0000019df410 x21: ffff8000826ebc88 [ 103.179397] x20: 000000000007d000 x19: ffff00000a3b3000 x18: 0000000000000000 [ 103.186522] x17: 0000000000000000 x16: 0000000000000000 x15: 000001e8c35e1cde [ 103.193647] x14: 0000000000000396 x13: 000000000000035c x12: 0000000000000000 [ 103.200772] x11: 000000000000003a x10: 00000000000009c0 x9 : ffff8000826eba20 [ 103.207897] x8 : ffff0000090b6d20 x7 : ffff00007728c180 x6 : ffff00007728c100 [ 103.215022] x5 : 0000000000000001 x4 : ffff000000508a50 x3 : ffff7ffff6146000 [ 103.222147] x2 : 0000000000000000 x1 : e300b4173ee6b200 x0 : 0000000000000000 [ 103.229274] Call trace: [ 103.231714] k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] (P) [ 103.238408] am65_cpsw_nuss_free_rx_chns+0x28/0x4c [ti_am65_cpsw_nuss] [ 103.244942] devm_action_release+0x14/0x20 [ 103.249040] release_nodes+0x3c/0x68 [ 103.252610] devres_release_all+0x8c/0xdc [ 103.256614] device_unbind_cleanup+0x18/0x60 [ 103.260876] device_release_driver_internal+0xf8/0x178 [ 103.266004] driver_detach+0x50/0x9c [ 103.269571] bus_remove_driver+0x6c/0xbc [ 103.273485] driver_unregister+0x30/0x60 [ 103.277401] platform_driver_unregister+0x14/0x20 [ 103.282096] am65_cpsw_nuss_driver_exit+0x18/0xff4 [ti_am65_cpsw_nuss] [ 103.288620] __arm64_sys_delete_module+0x17c/0x25c [ 103.293404] invoke_syscall+0x44/0x100 [ 103.297149] el0_svc_common.constprop.0+0xc0/0xe0 [ 103.301845] do_el0_svc+0x1c/0x28 [ 103.305155] el0_svc+0x28/0x98 ---truncated---
CVE-2025-38064: In the Linux kernel, the following vulnerability has been resolved: virtio: break and reset virtio devices on device_shutdown() Hongyu reported a hang on kexec in a VM. QEMU reported invalid memory accesses during the hang. Invalid read at addr 0x102877002, size 2, region '(null)', reason: rejected Invalid write at addr 0x102877A44, size 2, region '(null)', reason: rejected ... It was traced down to virtio-console. Kexec works fine if virtio-console is not in use. The issue is that virtio-console continues to write to the MMIO even after underlying virtio-pci device is reset. Additionally, Eric noticed that IOMMUs are reset before devices, if devices are not reset on shutdown they continue to poke at guest memory and get errors from the IOMMU. Some devices get wedged then. The problem can be solved by breaking all virtio devices on virtio bus shutdown, then resetting them.
CVE-2025-38132: In the Linux kernel, the following vulnerability has been resolved: coresight: holding cscfg_csdev_lock while removing cscfg from csdev There'll be possible race scenario for coresight config: CPU0 CPU1 (perf enable) load module cscfg_load_config_sets() activate config. // sysfs (sys_active_cnt == 1) ... cscfg_csdev_enable_active_config() lock(csdev->cscfg_csdev_lock) deactivate config // sysfs (sys_activec_cnt == 0) cscfg_unload_config_sets() <iterating config_csdev_list> cscfg_remove_owned_csdev_configs() // here load config activate by CPU1 unlock(csdev->cscfg_csdev_lock) iterating config_csdev_list could be raced with config_csdev_list's entry delete. To resolve this race , hold csdev->cscfg_csdev_lock() while cscfg_remove_owned_csdev_configs()
CVE-2025-38137: In the Linux kernel, the following vulnerability has been resolved: PCI/pwrctrl: Cancel outstanding rescan work when unregistering It's possible to trigger use-after-free here by: (a) forcing rescan_work_func() to take a long time and (b) utilizing a pwrctrl driver that may be unloaded for some reason Cancel outstanding work to ensure it is finished before we allow our data structures to be cleaned up. [bhelgaas: tidy commit log]
CVE-2025-38140: In the Linux kernel, the following vulnerability has been resolved: dm: limit swapping tables for devices with zone write plugs dm_revalidate_zones() only allowed new or previously unzoned devices to call blk_revalidate_disk_zones(). If the device was already zoned, disk->nr_zones would always equal md->nr_zones, so dm_revalidate_zones() returned without doing any work. This would make the zoned settings for the device not match the new table. If the device had zone write plug resources, it could run into errors like bdev_zone_is_seq() reading invalid memory because disk->conv_zones_bitmap was the wrong size. If the device doesn't have any zone write plug resources, calling blk_revalidate_disk_zones() will always correctly update device. If blk_revalidate_disk_zones() fails, it can still overwrite or clear the current disk->nr_zones value. In this case, DM must restore the previous value of disk->nr_zones, so that the zoned settings will continue to match the previous value that it fell back to. If the device already has zone write plug resources, blk_revalidate_disk_zones() will not correctly update them, if it is called for arbitrary zoned device changes. Since there is not much need for this ability, the easiest solution is to disallow any table reloads that change the zoned settings, for devices that already have zone plug resources. Specifically, if a device already has zone plug resources allocated, it can only switch to another zoned table that also emulates zone append. Also, it cannot change the device size or the zone size. A device can switch to an error target.
CVE-2025-38187: In the Linux kernel, the following vulnerability has been resolved: drm/nouveau: fix a use-after-free in r535_gsp_rpc_push() The RPC container is released after being passed to r535_gsp_rpc_send(). When sending the initial fragment of a large RPC and passing the caller's RPC container, the container will be freed prematurely. Subsequent attempts to send remaining fragments will therefore result in a use-after-free. Allocate a temporary RPC container for holding the initial fragment of a large RPC when sending. Free the caller's container when all fragments are successfully sent. [ Rebase onto Blackwell changes. - Danilo ]
CVE-2025-38199: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: Fix memory leak due to multiple rx_stats allocation rx_stats for each arsta is allocated when adding a station. arsta->rx_stats will be freed when a station is removed. Redundant allocations are occurring when the same station is added multiple times. This causes ath12k_mac_station_add() to be called multiple times, and rx_stats is allocated each time. As a result there is memory leaks. Prevent multiple allocations of rx_stats when ath12k_mac_station_add() is called repeatedly by checking if rx_stats is already allocated before allocating again. Allocate arsta->rx_stats if arsta->rx_stats is NULL respectively. Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1 Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
CVE-2025-38203: In the Linux kernel, the following vulnerability has been resolved: jfs: Fix null-ptr-deref in jfs_ioc_trim [ Syzkaller Report ] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000087: 0000 [#1 KASAN: null-ptr-deref in range [0x0000000000000438-0x000000000000043f] CPU: 2 UID: 0 PID: 10614 Comm: syz-executor.0 Not tainted 6.13.0-rc6-gfbfd64d25c7a-dirty #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Sched_ext: serialise (enabled+all), task: runnable_at=-30ms RIP: 0010:jfs_ioc_trim+0x34b/0x8f0 Code: e7 e8 59 a4 87 fe 4d 8b 24 24 4d 8d bc 24 38 04 00 00 48 8d 93 90 82 fe ff 4c 89 ff 31 f6 RSP: 0018:ffffc900055f7cd0 EFLAGS: 00010206 RAX: 0000000000000087 RBX: 00005866a9e67ff8 RCX: 000000000000000a RDX: 0000000000000001 RSI: 0000000000000004 RDI: 0000000000000001 RBP: dffffc0000000000 R08: ffff88807c180003 R09: 1ffff1100f830000 R10: dffffc0000000000 R11: ffffed100f830001 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000438 FS: 00007fe520225640(0000) GS:ffff8880b7e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005593c91b2c88 CR3: 000000014927c000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __die_body+0x61/0xb0 ? die_addr+0xb1/0xe0 ? exc_general_protection+0x333/0x510 ? asm_exc_general_protection+0x26/0x30 ? jfs_ioc_trim+0x34b/0x8f0 jfs_ioctl+0x3c8/0x4f0 ? __pfx_jfs_ioctl+0x10/0x10 ? __pfx_jfs_ioctl+0x10/0x10 __se_sys_ioctl+0x269/0x350 ? __pfx___se_sys_ioctl+0x10/0x10 ? do_syscall_64+0xfb/0x210 do_syscall_64+0xee/0x210 ? syscall_exit_to_user_mode+0x1e0/0x330 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fe51f4903ad Code: c3 e8 a7 2b 00 00 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d RSP: 002b:00007fe5202250c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fe51f5cbf80 RCX: 00007fe51f4903ad RDX: 0000000020000680 RSI: 00000000c0185879 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe520225640 R13: 000000000000000e R14: 00007fe51f44fca0 R15: 00007fe52021d000 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:jfs_ioc_trim+0x34b/0x8f0 Code: e7 e8 59 a4 87 fe 4d 8b 24 24 4d 8d bc 24 38 04 00 00 48 8d 93 90 82 fe ff 4c 89 ff 31 f6 RSP: 0018:ffffc900055f7cd0 EFLAGS: 00010206 RAX: 0000000000000087 RBX: 00005866a9e67ff8 RCX: 000000000000000a RDX: 0000000000000001 RSI: 0000000000000004 RDI: 0000000000000001 RBP: dffffc0000000000 R08: ffff88807c180003 R09: 1ffff1100f830000 R10: dffffc0000000000 R11: ffffed100f830001 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000438 FS: 00007fe520225640(0000) GS:ffff8880b7e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005593c91b2c88 CR3: 000000014927c000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Kernel panic - not syncing: Fatal exception [ Analysis ] We believe that we have found a concurrency bug in the `fs/jfs` module that results in a null pointer dereference. There is a closely related issue which has been fixed: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=d6c1b3599b2feb5c7291f5ac3a36e5fa7cedb234 ... but, unfortunately, the accepted patch appears to still be susceptible to a null pointer dereference under some interleavings. To trigger the bug, we think that `JFS_SBI(ipbmap->i_sb)->bmap` is set to NULL in `dbFreeBits` and then dereferenced in `jfs_ioc_trim`. This bug manifests quite rarely under normal circumstances, but is triggereable from a syz-program.
CVE-2025-38204: In the Linux kernel, the following vulnerability has been resolved: jfs: fix array-index-out-of-bounds read in add_missing_indices stbl is s8 but it must contain offsets into slot which can go from 0 to 127. Added a bound check for that error and return -EIO if the check fails. Also make jfs_readdir return with error if add_missing_indices returns with an error.
CVE-2025-38205: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Avoid divide by zero by initializing dummy pitch to 1 [Why] If the dummy values in `populate_dummy_dml_surface_cfg()` aren't updated then they can lead to a divide by zero in downstream callers like CalculateVMAndRowBytes() [How] Initialize dummy value to a value to avoid divide by zero.
CVE-2025-38206: In the Linux kernel, the following vulnerability has been resolved: exfat: fix double free in delayed_free The double free could happen in the following path. exfat_create_upcase_table() exfat_create_upcase_table() : return error exfat_free_upcase_table() : free ->vol_utbl exfat_load_default_upcase_table : return error exfat_kill_sb() delayed_free() exfat_free_upcase_table() <--------- double free This patch set ->vol_util as NULL after freeing it.
CVE-2025-38207: In the Linux kernel, the following vulnerability has been resolved: mm: fix uprobe pte be overwritten when expanding vma Patch series "Fix uprobe pte be overwritten when expanding vma". This patch (of 4): We encountered a BUG alert triggered by Syzkaller as follows: BUG: Bad rss-counter state mm:00000000b4a60fca type:MM_ANONPAGES val:1 And we can reproduce it with the following steps: 1. register uprobe on file at zero offset 2. mmap the file at zero offset: addr1 = mmap(NULL, 2 * 4096, PROT_NONE, MAP_PRIVATE, fd, 0); 3. mremap part of vma1 to new vma2: addr2 = mremap(addr1, 4096, 2 * 4096, MREMAP_MAYMOVE); 4. mremap back to orig addr1: mremap(addr2, 4096, 4096, MREMAP_MAYMOVE | MREMAP_FIXED, addr1); In step 3, the vma1 range [addr1, addr1 + 4096] will be remap to new vma2 with range [addr2, addr2 + 8192], and remap uprobe anon page from the vma1 to vma2, then unmap the vma1 range [addr1, addr1 + 4096]. In step 4, the vma2 range [addr2, addr2 + 4096] will be remap back to the addr range [addr1, addr1 + 4096]. Since the addr range [addr1 + 4096, addr1 + 8192] still maps the file, it will take vma_merge_new_range to expand the range, and then do uprobe_mmap in vma_complete. Since the merged vma pgoff is also zero offset, it will install uprobe anon page to the merged vma. However, the upcomming move_page_tables step, which use set_pte_at to remap the vma2 uprobe pte to the merged vma, will overwrite the newly uprobe pte in the merged vma, and lead that pte to be orphan. Since the uprobe pte will be remapped to the merged vma, we can remove the unnecessary uprobe_mmap upon merged vma. This problem was first found in linux-6.6.y and also exists in the community syzkaller: https://lore.kernel.org/all/000000000000ada39605a5e71711@google.com/T/
CVE-2025-38237: In the Linux kernel, the following vulnerability has been resolved: media: platform: exynos4-is: Add hardware sync wait to fimc_is_hw_change_mode() In fimc_is_hw_change_mode(), the function changes camera modes without waiting for hardware completion, risking corrupted data or system hangs if subsequent operations proceed before the hardware is ready. Add fimc_is_hw_wait_intmsr0_intmsd0() after mode configuration, ensuring hardware state synchronization and stable interrupt handling.
CVE-2025-38261: In the Linux kernel, the following vulnerability has been resolved: riscv: save the SR_SUM status over switches When threads/tasks are switched we need to ensure the old execution's SR_SUM state is saved and the new thread has the old SR_SUM state restored. The issue was seen under heavy load especially with the syz-stress tool running, with crashes as follows in schedule_tail: Unable to handle kernel access to user memory without uaccess routines at virtual address 000000002749f0d0 Oops [#1] Modules linked in: CPU: 1 PID: 4875 Comm: syz-executor.0 Not tainted 5.12.0-rc2-syzkaller-00467-g0d7588ab9ef9 #0 Hardware name: riscv-virtio,qemu (DT) epc : schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 ra : task_pid_vnr include/linux/sched.h:1421 [inline] ra : schedule_tail+0x70/0xb2 kernel/sched/core.c:4264 epc : ffffffe00008c8b0 ra : ffffffe00008c8ae sp : ffffffe025d17ec0 gp : ffffffe005d25378 tp : ffffffe00f0d0000 t0 : 0000000000000000 t1 : 0000000000000001 t2 : 00000000000f4240 s0 : ffffffe025d17ee0 s1 : 000000002749f0d0 a0 : 000000000000002a a1 : 0000000000000003 a2 : 1ffffffc0cfac500 a3 : ffffffe0000c80cc a4 : 5ae9db91c19bbe00 a5 : 0000000000000000 a6 : 0000000000f00000 a7 : ffffffe000082eba s2 : 0000000000040000 s3 : ffffffe00eef96c0 s4 : ffffffe022c77fe0 s5 : 0000000000004000 s6 : ffffffe067d74e00 s7 : ffffffe067d74850 s8 : ffffffe067d73e18 s9 : ffffffe067d74e00 s10: ffffffe00eef96e8 s11: 000000ae6cdf8368 t3 : 5ae9db91c19bbe00 t4 : ffffffc4043cafb2 t5 : ffffffc4043cafba t6 : 0000000000040000 status: 0000000000000120 badaddr: 000000002749f0d0 cause: 000000000000000f Call Trace: [<ffffffe00008c8b0>] schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 [<ffffffe000005570>] ret_from_exception+0x0/0x14 Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace b5f8f9231dc87dda ]--- The issue comes from the put_user() in schedule_tail (kernel/sched/core.c) doing the following: asmlinkage __visible void schedule_tail(struct task_struct *prev) { ... if (current->set_child_tid) put_user(task_pid_vnr(current), current->set_child_tid); ... } the put_user() macro causes the code sequence to come out as follows: 1: __enable_user_access() 2: reg = task_pid_vnr(current); 3: *current->set_child_tid = reg; 4: __disable_user_access() The problem is that we may have a sleeping function as argument which could clear SR_SUM causing the panic above. This was fixed by evaluating the argument of the put_user() macro outside the user-enabled section in commit 285a76bb2cf5 ("riscv: evaluate put_user() arg before enabling user access")" In order for riscv to take advantage of unsafe_get/put_XXX() macros and to avoid the same issue we had with put_user() and sleeping functions we must ensure code flow can go through switch_to() from within a region of code with SR_SUM enabled and come back with SR_SUM still enabled. This patch addresses the problem allowing future work to enable full use of unsafe_get/put_XXX() macros without needing to take a CSR bit flip cost on every access. Make switch_to() save and restore SR_SUM.
CVE-2025-38284: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw89: pci: configure manual DAC mode via PCI config API only To support 36-bit DMA, configure chip proprietary bit via PCI config API or chip DBI interface. However, the PCI device mmap isn't set yet and the DBI is also inaccessible via mmap, so only if the bit can be accessible via PCI config API, chip can support 36-bit DMA. Otherwise, fallback to 32-bit DMA. With NULL mmap address, kernel throws trace: BUG: unable to handle page fault for address: 0000000000001090 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: Oops: 0002 [#1] PREEMPT SMP PTI CPU: 1 UID: 0 PID: 71 Comm: irq/26-pciehp Tainted: G OE 6.14.2-061402-generic #202504101348 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE RIP: 0010:rtw89_pci_ops_write16+0x12/0x30 [rtw89_pci] RSP: 0018:ffffb0ffc0acf9d8 EFLAGS: 00010206 RAX: ffffffffc158f9c0 RBX: ffff94865e702020 RCX: 0000000000000000 RDX: 0000000000000718 RSI: 0000000000001090 RDI: ffff94865e702020 RBP: ffffb0ffc0acf9d8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000015 R13: 0000000000000719 R14: ffffb0ffc0acfa1f R15: ffffffffc1813060 FS: 0000000000000000(0000) GS:ffff9486f3480000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000001090 CR3: 0000000090440001 CR4: 00000000000626f0 Call Trace: <TASK> rtw89_pci_read_config_byte+0x6d/0x120 [rtw89_pci] rtw89_pci_cfg_dac+0x5b/0xb0 [rtw89_pci] rtw89_pci_probe+0xa96/0xbd0 [rtw89_pci] ? __pfx___device_attach_driver+0x10/0x10 ? __pfx___device_attach_driver+0x10/0x10 local_pci_probe+0x47/0xa0 pci_call_probe+0x5d/0x190 pci_device_probe+0xa7/0x160 really_probe+0xf9/0x370 ? pm_runtime_barrier+0x55/0xa0 __driver_probe_device+0x8c/0x140 driver_probe_device+0x24/0xd0 __device_attach_driver+0xcd/0x170 bus_for_each_drv+0x99/0x100 __device_attach+0xb4/0x1d0 device_attach+0x10/0x20 pci_bus_add_device+0x59/0x90 pci_bus_add_devices+0x31/0x80 pciehp_configure_device+0xaa/0x170 pciehp_enable_slot+0xd6/0x240 pciehp_handle_presence_or_link_change+0xf1/0x180 pciehp_ist+0x162/0x1c0 irq_thread_fn+0x24/0x70 irq_thread+0xef/0x1c0 ? __pfx_irq_thread_fn+0x10/0x10 ? __pfx_irq_thread_dtor+0x10/0x10 ? __pfx_irq_thread+0x10/0x10 kthread+0xfc/0x230 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x47/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2025-38311: In the Linux kernel, the following vulnerability has been resolved: iavf: get rid of the crit lock Get rid of the crit lock. That frees us from the error prone logic of try_locks. Thanks to netdev_lock() by Jakub it is now easy, and in most cases we were protected by it already - replace crit lock by netdev lock when it was not the case. Lockdep reports that we should cancel the work under crit_lock [splat1], and that was the scheme we have mostly followed since [1] by Slawomir. But when that is done we still got into deadlocks [splat2]. So instead we should look at the bigger problem, namely "weird locking/scheduling" of the iavf. The first step to fix that is to remove the crit lock. I will followup with a -next series that simplifies scheduling/tasks. Cancel the work without netdev lock (weird unlock+lock scheme), to fix the [splat2] (which would be totally ugly if we would kept the crit lock). Extend protected part of iavf_watchdog_task() to include scheduling more work. Note that the removed comment in iavf_reset_task() was misplaced, it belonged to inside of the removed if condition, so it's gone now. [splat1] - w/o this patch - The deadlock during VF removal: WARNING: possible circular locking dependency detected sh/3825 is trying to acquire lock: ((work_completion)(&(&adapter->watchdog_task)->work)){+.+.}-{0:0}, at: start_flush_work+0x1a1/0x470 but task is already holding lock: (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_remove+0xd1/0x690 [iavf] which lock already depends on the new lock. [splat2] - when cancelling work under crit lock, w/o this series, see [2] for the band aid attempt WARNING: possible circular locking dependency detected sh/3550 is trying to acquire lock: ((wq_completion)iavf){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: (&dev->lock){+.+.}-{4:4}, at: iavf_remove+0xa6/0x6e0 [iavf] which lock already depends on the new lock. [1] fc2e6b3b132a ("iavf: Rework mutexes for better synchronisation") [2] https://github.com/pkitszel/linux/commit/52dddbfc2bb60294083f5711a158a
CVE-2025-38359: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Fix in_atomic() handling in do_secure_storage_access() Kernel user spaces accesses to not exported pages in atomic context incorrectly try to resolve the page fault. With debug options enabled call traces like this can be seen: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1523 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 419074, name: qemu-system-s39 preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 INFO: lockdep is turned off. Preemption disabled at: [<00000383ea47cfa2>] copy_page_from_iter_atomic+0xa2/0x8a0 CPU: 12 UID: 0 PID: 419074 Comm: qemu-system-s39 Tainted: G W 6.16.0-20250531.rc0.git0.69b3a602feac.63.fc42.s390x+debug #1 PREEMPT Tainted: [W]=WARN Hardware name: IBM 3931 A01 703 (LPAR) Call Trace: [<00000383e990d282>] dump_stack_lvl+0xa2/0xe8 [<00000383e99bf152>] __might_resched+0x292/0x2d0 [<00000383eaa7c374>] down_read+0x34/0x2d0 [<00000383e99432f8>] do_secure_storage_access+0x108/0x360 [<00000383eaa724b0>] __do_pgm_check+0x130/0x220 [<00000383eaa842e4>] pgm_check_handler+0x114/0x160 [<00000383ea47d028>] copy_page_from_iter_atomic+0x128/0x8a0 ([<00000383ea47d016>] copy_page_from_iter_atomic+0x116/0x8a0) [<00000383e9c45eae>] generic_perform_write+0x16e/0x310 [<00000383e9eb87f4>] ext4_buffered_write_iter+0x84/0x160 [<00000383e9da0de4>] vfs_write+0x1c4/0x460 [<00000383e9da123c>] ksys_write+0x7c/0x100 [<00000383eaa7284e>] __do_syscall+0x15e/0x280 [<00000383eaa8417e>] system_call+0x6e/0x90 INFO: lockdep is turned off. It is not allowed to take the mmap_lock while in atomic context. Therefore handle such a secure storage access fault as if the accessed page is not mapped: the uaccess function will return -EFAULT, and the caller has to deal with this. Usually this means that the access is retried in process context, which allows to resolve the page fault (or in this case export the page).
CVE-2025-38421: In the Linux kernel, the following vulnerability has been resolved: platform/x86/amd: pmf: Use device managed allocations If setting up smart PC fails for any reason then this can lead to a double free when unloading amd-pmf. This is because dev->buf was freed but never set to NULL and is again freed in amd_pmf_remove(). To avoid subtle allocation bugs in failures leading to a double free change all allocations into device managed allocations.
CVE-2025-38426: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add basic validation for RAS header If RAS header read from EEPROM is corrupted, it could result in trying to allocate huge memory for reading the records. Add some validation to header fields.
CVE-2025-38584: In the Linux kernel, the following vulnerability has been resolved: padata: Fix pd UAF once and for all There is a race condition/UAF in padata_reorder that goes back to the initial commit. A reference count is taken at the start of the process in padata_do_parallel, and released at the end in padata_serial_worker. This reference count is (and only is) required for padata_replace to function correctly. If padata_replace is never called then there is no issue. In the function padata_reorder which serves as the core of padata, as soon as padata is added to queue->serial.list, and the associated spin lock released, that padata may be processed and the reference count on pd would go away. Fix this by getting the next padata before the squeue->serial lock is released. In order to make this possible, simplify padata_reorder by only calling it once the next padata arrives.
CVE-2025-38597: In the Linux kernel, the following vulnerability has been resolved: drm/rockchip: vop2: fail cleanly if missing a primary plane for a video-port Each window of a vop2 is usable by a specific set of video ports, so while binding the vop2, we look through the list of available windows trying to find one designated as primary-plane and usable by that specific port. The code later wants to use drm_crtc_init_with_planes with that found primary plane, but nothing has checked so far if a primary plane was actually found. For whatever reason, the rk3576 vp2 does not have a usable primary window (if vp0 is also in use) which brought the issue to light and ended in a null-pointer dereference further down. As we expect a primary-plane to exist for a video-port, add a check at the end of the window-iteration and fail probing if none was found.
CVE-2025-38605: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: Pass ab pointer directly to ath12k_dp_tx_get_encap_type() In ath12k_dp_tx_get_encap_type(), the arvif parameter is only used to retrieve the ab pointer. In vdev delete sequence the arvif->ar could become NULL and that would trigger kernel panic. Since the caller ath12k_dp_tx() already has a valid ab pointer, pass it directly to avoid panic and unnecessary dereferencing. PC points to "ath12k_dp_tx+0x228/0x988 [ath12k]" LR points to "ath12k_dp_tx+0xc8/0x988 [ath12k]". The Backtrace obtained is as follows: ath12k_dp_tx+0x228/0x988 [ath12k] ath12k_mac_tx_check_max_limit+0x608/0x920 [ath12k] ieee80211_process_measurement_req+0x320/0x348 [mac80211] ieee80211_tx_dequeue+0x9ac/0x1518 [mac80211] ieee80211_tx_dequeue+0xb14/0x1518 [mac80211] ieee80211_tx_prepare_skb+0x224/0x254 [mac80211] ieee80211_xmit+0xec/0x100 [mac80211] __ieee80211_subif_start_xmit+0xc50/0xf40 [mac80211] ieee80211_subif_start_xmit+0x2e8/0x308 [mac80211] netdev_start_xmit+0x150/0x18c dev_hard_start_xmit+0x74/0xc0 Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
CVE-2025-38621: In the Linux kernel, the following vulnerability has been resolved: md: make rdev_addable usable for rcu mode Our testcase trigger panic: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... Oops: Oops: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 85 Comm: kworker/2:1 Not tainted 6.16.0+ #94 PREEMPT(none) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Workqueue: md_misc md_start_sync RIP: 0010:rdev_addable+0x4d/0xf0 ... Call Trace: <TASK> md_start_sync+0x329/0x480 process_one_work+0x226/0x6d0 worker_thread+0x19e/0x340 kthread+0x10f/0x250 ret_from_fork+0x14d/0x180 ret_from_fork_asm+0x1a/0x30 </TASK> Modules linked in: raid10 CR2: 00000000000000e0 ---[ end trace 0000000000000000 ]--- RIP: 0010:rdev_addable+0x4d/0xf0 md_spares_need_change in md_start_sync will call rdev_addable which protected by rcu_read_lock/rcu_read_unlock. This rcu context will help protect rdev won't be released, but rdev->mddev will be set to NULL before we call synchronize_rcu in md_kick_rdev_from_array. Fix this by using READ_ONCE and check does rdev->mddev still alive.
CVE-2025-38627: In the Linux kernel, the following vulnerability has been resolved: f2fs: compress: fix UAF of f2fs_inode_info in f2fs_free_dic The decompress_io_ctx may be released asynchronously after I/O completion. If this file is deleted immediately after read, and the kworker of processing post_read_wq has not been executed yet due to high workloads, It is possible that the inode(f2fs_inode_info) is evicted and freed before it is used f2fs_free_dic. The UAF case as below: Thread A Thread B - f2fs_decompress_end_io - f2fs_put_dic - queue_work add free_dic work to post_read_wq - do_unlink - iput - evict - call_rcu This file is deleted after read. Thread C kworker to process post_read_wq - rcu_do_batch - f2fs_free_inode - kmem_cache_free inode is freed by rcu - process_scheduled_works - f2fs_late_free_dic - f2fs_free_dic - f2fs_release_decomp_mem read (dic->inode)->i_compress_algorithm This patch store compress_algorithm and sbi in dic to avoid inode UAF. In addition, the previous solution is deprecated in [1] may cause system hang. [1] https://lore.kernel.org/all/c36ab955-c8db-4a8b-a9d0-f07b5f426c3f@kernel.org
CVE-2025-38636: In the Linux kernel, the following vulnerability has been resolved: rv: Use strings in da monitors tracepoints Using DA monitors tracepoints with KASAN enabled triggers the following warning: BUG: KASAN: global-out-of-bounds in do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 Read of size 32 at addr ffffffffaada8980 by task ... Call Trace: <TASK> [...] do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 ? __pfx_do_trace_event_raw_event_event_da_monitor+0x10/0x10 ? trace_event_sncid+0x83/0x200 trace_event_sncid+0x163/0x200 [...] The buggy address belongs to the variable: automaton_snep+0x4e0/0x5e0 This is caused by the tracepoints reading 32 bytes __array instead of __string from the automata definition. Such strings are literals and reading 32 bytes ends up in out of bound memory accesses (e.g. the next automaton's data in this case). The error is harmless as, while printing the string, we stop at the null terminator, but it should still be fixed. Use the __string facilities while defining the tracepoints to avoid reading out of bound memory.
CVE-2025-39677: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix backlog accounting in qdisc_dequeue_internal This issue applies for the following qdiscs: hhf, fq, fq_codel, and fq_pie, and occurs in their change handlers when adjusting to the new limit. The problem is the following in the values passed to the subsequent qdisc_tree_reduce_backlog call given a tbf parent: When the tbf parent runs out of tokens, skbs of these qdiscs will be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued, which accounts for both qlen and backlog. However, in the case of qdisc_dequeue_internal, ONLY qlen is accounted for when pulling from gso_skb. This means that these qdiscs are missing a qdisc_qstats_backlog_dec when dropping packets to satisfy the new limit in their change handlers. One can observe this issue with the following (with tc patched to support a limit of 0): export TARGET=fq tc qdisc del dev lo root tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000 echo ''; echo 'add child'; tc -s -d qdisc show dev lo ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null echo ''; echo 'after ping'; tc -s -d qdisc show dev lo tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0 echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo tc qdisc replace dev lo handle 2: parent 1:1 sfq echo ''; echo 'post graft'; tc -s -d qdisc show dev lo The second to last show command shows 0 packets but a positive number (74) of backlog bytes. The problem becomes clearer in the last show command, where qdisc_purge_queue triggers qdisc_tree_reduce_backlog with the positive backlog and causes an underflow in the tbf parent's backlog (4096 Mb instead of 0). To fix this issue, the codepath for all clients of qdisc_dequeue_internal has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel. qdisc_dequeue_internal handles the backlog adjustments for all cases that do not directly use the dequeue handler. The old fq_codel_change limit adjustment loop accumulated the arguments to the subsequent qdisc_tree_reduce_backlog call through the cstats field. However, this is confusing and error prone as fq_codel_dequeue could also potentially mutate this field (which qdisc_dequeue_internal calls in the non gso_skb case), so we have unified the code here with other qdiscs.
CVE-2025-39762: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: add null check [WHY] Prevents null pointer dereferences to enhance function robustness [HOW] Adds early null check and return false if invalid.
CVE-2025-39764: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: remove refcounting in expectation dumpers Same pattern as previous patch: do not keep the expectation object alive via refcount, only store a cookie value and then use that as the skip hint for dump resumption. AFAICS this has the same issue as the one resolved in the conntrack dumper, when we do if (!refcount_inc_not_zero(&exp->use)) to increment the refcount, there is a chance that exp == last, which causes a double-increment of the refcount and subsequent memory leak.
CVE-2025-39775: In the Linux kernel, the following vulnerability has been resolved: mm/mremap: fix WARN with uffd that has remap events disabled Registering userfaultd on a VMA that spans at least one PMD and then mremap()'ing that VMA can trigger a WARN when recovering from a failed page table move due to a page table allocation error. The code ends up doing the right thing (recurse, avoiding moving actual page tables), but triggering that WARN is unpleasant: WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_normal_pmd mm/mremap.c:357 [inline] WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_pgt_entry mm/mremap.c:595 [inline] WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_page_tables+0x3832/0x44a0 mm/mremap.c:852 Modules linked in: CPU: 2 UID: 0 PID: 6133 Comm: syz.0.19 Not tainted 6.17.0-rc1-syzkaller-00004-g53e760d89498 #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:move_normal_pmd mm/mremap.c:357 [inline] RIP: 0010:move_pgt_entry mm/mremap.c:595 [inline] RIP: 0010:move_page_tables+0x3832/0x44a0 mm/mremap.c:852 Code: ... RSP: 0018:ffffc900037a76d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000032930007 RCX: ffffffff820c6645 RDX: ffff88802e56a440 RSI: ffffffff820c7201 RDI: 0000000000000007 RBP: ffff888037728fc0 R08: 0000000000000007 R09: 0000000000000000 R10: 0000000032930007 R11: 0000000000000000 R12: 0000000000000000 R13: ffffc900037a79a8 R14: 0000000000000001 R15: dffffc0000000000 FS: 000055556316a500(0000) GS:ffff8880d68bc000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b30863fff CR3: 0000000050171000 CR4: 0000000000352ef0 Call Trace: <TASK> copy_vma_and_data+0x468/0x790 mm/mremap.c:1215 move_vma+0x548/0x1780 mm/mremap.c:1282 mremap_to+0x1b7/0x450 mm/mremap.c:1406 do_mremap+0xfad/0x1f80 mm/mremap.c:1921 __do_sys_mremap+0x119/0x170 mm/mremap.c:1977 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcd/0x4c0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f00d0b8ebe9 Code: ... RSP: 002b:00007ffe5ea5ee98 EFLAGS: 00000246 ORIG_RAX: 0000000000000019 RAX: ffffffffffffffda RBX: 00007f00d0db5fa0 RCX: 00007f00d0b8ebe9 RDX: 0000000000400000 RSI: 0000000000c00000 RDI: 0000200000000000 RBP: 00007ffe5ea5eef0 R08: 0000200000c00000 R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000002 R13: 00007f00d0db5fa0 R14: 00007f00d0db5fa0 R15: 0000000000000005 </TASK> The underlying issue is that we recurse during the original page table move, but not during the recovery move. Fix it by checking for both VMAs and performing the check before the pmd_none() sanity check. Add a new helper where we perform+document that check for the PMD and PUD level. Thanks to Harry for bisecting.
CVE-2025-39789: In the Linux kernel, the following vulnerability has been resolved: crypto: x86/aegis - Add missing error checks The skcipher_walk functions can allocate memory and can fail, so checking for errors is necessary.
CVE-2025-39822: In the Linux kernel, the following vulnerability has been resolved: io_uring/kbuf: fix signedness in this_len calculation When importing and using buffers, buf->len is considered unsigned. However, buf->len is converted to signed int when committing. This can lead to unexpected behavior if the buffer is large enough to be interpreted as a negative value. Make min_t calculation unsigned.
CVE-2025-39830: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: HWS, Fix memory leak in hws_pool_buddy_init error path In the error path of hws_pool_buddy_init(), the buddy allocator cleanup doesn't free the allocator structure itself, causing a memory leak. Add the missing kfree() to properly release all allocated memory.
CVE-2025-39833: In the Linux kernel, the following vulnerability has been resolved: mISDN: hfcpci: Fix warning when deleting uninitialized timer With CONFIG_DEBUG_OBJECTS_TIMERS unloading hfcpci module leads to the following splat: [ 250.215892] ODEBUG: assert_init not available (active state 0) object: ffffffffc01a3dc0 object type: timer_list hint: 0x0 [ 250.217520] WARNING: CPU: 0 PID: 233 at lib/debugobjects.c:612 debug_print_object+0x1b6/0x2c0 [ 250.218775] Modules linked in: hfcpci(-) mISDN_core [ 250.219537] CPU: 0 UID: 0 PID: 233 Comm: rmmod Not tainted 6.17.0-rc2-g6f713187ac98 #2 PREEMPT(voluntary) [ 250.220940] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 250.222377] RIP: 0010:debug_print_object+0x1b6/0x2c0 [ 250.223131] Code: fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 4f 41 56 48 8b 14 dd a0 4e 01 9f 48 89 ee 48 c7 c7 20 46 01 9f e8 cb 84d [ 250.225805] RSP: 0018:ffff888015ea7c08 EFLAGS: 00010286 [ 250.226608] RAX: 0000000000000000 RBX: 0000000000000005 RCX: ffffffff9be93a95 [ 250.227708] RDX: 1ffff1100d945138 RSI: 0000000000000008 RDI: ffff88806ca289c0 [ 250.228993] RBP: ffffffff9f014a00 R08: 0000000000000001 R09: ffffed1002bd4f39 [ 250.230043] R10: ffff888015ea79cf R11: 0000000000000001 R12: 0000000000000001 [ 250.231185] R13: ffffffff9eea0520 R14: 0000000000000000 R15: ffff888015ea7cc8 [ 250.232454] FS: 00007f3208f01540(0000) GS:ffff8880caf5a000(0000) knlGS:0000000000000000 [ 250.233851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 250.234856] CR2: 00007f32090a7421 CR3: 0000000004d63000 CR4: 00000000000006f0 [ 250.236117] Call Trace: [ 250.236599] <TASK> [ 250.236967] ? trace_irq_enable.constprop.0+0xd4/0x130 [ 250.237920] debug_object_assert_init+0x1f6/0x310 [ 250.238762] ? __pfx_debug_object_assert_init+0x10/0x10 [ 250.239658] ? __lock_acquire+0xdea/0x1c70 [ 250.240369] __try_to_del_timer_sync+0x69/0x140 [ 250.241172] ? __pfx___try_to_del_timer_sync+0x10/0x10 [ 250.242058] ? __timer_delete_sync+0xc6/0x120 [ 250.242842] ? lock_acquire+0x30/0x80 [ 250.243474] ? __timer_delete_sync+0xc6/0x120 [ 250.244262] __timer_delete_sync+0x98/0x120 [ 250.245015] HFC_cleanup+0x10/0x20 [hfcpci] [ 250.245704] __do_sys_delete_module+0x348/0x510 [ 250.246461] ? __pfx___do_sys_delete_module+0x10/0x10 [ 250.247338] do_syscall_64+0xc1/0x360 [ 250.247924] entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by initializing hfc_tl timer with DEFINE_TIMER macro. Also, use mod_timer instead of manual timeout update.
CVE-2025-39834: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: HWS, Fix memory leak in hws_action_get_shared_stc_nic error flow When an invalid stc_type is provided, the function allocates memory for shared_stc but jumps to unlock_and_out without freeing it, causing a memory leak. Fix by jumping to free_shared_stc label instead to ensure proper cleanup.
CVE-2025-39859: In the Linux kernel, the following vulnerability has been resolved: ptp: ocp: fix use-after-free bugs causing by ptp_ocp_watchdog The ptp_ocp_detach() only shuts down the watchdog timer if it is pending. However, if the timer handler is already running, the timer_delete_sync() is not called. This leads to race conditions where the devlink that contains the ptp_ocp is deallocated while the timer handler is still accessing it, resulting in use-after-free bugs. The following details one of the race scenarios. (thread 1) | (thread 2) ptp_ocp_remove() | ptp_ocp_detach() | ptp_ocp_watchdog() if (timer_pending(&bp->watchdog))| bp = timer_container_of() timer_delete_sync() | | devlink_free(devlink) //free | | bp-> //use Resolve this by unconditionally calling timer_delete_sync() to ensure the timer is reliably deactivated, preventing any access after free.
CVE-2025-39862: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7915: fix list corruption after hardware restart Since stations are recreated from scratch, all lists that wcids are added to must be cleared before calling ieee80211_restart_hw. Set wcid->sta = 0 for each wcid entry in order to ensure that they are not added again before they are ready.
CVE-2025-39910: In the Linux kernel, the following vulnerability has been resolved: mm/vmalloc, mm/kasan: respect gfp mask in kasan_populate_vmalloc() kasan_populate_vmalloc() and its helpers ignore the caller's gfp_mask and always allocate memory using the hardcoded GFP_KERNEL flag. This makes them inconsistent with vmalloc(), which was recently extended to support GFP_NOFS and GFP_NOIO allocations. Page table allocations performed during shadow population also ignore the external gfp_mask. To preserve the intended semantics of GFP_NOFS and GFP_NOIO, wrap the apply_to_page_range() calls into the appropriate memalloc scope. xfs calls vmalloc with GFP_NOFS, so this bug could lead to deadlock. There was a report here https://lkml.kernel.org/r/686ea951.050a0220.385921.0016.GAE@google.com This patch: - Extends kasan_populate_vmalloc() and helpers to take gfp_mask; - Passes gfp_mask down to alloc_pages_bulk() and __get_free_page(); - Enforces GFP_NOFS/NOIO semantics with memalloc_*_save()/restore() around apply_to_page_range(); - Updates vmalloc.c and percpu allocator call sites accordingly.
CVE-2025-39925: In the Linux kernel, the following vulnerability has been resolved: can: j1939: implement NETDEV_UNREGISTER notification handler syzbot is reporting unregister_netdevice: waiting for vcan0 to become free. Usage count = 2 problem, for j1939 protocol did not have NETDEV_UNREGISTER notification handler for undoing changes made by j1939_sk_bind(). Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") expects that a call to j1939_priv_put() can be unconditionally delayed until j1939_sk_sock_destruct() is called. But we need to call j1939_priv_put() against an extra ref held by j1939_sk_bind() call (as a part of undoing changes made by j1939_sk_bind()) as soon as NETDEV_UNREGISTER notification fires (i.e. before j1939_sk_sock_destruct() is called via j1939_sk_release()). Otherwise, the extra ref on "struct j1939_priv" held by j1939_sk_bind() call prevents "struct net_device" from dropping the usage count to 1; making it impossible for unregister_netdevice() to continue. [mkl: remove space in front of label]
CVE-2025-39933: In the Linux kernel, the following vulnerability has been resolved: smb: client: let recv_done verify data_offset, data_length and remaining_data_length This is inspired by the related server fixes.
CVE-2025-39958: In the Linux kernel, the following vulnerability has been resolved: iommu/s390: Make attach succeed when the device was surprise removed When a PCI device is removed with surprise hotplug, there may still be attempts to attach the device to the default domain as part of tear down via (__iommu_release_dma_ownership()), or because the removal happens during probe (__iommu_probe_device()). In both cases zpci_register_ioat() fails with a cc value indicating that the device handle is invalid. This is because the device is no longer part of the instance as far as the hypervisor is concerned. Currently this leads to an error return and s390_iommu_attach_device() fails. This triggers the WARN_ON() in __iommu_group_set_domain_nofail() because attaching to the default domain must never fail. With the device fenced by the hypervisor no DMAs to or from memory are possible and the IOMMU translations have no effect. Proceed as if the registration was successful and let the hotplug event handling clean up the device. This is similar to how devices in the error state are handled since commit 59bbf596791b ("iommu/s390: Make attach succeed even if the device is in error state") except that for removal the domain will not be registered later. This approach was also previously discussed at the link. Handle both cases, error state and removal, in a helper which checks if the error needs to be propagated or ignored. Avoid magic number condition codes by using the pre-existing, but never used, defines for PCI load/store condition codes and rename them to reflect that they apply to all PCI instructions.
CVE-2025-40005: In the Linux kernel, the following vulnerability has been resolved: spi: cadence-quadspi: Implement refcount to handle unbind during busy driver support indirect read and indirect write operation with assumption no force device removal(unbind) operation. However force device removal(removal) is still available to root superuser. Unbinding driver during operation causes kernel crash. This changes ensure driver able to handle such operation for indirect read and indirect write by implementing refcount to track attached devices to the controller and gracefully wait and until attached devices remove operation completed before proceed with removal operation.
CVE-2025-40025: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer for non inode dnode As syzbot reported below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/file.c:1243! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 5354 Comm: syz.0.0 Not tainted 6.17.0-rc1-syzkaller-00211-g90d970cade8e #0 PREEMPT(full) RIP: 0010:f2fs_truncate_hole+0x69e/0x6c0 fs/f2fs/file.c:1243 Call Trace: <TASK> f2fs_punch_hole+0x2db/0x330 fs/f2fs/file.c:1306 f2fs_fallocate+0x546/0x990 fs/f2fs/file.c:2018 vfs_fallocate+0x666/0x7e0 fs/open.c:342 ksys_fallocate fs/open.c:366 [inline] __do_sys_fallocate fs/open.c:371 [inline] __se_sys_fallocate fs/open.c:369 [inline] __x64_sys_fallocate+0xc0/0x110 fs/open.c:369 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f1e65f8ebe9 w/ a fuzzed image, f2fs may encounter panic due to it detects inconsistent truncation range in direct node in f2fs_truncate_hole(). The root cause is: a non-inode dnode may has the same footer.ino and footer.nid, so the dnode will be parsed as an inode, then ADDRS_PER_PAGE() may return wrong blkaddr count which may be 923 typically, by chance, dn.ofs_in_node is equal to 923, then count can be calculated to 0 in below statement, later it will trigger panic w/ f2fs_bug_on(, count == 0 || ...). count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); This patch introduces a new node_type NODE_TYPE_NON_INODE, then allowing passing the new_type to sanity_check_node_footer in f2fs_get_node_folio() to detect corruption that a non-inode dnode has the same footer.ino and footer.nid. Scripts to reproduce: mkfs.f2fs -f /dev/vdb mount /dev/vdb /mnt/f2fs touch /mnt/f2fs/foo touch /mnt/f2fs/bar dd if=/dev/zero of=/mnt/f2fs/foo bs=1M count=8 umount /mnt/f2fs inject.f2fs --node --mb i_nid --nid 4 --idx 0 --val 5 /dev/vdb mount /dev/vdb /mnt/f2fs xfs_io /mnt/f2fs/foo -c "fpunch 6984k 4k"
CVE-2025-40054: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix UAF issue in f2fs_merge_page_bio() As JY reported in bugzilla [1], Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 pc : [0xffffffe51d249484] f2fs_is_cp_guaranteed+0x70/0x98 lr : [0xffffffe51d24adbc] f2fs_merge_page_bio+0x520/0x6d4 CPU: 3 UID: 0 PID: 6790 Comm: kworker/u16:3 Tainted: P B W OE 6.12.30-android16-5-maybe-dirty-4k #1 5f7701c9cbf727d1eebe77c89bbbeb3371e895e5 Tainted: [P]=PROPRIETARY_MODULE, [B]=BAD_PAGE, [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Workqueue: writeback wb_workfn (flush-254:49) Call trace: f2fs_is_cp_guaranteed+0x70/0x98 f2fs_inplace_write_data+0x174/0x2f4 f2fs_do_write_data_page+0x214/0x81c f2fs_write_single_data_page+0x28c/0x764 f2fs_write_data_pages+0x78c/0xce4 do_writepages+0xe8/0x2fc __writeback_single_inode+0x4c/0x4b4 writeback_sb_inodes+0x314/0x540 __writeback_inodes_wb+0xa4/0xf4 wb_writeback+0x160/0x448 wb_workfn+0x2f0/0x5dc process_scheduled_works+0x1c8/0x458 worker_thread+0x334/0x3f0 kthread+0x118/0x1ac ret_from_fork+0x10/0x20 [1] https://bugzilla.kernel.org/show_bug.cgi?id=220575 The panic was caused by UAF issue w/ below race condition: kworker - writepages - f2fs_write_cache_pages - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #1 into bio & cache bio in io->bio_list - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #2 into bio which is linked in io->bio_list write - f2fs_write_begin : write page #1 - f2fs_folio_wait_writeback - f2fs_submit_merged_ipu_write - f2fs_submit_write_bio : submit bio which inclues page #1 and #2 software IRQ - f2fs_write_end_io - fscrypt_free_bounce_page : freed bounced page which belongs to page #2 - inc_page_count( , WB_DATA_TYPE(data_folio), false) : data_folio points to fio->encrypted_page the bounced page can be freed before accessing it in f2fs_is_cp_guarantee() It can reproduce w/ below testcase: Run below script in shell #1: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" Run below script in shell #2: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" So, in f2fs_merge_page_bio(), let's avoid using fio->encrypted_page after commit page into internal ipu cache.
CVE-2025-40064: In the Linux kernel, the following vulnerability has been resolved: smc: Fix use-after-free in __pnet_find_base_ndev(). syzbot reported use-after-free of net_device in __pnet_find_base_ndev(), which was called during connect(). [0] smc_pnet_find_ism_resource() fetches sk_dst_get(sk)->dev and passes down to pnet_find_base_ndev(), where RTNL is held. Then, UAF happened at __pnet_find_base_ndev() when the dev is first used. This means dev had already been freed before acquiring RTNL in pnet_find_base_ndev(). While dev is going away, dst->dev could be swapped with blackhole_netdev, and the dev's refcnt by dst will be released. We must hold dev's refcnt before calling smc_pnet_find_ism_resource(). Also, smc_pnet_find_roce_resource() has the same problem. Let's use __sk_dst_get() and dst_dev_rcu() in the two functions. [0]: BUG: KASAN: use-after-free in __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 Read of size 1 at addr ffff888036bac33a by task syz.0.3632/18609 CPU: 1 UID: 0 PID: 18609 Comm: syz.0.3632 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 pnet_find_base_ndev net/smc/smc_pnet.c:946 [inline] smc_pnet_find_ism_by_pnetid net/smc/smc_pnet.c:1103 [inline] smc_pnet_find_ism_resource+0xef/0x390 net/smc/smc_pnet.c:1154 smc_find_ism_device net/smc/af_smc.c:1030 [inline] smc_find_proposal_devices net/smc/af_smc.c:1115 [inline] __smc_connect+0x372/0x1890 net/smc/af_smc.c:1545 smc_connect+0x877/0xd90 net/smc/af_smc.c:1715 __sys_connect_file net/socket.c:2086 [inline] __sys_connect+0x313/0x440 net/socket.c:2105 __do_sys_connect net/socket.c:2111 [inline] __se_sys_connect net/socket.c:2108 [inline] __x64_sys_connect+0x7a/0x90 net/socket.c:2108 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f47cbf8eba9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f47ccdb1038 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 00007f47cc1d5fa0 RCX: 00007f47cbf8eba9 RDX: 0000000000000010 RSI: 0000200000000280 RDI: 000000000000000b RBP: 00007f47cc011e19 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f47cc1d6038 R14: 00007f47cc1d5fa0 R15: 00007ffc512f8aa8 </TASK> The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888036bacd00 pfn:0x36bac flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000000 ffffea0001243d08 ffff8880b863fdc0 0000000000000000 raw: ffff888036bacd00 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as freed page last allocated via order 2, migratetype Unmovable, gfp_mask 0x446dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO|__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_COMP), pid 16741, tgid 16741 (syz-executor), ts 343313197788, free_ts 380670750466 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x240/0x2a0 mm/page_alloc.c:1851 prep_new_page mm/page_alloc.c:1859 [inline] get_page_from_freelist+0x21e4/0x22c0 mm/page_alloc.c:3858 __alloc_frozen_pages_noprof+0x181/0x370 mm/page_alloc.c:5148 alloc_pages_mpol+0x232/0x4a0 mm/mempolicy.c:2416 ___kmalloc_large_node+0x5f/0x1b0 mm/slub.c:4317 __kmalloc_large_node_noprof+0x18/0x90 mm/slub.c:4348 __do_kmalloc_node mm/slub.c:4364 [inline] __kvmalloc_node ---truncated---
CVE-2025-40065: In the Linux kernel, the following vulnerability has been resolved: RISC-V: KVM: Write hgatp register with valid mode bits According to the RISC-V Privileged Architecture Spec, when MODE=Bare is selected,software must write zero to the remaining fields of hgatp. We have detected the valid mode supported by the HW before, So using a valid mode to detect how many vmid bits are supported.
CVE-2025-40074: In the Linux kernel, the following vulnerability has been resolved: ipv4: start using dst_dev_rcu() Change icmpv4_xrlim_allow(), ip_defrag() to prevent possible UAF. Change ipmr_prepare_xmit(), ipmr_queue_fwd_xmit(), ip_mr_output(), ipv4_neigh_lookup() to use lockdep enabled dst_dev_rcu().
CVE-2025-40086: In the Linux kernel, the following vulnerability has been resolved: drm/xe: Don't allow evicting of BOs in same VM in array of VM binds An array of VM binds can potentially evict other buffer objects (BOs) within the same VM under certain conditions, which may lead to NULL pointer dereferences later in the bind pipeline. To prevent this, clear the allow_res_evict flag in the xe_bo_validate call. v2: - Invert polarity of no_res_evict (Thomas) - Add comment in code explaining issue (Thomas) (cherry picked from commit 8b9ba8d6d95fe75fed6b0480bb03da4b321bea08)
CVE-2025-40098: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: cs35l41: Fix NULL pointer dereference in cs35l41_get_acpi_mute_state() Return value of a function acpi_evaluate_dsm() is dereferenced without checking for NULL, but it is usually checked for this function. acpi_evaluate_dsm() may return NULL, when acpi_evaluate_object() returns acpi_status other than ACPI_SUCCESS, so add a check to prevent the crach. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2025-40102: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Prevent access to vCPU events before init Another day, another syzkaller bug. KVM erroneously allows userspace to pend vCPU events for a vCPU that hasn't been initialized yet, leading to KVM interpreting a bunch of uninitialized garbage for routing / injecting the exception. In one case the injection code and the hyp disagree on whether the vCPU has a 32bit EL1 and put the vCPU into an illegal mode for AArch64, tripping the BUG() in exception_target_el() during the next injection: kernel BUG at arch/arm64/kvm/inject_fault.c:40! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 3 UID: 0 PID: 318 Comm: repro Not tainted 6.17.0-rc4-00104-g10fd0285305d #6 PREEMPT Hardware name: linux,dummy-virt (DT) pstate: 21402009 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : exception_target_el+0x88/0x8c lr : pend_serror_exception+0x18/0x13c sp : ffff800082f03a10 x29: ffff800082f03a10 x28: ffff0000cb132280 x27: 0000000000000000 x26: 0000000000000000 x25: ffff0000c2a99c20 x24: 0000000000000000 x23: 0000000000008000 x22: 0000000000000002 x21: 0000000000000004 x20: 0000000000008000 x19: ffff0000c2a99c20 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000200000c0 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : ffff800082f03af8 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffff800080f621f0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 000000000040009b x1 : 0000000000000003 x0 : ffff0000c2a99c20 Call trace: exception_target_el+0x88/0x8c (P) kvm_inject_serror_esr+0x40/0x3b4 __kvm_arm_vcpu_set_events+0xf0/0x100 kvm_arch_vcpu_ioctl+0x180/0x9d4 kvm_vcpu_ioctl+0x60c/0x9f4 __arm64_sys_ioctl+0xac/0x104 invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x34/0xf0 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Code: f946bc01 b4fffe61 9101e020 17fffff2 (d4210000) Reject the ioctls outright as no sane VMM would call these before KVM_ARM_VCPU_INIT anyway. Even if it did the exception would've been thrown away by the eventual reset of the vCPU's state.
CVE-2025-40113: In the Linux kernel, the following vulnerability has been resolved: remoteproc: qcom: pas: Shutdown lite ADSP DTB on X1E The ADSP firmware on X1E has separate firmware binaries for the main firmware and the DTB. The same applies for the "lite" firmware loaded by the boot firmware. When preparing to load the new ADSP firmware we shutdown the lite_pas_id for the main firmware, but we don't shutdown the corresponding lite pas_id for the DTB. The fact that we're leaving it "running" forever becomes obvious if you try to reuse (or just access) the memory region used by the "lite" firmware: The &adsp_boot_mem is accessible, but accessing the &adsp_boot_dtb_mem results in a crash. We don't support reusing the memory regions currently, but nevertheless we should not keep part of the lite firmware running. Fix this by adding the lite_dtb_pas_id and shutting it down as well. We don't have a way to detect if the lite firmware is actually running yet, so ignore the return status of qcom_scm_pas_shutdown() for now. This was already the case before, the assignment to "ret" is not used anywhere.
CVE-2025-40130: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix data race in CPU latency PM QoS request handling The cpu_latency_qos_add/remove/update_request interfaces lack internal synchronization by design, requiring the caller to ensure thread safety. The current implementation relies on the 'pm_qos_enabled' flag, which is insufficient to prevent concurrent access and cannot serve as a proper synchronization mechanism. This has led to data races and list corruption issues. A typical race condition call trace is: [Thread A] ufshcd_pm_qos_exit() --> cpu_latency_qos_remove_request() --> cpu_latency_qos_apply(); --> pm_qos_update_target() --> plist_del <--(1) delete plist node --> memset(req, 0, sizeof(*req)); --> hba->pm_qos_enabled = false; [Thread B] ufshcd_devfreq_target --> ufshcd_devfreq_scale --> ufshcd_scale_clks --> ufshcd_pm_qos_update <--(2) pm_qos_enabled is true --> cpu_latency_qos_update_request --> pm_qos_update_target --> plist_del <--(3) plist node use-after-free Introduces a dedicated mutex to serialize PM QoS operations, preventing data races and ensuring safe access to PM QoS resources, including sysfs interface reads.
CVE-2025-40135: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_xmit() Use RCU in ip6_xmit() in order to use dst_dev_rcu() to prevent possible UAF.
CVE-2025-40136: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/qm - request reserved interrupt for virtual function The device interrupt vector 3 is an error interrupt for physical function and a reserved interrupt for virtual function. However, the driver has not registered the reserved interrupt for virtual function. When allocating interrupts, the number of interrupts is allocated based on powers of two, which includes this interrupt. When the system enables GICv4 and the virtual function passthrough to the virtual machine, releasing the interrupt in the driver triggers a warning. The WARNING report is: WARNING: CPU: 62 PID: 14889 at arch/arm64/kvm/vgic/vgic-its.c:852 its_free_ite+0x94/0xb4 Therefore, register a reserved interrupt for VF and set the IRQF_NO_AUTOEN flag to avoid that warning.
CVE-2025-40139: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in in smc_clc_prfx_set(). smc_clc_prfx_set() is called during connect() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dev_dst_rcu() under rcu_read_lock() after kernel_getsockname(). Note that the returned value of smc_clc_prfx_set() is not used in the caller. While at it, we change the 1st arg of smc_clc_prfx_set[46]_rcu() not to touch dst there.
CVE-2025-40146: In the Linux kernel, the following vulnerability has been resolved: blk-mq: fix potential deadlock while nr_requests grown Allocate and free sched_tags while queue is freezed can deadlock[1], this is a long term problem, hence allocate memory before freezing queue and free memory after queue is unfreezed. [1] https://lore.kernel.org/all/0659ea8d-a463-47c8-9180-43c719e106eb@linux.ibm.com/
CVE-2025-40147: In the Linux kernel, the following vulnerability has been resolved: blk-throttle: fix access race during throttle policy activation On repeated cold boots we occasionally hit a NULL pointer crash in blk_should_throtl() when throttling is consulted before the throttle policy is fully enabled for the queue. Checking only q->td != NULL is insufficient during early initialization, so blkg_to_pd() for the throttle policy can still return NULL and blkg_to_tg() becomes NULL, which later gets dereferenced. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000156 ... pc : submit_bio_noacct+0x14c/0x4c8 lr : submit_bio_noacct+0x48/0x4c8 sp : ffff800087f0b690 x29: ffff800087f0b690 x28: 0000000000005f90 x27: ffff00068af393c0 x26: 0000000000080000 x25: 000000000002fbc0 x24: ffff000684ddcc70 x23: 0000000000000000 x22: 0000000000000000 x21: 0000000000000000 x20: 0000000000080000 x19: ffff000684ddcd08 x18: ffffffffffffffff x17: 0000000000000000 x16: ffff80008132a550 x15: 0000ffff98020fff x14: 0000000000000000 x13: 1fffe000d11d7021 x12: ffff000688eb810c x11: ffff00077ec4bb80 x10: ffff000688dcb720 x9 : ffff80008068ef60 x8 : 00000a6fb8a86e85 x7 : 000000000000111e x6 : 0000000000000002 x5 : 0000000000000246 x4 : 0000000000015cff x3 : 0000000000394500 x2 : ffff000682e35e40 x1 : 0000000000364940 x0 : 000000000000001a Call trace: submit_bio_noacct+0x14c/0x4c8 verity_map+0x178/0x2c8 __map_bio+0x228/0x250 dm_submit_bio+0x1c4/0x678 __submit_bio+0x170/0x230 submit_bio_noacct_nocheck+0x16c/0x388 submit_bio_noacct+0x16c/0x4c8 submit_bio+0xb4/0x210 f2fs_submit_read_bio+0x4c/0xf0 f2fs_mpage_readpages+0x3b0/0x5f0 f2fs_readahead+0x90/0xe8 Tighten blk_throtl_activated() to also require that the throttle policy bit is set on the queue: return q->td != NULL && test_bit(blkcg_policy_throtl.plid, q->blkcg_pols); This prevents blk_should_throtl() from accessing throttle group state until policy data has been attached to blkgs.
CVE-2025-40150: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid migrating empty section It reports a bug from device w/ zufs: F2FS-fs (dm-64): Inconsistent segment (173822) type [1, 0] in SSA and SIT F2FS-fs (dm-64): Stopped filesystem due to reason: 4 Thread A Thread B - f2fs_expand_inode_data - f2fs_allocate_pinning_section - f2fs_gc_range - do_garbage_collect w/ segno #x - writepage - f2fs_allocate_data_block - new_curseg - allocate segno #x The root cause is: fallocate on pinning file may race w/ block allocation as above, result in do_garbage_collect() from fallocate() may migrate segment which is just allocated by a log, the log will update segment type in its in-memory structure, however GC will get segment type from on-disk SSA block, once segment type changes by log, we can detect such inconsistency, then shutdown filesystem. In this case, on-disk SSA shows type of segno #173822 is 1 (SUM_TYPE_NODE), however segno #173822 was just allocated as data type segment, so in-memory SIT shows type of segno #173822 is 0 (SUM_TYPE_DATA). Change as below to fix this issue: - check whether current section is empty before gc - add sanity checks on do_garbage_collect() to avoid any race case, result in migrating segment used by log. - btw, it fixes misc issue in printed logs: "SSA and SIT" -> "SIT and SSA".
CVE-2025-40158: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_output() Use RCU in ip6_output() in order to use dst_dev_rcu() to prevent possible UAF. We can remove rcu_read_lock()/rcu_read_unlock() pairs from ip6_finish_output2().
CVE-2025-40168: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in smc_clc_prfx_match(). smc_clc_prfx_match() is called from smc_listen_work() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dst_dev_rcu(). Note that the returned value of smc_clc_prfx_match() is not used in the caller.
CVE-2025-40217: In the Linux kernel, the following vulnerability has been resolved: pidfs: validate extensible ioctls Validate extensible ioctls stricter than we do now.
CVE-2025-40219: In the Linux kernel, the following vulnerability has been resolved: PCI/IOV: Fix race between SR-IOV enable/disable and hotplug Commit 05703271c3cd ("PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV") tried to fix a race between the VF removal inside sriov_del_vfs() and concurrent hot unplug by taking the PCI rescan/remove lock in sriov_del_vfs(). Similarly the PCI rescan/remove lock was also taken in sriov_add_vfs() to protect addition of VFs. This approach however causes deadlock on trying to remove PFs with SR-IOV enabled because PFs disable SR-IOV during removal and this removal happens under the PCI rescan/remove lock. So the original fix had to be reverted. Instead of taking the PCI rescan/remove lock in sriov_add_vfs() and sriov_del_vfs(), fix the race that occurs with SR-IOV enable and disable vs hotplug higher up in the callchain by taking the lock in sriov_numvfs_store() before calling into the driver's sriov_configure() callback.
CVE-2025-40247: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix pgtable prealloc error path The following splat was reported: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000008d0fd8000 [0000000000000010] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] SMP CPU: 5 UID: 1000 PID: 149076 Comm: Xwayland Tainted: G S 6.16.0-rc2-00809-g0b6974bb4134-dirty #367 PREEMPT Tainted: [S]=CPU_OUT_OF_SPEC Hardware name: Qualcomm Technologies, Inc. SM8650 HDK (DT) pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : build_detached_freelist+0x28/0x224 lr : kmem_cache_free_bulk.part.0+0x38/0x244 sp : ffff000a508c7a20 x29: ffff000a508c7a20 x28: ffff000a508c7d50 x27: ffffc4e49d16f350 x26: 0000000000000058 x25: 00000000fffffffc x24: 0000000000000000 x23: ffff00098c4e1450 x22: 00000000fffffffc x21: 0000000000000000 x20: ffff000a508c7af8 x19: 0000000000000002 x18: 00000000000003e8 x17: ffff000809523850 x16: ffff000809523820 x15: 0000000000401640 x14: ffff000809371140 x13: 0000000000000130 x12: ffff0008b5711e30 x11: 00000000001058fa x10: 0000000000000a80 x9 : ffff000a508c7940 x8 : ffff000809371ba0 x7 : 781fffe033087fff x6 : 0000000000000000 x5 : ffff0008003cd000 x4 : 781fffe033083fff x3 : ffff000a508c7af8 x2 : fffffdffc0000000 x1 : 0001000000000000 x0 : ffff0008001a6a00 Call trace: build_detached_freelist+0x28/0x224 (P) kmem_cache_free_bulk.part.0+0x38/0x244 kmem_cache_free_bulk+0x10/0x1c msm_iommu_pagetable_prealloc_cleanup+0x3c/0xd0 msm_vma_job_free+0x30/0x240 msm_ioctl_vm_bind+0x1d0/0x9a0 drm_ioctl_kernel+0x84/0x104 drm_ioctl+0x358/0x4d4 __arm64_sys_ioctl+0x8c/0xe0 invoke_syscall+0x44/0x100 el0_svc_common.constprop.0+0x3c/0xe0 do_el0_svc+0x18/0x20 el0_svc+0x30/0x100 el0t_64_sync_handler+0x104/0x130 el0t_64_sync+0x170/0x174 Code: aa0203f5 b26287e2 f2dfbfe2 aa0303f4 (f8737ab6) ---[ end trace 0000000000000000 ]--- Since msm_vma_job_free() is called directly from the ioctl, this looks like an error path cleanup issue. Which I think results from prealloc_cleanup() called without a preceding successful prealloc_allocate() call. So handle that case better. Patchwork: https://patchwork.freedesktop.org/patch/678677/
CVE-2025-40338: In the Linux kernel, the following vulnerability has been resolved: ASoC: Intel: avs: Do not share the name pointer between components By sharing 'name' directly, tearing down components may lead to use-after-free errors. Duplicate the name to avoid that. At the same time, update the order of operations - since commit cee28113db17 ("ASoC: dmaengine_pcm: Allow passing component name via config") the framework does not override component->name if set before invoking the initializer.
CVE-2025-40355: In the Linux kernel, the following vulnerability has been resolved: sysfs: check visibility before changing group attribute ownership Since commit 0c17270f9b92 ("net: sysfs: Implement is_visible for phys_(port_id, port_name, switch_id)"), __dev_change_net_namespace() can hit WARN_ON() when trying to change owner of a file that isn't visible. See the trace below: WARNING: CPU: 6 PID: 2938 at net/core/dev.c:12410 __dev_change_net_namespace+0xb89/0xc30 CPU: 6 UID: 0 PID: 2938 Comm: incusd Not tainted 6.17.1-1-mainline #1 PREEMPT(full) 4b783b4a638669fb644857f484487d17cb45ed1f Hardware name: Framework Laptop 13 (AMD Ryzen 7040Series)/FRANMDCP07, BIOS 03.07 02/19/2025 RIP: 0010:__dev_change_net_namespace+0xb89/0xc30 [...] Call Trace: <TASK> ? if6_seq_show+0x30/0x50 do_setlink.isra.0+0xc7/0x1270 ? __nla_validate_parse+0x5c/0xcc0 ? security_capable+0x94/0x1a0 rtnl_newlink+0x858/0xc20 ? update_curr+0x8e/0x1c0 ? update_entity_lag+0x71/0x80 ? sched_balance_newidle+0x358/0x450 ? psi_task_switch+0x113/0x2a0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x346/0x3e0 ? sched_clock+0x10/0x30 ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x59/0x110 netlink_unicast+0x285/0x3c0 ? __alloc_skb+0xdb/0x1a0 netlink_sendmsg+0x20d/0x430 ____sys_sendmsg+0x39f/0x3d0 ? import_iovec+0x2f/0x40 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x81/0x970 ? __sys_bind+0xe3/0x110 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? sock_alloc_file+0x63/0xc0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? alloc_fd+0x12e/0x190 ? put_unused_fd+0x2a/0x70 ? do_sys_openat2+0xa2/0xe0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? exc_page_fault+0x7e/0x1a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e [...] </TASK> Fix this by checking is_visible() before trying to touch the attribute.
CVE-2025-54505:
CVE-2025-68174: In the Linux kernel, the following vulnerability has been resolved: amd/amdkfd: enhance kfd process check in switch partition current switch partition only check if kfd_processes_table is empty. kfd_prcesses_table entry is deleted in kfd_process_notifier_release, but kfd_process tear down is in kfd_process_wq_release. consider two processes: Process A (workqueue) -> kfd_process_wq_release -> Access kfd_node member Process B switch partition -> amdgpu_xcp_pre_partition_switch -> amdgpu_amdkfd_device_fini_sw -> kfd_node tear down. Process A and B may trigger a race as shown in dmesg log. This patch is to resolve the race by adding an atomic kfd_process counter kfd_processes_count, it increment as create kfd process, decrement as finish kfd_process_wq_release. v2: Put kfd_processes_count per kfd_dev, move decrement to kfd_process_destroy_pdds and bug fix. (Philip Yang) [3966658.307702] divide error: 0000 [#1] SMP NOPTI [3966658.350818] i10nm_edac [3966658.356318] CPU: 124 PID: 38435 Comm: kworker/124:0 Kdump: loaded Tainted [3966658.356890] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] [3966658.362839] nfit [3966658.366457] RIP: 0010:kfd_get_num_sdma_engines+0x17/0x40 [amdgpu] [3966658.366460] Code: 00 00 e9 ac 81 02 00 66 66 2e 0f 1f 84 00 00 00 00 00 90 0f 1f 44 00 00 48 8b 4f 08 48 8b b7 00 01 00 00 8b 81 58 26 03 00 99 <f7> be b8 01 00 00 80 b9 70 2e 00 00 00 74 0b 83 f8 02 ba 02 00 00 [3966658.380967] x86_pkg_temp_thermal [3966658.391529] RSP: 0018:ffffc900a0edfdd8 EFLAGS: 00010246 [3966658.391531] RAX: 0000000000000008 RBX: ffff8974e593b800 RCX: ffff888645900000 [3966658.391531] RDX: 0000000000000000 RSI: ffff888129154400 RDI: ffff888129151c00 [3966658.391532] RBP: ffff8883ad79d400 R08: 0000000000000000 R09: ffff8890d2750af4 [3966658.391532] R10: 0000000000000018 R11: 0000000000000018 R12: 0000000000000000 [3966658.391533] R13: ffff8883ad79d400 R14: ffffe87ff662ba00 R15: ffff8974e593b800 [3966658.391533] FS: 0000000000000000(0000) GS:ffff88fe7f600000(0000) knlGS:0000000000000000 [3966658.391534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3966658.391534] CR2: 0000000000d71000 CR3: 000000dd0e970004 CR4: 0000000002770ee0 [3966658.391535] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [3966658.391535] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [3966658.391536] PKRU: 55555554 [3966658.391536] Call Trace: [3966658.391674] deallocate_sdma_queue+0x38/0xa0 [amdgpu] [3966658.391762] process_termination_cpsch+0x1ed/0x480 [amdgpu] [3966658.399754] intel_powerclamp [3966658.402831] kfd_process_dequeue_from_all_devices+0x5b/0xc0 [amdgpu] [3966658.402908] kfd_process_wq_release+0x1a/0x1a0 [amdgpu] [3966658.410516] coretemp [3966658.434016] process_one_work+0x1ad/0x380 [3966658.434021] worker_thread+0x49/0x310 [3966658.438963] kvm_intel [3966658.446041] ? process_one_work+0x380/0x380 [3966658.446045] kthread+0x118/0x140 [3966658.446047] ? __kthread_bind_mask+0x60/0x60 [3966658.446050] ret_from_fork+0x1f/0x30 [3966658.446053] Modules linked in: kpatch_20765354(OEK) [3966658.455310] kvm [3966658.464534] mptcp_diag xsk_diag raw_diag unix_diag af_packet_diag netlink_diag udp_diag act_pedit act_mirred act_vlan cls_flower kpatch_21951273(OEK) kpatch_18424469(OEK) kpatch_19749756(OEK) [3966658.473462] idxd_mdev [3966658.482306] kpatch_17971294(OEK) sch_ingress xt_conntrack amdgpu(OE) amdxcp(OE) amddrm_buddy(OE) amd_sched(OE) amdttm(OE) amdkcl(OE) intel_ifs iptable_mangle tcm_loop target_core_pscsi tcp_diag target_core_file inet_diag target_core_iblock target_core_user target_core_mod coldpgs kpatch_18383292(OEK) ip6table_nat ip6table_filter ip6_tables ip_set_hash_ipportip ip_set_hash_ipportnet ip_set_hash_ipport ip_set_bitmap_port xt_comment iptable_nat nf_nat iptable_filter ip_tables ip_set ip_vs_sh ip_vs_wrr ip_vs_rr ip_vs nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 sn_core_odd(OE) i40e overlay binfmt_misc tun bonding(OE) aisqos(OE) aisqo ---truncated---
CVE-2025-68175: In the Linux kernel, the following vulnerability has been resolved: media: nxp: imx8-isi: Fix streaming cleanup on release The current implementation unconditionally calls mxc_isi_video_cleanup_streaming() in mxc_isi_video_release(). This can lead to situations where any release call (like from a simple "v4l2-ctl -l") may release a currently streaming queue when called on such a device. This is reproducible on an i.MX8MP board by streaming from an ISI capture device using gstreamer: gst-launch-1.0 -v v4l2src device=/dev/videoX ! \ video/x-raw,format=GRAY8,width=1280,height=800,framerate=1/120 ! \ fakesink While this stream is running, querying the caps of the same device provokes the error state: v4l2-ctl -l -d /dev/videoX This results in the following trace: [ 155.452152] ------------[ cut here ]------------ [ 155.452163] WARNING: CPU: 0 PID: 1708 at drivers/media/platform/nxp/imx8-isi/imx8-isi-pipe.c:713 mxc_isi_pipe_irq_handler+0x19c/0x1b0 [imx8_isi] [ 157.004248] Modules linked in: cfg80211 rpmsg_ctrl rpmsg_char rpmsg_tty virtio_rpmsg_bus rpmsg_ns rpmsg_core rfkill nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables mcp251x6 [ 157.053499] CPU: 0 UID: 0 PID: 1708 Comm: python3 Not tainted 6.15.4-00114-g1f61ca5cad76 #1 PREEMPT [ 157.064369] Hardware name: imx8mp_board_01 (DT) [ 157.068205] pstate: 400000c5 (nZcv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 157.075169] pc : mxc_isi_pipe_irq_handler+0x19c/0x1b0 [imx8_isi] [ 157.081195] lr : mxc_isi_pipe_irq_handler+0x38/0x1b0 [imx8_isi] [ 157.087126] sp : ffff800080003ee0 [ 157.090438] x29: ffff800080003ee0 x28: ffff0000c3688000 x27: 0000000000000000 [ 157.097580] x26: 0000000000000000 x25: ffff0000c1e7ac00 x24: ffff800081b5ad50 [ 157.104723] x23: 00000000000000d1 x22: 0000000000000000 x21: ffff0000c25e4000 [ 157.111866] x20: 0000000060000200 x19: ffff80007a0608d0 x18: 0000000000000000 [ 157.119008] x17: ffff80006a4e3000 x16: ffff800080000000 x15: 0000000000000000 [ 157.126146] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 157.133287] x11: 0000000000000040 x10: ffff0000c01445f0 x9 : ffff80007a053a38 [ 157.140425] x8 : ffff0000c04004b8 x7 : 0000000000000000 x6 : 0000000000000000 [ 157.147567] x5 : ffff0000c0400490 x4 : ffff80006a4e3000 x3 : ffff0000c25e4000 [ 157.154706] x2 : 0000000000000000 x1 : ffff8000825c0014 x0 : 0000000060000200 [ 157.161850] Call trace: [ 157.164296] mxc_isi_pipe_irq_handler+0x19c/0x1b0 [imx8_isi] (P) [ 157.170319] __handle_irq_event_percpu+0x58/0x218 [ 157.175029] handle_irq_event+0x54/0xb8 [ 157.178867] handle_fasteoi_irq+0xac/0x248 [ 157.182968] handle_irq_desc+0x48/0x68 [ 157.186723] generic_handle_domain_irq+0x24/0x38 [ 157.191346] gic_handle_irq+0x54/0x120 [ 157.195098] call_on_irq_stack+0x24/0x30 [ 157.199027] do_interrupt_handler+0x88/0x98 [ 157.203212] el0_interrupt+0x44/0xc0 [ 157.206792] __el0_irq_handler_common+0x18/0x28 [ 157.211328] el0t_64_irq_handler+0x10/0x20 [ 157.215429] el0t_64_irq+0x198/0x1a0 [ 157.219009] ---[ end trace 0000000000000000 ]--- Address this issue by moving the streaming preparation and cleanup to the vb2 .prepare_streaming() and .unprepare_streaming() operations. This also simplifies the driver by allowing direct usage of the vb2_ioctl_streamon() and vb2_ioctl_streamoff() helpers, and removal of the manual cleanup from mxc_isi_video_release().
CVE-2025-68193: In the Linux kernel, the following vulnerability has been resolved: drm/xe/guc: Add devm release action to safely tear down CT When a buffer object (BO) is allocated with the XE_BO_FLAG_GGTT_INVALIDATE flag, the driver initiates TLB invalidation requests via the CTB mechanism while releasing the BO. However a premature release of the CTB BO can lead to system crashes, as observed in: Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:h2g_write+0x2f3/0x7c0 [xe] Call Trace: guc_ct_send_locked+0x8b/0x670 [xe] xe_guc_ct_send_locked+0x19/0x60 [xe] send_tlb_invalidation+0xb4/0x460 [xe] xe_gt_tlb_invalidation_ggtt+0x15e/0x2e0 [xe] ggtt_invalidate_gt_tlb.part.0+0x16/0x90 [xe] ggtt_node_remove+0x110/0x140 [xe] xe_ggtt_node_remove+0x40/0xa0 [xe] xe_ggtt_remove_bo+0x87/0x250 [xe] Introduce a devm-managed release action during xe_guc_ct_init() and xe_guc_ct_init_post_hwconfig() to ensure proper CTB disablement before resource deallocation, preventing the use-after-free scenario.
CVE-2025-68209: In the Linux kernel, the following vulnerability has been resolved: mlx5: Fix default values in create CQ Currently, CQs without a completion function are assigned the mlx5_add_cq_to_tasklet function by default. This is problematic since only user CQs created through the mlx5_ib driver are intended to use this function. Additionally, all CQs that will use doorbells instead of polling for completions must call mlx5_cq_arm. However, the default CQ creation flow leaves a valid value in the CQ's arm_db field, allowing FW to send interrupts to polling-only CQs in certain corner cases. These two factors would allow a polling-only kernel CQ to be triggered by an EQ interrupt and call a completion function intended only for user CQs, causing a null pointer exception. Some areas in the driver have prevented this issue with one-off fixes but did not address the root cause. This patch fixes the described issue by adding defaults to the create CQ flow. It adds a default dummy completion function to protect against null pointer exceptions, and it sets an invalid command sequence number by default in kernel CQs to prevent the FW from sending an interrupt to the CQ until it is armed. User CQs are responsible for their own initialization values. Callers of mlx5_core_create_cq are responsible for changing the completion function and arming the CQ per their needs.
CVE-2025-68236: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: ufs-qcom: Fix UFS OCP issue during UFS power down (PC=3) According to UFS specifications, the power-off sequence for a UFS device includes: - Sending an SSU command with Power_Condition=3 and await a response. - Asserting RST_N low. - Turning off REF_CLK. - Turning off VCC. - Turning off VCCQ/VCCQ2. As part of ufs shutdown, after the SSU command completion, asserting hardware reset (HWRST) triggers the device firmware to wake up and execute its reset routine. This routine initializes hardware blocks and takes a few milliseconds to complete. During this time, the ICCQ draws a large current. This large ICCQ current may cause issues for the regulator which is supplying power to UFS, because the turn off request from UFS driver to the regulator framework will be immediately followed by low power mode(LPM) request by regulator framework. This is done by framework because UFS which is the only client is requesting for disable. So if the rail is still in the process of shutting down while ICCQ exceeds LPM current thresholds, and LPM mode is activated in hardware during this state, it may trigger an overcurrent protection (OCP) fault in the regulator. To prevent this, a 10ms delay is added after asserting HWRST. This allows the reset operation to complete while power rails remain active and in high-power mode. Currently there is no way for Host to query whether the reset is completed or not and hence this the delay is based on experiments with Qualcomm UFS controllers across multiple UFS vendors.
CVE-2025-68239: In the Linux kernel, the following vulnerability has been resolved: binfmt_misc: restore write access before closing files opened by open_exec() bm_register_write() opens an executable file using open_exec(), which internally calls do_open_execat() and denies write access on the file to avoid modification while it is being executed. However, when an error occurs, bm_register_write() closes the file using filp_close() directly. This does not restore the write permission, which may cause subsequent write operations on the same file to fail. Fix this by calling exe_file_allow_write_access() before filp_close() to restore the write permission properly.
CVE-2025-68251: In the Linux kernel, the following vulnerability has been resolved: erofs: avoid infinite loops due to corrupted subpage compact indexes Robert reported an infinite loop observed by two crafted images. The root cause is that `clusterofs` can be larger than `lclustersize` for !NONHEAD `lclusters` in corrupted subpage compact indexes, e.g.: blocksize = lclustersize = 512 lcn = 6 clusterofs = 515 Move the corresponding check for full compress indexes to `z_erofs_load_lcluster_from_disk()` to also cover subpage compact compress indexes. It also fixes the position of `m->type >= Z_EROFS_LCLUSTER_TYPE_MAX` check, since it should be placed right after `z_erofs_load_{compact,full}_lcluster()`.
CVE-2025-68304: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: lookup hci_conn on RX path on protocol side The hdev lock/lookup/unlock/use pattern in the packet RX path doesn't ensure hci_conn* is not concurrently modified/deleted. This locking appears to be leftover from before conn_hash started using RCU commit bf4c63252490b ("Bluetooth: convert conn hash to RCU") and not clear if it had purpose since then. Currently, there are code paths that delete hci_conn* from elsewhere than the ordered hdev->workqueue where the RX work runs in. E.g. commit 5af1f84ed13a ("Bluetooth: hci_sync: Fix UAF on hci_abort_conn_sync") introduced some of these, and there probably were a few others before it. It's better to do the locking so that even if these run concurrently no UAF is possible. Move the lookup of hci_conn and associated socket-specific conn to protocol recv handlers, and do them within a single critical section to cover hci_conn* usage and lookup. syzkaller has reported a crash that appears to be this issue: [Task hdev->workqueue] [Task 2] hci_disconnect_all_sync l2cap_recv_acldata(hcon) hci_conn_get(hcon) hci_abort_conn_sync(hcon) hci_dev_lock hci_dev_lock hci_conn_del(hcon) v-------------------------------- hci_dev_unlock hci_conn_put(hcon) conn = hcon->l2cap_data (UAF)
CVE-2025-68318: In the Linux kernel, the following vulnerability has been resolved: clk: thead: th1520-ap: set all AXI clocks to CLK_IS_CRITICAL The AXI crossbar of TH1520 has no proper timeout handling, which means gating AXI clocks can easily lead to bus timeout and thus system hang. Set all AXI clock gates to CLK_IS_CRITICAL. All these clock gates are ungated by default on system reset. In addition, convert all current CLK_IGNORE_UNUSED usage to CLK_IS_CRITICAL to prevent unwanted clock gating.
CVE-2025-68319: In the Linux kernel, the following vulnerability has been resolved: netconsole: Acquire su_mutex before navigating configs hierarchy There is a race between operations that iterate over the userdata cg_children list and concurrent add/remove of userdata items through configfs. The update_userdata() function iterates over the nt->userdata_group.cg_children list, and count_extradata_entries() also iterates over this same list to count nodes. Quoting from Documentation/filesystems/configfs.rst: > A subsystem can navigate the cg_children list and the ci_parent pointer > to see the tree created by the subsystem. This can race with configfs' > management of the hierarchy, so configfs uses the subsystem mutex to > protect modifications. Whenever a subsystem wants to navigate the > hierarchy, it must do so under the protection of the subsystem > mutex. Without proper locking, if a userdata item is added or removed concurrently while these functions are iterating, the list can be accessed in an inconsistent state. For example, the list_for_each() loop can reach a node that is being removed from the list by list_del_init() which sets the nodes' .next pointer to point to itself, so the loop will never end (or reach the WARN_ON_ONCE in update_userdata() ). Fix this by holding the configfs subsystem mutex (su_mutex) during all operations that iterate over cg_children. This includes: - userdatum_value_store() which calls update_userdata() to iterate over cg_children - All sysdata_*_enabled_store() functions which call count_extradata_entries() to iterate over cg_children The su_mutex must be acquired before dynamic_netconsole_mutex to avoid potential lock ordering issues, as configfs operations may already hold su_mutex when calling into our code.
CVE-2025-68334: In the Linux kernel, the following vulnerability has been resolved: platform/x86/amd/pmc: Add support for Van Gogh SoC The ROG Xbox Ally (non-X) SoC features a similar architecture to the Steam Deck. While the Steam Deck supports S3 (s2idle causes a crash), this support was dropped by the Xbox Ally which only S0ix suspend. Since the handler is missing here, this causes the device to not suspend and the AMD GPU driver to crash while trying to resume afterwards due to a power hang.
CVE-2025-68353: In the Linux kernel, the following vulnerability has been resolved: net: vxlan: prevent NULL deref in vxlan_xmit_one Neither sock4 nor sock6 pointers are guaranteed to be non-NULL in vxlan_xmit_one, e.g. if the iface is brought down. This can lead to the following NULL dereference: BUG: kernel NULL pointer dereference, address: 0000000000000010 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:vxlan_xmit_one+0xbb3/0x1580 Call Trace: vxlan_xmit+0x429/0x610 dev_hard_start_xmit+0x55/0xa0 __dev_queue_xmit+0x6d0/0x7f0 ip_finish_output2+0x24b/0x590 ip_output+0x63/0x110 Mentioned commits changed the code path in vxlan_xmit_one and as a side effect the sock4/6 pointer validity checks in vxlan(6)_get_route were lost. Fix this by adding back checks. Since both commits being fixed were released in the same version (v6.7) and are strongly related, bundle the fixes in a single commit.
CVE-2025-68359: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double free of qgroup record after failure to add delayed ref head In the previous code it was possible to incur into a double kfree() scenario when calling add_delayed_ref_head(). This could happen if the record was reported to already exist in the btrfs_qgroup_trace_extent_nolock() call, but then there was an error later on add_delayed_ref_head(). In this case, since add_delayed_ref_head() returned an error, the caller went to free the record. Since add_delayed_ref_head() couldn't set this kfree'd pointer to NULL, then kfree() would have acted on a non-NULL 'record' object which was pointing to memory already freed by the callee. The problem comes from the fact that the responsibility to kfree the object is on both the caller and the callee at the same time. Hence, the fix for this is to shift the ownership of the 'qrecord' object out of the add_delayed_ref_head(). That is, we will never attempt to kfree() the given object inside of this function, and will expect the caller to act on the 'qrecord' object on its own. The only exception where the 'qrecord' object cannot be kfree'd is if it was inserted into the tracing logic, for which we already have the 'qrecord_inserted_ret' boolean to account for this. Hence, the caller has to kfree the object only if add_delayed_ref_head() reports not to have inserted it on the tracing logic. As a side-effect of the above, we must guarantee that 'qrecord_inserted_ret' is properly initialized at the start of the function, not at the end, and then set when an actual insert happens. This way we avoid 'qrecord_inserted_ret' having an invalid value on an early exit. The documentation from the add_delayed_ref_head() has also been updated to reflect on the exact ownership of the 'qrecord' object.
CVE-2025-68360: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: wed: use proper wed reference in mt76 wed driver callabacks MT7996 driver can use both wed and wed_hif2 devices to offload traffic from/to the wireless NIC. In the current codebase we assume to always use the primary wed device in wed callbacks resulting in the following crash if the hw runs wed_hif2 (e.g. 6GHz link). [ 297.455876] Unable to handle kernel read from unreadable memory at virtual address 000000000000080a [ 297.464928] Mem abort info: [ 297.467722] ESR = 0x0000000096000005 [ 297.471461] EC = 0x25: DABT (current EL), IL = 32 bits [ 297.476766] SET = 0, FnV = 0 [ 297.479809] EA = 0, S1PTW = 0 [ 297.482940] FSC = 0x05: level 1 translation fault [ 297.487809] Data abort info: [ 297.490679] ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 [ 297.496156] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 297.501196] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 297.506500] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000107480000 [ 297.512927] [000000000000080a] pgd=08000001097fb003, p4d=08000001097fb003, pud=08000001097fb003, pmd=0000000000000000 [ 297.523532] Internal error: Oops: 0000000096000005 [#1] SMP [ 297.715393] CPU: 2 UID: 0 PID: 45 Comm: kworker/u16:2 Tainted: G O 6.12.50 #0 [ 297.723908] Tainted: [O]=OOT_MODULE [ 297.727384] Hardware name: Banana Pi BPI-R4 (2x SFP+) (DT) [ 297.732857] Workqueue: nf_ft_offload_del nf_flow_rule_route_ipv6 [nf_flow_table] [ 297.740254] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 297.747205] pc : mt76_wed_offload_disable+0x64/0xa0 [mt76] [ 297.752688] lr : mtk_wed_flow_remove+0x58/0x80 [ 297.757126] sp : ffffffc080fe3ae0 [ 297.760430] x29: ffffffc080fe3ae0 x28: ffffffc080fe3be0 x27: 00000000deadbef7 [ 297.767557] x26: ffffff80c5ebca00 x25: 0000000000000001 x24: ffffff80c85f4c00 [ 297.774683] x23: ffffff80c1875b78 x22: ffffffc080d42cd0 x21: ffffffc080660018 [ 297.781809] x20: ffffff80c6a076d0 x19: ffffff80c6a043c8 x18: 0000000000000000 [ 297.788935] x17: 0000000000000000 x16: 0000000000000001 x15: 0000000000000000 [ 297.796060] x14: 0000000000000019 x13: ffffff80c0ad8ec0 x12: 00000000fa83b2da [ 297.803185] x11: ffffff80c02700c0 x10: ffffff80c0ad8ec0 x9 : ffffff81fef96200 [ 297.810311] x8 : ffffff80c02700c0 x7 : ffffff80c02700d0 x6 : 0000000000000002 [ 297.817435] x5 : 0000000000000400 x4 : 0000000000000000 x3 : 0000000000000000 [ 297.824561] x2 : 0000000000000001 x1 : 0000000000000800 x0 : ffffff80c6a063c8 [ 297.831686] Call trace: [ 297.834123] mt76_wed_offload_disable+0x64/0xa0 [mt76] [ 297.839254] mtk_wed_flow_remove+0x58/0x80 [ 297.843342] mtk_flow_offload_cmd+0x434/0x574 [ 297.847689] mtk_wed_setup_tc_block_cb+0x30/0x40 [ 297.852295] nf_flow_offload_ipv6_hook+0x7f4/0x964 [nf_flow_table] [ 297.858466] nf_flow_rule_route_ipv6+0x438/0x4a4 [nf_flow_table] [ 297.864463] process_one_work+0x174/0x300 [ 297.868465] worker_thread+0x278/0x430 [ 297.872204] kthread+0xd8/0xdc [ 297.875251] ret_from_fork+0x10/0x20 [ 297.878820] Code: 928b5ae0 8b000273 91400a60 f943fa61 (79401421) [ 297.884901] ---[ end trace 0000000000000000 ]--- Fix the issue detecting the proper wed reference to use running wed callabacks.
CVE-2025-68368: In the Linux kernel, the following vulnerability has been resolved: md: init bioset in mddev_init IO operations may be needed before md_run(), such as updating metadata after writing sysfs. Without bioset, this triggers a NULL pointer dereference as below: BUG: kernel NULL pointer dereference, address: 0000000000000020 Call Trace: md_update_sb+0x658/0xe00 new_level_store+0xc5/0x120 md_attr_store+0xc9/0x1e0 sysfs_kf_write+0x6f/0xa0 kernfs_fop_write_iter+0x141/0x2a0 vfs_write+0x1fc/0x5a0 ksys_write+0x79/0x180 __x64_sys_write+0x1d/0x30 x64_sys_call+0x2818/0x2880 do_syscall_64+0xa9/0x580 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Reproducer ``` mdadm -CR /dev/md0 -l1 -n2 /dev/sd[cd] echo inactive > /sys/block/md0/md/array_state echo 10 > /sys/block/md0/md/new_level ``` mddev_init() can only be called once per mddev, no need to test if bioset has been initialized anymore.
CVE-2025-68376: In the Linux kernel, the following vulnerability has been resolved: coresight: ETR: Fix ETR buffer use-after-free issue When ETR is enabled as CS_MODE_SYSFS, if the buffer size is changed and enabled again, currently sysfs_buf will point to the newly allocated memory(buf_new) and free the old memory(buf_old). But the etr_buf that is being used by the ETR remains pointed to buf_old, not updated to buf_new. In this case, it will result in a memory use-after-free issue. Fix this by checking ETR's mode before updating and releasing buf_old, if the mode is CS_MODE_SYSFS, then skip updating and releasing it.
CVE-2025-68729: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: Fix MSDU buffer types handling in RX error path Currently, packets received on the REO exception ring from unassociated peers are of MSDU buffer type, while the driver expects link descriptor type packets. These packets are not parsed further due to a return check on packet type in ath12k_hal_desc_reo_parse_err(), but the associated skb is not freed. This may lead to kernel crashes and buffer leaks. Hence to fix, update the RX error handler to explicitly drop MSDU buffer type packets received on the REO exception ring. This prevents further processing of invalid packets and ensures stability in the RX error handling path. Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
CVE-2025-68730: In the Linux kernel, the following vulnerability has been resolved: accel/ivpu: Fix page fault in ivpu_bo_unbind_all_bos_from_context() Don't add BO to the vdev->bo_list in ivpu_gem_create_object(). When failure happens inside drm_gem_shmem_create(), the BO is not fully created and ivpu_gem_bo_free() callback will not be called causing a deleted BO to be left on the list.
CVE-2025-68735: In the Linux kernel, the following vulnerability has been resolved: drm/panthor: Prevent potential UAF in group creation This commit prevents the possibility of a use after free issue in the GROUP_CREATE ioctl function, which arose as pointer to the group is accessed in that ioctl function after storing it in the Xarray. A malicious userspace can second guess the handle of a group and try to call GROUP_DESTROY ioctl from another thread around the same time as GROUP_CREATE ioctl. To prevent the use after free exploit, this commit uses a mark on an entry of group pool Xarray which is added just before returning from the GROUP_CREATE ioctl function. The mark is checked for all ioctls that specify the group handle and so userspace won't be abe to delete a group that isn't marked yet. v2: Add R-bs and fixes tags
CVE-2025-68736: In the Linux kernel, the following vulnerability has been resolved: landlock: Fix handling of disconnected directories Disconnected files or directories can appear when they are visible and opened from a bind mount, but have been renamed or moved from the source of the bind mount in a way that makes them inaccessible from the mount point (i.e. out of scope). Previously, access rights tied to files or directories opened through a disconnected directory were collected by walking the related hierarchy down to the root of the filesystem, without taking into account the mount point because it couldn't be found. This could lead to inconsistent access results, potential access right widening, and hard-to-debug renames, especially since such paths cannot be printed. For a sandboxed task to create a disconnected directory, it needs to have write access (i.e. FS_MAKE_REG, FS_REMOVE_FILE, and FS_REFER) to the underlying source of the bind mount, and read access to the related mount point. Because a sandboxed task cannot acquire more access rights than those defined by its Landlock domain, this could lead to inconsistent access rights due to missing permissions that should be inherited from the mount point hierarchy, while inheriting permissions from the filesystem hierarchy hidden by this mount point instead. Landlock now handles files and directories opened from disconnected directories by taking into account the filesystem hierarchy when the mount point is not found in the hierarchy walk, and also always taking into account the mount point from which these disconnected directories were opened. This ensures that a rename is not allowed if it would widen access rights [1]. The rationale is that, even if disconnected hierarchies might not be visible or accessible to a sandboxed task, relying on the collected access rights from them improves the guarantee that access rights will not be widened during a rename because of the access right comparison between the source and the destination (see LANDLOCK_ACCESS_FS_REFER). It may look like this would grant more access on disconnected files and directories, but the security policies are always enforced for all the evaluated hierarchies. This new behavior should be less surprising to users and safer from an access control perspective. Remove a wrong WARN_ON_ONCE() canary in collect_domain_accesses() and fix the related comment. Because opened files have their access rights stored in the related file security properties, there is no impact for disconnected or unlinked files.
CVE-2025-68745: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Clear cmds after chip reset Commit aefed3e5548f ("scsi: qla2xxx: target: Fix offline port handling and host reset handling") caused two problems: 1. Commands sent to FW, after chip reset got stuck and never freed as FW is not going to respond to them anymore. 2. BUG_ON(cmd->sg_mapped) in qlt_free_cmd(). Commit 26f9ce53817a ("scsi: qla2xxx: Fix missed DMA unmap for aborted commands") attempted to fix this, but introduced another bug under different circumstances when two different CPUs were racing to call qlt_unmap_sg() at the same time: BUG_ON(!valid_dma_direction(dir)) in dma_unmap_sg_attrs(). So revert "scsi: qla2xxx: Fix missed DMA unmap for aborted commands" and partially revert "scsi: qla2xxx: target: Fix offline port handling and host reset handling" at __qla2x00_abort_all_cmds.
CVE-2025-68751: In the Linux kernel, the following vulnerability has been resolved: s390/fpu: Fix false-positive kmsan report in fpu_vstl() A false-positive kmsan report is detected when running ping command. An inline assembly instruction 'vstl' can write varied amount of bytes depending on value of 'index' argument. If 'index' > 0, 'vstl' writes at least 2 bytes. clang generates kmsan write helper call depending on inline assembly constraints. Constraints are evaluated compile-time, but value of 'index' argument is known only at runtime. clang currently generates call to __msan_instrument_asm_store with 1 byte as size. Manually call kmsan function to indicate correct amount of bytes written and fix false-positive report. This change fixes following kmsan reports: [ 36.563119] ===================================================== [ 36.563594] BUG: KMSAN: uninit-value in virtqueue_add+0x35c6/0x7c70 [ 36.563852] virtqueue_add+0x35c6/0x7c70 [ 36.564016] virtqueue_add_outbuf+0xa0/0xb0 [ 36.564266] start_xmit+0x288c/0x4a20 [ 36.564460] dev_hard_start_xmit+0x302/0x900 [ 36.564649] sch_direct_xmit+0x340/0xea0 [ 36.564894] __dev_queue_xmit+0x2e94/0x59b0 [ 36.565058] neigh_resolve_output+0x936/0xb40 [ 36.565278] __neigh_update+0x2f66/0x3a60 [ 36.565499] neigh_update+0x52/0x60 [ 36.565683] arp_process+0x1588/0x2de0 [ 36.565916] NF_HOOK+0x1da/0x240 [ 36.566087] arp_rcv+0x3e4/0x6e0 [ 36.566306] __netif_receive_skb_list_core+0x1374/0x15a0 [ 36.566527] netif_receive_skb_list_internal+0x1116/0x17d0 [ 36.566710] napi_complete_done+0x376/0x740 [ 36.566918] virtnet_poll+0x1bae/0x2910 [ 36.567130] __napi_poll+0xf4/0x830 [ 36.567294] net_rx_action+0x97c/0x1ed0 [ 36.567556] handle_softirqs+0x306/0xe10 [ 36.567731] irq_exit_rcu+0x14c/0x2e0 [ 36.567910] do_io_irq+0xd4/0x120 [ 36.568139] io_int_handler+0xc2/0xe8 [ 36.568299] arch_cpu_idle+0xb0/0xc0 [ 36.568540] arch_cpu_idle+0x76/0xc0 [ 36.568726] default_idle_call+0x40/0x70 [ 36.568953] do_idle+0x1d6/0x390 [ 36.569486] cpu_startup_entry+0x9a/0xb0 [ 36.569745] rest_init+0x1ea/0x290 [ 36.570029] start_kernel+0x95e/0xb90 [ 36.570348] startup_continue+0x2e/0x40 [ 36.570703] [ 36.570798] Uninit was created at: [ 36.571002] kmem_cache_alloc_node_noprof+0x9e8/0x10e0 [ 36.571261] kmalloc_reserve+0x12a/0x470 [ 36.571553] __alloc_skb+0x310/0x860 [ 36.571844] __ip_append_data+0x483e/0x6a30 [ 36.572170] ip_append_data+0x11c/0x1e0 [ 36.572477] raw_sendmsg+0x1c8c/0x2180 [ 36.572818] inet_sendmsg+0xe6/0x190 [ 36.573142] __sys_sendto+0x55e/0x8e0 [ 36.573392] __s390x_sys_socketcall+0x19ae/0x2ba0 [ 36.573571] __do_syscall+0x12e/0x240 [ 36.573823] system_call+0x6e/0x90 [ 36.573976] [ 36.574017] Byte 35 of 98 is uninitialized [ 36.574082] Memory access of size 98 starts at 0000000007aa0012 [ 36.574218] [ 36.574325] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Tainted: G B N 6.17.0-dirty #16 NONE [ 36.574541] Tainted: [B]=BAD_PAGE, [N]=TEST [ 36.574617] Hardware name: IBM 3931 A01 703 (KVM/Linux) [ 36.574755] ===================================================== [ 63.532541] ===================================================== [ 63.533639] BUG: KMSAN: uninit-value in virtqueue_add+0x35c6/0x7c70 [ 63.533989] virtqueue_add+0x35c6/0x7c70 [ 63.534940] virtqueue_add_outbuf+0xa0/0xb0 [ 63.535861] start_xmit+0x288c/0x4a20 [ 63.536708] dev_hard_start_xmit+0x302/0x900 [ 63.537020] sch_direct_xmit+0x340/0xea0 [ 63.537997] __dev_queue_xmit+0x2e94/0x59b0 [ 63.538819] neigh_resolve_output+0x936/0xb40 [ 63.539793] ip_finish_output2+0x1ee2/0x2200 [ 63.540784] __ip_finish_output+0x272/0x7a0 [ 63.541765] ip_finish_output+0x4e/0x5e0 [ 63.542791] ip_output+0x166/0x410 [ 63.543771] ip_push_pending_frames+0x1a2/0x470 [ 63.544753] raw_sendmsg+0x1f06/0x2180 [ 63.545033] inet_sendmsg+0xe6/0x190 [ 63.546006] __sys_sendto+0x55e/0x8e0 ---truncated---
CVE-2025-68755: In the Linux kernel, the following vulnerability has been resolved: staging: most: remove broken i2c driver The MOST I2C driver has been completely broken for five years without anyone noticing so remove the driver from staging. Specifically, commit 723de0f9171e ("staging: most: remove device from interface structure") started requiring drivers to set the interface device pointer before registration, but the I2C driver was never updated which results in a NULL pointer dereference if anyone ever tries to probe it.
CVE-2025-68768: In the Linux kernel, the following vulnerability has been resolved: inet: frags: flush pending skbs in fqdir_pre_exit() We have been seeing occasional deadlocks on pernet_ops_rwsem since September in NIPA. The stuck task was usually modprobe (often loading a driver like ipvlan), trying to take the lock as a Writer. lockdep does not track readers for rwsems so the read wasn't obvious from the reports. On closer inspection the Reader holding the lock was conntrack looping forever in nf_conntrack_cleanup_net_list(). Based on past experience with occasional NIPA crashes I looked thru the tests which run before the crash and noticed that the crash follows ip_defrag.sh. An immediate red flag. Scouring thru (de)fragmentation queues reveals skbs sitting around, holding conntrack references. The problem is that since conntrack depends on nf_defrag_ipv6, nf_defrag_ipv6 will load first. Since nf_defrag_ipv6 loads first its netns exit hooks run _after_ conntrack's netns exit hook. Flush all fragment queue SKBs during fqdir_pre_exit() to release conntrack references before conntrack cleanup runs. Also flush the queues in timer expiry handlers when they discover fqdir->dead is set, in case packet sneaks in while we're running the pre_exit flush. The commit under Fixes is not exactly the culprit, but I think previously the timer firing would eventually unblock the spinning conntrack.
CVE-2025-71074: In the Linux kernel, the following vulnerability has been resolved: functionfs: fix the open/removal races ffs_epfile_open() can race with removal, ending up with file->private_data pointing to freed object. There is a total count of opened files on functionfs (both ep0 and dynamic ones) and when it hits zero, dynamic files get removed. Unfortunately, that removal can happen while another thread is in ffs_epfile_open(), but has not incremented the count yet. In that case open will succeed, leaving us with UAF on any subsequent read() or write(). The root cause is that ffs->opened is misused; atomic_dec_and_test() vs. atomic_add_return() is not a good idea, when object remains visible all along. To untangle that * serialize openers on ffs->mutex (both for ep0 and for dynamic files) * have dynamic ones use atomic_inc_not_zero() and fail if we had zero ->opened; in that case the file we are opening is doomed. * have the inodes of dynamic files marked on removal (from the callback of simple_recursive_removal()) - clear ->i_private there. * have open of dynamic ones verify they hadn't been already removed, along with checking that state is FFS_ACTIVE.
CVE-2025-71117: In the Linux kernel, the following vulnerability has been resolved: block: Remove queue freezing from several sysfs store callbacks Freezing the request queue from inside sysfs store callbacks may cause a deadlock in combination with the dm-multipath driver and the queue_if_no_path option. Additionally, freezing the request queue slows down system boot on systems where sysfs attributes are set synchronously. Fix this by removing the blk_mq_freeze_queue() / blk_mq_unfreeze_queue() calls from the store callbacks that do not strictly need these callbacks. Add the __data_racy annotation to request_queue.rq_timeout to suppress KCSAN data race reports about the rq_timeout reads. This patch may cause a small delay in applying the new settings. For all the attributes affected by this patch, I/O will complete correctly whether the old or the new value of the attribute is used. This patch affects the following sysfs attributes: * io_poll_delay * io_timeout * nomerges * read_ahead_kb * rq_affinity Here is an example of a deadlock triggered by running test srp/002 if this patch is not applied: task:multipathd Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 schedule_preempt_disabled+0x1c/0x30 __mutex_lock+0xb89/0x1650 mutex_lock_nested+0x1f/0x30 dm_table_set_restrictions+0x823/0xdf0 __bind+0x166/0x590 dm_swap_table+0x2a7/0x490 do_resume+0x1b1/0x610 dev_suspend+0x55/0x1a0 ctl_ioctl+0x3a5/0x7e0 dm_ctl_ioctl+0x12/0x20 __x64_sys_ioctl+0x127/0x1a0 x64_sys_call+0xe2b/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK> task:(udev-worker) Call Trace: <TASK> __schedule+0x8c1/0x1bf0 schedule+0xdd/0x270 blk_mq_freeze_queue_wait+0xf2/0x140 blk_mq_freeze_queue_nomemsave+0x23/0x30 queue_ra_store+0x14e/0x290 queue_attr_store+0x23e/0x2c0 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3b2/0x630 vfs_write+0x4fd/0x1390 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x276/0x17d0 do_syscall_64+0x96/0x3a0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 </TASK>
CVE-2025-71141: In the Linux kernel, the following vulnerability has been resolved: drm/tilcdc: Fix removal actions in case of failed probe The drm_kms_helper_poll_fini() and drm_atomic_helper_shutdown() helpers should only be called when the device has been successfully registered. Currently, these functions are called unconditionally in tilcdc_fini(), which causes warnings during probe deferral scenarios. [ 7.972317] WARNING: CPU: 0 PID: 23 at drivers/gpu/drm/drm_atomic_state_helper.c:175 drm_atomic_helper_crtc_duplicate_state+0x60/0x68 ... [ 8.005820] drm_atomic_helper_crtc_duplicate_state from drm_atomic_get_crtc_state+0x68/0x108 [ 8.005858] drm_atomic_get_crtc_state from drm_atomic_helper_disable_all+0x90/0x1c8 [ 8.005885] drm_atomic_helper_disable_all from drm_atomic_helper_shutdown+0x90/0x144 [ 8.005911] drm_atomic_helper_shutdown from tilcdc_fini+0x68/0xf8 [tilcdc] [ 8.005957] tilcdc_fini [tilcdc] from tilcdc_pdev_probe+0xb0/0x6d4 [tilcdc] Fix this by rewriting the failed probe cleanup path using the standard goto error handling pattern, which ensures that cleanup functions are only called on successfully initialized resources. Additionally, remove the now-unnecessary is_registered flag.
CVE-2025-71152: In the Linux kernel, the following vulnerability has been resolved: net: dsa: properly keep track of conduit reference Problem description ------------------- DSA has a mumbo-jumbo of reference handling of the conduit net device and its kobject which, sadly, is just wrong and doesn't make sense. There are two distinct problems. 1. The OF path, which uses of_find_net_device_by_node(), never releases the elevated refcount on the conduit's kobject. Nominally, the OF and non-OF paths should result in objects having identical reference counts taken, and it is already suspicious that dsa_dev_to_net_device() has a put_device() call which is missing in dsa_port_parse_of(), but we can actually even verify that an issue exists. With CONFIG_DEBUG_KOBJECT_RELEASE=y, if we run this command "before" and "after" applying this patch: (unbind the conduit driver for net device eno2) echo 0000:00:00.2 > /sys/bus/pci/drivers/fsl_enetc/unbind we see these lines in the output diff which appear only with the patch applied: kobject: 'eno2' (ffff002009a3a6b8): kobject_release, parent 0000000000000000 (delayed 1000) kobject: '109' (ffff0020099d59a0): kobject_release, parent 0000000000000000 (delayed 1000) 2. After we find the conduit interface one way (OF) or another (non-OF), it can get unregistered at any time, and DSA remains with a long-lived, but in this case stale, cpu_dp->conduit pointer. Holding the net device's underlying kobject isn't actually of much help, it just prevents it from being freed (but we never need that kobject directly). What helps us to prevent the net device from being unregistered is the parallel netdev reference mechanism (dev_hold() and dev_put()). Actually we actually use that netdev tracker mechanism implicitly on user ports since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), via netdev_upper_dev_link(). But time still passes at DSA switch probe time between the initial of_find_net_device_by_node() code and the user port creation time, time during which the conduit could unregister itself and DSA wouldn't know about it. So we have to run of_find_net_device_by_node() under rtnl_lock() to prevent that from happening, and release the lock only with the netdev tracker having acquired the reference. Do we need to keep the reference until dsa_unregister_switch() / dsa_switch_shutdown()? 1: Maybe yes. A switch device will still be registered even if all user ports failed to probe, see commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal"), and the cpu_dp->conduit pointers remain valid. I haven't audited all call paths to see whether they will actually use the conduit in lack of any user port, but if they do, it seems safer to not rely on user ports for that reference. 2. Definitely yes. We support changing the conduit which a user port is associated to, and we can get into a situation where we've moved all user ports away from a conduit, thus no longer hold any reference to it via the net device tracker. But we shouldn't let it go nonetheless - see the next change in relation to dsa_tree_find_first_conduit() and LAG conduits which disappear. We have to be prepared to return to the physical conduit, so the CPU port must explicitly keep another reference to it. This is also to say: the user ports and their CPU ports may not always keep a reference to the same conduit net device, and both are needed. As for the conduit's kobject for the /sys/class/net/ entry, we don't care about it, we can release it as soon as we hold the net device object itself. History and blame attribution ----------------------------- The code has been refactored so many times, it is very difficult to follow and properly attribute a blame, but I'll try to make a short history which I hope to be correct. We have two distinct probing paths: - one for OF, introduced in 2016 i ---truncated---
CVE-2025-71161: In the Linux kernel, the following vulnerability has been resolved: dm-verity: disable recursive forward error correction There are two problems with the recursive correction: 1. It may cause denial-of-service. In fec_read_bufs, there is a loop that has 253 iterations. For each iteration, we may call verity_hash_for_block recursively. There is a limit of 4 nested recursions - that means that there may be at most 253^4 (4 billion) iterations. Red Hat QE team actually created an image that pushes dm-verity to this limit - and this image just makes the udev-worker process get stuck in the 'D' state. 2. It doesn't work. In fec_read_bufs we store data into the variable "fio->bufs", but fio bufs is shared between recursive invocations, if "verity_hash_for_block" invoked correction recursively, it would overwrite partially filled fio->bufs.
CVE-2025-71202: In the Linux kernel, the following vulnerability has been resolved: iommu/sva: invalidate stale IOTLB entries for kernel address space Introduce a new IOMMU interface to flush IOTLB paging cache entries for the CPU kernel address space. This interface is invoked from the x86 architecture code that manages combined user and kernel page tables, specifically before any kernel page table page is freed and reused. This addresses the main issue with vfree() which is a common occurrence and can be triggered by unprivileged users. While this resolves the primary problem, it doesn't address some extremely rare case related to memory unplug of memory that was present as reserved memory at boot, which cannot be triggered by unprivileged users. The discussion can be found at the link below. Enable SVA on x86 architecture since the IOMMU can now receive notification to flush the paging cache before freeing the CPU kernel page table pages.
CVE-2025-71221: In the Linux kernel, the following vulnerability has been resolved: dmaengine: mmp_pdma: Fix race condition in mmp_pdma_residue() Add proper locking in mmp_pdma_residue() to prevent use-after-free when accessing descriptor list and descriptor contents. The race occurs when multiple threads call tx_status() while the tasklet on another CPU is freeing completed descriptors: CPU 0 CPU 1 ----- ----- mmp_pdma_tx_status() mmp_pdma_residue() -> NO LOCK held list_for_each_entry(sw, ..) DMA interrupt dma_do_tasklet() -> spin_lock(&desc_lock) list_move(sw->node, ...) spin_unlock(&desc_lock) | dma_pool_free(sw) <- FREED! -> access sw->desc <- UAF! This issue can be reproduced when running dmatest on the same channel with multiple threads (threads_per_chan > 1). Fix by protecting the chain_running list iteration and descriptor access with the chan->desc_lock spinlock.
CVE-2025-71227: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: don't WARN for connections on invalid channels It's not clear (to me) how exactly syzbot managed to hit this, but it seems conceivable that e.g. regulatory changed and has disabled a channel between scanning (channel is checked to be usable by cfg80211_get_ies_channel_number) and connecting on the channel later. With one scenario that isn't covered elsewhere described above, the warning isn't good, replace it with a (more informative) error message.
CVE-2025-71239: In the Linux kernel, the following vulnerability has been resolved: audit: add fchmodat2() to change attributes class fchmodat2(), introduced in version 6.6 is currently not in the change attribute class of audit. Calling fchmodat2() to change a file attribute in the same fashion than chmod() or fchmodat() will bypass audit rules such as: -w /tmp/test -p rwa -k test_rwa The current patch adds fchmodat2() to the change attributes class.
CVE-2025-71265: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop in attr_load_runs_range on inconsistent metadata We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an attribute header indicates an empty run list, while directory entries reference it as containing actual data. In NTFS, setting evcn=-1 with svcn=0 is a valid way to represent an empty run list, and run_unpack() correctly handles this by checking if evcn + 1 equals svcn and returning early without parsing any run data. However, this creates a problem when there is metadata inconsistency, where the attribute header claims to be empty (evcn=-1) but the caller expects to read actual data. When run_unpack() immediately returns success upon seeing this condition, it leaves the runs_tree uninitialized with run->runs as a NULL. The calling function attr_load_runs_range() assumes that a successful return means that the runs were loaded and sets clen to 0, expecting the next run_lookup_entry() call to succeed. Because runs_tree remains uninitialized, run_lookup_entry() continues to fail, and the loop increments vcn by zero (vcn += 0), leading to an infinite loop. This patch adds a retry counter to detect when run_lookup_entry() fails consecutively after attr_load_runs_vcn(). If the run is still not found on the second attempt, it indicates corrupted metadata and returns -EINVAL, preventing the Denial-of-Service (DoS) vulnerability.
CVE-2025-71266: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: check return value of indx_find to avoid infinite loop We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed dentry in the ntfs3 filesystem can cause the kernel to hang during the lookup operations. By setting the HAS_SUB_NODE flag in an INDEX_ENTRY within a directory's INDEX_ALLOCATION block and manipulating the VCN pointer, an attacker can cause the indx_find() function to repeatedly read the same block, allocating 4 KB of memory each time. The kernel lacks VCN loop detection and depth limits, causing memory exhaustion and an OOM crash. This patch adds a return value check for fnd_push() to prevent a memory exhaustion vulnerability caused by infinite loops. When the index exceeds the size of the fnd->nodes array, fnd_push() returns -EINVAL. The indx_find() function checks this return value and stops processing, preventing further memory allocation.
CVE-2025-71267: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop triggered by zero-sized ATTR_LIST We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an ATTR_LIST attribute indicates a zero data size while the driver allocates memory for it. When ntfs_load_attr_list() processes a resident ATTR_LIST with data_size set to zero, it still allocates memory because of al_aligned(0). This creates an inconsistent state where ni->attr_list.size is zero, but ni->attr_list.le is non-null. This causes ni_enum_attr_ex to incorrectly assume that no attribute list exists and enumerates only the primary MFT record. When it finds ATTR_LIST, the code reloads it and restarts the enumeration, repeating indefinitely. The mount operation never completes, hanging the kernel thread. This patch adds validation to ensure that data_size is non-zero before memory allocation. When a zero-sized ATTR_LIST is detected, the function returns -EINVAL, preventing a DoS vulnerability.
CVE-2025-71269: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not free data reservation in fallback from inline due to -ENOSPC If we fail to create an inline extent due to -ENOSPC, we will attempt to go through the normal COW path, reserve an extent, create an ordered extent, etc. However we were always freeing the reserved qgroup data, which is wrong since we will use data. Fix this by freeing the reserved qgroup data in __cow_file_range_inline() only if we are not doing the fallback (ret is <= 0).
CVE-2026-22981: In the Linux kernel, the following vulnerability has been resolved: idpf: detach and close netdevs while handling a reset Protect the reset path from callbacks by setting the netdevs to detached state and close any netdevs in UP state until the reset handling has completed. During a reset, the driver will de-allocate resources for the vport, and there is no guarantee that those will recover, which is why the existing vport_ctrl_lock does not provide sufficient protection. idpf_detach_and_close() is called right before reset handling. If the reset handling succeeds, the netdevs state is recovered via call to idpf_attach_and_open(). If the reset handling fails the netdevs remain down. The detach/down calls are protected with RTNL lock to avoid racing with callbacks. On the recovery side the attach can be done without holding the RTNL lock as there are no callbacks expected at that point, due to detach/close always being done first in that flow. The previous logic restoring the netdevs state based on the IDPF_VPORT_UP_REQUESTED flag in the init task is not needed anymore, hence the removal of idpf_set_vport_state(). The IDPF_VPORT_UP_REQUESTED is still being used to restore the state of the netdevs following the reset, but has no use outside of the reset handling flow. idpf_init_hard_reset() is converted to void, since it was used as such and there is no error handling being done based on its return value. Before this change, invoking hard and soft resets simultaneously will cause the driver to lose the vport state: ip -br a <inf> UP echo 1 > /sys/class/net/ens801f0/device/reset& \ ethtool -L ens801f0 combined 8 ip -br a <inf> DOWN ip link set <inf> up ip -br a <inf> DOWN Also in case of a failure in the reset path, the netdev is left exposed to external callbacks, while vport resources are not initialized, leading to a crash on subsequent ifup/down: [408471.398966] idpf 0000:83:00.0: HW reset detected [408471.411744] idpf 0000:83:00.0: Device HW Reset initiated [408472.277901] idpf 0000:83:00.0: The driver was unable to contact the device's firmware. Check that the FW is running. Driver state= 0x2 [408508.125551] BUG: kernel NULL pointer dereference, address: 0000000000000078 [408508.126112] #PF: supervisor read access in kernel mode [408508.126687] #PF: error_code(0x0000) - not-present page [408508.127256] PGD 2aae2f067 P4D 0 [408508.127824] Oops: Oops: 0000 [#1] SMP NOPTI ... [408508.130871] RIP: 0010:idpf_stop+0x39/0x70 [idpf] ... [408508.139193] Call Trace: [408508.139637] <TASK> [408508.140077] __dev_close_many+0xbb/0x260 [408508.140533] __dev_change_flags+0x1cf/0x280 [408508.140987] netif_change_flags+0x26/0x70 [408508.141434] dev_change_flags+0x3d/0xb0 [408508.141878] devinet_ioctl+0x460/0x890 [408508.142321] inet_ioctl+0x18e/0x1d0 [408508.142762] ? _copy_to_user+0x22/0x70 [408508.143207] sock_do_ioctl+0x3d/0xe0 [408508.143652] sock_ioctl+0x10e/0x330 [408508.144091] ? find_held_lock+0x2b/0x80 [408508.144537] __x64_sys_ioctl+0x96/0xe0 [408508.144979] do_syscall_64+0x79/0x3d0 [408508.145415] entry_SYSCALL_64_after_hwframe+0x76/0x7e [408508.145860] RIP: 0033:0x7f3e0bb4caff
CVE-2026-22985: In the Linux kernel, the following vulnerability has been resolved: idpf: Fix RSS LUT NULL pointer crash on early ethtool operations The RSS LUT is not initialized until the interface comes up, causing the following NULL pointer crash when ethtool operations like rxhash on/off are performed before the interface is brought up for the first time. Move RSS LUT initialization from ndo_open to vport creation to ensure LUT is always available. This enables RSS configuration via ethtool before bringing the interface up. Simplify LUT management by maintaining all changes in the driver's soft copy and programming zeros to the indirection table when rxhash is disabled. Defer HW programming until the interface comes up if it is down during rxhash and LUT configuration changes. Steps to reproduce: ** Load idpf driver; interfaces will be created modprobe idpf ** Before bringing the interfaces up, turn rxhash off ethtool -K eth2 rxhash off [89408.371875] BUG: kernel NULL pointer dereference, address: 0000000000000000 [89408.371908] #PF: supervisor read access in kernel mode [89408.371924] #PF: error_code(0x0000) - not-present page [89408.371940] PGD 0 P4D 0 [89408.371953] Oops: Oops: 0000 [#1] SMP NOPTI <snip> [89408.372052] RIP: 0010:memcpy_orig+0x16/0x130 [89408.372310] Call Trace: [89408.372317] <TASK> [89408.372326] ? idpf_set_features+0xfc/0x180 [idpf] [89408.372363] __netdev_update_features+0x295/0xde0 [89408.372384] ethnl_set_features+0x15e/0x460 [89408.372406] genl_family_rcv_msg_doit+0x11f/0x180 [89408.372429] genl_rcv_msg+0x1ad/0x2b0 [89408.372446] ? __pfx_ethnl_set_features+0x10/0x10 [89408.372465] ? __pfx_genl_rcv_msg+0x10/0x10 [89408.372482] netlink_rcv_skb+0x58/0x100 [89408.372502] genl_rcv+0x2c/0x50 [89408.372516] netlink_unicast+0x289/0x3e0 [89408.372533] netlink_sendmsg+0x215/0x440 [89408.372551] __sys_sendto+0x234/0x240 [89408.372571] __x64_sys_sendto+0x28/0x30 [89408.372585] x64_sys_call+0x1909/0x1da0 [89408.372604] do_syscall_64+0x7a/0xfa0 [89408.373140] ? clear_bhb_loop+0x60/0xb0 [89408.373647] entry_SYSCALL_64_after_hwframe+0x76/0x7e [89408.378887] </TASK> <snip>
CVE-2026-22986: In the Linux kernel, the following vulnerability has been resolved: gpiolib: fix race condition for gdev->srcu If two drivers were calling gpiochip_add_data_with_key(), one may be traversing the srcu-protected list in gpio_name_to_desc(), meanwhile other has just added its gdev in gpiodev_add_to_list_unlocked(). This creates a non-mutexed and non-protected timeframe, when one instance is dereferencing and using &gdev->srcu, before the other has initialized it, resulting in crash: [ 4.935481] Unable to handle kernel paging request at virtual address ffff800272bcc000 [ 4.943396] Mem abort info: [ 4.943400] ESR = 0x0000000096000005 [ 4.943403] EC = 0x25: DABT (current EL), IL = 32 bits [ 4.943407] SET = 0, FnV = 0 [ 4.943410] EA = 0, S1PTW = 0 [ 4.943413] FSC = 0x05: level 1 translation fault [ 4.943416] Data abort info: [ 4.943418] ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 [ 4.946220] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 4.955261] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 4.955268] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000038e6c000 [ 4.961449] [ffff800272bcc000] pgd=0000000000000000 [ 4.969203] , p4d=1000000039739003 [ 4.979730] , pud=0000000000000000 [ 4.980210] phandle (CPU): 0x0000005e, phandle (BE): 0x5e000000 for node "reset" [ 4.991736] Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP ... [ 5.121359] pc : __srcu_read_lock+0x44/0x98 [ 5.131091] lr : gpio_name_to_desc+0x60/0x1a0 [ 5.153671] sp : ffff8000833bb430 [ 5.298440] [ 5.298443] Call trace: [ 5.298445] __srcu_read_lock+0x44/0x98 [ 5.309484] gpio_name_to_desc+0x60/0x1a0 [ 5.320692] gpiochip_add_data_with_key+0x488/0xf00 5.946419] ---[ end trace 0000000000000000 ]--- Move initialization code for gdev fields before it is added to gpio_devices, with adjacent initialization code. Adjust goto statements to reflect modified order of operations [Bartosz: fixed a build issue, removed stray newline]
CVE-2026-22993: In the Linux kernel, the following vulnerability has been resolved: idpf: Fix RSS LUT NULL ptr issue after soft reset During soft reset, the RSS LUT is freed and not restored unless the interface is up. If an ethtool command that accesses the rss lut is attempted immediately after reset, it will result in NULL ptr dereference. Also, there is no need to reset the rss lut if the soft reset does not involve queue count change. After soft reset, set the RSS LUT to default values based on the updated queue count only if the reset was a result of a queue count change and the LUT was not configured by the user. In all other cases, don't touch the LUT. Steps to reproduce: ** Bring the interface down (if up) ifconfig eth1 down ** update the queue count (eg., 27->20) ethtool -L eth1 combined 20 ** display the RSS LUT ethtool -x eth1 [82375.558338] BUG: kernel NULL pointer dereference, address: 0000000000000000 [82375.558373] #PF: supervisor read access in kernel mode [82375.558391] #PF: error_code(0x0000) - not-present page [82375.558408] PGD 0 P4D 0 [82375.558421] Oops: Oops: 0000 [#1] SMP NOPTI <snip> [82375.558516] RIP: 0010:idpf_get_rxfh+0x108/0x150 [idpf] [82375.558786] Call Trace: [82375.558793] <TASK> [82375.558804] rss_prepare.isra.0+0x187/0x2a0 [82375.558827] rss_prepare_data+0x3a/0x50 [82375.558845] ethnl_default_doit+0x13d/0x3e0 [82375.558863] genl_family_rcv_msg_doit+0x11f/0x180 [82375.558886] genl_rcv_msg+0x1ad/0x2b0 [82375.558902] ? __pfx_ethnl_default_doit+0x10/0x10 [82375.558920] ? __pfx_genl_rcv_msg+0x10/0x10 [82375.558937] netlink_rcv_skb+0x58/0x100 [82375.558957] genl_rcv+0x2c/0x50 [82375.558971] netlink_unicast+0x289/0x3e0 [82375.558988] netlink_sendmsg+0x215/0x440 [82375.559005] __sys_sendto+0x234/0x240 [82375.559555] __x64_sys_sendto+0x28/0x30 [82375.560068] x64_sys_call+0x1909/0x1da0 [82375.560576] do_syscall_64+0x7a/0xfa0 [82375.561076] ? clear_bhb_loop+0x60/0xb0 [82375.561567] entry_SYSCALL_64_after_hwframe+0x76/0x7e <snip>
CVE-2026-23004: In the Linux kernel, the following vulnerability has been resolved: dst: fix races in rt6_uncached_list_del() and rt_del_uncached_list() syzbot was able to crash the kernel in rt6_uncached_list_flush_dev() in an interesting way [1] Crash happens in list_del_init()/INIT_LIST_HEAD() while writing list->prev, while the prior write on list->next went well. static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); // This went well WRITE_ONCE(list->prev, list); // Crash, @list has been freed. } Issue here is that rt6_uncached_list_del() did not attempt to lock ul->lock, as list_empty(&rt->dst.rt_uncached) returned true because the WRITE_ONCE(list->next, list) happened on the other CPU. We might use list_del_init_careful() and list_empty_careful(), or make sure rt6_uncached_list_del() always grabs the spinlock whenever rt->dst.rt_uncached_list has been set. A similar fix is neeed for IPv4. [1] BUG: KASAN: slab-use-after-free in INIT_LIST_HEAD include/linux/list.h:46 [inline] BUG: KASAN: slab-use-after-free in list_del_init include/linux/list.h:296 [inline] BUG: KASAN: slab-use-after-free in rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] BUG: KASAN: slab-use-after-free in rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 Write of size 8 at addr ffff8880294cfa78 by task kworker/u8:14/3450 CPU: 0 UID: 0 PID: 3450 Comm: kworker/u8:14 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025 Workqueue: netns cleanup_net Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 INIT_LIST_HEAD include/linux/list.h:46 [inline] list_del_init include/linux/list.h:296 [inline] rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 addrconf_ifdown+0x143/0x18a0 net/ipv6/addrconf.c:3853 addrconf_notify+0x1bc/0x1050 net/ipv6/addrconf.c:-1 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85 call_netdevice_notifiers_extack net/core/dev.c:2268 [inline] call_netdevice_notifiers net/core/dev.c:2282 [inline] netif_close_many+0x29c/0x410 net/core/dev.c:1785 unregister_netdevice_many_notify+0xb50/0x2330 net/core/dev.c:12353 ops_exit_rtnl_list net/core/net_namespace.c:187 [inline] ops_undo_list+0x3dc/0x990 net/core/net_namespace.c:248 cleanup_net+0x4de/0x7b0 net/core/net_namespace.c:696 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 </TASK> Allocated by task 803: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 unpoison_slab_object mm/kasan/common.c:340 [inline] __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366 kasan_slab_alloc include/linux/kasan.h:253 [inline] slab_post_alloc_hook mm/slub.c:4953 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x18d/0x6c0 mm/slub.c:5270 dst_alloc+0x105/0x170 net/core/dst.c:89 ip6_dst_alloc net/ipv6/route.c:342 [inline] icmp6_dst_alloc+0x75/0x460 net/ipv6/route.c:3333 mld_sendpack+0x683/0xe60 net/ipv6/mcast.c:1844 mld_send_cr net/ipv6/mcast.c:2154 [inline] mld_ifc_work+0x83e/0xd60 net/ipv6/mcast.c:2693 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entr ---truncated---
CVE-2026-23007: In the Linux kernel, the following vulnerability has been resolved: block: zero non-PI portion of auto integrity buffer The auto-generated integrity buffer for writes needs to be fully initialized before being passed to the underlying block device, otherwise the uninitialized memory can be read back by userspace or anyone with physical access to the storage device. If protection information is generated, that portion of the integrity buffer is already initialized. The integrity data is also zeroed if PI generation is disabled via sysfs or the PI tuple size is 0. However, this misses the case where PI is generated and the PI tuple size is nonzero, but the metadata size is larger than the PI tuple. In this case, the remainder ("opaque") of the metadata is left uninitialized. Generalize the BLK_INTEGRITY_CSUM_NONE check to cover any case when the metadata is larger than just the PI tuple.
CVE-2026-23017: In the Linux kernel, the following vulnerability has been resolved: idpf: fix error handling in the init_task on load If the init_task fails during a driver load, we end up without vports and netdevs, effectively failing the entire process. In that state a subsequent reset will result in a crash as the service task attempts to access uninitialized resources. Following trace is from an error in the init_task where the CREATE_VPORT (op 501) is rejected by the FW: [40922.763136] idpf 0000:83:00.0: Device HW Reset initiated [40924.449797] idpf 0000:83:00.0: Transaction failed (op 501) [40958.148190] idpf 0000:83:00.0: HW reset detected [40958.161202] BUG: kernel NULL pointer dereference, address: 00000000000000a8 ... [40958.168094] Workqueue: idpf-0000:83:00.0-vc_event idpf_vc_event_task [idpf] [40958.168865] RIP: 0010:idpf_vc_event_task+0x9b/0x350 [idpf] ... [40958.177932] Call Trace: [40958.178491] <TASK> [40958.179040] process_one_work+0x226/0x6d0 [40958.179609] worker_thread+0x19e/0x340 [40958.180158] ? __pfx_worker_thread+0x10/0x10 [40958.180702] kthread+0x10f/0x250 [40958.181238] ? __pfx_kthread+0x10/0x10 [40958.181774] ret_from_fork+0x251/0x2b0 [40958.182307] ? __pfx_kthread+0x10/0x10 [40958.182834] ret_from_fork_asm+0x1a/0x30 [40958.183370] </TASK> Fix the error handling in the init_task to make sure the service and mailbox tasks are disabled if the error happens during load. These are started in idpf_vc_core_init(), which spawns the init_task and has no way of knowing if it failed. If the error happens on reset, following successful driver load, the tasks can still run, as that will allow the netdevs to attempt recovery through another reset. Stop the PTP callbacks either way as those will be restarted by the call to idpf_vc_core_init() during a successful reset.
CVE-2026-23066: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix recvmsg() unconditional requeue If rxrpc_recvmsg() fails because MSG_DONTWAIT was specified but the call at the front of the recvmsg queue already has its mutex locked, it requeues the call - whether or not the call is already queued. The call may be on the queue because MSG_PEEK was also passed and so the call was not dequeued or because the I/O thread requeued it. The unconditional requeue may then corrupt the recvmsg queue, leading to things like UAFs or refcount underruns. Fix this by only requeuing the call if it isn't already on the queue - and moving it to the front if it is already queued. If we don't queue it, we have to put the ref we obtained by dequeuing it. Also, MSG_PEEK doesn't dequeue the call so shouldn't call rxrpc_notify_socket() for the call if we didn't use up all the data on the queue, so fix that also.
CVE-2026-23070: In the Linux kernel, the following vulnerability has been resolved: Octeontx2-af: Add proper checks for fwdata firmware populates MAC address, link modes (supported, advertised) and EEPROM data in shared firmware structure which kernel access via MAC block(CGX/RPM). Accessing fwdata, on boards booted with out MAC block leading to kernel panics. Internal error: Oops: 0000000096000005 [#1] SMP [ 10.460721] Modules linked in: [ 10.463779] CPU: 0 UID: 0 PID: 174 Comm: kworker/0:3 Not tainted 6.19.0-rc5-00154-g76ec646abdf7-dirty #3 PREEMPT [ 10.474045] Hardware name: Marvell OcteonTX CN98XX board (DT) [ 10.479793] Workqueue: events work_for_cpu_fn [ 10.484159] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 10.491124] pc : rvu_sdp_init+0x18/0x114 [ 10.495051] lr : rvu_probe+0xe58/0x1d18
CVE-2026-23102: In the Linux kernel, the following vulnerability has been resolved: arm64/fpsimd: signal: Fix restoration of SVE context When SME is supported, Restoring SVE signal context can go wrong in a few ways, including placing the task into an invalid state where the kernel may read from out-of-bounds memory (and may potentially take a fatal fault) and/or may kill the task with a SIGKILL. (1) Restoring a context with SVE_SIG_FLAG_SM set can place the task into an invalid state where SVCR.SM is set (and sve_state is non-NULL) but TIF_SME is clear, consequently resuting in out-of-bounds memory reads and/or killing the task with SIGKILL. This can only occur in unusual (but legitimate) cases where the SVE signal context has either been modified by userspace or was saved in the context of another task (e.g. as with CRIU), as otherwise the presence of an SVE signal context with SVE_SIG_FLAG_SM implies that TIF_SME is already set. While in this state, task_fpsimd_load() will NOT configure SMCR_ELx (leaving some arbitrary value configured in hardware) before restoring SVCR and attempting to restore the streaming mode SVE registers from memory via sve_load_state(). As the value of SMCR_ELx.LEN may be larger than the task's streaming SVE vector length, this may read memory outside of the task's allocated sve_state, reading unrelated data and/or triggering a fault. While this can result in secrets being loaded into streaming SVE registers, these values are never exposed. As TIF_SME is clear, fpsimd_bind_task_to_cpu() will configure CPACR_ELx.SMEN to trap EL0 accesses to streaming mode SVE registers, so these cannot be accessed directly at EL0. As fpsimd_save_user_state() verifies the live vector length before saving (S)SVE state to memory, no secret values can be saved back to memory (and hence cannot be observed via ptrace, signals, etc). When the live vector length doesn't match the expected vector length for the task, fpsimd_save_user_state() will send a fatal SIGKILL signal to the task. Hence the task may be killed after executing userspace for some period of time. (2) Restoring a context with SVE_SIG_FLAG_SM clear does not clear the task's SVCR.SM. If SVCR.SM was set prior to restoring the context, then the task will be left in streaming mode unexpectedly, and some register state will be combined inconsistently, though the task will be left in legitimate state from the kernel's PoV. This can only occur in unusual (but legitimate) cases where ptrace has been used to set SVCR.SM after entry to the sigreturn syscall, as syscall entry clears SVCR.SM. In these cases, the the provided SVE register data will be loaded into the task's sve_state using the non-streaming SVE vector length and the FPSIMD registers will be merged into this using the streaming SVE vector length. Fix (1) by setting TIF_SME when setting SVCR.SM. This also requires ensuring that the task's sme_state has been allocated, but as this could contain live ZA state, it should not be zeroed. Fix (2) by clearing SVCR.SM when restoring a SVE signal context with SVE_SIG_FLAG_SM clear. For consistency, I've pulled the manipulation of SVCR, TIF_SVE, TIF_SME, and fp_type earlier, immediately after the allocation of sve_state/sme_state, before the restore of the actual register state. This makes it easier to ensure that these are always modified consistently, even if a fault is taken while reading the register data from the signal context. I do not expect any software to depend on the exact state restored when a fault is taken while reading the context.
CVE-2026-23104: In the Linux kernel, the following vulnerability has been resolved: ice: fix devlink reload call trace Commit 4da71a77fc3b ("ice: read internal temperature sensor") introduced internal temperature sensor reading via HWMON. ice_hwmon_init() was added to ice_init_feature() and ice_hwmon_exit() was added to ice_remove(). As a result if devlink reload is used to reinit the device and then the driver is removed, a call trace can occur. BUG: unable to handle page fault for address: ffffffffc0fd4b5d Call Trace: string+0x48/0xe0 vsnprintf+0x1f9/0x650 sprintf+0x62/0x80 name_show+0x1f/0x30 dev_attr_show+0x19/0x60 The call trace repeats approximately every 10 minutes when system monitoring tools (e.g., sadc) attempt to read the orphaned hwmon sysfs attributes that reference freed module memory. The sequence is: 1. Driver load, ice_hwmon_init() gets called from ice_init_feature() 2. Devlink reload down, flow does not call ice_remove() 3. Devlink reload up, ice_hwmon_init() gets called from ice_init_feature() resulting in a second instance 4. Driver unload, ice_hwmon_exit() called from ice_remove() leaving the first hwmon instance orphaned with dangling pointer Fix this by moving ice_hwmon_exit() from ice_remove() to ice_deinit_features() to ensure proper cleanup symmetry with ice_hwmon_init().
CVE-2026-23137: In the Linux kernel, the following vulnerability has been resolved: of: unittest: Fix memory leak in unittest_data_add() In unittest_data_add(), if of_resolve_phandles() fails, the allocated unittest_data is not freed, leading to a memory leak. Fix this by using scope-based cleanup helper __free(kfree) for automatic resource cleanup. This ensures unittest_data is automatically freed when it goes out of scope in error paths. For the success path, use retain_and_null_ptr() to transfer ownership of the memory to the device tree and prevent double freeing.
CVE-2026-23138: In the Linux kernel, the following vulnerability has been resolved: tracing: Add recursion protection in kernel stack trace recording A bug was reported about an infinite recursion caused by tracing the rcu events with the kernel stack trace trigger enabled. The stack trace code called back into RCU which then called the stack trace again. Expand the ftrace recursion protection to add a set of bits to protect events from recursion. Each bit represents the context that the event is in (normal, softirq, interrupt and NMI). Have the stack trace code use the interrupt context to protect against recursion. Note, the bug showed an issue in both the RCU code as well as the tracing stacktrace code. This only handles the tracing stack trace side of the bug. The RCU fix will be handled separately.
CVE-2026-23152: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: correctly decode TTLM with default link map TID-To-Link Mapping (TTLM) elements do not contain any link mapping presence indicator if a default mapping is used and parsing needs to be skipped. Note that access points should not explicitly report an advertised TTLM with a default mapping as that is the implied mapping if the element is not included, this is even the case when switching back to the default mapping. However, mac80211 would incorrectly parse the frame and would also read one byte beyond the end of the element.
CVE-2026-23157: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not strictly require dirty metadata threshold for metadata writepages [BUG] There is an internal report that over 1000 processes are waiting at the io_schedule_timeout() of balance_dirty_pages(), causing a system hang and trigger a kernel coredump. The kernel is v6.4 kernel based, but the root problem still applies to any upstream kernel before v6.18. [CAUSE] From Jan Kara for his wisdom on the dirty page balance behavior first. This cgroup dirty limit was what was actually playing the role here because the cgroup had only a small amount of memory and so the dirty limit for it was something like 16MB. Dirty throttling is responsible for enforcing that nobody can dirty (significantly) more dirty memory than there's dirty limit. Thus when a task is dirtying pages it periodically enters into balance_dirty_pages() and we let it sleep there to slow down the dirtying. When the system is over dirty limit already (either globally or within a cgroup of the running task), we will not let the task exit from balance_dirty_pages() until the number of dirty pages drops below the limit. So in this particular case, as I already mentioned, there was a cgroup with relatively small amount of memory and as a result with dirty limit set at 16MB. A task from that cgroup has dirtied about 28MB worth of pages in btrfs btree inode and these were practically the only dirty pages in that cgroup. So that means the only way to reduce the dirty pages of that cgroup is to writeback the dirty pages of btrfs btree inode, and only after that those processes can exit balance_dirty_pages(). Now back to the btrfs part, btree_writepages() is responsible for writing back dirty btree inode pages. The problem here is, there is a btrfs internal threshold that if the btree inode's dirty bytes are below the 32M threshold, it will not do any writeback. This behavior is to batch as much metadata as possible so we won't write back those tree blocks and then later re-COW them again for another modification. This internal 32MiB is higher than the existing dirty page size (28MiB), meaning no writeback will happen, causing a deadlock between btrfs and cgroup: - Btrfs doesn't want to write back btree inode until more dirty pages - Cgroup/MM doesn't want more dirty pages for btrfs btree inode Thus any process touching that btree inode is put into sleep until the number of dirty pages is reduced. Thanks Jan Kara a lot for the analysis of the root cause. [ENHANCEMENT] Since kernel commit b55102826d7d ("btrfs: set AS_KERNEL_FILE on the btree_inode"), btrfs btree inode pages will only be charged to the root cgroup which should have a much larger limit than btrfs' 32MiB threshold. So it should not affect newer kernels. But for all current LTS kernels, they are all affected by this problem, and backporting the whole AS_KERNEL_FILE may not be a good idea. Even for newer kernels I still think it's a good idea to get rid of the internal threshold at btree_writepages(), since for most cases cgroup/MM has a better view of full system memory usage than btrfs' fixed threshold. For internal callers using btrfs_btree_balance_dirty() since that function is already doing internal threshold check, we don't need to bother them. But for external callers of btree_writepages(), just respect their requests and write back whatever they want, ignoring the internal btrfs threshold to avoid such deadlock on btree inode dirty page balancing.
CVE-2026-23171: In the Linux kernel, the following vulnerability has been resolved: bonding: fix use-after-free due to enslave fail after slave array update Fix a use-after-free which happens due to enslave failure after the new slave has been added to the array. Since the new slave can be used for Tx immediately, we can use it after it has been freed by the enslave error cleanup path which frees the allocated slave memory. Slave update array is supposed to be called last when further enslave failures are not expected. Move it after xdp setup to avoid any problems. It is very easy to reproduce the problem with a simple xdp_pass prog: ip l add bond1 type bond mode balance-xor ip l set bond1 up ip l set dev bond1 xdp object xdp_pass.o sec xdp_pass ip l add dumdum type dummy Then run in parallel: while :; do ip l set dumdum master bond1 1>/dev/null 2>&1; done; mausezahn bond1 -a own -b rand -A rand -B 1.1.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" The crash happens almost immediately: [ 605.602850] Oops: general protection fault, probably for non-canonical address 0xe0e6fc2460000137: 0000 [#1] SMP KASAN NOPTI [ 605.602916] KASAN: maybe wild-memory-access in range [0x07380123000009b8-0x07380123000009bf] [ 605.602946] CPU: 0 UID: 0 PID: 2445 Comm: mausezahn Kdump: loaded Tainted: G B 6.19.0-rc6+ #21 PREEMPT(voluntary) [ 605.602979] Tainted: [B]=BAD_PAGE [ 605.602998] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 605.603032] RIP: 0010:netdev_core_pick_tx+0xcd/0x210 [ 605.603063] Code: 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 3e 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 6b 08 49 8d 7d 30 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 25 01 00 00 49 8b 45 30 4c 89 e2 48 89 ee 48 89 [ 605.603111] RSP: 0018:ffff88817b9af348 EFLAGS: 00010213 [ 605.603145] RAX: dffffc0000000000 RBX: ffff88817d28b420 RCX: 0000000000000000 [ 605.603172] RDX: 00e7002460000137 RSI: 0000000000000008 RDI: 07380123000009be [ 605.603199] RBP: ffff88817b541a00 R08: 0000000000000001 R09: fffffbfff3ed8c0c [ 605.603226] R10: ffffffff9f6c6067 R11: 0000000000000001 R12: 0000000000000000 [ 605.603253] R13: 073801230000098e R14: ffff88817d28b448 R15: ffff88817b541a84 [ 605.603286] FS: 00007f6570ef67c0(0000) GS:ffff888221dfa000(0000) knlGS:0000000000000000 [ 605.603319] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 605.603343] CR2: 00007f65712fae40 CR3: 000000011371b000 CR4: 0000000000350ef0 [ 605.603373] Call Trace: [ 605.603392] <TASK> [ 605.603410] __dev_queue_xmit+0x448/0x32a0 [ 605.603434] ? __pfx_vprintk_emit+0x10/0x10 [ 605.603461] ? __pfx_vprintk_emit+0x10/0x10 [ 605.603484] ? __pfx___dev_queue_xmit+0x10/0x10 [ 605.603507] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603546] ? _printk+0xcb/0x100 [ 605.603566] ? __pfx__printk+0x10/0x10 [ 605.603589] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603627] ? add_taint+0x5e/0x70 [ 605.603648] ? add_taint+0x2a/0x70 [ 605.603670] ? end_report.cold+0x51/0x75 [ 605.603693] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603731] bond_start_xmit+0x623/0xc20 [bonding]
CVE-2026-23207: In the Linux kernel, the following vulnerability has been resolved: spi: tegra210-quad: Protect curr_xfer check in IRQ handler Now that all other accesses to curr_xfer are done under the lock, protect the curr_xfer NULL check in tegra_qspi_isr_thread() with the spinlock. Without this protection, the following race can occur: CPU0 (ISR thread) CPU1 (timeout path) ---------------- ------------------- if (!tqspi->curr_xfer) // sees non-NULL spin_lock() tqspi->curr_xfer = NULL spin_unlock() handle_*_xfer() spin_lock() t = tqspi->curr_xfer // NULL! ... t->len ... // NULL dereference! With this patch, all curr_xfer accesses are now properly synchronized. Although all accesses to curr_xfer are done under the lock, in tegra_qspi_isr_thread() it checks for NULL, releases the lock and reacquires it later in handle_cpu_based_xfer()/handle_dma_based_xfer(). There is a potential for an update in between, which could cause a NULL pointer dereference. To handle this, add a NULL check inside the handlers after acquiring the lock. This ensures that if the timeout path has already cleared curr_xfer, the handler will safely return without dereferencing the NULL pointer.
CVE-2026-23208: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Prevent excessive number of frames In this case, the user constructed the parameters with maxpacksize 40 for rate 22050 / pps 1000, and packsize[0] 22 packsize[1] 23. The buffer size for each data URB is maxpacksize * packets, which in this example is 40 * 6 = 240; When the user performs a write operation to send audio data into the ALSA PCM playback stream, the calculated number of frames is packsize[0] * packets = 264, which exceeds the allocated URB buffer size, triggering the out-of-bounds (OOB) issue reported by syzbot [1]. Added a check for the number of single data URB frames when calculating the number of frames to prevent [1]. [1] BUG: KASAN: slab-out-of-bounds in copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 Write of size 264 at addr ffff88804337e800 by task syz.0.17/5506 Call Trace: copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 prepare_playback_urb+0x953/0x13d0 sound/usb/pcm.c:1611 prepare_outbound_urb+0x377/0xc50 sound/usb/endpoint.c:333
CVE-2026-23210: In the Linux kernel, the following vulnerability has been resolved: ice: Fix PTP NULL pointer dereference during VSI rebuild Fix race condition where PTP periodic work runs while VSI is being rebuilt, accessing NULL vsi->rx_rings. The sequence was: 1. ice_ptp_prepare_for_reset() cancels PTP work 2. ice_ptp_rebuild() immediately queues PTP work 3. VSI rebuild happens AFTER ice_ptp_rebuild() 4. PTP work runs and accesses NULL vsi->rx_rings Fix: Keep PTP work cancelled during rebuild, only queue it after VSI rebuild completes in ice_rebuild(). Added ice_ptp_queue_work() helper function to encapsulate the logic for queuing PTP work, ensuring it's only queued when PTP is supported and the state is ICE_PTP_READY. Error log: [ 121.392544] ice 0000:60:00.1: PTP reset successful [ 121.392692] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 121.392712] #PF: supervisor read access in kernel mode [ 121.392720] #PF: error_code(0x0000) - not-present page [ 121.392727] PGD 0 [ 121.392734] Oops: Oops: 0000 [#1] SMP NOPTI [ 121.392746] CPU: 8 UID: 0 PID: 1005 Comm: ice-ptp-0000:60 Tainted: G S 6.19.0-rc6+ #4 PREEMPT(voluntary) [ 121.392761] Tainted: [S]=CPU_OUT_OF_SPEC [ 121.392773] RIP: 0010:ice_ptp_update_cached_phctime+0xbf/0x150 [ice] [ 121.393042] Call Trace: [ 121.393047] <TASK> [ 121.393055] ice_ptp_periodic_work+0x69/0x180 [ice] [ 121.393202] kthread_worker_fn+0xa2/0x260 [ 121.393216] ? __pfx_ice_ptp_periodic_work+0x10/0x10 [ice] [ 121.393359] ? __pfx_kthread_worker_fn+0x10/0x10 [ 121.393371] kthread+0x10d/0x230 [ 121.393382] ? __pfx_kthread+0x10/0x10 [ 121.393393] ret_from_fork+0x273/0x2b0 [ 121.393407] ? __pfx_kthread+0x10/0x10 [ 121.393417] ret_from_fork_asm+0x1a/0x30 [ 121.393432] </TASK>
CVE-2026-23217: In the Linux kernel, the following vulnerability has been resolved: riscv: trace: fix snapshot deadlock with sbi ecall If sbi_ecall.c's functions are traceable, echo "__sbi_ecall:snapshot" > /sys/kernel/tracing/set_ftrace_filter may get the kernel into a deadlock. (Functions in sbi_ecall.c are excluded from tracing if CONFIG_RISCV_ALTERNATIVE_EARLY is set.) __sbi_ecall triggers a snapshot of the ringbuffer. The snapshot code raises an IPI interrupt, which results in another call to __sbi_ecall and another snapshot... All it takes to get into this endless loop is one initial __sbi_ecall. On RISC-V systems without SSTC extension, the clock events in timer-riscv.c issue periodic sbi ecalls, making the problem easy to trigger. Always exclude the sbi_ecall.c functions from tracing to fix the potential deadlock. sbi ecalls can easiliy be logged via trace events, excluding ecall functions from function tracing is not a big limitation.
CVE-2026-23226: In the Linux kernel, the following vulnerability has been resolved: ksmbd: add chann_lock to protect ksmbd_chann_list xarray ksmbd_chann_list xarray lacks synchronization, allowing use-after-free in multi-channel sessions (between lookup_chann_list() and ksmbd_chann_del). Adds rw_semaphore chann_lock to struct ksmbd_session and protects all xa_load/xa_store/xa_erase accesses.
CVE-2026-23227: In the Linux kernel, the following vulnerability has been resolved: drm/exynos: vidi: use ctx->lock to protect struct vidi_context member variables related to memory alloc/free Exynos Virtual Display driver performs memory alloc/free operations without lock protection, which easily causes concurrency problem. For example, use-after-free can occur in race scenario like this: ``` CPU0 CPU1 CPU2 ---- ---- ---- vidi_connection_ioctl() if (vidi->connection) // true drm_edid = drm_edid_alloc(); // alloc drm_edid ... ctx->raw_edid = drm_edid; ... drm_mode_getconnector() drm_helper_probe_single_connector_modes() vidi_get_modes() if (ctx->raw_edid) // true drm_edid_dup(ctx->raw_edid); if (!drm_edid) // false ... vidi_connection_ioctl() if (vidi->connection) // false drm_edid_free(ctx->raw_edid); // free drm_edid ... drm_edid_alloc(drm_edid->edid) kmemdup(edid); // UAF!! ... ``` To prevent these vulns, at least in vidi_context, member variables related to memory alloc/free should be protected with ctx->lock.
CVE-2026-23231: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix use-after-free in nf_tables_addchain() nf_tables_addchain() publishes the chain to table->chains via list_add_tail_rcu() (in nft_chain_add()) before registering hooks. If nf_tables_register_hook() then fails, the error path calls nft_chain_del() (list_del_rcu()) followed by nf_tables_chain_destroy() with no RCU grace period in between. This creates two use-after-free conditions: 1) Control-plane: nf_tables_dump_chains() traverses table->chains under rcu_read_lock(). A concurrent dump can still be walking the chain when the error path frees it. 2) Packet path: for NFPROTO_INET, nf_register_net_hook() briefly installs the IPv4 hook before IPv6 registration fails. Packets entering nft_do_chain() via the transient IPv4 hook can still be dereferencing chain->blob_gen_X when the error path frees the chain. Add synchronize_rcu() between nft_chain_del() and the chain destroy so that all RCU readers -- both dump threads and in-flight packet evaluation -- have finished before the chain is freed.
CVE-2026-23239: In the Linux kernel, the following vulnerability has been resolved: espintcp: Fix race condition in espintcp_close() This issue was discovered during a code audit. After cancel_work_sync() is called from espintcp_close(), espintcp_tx_work() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the espintcp_tx_work() worker may dereference a freed espintcp ctx or sk. The following is a simple race scenario: cpu0 cpu1 espintcp_close() cancel_work_sync(&ctx->work); espintcp_write_space() schedule_work(&ctx->work); To prevent this race condition, cancel_work_sync() is replaced with disable_work_sync().
CVE-2026-23240: In the Linux kernel, the following vulnerability has been resolved: tls: Fix race condition in tls_sw_cancel_work_tx() This issue was discovered during a code audit. After cancel_delayed_work_sync() is called from tls_sk_proto_close(), tx_work_handler() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the tx_work_handler() worker may dereference a freed TLS object. The following is a simple race scenario: cpu0 cpu1 tls_sk_proto_close() tls_sw_cancel_work_tx() tls_write_space() tls_sw_write_space() if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); cancel_delayed_work_sync(&ctx->tx_work.work); schedule_delayed_work(&tx_ctx->tx_work.work, 0); To prevent this race condition, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().
CVE-2026-23242: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Fix potential NULL pointer dereference in header processing If siw_get_hdr() returns -EINVAL before set_rx_fpdu_context(), qp->rx_fpdu can be NULL. The error path in siw_tcp_rx_data() dereferences qp->rx_fpdu->more_ddp_segs without checking, which may lead to a NULL pointer deref. Only check more_ddp_segs when rx_fpdu is present. KASAN splat: [ 101.384271] KASAN: null-ptr-deref in range [0x00000000000000c0-0x00000000000000c7] [ 101.385869] RIP: 0010:siw_tcp_rx_data+0x13ad/0x1e50
CVE-2026-23243: In the Linux kernel, the following vulnerability has been resolved: RDMA/umad: Reject negative data_len in ib_umad_write ib_umad_write computes data_len from user-controlled count and the MAD header sizes. With a mismatched user MAD header size and RMPP header length, data_len can become negative and reach ib_create_send_mad(). This can make the padding calculation exceed the segment size and trigger an out-of-bounds memset in alloc_send_rmpp_list(). Add an explicit check to reject negative data_len before creating the send buffer. KASAN splat: [ 211.363464] BUG: KASAN: slab-out-of-bounds in ib_create_send_mad+0xa01/0x11b0 [ 211.364077] Write of size 220 at addr ffff88800c3fa1f8 by task spray_thread/102 [ 211.365867] ib_create_send_mad+0xa01/0x11b0 [ 211.365887] ib_umad_write+0x853/0x1c80
CVE-2026-23244: In the Linux kernel, the following vulnerability has been resolved: nvme: fix memory allocation in nvme_pr_read_keys() nvme_pr_read_keys() takes num_keys from userspace and uses it to calculate the allocation size for rse via struct_size(). The upper limit is PR_KEYS_MAX (64K). A malicious or buggy userspace can pass a large num_keys value that results in a 4MB allocation attempt at most, causing a warning in the page allocator when the order exceeds MAX_PAGE_ORDER. To fix this, use kvzalloc() instead of kzalloc(). This bug has the same reasoning and fix with the patch below: https://lore.kernel.org/linux-block/20251212013510.3576091-1-kartikey406@gmail.com/ Warning log: WARNING: mm/page_alloc.c:5216 at __alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216, CPU#1: syz-executor117/272 Modules linked in: CPU: 1 UID: 0 PID: 272 Comm: syz-executor117 Not tainted 6.19.0 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:__alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216 Code: ff 83 bd a8 fe ff ff 0a 0f 86 69 fb ff ff 0f b6 1d f9 f9 c4 04 80 fb 01 0f 87 3b 76 30 ff 83 e3 01 75 09 c6 05 e4 f9 c4 04 01 <0f> 0b 48 c7 85 70 fe ff ff 00 00 00 00 e9 8f fd ff ff 31 c0 e9 0d RSP: 0018:ffffc90000fcf450 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff920001f9ea0 RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000040dc0 RBP: ffffc90000fcf648 R08: ffff88800b6c3380 R09: 0000000000000001 R10: ffffc90000fcf840 R11: ffff88807ffad280 R12: 0000000000000000 R13: 0000000000040dc0 R14: 0000000000000001 R15: ffffc90000fcf620 FS: 0000555565db33c0(0000) GS:ffff8880be26c000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000002000000c CR3: 0000000003b72000 CR4: 00000000000006f0 Call Trace: <TASK> alloc_pages_mpol+0x236/0x4d0 mm/mempolicy.c:2486 alloc_frozen_pages_noprof+0x149/0x180 mm/mempolicy.c:2557 ___kmalloc_large_node+0x10c/0x140 mm/slub.c:5598 __kmalloc_large_node_noprof+0x25/0xc0 mm/slub.c:5629 __do_kmalloc_node mm/slub.c:5645 [inline] __kmalloc_noprof+0x483/0x6f0 mm/slub.c:5669 kmalloc_noprof include/linux/slab.h:961 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] nvme_pr_read_keys+0x8f/0x4c0 drivers/nvme/host/pr.c:245 blkdev_pr_read_keys block/ioctl.c:456 [inline] blkdev_common_ioctl+0x1b71/0x29b0 block/ioctl.c:730 blkdev_ioctl+0x299/0x700 block/ioctl.c:786 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x1bf/0x220 fs/ioctl.c:583 x64_sys_call+0x1280/0x21b0 mnt/fuzznvme_1/fuzznvme/linux-build/v6.19/./arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x71/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fb893d3108d Code: 28 c3 e8 46 1e 00 00 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffff61f2f38 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffff61f3138 RCX: 00007fb893d3108d RDX: 0000000020000040 RSI: 00000000c01070ce RDI: 0000000000000003 RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffff61f3138 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 R13: 00007ffff61f3128 R14: 00007fb893dae530 R15: 0000000000000001 </TASK>
CVE-2026-23245: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_gate: snapshot parameters with RCU on replace The gate action can be replaced while the hrtimer callback or dump path is walking the schedule list. Convert the parameters to an RCU-protected snapshot and swap updates under tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits the entry list, preserve the existing schedule so the effective state is unchanged.
CVE-2026-23246: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration link_id is taken from the ML Reconfiguration element (control & 0x000f), so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS (15) elements, so index 15 is out-of-bounds. Skip subelements with link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds write.
CVE-2026-23247: In the Linux kernel, the following vulnerability has been resolved: tcp: secure_seq: add back ports to TS offset This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets") tcp_tw_recycle went away in 2017. Zhouyan Deng reported off-path TCP source port leakage via SYN cookie side-channel that can be fixed in multiple ways. One of them is to bring back TCP ports in TS offset randomization. As a bonus, we perform a single siphash() computation to provide both an ISN and a TS offset.
CVE-2026-23249: In the Linux kernel, the following vulnerability has been resolved: xfs: check for deleted cursors when revalidating two btrees The free space and inode btree repair functions will rebuild both btrees at the same time, after which it needs to evaluate both btrees to confirm that the corruptions are gone. However, Jiaming Zhang ran syzbot and produced a crash in the second xchk_allocbt call. His root-cause analysis is as follows (with minor corrections): In xrep_revalidate_allocbt(), xchk_allocbt() is called twice (first for BNOBT, second for CNTBT). The cause of this issue is that the first call nullified the cursor required by the second call. Let's first enter xrep_revalidate_allocbt() via following call chain: xfs_file_ioctl() -> xfs_ioc_scrubv_metadata() -> xfs_scrub_metadata() -> `sc->ops->repair_eval(sc)` -> xrep_revalidate_allocbt() xchk_allocbt() is called twice in this function. In the first call: /* Note that sc->sm->sm_type is XFS_SCRUB_TYPE_BNOPT now */ xchk_allocbt() -> xchk_btree() -> `bs->scrub_rec(bs, recp)` -> xchk_allocbt_rec() -> xchk_allocbt_xref() -> xchk_allocbt_xref_other() since sm_type is XFS_SCRUB_TYPE_BNOBT, pur is set to &sc->sa.cnt_cur. Kernel called xfs_alloc_get_rec() and returned -EFSCORRUPTED. Call chain: xfs_alloc_get_rec() -> xfs_btree_get_rec() -> xfs_btree_check_block() -> (XFS_IS_CORRUPT || XFS_TEST_ERROR), the former is false and the latter is true, return -EFSCORRUPTED. This should be caused by ioctl$XFS_IOC_ERROR_INJECTION I guess. Back to xchk_allocbt_xref_other(), after receiving -EFSCORRUPTED from xfs_alloc_get_rec(), kernel called xchk_should_check_xref(). In this function, *curpp (points to sc->sa.cnt_cur) is nullified. Back to xrep_revalidate_allocbt(), since sc->sa.cnt_cur has been nullified, it then triggered null-ptr-deref via xchk_allocbt() (second call) -> xchk_btree(). So. The bnobt revalidation failed on a cross-reference attempt, so we deleted the cntbt cursor, and then crashed when we tried to revalidate the cntbt. Therefore, check for a null cntbt cursor before that revalidation, and mark the repair incomplete. Also we can ignore the second tree entirely if the first tree was rebuilt but is already corrupt. Apply the same fix to xrep_revalidate_iallocbt because it has the same problem.
CVE-2026-23250: In the Linux kernel, the following vulnerability has been resolved: xfs: check return value of xchk_scrub_create_subord Fix this function to return NULL instead of a mangled ENOMEM, then fix the callers to actually check for a null pointer and return ENOMEM. Most of the corrections here are for code merged between 6.2 and 6.10.
CVE-2026-23251: In the Linux kernel, the following vulnerability has been resolved: xfs: only call xf{array,blob}_destroy if we have a valid pointer Only call the xfarray and xfblob destructor if we have a valid pointer, and be sure to null out that pointer afterwards. Note that this patch fixes a large number of commits, most of which were merged between 6.9 and 6.10.
CVE-2026-23252: In the Linux kernel, the following vulnerability has been resolved: xfs: get rid of the xchk_xfile_*_descr calls The xchk_xfile_*_descr macros call kasprintf, which can fail to allocate memory if the formatted string is larger than 16 bytes (or whatever the nofail guarantees are nowadays). Some of them could easily exceed that, and Jiaming Zhang found a few places where that can happen with syzbot. The descriptions are debugging aids and aren't required to be unique, so let's just pass in static strings and eliminate this path to failure. Note this patch touches a number of commits, most of which were merged between 6.6 and 6.14.
CVE-2026-23253: In the Linux kernel, the following vulnerability has been resolved: media: dvb-core: fix wrong reinitialization of ringbuffer on reopen dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty. Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}. The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions. Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.
CVE-2026-23255: In the Linux kernel, the following vulnerability has been resolved: net: add proper RCU protection to /proc/net/ptype Yin Fengwei reported an RCU stall in ptype_seq_show() and provided a patch. Real issue is that ptype_seq_next() and ptype_seq_show() violate RCU rules. ptype_seq_show() runs under rcu_read_lock(), and reads pt->dev to get device name without any barrier. At the same time, concurrent writers can remove a packet_type structure (which is correctly freed after an RCU grace period) and clear pt->dev without an RCU grace period. Define ptype_iter_state to carry a dev pointer along seq_net_private: struct ptype_iter_state { struct seq_net_private p; struct net_device *dev; // added in this patch }; We need to record the device pointer in ptype_get_idx() and ptype_seq_next() so that ptype_seq_show() is safe against concurrent pt->dev changes. We also need to add full RCU protection in ptype_seq_next(). (Missing READ_ONCE() when reading list.next values) Many thanks to Dong Chenchen for providing a repro.
CVE-2026-23259: In the Linux kernel, the following vulnerability has been resolved: io_uring/rw: free potentially allocated iovec on cache put failure If a read/write request goes through io_req_rw_cleanup() and has an allocated iovec attached and fails to put to the rw_cache, then it may end up with an unaccounted iovec pointer. Have io_rw_recycle() return whether it recycled the request or not, and use that to gauge whether to free a potential iovec or not.
CVE-2026-23265: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer in {read,write}_end_io -----------[ cut here ]------------ kernel BUG at fs/f2fs/data.c:358! Call Trace: <IRQ> blk_update_request+0x5eb/0xe70 block/blk-mq.c:987 blk_mq_end_request+0x3e/0x70 block/blk-mq.c:1149 blk_complete_reqs block/blk-mq.c:1224 [inline] blk_done_softirq+0x107/0x160 block/blk-mq.c:1229 handle_softirqs+0x283/0x870 kernel/softirq.c:579 __do_softirq kernel/softirq.c:613 [inline] invoke_softirq kernel/softirq.c:453 [inline] __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1050 </IRQ> In f2fs_write_end_io(), it detects there is inconsistency in between node page index (nid) and footer.nid of node page. If footer of node page is corrupted in fuzzed image, then we load corrupted node page w/ async method, e.g. f2fs_ra_node_pages() or f2fs_ra_node_page(), in where we won't do sanity check on node footer, once node page becomes dirty, we will encounter this bug after node page writeback.
CVE-2026-23270: In the Linux kernel, the following vulnerability has been resolved: net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and shared blocks As Paolo said earlier [1]: "Since the blamed commit below, classify can return TC_ACT_CONSUMED while the current skb being held by the defragmentation engine. As reported by GangMin Kim, if such packet is that may cause a UaF when the defrag engine later on tries to tuch again such packet." act_ct was never meant to be used in the egress path, however some users are attaching it to egress today [2]. Attempting to reach a middle ground, we noticed that, while most qdiscs are not handling TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we address the issue by only allowing act_ct to bind to clsact/ingress qdiscs and shared blocks. That way it's still possible to attach act_ct to egress (albeit only with clsact). [1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/ [2] https://lore.kernel.org/netdev/cc6bfb4a-4a2b-42d8-b9ce-7ef6644fb22b@ovn.org/
CVE-2026-23271: In the Linux kernel, the following vulnerability has been resolved: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race Make sure that __perf_event_overflow() runs with IRQs disabled for all possible callchains. Specifically the software events can end up running it with only preemption disabled. This opens up a race vs perf_event_exit_event() and friends that will go and free various things the overflow path expects to be present, like the BPF program.
CVE-2026-23272: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: unconditionally bump set->nelems before insertion In case that the set is full, a new element gets published then removed without waiting for the RCU grace period, while RCU reader can be walking over it already. To address this issue, add the element transaction even if set is full, but toggle the set_full flag to report -ENFILE so the abort path safely unwinds the set to its previous state. As for element updates, decrement set->nelems to restore it. A simpler fix is to call synchronize_rcu() in the error path. However, with a large batch adding elements to already maxed-out set, this could cause noticeable slowdown of such batches.
CVE-2026-23273: In the Linux kernel, the following vulnerability has been resolved: macvlan: observe an RCU grace period in macvlan_common_newlink() error path valis reported that a race condition still happens after my prior patch. macvlan_common_newlink() might have made @dev visible before detecting an error, and its caller will directly call free_netdev(dev). We must respect an RCU period, either in macvlan or the core networking stack. After adding a temporary mdelay(1000) in macvlan_forward_source_one() to open the race window, valis repro was: ip link add p1 type veth peer p2 ip link set address 00:00:00:00:00:20 dev p1 ip link set up dev p1 ip link set up dev p2 ip link add mv0 link p2 type macvlan mode source (ip link add invalid% link p2 type macvlan mode source macaddr add 00:00:00:00:00:20 &) ; sleep 0.5 ; ping -c1 -I p1 1.2.3.4 PING 1.2.3.4 (1.2.3.4): 56 data bytes RTNETLINK answers: Invalid argument BUG: KASAN: slab-use-after-free in macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) Read of size 8 at addr ffff888016bb89c0 by task e/175 CPU: 1 UID: 1000 PID: 175 Comm: e Not tainted 6.19.0-rc8+ #33 NONE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) kasan_report (mm/kasan/report.c:597) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) ? tasklet_init (kernel/softirq.c:983) macvlan_handle_frame (drivers/net/macvlan.c:501) Allocated by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) __kasan_kmalloc (mm/kasan/common.c:419) __kvmalloc_node_noprof (./include/linux/kasan.h:263 mm/slub.c:5657 mm/slub.c:7140) alloc_netdev_mqs (net/core/dev.c:12012) rtnl_create_link (net/core/rtnetlink.c:3648) rtnl_newlink (net/core/rtnetlink.c:3830 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131) Freed by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) kasan_save_free_info (mm/kasan/generic.c:587) __kasan_slab_free (mm/kasan/common.c:287) kfree (mm/slub.c:6674 mm/slub.c:6882) rtnl_newlink (net/core/rtnetlink.c:3845 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
CVE-2026-23274: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels IDLETIMER revision 0 rules reuse existing timers by label and always call mod_timer() on timer->timer. If the label was created first by revision 1 with XT_IDLETIMER_ALARM, the object uses alarm timer semantics and timer->timer is never initialized. Reusing that object from revision 0 causes mod_timer() on an uninitialized timer_list, triggering debugobjects warnings and possible panic when panic_on_warn=1. Fix this by rejecting revision 0 rule insertion when an existing timer with the same label is of ALARM type.
CVE-2026-23276: In the Linux kernel, the following vulnerability has been resolved: net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: <TASK> __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread </TASK>
CVE-2026-23277: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit through slave devices, but does not update skb->dev to the slave device beforehand. When a gretap tunnel is a TEQL slave, the transmit path reaches iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0 master) and later calls iptunnel_xmit_stats(dev, pkt_len). This function does: get_cpu_ptr(dev->tstats) Since teql_master_setup() does not set dev->pcpu_stat_type to NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes NULL + __per_cpu_offset[cpu], resulting in a page fault. BUG: unable to handle page fault for address: ffff8880e6659018 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 68bc067 P4D 68bc067 PUD 0 Oops: Oops: 0002 [#1] SMP KASAN PTI RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89) Call Trace: <TASK> ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) __gre_xmit (net/ipv4/ip_gre.c:478) gre_tap_xmit (net/ipv4/ip_gre.c:779) teql_master_xmit (net/sched/sch_teql.c:319) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) neigh_direct_output (net/core/neighbour.c:1660) ip_finish_output2 (net/ipv4/ip_output.c:237) __ip_finish_output.part.0 (net/ipv4/ip_output.c:315) ip_mc_output (net/ipv4/ip_output.c:369) ip_send_skb (net/ipv4/ip_output.c:1508) udp_send_skb (net/ipv4/udp.c:1195) udp_sendmsg (net/ipv4/udp.c:1485) inet_sendmsg (net/ipv4/af_inet.c:859) __sys_sendto (net/socket.c:2206) Fix this by setting skb->dev = slave before calling netdev_start_xmit(), so that tunnel xmit functions see the correct slave device with properly allocated tstats.
CVE-2026-23278: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: always walk all pending catchall elements During transaction processing we might have more than one catchall element: 1 live catchall element and 1 pending element that is coming as part of the new batch. If the map holding the catchall elements is also going away, its required to toggle all catchall elements and not just the first viable candidate. Otherwise, we get: WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables] [..] __nft_set_elem_destroy+0x106/0x380 [nf_tables] nf_tables_abort_release+0x348/0x8d0 [nf_tables] nf_tables_abort+0xcf2/0x3ac0 [nf_tables] nfnetlink_rcv_batch+0x9c9/0x20e0 [..]
CVE-2026-23279: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame() In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check: ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl; ... pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value); The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference. A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required. Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211] CR2: 0000000000000000 Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code. The bug has been present since v3.13 (released 2014-01-19).
CVE-2026-23281: In the Linux kernel, the following vulnerability has been resolved: wifi: libertas: fix use-after-free in lbs_free_adapter() The lbs_free_adapter() function uses timer_delete() (non-synchronous) for both command_timer and tx_lockup_timer before the structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete. If a timer callback is executing when lbs_free_adapter() is called, the callback will access freed memory since lbs_cfg_free() frees the containing structure immediately after lbs_free_adapter() returns. Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler) access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields, which would all be use-after-free violations. Use timer_delete_sync() instead to ensure any running timer callback has completed before returning. This bug was introduced in commit 8f641d93c38a ("libertas: detect TX lockups and reset hardware") where del_timer() was used instead of del_timer_sync() in the cleanup path. The command_timer has had the same issue since the driver was first written.
CVE-2026-23284: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: mtk_eth_soc: Reset prog ptr to old_prog in case of error in mtk_xdp_setup() Reset eBPF program pointer to old_prog and do not decrease its ref-count if mtk_open routine in mtk_xdp_setup() fails.
CVE-2026-23285: In the Linux kernel, the following vulnerability has been resolved: drbd: fix null-pointer dereference on local read error In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to __req_mod() with a NULL peer_device: __req_mod(req, what, NULL, &m); The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this NULL peer_device to drbd_set_out_of_sync(), which dereferences it, causing a null-pointer dereference. Fix this by obtaining the peer_device via first_peer_device(device), matching how drbd_req_destroy() handles the same situation.
CVE-2026-23286: In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix null-ptr-deref in lec_arp_clear_vccs syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer. In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry. For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables: 1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL. 2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash. Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers. The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket. The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.
CVE-2026-23287: In the Linux kernel, the following vulnerability has been resolved: irqchip/sifive-plic: Fix frozen interrupt due to affinity setting PLIC ignores interrupt completion message for disabled interrupt, explained by the specification: The PLIC signals it has completed executing an interrupt handler by writing the interrupt ID it received from the claim to the claim/complete register. The PLIC does not check whether the completion ID is the same as the last claim ID for that target. If the completion ID does not match an interrupt source that is currently enabled for the target, the completion is silently ignored. This caused problems in the past, because an interrupt can be disabled while still being handled and plic_irq_eoi() had no effect. That was fixed by checking if the interrupt is disabled, and if so enable it, before sending the completion message. That check is done with irqd_irq_disabled(). However, that is not sufficient because the enable bit for the handling hart can be zero despite irqd_irq_disabled(d) being false. This can happen when affinity setting is changed while a hart is still handling the interrupt. This problem is easily reproducible by dumping a large file to uart (which generates lots of interrupts) and at the same time keep changing the uart interrupt's affinity setting. The uart port becomes frozen almost instantaneously. Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().
CVE-2026-23289: In the Linux kernel, the following vulnerability has been resolved: IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq() Fix a user triggerable leak on the system call failure path.
CVE-2026-23290: In the Linux kernel, the following vulnerability has been resolved: net: usb: pegasus: validate USB endpoints The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23291: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: properly drop the usb interface reference on disconnect When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.
CVE-2026-23292: In the Linux kernel, the following vulnerability has been resolved: scsi: target: Fix recursive locking in __configfs_open_file() In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace: down_read __configfs_open_file do_dentry_open vfs_open do_open path_openat do_filp_open file_open_name filp_open target_core_item_dbroot_store flush_write_buffer configfs_write_iter target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows: db_root: not a directory: /sys/kernel/config/target/dbroot indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking. Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.
CVE-2026-23293: In the Linux kernel, the following vulnerability has been resolved: net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If an IPv6 packet is injected into the interface, route_shortcircuit() is called and a NULL pointer dereference happens on neigh_lookup(). BUG: kernel NULL pointer dereference, address: 0000000000000380 Oops: Oops: 0000 [#1] SMP NOPTI [...] RIP: 0010:neigh_lookup+0x20/0x270 [...] Call Trace: <TASK> vxlan_xmit+0x638/0x1ef0 [vxlan] dev_hard_start_xmit+0x9e/0x2e0 __dev_queue_xmit+0xbee/0x14e0 packet_sendmsg+0x116f/0x1930 __sys_sendto+0x1f5/0x200 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x12f/0x1590 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fix this by adding an early check on route_shortcircuit() when protocol is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because VXLAN can be built-in even when IPv6 is built as a module.
CVE-2026-23296: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix refcount leak for tagset_refcnt This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace: [130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid" #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef
CVE-2026-23297: In the Linux kernel, the following vulnerability has been resolved: nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit(). syzbot reported memory leak of struct cred. [0] nfsd_nl_threads_set_doit() passes get_current_cred() to nfsd_svc(), but put_cred() is not called after that. The cred is finally passed down to _svc_xprt_create(), which calls get_cred() with the cred for struct svc_xprt. The ownership of the refcount by get_current_cred() is not transferred to anywhere and is just leaked. nfsd_svc() is also called from write_threads(), but it does not bump file->f_cred there. nfsd_nl_threads_set_doit() is called from sendmsg() and current->cred does not go away. Let's use current_cred() in nfsd_nl_threads_set_doit(). [0]: BUG: memory leak unreferenced object 0xffff888108b89480 (size 184): comm "syz-executor", pid 5994, jiffies 4294943386 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc 369454a7): kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline] slab_post_alloc_hook mm/slub.c:4958 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270 prepare_creds+0x22/0x600 kernel/cred.c:185 copy_creds+0x44/0x290 kernel/cred.c:286 copy_process+0x7a7/0x2870 kernel/fork.c:2086 kernel_clone+0xac/0x6e0 kernel/fork.c:2651 __do_sys_clone+0x7f/0xb0 kernel/fork.c:2792 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f
CVE-2026-23298: In the Linux kernel, the following vulnerability has been resolved: can: ucan: Fix infinite loop from zero-length messages If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one. This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.
CVE-2026-23300: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop When a standalone IPv6 nexthop object is created with a loopback device (e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies it as a reject route. This is because nexthop objects have no destination prefix (fc_dst=::), causing fib6_is_reject() to match any loopback nexthop. The reject path skips fib_nh_common_init(), leaving nhc_pcpu_rth_output unallocated. If an IPv4 route later references this nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and panics. Simplify the check in fib6_nh_init() to only match explicit reject routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback promotion heuristic in fib6_is_reject() is handled separately by ip6_route_info_create_nh(). After this change, the three cases behave as follows: 1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"): RTF_REJECT is set, enters reject path, skips fib_nh_common_init(). No behavior change. 2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. ip6_route_info_create_nh() still promotes it to reject afterward. nhc_pcpu_rth_output is allocated but unused, which is harmless. 3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. nhc_pcpu_rth_output is properly allocated, fixing the crash when IPv4 routes reference this nexthop.
CVE-2026-23302: In the Linux kernel, the following vulnerability has been resolved: net: annotate data-races around sk->sk_{data_ready,write_space} skmsg (and probably other layers) are changing these pointers while other cpus might read them concurrently. Add corresponding READ_ONCE()/WRITE_ONCE() annotations for UDP, TCP and AF_UNIX.
CVE-2026-23303: In the Linux kernel, the following vulnerability has been resolved: smb: client: Don't log plaintext credentials in cifs_set_cifscreds When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.
CVE-2026-23304: In the Linux kernel, the following vulnerability has been resolved: ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu() l3mdev_master_dev_rcu() can return NULL when the slave device is being un-slaved from a VRF. All other callers deal with this, but we lost the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu() with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address"). KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f] RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418) Call Trace: ip6_pol_route (net/ipv6/route.c:2318) fib6_rule_lookup (net/ipv6/fib6_rules.c:115) ip6_route_output_flags (net/ipv6/route.c:2607) vrf_process_v6_outbound (drivers/net/vrf.c:437) I was tempted to rework the un-slaving code to clear the flag first and insert synchronize_rcu() before we remove the upper. But looks like the explicit fallback to loopback_dev is an established pattern. And I guess avoiding the synchronize_rcu() is nice, too.
CVE-2026-23306: In the Linux kernel, the following vulnerability has been resolved: scsi: pm8001: Fix use-after-free in pm8001_queue_command() Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors pm8001_queue_command(), however it introduces a potential cause of a double free scenario when it changes the function to return -ENODEV in case of phy down/device gone state. In this path, pm8001_queue_command() updates task status and calls task_done to indicate to upper layer that the task has been handled. However, this also frees the underlying SAS task. A -ENODEV is then returned to the caller. When libsas sas_ata_qc_issue() receives this error value, it assumes the task wasn't handled/queued by LLDD and proceeds to clean up and free the task again, resulting in a double free. Since pm8001_queue_command() handles the SAS task in this case, it should return 0 to the caller indicating that the task has been handled.
CVE-2026-23307: In the Linux kernel, the following vulnerability has been resolved: can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer. When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.
CVE-2026-23308: In the Linux kernel, the following vulnerability has been resolved: pinctrl: equilibrium: fix warning trace on load The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also called in the callback function 'eqbr_irq_mask_ack()'. This is done to avoid source code duplication. The problem, is that in the function 'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()' This generates the following warning trace in the log for every gpio on load. [ 6.088111] ------------[ cut here ]------------ [ 6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50 [ 6.097847] Modules linked in: [ 6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.12.59+ #0 [ 6.097847] Tainted: [W]=WARN [ 6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50 [ 6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 [ 6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046 [ 6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008 [ 6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0 [ 6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000 [ 6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514 [ 6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000 [ 6.097847] FS: 0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000 [ 6.097847] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0 [ 6.097847] Call Trace: [ 6.097847] <TASK> [ 6.097847] ? eqbr_irq_mask+0x63/0x70 [ 6.097847] ? no_action+0x10/0x10 [ 6.097847] eqbr_irq_mask_ack+0x11/0x60 In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the interrupt is not disabled here. To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()' function. Implement instead this directly without disabling the interrupts.
CVE-2026-23310: In the Linux kernel, the following vulnerability has been resolved: bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard. For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can: 1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3). 2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded. This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering: WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)) Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode. commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set(). Note: commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.
CVE-2026-23312: In the Linux kernel, the following vulnerability has been resolved: net: usb: kaweth: validate USB endpoints The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23313: In the Linux kernel, the following vulnerability has been resolved: i40e: Fix preempt count leak in napi poll tracepoint Using get_cpu() in the tracepoint assignment causes an obvious preempt count leak because nothing invokes put_cpu() to undo it: softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101? This clearly has seen a lot of testing in the last 3+ years... Use smp_processor_id() instead.
CVE-2026-23315: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob access. [fix check to also cover mgmt->u.action.u.addba_req.capab, correct Fixes tag]
CVE-2026-23316: In the Linux kernel, the following vulnerability has been resolved: net: ipv4: fix ARM64 alignment fault in multipath hash seed `struct sysctl_fib_multipath_hash_seed` contains two u32 fields (user_seed and mp_seed), making it an 8-byte structure with a 4-byte alignment requirement. In `fib_multipath_hash_from_keys()`, the code evaluates the entire struct atomically via `READ_ONCE()`: mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; While this silently works on GCC by falling back to unaligned regular loads which the ARM64 kernel tolerates, it causes a fatal kernel panic when compiled with Clang and LTO enabled. Commit e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y") strengthens `READ_ONCE()` to use Load-Acquire instructions (`ldar` / `ldapr`) to prevent compiler reordering bugs under Clang LTO. Since the macro evaluates the full 8-byte struct, Clang emits a 64-bit `ldar` instruction. ARM64 architecture strictly requires `ldar` to be naturally aligned, thus executing it on a 4-byte aligned address triggers a strict Alignment Fault (FSC = 0x21). Fix the read side by moving the `READ_ONCE()` directly to the `u32` member, which emits a safe 32-bit `ldar Wn`. Furthermore, Eric Dumazet pointed out that `WRITE_ONCE()` on the entire struct in `proc_fib_multipath_hash_set_seed()` is also flawed. Analysis shows that Clang splits this 8-byte write into two separate 32-bit `str` instructions. While this avoids an alignment fault, it destroys atomicity and exposes a tear-write vulnerability. Fix this by explicitly splitting the write into two 32-bit `WRITE_ONCE()` operations. Finally, add the missing `READ_ONCE()` when reading `user_seed` in `proc_fib_multipath_hash_seed()` to ensure proper pairing and concurrency safety.
CVE-2026-23317: In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Return the correct value in vmw_translate_ptr functions Before the referenced fixes these functions used a lookup function that returned a pointer. This was changed to another lookup function that returned an error code with the pointer becoming an out parameter. The error path when the lookup failed was not changed to reflect this change and the code continued to return the PTR_ERR of the now uninitialized pointer. This could cause the vmw_translate_ptr functions to return success when they actually failed causing further uninitialized and OOB accesses.
CVE-2026-23318: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Use correct version for UAC3 header validation The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields. The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.
CVE-2026-23319: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim The root cause of this bug is that when 'bpf_link_put' reduces the refcount of 'shim_link->link.link' to zero, the resource is considered released but may still be referenced via 'tr->progs_hlist' in 'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in 'bpf_shim_tramp_link_release' is deferred. During this window, another process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'. Based on Martin KaFai Lau's suggestions, I have created a simple patch. To fix this: Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'. Only increment the refcount if it is not already zero. Testing: I verified the fix by adding a delay in 'bpf_shim_tramp_link_release' to make the bug easier to trigger: static void bpf_shim_tramp_link_release(struct bpf_link *link) { /* ... */ if (!shim_link->trampoline) return; + msleep(100); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } Before the patch, running a PoC easily reproduced the crash(almost 100%) with a call trace similar to KaiyanM's report. After the patch, the bug no longer occurs even after millions of iterations.
CVE-2026-23321: In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: in-kernel: always mark signal+subflow endp as used Syzkaller managed to find a combination of actions that was generating this warning: msk->pm.local_addr_used == 0 WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961 Modules linked in: CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full) Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014 RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline] RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline] RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210 Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a RSP: 0018:ffffc90001663880 EFLAGS: 00010293 RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640 R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650 FS: 00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0 Call Trace: <TASK> genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115 genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg+0xc9/0xf0 net/socket.c:742 ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592 ___sys_sendmsg+0x2de/0x320 net/socket.c:2646 __sys_sendmsg net/socket.c:2678 [inline] __do_sys_sendmsg net/socket.c:2683 [inline] __se_sys_sendmsg net/socket.c:2681 [inline] __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f66346f826d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8 R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770 </TASK> The actions that caused that seem to be: - Set the MPTCP subflows limit to 0 - Create an MPTCP endpoint with both the 'signal' and 'subflow' flags - Create a new MPTCP connection from a different address: an ADD_ADDR linked to the MPTCP endpoint will be sent ('signal' flag), but no subflows is initiated ('subflow' flag) - Remove the MPTCP endpoint ---truncated---
CVE-2026-23324: In the Linux kernel, the following vulnerability has been resolved: can: usb: etas_es58x: correctly anchor the urb in the read bulk callback When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.
CVE-2026-23325: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7996: Fix possible oob access in mt7996_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.
CVE-2026-23327: In the Linux kernel, the following vulnerability has been resolved: cxl/mbox: validate payload size before accessing contents in cxl_payload_from_user_allowed() cxl_payload_from_user_allowed() casts and dereferences the input payload without first verifying its size. When a raw mailbox command is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG, which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer, triggering a KASAN splat: BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683 Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258 CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xab/0xe0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xce/0x650 mm/kasan/report.c:482 kasan_report+0xce/0x100 mm/kasan/report.c:595 memcmp+0x176/0x1d0 lib/string.c:683 uuid_equal include/linux/uuid.h:73 [inline] cxl_payload_from_user_allowed drivers/cxl/core/mbox.c:345 [inline] cxl_mbox_cmd_ctor drivers/cxl/core/mbox.c:368 [inline] cxl_validate_cmd_from_user drivers/cxl/core/mbox.c:522 [inline] cxl_send_cmd+0x9c0/0xb50 drivers/cxl/core/mbox.c:643 __cxl_memdev_ioctl drivers/cxl/core/memdev.c:698 [inline] cxl_memdev_ioctl+0x14f/0x190 drivers/cxl/core/memdev.c:713 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xa8/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fdaf331ba79 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fdaf1d77038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fdaf3585fa0 RCX: 00007fdaf331ba79 RDX: 00002000000001c0 RSI: 00000000c030ce02 RDI: 0000000000000003 RBP: 00007fdaf33749df R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fdaf3586038 R14: 00007fdaf3585fa0 R15: 00007ffced2af768 </TASK> Add 'in_size' parameter to cxl_payload_from_user_allowed() and validate the payload is large enough.
CVE-2026-23330: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: complete pending data exchange on device close In nci_close_device(), complete any pending data exchange before closing. The data exchange callback (e.g. rawsock_data_exchange_complete) holds a socket reference. NIPA occasionally hits this leak: unreferenced object 0xff1100000f435000 (size 2048): comm "nci_dev", pid 3954, jiffies 4295441245 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00 '..@............ backtrace (crc ec2b3c5): __kmalloc_noprof+0x4db/0x730 sk_prot_alloc.isra.0+0xe4/0x1d0 sk_alloc+0x36/0x760 rawsock_create+0xd1/0x540 nfc_sock_create+0x11f/0x280 __sock_create+0x22d/0x630 __sys_socket+0x115/0x1d0 __x64_sys_socket+0x72/0xd0 do_syscall_64+0x117/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53
CVE-2026-23334: In the Linux kernel, the following vulnerability has been resolved: can: usb: f81604: handle short interrupt urb messages properly If an interrupt urb is received that is not the correct length, properly detect it and don't attempt to treat the data as valid.
CVE-2026-23335: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah() struct irdma_create_ah_resp { // 8 bytes, no padding __u32 ah_id; // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx) __u8 rsvd[4]; // offset 4 - NEVER SET <- LEAK }; rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata(). The reserved members of the structure were not zeroed.
CVE-2026-23336: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel rfkill_block work in wiphy_unregister() There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller: BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220 Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326 CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: events cfg80211_rfkill_block_work Call Trace: <TASK> dump_stack_lvl+0x116/0x1f0 print_report+0xcd/0x630 kasan_report+0xe0/0x110 cfg80211_shutdown_all_interfaces+0x213/0x220 cfg80211_rfkill_block_work+0x1e/0x30 process_one_work+0x9cf/0x1b70 worker_thread+0x6c8/0xf10 kthread+0x3c5/0x780 ret_from_fork+0x56d/0x700 ret_from_fork_asm+0x1a/0x30 </TASK> The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2026-23339: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: free skb on nci_transceive early error paths nci_transceive() takes ownership of the skb passed by the caller, but the -EPROTO, -EINVAL, and -EBUSY error paths return without freeing it. Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes the nci/nci_dev selftest hits the error path occasionally in NIPA, and kmemleak detects leaks: unreferenced object 0xff11000015ce6a40 (size 640): comm "nci_dev", pid 3954, jiffies 4295441246 hex dump (first 32 bytes): 6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b kkkk.......kkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace (crc 7c40cc2a): kmem_cache_alloc_node_noprof+0x492/0x630 __alloc_skb+0x11e/0x5f0 alloc_skb_with_frags+0xc6/0x8f0 sock_alloc_send_pskb+0x326/0x3f0 nfc_alloc_send_skb+0x94/0x1d0 rawsock_sendmsg+0x162/0x4c0 do_syscall_64+0x117/0xfc0
CVE-2026-23340: In the Linux kernel, the following vulnerability has been resolved: net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs When shrinking the number of real tx queues, netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush qdiscs for queues which will no longer be used. qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with qdisc_lock(). However, for lockless qdiscs, the dequeue path is serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so qdisc_reset() can run concurrently with __qdisc_run() and free skbs while they are still being dequeued, leading to UAF. This can easily be reproduced on e.g. virtio-net by imposing heavy traffic while frequently changing the number of queue pairs: iperf3 -ub0 -c $peer -t 0 & while :; do ethtool -L eth0 combined 1 ethtool -L eth0 combined 2 done With KASAN enabled, this leads to reports like: BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760 ... Call Trace: <TASK> ... __qdisc_run+0x133f/0x1760 __dev_queue_xmit+0x248f/0x3550 ip_finish_output2+0xa42/0x2110 ip_output+0x1a7/0x410 ip_send_skb+0x2e6/0x480 udp_send_skb+0xb0a/0x1590 udp_sendmsg+0x13c9/0x1fc0 ... </TASK> Allocated by task 1270 on cpu 5 at 44.558414s: ... alloc_skb_with_frags+0x84/0x7c0 sock_alloc_send_pskb+0x69a/0x830 __ip_append_data+0x1b86/0x48c0 ip_make_skb+0x1e8/0x2b0 udp_sendmsg+0x13a6/0x1fc0 ... Freed by task 1306 on cpu 3 at 44.558445s: ... kmem_cache_free+0x117/0x5e0 pfifo_fast_reset+0x14d/0x580 qdisc_reset+0x9e/0x5f0 netif_set_real_num_tx_queues+0x303/0x840 virtnet_set_channels+0x1bf/0x260 [virtio_net] ethnl_set_channels+0x684/0xae0 ethnl_default_set_doit+0x31a/0x890 ... Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the serialization model already used by dev_reset_queue(). Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state reflects an empty queue, avoiding needless re-scheduling.
CVE-2026-23343: In the Linux kernel, the following vulnerability has been resolved: xdp: produce a warning when calculated tailroom is negative Many ethernet drivers report xdp Rx queue frag size as being the same as DMA write size. However, the only user of this field, namely bpf_xdp_frags_increase_tail(), clearly expects a truesize. Such difference leads to unspecific memory corruption issues under certain circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses all DMA-writable space in 2 buffers. This would be fine, if only rxq->frag_size was properly set to 4K, but value of 3K results in a negative tailroom, because there is a non-zero page offset. We are supposed to return -EINVAL and be done with it in such case, but due to tailroom being stored as an unsigned int, it is reported to be somewhere near UINT_MAX, resulting in a tail being grown, even if the requested offset is too much (it is around 2K in the abovementioned test). This later leads to all kinds of unspecific calltraces. [ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6 [ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4 [ 7340.338179] in libc.so.6[61c9d,7f4161aaf000+160000] [ 7340.339230] in xskxceiver[42b5,400000+69000] [ 7340.340300] likely on CPU 6 (core 0, socket 6) [ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe [ 7340.340888] likely on CPU 3 (core 0, socket 3) [ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7 [ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI [ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy) [ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014 [ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80 [ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89 [ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202 [ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010 [ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff [ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0 [ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0 [ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500 [ 7340.418229] FS: 0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000 [ 7340.419489] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0 [ 7340.421237] PKRU: 55555554 [ 7340.421623] Call Trace: [ 7340.421987] <TASK> [ 7340.422309] ? softleaf_from_pte+0x77/0xa0 [ 7340.422855] swap_pte_batch+0xa7/0x290 [ 7340.423363] zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270 [ 7340.424102] zap_pte_range+0x281/0x580 [ 7340.424607] zap_pmd_range.isra.0+0xc9/0x240 [ 7340.425177] unmap_page_range+0x24d/0x420 [ 7340.425714] unmap_vmas+0xa1/0x180 [ 7340.426185] exit_mmap+0xe1/0x3b0 [ 7340.426644] __mmput+0x41/0x150 [ 7340.427098] exit_mm+0xb1/0x110 [ 7340.427539] do_exit+0x1b2/0x460 [ 7340.427992] do_group_exit+0x2d/0xc0 [ 7340.428477] get_signal+0x79d/0x7e0 [ 7340.428957] arch_do_signal_or_restart+0x34/0x100 [ 7340.429571] exit_to_user_mode_loop+0x8e/0x4c0 [ 7340.430159] do_syscall_64+0x188/ ---truncated---
CVE-2026-23346: In the Linux kernel, the following vulnerability has been resolved: arm64: io: Extract user memory type in ioremap_prot() The only caller of ioremap_prot() outside of the generic ioremap() implementation is generic_access_phys(), which passes a 'pgprot_t' value determined from the user mapping of the target 'pfn' being accessed by the kernel. On arm64, the 'pgprot_t' contains all of the non-address bits from the pte, including the permission controls, and so we end up returning a new user mapping from ioremap_prot() which faults when accessed from the kernel on systems with PAN: | Unable to handle kernel read from unreadable memory at virtual address ffff80008ea89000 | ... | Call trace: | __memcpy_fromio+0x80/0xf8 | generic_access_phys+0x20c/0x2b8 | __access_remote_vm+0x46c/0x5b8 | access_remote_vm+0x18/0x30 | environ_read+0x238/0x3e8 | vfs_read+0xe4/0x2b0 | ksys_read+0xcc/0x178 | __arm64_sys_read+0x4c/0x68 Extract only the memory type from the user 'pgprot_t' in ioremap_prot() and assert that we're being passed a user mapping, to protect us against any changes in future that may require additional handling. To avoid falsely flagging users of ioremap(), provide our own ioremap() macro which simply wraps __ioremap_prot().
CVE-2026-23347: In the Linux kernel, the following vulnerability has been resolved: can: usb: f81604: correctly anchor the urb in the read bulk callback When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.
CVE-2026-23348: In the Linux kernel, the following vulnerability has been resolved: cxl: Fix race of nvdimm_bus object when creating nvdimm objects Found issue during running of cxl-translate.sh unit test. Adding a 3s sleep right before the test seems to make the issue reproduce fairly consistently. The cxl_translate module has dependency on cxl_acpi and causes orphaned nvdimm objects to reprobe after cxl_acpi is removed. The nvdimm_bus object is registered by the cxl_nvb object when cxl_acpi_probe() is called. With the nvdimm_bus object missing, __nd_device_register() will trigger NULL pointer dereference when accessing the dev->parent that points to &nvdimm_bus->dev. [ 192.884510] BUG: kernel NULL pointer dereference, address: 000000000000006c [ 192.895383] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20250812-19.fc42 08/12/2025 [ 192.897721] Workqueue: cxl_port cxl_bus_rescan_queue [cxl_core] [ 192.899459] RIP: 0010:kobject_get+0xc/0x90 [ 192.924871] Call Trace: [ 192.925959] <TASK> [ 192.926976] ? pm_runtime_init+0xb9/0xe0 [ 192.929712] __nd_device_register.part.0+0x4d/0xc0 [libnvdimm] [ 192.933314] __nvdimm_create+0x206/0x290 [libnvdimm] [ 192.936662] cxl_nvdimm_probe+0x119/0x1d0 [cxl_pmem] [ 192.940245] cxl_bus_probe+0x1a/0x60 [cxl_core] [ 192.943349] really_probe+0xde/0x380 This patch also relies on the previous change where devm_cxl_add_nvdimm_bridge() is called from drivers/cxl/pmem.c instead of drivers/cxl/core.c to ensure the dependency of cxl_acpi on cxl_pmem. 1. Set probe_type of cxl_nvb to PROBE_FORCE_SYNCHRONOUS to ensure the driver is probed synchronously when add_device() is called. 2. Add a check in __devm_cxl_add_nvdimm_bridge() to ensure that the cxl_nvb driver is attached during cxl_acpi_probe(). 3. Take the cxl_root uport_dev lock and the cxl_nvb->dev lock in devm_cxl_add_nvdimm() before checking nvdimm_bus is valid. 4. Set cxl_nvdimm flag to CXL_NVD_F_INVALIDATED so cxl_nvdimm_probe() will exit with -EBUSY. The removal of cxl_nvdimm devices should prevent any orphaned devices from probing once the nvdimm_bus is gone. [ dj: Fixed 0-day reported kdoc issue. ] [ dj: Fix cxl_nvb reference leak on error. Gregory (kreview-0811365) ]
CVE-2026-23351: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: split gc into unlink and reclaim phase Yiming Qian reports Use-after-free in the pipapo set type: Under a large number of expired elements, commit-time GC can run for a very long time in a non-preemptible context, triggering soft lockup warnings and RCU stall reports (local denial of service). We must split GC in an unlink and a reclaim phase. We cannot queue elements for freeing until pointers have been swapped. Expired elements are still exposed to both the packet path and userspace dumpers via the live copy of the data structure. call_rcu() does not protect us: dump operations or element lookups starting after call_rcu has fired can still observe the free'd element, unless the commit phase has made enough progress to swap the clone and live pointers before any new reader has picked up the old version. This a similar approach as done recently for the rbtree backend in commit 35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").
CVE-2026-23352: In the Linux kernel, the following vulnerability has been resolved: x86/efi: defer freeing of boot services memory efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late(). There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area(). More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete. Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM. If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages. Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map. Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency. More robust approach is to only defer freeing of the EFI boot services memory. Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.
CVE-2026-23354: In the Linux kernel, the following vulnerability has been resolved: x86/fred: Correct speculative safety in fred_extint() array_index_nospec() is no use if the result gets spilled to the stack, as it makes the believed safe-under-speculation value subject to memory predictions. For all practical purposes, this means array_index_nospec() must be used in the expression that accesses the array. As the code currently stands, it's the wrong side of irqentry_enter(), and 'index' is put into %ebp across the function call. Remove the index variable and reposition array_index_nospec(), so it's calculated immediately before the array access.
CVE-2026-23356: In the Linux kernel, the following vulnerability has been resolved: drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock() Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing. If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error. The rest of the code now assumed that this request has references for the relevant activity log extents. The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case. Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put(). Fix: Do not crash the kernel for a condition that is harmless during normal operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n". And do not try to be smart and "guess" whether something will work, then be surprised when it does not. Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock(). A latter call for the same request will then resume from where we left off.
CVE-2026-23357: In the Linux kernel, the following vulnerability has been resolved: can: mcp251x: fix deadlock in error path of mcp251x_open The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish. This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can: mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path. To solve this issue move the call to free_irq() after the lock is released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ handler will exit right away once it acquired the lock.
CVE-2026-23359: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix stack-out-of-bounds write in devmap get_upper_ifindexes() iterates over all upper devices and writes their indices into an array without checking bounds. Also the callers assume that the max number of upper devices is MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack, but that assumption is not correct and the number of upper devices could be larger than MAX_NEST_DEV (e.g., many macvlans), causing a stack-out-of-bounds write. Add a max parameter to get_upper_ifindexes() to avoid the issue. When there are too many upper devices, return -EOVERFLOW and abort the redirect. To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS. Then send a packet to the device to trigger the XDP redirect path.
CVE-2026-23360: In the Linux kernel, the following vulnerability has been resolved: nvme: fix admin queue leak on controller reset When nvme_alloc_admin_tag_set() is called during a controller reset, a previous admin queue may still exist. Release it properly before allocating a new one to avoid orphaning the old queue. This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").
CVE-2026-23361: In the Linux kernel, the following vulnerability has been resolved: PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X interrupt to the host using a writel(), which generates a PCI posted write transaction. There's no completion for posted writes, so the writel() may return before the PCI write completes. dw_pcie_ep_raise_msix_irq() also unmaps the outbound ATU entry used for the PCI write, so the write races with the unmap. If the PCI write loses the race with the ATU unmap, the write may corrupt host memory or cause IOMMU errors, e.g., these when running fio with a larger queue depth against nvmet-pci-epf: arm-smmu-v3 fc900000.iommu: 0x0000010000000010 arm-smmu-v3 fc900000.iommu: 0x0000020000000000 arm-smmu-v3 fc900000.iommu: 0x000000090000f040 arm-smmu-v3 fc900000.iommu: 0x0000000000000000 arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0 arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0 Flush the write by performing a readl() of the same address to ensure that the write has reached the destination before the ATU entry is unmapped. The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there it was solved by dedicating an outbound iATU only for MSI. We can't do the same for MSI-X because each vector can have a different msg_addr and the msg_addr may be changed while the vector is masked. [bhelgaas: commit log]
CVE-2026-23362: In the Linux kernel, the following vulnerability has been resolved: can: bcm: fix locking for bcm_op runtime updates Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup(). Usually the RX_SETUP only handles and filters incoming traffic with one exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.
CVE-2026-23363: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7925: Fix possible oob access in mt7925_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.
CVE-2026-23364: In the Linux kernel, the following vulnerability has been resolved: ksmbd: Compare MACs in constant time To prevent timing attacks, MAC comparisons need to be constant-time. Replace the memcmp() with the correct function, crypto_memneq().
CVE-2026-23365: In the Linux kernel, the following vulnerability has been resolved: net: usb: kalmia: validate USB endpoints The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23367: In the Linux kernel, the following vulnerability has been resolved: wifi: radiotap: reject radiotap with unknown bits The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value. Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.
CVE-2026-23368: In the Linux kernel, the following vulnerability has been resolved: net: phy: register phy led_triggers during probe to avoid AB-BA deadlock There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and LED_TRIGGER_PHY are enabled: [ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock); [ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234 [ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c [ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c [ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0 [ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0 [ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c [ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78 [ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654 <-- Hold lock "rtnl_mutex" by calling rtnl_lock(); [ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0 [ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c [ 1362.104022] [<80014504>] syscall_common+0x34/0x58 Here LED_TRIGGER_PHY is registering LED triggers during phy_attach while holding RTNL and then taking triggers_list_lock. [ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168 <-- Trying to get lock "rtnl_mutex" via rtnl_lock(); [ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4 [ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock); [ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c [ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc [ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c [ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4 [ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c [ 1362.232164] [<80014504>] syscall_common+0x34/0x58 Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes triggers_list_lock and then RTNL. A classical AB-BA deadlock. phy_led_triggers_registers() does not require the RTNL, it does not make any calls into the network stack which require protection. There is also no requirement the PHY has been attached to a MAC, the triggers only make use of phydev state. This allows the call to phy_led_triggers_registers() to be placed elsewhere. PHY probe() and release() don't hold RTNL, so solving the AB-BA deadlock.
CVE-2026-23369: In the Linux kernel, the following vulnerability has been resolved: i2c: i801: Revert "i2c: i801: replace acpi_lock with I2C bus lock" This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1. Under rare circumstances, multiple udev threads can collect i801 device info on boot and walk i801_acpi_io_handler somewhat concurrently. The first will note the area is reserved by acpi to prevent further touches. This ultimately causes the area to be deregistered. The second will enter i801_acpi_io_handler after the area is unregistered but before a check can be made that the area is unregistered. i2c_lock_bus relies on the now unregistered area containing lock_ops to lock the bus. The end result is a kernel panic on boot with the following backtrace; [ 14.971872] ioatdma 0000:09:00.2: enabling device (0100 -> 0102) [ 14.971873] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 14.971880] #PF: supervisor read access in kernel mode [ 14.971884] #PF: error_code(0x0000) - not-present page [ 14.971887] PGD 0 P4D 0 [ 14.971894] Oops: 0000 [#1] PREEMPT SMP PTI [ 14.971900] CPU: 5 PID: 956 Comm: systemd-udevd Not tainted 5.14.0-611.5.1.el9_7.x86_64 #1 [ 14.971905] Hardware name: XXXXXXXXXXXXXXXXXXXXXXX BIOS 1.20.10.SV91 01/30/2023 [ 14.971908] RIP: 0010:i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.971929] Code: 00 00 49 8b 40 20 41 57 41 56 4d 8b b8 30 04 00 00 49 89 ce 41 55 41 89 d5 41 54 49 89 f4 be 02 00 00 00 55 4c 89 c5 53 89 fb <48> 8b 00 4c 89 c7 e8 18 61 54 e9 80 bd 80 04 00 00 00 75 09 4c 3b [ 14.971933] RSP: 0018:ffffbaa841483838 EFLAGS: 00010282 [ 14.971938] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9685e01ba568 [ 14.971941] RDX: 0000000000000008 RSI: 0000000000000002 RDI: 0000000000000000 [ 14.971944] RBP: ffff9685ca22f028 R08: ffff9685ca22f028 R09: ffff9685ca22f028 [ 14.971948] R10: 000000000000000b R11: 0000000000000580 R12: 0000000000000580 [ 14.971951] R13: 0000000000000008 R14: ffff9685e01ba568 R15: ffff9685c222f000 [ 14.971954] FS: 00007f8287c0ab40(0000) GS:ffff96a47f940000(0000) knlGS:0000000000000000 [ 14.971959] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 14.971963] CR2: 0000000000000000 CR3: 0000000168090001 CR4: 00000000003706f0 [ 14.971966] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 14.971968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 14.971972] Call Trace: [ 14.971977] <TASK> [ 14.971981] ? show_trace_log_lvl+0x1c4/0x2df [ 14.971994] ? show_trace_log_lvl+0x1c4/0x2df [ 14.972003] ? acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972014] ? __die_body.cold+0x8/0xd [ 14.972021] ? page_fault_oops+0x132/0x170 [ 14.972028] ? exc_page_fault+0x61/0x150 [ 14.972036] ? asm_exc_page_fault+0x22/0x30 [ 14.972045] ? i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.972061] acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972069] ? __pfx_i801_acpi_io_handler+0x10/0x10 [i2c_i801] [ 14.972085] acpi_ex_access_region+0x5b/0xd0 [ 14.972093] acpi_ex_field_datum_io+0x73/0x2e0 [ 14.972100] acpi_ex_read_data_from_field+0x8e/0x230 [ 14.972106] acpi_ex_resolve_node_to_value+0x23d/0x310 [ 14.972114] acpi_ds_evaluate_name_path+0xad/0x110 [ 14.972121] acpi_ds_exec_end_op+0x321/0x510 [ 14.972127] acpi_ps_parse_loop+0xf7/0x680 [ 14.972136] acpi_ps_parse_aml+0x17a/0x3d0 [ 14.972143] acpi_ps_execute_method+0x137/0x270 [ 14.972150] acpi_ns_evaluate+0x1f4/0x2e0 [ 14.972158] acpi_evaluate_object+0x134/0x2f0 [ 14.972164] acpi_evaluate_integer+0x50/0xe0 [ 14.972173] ? vsnprintf+0x24b/0x570 [ 14.972181] acpi_ac_get_state.part.0+0x23/0x70 [ 14.972189] get_ac_property+0x4e/0x60 [ 14.972195] power_supply_show_property+0x90/0x1f0 [ 14.972205] add_prop_uevent+0x29/0x90 [ 14.972213] power_supply_uevent+0x109/0x1d0 [ 14.972222] dev_uevent+0x10e/0x2f0 [ 14.972228] uevent_show+0x8e/0x100 [ 14.972236] dev_attr_show+0x19 ---truncated---
CVE-2026-23370: In the Linux kernel, the following vulnerability has been resolved: platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data set_new_password() hex dumps the entire buffer, which contains plaintext password data, including current and new passwords. Remove the hex dump to avoid leaking credentials.
CVE-2026-23371: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting Running stress-ng --schedpolicy 0 on an RT kernel on a big machine might lead to the following WARNINGs (edited). sched: DL de-boosted task PID 22725: REPLENISH flag missing WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8 ... (running_bw underflow) Call trace: dequeue_task_dl+0x15c/0x1f8 (P) dequeue_task+0x80/0x168 deactivate_task+0x24/0x50 push_dl_task+0x264/0x2e0 dl_task_timer+0x1b0/0x228 __hrtimer_run_queues+0x188/0x378 hrtimer_interrupt+0xfc/0x260 ... The problem is that when a SCHED_DEADLINE task (lock holder) is changed to a lower priority class via sched_setscheduler(), it may fail to properly inherit the parameters of potential DEADLINE donors if it didn't already inherit them in the past (shorter deadline than donor's at that time). This might lead to bandwidth accounting corruption, as enqueue_task_dl() won't recognize the lock holder as boosted. The scenario occurs when: 1. A DEADLINE task (donor) blocks on a PI mutex held by another DEADLINE task (holder), but the holder doesn't inherit parameters (e.g., it already has a shorter deadline) 2. sched_setscheduler() changes the holder from DEADLINE to a lower class while still holding the mutex 3. The holder should now inherit DEADLINE parameters from the donor and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen Fix the issue by introducing __setscheduler_dl_pi(), which detects when a DEADLINE (proper or boosted) task gets setscheduled to a lower priority class. In case, the function makes the task inherit DEADLINE parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to ensure proper bandwidth accounting during the next enqueue operation.
CVE-2026-23372: In the Linux kernel, the following vulnerability has been resolved: nfc: rawsock: cancel tx_work before socket teardown In rawsock_release(), cancel any pending tx_work and purge the write queue before orphaning the socket. rawsock_tx_work runs on the system workqueue and calls nfc_data_exchange which dereferences the NCI device. Without synchronization, tx_work can race with socket and device teardown when a process is killed (e.g. by SIGKILL), leading to use-after-free or leaked references. Set SEND_SHUTDOWN first so that if tx_work is already running it will see the flag and skip transmitting, then use cancel_work_sync to wait for any in-progress execution to finish, and finally purge any remaining queued skbs.
CVE-2026-23373: In the Linux kernel, the following vulnerability has been resolved: wifi: rsi: Don't default to -EOPNOTSUPP in rsi_mac80211_config This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected behavior from the driver - other drivers default to 0 too.
CVE-2026-23374: In the Linux kernel, the following vulnerability has been resolved: blktrace: fix __this_cpu_read/write in preemptible context tracing_record_cmdline() internally uses __this_cpu_read() and __this_cpu_write() on the per-CPU variable trace_cmdline_save, and trace_save_cmdline() explicitly asserts preemption is disabled via lockdep_assert_preemption_disabled(). These operations are only safe when preemption is off, as they were designed to be called from the scheduler context (probe_wakeup_sched_switch() / probe_wakeup()). __blk_add_trace() was calling tracing_record_cmdline(current) early in the blk_tracer path, before ring buffer reservation, from process context where preemption is fully enabled. This triggers the following using blktests/blktrace/002: blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed] runtime 0.367s ... 0.437s something found in dmesg: [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 ... (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message) [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 [ 81.362895] check_preemption_disabled+0xce/0xe0 [ 81.362902] tracing_record_cmdline+0x10/0x40 [ 81.362923] __blk_add_trace+0x307/0x5d0 [ 81.362934] ? lock_acquire+0xe0/0x300 [ 81.362940] ? iov_iter_extract_pages+0x101/0xa30 [ 81.362959] blk_add_trace_bio+0x106/0x1e0 [ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0 [ 81.362979] ? lockdep_init_map_type+0x58/0x260 [ 81.362988] submit_bio_wait+0x56/0x90 [ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250 [ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10 [ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0 [ 81.363051] blkdev_read_iter+0xc1/0x140 [ 81.363059] vfs_read+0x20b/0x330 [ 81.363083] ksys_read+0x67/0xe0 [ 81.363090] do_syscall_64+0xbf/0xf00 [ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 81.363106] RIP: 0033:0x7f281906029d [ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec [ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d [ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000 [ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000 [ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000 [ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a [ 81.363142] </TASK> The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(), and blk_add_trace_rq() paths as well. The purpose of tracin ---truncated---
CVE-2026-23375: In the Linux kernel, the following vulnerability has been resolved: mm: thp: deny THP for files on anonymous inodes file_thp_enabled() incorrectly allows THP for files on anonymous inodes (e.g. guest_memfd and secretmem). These files are created via alloc_file_pseudo(), which does not call get_write_access() and leaves inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being true, they appear as read-only regular files when CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP collapse. Anonymous inodes can never pass the inode_is_open_for_write() check since their i_writecount is never incremented through the normal VFS open path. The right thing to do is to exclude them from THP eligibility altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real filesystem files (e.g. shared libraries), not for pseudo-filesystem inodes. For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create large folios in the page cache via the collapse path, but the guest_memfd fault handler does not support large folios. This triggers WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping(). For secretmem, collapse_file() tries to copy page contents through the direct map, but secretmem pages are removed from the direct map. This can result in a kernel crash: BUG: unable to handle page fault for address: ffff88810284d000 RIP: 0010:memcpy_orig+0x16/0x130 Call Trace: collapse_file hpage_collapse_scan_file madvise_collapse Secretmem is not affected by the crash on upstream as the memory failure recovery handles the failed copy gracefully, but it still triggers confusing false memory failure reports: Memory failure: 0x106d96f: recovery action for clean unevictable LRU page: Recovered Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all anonymous inode files.
CVE-2026-23377: In the Linux kernel, the following vulnerability has been resolved: ice: change XDP RxQ frag_size from DMA write length to xdp.frame_sz The only user of frag_size field in XDP RxQ info is bpf_xdp_frags_increase_tail(). It clearly expects whole buff size instead of DMA write size. Different assumptions in ice driver configuration lead to negative tailroom. This allows to trigger kernel panic, when using XDP_ADJUST_TAIL_GROW_MULTI_BUFF xskxceiver test and changing packet size to 6912 and the requested offset to a huge value, e.g. XSK_UMEM__MAX_FRAME_SIZE * 100. Due to other quirks of the ZC configuration in ice, panic is not observed in ZC mode, but tailroom growing still fails when it should not. Use fill queue buffer truesize instead of DMA write size in XDP RxQ info. Fix ZC mode too by using the new helper.
CVE-2026-23378: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ife: Fix metalist update behavior Whenever an ife action replace changes the metalist, instead of replacing the old data on the metalist, the current ife code is appending the new metadata. Aside from being innapropriate behavior, this may lead to an unbounded addition of metadata to the metalist which might cause an out of bounds error when running the encode op: [ 138.423369][ C1] ================================================================== [ 138.424317][ C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.424906][ C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255 [ 138.425778][ C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full) [ 138.425795][ C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 138.425800][ C1] Call Trace: [ 138.425804][ C1] <IRQ> [ 138.425808][ C1] dump_stack_lvl (lib/dump_stack.c:122) [ 138.425828][ C1] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 138.425839][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425844][ C1] ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1)) [ 138.425853][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425859][ C1] kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597) [ 138.425868][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425878][ C1] kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1)) [ 138.425884][ C1] __asan_memset (mm/kasan/shadow.c:84 (discriminator 2)) [ 138.425889][ C1] ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425893][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:171) [ 138.425898][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425903][ C1] ife_encode_meta_u16 (net/sched/act_ife.c:57) [ 138.425910][ C1] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114) [ 138.425916][ C1] ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3)) [ 138.425921][ C1] ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45) [ 138.425927][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425931][ C1] tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879) To solve this issue, fix the replace behavior by adding the metalist to the ife rcu data structure.
CVE-2026-23379: In the Linux kernel, the following vulnerability has been resolved: net/sched: ets: fix divide by zero in the offload path Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat: Oops: divide error: 0000 [#1] SMP PTI CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full) Tainted: [E]=UNSIGNED_MODULE Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Call Trace: <TASK> ets_qdisc_change+0x870/0xf40 [sch_ets] qdisc_create+0x12b/0x540 tc_modify_qdisc+0x6d7/0xbd0 rtnetlink_rcv_msg+0x168/0x6b0 netlink_rcv_skb+0x5c/0x110 netlink_unicast+0x1d6/0x2b0 netlink_sendmsg+0x22e/0x470 ____sys_sendmsg+0x38a/0x3c0 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x111/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f440b81c77e Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980 </TASK> Modules linked in: sch_ets(E) netdevsim(E) ---[ end trace 0000000000000000 ]--- RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- Fix this using 64-bit integers for 'q_sum' and 'q_psum'.
CVE-2026-23380: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix WARN_ON in tracing_buffers_mmap_close When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON. Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork. Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback.
CVE-2026-23381: In the Linux kernel, the following vulnerability has been resolved: net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. Then, if neigh_suppress is enabled and an ICMPv6 Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will dereference ipv6_stub->nd_tbl which is NULL, passing it to neigh_lookup(). This causes a kernel NULL pointer dereference. BUG: kernel NULL pointer dereference, address: 0000000000000268 Oops: 0000 [#1] PREEMPT SMP NOPTI [...] RIP: 0010:neigh_lookup+0x16/0xe0 [...] Call Trace: <IRQ> ? neigh_lookup+0x16/0xe0 br_do_suppress_nd+0x160/0x290 [bridge] br_handle_frame_finish+0x500/0x620 [bridge] br_handle_frame+0x353/0x440 [bridge] __netif_receive_skb_core.constprop.0+0x298/0x1110 __netif_receive_skb_one_core+0x3d/0xa0 process_backlog+0xa0/0x140 __napi_poll+0x2c/0x170 net_rx_action+0x2c4/0x3a0 handle_softirqs+0xd0/0x270 do_softirq+0x3f/0x60 Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in the callers. This is in essence disabling NS/NA suppression when IPv6 is disabled.
CVE-2026-23382: In the Linux kernel, the following vulnerability has been resolved: HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system. Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.
CVE-2026-23383: In the Linux kernel, the following vulnerability has been resolved: bpf, arm64: Force 8-byte alignment for JIT buffer to prevent atomic tearing struct bpf_plt contains a u64 target field. Currently, the BPF JIT allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT buffer. Because the base address of the JIT buffer can be 4-byte aligned (e.g., ending in 0x4 or 0xc), the relative padding logic in build_plt() fails to ensure that target lands on an 8-byte boundary. This leads to two issues: 1. UBSAN reports misaligned-access warnings when dereferencing the structure. 2. More critically, target is updated concurrently via WRITE_ONCE() in bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64, 64-bit loads/stores are only guaranteed to be single-copy atomic if they are 64-bit aligned. A misaligned target risks a torn read, causing the JIT to jump to a corrupted address. Fix this by increasing the allocation alignment requirement to 8 bytes (sizeof(u64)) in bpf_jit_binary_pack_alloc(). This anchors the base of the JIT buffer to an 8-byte boundary, allowing the relative padding math in build_plt() to correctly align the target field.
CVE-2026-23385: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: clone set on flush only Syzbot with fault injection triggered a failing memory allocation with GFP_KERNEL which results in a WARN splat: iter.err WARNING: net/netfilter/nf_tables_api.c:845 at nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845, CPU#0: syz.0.17/5992 Modules linked in: CPU: 0 UID: 0 PID: 5992 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026 RIP: 0010:nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845 Code: 8b 05 86 5a 4e 09 48 3b 84 24 a0 00 00 00 75 62 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc e8 63 6d fa f7 90 <0f> 0b 90 43 +80 7c 35 00 00 0f 85 23 fe ff ff e9 26 fe ff ff 89 d9 RSP: 0018:ffffc900045af780 EFLAGS: 00010293 RAX: ffffffff89ca45bd RBX: 00000000fffffff4 RCX: ffff888028111e40 RDX: 0000000000000000 RSI: 00000000fffffff4 RDI: 0000000000000000 RBP: ffffc900045af870 R08: 0000000000400dc0 R09: 00000000ffffffff R10: dffffc0000000000 R11: fffffbfff1d141db R12: ffffc900045af7e0 R13: 1ffff920008b5f24 R14: dffffc0000000000 R15: ffffc900045af920 FS: 000055557a6a5500(0000) GS:ffff888125496000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fb5ea271fc0 CR3: 000000003269e000 CR4: 00000000003526f0 Call Trace: <TASK> __nft_release_table+0xceb/0x11f0 net/netfilter/nf_tables_api.c:12115 nft_rcv_nl_event+0xc25/0xdb0 net/netfilter/nf_tables_api.c:12187 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85 blocking_notifier_call_chain+0x6a/0x90 kernel/notifier.c:380 netlink_release+0x123b/0x1ad0 net/netlink/af_netlink.c:761 __sock_release net/socket.c:662 [inline] sock_close+0xc3/0x240 net/socket.c:1455 Restrict set clone to the flush set command in the preparation phase. Add NFT_ITER_UPDATE_CLONE and use it for this purpose, update the rbtree and pipapo backends to only clone the set when this iteration type is used. As for the existing NFT_ITER_UPDATE type, update the pipapo backend to use the existing set clone if available, otherwise use the existing set representation. After this update, there is no need to clone a set that is being deleted, this includes bound anonymous set. An alternative approach to NFT_ITER_UPDATE_CLONE is to add a .clone interface and call it from the flush set path.
CVE-2026-23386: In the Linux kernel, the following vulnerability has been resolved: gve: fix incorrect buffer cleanup in gve_tx_clean_pending_packets for QPL In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA buffer cleanup path. It iterates num_bufs times and attempts to unmap entries in the dma array. This leads to two issues: 1. The dma array shares storage with tx_qpl_buf_ids (union). Interpreting buffer IDs as DMA addresses results in attempting to unmap incorrect memory locations. 2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed the size of the dma array, causing out-of-bounds access warnings (trace below is how we noticed this issue). UBSAN: array-index-out-of-bounds in drivers/net/ethernet/drivers/net/ethernet/google/gve/gve_tx_dqo.c:178:5 index 18 is out of range for type 'dma_addr_t[18]' (aka 'unsigned long long[18]') Workqueue: gve gve_service_task [gve] Call Trace: <TASK> dump_stack_lvl+0x33/0xa0 __ubsan_handle_out_of_bounds+0xdc/0x110 gve_tx_stop_ring_dqo+0x182/0x200 [gve] gve_close+0x1be/0x450 [gve] gve_reset+0x99/0x120 [gve] gve_service_task+0x61/0x100 [gve] process_scheduled_works+0x1e9/0x380 Fix this by properly checking for QPL mode and delegating to gve_free_tx_qpl_bufs() to reclaim the buffers.
CVE-2026-23387: In the Linux kernel, the following vulnerability has been resolved: pinctrl: cirrus: cs42l43: Fix double-put in cs42l43_pin_probe() devm_add_action_or_reset() already invokes the action on failure, so the explicit put causes a double-put.
CVE-2026-23388: In the Linux kernel, the following vulnerability has been resolved: Squashfs: check metadata block offset is within range Syzkaller reports a "general protection fault in squashfs_copy_data" This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset. This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access. The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.
CVE-2026-23389: In the Linux kernel, the following vulnerability has been resolved: ice: Fix memory leak in ice_set_ringparam() In ice_set_ringparam, tx_rings and xdp_rings are allocated before rx_rings. If the allocation of rx_rings fails, the code jumps to the done label leaking both tx_rings and xdp_rings. Furthermore, if the setup of an individual Rx ring fails during the loop, the code jumps to the free_tx label which releases tx_rings but leaks xdp_rings. Fix this by introducing a free_xdp label and updating the error paths to ensure both xdp_rings and tx_rings are properly freed if rx_rings allocation or setup fails. Compile tested only. Issue found using a prototype static analysis tool and code review.
CVE-2026-23391: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_CT: drop pending enqueued packets on template removal Templates refer to objects that can go away while packets are sitting in nfqueue refer to: - helper, this can be an issue on module removal. - timeout policy, nfnetlink_cttimeout might remove it. The use of templates with zone and event cache filter are safe, since this just copies values. Flush these enqueued packets in case the template rule gets removed.
CVE-2026-23392: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: release flowtable after rcu grace period on error Call synchronize_rcu() after unregistering the hooks from error path, since a hook that already refers to this flowtable can be already registered, exposing this flowtable to packet path and nfnetlink_hook control plane. This error path is rare, it should only happen by reaching the maximum number hooks or by failing to set up to hardware offload, just call synchronize_rcu(). There is a check for already used device hooks by different flowtable that could result in EEXIST at this late stage. The hook parser can be updated to perform this check earlier to this error path really becomes rarely exercised. Uncovered by KASAN reported as use-after-free from nfnetlink_hook path when dumping hooks.
CVE-2026-23393: In the Linux kernel, the following vulnerability has been resolved: bridge: cfm: Fix race condition in peer_mep deletion When a peer MEP is being deleted, cancel_delayed_work_sync() is called on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in softirq context under rcu_read_lock (without RTNL) and can re-schedule ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync() returning and kfree_rcu() being called. The following is a simple race scenario: cpu0 cpu1 mep_delete_implementation() cancel_delayed_work_sync(ccm_rx_dwork); br_cfm_frame_rx() // peer_mep still in hlist if (peer_mep->ccm_defect) ccm_rx_timer_start() queue_delayed_work(ccm_rx_dwork) hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); ccm_rx_work_expired() // on freed peer_mep To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync() in both peer MEP deletion paths, so that subsequent queue_delayed_work() calls from br_cfm_frame_rx() are silently rejected. The cc_peer_disable() helper retains cancel_delayed_work_sync() because it is also used for the CC enable/disable toggle path where the work must remain re-schedulable.
CVE-2026-23394: In the Linux kernel, the following vulnerability has been resolved: af_unix: Give up GC if MSG_PEEK intervened. Igor Ushakov reported that GC purged the receive queue of an alive socket due to a race with MSG_PEEK with a nice repro. This is the exact same issue previously fixed by commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK"). After GC was replaced with the current algorithm, the cited commit removed the locking dance in unix_peek_fds() and reintroduced the same issue. The problem is that MSG_PEEK bumps a file refcount without interacting with GC. Consider an SCC containing sk-A and sk-B, where sk-A is close()d but can be recv()ed via sk-B. The bad thing happens if sk-A is recv()ed with MSG_PEEK from sk-B and sk-B is close()d while GC is checking unix_vertex_dead() for sk-A and sk-B. GC thread User thread --------- ----------- unix_vertex_dead(sk-A) -> true <------. \ `------ recv(sk-B, MSG_PEEK) invalidate !! -> sk-A's file refcount : 1 -> 2 close(sk-B) -> sk-B's file refcount : 2 -> 1 unix_vertex_dead(sk-B) -> true Initially, sk-A's file refcount is 1 by the inflight fd in sk-B recvq. GC thinks sk-A is dead because the file refcount is the same as the number of its inflight fds. However, sk-A's file refcount is bumped silently by MSG_PEEK, which invalidates the previous evaluation. At this moment, sk-B's file refcount is 2; one by the open fd, and one by the inflight fd in sk-A. The subsequent close() releases one refcount by the former. Finally, GC incorrectly concludes that both sk-A and sk-B are dead. One option is to restore the locking dance in unix_peek_fds(), but we can resolve this more elegantly thanks to the new algorithm. The point is that the issue does not occur without the subsequent close() and we actually do not need to synchronise MSG_PEEK with the dead SCC detection. When the issue occurs, close() and GC touch the same file refcount. If GC sees the refcount being decremented by close(), it can just give up garbage-collecting the SCC. Therefore, we only need to signal the race during MSG_PEEK with a proper memory barrier to make it visible to the GC. Let's use seqcount_t to notify GC when MSG_PEEK occurs and let it defer the SCC to the next run. This way no locking is needed on the MSG_PEEK side, and we can avoid imposing a penalty on every MSG_PEEK unnecessarily. Note that we can retry within unix_scc_dead() if MSG_PEEK is detected, but we do not do so to avoid hung task splat from abusive MSG_PEEK calls.
CVE-2026-23395: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ Currently the code attempts to accept requests regardless of the command identifier which may cause multiple requests to be marked as pending (FLAG_DEFER_SETUP) which can cause more than L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer causing an overflow. The spec is quite clear that the same identifier shall not be used on subsequent requests: 'Within each signaling channel a different Identifier shall be used for each successive request or indication.' https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-adaptation-protocol-specification.html#UUID-32a25a06-4aa4-c6c7-77c5-dcfe3682355d So this attempts to check if there are any channels pending with the same identifier and rejects if any are found.
CVE-2026-23396: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL deref in mesh_matches_local() mesh_matches_local() unconditionally dereferences ie->mesh_config to compare mesh configuration parameters. When called from mesh_rx_csa_frame(), the parsed action-frame elements may not contain a Mesh Configuration IE, leaving ie->mesh_config NULL and triggering a kernel NULL pointer dereference. The other two callers are already safe: - ieee80211_mesh_rx_bcn_presp() checks !elems->mesh_config before calling mesh_matches_local() - mesh_plink_get_event() is only reached through mesh_process_plink_frame(), which checks !elems->mesh_config, too mesh_rx_csa_frame() is the only caller that passes raw parsed elements to mesh_matches_local() without guarding mesh_config. An adjacent attacker can exploit this by sending a crafted CSA action frame that includes a valid Mesh ID IE but omits the Mesh Configuration IE, crashing the kernel. The captured crash log: Oops: general protection fault, probably for non-canonical address ... KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Workqueue: events_unbound cfg80211_wiphy_work [...] Call Trace: <TASK> ? __pfx_mesh_matches_local (net/mac80211/mesh.c:65) ieee80211_mesh_rx_queued_mgmt (net/mac80211/mesh.c:1686) [...] ieee80211_iface_work (net/mac80211/iface.c:1754 net/mac80211/iface.c:1802) [...] cfg80211_wiphy_work (net/wireless/core.c:426) process_one_work (net/kernel/workqueue.c:3280) ? assign_work (net/kernel/workqueue.c:1219) worker_thread (net/kernel/workqueue.c:3352) ? __pfx_worker_thread (net/kernel/workqueue.c:3385) kthread (net/kernel/kthread.c:436) [...] ret_from_fork_asm (net/arch/x86/entry/entry_64.S:255) </TASK> This patch adds a NULL check for ie->mesh_config at the top of mesh_matches_local() to return false early when the Mesh Configuration IE is absent.
CVE-2026-23397: In the Linux kernel, the following vulnerability has been resolved: nfnetlink_osf: validate individual option lengths in fingerprints nfnl_osf_add_callback() validates opt_num bounds and string NUL-termination but does not check individual option length fields. A zero-length option causes nf_osf_match_one() to enter the option matching loop even when foptsize sums to zero, which matches packets with no TCP options where ctx->optp is NULL: Oops: general protection fault KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:227) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:293) nf_hook_slow (net/netfilter/core.c:623) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) Additionally, an MSS option (kind=2) with length < 4 causes out-of-bounds reads when nf_osf_match_one() unconditionally accesses optp[2] and optp[3] for MSS value extraction. While RFC 9293 section 3.2 specifies that the MSS option is always exactly 4 bytes (Kind=2, Length=4), the check uses "< 4" rather than "!= 4" because lengths greater than 4 do not cause memory safety issues -- the buffer is guaranteed to be at least foptsize bytes by the ctx->optsize == foptsize check. Reject fingerprints where any option has zero length, or where an MSS option has length less than 4, at add time rather than trusting these values in the packet matching hot path.
CVE-2026-23398: In the Linux kernel, the following vulnerability has been resolved: icmp: fix NULL pointer dereference in icmp_tag_validation() icmp_tag_validation() unconditionally dereferences the result of rcu_dereference(inet_protos[proto]) without checking for NULL. The inet_protos[] array is sparse -- only about 15 of 256 protocol numbers have registered handlers. When ip_no_pmtu_disc is set to 3 (hardened PMTU mode) and the kernel receives an ICMP Fragmentation Needed error with a quoted inner IP header containing an unregistered protocol number, the NULL dereference causes a kernel panic in softirq context. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:icmp_unreach (net/ipv4/icmp.c:1085 net/ipv4/icmp.c:1143) Call Trace: <IRQ> icmp_rcv (net/ipv4/icmp.c:1527) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207) ip_local_deliver_finish (net/ipv4/ip_input.c:242) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) __netif_receive_skb_one_core (net/core/dev.c:6164) process_backlog (net/core/dev.c:6628) handle_softirqs (kernel/softirq.c:561) </IRQ> Add a NULL check before accessing icmp_strict_tag_validation. If the protocol has no registered handler, return false since it cannot perform strict tag validation.
CVE-2026-23399: In the Linux kernel, the following vulnerability has been resolved: nf_tables: nft_dynset: fix possible stateful expression memleak in error path If cloning the second stateful expression in the element via GFP_ATOMIC fails, then the first stateful expression remains in place without being released. unreferenced object (percpu) 0x607b97e9cab8 (size 16): comm "softirq", pid 0, jiffies 4294931867 hex dump (first 16 bytes on cpu 3): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 backtrace (crc 0): pcpu_alloc_noprof+0x453/0xd80 nft_counter_clone+0x9c/0x190 [nf_tables] nft_expr_clone+0x8f/0x1b0 [nf_tables] nft_dynset_new+0x2cb/0x5f0 [nf_tables] nft_rhash_update+0x236/0x11c0 [nf_tables] nft_dynset_eval+0x11f/0x670 [nf_tables] nft_do_chain+0x253/0x1700 [nf_tables] nft_do_chain_ipv4+0x18d/0x270 [nf_tables] nf_hook_slow+0xaa/0x1e0 ip_local_deliver+0x209/0x330
CVE-2026-23401: In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE When installing an emulated MMIO SPTE, do so *after* dropping/zapping the existing SPTE (if it's shadow-present). While commit a54aa15c6bda3 was right about it being impossible to convert a shadow-present SPTE to an MMIO SPTE due to a _guest_ write, it failed to account for writes to guest memory that are outside the scope of KVM. E.g. if host userspace modifies a shadowed gPTE to switch from a memslot to emulted MMIO and then the guest hits a relevant page fault, KVM will install the MMIO SPTE without first zapping the shadow-present SPTE. ------------[ cut here ]------------ is_shadow_present_pte(*sptep) WARNING: arch/x86/kvm/mmu/mmu.c:484 at mark_mmio_spte+0xb2/0xc0 [kvm], CPU#0: vmx_ept_stale_r/4292 Modules linked in: kvm_intel kvm irqbypass CPU: 0 UID: 1000 PID: 4292 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:mark_mmio_spte+0xb2/0xc0 [kvm] Call Trace: <TASK> mmu_set_spte+0x237/0x440 [kvm] ept_page_fault+0x535/0x7f0 [kvm] kvm_mmu_do_page_fault+0xee/0x1f0 [kvm] kvm_mmu_page_fault+0x8d/0x620 [kvm] vmx_handle_exit+0x18c/0x5a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm] kvm_vcpu_ioctl+0x2d5/0x980 [kvm] __x64_sys_ioctl+0x8a/0xd0 do_syscall_64+0xb5/0x730 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x47fa3f </TASK> ---[ end trace 0000000000000000 ]---
CVE-2026-23412: In the Linux kernel, the following vulnerability has been resolved: netfilter: bpf: defer hook memory release until rcu readers are done Yiming Qian reports UaF when concurrent process is dumping hooks via nfnetlink_hooks: BUG: KASAN: slab-use-after-free in nfnl_hook_dump_one.isra.0+0xe71/0x10f0 Read of size 8 at addr ffff888003edbf88 by task poc/79 Call Trace: <TASK> nfnl_hook_dump_one.isra.0+0xe71/0x10f0 netlink_dump+0x554/0x12b0 nfnl_hook_get+0x176/0x230 [..] Defer release until after concurrent readers have completed.
CVE-2026-23413: In the Linux kernel, the following vulnerability has been resolved: clsact: Fix use-after-free in init/destroy rollback asymmetry Fix a use-after-free in the clsact qdisc upon init/destroy rollback asymmetry. The latter is achieved by first fully initializing a clsact instance, and then in a second step having a replacement failure for the new clsact qdisc instance. clsact_init() initializes ingress first and then takes care of the egress part. This can fail midway, for example, via tcf_block_get_ext(). Upon failure, the kernel will trigger the clsact_destroy() callback. Commit 1cb6f0bae504 ("bpf: Fix too early release of tcx_entry") details the way how the transition is happening. If tcf_block_get_ext on the q->ingress_block ends up failing, we took the tcx_miniq_inc reference count on the ingress side, but not yet on the egress side. clsact_destroy() tests whether the {ingress,egress}_entry was non-NULL. However, even in midway failure on the replacement, both are in fact non-NULL with a valid egress_entry from the previous clsact instance. What we really need to test for is whether the qdisc instance-specific ingress or egress side previously got initialized. This adds a small helper for checking the miniq initialization called mini_qdisc_pair_inited, and utilizes that upon clsact_destroy() in order to fix the use-after-free scenario. Convert the ingress_destroy() side as well so both are consistent to each other.
CVE-2026-23414: In the Linux kernel, the following vulnerability has been resolved: tls: Purge async_hold in tls_decrypt_async_wait() The async_hold queue pins encrypted input skbs while the AEAD engine references their scatterlist data. Once tls_decrypt_async_wait() returns, every AEAD operation has completed and the engine no longer references those skbs, so they can be freed unconditionally. A subsequent patch adds batch async decryption to tls_sw_read_sock(), introducing a new call site that must drain pending AEAD operations and release held skbs. Move __skb_queue_purge(&ctx->async_hold) into tls_decrypt_async_wait() so the purge is centralized and every caller -- recvmsg's drain path, the -EBUSY fallback in tls_do_decryption(), and the new read_sock batch path -- releases held skbs on synchronization without each site managing the purge independently. This fixes a leak when tls_strp_msg_hold() fails part-way through, after having added some cloned skbs to the async_hold queue. tls_decrypt_sg() will then call tls_decrypt_async_wait() to process all pending decrypts, and drop back to synchronous mode, but tls_sw_recvmsg() only flushes the async_hold queue when one record has been processed in "fully-async" mode, which may not be the case here. [pabeni@redhat.com: added leak comment]
CVE-2026-23417: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix constant blinding for PROBE_MEM32 stores BPF_ST | BPF_PROBE_MEM32 immediate stores are not handled by bpf_jit_blind_insn(), allowing user-controlled 32-bit immediates to survive unblinded into JIT-compiled native code when bpf_jit_harden >= 1. The root cause is that convert_ctx_accesses() rewrites BPF_ST|BPF_MEM to BPF_ST|BPF_PROBE_MEM32 for arena pointer stores during verification, before bpf_jit_blind_constants() runs during JIT compilation. The blinding switch only matches BPF_ST|BPF_MEM (mode 0x60), not BPF_ST|BPF_PROBE_MEM32 (mode 0xa0). The instruction falls through unblinded. Add BPF_ST|BPF_PROBE_MEM32 cases to bpf_jit_blind_insn() alongside the existing BPF_ST|BPF_MEM cases. The blinding transformation is identical: load the blinded immediate into BPF_REG_AX via mov+xor, then convert the immediate store to a register store (BPF_STX). The rewritten STX instruction must preserve the BPF_PROBE_MEM32 mode so the architecture JIT emits the correct arena addressing (R12-based on x86-64). Cannot use the BPF_STX_MEM() macro here because it hardcodes BPF_MEM mode; construct the instruction directly instead.
CVE-2026-23419: In the Linux kernel, the following vulnerability has been resolved: net/rds: Fix circular locking dependency in rds_tcp_tune syzbot reported a circular locking dependency in rds_tcp_tune() where sk_net_refcnt_upgrade() is called while holding the socket lock: ====================================================== WARNING: possible circular locking dependency detected ====================================================== kworker/u10:8/15040 is trying to acquire lock: ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0}, at: __kmalloc_cache_noprof+0x4b/0x6f0 but task is already holding lock: ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: rds_tcp_tune+0xd7/0x930 The issue occurs because sk_net_refcnt_upgrade() performs memory allocation (via get_net_track() -> ref_tracker_alloc()) while the socket lock is held, creating a circular dependency with fs_reclaim. Fix this by moving sk_net_refcnt_upgrade() outside the socket lock critical section. This is safe because the fields modified by the sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not accessed by any concurrent code path at this point. v2: - Corrected fixes tag - check patch line wrap nits - ai commentary nits
CVE-2026-23420: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Fix a locking bug Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.
CVE-2026-23422: In the Linux kernel, the following vulnerability has been resolved: dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ handler Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler") introduces a range check for if_id to avoid an out-of-bounds access. If an out-of-bounds if_id is detected, the interrupt status is not cleared. This may result in an interrupt storm. Clear the interrupt status after detecting an out-of-bounds if_id to avoid the problem. Found by an experimental AI code review agent at Google.
CVE-2026-23426: In the Linux kernel, the following vulnerability has been resolved: drm/logicvc: Fix device node reference leak in logicvc_drm_config_parse() The logicvc_drm_config_parse() function calls of_get_child_by_name() to find the "layers" node but fails to release the reference, leading to a device node reference leak. Fix this by using the __free(device_node) cleanup attribute to automatic release the reference when the variable goes out of scope.
CVE-2026-23427: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in durable v2 replay of active file handles parse_durable_handle_context() unconditionally assigns dh_info->fp->conn to the current connection when handling a DURABLE_REQ_V2 context with SMB2_FLAGS_REPLAY_OPERATION. ksmbd_lookup_fd_cguid() does not filter by fp->conn, so it returns file handles that are already actively connected. The unconditional overwrite replaces fp->conn, and when the overwriting connection is subsequently freed, __ksmbd_close_fd() dereferences the stale fp->conn via spin_lock(&fp->conn->llist_lock), causing a use-after-free. KASAN report: [ 7.349357] ================================================================== [ 7.349607] BUG: KASAN: slab-use-after-free in _raw_spin_lock+0x75/0xe0 [ 7.349811] Write of size 4 at addr ffff8881056ac18c by task kworker/1:2/108 [ 7.350010] [ 7.350064] CPU: 1 UID: 0 PID: 108 Comm: kworker/1:2 Not tainted 7.0.0-rc3+ #58 PREEMPTLAZY [ 7.350068] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 7.350070] Workqueue: ksmbd-io handle_ksmbd_work [ 7.350083] Call Trace: [ 7.350087] <TASK> [ 7.350087] dump_stack_lvl+0x64/0x80 [ 7.350094] print_report+0xce/0x660 [ 7.350100] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 7.350101] ? __pfx___mod_timer+0x10/0x10 [ 7.350106] ? _raw_spin_lock+0x75/0xe0 [ 7.350108] kasan_report+0xce/0x100 [ 7.350109] ? _raw_spin_lock+0x75/0xe0 [ 7.350114] kasan_check_range+0x105/0x1b0 [ 7.350116] _raw_spin_lock+0x75/0xe0 [ 7.350118] ? __pfx__raw_spin_lock+0x10/0x10 [ 7.350119] ? __call_rcu_common.constprop.0+0x25e/0x780 [ 7.350125] ? close_id_del_oplock+0x2cc/0x4e0 [ 7.350128] __ksmbd_close_fd+0x27f/0xaf0 [ 7.350131] ksmbd_close_fd+0x135/0x1b0 [ 7.350133] smb2_close+0xb19/0x15b0 [ 7.350142] ? __pfx_smb2_close+0x10/0x10 [ 7.350143] ? xas_load+0x18/0x270 [ 7.350146] ? _raw_spin_lock+0x84/0xe0 [ 7.350148] ? __pfx__raw_spin_lock+0x10/0x10 [ 7.350150] ? _raw_spin_unlock+0xe/0x30 [ 7.350151] ? ksmbd_smb2_check_message+0xeb2/0x24c0 [ 7.350153] ? ksmbd_tree_conn_lookup+0xcd/0xf0 [ 7.350154] handle_ksmbd_work+0x40f/0x1080 [ 7.350156] process_one_work+0x5fa/0xef0 [ 7.350162] ? assign_work+0x122/0x3e0 [ 7.350163] worker_thread+0x54b/0xf70 [ 7.350165] ? __pfx_worker_thread+0x10/0x10 [ 7.350166] kthread+0x346/0x470 [ 7.350170] ? recalc_sigpending+0x19b/0x230 [ 7.350176] ? __pfx_kthread+0x10/0x10 [ 7.350178] ret_from_fork+0x4fb/0x6c0 [ 7.350183] ? __pfx_ret_from_fork+0x10/0x10 [ 7.350185] ? __switch_to+0x36c/0xbe0 [ 7.350188] ? __pfx_kthread+0x10/0x10 [ 7.350190] ret_from_fork_asm+0x1a/0x30 [ 7.350197] </TASK> [ 7.350197] [ 7.355160] Allocated by task 123: [ 7.355261] kasan_save_stack+0x33/0x60 [ 7.355373] kasan_save_track+0x14/0x30 [ 7.355484] __kasan_kmalloc+0x8f/0xa0 [ 7.355593] ksmbd_conn_alloc+0x44/0x6d0 [ 7.355711] ksmbd_kthread_fn+0x243/0xd70 [ 7.355839] kthread+0x346/0x470 [ 7.355942] ret_from_fork+0x4fb/0x6c0 [ 7.356051] ret_from_fork_asm+0x1a/0x30 [ 7.356164] [ 7.356214] Freed by task 134: [ 7.356305] kasan_save_stack+0x33/0x60 [ 7.356416] kasan_save_track+0x14/0x30 [ 7.356527] kasan_save_free_info+0x3b/0x60 [ 7.356646] __kasan_slab_free+0x43/0x70 [ 7.356761] kfree+0x1ca/0x430 [ 7.356862] ksmbd_tcp_disconnect+0x59/0xe0 [ 7.356993] ksmbd_conn_handler_loop+0x77e/0xd40 [ 7.357138] kthread+0x346/0x470 [ 7.357240] ret_from_fork+0x4fb/0x6c0 [ 7.357350] ret_from_fork_asm+0x1a/0x30 [ 7.357463] [ 7.357513] The buggy address belongs to the object at ffff8881056ac000 [ 7.357513] which belongs to the cache kmalloc-1k of size 1024 [ 7.357857] The buggy address is located 396 bytes inside of [ 7.357857] freed 1024-byte region ---truncated---
CVE-2026-23428: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free of share_conf in compound request smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state == TREE_CONNECTED on the initial lookup path, but the compound reuse path bypasses this check entirely. If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(), subsequent commands dereference the freed share_conf through work->tcon->share_conf. KASAN report: [ 4.144653] ================================================================== [ 4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70 [ 4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44 [ 4.145772] [ 4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY [ 4.145871] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 4.145875] Workqueue: ksmbd-io handle_ksmbd_work [ 4.145888] Call Trace: [ 4.145892] <TASK> [ 4.145894] dump_stack_lvl+0x64/0x80 [ 4.145910] print_report+0xce/0x660 [ 4.145919] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 4.145928] ? smb2_write+0xc74/0xe70 [ 4.145931] kasan_report+0xce/0x100 [ 4.145934] ? smb2_write+0xc74/0xe70 [ 4.145937] smb2_write+0xc74/0xe70 [ 4.145939] ? __pfx_smb2_write+0x10/0x10 [ 4.145942] ? _raw_spin_unlock+0xe/0x30 [ 4.145945] ? ksmbd_smb2_check_message+0xeb2/0x24c0 [ 4.145948] ? smb2_tree_disconnect+0x31c/0x480 [ 4.145951] handle_ksmbd_work+0x40f/0x1080 [ 4.145953] process_one_work+0x5fa/0xef0 [ 4.145962] ? assign_work+0x122/0x3e0 [ 4.145964] worker_thread+0x54b/0xf70 [ 4.145967] ? __pfx_worker_thread+0x10/0x10 [ 4.145970] kthread+0x346/0x470 [ 4.145976] ? recalc_sigpending+0x19b/0x230 [ 4.145980] ? __pfx_kthread+0x10/0x10 [ 4.145984] ret_from_fork+0x4fb/0x6c0 [ 4.145992] ? __pfx_ret_from_fork+0x10/0x10 [ 4.145995] ? __switch_to+0x36c/0xbe0 [ 4.145999] ? __pfx_kthread+0x10/0x10 [ 4.146003] ret_from_fork_asm+0x1a/0x30 [ 4.146013] </TASK> [ 4.146014] [ 4.149858] Allocated by task 44: [ 4.149953] kasan_save_stack+0x33/0x60 [ 4.150061] kasan_save_track+0x14/0x30 [ 4.150169] __kasan_kmalloc+0x8f/0xa0 [ 4.150274] ksmbd_share_config_get+0x1dd/0xdd0 [ 4.150401] ksmbd_tree_conn_connect+0x7e/0x600 [ 4.150529] smb2_tree_connect+0x2e6/0x1000 [ 4.150645] handle_ksmbd_work+0x40f/0x1080 [ 4.150761] process_one_work+0x5fa/0xef0 [ 4.150873] worker_thread+0x54b/0xf70 [ 4.150978] kthread+0x346/0x470 [ 4.151071] ret_from_fork+0x4fb/0x6c0 [ 4.151176] ret_from_fork_asm+0x1a/0x30 [ 4.151286] [ 4.151332] Freed by task 44: [ 4.151418] kasan_save_stack+0x33/0x60 [ 4.151526] kasan_save_track+0x14/0x30 [ 4.151634] kasan_save_free_info+0x3b/0x60 [ 4.151751] __kasan_slab_free+0x43/0x70 [ 4.151861] kfree+0x1ca/0x430 [ 4.151952] __ksmbd_tree_conn_disconnect+0xc8/0x190 [ 4.152088] smb2_tree_disconnect+0x1cd/0x480 [ 4.152211] handle_ksmbd_work+0x40f/0x1080 [ 4.152326] process_one_work+0x5fa/0xef0 [ 4.152438] worker_thread+0x54b/0xf70 [ 4.152545] kthread+0x346/0x470 [ 4.152638] ret_from_fork+0x4fb/0x6c0 [ 4.152743] ret_from_fork_asm+0x1a/0x30 [ 4.152853] [ 4.152900] The buggy address belongs to the object at ffff88810430c180 [ 4.152900] which belongs to the cache kmalloc-96 of size 96 [ 4.153226] The buggy address is located 20 bytes inside of [ 4.153226] freed 96-byte region [ffff88810430c180, ffff88810430c1e0) [ 4.153549] [ 4.153596] The buggy address belongs to the physical page: [ 4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c [ 4.154000] flags: 0x ---truncated---
CVE-2026-23434: In the Linux kernel, the following vulnerability has been resolved: mtd: rawnand: serialize lock/unlock against other NAND operations nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area without holding the NAND device lock. On controllers that implement SET_FEATURES via multiple low-level PIO commands, these can race with concurrent UBI/UBIFS background erase/write operations that hold the device lock, resulting in cmd_pending conflicts on the NAND controller. Add nand_get_device()/nand_release_device() around the lock/unlock operations to serialize them against all other NAND controller access.
CVE-2026-23438: In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: guard flow control update with global_tx_fc in buffer switching mvpp2_bm_switch_buffers() unconditionally calls mvpp2_bm_pool_update_priv_fc() when switching between per-cpu and shared buffer pool modes. This function programs CM3 flow control registers via mvpp2_cm3_read()/mvpp2_cm3_write(), which dereference priv->cm3_base without any NULL check. When the CM3 SRAM resource is not present in the device tree (the third reg entry added by commit 60523583b07c ("dts: marvell: add CM3 SRAM memory to cp11x ethernet device tree")), priv->cm3_base remains NULL and priv->global_tx_fc is false. Any operation that triggers mvpp2_bm_switch_buffers(), for example an MTU change that crosses the jumbo frame threshold, will crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits pc : readl+0x0/0x18 lr : mvpp2_cm3_read.isra.0+0x14/0x20 Call trace: readl+0x0/0x18 mvpp2_bm_pool_update_fc+0x40/0x12c mvpp2_bm_pool_update_priv_fc+0x94/0xd8 mvpp2_bm_switch_buffers.isra.0+0x80/0x1c0 mvpp2_change_mtu+0x140/0x380 __dev_set_mtu+0x1c/0x38 dev_set_mtu_ext+0x78/0x118 dev_set_mtu+0x48/0xa8 dev_ifsioc+0x21c/0x43c dev_ioctl+0x2d8/0x42c sock_ioctl+0x314/0x378 Every other flow control call site in the driver already guards hardware access with either priv->global_tx_fc or port->tx_fc. mvpp2_bm_switch_buffers() is the only place that omits this check. Add the missing priv->global_tx_fc guard to both the disable and re-enable calls in mvpp2_bm_switch_buffers(), consistent with the rest of the driver.
CVE-2026-23439: In the Linux kernel, the following vulnerability has been resolved: udp_tunnel: fix NULL deref caused by udp_sock_create6 when CONFIG_IPV6=n When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0 (success) without actually creating a socket. Callers such as fou_create() then proceed to dereference the uninitialized socket pointer, resulting in a NULL pointer dereference. The captured NULL deref crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764) [...] Call Trace: <TASK> genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209) [...] netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sock_sendmsg (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1)) __sys_sendto (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:2183 (discriminator 1)) __x64_sys_sendto (net/socket.c:2213 (discriminator 1) net/socket.c:2209 (discriminator 1) net/socket.c:2209 (discriminator 1)) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (net/arch/x86/entry/entry_64.S:130) This patch makes udp_sock_create6 return -EPFNOSUPPORT instead, so callers correctly take their error paths. There is only one caller of the vulnerable function and only privileged users can trigger it.
CVE-2026-23440: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix race condition during IPSec ESN update In IPSec full offload mode, the device reports an ESN (Extended Sequence Number) wrap event to the driver. The driver validates this event by querying the IPSec ASO and checking that the esn_event_arm field is 0x0, which indicates an event has occurred. After handling the event, the driver must re-arm the context by setting esn_event_arm back to 0x1. A race condition exists in this handling path. After validating the event, the driver calls mlx5_accel_esp_modify_xfrm() to update the kernel's xfrm state. This function temporarily releases and re-acquires the xfrm state lock. So, need to acknowledge the event first by setting esn_event_arm to 0x1. This prevents the driver from reprocessing the same ESN update if the hardware sends events for other reason. Since the next ESN update only occurs after nearly 2^31 packets are received, there's no risk of missing an update, as it will happen long after this handling has finished. Processing the event twice causes the ESN high-order bits (esn_msb) to be incremented incorrectly. The driver then programs the hardware with this invalid ESN state, which leads to anti-replay failures and a complete halt of IPSec traffic. Fix this by re-arming the ESN event immediately after it is validated, before calling mlx5_accel_esp_modify_xfrm(). This ensures that any spurious, duplicate events are correctly ignored, closing the race window.
CVE-2026-23441: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Prevent concurrent access to IPSec ASO context The query or updating IPSec offload object is through Access ASO WQE. The driver uses a single mlx5e_ipsec_aso struct for each PF, which contains a shared DMA-mapped context for all ASO operations. A race condition exists because the ASO spinlock is released before the hardware has finished processing WQE. If a second operation is initiated immediately after, it overwrites the shared context in the DMA area. When the first operation's completion is processed later, it reads this corrupted context, leading to unexpected behavior and incorrect results. This commit fixes the race by introducing a private context within each IPSec offload object. The shared ASO context is now copied to this private context while the ASO spinlock is held. Subsequent processing uses this saved, per-object context, ensuring its integrity is maintained.
CVE-2026-23442: In the Linux kernel, the following vulnerability has been resolved: ipv6: add NULL checks for idev in SRv6 paths __in6_dev_get() can return NULL when the device has no IPv6 configuration (e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER). Add NULL checks for idev returned by __in6_dev_get() in both seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL pointer dereferences.
CVE-2026-23444: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure ieee80211_tx_prepare_skb() has three error paths, but only two of them free the skb. The first error path (ieee80211_tx_prepare() returning TX_DROP) does not free it, while invoke_tx_handlers() failure and the fragmentation check both do. Add kfree_skb() to the first error path so all three are consistent, and remove the now-redundant frees in callers (ath9k, mt76, mac80211_hwsim) to avoid double-free. Document the skb ownership guarantee in the function's kdoc.
CVE-2026-23445: In the Linux kernel, the following vulnerability has been resolved: igc: fix page fault in XDP TX timestamps handling If an XDP application that requested TX timestamping is shutting down while the link of the interface in use is still up the following kernel splat is reported: [ 883.803618] [ T1554] BUG: unable to handle page fault for address: ffffcfb6200fd008 ... [ 883.803650] [ T1554] Call Trace: [ 883.803652] [ T1554] <TASK> [ 883.803654] [ T1554] igc_ptp_tx_tstamp_event+0xdf/0x160 [igc] [ 883.803660] [ T1554] igc_tsync_interrupt+0x2d5/0x300 [igc] ... During shutdown of the TX ring the xsk_meta pointers are left behind, so that the IRQ handler is trying to touch them. This issue is now being fixed by cleaning up the stale xsk meta data on TX shutdown. TX timestamps on other queues remain unaffected.
CVE-2026-23446: In the Linux kernel, the following vulnerability has been resolved: net: usb: aqc111: Do not perform PM inside suspend callback syzbot reports "task hung in rpm_resume" This is caused by aqc111_suspend calling the PM variant of its write_cmd routine. The simplified call trace looks like this: rpm_suspend() usb_suspend_both() - here udev->dev.power.runtime_status == RPM_SUSPENDING aqc111_suspend() - called for the usb device interface aqc111_write32_cmd() usb_autopm_get_interface() pm_runtime_resume_and_get() rpm_resume() - here we call rpm_resume() on our parent rpm_resume() - Here we wait for a status change that will never happen. At this point we block another task which holds rtnl_lock and locks up the whole networking stack. Fix this by replacing the write_cmd calls with their _nopm variants
CVE-2026-23447: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check The same bounds-check bug fixed for NDP16 in the previous patch also exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated against the total skb length without accounting for ndpoffset, allowing out-of-bounds reads when the NDP32 is placed near the end of the NTB. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly. Compile-tested only.
CVE-2026-23448: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE entries fit within the skb. The first check correctly accounts for ndpoffset: if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len) but the second check omits it: if ((sizeof(struct usb_cdc_ncm_ndp16) + ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len) This validates the DPE array size against the total skb length as if the NDP were at offset 0, rather than at ndpoffset. When the NDP is placed near the end of the NTB (large wNdpIndex), the DPE entries can extend past the skb data buffer even though the check passes. cdc_ncm_rx_fixup() then reads out-of-bounds memory when iterating the DPE array. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly.
CVE-2026-23449: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: Fix double-free in teql_master_xmit Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should be called using the seq_lock to avoid racing with the datapath. Failure to do so may cause crashes like the following: [ 238.028993][ T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139) [ 238.029328][ T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318 [ 238.029749][ T318] [ 238.029900][ T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full) [ 238.029906][ T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 238.029910][ T318] Call Trace: [ 238.029913][ T318] <TASK> [ 238.029916][ T318] dump_stack_lvl (lib/dump_stack.c:122) [ 238.029928][ T318] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 238.029940][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029944][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.029957][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029969][ T318] kasan_report_invalid_free (mm/kasan/report.c:221 mm/kasan/report.c:563) [ 238.029979][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029989][ T318] check_slab_allocation (mm/kasan/common.c:231) [ 238.029995][ T318] kmem_cache_free (mm/slub.c:2637 (discriminator 1) mm/slub.c:6168 (discriminator 1) mm/slub.c:6298 (discriminator 1)) [ 238.030004][ T318] skb_release_data (net/core/skbuff.c:1139) ... [ 238.030025][ T318] sk_skb_reason_drop (net/core/skbuff.c:1256) [ 238.030032][ T318] pfifo_fast_reset (./include/linux/ptr_ring.h:171 ./include/linux/ptr_ring.h:309 ./include/linux/skb_array.h:98 net/sched/sch_generic.c:827) [ 238.030039][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.030054][ T318] qdisc_reset (net/sched/sch_generic.c:1034) [ 238.030062][ T318] teql_destroy (./include/linux/spinlock.h:395 net/sched/sch_teql.c:157) [ 238.030071][ T318] __qdisc_destroy (./include/net/pkt_sched.h:328 net/sched/sch_generic.c:1077) [ 238.030077][ T318] qdisc_graft (net/sched/sch_api.c:1062 net/sched/sch_api.c:1053 net/sched/sch_api.c:1159) [ 238.030089][ T318] ? __pfx_qdisc_graft (net/sched/sch_api.c:1091) [ 238.030095][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030102][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030106][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030114][ T318] tc_get_qdisc (net/sched/sch_api.c:1529 net/sched/sch_api.c:1556) ... [ 238.072958][ T318] Allocated by task 303 on cpu 5 at 238.026275s: [ 238.073392][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.073884][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.074230][ T318] __kasan_slab_alloc (mm/kasan/common.c:369) [ 238.074578][ T318] kmem_cache_alloc_node_noprof (./include/linux/kasan.h:253 mm/slub.c:4542 mm/slub.c:4869 mm/slub.c:4921) [ 238.076091][ T318] kmalloc_reserve (net/core/skbuff.c:616 (discriminator 107)) [ 238.076450][ T318] __alloc_skb (net/core/skbuff.c:713) [ 238.076834][ T318] alloc_skb_with_frags (./include/linux/skbuff.h:1383 net/core/skbuff.c:6763) [ 238.077178][ T318] sock_alloc_send_pskb (net/core/sock.c:2997) [ 238.077520][ T318] packet_sendmsg (net/packet/af_packet.c:2926 net/packet/af_packet.c:3019 net/packet/af_packet.c:3108) [ 238.081469][ T318] [ 238.081870][ T318] Freed by task 299 on cpu 1 at 238.028496s: [ 238.082761][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.083481][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.085348][ T318] kasan_save_free_info (mm/kasan/generic.c:587 (discriminator 1)) [ 238.085900][ T318] __kasan_slab_free (mm/ ---truncated---
CVE-2026-23450: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix NULL dereference and UAF in smc_tcp_syn_recv_sock() Syzkaller reported a panic in smc_tcp_syn_recv_sock() [1]. smc_tcp_syn_recv_sock() is called in the TCP receive path (softirq) via icsk_af_ops->syn_recv_sock on the clcsock (TCP listening socket). It reads sk_user_data to get the smc_sock pointer. However, when the SMC listen socket is being closed concurrently, smc_close_active() sets clcsock->sk_user_data to NULL under sk_callback_lock, and then the smc_sock itself can be freed via sock_put() in smc_release(). This leads to two issues: 1) NULL pointer dereference: sk_user_data is NULL when accessed. 2) Use-after-free: sk_user_data is read as non-NULL, but the smc_sock is freed before its fields (e.g., queued_smc_hs, ori_af_ops) are accessed. The race window looks like this (the syzkaller crash [1] triggers via the SYN cookie path: tcp_get_cookie_sock() -> smc_tcp_syn_recv_sock(), but the normal tcp_check_req() path has the same race): CPU A (softirq) CPU B (process ctx) tcp_v4_rcv() TCP_NEW_SYN_RECV: sk = req->rsk_listener sock_hold(sk) /* No lock on listener */ smc_close_active(): write_lock_bh(cb_lock) sk_user_data = NULL write_unlock_bh(cb_lock) ... smc_clcsock_release() sock_put(smc->sk) x2 -> smc_sock freed! tcp_check_req() smc_tcp_syn_recv_sock(): smc = user_data(sk) -> NULL or dangling smc->queued_smc_hs -> crash! Note that the clcsock and smc_sock are two independent objects with separate refcounts. TCP stack holds a reference on the clcsock, which keeps it alive, but this does NOT prevent the smc_sock from being freed. Fix this by using RCU and refcount_inc_not_zero() to safely access smc_sock. Since smc_tcp_syn_recv_sock() is called in the TCP three-way handshake path, taking read_lock_bh on sk_callback_lock is too heavy and would not survive a SYN flood attack. Using rcu_read_lock() is much more lightweight. - Set SOCK_RCU_FREE on the SMC listen socket so that smc_sock freeing is deferred until after the RCU grace period. This guarantees the memory is still valid when accessed inside rcu_read_lock(). - Use rcu_read_lock() to protect reading sk_user_data. - Use refcount_inc_not_zero(&smc->sk.sk_refcnt) to pin the smc_sock. If the refcount has already reached zero (close path completed), it returns false and we bail out safely. Note: smc_hs_congested() has a similar lockless read of sk_user_data without rcu_read_lock(), but it only checks for NULL and accesses the global smc_hs_wq, never dereferencing any smc_sock field, so it is not affected. Reproducer was verified with mdelay injection and smc_run, the issue no longer occurs with this patch applied. [1] https://syzkaller.appspot.com/bug?extid=827ae2bfb3a3529333e9
CVE-2026-23452: In the Linux kernel, the following vulnerability has been resolved: PM: runtime: Fix a race condition related to device removal The following code in pm_runtime_work() may dereference the dev->parent pointer after the parent device has been freed: /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } Fix this by inserting a flush_work() call in pm_runtime_remove(). Without this patch blktest block/001 triggers the following complaint sporadically: BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160 Read of size 1 at addr ffff88812bef7198 by task kworker/u553:1/3081 Workqueue: pm pm_runtime_work Call Trace: <TASK> dump_stack_lvl+0x61/0x80 print_address_description.constprop.0+0x8b/0x310 print_report+0xfd/0x1d7 kasan_report+0xd8/0x1d0 __kasan_check_byte+0x42/0x60 lock_acquire.part.0+0x38/0x230 lock_acquire+0x70/0x160 _raw_spin_lock+0x36/0x50 rpm_suspend+0xc6a/0xfe0 rpm_idle+0x578/0x770 pm_runtime_work+0xee/0x120 process_one_work+0xde3/0x1410 worker_thread+0x5eb/0xfe0 kthread+0x37b/0x480 ret_from_fork+0x6cb/0x920 ret_from_fork_asm+0x11/0x20 </TASK> Allocated by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_alloc_info+0x3d/0x50 __kasan_kmalloc+0xa0/0xb0 __kmalloc_noprof+0x311/0x990 scsi_alloc_target+0x122/0xb60 [scsi_mod] __scsi_scan_target+0x101/0x460 [scsi_mod] scsi_scan_channel+0x179/0x1c0 [scsi_mod] scsi_scan_host_selected+0x259/0x2d0 [scsi_mod] store_scan+0x2d2/0x390 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810 do_syscall_64+0xee/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Freed by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_free_info+0x3f/0x50 __kasan_slab_free+0x67/0x80 kfree+0x225/0x6c0 scsi_target_dev_release+0x3d/0x60 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_dev_release+0xacf/0x12c0 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_put+0x7f/0xc0 [scsi_mod] sdev_store_delete+0xa5/0x120 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810
CVE-2026-23454: In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potential race condition exists in mana_hwc_destroy_channel() where hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt handler to dereference freed memory, leading to a use-after-free or NULL pointer dereference in mana_hwc_handle_resp(). mana_smc_teardown_hwc() signals the hardware to stop but does not synchronize against IRQ handlers already executing on other CPUs. The IRQ synchronization only happens in mana_hwc_destroy_cq() via mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler() can dereference freed caller_ctx (and rxq->msg_buf) in mana_hwc_handle_resp(). Fix this by reordering teardown to reverse-of-creation order: destroy the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This ensures all in-flight interrupt handlers complete before the memory they access is freed.
CVE-2026-23455: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement.
CVE-2026-23456: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint().
CVE-2026-23457: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length.
CVE-2026-23458: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0
CVE-2026-23460: In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516
CVE-2026-23461: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to conn->users. However, l2cap_register_user() and l2cap_unregister_user() don't use conn->lock, creating a race condition where these functions can access conn->users and conn->hchan concurrently with l2cap_conn_del(). This can lead to use-after-free and list corruption bugs, as reported by syzbot. Fix this by changing l2cap_register_user() and l2cap_unregister_user() to use conn->lock instead of hci_dev_lock(), ensuring consistent locking for the l2cap_conn structure.
CVE-2026-23462: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated---
CVE-2026-23463: In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between fq_table[fq->idx] state and freeing/allocating from the pool and WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered. Indeed, we can have: Thread A Thread B qman_destroy_fq() qman_create_fq() qman_release_fqid() qman_shutdown_fq() gen_pool_free() -- At this point, the fqid is available again -- qman_alloc_fqid() -- so, we can get the just-freed fqid in thread B -- fq->fqid = fqid; fq->idx = fqid * 2; WARN_ON(fq_table[fq->idx]); fq_table[fq->idx] = fq; fq_table[fq->idx] = NULL; And adding some logs between qman_release_fqid() and fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more. To prevent that, ensure that fq_table[fq->idx] is set to NULL before gen_pool_free() is called by using smp_wmb().
CVE-2026-23464: In the Linux kernel, the following vulnerability has been resolved: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe() In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails, the function returns immediately without freeing the allocated memory for sys_controller, leading to a memory leak. Fix this by jumping to the out_free label to ensure the memory is properly freed. Also, consolidate the error handling for the mbox_request_channel() failure case to use the same label.
CVE-2026-23465: In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . <power failure> # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon.
CVE-2026-23466: In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hotplug (drm_dev_enter), which works correctly when the driver loads successfully and is later unbound or unloaded. However, if driver load fails, this protection is insufficient because drm_dev_unplug() is never called. Additionally, devm release functions cannot guarantee that all BOs with GGTT mappings are destroyed before the GGTT MMIO region is removed, as some BOs may be freed asynchronously by worker threads. To address this, introduce an open-coded flag, protected by the GGTT lock, that guards GGTT MMIO access. The flag is cleared during the dev_fini_ggtt devm release function to ensure MMIO access is disabled once teardown begins. (cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431)
CVE-2026-23468: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion Userspace can pass an arbitrary number of BO list entries via the bo_number field. Although the previous multiplication overflow check prevents out-of-bounds allocation, a large number of entries could still cause excessive memory allocation (up to potentially gigabytes) and unnecessarily long list processing times. Introduce a hard limit of 128k entries per BO list, which is more than sufficient for any realistic use case (e.g., a single list containing all buffers in a large scene). This prevents memory exhaustion attacks and ensures predictable performance. Return -EINVAL if the requested entry count exceeds the limit (cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332)
CVE-2026-23469: In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Synchronize interrupts before suspending the GPU The runtime PM suspend callback doesn't know whether the IRQ handler is in progress on a different CPU core and doesn't wait for it to finish. Depending on timing, the IRQ handler could be running while the GPU is suspended, leading to kernel crashes when trying to access GPU registers. See example signature below. In a power off sequence initiated by the runtime PM suspend callback, wait for any IRQ handlers in progress on other CPU cores to finish, by calling synchronize_irq(). At the same time, remove the runtime PM resume/put calls in the threaded IRQ handler. On top of not being the right approach to begin with, and being at the wrong place as they should have wrapped all GPU register accesses, the driver would hit a deadlock between synchronize_irq() being called from a runtime PM suspend callback, holding the device power lock, and the resume callback requiring the same. Example crash signature on a TI AM68 SK platform: [ 337.241218] SError Interrupt on CPU0, code 0x00000000bf000000 -- SError [ 337.241239] CPU: 0 UID: 0 PID: 112 Comm: irq/234-gpu Tainted: G M 6.17.7-B2C-00005-g9c7bbe4ea16c #2 PREEMPT [ 337.241246] Tainted: [M]=MACHINE_CHECK [ 337.241249] Hardware name: Texas Instruments AM68 SK (DT) [ 337.241252] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 337.241256] pc : pvr_riscv_irq_pending+0xc/0x24 [ 337.241277] lr : pvr_device_irq_thread_handler+0x64/0x310 [ 337.241282] sp : ffff800085b0bd30 [ 337.241284] x29: ffff800085b0bd50 x28: ffff0008070d9eab x27: ffff800083a5ce10 [ 337.241291] x26: ffff000806e48f80 x25: ffff0008070d9eac x24: 0000000000000000 [ 337.241296] x23: ffff0008068e9bf0 x22: ffff0008068e9bd0 x21: ffff800085b0bd30 [ 337.241301] x20: ffff0008070d9e00 x19: ffff0008068e9000 x18: 0000000000000001 [ 337.241305] x17: 637365645f656c70 x16: 0000000000000000 x15: ffff000b7df9ff40 [ 337.241310] x14: 0000a585fe3c0d0e x13: 000000999704f060 x12: 000000000002771a [ 337.241314] x11: 00000000000000c0 x10: 0000000000000af0 x9 : ffff800085b0bd00 [ 337.241318] x8 : ffff0008071175d0 x7 : 000000000000b955 x6 : 0000000000000003 [ 337.241323] x5 : 0000000000000000 x4 : 0000000000000002 x3 : 0000000000000000 [ 337.241327] x2 : ffff800080e39d20 x1 : ffff800080e3fc48 x0 : 0000000000000000 [ 337.241333] Kernel panic - not syncing: Asynchronous SError Interrupt [ 337.241337] CPU: 0 UID: 0 PID: 112 Comm: irq/234-gpu Tainted: G M 6.17.7-B2C-00005-g9c7bbe4ea16c #2 PREEMPT [ 337.241342] Tainted: [M]=MACHINE_CHECK [ 337.241343] Hardware name: Texas Instruments AM68 SK (DT) [ 337.241345] Call trace: [ 337.241348] show_stack+0x18/0x24 (C) [ 337.241357] dump_stack_lvl+0x60/0x80 [ 337.241364] dump_stack+0x18/0x24 [ 337.241368] vpanic+0x124/0x2ec [ 337.241373] abort+0x0/0x4 [ 337.241377] add_taint+0x0/0xbc [ 337.241384] arm64_serror_panic+0x70/0x80 [ 337.241389] do_serror+0x3c/0x74 [ 337.241392] el1h_64_error_handler+0x30/0x48 [ 337.241400] el1h_64_error+0x6c/0x70 [ 337.241404] pvr_riscv_irq_pending+0xc/0x24 (P) [ 337.241410] irq_thread_fn+0x2c/0xb0 [ 337.241416] irq_thread+0x170/0x334 [ 337.241421] kthread+0x12c/0x210 [ 337.241428] ret_from_fork+0x10/0x20 [ 337.241434] SMP: stopping secondary CPUs [ 337.241451] Kernel Offset: disabled [ 337.241453] CPU features: 0x040000,02002800,20002001,0400421b [ 337.241456] Memory Limit: none [ 337.457921] ---[ end Kernel panic - not syncing: Asynchronous SError Interrupt ]---
CVE-2026-23470: In the Linux kernel, the following vulnerability has been resolved: drm/imagination: Fix deadlock in soft reset sequence The soft reset sequence is currently executed from the threaded IRQ handler, hence it cannot call disable_irq() which internally waits for IRQ handlers, i.e. itself, to complete. Use disable_irq_nosync() during a soft reset instead.
CVE-2026-23472: In the Linux kernel, the following vulnerability has been resolved: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN uart_write_room() and uart_write() behave inconsistently when xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were never properly initialized): - uart_write_room() returns kfifo_avail() which can be > 0 - uart_write() checks xmit_buf and returns 0 if NULL This inconsistency causes an infinite loop in drivers that rely on tty_write_room() to determine if they can write: while (tty_write_room(tty) > 0) { written = tty->ops->write(...); // written is always 0, loop never exits } For example, caif_serial's handle_tx() enters an infinite loop when used with PORT_UNKNOWN serial ports, causing system hangs. Fix by making uart_write_room() also check xmit_buf and return 0 if it's NULL, consistent with uart_write(). Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13
CVE-2026-23473: In the Linux kernel, the following vulnerability has been resolved: io_uring/poll: fix multishot recv missing EOF on wakeup race When a socket send and shutdown() happen back-to-back, both fire wake-ups before the receiver's task_work has a chance to run. The first wake gets poll ownership (poll_refs=1), and the second bumps it to 2. When io_poll_check_events() runs, it calls io_poll_issue() which does a recv that reads the data and returns IOU_RETRY. The loop then drains all accumulated refs (atomic_sub_return(2) -> 0) and exits, even though only the first event was consumed. Since the shutdown is a persistent state change, no further wakeups will happen, and the multishot recv can hang forever. Check specifically for HUP in the poll loop, and ensure that another loop is done to check for status if more than a single poll activation is pending. This ensures we don't lose the shutdown event.
CVE-2026-23474: In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds.
CVE-2026-23475: In the Linux kernel, the following vulnerability has been resolved: spi: fix statistics allocation The controller per-cpu statistics is not allocated until after the controller has been registered with driver core, which leaves a window where accessing the sysfs attributes can trigger a NULL-pointer dereference. Fix this by moving the statistics allocation to controller allocation while tying its lifetime to that of the controller (rather than using implicit devres).
CVE-2026-31389: In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses.
CVE-2026-31391: In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tfm_count to avoid blocking future reads.
CVE-2026-31392: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5 mounts were failing against a single server as the client was trying to mount the shares with wrong credentials. It turned out the client was reusing SMB session from first mount to try mounting the other shares, even though a different username= option had been specified to the other mounts. By using username mount option along with sec=krb5 to search for principals from keytab is supported by cifs.upcall(8) since cifs-utils-4.8. So fix this by matching username mount option in match_session() even with Kerberos. For example, the second mount below should fail with -ENOKEY as there is no 'foobar' principal in keytab (/etc/krb5.keytab). The client ends up reusing SMB session from first mount to perform the second one, which is wrong. ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ---------------------------------------------------------------- 1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96) $ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser $ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar $ mount -t cifs | grep -Po 'username=\K\w+' testuser testuser ```
CVE-2026-31393: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled.
CVE-2026-31394: In the Linux kernel, the following vulnerability has been resolved: mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations ieee80211_chan_bw_change() iterates all stations and accesses link->reserved.oper via sta->sdata->link[link_id]. For stations on AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to the VLAN sdata, whose link never participates in chanctx reservations. This leaves link->reserved.oper zero-initialized with chan == NULL, causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw() when accessing chandef->chan->band during CSA. Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata() before accessing link data. [also change sta->sdata in ARRAY_SIZE even if it doesn't matter]
CVE-2026-31396: In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every opening of the interface and destroyed on every closing. However it may be accessed via get_ts_info ethtool call which is possible while the interface is just present in the kernel. BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 Read of size 4 at addr ffff8880194345cc by task syz.0.6/948 CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106 print_address_description mm/kasan/report.c:316 [inline] print_report+0x17f/0x496 mm/kasan/report.c:420 kasan_report+0xd9/0x180 mm/kasan/report.c:524 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558 ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline] __dev_ethtool net/ethtool/ioctl.c:3017 [inline] dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215 sock_ioctl+0x577/0x6d0 net/socket.c:1320 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 </TASK> Allocated by task 457: kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:699 [inline] ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920 __dev_open+0x2ce/0x500 net/core/dev.c:1501 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651 dev_change_flags+0x92/0x170 net/core/dev.c:8722 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x14b/0x180 net/socket.c:730 __sys_sendto+0x320/0x3b0 net/socket.c:2152 __do_sys_sendto net/socket.c:2164 [inline] __se_sys_sendto net/socket.c:2160 [inline] __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 938: kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1729 [inline] slab_free_freelist_hook mm/slub.c:1755 [inline] slab_free mm/slub.c:3687 [inline] __kmem_cache_free+0xbc/0x320 mm/slub.c:3700 device_release+0xa0/0x240 drivers/base/core.c:2507 kobject_cleanup lib/kobject.c:681 [inline] kobject_release lib/kobject.c:712 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1cd/0x350 lib/kobject.c:729 put_device+0x1b/0x30 drivers/base/core.c:3805 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585 __dev_close net/core/dev.c:1597 [inline] __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649 dev_change_fl ---truncated---
CVE-2026-31399: In the Linux kernel, the following vulnerability has been resolved: nvdimm/bus: Fix potential use after free in asynchronous initialization Dingisoul with KASAN reports a use after free if device_add() fails in nd_async_device_register(). Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while scheduling async init") correctly added a reference on the parent device to be held until asynchronous initialization was complete. However, if device_add() results in an allocation failure the ref count of the device drops to 0 prior to the parent pointer being accessed. Thus resulting in use after free. The bug bot AI correctly identified the fix. Save a reference to the parent pointer to be used to drop the parent reference regardless of the outcome of device_add().
CVE-2026-31400: In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed while in the middle of reading a cache_request (rp->offset != 0), cache_release() decrements the request's readers count but never checks whether it should free the request. In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the cache_request is removed from the queue and freed along with its buffer and cache_head reference. cache_release() lacks this cleanup. The only other path that frees requests with readers == 0 is cache_dequeue(), but it runs only when CACHE_PENDING transitions from set to clear. If that transition already happened while readers was still non-zero, cache_dequeue() will have skipped the request, and no subsequent call will clean it up. Add the same cleanup logic from cache_read() to cache_release(): after decrementing readers, check if it reached 0 with CACHE_PENDING clear, and if so, dequeue and free the cache_request.
CVE-2026-31401: In the Linux kernel, the following vulnerability has been resolved: HID: bpf: prevent buffer overflow in hid_hw_request right now the returned value is considered to be always valid. However, when playing with HID-BPF, the return value can be arbitrary big, because it's the return value of dispatch_hid_bpf_raw_requests(), which calls the struct_ops and we have no guarantees that the value makes sense.
CVE-2026-31402: In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request.
CVE-2026-31403: In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/exports proc entry is created at module init and persists for the module's lifetime. exports_proc_open() captures the caller's current network namespace and stores its svc_export_cache in seq->private, but takes no reference on the namespace. If the namespace is subsequently torn down (e.g. container destruction after the opener does setns() to a different namespace), nfsd_net_exit() calls nfsd_export_shutdown() which frees the cache. Subsequent reads on the still-open fd dereference the freed cache_detail, walking a freed hash table. Hold a reference on the struct net for the lifetime of the open file descriptor. This prevents nfsd_net_exit() from running -- and thus prevents nfsd_export_shutdown() from freeing the cache -- while any exports fd is open. cache_detail already stores its net pointer (cd->net, set by cache_create_net()), so exports_release() can retrieve it without additional per-file storage.
CVE-2026-31405: In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded.
CVE-2026-31406: In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini() After cancel_delayed_work_sync() is called from xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining states via __xfrm_state_delete(), which calls xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work. The following is a simple race scenario: cpu0 cpu1 cleanup_net() [Round 1] ops_undo_list() xfrm_net_exit() xfrm_nat_keepalive_net_fini() cancel_delayed_work_sync(nat_keepalive_work); xfrm_state_fini() xfrm_state_flush() xfrm_state_delete(x) __xfrm_state_delete(x) xfrm_nat_keepalive_state_updated(x) schedule_delayed_work(nat_keepalive_work); rcu_barrier(); net_complete_free(); net_passive_dec(net); llist_add(&net->defer_free_list, &defer_free_list); cleanup_net() [Round 2] rcu_barrier(); net_complete_free() kmem_cache_free(net_cachep, net); nat_keepalive_work() // on freed net To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().
CVE-2026-31407: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.
CVE-2026-31408: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.
CVE-2026-31409: In the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multichannel SMB2_SESSION_SETUP request with SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true but never clears it on the error path. This leaves the connection in a binding state where all subsequent ksmbd_session_lookup_all() calls fall back to the global sessions table. This fix it by clearing conn->binding = false in the error path.
CVE-2026-31410: In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs().
CVE-2026-31411: In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock as its first member, they share the same lifetime. Therefore using sock_hold/sock_put is sufficient to keep the vcc alive while it is being used. Note that there may be a race with sigd_close() which could mark the vcc with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns. However, sock_hold() guarantees the memory remains valid, so this race only affects the logical state, not memory safety. [1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3
CVE-2026-31412: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows.
CVE-2026-31414: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /proc to dump the helper name. Using nfct_help() without holding a reference to the master conntrack is unsafe. Use exp->master->helper in ctnetlink path if userspace does not provide an explicit helper when creating an expectation to retain the existing behaviour. The ctnetlink expectation path holds the reference on the master conntrack and nf_conntrack_expect lock and the nfnetlink glue path refers to the master ct that is attached to the skb.
CVE-2026-31415: In the Linux kernel, the following vulnerability has been resolved: ipv6: avoid overflows in ip6_datagram_send_ctl() Yiming Qian reported : <quote> I believe I found a locally triggerable kernel bug in the IPv6 sendmsg ancillary-data path that can panic the kernel via `skb_under_panic()` (local DoS). The core issue is a mismatch between: - a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type `__u16`) and - a pointer to the *last* provided destination-options header (`opt->dst1opt`) when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided. - `include/net/ipv6.h`: - `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible). (lines 291-307, especially 298) - `net/ipv6/datagram.c:ip6_datagram_send_ctl()`: - Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen` without rejecting duplicates. (lines 909-933) - `net/ipv6/ip6_output.c:__ip6_append_data()`: - Uses `opt->opt_flen + opt->opt_nflen` to compute header sizes/headroom decisions. (lines 1448-1466, especially 1463-1465) - `net/ipv6/ip6_output.c:__ip6_make_skb()`: - Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero. (lines 1930-1934) - `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`: - Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the pointed-to header). (lines 1179-1185 and 1206-1211) 1. `opt_flen` is a 16-bit accumulator: - `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr */`. 2. `ip6_datagram_send_ctl()` accepts *repeated* `IPV6_DSTOPTS` cmsgs and increments `opt_flen` each time: - In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`: - It computes `len = ((hdr->hdrlen + 1) << 3);` - It checks `CAP_NET_RAW` using `ns_capable(net->user_ns, CAP_NET_RAW)`. (line 922) - Then it does: - `opt->opt_flen += len;` (line 927) - `opt->dst1opt = hdr;` (line 928) There is no duplicate rejection here (unlike the legacy `IPV6_2292DSTOPTS` path which rejects duplicates at `net/ipv6/datagram.c:901-904`). If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps while `dst1opt` still points to a large (2048-byte) destination-options header. In the attached PoC (`poc.c`): - 32 cmsgs with `hdrlen=255` => `len = (255+1)*8 = 2048` - 1 cmsg with `hdrlen=0` => `len = 8` - Total increment: `32*2048 + 8 = 65544`, so `(__u16)opt_flen == 8` - The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header. 3. The transmit path sizes headers using the wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1463-1465`: - `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + ...;` With wrapped `opt_flen`, `headersize`/headroom decisions underestimate what will be pushed later. 4. When building the final skb, the actual push length comes from `dst1opt` and is not limited by wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1930-1934`: - `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);` - In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes `dst1opt` via `ipv6_push_exthdr()`. - In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does: - `skb_push(skb, ipv6_optlen(opt));` - `memcpy(h, opt, ipv6_optlen(opt));` With insufficient headroom, `skb_push()` underflows and triggers `skb_under_panic()` -> `BUG()`: - `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`) - `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`) - The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`). - Root (or any task with `CAP_NET_RAW`) can trigger this without user namespaces. - An unprivileged `uid=1000` user can trigger this if unprivileged user namespaces are enabled and it can create a userns+netns to obtain namespaced `CAP_NET_RAW` (the attached PoC does this). - Local denial of service: kernel BUG/panic (system crash). - ---truncated---
CVE-2026-31416: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: account for netlink header size This is a followup to an old bug fix: NLMSG_DONE needs to account for the netlink header size, not just the attribute size. This can result in a WARN splat + drop of the netlink message, but other than this there are no ill effects.
CVE-2026-31417: In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`.
CVE-2026-31418: In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: drop logically empty buckets in mtype_del mtype_del() counts empty slots below n->pos in k, but it only drops the bucket when both n->pos and k are zero. This misses buckets whose live entries have all been removed while n->pos still points past deleted slots. Treat a bucket as empty when all positions below n->pos are unused and release it directly instead of shrinking it further.
CVE-2026-31419: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================
CVE-2026-31420: In the Linux kernel, the following vulnerability has been resolved: bridge: mrp: reject zero test interval to avoid OOM panic br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied interval value from netlink without validation. When interval is 0, usecs_to_jiffies(0) yields 0, causing the delayed work (br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule itself with zero delay. This creates a tight loop on system_percpu_wq that allocates and transmits MRP test frames at maximum rate, exhausting all system memory and causing a kernel panic via OOM deadlock. The same zero-interval issue applies to br_mrp_start_in_test_parse() for interconnect test frames. Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both IFLA_BRIDGE_MRP_START_TEST_INTERVAL and IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the netlink attribute parsing layer before the value ever reaches the workqueue scheduling code. This is consistent with how other bridge subsystems (br_fdb, br_mst) enforce range constraints on netlink attributes.
CVE-2026-31421: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_fw: fix NULL pointer dereference on shared blocks The old-method path in fw_classify() calls tcf_block_q() and dereferences q->handle. Shared blocks leave block->q NULL, causing a NULL deref when an empty cls_fw filter is attached to a shared block and a packet with a nonzero major skb mark is classified. Reject the configuration in fw_change() when the old method (no TCA_OPTIONS) is used on a shared block, since fw_classify()'s old-method path needs block->q which is NULL for shared blocks. The fixed null-ptr-deref calling stack: KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:fw_classify (net/sched/cls_fw.c:81) Call Trace: tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860) tc_run (net/core/dev.c:4401) __dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790)
CVE-2026-31422: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_flow: fix NULL pointer dereference on shared blocks flow_change() calls tcf_block_q() and dereferences q->handle to derive a default baseclass. Shared blocks leave block->q NULL, causing a NULL deref when a flow filter without a fully qualified baseclass is created on a shared block. Check tcf_block_shared() before accessing block->q and return -EINVAL for shared blocks. This avoids the null-deref shown below: ======================================================================= KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:flow_change (net/sched/cls_flow.c:508) Call Trace: tc_new_tfilter (net/sched/cls_api.c:2432) rtnetlink_rcv_msg (net/core/rtnetlink.c:6980) [...] =======================================================================
CVE-2026-31423: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_hfsc: fix divide-by-zero in rtsc_min() m2sm() converts a u32 slope to a u64 scaled value. For large inputs (e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores the difference of two such u64 values in a u32 variable `dsm` and uses it as a divisor. When the difference is exactly 2^32 the truncation yields zero, causing a divide-by-zero oops in the concave-curve intersection path: Oops: divide error: 0000 RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601) Call Trace: init_ed (net/sched/sch_hfsc.c:629) hfsc_enqueue (net/sched/sch_hfsc.c:1569) [...] Widen `dsm` to u64 and replace do_div() with div64_u64() so the full difference is preserved.
CVE-2026-31424: In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: restrict xt_check_match/xt_check_target extensions for NFPROTO_ARP Weiming Shi says: xt_match and xt_target structs registered with NFPROTO_UNSPEC can be loaded by any protocol family through nft_compat. When such a match/target sets .hooks to restrict which hooks it may run on, the bitmask uses NF_INET_* constants. This is only correct for families whose hook layout matches NF_INET_*: IPv4, IPv6, INET, and bridge all share the same five hooks (PRE_ROUTING ... POST_ROUTING). ARP only has three hooks (IN=0, OUT=1, FORWARD=2) with different semantics. Because NF_ARP_OUT == 1 == NF_INET_LOCAL_IN, the .hooks validation silently passes for the wrong reasons, allowing matches to run on ARP chains where the hook assumptions (e.g. state->in being set on input hooks) do not hold. This leads to NULL pointer dereferences; xt_devgroup is one concrete example: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000044: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000220-0x0000000000000227] RIP: 0010:devgroup_mt+0xff/0x350 Call Trace: <TASK> nft_match_eval (net/netfilter/nft_compat.c:407) nft_do_chain (net/netfilter/nf_tables_core.c:285) nft_do_chain_arp (net/netfilter/nft_chain_filter.c:61) nf_hook_slow (net/netfilter/core.c:623) arp_xmit (net/ipv4/arp.c:666) </TASK> Kernel panic - not syncing: Fatal exception in interrupt Fix it by restricting arptables to NFPROTO_ARP extensions only. Note that arptables-legacy only supports: - arpt_CLASSIFY - arpt_mangle - arpt_MARK that provide explicit NFPROTO_ARP match/target declarations.
CVE-2026-31425: In the Linux kernel, the following vulnerability has been resolved: rds: ib: reject FRMR registration before IB connection is established rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with i_cm_id = NULL because the connection worker has not yet called rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses the control message before any connection establishment, allowing rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the kernel. The existing guard in rds_ib_reg_frmr() only checks for !ic (added in commit 9e630bcb7701), which does not catch this case since ic is allocated early and is always non-NULL once the connection object exists. KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920 Call Trace: rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167) rds_ib_map_frmr (net/rds/ib_frmr.c:252) rds_ib_reg_frmr (net/rds/ib_frmr.c:430) rds_ib_get_mr (net/rds/ib_rdma.c:615) __rds_rdma_map (net/rds/rdma.c:295) rds_cmsg_rdma_map (net/rds/rdma.c:860) rds_sendmsg (net/rds/send.c:1363) ____sys_sendmsg do_syscall_64 Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all non-NULL before proceeding with FRMR registration, mirroring the guard already present in rds_ib_post_inv(). Return -ENODEV when the connection is not ready, which the existing error handling in rds_cmsg_send() converts to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to start the connection worker.
CVE-2026-31426: In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: <TASK> mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) </TASK> Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC
CVE-2026-31427: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp process_sdp() declares union nf_inet_addr rtp_addr on the stack and passes it to the nf_nat_sip sdp_session hook after walking the SDP media descriptions. However rtp_addr is only initialized inside the media loop when a recognized media type with a non-zero port is found. If the SDP body contains no m= lines, only inactive media sections (m=audio 0 ...) or only unrecognized media types, rtp_addr is never assigned. Despite that, the function still calls hooks->sdp_session() with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack value as an IP address and rewrite the SDP session owner and connection lines with it. With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this results in the session-level o= and c= addresses being rewritten to 0.0.0.0 for inactive SDP sessions. Without stack auto-init the rewritten address is whatever happened to be on the stack. Fix this by pre-initializing rtp_addr from the session-level connection address (caddr) when available, and tracking via a have_rtp_addr flag whether any valid address was established. Skip the sdp_session hook entirely when no valid address exists.
CVE-2026-31428: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD __build_packet_message() manually constructs the NFULA_PAYLOAD netlink attribute using skb_put() and skb_copy_bits(), bypassing the standard nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes are allocated (including NLA alignment padding), only data_len bytes of actual packet data are copied. The trailing nla_padlen(data_len) bytes (1-3 when data_len is not 4-byte aligned) are never initialized, leaking stale heap contents to userspace via the NFLOG netlink socket. Replace the manual attribute construction with nla_reserve(), which handles the tailroom check, header setup, and padding zeroing via __nla_reserve(). The subsequent skb_copy_bits() fills in the payload data on top of the properly initialized attribute.
CVE-2026-31429: In the Linux kernel, the following vulnerability has been resolved: net: skb: fix cross-cache free of KFENCE-allocated skb head SKB_SMALL_HEAD_CACHE_SIZE is intentionally set to a non-power-of-2 value (e.g. 704 on x86_64) to avoid collisions with generic kmalloc bucket sizes. This ensures that skb_kfree_head() can reliably use skb_end_offset to distinguish skb heads allocated from skb_small_head_cache vs. generic kmalloc caches. However, when KFENCE is enabled, kfence_ksize() returns the exact requested allocation size instead of the slab bucket size. If a caller (e.g. bpf_test_init) allocates skb head data via kzalloc() and the requested size happens to equal SKB_SMALL_HEAD_CACHE_SIZE, then slab_build_skb() -> ksize() returns that exact value. After subtracting skb_shared_info overhead, skb_end_offset ends up matching SKB_SMALL_HEAD_HEADROOM, causing skb_kfree_head() to incorrectly free the object to skb_small_head_cache instead of back to the original kmalloc cache, resulting in a slab cross-cache free: kmem_cache_free(skbuff_small_head): Wrong slab cache. Expected skbuff_small_head but got kmalloc-1k Fix this by always calling kfree(head) in skb_kfree_head(). This keeps the free path generic and avoids allocator-specific misclassification for KFENCE objects.
CVE-2026-31430: In the Linux kernel, the following vulnerability has been resolved: X.509: Fix out-of-bounds access when parsing extensions Leo reports an out-of-bounds access when parsing a certificate with empty Basic Constraints or Key Usage extension because the first byte of the extension is read before checking its length. Fix it. The bug can be triggered by an unprivileged user by submitting a specially crafted certificate to the kernel through the keyrings(7) API. Leo has demonstrated this with a proof-of-concept program responsibly disclosed off-list.
CVE-2026-31431: In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.
CVE-2026-31432: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix OOB write in QUERY_INFO for compound requests When a compound request such as READ + QUERY_INFO(Security) is received, and the first command (READ) consumes most of the response buffer, ksmbd could write beyond the allocated buffer while building a security descriptor. The root cause was that smb2_get_info_sec() checked buffer space using ppntsd_size from xattr, while build_sec_desc() often synthesized a significantly larger descriptor from POSIX ACLs. This patch introduces smb_acl_sec_desc_scratch_len() to accurately compute the final descriptor size beforehand, performs proper buffer checking with smb2_calc_max_out_buf_len(), and uses exact-sized allocation + iov pinning.
CVE-2026-31433: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix potencial OOB in get_file_all_info() for compound requests When a compound request consists of QUERY_DIRECTORY + QUERY_INFO (FILE_ALL_INFORMATION) and the first command consumes nearly the entire max_trans_size, get_file_all_info() would blindly call smbConvertToUTF16() with PATH_MAX, causing out-of-bounds write beyond the response buffer. In get_file_all_info(), there was a missing validation check for the client-provided OutputBufferLength before copying the filename into FileName field of the smb2_file_all_info structure. If the filename length exceeds the available buffer space, it could lead to potential buffer overflows or memory corruption during smbConvertToUTF16 conversion. This calculating the actual free buffer size using smb2_calc_max_out_buf_len() and returning -EINVAL if the buffer is insufficient and updating smbConvertToUTF16 to use the actual filename length (clamped by PATH_MAX) to ensure a safe copy operation.
CVE-2026-31434: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix leak of kobject name for sub-group space_info When create_space_info_sub_group() allocates elements of space_info->sub_group[], kobject_init_and_add() is called for each element via btrfs_sysfs_add_space_info_type(). However, when check_removing_space_info() frees these elements, it does not call btrfs_sysfs_remove_space_info() on them. As a result, kobject_put() is not called and the associated kobj->name objects are leaked. This memory leak is reproduced by running the blktests test case zbd/009 on kernels built with CONFIG_DEBUG_KMEMLEAK. The kmemleak feature reports the following error: unreferenced object 0xffff888112877d40 (size 16): comm "mount", pid 1244, jiffies 4294996972 hex dump (first 16 bytes): 64 61 74 61 2d 72 65 6c 6f 63 00 c4 c6 a7 cb 7f data-reloc...... backtrace (crc 53ffde4d): __kmalloc_node_track_caller_noprof+0x619/0x870 kstrdup+0x42/0xc0 kobject_set_name_vargs+0x44/0x110 kobject_init_and_add+0xcf/0x150 btrfs_sysfs_add_space_info_type+0xfc/0x210 [btrfs] create_space_info_sub_group.constprop.0+0xfb/0x1b0 [btrfs] create_space_info+0x211/0x320 [btrfs] btrfs_init_space_info+0x15a/0x1b0 [btrfs] open_ctree+0x33c7/0x4a50 [btrfs] btrfs_get_tree.cold+0x9f/0x1ee [btrfs] vfs_get_tree+0x87/0x2f0 vfs_cmd_create+0xbd/0x280 __do_sys_fsconfig+0x3df/0x990 do_syscall_64+0x136/0x1540 entry_SYSCALL_64_after_hwframe+0x76/0x7e To avoid the leak, call btrfs_sysfs_remove_space_info() instead of kfree() for the elements.
CVE-2026-31435: In the Linux kernel, the following vulnerability has been resolved: netfs: Fix read abandonment during retry Under certain circumstances, all the remaining subrequests from a read request will get abandoned during retry. The abandonment process expects the 'subreq' variable to be set to the place to start abandonment from, but it doesn't always have a useful value (it will be uninitialised on the first pass through the loop and it may point to a deleted subrequest on later passes). Fix the first jump to "abandon:" to set subreq to the start of the first subrequest expected to need retry (which, in this abandonment case, turned out unexpectedly to no longer have NEED_RETRY set). Also clear the subreq pointer after discarding superfluous retryable subrequests to cause an oops if we do try to access it.
CVE-2026-31436: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: fix possible wrong descriptor completion in llist_abort_desc() At the end of this function, d is the traversal cursor of flist, but the code completes found instead. This can lead to issues such as NULL pointer dereferences, double completion, or descriptor leaks. Fix this by completing d instead of found in the final list_for_each_entry_safe() loop.
CVE-2026-31438: In the Linux kernel, the following vulnerability has been resolved: netfs: Fix kernel BUG in netfs_limit_iter() for ITER_KVEC iterators When a process crashes and the kernel writes a core dump to a 9P filesystem, __kernel_write() creates an ITER_KVEC iterator. This iterator reaches netfs_limit_iter() via netfs_unbuffered_write(), which only handles ITER_FOLIOQ, ITER_BVEC and ITER_XARRAY iterator types, hitting the BUG() for any other type. Fix this by adding netfs_limit_kvec() following the same pattern as netfs_limit_bvec(), since both kvec and bvec are simple segment arrays with pointer and length fields. Dispatch it from netfs_limit_iter() when the iterator type is ITER_KVEC.
CVE-2026-31439: In the Linux kernel, the following vulnerability has been resolved: dmaengine: xilinx: xdma: Fix regmap init error handling devm_regmap_init_mmio returns an ERR_PTR() upon error, not NULL. Fix the error check and also fix the error message. Use the error code from ERR_PTR() instead of the wrong value in ret.
CVE-2026-31440: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix leaking event log memory During the device remove process, the device is reset, causing the configuration registers to go back to their default state, which is zero. As the driver is checking if the event log support was enabled before deallocating, it will fail if a reset happened before. Do not check if the support was enabled, the check for 'idxd->evl' being valid (only allocated if the HW capability is available) is enough.
CVE-2026-31441: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix memory leak when a wq is reset idxd_wq_disable_cleanup() which is called from the reset path for a workqueue, sets the wq type to NONE, which for other parts of the driver mean that the wq is empty (all its resources were released). Only set the wq type to NONE after its resources are released.
CVE-2026-31446: In the Linux kernel, the following vulnerability has been resolved: ext4: fix use-after-free in update_super_work when racing with umount Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups reads during unmount. However, this introduced a use-after-free because update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which accesses the kobject's kernfs_node after it has been freed by kobject_del() in ext4_unregister_sysfs(): update_super_work ext4_put_super ----------------- -------------- ext4_unregister_sysfs(sb) kobject_del(&sbi->s_kobj) __kobject_del() sysfs_remove_dir() kobj->sd = NULL sysfs_put(sd) kernfs_put() // RCU free ext4_notify_error_sysfs(sbi) sysfs_notify(&sbi->s_kobj) kn = kobj->sd // stale pointer kernfs_get(kn) // UAF on freed kernfs_node ext4_journal_destroy() flush_work(&sbi->s_sb_upd_work) Instead of reordering the teardown sequence, fix this by making ext4_notify_error_sysfs() detect that sysfs has already been torn down by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call in that case. A dedicated mutex (s_error_notify_mutex) serializes ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs() to prevent TOCTOU races where the kobject could be deleted between the state_in_sysfs check and the sysfs_notify() call.
CVE-2026-31447: In the Linux kernel, the following vulnerability has been resolved: ext4: reject mount if bigalloc with s_first_data_block != 0 bigalloc with s_first_data_block != 0 is not supported, reject mounting it.
CVE-2026-31448: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid infinite loops caused by residual data On the mkdir/mknod path, when mapping logical blocks to physical blocks, if inserting a new extent into the extent tree fails (in this example, because the file system disabled the huge file feature when marking the inode as dirty), ext4_ext_map_blocks() only calls ext4_free_blocks() to reclaim the physical block without deleting the corresponding data in the extent tree. This causes subsequent mkdir operations to reference the previously reclaimed physical block number again, even though this physical block is already being used by the xattr block. Therefore, a situation arises where both the directory and xattr are using the same buffer head block in memory simultaneously. The above causes ext4_xattr_block_set() to enter an infinite loop about "inserted" and cannot release the inode lock, ultimately leading to the 143s blocking problem mentioned in [1]. If the metadata is corrupted, then trying to remove some extent space can do even more harm. Also in case EXT4_GET_BLOCKS_DELALLOC_RESERVE was passed, remove space wrongly update quota information. Jan Kara suggests distinguishing between two cases: 1) The error is ENOSPC or EDQUOT - in this case the filesystem is fully consistent and we must maintain its consistency including all the accounting. However these errors can happen only early before we've inserted the extent into the extent tree. So current code works correctly for this case. 2) Some other error - this means metadata is corrupted. We should strive to do as few modifications as possible to limit damage. So I'd just skip freeing of allocated blocks. [1] INFO: task syz.0.17:5995 blocked for more than 143 seconds. Call Trace: inode_lock_nested include/linux/fs.h:1073 [inline] __start_dirop fs/namei.c:2923 [inline] start_dirop fs/namei.c:2934 [inline]
CVE-2026-31449: In the Linux kernel, the following vulnerability has been resolved: ext4: validate p_idx bounds in ext4_ext_correct_indexes ext4_ext_correct_indexes() walks up the extent tree correcting index entries when the first extent in a leaf is modified. Before accessing path[k].p_idx->ei_block, there is no validation that p_idx falls within the valid range of index entries for that level. If the on-disk extent header contains a corrupted or crafted eh_entries value, p_idx can point past the end of the allocated buffer, causing a slab-out-of-bounds read. Fix this by validating path[k].p_idx against EXT_LAST_INDEX() at both access sites: before the while loop and inside it. Return -EFSCORRUPTED if the index pointer is out of range, consistent with how other bounds violations are handled in the ext4 extent tree code.
CVE-2026-31450: In the Linux kernel, the following vulnerability has been resolved: ext4: publish jinode after initialization ext4_inode_attach_jinode() publishes ei->jinode to concurrent users. It used to set ei->jinode before jbd2_journal_init_jbd_inode(), allowing a reader to observe a non-NULL jinode with i_vfs_inode still unset. The fast commit flush path can then pass this jinode to jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and may crash. Below is the crash I observe: ``` BUG: unable to handle page fault for address: 000000010beb47f4 PGD 110e51067 P4D 110e51067 PUD 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014 RIP: 0010:xas_find_marked+0x3d/0x2e0 Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02 RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246 RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003 RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10 RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000 R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88 FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> filemap_get_folios_tag+0x87/0x2a0 __filemap_fdatawait_range+0x5f/0xd0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __schedule+0x3e7/0x10c0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? cap_safe_nice+0x37/0x70 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 filemap_fdatawait_range_keep_errors+0x12/0x40 ext4_fc_commit+0x697/0x8b0 ? ext4_file_write_iter+0x64b/0x950 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? vfs_write+0x356/0x480 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ext4_sync_file+0xf7/0x370 do_fsync+0x3b/0x80 ? syscall_trace_enter+0x108/0x1d0 __x64_sys_fdatasync+0x16/0x20 do_syscall_64+0x62/0x2c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... ``` Fix this by initializing the jbd2_inode first. Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after initialization. Readers use READ_ONCE() to fetch the pointer.
CVE-2026-31451: In the Linux kernel, the following vulnerability has been resolved: ext4: replace BUG_ON with proper error handling in ext4_read_inline_folio Replace BUG_ON() with proper error handling when inline data size exceeds PAGE_SIZE. This prevents kernel panic and allows the system to continue running while properly reporting the filesystem corruption. The error is logged via ext4_error_inode(), the buffer head is released to prevent memory leak, and -EFSCORRUPTED is returned to indicate filesystem corruption.
CVE-2026-31452: In the Linux kernel, the following vulnerability has been resolved: ext4: convert inline data to extents when truncate exceeds inline size Add a check in ext4_setattr() to convert files from inline data storage to extent-based storage when truncate() grows the file size beyond the inline capacity. This prevents the filesystem from entering an inconsistent state where the inline data flag is set but the file size exceeds what can be stored inline. Without this fix, the following sequence causes a kernel BUG_ON(): 1. Mount filesystem with inode that has inline flag set and small size 2. truncate(file, 50MB) - grows size but inline flag remains set 3. sendfile() attempts to write data 4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity) The crash occurs because ext4_write_inline_data() expects inline storage to accommodate the write, but the actual inline capacity (~60 bytes for i_block + ~96 bytes for xattrs) is far smaller than the file size and write request. The fix checks if the new size from setattr exceeds the inode's actual inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to extent-based storage before proceeding with the size change. This addresses the root cause by ensuring the inline data flag and file size remain consistent during truncate operations.
CVE-2026-31453: In the Linux kernel, the following vulnerability has been resolved: xfs: avoid dereferencing log items after push callbacks After xfsaild_push_item() calls iop_push(), the log item may have been freed if the AIL lock was dropped during the push. Background inode reclaim or the dquot shrinker can free the log item while the AIL lock is not held, and the tracepoints in the switch statement dereference the log item after iop_push() returns. Fix this by capturing the log item type, flags, and LSN before calling xfsaild_push_item(), and introducing a new xfs_ail_push_class trace event class that takes these pre-captured values and the ailp pointer instead of the log item pointer.
CVE-2026-31454: In the Linux kernel, the following vulnerability has been resolved: xfs: save ailp before dropping the AIL lock in push callbacks In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock is dropped to perform buffer IO. Once the cluster buffer no longer protects the log item from reclaim, the log item may be freed by background reclaim or the dquot shrinker. The subsequent spin_lock() call dereferences lip->li_ailp, which is a use-after-free. Fix this by saving the ailp pointer in a local variable while the AIL lock is held and the log item is guaranteed to be valid.
CVE-2026-31455: In the Linux kernel, the following vulnerability has been resolved: xfs: stop reclaim before pushing AIL during unmount The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while background reclaim and inodegc are still running. This is broken independently of any use-after-free issues - background reclaim and inodegc should not be running while the AIL is being pushed during unmount, as inodegc can dirty and insert inodes into the AIL during the flush, and background reclaim can race to abort and free dirty inodes. Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background reclaim before pushing the AIL. Stop inodegc before cancelling m_reclaim_work because the inodegc worker can re-queue m_reclaim_work via xfs_inodegc_set_reclaimable.
CVE-2026-31456: In the Linux kernel, the following vulnerability has been resolved: mm/pagewalk: fix race between concurrent split and refault The splitting of a PUD entry in walk_pud_range() can race with a concurrent thread refaulting the PUD leaf entry causing it to try walking a PMD range that has disappeared. An example and reproduction of this is to try reading numa_maps of a process while VFIO-PCI is setting up DMA (specifically the vfio_pin_pages_remote call) on a large BAR for that process. This will trigger a kernel BUG: vfio-pci 0000:03:00.0: enabling device (0000 -> 0002) BUG: unable to handle page fault for address: ffffa23980000000 PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI ... RIP: 0010:walk_pgd_range+0x3b5/0x7a0 Code: 8d 43 ff 48 89 44 24 28 4d 89 ce 4d 8d a7 00 00 20 00 48 8b 4c 24 28 49 81 e4 00 00 e0 ff 49 8d 44 24 ff 48 39 c8 4c 0f 43 e3 <49> f7 06 9f ff ff ff 75 3b 48 8b 44 24 20 48 8b 40 28 48 85 c0 74 RSP: 0018:ffffac23e1ecf808 EFLAGS: 00010287 RAX: 00007f44c01fffff RBX: 00007f4500000000 RCX: 00007f44ffffffff RDX: 0000000000000000 RSI: 000ffffffffff000 RDI: ffffffff93378fe0 RBP: ffffac23e1ecf918 R08: 0000000000000004 R09: ffffa23980000000 R10: 0000000000000020 R11: 0000000000000004 R12: 00007f44c0200000 R13: 00007f44c0000000 R14: ffffa23980000000 R15: 00007f44c0000000 FS: 00007fe884739580(0000) GS:ffff9b7d7a9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffa23980000000 CR3: 000000c0650e2005 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: <TASK> __walk_page_range+0x195/0x1b0 walk_page_vma+0x62/0xc0 show_numa_map+0x12b/0x3b0 seq_read_iter+0x297/0x440 seq_read+0x11d/0x140 vfs_read+0xc2/0x340 ksys_read+0x5f/0xe0 do_syscall_64+0x68/0x130 ? get_page_from_freelist+0x5c2/0x17e0 ? mas_store_prealloc+0x17e/0x360 ? vma_set_page_prot+0x4c/0xa0 ? __alloc_pages_noprof+0x14e/0x2d0 ? __mod_memcg_lruvec_state+0x8d/0x140 ? __lruvec_stat_mod_folio+0x76/0xb0 ? __folio_mod_stat+0x26/0x80 ? do_anonymous_page+0x705/0x900 ? __handle_mm_fault+0xa8d/0x1000 ? __count_memcg_events+0x53/0xf0 ? handle_mm_fault+0xa5/0x360 ? do_user_addr_fault+0x342/0x640 ? arch_exit_to_user_mode_prepare.constprop.0+0x16/0xa0 ? irqentry_exit_to_user_mode+0x24/0x100 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fe88464f47e Code: c0 e9 b6 fe ff ff 50 48 8d 3d be 07 0b 00 e8 69 01 02 00 66 0f 1f 84 00 00 00 00 00 64 8b 04 25 18 00 00 00 85 c0 75 14 0f 05 <48> 3d 00 f0 ff ff 77 5a c3 66 0f 1f 84 00 00 00 00 00 48 83 ec 28 RSP: 002b:00007ffe6cd9a9b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007fe88464f47e RDX: 0000000000020000 RSI: 00007fe884543000 RDI: 0000000000000003 RBP: 00007fe884543000 R08: 00007fe884542010 R09: 0000000000000000 R10: fffffffffffffbc5 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000 </TASK> Fix this by validating the PUD entry in walk_pmd_range() using a stable snapshot (pudp_get()). If the PUD is not present or is a leaf, retry the walk via ACTION_AGAIN instead of descending further. This mirrors the retry logic in walk_pte_range(), which lets walk_pmd_range() retry if the PTE is not being got by pte_offset_map_lock().
CVE-2026-31458: In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: check contexts->nr before accessing contexts_arr[0] Multiple sysfs command paths dereference contexts_arr[0] without first verifying that kdamond->contexts->nr == 1. A user can set nr_contexts to 0 via sysfs while DAMON is running, causing NULL pointer dereferences. In more detail, the issue can be triggered by privileged users like below. First, start DAMON and make contexts directory empty (kdamond->contexts->nr == 0). # damo start # cd /sys/kernel/mm/damon/admin/kdamonds/0 # echo 0 > contexts/nr_contexts Then, each of below commands will cause the NULL pointer dereference. # echo update_schemes_stats > state # echo update_schemes_tried_regions > state # echo update_schemes_tried_bytes > state # echo update_schemes_effective_quotas > state # echo update_tuned_intervals > state Guard all commands (except OFF) at the entry point of damon_sysfs_handle_cmd().
CVE-2026-31462: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: prevent immediate PASID reuse case PASID resue could cause interrupt issue when process immediately runs into hw state left by previous process exited with the same PASID, it's possible that page faults are still pending in the IH ring buffer when the process exits and frees up its PASID. To prevent the case, it uses idr cyclic allocator same as kernel pid's. (cherry picked from commit 8f1de51f49be692de137c8525106e0fce2d1912d)
CVE-2026-31464: In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Fix OOB access in ibmvfc_discover_targets_done() A malicious or compromised VIO server can return a num_written value in the discover targets MAD response that exceeds max_targets. This value is stored directly in vhost->num_targets without validation, and is then used as the loop bound in ibmvfc_alloc_targets() to index into disc_buf[], which is only allocated for max_targets entries. Indices at or beyond max_targets access kernel memory outside the DMA-coherent allocation. The out-of-bounds data is subsequently embedded in Implicit Logout and PLOGI MADs that are sent back to the VIO server, leaking kernel memory. Fix by clamping num_written to max_targets before storing it.
CVE-2026-31466: In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix folio isn't locked in softleaf_to_folio() On arm64 server, we found folio that get from migration entry isn't locked in softleaf_to_folio(). This issue triggers when mTHP splitting and zap_nonpresent_ptes() races, and the root cause is lack of memory barrier in softleaf_to_folio(). The race is as follows: CPU0 CPU1 deferred_split_scan() zap_nonpresent_ptes() lock folio split_folio() unmap_folio() change ptes to migration entries __split_folio_to_order() softleaf_to_folio() set flags(including PG_locked) for tail pages folio = pfn_folio(softleaf_to_pfn(entry)) smp_wmb() VM_WARN_ON_ONCE(!folio_test_locked(folio)) prep_compound_page() for tail pages In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages are visible before the tail page becomes non-compound. smp_wmb() should be paired with smp_rmb() in softleaf_to_folio(), which is missed. As a result, if zap_nonpresent_ptes() accesses migration entry that stores tail pfn, softleaf_to_folio() may see the updated compound_head of tail page before page->flags. This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio() because of the race between folio split and zap_nonpresent_ptes() leading to a folio incorrectly undergoing modification without a folio lock being held. This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further swapops predicates"), which in merged in v6.19-rc1. To fix it, add missing smp_rmb() if the softleaf entry is migration entry in softleaf_to_folio() and softleaf_to_page(). [tujinjiang@huawei.com: update function name and comments]
CVE-2026-31467: In the Linux kernel, the following vulnerability has been resolved: erofs: add GFP_NOIO in the bio completion if needed The bio completion path in the process context (e.g. dm-verity) will directly call into decompression rather than trigger another workqueue context for minimal scheduling latencies, which can then call vm_map_ram() with GFP_KERNEL. Due to insufficient memory, vm_map_ram() may generate memory swapping I/O, which can cause submit_bio_wait to deadlock in some scenarios. Trimmed down the call stack, as follows: f2fs_submit_read_io submit_bio //bio_list is initialized. mmc_blk_mq_recovery z_erofs_endio vm_map_ram __pte_alloc_kernel __alloc_pages_direct_reclaim shrink_folio_list __swap_writepage submit_bio_wait //bio_list is non-NULL, hang!!! Use memalloc_noio_{save,restore}() to wrap up this path.
CVE-2026-31469: In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared and napi_tx is false A UAF issue occurs when the virtio_net driver is configured with napi_tx=N and the device's IFF_XMIT_DST_RELEASE flag is cleared (e.g., during the configuration of tc route filter rules). When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack expects the driver to hold the reference to skb->dst until the packet is fully transmitted and freed. In virtio_net with napi_tx=N, skbs may remain in the virtio transmit ring for an extended period. If the network namespace is destroyed while these skbs are still pending, the corresponding dst_ops structure has freed. When a subsequent packet is transmitted, free_old_xmit() is triggered to clean up old skbs. It then calls dst_release() on the skb associated with the stale dst_entry. Since the dst_ops (referenced by the dst_entry) has already been freed, a UAF kernel paging request occurs. fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release the dst reference before the skb is queued in virtio_net. Call Trace: Unable to handle kernel paging request at virtual address ffff80007e150000 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT ... percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P) dst_release+0xe0/0x110 net/core/dst.c:177 skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177 sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255 dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469 napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527 __free_old_xmit+0x164/0x230 drivers/net/virtio_net.c:611 [virtio_net] free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net] start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net] ... Reproduction Steps: NETDEV="enp3s0" config_qdisc_route_filter() { tc qdisc del dev $NETDEV root tc qdisc add dev $NETDEV root handle 1: prio tc filter add dev $NETDEV parent 1:0 \ protocol ip prio 100 route to 100 flowid 1:1 ip route add 192.168.1.100/32 dev $NETDEV realm 100 } test_ns() { ip netns add testns ip link set $NETDEV netns testns ip netns exec testns ifconfig $NETDEV 10.0.32.46/24 ip netns exec testns ping -c 1 10.0.32.1 ip netns del testns } config_qdisc_route_filter test_ns sleep 2 test_ns
CVE-2026-31470: In the Linux kernel, the following vulnerability has been resolved: virt: tdx-guest: Fix handling of host controlled 'quote' buffer length Validate host controlled value `quote_buf->out_len` that determines how many bytes of the quote are copied out to guest userspace. In TDX environments with remote attestation, quotes are not considered private, and can be forwarded to an attestation server. Catch scenarios where the host specifies a response length larger than the guest's allocation, or otherwise races modifying the response while the guest consumes it. This prevents contents beyond the pages allocated for `quote_buf` (up to TSM_REPORT_OUTBLOB_MAX) from being read out to guest userspace, and possibly forwarded in attestation requests. Recall that some deployments want per-container configs-tsm-report interfaces, so the leak may cross container protection boundaries, not just local root.
CVE-2026-31473: In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.
CVE-2026-31474: In the Linux kernel, the following vulnerability has been resolved: can: isotp: fix tx.buf use-after-free in isotp_sendmsg() isotp_sendmsg() uses only cmpxchg() on so->tx.state to serialize access to so->tx.buf. isotp_release() waits for ISOTP_IDLE via wait_event_interruptible() and then calls kfree(so->tx.buf). If a signal interrupts the wait_event_interruptible() inside close() while tx.state is ISOTP_SENDING, the loop exits early and release proceeds to force ISOTP_SHUTDOWN and continues to kfree(so->tx.buf) while sendmsg may still be reading so->tx.buf for the final CAN frame in isotp_fill_dataframe(). The so->tx.buf can be allocated once when the standard tx.buf length needs to be extended. Move the kfree() of this potentially extended tx.buf to sk_destruct time when either isotp_sendmsg() and isotp_release() are done.
CVE-2026-31476: In the Linux kernel, the following vulnerability has been resolved: ksmbd: do not expire session on binding failure When a multichannel session binding request fails (e.g. wrong password), the error path unconditionally sets sess->state = SMB2_SESSION_EXPIRED. However, during binding, sess points to the target session looked up via ksmbd_session_lookup_slowpath() -- which belongs to another connection's user. This allows a remote attacker to invalidate any active session by simply sending a binding request with a wrong password (DoS). Fix this by skipping session expiration when the failed request was a binding attempt, since the session does not belong to the current connection. The reference taken by ksmbd_session_lookup_slowpath() is still correctly released via ksmbd_user_session_put().
CVE-2026-31477: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix memory leaks and NULL deref in smb2_lock() smb2_lock() has three error handling issues after list_del() detaches smb_lock from lock_list at no_check_cl: 1) If vfs_lock_file() returns an unexpected error in the non-UNLOCK path, goto out leaks smb_lock and its flock because the out: handler only iterates lock_list and rollback_list, neither of which contains the detached smb_lock. 2) If vfs_lock_file() returns -ENOENT in the UNLOCK path, goto out leaks smb_lock and flock for the same reason. The error code returned to the dispatcher is also stale. 3) In the rollback path, smb_flock_init() can return NULL on allocation failure. The result is dereferenced unconditionally, causing a kernel NULL pointer dereference. Add a NULL check to prevent the crash and clean up the bookkeeping; the VFS lock itself cannot be rolled back without the allocation and will be released at file or connection teardown. Fix cases 1 and 2 by hoisting the locks_free_lock()/kfree() to before the if(!rc) check in the UNLOCK branch so all exit paths share one free site, and by freeing smb_lock and flock before goto out in the non-UNLOCK branch. Propagate the correct error code in both cases. Fix case 3 by wrapping the VFS unlock in an if(rlock) guard and adding a NULL check for locks_free_lock(rlock) in the shared cleanup. Found via call-graph analysis using sqry.
CVE-2026-31478: In the Linux kernel, the following vulnerability has been resolved: ksmbd: replace hardcoded hdr2_len with offsetof() in smb2_calc_max_out_buf_len() After this commit (e2b76ab8b5c9 "ksmbd: add support for read compound"), response buffer management was changed to use dynamic iov array. In the new design, smb2_calc_max_out_buf_len() expects the second argument (hdr2_len) to be the offset of ->Buffer field in the response structure, not a hardcoded magic number. Fix the remaining call sites to use the correct offsetof() value.
CVE-2026-31479: In the Linux kernel, the following vulnerability has been resolved: drm/xe: always keep track of remap prev/next During 3D workload, user is reporting hitting: [ 413.361679] WARNING: drivers/gpu/drm/xe/xe_vm.c:1217 at vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe], CPU#7: vkd3d_queue/9925 [ 413.361944] CPU: 7 UID: 1000 PID: 9925 Comm: vkd3d_queue Kdump: loaded Not tainted 7.0.0-070000rc3-generic #202603090038 PREEMPT(lazy) [ 413.361949] RIP: 0010:vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe] [ 413.362074] RSP: 0018:ffffd4c25c3df930 EFLAGS: 00010282 [ 413.362077] RAX: 0000000000000000 RBX: ffff8f3ee817ed10 RCX: 0000000000000000 [ 413.362078] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 413.362079] RBP: ffffd4c25c3df980 R08: 0000000000000000 R09: 0000000000000000 [ 413.362081] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f41fbf99380 [ 413.362082] R13: ffff8f3ee817e968 R14: 00000000ffffffef R15: ffff8f43d00bd380 [ 413.362083] FS: 00000001040ff6c0(0000) GS:ffff8f4696d89000(0000) knlGS:00000000330b0000 [ 413.362085] CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 [ 413.362086] CR2: 00007ddfc4747000 CR3: 00000002e6262005 CR4: 0000000000f72ef0 [ 413.362088] PKRU: 55555554 [ 413.362089] Call Trace: [ 413.362092] <TASK> [ 413.362096] xe_vm_bind_ioctl+0xa9a/0xc60 [xe] Which seems to hint that the vma we are re-inserting for the ops unwind is either invalid or overlapping with something already inserted in the vm. It shouldn't be invalid since this is a re-insertion, so must have worked before. Leaving the likely culprit as something already placed where we want to insert the vma. Following from that, for the case where we do something like a rebind in the middle of a vma, and one or both mapped ends are already compatible, we skip doing the rebind of those vma and set next/prev to NULL. As well as then adjust the original unmap va range, to avoid unmapping the ends. However, if we trigger the unwind path, we end up with three va, with the two ends never being removed and the original va range in the middle still being the shrunken size. If this occurs, one failure mode is when another unwind op needs to interact with that range, which can happen with a vector of binds. For example, if we need to re-insert something in place of the original va. In this case the va is still the shrunken version, so when removing it and then doing a re-insert it can overlap with the ends, which were never removed, triggering a warning like above, plus leaving the vm in a bad state. With that, we need two things here: 1) Stop nuking the prev/next tracking for the skip cases. Instead relying on checking for skip prev/next, where needed. That way on the unwind path, we now correctly remove both ends. 2) Undo the unmap va shrinkage, on the unwind path. With the two ends now removed the unmap va should expand back to the original size again, before re-insertion. v2: - Update the explanation in the commit message, based on an actual IGT of triggering this issue, rather than conjecture. - Also undo the unmap shrinkage, for the skip case. With the two ends now removed, the original unmap va range should expand back to the original range. v3: - Track the old start/range separately. vma_size/start() uses the va info directly. (cherry picked from commit aec6969f75afbf4e01fd5fb5850ed3e9c27043ac)
CVE-2026-31480: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix potential deadlock in cpu hotplug with osnoise The following sequence may leads deadlock in cpu hotplug: task1 task2 task3 ----- ----- ----- mutex_lock(&interface_lock) [CPU GOING OFFLINE] cpus_write_lock(); osnoise_cpu_die(); kthread_stop(task3); wait_for_completion(); osnoise_sleep(); mutex_lock(&interface_lock); cpus_read_lock(); [DEAD LOCK] Fix by swap the order of cpus_read_lock() and mutex_lock(&interface_lock).
CVE-2026-31482: In the Linux kernel, the following vulnerability has been resolved: s390/entry: Scrub r12 register on kernel entry Before commit f33f2d4c7c80 ("s390/bp: remove TIF_ISOLATE_BP"), all entry handlers loaded r12 with the current task pointer (lg %r12,__LC_CURRENT) for use by the BPENTER/BPEXIT macros. That commit removed TIF_ISOLATE_BP, dropping both the branch prediction macros and the r12 load, but did not add r12 to the register clearing sequence. Add the missing xgr %r12,%r12 to make the register scrub consistent across all entry points.
CVE-2026-31483: In the Linux kernel, the following vulnerability has been resolved: s390/syscalls: Add spectre boundary for syscall dispatch table The s390 syscall number is directly controlled by userspace, but does not have an array_index_nospec() boundary to prevent access past the syscall function pointer tables.
CVE-2026-31485: In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().
CVE-2026-31486: In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/core) Protect regulator operations with mutex The regulator operations pmbus_regulator_get_voltage(), pmbus_regulator_set_voltage(), and pmbus_regulator_list_voltage() access PMBus registers and shared data but were not protected by the update_lock mutex. This could lead to race conditions. However, adding mutex protection directly to these functions causes a deadlock because pmbus_regulator_notify() (which calls regulator_notifier_call_chain()) is often called with the mutex already held (e.g., from pmbus_fault_handler()). If a regulator callback then calls one of the now-protected voltage functions, it will attempt to acquire the same mutex. Rework pmbus_regulator_notify() to utilize a worker function to send notifications outside of the mutex protection. Events are stored as atomics in a per-page bitmask and processed by the worker. Initialize the worker and its associated data during regulator registration, and ensure it is cancelled on device removal using devm_add_action_or_reset(). While at it, remove the unnecessary include of linux/of.h.
CVE-2026-31487: In the Linux kernel, the following vulnerability has been resolved: spi: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Also note that we do not enable the driver_override feature of struct bus_type, as SPI - in contrast to most other buses - passes "" to sysfs_emit() when the driver_override pointer is NULL. Thus, printing "\n" instead of "(null)\n".
CVE-2026-31488: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not skip unrelated mode changes in DSC validation Starting with commit 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in atomic check"), amdgpu resets the CRTC state mode_changed flag to false when recomputing the DSC configuration results in no timing change for a particular stream. However, this is incorrect in scenarios where a change in MST/DSC configuration happens in the same KMS commit as another (unrelated) mode change. For example, the integrated panel of a laptop may be configured differently (e.g., HDR enabled/disabled) depending on whether external screens are attached. In this case, plugging in external DP-MST screens may result in the mode_changed flag being dropped incorrectly for the integrated panel if its DSC configuration did not change during precomputation in pre_validate_dsc(). At this point, however, dm_update_crtc_state() has already created new streams for CRTCs with DSC-independent mode changes. In turn, amdgpu_dm_commit_streams() will never release the old stream, resulting in a memory leak. amdgpu_dm_atomic_commit_tail() will never acquire a reference to the new stream either, which manifests as a use-after-free when the stream gets disabled later on: BUG: KASAN: use-after-free in dc_stream_release+0x25/0x90 [amdgpu] Write of size 4 at addr ffff88813d836524 by task kworker/9:9/29977 Workqueue: events drm_mode_rmfb_work_fn Call Trace: <TASK> dump_stack_lvl+0x6e/0xa0 print_address_description.constprop.0+0x88/0x320 ? dc_stream_release+0x25/0x90 [amdgpu] print_report+0xfc/0x1ff ? srso_alias_return_thunk+0x5/0xfbef5 ? __virt_addr_valid+0x225/0x4e0 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_report+0xe1/0x180 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_check_range+0x125/0x200 dc_stream_release+0x25/0x90 [amdgpu] dc_state_destruct+0x14d/0x5c0 [amdgpu] dc_state_release.part.0+0x4e/0x130 [amdgpu] dm_atomic_destroy_state+0x3f/0x70 [amdgpu] drm_atomic_state_default_clear+0x8ee/0xf30 ? drm_mode_object_put.part.0+0xb1/0x130 __drm_atomic_state_free+0x15c/0x2d0 atomic_remove_fb+0x67e/0x980 Since there is no reliable way of figuring out whether a CRTC has unrelated mode changes pending at the time of DSC validation, remember the value of the mode_changed flag from before the point where a CRTC was marked as potentially affected by a change in DSC configuration. Reset the mode_changed flag to this earlier value instead in pre_validate_dsc(). (cherry picked from commit cc7c7121ae082b7b82891baa7280f1ff2608f22b)
CVE-2026-31489: In the Linux kernel, the following vulnerability has been resolved: spi: meson-spicc: Fix double-put in remove path meson_spicc_probe() registers the controller with devm_spi_register_controller(), so teardown already drops the controller reference via devm cleanup. Calling spi_controller_put() again in meson_spicc_remove() causes a double-put.
CVE-2026-31492: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Initialize free_qp completion before using it In irdma_create_qp, if ib_copy_to_udata fails, it will call irdma_destroy_qp to clean up which will attempt to wait on the free_qp completion, which is not initialized yet. Fix this by initializing the completion before the ib_copy_to_udata call.
CVE-2026-31493: In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix use of completion ctx after free On admin queue completion handling, if the admin command completed with error we print data from the completion context. The issue is that we already freed the completion context in polling/interrupts handler which means we print data from context in an unknown state (it might be already used again). Change the admin submission flow so alloc/dealloc of the context will be symmetric and dealloc will be called after any potential use of the context.
CVE-2026-31494: In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.
CVE-2026-31495: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: use netlink policy range checks Replace manual range and mask validations with netlink policy annotations in ctnetlink code paths, so that the netlink core rejects invalid values early and can generate extack errors. - CTA_PROTOINFO_TCP_STATE: reject values > TCP_CONNTRACK_SYN_SENT2 at policy level, removing the manual >= TCP_CONNTRACK_MAX check. - CTA_PROTOINFO_TCP_WSCALE_ORIGINAL/REPLY: reject values > TCP_MAX_WSCALE (14). The normal TCP option parsing path already clamps to this value, but the ctnetlink path accepted 0-255, causing undefined behavior when used as a u32 shift count. - CTA_FILTER_ORIG_FLAGS/REPLY_FLAGS: use NLA_POLICY_MASK with CTA_FILTER_F_ALL, removing the manual mask checks. - CTA_EXPECT_FLAGS: use NLA_POLICY_MASK with NF_CT_EXPECT_MASK, adding a new mask define grouping all valid expect flags. Extracted from a broader nf-next patch by Florian Westphal, scoped to ctnetlink for the fixes tree.
CVE-2026-31496: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: skip expectations in other netns via proc Skip expectations that do not reside in this netns. Similar to e77e6ff502ea ("netfilter: conntrack: do not dump other netns's conntrack entries via proc").
CVE-2026-31497: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: clamp SCO altsetting table indices btusb_work() maps the number of active SCO links to USB alternate settings through a three-entry lookup table when CVSD traffic uses transparent voice settings. The lookup currently indexes alts[] with data->sco_num - 1 without first constraining sco_num to the number of available table entries. While the table only defines alternate settings for up to three SCO links, data->sco_num comes from hci_conn_num() and is used directly. Cap the lookup to the last table entry before indexing it so the driver keeps selecting the highest supported alternate setting without reading past alts[].
CVE-2026-31498: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop l2cap_config_req() processes CONFIG_REQ for channels in BT_CONNECTED state to support L2CAP reconfiguration (e.g. MTU changes). However, since both CONF_INPUT_DONE and CONF_OUTPUT_DONE are already set from the initial configuration, the reconfiguration path falls through to l2cap_ertm_init(), which re-initializes tx_q, srej_q, srej_list, and retrans_list without freeing the previous allocations and sets chan->sdu to NULL without freeing the existing skb. This leaks all previously allocated ERTM resources. Additionally, l2cap_parse_conf_req() does not validate the minimum value of remote_mps derived from the RFC max_pdu_size option. A zero value propagates to l2cap_segment_sdu() where pdu_len becomes zero, causing the while loop to never terminate since len is never decremented, exhausting all available memory. Fix the double-init by skipping l2cap_ertm_init() and l2cap_chan_ready() when the channel is already in BT_CONNECTED state, while still allowing the reconfiguration parameters to be updated through l2cap_parse_conf_req(). Also add a pdu_len zero check in l2cap_segment_sdu() as a safeguard.
CVE-2026-31499: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix deadlock in l2cap_conn_del() l2cap_conn_del() calls cancel_delayed_work_sync() for both info_timer and id_addr_timer while holding conn->lock. However, the work functions l2cap_info_timeout() and l2cap_conn_update_id_addr() both acquire conn->lock, creating a potential AB-BA deadlock if the work is already executing when l2cap_conn_del() takes the lock. Move the work cancellations before acquiring conn->lock and use disable_delayed_work_sync() to additionally prevent the works from being rearmed after cancellation, consistent with the pattern used in hci_conn_del().
CVE-2026-31500: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock btintel_hw_error() issues two __hci_cmd_sync() calls (HCI_OP_RESET and Intel exception-info retrieval) without holding hci_req_sync_lock(). This lets it race against hci_dev_do_close() -> btintel_shutdown_combined(), which also runs __hci_cmd_sync() under the same lock. When both paths manipulate hdev->req_status/req_rsp concurrently, the close path may free the response skb first, and the still-running hw_error path hits a slab-use-after-free in kfree_skb(). Wrap the whole recovery sequence in hci_req_sync_lock/unlock so it is serialized with every other synchronous HCI command issuer. Below is the data race report and the kasan report: BUG: data-race in __hci_cmd_sync_sk / btintel_shutdown_combined read of hdev->req_rsp at net/bluetooth/hci_sync.c:199 by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x114/0x670 drivers/bluetooth/btintel.c:254 hci_error_reset+0x348/0xa30 net/bluetooth/hci_core.c:1030 write/free by task ioctl/22580: btintel_shutdown_combined+0xd0/0x360 drivers/bluetooth/btintel.c:3648 hci_dev_close_sync+0x9ae/0x2c10 net/bluetooth/hci_sync.c:5246 hci_dev_do_close+0x232/0x460 net/bluetooth/hci_core.c:526 BUG: KASAN: slab-use-after-free in sk_skb_reason_drop+0x43/0x380 net/core/skbuff.c:1202 Read of size 4 at addr ffff888144a738dc by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x186/0x670 drivers/bluetooth/btintel.c:260
CVE-2026-31502: In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.
CVE-2026-31503: In the Linux kernel, the following vulnerability has been resolved: udp: Fix wildcard bind conflict check when using hash2 When binding a udp_sock to a local address and port, UDP uses two hashes (udptable->hash and udptable->hash2) for collision detection. The current code switches to "hash2" when hslot->count > 10. "hash2" is keyed by local address and local port. "hash" is keyed by local port only. The issue can be shown in the following bind sequence (pseudo code): bind(fd1, "[fd00::1]:8888") bind(fd2, "[fd00::2]:8888") bind(fd3, "[fd00::3]:8888") bind(fd4, "[fd00::4]:8888") bind(fd5, "[fd00::5]:8888") bind(fd6, "[fd00::6]:8888") bind(fd7, "[fd00::7]:8888") bind(fd8, "[fd00::8]:8888") bind(fd9, "[fd00::9]:8888") bind(fd10, "[fd00::10]:8888") /* Correctly return -EADDRINUSE because "hash" is used * instead of "hash2". udp_lib_lport_inuse() detects the * conflict. */ bind(fail_fd, "[::]:8888") /* After one more socket is bound to "[fd00::11]:8888", * hslot->count exceeds 10 and "hash2" is used instead. */ bind(fd11, "[fd00::11]:8888") bind(fail_fd, "[::]:8888") /* succeeds unexpectedly */ The same issue applies to the IPv4 wildcard address "0.0.0.0" and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For example, if there are existing sockets bound to "192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or "[::ffff:0.0.0.0]:8888" can also miss the conflict when hslot->count > 10. TCP inet_csk_get_port() already has the correct check in inet_use_bhash2_on_bind(). Rename it to inet_use_hash2_on_bind() and move it to inet_hashtables.h so udp.c can reuse it in this fix.
CVE-2026-31504: In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.
CVE-2026-31505: In the Linux kernel, the following vulnerability has been resolved: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats() iavf incorrectly uses real_num_tx_queues for ETH_SS_STATS. Since the value could change in runtime, we should use num_tx_queues instead. Moreover iavf_get_ethtool_stats() uses num_active_queues while iavf_get_sset_count() and iavf_get_stat_strings() use real_num_tx_queues, which triggers out-of-bounds writes when we do "ethtool -L" and "ethtool -S" simultaneously [1]. For example when we change channels from 1 to 8, Thread 3 could be scheduled before Thread 2, and out-of-bounds writes could be triggered in Thread 3: Thread 1 (ethtool -L) Thread 2 (work) Thread 3 (ethtool -S) iavf_set_channels() ... iavf_alloc_queues() -> num_active_queues = 8 iavf_schedule_finish_config() iavf_get_sset_count() real_num_tx_queues: 1 -> buffer for 1 queue iavf_get_ethtool_stats() num_active_queues: 8 -> out-of-bounds! iavf_finish_config() -> real_num_tx_queues = 8 Use immutable num_tx_queues in all related functions to avoid the issue. [1] BUG: KASAN: vmalloc-out-of-bounds in iavf_add_one_ethtool_stat+0x200/0x270 Write of size 8 at addr ffffc900031c9080 by task ethtool/5800 CPU: 1 UID: 0 PID: 5800 Comm: ethtool Not tainted 6.19.0-enjuk-08403-g8137e3db7f1c #241 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x6f/0xb0 print_report+0x170/0x4f3 kasan_report+0xe1/0x180 iavf_add_one_ethtool_stat+0x200/0x270 iavf_get_ethtool_stats+0x14c/0x2e0 __dev_ethtool+0x3d0c/0x5830 dev_ethtool+0x12d/0x270 dev_ioctl+0x53c/0xe30 sock_do_ioctl+0x1a9/0x270 sock_ioctl+0x3d4/0x5e0 __x64_sys_ioctl+0x137/0x1c0 do_syscall_64+0xf3/0x690 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7da0e6e36d ... </TASK> The buggy address belongs to a 1-page vmalloc region starting at 0xffffc900031c9000 allocated at __dev_ethtool+0x3cc9/0x5830 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88813a013de0 pfn:0x13a013 flags: 0x200000000000000(node=0|zone=2) raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff88813a013de0 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffc900031c8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffc900031c9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffffc900031c9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9180: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
CVE-2026-31506: In the Linux kernel, the following vulnerability has been resolved: net: bcmasp: fix double free of WoL irq We do not need to free wol_irq since it was instantiated with devm_request_irq(). So devres will free for us.
CVE-2026-31507: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: <TASK> smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.
CVE-2026-31508: In the Linux kernel, the following vulnerability has been resolved: net: openvswitch: Avoid releasing netdev before teardown completes The patch cited in the Fixes tag below changed the teardown code for OVS ports to no longer unconditionally take the RTNL. After this change, the netdev_destroy() callback can proceed immediately to the call_rcu() invocation if the IFF_OVS_DATAPATH flag is already cleared on the netdev. The ovs_netdev_detach_dev() function clears the flag before completing the unregistration, and if it gets preempted after clearing the flag (as can happen on an -rt kernel), netdev_destroy() can complete and the device can be freed before the unregistration completes. This leads to a splat like: [ 998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI [ 998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT [ 998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025 [ 998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0 [ 998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90 [ 998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246 [ 998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000 [ 998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05 [ 998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000 [ 998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006 [ 998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000 [ 998.393931] FS: 00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000 [ 998.393936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0 [ 998.393944] PKRU: 55555554 [ 998.393946] Call Trace: [ 998.393949] <TASK> [ 998.393952] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393961] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393975] ? dp_device_event+0x41/0x80 [openvswitch] [ 998.394009] ? __die_body.cold+0x8/0x12 [ 998.394016] ? die_addr+0x3c/0x60 [ 998.394027] ? exc_general_protection+0x16d/0x390 [ 998.394042] ? asm_exc_general_protection+0x26/0x30 [ 998.394058] ? dev_set_promiscuity+0x8d/0xa0 [ 998.394066] ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch] [ 998.394092] dp_device_event+0x41/0x80 [openvswitch] [ 998.394102] notifier_call_chain+0x5a/0xd0 [ 998.394106] unregister_netdevice_many_notify+0x51b/0xa60 [ 998.394110] rtnl_dellink+0x169/0x3e0 [ 998.394121] ? rt_mutex_slowlock.constprop.0+0x95/0xd0 [ 998.394125] rtnetlink_rcv_msg+0x142/0x3f0 [ 998.394128] ? avc_has_perm_noaudit+0x69/0xf0 [ 998.394130] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 998.394132] netlink_rcv_skb+0x50/0x100 [ 998.394138] netlink_unicast+0x292/0x3f0 [ 998.394141] netlink_sendmsg+0x21b/0x470 [ 998.394145] ____sys_sendmsg+0x39d/0x3d0 [ 998.394149] ___sys_sendmsg+0x9a/0xe0 [ 998.394156] __sys_sendmsg+0x7a/0xd0 [ 998.394160] do_syscall_64+0x7f/0x170 [ 998.394162] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 998.394165] RIP: 0033:0x7fad61bf4724 [ 998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 [ 998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724 [ 998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003 [ 998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f [ 998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2 ---truncated---
CVE-2026-31509: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: fix circular locking dependency in nci_close_device nci_close_device() flushes rx_wq and tx_wq while holding req_lock. This causes a circular locking dependency because nci_rx_work() running on rx_wq can end up taking req_lock too: nci_rx_work -> nci_rx_data_packet -> nci_data_exchange_complete -> __sk_destruct -> rawsock_destruct -> nfc_deactivate_target -> nci_deactivate_target -> nci_request -> mutex_lock(&ndev->req_lock) Move the flush of rx_wq after req_lock has been released. This should safe (I think) because NCI_UP has already been cleared and the transport is closed, so the work will see it and return -ENETDOWN. NIPA has been hitting this running the nci selftest with a debug kernel on roughly 4% of the runs.
CVE-2026-31510: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref on l2cap_sock_ready_cb Before using sk pointer, check if it is null. Fix the following: KASAN: null-ptr-deref in range [0x0000000000000260-0x0000000000000267] CPU: 0 UID: 0 PID: 5985 Comm: kworker/0:5 Not tainted 7.0.0-rc4-00029-ga989fde763f4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-9.fc43 06/10/2025 Workqueue: events l2cap_info_timeout RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce veth0_macvtap: entered promiscuous mode RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005582615a5008 CR3: 000000007007e000 CR4: 0000000000752ef0 PKRU: 55555554 Call Trace: <TASK> __kasan_check_byte+0x12/0x40 lock_acquire+0x79/0x2e0 lock_sock_nested+0x48/0x100 ? l2cap_sock_ready_cb+0x46/0x160 l2cap_sock_ready_cb+0x46/0x160 l2cap_conn_start+0x779/0xff0 ? __pfx_l2cap_conn_start+0x10/0x10 ? l2cap_info_timeout+0x60/0xa0 ? __pfx___mutex_lock+0x10/0x10 l2cap_info_timeout+0x68/0xa0 ? process_scheduled_works+0xa8d/0x18c0 process_scheduled_works+0xb6e/0x18c0 ? __pfx_process_scheduled_works+0x10/0x10 ? assign_work+0x3d5/0x5e0 worker_thread+0xa53/0xfc0 kthread+0x388/0x470 ? __pfx_worker_thread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x51e/0xb90 ? __pfx_ret_from_fork+0x10/0x10 veth1_macvtap: entered promiscuous mode ? __switch_to+0xc7d/0x1450 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- batman_adv: batadv0: Interface activated: batadv_slave_0 batman_adv: batadv0: Interface activated: batadv_slave_1 netdevsim netdevsim7 netdevsim0: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim1: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim2: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0 RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce ieee80211 phy39: Selected rate control algorithm 'minstrel_ht' RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7e16139e9c CR3: 000000000e74e000 CR4: 0000000000752ef0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception
CVE-2026-31511: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix dangling pointer on mgmt_add_adv_patterns_monitor_complete This fixes the condition checking so mgmt_pending_valid is executed whenever status != -ECANCELED otherwise calling mgmt_pending_free(cmd) would kfree(cmd) without unlinking it from the list first, leaving a dangling pointer. Any subsequent list traversal (e.g., mgmt_pending_foreach during __mgmt_power_off, or another mgmt_pending_valid call) would dereference freed memory.
CVE-2026-31512: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate PDU length before reading SDU length in l2cap_ecred_data_rcv() l2cap_ecred_data_rcv() reads the SDU length field from skb->data using get_unaligned_le16() without first verifying that skb contains at least L2CAP_SDULEN_SIZE (2) bytes. When skb->len is less than 2, this reads past the valid data in the skb. The ERTM reassembly path correctly calls pskb_may_pull() before reading the SDU length (l2cap_reassemble_sdu, L2CAP_SAR_START case). Apply the same validation to the Enhanced Credit Based Flow Control data path.
CVE-2026-31515: In the Linux kernel, the following vulnerability has been resolved: af_key: validate families in pfkey_send_migrate() syzbot was able to trigger a crash in skb_put() [1] Issue is that pfkey_send_migrate() does not check old/new families, and that set_ipsecrequest() @family argument was truncated, thus possibly overfilling the skb. Validate families early, do not wait set_ipsecrequest(). [1] skbuff: skb_over_panic: text:ffffffff8a752120 len:392 put:16 head:ffff88802a4ad040 data:ffff88802a4ad040 tail:0x188 end:0x180 dev:<NULL> kernel BUG at net/core/skbuff.c:214 ! Call Trace: <TASK> skb_over_panic net/core/skbuff.c:219 [inline] skb_put+0x159/0x210 net/core/skbuff.c:2655 skb_put_zero include/linux/skbuff.h:2788 [inline] set_ipsecrequest net/key/af_key.c:3532 [inline] pfkey_send_migrate+0x1270/0x2e50 net/key/af_key.c:3636 km_migrate+0x155/0x260 net/xfrm/xfrm_state.c:2848 xfrm_migrate+0x2140/0x2450 net/xfrm/xfrm_policy.c:4705 xfrm_do_migrate+0x8ff/0xaa0 net/xfrm/xfrm_user.c:3150
CVE-2026-31516: In the Linux kernel, the following vulnerability has been resolved: xfrm: prevent policy_hthresh.work from racing with netns teardown A XFRM_MSG_NEWSPDINFO request can queue the per-net work item policy_hthresh.work onto the system workqueue. The queued callback, xfrm_hash_rebuild(), retrieves the enclosing struct net via container_of(). If the net namespace is torn down before that work runs, the associated struct net may already have been freed, and xfrm_hash_rebuild() may then dereference stale memory. xfrm_policy_fini() already flushes policy_hash_work during teardown, but it does not synchronize policy_hthresh.work. Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the queued work cannot outlive the net namespace teardown and access a freed struct net.
CVE-2026-31518: In the Linux kernel, the following vulnerability has been resolved: esp: fix skb leak with espintcp and async crypto When the TX queue for espintcp is full, esp_output_tail_tcp will return an error and not free the skb, because with synchronous crypto, the common xfrm output code will drop the packet for us. With async crypto (esp_output_done), we need to drop the skb when esp_output_tail_tcp returns an error.
CVE-2026-31519: In the Linux kernel, the following vulnerability has been resolved: btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create We have recently observed a number of subvolumes with broken dentries. ls-ing the parent dir looks like: drwxrwxrwt 1 root root 16 Jan 23 16:49 . drwxr-xr-x 1 root root 24 Jan 23 16:48 .. d????????? ? ? ? ? ? broken_subvol and similarly stat-ing the file fails. In this state, deleting the subvol fails with ENOENT, but attempting to create a new file or subvol over it errors out with EEXIST and even aborts the fs. Which leaves us a bit stuck. dmesg contains a single notable error message reading: "could not do orphan cleanup -2" 2 is ENOENT and the error comes from the failure handling path of btrfs_orphan_cleanup(), with the stack leading back up to btrfs_lookup(). btrfs_lookup btrfs_lookup_dentry btrfs_orphan_cleanup // prints that message and returns -ENOENT After some detailed inspection of the internal state, it became clear that: - there are no orphan items for the subvol - the subvol is otherwise healthy looking, it is not half-deleted or anything, there is no drop progress, etc. - the subvol was created a while ago and does the meaningful first btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much later. - after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT, which results in a negative dentry for the subvolume via d_splice_alias(NULL, dentry), leading to the observed behavior. The bug can be mitigated by dropping the dentry cache, at which point we can successfully delete the subvolume if we want. i.e., btrfs_lookup() btrfs_lookup_dentry() if (!sb_rdonly(inode->vfs_inode)->vfs_inode) btrfs_orphan_cleanup(sub_root) test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) btrfs_search_slot() // finds orphan item for inode N ... prints "could not do orphan cleanup -2" if (inode == ERR_PTR(-ENOENT)) inode = NULL; return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) on the root when it runs, so it cannot run more than once on a given root, so something else must run concurrently. However, the obvious routes to deleting an orphan when nlinks goes to 0 should not be able to run without first doing a lookup into the subvolume, which should run btrfs_orphan_cleanup() and set the bit. The final important observation is that create_subvol() calls d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if the dentry cache gets dropped, the next lookup into the subvolume will make a real call into btrfs_orphan_cleanup() for the first time. This opens up the possibility of concurrently deleting the inode/orphan items but most typical evict() paths will be holding a reference on the parent dentry (child dentry holds parent->d_lockref.count via dget in d_alloc(), released in __dentry_kill()) and prevent the parent from being removed from the dentry cache. The one exception is delayed iputs. Ordered extent creation calls igrab() on the inode. If the file is unlinked and closed while those refs are held, iput() in __dentry_kill() decrements i_count but does not trigger eviction (i_count > 0). The child dentry is freed and the subvol dentry's d_lockref.count drops to 0, making it evictable while the inode is still alive. Since there are two races (the race between writeback and unlink and the race between lookup and delayed iputs), and there are too many moving parts, the following three diagrams show the complete picture. (Only the second and third are races) Phase 1: Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set btrfs_mksubvol() lookup_one_len() __lookup_slow() d_alloc_parallel() __d_alloc() // d_lockref.count = 1 create_subvol(dentry) // doesn't touch the bit.. d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.c ---truncated---
CVE-2026-31520: In the Linux kernel, the following vulnerability has been resolved: HID: apple: avoid memory leak in apple_report_fixup() The apple_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it *is* permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.
CVE-2026-31521: In the Linux kernel, the following vulnerability has been resolved: module: Fix kernel panic when a symbol st_shndx is out of bounds The module loader doesn't check for bounds of the ELF section index in simplify_symbols(): for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char *name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: [...] default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else /** HERE --> **/ secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } A symbol with an out-of-bounds st_shndx value, for example 0xffff (known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic: BUG: unable to handle page fault for address: ... RIP: 0010:simplify_symbols+0x2b2/0x480 ... Kernel panic - not syncing: Fatal exception This can happen when module ELF is legitimately using SHN_XINDEX or when it is corrupted. Add a bounds check in simplify_symbols() to validate that st_shndx is within the valid range before using it. This issue was discovered due to a bug in llvm-objcopy, see relevant discussion for details [1]. [1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/
CVE-2026-31522: In the Linux kernel, the following vulnerability has been resolved: HID: magicmouse: avoid memory leak in magicmouse_report_fixup() The magicmouse_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it *is* permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.
CVE-2026-31523: In the Linux kernel, the following vulnerability has been resolved: nvme-pci: ensure we're polling a polled queue A user can change the polled queue count at run time. There's a brief window during a reset where a hipri task may try to poll that queue before the block layer has updated the queue maps, which would race with the now interrupt driven queue and may cause double completions.
CVE-2026-31524: In the Linux kernel, the following vulnerability has been resolved: HID: asus: avoid memory leak in asus_report_fixup() The asus_report_fixup() function was returning a newly allocated kmemdup()-allocated buffer, but never freeing it. Switch to devm_kzalloc() to ensure the memory is managed and freed automatically when the device is removed. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a pointer whose lifetime is at least that of the input buffer. Also fix a harmless out-of-bounds read by copying only the original descriptor size.
CVE-2026-31525: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix undefined behavior in interpreter sdiv/smod for INT_MIN The BPF interpreter's signed 32-bit division and modulo handlers use the kernel abs() macro on s32 operands. The abs() macro documentation (include/linux/math.h) explicitly states the result is undefined when the input is the type minimum. When DST contains S32_MIN (0x80000000), abs((s32)DST) triggers undefined behavior and returns S32_MIN unchanged on arm64/x86. This value is then sign-extended to u64 as 0xFFFFFFFF80000000, causing do_div() to compute the wrong result. The verifier's abstract interpretation (scalar32_min_max_sdiv) computes the mathematically correct result for range tracking, creating a verifier/interpreter mismatch that can be exploited for out-of-bounds map value access. Introduce abs_s32() which handles S32_MIN correctly by casting to u32 before negating, avoiding signed overflow entirely. Replace all 8 abs((s32)...) call sites in the interpreter's sdiv32/smod32 handlers. s32 is the only affected case -- the s64 division/modulo handlers do not use abs().
CVE-2026-31526: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix exception exit lock checking for subprogs process_bpf_exit_full() passes check_lock = !curframe to check_resource_leak(), which is false in cases when bpf_throw() is called from a static subprog. This makes check_resource_leak() to skip validation of active_rcu_locks, active_preempt_locks, and active_irq_id on exception exits from subprogs. At runtime bpf_throw() unwinds the stack via ORC without releasing any user-acquired locks, which may cause various issues as the result. Fix by setting check_lock = true for exception exits regardless of curframe, since exceptions bypass all intermediate frame cleanup. Update the error message prefix to "bpf_throw" for exception exits to distinguish them from normal BPF_EXIT. Fix reject_subprog_with_rcu_read_lock test which was previously passing for the wrong reason. Test program returned directly from the subprog call without closing the RCU section, so the error was triggered by the unclosed RCU lock on normal exit, not by bpf_throw. Update __msg annotations for affected tests to match the new "bpf_throw" error prefix. The spin_lock case is not affected because they are already checked [1] at the call site in do_check_insn() before bpf_throw can run. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/kernel/bpf/verifier.c?h=v7.0-rc4#n21098
CVE-2026-31527: In the Linux kernel, the following vulnerability has been resolved: driver core: platform: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1]
CVE-2026-31528: In the Linux kernel, the following vulnerability has been resolved: perf: Make sure to use pmu_ctx->pmu for groups Oliver reported that x86_pmu_del() ended up doing an out-of-bound memory access when group_sched_in() fails and needs to roll back. This *should* be handled by the transaction callbacks, but he found that when the group leader is a software event, the transaction handlers of the wrong PMU are used. Despite the move_group case in perf_event_open() and group_sched_in() using pmu_ctx->pmu. Turns out, inherit uses event->pmu to clone the events, effectively undoing the move_group case for all inherited contexts. Fix this by also making inherit use pmu_ctx->pmu, ensuring all inherited counters end up in the same pmu context. Similarly, __perf_event_read() should use equally use pmu_ctx->pmu for the group case.
CVE-2026-31530: In the Linux kernel, the following vulnerability has been resolved: cxl/port: Fix use after free of parent_port in cxl_detach_ep() cxl_detach_ep() is called during bottom-up removal when all CXL memory devices beneath a switch port have been removed. For each port in the hierarchy it locks both the port and its parent, removes the endpoint, and if the port is now empty, marks it dead and unregisters the port by calling delete_switch_port(). There are two places during this work where the parent_port may be used after freeing: First, a concurrent detach may have already processed a port by the time a second worker finds it via bus_find_device(). Without pinning parent_port, it may already be freed when we discover port->dead and attempt to unlock the parent_port. In a production kernel that's a silent memory corruption, with lock debug, it looks like this: []DEBUG_LOCKS_WARN_ON(__owner_task(owner) != get_current()) []WARNING: kernel/locking/mutex.c:949 at __mutex_unlock_slowpath+0x1ee/0x310 []Call Trace: []mutex_unlock+0xd/0x20 []cxl_detach_ep+0x180/0x400 [cxl_core] []devm_action_release+0x10/0x20 []devres_release_all+0xa8/0xe0 []device_unbind_cleanup+0xd/0xa0 []really_probe+0x1a6/0x3e0 Second, delete_switch_port() releases three devm actions registered against parent_port. The last of those is unregister_port() and it calls device_unregister() on the child port, which can cascade. If parent_port is now also empty the device core may unregister and free it too. So by the time delete_switch_port() returns, parent_port may be free, and the subsequent device_unlock(&parent_port->dev) operates on freed memory. The kernel log looks same as above, with a different offset in cxl_detach_ep(). Both of these issues stem from the absence of a lifetime guarantee between a child port and its parent port. Establish a lifetime rule for ports: child ports hold a reference to their parent device until release. Take the reference when the port is allocated and drop it when released. This ensures the parent is valid for the full lifetime of the child and eliminates the use after free window in cxl_detach_ep(). This is easily reproduced with a reload of cxl_acpi in QEMU with CXL devices present.
CVE-2026-31531: In the Linux kernel, the following vulnerability has been resolved: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop() When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for single nexthops and small Equal-Cost Multi-Path groups, this fixed allocation fails for large nexthop groups like 512 nexthops. This results in the following warning splat: WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608 [...] RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395) [...] Call Trace: <TASK> rtnetlink_rcv_msg (net/core/rtnetlink.c:6989) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585) ___sys_sendmsg (net/socket.c:2641) __sys_sendmsg (net/socket.c:2671) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Fix this by allocating the size dynamically using nh_nlmsg_size() and using nlmsg_new(), this is consistent with nexthop_notify() behavior. In addition, adjust nh_nlmsg_size_grp() so it calculates the size needed based on flags passed. While at it, also add the size of NHA_FDB for nexthop group size calculation as it was missing too. This cannot be reproduced via iproute2 as the group size is currently limited and the command fails as follows: addattr_l ERROR: message exceeded bound of 1048
CVE-2026-31532: In the Linux kernel, the following vulnerability has been resolved: can: raw: fix ro->uniq use-after-free in raw_rcv() raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage. Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained. [mkl: applied manually]
CVE-2026-31533: In the Linux kernel, the following vulnerability has been resolved: net/tls: fix use-after-free in -EBUSY error path of tls_do_encryption The -EBUSY handling in tls_do_encryption(), introduced by commit 859054147318 ("net: tls: handle backlogging of crypto requests"), has a use-after-free due to double cleanup of encrypt_pending and the scatterlist entry. When crypto_aead_encrypt() returns -EBUSY, the request is enqueued to the cryptd backlog and the async callback tls_encrypt_done() will be invoked upon completion. That callback unconditionally restores the scatterlist entry (sge->offset, sge->length) and decrements ctx->encrypt_pending. However, if tls_encrypt_async_wait() returns an error, the synchronous error path in tls_do_encryption() performs the same cleanup again, double-decrementing encrypt_pending and double-restoring the scatterlist. The double-decrement corrupts the encrypt_pending sentinel (initialized to 1), making tls_encrypt_async_wait() permanently skip the wait for pending async callbacks. A subsequent sendmsg can then free the tls_rec via bpf_exec_tx_verdict() while a cryptd callback is still pending, resulting in a use-after-free when the callback fires on the freed record. Fix this by skipping the synchronous cleanup when the -EBUSY async wait returns an error, since the callback has already handled encrypt_pending and sge restoration.
CVE-2026-31536: In the Linux kernel, the following vulnerability has been resolved: smb: server: let send_done handle a completion without IB_SEND_SIGNALED With smbdirect_send_batch processing we likely have requests without IB_SEND_SIGNALED, which will be destroyed in the final request that has IB_SEND_SIGNALED set. If the connection is broken all requests are signaled even without explicit IB_SEND_SIGNALED.
CVE-2026-31537: In the Linux kernel, the following vulnerability has been resolved: smb: server: make use of smbdirect_socket.send_io.bcredits It turns out that our code will corrupt the stream of reassabled data transfer messages when we trigger an immendiate (empty) send. In order to fix this we'll have a single 'batch' credit per connection. And code getting that credit is free to use as much messages until remaining_length reaches 0, then the batch credit it given back and the next logical send can happen.
CVE-2026-31540: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: Check set_default_submission() before deferencing When the i915 driver firmware binaries are not present, the set_default_submission pointer is not set. This pointer is dereferenced during suspend anyways. Add a check to make sure it is set before dereferencing. [ 23.289926] PM: suspend entry (deep) [ 23.293558] Filesystems sync: 0.000 seconds [ 23.298010] Freezing user space processes [ 23.302771] Freezing user space processes completed (elapsed 0.000 seconds) [ 23.309766] OOM killer disabled. [ 23.313027] Freezing remaining freezable tasks [ 23.318540] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 23.342038] serial 00:05: disabled [ 23.345719] serial 00:02: disabled [ 23.349342] serial 00:01: disabled [ 23.353782] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 23.358993] sd 1:0:0:0: [sdb] Synchronizing SCSI cache [ 23.361635] ata1.00: Entering standby power mode [ 23.368863] ata2.00: Entering standby power mode [ 23.445187] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 23.452194] #PF: supervisor instruction fetch in kernel mode [ 23.457896] #PF: error_code(0x0010) - not-present page [ 23.463065] PGD 0 P4D 0 [ 23.465640] Oops: Oops: 0010 [#1] SMP NOPTI [ 23.469869] CPU: 8 UID: 0 PID: 211 Comm: kworker/u48:18 Tainted: G S W 6.19.0-rc4-00020-gf0b9d8eb98df #10 PREEMPT(voluntary) [ 23.482512] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 23.496511] Workqueue: async async_run_entry_fn [ 23.501087] RIP: 0010:0x0 [ 23.503755] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 23.510324] RSP: 0018:ffffb4a60065fca8 EFLAGS: 00010246 [ 23.515592] RAX: 0000000000000000 RBX: ffff9f428290e000 RCX: 000000000000000f [ 23.522765] RDX: 0000000000000000 RSI: 0000000000000282 RDI: ffff9f428290e000 [ 23.529937] RBP: ffff9f4282907070 R08: ffff9f4281130428 R09: 00000000ffffffff [ 23.537111] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f42829070f8 [ 23.544284] R13: ffff9f4282906028 R14: ffff9f4282900000 R15: ffff9f4282906b68 [ 23.551457] FS: 0000000000000000(0000) GS:ffff9f466b2cf000(0000) knlGS:0000000000000000 [ 23.559588] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 23.565365] CR2: ffffffffffffffd6 CR3: 000000031c230001 CR4: 0000000000f70ef0 [ 23.572539] PKRU: 55555554 [ 23.575281] Call Trace: [ 23.577770] <TASK> [ 23.579905] intel_engines_reset_default_submission+0x42/0x60 [ 23.585695] __intel_gt_unset_wedged+0x191/0x200 [ 23.590360] intel_gt_unset_wedged+0x20/0x40 [ 23.594675] gt_sanitize+0x15e/0x170 [ 23.598290] i915_gem_suspend_late+0x6b/0x180 [ 23.602692] i915_drm_suspend_late+0x35/0xf0 [ 23.607008] ? __pfx_pci_pm_suspend_late+0x10/0x10 [ 23.611843] dpm_run_callback+0x78/0x1c0 [ 23.615817] device_suspend_late+0xde/0x2e0 [ 23.620037] async_suspend_late+0x18/0x30 [ 23.624082] async_run_entry_fn+0x25/0xa0 [ 23.628129] process_one_work+0x15b/0x380 [ 23.632182] worker_thread+0x2a5/0x3c0 [ 23.635973] ? __pfx_worker_thread+0x10/0x10 [ 23.640279] kthread+0xf6/0x1f0 [ 23.643464] ? __pfx_kthread+0x10/0x10 [ 23.647263] ? __pfx_kthread+0x10/0x10 [ 23.651045] ret_from_fork+0x131/0x190 [ 23.654837] ? __pfx_kthread+0x10/0x10 [ 23.658634] ret_from_fork_asm+0x1a/0x30 [ 23.662597] </TASK> [ 23.664826] Modules linked in: [ 23.667914] CR2: 0000000000000000 [ 23.671271] ------------[ cut here ]------------ (cherry picked from commit daa199abc3d3d1740c9e3a2c3e9216ae5b447cad)
CVE-2026-31542: In the Linux kernel, the following vulnerability has been resolved: x86/platform/uv: Handle deconfigured sockets When a socket is deconfigured, it's mapped to SOCK_EMPTY (0xffff). This causes a panic while allocating UV hub info structures. Fix this by using NUMA_NO_NODE, allowing UV hub info structures to be allocated on valid nodes.
CVE-2026-31545: In the Linux kernel, the following vulnerability has been resolved: NFC: nxp-nci: allow GPIOs to sleep Allow the firmware and enable GPIOs to sleep. This fixes a `WARN_ON' and allows the driver to operate GPIOs which are connected to I2C GPIO expanders. -- >8 -- kernel: WARNING: CPU: 3 PID: 2636 at drivers/gpio/gpiolib.c:3880 gpiod_set_value+0x88/0x98 -- >8 --
CVE-2026-31546: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix NULL deref in bond_debug_rlb_hash_show rlb_clear_slave intentionally keeps RLB hash-table entries on the rx_hashtbl_used_head list with slave set to NULL when no replacement slave is available. However, bond_debug_rlb_hash_show visites client_info->slave without checking if it's NULL. Other used-list iterators in bond_alb.c already handle this NULL-slave state safely: - rlb_update_client returns early on !client_info->slave - rlb_req_update_slave_clients, rlb_clear_slave, and rlb_rebalance compare slave values before visiting - lb_req_update_subnet_clients continues if slave is NULL The following NULL deref crash can be trigger in bond_debug_rlb_hash_show: [ 1.289791] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 1.292058] RIP: 0010:bond_debug_rlb_hash_show (drivers/net/bonding/bond_debugfs.c:41) [ 1.293101] RSP: 0018:ffffc900004a7d00 EFLAGS: 00010286 [ 1.293333] RAX: 0000000000000000 RBX: ffff888102b48200 RCX: ffff888102b48204 [ 1.293631] RDX: ffff888102b48200 RSI: ffffffff839daad5 RDI: ffff888102815078 [ 1.293924] RBP: ffff888102815078 R08: ffff888102b4820e R09: 0000000000000000 [ 1.294267] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100f929c0 [ 1.294564] R13: ffff888100f92a00 R14: 0000000000000001 R15: ffffc900004a7ed8 [ 1.294864] FS: 0000000001395380(0000) GS:ffff888196e75000(0000) knlGS:0000000000000000 [ 1.295239] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.295480] CR2: 0000000000000000 CR3: 0000000102adc004 CR4: 0000000000772ef0 [ 1.295897] Call Trace: [ 1.296134] seq_read_iter (fs/seq_file.c:231) [ 1.296341] seq_read (fs/seq_file.c:164) [ 1.296493] full_proxy_read (fs/debugfs/file.c:378 (discriminator 1)) [ 1.296658] vfs_read (fs/read_write.c:572) [ 1.296981] ksys_read (fs/read_write.c:717) [ 1.297132] do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) [ 1.297325] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Add a NULL check and print "(none)" for entries with no assigned slave.
CVE-2026-31548: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel pmsr_free_wk in cfg80211_pmsr_wdev_down When the nl80211 socket that originated a PMSR request is closed, cfg80211_release_pmsr() sets the request's nl_portid to zero and schedules pmsr_free_wk to process the abort asynchronously. If the interface is concurrently torn down before that work runs, cfg80211_pmsr_wdev_down() calls cfg80211_pmsr_process_abort() directly. However, the already- scheduled pmsr_free_wk work item remains pending and may run after the interface has been removed from the driver. This could cause the driver's abort_pmsr callback to operate on a torn-down interface, leading to undefined behavior and potential crashes. Cancel pmsr_free_wk synchronously in cfg80211_pmsr_wdev_down() before calling cfg80211_pmsr_process_abort(). This ensures any pending or in-progress work is drained before interface teardown proceeds, preventing the work from invoking the driver abort callback after the interface is gone.
CVE-2026-31549: In the Linux kernel, the following vulnerability has been resolved: i2c: cp2615: fix serial string NULL-deref at probe The cp2615 driver uses the USB device serial string as the i2c adapter name but does not make sure that the string exists. Verify that the device has a serial number before accessing it to avoid triggering a NULL-pointer dereference (e.g. with malicious devices).
CVE-2026-31550: In the Linux kernel, the following vulnerability has been resolved: pmdomain: bcm: bcm2835-power: Increase ASB control timeout The bcm2835_asb_control() function uses a tight polling loop to wait for the ASB bridge to acknowledge a request. During intensive workloads, this handshake intermittently fails for V3D's master ASB on BCM2711, resulting in "Failed to disable ASB master for v3d" errors during runtime PM suspend. As a consequence, the failed power-off leaves V3D in a broken state, leading to bus faults or system hangs on later accesses. As the timeout is insufficient in some scenarios, increase the polling timeout from 1us to 5us, which is still negligible in the context of a power domain transition. Also, replace the open-coded ktime_get_ns()/ cpu_relax() polling loop with readl_poll_timeout_atomic().
CVE-2026-31551: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: Fix static_branch_dec() underflow for aql_disable. syzbot reported static_branch_dec() underflow in aql_enable_write(). [0] The problem is that aql_enable_write() does not serialise concurrent write()s to the debugfs. aql_enable_write() checks static_key_false(&aql_disable.key) and later calls static_branch_inc() or static_branch_dec(), but the state may change between the two calls. aql_disable does not need to track inc/dec. Let's use static_branch_enable() and static_branch_disable(). [0]: val == 0 WARNING: kernel/jump_label.c:311 at __static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311, CPU#0: syz.1.3155/20288 Modules linked in: CPU: 0 UID: 0 PID: 20288 Comm: syz.1.3155 Tainted: G U L syzkaller #0 PREEMPT(full) Tainted: [U]=USER, [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/24/2026 RIP: 0010:__static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311 Code: f2 c9 ff 5b 5d c3 cc cc cc cc e8 54 f2 c9 ff 48 89 df e8 ac f9 ff ff eb ad e8 45 f2 c9 ff 90 0f 0b 90 eb a2 e8 3a f2 c9 ff 90 <0f> 0b 90 eb 97 48 89 df e8 5c 4b 33 00 e9 36 ff ff ff 0f 1f 80 00 RSP: 0018:ffffc9000b9f7c10 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffffffff9b3e5d40 RCX: ffffffff823c57b4 RDX: ffff8880285a0000 RSI: ffffffff823c5846 RDI: ffff8880285a0000 RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000000a R13: 1ffff9200173ef88 R14: 0000000000000001 R15: ffffc9000b9f7e98 FS: 00007f530dd726c0(0000) GS:ffff8881245e3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000001140 CR3: 000000007cc4a000 CR4: 00000000003526f0 Call Trace: <TASK> __static_key_slow_dec_cpuslocked kernel/jump_label.c:297 [inline] __static_key_slow_dec kernel/jump_label.c:321 [inline] static_key_slow_dec+0x7c/0xc0 kernel/jump_label.c:336 aql_enable_write+0x2b2/0x310 net/mac80211/debugfs.c:343 short_proxy_write+0x133/0x1a0 fs/debugfs/file.c:383 vfs_write+0x2aa/0x1070 fs/read_write.c:684 ksys_pwrite64 fs/read_write.c:793 [inline] __do_sys_pwrite64 fs/read_write.c:801 [inline] __se_sys_pwrite64 fs/read_write.c:798 [inline] __x64_sys_pwrite64+0x1eb/0x250 fs/read_write.c:798 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xc9/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f530cf9aeb9 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f530dd72028 EFLAGS: 00000246 ORIG_RAX: 0000000000000012 RAX: ffffffffffffffda RBX: 00007f530d215fa0 RCX: 00007f530cf9aeb9 RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000010 RBP: 00007f530d008c1f R08: 0000000000000000 R09: 0000000000000000 R10: 4200000000000005 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f530d216038 R14: 00007f530d215fa0 R15: 00007ffde89fb978 </TASK>
CVE-2026-31552: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Return -ENOMEM instead of -EAGAIN if there is not enough headroom Since upstream commit e75665dd0968 ("wifi: wlcore: ensure skb headroom before skb_push"), wl1271_tx_allocate() and with it wl1271_prepare_tx_frame() returns -EAGAIN if pskb_expand_head() fails. However, in wlcore_tx_work_locked(), a return value of -EAGAIN from wl1271_prepare_tx_frame() is interpreted as the aggregation buffer being full. This causes the code to flush the buffer, put the skb back at the head of the queue, and immediately retry the same skb in a tight while loop. Because wlcore_tx_work_locked() holds wl->mutex, and the retry happens immediately with GFP_ATOMIC, this will result in an infinite loop and a CPU soft lockup. Return -ENOMEM instead so the packet is dropped and the loop terminates. The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y.
CVE-2026-31554: In the Linux kernel, the following vulnerability has been resolved: futex: Require sys_futex_requeue() to have identical flags Nicholas reported that his LLM found it was possible to create a UaF when sys_futex_requeue() is used with different flags. The initial motivation for allowing different flags was the variable sized futex, but since that hasn't been merged (yet), simply mandate the flags are identical, as is the case for the old style sys_futex() requeue operations.
CVE-2026-31555: In the Linux kernel, the following vulnerability has been resolved: futex: Clear stale exiting pointer in futex_lock_pi() retry path Fuzzying/stressing futexes triggered: WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524 When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY and stores a refcounted task pointer in 'exiting'. After wait_for_owner_exiting() consumes that reference, the local pointer is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a different error, the bogus pointer is passed to wait_for_owner_exiting(). CPU0 CPU1 CPU2 futex_lock_pi(uaddr) // acquires the PI futex exit() futex_cleanup_begin() futex_state = EXITING; futex_lock_pi(uaddr) futex_lock_pi_atomic() attach_to_pi_owner() // observes EXITING *exiting = owner; // takes ref return -EBUSY wait_for_owner_exiting(-EBUSY, owner) put_task_struct(); // drops ref // exiting still points to owner goto retry; futex_lock_pi_atomic() lock_pi_update_atomic() cmpxchg(uaddr) *uaddr ^= WAITERS // whatever // value changed return -EAGAIN; wait_for_owner_exiting(-EAGAIN, exiting) // stale WARN_ON_ONCE(exiting) Fix this by resetting upon retry, essentially aligning it with requeue_pi.
CVE-2026-31556: In the Linux kernel, the following vulnerability has been resolved: xfs: scrub: unlock dquot before early return in quota scrub xchk_quota_item can return early after calling xchk_fblock_process_error. When that helper returns false, the function returned immediately without dropping dq->q_qlock, which can leave the dquot lock held and risk lock leaks or deadlocks in later quota operations. Fix this by unlocking dq->q_qlock before the early return.
CVE-2026-31557: In the Linux kernel, the following vulnerability has been resolved: nvmet: move async event work off nvmet-wq For target nvmet_ctrl_free() flushes ctrl->async_event_work. If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue completion for the same worker:- A. Async event work queued on nvmet-wq (prior to disconnect): nvmet_execute_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) nvmet_add_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) B. Full pre-work chain (RDMA CM path): nvmet_rdma_cm_handler() nvmet_rdma_queue_disconnect() __nvmet_rdma_queue_disconnect() queue_work(nvmet_wq, &queue->release_work) process_one_work() lock((wq_completion)nvmet-wq) <--------- 1st nvmet_rdma_release_queue_work() C. Recursive path (same worker): nvmet_rdma_release_queue_work() nvmet_rdma_free_queue() nvmet_sq_destroy() nvmet_ctrl_put() nvmet_ctrl_free() flush_work(&ctrl->async_event_work) __flush_work() touch_wq_lockdep_map() lock((wq_completion)nvmet-wq) <--------- 2nd Lockdep splat: ============================================ WARNING: possible recursive locking detected 6.19.0-rc3nvme+ #14 Tainted: G N -------------------------------------------- kworker/u192:42/44933 is trying to acquire lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 3 locks held by kworker/u192:42/44933: #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660 #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530 Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma] Call Trace: __flush_work+0x268/0x530 nvmet_ctrl_free+0x140/0x310 [nvmet] nvmet_cq_put+0x74/0x90 [nvmet] nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma] nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma] process_one_work+0x206/0x660 worker_thread+0x184/0x320 kthread+0x10c/0x240 ret_from_fork+0x319/0x390 Move async event work to a dedicated nvmet-aen-wq to avoid reentrant flush on nvmet-wq.
CVE-2026-31558: In the Linux kernel, the following vulnerability has been resolved: LoongArch: KVM: Make kvm_get_vcpu_by_cpuid() more robust kvm_get_vcpu_by_cpuid() takes a cpuid parameter whose type is int, so cpuid can be negative. Let kvm_get_vcpu_by_cpuid() return NULL for this case so as to make it more robust. This fix an out-of-bounds access to kvm_arch::phyid_map::phys_map[].
CVE-2026-31559: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Fix missing NULL checks for kstrdup() 1. Replace "of_find_node_by_path("/")" with "of_root" to avoid multiple calls to "of_node_put()". 2. Fix a potential kernel oops during early boot when memory allocation fails while parsing CPU model from device tree.
CVE-2026-31560: In the Linux kernel, the following vulnerability has been resolved: spi: spi-dw-dma: fix print error log when wait finish transaction If an error occurs, the device may not have a current message. In this case, the system will crash. In this case, it's better to use dev from the struct ctlr (struct spi_controller*).
CVE-2026-31561: In the Linux kernel, the following vulnerability has been resolved: x86/cpu: Remove X86_CR4_FRED from the CR4 pinned bits mask Commit in Fixes added the FRED CR4 bit to the CR4 pinned bits mask so that whenever something else modifies CR4, that bit remains set. Which in itself is a perfectly fine idea. However, there's an issue when during boot FRED is initialized: first on the BSP and later on the APs. Thus, there's a window in time when exceptions cannot be handled. This becomes particularly nasty when running as SEV-{ES,SNP} or TDX guests which, when they manage to trigger exceptions during that short window described above, triple fault due to FRED MSRs not being set up yet. See Link tag below for a much more detailed explanation of the situation. So, as a result, the commit in that Link URL tried to address this shortcoming by temporarily disabling CR4 pinning when an AP is not online yet. However, that is a problem in itself because in this case, an attack on the kernel needs to only modify the online bit - a single bit in RW memory - and then disable CR4 pinning and then disable SM*P, leading to more and worse things to happen to the system. So, instead, remove the FRED bit from the CR4 pinning mask, thus obviating the need to temporarily disable CR4 pinning. If someone manages to disable FRED when poking at CR4, then idt_invalidate() would make sure the system would crash'n'burn on the first exception triggered, which is a much better outcome security-wise.
CVE-2026-31562: In the Linux kernel, the following vulnerability has been resolved: drm/mediatek: dsi: Store driver data before invoking mipi_dsi_host_register The call to mipi_dsi_host_register triggers a callback to mtk_dsi_bind, which uses dev_get_drvdata to retrieve the mtk_dsi struct, so this structure needs to be stored inside the driver data before invoking it. As drvdata is currently uninitialized it leads to a crash when registering the DSI DRM encoder right after acquiring the mode_config.idr_mutex, blocking all subsequent DRM operations. Fixes the following crash during mediatek-drm probe (tested on Xiaomi Smart Clock x04g): Unable to handle kernel NULL pointer dereference at virtual address 0000000000000040 [...] Modules linked in: mediatek_drm(+) drm_display_helper cec drm_client_lib drm_dma_helper drm_kms_helper panel_simple [...] Call trace: drm_mode_object_add+0x58/0x98 (P) __drm_encoder_init+0x48/0x140 drm_encoder_init+0x6c/0xa0 drm_simple_encoder_init+0x20/0x34 [drm_kms_helper] mtk_dsi_bind+0x34/0x13c [mediatek_drm] component_bind_all+0x120/0x280 mtk_drm_bind+0x284/0x67c [mediatek_drm] try_to_bring_up_aggregate_device+0x23c/0x320 __component_add+0xa4/0x198 component_add+0x14/0x20 mtk_dsi_host_attach+0x78/0x100 [mediatek_drm] mipi_dsi_attach+0x2c/0x50 panel_simple_dsi_probe+0x4c/0x9c [panel_simple] mipi_dsi_drv_probe+0x1c/0x28 really_probe+0xc0/0x3dc __driver_probe_device+0x80/0x160 driver_probe_device+0x40/0x120 __device_attach_driver+0xbc/0x17c bus_for_each_drv+0x88/0xf0 __device_attach+0x9c/0x1cc device_initial_probe+0x54/0x60 bus_probe_device+0x34/0xa0 device_add+0x5b0/0x800 mipi_dsi_device_register_full+0xdc/0x16c mipi_dsi_host_register+0xc4/0x17c mtk_dsi_probe+0x10c/0x260 [mediatek_drm] platform_probe+0x5c/0xa4 really_probe+0xc0/0x3dc __driver_probe_device+0x80/0x160 driver_probe_device+0x40/0x120 __driver_attach+0xc8/0x1f8 bus_for_each_dev+0x7c/0xe0 driver_attach+0x24/0x30 bus_add_driver+0x11c/0x240 driver_register+0x68/0x130 __platform_register_drivers+0x64/0x160 mtk_drm_init+0x24/0x1000 [mediatek_drm] do_one_initcall+0x60/0x1d0 do_init_module+0x54/0x240 load_module+0x1838/0x1dc0 init_module_from_file+0xd8/0xf0 __arm64_sys_finit_module+0x1b4/0x428 invoke_syscall.constprop.0+0x48/0xc8 do_el0_svc+0x3c/0xb8 el0_svc+0x34/0xe8 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Code: 52800022 941004ab 2a0003f3 37f80040 (29005a80)
CVE-2026-31563: In the Linux kernel, the following vulnerability has been resolved: net: macb: Use dev_consume_skb_any() to free TX SKBs The napi_consume_skb() function is not intended to be called in an IRQ disabled context. However, after commit 6bc8a5098bf4 ("net: macb: Fix tx_ptr_lock locking"), the freeing of TX SKBs is performed with IRQs disabled. To resolve the following call trace, use dev_consume_skb_any() for freeing TX SKBs: WARNING: kernel/softirq.c:430 at __local_bh_enable_ip+0x174/0x188, CPU#0: ksoftirqd/0/15 Modules linked in: CPU: 0 UID: 0 PID: 15 Comm: ksoftirqd/0 Not tainted 7.0.0-rc4-next-20260319-yocto-standard-dirty #37 PREEMPT Hardware name: ZynqMP ZCU102 Rev1.1 (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __local_bh_enable_ip+0x174/0x188 lr : local_bh_enable+0x24/0x38 sp : ffff800082b3bb10 x29: ffff800082b3bb10 x28: ffff0008031f3c00 x27: 000000000011ede0 x26: ffff000800a7ff00 x25: ffff800083937ce8 x24: 0000000000017a80 x23: ffff000803243a78 x22: 0000000000000040 x21: 0000000000000000 x20: ffff000800394c80 x19: 0000000000000200 x18: 0000000000000001 x17: 0000000000000001 x16: ffff000803240000 x15: 0000000000000000 x14: ffffffffffffffff x13: 0000000000000028 x12: ffff000800395650 x11: ffff8000821d1528 x10: ffff800081c2bc08 x9 : ffff800081c1e258 x8 : 0000000100000301 x7 : ffff8000810426ec x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000008 x1 : 0000000000000200 x0 : ffff8000810428dc Call trace: __local_bh_enable_ip+0x174/0x188 (P) local_bh_enable+0x24/0x38 skb_attempt_defer_free+0x190/0x1d8 napi_consume_skb+0x58/0x108 macb_tx_poll+0x1a4/0x558 __napi_poll+0x50/0x198 net_rx_action+0x1f4/0x3d8 handle_softirqs+0x16c/0x560 run_ksoftirqd+0x44/0x80 smpboot_thread_fn+0x1d8/0x338 kthread+0x120/0x150 ret_from_fork+0x10/0x20 irq event stamp: 29751 hardirqs last enabled at (29750): [<ffff8000813be184>] _raw_spin_unlock_irqrestore+0x44/0x88 hardirqs last disabled at (29751): [<ffff8000813bdf60>] _raw_spin_lock_irqsave+0x38/0x98 softirqs last enabled at (29150): [<ffff8000800f1aec>] handle_softirqs+0x504/0x560 softirqs last disabled at (29153): [<ffff8000800f2fec>] run_ksoftirqd+0x44/0x80
CVE-2026-31565: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix deadlock during netdev reset with active connections Resolve deadlock that occurs when user executes netdev reset while RDMA applications (e.g., rping) are active. The netdev reset causes ice driver to remove irdma auxiliary driver, triggering device_delete and subsequent client removal. During client removal, uverbs_client waits for QP reference count to reach zero while cma_client holds the final reference, creating circular dependency and indefinite wait in iWARP mode. Skip QP reference count wait during device reset to prevent deadlock.
CVE-2026-31566: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix fence put before wait in amdgpu_amdkfd_submit_ib amdgpu_amdkfd_submit_ib() submits a GPU job and gets a fence from amdgpu_ib_schedule(). This fence is used to wait for job completion. Currently, the code drops the fence reference using dma_fence_put() before calling dma_fence_wait(). If dma_fence_put() releases the last reference, the fence may be freed before dma_fence_wait() is called. This can lead to a use-after-free. Fix this by waiting on the fence first and releasing the reference only after dma_fence_wait() completes. Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:697 amdgpu_amdkfd_submit_ib() warn: passing freed memory 'f' (line 696) (cherry picked from commit 8b9e5259adc385b61a6590a13b82ae0ac2bd3482)
CVE-2026-31568: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Add missing secure storage access fixups for donated memory There are special cases where secure storage access exceptions happen in a kernel context for pages that don't have the PG_arch_1 bit set. That bit is set for non-exported guest secure storage (memory) but is absent on storage donated to the Ultravisor since the kernel isn't allowed to export donated pages. Prior to this patch we would try to export the page by calling arch_make_folio_accessible() which would instantly return since the arch bit is absent signifying that the page was already exported and no further action is necessary. This leads to secure storage access exception loops which can never be resolved. With this patch we unconditionally try to export and if that fails we fixup.
CVE-2026-31570: In the Linux kernel, the following vulnerability has been resolved: can: gw: fix OOB heap access in cgw_csum_crc8_rel() cgw_csum_crc8_rel() correctly computes bounds-safe indices via calc_idx(): int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); if (from < 0 || to < 0 || res < 0) return; However, the loop and the result write then use the raw s8 fields directly instead of the computed variables: for (i = crc8->from_idx; ...) /* BUG: raw negative index */ cf->data[crc8->result_idx] = ...; /* BUG: raw negative index */ With from_idx = to_idx = result_idx = -64 on a 64-byte CAN FD frame, calc_idx(-64, 64) = 0 so the guard passes, but the loop iterates with i = -64, reading cf->data[-64], and the write goes to cf->data[-64]. This write might end up to 56 (7.0-rc) or 40 (<= 6.19) bytes before the start of the canfd_frame on the heap. The companion function cgw_csum_xor_rel() uses `from`/`to`/`res` correctly throughout; fix cgw_csum_crc8_rel() to match. Confirmed with KASAN on linux-7.0-rc2: BUG: KASAN: slab-out-of-bounds in cgw_csum_crc8_rel+0x515/0x5b0 Read of size 1 at addr ffff8880076619c8 by task poc_cgw_oob/62 To configure the can-gw crc8 checksums CAP_NET_ADMIN is needed.
CVE-2026-31574: In the Linux kernel, the following vulnerability has been resolved: clockevents: Add missing resets of the next_event_forced flag The prevention mechanism against timer interrupt starvation missed to reset the next_event_forced flag in a couple of places: - When the clock event state changes. That can cause the flag to be stale over a shutdown/startup sequence - When a non-forced event is armed, which then prevents rearming before that event. If that event is far out in the future this will cause missed timer interrupts. - In the suspend wakeup handler. That led to stalls which have been reported by several people. Add the missing resets, which fixes the problems for the reporters.
CVE-2026-31575: In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: fix hugetlb fault mutex hash calculation In mfill_atomic_hugetlb(), linear_page_index() is used to calculate the page index for hugetlb_fault_mutex_hash(). However, linear_page_index() returns the index in PAGE_SIZE units, while hugetlb_fault_mutex_hash() expects the index in huge page units. This mismatch means that different addresses within the same huge page can produce different hash values, leading to the use of different mutexes for the same huge page. This can cause races between faulting threads, which can corrupt the reservation map and trigger the BUG_ON in resv_map_release(). Fix this by introducing hugetlb_linear_page_index(), which returns the page index in huge page granularity, and using it in place of linear_page_index().
CVE-2026-31576: In the Linux kernel, the following vulnerability has been resolved: media: hackrf: fix to not free memory after the device is registered in hackrf_probe() In hackrf driver, the following race condition occurs: ``` CPU0 CPU1 hackrf_probe() kzalloc(); // alloc hackrf_dev .... v4l2_device_register(); .... fd = sys_open("/path/to/dev"); // open hackrf fd .... v4l2_device_unregister(); .... kfree(); // free hackrf_dev .... sys_ioctl(fd, ...); v4l2_ioctl(); video_is_registered() // UAF!! .... sys_close(fd); v4l2_release() // UAF!! hackrf_video_release() kfree(); // DFB!! ``` When a V4L2 or video device is unregistered, the device node is removed so new open() calls are blocked. However, file descriptors that are already open-and any in-flight I/O-do not terminate immediately; they remain valid until the last reference is dropped and the driver's release() is invoked. Therefore, freeing device memory on the error path after hackrf_probe() has registered dev it will lead to a race to use-after-free vuln, since those already-open handles haven't been released yet. And since release() free memory too, race to use-after-free and double-free vuln occur. To prevent this, if device is registered from probe(), it should be modified to free memory only through release() rather than calling kfree() directly.
CVE-2026-31577: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map The DAT inode's btree node cache (i_assoc_inode) is initialized lazily during btree operations. However, nilfs_mdt_save_to_shadow_map() assumes i_assoc_inode is already initialized when copying dirty pages to the shadow map during GC. If NILFS_IOCTL_CLEAN_SEGMENTS is called immediately after mount before any btree operation has occurred on the DAT inode, i_assoc_inode is NULL leading to a general protection fault. Fix this by calling nilfs_attach_btree_node_cache() on the DAT inode in nilfs_dat_read() at mount time, ensuring i_assoc_inode is always initialized before any GC operation can use it.
CVE-2026-31578: In the Linux kernel, the following vulnerability has been resolved: media: as102: fix to not free memory after the device is registered in as102_usb_probe() In as102_usb driver, the following race condition occurs: ``` CPU0 CPU1 as102_usb_probe() kzalloc(); // alloc as102_dev_t .... usb_register_dev(); fd = sys_open("/path/to/dev"); // open as102 fd .... usb_deregister_dev(); .... kfree(); // free as102_dev_t .... sys_close(fd); as102_release() // UAF!! as102_usb_release() kfree(); // DFB!! ``` When a USB character device registered with usb_register_dev() is later unregistered (via usb_deregister_dev() or disconnect), the device node is removed so new open() calls fail. However, file descriptors that are already open do not go away immediately: they remain valid until the last reference is dropped and the driver's .release() is invoked. In as102, as102_usb_probe() calls usb_register_dev() and then, on an error path, does usb_deregister_dev() and frees as102_dev_t right away. If userspace raced a successful open() before the deregistration, that open FD will later hit as102_release() --> as102_usb_release() and access or free as102_dev_t again, occur a race to use-after-free and double-free vuln. The fix is to never kfree(as102_dev_t) directly once usb_register_dev() has succeeded. After deregistration, defer freeing memory to .release(). In other words, let release() perform the last kfree when the final open FD is closed.
CVE-2026-31579: In the Linux kernel, the following vulnerability has been resolved: wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wg_netns_pre_exit() manually acquires rtnl_lock() inside the pernet .pre_exit callback. This causes a hung task when another thread holds rtnl_mutex - the cleanup_net workqueue (or the setup_net failure rollback path) blocks indefinitely in wg_netns_pre_exit() waiting to acquire the lock. Convert to .exit_rtnl, introduced in commit 7a60d91c690b ("net: Add ->exit_rtnl() hook to struct pernet_operations."), where the framework already holds RTNL and batches all callbacks under a single rtnl_lock()/rtnl_unlock() pair, eliminating the contention window. The rcu_assign_pointer(wg->creating_net, NULL) is safe to move from .pre_exit to .exit_rtnl (which runs after synchronize_rcu()) because all RCU readers of creating_net either use maybe_get_net() - which returns NULL for a dying namespace with zero refcount - or access net->user_ns which remains valid throughout the entire ops_undo_list sequence. [ Jason: added __net_exit and __read_mostly annotations that were missing. ]
CVE-2026-31580: In the Linux kernel, the following vulnerability has been resolved: bcache: fix cached_dev.sb_bio use-after-free and crash In our production environment, we have received multiple crash reports regarding libceph, which have caught our attention: ``` [6888366.280350] Call Trace: [6888366.280452] blk_update_request+0x14e/0x370 [6888366.280561] blk_mq_end_request+0x1a/0x130 [6888366.280671] rbd_img_handle_request+0x1a0/0x1b0 [rbd] [6888366.280792] rbd_obj_handle_request+0x32/0x40 [rbd] [6888366.280903] __complete_request+0x22/0x70 [libceph] [6888366.281032] osd_dispatch+0x15e/0xb40 [libceph] [6888366.281164] ? inet_recvmsg+0x5b/0xd0 [6888366.281272] ? ceph_tcp_recvmsg+0x6f/0xa0 [libceph] [6888366.281405] ceph_con_process_message+0x79/0x140 [libceph] [6888366.281534] ceph_con_v1_try_read+0x5d7/0xf30 [libceph] [6888366.281661] ceph_con_workfn+0x329/0x680 [libceph] ``` After analyzing the coredump file, we found that the address of dc->sb_bio has been freed. We know that cached_dev is only freed when it is stopped. Since sb_bio is a part of struct cached_dev, rather than an alloc every time. If the device is stopped while writing to the superblock, the released address will be accessed at endio. This patch hopes to wait for sb_write to complete in cached_dev_free. It should be noted that we analyzed the cause of the problem, then tell all details to the QWEN and adopted the modifications it made.
CVE-2026-31581: In the Linux kernel, the following vulnerability has been resolved: ALSA: 6fire: fix use-after-free on disconnect In usb6fire_chip_abort(), the chip struct is allocated as the card's private data (via snd_card_new with sizeof(struct sfire_chip)). When snd_card_free_when_closed() is called and no file handles are open, the card and embedded chip are freed synchronously. The subsequent chip->card = NULL write then hits freed slab memory. Call trace: usb6fire_chip_abort sound/usb/6fire/chip.c:59 [inline] usb6fire_chip_disconnect+0x348/0x358 sound/usb/6fire/chip.c:182 usb_unbind_interface+0x1a8/0x88c drivers/usb/core/driver.c:458 ... hub_event+0x1a04/0x4518 drivers/usb/core/hub.c:5953 Fix by moving the card lifecycle out of usb6fire_chip_abort() and into usb6fire_chip_disconnect(). The card pointer is saved in a local before any teardown, snd_card_disconnect() is called first to prevent new opens, URBs are aborted while chip is still valid, and snd_card_free_when_closed() is called last so chip is never accessed after the card may be freed.
CVE-2026-31582: In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix use-after-free on USB disconnect After powerz_disconnect() frees the URB and releases the mutex, a subsequent powerz_read() call can acquire the mutex and call powerz_read_data(), which dereferences the freed URB pointer. Fix by: - Setting priv->urb to NULL in powerz_disconnect() so that powerz_read_data() can detect the disconnected state. - Adding a !priv->urb check at the start of powerz_read_data() to return -ENODEV on a disconnected device. - Moving usb_set_intfdata() before hwmon registration so the disconnect handler can always find the priv pointer.
CVE-2026-31583: In the Linux kernel, the following vulnerability has been resolved: media: em28xx: fix use-after-free in em28xx_v4l2_open() em28xx_v4l2_open() reads dev->v4l2 without holding dev->lock, creating a race with em28xx_v4l2_init()'s error path and em28xx_v4l2_fini(), both of which free the em28xx_v4l2 struct and set dev->v4l2 to NULL under dev->lock. This race leads to two issues: - use-after-free in v4l2_fh_init() when accessing vdev->ctrl_handler, since the video_device is embedded in the freed em28xx_v4l2 struct. - NULL pointer dereference in em28xx_resolution_set() when accessing v4l2->norm, since dev->v4l2 has been set to NULL. Fix this by moving the mutex_lock() before the dev->v4l2 read and adding a NULL check for dev->v4l2 under the lock.
CVE-2026-31584: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: fix use-after-free in encoder release path The fops_vcodec_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->encode_work. This creates a race window where the workqueue handler (mtk_venc_worker) may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release path) CPU 1 (workqueue) --------------------- ------------------ fops_vcodec_release() v4l2_m2m_ctx_release() v4l2_m2m_cancel_job() // waits for m2m job "done" mtk_venc_worker() v4l2_m2m_job_finish() // m2m job "done" // BUT worker still running! // post-job_finish access: other ctx dereferences // UAF if ctx already freed // returns (job "done") kfree(ctx) // ctx freed Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle. After v4l2_m2m_job_finish() is called, the m2m framework considers the job complete and v4l2_m2m_ctx_release() returns, but the worker function continues executing and may still access ctx. The work is queued during encode operations via: queue_work(ctx->dev->encode_workqueue, &ctx->encode_work) The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx fields even after calling v4l2_m2m_job_finish(). This vulnerability was confirmed with KASAN by running an instrumented test module that widens the post-job_finish race window. KASAN detected: BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180 Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12 Workqueue: mtk_vcodec_enc_wq mtk_venc_worker Allocated by task 47: __kasan_kmalloc+0x7f/0x90 fops_vcodec_open+0x85/0x1a0 Freed by task 47: __kasan_slab_free+0x43/0x70 kfree+0xee/0x3a0 fops_vcodec_release+0xb7/0x190 Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx). This ensures the workqueue handler is both cancelled (if pending) and synchronized (waits for any running handler to complete) before the context is freed. Placement rationale: The fix is placed after v4l2_ctrl_handler_free() and before list_del_init(&ctx->list). At this point, all m2m operations are done (v4l2_m2m_ctx_release() has returned), and we need to ensure the workqueue is synchronized before removing ctx from the list and freeing it. Note: The open error path does NOT need cancel_work_sync() because INIT_WORK() only initializes the work structure - it does not schedule it. Work is only scheduled later during device_run() operations.
CVE-2026-31585: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix nfeeds state corruption on start_streaming failure syzbot reported a memory leak in vidtv_psi_service_desc_init [1]. When vidtv_start_streaming() fails inside vidtv_start_feed(), the nfeeds counter is left incremented even though no feed was actually started. This corrupts the driver state: subsequent start_feed calls see nfeeds > 1 and skip starting the mux, while stop_feed calls eventually try to stop a non-existent stream. This state corruption can also lead to memory leaks, since the mux and channel resources may be partially allocated during a failed start_streaming but never cleaned up, as the stop path finds dvb->streaming == false and returns early. Fix by decrementing nfeeds back when start_streaming fails, keeping the counter in sync with the actual number of active feeds. [1] BUG: memory leak unreferenced object 0xffff888145b50820 (size 32): comm "syz.0.17", pid 6068, jiffies 4294944486 backtrace (crc 90a0c7d4): vidtv_psi_service_desc_init+0x74/0x1b0 drivers/media/test-drivers/vidtv/vidtv_psi.c:288 vidtv_channel_s302m_init+0xb1/0x2a0 drivers/media/test-drivers/vidtv/vidtv_channel.c:83 vidtv_channels_init+0x1b/0x40 drivers/media/test-drivers/vidtv/vidtv_channel.c:524 vidtv_mux_init+0x516/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:518 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31586: In the Linux kernel, the following vulnerability has been resolved: mm: blk-cgroup: fix use-after-free in cgwb_release_workfn() cgwb_release_workfn() calls css_put(wb->blkcg_css) and then later accesses wb->blkcg_css again via blkcg_unpin_online(). If css_put() drops the last reference, the blkcg can be freed asynchronously (css_free_rwork_fn -> blkcg_css_free -> kfree) before blkcg_unpin_online() dereferences the pointer to access blkcg->online_pin, resulting in a use-after-free: BUG: KASAN: slab-use-after-free in blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) Write of size 4 at addr ff11000117aa6160 by task kworker/71:1/531 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) cgwb_release_workfn (mm/backing-dev.c:629) process_scheduled_works (kernel/workqueue.c:3278 kernel/workqueue.c:3385) Freed by task 1016: kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6246 mm/slub.c:6561) css_free_rwork_fn (kernel/cgroup/cgroup.c:5542) process_scheduled_works (kernel/workqueue.c:3302 kernel/workqueue.c:3385) ** Stack based on commit 66672af7a095 ("Add linux-next specific files for 20260410") I am seeing this crash sporadically in Meta fleet across multiple kernel versions. A full reproducer is available at: https://github.com/leitao/debug/blob/main/reproducers/repro_blkcg_uaf.sh (The race window is narrow. To make it easily reproducible, inject a msleep(100) between css_put() and blkcg_unpin_online() in cgwb_release_workfn(). With that delay and a KASAN-enabled kernel, the reproducer triggers the splat reliably in less than a second.) Fix this by moving blkcg_unpin_online() before css_put(), so the cgwb's CSS reference keeps the blkcg alive while blkcg_unpin_online() accesses it.
CVE-2026-31587: In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm: move component registration to unmanaged version q6apm component registers dais dynamically from ASoC toplology, which are allocated using device managed version apis. Allocating both component and dynamic dais using managed version could lead to incorrect free ordering, dai will be freed while component still holding references to it. Fix this issue by moving component to unmanged version so that the dai pointers are only freeded after the component is removed. ================================================================== BUG: KASAN: slab-use-after-free in snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] Read of size 8 at addr ffff00084493a6e8 by task kworker/u48:0/3426 Tainted: [W]=WARN Hardware name: LENOVO 21N2ZC5PUS/21N2ZC5PUS, BIOS N42ET57W (1.31 ) 08/08/2024 Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] Call trace: show_stack+0x28/0x7c (C) dump_stack_lvl+0x60/0x80 print_report+0x160/0x4b4 kasan_report+0xac/0xfc __asan_report_load8_noabort+0x20/0x34 snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] snd_soc_unregister_component_by_driver+0x50/0x88 [snd_soc_core] devm_component_release+0x30/0x5c [snd_soc_core] devres_release_all+0x13c/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Allocated by task 77: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 kasan_save_alloc_info+0x44/0x58 __kasan_kmalloc+0xbc/0xdc __kmalloc_node_track_caller_noprof+0x1f4/0x620 devm_kmalloc+0x7c/0x1c8 snd_soc_register_dai+0x50/0x4f0 [snd_soc_core] soc_tplg_pcm_elems_load+0x55c/0x1eb8 [snd_soc_core] snd_soc_tplg_component_load+0x4f8/0xb60 [snd_soc_core] audioreach_tplg_init+0x124/0x1fc [snd_q6apm] q6apm_audio_probe+0x10/0x1c [snd_q6apm] snd_soc_component_probe+0x5c/0x118 [snd_soc_core] soc_probe_component+0x44c/0xaf0 [snd_soc_core] snd_soc_bind_card+0xad0/0x2370 [snd_soc_core] snd_soc_register_card+0x3b0/0x4c0 [snd_soc_core] devm_snd_soc_register_card+0x50/0xc8 [snd_soc_core] x1e80100_platform_probe+0x208/0x368 [snd_soc_x1e80100] platform_probe+0xc0/0x188 really_probe+0x188/0x804 __driver_probe_device+0x158/0x358 driver_probe_device+0x60/0x190 __device_attach_driver+0x16c/0x2a8 bus_for_each_drv+0x100/0x194 __device_attach+0x174/0x380 device_initial_probe+0x14/0x20 bus_probe_device+0x124/0x154 deferred_probe_work_func+0x140/0x220 process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Freed by task 3426: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 __kasan_save_free_info+0x4c/0x80 __kasan_slab_free+0x78/0xa0 kfree+0x100/0x4a4 devres_release_all+0x144/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20
CVE-2026-31588: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use scratch field in MMIO fragment to hold small write values When exiting to userspace to service an emulated MMIO write, copy the to-be-written value to a scratch field in the MMIO fragment if the size of the data payload is 8 bytes or less, i.e. can fit in a single chunk, instead of pointing the fragment directly at the source value. This fixes a class of use-after-free bugs that occur when the emulator initiates a write using an on-stack, local variable as the source, the write splits a page boundary, *and* both pages are MMIO pages. Because KVM's ABI only allows for physically contiguous MMIO requests, accesses that split MMIO pages are separated into two fragments, and are sent to userspace one at a time. When KVM attempts to complete userspace MMIO in response to KVM_RUN after the first fragment, KVM will detect the second fragment and generate a second userspace exit, and reference the on-stack variable. The issue is most visible if the second KVM_RUN is performed by a separate task, in which case the stack of the initiating task can show up as truly freed data. ================================================================== BUG: KASAN: use-after-free in complete_emulated_mmio+0x305/0x420 Read of size 1 at addr ffff888009c378d1 by task syz-executor417/984 CPU: 1 PID: 984 Comm: syz-executor417 Not tainted 5.10.0-182.0.0.95.h2627.eulerosv2r13.x86_64 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xbe/0xfd print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 check_memory_region+0xfd/0x1f0 memcpy+0x20/0x60 complete_emulated_mmio+0x305/0x420 kvm_arch_vcpu_ioctl_run+0x63f/0x6d0 kvm_vcpu_ioctl+0x413/0xb20 __se_sys_ioctl+0x111/0x160 do_syscall_64+0x30/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 RIP: 0033:0x42477d Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007faa8e6890e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000004d7338 RCX: 000000000042477d RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005 RBP: 00000000004d7330 R08: 00007fff28d546df R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d733c R13: 0000000000000000 R14: 000000000040a200 R15: 00007fff28d54720 The buggy address belongs to the page: page:0000000029f6a428 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9c37 flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea0000270dc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888009c37780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888009c37880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888009c37900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== The bug can also be reproduced with a targeted KVM-Unit-Test by hacking KVM to fill a large on-stack variable in complete_emulated_mmio(), i.e. by overwrite the data value with garbage. Limit the use of the scratch fields to 8-byte or smaller accesses, and to just writes, as larger accesses and reads are not affected thanks to implementation details in the emulator, but add a sanity check to ensure those details don't change in the future. Specifically, KVM never uses on-stack variables for accesses larger that 8 bytes, e.g. uses an operand in the emulator context, and *al ---truncated---
CVE-2026-31589: In the Linux kernel, the following vulnerability has been resolved: mm: call ->free_folio() directly in folio_unmap_invalidate() We can only call filemap_free_folio() if we have a reference to (or hold a lock on) the mapping. Otherwise, we've already removed the folio from the mapping so it no longer pins the mapping and the mapping can be removed, causing a use-after-free when accessing mapping->a_ops. Follow the same pattern as __remove_mapping() and load the free_folio function pointer before dropping the lock on the mapping. That lets us make filemap_free_folio() static as this was the only caller outside filemap.c.
CVE-2026-31590: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing: struct kvm_enc_region range = { .addr = 0, .size = -1ul, }; __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future. if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.
CVE-2026-31591: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel. Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).
CVE-2026-31592: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Protect *all* of sev_mem_enc_register_region() with kvm->lock Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G U W O 6.16.0-smp-DEV #1 NONE Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024 RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83 Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00 RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256 RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000 RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000 R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000 R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000 FS: 00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0 Call Trace: <TASK> kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371 kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363 __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f34e9f7e9a9 Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9 RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007 RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8 </TASK> with a syzlang reproducer that looks like: syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async) r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0) r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0) r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0) r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0) ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async) ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async) r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0) openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async) ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2) close(r0) (async) openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async) ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0) Opportunistically use guard() to avoid having to define a new error label and goto usage.
CVE-2026-31593: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host. BUG: unable to handle page fault for address: ff1276cbfdf36000 #PF: supervisor write access in kernel mode #PF: error_code(0x80000003) - RMP violation PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163 SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f] Oops: Oops: 0003 [#1] SMP NOPTI CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G OE Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023 RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd] Call Trace: <TASK> snp_launch_update_vmsa+0x19d/0x290 [kvm_amd] snp_launch_finish+0xb6/0x380 [kvm_amd] sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd] kvm_arch_vm_ioctl+0x837/0xcf0 [kvm] kvm_vm_ioctl+0x3fd/0xcc0 [kvm] __x64_sys_ioctl+0xa3/0x100 x64_sys_call+0xfe0/0x2350 do_syscall_64+0x81/0x10f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7ffff673287d </TASK> Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().
CVE-2026-31594: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case: Unable to handle kernel paging request at virtual address dead000000000108 [...] [dead000000000108] address between user and kernel address ranges Internal error: Oops: 0000000096000044 [#1] SMP [...] Call trace: pci_epc_remove_epf+0x78/0xe0 (P) pci_primary_epc_epf_link+0x88/0xa8 configfs_symlink+0x1f4/0x5a0 vfs_symlink+0x134/0x1d8 do_symlinkat+0x88/0x138 __arm64_sys_symlinkat+0x74/0xe0 [...] Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.
CVE-2026-31595: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down. Unable to handle kernel paging request at virtual address ffff800083f46004 [...] Internal error: Oops: 0000000096000007 [#1] SMP [...] Call trace: epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P) process_one_work+0x154/0x3b0 worker_thread+0x2c8/0x400 kthread+0x148/0x210 ret_from_fork+0x10/0x20
CVE-2026-31596: In the Linux kernel, the following vulnerability has been resolved: ocfs2: handle invalid dinode in ocfs2_group_extend [BUG] kernel BUG at fs/ocfs2/resize.c:308! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308 Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe Call Trace: ... ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... [CAUSE] ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl. [FIX] Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.
CVE-2026-31597: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.
CVE-2026-31598: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix possible deadlock between unlink and dio_end_io_write ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key. Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem): ocfs2_unlink ocfs2_prepare_orphan_dir ocfs2_lookup_lock_orphan_dir inode_lock(orphan_dir_inode) <- lock A __ocfs2_prepare_orphan_dir ocfs2_prepare_dir_for_insert ocfs2_extend_dir ocfs2_expand_inline_dir down_write(&oi->ip_alloc_sem) <- Lock B Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock): ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan() inode_lock(orphan_dir_inode) <- Lock A Deadlock Scenario: CPU0 (unlink) CPU1 (dio_end_io_write) ------ ------ inode_lock(orphan_dir_inode) down_write(ip_alloc_sem) down_write(ip_alloc_sem) inode_lock(orphan_dir_inode) Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.
CVE-2026-31599: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections syzbot reported a general protection fault in vidtv_psi_desc_assign [1]. vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault. Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629 Call Trace: <TASK> vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline] vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31600: In the Linux kernel, the following vulnerability has been resolved: arm64: mm: Handle invalid large leaf mappings correctly It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way. It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result: [ 15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers [ 15.476896] Unable to handle kernel paging request at virtual address ffff000019600000 [ 15.513762] Mem abort info: [ 15.527245] ESR = 0x0000000096000046 [ 15.548553] EC = 0x25: DABT (current EL), IL = 32 bits [ 15.572146] SET = 0, FnV = 0 [ 15.592141] EA = 0, S1PTW = 0 [ 15.612694] FSC = 0x06: level 2 translation fault [ 15.640644] Data abort info: [ 15.661983] ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000 [ 15.694875] CM = 0, WnR = 1, TnD = 0, TagAccess = 0 [ 15.723740] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000 [ 15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704 [ 15.855046] Internal error: Oops: 0000000096000046 [#1] SMP [ 15.886394] Modules linked in: [ 15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT [ 15.935258] Hardware name: linux,dummy-virt (DT) [ 15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 15.986009] pc : __pi_memcpy_generic+0x128/0x22c [ 16.006163] lr : swiotlb_bounce+0xf4/0x158 [ 16.024145] sp : ffff80008000b8f0 [ 16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000 [ 16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000 [ 16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0 [ 16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc [ 16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974 [ 16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018 [ 16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000 [ 16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000 [ 16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000 [ 16.349071] Call trace: [ 16.360143] __pi_memcpy_generic+0x128/0x22c (P) [ 16.380310] swiotlb_tbl_map_single+0x154/0x2b4 [ 16.400282] swiotlb_map+0x5c/0x228 [ 16.415984] dma_map_phys+0x244/0x2b8 [ 16.432199] dma_map_page_attrs+0x44/0x58 [ 16.449782] virtqueue_map_page_attrs+0x38/0x44 [ 16.469596] virtqueue_map_single_attrs+0xc0/0x130 [ 16.490509] virtnet_rq_alloc.isra.0+0xa4/0x1fc [ 16.510355] try_fill_recv+0x2a4/0x584 [ 16.526989] virtnet_open+0xd4/0x238 [ 16.542775] __dev_open+0x110/0x24c [ 16.558280] __dev_change_flags+0x194/0x20c [ 16.576879] netif_change_flags+0x24/0x6c [ 16.594489] dev_change_flags+0x48/0x7c [ 16.611462] ip_auto_config+0x258/0x1114 [ 16.628727] do_one_initcall+0x80/0x1c8 [ 16.645590] kernel_init_freeable+0x208/0x2f0 [ 16.664917] kernel_init+0x24/0x1e0 [ 16.680295] ret_from_fork+0x10/0x20 [ 16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c) [ 16.723106] ---[ end trace 0000000000000000 ]--- [ 16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 16.792556] Kernel Offset: 0x3396ea200000 from 0xffff8000800000 ---truncated---
CVE-2026-31601: In the Linux kernel, the following vulnerability has been resolved: vfio/xe: Reorganize the init to decouple migration from reset Attempting to issue reset on VF devices that don't support migration leads to the following: BUG: unable to handle page fault for address: 00000000000011f8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 7443 Comm: xe_sriov_flr Tainted: G S U 7.0.0-rc1-lgci-xe-xe-4588-cec43d5c2696af219-nodebug+ #1 PREEMPT(lazy) Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR4 RVP, BIOS RPLPFWI1.R00.4035.A00.2301200723 01/20/2023 RIP: 0010:xe_sriov_vfio_wait_flr_done+0xc/0x80 [xe] Code: ff c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 54 53 <83> bf f8 11 00 00 02 75 61 41 89 f4 85 f6 74 52 48 8b 47 08 48 89 RSP: 0018:ffffc9000f7c39b8 EFLAGS: 00010202 RAX: ffffffffa04d8660 RBX: ffff88813e3e4000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc9000f7c39c8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888101a48800 R13: ffff88813e3e4150 R14: ffff888130d0d008 R15: ffff88813e3e40d0 FS: 00007877d3d0d940(0000) GS:ffff88890b6d3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000011f8 CR3: 000000015a762000 CR4: 0000000000f52ef0 PKRU: 55555554 Call Trace: <TASK> xe_vfio_pci_reset_done+0x49/0x120 [xe_vfio_pci] pci_dev_restore+0x3b/0x80 pci_reset_function+0x109/0x140 reset_store+0x5c/0xb0 dev_attr_store+0x17/0x40 sysfs_kf_write+0x72/0x90 kernfs_fop_write_iter+0x161/0x1f0 vfs_write+0x261/0x440 ksys_write+0x69/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x259/0x26e0 do_syscall_64+0xcb/0x1500 ? __fput+0x1a2/0x2d0 ? fput_close_sync+0x3d/0xa0 ? __x64_sys_close+0x3e/0x90 ? x64_sys_call+0x1b7c/0x26e0 ? do_syscall_64+0x109/0x1500 ? __task_pid_nr_ns+0x68/0x100 ? __do_sys_getpid+0x1d/0x30 ? x64_sys_call+0x10b5/0x26e0 ? do_syscall_64+0x109/0x1500 ? putname+0x41/0x90 ? do_faccessat+0x1e8/0x300 ? __x64_sys_access+0x1c/0x30 ? x64_sys_call+0x1822/0x26e0 ? do_syscall_64+0x109/0x1500 ? tick_program_event+0x43/0xa0 ? hrtimer_interrupt+0x126/0x260 ? irqentry_exit+0xb2/0x710 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7877d5f1c5a4 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fff48e5f908 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007877d5f1c5a4 RDX: 0000000000000001 RSI: 00007877d621b0c9 RDI: 0000000000000009 RBP: 0000000000000001 R08: 00005fb49113b010 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000202 R12: 00007877d621b0c9 R13: 0000000000000009 R14: 00007fff48e5fac0 R15: 00007fff48e5fac0 </TASK> This is caused by the fact that some of the xe_vfio_pci_core_device members needed for handling reset are only initialized as part of migration init. Fix the problem by reorganizing the code to decouple VF init from migration init.
CVE-2026-31602: In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Limit PTP to a single page Commit 391e69143d0a increased CT_PTP_NUM from 1 to 4 to support 256 playback streams, but the additional pages are not used by the card correctly. The CT20K2 hardware already has multiple VMEM_PTPAL registers, but using them separately would require refactoring the entire virtual memory allocation logic. ct_vm_map() always uses PTEs in vm->ptp[0].area regardless of CT_PTP_NUM. On AMD64 systems, a single PTP covers 512 PTEs (2M). When aggregate memory allocations exceed this limit, ct_vm_map() tries to access beyond the allocated space and causes a page fault: BUG: unable to handle page fault for address: ffffd4ae8a10a000 Oops: Oops: 0002 [#1] SMP PTI RIP: 0010:ct_vm_map+0x17c/0x280 [snd_ctxfi] Call Trace: atc_pcm_playback_prepare+0x225/0x3b0 ct_pcm_playback_prepare+0x38/0x60 snd_pcm_do_prepare+0x2f/0x50 snd_pcm_action_single+0x36/0x90 snd_pcm_action_nonatomic+0xbf/0xd0 snd_pcm_ioctl+0x28/0x40 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x81/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Revert CT_PTP_NUM to 1. The 256 SRC_RESOURCE_NUM and playback_count remain unchanged.
CVE-2026-31603: In the Linux kernel, the following vulnerability has been resolved: staging: sm750fb: fix division by zero in ps_to_hz() ps_to_hz() is called from hw_sm750_crtc_set_mode() without validating that pixclock is non-zero. A zero pixclock passed via FBIOPUT_VSCREENINFO causes a division by zero. Fix by rejecting zero pixclock in lynxfb_ops_check_var(), consistent with other framebuffer drivers.
CVE-2026-31604: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on all probe errors (e.g. when descriptor parsing fails). Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks.
CVE-2026-31605: In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31606: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: don't call cdev_init while cdev in use When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes. This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.
CVE-2026-31607: In the Linux kernel, the following vulnerability has been resolved: usbip: validate number_of_packets in usbip_pack_ret_submit() When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the *original* number_of_packets from the CMD_SUBMIT. A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region. KASAN confirmed this with kernel 7.0.0-rc5: BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640 Write of size 4 at addr ffff888106351d40 by task vhci_rx/69 The buggy address is located 0 bytes to the right of allocated 320-byte region [ffff888106351c00, ffff888106351d40) The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter bound: the response must not exceed the original number_of_packets. This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size. Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit. Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.
CVE-2026-31608: In the Linux kernel, the following vulnerability has been resolved: smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list() smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg() moved it to the batch list.
CVE-2026-31609: In the Linux kernel, the following vulnerability has been resolved: smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush() smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.
CVE-2026-31610: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix mechToken leak when SPNEGO decode fails after token alloc The kernel ASN.1 BER decoder calls action callbacks incrementally as it walks the input. When ksmbd_decode_negTokenInit() reaches the mechToken [2] OCTET STRING element, ksmbd_neg_token_alloc() allocates conn->mechToken immediately via kmemdup_nul(). If a later element in the same blob is malformed, then the decoder will return nonzero after the allocation is already live. This could happen if mechListMIC [3] overrunse the enclosing SEQUENCE. decode_negotiation_token() then sets conn->use_spnego = false because both the negTokenInit and negTokenTarg grammars failed. The cleanup at the bottom of smb2_sess_setup() is gated on use_spnego: if (conn->use_spnego && conn->mechToken) { kfree(conn->mechToken); conn->mechToken = NULL; } so the kfree is skipped, causing the mechToken to never be freed. This codepath is reachable pre-authentication, so untrusted clients can cause slow memory leaks on a server without even being properly authenticated. Fix this up by not checking check for use_spnego, as it's not required, so the memory will always be properly freed. At the same time, always free the memory in ksmbd_conn_free() incase some other failure path forgot to free it.
CVE-2026-31611: In the Linux kernel, the following vulnerability has been resolved: ksmbd: require 3 sub-authorities before reading sub_auth[2] parse_dacl() compares each ACE SID against sid_unix_NFS_mode and on match reads sid.sub_auth[2] as the file mode. If sid_unix_NFS_mode is the prefix S-1-5-88-3 with num_subauth = 2 then compare_sids() compares only min(num_subauth, 2) sub-authorities so a client SID with num_subauth = 2 and sub_auth = {88, 3} will match. If num_subauth = 2 and the ACE is placed at the very end of the security descriptor, sub_auth[2] will be 4 bytes past end_of_acl. The out-of-band bytes will then be masked to the low 9 bits and applied as the file's POSIX mode, probably not something that is good to have happen. Fix this up by forcing the SID to actually carry a third sub-authority before reading it at all.
CVE-2026-31612: In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate EaNameLength in smb2_get_ea() smb2_get_ea() reads ea_req->EaNameLength from the client request and passes it directly to strncmp() as the comparison length without verifying that the length of the name really is the size of the input buffer received. Fix this up by properly checking the size of the name based on the value received and the overall size of the request, to prevent a later strncmp() call to use the length as a "trusted" size of the buffer. Without this check, uninitialized heap values might be slowly leaked to the client.
CVE-2026-31613: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB reads parsing symlink error response When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server. symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset 0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits. smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0. With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2). Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset. Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than.
CVE-2026-31614: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix off-by-8 bounds check in check_wsl_eas() The bounds check uses (u8 *)ea + nlen + 1 + vlen as the end of the EA name and value, but ea_data sits at offset sizeof(struct smb2_file_full_ea_info) = 8 from ea, not at offset 0. The strncmp() later reads ea->ea_data[0..nlen-1] and the value bytes follow at ea_data[nlen+1..nlen+vlen], so the actual end is ea->ea_data + nlen + 1 + vlen. Isn't pointer math fun? The earlier check (u8 *)ea > end - sizeof(*ea) only guarantees the 8-byte header is in bounds, but since the last EA is placed within 8 bytes of the end of the response, the name and value bytes are read past the end of iov. Fix this mess all up by using ea->ea_data as the base for the bounds check. An "untrusted" server can use this to leak up to 8 bytes of kernel heap into the EA name comparison and influence which WSL xattr the data is interpreted as.
CVE-2026-31615: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: renesas_usb3: validate endpoint index in standard request handlers The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math. This is just like what was done in commit ee0d382feb44 ("usb: gadget: aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.
CVE-2026-31616: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete() A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers. pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap. Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path").
CVE-2026-31617: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb() The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of: ndp_index > (block_len - opts->ndp_size) will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely. The same underflow occurs in the datagram index checks against block_len - opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb. Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined. Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.
CVE-2026-31618: In the Linux kernel, the following vulnerability has been resolved: fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31619: In the Linux kernel, the following vulnerability has been resolved: ALSA: fireworks: bound device-supplied status before string array lookup The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value. Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings. Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.
CVE-2026-31620: In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0 A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly. Fix this up by checking the return value properly.
CVE-2026-31621: In the Linux kernel, the following vulnerability has been resolved: bnge: return after auxiliary_device_uninit() in error path When auxiliary_device_add() fails, the error block calls auxiliary_device_uninit() but does not return. The uninit drops the last reference and synchronously runs bnge_aux_dev_release(), which sets bd->auxr_dev = NULL and frees the underlying object. The subsequent bd->auxr_dev->net = bd->netdev then dereferences NULL, which is not a good thing to have happen when trying to clean up from an error. Add the missing return, as the auxiliary bus documentation states is a requirement (seems that LLM tools read documentation better than humans do...)
CVE-2026-31622: In the Linux kernel, the following vulnerability has been resolved: NFC: digital: Bounds check NFC-A cascade depth in SDD response handler The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows). ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round. Fix this by rejecting the response when the accumulated UID would exceed the buffer. Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.
CVE-2026-31623: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers. Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.
CVE-2026-31624: In the Linux kernel, the following vulnerability has been resolved: HID: core: clamp report_size in s32ton() to avoid undefined shift s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field(). Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way. Fix this up by just clamping the max value of n, just like snto32() does.
CVE-2026-31625: In the Linux kernel, the following vulnerability has been resolved: HID: alps: fix NULL pointer dereference in alps_raw_event() Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), but the alps driver was missed. Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.
CVE-2026-31626: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify() Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data. Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized: drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify() warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes) Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.
CVE-2026-31627: In the Linux kernel, the following vulnerability has been resolved: i2c: s3c24xx: check the size of the SMBUS message before using it The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it. This is the same logic that was added in commit a6e04f05ce0b ("i2c: tegra: check msg length in SMBUS block read") to the i2c tegra driver.
CVE-2026-31628: In the Linux kernel, the following vulnerability has been resolved: x86/CPU: Fix FPDSS on Zen1 Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread. Fix that with a chicken bit.
CVE-2026-31629: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: add missing return after LLCP_CLOSED checks In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free. Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.
CVE-2026-31630: In the Linux kernel, the following vulnerability has been resolved: rxrpc: proc: size address buffers for %pISpc output The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example
CVE-2026-31634: In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix reference count leak in rxrpc_server_keyring() This patch fixes a reference count leak in rxrpc_server_keyring() by checking if rx->securities is already set.
CVE-2026-31637: In the Linux kernel, the following vulnerability has been resolved: rxrpc: reject undecryptable rxkad response tickets rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then parses the buffer as plaintext without checking whether crypto_skcipher_decrypt() succeeded. A malformed RESPONSE can therefore use a non-block-aligned ticket length, make the decrypt operation fail, and still drive the ticket parser with attacker-controlled bytes. Check the decrypt result and abort the connection with RXKADBADTICKET when ticket decryption fails.
CVE-2026-31638: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Only put the call ref if one was acquired rxrpc_input_packet_on_conn() can process a to-client packet after the current client call on the channel has already been torn down. In that case chan->call is NULL, rxrpc_try_get_call() returns NULL and there is no reference to drop. The client-side implicit-end error path does not account for that and unconditionally calls rxrpc_put_call(). This turns a protocol error path into a kernel crash instead of rejecting the packet. Only drop the call reference if one was actually acquired. Keep the existing protocol error handling unchanged.
CVE-2026-31639: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix key reference count leak from call->key When creating a client call in rxrpc_alloc_client_call(), the code obtains a reference to the key. This is never cleaned up and gets leaked when the call is destroyed. Fix this by freeing call->key in rxrpc_destroy_call(). Before the patch, it shows the key reference counter elevated: $ cat /proc/keys | grep afs@54321 1bffe9cd I--Q--i 8053480 4169w 3b010000 1000 1000 rxrpc afs@54321: ka $ After the patch, the invalidated key is removed when the code exits: $ cat /proc/keys | grep afs@54321 $
CVE-2026-31642: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix call removal to use RCU safe deletion Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu() rather than list_del_init() to prevent stuffing up reading /proc/net/rxrpc/calls from potentially getting into an infinite loop. This, however, means that list_empty() no longer works on an entry that's been deleted from the list, making it harder to detect prior deletion. Fix this by: Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that are unexpectedly still on the list. Limiting the number of steps means there's no need to call cond_resched() or to remove calls from the list here, thereby eliminating the need for rxrpc_put_call() to check for that. rxrpc_put_call() can then be fixed to unconditionally delete the call from the list as it is the only place that the deletion occurs.
CVE-2026-31644: In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix use-after-free and leak in lan966x_fdma_reload() When lan966x_fdma_reload() fails to allocate new RX buffers, the restore path restarts DMA using old descriptors whose pages were already freed via lan966x_fdma_rx_free_pages(). Since page_pool_put_full_page() can release pages back to the buddy allocator, the hardware may DMA into memory now owned by other kernel subsystems. Additionally, on the restore path, the newly created page pool (if allocation partially succeeded) is overwritten without being destroyed, leaking it. Fix both issues by deferring the release of old pages until after the new allocation succeeds. Save the old page array before the allocation so old pages can be freed on the success path. On the failure path, the old descriptors, pages and page pool are all still valid, making the restore safe. Also ensure the restore path re-enables NAPI and wakes the netdev, matching the success path.
CVE-2026-31645: In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix page pool leak in error paths lan966x_fdma_rx_alloc() creates a page pool but does not destroy it if the subsequent fdma_alloc_coherent() call fails, leaking the pool. Similarly, lan966x_fdma_init() frees the coherent DMA memory when lan966x_fdma_tx_alloc() fails but does not destroy the page pool that was successfully created by lan966x_fdma_rx_alloc(), leaking it. Add the missing page_pool_destroy() calls in both error paths.
CVE-2026-31646: In the Linux kernel, the following vulnerability has been resolved: net: lan966x: fix page_pool error handling in lan966x_fdma_rx_alloc_page_pool() page_pool_create() can return an ERR_PTR on failure. The return value is used unconditionally in the loop that follows, passing the error pointer through xdp_rxq_info_reg_mem_model() into page_pool_use_xdp_mem(), which dereferences it, causing a kernel oops. Add an IS_ERR check after page_pool_create() to return early on failure.
CVE-2026-31647: In the Linux kernel, the following vulnerability has been resolved: idpf: fix PREEMPT_RT raw/bh spinlock nesting for async VC handling Switch from using the completion's raw spinlock to a local lock in the idpf_vc_xn struct. The conversion is safe because complete/_all() are called outside the lock and there is no reason to share the completion lock in the current logic. This avoids invalid wait context reported by the kernel due to the async handler taking BH spinlock: [ 805.726977] ============================= [ 805.726991] [ BUG: Invalid wait context ] [ 805.727006] 7.0.0-rc2-net-devq-031026+ #28 Tainted: G S OE [ 805.727026] ----------------------------- [ 805.727038] kworker/u261:0/572 is trying to lock: [ 805.727051] ff190da6a8dbb6a0 (&vport_config->mac_filter_list_lock){+...}-{3:3}, at: idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727099] other info that might help us debug this: [ 805.727111] context-{5:5} [ 805.727119] 3 locks held by kworker/u261:0/572: [ 805.727132] #0: ff190da6db3e6148 ((wq_completion)idpf-0000:83:00.0-mbx){+.+.}-{0:0}, at: process_one_work+0x4b5/0x730 [ 805.727163] #1: ff3c6f0a6131fe50 ((work_completion)(&(&adapter->mbx_task)->work)){+.+.}-{0:0}, at: process_one_work+0x1e5/0x730 [ 805.727191] #2: ff190da765190020 (&x->wait#34){+.+.}-{2:2}, at: idpf_recv_mb_msg+0xc8/0x710 [idpf] [ 805.727218] stack backtrace: ... [ 805.727238] Workqueue: idpf-0000:83:00.0-mbx idpf_mbx_task [idpf] [ 805.727247] Call Trace: [ 805.727249] <TASK> [ 805.727251] dump_stack_lvl+0x77/0xb0 [ 805.727259] __lock_acquire+0xb3b/0x2290 [ 805.727268] ? __irq_work_queue_local+0x59/0x130 [ 805.727275] lock_acquire+0xc6/0x2f0 [ 805.727277] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727284] ? _printk+0x5b/0x80 [ 805.727290] _raw_spin_lock_bh+0x38/0x50 [ 805.727298] ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727303] idpf_mac_filter_async_handler+0xe9/0x260 [idpf] [ 805.727310] idpf_recv_mb_msg+0x1c8/0x710 [idpf] [ 805.727317] process_one_work+0x226/0x730 [ 805.727322] worker_thread+0x19e/0x340 [ 805.727325] ? __pfx_worker_thread+0x10/0x10 [ 805.727328] kthread+0xf4/0x130 [ 805.727333] ? __pfx_kthread+0x10/0x10 [ 805.727336] ret_from_fork+0x32c/0x410 [ 805.727345] ? __pfx_kthread+0x10/0x10 [ 805.727347] ret_from_fork_asm+0x1a/0x30 [ 805.727354] </TASK>
CVE-2026-31648: In the Linux kernel, the following vulnerability has been resolved: mm: filemap: fix nr_pages calculation overflow in filemap_map_pages() When running stress-ng on my Arm64 machine with v7.0-rc3 kernel, I encountered some very strange crash issues showing up as "Bad page state": " [ 734.496287] BUG: Bad page state in process stress-ng-env pfn:415735fb [ 734.496427] page: refcount:0 mapcount:1 mapping:0000000000000000 index:0x4cf316 pfn:0x415735fb [ 734.496434] flags: 0x57fffe000000800(owner_2|node=1|zone=2|lastcpupid=0x3ffff) [ 734.496439] raw: 057fffe000000800 0000000000000000 dead000000000122 0000000000000000 [ 734.496440] raw: 00000000004cf316 0000000000000000 0000000000000000 0000000000000000 [ 734.496442] page dumped because: nonzero mapcount " After analyzing this page’s state, it is hard to understand why the mapcount is not 0 while the refcount is 0, since this page is not where the issue first occurred. By enabling the CONFIG_DEBUG_VM config, I can reproduce the crash as well and captured the first warning where the issue appears: " [ 734.469226] page: refcount:33 mapcount:0 mapping:00000000bef2d187 index:0x81a0 pfn:0x415735c0 [ 734.469304] head: order:5 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 734.469315] memcg:ffff000807a8ec00 [ 734.469320] aops:ext4_da_aops ino:100b6f dentry name(?):"stress-ng-mmaptorture-9397-0-2736200540" [ 734.469335] flags: 0x57fffe400000069(locked|uptodate|lru|head|node=1|zone=2|lastcpupid=0x3ffff) ...... [ 734.469364] page dumped because: VM_WARN_ON_FOLIO((_Generic((page + nr_pages - 1), const struct page *: (const struct folio *)_compound_head(page + nr_pages - 1), struct page *: (struct folio *)_compound_head(page + nr_pages - 1))) != folio) [ 734.469390] ------------[ cut here ]------------ [ 734.469393] WARNING: ./include/linux/rmap.h:351 at folio_add_file_rmap_ptes+0x3b8/0x468, CPU#90: stress-ng-mlock/9430 [ 734.469551] folio_add_file_rmap_ptes+0x3b8/0x468 (P) [ 734.469555] set_pte_range+0xd8/0x2f8 [ 734.469566] filemap_map_folio_range+0x190/0x400 [ 734.469579] filemap_map_pages+0x348/0x638 [ 734.469583] do_fault_around+0x140/0x198 ...... [ 734.469640] el0t_64_sync+0x184/0x188 " The code that triggers the warning is: "VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio)", which indicates that set_pte_range() tried to map beyond the large folio’s size. By adding more debug information, I found that 'nr_pages' had overflowed in filemap_map_pages(), causing set_pte_range() to establish mappings for a range exceeding the folio size, potentially corrupting fields of pages that do not belong to this folio (e.g., page->_mapcount). After above analysis, I think the possible race is as follows: CPU 0 CPU 1 filemap_map_pages() ext4_setattr() //get and lock folio with old inode->i_size next_uptodate_folio() ....... //shrink the inode->i_size i_size_write(inode, attr->ia_size); //calculate the end_pgoff with the new inode->i_size file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); ...... //nr_pages can be overflowed, cause xas.xa_index > end_pgoff end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; ...... //map large folio filemap_map_folio_range() ...... //truncate folios truncate_pagecache(inode, inode->i_size); To fix this issue, move the 'end_pgoff' calculation before next_uptodate_folio(), so the retrieved folio stays consistent with the file end to avoid ---truncated---
CVE-2026-31649: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix integer underflow in chain mode The jumbo_frm() chain-mode implementation unconditionally computes len = nopaged_len - bmax; where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is BUF_SIZE_8KiB or BUF_SIZE_2KiB. However, the caller stmmac_xmit() decides to invoke jumbo_frm() based on skb->len (total length including page fragments): is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); When a packet has a small linear portion (nopaged_len <= bmax) but a large total length due to page fragments (skb->len > bmax), the subtraction wraps as an unsigned integer, producing a huge len value (~0xFFFFxxxx). This causes the while (len != 0) loop to execute hundreds of thousands of iterations, passing skb->data + bmax * i pointers far beyond the skb buffer to dma_map_single(). On IOMMU-less SoCs (the typical deployment for stmmac), this maps arbitrary kernel memory to the DMA engine, constituting a kernel memory disclosure and potential memory corruption from hardware. Fix this by introducing a buf_len local variable clamped to min(nopaged_len, bmax). Computing len = nopaged_len - buf_len is then always safe: it is zero when the linear portion fits within a single descriptor, causing the while (len != 0) loop to be skipped naturally, and the fragment loop in stmmac_xmit() handles page fragments afterward.
CVE-2026-31651: In the Linux kernel, the following vulnerability has been resolved: mmc: vub300: fix NULL-deref on disconnect Make sure to deregister the controller before dropping the reference to the driver data on disconnect to avoid NULL-pointer dereferences or use-after-free.
CVE-2026-31655: In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx8mp-blk-ctrl: Keep the NOC_HDCP clock enabled Keep the NOC_HDCP clock always enabled to fix the potential hang caused by the NoC ADB400 port power down handshake.
CVE-2026-31656: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <TASK> <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] </TASK> ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)
CVE-2026-31657: In the Linux kernel, the following vulnerability has been resolved: batman-adv: hold claim backbone gateways by reference batadv_bla_add_claim() can replace claim->backbone_gw and drop the old gateway's last reference while readers still follow the pointer. The netlink claim dump path dereferences claim->backbone_gw->orig and takes claim->backbone_gw->crc_lock without pinning the underlying backbone gateway. batadv_bla_check_claim() still has the same naked pointer access pattern. Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate on a stable gateway reference until the read-side work is complete. This keeps the dump and claim-check paths aligned with the lifetime rules introduced for the other BLA claim readers.
CVE-2026-31658: In the Linux kernel, the following vulnerability has been resolved: net: altera-tse: fix skb leak on DMA mapping error in tse_start_xmit() When dma_map_single() fails in tse_start_xmit(), the function returns NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the stack the packet was consumed, the skb is never freed, leaking memory on every DMA mapping failure. Add dev_kfree_skb_any() before returning to properly free the skb.
CVE-2026-31659: In the Linux kernel, the following vulnerability has been resolved: batman-adv: reject oversized global TT response buffers batadv_tt_prepare_tvlv_global_data() builds the allocation length for a global TT response in 16-bit temporaries. When a remote originator advertises a large enough global TT, the TT payload length plus the VLAN header offset can exceed 65535 and wrap before kmalloc(). The full-table response path still uses the original TT payload length when it fills tt_change, so the wrapped allocation is too small and batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object before the later packet-size check runs. Fix this by rejecting TT responses whose TVLV value length cannot fit in the 16-bit TVLV payload length field.
CVE-2026-31660: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: allocate rx skb before consuming bytes pn532_receive_buf() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already hand a complete frame to pn533_recv_frame() before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted.
CVE-2026-31661: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmsmac: Fix dma_free_coherent() size dma_alloc_consistent() may change the size to align it. The new size is saved in alloced. Change the free size to match the allocation size.
CVE-2026-31662: In the Linux kernel, the following vulnerability has been resolved: tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements bc_ackers on every inbound group ACK, even when the same member has already acknowledged the current broadcast round. Because bc_ackers is a u16, a duplicate ACK received after the last legitimate ACK wraps the counter to 65535. Once wrapped, tipc_group_bc_cong() keeps reporting congestion and later group broadcasts on the affected socket stay blocked until the group is recreated. Fix this by ignoring duplicate or stale ACKs before touching bc_acked or bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and prevents the underflow path.
CVE-2026-31663: In the Linux kernel, the following vulnerability has been resolved: xfrm: hold dev ref until after transport_finish NF_HOOK After async crypto completes, xfrm_input_resume() calls dev_put() immediately on re-entry before the skb reaches transport_finish. The skb->dev pointer is then used inside NF_HOOK and its okfn, which can race with device teardown. Remove the dev_put from the async resumption entry and instead drop the reference after the NF_HOOK call in transport_finish, using a saved device pointer since NF_HOOK may consume the skb. This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip the okfn. For non-transport exits (decaps, gro, drop) and secondary async return points, release the reference inline when async is set.
CVE-2026-31664: In the Linux kernel, the following vulnerability has been resolved: xfrm: clear trailing padding in build_polexpire() build_expire() clears the trailing padding bytes of struct xfrm_user_expire after setting the hard field via memset_after(), but the analogous function build_polexpire() does not do this for struct xfrm_user_polexpire. The padding bytes after the __u8 hard field are left uninitialized from the heap allocation, and are then sent to userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners, leaking kernel heap memory contents. Add the missing memset_after() call, matching build_expire().
CVE-2026-31665: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: fix use-after-free in timeout object destroy nft_ct_timeout_obj_destroy() frees the timeout object with kfree() immediately after nf_ct_untimeout(), without waiting for an RCU grace period. Concurrent packet processing on other CPUs may still hold RCU-protected references to the timeout object obtained via rcu_dereference() in nf_ct_timeout_data(). Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer freeing until after an RCU grace period, matching the approach already used in nfnetlink_cttimeout.c. KASAN report: BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0 Read of size 4 at addr ffff8881035fe19c by task exploit/80 Call Trace: nf_conntrack_tcp_packet+0x1381/0x29d0 nf_conntrack_in+0x612/0x8b0 nf_hook_slow+0x70/0x100 __ip_local_out+0x1b2/0x210 tcp_sendmsg_locked+0x722/0x1580 __sys_sendto+0x2d8/0x320 Allocated by task 75: nft_ct_timeout_obj_init+0xf6/0x290 nft_obj_init+0x107/0x1b0 nf_tables_newobj+0x680/0x9c0 nfnetlink_rcv_batch+0xc29/0xe00 Freed by task 26: nft_obj_destroy+0x3f/0xa0 nf_tables_trans_destroy_work+0x51c/0x5c0 process_one_work+0x2c4/0x5a0
CVE-2026-31666: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix incorrect return value after changing leaf in lookup_extent_data_ref() After commit 1618aa3c2e01 ("btrfs: simplify return variables in lookup_extent_data_ref()"), the err and ret variables were merged into a single ret variable. However, when btrfs_next_leaf() returns 0 (success), ret is overwritten from -ENOENT to 0. If the first key in the next leaf does not match (different objectid or type), the function returns 0 instead of -ENOENT, making the caller believe the lookup succeeded when it did not. This can lead to operations on the wrong extent tree item, potentially causing extent tree corruption. Fix this by returning -ENOENT directly when the key does not match, instead of relying on the ret variable.
CVE-2026-31667: In the Linux kernel, the following vulnerability has been resolved: Input: uinput - fix circular locking dependency with ff-core A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)
CVE-2026-31668: In the Linux kernel, the following vulnerability has been resolved: seg6: separate dst_cache for input and output paths in seg6 lwtunnel The seg6 lwtunnel uses a single dst_cache per encap route, shared between seg6_input_core() and seg6_output_core(). These two paths can perform the post-encap SID lookup in different routing contexts (e.g., ip rules matching on the ingress interface, or VRF table separation). Whichever path runs first populates the cache, and the other reuses it blindly, bypassing its own lookup. Fix this by splitting the cache into cache_input and cache_output, so each path maintains its own cached dst independently.
CVE-2026-31669: In the Linux kernel, the following vulnerability has been resolved: mptcp: fix slab-use-after-free in __inet_lookup_established The ehash table lookups are lockless and rely on SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability during RCU read-side critical sections. Both tcp_prot and tcpv6_prot have their slab caches created with this flag via proto_register(). However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into tcpv6_prot_override during inet_init() (fs_initcall, level 5), before inet6_init() (module_init/device_initcall, level 6) has called proto_register(&tcpv6_prot). At that point, tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab remains NULL permanently. This causes MPTCP v6 subflow child sockets to be allocated via kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so when these sockets are freed without SOCK_RCU_FREE (which is cleared for child sockets by design), the memory can be immediately reused. Concurrent ehash lookups under rcu_read_lock can then access freed memory, triggering a slab-use-after-free in __inet_lookup_established. Fix this by splitting the IPv6-specific initialization out of mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called from mptcp_proto_v6_init() before protocol registration. This ensures tcpv6_prot_override.slab correctly inherits the SLAB_TYPESAFE_BY_RCU slab cache.
CVE-2026-31670: In the Linux kernel, the following vulnerability has been resolved: net: rfkill: prevent unlimited numbers of rfkill events from being created Userspace can create an unlimited number of rfkill events if the system is so configured, while not consuming them from the rfkill file descriptor, causing a potential out of memory situation. Prevent this from bounding the number of pending rfkill events at a "large" number (i.e. 1000) to prevent abuses like this.
CVE-2026-31671: In the Linux kernel, the following vulnerability has been resolved: xfrm_user: fix info leak in build_report() struct xfrm_user_report is a __u8 proto field followed by a struct xfrm_selector which means there is three "empty" bytes of padding, but the padding is never zeroed before copying to userspace. Fix that up by zeroing the structure before setting individual member variables.
CVE-2026-31672: In the Linux kernel, the following vulnerability has been resolved: wifi: rt2x00usb: fix devres lifetime USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the USB anchor lifetime so that it is released on driver unbind.
CVE-2026-31673: In the Linux kernel, the following vulnerability has been resolved: af_unix: read UNIX_DIAG_VFS data under unix_state_lock Exact UNIX diag lookups hold a reference to the socket, but not to u->path. Meanwhile, unix_release_sock() clears u->path under unix_state_lock() and drops the path reference after unlocking. Read the inode and device numbers for UNIX_DIAG_VFS while holding unix_state_lock(), then emit the netlink attribute after dropping the lock. This keeps the VFS data stable while the reply is being built.
CVE-2026-31674: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check() Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS. rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[]. Validate addrnr during rule installation so malformed rules are rejected before the match logic can use an out-of-range value.
CVE-2026-31675: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_netem: fix out-of-bounds access in packet corruption In netem_enqueue(), the packet corruption logic uses get_random_u32_below(skb_headlen(skb)) to select an index for modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0. Passing 0 to get_random_u32_below() takes the variable-ceil slow path which returns an unconstrained 32-bit random integer. Using this unconstrained value as an offset into skb->data results in an out-of-bounds memory access. Fix this by verifying skb_headlen(skb) is non-zero before attempting to corrupt the linear data area. Fully non-linear packets will silently bypass the corruption logic.
CVE-2026-31676: In the Linux kernel, the following vulnerability has been resolved: rxrpc: only handle RESPONSE during service challenge Only process RESPONSE packets while the service connection is still in RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before running response verification and security initialization, then use a local secured flag to decide whether to queue the secured-connection work after the state transition. This keeps duplicate or late RESPONSE packets from re-running the setup path and removes the unlocked post-transition state test.
CVE-2026-31677: In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - limit RX SG extraction by receive buffer budget Make af_alg_get_rsgl() limit each RX scatterlist extraction to the remaining receive buffer budget. af_alg_get_rsgl() currently uses af_alg_readable() only as a gate before extracting data into the RX scatterlist. Limit each extraction to the remaining af_alg_rcvbuf(sk) budget so that receive-side accounting matches the amount of data attached to the request. If skcipher cannot obtain enough RX space for at least one chunk while more data remains to be processed, reject the recvmsg call instead of rounding the request length down to zero.
CVE-2026-31678: In the Linux kernel, the following vulnerability has been resolved: openvswitch: defer tunnel netdev_put to RCU release ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already detached the device. Dropping the netdev reference in destroy can race with concurrent readers that still observe vport->dev. Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let vport_netdev_free() drop the reference from the RCU callback, matching the non-tunnel destroy path and avoiding additional synchronization under RTNL.
CVE-2026-31679: In the Linux kernel, the following vulnerability has been resolved: openvswitch: validate MPLS set/set_masked payload length validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for SET/SET_MASKED actions. In action handling, OVS expects fixed-size MPLS key data (struct ovs_key_mpls). Use the already normalized key_len (masked case included) and reject non-matching MPLS action key sizes. Reject invalid MPLS action payload lengths early.
CVE-2026-31680: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: flowlabel: defer exclusive option free until RCU teardown `ip6fl_seq_show()` walks the global flowlabel hash under the seq-file RCU read-side lock and prints `fl->opt->opt_nflen` when an option block is present. Exclusive flowlabels currently free `fl->opt` as soon as `fl->users` drops to zero in `fl_release()`. However, the surrounding `struct ip6_flowlabel` remains visible in the global hash table until later garbage collection removes it and `fl_free_rcu()` finally tears it down. A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that early `kfree()` and dereference freed option state, triggering a crash in `ip6fl_seq_show()`. Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches the lifetime already required for the enclosing flowlabel while readers can still reach it under RCU.
CVE-2026-31681: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_multiport: validate range encoding in checkentry ports_match_v1() treats any non-zero pflags entry as the start of a port range and unconditionally consumes the next ports[] element as the range end. The checkentry path currently validates protocol, flags and count, but it does not validate the range encoding itself. As a result, malformed rules can mark the last slot as a range start or place two range starts back to back, leaving ports_match_v1() to step past the last valid ports[] element while interpreting the rule. Reject malformed multiport v1 rules in checkentry by validating that each range start has a following element and that the following element is not itself marked as another range start.
CVE-2026-31682: In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: linearize skb before parsing ND options br_nd_send() parses neighbour discovery options from ns->opt[] and assumes that these options are in the linear part of request. Its callers only guarantee that the ICMPv6 header and target address are available, so the option area can still be non-linear. Parsing ns->opt[] in that case can access data past the linear buffer. Linearize request before option parsing and derive ns from the linear network header.
CVE-2026-31683: In the Linux kernel, the following vulnerability has been resolved: batman-adv: avoid OGM aggregation when skb tailroom is insufficient When OGM aggregation state is toggled at runtime, an existing forwarded packet may have been allocated with only packet_len bytes, while a later packet can still be selected for aggregation. Appending in this case can hit skb_put overflow conditions. Reject aggregation when the target skb tailroom cannot accommodate the new packet. The caller then falls back to creating a new forward packet instead of appending.
CVE-2026-31684: In the Linux kernel, the following vulnerability has been resolved: net: sched: act_csum: validate nested VLAN headers tcf_csum_act() walks nested VLAN headers directly from skb->data when an skb still carries in-payload VLAN tags. The current code reads vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without first ensuring that the full VLAN header is present in the linear area. If only part of an inner VLAN header is linearized, accessing h_vlan_encapsulated_proto reads past the linear area, and the following skb_pull(VLAN_HLEN) may violate skb invariants. Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and pulling each nested VLAN header. If the header still is not fully available, drop the packet through the existing error path.
CVE-2026-31685: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_eui64: reject invalid MAC header for all packets `eui64_mt6()` derives a modified EUI-64 from the Ethernet source address and compares it with the low 64 bits of the IPv6 source address. The existing guard only rejects an invalid MAC header when `par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()` can still reach `eth_hdr(skb)` even when the MAC header is not valid. Fix this by removing the `par->fragoff != 0` condition so that packets with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.
CVE-2026-31788: In the Linux kernel, the following vulnerability has been resolved: xen/privcmd: restrict usage in unprivileged domU The Xen privcmd driver allows to issue arbitrary hypercalls from user space processes. This is normally no problem, as access is usually limited to root and the hypervisor will deny any hypercalls affecting other domains. In case the guest is booted using secure boot, however, the privcmd driver would be enabling a root user process to modify e.g. kernel memory contents, thus breaking the secure boot feature. The only known case where an unprivileged domU is really needing to use the privcmd driver is the case when it is acting as the device model for another guest. In this case all hypercalls issued via the privcmd driver will target that other guest. Fortunately the privcmd driver can already be locked down to allow only hypercalls targeting a specific domain, but this mode can be activated from user land only today. The target domain can be obtained from Xenstore, so when not running in dom0 restrict the privcmd driver to that target domain from the beginning, resolving the potential problem of breaking secure boot. This is XSA-482 --- V2: - defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich) - wait in open() if target domain isn't known yet - issue message in case no target domain found (Jan Beulich)

1 ignored issue:

CVE-2025-71188: In the Linux kernel, the following vulnerability has been resolved: dmaengine: lpc18xx-dmamux: fix device leak on route allocation Make sure to drop the reference taken when looking up the DMA mux platform device during route allocation. Note that holding a reference to a device does not prevent its driver data from going away so there is no point in keeping the reference.

Created: 2023-06-11 Last update: 2026-04-26 05:02

23 security issues in sid high

There are 23 open security issues in sid.

23 important issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-6238: A buffer overflow vulnerability was found in the NVM Express (NVMe) driver in the Linux kernel. Only privileged user could specify a small meta buffer and let the device perform larger Direct Memory Access (DMA) into the same buffer, overwriting unrelated kernel memory, causing random kernel crashes and memory corruption.
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2019-15213: An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-16089: An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-56709: In the Linux kernel, the following vulnerability has been resolved: io_uring: check if iowq is killed before queuing task work can be executed after the task has gone through io_uring termination, whether it's the final task_work run or the fallback path. In this case, task work will find ->io_wq being already killed and null'ed, which is a problem if it then tries to forward the request to io_queue_iowq(). Make io_queue_iowq() fail requests in this case. Note that it also checks PF_KTHREAD, because the user can first close a DEFER_TASKRUN ring and shortly after kill the task, in which case ->iowq check would race.
CVE-2026-31574: In the Linux kernel, the following vulnerability has been resolved: clockevents: Add missing resets of the next_event_forced flag The prevention mechanism against timer interrupt starvation missed to reset the next_event_forced flag in a couple of places: - When the clock event state changes. That can cause the flag to be stale over a shutdown/startup sequence - When a non-forced event is armed, which then prevents rearming before that event. If that event is far out in the future this will cause missed timer interrupts. - In the suspend wakeup handler. That led to stalls which have been reported by several people. Add the missing resets, which fixes the problems for the reporters.

Created: 2022-07-04 Last update: 2026-04-26 05:02

84 security issues in forky high

There are 84 open security issues in forky.

84 important issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-6238: A buffer overflow vulnerability was found in the NVM Express (NVMe) driver in the Linux kernel. Only privileged user could specify a small meta buffer and let the device perform larger Direct Memory Access (DMA) into the same buffer, overwriting unrelated kernel memory, causing random kernel crashes and memory corruption.
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2019-15213: An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-16089: An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-56709: In the Linux kernel, the following vulnerability has been resolved: io_uring: check if iowq is killed before queuing task work can be executed after the task has gone through io_uring termination, whether it's the final task_work run or the fallback path. In this case, task work will find ->io_wq being already killed and null'ed, which is a problem if it then tries to forward the request to io_queue_iowq(). Make io_queue_iowq() fail requests in this case. Note that it also checks PF_KTHREAD, because the user can first close a DEFER_TASKRUN ring and shortly after kill the task, in which case ->iowq check would race.
CVE-2026-31531: In the Linux kernel, the following vulnerability has been resolved: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop() When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for single nexthops and small Equal-Cost Multi-Path groups, this fixed allocation fails for large nexthop groups like 512 nexthops. This results in the following warning splat: WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608 [...] RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395) [...] Call Trace: <TASK> rtnetlink_rcv_msg (net/core/rtnetlink.c:6989) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585) ___sys_sendmsg (net/socket.c:2641) __sys_sendmsg (net/socket.c:2671) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Fix this by allocating the size dynamically using nh_nlmsg_size() and using nlmsg_new(), this is consistent with nexthop_notify() behavior. In addition, adjust nh_nlmsg_size_grp() so it calculates the size needed based on flags passed. While at it, also add the size of NHA_FDB for nexthop group size calculation as it was missing too. This cannot be reproduced via iproute2 as the group size is currently limited and the command fails as follows: addattr_l ERROR: message exceeded bound of 1048
CVE-2026-31532: In the Linux kernel, the following vulnerability has been resolved: can: raw: fix ro->uniq use-after-free in raw_rcv() raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage. Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained. [mkl: applied manually]
CVE-2026-31574: In the Linux kernel, the following vulnerability has been resolved: clockevents: Add missing resets of the next_event_forced flag The prevention mechanism against timer interrupt starvation missed to reset the next_event_forced flag in a couple of places: - When the clock event state changes. That can cause the flag to be stale over a shutdown/startup sequence - When a non-forced event is armed, which then prevents rearming before that event. If that event is far out in the future this will cause missed timer interrupts. - In the suspend wakeup handler. That led to stalls which have been reported by several people. Add the missing resets, which fixes the problems for the reporters.
CVE-2026-31575: In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: fix hugetlb fault mutex hash calculation In mfill_atomic_hugetlb(), linear_page_index() is used to calculate the page index for hugetlb_fault_mutex_hash(). However, linear_page_index() returns the index in PAGE_SIZE units, while hugetlb_fault_mutex_hash() expects the index in huge page units. This mismatch means that different addresses within the same huge page can produce different hash values, leading to the use of different mutexes for the same huge page. This can cause races between faulting threads, which can corrupt the reservation map and trigger the BUG_ON in resv_map_release(). Fix this by introducing hugetlb_linear_page_index(), which returns the page index in huge page granularity, and using it in place of linear_page_index().
CVE-2026-31576: In the Linux kernel, the following vulnerability has been resolved: media: hackrf: fix to not free memory after the device is registered in hackrf_probe() In hackrf driver, the following race condition occurs: ``` CPU0 CPU1 hackrf_probe() kzalloc(); // alloc hackrf_dev .... v4l2_device_register(); .... fd = sys_open("/path/to/dev"); // open hackrf fd .... v4l2_device_unregister(); .... kfree(); // free hackrf_dev .... sys_ioctl(fd, ...); v4l2_ioctl(); video_is_registered() // UAF!! .... sys_close(fd); v4l2_release() // UAF!! hackrf_video_release() kfree(); // DFB!! ``` When a V4L2 or video device is unregistered, the device node is removed so new open() calls are blocked. However, file descriptors that are already open-and any in-flight I/O-do not terminate immediately; they remain valid until the last reference is dropped and the driver's release() is invoked. Therefore, freeing device memory on the error path after hackrf_probe() has registered dev it will lead to a race to use-after-free vuln, since those already-open handles haven't been released yet. And since release() free memory too, race to use-after-free and double-free vuln occur. To prevent this, if device is registered from probe(), it should be modified to free memory only through release() rather than calling kfree() directly.
CVE-2026-31577: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map The DAT inode's btree node cache (i_assoc_inode) is initialized lazily during btree operations. However, nilfs_mdt_save_to_shadow_map() assumes i_assoc_inode is already initialized when copying dirty pages to the shadow map during GC. If NILFS_IOCTL_CLEAN_SEGMENTS is called immediately after mount before any btree operation has occurred on the DAT inode, i_assoc_inode is NULL leading to a general protection fault. Fix this by calling nilfs_attach_btree_node_cache() on the DAT inode in nilfs_dat_read() at mount time, ensuring i_assoc_inode is always initialized before any GC operation can use it.
CVE-2026-31578: In the Linux kernel, the following vulnerability has been resolved: media: as102: fix to not free memory after the device is registered in as102_usb_probe() In as102_usb driver, the following race condition occurs: ``` CPU0 CPU1 as102_usb_probe() kzalloc(); // alloc as102_dev_t .... usb_register_dev(); fd = sys_open("/path/to/dev"); // open as102 fd .... usb_deregister_dev(); .... kfree(); // free as102_dev_t .... sys_close(fd); as102_release() // UAF!! as102_usb_release() kfree(); // DFB!! ``` When a USB character device registered with usb_register_dev() is later unregistered (via usb_deregister_dev() or disconnect), the device node is removed so new open() calls fail. However, file descriptors that are already open do not go away immediately: they remain valid until the last reference is dropped and the driver's .release() is invoked. In as102, as102_usb_probe() calls usb_register_dev() and then, on an error path, does usb_deregister_dev() and frees as102_dev_t right away. If userspace raced a successful open() before the deregistration, that open FD will later hit as102_release() --> as102_usb_release() and access or free as102_dev_t again, occur a race to use-after-free and double-free vuln. The fix is to never kfree(as102_dev_t) directly once usb_register_dev() has succeeded. After deregistration, defer freeing memory to .release(). In other words, let release() perform the last kfree when the final open FD is closed.
CVE-2026-31579: In the Linux kernel, the following vulnerability has been resolved: wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wg_netns_pre_exit() manually acquires rtnl_lock() inside the pernet .pre_exit callback. This causes a hung task when another thread holds rtnl_mutex - the cleanup_net workqueue (or the setup_net failure rollback path) blocks indefinitely in wg_netns_pre_exit() waiting to acquire the lock. Convert to .exit_rtnl, introduced in commit 7a60d91c690b ("net: Add ->exit_rtnl() hook to struct pernet_operations."), where the framework already holds RTNL and batches all callbacks under a single rtnl_lock()/rtnl_unlock() pair, eliminating the contention window. The rcu_assign_pointer(wg->creating_net, NULL) is safe to move from .pre_exit to .exit_rtnl (which runs after synchronize_rcu()) because all RCU readers of creating_net either use maybe_get_net() - which returns NULL for a dying namespace with zero refcount - or access net->user_ns which remains valid throughout the entire ops_undo_list sequence. [ Jason: added __net_exit and __read_mostly annotations that were missing. ]
CVE-2026-31580: In the Linux kernel, the following vulnerability has been resolved: bcache: fix cached_dev.sb_bio use-after-free and crash In our production environment, we have received multiple crash reports regarding libceph, which have caught our attention: ``` [6888366.280350] Call Trace: [6888366.280452] blk_update_request+0x14e/0x370 [6888366.280561] blk_mq_end_request+0x1a/0x130 [6888366.280671] rbd_img_handle_request+0x1a0/0x1b0 [rbd] [6888366.280792] rbd_obj_handle_request+0x32/0x40 [rbd] [6888366.280903] __complete_request+0x22/0x70 [libceph] [6888366.281032] osd_dispatch+0x15e/0xb40 [libceph] [6888366.281164] ? inet_recvmsg+0x5b/0xd0 [6888366.281272] ? ceph_tcp_recvmsg+0x6f/0xa0 [libceph] [6888366.281405] ceph_con_process_message+0x79/0x140 [libceph] [6888366.281534] ceph_con_v1_try_read+0x5d7/0xf30 [libceph] [6888366.281661] ceph_con_workfn+0x329/0x680 [libceph] ``` After analyzing the coredump file, we found that the address of dc->sb_bio has been freed. We know that cached_dev is only freed when it is stopped. Since sb_bio is a part of struct cached_dev, rather than an alloc every time. If the device is stopped while writing to the superblock, the released address will be accessed at endio. This patch hopes to wait for sb_write to complete in cached_dev_free. It should be noted that we analyzed the cause of the problem, then tell all details to the QWEN and adopted the modifications it made.
CVE-2026-31581: In the Linux kernel, the following vulnerability has been resolved: ALSA: 6fire: fix use-after-free on disconnect In usb6fire_chip_abort(), the chip struct is allocated as the card's private data (via snd_card_new with sizeof(struct sfire_chip)). When snd_card_free_when_closed() is called and no file handles are open, the card and embedded chip are freed synchronously. The subsequent chip->card = NULL write then hits freed slab memory. Call trace: usb6fire_chip_abort sound/usb/6fire/chip.c:59 [inline] usb6fire_chip_disconnect+0x348/0x358 sound/usb/6fire/chip.c:182 usb_unbind_interface+0x1a8/0x88c drivers/usb/core/driver.c:458 ... hub_event+0x1a04/0x4518 drivers/usb/core/hub.c:5953 Fix by moving the card lifecycle out of usb6fire_chip_abort() and into usb6fire_chip_disconnect(). The card pointer is saved in a local before any teardown, snd_card_disconnect() is called first to prevent new opens, URBs are aborted while chip is still valid, and snd_card_free_when_closed() is called last so chip is never accessed after the card may be freed.
CVE-2026-31582: In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix use-after-free on USB disconnect After powerz_disconnect() frees the URB and releases the mutex, a subsequent powerz_read() call can acquire the mutex and call powerz_read_data(), which dereferences the freed URB pointer. Fix by: - Setting priv->urb to NULL in powerz_disconnect() so that powerz_read_data() can detect the disconnected state. - Adding a !priv->urb check at the start of powerz_read_data() to return -ENODEV on a disconnected device. - Moving usb_set_intfdata() before hwmon registration so the disconnect handler can always find the priv pointer.
CVE-2026-31583: In the Linux kernel, the following vulnerability has been resolved: media: em28xx: fix use-after-free in em28xx_v4l2_open() em28xx_v4l2_open() reads dev->v4l2 without holding dev->lock, creating a race with em28xx_v4l2_init()'s error path and em28xx_v4l2_fini(), both of which free the em28xx_v4l2 struct and set dev->v4l2 to NULL under dev->lock. This race leads to two issues: - use-after-free in v4l2_fh_init() when accessing vdev->ctrl_handler, since the video_device is embedded in the freed em28xx_v4l2 struct. - NULL pointer dereference in em28xx_resolution_set() when accessing v4l2->norm, since dev->v4l2 has been set to NULL. Fix this by moving the mutex_lock() before the dev->v4l2 read and adding a NULL check for dev->v4l2 under the lock.
CVE-2026-31584: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: fix use-after-free in encoder release path The fops_vcodec_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->encode_work. This creates a race window where the workqueue handler (mtk_venc_worker) may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release path) CPU 1 (workqueue) --------------------- ------------------ fops_vcodec_release() v4l2_m2m_ctx_release() v4l2_m2m_cancel_job() // waits for m2m job "done" mtk_venc_worker() v4l2_m2m_job_finish() // m2m job "done" // BUT worker still running! // post-job_finish access: other ctx dereferences // UAF if ctx already freed // returns (job "done") kfree(ctx) // ctx freed Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle. After v4l2_m2m_job_finish() is called, the m2m framework considers the job complete and v4l2_m2m_ctx_release() returns, but the worker function continues executing and may still access ctx. The work is queued during encode operations via: queue_work(ctx->dev->encode_workqueue, &ctx->encode_work) The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx fields even after calling v4l2_m2m_job_finish(). This vulnerability was confirmed with KASAN by running an instrumented test module that widens the post-job_finish race window. KASAN detected: BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180 Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12 Workqueue: mtk_vcodec_enc_wq mtk_venc_worker Allocated by task 47: __kasan_kmalloc+0x7f/0x90 fops_vcodec_open+0x85/0x1a0 Freed by task 47: __kasan_slab_free+0x43/0x70 kfree+0xee/0x3a0 fops_vcodec_release+0xb7/0x190 Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx). This ensures the workqueue handler is both cancelled (if pending) and synchronized (waits for any running handler to complete) before the context is freed. Placement rationale: The fix is placed after v4l2_ctrl_handler_free() and before list_del_init(&ctx->list). At this point, all m2m operations are done (v4l2_m2m_ctx_release() has returned), and we need to ensure the workqueue is synchronized before removing ctx from the list and freeing it. Note: The open error path does NOT need cancel_work_sync() because INIT_WORK() only initializes the work structure - it does not schedule it. Work is only scheduled later during device_run() operations.
CVE-2026-31585: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix nfeeds state corruption on start_streaming failure syzbot reported a memory leak in vidtv_psi_service_desc_init [1]. When vidtv_start_streaming() fails inside vidtv_start_feed(), the nfeeds counter is left incremented even though no feed was actually started. This corrupts the driver state: subsequent start_feed calls see nfeeds > 1 and skip starting the mux, while stop_feed calls eventually try to stop a non-existent stream. This state corruption can also lead to memory leaks, since the mux and channel resources may be partially allocated during a failed start_streaming but never cleaned up, as the stop path finds dvb->streaming == false and returns early. Fix by decrementing nfeeds back when start_streaming fails, keeping the counter in sync with the actual number of active feeds. [1] BUG: memory leak unreferenced object 0xffff888145b50820 (size 32): comm "syz.0.17", pid 6068, jiffies 4294944486 backtrace (crc 90a0c7d4): vidtv_psi_service_desc_init+0x74/0x1b0 drivers/media/test-drivers/vidtv/vidtv_psi.c:288 vidtv_channel_s302m_init+0xb1/0x2a0 drivers/media/test-drivers/vidtv/vidtv_channel.c:83 vidtv_channels_init+0x1b/0x40 drivers/media/test-drivers/vidtv/vidtv_channel.c:524 vidtv_mux_init+0x516/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:518 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31586: In the Linux kernel, the following vulnerability has been resolved: mm: blk-cgroup: fix use-after-free in cgwb_release_workfn() cgwb_release_workfn() calls css_put(wb->blkcg_css) and then later accesses wb->blkcg_css again via blkcg_unpin_online(). If css_put() drops the last reference, the blkcg can be freed asynchronously (css_free_rwork_fn -> blkcg_css_free -> kfree) before blkcg_unpin_online() dereferences the pointer to access blkcg->online_pin, resulting in a use-after-free: BUG: KASAN: slab-use-after-free in blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) Write of size 4 at addr ff11000117aa6160 by task kworker/71:1/531 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) cgwb_release_workfn (mm/backing-dev.c:629) process_scheduled_works (kernel/workqueue.c:3278 kernel/workqueue.c:3385) Freed by task 1016: kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6246 mm/slub.c:6561) css_free_rwork_fn (kernel/cgroup/cgroup.c:5542) process_scheduled_works (kernel/workqueue.c:3302 kernel/workqueue.c:3385) ** Stack based on commit 66672af7a095 ("Add linux-next specific files for 20260410") I am seeing this crash sporadically in Meta fleet across multiple kernel versions. A full reproducer is available at: https://github.com/leitao/debug/blob/main/reproducers/repro_blkcg_uaf.sh (The race window is narrow. To make it easily reproducible, inject a msleep(100) between css_put() and blkcg_unpin_online() in cgwb_release_workfn(). With that delay and a KASAN-enabled kernel, the reproducer triggers the splat reliably in less than a second.) Fix this by moving blkcg_unpin_online() before css_put(), so the cgwb's CSS reference keeps the blkcg alive while blkcg_unpin_online() accesses it.
CVE-2026-31587: In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm: move component registration to unmanaged version q6apm component registers dais dynamically from ASoC toplology, which are allocated using device managed version apis. Allocating both component and dynamic dais using managed version could lead to incorrect free ordering, dai will be freed while component still holding references to it. Fix this issue by moving component to unmanged version so that the dai pointers are only freeded after the component is removed. ================================================================== BUG: KASAN: slab-use-after-free in snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] Read of size 8 at addr ffff00084493a6e8 by task kworker/u48:0/3426 Tainted: [W]=WARN Hardware name: LENOVO 21N2ZC5PUS/21N2ZC5PUS, BIOS N42ET57W (1.31 ) 08/08/2024 Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] Call trace: show_stack+0x28/0x7c (C) dump_stack_lvl+0x60/0x80 print_report+0x160/0x4b4 kasan_report+0xac/0xfc __asan_report_load8_noabort+0x20/0x34 snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] snd_soc_unregister_component_by_driver+0x50/0x88 [snd_soc_core] devm_component_release+0x30/0x5c [snd_soc_core] devres_release_all+0x13c/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Allocated by task 77: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 kasan_save_alloc_info+0x44/0x58 __kasan_kmalloc+0xbc/0xdc __kmalloc_node_track_caller_noprof+0x1f4/0x620 devm_kmalloc+0x7c/0x1c8 snd_soc_register_dai+0x50/0x4f0 [snd_soc_core] soc_tplg_pcm_elems_load+0x55c/0x1eb8 [snd_soc_core] snd_soc_tplg_component_load+0x4f8/0xb60 [snd_soc_core] audioreach_tplg_init+0x124/0x1fc [snd_q6apm] q6apm_audio_probe+0x10/0x1c [snd_q6apm] snd_soc_component_probe+0x5c/0x118 [snd_soc_core] soc_probe_component+0x44c/0xaf0 [snd_soc_core] snd_soc_bind_card+0xad0/0x2370 [snd_soc_core] snd_soc_register_card+0x3b0/0x4c0 [snd_soc_core] devm_snd_soc_register_card+0x50/0xc8 [snd_soc_core] x1e80100_platform_probe+0x208/0x368 [snd_soc_x1e80100] platform_probe+0xc0/0x188 really_probe+0x188/0x804 __driver_probe_device+0x158/0x358 driver_probe_device+0x60/0x190 __device_attach_driver+0x16c/0x2a8 bus_for_each_drv+0x100/0x194 __device_attach+0x174/0x380 device_initial_probe+0x14/0x20 bus_probe_device+0x124/0x154 deferred_probe_work_func+0x140/0x220 process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Freed by task 3426: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 __kasan_save_free_info+0x4c/0x80 __kasan_slab_free+0x78/0xa0 kfree+0x100/0x4a4 devres_release_all+0x144/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20
CVE-2026-31588: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use scratch field in MMIO fragment to hold small write values When exiting to userspace to service an emulated MMIO write, copy the to-be-written value to a scratch field in the MMIO fragment if the size of the data payload is 8 bytes or less, i.e. can fit in a single chunk, instead of pointing the fragment directly at the source value. This fixes a class of use-after-free bugs that occur when the emulator initiates a write using an on-stack, local variable as the source, the write splits a page boundary, *and* both pages are MMIO pages. Because KVM's ABI only allows for physically contiguous MMIO requests, accesses that split MMIO pages are separated into two fragments, and are sent to userspace one at a time. When KVM attempts to complete userspace MMIO in response to KVM_RUN after the first fragment, KVM will detect the second fragment and generate a second userspace exit, and reference the on-stack variable. The issue is most visible if the second KVM_RUN is performed by a separate task, in which case the stack of the initiating task can show up as truly freed data. ================================================================== BUG: KASAN: use-after-free in complete_emulated_mmio+0x305/0x420 Read of size 1 at addr ffff888009c378d1 by task syz-executor417/984 CPU: 1 PID: 984 Comm: syz-executor417 Not tainted 5.10.0-182.0.0.95.h2627.eulerosv2r13.x86_64 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xbe/0xfd print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 check_memory_region+0xfd/0x1f0 memcpy+0x20/0x60 complete_emulated_mmio+0x305/0x420 kvm_arch_vcpu_ioctl_run+0x63f/0x6d0 kvm_vcpu_ioctl+0x413/0xb20 __se_sys_ioctl+0x111/0x160 do_syscall_64+0x30/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 RIP: 0033:0x42477d Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007faa8e6890e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000004d7338 RCX: 000000000042477d RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005 RBP: 00000000004d7330 R08: 00007fff28d546df R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d733c R13: 0000000000000000 R14: 000000000040a200 R15: 00007fff28d54720 The buggy address belongs to the page: page:0000000029f6a428 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9c37 flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea0000270dc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888009c37780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888009c37880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888009c37900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== The bug can also be reproduced with a targeted KVM-Unit-Test by hacking KVM to fill a large on-stack variable in complete_emulated_mmio(), i.e. by overwrite the data value with garbage. Limit the use of the scratch fields to 8-byte or smaller accesses, and to just writes, as larger accesses and reads are not affected thanks to implementation details in the emulator, but add a sanity check to ensure those details don't change in the future. Specifically, KVM never uses on-stack variables for accesses larger that 8 bytes, e.g. uses an operand in the emulator context, and *al ---truncated---
CVE-2026-31589: In the Linux kernel, the following vulnerability has been resolved: mm: call ->free_folio() directly in folio_unmap_invalidate() We can only call filemap_free_folio() if we have a reference to (or hold a lock on) the mapping. Otherwise, we've already removed the folio from the mapping so it no longer pins the mapping and the mapping can be removed, causing a use-after-free when accessing mapping->a_ops. Follow the same pattern as __remove_mapping() and load the free_folio function pointer before dropping the lock on the mapping. That lets us make filemap_free_folio() static as this was the only caller outside filemap.c.
CVE-2026-31590: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing: struct kvm_enc_region range = { .addr = 0, .size = -1ul, }; __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future. if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.
CVE-2026-31591: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel. Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).
CVE-2026-31592: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Protect *all* of sev_mem_enc_register_region() with kvm->lock Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G U W O 6.16.0-smp-DEV #1 NONE Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024 RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83 Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00 RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256 RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000 RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000 R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000 R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000 FS: 00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0 Call Trace: <TASK> kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371 kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363 __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f34e9f7e9a9 Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9 RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007 RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8 </TASK> with a syzlang reproducer that looks like: syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async) r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0) r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0) r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0) r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0) ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async) ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async) r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0) openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async) ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2) close(r0) (async) openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async) ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0) Opportunistically use guard() to avoid having to define a new error label and goto usage.
CVE-2026-31593: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host. BUG: unable to handle page fault for address: ff1276cbfdf36000 #PF: supervisor write access in kernel mode #PF: error_code(0x80000003) - RMP violation PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163 SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f] Oops: Oops: 0003 [#1] SMP NOPTI CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G OE Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023 RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd] Call Trace: <TASK> snp_launch_update_vmsa+0x19d/0x290 [kvm_amd] snp_launch_finish+0xb6/0x380 [kvm_amd] sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd] kvm_arch_vm_ioctl+0x837/0xcf0 [kvm] kvm_vm_ioctl+0x3fd/0xcc0 [kvm] __x64_sys_ioctl+0xa3/0x100 x64_sys_call+0xfe0/0x2350 do_syscall_64+0x81/0x10f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7ffff673287d </TASK> Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().
CVE-2026-31594: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case: Unable to handle kernel paging request at virtual address dead000000000108 [...] [dead000000000108] address between user and kernel address ranges Internal error: Oops: 0000000096000044 [#1] SMP [...] Call trace: pci_epc_remove_epf+0x78/0xe0 (P) pci_primary_epc_epf_link+0x88/0xa8 configfs_symlink+0x1f4/0x5a0 vfs_symlink+0x134/0x1d8 do_symlinkat+0x88/0x138 __arm64_sys_symlinkat+0x74/0xe0 [...] Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.
CVE-2026-31595: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down. Unable to handle kernel paging request at virtual address ffff800083f46004 [...] Internal error: Oops: 0000000096000007 [#1] SMP [...] Call trace: epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P) process_one_work+0x154/0x3b0 worker_thread+0x2c8/0x400 kthread+0x148/0x210 ret_from_fork+0x10/0x20
CVE-2026-31596: In the Linux kernel, the following vulnerability has been resolved: ocfs2: handle invalid dinode in ocfs2_group_extend [BUG] kernel BUG at fs/ocfs2/resize.c:308! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308 Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe Call Trace: ... ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... [CAUSE] ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl. [FIX] Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.
CVE-2026-31597: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.
CVE-2026-31598: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix possible deadlock between unlink and dio_end_io_write ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key. Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem): ocfs2_unlink ocfs2_prepare_orphan_dir ocfs2_lookup_lock_orphan_dir inode_lock(orphan_dir_inode) <- lock A __ocfs2_prepare_orphan_dir ocfs2_prepare_dir_for_insert ocfs2_extend_dir ocfs2_expand_inline_dir down_write(&oi->ip_alloc_sem) <- Lock B Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock): ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan() inode_lock(orphan_dir_inode) <- Lock A Deadlock Scenario: CPU0 (unlink) CPU1 (dio_end_io_write) ------ ------ inode_lock(orphan_dir_inode) down_write(ip_alloc_sem) down_write(ip_alloc_sem) inode_lock(orphan_dir_inode) Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.
CVE-2026-31599: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections syzbot reported a general protection fault in vidtv_psi_desc_assign [1]. vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault. Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629 Call Trace: <TASK> vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline] vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31600: In the Linux kernel, the following vulnerability has been resolved: arm64: mm: Handle invalid large leaf mappings correctly It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way. It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result: [ 15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers [ 15.476896] Unable to handle kernel paging request at virtual address ffff000019600000 [ 15.513762] Mem abort info: [ 15.527245] ESR = 0x0000000096000046 [ 15.548553] EC = 0x25: DABT (current EL), IL = 32 bits [ 15.572146] SET = 0, FnV = 0 [ 15.592141] EA = 0, S1PTW = 0 [ 15.612694] FSC = 0x06: level 2 translation fault [ 15.640644] Data abort info: [ 15.661983] ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000 [ 15.694875] CM = 0, WnR = 1, TnD = 0, TagAccess = 0 [ 15.723740] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000 [ 15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704 [ 15.855046] Internal error: Oops: 0000000096000046 [#1] SMP [ 15.886394] Modules linked in: [ 15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT [ 15.935258] Hardware name: linux,dummy-virt (DT) [ 15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 15.986009] pc : __pi_memcpy_generic+0x128/0x22c [ 16.006163] lr : swiotlb_bounce+0xf4/0x158 [ 16.024145] sp : ffff80008000b8f0 [ 16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000 [ 16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000 [ 16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0 [ 16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc [ 16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974 [ 16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018 [ 16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000 [ 16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000 [ 16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000 [ 16.349071] Call trace: [ 16.360143] __pi_memcpy_generic+0x128/0x22c (P) [ 16.380310] swiotlb_tbl_map_single+0x154/0x2b4 [ 16.400282] swiotlb_map+0x5c/0x228 [ 16.415984] dma_map_phys+0x244/0x2b8 [ 16.432199] dma_map_page_attrs+0x44/0x58 [ 16.449782] virtqueue_map_page_attrs+0x38/0x44 [ 16.469596] virtqueue_map_single_attrs+0xc0/0x130 [ 16.490509] virtnet_rq_alloc.isra.0+0xa4/0x1fc [ 16.510355] try_fill_recv+0x2a4/0x584 [ 16.526989] virtnet_open+0xd4/0x238 [ 16.542775] __dev_open+0x110/0x24c [ 16.558280] __dev_change_flags+0x194/0x20c [ 16.576879] netif_change_flags+0x24/0x6c [ 16.594489] dev_change_flags+0x48/0x7c [ 16.611462] ip_auto_config+0x258/0x1114 [ 16.628727] do_one_initcall+0x80/0x1c8 [ 16.645590] kernel_init_freeable+0x208/0x2f0 [ 16.664917] kernel_init+0x24/0x1e0 [ 16.680295] ret_from_fork+0x10/0x20 [ 16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c) [ 16.723106] ---[ end trace 0000000000000000 ]--- [ 16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 16.792556] Kernel Offset: 0x3396ea200000 from 0xffff8000800000 ---truncated---
CVE-2026-31601: In the Linux kernel, the following vulnerability has been resolved: vfio/xe: Reorganize the init to decouple migration from reset Attempting to issue reset on VF devices that don't support migration leads to the following: BUG: unable to handle page fault for address: 00000000000011f8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 7443 Comm: xe_sriov_flr Tainted: G S U 7.0.0-rc1-lgci-xe-xe-4588-cec43d5c2696af219-nodebug+ #1 PREEMPT(lazy) Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR4 RVP, BIOS RPLPFWI1.R00.4035.A00.2301200723 01/20/2023 RIP: 0010:xe_sriov_vfio_wait_flr_done+0xc/0x80 [xe] Code: ff c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 54 53 <83> bf f8 11 00 00 02 75 61 41 89 f4 85 f6 74 52 48 8b 47 08 48 89 RSP: 0018:ffffc9000f7c39b8 EFLAGS: 00010202 RAX: ffffffffa04d8660 RBX: ffff88813e3e4000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc9000f7c39c8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888101a48800 R13: ffff88813e3e4150 R14: ffff888130d0d008 R15: ffff88813e3e40d0 FS: 00007877d3d0d940(0000) GS:ffff88890b6d3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000011f8 CR3: 000000015a762000 CR4: 0000000000f52ef0 PKRU: 55555554 Call Trace: <TASK> xe_vfio_pci_reset_done+0x49/0x120 [xe_vfio_pci] pci_dev_restore+0x3b/0x80 pci_reset_function+0x109/0x140 reset_store+0x5c/0xb0 dev_attr_store+0x17/0x40 sysfs_kf_write+0x72/0x90 kernfs_fop_write_iter+0x161/0x1f0 vfs_write+0x261/0x440 ksys_write+0x69/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x259/0x26e0 do_syscall_64+0xcb/0x1500 ? __fput+0x1a2/0x2d0 ? fput_close_sync+0x3d/0xa0 ? __x64_sys_close+0x3e/0x90 ? x64_sys_call+0x1b7c/0x26e0 ? do_syscall_64+0x109/0x1500 ? __task_pid_nr_ns+0x68/0x100 ? __do_sys_getpid+0x1d/0x30 ? x64_sys_call+0x10b5/0x26e0 ? do_syscall_64+0x109/0x1500 ? putname+0x41/0x90 ? do_faccessat+0x1e8/0x300 ? __x64_sys_access+0x1c/0x30 ? x64_sys_call+0x1822/0x26e0 ? do_syscall_64+0x109/0x1500 ? tick_program_event+0x43/0xa0 ? hrtimer_interrupt+0x126/0x260 ? irqentry_exit+0xb2/0x710 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7877d5f1c5a4 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fff48e5f908 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007877d5f1c5a4 RDX: 0000000000000001 RSI: 00007877d621b0c9 RDI: 0000000000000009 RBP: 0000000000000001 R08: 00005fb49113b010 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000202 R12: 00007877d621b0c9 R13: 0000000000000009 R14: 00007fff48e5fac0 R15: 00007fff48e5fac0 </TASK> This is caused by the fact that some of the xe_vfio_pci_core_device members needed for handling reset are only initialized as part of migration init. Fix the problem by reorganizing the code to decouple VF init from migration init.
CVE-2026-31602: In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Limit PTP to a single page Commit 391e69143d0a increased CT_PTP_NUM from 1 to 4 to support 256 playback streams, but the additional pages are not used by the card correctly. The CT20K2 hardware already has multiple VMEM_PTPAL registers, but using them separately would require refactoring the entire virtual memory allocation logic. ct_vm_map() always uses PTEs in vm->ptp[0].area regardless of CT_PTP_NUM. On AMD64 systems, a single PTP covers 512 PTEs (2M). When aggregate memory allocations exceed this limit, ct_vm_map() tries to access beyond the allocated space and causes a page fault: BUG: unable to handle page fault for address: ffffd4ae8a10a000 Oops: Oops: 0002 [#1] SMP PTI RIP: 0010:ct_vm_map+0x17c/0x280 [snd_ctxfi] Call Trace: atc_pcm_playback_prepare+0x225/0x3b0 ct_pcm_playback_prepare+0x38/0x60 snd_pcm_do_prepare+0x2f/0x50 snd_pcm_action_single+0x36/0x90 snd_pcm_action_nonatomic+0xbf/0xd0 snd_pcm_ioctl+0x28/0x40 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x81/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Revert CT_PTP_NUM to 1. The 256 SRC_RESOURCE_NUM and playback_count remain unchanged.
CVE-2026-31603: In the Linux kernel, the following vulnerability has been resolved: staging: sm750fb: fix division by zero in ps_to_hz() ps_to_hz() is called from hw_sm750_crtc_set_mode() without validating that pixclock is non-zero. A zero pixclock passed via FBIOPUT_VSCREENINFO causes a division by zero. Fix by rejecting zero pixclock in lynxfb_ops_check_var(), consistent with other framebuffer drivers.
CVE-2026-31604: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on all probe errors (e.g. when descriptor parsing fails). Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks.
CVE-2026-31605: In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31606: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: don't call cdev_init while cdev in use When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes. This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.
CVE-2026-31607: In the Linux kernel, the following vulnerability has been resolved: usbip: validate number_of_packets in usbip_pack_ret_submit() When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the *original* number_of_packets from the CMD_SUBMIT. A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region. KASAN confirmed this with kernel 7.0.0-rc5: BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640 Write of size 4 at addr ffff888106351d40 by task vhci_rx/69 The buggy address is located 0 bytes to the right of allocated 320-byte region [ffff888106351c00, ffff888106351d40) The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter bound: the response must not exceed the original number_of_packets. This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size. Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit. Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.
CVE-2026-31608: In the Linux kernel, the following vulnerability has been resolved: smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list() smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg() moved it to the batch list.
CVE-2026-31609: In the Linux kernel, the following vulnerability has been resolved: smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush() smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.
CVE-2026-31610: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix mechToken leak when SPNEGO decode fails after token alloc The kernel ASN.1 BER decoder calls action callbacks incrementally as it walks the input. When ksmbd_decode_negTokenInit() reaches the mechToken [2] OCTET STRING element, ksmbd_neg_token_alloc() allocates conn->mechToken immediately via kmemdup_nul(). If a later element in the same blob is malformed, then the decoder will return nonzero after the allocation is already live. This could happen if mechListMIC [3] overrunse the enclosing SEQUENCE. decode_negotiation_token() then sets conn->use_spnego = false because both the negTokenInit and negTokenTarg grammars failed. The cleanup at the bottom of smb2_sess_setup() is gated on use_spnego: if (conn->use_spnego && conn->mechToken) { kfree(conn->mechToken); conn->mechToken = NULL; } so the kfree is skipped, causing the mechToken to never be freed. This codepath is reachable pre-authentication, so untrusted clients can cause slow memory leaks on a server without even being properly authenticated. Fix this up by not checking check for use_spnego, as it's not required, so the memory will always be properly freed. At the same time, always free the memory in ksmbd_conn_free() incase some other failure path forgot to free it.
CVE-2026-31611: In the Linux kernel, the following vulnerability has been resolved: ksmbd: require 3 sub-authorities before reading sub_auth[2] parse_dacl() compares each ACE SID against sid_unix_NFS_mode and on match reads sid.sub_auth[2] as the file mode. If sid_unix_NFS_mode is the prefix S-1-5-88-3 with num_subauth = 2 then compare_sids() compares only min(num_subauth, 2) sub-authorities so a client SID with num_subauth = 2 and sub_auth = {88, 3} will match. If num_subauth = 2 and the ACE is placed at the very end of the security descriptor, sub_auth[2] will be 4 bytes past end_of_acl. The out-of-band bytes will then be masked to the low 9 bits and applied as the file's POSIX mode, probably not something that is good to have happen. Fix this up by forcing the SID to actually carry a third sub-authority before reading it at all.
CVE-2026-31612: In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate EaNameLength in smb2_get_ea() smb2_get_ea() reads ea_req->EaNameLength from the client request and passes it directly to strncmp() as the comparison length without verifying that the length of the name really is the size of the input buffer received. Fix this up by properly checking the size of the name based on the value received and the overall size of the request, to prevent a later strncmp() call to use the length as a "trusted" size of the buffer. Without this check, uninitialized heap values might be slowly leaked to the client.
CVE-2026-31613: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB reads parsing symlink error response When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server. symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset 0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits. smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0. With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2). Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset. Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than.
CVE-2026-31614: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix off-by-8 bounds check in check_wsl_eas() The bounds check uses (u8 *)ea + nlen + 1 + vlen as the end of the EA name and value, but ea_data sits at offset sizeof(struct smb2_file_full_ea_info) = 8 from ea, not at offset 0. The strncmp() later reads ea->ea_data[0..nlen-1] and the value bytes follow at ea_data[nlen+1..nlen+vlen], so the actual end is ea->ea_data + nlen + 1 + vlen. Isn't pointer math fun? The earlier check (u8 *)ea > end - sizeof(*ea) only guarantees the 8-byte header is in bounds, but since the last EA is placed within 8 bytes of the end of the response, the name and value bytes are read past the end of iov. Fix this mess all up by using ea->ea_data as the base for the bounds check. An "untrusted" server can use this to leak up to 8 bytes of kernel heap into the EA name comparison and influence which WSL xattr the data is interpreted as.
CVE-2026-31615: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: renesas_usb3: validate endpoint index in standard request handlers The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math. This is just like what was done in commit ee0d382feb44 ("usb: gadget: aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.
CVE-2026-31616: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete() A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers. pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap. Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path").
CVE-2026-31617: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb() The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of: ndp_index > (block_len - opts->ndp_size) will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely. The same underflow occurs in the datagram index checks against block_len - opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb. Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined. Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.
CVE-2026-31618: In the Linux kernel, the following vulnerability has been resolved: fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31619: In the Linux kernel, the following vulnerability has been resolved: ALSA: fireworks: bound device-supplied status before string array lookup The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value. Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings. Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.
CVE-2026-31620: In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0 A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly. Fix this up by checking the return value properly.
CVE-2026-31621: In the Linux kernel, the following vulnerability has been resolved: bnge: return after auxiliary_device_uninit() in error path When auxiliary_device_add() fails, the error block calls auxiliary_device_uninit() but does not return. The uninit drops the last reference and synchronously runs bnge_aux_dev_release(), which sets bd->auxr_dev = NULL and frees the underlying object. The subsequent bd->auxr_dev->net = bd->netdev then dereferences NULL, which is not a good thing to have happen when trying to clean up from an error. Add the missing return, as the auxiliary bus documentation states is a requirement (seems that LLM tools read documentation better than humans do...)
CVE-2026-31622: In the Linux kernel, the following vulnerability has been resolved: NFC: digital: Bounds check NFC-A cascade depth in SDD response handler The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows). ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round. Fix this by rejecting the response when the accumulated UID would exceed the buffer. Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.
CVE-2026-31623: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers. Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.
CVE-2026-31624: In the Linux kernel, the following vulnerability has been resolved: HID: core: clamp report_size in s32ton() to avoid undefined shift s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field(). Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way. Fix this up by just clamping the max value of n, just like snto32() does.
CVE-2026-31625: In the Linux kernel, the following vulnerability has been resolved: HID: alps: fix NULL pointer dereference in alps_raw_event() Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), but the alps driver was missed. Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.
CVE-2026-31626: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify() Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data. Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized: drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify() warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes) Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.
CVE-2026-31627: In the Linux kernel, the following vulnerability has been resolved: i2c: s3c24xx: check the size of the SMBUS message before using it The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it. This is the same logic that was added in commit a6e04f05ce0b ("i2c: tegra: check msg length in SMBUS block read") to the i2c tegra driver.
CVE-2026-31629: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: add missing return after LLCP_CLOSED checks In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free. Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.
CVE-2026-31673: In the Linux kernel, the following vulnerability has been resolved: af_unix: read UNIX_DIAG_VFS data under unix_state_lock Exact UNIX diag lookups hold a reference to the socket, but not to u->path. Meanwhile, unix_release_sock() clears u->path under unix_state_lock() and drops the path reference after unlocking. Read the inode and device numbers for UNIX_DIAG_VFS while holding unix_state_lock(), then emit the netlink attribute after dropping the lock. This keeps the VFS data stable while the reply is being built.
CVE-2026-31677: In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - limit RX SG extraction by receive buffer budget Make af_alg_get_rsgl() limit each RX scatterlist extraction to the remaining receive buffer budget. af_alg_get_rsgl() currently uses af_alg_readable() only as a gate before extracting data into the RX scatterlist. Limit each extraction to the remaining af_alg_rcvbuf(sk) budget so that receive-side accounting matches the amount of data attached to the request. If skcipher cannot obtain enough RX space for at least one chunk while more data remains to be processed, reject the recvmsg call instead of rounding the request length down to zero.
CVE-2026-31681: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_multiport: validate range encoding in checkentry ports_match_v1() treats any non-zero pflags entry as the start of a port range and unconditionally consumes the next ports[] element as the range end. The checkentry path currently validates protocol, flags and count, but it does not validate the range encoding itself. As a result, malformed rules can mark the last slot as a range start or place two range starts back to back, leaving ports_match_v1() to step past the last valid ports[] element while interpreting the rule. Reject malformed multiport v1 rules in checkentry by validating that each range start has a following element and that the following element is not itself marked as another range start.
CVE-2026-31684: In the Linux kernel, the following vulnerability has been resolved: net: sched: act_csum: validate nested VLAN headers tcf_csum_act() walks nested VLAN headers directly from skb->data when an skb still carries in-payload VLAN tags. The current code reads vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without first ensuring that the full VLAN header is present in the linear area. If only part of an inner VLAN header is linearized, accessing h_vlan_encapsulated_proto reads past the linear area, and the following skb_pull(VLAN_HLEN) may violate skb invariants. Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and pulling each nested VLAN header. If the header still is not fully available, drop the packet through the existing error path.
CVE-2026-31685: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_eui64: reject invalid MAC header for all packets `eui64_mt6()` derives a modified EUI-64 from the Ethernet source address and compares it with the low 64 bits of the IPv6 source address. The existing guard only rejects an invalid MAC header when `par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()` can still reach `eth_hdr(skb)` even when the MAC header is not valid. Fix this by removing the `par->fragoff != 0` condition so that packets with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.

Created: 2025-08-09 Last update: 2026-04-26 05:02

1594 security issues in bullseye high

There are 1594 open security issues in bullseye.

1545 important issues:

CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2021-4023: A flaw was found in the io-workqueue implementation in the Linux kernel versions prior to 5.15-rc1. The kernel can panic when an improper cancellation operation triggers the submission of new io-uring operations during a shortage of free space. This flaw allows a local user with permissions to execute io-uring requests to possibly crash the system.
CVE-2021-4149: A vulnerability was found in btrfs_alloc_tree_b in fs/btrfs/extent-tree.c in the Linux kernel due to an improper lock operation in btrfs. In this flaw, a user with a local privilege may cause a denial of service (DOS) due to a deadlock problem.
CVE-2021-4204: An out-of-bounds (OOB) memory access flaw was found in the Linux kernel's eBPF due to an Improper Input Validation. This flaw allows a local attacker with a special privilege to crash the system or leak internal information.
CVE-2022-0500: A flaw was found in unrestricted eBPF usage by the BPF_BTF_LOAD, leading to a possible out-of-bounds memory write in the Linux kernel’s BPF subsystem due to the way a user loads BTF. This flaw allows a local user to crash or escalate their privileges on the system.
CVE-2022-1280: A use-after-free vulnerability was found in drm_lease_held in drivers/gpu/drm/drm_lease.c in the Linux kernel due to a race problem. This flaw allows a local user privilege attacker to cause a denial of service (DoS) or a kernel information leak.
CVE-2022-3108: An issue was discovered in the Linux kernel through 5.16-rc6. kfd_parse_subtype_iolink in drivers/gpu/drm/amd/amdkfd/kfd_crat.c lacks check of the return value of kmemdup().
CVE-2022-3114: An issue was discovered in the Linux kernel through 5.16-rc6. imx_register_uart_clocks in drivers/clk/imx/clk.c lacks check of the return value of kcalloc() and will cause the null pointer dereference.
CVE-2022-3344: A flaw was found in the KVM's AMD nested virtualization (SVM). A malicious L1 guest could purposely fail to intercept the shutdown of a cooperative nested guest (L2), possibly leading to a page fault and kernel panic in the host (L0).
CVE-2022-3523: A vulnerability was found in Linux Kernel. It has been classified as problematic. Affected is an unknown function of the file mm/memory.c of the component Driver Handler. The manipulation leads to use after free. It is possible to launch the attack remotely. It is recommended to apply a patch to fix this issue. The identifier of this vulnerability is VDB-211020.
CVE-2022-3566: A vulnerability, which was classified as problematic, was found in Linux Kernel. This affects the function tcp_getsockopt/tcp_setsockopt of the component TCP Handler. The manipulation leads to race condition. It is recommended to apply a patch to fix this issue. The identifier VDB-211089 was assigned to this vulnerability.
CVE-2022-3567: A vulnerability has been found in Linux Kernel and classified as problematic. This vulnerability affects the function inet6_stream_ops/inet6_dgram_ops of the component IPv6 Handler. The manipulation leads to race condition. It is recommended to apply a patch to fix this issue. VDB-211090 is the identifier assigned to this vulnerability.
CVE-2023-0597: A flaw possibility of memory leak in the Linux kernel cpu_entry_area mapping of X86 CPU data to memory was found in the way user can guess location of exception stack(s) or other important data. A local user could use this flaw to get access to some important data with expected location in memory.
CVE-2023-1075: A flaw was found in the Linux Kernel. The tls_is_tx_ready() incorrectly checks for list emptiness, potentially accessing a type confused entry to the list_head, leaking the last byte of the confused field that overlaps with rec->tx_ready.
CVE-2023-1192: A use-after-free flaw was found in smb2_is_status_io_timeout() in CIFS in the Linux Kernel. After CIFS transfers response data to a system call, there are still local variable points to the memory region, and if the system call frees it faster than CIFS uses it, CIFS will access a free memory region, leading to a denial of service.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-4133: A use-after-free vulnerability was found in the cxgb4 driver in the Linux kernel. The bug occurs when the cxgb4 device is detaching due to a possible rearming of the flower_stats_timer from the work queue. This flaw allows a local user to crash the system, causing a denial of service condition.
CVE-2023-4569: A memory leak flaw was found in nft_set_catchall_flush in net/netfilter/nf_tables_api.c in the Linux Kernel. This issue may allow a local attacker to cause double-deactivations of catchall elements, which can result in a memory leak.
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2024-2201: A cross-privilege Spectre v2 vulnerability allows attackers to bypass all deployed mitigations, including the recent Fine(IBT), and to leak arbitrary Linux kernel memory on Intel systems.
CVE-2024-8805: BlueZ HID over GATT Profile Improper Access Control Remote Code Execution Vulnerability. This vulnerability allows network-adjacent attackers to execute arbitrary code on affected installations of BlueZ. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the HID over GATT Profile. The issue results from the lack of authorization prior to allowing access to functionality. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-25177.
CVE-2019-15794: Overlayfs in the Linux kernel and shiftfs, a non-upstream patch to the Linux kernel included in the Ubuntu 5.0 and 5.3 kernel series, both replace vma->vm_file in their mmap handlers. On error the original value is not restored, and the reference is put for the file to which vm_file points. On upstream kernels this is not an issue, as no callers dereference vm_file following after call_mmap() returns an error. However, the aufs patchs change mmap_region() to replace the fput() using a local variable with vma_fput(), which will fput() vm_file, leading to a refcount underflow.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2021-33061: Insufficient control flow management for the Intel(R) 82599 Ethernet Controllers and Adapters may allow an authenticated user to potentially enable denial of service via local access.
CVE-2021-39686: In several functions of binder.c, there is a possible way to represent the wrong domain to SELinux due to a race condition. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android kernelAndroid ID: A-200688826References: Upstream kernel
CVE-2021-46926: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: intel-sdw-acpi: harden detection of controller The existing code currently sets a pointer to an ACPI handle before checking that it's actually a SoundWire controller. This can lead to issues where the graph walk continues and eventually fails, but the pointer was set already. This patch changes the logic so that the information provided to the caller is set when a controller is found.
CVE-2021-46937: In the Linux kernel, the following vulnerability has been resolved: mm/damon/dbgfs: fix 'struct pid' leaks in 'dbgfs_target_ids_write()' DAMON debugfs interface increases the reference counts of 'struct pid's for targets from the 'target_ids' file write callback ('dbgfs_target_ids_write()'), but decreases the counts only in DAMON monitoring termination callback ('dbgfs_before_terminate()'). Therefore, when 'target_ids' file is repeatedly written without DAMON monitoring start/termination, the reference count is not decreased and therefore memory for the 'struct pid' cannot be freed. This commit fixes this issue by decreasing the reference counts when 'target_ids' is written.
CVE-2021-47014: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ct: fix wild memory access when clearing fragments while testing re-assembly/re-fragmentation using act_ct, it's possible to observe a crash like the following one: KASAN: maybe wild-memory-access in range [0x0001000000000448-0x000100000000044f] CPU: 50 PID: 0 Comm: swapper/50 Tainted: G S 5.12.0-rc7+ #424 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 RIP: 0010:inet_frag_rbtree_purge+0x50/0xc0 Code: 00 fc ff df 48 89 c3 31 ed 48 89 df e8 a9 7a 38 ff 4c 89 fe 48 89 df 49 89 c6 e8 5b 3a 38 ff 48 8d 7b 40 48 89 f8 48 c1 e8 03 <42> 80 3c 20 00 75 59 48 8d bb d0 00 00 00 4c 8b 6b 40 48 89 f8 48 RSP: 0018:ffff888c31449db8 EFLAGS: 00010203 RAX: 0000200000000089 RBX: 000100000000040e RCX: ffffffff989eb960 RDX: 0000000000000140 RSI: ffffffff97cfb977 RDI: 000100000000044e RBP: 0000000000000900 R08: 0000000000000000 R09: ffffed1186289350 R10: 0000000000000003 R11: ffffed1186289350 R12: dffffc0000000000 R13: 000100000000040e R14: 0000000000000000 R15: ffff888155e02160 FS: 0000000000000000(0000) GS:ffff888c31440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005600cb70a5b8 CR3: 0000000a2c014005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_frag_destroy+0xa9/0x150 call_timer_fn+0x2d/0x180 run_timer_softirq+0x4fe/0xe70 __do_softirq+0x197/0x5a0 irq_exit_rcu+0x1de/0x200 sysvec_apic_timer_interrupt+0x6b/0x80 </IRQ> when act_ct temporarily stores an IP fragment, restoring the skb qdisc cb results in putting random data in FRAG_CB(), and this causes those "wild" memory accesses later, when the rbtree is purged. Never overwrite the skb cb in case tcf_ct_handle_fragments() returns -EINPROGRESS.
CVE-2021-47028: In the Linux kernel, the following vulnerability has been resolved: mt76: mt7915: fix txrate reporting Properly check rate_info to fix unexpected reporting. [ 1215.161863] Call trace: [ 1215.164307] cfg80211_calculate_bitrate+0x124/0x200 [cfg80211] [ 1215.170139] ieee80211s_update_metric+0x80/0xc0 [mac80211] [ 1215.175624] ieee80211_tx_status_ext+0x508/0x838 [mac80211] [ 1215.181190] mt7915_mcu_get_rx_rate+0x28c/0x8d0 [mt7915e] [ 1215.186580] mt7915_mac_tx_free+0x324/0x7c0 [mt7915e] [ 1215.191623] mt7915_queue_rx_skb+0xa8/0xd0 [mt7915e] [ 1215.196582] mt76_dma_cleanup+0x7b0/0x11d0 [mt76] [ 1215.201276] __napi_poll+0x38/0xf8 [ 1215.204668] napi_workfn+0x40/0x80 [ 1215.208062] process_one_work+0x1fc/0x390 [ 1215.212062] worker_thread+0x48/0x4d0 [ 1215.215715] kthread+0x120/0x128 [ 1215.218935] ret_from_fork+0x10/0x1c
CVE-2021-47036: In the Linux kernel, the following vulnerability has been resolved: udp: skip L4 aggregation for UDP tunnel packets If NETIF_F_GRO_FRAGLIST or NETIF_F_GRO_UDP_FWD are enabled, and there are UDP tunnels available in the system, udp_gro_receive() could end-up doing L4 aggregation (either SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST) at the outer UDP tunnel level for packets effectively carrying and UDP tunnel header. That could cause inner protocol corruption. If e.g. the relevant packets carry a vxlan header, different vxlan ids will be ignored/ aggregated to the same GSO packet. Inner headers will be ignored, too, so that e.g. TCP over vxlan push packets will be held in the GRO engine till the next flush, etc. Just skip the SKB_GSO_UDP_L4 and SKB_GSO_FRAGLIST code path if the current packet could land in a UDP tunnel, and let udp_gro_receive() do GRO via udp_sk(sk)->gro_receive. The check implemented in this patch is broader than what is strictly needed, as the existing UDP tunnel could be e.g. configured on top of a different device: we could end-up skipping GRO at-all for some packets. Anyhow, that is a very thin corner case and covering it will add quite a bit of complexity. v1 -> v2: - hopefully clarify the commit message
CVE-2021-47094: In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Don't advance iterator after restart due to yielding After dropping mmu_lock in the TDP MMU, restart the iterator during tdp_iter_next() and do not advance the iterator. Advancing the iterator results in skipping the top-level SPTE and all its children, which is fatal if any of the skipped SPTEs were not visited before yielding. When zapping all SPTEs, i.e. when min_level == root_level, restarting the iter and then invoking tdp_iter_next() is always fatal if the current gfn has as a valid SPTE, as advancing the iterator results in try_step_side() skipping the current gfn, which wasn't visited before yielding. Sprinkle WARNs on iter->yielded being true in various helpers that are often used in conjunction with yielding, and tag the helper with __must_check to reduce the probabily of improper usage. Failing to zap a top-level SPTE manifests in one of two ways. If a valid SPTE is skipped by both kvm_tdp_mmu_zap_all() and kvm_tdp_mmu_put_root(), the shadow page will be leaked and KVM will WARN accordingly. WARNING: CPU: 1 PID: 3509 at arch/x86/kvm/mmu/tdp_mmu.c:46 [kvm] RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x3e/0x50 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2a0 [kvm] kvm_vcpu_release+0x34/0x60 [kvm] __fput+0x82/0x240 task_work_run+0x5c/0x90 do_exit+0x364/0xa10 ? futex_unqueue+0x38/0x60 do_group_exit+0x33/0xa0 get_signal+0x155/0x850 arch_do_signal_or_restart+0xed/0x750 exit_to_user_mode_prepare+0xc5/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x48/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae If kvm_tdp_mmu_zap_all() skips a gfn/SPTE but that SPTE is then zapped by kvm_tdp_mmu_put_root(), KVM triggers a use-after-free in the form of marking a struct page as dirty/accessed after it has been put back on the free list. This directly triggers a WARN due to encountering a page with page_count() == 0, but it can also lead to data corruption and additional errors in the kernel. WARNING: CPU: 7 PID: 1995658 at arch/x86/kvm/../../../virt/kvm/kvm_main.c:171 RIP: 0010:kvm_is_zone_device_pfn.part.0+0x9e/0xd0 [kvm] Call Trace: <TASK> kvm_set_pfn_dirty+0x120/0x1d0 [kvm] __handle_changed_spte+0x92e/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] __handle_changed_spte+0x63c/0xca0 [kvm] zap_gfn_range+0x549/0x620 [kvm] kvm_tdp_mmu_put_root+0x1b6/0x270 [kvm] mmu_free_root_page+0x219/0x2c0 [kvm] kvm_mmu_free_roots+0x1b4/0x4e0 [kvm] kvm_mmu_unload+0x1c/0xa0 [kvm] kvm_arch_destroy_vm+0x1f2/0x5c0 [kvm] kvm_put_kvm+0x3b1/0x8b0 [kvm] kvm_vcpu_release+0x4e/0x70 [kvm] __fput+0x1f7/0x8c0 task_work_run+0xf8/0x1a0 do_exit+0x97b/0x2230 do_group_exit+0xda/0x2a0 get_signal+0x3be/0x1e50 arch_do_signal_or_restart+0x244/0x17f0 exit_to_user_mode_prepare+0xcb/0x120 syscall_exit_to_user_mode+0x1d/0x40 do_syscall_64+0x4d/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae Note, the underlying bug existed even before commit 1af4a96025b3 ("KVM: x86/mmu: Yield in TDU MMU iter even if no SPTES changed") moved calls to tdp_mmu_iter_cond_resched() to the beginning of loops, as KVM could still incorrectly advance past a top-level entry when yielding on a lower-level entry. But with respect to leaking shadow pages, the bug was introduced by yielding before processing the current gfn. Alternatively, tdp_mmu_iter_cond_resched() could simply fall through, or callers could jump to their "retry" label. The downside of that approach is that tdp_mmu_iter_cond_resched() _must_ be called before anything else in the loop, and there's no easy way to enfornce that requirement. Ideally, KVM would handling the cond_resched() fully within the iterator macro (the code is actually quite clean) and avoid this entire class of bugs, but that is extremely difficult do wh ---truncated---
CVE-2021-47101: In the Linux kernel, the following vulnerability has been resolved: asix: fix uninit-value in asix_mdio_read() asix_read_cmd() may read less than sizeof(smsr) bytes and in this case smsr will be uninitialized. Fail log: BUG: KMSAN: uninit-value in asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] BUG: KMSAN: uninit-value in asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] drivers/net/usb/asix_common.c:497 BUG: KMSAN: uninit-value in asix_mdio_read+0x3c1/0xb00 drivers/net/usb/asix_common.c:497 drivers/net/usb/asix_common.c:497 asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] drivers/net/usb/asix_common.c:497 asix_mdio_read+0x3c1/0xb00 drivers/net/usb/asix_common.c:497 drivers/net/usb/asix_common.c:497
CVE-2021-47105: In the Linux kernel, the following vulnerability has been resolved: ice: xsk: return xsk buffers back to pool when cleaning the ring Currently we only NULL the xdp_buff pointer in the internal SW ring but we never give it back to the xsk buffer pool. This means that buffers can be leaked out of the buff pool and never be used again. Add missing xsk_buff_free() call to the routine that is supposed to clean the entries that are left in the ring so that these buffers in the umem can be used by other sockets. Also, only go through the space that is actually left to be cleaned instead of a whole ring.
CVE-2021-47182: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix scsi_mode_sense() buffer length handling Several problems exist with scsi_mode_sense() buffer length handling: 1) The allocation length field of the MODE SENSE(10) command is 16-bits, occupying bytes 7 and 8 of the CDB. With this command, access to mode pages larger than 255 bytes is thus possible. However, the CDB allocation length field is set by assigning len to byte 8 only, thus truncating buffer length larger than 255. 2) If scsi_mode_sense() is called with len smaller than 8 with sdev->use_10_for_ms set, or smaller than 4 otherwise, the buffer length is increased to 8 and 4 respectively, and the buffer is zero filled with these increased values, thus corrupting the memory following the buffer. Fix these 2 problems by using put_unaligned_be16() to set the allocation length field of MODE SENSE(10) CDB and by returning an error when len is too small. Furthermore, if len is larger than 255B, always try MODE SENSE(10) first, even if the device driver did not set sdev->use_10_for_ms. In case of invalid opcode error for MODE SENSE(10), access to mode pages larger than 255 bytes are not retried using MODE SENSE(6). To avoid buffer length overflows for the MODE_SENSE(10) case, check that len is smaller than 65535 bytes. While at it, also fix the folowing: * Use get_unaligned_be16() to retrieve the mode data length and block descriptor length fields of the mode sense reply header instead of using an open coded calculation. * Fix the kdoc dbd argument explanation: the DBD bit stands for Disable Block Descriptor, which is the opposite of what the dbd argument description was.
CVE-2021-47188: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Improve SCSI abort handling The following has been observed on a test setup: WARNING: CPU: 4 PID: 250 at drivers/scsi/ufs/ufshcd.c:2737 ufshcd_queuecommand+0x468/0x65c Call trace: ufshcd_queuecommand+0x468/0x65c scsi_send_eh_cmnd+0x224/0x6a0 scsi_eh_test_devices+0x248/0x418 scsi_eh_ready_devs+0xc34/0xe58 scsi_error_handler+0x204/0x80c kthread+0x150/0x1b4 ret_from_fork+0x10/0x30 That warning is triggered by the following statement: WARN_ON(lrbp->cmd); Fix this warning by clearing lrbp->cmd from the abort handler.
CVE-2021-47199: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: CT, Fix multiple allocations and memleak of mod acts CT clear action offload adds additional mod hdr actions to the flow's original mod actions in order to clear the registers which hold ct_state. When such flow also includes encap action, a neigh update event can cause the driver to unoffload the flow and then reoffload it. Each time this happens, the ct clear handling adds that same set of mod hdr actions to reset ct_state until the max of mod hdr actions is reached. Also the driver never releases the allocated mod hdr actions and causing a memleak. Fix above two issues by moving CT clear mod acts allocation into the parsing actions phase and only use it when offloading the rule. The release of mod acts will be done in the normal flow_put(). backtrace: [<000000007316e2f3>] krealloc+0x83/0xd0 [<00000000ef157de1>] mlx5e_mod_hdr_alloc+0x147/0x300 [mlx5_core] [<00000000970ce4ae>] mlx5e_tc_match_to_reg_set_and_get_id+0xd7/0x240 [mlx5_core] [<0000000067c5fa17>] mlx5e_tc_match_to_reg_set+0xa/0x20 [mlx5_core] [<00000000d032eb98>] mlx5_tc_ct_entry_set_registers.isra.0+0x36/0xc0 [mlx5_core] [<00000000fd23b869>] mlx5_tc_ct_flow_offload+0x272/0x1f10 [mlx5_core] [<000000004fc24acc>] mlx5e_tc_offload_fdb_rules.part.0+0x150/0x620 [mlx5_core] [<00000000dc741c17>] mlx5e_tc_encap_flows_add+0x489/0x690 [mlx5_core] [<00000000e92e49d7>] mlx5e_rep_update_flows+0x6e4/0x9b0 [mlx5_core] [<00000000f60f5602>] mlx5e_rep_neigh_update+0x39a/0x5d0 [mlx5_core]
CVE-2021-47200: In the Linux kernel, the following vulnerability has been resolved: drm/prime: Fix use after free in mmap with drm_gem_ttm_mmap drm_gem_ttm_mmap() drops a reference to the gem object on success. If the gem object's refcount == 1 on entry to drm_gem_prime_mmap(), that drop will free the gem object, and the subsequent drm_gem_object_get() will be a UAF. Fix by grabbing a reference before calling the mmap helper. This issue was forseen when the reference dropping was adding in commit 9786b65bc61ac ("drm/ttm: fix mmap refcounting"): "For that to work properly the drm_gem_object_get() call in drm_gem_ttm_mmap() must be moved so it happens before calling obj->funcs->mmap(), otherwise the gem refcount would go down to zero."
CVE-2021-47205: In the Linux kernel, the following vulnerability has been resolved: clk: sunxi-ng: Unregister clocks/resets when unbinding Currently, unbinding a CCU driver unmaps the device's MMIO region, while leaving its clocks/resets and their providers registered. This can cause a page fault later when some clock operation tries to perform MMIO. Fix this by separating the CCU initialization from the memory allocation, and then using a devres callback to unregister the clocks and resets. This also fixes a memory leak of the `struct ccu_reset`, and uses the correct owner (the specific platform driver) for the clocks and resets. Early OF clock providers are never unregistered, and limited error handling is possible, so they are mostly unchanged. The error reporting is made more consistent by moving the message inside of_sunxi_ccu_probe.
CVE-2021-47211: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: fix null pointer dereference on pointer cs_desc The pointer cs_desc return from snd_usb_find_clock_source could be null, so there is a potential null pointer dereference issue. Fix this by adding a null check before dereference.
CVE-2021-47212: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Update error handler for UCTX and UMEM In the fast unload flow, the device state is set to internal error, which indicates that the driver started the destroy process. In this case, when a destroy command is being executed, it should return MLX5_CMD_STAT_OK. Fix MLX5_CMD_OP_DESTROY_UCTX and MLX5_CMD_OP_DESTROY_UMEM to return OK instead of EIO. This fixes a call trace in the umem release process - [ 2633.536695] Call Trace: [ 2633.537518] ib_uverbs_remove_one+0xc3/0x140 [ib_uverbs] [ 2633.538596] remove_client_context+0x8b/0xd0 [ib_core] [ 2633.539641] disable_device+0x8c/0x130 [ib_core] [ 2633.540615] __ib_unregister_device+0x35/0xa0 [ib_core] [ 2633.541640] ib_unregister_device+0x21/0x30 [ib_core] [ 2633.542663] __mlx5_ib_remove+0x38/0x90 [mlx5_ib] [ 2633.543640] auxiliary_bus_remove+0x1e/0x30 [auxiliary] [ 2633.544661] device_release_driver_internal+0x103/0x1f0 [ 2633.545679] bus_remove_device+0xf7/0x170 [ 2633.546640] device_del+0x181/0x410 [ 2633.547606] mlx5_rescan_drivers_locked.part.10+0x63/0x160 [mlx5_core] [ 2633.548777] mlx5_unregister_device+0x27/0x40 [mlx5_core] [ 2633.549841] mlx5_uninit_one+0x21/0xc0 [mlx5_core] [ 2633.550864] remove_one+0x69/0xe0 [mlx5_core] [ 2633.551819] pci_device_remove+0x3b/0xc0 [ 2633.552731] device_release_driver_internal+0x103/0x1f0 [ 2633.553746] unbind_store+0xf6/0x130 [ 2633.554657] kernfs_fop_write+0x116/0x190 [ 2633.555567] vfs_write+0xa5/0x1a0 [ 2633.556407] ksys_write+0x4f/0xb0 [ 2633.557233] do_syscall_64+0x5b/0x1a0 [ 2633.558071] entry_SYSCALL_64_after_hwframe+0x65/0xca [ 2633.559018] RIP: 0033:0x7f9977132648 [ 2633.559821] Code: 89 02 48 c7 c0 ff ff ff ff eb b3 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 55 6f 2d 00 8b 00 85 c0 75 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 41 54 49 89 d4 55 [ 2633.562332] RSP: 002b:00007fffb1a83888 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 2633.563472] RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f9977132648 [ 2633.564541] RDX: 000000000000000c RSI: 000055b90546e230 RDI: 0000000000000001 [ 2633.565596] RBP: 000055b90546e230 R08: 00007f9977406860 R09: 00007f9977a54740 [ 2633.566653] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f99774056e0 [ 2633.567692] R13: 000000000000000c R14: 00007f9977400880 R15: 000000000000000c [ 2633.568725] ---[ end trace 10b4fe52945e544d ]---
CVE-2021-47265: In the Linux kernel, the following vulnerability has been resolved: RDMA: Verify port when creating flow rule Validate port value provided by the user and with that remove no longer needed validation by the driver. The missing check in the mlx5_ib driver could cause to the below oops. Call trace: _create_flow_rule+0x2d4/0xf28 [mlx5_ib] mlx5_ib_create_flow+0x2d0/0x5b0 [mlx5_ib] ib_uverbs_ex_create_flow+0x4cc/0x624 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xd4/0x150 [ib_uverbs] ib_uverbs_cmd_verbs.isra.7+0xb28/0xc50 [ib_uverbs] ib_uverbs_ioctl+0x158/0x1d0 [ib_uverbs] do_vfs_ioctl+0xd0/0xaf0 ksys_ioctl+0x84/0xb4 __arm64_sys_ioctl+0x28/0xc4 el0_svc_common.constprop.3+0xa4/0x254 el0_svc_handler+0x84/0xa0 el0_svc+0x10/0x26c Code: b9401260 f9615681 51000400 8b001c20 (f9403c1a)
CVE-2021-47275: In the Linux kernel, the following vulnerability has been resolved: bcache: avoid oversized read request in cache missing code path In the cache missing code path of cached device, if a proper location from the internal B+ tree is matched for a cache miss range, function cached_dev_cache_miss() will be called in cache_lookup_fn() in the following code block, [code block 1] 526 unsigned int sectors = KEY_INODE(k) == s->iop.inode 527 ? min_t(uint64_t, INT_MAX, 528 KEY_START(k) - bio->bi_iter.bi_sector) 529 : INT_MAX; 530 int ret = s->d->cache_miss(b, s, bio, sectors); Here s->d->cache_miss() is the call backfunction pointer initialized as cached_dev_cache_miss(), the last parameter 'sectors' is an important hint to calculate the size of read request to backing device of the missing cache data. Current calculation in above code block may generate oversized value of 'sectors', which consequently may trigger 2 different potential kernel panics by BUG() or BUG_ON() as listed below, 1) BUG_ON() inside bch_btree_insert_key(), [code block 2] 886 BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); 2) BUG() inside biovec_slab(), [code block 3] 51 default: 52 BUG(); 53 return NULL; All the above panics are original from cached_dev_cache_miss() by the oversized parameter 'sectors'. Inside cached_dev_cache_miss(), parameter 'sectors' is used to calculate the size of data read from backing device for the cache missing. This size is stored in s->insert_bio_sectors by the following lines of code, [code block 4] 909 s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada); Then the actual key inserting to the internal B+ tree is generated and stored in s->iop.replace_key by the following lines of code, [code block 5] 911 s->iop.replace_key = KEY(s->iop.inode, 912 bio->bi_iter.bi_sector + s->insert_bio_sectors, 913 s->insert_bio_sectors); The oversized parameter 'sectors' may trigger panic 1) by BUG_ON() from the above code block. And the bio sending to backing device for the missing data is allocated with hint from s->insert_bio_sectors by the following lines of code, [code block 6] 926 cache_bio = bio_alloc_bioset(GFP_NOWAIT, 927 DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS), 928 &dc->disk.bio_split); The oversized parameter 'sectors' may trigger panic 2) by BUG() from the agove code block. Now let me explain how the panics happen with the oversized 'sectors'. In code block 5, replace_key is generated by macro KEY(). From the definition of macro KEY(), [code block 7] 71 #define KEY(inode, offset, size) \ 72 ((struct bkey) { \ 73 .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ 74 .low = (offset) \ 75 }) Here 'size' is 16bits width embedded in 64bits member 'high' of struct bkey. But in code block 1, if "KEY_START(k) - bio->bi_iter.bi_sector" is very probably to be larger than (1<<16) - 1, which makes the bkey size calculation in code block 5 is overflowed. In one bug report the value of parameter 'sectors' is 131072 (= 1 << 17), the overflowed 'sectors' results the overflowed s->insert_bio_sectors in code block 4, then makes size field of s->iop.replace_key to be 0 in code block 5. Then the 0- sized s->iop.replace_key is inserted into the internal B+ tree as cache missing check key (a special key to detect and avoid a racing between normal write request and cache missing read request) as, [code block 8] 915 ret = bch_btree_insert_check_key(b, &s->op, &s->iop.replace_key); Then the 0-sized s->iop.replace_key as 3rd parameter triggers the bkey size check BUG_ON() in code block 2, and causes the kernel panic 1). Another ke ---truncated---
CVE-2021-47366: In the Linux kernel, the following vulnerability has been resolved: afs: Fix corruption in reads at fpos 2G-4G from an OpenAFS server AFS-3 has two data fetch RPC variants, FS.FetchData and FS.FetchData64, and Linux's afs client switches between them when talking to a non-YFS server if the read size, the file position or the sum of the two have the upper 32 bits set of the 64-bit value. This is a problem, however, since the file position and length fields of FS.FetchData are *signed* 32-bit values. Fix this by capturing the capability bits obtained from the fileserver when it's sent an FS.GetCapabilities RPC, rather than just discarding them, and then picking out the VICED_CAPABILITY_64BITFILES flag. This can then be used to decide whether to use FS.FetchData or FS.FetchData64 - and also FS.StoreData or FS.StoreData64 - rather than using upper_32_bits() to switch on the parameter values. This capabilities flag could also be used to limit the maximum size of the file, but all servers must be checked for that. Note that the issue does not exist with FS.StoreData - that uses *unsigned* 32-bit values. It's also not a problem with Auristor servers as its YFS.FetchData64 op uses unsigned 64-bit values. This can be tested by cloning a git repo through an OpenAFS client to an OpenAFS server and then doing "git status" on it from a Linux afs client[1]. Provided the clone has a pack file that's in the 2G-4G range, the git status will show errors like: error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index This can be observed in the server's FileLog with something like the following appearing: Sun Aug 29 19:31:39 2021 SRXAFS_FetchData, Fid = 2303380852.491776.3263114, Host 192.168.11.201:7001, Id 1001 Sun Aug 29 19:31:39 2021 CheckRights: len=0, for host=192.168.11.201:7001 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: Pos 18446744071815340032, Len 3154 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: file size 2400758866 ... Sun Aug 29 19:31:40 2021 SRXAFS_FetchData returns 5 Note the file position of 18446744071815340032. This is the requested file position sign-extended.
CVE-2021-47381: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Fix DSP oops stack dump output contents Fix @buf arg given to hex_dump_to_buffer() and stack address used in dump error output.
CVE-2021-47382: In the Linux kernel, the following vulnerability has been resolved: s390/qeth: fix deadlock during failing recovery Commit 0b9902c1fcc5 ("s390/qeth: fix deadlock during recovery") removed taking discipline_mutex inside qeth_do_reset(), fixing potential deadlocks. An error path was missed though, that still takes discipline_mutex and thus has the original deadlock potential. Intermittent deadlocks were seen when a qeth channel path is configured offline, causing a race between qeth_do_reset and ccwgroup_remove. Call qeth_set_offline() directly in the qeth_do_reset() error case and then a new variant of ccwgroup_set_offline(), without taking discipline_mutex.
CVE-2021-47410: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: fix svm_migrate_fini warning Device manager releases device-specific resources when a driver disconnects from a device, devm_memunmap_pages and devm_release_mem_region calls in svm_migrate_fini are redundant. It causes below warning trace after patch "drm/amdgpu: Split amdgpu_device_fini into early and late", so remove function svm_migrate_fini. BUG: https://gitlab.freedesktop.org/drm/amd/-/issues/1718 WARNING: CPU: 1 PID: 3646 at drivers/base/devres.c:795 devm_release_action+0x51/0x60 Call Trace: ? memunmap_pages+0x360/0x360 svm_migrate_fini+0x2d/0x60 [amdgpu] kgd2kfd_device_exit+0x23/0xa0 [amdgpu] amdgpu_amdkfd_device_fini_sw+0x1d/0x30 [amdgpu] amdgpu_device_fini_sw+0x45/0x290 [amdgpu] amdgpu_driver_release_kms+0x12/0x30 [amdgpu] drm_dev_release+0x20/0x40 [drm] release_nodes+0x196/0x1e0 device_release_driver_internal+0x104/0x1d0 driver_detach+0x47/0x90 bus_remove_driver+0x7a/0xd0 pci_unregister_driver+0x3d/0x90 amdgpu_exit+0x11/0x20 [amdgpu]
CVE-2021-47432: In the Linux kernel, the following vulnerability has been resolved: lib/generic-radix-tree.c: Don't overflow in peek() When we started spreading new inode numbers throughout most of the 64 bit inode space, that triggered some corner case bugs, in particular some integer overflows related to the radix tree code. Oops.
CVE-2021-47448: In the Linux kernel, the following vulnerability has been resolved: mptcp: fix possible stall on recvmsg() recvmsg() can enter an infinite loop if the caller provides the MSG_WAITALL, the data present in the receive queue is not sufficient to fulfill the request, and no more data is received by the peer. When the above happens, mptcp_wait_data() will always return with no wait, as the MPTCP_DATA_READY flag checked by such function is set and never cleared in such code path. Leveraging the above syzbot was able to trigger an RCU stall: rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 0-...!: (10499 ticks this GP) idle=0af/1/0x4000000000000000 softirq=10678/10678 fqs=1 (t=10500 jiffies g=13089 q=109) rcu: rcu_preempt kthread starved for 10497 jiffies! g13089 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=1 rcu: Unless rcu_preempt kthread gets sufficient CPU time, OOM is now expected behavior. rcu: RCU grace-period kthread stack dump: task:rcu_preempt state:R running task stack:28696 pid: 14 ppid: 2 flags:0x00004000 Call Trace: context_switch kernel/sched/core.c:4955 [inline] __schedule+0x940/0x26f0 kernel/sched/core.c:6236 schedule+0xd3/0x270 kernel/sched/core.c:6315 schedule_timeout+0x14a/0x2a0 kernel/time/timer.c:1881 rcu_gp_fqs_loop+0x186/0x810 kernel/rcu/tree.c:1955 rcu_gp_kthread+0x1de/0x320 kernel/rcu/tree.c:2128 kthread+0x405/0x4f0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 rcu: Stack dump where RCU GP kthread last ran: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 8510 Comm: syz-executor827 Not tainted 5.15.0-rc2-next-20210920-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:bytes_is_nonzero mm/kasan/generic.c:84 [inline] RIP: 0010:memory_is_nonzero mm/kasan/generic.c:102 [inline] RIP: 0010:memory_is_poisoned_n mm/kasan/generic.c:128 [inline] RIP: 0010:memory_is_poisoned mm/kasan/generic.c:159 [inline] RIP: 0010:check_region_inline mm/kasan/generic.c:180 [inline] RIP: 0010:kasan_check_range+0xc8/0x180 mm/kasan/generic.c:189 Code: 38 00 74 ed 48 8d 50 08 eb 09 48 83 c0 01 48 39 d0 74 7a 80 38 00 74 f2 48 89 c2 b8 01 00 00 00 48 85 d2 75 56 5b 5d 41 5c c3 <48> 85 d2 74 5e 48 01 ea eb 09 48 83 c0 01 48 39 d0 74 50 80 38 00 RSP: 0018:ffffc9000cd676c8 EFLAGS: 00000283 RAX: ffffed100e9a110e RBX: ffffed100e9a110f RCX: ffffffff88ea062a RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888074d08870 RBP: ffffed100e9a110e R08: 0000000000000001 R09: ffff888074d08877 R10: ffffed100e9a110e R11: 0000000000000000 R12: ffff888074d08000 R13: ffff888074d08000 R14: ffff888074d08088 R15: ffff888074d08000 FS: 0000555556d8e300(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 S: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000180 CR3: 0000000068909000 CR4: 00000000001506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: instrument_atomic_read_write include/linux/instrumented.h:101 [inline] test_and_clear_bit include/asm-generic/bitops/instrumented-atomic.h:83 [inline] mptcp_release_cb+0x14a/0x210 net/mptcp/protocol.c:3016 release_sock+0xb4/0x1b0 net/core/sock.c:3204 mptcp_wait_data net/mptcp/protocol.c:1770 [inline] mptcp_recvmsg+0xfd1/0x27b0 net/mptcp/protocol.c:2080 inet6_recvmsg+0x11b/0x5e0 net/ipv6/af_inet6.c:659 sock_recvmsg_nosec net/socket.c:944 [inline] ____sys_recvmsg+0x527/0x600 net/socket.c:2626 ___sys_recvmsg+0x127/0x200 net/socket.c:2670 do_recvmmsg+0x24d/0x6d0 net/socket.c:2764 __sys_recvmmsg net/socket.c:2843 [inline] __do_sys_recvmmsg net/socket.c:2866 [inline] __se_sys_recvmmsg net/socket.c:2859 [inline] __x64_sys_recvmmsg+0x20b/0x260 net/socket.c:2859 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7fc200d2 ---truncated---
CVE-2021-47452: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: skip netdev events generated on netns removal syzbot reported following (harmless) WARN: WARNING: CPU: 1 PID: 2648 at net/netfilter/core.c:468 nft_netdev_unregister_hooks net/netfilter/nf_tables_api.c:230 [inline] nf_tables_unregister_hook include/net/netfilter/nf_tables.h:1090 [inline] __nft_release_basechain+0x138/0x640 net/netfilter/nf_tables_api.c:9524 nft_netdev_event net/netfilter/nft_chain_filter.c:351 [inline] nf_tables_netdev_event+0x521/0x8a0 net/netfilter/nft_chain_filter.c:382 reproducer: unshare -n bash -c 'ip link add br0 type bridge; nft add table netdev t ; \ nft add chain netdev t ingress \{ type filter hook ingress device "br0" \ priority 0\; policy drop\; \}' Problem is that when netns device exit hooks create the UNREGISTER event, the .pre_exit hook for nf_tables core has already removed the base hook. Notifier attempts to do this again. The need to do base hook unregister unconditionally was needed in the past, because notifier was last stage where reg->dev dereference was safe. Now that nf_tables does the hook removal in .pre_exit, this isn't needed anymore.
CVE-2021-47484: In the Linux kernel, the following vulnerability has been resolved: octeontx2-af: Fix possible null pointer dereference. This patch fixes possible null pointer dereference in files "rvu_debugfs.c" and "rvu_nix.c"
CVE-2021-47504: In the Linux kernel, the following vulnerability has been resolved: io_uring: ensure task_work gets run as part of cancelations If we successfully cancel a work item but that work item needs to be processed through task_work, then we can be sleeping uninterruptibly in io_uring_cancel_generic() and never process it. Hence we don't make forward progress and we end up with an uninterruptible sleep warning. While in there, correct a comment that should be IFF, not IIF.
CVE-2021-47508: In the Linux kernel, the following vulnerability has been resolved: btrfs: free exchange changeset on failures Fstests runs on my VMs have show several kmemleak reports like the following. unreferenced object 0xffff88811ae59080 (size 64): comm "xfs_io", pid 12124, jiffies 4294987392 (age 6.368s) hex dump (first 32 bytes): 00 c0 1c 00 00 00 00 00 ff cf 1c 00 00 00 00 00 ................ 90 97 e5 1a 81 88 ff ff 90 97 e5 1a 81 88 ff ff ................ backtrace: [<00000000ac0176d2>] ulist_add_merge+0x60/0x150 [btrfs] [<0000000076e9f312>] set_state_bits+0x86/0xc0 [btrfs] [<0000000014fe73d6>] set_extent_bit+0x270/0x690 [btrfs] [<000000004f675208>] set_record_extent_bits+0x19/0x20 [btrfs] [<00000000b96137b1>] qgroup_reserve_data+0x274/0x310 [btrfs] [<0000000057e9dcbb>] btrfs_check_data_free_space+0x5c/0xa0 [btrfs] [<0000000019c4511d>] btrfs_delalloc_reserve_space+0x1b/0xa0 [btrfs] [<000000006d37e007>] btrfs_dio_iomap_begin+0x415/0x970 [btrfs] [<00000000fb8a74b8>] iomap_iter+0x161/0x1e0 [<0000000071dff6ff>] __iomap_dio_rw+0x1df/0x700 [<000000002567ba53>] iomap_dio_rw+0x5/0x20 [<0000000072e555f8>] btrfs_file_write_iter+0x290/0x530 [btrfs] [<000000005eb3d845>] new_sync_write+0x106/0x180 [<000000003fb505bf>] vfs_write+0x24d/0x2f0 [<000000009bb57d37>] __x64_sys_pwrite64+0x69/0xa0 [<000000003eba3fdf>] do_syscall_64+0x43/0x90 In case brtfs_qgroup_reserve_data() or btrfs_delalloc_reserve_metadata() fail the allocated extent_changeset will not be freed. So in btrfs_check_data_free_space() and btrfs_delalloc_reserve_space() free the allocated extent_changeset to get rid of the allocated memory. The issue currently only happens in the direct IO write path, but only after 65b3c08606e5 ("btrfs: fix ENOSPC failure when attempting direct IO write into NOCOW range"), and also at defrag_one_locked_target(). Every other place is always calling extent_changeset_free() even if its call to btrfs_delalloc_reserve_space() or btrfs_check_data_free_space() has failed.
CVE-2021-47552: In the Linux kernel, the following vulnerability has been resolved: blk-mq: cancel blk-mq dispatch work in both blk_cleanup_queue and disk_release() For avoiding to slow down queue destroy, we don't call blk_mq_quiesce_queue() in blk_cleanup_queue(), instead of delaying to cancel dispatch work in blk_release_queue(). However, this way has caused kernel oops[1], reported by Changhui. The log shows that scsi_device can be freed before running blk_release_queue(), which is expected too since scsi_device is released after the scsi disk is closed and the scsi_device is removed. Fixes the issue by canceling blk-mq dispatch work in both blk_cleanup_queue() and disk_release(): 1) when disk_release() is run, the disk has been closed, and any sync dispatch activities have been done, so canceling dispatch work is enough to quiesce filesystem I/O dispatch activity. 2) in blk_cleanup_queue(), we only focus on passthrough request, and passthrough request is always explicitly allocated & freed by its caller, so once queue is frozen, all sync dispatch activity for passthrough request has been done, then it is enough to just cancel dispatch work for avoiding any dispatch activity. [1] kernel panic log [12622.769416] BUG: kernel NULL pointer dereference, address: 0000000000000300 [12622.777186] #PF: supervisor read access in kernel mode [12622.782918] #PF: error_code(0x0000) - not-present page [12622.788649] PGD 0 P4D 0 [12622.791474] Oops: 0000 [#1] PREEMPT SMP PTI [12622.796138] CPU: 10 PID: 744 Comm: kworker/10:1H Kdump: loaded Not tainted 5.15.0+ #1 [12622.804877] Hardware name: Dell Inc. PowerEdge R730/0H21J3, BIOS 1.5.4 10/002/2015 [12622.813321] Workqueue: kblockd blk_mq_run_work_fn [12622.818572] RIP: 0010:sbitmap_get+0x75/0x190 [12622.823336] Code: 85 80 00 00 00 41 8b 57 08 85 d2 0f 84 b1 00 00 00 45 31 e4 48 63 cd 48 8d 1c 49 48 c1 e3 06 49 03 5f 10 4c 8d 6b 40 83 f0 01 <48> 8b 33 44 89 f2 4c 89 ef 0f b6 c8 e8 fa f3 ff ff 83 f8 ff 75 58 [12622.844290] RSP: 0018:ffffb00a446dbd40 EFLAGS: 00010202 [12622.850120] RAX: 0000000000000001 RBX: 0000000000000300 RCX: 0000000000000004 [12622.858082] RDX: 0000000000000006 RSI: 0000000000000082 RDI: ffffa0b7a2dfe030 [12622.866042] RBP: 0000000000000004 R08: 0000000000000001 R09: ffffa0b742721334 [12622.874003] R10: 0000000000000008 R11: 0000000000000008 R12: 0000000000000000 [12622.881964] R13: 0000000000000340 R14: 0000000000000000 R15: ffffa0b7a2dfe030 [12622.889926] FS: 0000000000000000(0000) GS:ffffa0baafb40000(0000) knlGS:0000000000000000 [12622.898956] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12622.905367] CR2: 0000000000000300 CR3: 0000000641210001 CR4: 00000000001706e0 [12622.913328] Call Trace: [12622.916055] <TASK> [12622.918394] scsi_mq_get_budget+0x1a/0x110 [12622.922969] __blk_mq_do_dispatch_sched+0x1d4/0x320 [12622.928404] ? pick_next_task_fair+0x39/0x390 [12622.933268] __blk_mq_sched_dispatch_requests+0xf4/0x140 [12622.939194] blk_mq_sched_dispatch_requests+0x30/0x60 [12622.944829] __blk_mq_run_hw_queue+0x30/0xa0 [12622.949593] process_one_work+0x1e8/0x3c0 [12622.954059] worker_thread+0x50/0x3b0 [12622.958144] ? rescuer_thread+0x370/0x370 [12622.962616] kthread+0x158/0x180 [12622.966218] ? set_kthread_struct+0x40/0x40 [12622.970884] ret_from_fork+0x22/0x30 [12622.974875] </TASK> [12622.977309] Modules linked in: scsi_debug rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs sunrpc dm_multipath intel_rapl_msr intel_rapl_common dell_wmi_descriptor sb_edac rfkill video x86_pkg_temp_thermal intel_powerclamp dcdbas coretemp kvm_intel kvm mgag200 irqbypass i2c_algo_bit rapl drm_kms_helper ipmi_ssif intel_cstate intel_uncore syscopyarea sysfillrect sysimgblt fb_sys_fops pcspkr cec mei_me lpc_ich mei ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sr_mod cdrom sd_mod t10_pi sg ixgbe ahci libahci crct10dif_pclmul crc32_pclmul crc32c_intel libata megaraid_sas ghash_clmulni_intel tg3 wdat_w ---truncated---
CVE-2021-47558: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: Disable Tx queues when reconfiguring the interface The Tx queues were not disabled in situations where the driver needed to stop the interface to apply a new configuration. This could result in a kernel panic when doing any of the 3 following actions: * reconfiguring the number of queues (ethtool -L) * reconfiguring the size of the ring buffers (ethtool -G) * installing/removing an XDP program (ip l set dev ethX xdp) Prevent the panic by making sure netif_tx_disable is called when stopping an interface. Without this patch, the following kernel panic can be observed when doing any of the actions above: Unable to handle kernel paging request at virtual address ffff80001238d040 [....] Call trace: dwmac4_set_addr+0x8/0x10 dev_hard_start_xmit+0xe4/0x1ac sch_direct_xmit+0xe8/0x39c __dev_queue_xmit+0x3ec/0xaf0 dev_queue_xmit+0x14/0x20 [...] [ end trace 0000000000000002 ]---
CVE-2021-47582: In the Linux kernel, the following vulnerability has been resolved: USB: core: Make do_proc_control() and do_proc_bulk() killable The USBDEVFS_CONTROL and USBDEVFS_BULK ioctls invoke usb_start_wait_urb(), which contains an uninterruptible wait with a user-specified timeout value. If timeout value is very large and the device being accessed does not respond in a reasonable amount of time, the kernel will complain about "Task X blocked for more than N seconds", as found in testing by syzbot: INFO: task syz-executor.0:8700 blocked for more than 143 seconds. Not tainted 5.14.0-rc7-syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:23192 pid: 8700 ppid: 8455 flags:0x00004004 Call Trace: context_switch kernel/sched/core.c:4681 [inline] __schedule+0xc07/0x11f0 kernel/sched/core.c:5938 schedule+0x14b/0x210 kernel/sched/core.c:6017 schedule_timeout+0x98/0x2f0 kernel/time/timer.c:1857 do_wait_for_common+0x2da/0x480 kernel/sched/completion.c:85 __wait_for_common kernel/sched/completion.c:106 [inline] wait_for_common kernel/sched/completion.c:117 [inline] wait_for_completion_timeout+0x46/0x60 kernel/sched/completion.c:157 usb_start_wait_urb+0x167/0x550 drivers/usb/core/message.c:63 do_proc_bulk+0x978/0x1080 drivers/usb/core/devio.c:1236 proc_bulk drivers/usb/core/devio.c:1273 [inline] usbdev_do_ioctl drivers/usb/core/devio.c:2547 [inline] usbdev_ioctl+0x3441/0x6b10 drivers/usb/core/devio.c:2713 ... To fix this problem, this patch replaces usbfs's calls to usb_control_msg() and usb_bulk_msg() with special-purpose code that does essentially the same thing (as recommended in the comment for usb_start_wait_urb()), except that it always uses a killable wait and it uses GFP_KERNEL rather than GFP_NOIO.
CVE-2021-47599: In the Linux kernel, the following vulnerability has been resolved: btrfs: use latest_dev in btrfs_show_devname The test case btrfs/238 reports the warning below: WARNING: CPU: 3 PID: 481 at fs/btrfs/super.c:2509 btrfs_show_devname+0x104/0x1e8 [btrfs] CPU: 2 PID: 1 Comm: systemd Tainted: G W O 5.14.0-rc1-custom #72 Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: btrfs_show_devname+0x108/0x1b4 [btrfs] show_mountinfo+0x234/0x2c4 m_show+0x28/0x34 seq_read_iter+0x12c/0x3c4 vfs_read+0x29c/0x2c8 ksys_read+0x80/0xec __arm64_sys_read+0x28/0x34 invoke_syscall+0x50/0xf8 do_el0_svc+0x88/0x138 el0_svc+0x2c/0x8c el0t_64_sync_handler+0x84/0xe4 el0t_64_sync+0x198/0x19c Reason: While btrfs_prepare_sprout() moves the fs_devices::devices into fs_devices::seed_list, the btrfs_show_devname() searches for the devices and found none, leading to the warning as in above. Fix: latest_dev is updated according to the changes to the device list. That means we could use the latest_dev->name to show the device name in /proc/self/mounts, the pointer will be always valid as it's assigned before the device is deleted from the list in remove or replace. The RCU protection is sufficient as the device structure is freed after synchronization.
CVE-2021-47610: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix null ptr access msm_ioctl_gem_submit() Fix the below null pointer dereference in msm_ioctl_gem_submit(): 26545.260705: Call trace: 26545.263223: kref_put+0x1c/0x60 26545.266452: msm_ioctl_gem_submit+0x254/0x744 26545.270937: drm_ioctl_kernel+0xa8/0x124 26545.274976: drm_ioctl+0x21c/0x33c 26545.278478: drm_compat_ioctl+0xdc/0xf0 26545.282428: __arm64_compat_sys_ioctl+0xc8/0x100 26545.287169: el0_svc_common+0xf8/0x250 26545.291025: do_el0_svc_compat+0x28/0x54 26545.295066: el0_svc_compat+0x10/0x1c 26545.298838: el0_sync_compat_handler+0xa8/0xcc 26545.303403: el0_sync_compat+0x188/0x1c0 26545.307445: Code: d503201f d503201f 52800028 4b0803e8 (b8680008) 26545.318799: Kernel panic - not syncing: Oops: Fatal exception
CVE-2021-47618: In the Linux kernel, the following vulnerability has been resolved: ARM: 9170/1: fix panic when kasan and kprobe are enabled arm32 uses software to simulate the instruction replaced by kprobe. some instructions may be simulated by constructing assembly functions. therefore, before executing instruction simulation, it is necessary to construct assembly function execution environment in C language through binding registers. after kasan is enabled, the register binding relationship will be destroyed, resulting in instruction simulation errors and causing kernel panic. the kprobe emulate instruction function is distributed in three files: actions-common.c actions-arm.c actions-thumb.c, so disable KASAN when compiling these files. for example, use kprobe insert on cap_capable+20 after kasan enabled, the cap_capable assembly code is as follows: <cap_capable>: e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} e1a05000 mov r5, r0 e280006c add r0, r0, #108 ; 0x6c e1a04001 mov r4, r1 e1a06002 mov r6, r2 e59fa090 ldr sl, [pc, #144] ; ebfc7bf8 bl c03aa4b4 <__asan_load4> e595706c ldr r7, [r5, #108] ; 0x6c e2859014 add r9, r5, #20 ...... The emulate_ldr assembly code after enabling kasan is as follows: c06f1384 <emulate_ldr>: e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} e282803c add r8, r2, #60 ; 0x3c e1a05000 mov r5, r0 e7e37855 ubfx r7, r5, #16, #4 e1a00008 mov r0, r8 e1a09001 mov r9, r1 e1a04002 mov r4, r2 ebf35462 bl c03c6530 <__asan_load4> e357000f cmp r7, #15 e7e36655 ubfx r6, r5, #12, #4 e205a00f and sl, r5, #15 0a000001 beq c06f13bc <emulate_ldr+0x38> e0840107 add r0, r4, r7, lsl #2 ebf3545c bl c03c6530 <__asan_load4> e084010a add r0, r4, sl, lsl #2 ebf3545a bl c03c6530 <__asan_load4> e2890010 add r0, r9, #16 ebf35458 bl c03c6530 <__asan_load4> e5990010 ldr r0, [r9, #16] e12fff30 blx r0 e356000f cm r6, #15 1a000014 bne c06f1430 <emulate_ldr+0xac> e1a06000 mov r6, r0 e2840040 add r0, r4, #64 ; 0x40 ...... when running in emulate_ldr to simulate the ldr instruction, panic occurred, and the log is as follows: Unable to handle kernel NULL pointer dereference at virtual address 00000090 pgd = ecb46400 [00000090] *pgd=2e0fa003, *pmd=00000000 Internal error: Oops: 206 [#1] SMP ARM PC is at cap_capable+0x14/0xb0 LR is at emulate_ldr+0x50/0xc0 psr: 600d0293 sp : ecd63af8 ip : 00000004 fp : c0a7c30c r10: 00000000 r9 : c30897f4 r8 : ecd63cd4 r7 : 0000000f r6 : 0000000a r5 : e59fa090 r4 : ecd63c98 r3 : c06ae294 r2 : 00000000 r1 : b7611300 r0 : bf4ec008 Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment user Control: 32c5387d Table: 2d546400 DAC: 55555555 Process bash (pid: 1643, stack limit = 0xecd60190) (cap_capable) from (kprobe_handler+0x218/0x340) (kprobe_handler) from (kprobe_trap_handler+0x24/0x48) (kprobe_trap_handler) from (do_undefinstr+0x13c/0x364) (do_undefinstr) from (__und_svc_finish+0x0/0x30) (__und_svc_finish) from (cap_capable+0x18/0xb0) (cap_capable) from (cap_vm_enough_memory+0x38/0x48) (cap_vm_enough_memory) from (security_vm_enough_memory_mm+0x48/0x6c) (security_vm_enough_memory_mm) from (copy_process.constprop.5+0x16b4/0x25c8) (copy_process.constprop.5) from (_do_fork+0xe8/0x55c) (_do_fork) from (SyS_clone+0x1c/0x24) (SyS_clone) from (__sys_trace_return+0x0/0x10) Code: 0050a0e1 6c0080e2 0140a0e1 0260a0e1 (f801f0e7)
CVE-2021-47622: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: Fix a deadlock in the error handler The following deadlock has been observed on a test setup: - All tags allocated - The SCSI error handler calls ufshcd_eh_host_reset_handler() - ufshcd_eh_host_reset_handler() queues work that calls ufshcd_err_handler() - ufshcd_err_handler() locks up as follows: Workqueue: ufs_eh_wq_0 ufshcd_err_handler.cfi_jt Call trace: __switch_to+0x298/0x5d8 __schedule+0x6cc/0xa94 schedule+0x12c/0x298 blk_mq_get_tag+0x210/0x480 __blk_mq_alloc_request+0x1c8/0x284 blk_get_request+0x74/0x134 ufshcd_exec_dev_cmd+0x68/0x640 ufshcd_verify_dev_init+0x68/0x35c ufshcd_probe_hba+0x12c/0x1cb8 ufshcd_host_reset_and_restore+0x88/0x254 ufshcd_reset_and_restore+0xd0/0x354 ufshcd_err_handler+0x408/0xc58 process_one_work+0x24c/0x66c worker_thread+0x3e8/0xa4c kthread+0x150/0x1b4 ret_from_fork+0x10/0x30 Fix this lockup by making ufshcd_exec_dev_cmd() allocate a reserved request.
CVE-2021-47653: In the Linux kernel, the following vulnerability has been resolved: media: davinci: vpif: fix use-after-free on driver unbind The driver allocates and registers two platform device structures during probe, but the devices were never deregistered on driver unbind. This results in a use-after-free on driver unbind as the device structures were allocated using devres and would be freed by driver core when remove() returns. Fix this by adding the missing deregistration calls to the remove() callback and failing probe on registration errors. Note that the platform device structures must be freed using a proper release callback to avoid leaking associated resources like device names.
CVE-2021-47658: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: fix a potential gpu_metrics_table memory leak Memory is allocated for gpu_metrics_table in renoir_init_smc_tables(), but not freed in int smu_v12_0_fini_smc_tables(). Free it!
CVE-2022-27672: When SMT is enabled, certain AMD processors may speculatively execute instructions using a target from the sibling thread after an SMT mode switch potentially resulting in information disclosure.
CVE-2022-38457: A use-after-free(UAF) vulnerability was found in function 'vmw_cmd_res_check' in drivers/gpu/vmxgfx/vmxgfx_execbuf.c in Linux kernel's vmwgfx driver with device file '/dev/dri/renderD128 (or Dxxx)'. This flaw allows a local attacker with a user account on the system to gain privilege, causing a denial of service(DoS).
CVE-2022-40133: A use-after-free(UAF) vulnerability was found in function 'vmw_execbuf_tie_context' in drivers/gpu/vmxgfx/vmxgfx_execbuf.c in Linux kernel's vmwgfx driver with device file '/dev/dri/renderD128 (or Dxxx)'. This flaw allows a local attacker with a user account on the system to gain privilege, causing a denial of service(DoS).
CVE-2022-48626: In the Linux kernel, the following vulnerability has been resolved: moxart: fix potential use-after-free on remove path It was reported that the mmc host structure could be accessed after it was freed in moxart_remove(), so fix this by saving the base register of the device and using it instead of the pointer dereference.
CVE-2022-48628: In the Linux kernel, the following vulnerability has been resolved: ceph: drop messages from MDS when unmounting When unmounting all the dirty buffers will be flushed and after the last osd request is finished the last reference of the i_count will be released. Then it will flush the dirty cap/snap to MDSs, and the unmounting won't wait the possible acks, which will ihold the inodes when updating the metadata locally but makes no sense any more, of this. This will make the evict_inodes() to skip these inodes. If encrypt is enabled the kernel generate a warning when removing the encrypt keys when the skipped inodes still hold the keyring: WARNING: CPU: 4 PID: 168846 at fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0 CPU: 4 PID: 168846 Comm: umount Tainted: G S 6.1.0-rc5-ceph-g72ead199864c #1 Hardware name: Supermicro SYS-5018R-WR/X10SRW-F, BIOS 2.0 12/17/2015 RIP: 0010:fscrypt_destroy_keyring+0x7e/0xd0 RSP: 0018:ffffc9000b277e28 EFLAGS: 00010202 RAX: 0000000000000002 RBX: ffff88810d52ac00 RCX: ffff88810b56aa00 RDX: 0000000080000000 RSI: ffffffff822f3a09 RDI: ffff888108f59000 RBP: ffff8881d394fb88 R08: 0000000000000028 R09: 0000000000000000 R10: 0000000000000001 R11: 11ff4fe6834fcd91 R12: ffff8881d394fc40 R13: ffff888108f59000 R14: ffff8881d394f800 R15: 0000000000000000 FS: 00007fd83f6f1080(0000) GS:ffff88885fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f918d417000 CR3: 000000017f89a005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> generic_shutdown_super+0x47/0x120 kill_anon_super+0x14/0x30 ceph_kill_sb+0x36/0x90 [ceph] deactivate_locked_super+0x29/0x60 cleanup_mnt+0xb8/0x140 task_work_run+0x67/0xb0 exit_to_user_mode_prepare+0x23d/0x240 syscall_exit_to_user_mode+0x25/0x60 do_syscall_64+0x40/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd83dc39e9b Later the kernel will crash when iput() the inodes and dereferencing the "sb->s_master_keys", which has been released by the generic_shutdown_super().
CVE-2022-48633: In the Linux kernel, the following vulnerability has been resolved: drm/gma500: Fix WARN_ON(lock->magic != lock) error psb_gem_unpin() calls dma_resv_lock() but the underlying ww_mutex gets destroyed by drm_gem_object_release() move the drm_gem_object_release() call in psb_gem_free_object() to after the unpin to fix the below warning: [ 79.693962] ------------[ cut here ]------------ [ 79.693992] DEBUG_LOCKS_WARN_ON(lock->magic != lock) [ 79.694015] WARNING: CPU: 0 PID: 240 at kernel/locking/mutex.c:582 __ww_mutex_lock.constprop.0+0x569/0xfb0 [ 79.694052] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer qrtr bnep ath9k ath9k_common ath9k_hw snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio snd_hda_codec_hdmi snd_hda_intel ath3k snd_intel_dspcfg mac80211 snd_intel_sdw_acpi btusb snd_hda_codec btrtl btbcm btintel btmtk bluetooth at24 snd_hda_core snd_hwdep uvcvideo snd_seq libarc4 videobuf2_vmalloc ath videobuf2_memops videobuf2_v4l2 videobuf2_common snd_seq_device videodev acer_wmi intel_powerclamp coretemp mc snd_pcm joydev sparse_keymap ecdh_generic pcspkr wmi_bmof cfg80211 i2c_i801 i2c_smbus snd_timer snd r8169 rfkill lpc_ich soundcore acpi_cpufreq zram rtsx_pci_sdmmc mmc_core serio_raw rtsx_pci gma500_gfx(E) video wmi ip6_tables ip_tables i2c_dev fuse [ 79.694436] CPU: 0 PID: 240 Comm: plymouthd Tainted: G W E 6.0.0-rc3+ #490 [ 79.694457] Hardware name: Packard Bell dot s/SJE01_CT, BIOS V1.10 07/23/2013 [ 79.694469] RIP: 0010:__ww_mutex_lock.constprop.0+0x569/0xfb0 [ 79.694496] Code: ff 85 c0 0f 84 15 fb ff ff 8b 05 ca 3c 11 01 85 c0 0f 85 07 fb ff ff 48 c7 c6 30 cb 84 aa 48 c7 c7 a3 e1 82 aa e8 ac 29 f8 ff <0f> 0b e9 ed fa ff ff e8 5b 83 8a ff 85 c0 74 10 44 8b 0d 98 3c 11 [ 79.694513] RSP: 0018:ffffad1dc048bbe0 EFLAGS: 00010282 [ 79.694623] RAX: 0000000000000028 RBX: 0000000000000000 RCX: 0000000000000000 [ 79.694636] RDX: 0000000000000001 RSI: ffffffffaa8b0ffc RDI: 00000000ffffffff [ 79.694650] RBP: ffffad1dc048bc80 R08: 0000000000000000 R09: ffffad1dc048ba90 [ 79.694662] R10: 0000000000000003 R11: ffffffffaad62fe8 R12: ffff9ff302103138 [ 79.694675] R13: ffff9ff306ec8000 R14: ffff9ff307779078 R15: ffff9ff3014c0270 [ 79.694690] FS: 00007ff1cccf1740(0000) GS:ffff9ff3bc200000(0000) knlGS:0000000000000000 [ 79.694705] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 79.694719] CR2: 0000559ecbcb4420 CR3: 0000000013210000 CR4: 00000000000006f0 [ 79.694734] Call Trace: [ 79.694749] <TASK> [ 79.694761] ? __schedule+0x47f/0x1670 [ 79.694796] ? psb_gem_unpin+0x27/0x1a0 [gma500_gfx] [ 79.694830] ? lock_is_held_type+0xe3/0x140 [ 79.694864] ? ww_mutex_lock+0x38/0xa0 [ 79.694885] ? __cond_resched+0x1c/0x30 [ 79.694902] ww_mutex_lock+0x38/0xa0 [ 79.694925] psb_gem_unpin+0x27/0x1a0 [gma500_gfx] [ 79.694964] psb_gem_unpin+0x199/0x1a0 [gma500_gfx] [ 79.694996] drm_gem_object_release_handle+0x50/0x60 [ 79.695020] ? drm_gem_object_handle_put_unlocked+0xf0/0xf0 [ 79.695042] idr_for_each+0x4b/0xb0 [ 79.695066] ? _raw_spin_unlock_irqrestore+0x30/0x60 [ 79.695095] drm_gem_release+0x1c/0x30 [ 79.695118] drm_file_free.part.0+0x1ea/0x260 [ 79.695150] drm_release+0x6a/0x120 [ 79.695175] __fput+0x9f/0x260 [ 79.695203] task_work_run+0x59/0xa0 [ 79.695227] do_exit+0x387/0xbe0 [ 79.695250] ? seqcount_lockdep_reader_access.constprop.0+0x82/0x90 [ 79.695275] ? lockdep_hardirqs_on+0x7d/0x100 [ 79.695304] do_group_exit+0x33/0xb0 [ 79.695331] __x64_sys_exit_group+0x14/0x20 [ 79.695353] do_syscall_64+0x58/0x80 [ 79.695376] ? up_read+0x17/0x20 [ 79.695401] ? lock_is_held_type+0xe3/0x140 [ 79.695429] ? asm_exc_page_fault+0x22/0x30 [ 79.695450] ? lockdep_hardirqs_on+0x7d/0x100 [ 79.695473] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 79.695493] RIP: 0033:0x7ff1ccefe3f1 [ 79.695516] Code: Unable to access opcode bytes at RIP 0x7ff1ccefe3c7. [ 79.695607] RSP: 002b:00007ffed4413378 EFLAGS: ---truncated---
CVE-2022-48645: In the Linux kernel, the following vulnerability has been resolved: net: enetc: deny offload of tc-based TSN features on VF interfaces TSN features on the ENETC (taprio, cbs, gate, police) are configured through a mix of command BD ring messages and port registers: enetc_port_rd(), enetc_port_wr(). Port registers are a region of the ENETC memory map which are only accessible from the PCIe Physical Function. They are not accessible from the Virtual Functions. Moreover, attempting to access these registers crashes the kernel: $ echo 1 > /sys/bus/pci/devices/0000\:00\:00.0/sriov_numvfs pci 0000:00:01.0: [1957:ef00] type 00 class 0x020001 fsl_enetc_vf 0000:00:01.0: Adding to iommu group 15 fsl_enetc_vf 0000:00:01.0: enabling device (0000 -> 0002) fsl_enetc_vf 0000:00:01.0 eno0vf0: renamed from eth0 $ tc qdisc replace dev eno0vf0 root taprio num_tc 8 map 0 1 2 3 4 5 6 7 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 \ sched-entry S 0x7f 900000 sched-entry S 0x80 100000 flags 0x2 Unable to handle kernel paging request at virtual address ffff800009551a08 Internal error: Oops: 96000007 [#1] PREEMPT SMP pc : enetc_setup_tc_taprio+0x170/0x47c lr : enetc_setup_tc_taprio+0x16c/0x47c Call trace: enetc_setup_tc_taprio+0x170/0x47c enetc_setup_tc+0x38/0x2dc taprio_change+0x43c/0x970 taprio_init+0x188/0x1e0 qdisc_create+0x114/0x470 tc_modify_qdisc+0x1fc/0x6c0 rtnetlink_rcv_msg+0x12c/0x390 Split enetc_setup_tc() into separate functions for the PF and for the VF drivers. Also remove enetc_qos.o from being included into enetc-vf.ko, since it serves absolutely no purpose there.
CVE-2022-48646: In the Linux kernel, the following vulnerability has been resolved: sfc/siena: fix null pointer dereference in efx_hard_start_xmit Like in previous patch for sfc, prevent potential (but unlikely) NULL pointer dereference.
CVE-2022-48673: In the Linux kernel, the following vulnerability has been resolved: net/smc: Fix possible access to freed memory in link clear After modifying the QP to the Error state, all RX WR would be completed with WC in IB_WC_WR_FLUSH_ERR status. Current implementation does not wait for it is done, but destroy the QP and free the link group directly. So there is a risk that accessing the freed memory in tasklet context. Here is a crash example: BUG: unable to handle page fault for address: ffffffff8f220860 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD f7300e067 P4D f7300e067 PUD f7300f063 PMD 8c4e45063 PTE 800ffff08c9df060 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: G S OE 5.10.0-0607+ #23 Hardware name: Inspur NF5280M4/YZMB-00689-101, BIOS 4.1.20 07/09/2018 RIP: 0010:native_queued_spin_lock_slowpath+0x176/0x1b0 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb d5 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 00 c8 02 00 48 03 04 f5 00 09 98 8e <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32 RSP: 0018:ffffb3b6c001ebd8 EFLAGS: 00010086 RAX: ffffffff8f220860 RBX: 0000000000000246 RCX: 0000000000080000 RDX: ffff91db1f86c800 RSI: 000000000000173c RDI: ffff91db62bace00 RBP: ffff91db62bacc00 R08: 0000000000000000 R09: c00000010000028b R10: 0000000000055198 R11: ffffb3b6c001ea58 R12: ffff91db80e05010 R13: 000000000000000a R14: 0000000000000006 R15: 0000000000000040 FS: 0000000000000000(0000) GS:ffff91db1f840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8f220860 CR3: 00000001f9580004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> _raw_spin_lock_irqsave+0x30/0x40 mlx5_ib_poll_cq+0x4c/0xc50 [mlx5_ib] smc_wr_rx_tasklet_fn+0x56/0xa0 [smc] tasklet_action_common.isra.21+0x66/0x100 __do_softirq+0xd5/0x29c asm_call_irq_on_stack+0x12/0x20 </IRQ> do_softirq_own_stack+0x37/0x40 irq_exit_rcu+0x9d/0xa0 sysvec_call_function_single+0x34/0x80 asm_sysvec_call_function_single+0x12/0x20
CVE-2022-48674: In the Linux kernel, the following vulnerability has been resolved: erofs: fix pcluster use-after-free on UP platforms During stress testing with CONFIG_SMP disabled, KASAN reports as below: ================================================================== BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30 Read of size 8 at addr ffff8881094223f8 by task stress/7789 CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Call Trace: <TASK> .. __mutex_lock+0xe5/0xc30 .. z_erofs_do_read_page+0x8ce/0x1560 .. z_erofs_readahead+0x31c/0x580 .. Freed by task 7787 kasan_save_stack+0x1e/0x40 kasan_set_track+0x20/0x30 kasan_set_free_info+0x20/0x40 __kasan_slab_free+0x10c/0x190 kmem_cache_free+0xed/0x380 rcu_core+0x3d5/0xc90 __do_softirq+0x12d/0x389 Last potentially related work creation: kasan_save_stack+0x1e/0x40 __kasan_record_aux_stack+0x97/0xb0 call_rcu+0x3d/0x3f0 erofs_shrink_workstation+0x11f/0x210 erofs_shrink_scan+0xdc/0x170 shrink_slab.constprop.0+0x296/0x530 drop_slab+0x1c/0x70 drop_caches_sysctl_handler+0x70/0x80 proc_sys_call_handler+0x20a/0x2f0 vfs_write+0x555/0x6c0 ksys_write+0xbe/0x160 do_syscall_64+0x3b/0x90 The root cause is that erofs_workgroup_unfreeze() doesn't reset to orig_val thus it causes a race that the pcluster reuses unexpectedly before freeing. Since UP platforms are quite rare now, such path becomes unnecessary. Let's drop such specific-designed path directly instead.
CVE-2022-48703: In the Linux kernel, the following vulnerability has been resolved: thermal/int340x_thermal: handle data_vault when the value is ZERO_SIZE_PTR In some case, the GDDV returns a package with a buffer which has zero length. It causes that kmemdup() returns ZERO_SIZE_PTR (0x10). Then the data_vault_read() got NULL point dereference problem when accessing the 0x10 value in data_vault. [ 71.024560] BUG: kernel NULL pointer dereference, address: 0000000000000010 This patch uses ZERO_OR_NULL_PTR() for checking ZERO_SIZE_PTR or NULL value in data_vault.
CVE-2022-48721: In the Linux kernel, the following vulnerability has been resolved: net/smc: Forward wakeup to smc socket waitqueue after fallback When we replace TCP with SMC and a fallback occurs, there may be some socket waitqueue entries remaining in smc socket->wq, such as eppoll_entries inserted by userspace applications. After the fallback, data flows over TCP/IP and only clcsocket->wq will be woken up. Applications can't be notified by the entries which were inserted in smc socket->wq before fallback. So we need a mechanism to wake up smc socket->wq at the same time if some entries remaining in it. The current workaround is to transfer the entries from smc socket->wq to clcsock->wq during the fallback. But this may cause a crash like this: general protection fault, probably for non-canonical address 0xdead000000000100: 0000 [#1] PREEMPT SMP PTI CPU: 3 PID: 0 Comm: swapper/3 Kdump: loaded Tainted: G E 5.16.0+ #107 RIP: 0010:__wake_up_common+0x65/0x170 Call Trace: <IRQ> __wake_up_common_lock+0x7a/0xc0 sock_def_readable+0x3c/0x70 tcp_data_queue+0x4a7/0xc40 tcp_rcv_established+0x32f/0x660 ? sk_filter_trim_cap+0xcb/0x2e0 tcp_v4_do_rcv+0x10b/0x260 tcp_v4_rcv+0xd2a/0xde0 ip_protocol_deliver_rcu+0x3b/0x1d0 ip_local_deliver_finish+0x54/0x60 ip_local_deliver+0x6a/0x110 ? tcp_v4_early_demux+0xa2/0x140 ? tcp_v4_early_demux+0x10d/0x140 ip_sublist_rcv_finish+0x49/0x60 ip_sublist_rcv+0x19d/0x230 ip_list_rcv+0x13e/0x170 __netif_receive_skb_list_core+0x1c2/0x240 netif_receive_skb_list_internal+0x1e6/0x320 napi_complete_done+0x11d/0x190 mlx5e_napi_poll+0x163/0x6b0 [mlx5_core] __napi_poll+0x3c/0x1b0 net_rx_action+0x27c/0x300 __do_softirq+0x114/0x2d2 irq_exit_rcu+0xb4/0xe0 common_interrupt+0xba/0xe0 </IRQ> <TASK> The crash is caused by privately transferring waitqueue entries from smc socket->wq to clcsock->wq. The owners of these entries, such as epoll, have no idea that the entries have been transferred to a different socket wait queue and still use original waitqueue spinlock (smc socket->wq.wait.lock) to make the entries operation exclusive, but it doesn't work. The operations to the entries, such as removing from the waitqueue (now is clcsock->wq after fallback), may cause a crash when clcsock waitqueue is being iterated over at the moment. This patch tries to fix this by no longer transferring wait queue entries privately, but introducing own implementations of clcsock's callback functions in fallback situation. The callback functions will forward the wakeup to smc socket->wq if clcsock->wq is actually woken up and smc socket->wq has remaining entries.
CVE-2022-48751: In the Linux kernel, the following vulnerability has been resolved: net/smc: Transitional solution for clcsock race issue We encountered a crash in smc_setsockopt() and it is caused by accessing smc->clcsock after clcsock was released. BUG: kernel NULL pointer dereference, address: 0000000000000020 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 50309 Comm: nginx Kdump: loaded Tainted: G E 5.16.0-rc4+ #53 RIP: 0010:smc_setsockopt+0x59/0x280 [smc] Call Trace: <TASK> __sys_setsockopt+0xfc/0x190 __x64_sys_setsockopt+0x20/0x30 do_syscall_64+0x34/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f16ba83918e </TASK> This patch tries to fix it by holding clcsock_release_lock and checking whether clcsock has already been released before access. In case that a crash of the same reason happens in smc_getsockopt() or smc_switch_to_fallback(), this patch also checkes smc->clcsock in them too. And the caller of smc_switch_to_fallback() will identify whether fallback succeeds according to the return value.
CVE-2022-48765: In the Linux kernel, the following vulnerability has been resolved: KVM: LAPIC: Also cancel preemption timer during SET_LAPIC The below warning is splatting during guest reboot. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1931 at arch/x86/kvm/x86.c:10322 kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm] CPU: 0 PID: 1931 Comm: qemu-system-x86 Tainted: G I 5.17.0-rc1+ #5 RIP: 0010:kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm] Call Trace: <TASK> kvm_vcpu_ioctl+0x279/0x710 [kvm] __x64_sys_ioctl+0x83/0xb0 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7fd39797350b This can be triggered by not exposing tsc-deadline mode and doing a reboot in the guest. The lapic_shutdown() function which is called in sys_reboot path will not disarm the flying timer, it just masks LVTT. lapic_shutdown() clears APIC state w/ LVT_MASKED and timer-mode bit is 0, this can trigger timer-mode switch between tsc-deadline and oneshot/periodic, which can result in preemption timer be cancelled in apic_update_lvtt(). However, We can't depend on this when not exposing tsc-deadline mode and oneshot/periodic modes emulated by preemption timer. Qemu will synchronise states around reset, let's cancel preemption timer under KVM_SET_LAPIC.
CVE-2022-48811: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: don't release napi in __ibmvnic_open() If __ibmvnic_open() encounters an error such as when setting link state, it calls release_resources() which frees the napi structures needlessly. Instead, have __ibmvnic_open() only clean up the work it did so far (i.e. disable napi and irqs) and leave the rest to the callers. If caller of __ibmvnic_open() is ibmvnic_open(), it should release the resources immediately. If the caller is do_reset() or do_hard_reset(), they will release the resources on the next reset. This fixes following crash that occurred when running the drmgr command several times to add/remove a vnic interface: [102056] ibmvnic 30000003 env3: Disabling rx_scrq[6] irq [102056] ibmvnic 30000003 env3: Disabling rx_scrq[7] irq [102056] ibmvnic 30000003 env3: Replenished 8 pools Kernel attempted to read user page (10) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000010 Faulting instruction address: 0xc000000000a3c840 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries ... CPU: 9 PID: 102056 Comm: kworker/9:2 Kdump: loaded Not tainted 5.16.0-rc5-autotest-g6441998e2e37 #1 Workqueue: events_long __ibmvnic_reset [ibmvnic] NIP: c000000000a3c840 LR: c0080000029b5378 CTR: c000000000a3c820 REGS: c0000000548e37e0 TRAP: 0300 Not tainted (5.16.0-rc5-autotest-g6441998e2e37) MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 28248484 XER: 00000004 CFAR: c0080000029bdd24 DAR: 0000000000000010 DSISR: 40000000 IRQMASK: 0 GPR00: c0080000029b55d0 c0000000548e3a80 c0000000028f0200 0000000000000000 ... NIP [c000000000a3c840] napi_enable+0x20/0xc0 LR [c0080000029b5378] __ibmvnic_open+0xf0/0x430 [ibmvnic] Call Trace: [c0000000548e3a80] [0000000000000006] 0x6 (unreliable) [c0000000548e3ab0] [c0080000029b55d0] __ibmvnic_open+0x348/0x430 [ibmvnic] [c0000000548e3b40] [c0080000029bcc28] __ibmvnic_reset+0x500/0xdf0 [ibmvnic] [c0000000548e3c60] [c000000000176228] process_one_work+0x288/0x570 [c0000000548e3d00] [c000000000176588] worker_thread+0x78/0x660 [c0000000548e3da0] [c0000000001822f0] kthread+0x1c0/0x1d0 [c0000000548e3e10] [c00000000000cf64] ret_from_kernel_thread+0x5c/0x64 Instruction dump: 7d2948f8 792307e0 4e800020 60000000 3c4c01eb 384239e0 f821ffd1 39430010 38a0fff6 e92d1100 f9210028 39200000 <e9030010> f9010020 60420000 e9210020 ---[ end trace 5f8033b08fd27706 ]---
CVE-2022-48814: In the Linux kernel, the following vulnerability has been resolved: net: dsa: seville: register the mdiobus under devres As explained in commits: 74b6d7d13307 ("net: dsa: realtek: register the MDIO bus under devres") 5135e96a3dd2 ("net: dsa: don't allocate the slave_mii_bus using devres") mdiobus_free() will panic when called from devm_mdiobus_free() <- devres_release_all() <- __device_release_driver(), and that mdiobus was not previously unregistered. The Seville VSC9959 switch is a platform device, so the initial set of constraints that I thought would cause this (I2C or SPI buses which call ->remove on ->shutdown) do not apply. But there is one more which applies here. If the DSA master itself is on a bus that calls ->remove from ->shutdown (like dpaa2-eth, which is on the fsl-mc bus), there is a device link between the switch and the DSA master, and device_links_unbind_consumers() will unbind the seville switch driver on shutdown. So the same treatment must be applied to all DSA switch drivers, which is: either use devres for both the mdiobus allocation and registration, or don't use devres at all. The seville driver has a code structure that could accommodate both the mdiobus_unregister and mdiobus_free calls, but it has an external dependency upon mscc_miim_setup() from mdio-mscc-miim.c, which calls devm_mdiobus_alloc_size() on its behalf. So rather than restructuring that, and exporting yet one more symbol mscc_miim_teardown(), let's work with devres and replace of_mdiobus_register with the devres variant. When we use all-devres, we can ensure that devres doesn't free a still-registered bus (it either runs both callbacks, or none).
CVE-2022-48816: In the Linux kernel, the following vulnerability has been resolved: SUNRPC: lock against ->sock changing during sysfs read ->sock can be set to NULL asynchronously unless ->recv_mutex is held. So it is important to hold that mutex. Otherwise a sysfs read can trigger an oops. Commit 17f09d3f619a ("SUNRPC: Check if the xprt is connected before handling sysfs reads") appears to attempt to fix this problem, but it only narrows the race window.
CVE-2022-48833: In the Linux kernel, the following vulnerability has been resolved: btrfs: skip reserved bytes warning on unmount after log cleanup failure After the recent changes made by commit c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") and its followup fix, commit 651740a5024117 ("btrfs: check WRITE_ERR when trying to read an extent buffer"), we can now end up not cleaning up space reservations of log tree extent buffers after a transaction abort happens, as well as not cleaning up still dirty extent buffers. This happens because if writeback for a log tree extent buffer failed, then we have cleared the bit EXTENT_BUFFER_UPTODATE from the extent buffer and we have also set the bit EXTENT_BUFFER_WRITE_ERR on it. Later on, when trying to free the log tree with free_log_tree(), which iterates over the tree, we can end up getting an -EIO error when trying to read a node or a leaf, since read_extent_buffer_pages() returns -EIO if an extent buffer does not have EXTENT_BUFFER_UPTODATE set and has the EXTENT_BUFFER_WRITE_ERR bit set. Getting that -EIO means that we return immediately as we can not iterate over the entire tree. In that case we never update the reserved space for an extent buffer in the respective block group and space_info object. When this happens we get the following traces when unmounting the fs: [174957.284509] BTRFS: error (device dm-0) in cleanup_transaction:1913: errno=-5 IO failure [174957.286497] BTRFS: error (device dm-0) in free_log_tree:3420: errno=-5 IO failure [174957.399379] ------------[ cut here ]------------ [174957.402497] WARNING: CPU: 2 PID: 3206883 at fs/btrfs/block-group.c:127 btrfs_put_block_group+0x77/0xb0 [btrfs] [174957.407523] Modules linked in: btrfs overlay dm_zero (...) [174957.424917] CPU: 2 PID: 3206883 Comm: umount Tainted: G W 5.16.0-rc5-btrfs-next-109 #1 [174957.426689] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [174957.428716] RIP: 0010:btrfs_put_block_group+0x77/0xb0 [btrfs] [174957.429717] Code: 21 48 8b bd (...) [174957.432867] RSP: 0018:ffffb70d41cffdd0 EFLAGS: 00010206 [174957.433632] RAX: 0000000000000001 RBX: ffff8b09c3848000 RCX: ffff8b0758edd1c8 [174957.434689] RDX: 0000000000000001 RSI: ffffffffc0b467e7 RDI: ffff8b0758edd000 [174957.436068] RBP: ffff8b0758edd000 R08: 0000000000000000 R09: 0000000000000000 [174957.437114] R10: 0000000000000246 R11: 0000000000000000 R12: ffff8b09c3848148 [174957.438140] R13: ffff8b09c3848198 R14: ffff8b0758edd188 R15: dead000000000100 [174957.439317] FS: 00007f328fb82800(0000) GS:ffff8b0a2d200000(0000) knlGS:0000000000000000 [174957.440402] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [174957.441164] CR2: 00007fff13563e98 CR3: 0000000404f4e005 CR4: 0000000000370ee0 [174957.442117] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [174957.443076] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [174957.443948] Call Trace: [174957.444264] <TASK> [174957.444538] btrfs_free_block_groups+0x255/0x3c0 [btrfs] [174957.445238] close_ctree+0x301/0x357 [btrfs] [174957.445803] ? call_rcu+0x16c/0x290 [174957.446250] generic_shutdown_super+0x74/0x120 [174957.446832] kill_anon_super+0x14/0x30 [174957.447305] btrfs_kill_super+0x12/0x20 [btrfs] [174957.447890] deactivate_locked_super+0x31/0xa0 [174957.448440] cleanup_mnt+0x147/0x1c0 [174957.448888] task_work_run+0x5c/0xa0 [174957.449336] exit_to_user_mode_prepare+0x1e5/0x1f0 [174957.449934] syscall_exit_to_user_mode+0x16/0x40 [174957.450512] do_syscall_64+0x48/0xc0 [174957.450980] entry_SYSCALL_64_after_hwframe+0x44/0xae [174957.451605] RIP: 0033:0x7f328fdc4a97 [174957.452059] Code: 03 0c 00 f7 (...) [174957.454320] RSP: 002b:00007fff13564ec8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [174957.455262] RAX: 0000000000000000 RBX: 00007f328feea264 RCX: 00007f328fdc4a97 [174957.456131] RDX: 0000000000000000 RSI: 00000000000000 ---truncated---
CVE-2022-48859: In the Linux kernel, the following vulnerability has been resolved: net: marvell: prestera: Add missing of_node_put() in prestera_switch_set_base_mac_addr This node pointer is returned by of_find_compatible_node() with refcount incremented. Calling of_node_put() to aovid the refcount leak.
CVE-2022-48862: In the Linux kernel, the following vulnerability has been resolved: vhost: fix hung thread due to erroneous iotlb entries In vhost_iotlb_add_range_ctx(), range size can overflow to 0 when start is 0 and last is ULONG_MAX. One instance where it can happen is when userspace sends an IOTLB message with iova=size=uaddr=0 (vhost_process_iotlb_msg). So, an entry with size = 0, start = 0, last = ULONG_MAX ends up in the iotlb. Next time a packet is sent, iotlb_access_ok() loops indefinitely due to that erroneous entry. Call Trace: <TASK> iotlb_access_ok+0x21b/0x3e0 drivers/vhost/vhost.c:1340 vq_meta_prefetch+0xbc/0x280 drivers/vhost/vhost.c:1366 vhost_transport_do_send_pkt+0xe0/0xfd0 drivers/vhost/vsock.c:104 vhost_worker+0x23d/0x3d0 drivers/vhost/vhost.c:372 kthread+0x2e9/0x3a0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 </TASK> Reported by syzbot at: https://syzkaller.appspot.com/bug?extid=0abd373e2e50d704db87 To fix this, do two things: 1. Return -EINVAL in vhost_chr_write_iter() when userspace asks to map a range with size 0. 2. Fix vhost_iotlb_add_range_ctx() to handle the range [0, ULONG_MAX] by splitting it into two entries.
CVE-2022-48887: In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Remove rcu locks from user resources User resource lookups used rcu to avoid two extra atomics. Unfortunately the rcu paths were buggy and it was easy to make the driver crash by submitting command buffers from two different threads. Because the lookups never show up in performance profiles replace them with a regular spin lock which fixes the races in accesses to those shared resources. Fixes kernel oops'es in IGT's vmwgfx execution_buffer stress test and seen crashes with apps using shared resources.
CVE-2022-48901: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not start relocation until in progress drops are done We hit a bug with a recovering relocation on mount for one of our file systems in production. I reproduced this locally by injecting errors into snapshot delete with balance running at the same time. This presented as an error while looking up an extent item WARNING: CPU: 5 PID: 1501 at fs/btrfs/extent-tree.c:866 lookup_inline_extent_backref+0x647/0x680 CPU: 5 PID: 1501 Comm: btrfs-balance Not tainted 5.16.0-rc8+ #8 RIP: 0010:lookup_inline_extent_backref+0x647/0x680 RSP: 0018:ffffae0a023ab960 EFLAGS: 00010202 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 000000000000000c RDI: 0000000000000000 RBP: ffff943fd2a39b60 R08: 0000000000000000 R09: 0000000000000001 R10: 0001434088152de0 R11: 0000000000000000 R12: 0000000001d05000 R13: ffff943fd2a39b60 R14: ffff943fdb96f2a0 R15: ffff9442fc923000 FS: 0000000000000000(0000) GS:ffff944e9eb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1157b1fca8 CR3: 000000010f092000 CR4: 0000000000350ee0 Call Trace: <TASK> insert_inline_extent_backref+0x46/0xd0 __btrfs_inc_extent_ref.isra.0+0x5f/0x200 ? btrfs_merge_delayed_refs+0x164/0x190 __btrfs_run_delayed_refs+0x561/0xfa0 ? btrfs_search_slot+0x7b4/0xb30 ? btrfs_update_root+0x1a9/0x2c0 btrfs_run_delayed_refs+0x73/0x1f0 ? btrfs_update_root+0x1a9/0x2c0 btrfs_commit_transaction+0x50/0xa50 ? btrfs_update_reloc_root+0x122/0x220 prepare_to_merge+0x29f/0x320 relocate_block_group+0x2b8/0x550 btrfs_relocate_block_group+0x1a6/0x350 btrfs_relocate_chunk+0x27/0xe0 btrfs_balance+0x777/0xe60 balance_kthread+0x35/0x50 ? btrfs_balance+0xe60/0xe60 kthread+0x16b/0x190 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x22/0x30 </TASK> Normally snapshot deletion and relocation are excluded from running at the same time by the fs_info->cleaner_mutex. However if we had a pending balance waiting to get the ->cleaner_mutex, and a snapshot deletion was running, and then the box crashed, we would come up in a state where we have a half deleted snapshot. Again, in the normal case the snapshot deletion needs to complete before relocation can start, but in this case relocation could very well start before the snapshot deletion completes, as we simply add the root to the dead roots list and wait for the next time the cleaner runs to clean up the snapshot. Fix this by setting a bit on the fs_info if we have any DEAD_ROOT's that had a pending drop_progress key. If they do then we know we were in the middle of the drop operation and set a flag on the fs_info. Then balance can wait until this flag is cleared to start up again. If there are DEAD_ROOT's that don't have a drop_progress set then we're safe to start balance right away as we'll be properly protected by the cleaner_mutex.
CVE-2022-48902: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not WARN_ON() if we have PageError set Whenever we do any extent buffer operations we call assert_eb_page_uptodate() to complain loudly if we're operating on an non-uptodate page. Our overnight tests caught this warning earlier this week WARNING: CPU: 1 PID: 553508 at fs/btrfs/extent_io.c:6849 assert_eb_page_uptodate+0x3f/0x50 CPU: 1 PID: 553508 Comm: kworker/u4:13 Tainted: G W 5.17.0-rc3+ #564 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Workqueue: btrfs-cache btrfs_work_helper RIP: 0010:assert_eb_page_uptodate+0x3f/0x50 RSP: 0018:ffffa961440a7c68 EFLAGS: 00010246 RAX: 0017ffffc0002112 RBX: ffffe6e74453f9c0 RCX: 0000000000001000 RDX: ffffe6e74467c887 RSI: ffffe6e74453f9c0 RDI: ffff8d4c5efc2fc0 RBP: 0000000000000d56 R08: ffff8d4d4a224000 R09: 0000000000000000 R10: 00015817fa9d1ef0 R11: 000000000000000c R12: 00000000000007b1 R13: ffff8d4c5efc2fc0 R14: 0000000001500000 R15: 0000000001cb1000 FS: 0000000000000000(0000) GS:ffff8d4dbbd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ff31d3448d8 CR3: 0000000118be8004 CR4: 0000000000370ee0 Call Trace: extent_buffer_test_bit+0x3f/0x70 free_space_test_bit+0xa6/0xc0 load_free_space_tree+0x1f6/0x470 caching_thread+0x454/0x630 ? rcu_read_lock_sched_held+0x12/0x60 ? rcu_read_lock_sched_held+0x12/0x60 ? rcu_read_lock_sched_held+0x12/0x60 ? lock_release+0x1f0/0x2d0 btrfs_work_helper+0xf2/0x3e0 ? lock_release+0x1f0/0x2d0 ? finish_task_switch.isra.0+0xf9/0x3a0 process_one_work+0x26d/0x580 ? process_one_work+0x580/0x580 worker_thread+0x55/0x3b0 ? process_one_work+0x580/0x580 kthread+0xf0/0x120 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 This was partially fixed by c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it"), however all that fix did was keep us from finding extent buffers after a failed writeout. It didn't keep us from continuing to use a buffer that we already had found. In this case we're searching the commit root to cache the block group, so we can start committing the transaction and switch the commit root and then start writing. After the switch we can look up an extent buffer that hasn't been written yet and start processing that block group. Then we fail to write that block out and clear Uptodate on the page, and then we start spewing these errors. Normally we're protected by the tree lock to a certain degree here. If we read a block we have that block read locked, and we block the writer from locking the block before we submit it for the write. However this isn't necessarily fool proof because the read could happen before we do the submit_bio and after we locked and unlocked the extent buffer. Also in this particular case we have path->skip_locking set, so that won't save us here. We'll simply get a block that was valid when we read it, but became invalid while we were using it. What we really want is to catch the case where we've "read" a block but it's not marked Uptodate. On read we ClearPageError(), so if we're !Uptodate and !Error we know we didn't do the right thing for reading the page. Fix this by checking !Uptodate && !Error, this way we will not complain if our buffer gets invalidated while we're using it, and we'll maintain the spirit of the check which is to make sure we have a fully in-cache block while we're messing with it.
CVE-2022-48920: In the Linux kernel, the following vulnerability has been resolved: btrfs: get rid of warning on transaction commit when using flushoncommit When using the flushoncommit mount option, during almost every transaction commit we trigger a warning from __writeback_inodes_sb_nr(): $ cat fs/fs-writeback.c: (...) static void __writeback_inodes_sb_nr(struct super_block *sb, ... { (...) WARN_ON(!rwsem_is_locked(&sb->s_umount)); (...) } (...) The trace produced in dmesg looks like the following: [947.473890] WARNING: CPU: 5 PID: 930 at fs/fs-writeback.c:2610 __writeback_inodes_sb_nr+0x7e/0xb3 [947.481623] Modules linked in: nfsd nls_cp437 cifs asn1_decoder cifs_arc4 fscache cifs_md4 ipmi_ssif [947.489571] CPU: 5 PID: 930 Comm: btrfs-transacti Not tainted 95.16.3-srb-asrock-00001-g36437ad63879 #186 [947.497969] RIP: 0010:__writeback_inodes_sb_nr+0x7e/0xb3 [947.502097] Code: 24 10 4c 89 44 24 18 c6 (...) [947.519760] RSP: 0018:ffffc90000777e10 EFLAGS: 00010246 [947.523818] RAX: 0000000000000000 RBX: 0000000000963300 RCX: 0000000000000000 [947.529765] RDX: 0000000000000000 RSI: 000000000000fa51 RDI: ffffc90000777e50 [947.535740] RBP: ffff888101628a90 R08: ffff888100955800 R09: ffff888100956000 [947.541701] R10: 0000000000000002 R11: 0000000000000001 R12: ffff888100963488 [947.547645] R13: ffff888100963000 R14: ffff888112fb7200 R15: ffff888100963460 [947.553621] FS: 0000000000000000(0000) GS:ffff88841fd40000(0000) knlGS:0000000000000000 [947.560537] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [947.565122] CR2: 0000000008be50c4 CR3: 000000000220c000 CR4: 00000000001006e0 [947.571072] Call Trace: [947.572354] <TASK> [947.573266] btrfs_commit_transaction+0x1f1/0x998 [947.576785] ? start_transaction+0x3ab/0x44e [947.579867] ? schedule_timeout+0x8a/0xdd [947.582716] transaction_kthread+0xe9/0x156 [947.585721] ? btrfs_cleanup_transaction.isra.0+0x407/0x407 [947.590104] kthread+0x131/0x139 [947.592168] ? set_kthread_struct+0x32/0x32 [947.595174] ret_from_fork+0x22/0x30 [947.597561] </TASK> [947.598553] ---[ end trace 644721052755541c ]--- This is because we started using writeback_inodes_sb() to flush delalloc when committing a transaction (when using -o flushoncommit), in order to avoid deadlocks with filesystem freeze operations. This change was made by commit ce8ea7cc6eb313 ("btrfs: don't call btrfs_start_delalloc_roots in flushoncommit"). After that change we started producing that warning, and every now and then a user reports this since the warning happens too often, it spams dmesg/syslog, and a user is unsure if this reflects any problem that might compromise the filesystem's reliability. We can not just lock the sb->s_umount semaphore before calling writeback_inodes_sb(), because that would at least deadlock with filesystem freezing, since at fs/super.c:freeze_super() sync_filesystem() is called while we are holding that semaphore in write mode, and that can trigger a transaction commit, resulting in a deadlock. It would also trigger the same type of deadlock in the unmount path. Possibly, it could also introduce some other locking dependencies that lockdep would report. To fix this call try_to_writeback_inodes_sb() instead of writeback_inodes_sb(), because that will try to read lock sb->s_umount and then will only call writeback_inodes_sb() if it was able to lock it. This is fine because the cases where it can't read lock sb->s_umount are during a filesystem unmount or during a filesystem freeze - in those cases sb->s_umount is write locked and sync_filesystem() is called, which calls writeback_inodes_sb(). In other words, in all cases where we can't take a read lock on sb->s_umount, writeback is already being triggered elsewhere. An alternative would be to call btrfs_start_delalloc_roots() with a number of pages different from LONG_MAX, for example matching the number of delalloc bytes we currently have, in ---truncated---
CVE-2022-48944: In the Linux kernel, the following vulnerability has been resolved: sched: Fix yet more sched_fork() races Where commit 4ef0c5c6b5ba ("kernel/sched: Fix sched_fork() access an invalid sched_task_group") fixed a fork race vs cgroup, it opened up a race vs syscalls by not placing the task on the runqueue before it gets exposed through the pidhash. Commit 13765de8148f ("sched/fair: Fix fault in reweight_entity") is trying to fix a single instance of this, instead fix the whole class of issues, effectively reverting this commit.
CVE-2022-48952: In the Linux kernel, the following vulnerability has been resolved: PCI: mt7621: Add sentinel to quirks table Current driver is missing a sentinel in the struct soc_device_attribute array, which causes an oops when assessed by the soc_device_match(mt7621_pcie_quirks_match) call. This was only exposed once the CONFIG_SOC_MT7621 mt7621 soc_dev_attr was fixed to register the SOC as a device, in: commit 7c18b64bba3b ("mips: ralink: mt7621: do not use kzalloc too early") Fix it by adding the required sentinel.
CVE-2022-48961: In the Linux kernel, the following vulnerability has been resolved: net: mdio: fix unbalanced fwnode reference count in mdio_device_release() There is warning report about of_node refcount leak while probing mdio device: OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /spi/soc@0/mdio@710700c0/ethernet@4 In of_mdiobus_register_device(), we increase fwnode refcount by fwnode_handle_get() before associating the of_node with mdio device, but it has never been decreased in normal path. Since that, in mdio_device_release(), it needs to call fwnode_handle_put() in addition instead of calling kfree() directly. After above, just calling mdio_device_free() in the error handle path of of_mdiobus_register_device() is enough to keep the refcount balanced.
CVE-2022-48975: In the Linux kernel, the following vulnerability has been resolved: gpiolib: fix memory leak in gpiochip_setup_dev() Here is a backtrace report about memory leak detected in gpiochip_setup_dev(): unreferenced object 0xffff88810b406400 (size 512): comm "python3", pid 1682, jiffies 4295346908 (age 24.090s) backtrace: kmalloc_trace device_add device_private_init at drivers/base/core.c:3361 (inlined by) device_add at drivers/base/core.c:3411 cdev_device_add gpiolib_cdev_register gpiochip_setup_dev gpiochip_add_data_with_key gcdev_register() & gcdev_unregister() would call device_add() & device_del() (no matter CONFIG_GPIO_CDEV is enabled or not) to register/unregister device. However, if device_add() succeeds, some resource (like struct device_private allocated by device_private_init()) is not released by device_del(). Therefore, after device_add() succeeds by gcdev_register(), it needs to call put_device() to release resource in the error handle path. Here we move forward the register of release function, and let it release every piece of resource by put_device() instead of kfree(). While at it, fix another subtle issue, i.e. when gc->ngpio is equal to 0, we still call kcalloc() and, in case of further error, kfree() on the ZERO_PTR pointer, which is not NULL. It's not a bug per se, but rather waste of the resources and potentially wrong expectation about contents of the gdev->descs variable.
CVE-2022-48979: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix array index out of bound error in DCN32 DML [Why&How] LinkCapacitySupport array is indexed with the number of voltage states and not the number of max DPPs. Fix the error by changing the array declaration to use the correct (larger) array size of total number of voltage states.
CVE-2022-49004: In the Linux kernel, the following vulnerability has been resolved: riscv: Sync efi page table's kernel mappings before switching The EFI page table is initially created as a copy of the kernel page table. With VMAP_STACK enabled, kernel stacks are allocated in the vmalloc area: if the stack is allocated in a new PGD (one that was not present at the moment of the efi page table creation or not synced in a previous vmalloc fault), the kernel will take a trap when switching to the efi page table when the vmalloc kernel stack is accessed, resulting in a kernel panic. Fix that by updating the efi kernel mappings before switching to the efi page table.
CVE-2022-49069: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix by adding FPU protection for dcn30_internal_validate_bw [Why] Below general protection fault observed when WebGL Aquarium is run for longer duration. If drm debug logs are enabled and set to 0x1f then the issue is observed within 10 minutes of run. [ 100.717056] general protection fault, probably for non-canonical address 0x2d33302d32323032: 0000 [#1] PREEMPT SMP NOPTI [ 100.727921] CPU: 3 PID: 1906 Comm: DrmThread Tainted: G W 5.15.30 #12 d726c6a2d6ebe5cf9223931cbca6892f916fe18b [ 100.754419] RIP: 0010:CalculateSwathWidth+0x1f7/0x44f [ 100.767109] Code: 00 00 00 f2 42 0f 11 04 f0 48 8b 85 88 00 00 00 f2 42 0f 10 04 f0 48 8b 85 98 00 00 00 f2 42 0f 11 04 f0 48 8b 45 10 0f 57 c0 <f3> 42 0f 2a 04 b0 0f 57 c9 f3 43 0f 2a 0c b4 e8 8c e2 f3 ff 48 8b [ 100.781269] RSP: 0018:ffffa9230079eeb0 EFLAGS: 00010246 [ 100.812528] RAX: 2d33302d32323032 RBX: 0000000000000500 RCX: 0000000000000000 [ 100.819656] RDX: 0000000000000001 RSI: ffff99deb712c49c RDI: 0000000000000000 [ 100.826781] RBP: ffffa9230079ef50 R08: ffff99deb712460c R09: ffff99deb712462c [ 100.833907] R10: ffff99deb7124940 R11: ffff99deb7124d70 R12: ffff99deb712ae44 [ 100.841033] R13: 0000000000000001 R14: 0000000000000000 R15: ffffa9230079f0a0 [ 100.848159] FS: 00007af121212640(0000) GS:ffff99deba780000(0000) knlGS:0000000000000000 [ 100.856240] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 100.861980] CR2: 0000209000fe1000 CR3: 000000011b18c000 CR4: 0000000000350ee0 [ 100.869106] Call Trace: [ 100.871555] <TASK> [ 100.873655] ? asm_sysvec_reschedule_ipi+0x12/0x20 [ 100.878449] CalculateSwathAndDETConfiguration+0x1a3/0x6dd [ 100.883937] dml31_ModeSupportAndSystemConfigurationFull+0x2ce4/0x76da [ 100.890467] ? kallsyms_lookup_buildid+0xc8/0x163 [ 100.895173] ? kallsyms_lookup_buildid+0xc8/0x163 [ 100.899874] ? __sprint_symbol+0x80/0x135 [ 100.903883] ? dm_update_plane_state+0x3f9/0x4d2 [ 100.908500] ? symbol_string+0xb7/0xde [ 100.912250] ? number+0x145/0x29b [ 100.915566] ? vsnprintf+0x341/0x5ff [ 100.919141] ? desc_read_finalized_seq+0x39/0x87 [ 100.923755] ? update_load_avg+0x1b9/0x607 [ 100.927849] ? compute_mst_dsc_configs_for_state+0x7d/0xd5b [ 100.933416] ? fetch_pipe_params+0xa4d/0xd0c [ 100.937686] ? dc_fpu_end+0x3d/0xa8 [ 100.941175] dml_get_voltage_level+0x16b/0x180 [ 100.945619] dcn30_internal_validate_bw+0x10e/0x89b [ 100.950495] ? dcn31_validate_bandwidth+0x68/0x1fc [ 100.955285] ? resource_build_scaling_params+0x98b/0xb8c [ 100.960595] ? dcn31_validate_bandwidth+0x68/0x1fc [ 100.965384] dcn31_validate_bandwidth+0x9a/0x1fc [ 100.970001] dc_validate_global_state+0x238/0x295 [ 100.974703] amdgpu_dm_atomic_check+0x9c1/0xbce [ 100.979235] ? _printk+0x59/0x73 [ 100.982467] drm_atomic_check_only+0x403/0x78b [ 100.986912] drm_mode_atomic_ioctl+0x49b/0x546 [ 100.991358] ? drm_ioctl+0x1c1/0x3b3 [ 100.994936] ? drm_atomic_set_property+0x92a/0x92a [ 100.999725] drm_ioctl_kernel+0xdc/0x149 [ 101.003648] drm_ioctl+0x27f/0x3b3 [ 101.007051] ? drm_atomic_set_property+0x92a/0x92a [ 101.011842] amdgpu_drm_ioctl+0x49/0x7d [ 101.015679] __se_sys_ioctl+0x7c/0xb8 [ 101.015685] do_syscall_64+0x5f/0xb8 [ 101.015690] ? __irq_exit_rcu+0x34/0x96 [How] It calles populate_dml_pipes which uses doubles to initialize. Adding FPU protection avoids context switch and probable loss of vba context as there is potential contention while drm debug logs are enabled.
CVE-2022-49096: In the Linux kernel, the following vulnerability has been resolved: net: sfc: add missing xdp queue reinitialization After rx/tx ring buffer size is changed, kernel panic occurs when it acts XDP_TX or XDP_REDIRECT. When tx/rx ring buffer size is changed(ethtool -G), sfc driver reallocates and reinitializes rx and tx queues and their buffer (tx_queue->buffer). But it misses reinitializing xdp queues(efx->xdp_tx_queues). So, while it is acting XDP_TX or XDP_REDIRECT, it uses the uninitialized tx_queue->buffer. A new function efx_set_xdp_channels() is separated from efx_set_channels() to handle only xdp queues. Splat looks like: BUG: kernel NULL pointer dereference, address: 000000000000002a #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#4] PREEMPT SMP NOPTI RIP: 0010:efx_tx_map_chunk+0x54/0x90 [sfc] CPU: 2 PID: 0 Comm: swapper/2 Tainted: G D 5.17.0+ #55 e8beeee8289528f11357029357cf Code: 48 8b 8d a8 01 00 00 48 8d 14 52 4c 8d 2c d0 44 89 e0 48 85 c9 74 0e 44 89 e2 4c 89 f6 48 80 RSP: 0018:ffff92f121e45c60 EFLAGS: 00010297 RIP: 0010:efx_tx_map_chunk+0x54/0x90 [sfc] RAX: 0000000000000040 RBX: ffff92ea506895c0 RCX: ffffffffc0330870 RDX: 0000000000000001 RSI: 00000001139b10ce RDI: ffff92ea506895c0 RBP: ffffffffc0358a80 R08: 00000001139b110d R09: 0000000000000000 R10: 0000000000000001 R11: ffff92ea414c0088 R12: 0000000000000040 R13: 0000000000000018 R14: 00000001139b10ce R15: ffff92ea506895c0 FS: 0000000000000000(0000) GS:ffff92f121ec0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 Code: 48 8b 8d a8 01 00 00 48 8d 14 52 4c 8d 2c d0 44 89 e0 48 85 c9 74 0e 44 89 e2 4c 89 f6 48 80 CR2: 000000000000002a CR3: 00000003e6810004 CR4: 00000000007706e0 RSP: 0018:ffff92f121e85c60 EFLAGS: 00010297 PKRU: 55555554 RAX: 0000000000000040 RBX: ffff92ea50689700 RCX: ffffffffc0330870 RDX: 0000000000000001 RSI: 00000001145a90ce RDI: ffff92ea50689700 RBP: ffffffffc0358a80 R08: 00000001145a910d R09: 0000000000000000 R10: 0000000000000001 R11: ffff92ea414c0088 R12: 0000000000000040 R13: 0000000000000018 R14: 00000001145a90ce R15: ffff92ea50689700 FS: 0000000000000000(0000) GS:ffff92f121e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000002a CR3: 00000003e6810005 CR4: 00000000007706e0 PKRU: 55555554 Call Trace: <IRQ> efx_xdp_tx_buffers+0x12b/0x3d0 [sfc 84c94b8e32d44d296c17e10a634d3ad454de4ba5] __efx_rx_packet+0x5c3/0x930 [sfc 84c94b8e32d44d296c17e10a634d3ad454de4ba5] efx_rx_packet+0x28c/0x2e0 [sfc 84c94b8e32d44d296c17e10a634d3ad454de4ba5] efx_ef10_ev_process+0x5f8/0xf40 [sfc 84c94b8e32d44d296c17e10a634d3ad454de4ba5] ? enqueue_task_fair+0x95/0x550 efx_poll+0xc4/0x360 [sfc 84c94b8e32d44d296c17e10a634d3ad454de4ba5]
CVE-2022-49102: In the Linux kernel, the following vulnerability has been resolved: habanalabs: fix possible memory leak in MMU DR fini This patch fixes what seems to be copy paste error. We will have a memory leak if the host-resident shadow is NULL (which will likely happen as the DR and HR are not dependent).
CVE-2022-49106: In the Linux kernel, the following vulnerability has been resolved: staging: vchiq_arm: Avoid NULL ptr deref in vchiq_dump_platform_instances vchiq_get_state() can return a NULL pointer. So handle this cases and avoid a NULL pointer derefence in vchiq_dump_platform_instances.
CVE-2022-49109: In the Linux kernel, the following vulnerability has been resolved: ceph: fix inode reference leakage in ceph_get_snapdir() The ceph_get_inode() will search for or insert a new inode into the hash for the given vino, and return a reference to it. If new is non-NULL, its reference is consumed. We should release the reference when in error handing cases.
CVE-2022-49110: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: revisit gc autotuning as of commit 4608fdfc07e1 ("netfilter: conntrack: collect all entries in one cycle") conntrack gc was changed to run every 2 minutes. On systems where conntrack hash table is set to large value, most evictions happen from gc worker rather than the packet path due to hash table distribution. This causes netlink event overflows when events are collected. This change collects average expiry of scanned entries and reschedules to the average remaining value, within 1 to 60 second interval. To avoid event overflows, reschedule after each bucket and add a limit for both run time and number of evictions per run. If more entries have to be evicted, reschedule and restart 1 jiffy into the future.
CVE-2022-49112: In the Linux kernel, the following vulnerability has been resolved: mt76: fix monitor mode crash with sdio driver mt7921s driver may receive frames with fragment buffers. If there is a CTS packet received in monitor mode, the payload is 10 bytes only and need 6 bytes header padding after RXD buffer. However, only RXD in the first linear buffer, if we pull buffer size RXD-size+6 bytes with skb_pull(), that would trigger "BUG_ON(skb->len < skb->data_len)" in __skb_pull(). To avoid the nonlinear buffer issue, enlarge the RXD size from 128 to 256 to make sure all MCU operation in linear buffer. [ 52.007562] kernel BUG at include/linux/skbuff.h:2313! [ 52.007578] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [ 52.007987] pc : skb_pull+0x48/0x4c [ 52.008015] lr : mt7921_queue_rx_skb+0x494/0x890 [mt7921_common] [ 52.008361] Call trace: [ 52.008377] skb_pull+0x48/0x4c [ 52.008400] mt76s_net_worker+0x134/0x1b0 [mt76_sdio 35339a92c6eb7d4bbcc806a1d22f56365565135c] [ 52.008431] __mt76_worker_fn+0xe8/0x170 [mt76 ef716597d11a77150bc07e3fdd68eeb0f9b56917] [ 52.008449] kthread+0x148/0x3ac [ 52.008466] ret_from_fork+0x10/0x30
CVE-2022-49123: In the Linux kernel, the following vulnerability has been resolved: ath11k: Fix frames flush failure caused by deadlock We are seeing below warnings: kernel: [25393.301506] ath11k_pci 0000:01:00.0: failed to flush mgmt transmit queue 0 kernel: [25398.421509] ath11k_pci 0000:01:00.0: failed to flush mgmt transmit queue 0 kernel: [25398.421831] ath11k_pci 0000:01:00.0: dropping mgmt frame for vdev 0, is_started 0 this means ath11k fails to flush mgmt. frames because wmi_mgmt_tx_work has no chance to run in 5 seconds. By setting /proc/sys/kernel/hung_task_timeout_secs to 20 and increasing ATH11K_FLUSH_TIMEOUT to 50 we get below warnings: kernel: [ 120.763160] INFO: task wpa_supplicant:924 blocked for more than 20 seconds. kernel: [ 120.763169] Not tainted 5.10.90 #12 kernel: [ 120.763177] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: [ 120.763186] task:wpa_supplicant state:D stack: 0 pid: 924 ppid: 1 flags:0x000043a0 kernel: [ 120.763201] Call Trace: kernel: [ 120.763214] __schedule+0x785/0x12fa kernel: [ 120.763224] ? lockdep_hardirqs_on_prepare+0xe2/0x1bb kernel: [ 120.763242] schedule+0x7e/0xa1 kernel: [ 120.763253] schedule_timeout+0x98/0xfe kernel: [ 120.763266] ? run_local_timers+0x4a/0x4a kernel: [ 120.763291] ath11k_mac_flush_tx_complete+0x197/0x2b1 [ath11k 13c3a9bf37790f4ac8103b3decf7ab4008ac314a] kernel: [ 120.763306] ? init_wait_entry+0x2e/0x2e kernel: [ 120.763343] __ieee80211_flush_queues+0x167/0x21f [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763378] __ieee80211_recalc_idle+0x105/0x125 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763411] ieee80211_recalc_idle+0x14/0x27 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763441] ieee80211_free_chanctx+0x77/0xa2 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763473] __ieee80211_vif_release_channel+0x100/0x131 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763540] ieee80211_vif_release_channel+0x66/0x81 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763572] ieee80211_destroy_auth_data+0xa3/0xe6 [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763612] ieee80211_mgd_deauth+0x178/0x29b [mac80211 335da900954f1c5ea7f1613d92088ce83342042c] kernel: [ 120.763654] cfg80211_mlme_deauth+0x1a8/0x22c [cfg80211 8945aa5bc2af5f6972336665d8ad6f9c191ad5be] kernel: [ 120.763697] nl80211_deauthenticate+0xfa/0x123 [cfg80211 8945aa5bc2af5f6972336665d8ad6f9c191ad5be] kernel: [ 120.763715] genl_rcv_msg+0x392/0x3c2 kernel: [ 120.763750] ? nl80211_associate+0x432/0x432 [cfg80211 8945aa5bc2af5f6972336665d8ad6f9c191ad5be] kernel: [ 120.763782] ? nl80211_associate+0x432/0x432 [cfg80211 8945aa5bc2af5f6972336665d8ad6f9c191ad5be] kernel: [ 120.763802] ? genl_rcv+0x36/0x36 kernel: [ 120.763814] netlink_rcv_skb+0x89/0xf7 kernel: [ 120.763829] genl_rcv+0x28/0x36 kernel: [ 120.763840] netlink_unicast+0x179/0x24b kernel: [ 120.763854] netlink_sendmsg+0x393/0x401 kernel: [ 120.763872] sock_sendmsg+0x72/0x76 kernel: [ 120.763886] ____sys_sendmsg+0x170/0x1e6 kernel: [ 120.763897] ? copy_msghdr_from_user+0x7a/0xa2 kernel: [ 120.763914] ___sys_sendmsg+0x95/0xd1 kernel: [ 120.763940] __sys_sendmsg+0x85/0xbf kernel: [ 120.763956] do_syscall_64+0x43/0x55 kernel: [ 120.763966] entry_SYSCALL_64_after_hwframe+0x44/0xa9 kernel: [ 120.763977] RIP: 0033:0x79089f3fcc83 kernel: [ 120.763986] RSP: 002b:00007ffe604f0508 EFLAGS: 00000246 ORIG_RAX: 000000000000002e kernel: [ 120.763997] RAX: ffffffffffffffda RBX: 000059b40e987690 RCX: 000079089f3fcc83 kernel: [ 120.764006] RDX: 0000000000000000 RSI: 00007ffe604f0558 RDI: 0000000000000009 kernel: [ 120.764014] RBP: 00007ffe604f0540 R08: 0000000000000004 R09: 0000000000400000 kernel: [ 120.764023] R10: 00007ffe604f0638 R11: 0000000000000246 R12: 000059b40ea04980 kernel: [ 120.764032] R13: 00007ffe604 ---truncated---
CVE-2022-49124: In the Linux kernel, the following vulnerability has been resolved: x86/mce: Work around an erratum on fast string copy instructions A rare kernel panic scenario can happen when the following conditions are met due to an erratum on fast string copy instructions: 1) An uncorrected error. 2) That error must be in first cache line of a page. 3) Kernel must execute page_copy from the page immediately before that page. The fast string copy instructions ("REP; MOVS*") could consume an uncorrectable memory error in the cache line _right after_ the desired region to copy and raise an MCE. Bit 0 of MSR_IA32_MISC_ENABLE can be cleared to disable fast string copy and will avoid such spurious machine checks. However, that is less preferable due to the permanent performance impact. Considering memory poison is rare, it's desirable to keep fast string copy enabled until an MCE is seen. Intel has confirmed the following: 1. The CPU erratum of fast string copy only applies to Skylake, Cascade Lake and Cooper Lake generations. Directly return from the MCE handler: 2. Will result in complete execution of the "REP; MOVS*" with no data loss or corruption. 3. Will not result in another MCE firing on the next poisoned cache line due to "REP; MOVS*". 4. Will resume execution from a correct point in code. 5. Will result in the same instruction that triggered the MCE firing a second MCE immediately for any other software recoverable data fetch errors. 6. Is not safe without disabling the fast string copy, as the next fast string copy of the same buffer on the same CPU would result in a PANIC MCE. This should mitigate the erratum completely with the only caveat that the fast string copy is disabled on the affected hyper thread thus performance degradation. This is still better than the OS crashing on MCEs raised on an irrelevant process due to "REP; MOVS*' accesses in a kernel context, e.g., copy_page. Injected errors on 1st cache line of 8 anonymous pages of process 'proc1' and observed MCE consumption from 'proc2' with no panic (directly returned). Without the fix, the host panicked within a few minutes on a random 'proc2' process due to kernel access from copy_page. [ bp: Fix comment style + touch ups, zap an unlikely(), improve the quirk function's readability. ]
CVE-2022-49128: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: Add missing pm_runtime_put_sync pm_runtime_get_sync() will increase the rumtime PM counter even when it returns an error. Thus a pairing decrement is needed to prevent refcount leak. Fix this by replacing this API with pm_runtime_resume_and_get(), which will not change the runtime PM counter on error. Besides, a matching decrement is needed on the error handling path to keep the counter balanced.
CVE-2022-49132: In the Linux kernel, the following vulnerability has been resolved: ath11k: pci: fix crash on suspend if board file is not found Mario reported that the kernel was crashing on suspend if ath11k was not able to find a board file: [ 473.693286] PM: Suspending system (s2idle) [ 473.693291] printk: Suspending console(s) (use no_console_suspend to debug) [ 474.407787] BUG: unable to handle page fault for address: 0000000000002070 [ 474.407791] #PF: supervisor read access in kernel mode [ 474.407794] #PF: error_code(0x0000) - not-present page [ 474.407798] PGD 0 P4D 0 [ 474.407801] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 474.407805] CPU: 2 PID: 2350 Comm: kworker/u32:14 Tainted: G W 5.16.0 #248 [...] [ 474.407868] Call Trace: [ 474.407870] <TASK> [ 474.407874] ? _raw_spin_lock_irqsave+0x2a/0x60 [ 474.407882] ? lock_timer_base+0x72/0xa0 [ 474.407889] ? _raw_spin_unlock_irqrestore+0x29/0x3d [ 474.407892] ? try_to_del_timer_sync+0x54/0x80 [ 474.407896] ath11k_dp_rx_pktlog_stop+0x49/0xc0 [ath11k] [ 474.407912] ath11k_core_suspend+0x34/0x130 [ath11k] [ 474.407923] ath11k_pci_pm_suspend+0x1b/0x50 [ath11k_pci] [ 474.407928] pci_pm_suspend+0x7e/0x170 [ 474.407935] ? pci_pm_freeze+0xc0/0xc0 [ 474.407939] dpm_run_callback+0x4e/0x150 [ 474.407947] __device_suspend+0x148/0x4c0 [ 474.407951] async_suspend+0x20/0x90 dmesg-efi-164255130401001: Oops#1 Part1 [ 474.407955] async_run_entry_fn+0x33/0x120 [ 474.407959] process_one_work+0x220/0x3f0 [ 474.407966] worker_thread+0x4a/0x3d0 [ 474.407971] kthread+0x17a/0x1a0 [ 474.407975] ? process_one_work+0x3f0/0x3f0 [ 474.407979] ? set_kthread_struct+0x40/0x40 [ 474.407983] ret_from_fork+0x22/0x30 [ 474.407991] </TASK> The issue here is that board file loading happens after ath11k_pci_probe() succesfully returns (ath11k initialisation happends asynchronously) and the suspend handler is still enabled, of course failing as ath11k is not properly initialised. Fix this by checking ATH11K_FLAG_QMI_FAIL during both suspend and resume. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2
CVE-2022-49134: In the Linux kernel, the following vulnerability has been resolved: mlxsw: spectrum: Guard against invalid local ports When processing events generated by the device's firmware, the driver protects itself from events reported for non-existent local ports, but not for the CPU port (local port 0), which exists, but does not have all the fields as any local port. This can result in a NULL pointer dereference when trying access 'struct mlxsw_sp_port' fields which are not initialized for CPU port. Commit 63b08b1f6834 ("mlxsw: spectrum: Protect driver from buggy firmware") already handled such issue by bailing early when processing a PUDE event reported for the CPU port. Generalize the approach by moving the check to a common function and making use of it in all relevant places.
CVE-2022-49135: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix memory leak [why] Resource release is needed on the error handling path to prevent memory leak. [how] Fix this by adding kfree on the error handling path.
CVE-2022-49138: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: Ignore multiple conn complete events When one of the three connection complete events is received multiple times for the same handle, the device is registered multiple times which leads to memory corruptions. Therefore, consequent events for a single connection are ignored. The conn->state can hold different values, therefore HCI_CONN_HANDLE_UNSET is introduced to identify new connections. To make sure the events do not contain this or another invalid handle HCI_CONN_HANDLE_MAX and checks are introduced. Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=215497
CVE-2022-49142: In the Linux kernel, the following vulnerability has been resolved: net: preserve skb_end_offset() in skb_unclone_keeptruesize() syzbot found another way to trigger the infamous WARN_ON_ONCE(delta < len) in skb_try_coalesce() [1] I was able to root cause the issue to kfence. When kfence is in action, the following assertion is no longer true: int size = xxxx; void *ptr1 = kmalloc(size, gfp); void *ptr2 = kmalloc(size, gfp); if (ptr1 && ptr2) ASSERT(ksize(ptr1) == ksize(ptr2)); We attempted to fix these issues in the blamed commits, but forgot that TCP was possibly shifting data after skb_unclone_keeptruesize() has been used, notably from tcp_retrans_try_collapse(). So we not only need to keep same skb->truesize value, we also need to make sure TCP wont fill new tailroom that pskb_expand_head() was able to get from a addr = kmalloc(...) followed by ksize(addr) Split skb_unclone_keeptruesize() into two parts: 1) Inline skb_unclone_keeptruesize() for the common case, when skb is not cloned. 2) Out of line __skb_unclone_keeptruesize() for the 'slow path'. WARNING: CPU: 1 PID: 6490 at net/core/skbuff.c:5295 skb_try_coalesce+0x1235/0x1560 net/core/skbuff.c:5295 Modules linked in: CPU: 1 PID: 6490 Comm: syz-executor161 Not tainted 5.17.0-rc4-syzkaller-00229-g4f12b742eb2b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:skb_try_coalesce+0x1235/0x1560 net/core/skbuff.c:5295 Code: bf 01 00 00 00 0f b7 c0 89 c6 89 44 24 20 e8 62 24 4e fa 8b 44 24 20 83 e8 01 0f 85 e5 f0 ff ff e9 87 f4 ff ff e8 cb 20 4e fa <0f> 0b e9 06 f9 ff ff e8 af b2 95 fa e9 69 f0 ff ff e8 95 b2 95 fa RSP: 0018:ffffc900063af268 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 00000000ffffffd5 RCX: 0000000000000000 RDX: ffff88806fc05700 RSI: ffffffff872abd55 RDI: 0000000000000003 RBP: ffff88806e675500 R08: 00000000ffffffd5 R09: 0000000000000000 R10: ffffffff872ab659 R11: 0000000000000000 R12: ffff88806dd554e8 R13: ffff88806dd9bac0 R14: ffff88806dd9a2c0 R15: 0000000000000155 FS: 00007f18014f9700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020002000 CR3: 000000006be7a000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_try_coalesce net/ipv4/tcp_input.c:4651 [inline] tcp_try_coalesce+0x393/0x920 net/ipv4/tcp_input.c:4630 tcp_queue_rcv+0x8a/0x6e0 net/ipv4/tcp_input.c:4914 tcp_data_queue+0x11fd/0x4bb0 net/ipv4/tcp_input.c:5025 tcp_rcv_established+0x81e/0x1ff0 net/ipv4/tcp_input.c:5947 tcp_v4_do_rcv+0x65e/0x980 net/ipv4/tcp_ipv4.c:1719 sk_backlog_rcv include/net/sock.h:1037 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2779 release_sock+0x54/0x1b0 net/core/sock.c:3311 sk_wait_data+0x177/0x450 net/core/sock.c:2821 tcp_recvmsg_locked+0xe28/0x1fd0 net/ipv4/tcp.c:2457 tcp_recvmsg+0x137/0x610 net/ipv4/tcp.c:2572 inet_recvmsg+0x11b/0x5e0 net/ipv4/af_inet.c:850 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_recvmsg net/socket.c:962 [inline] ____sys_recvmsg+0x2c4/0x600 net/socket.c:2632 ___sys_recvmsg+0x127/0x200 net/socket.c:2674 __sys_recvmsg+0xe2/0x1a0 net/socket.c:2704 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2022-49157: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix premature hw access after PCI error After a recoverable PCI error has been detected and recovered, qla driver needs to check to see if the error condition still persist and/or wait for the OS to give the resume signal. Sep 8 22:26:03 localhost kernel: WARNING: CPU: 9 PID: 124606 at qla_tmpl.c:440 qla27xx_fwdt_entry_t266+0x55/0x60 [qla2xxx] Sep 8 22:26:03 localhost kernel: RIP: 0010:qla27xx_fwdt_entry_t266+0x55/0x60 [qla2xxx] Sep 8 22:26:03 localhost kernel: Call Trace: Sep 8 22:26:03 localhost kernel: ? qla27xx_walk_template+0xb1/0x1b0 [qla2xxx] Sep 8 22:26:03 localhost kernel: ? qla27xx_execute_fwdt_template+0x12a/0x160 [qla2xxx] Sep 8 22:26:03 localhost kernel: ? qla27xx_fwdump+0xa0/0x1c0 [qla2xxx] Sep 8 22:26:03 localhost kernel: ? qla2xxx_pci_mmio_enabled+0xfb/0x120 [qla2xxx] Sep 8 22:26:03 localhost kernel: ? report_mmio_enabled+0x44/0x80 Sep 8 22:26:03 localhost kernel: ? report_slot_reset+0x80/0x80 Sep 8 22:26:03 localhost kernel: ? pci_walk_bus+0x70/0x90 Sep 8 22:26:03 localhost kernel: ? aer_dev_correctable_show+0xc0/0xc0 Sep 8 22:26:03 localhost kernel: ? pcie_do_recovery+0x1bb/0x240 Sep 8 22:26:03 localhost kernel: ? aer_recover_work_func+0xaa/0xd0 Sep 8 22:26:03 localhost kernel: ? process_one_work+0x1a7/0x360 .. Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-8041:22: detected PCI disconnect. Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22: qla27xx_fwdt_entry_t262: dump ram MB failed. Area 5h start 198013h end 198013h Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-107ff:22: Unable to capture FW dump Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-1015:22: cmd=0x0, waited 5221 msecs Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-680d:22: mmio enabled returning. Sep 8 22:26:03 localhost kernel: qla2xxx [0000:42:00.2]-d04c:22: MBX Command timeout for cmd 0, iocontrol=ffffffff jiffies=10140f2e5 mb[0-3]=[0xffff 0xffff 0xffff 0xffff]
CVE-2022-49158: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix warning message due to adisc being flushed Fix warning message due to adisc being flushed. Linux kernel triggered a warning message where a different error code type is not matching up with the expected type. Add additional translation of one error code type to another. WARNING: CPU: 2 PID: 1131623 at drivers/scsi/qla2xxx/qla_init.c:498 qla2x00_async_adisc_sp_done+0x294/0x2b0 [qla2xxx] CPU: 2 PID: 1131623 Comm: drmgr Not tainted 5.13.0-rc1-autotest #1 .. GPR28: c000000aaa9c8890 c0080000079ab678 c00000140a104800 c00000002bd19000 NIP [c00800000790857c] qla2x00_async_adisc_sp_done+0x294/0x2b0 [qla2xxx] LR [c008000007908578] qla2x00_async_adisc_sp_done+0x290/0x2b0 [qla2xxx] Call Trace: [c00000001cdc3620] [c008000007908578] qla2x00_async_adisc_sp_done+0x290/0x2b0 [qla2xxx] (unreliable) [c00000001cdc3710] [c0080000078f3080] __qla2x00_abort_all_cmds+0x1b8/0x580 [qla2xxx] [c00000001cdc3840] [c0080000078f589c] qla2x00_abort_all_cmds+0x34/0xd0 [qla2xxx] [c00000001cdc3880] [c0080000079153d8] qla2x00_abort_isp_cleanup+0x3f0/0x570 [qla2xxx] [c00000001cdc3920] [c0080000078fb7e8] qla2x00_remove_one+0x3d0/0x480 [qla2xxx] [c00000001cdc39b0] [c00000000071c274] pci_device_remove+0x64/0x120 [c00000001cdc39f0] [c0000000007fb818] device_release_driver_internal+0x168/0x2a0 [c00000001cdc3a30] [c00000000070e304] pci_stop_bus_device+0xb4/0x100 [c00000001cdc3a70] [c00000000070e4f0] pci_stop_and_remove_bus_device+0x20/0x40 [c00000001cdc3aa0] [c000000000073940] pci_hp_remove_devices+0x90/0x130 [c00000001cdc3b30] [c0080000070704d0] disable_slot+0x38/0x90 [rpaphp] [ c00000001cdc3b60] [c00000000073eb4c] power_write_file+0xcc/0x180 [c00000001cdc3be0] [c0000000007354bc] pci_slot_attr_store+0x3c/0x60 [c00000001cdc3c00] [c00000000055f820] sysfs_kf_write+0x60/0x80 [c00000001cdc3c20] [c00000000055df10] kernfs_fop_write_iter+0x1a0/0x290 [c00000001cdc3c70] [c000000000447c4c] new_sync_write+0x14c/0x1d0 [c00000001cdc3d10] [c00000000044b134] vfs_write+0x224/0x330 [c00000001cdc3d60] [c00000000044b3f4] ksys_write+0x74/0x130 [c00000001cdc3db0] [c00000000002df70] system_call_exception+0x150/0x2d0 [c00000001cdc3e10] [c00000000000d45c] system_call_common+0xec/0x278
CVE-2022-49160: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix crash during module load unload test During purex packet handling the driver was incorrectly freeing a pre-allocated structure. Fix this by skipping that entry. System crashed with the following stack during a module unload test. Call Trace: sbitmap_init_node+0x7f/0x1e0 sbitmap_queue_init_node+0x24/0x150 blk_mq_init_bitmaps+0x3d/0xa0 blk_mq_init_tags+0x68/0x90 blk_mq_alloc_map_and_rqs+0x44/0x120 blk_mq_alloc_set_map_and_rqs+0x63/0x150 blk_mq_alloc_tag_set+0x11b/0x230 scsi_add_host_with_dma.cold+0x3f/0x245 qla2x00_probe_one+0xd5a/0x1b80 [qla2xxx] Call Trace with slub_debug and debug kernel: kasan_report_invalid_free+0x50/0x80 __kasan_slab_free+0x137/0x150 slab_free_freelist_hook+0xc6/0x190 kfree+0xe8/0x2e0 qla2x00_free_device+0x3bb/0x5d0 [qla2xxx] qla2x00_remove_one+0x668/0xcf0 [qla2xxx]
CVE-2022-49161: In the Linux kernel, the following vulnerability has been resolved: ASoC: mediatek: Fix error handling in mt8183_da7219_max98357_dev_probe The device_node pointer is returned by of_parse_phandle() with refcount incremented. We should use of_node_put() on it when done. This function only calls of_node_put() in the regular path. And it will cause refcount leak in error paths. Fix this by calling of_node_put() in error handling too.
CVE-2022-49164: In the Linux kernel, the following vulnerability has been resolved: powerpc/tm: Fix more userspace r13 corruption Commit cf13435b730a ("powerpc/tm: Fix userspace r13 corruption") fixes a problem in treclaim where a SLB miss can occur on the thread_struct->ckpt_regs while SCRATCH0 is live with the saved user r13 value, clobbering it with the kernel r13 and ultimately resulting in kernel r13 being stored in ckpt_regs. There is an equivalent problem in trechkpt where the user r13 value is loaded into r13 from chkpt_regs to be recheckpointed, but a SLB miss could occur on ckpt_regs accesses after that, which will result in r13 being clobbered with a kernel value and that will get recheckpointed and then restored to user registers. The same memory page is accessed right before this critical window where a SLB miss could cause corruption, so hitting the bug requires the SLB entry be removed within a small window of instructions, which is possible if a SLB related MCE hits there. PAPR also permits the hypervisor to discard this SLB entry (because slb_shadow->persistent is only set to SLB_NUM_BOLTED) although it's not known whether any implementations would do this (KVM does not). So this is an extremely unlikely bug, only found by inspection. Fix this by also storing user r13 in a temporary location on the kernel stack and don't change the r13 register from kernel r13 until the RI=0 critical section that does not fault. The SCRATCH0 change is not strictly part of the fix, it's only used in the RI=0 section so it does not have the same problem as the previous SCRATCH0 bug.
CVE-2022-49169: In the Linux kernel, the following vulnerability has been resolved: f2fs: use spin_lock to avoid hang [14696.634553] task:cat state:D stack: 0 pid:1613738 ppid:1613735 flags:0x00000004 [14696.638285] Call Trace: [14696.639038] <TASK> [14696.640032] __schedule+0x302/0x930 [14696.640969] schedule+0x58/0xd0 [14696.641799] schedule_preempt_disabled+0x18/0x30 [14696.642890] __mutex_lock.constprop.0+0x2fb/0x4f0 [14696.644035] ? mod_objcg_state+0x10c/0x310 [14696.645040] ? obj_cgroup_charge+0xe1/0x170 [14696.646067] __mutex_lock_slowpath+0x13/0x20 [14696.647126] mutex_lock+0x34/0x40 [14696.648070] stat_show+0x25/0x17c0 [f2fs] [14696.649218] seq_read_iter+0x120/0x4b0 [14696.650289] ? aa_file_perm+0x12a/0x500 [14696.651357] ? lru_cache_add+0x1c/0x20 [14696.652470] seq_read+0xfd/0x140 [14696.653445] full_proxy_read+0x5c/0x80 [14696.654535] vfs_read+0xa0/0x1a0 [14696.655497] ksys_read+0x67/0xe0 [14696.656502] __x64_sys_read+0x1a/0x20 [14696.657580] do_syscall_64+0x3b/0xc0 [14696.658671] entry_SYSCALL_64_after_hwframe+0x44/0xae [14696.660068] RIP: 0033:0x7efe39df1cb2 [14696.661133] RSP: 002b:00007ffc8badd948 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [14696.662958] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007efe39df1cb2 [14696.664757] RDX: 0000000000020000 RSI: 00007efe399df000 RDI: 0000000000000003 [14696.666542] RBP: 00007efe399df000 R08: 00007efe399de010 R09: 00007efe399de010 [14696.668363] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000000000 [14696.670155] R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000 [14696.671965] </TASK> [14696.672826] task:umount state:D stack: 0 pid:1614985 ppid:1614984 flags:0x00004000 [14696.674930] Call Trace: [14696.675903] <TASK> [14696.676780] __schedule+0x302/0x930 [14696.677927] schedule+0x58/0xd0 [14696.679019] schedule_preempt_disabled+0x18/0x30 [14696.680412] __mutex_lock.constprop.0+0x2fb/0x4f0 [14696.681783] ? destroy_inode+0x65/0x80 [14696.683006] __mutex_lock_slowpath+0x13/0x20 [14696.684305] mutex_lock+0x34/0x40 [14696.685442] f2fs_destroy_stats+0x1e/0x60 [f2fs] [14696.686803] f2fs_put_super+0x158/0x390 [f2fs] [14696.688238] generic_shutdown_super+0x7a/0x120 [14696.689621] kill_block_super+0x27/0x50 [14696.690894] kill_f2fs_super+0x7f/0x100 [f2fs] [14696.692311] deactivate_locked_super+0x35/0xa0 [14696.693698] deactivate_super+0x40/0x50 [14696.694985] cleanup_mnt+0x139/0x190 [14696.696209] __cleanup_mnt+0x12/0x20 [14696.697390] task_work_run+0x64/0xa0 [14696.698587] exit_to_user_mode_prepare+0x1b7/0x1c0 [14696.700053] syscall_exit_to_user_mode+0x27/0x50 [14696.701418] do_syscall_64+0x48/0xc0 [14696.702630] entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2022-49172: In the Linux kernel, the following vulnerability has been resolved: parisc: Fix non-access data TLB cache flush faults When a page is not present, we get non-access data TLB faults from the fdc and fic instructions in flush_user_dcache_range_asm and flush_user_icache_range_asm. When these occur, the cache line is not invalidated and potentially we get memory corruption. The problem was hidden by the nullification of the flush instructions. These faults also affect performance. With pa8800/pa8900 processors, there will be 32 faults per 4 KB page since the cache line is 128 bytes. There will be more faults with earlier processors. The problem is fixed by using flush_cache_pages(). It does the flush using a tmp alias mapping. The flush_cache_pages() call in flush_cache_range() flushed too large a range. V2: Remove unnecessary preempt_disable() and preempt_enable() calls.
CVE-2022-49173: In the Linux kernel, the following vulnerability has been resolved: spi: fsi: Implement a timeout for polling status The data transfer routines must poll the status register to determine when more data can be shifted in or out. If the hardware gets into a bad state, these polling loops may never exit. Prevent this by returning an error if a timeout is exceeded.
CVE-2022-49178: In the Linux kernel, the following vulnerability has been resolved: memstick/mspro_block: fix handling of read-only devices Use set_disk_ro to propagate the read-only state to the block layer instead of checking for it in ->open and leaking a reference in case of a read-only device.
CVE-2022-49182: In the Linux kernel, the following vulnerability has been resolved: net: hns3: add vlan list lock to protect vlan list When adding port base VLAN, vf VLAN need to remove from HW and modify the vlan state in vf VLAN list as false. If the periodicity task is freeing the same node, it may cause "use after free" error. This patch adds a vlan list lock to protect the vlan list.
CVE-2022-49183: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ct: fix ref leak when switching zones When switching zones or network namespaces without doing a ct clear in between, it is now leaking a reference to the old ct entry. That's because tcf_ct_skb_nfct_cached() returns false and tcf_ct_flow_table_lookup() may simply overwrite it. The fix is to, as the ct entry is not reusable, free it already at tcf_ct_skb_nfct_cached().
CVE-2022-49196: In the Linux kernel, the following vulnerability has been resolved: powerpc/pseries: Fix use after free in remove_phb_dynamic() In remove_phb_dynamic() we use &phb->io_resource, after we've called device_unregister(&host_bridge->dev). But the unregister may have freed phb, because pcibios_free_controller_deferred() is the release function for the host_bridge. If there are no outstanding references when we call device_unregister() then phb will be freed out from under us. This has gone mainly unnoticed, but with slub_debug and page_poison enabled it can lead to a crash: PID: 7574 TASK: c0000000d492cb80 CPU: 13 COMMAND: "drmgr" #0 [c0000000e4f075a0] crash_kexec at c00000000027d7dc #1 [c0000000e4f075d0] oops_end at c000000000029608 #2 [c0000000e4f07650] __bad_page_fault at c0000000000904b4 #3 [c0000000e4f076c0] do_bad_slb_fault at c00000000009a5a8 #4 [c0000000e4f076f0] data_access_slb_common_virt at c000000000008b30 Data SLB Access [380] exception frame: R0: c000000000167250 R1: c0000000e4f07a00 R2: c000000002a46100 R3: c000000002b39ce8 R4: 00000000000000c0 R5: 00000000000000a9 R6: 3894674d000000c0 R7: 0000000000000000 R8: 00000000000000ff R9: 0000000000000100 R10: 6b6b6b6b6b6b6b6b R11: 0000000000008000 R12: c00000000023da80 R13: c0000009ffd38b00 R14: 0000000000000000 R15: 000000011c87f0f0 R16: 0000000000000006 R17: 0000000000000003 R18: 0000000000000002 R19: 0000000000000004 R20: 0000000000000005 R21: 000000011c87ede8 R22: 000000011c87c5a8 R23: 000000011c87d3a0 R24: 0000000000000000 R25: 0000000000000001 R26: c0000000e4f07cc8 R27: c00000004d1cc400 R28: c0080000031d00e8 R29: c00000004d23d800 R30: c00000004d1d2400 R31: c00000004d1d2540 NIP: c000000000167258 MSR: 8000000000009033 OR3: c000000000e9f474 CTR: 0000000000000000 LR: c000000000167250 XER: 0000000020040003 CCR: 0000000024088420 MQ: 0000000000000000 DAR: 6b6b6b6b6b6b6ba3 DSISR: c0000000e4f07920 Syscall Result: fffffffffffffff2 [NIP : release_resource+56] [LR : release_resource+48] #5 [c0000000e4f07a00] release_resource at c000000000167258 (unreliable) #6 [c0000000e4f07a30] remove_phb_dynamic at c000000000105648 #7 [c0000000e4f07ab0] dlpar_remove_slot at c0080000031a09e8 [rpadlpar_io] #8 [c0000000e4f07b50] remove_slot_store at c0080000031a0b9c [rpadlpar_io] #9 [c0000000e4f07be0] kobj_attr_store at c000000000817d8c #10 [c0000000e4f07c00] sysfs_kf_write at c00000000063e504 #11 [c0000000e4f07c20] kernfs_fop_write_iter at c00000000063d868 #12 [c0000000e4f07c70] new_sync_write at c00000000054339c #13 [c0000000e4f07d10] vfs_write at c000000000546624 #14 [c0000000e4f07d60] ksys_write at c0000000005469f4 #15 [c0000000e4f07db0] system_call_exception at c000000000030840 #16 [c0000000e4f07e10] system_call_vectored_common at c00000000000c168 To avoid it, we can take a reference to the host_bridge->dev until we're done using phb. Then when we drop the reference the phb will be freed.
CVE-2022-49201: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: fix race between xmit and reset There is a race between reset and the transmit paths that can lead to ibmvnic_xmit() accessing an scrq after it has been freed in the reset path. It can result in a crash like: Kernel attempted to read user page (0) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc0080000016189f8 Oops: Kernel access of bad area, sig: 11 [#1] ... NIP [c0080000016189f8] ibmvnic_xmit+0x60/0xb60 [ibmvnic] LR [c000000000c0046c] dev_hard_start_xmit+0x11c/0x280 Call Trace: [c008000001618f08] ibmvnic_xmit+0x570/0xb60 [ibmvnic] (unreliable) [c000000000c0046c] dev_hard_start_xmit+0x11c/0x280 [c000000000c9cfcc] sch_direct_xmit+0xec/0x330 [c000000000bfe640] __dev_xmit_skb+0x3a0/0x9d0 [c000000000c00ad4] __dev_queue_xmit+0x394/0x730 [c008000002db813c] __bond_start_xmit+0x254/0x450 [bonding] [c008000002db8378] bond_start_xmit+0x40/0xc0 [bonding] [c000000000c0046c] dev_hard_start_xmit+0x11c/0x280 [c000000000c00ca4] __dev_queue_xmit+0x564/0x730 [c000000000cf97e0] neigh_hh_output+0xd0/0x180 [c000000000cfa69c] ip_finish_output2+0x31c/0x5c0 [c000000000cfd244] __ip_queue_xmit+0x194/0x4f0 [c000000000d2a3c4] __tcp_transmit_skb+0x434/0x9b0 [c000000000d2d1e0] __tcp_retransmit_skb+0x1d0/0x6a0 [c000000000d2d984] tcp_retransmit_skb+0x34/0x130 [c000000000d310e8] tcp_retransmit_timer+0x388/0x6d0 [c000000000d315ec] tcp_write_timer_handler+0x1bc/0x330 [c000000000d317bc] tcp_write_timer+0x5c/0x200 [c000000000243270] call_timer_fn+0x50/0x1c0 [c000000000243704] __run_timers.part.0+0x324/0x460 [c000000000243894] run_timer_softirq+0x54/0xa0 [c000000000ea713c] __do_softirq+0x15c/0x3e0 [c000000000166258] __irq_exit_rcu+0x158/0x190 [c000000000166420] irq_exit+0x20/0x40 [c00000000002853c] timer_interrupt+0x14c/0x2b0 [c000000000009a00] decrementer_common_virt+0x210/0x220 --- interrupt: 900 at plpar_hcall_norets_notrace+0x18/0x2c The immediate cause of the crash is the access of tx_scrq in the following snippet during a reset, where the tx_scrq can be either NULL or an address that will soon be invalid: ibmvnic_xmit() { ... tx_scrq = adapter->tx_scrq[queue_num]; txq = netdev_get_tx_queue(netdev, queue_num); ind_bufp = &tx_scrq->ind_buf; if (test_bit(0, &adapter->resetting)) { ... } But beyond that, the call to ibmvnic_xmit() itself is not safe during a reset and the reset path attempts to avoid this by stopping the queue in ibmvnic_cleanup(). However just after the queue was stopped, an in-flight ibmvnic_complete_tx() could have restarted the queue even as the reset is progressing. Since the queue was restarted we could get a call to ibmvnic_xmit() which can then access the bad tx_scrq (or other fields). We cannot however simply have ibmvnic_complete_tx() check the ->resetting bit and skip starting the queue. This can race at the "back-end" of a good reset which just restarted the queue but has not cleared the ->resetting bit yet. If we skip restarting the queue due to ->resetting being true, the queue would remain stopped indefinitely potentially leading to transmit timeouts. IOW ->resetting is too broad for this purpose. Instead use a new flag that indicates whether or not the queues are active. Only the open/ reset paths control when the queues are active. ibmvnic_complete_tx() and others wake up the queue only if the queue is marked active. So we will have: A. reset/open thread in ibmvnic_cleanup() and __ibmvnic_open() ->resetting = true ->tx_queues_active = false disable tx queues ... ->tx_queues_active = true start tx queues B. Tx interrupt in ibmvnic_complete_tx(): if (->tx_queues_active) netif_wake_subqueue(); To ensure that ->tx_queues_active and state of the queues are consistent, we need a lock which: - must also be taken in the interrupt path (ibmvnic_complete_tx()) - shared across the multiple ---truncated---
CVE-2022-49214: In the Linux kernel, the following vulnerability has been resolved: powerpc/64s: Don't use DSISR for SLB faults Since commit 46ddcb3950a2 ("powerpc/mm: Show if a bad page fault on data is read or write.") we use page_fault_is_write(regs->dsisr) in __bad_page_fault() to determine if the fault is for a read or write, and change the message printed accordingly. But SLB faults, aka Data Segment Interrupts, don't set DSISR (Data Storage Interrupt Status Register) to a useful value. All ISA versions from v2.03 through v3.1 specify that the Data Segment Interrupt sets DSISR "to an undefined value". As far as I can see there's no mention of SLB faults setting DSISR in any BookIV content either. This manifests as accesses that should be a read being incorrectly reported as writes, for example, using the xmon "dump" command: 0:mon> d 0x5deadbeef0000000 5deadbeef0000000 [359526.415354][ C6] BUG: Unable to handle kernel data access on write at 0x5deadbeef0000000 [359526.415611][ C6] Faulting instruction address: 0xc00000000010a300 cpu 0x6: Vector: 380 (Data SLB Access) at [c00000000ffbf400] pc: c00000000010a300: mread+0x90/0x190 If we disassemble the PC, we see a load instruction: 0:mon> di c00000000010a300 c00000000010a300 89490000 lbz r10,0(r9) We can also see in exceptions-64s.S that the data_access_slb block doesn't set IDSISR=1, which means it doesn't load DSISR into pt_regs. So the value we're using to determine if the fault is a read/write is some stale value in pt_regs from a previous page fault. Rework the printing logic to separate the SLB fault case out, and only print read/write in the cases where we can determine it. The result looks like eg: 0:mon> d 0x5deadbeef0000000 5deadbeef0000000 [ 721.779525][ C6] BUG: Unable to handle kernel data access at 0x5deadbeef0000000 [ 721.779697][ C6] Faulting instruction address: 0xc00000000014cbe0 cpu 0x6: Vector: 380 (Data SLB Access) at [c00000000ffbf390] 0:mon> d 0 0000000000000000 [ 742.793242][ C6] BUG: Kernel NULL pointer dereference at 0x00000000 [ 742.793316][ C6] Faulting instruction address: 0xc00000000014cbe0 cpu 0x6: Vector: 380 (Data SLB Access) at [c00000000ffbf390]
CVE-2022-49215: In the Linux kernel, the following vulnerability has been resolved: xsk: Fix race at socket teardown Fix a race in the xsk socket teardown code that can lead to a NULL pointer dereference splat. The current xsk unbind code in xsk_unbind_dev() starts by setting xs->state to XSK_UNBOUND, sets xs->dev to NULL and then waits for any NAPI processing to terminate using synchronize_net(). After that, the release code starts to tear down the socket state and free allocated memory. BUG: kernel NULL pointer dereference, address: 00000000000000c0 PGD 8000000932469067 P4D 8000000932469067 PUD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 25 PID: 69132 Comm: grpcpp_sync_ser Tainted: G I 5.16.0+ #2 Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.2.10 03/09/2015 RIP: 0010:__xsk_sendmsg+0x2c/0x690 [...] RSP: 0018:ffffa2348bd13d50 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000040 RCX: ffff8d5fc632d258 RDX: 0000000000400000 RSI: ffffa2348bd13e10 RDI: ffff8d5fc5489800 RBP: ffffa2348bd13db0 R08: 0000000000000000 R09: 00007ffffffff000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8d5fc5489800 R13: ffff8d5fcb0f5140 R14: ffff8d5fcb0f5140 R15: 0000000000000000 FS: 00007f991cff9400(0000) GS:ffff8d6f1f700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c0 CR3: 0000000114888005 CR4: 00000000001706e0 Call Trace: <TASK> ? aa_sk_perm+0x43/0x1b0 xsk_sendmsg+0xf0/0x110 sock_sendmsg+0x65/0x70 __sys_sendto+0x113/0x190 ? debug_smp_processor_id+0x17/0x20 ? fpregs_assert_state_consistent+0x23/0x50 ? exit_to_user_mode_prepare+0xa5/0x1d0 __x64_sys_sendto+0x29/0x30 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae There are two problems with the current code. First, setting xs->dev to NULL before waiting for all users to stop using the socket is not correct. The entry to the data plane functions xsk_poll(), xsk_sendmsg(), and xsk_recvmsg() are all guarded by a test that xs->state is in the state XSK_BOUND and if not, it returns right away. But one process might have passed this test but still have not gotten to the point in which it uses xs->dev in the code. In this interim, a second process executing xsk_unbind_dev() might have set xs->dev to NULL which will lead to a crash for the first process. The solution here is just to get rid of this NULL assignment since it is not used anymore. Before commit 42fddcc7c64b ("xsk: use state member for socket synchronization"), xs->dev was the gatekeeper to admit processes into the data plane functions, but it was replaced with the state variable xs->state in the aforementioned commit. The second problem is that synchronize_net() does not wait for any process in xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() to complete, which means that the state they rely on might be cleaned up prematurely. This can happen when the notifier gets called (at driver unload for example) as it uses xsk_unbind_dev(). Solve this by extending the RCU critical region from just the ndo_xsk_wakeup to the whole functions mentioned above, so that both the test of xs->state == XSK_BOUND and the last use of any member of xs is covered by the RCU critical section. This will guarantee that when synchronize_net() completes, there will be no processes left executing xsk_poll(), xsk_sendmsg(), or xsk_recvmsg() and state can be cleaned up safely. Note that we need to drop the RCU lock for the skb xmit path as it uses functions that might sleep. Due to this, we have to retest the xs->state after we grab the mutex that protects the skb xmit code from, among a number of things, an xsk_unbind_dev() being executed from the notifier at the same time.
CVE-2022-49218: In the Linux kernel, the following vulnerability has been resolved: drm/dp: Fix OOB read when handling Post Cursor2 register The link_status array was not large enough to read the Adjust Request Post Cursor2 register, so remove the common helper function to avoid an OOB read, found with a -Warray-bounds build: drivers/gpu/drm/drm_dp_helper.c: In function 'drm_dp_get_adjust_request_post_cursor': drivers/gpu/drm/drm_dp_helper.c:59:27: error: array subscript 10 is outside array bounds of 'const u8[6]' {aka 'const unsigned char[6]'} [-Werror=array-bounds] 59 | return link_status[r - DP_LANE0_1_STATUS]; | ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/drm_dp_helper.c:147:51: note: while referencing 'link_status' 147 | u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], | ~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Replace the only user of the helper with an open-coded fetch and decode, similar to drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c.
CVE-2022-49226: In the Linux kernel, the following vulnerability has been resolved: net: asix: add proper error handling of usb read errors Syzbot once again hit uninit value in asix driver. The problem still the same -- asix_read_cmd() reads less bytes, than was requested by caller. Since all read requests are performed via asix_read_cmd() let's catch usb related error there and add __must_check notation to be sure all callers actually check return value. So, this patch adds sanity check inside asix_read_cmd(), that simply checks if bytes read are not less, than was requested and adds missing error handling of asix_read_cmd() all across the driver code.
CVE-2022-49234: In the Linux kernel, the following vulnerability has been resolved: net: dsa: Avoid cross-chip syncing of VLAN filtering Changes to VLAN filtering are not applicable to cross-chip notifications. On a system like this: .-----. .-----. .-----. | sw1 +---+ sw2 +---+ sw3 | '-1-2-' '-1-2-' '-1-2-' Before this change, upon sw1p1 leaving a bridge, a call to dsa_port_vlan_filtering would also be made to sw2p1 and sw3p1. In this scenario: .---------. .-----. .-----. | sw1 +---+ sw2 +---+ sw3 | '-1-2-3-4-' '-1-2-' '-1-2-' When sw1p4 would leave a bridge, dsa_port_vlan_filtering would be called for sw2 and sw3 with a non-existing port - leading to array out-of-bounds accesses and crashes on mv88e6xxx.
CVE-2022-49246: In the Linux kernel, the following vulnerability has been resolved: ASoC: atmel: Fix error handling in snd_proto_probe The device_node pointer is returned by of_parse_phandle() with refcount incremented. We should use of_node_put() on it when done. This function only calls of_node_put() in the regular path. And it will cause refcount leak in error paths. Fix this by calling of_node_put() in error handling too.
CVE-2022-49266: In the Linux kernel, the following vulnerability has been resolved: block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0%
CVE-2022-49285: In the Linux kernel, the following vulnerability has been resolved: iio: accel: mma8452: use the correct logic to get mma8452_data The original logic to get mma8452_data is wrong, the *dev point to the device belong to iio_dev. we can't use this dev to find the correct i2c_client. The original logic happen to work because it finally use dev->driver_data to get iio_dev. Here use the API to_i2c_client() is wrong and make reader confuse. To correct the logic, it should be like this struct mma8452_data *data = iio_priv(dev_get_drvdata(dev)); But after commit 8b7651f25962 ("iio: iio_device_alloc(): Remove unnecessary self drvdata"), the upper logic also can't work. When try to show the avialable scale in userspace, will meet kernel dump, kernel handle NULL pointer dereference. So use dev_to_iio_dev() to correct the logic. Dual fixes tags as the second reflects when the bug was exposed, whilst the first reflects when the original bug was introduced.
CVE-2022-49289: In the Linux kernel, the following vulnerability has been resolved: uaccess: fix integer overflow on access_ok() Three architectures check the end of a user access against the address limit without taking a possible overflow into account. Passing a negative length or another overflow in here returns success when it should not. Use the most common correct implementation here, which optimizes for a constant 'size' argument, and turns the common case into a single comparison.
CVE-2022-49294: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check if modulo is 0 before dividing. [How & Why] If a value of 0 is read, then this will cause a divide-by-0 panic.
CVE-2022-49296: In the Linux kernel, the following vulnerability has been resolved: ceph: fix possible deadlock when holding Fwb to get inline_data 1, mount with wsync. 2, create a file with O_RDWR, and the request was sent to mds.0: ceph_atomic_open()--> ceph_mdsc_do_request(openc) finish_open(file, dentry, ceph_open)--> ceph_open()--> ceph_init_file()--> ceph_init_file_info()--> ceph_uninline_data()--> { ... if (inline_version == 1 || /* initial version, no data */ inline_version == CEPH_INLINE_NONE) goto out_unlock; ... } The inline_version will be 1, which is the initial version for the new create file. And here the ci->i_inline_version will keep with 1, it's buggy. 3, buffer write to the file immediately: ceph_write_iter()--> ceph_get_caps(file, need=Fw, want=Fb, ...); generic_perform_write()--> a_ops->write_begin()--> ceph_write_begin()--> netfs_write_begin()--> netfs_begin_read()--> netfs_rreq_submit_slice()--> netfs_read_from_server()--> rreq->netfs_ops->issue_read()--> ceph_netfs_issue_read()--> { ... if (ci->i_inline_version != CEPH_INLINE_NONE && ceph_netfs_issue_op_inline(subreq)) return; ... } ceph_put_cap_refs(ci, Fwb); The ceph_netfs_issue_op_inline() will send a getattr(Fsr) request to mds.1. 4, then the mds.1 will request the rd lock for CInode::filelock from the auth mds.0, the mds.0 will do the CInode::filelock state transation from excl --> sync, but it need to revoke the Fxwb caps back from the clients. While the kernel client has aleady held the Fwb caps and waiting for the getattr(Fsr). It's deadlock! URL: https://tracker.ceph.com/issues/55377
CVE-2022-49306: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: host: Stop setting the ACPI companion It is no longer needed. The sysdev pointer is now used when assigning the ACPI companions to the xHCI ports and USB devices. Assigning the ACPI companion here resulted in the fwnode->secondary pointer to be replaced also for the parent dwc3 device since the primary fwnode (the ACPI companion) was shared. That was unintentional and it created potential side effects like resource leaks.
CVE-2022-49311: In the Linux kernel, the following vulnerability has been resolved: drivers: staging: rtl8192bs: Fix deadlock in rtw_joinbss_event_prehandle() There is a deadlock in rtw_joinbss_event_prehandle(), which is shown below: (Thread 1) | (Thread 2) | _set_timer() rtw_joinbss_event_prehandle()| mod_timer() spin_lock_bh() //(1) | (wait a time) ... | _rtw_join_timeout_handler() del_timer_sync() | spin_lock_bh() //(2) (wait timer to stop) | ... We hold pmlmepriv->lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need pmlmepriv->lock in position (2) of thread 2. As a result, rtw_joinbss_event_prehandle() will block forever. This patch extracts del_timer_sync() from the protection of spin_lock_bh(), which could let timer handler to obtain the needed lock. What`s more, we change spin_lock_bh() to spin_lock_irq() in _rtw_join_timeout_handler() in order to prevent deadlock.
CVE-2022-49317: In the Linux kernel, the following vulnerability has been resolved: f2fs: avoid infinite loop to flush node pages xfstests/generic/475 can give EIO all the time which give an infinite loop to flush node page like below. Let's avoid it. [16418.518551] Call Trace: [16418.518553] ? dm_submit_bio+0x48/0x400 [16418.518574] ? submit_bio_checks+0x1ac/0x5a0 [16418.525207] __submit_bio+0x1a9/0x230 [16418.525210] ? kmem_cache_alloc+0x29e/0x3c0 [16418.525223] submit_bio_noacct+0xa8/0x2b0 [16418.525226] submit_bio+0x4d/0x130 [16418.525238] __submit_bio+0x49/0x310 [f2fs] [16418.525339] ? bio_add_page+0x6a/0x90 [16418.525344] f2fs_submit_page_bio+0x134/0x1f0 [f2fs] [16418.525365] read_node_page+0x125/0x1b0 [f2fs] [16418.525388] __get_node_page.part.0+0x58/0x3f0 [f2fs] [16418.525409] __get_node_page+0x2f/0x60 [f2fs] [16418.525431] f2fs_get_dnode_of_data+0x423/0x860 [f2fs] [16418.525452] ? asm_sysvec_apic_timer_interrupt+0x12/0x20 [16418.525458] ? __mod_memcg_state.part.0+0x2a/0x30 [16418.525465] ? __mod_memcg_lruvec_state+0x27/0x40 [16418.525467] ? __xa_set_mark+0x57/0x70 [16418.525472] f2fs_do_write_data_page+0x10e/0x7b0 [f2fs] [16418.525493] f2fs_write_single_data_page+0x555/0x830 [f2fs] [16418.525514] ? sysvec_apic_timer_interrupt+0x4e/0x90 [16418.525518] ? asm_sysvec_apic_timer_interrupt+0x12/0x20 [16418.525523] f2fs_write_cache_pages+0x303/0x880 [f2fs] [16418.525545] ? blk_flush_plug_list+0x47/0x100 [16418.525548] f2fs_write_data_pages+0xfd/0x320 [f2fs] [16418.525569] do_writepages+0xd5/0x210 [16418.525648] filemap_fdatawrite_wbc+0x7d/0xc0 [16418.525655] filemap_fdatawrite+0x50/0x70 [16418.525658] f2fs_sync_dirty_inodes+0xa4/0x230 [f2fs] [16418.525679] f2fs_write_checkpoint+0x16d/0x1720 [f2fs] [16418.525699] ? ttwu_do_wakeup+0x1c/0x160 [16418.525709] ? ttwu_do_activate+0x6d/0xd0 [16418.525711] ? __wait_for_common+0x11d/0x150 [16418.525715] kill_f2fs_super+0xca/0x100 [f2fs] [16418.525733] deactivate_locked_super+0x3b/0xb0 [16418.525739] deactivate_super+0x40/0x50 [16418.525741] cleanup_mnt+0x139/0x190 [16418.525747] __cleanup_mnt+0x12/0x20 [16418.525749] task_work_run+0x6d/0xa0 [16418.525765] exit_to_user_mode_prepare+0x1ad/0x1b0 [16418.525771] syscall_exit_to_user_mode+0x27/0x50 [16418.525774] do_syscall_64+0x48/0xc0 [16418.525776] entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2022-49325: In the Linux kernel, the following vulnerability has been resolved: tcp: add accessors to read/set tp->snd_cwnd We had various bugs over the years with code breaking the assumption that tp->snd_cwnd is greater than zero. Lately, syzbot reported the WARN_ON_ONCE(!tp->prior_cwnd) added in commit 8b8a321ff72c ("tcp: fix zero cwnd in tcp_cwnd_reduction") can trigger, and without a repro we would have to spend considerable time finding the bug. Instead of complaining too late, we want to catch where and when tp->snd_cwnd is set to an illegal value.
CVE-2022-49328: In the Linux kernel, the following vulnerability has been resolved: mt76: fix use-after-free by removing a non-RCU wcid pointer Fixes an issue caught by KASAN about use-after-free in mt76_txq_schedule by protecting mtxq->wcid with rcu_lock between mt76_txq_schedule and sta_info_[alloc, free]. [18853.876689] ================================================================== [18853.876751] BUG: KASAN: use-after-free in mt76_txq_schedule+0x204/0xaf8 [mt76] [18853.876773] Read of size 8 at addr ffffffaf989a2138 by task mt76-tx phy0/883 [18853.876786] [18853.876810] CPU: 5 PID: 883 Comm: mt76-tx phy0 Not tainted 5.10.100-fix-510-56778d365941-kasan #5 0b01fbbcf41a530f52043508fec2e31a4215 [18853.876840] Call trace: [18853.876861] dump_backtrace+0x0/0x3ec [18853.876878] show_stack+0x20/0x2c [18853.876899] dump_stack+0x11c/0x1ac [18853.876918] print_address_description+0x74/0x514 [18853.876934] kasan_report+0x134/0x174 [18853.876948] __asan_report_load8_noabort+0x44/0x50 [18853.876976] mt76_txq_schedule+0x204/0xaf8 [mt76 074e03e4640e97fe7405ee1fab547b81c4fa45d2] [18853.877002] mt76_txq_schedule_all+0x2c/0x48 [mt76 074e03e4640e97fe7405ee1fab547b81c4fa45d2] [18853.877030] mt7921_tx_worker+0xa0/0x1cc [mt7921_common f0875ebac9d7b4754e1010549e7db50fbd90a047] [18853.877054] __mt76_worker_fn+0x190/0x22c [mt76 074e03e4640e97fe7405ee1fab547b81c4fa45d2] [18853.877071] kthread+0x2f8/0x3b8 [18853.877087] ret_from_fork+0x10/0x30 [18853.877098] [18853.877112] Allocated by task 941: [18853.877131] kasan_save_stack+0x38/0x68 [18853.877147] __kasan_kmalloc+0xd4/0xfc [18853.877163] kasan_kmalloc+0x10/0x1c [18853.877177] __kmalloc+0x264/0x3c4 [18853.877294] sta_info_alloc+0x460/0xf88 [mac80211] [18853.877410] ieee80211_prep_connection+0x204/0x1ee0 [mac80211] [18853.877523] ieee80211_mgd_auth+0x6c4/0xa4c [mac80211] [18853.877635] ieee80211_auth+0x20/0x2c [mac80211] [18853.877733] rdev_auth+0x7c/0x438 [cfg80211] [18853.877826] cfg80211_mlme_auth+0x26c/0x390 [cfg80211] [18853.877919] nl80211_authenticate+0x6d4/0x904 [cfg80211] [18853.877938] genl_rcv_msg+0x748/0x93c [18853.877954] netlink_rcv_skb+0x160/0x2a8 [18853.877969] genl_rcv+0x3c/0x54 [18853.877985] netlink_unicast_kernel+0x104/0x1ec [18853.877999] netlink_unicast+0x178/0x268 [18853.878015] netlink_sendmsg+0x3cc/0x5f0 [18853.878030] sock_sendmsg+0xb4/0xd8 [18853.878043] ____sys_sendmsg+0x2f8/0x53c [18853.878058] ___sys_sendmsg+0xe8/0x150 [18853.878071] __sys_sendmsg+0xc4/0x1f4 [18853.878087] __arm64_compat_sys_sendmsg+0x88/0x9c [18853.878101] el0_svc_common+0x1b4/0x390 [18853.878115] do_el0_svc_compat+0x8c/0xdc [18853.878131] el0_svc_compat+0x10/0x1c [18853.878146] el0_sync_compat_handler+0xa8/0xcc [18853.878161] el0_sync_compat+0x188/0x1c0 [18853.878171] [18853.878183] Freed by task 10927: [18853.878200] kasan_save_stack+0x38/0x68 [18853.878215] kasan_set_track+0x28/0x3c [18853.878228] kasan_set_free_info+0x24/0x48 [18853.878244] __kasan_slab_free+0x11c/0x154 [18853.878259] kasan_slab_free+0x14/0x24 [18853.878273] slab_free_freelist_hook+0xac/0x1b0 [18853.878287] kfree+0x104/0x390 [18853.878402] sta_info_free+0x198/0x210 [mac80211] [18853.878515] __sta_info_destroy_part2+0x230/0x2d4 [mac80211] [18853.878628] __sta_info_flush+0x300/0x37c [mac80211] [18853.878740] ieee80211_set_disassoc+0x2cc/0xa7c [mac80211] [18853.878851] ieee80211_mgd_deauth+0x4a4/0x10a0 [mac80211] [18853.878962] ieee80211_deauth+0x20/0x2c [mac80211] [18853.879057] rdev_deauth+0x7c/0x438 [cfg80211] [18853.879150] cfg80211_mlme_deauth+0x274/0x414 [cfg80211] [18853.879243] cfg80211_mlme_down+0xe4/0x118 [cfg80211] [18853.879335] cfg80211_disconnect+0x218/0x2d8 [cfg80211] [18853.879427] __cfg80211_leave+0x17c/0x240 [cfg80211] [18853.879519] cfg80211_leave+0x3c/0x58 [cfg80211] [18853.879611] wiphy_suspend+0xdc/0x200 [cfg80211] [18853.879628] dpm_run_callback+0x58/0x408 [18853.879642] __device_suspend+0x4cc/0x864 [18853.879658] async_suspend+0x34/0xf4 [18 ---truncated---
CVE-2022-49342: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: bgmac: Fix refcount leak in bcma_mdio_mii_register of_get_child_by_name() returns a node pointer with refcount incremented, we should use of_node_put() on it when not need anymore. Add missing of_node_put() to avoid refcount leak.
CVE-2022-49359: In the Linux kernel, the following vulnerability has been resolved: drm/panfrost: Job should reference MMU not file_priv For a while now it's been allowed for a MMU context to outlive it's corresponding panfrost_priv, however the job structure still references panfrost_priv to get hold of the MMU context. If panfrost_priv has been freed this is a use-after-free which I've been able to trigger resulting in a splat. To fix this, drop the reference to panfrost_priv in the job structure and add a direct reference to the MMU structure which is what's actually needed.
CVE-2022-49390: In the Linux kernel, the following vulnerability has been resolved: macsec: fix UAF bug for real_dev Create a new macsec device but not get reference to real_dev. That can not ensure that real_dev is freed after macsec. That will trigger the UAF bug for real_dev as following: ================================================================== BUG: KASAN: use-after-free in macsec_get_iflink+0x5f/0x70 drivers/net/macsec.c:3662 Call Trace: ... macsec_get_iflink+0x5f/0x70 drivers/net/macsec.c:3662 dev_get_iflink+0x73/0xe0 net/core/dev.c:637 default_operstate net/core/link_watch.c:42 [inline] rfc2863_policy+0x233/0x2d0 net/core/link_watch.c:54 linkwatch_do_dev+0x2a/0x150 net/core/link_watch.c:161 Allocated by task 22209: ... alloc_netdev_mqs+0x98/0x1100 net/core/dev.c:10549 rtnl_create_link+0x9d7/0xc00 net/core/rtnetlink.c:3235 veth_newlink+0x20e/0xa90 drivers/net/veth.c:1748 Freed by task 8: ... kfree+0xd6/0x4d0 mm/slub.c:4552 kvfree+0x42/0x50 mm/util.c:615 device_release+0x9f/0x240 drivers/base/core.c:2229 kobject_cleanup lib/kobject.c:673 [inline] kobject_release lib/kobject.c:704 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1c8/0x540 lib/kobject.c:721 netdev_run_todo+0x72e/0x10b0 net/core/dev.c:10327 After commit faab39f63c1f ("net: allow out-of-order netdev unregistration") and commit e5f80fcf869a ("ipv6: give an IPv6 dev to blackhole_netdev"), we can add dev_hold_track() in macsec_dev_init() and dev_put_track() in macsec_free_netdev() to fix the problem.
CVE-2022-49398: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: gadget: Replace list_for_each_entry_safe() if using giveback The list_for_each_entry_safe() macro saves the current item (n) and the item after (n+1), so that n can be safely removed without corrupting the list. However, when traversing the list and removing items using gadget giveback, the DWC3 lock is briefly released, allowing other routines to execute. There is a situation where, while items are being removed from the cancelled_list using dwc3_gadget_ep_cleanup_cancelled_requests(), the pullup disable routine is running in parallel (due to UDC unbind). As the cleanup routine removes n, and the pullup disable removes n+1, once the cleanup retakes the DWC3 lock, it references a request who was already removed/handled. With list debug enabled, this leads to a panic. Ensure all instances of the macro are replaced where gadget giveback is used. Example call stack: Thread#1: __dwc3_gadget_ep_set_halt() - CLEAR HALT -> dwc3_gadget_ep_cleanup_cancelled_requests() ->list_for_each_entry_safe() ->dwc3_gadget_giveback(n) ->dwc3_gadget_del_and_unmap_request()- n deleted[cancelled_list] ->spin_unlock ->Thread#2 executes ... ->dwc3_gadget_giveback(n+1) ->Already removed! Thread#2: dwc3_gadget_pullup() ->waiting for dwc3 spin_lock ... ->Thread#1 released lock ->dwc3_stop_active_transfers() ->dwc3_remove_requests() ->fetches n+1 item from cancelled_list (n removed by Thread#1) ->dwc3_gadget_giveback() ->dwc3_gadget_del_and_unmap_request()- n+1 deleted[cancelled_list] ->spin_unlock
CVE-2022-49420: In the Linux kernel, the following vulnerability has been resolved: net: annotate races around sk->sk_bound_dev_if UDP sendmsg() is lockless, and reads sk->sk_bound_dev_if while this field can be changed by another thread. Adds minimal annotations to avoid KCSAN splats for UDP. Following patches will add more annotations to potential lockless readers. BUG: KCSAN: data-race in __ip6_datagram_connect / udpv6_sendmsg write to 0xffff888136d47a94 of 4 bytes by task 7681 on cpu 0: __ip6_datagram_connect+0x6e2/0x930 net/ipv6/datagram.c:221 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272 inet_dgram_connect+0x107/0x190 net/ipv4/af_inet.c:576 __sys_connect_file net/socket.c:1900 [inline] __sys_connect+0x197/0x1b0 net/socket.c:1917 __do_sys_connect net/socket.c:1927 [inline] __se_sys_connect net/socket.c:1924 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1924 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888136d47a94 of 4 bytes by task 7670 on cpu 1: udpv6_sendmsg+0xc60/0x16e0 net/ipv6/udp.c:1436 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:652 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0xffffff9b Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7670 Comm: syz-executor.3 Tainted: G W 5.18.0-rc1-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 I chose to not add Fixes: tag because race has minor consequences and stable teams busy enough.
CVE-2022-49428: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on inline_dots inode As Wenqing reported in bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=215765 It will cause a kernel panic with steps: - mkdir mnt - mount tmp40.img mnt - ls mnt folio_mark_dirty+0x33/0x50 f2fs_add_regular_entry+0x541/0xad0 [f2fs] f2fs_add_dentry+0x6c/0xb0 [f2fs] f2fs_do_add_link+0x182/0x230 [f2fs] __recover_dot_dentries+0x2d6/0x470 [f2fs] f2fs_lookup+0x5af/0x6a0 [f2fs] __lookup_slow+0xac/0x200 lookup_slow+0x45/0x70 walk_component+0x16c/0x250 path_lookupat+0x8b/0x1f0 filename_lookup+0xef/0x250 user_path_at_empty+0x46/0x70 vfs_statx+0x98/0x190 __do_sys_newlstat+0x41/0x90 __x64_sys_newlstat+0x1a/0x30 do_syscall_64+0x37/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xae The root cause is for special file: e.g. character, block, fifo or socket file, f2fs doesn't assign address space operations pointer array for mapping->a_ops field, so, in a fuzzed image, if inline_dots flag was tagged in special file, during lookup(), when f2fs runs into __recover_dot_dentries(), it will cause NULL pointer access once f2fs_add_regular_entry() calls a_ops->set_dirty_page().
CVE-2022-49437: In the Linux kernel, the following vulnerability has been resolved: powerpc/xive: Fix refcount leak in xive_spapr_init of_find_compatible_node() returns a node pointer with refcount incremented, we should use of_node_put() on it when done. Add missing of_node_put() to avoid refcount leak.
CVE-2022-49440: In the Linux kernel, the following vulnerability has been resolved: powerpc/rtas: Keep MSR[RI] set when calling RTAS RTAS runs in real mode (MSR[DR] and MSR[IR] unset) and in 32-bit big endian mode (MSR[SF,LE] unset). The change in MSR is done in enter_rtas() in a relatively complex way, since the MSR value could be hardcoded. Furthermore, a panic has been reported when hitting the watchdog interrupt while running in RTAS, this leads to the following stack trace: watchdog: CPU 24 Hard LOCKUP watchdog: CPU 24 TB:997512652051031, last heartbeat TB:997504470175378 (15980ms ago) ... Supported: No, Unreleased kernel CPU: 24 PID: 87504 Comm: drmgr Kdump: loaded Tainted: G E X 5.14.21-150400.71.1.bz196362_2-default #1 SLE15-SP4 (unreleased) 0d821077ef4faa8dfaf370efb5fdca1fa35f4e2c NIP: 000000001fb41050 LR: 000000001fb4104c CTR: 0000000000000000 REGS: c00000000fc33d60 TRAP: 0100 Tainted: G E X (5.14.21-150400.71.1.bz196362_2-default) MSR: 8000000002981000 <SF,VEC,VSX,ME> CR: 48800002 XER: 20040020 CFAR: 000000000000011c IRQMASK: 1 GPR00: 0000000000000003 ffffffffffffffff 0000000000000001 00000000000050dc GPR04: 000000001ffb6100 0000000000000020 0000000000000001 000000001fb09010 GPR08: 0000000020000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 80040000072a40a8 c00000000ff8b680 0000000000000007 0000000000000034 GPR16: 000000001fbf6e94 000000001fbf6d84 000000001fbd1db0 000000001fb3f008 GPR20: 000000001fb41018 ffffffffffffffff 000000000000017f fffffffffffff68f GPR24: 000000001fb18fe8 000000001fb3e000 000000001fb1adc0 000000001fb1cf40 GPR28: 000000001fb26000 000000001fb460f0 000000001fb17f18 000000001fb17000 NIP [000000001fb41050] 0x1fb41050 LR [000000001fb4104c] 0x1fb4104c Call Trace: Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX Oops: Unrecoverable System Reset, sig: 6 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries ... Supported: No, Unreleased kernel CPU: 24 PID: 87504 Comm: drmgr Kdump: loaded Tainted: G E X 5.14.21-150400.71.1.bz196362_2-default #1 SLE15-SP4 (unreleased) 0d821077ef4faa8dfaf370efb5fdca1fa35f4e2c NIP: 000000001fb41050 LR: 000000001fb4104c CTR: 0000000000000000 REGS: c00000000fc33d60 TRAP: 0100 Tainted: G E X (5.14.21-150400.71.1.bz196362_2-default) MSR: 8000000002981000 <SF,VEC,VSX,ME> CR: 48800002 XER: 20040020 CFAR: 000000000000011c IRQMASK: 1 GPR00: 0000000000000003 ffffffffffffffff 0000000000000001 00000000000050dc GPR04: 000000001ffb6100 0000000000000020 0000000000000001 000000001fb09010 GPR08: 0000000020000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 80040000072a40a8 c00000000ff8b680 0000000000000007 0000000000000034 GPR16: 000000001fbf6e94 000000001fbf6d84 000000001fbd1db0 000000001fb3f008 GPR20: 000000001fb41018 ffffffffffffffff 000000000000017f fffffffffffff68f GPR24: 000000001fb18fe8 000000001fb3e000 000000001fb1adc0 000000001fb1cf40 GPR28: 000000001fb26000 000000001fb460f0 000000001fb17f18 000000001fb17000 NIP [000000001fb41050] 0x1fb41050 LR [000000001fb4104c] 0x1fb4104c Call Trace: Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX ---[ end trace 3ddec07f638c34a2 ]--- This happens because MSR[RI] is unset when entering RTAS but there is no valid reason to not set it here. RTAS is expected to be called with MSR[RI] as specified in PAPR+ section "7.2.1 Machine State": R1–7.2.1–9. If called with MSR[RI] equal to 1, then RTAS must protect its own critical regions from recursion by setting the MSR[RI] bit to 0 when in the critical regions. Fixing this by reviewing the way MSR is compute before calling RTAS. Now a hardcoded value meaning real ---truncated---
CVE-2022-49443: In the Linux kernel, the following vulnerability has been resolved: list: fix a data-race around ep->rdllist ep_poll() first calls ep_events_available() with no lock held and checks if ep->rdllist is empty by list_empty_careful(), which reads rdllist->prev. Thus all accesses to it need some protection to avoid store/load-tearing. Note INIT_LIST_HEAD_RCU() already has the annotation for both prev and next. Commit bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") added the first lockless ep_events_available(), and commit c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") made some ep_events_available() calls lockless and added single call under a lock, finally commit e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") made the last ep_events_available() lockless. BUG: KCSAN: data-race in do_epoll_wait / do_epoll_wait write to 0xffff88810480c7d8 of 8 bytes by task 1802 on cpu 0: INIT_LIST_HEAD include/linux/list.h:38 [inline] list_splice_init include/linux/list.h:492 [inline] ep_start_scan fs/eventpoll.c:622 [inline] ep_send_events fs/eventpoll.c:1656 [inline] ep_poll fs/eventpoll.c:1806 [inline] do_epoll_wait+0x4eb/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88810480c7d8 of 8 bytes by task 1799 on cpu 1: list_empty_careful include/linux/list.h:329 [inline] ep_events_available fs/eventpoll.c:381 [inline] ep_poll fs/eventpoll.c:1797 [inline] do_epoll_wait+0x279/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffff88810480c7d0 -> 0xffff888103c15098 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1799 Comm: syz-fuzzer Tainted: G W 5.17.0-rc7-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
CVE-2022-49444: In the Linux kernel, the following vulnerability has been resolved: module: fix [e_shstrndx].sh_size=0 OOB access It is trivial to craft a module to trigger OOB access in this line: if (info->secstrings[strhdr->sh_size - 1] != '\0') { BUG: unable to handle page fault for address: ffffc90000aa0fff PGD 100000067 P4D 100000067 PUD 100066067 PMD 10436f067 PTE 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 7 PID: 1215 Comm: insmod Not tainted 5.18.0-rc5-00007-g9bf578647087-dirty #10 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:load_module+0x19b/0x2391 [rebased patch onto modules-next]
CVE-2022-49469: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix anon_dev leak in create_subvol() When btrfs_qgroup_inherit(), btrfs_alloc_tree_block, or btrfs_insert_root() fail in create_subvol(), we return without freeing anon_dev. Reorganize the error handling in create_subvol() to fix this.
CVE-2022-49470: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btmtksdio: fix use-after-free at btmtksdio_recv_event We should not access skb buffer data anymore after hci_recv_frame was called. [ 39.634809] BUG: KASAN: use-after-free in btmtksdio_recv_event+0x1b0 [ 39.634855] Read of size 1 at addr ffffff80cf28a60d by task kworker [ 39.634962] Call trace: [ 39.634974] dump_backtrace+0x0/0x3b8 [ 39.634999] show_stack+0x20/0x2c [ 39.635016] dump_stack_lvl+0x60/0x78 [ 39.635040] print_address_description+0x70/0x2f0 [ 39.635062] kasan_report+0x154/0x194 [ 39.635079] __asan_report_load1_noabort+0x44/0x50 [ 39.635099] btmtksdio_recv_event+0x1b0/0x1c4 [ 39.635129] btmtksdio_txrx_work+0x6cc/0xac4 [ 39.635157] process_one_work+0x560/0xc5c [ 39.635177] worker_thread+0x7ec/0xcc0 [ 39.635195] kthread+0x2d0/0x3d0 [ 39.635215] ret_from_fork+0x10/0x20 [ 39.635247] Allocated by task 0: [ 39.635260] (stack is not available) [ 39.635281] Freed by task 2392: [ 39.635295] kasan_save_stack+0x38/0x68 [ 39.635319] kasan_set_track+0x28/0x3c [ 39.635338] kasan_set_free_info+0x28/0x4c [ 39.635357] ____kasan_slab_free+0x104/0x150 [ 39.635374] __kasan_slab_free+0x18/0x28 [ 39.635391] slab_free_freelist_hook+0x114/0x248 [ 39.635410] kfree+0xf8/0x2b4 [ 39.635427] skb_free_head+0x58/0x98 [ 39.635447] skb_release_data+0x2f4/0x410 [ 39.635464] skb_release_all+0x50/0x60 [ 39.635481] kfree_skb+0xc8/0x25c [ 39.635498] hci_event_packet+0x894/0xca4 [bluetooth] [ 39.635721] hci_rx_work+0x1c8/0x68c [bluetooth] [ 39.635925] process_one_work+0x560/0xc5c [ 39.635951] worker_thread+0x7ec/0xcc0 [ 39.635970] kthread+0x2d0/0x3d0 [ 39.635990] ret_from_fork+0x10/0x20 [ 39.636021] The buggy address belongs to the object at ffffff80cf28a600 which belongs to the cache kmalloc-512 of size 512 [ 39.636039] The buggy address is located 13 bytes inside of 512-byte region [ffffff80cf28a600, ffffff80cf28a800)
CVE-2022-49496: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: prevent kernel crash when rmmod mtk-vcodec-dec.ko If the driver support subdev mode, the parameter "dev->pm.dev" will be NULL in mtk_vcodec_dec_remove. Kernel will crash when try to rmmod mtk-vcodec-dec.ko. [ 4380.702726] pc : do_raw_spin_trylock+0x4/0x80 [ 4380.707075] lr : _raw_spin_lock_irq+0x90/0x14c [ 4380.711509] sp : ffff80000819bc10 [ 4380.714811] x29: ffff80000819bc10 x28: ffff3600c03e4000 x27: 0000000000000000 [ 4380.721934] x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 [ 4380.729057] x23: ffff3600c0f34930 x22: ffffd5e923549000 x21: 0000000000000220 [ 4380.736179] x20: 0000000000000208 x19: ffffd5e9213e8ebc x18: 0000000000000020 [ 4380.743298] x17: 0000002000000000 x16: ffffd5e9213e8e90 x15: 696c346f65646976 [ 4380.750420] x14: 0000000000000000 x13: 0000000000000001 x12: 0000000000000040 [ 4380.757542] x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 [ 4380.764664] x8 : 0000000000000000 x7 : ffff3600c7273ae8 x6 : ffffd5e9213e8ebc [ 4380.771786] x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 [ 4380.778908] x2 : 0000000000000000 x1 : ffff3600c03e4000 x0 : 0000000000000208 [ 4380.786031] Call trace: [ 4380.788465] do_raw_spin_trylock+0x4/0x80 [ 4380.792462] __pm_runtime_disable+0x2c/0x1b0 [ 4380.796723] mtk_vcodec_dec_remove+0x5c/0xa0 [mtk_vcodec_dec] [ 4380.802466] platform_remove+0x2c/0x60 [ 4380.806204] __device_release_driver+0x194/0x250 [ 4380.810810] driver_detach+0xc8/0x15c [ 4380.814462] bus_remove_driver+0x5c/0xb0 [ 4380.818375] driver_unregister+0x34/0x64 [ 4380.822288] platform_driver_unregister+0x18/0x24 [ 4380.826979] mtk_vcodec_dec_driver_exit+0x1c/0x888 [mtk_vcodec_dec] [ 4380.833240] __arm64_sys_delete_module+0x190/0x224 [ 4380.838020] invoke_syscall+0x48/0x114 [ 4380.841760] el0_svc_common.constprop.0+0x60/0x11c [ 4380.846540] do_el0_svc+0x28/0x90 [ 4380.849844] el0_svc+0x4c/0x100 [ 4380.852975] el0t_64_sync_handler+0xec/0xf0 [ 4380.857148] el0t_64_sync+0x190/0x194 [ 4380.860801] Code: 94431515 17ffffca d503201f d503245f (b9400004)
CVE-2022-49504: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Inhibit aborts if external loopback plug is inserted After running a short external loopback test, when the external loopback is removed and a normal cable inserted that is directly connected to a target device, the system oops in the llpfc_set_rrq_active() routine. When the loopback was inserted an FLOGI was transmit. As we're looped back, we receive the FLOGI request. The FLOGI is ABTS'd as we recognize the same wppn thus understand it's a loopback. However, as the ABTS sends address information the port is not set to (fffffe), the ABTS is dropped on the wire. A short 1 frame loopback test is run and completes before the ABTS times out. The looback is unplugged and the new cable plugged in, and the an FLOGI to the new device occurs and completes. Due to a mixup in ref counting the completion of the new FLOGI releases the fabric ndlp. Then the original ABTS completes and references the released ndlp generating the oops. Correct by no-op'ing the ABTS when in loopback mode (it will be dropped anyway). Added a flag to track the mode to recognize when it should be no-op'd.
CVE-2022-49509: In the Linux kernel, the following vulnerability has been resolved: media: i2c: max9286: fix kernel oops when removing module When removing the max9286 module we get a kernel oops: Unable to handle kernel paging request at virtual address 000000aa00000094 Mem abort info: ESR = 0x96000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=0000000880d85000 [000000aa00000094] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 96000004 [#1] PREEMPT SMP Modules linked in: fsl_jr_uio caam_jr rng_core libdes caamkeyblob_desc caamhash_desc caamalg_desc crypto_engine max9271 authenc crct10dif_ce mxc_jpeg_encdec CPU: 2 PID: 713 Comm: rmmod Tainted: G C 5.15.5-00057-gaebcd29c8ed7-dirty #5 Hardware name: Freescale i.MX8QXP MEK (DT) pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : i2c_mux_del_adapters+0x24/0xf0 lr : max9286_remove+0x28/0xd0 [max9286] sp : ffff800013a9bbf0 x29: ffff800013a9bbf0 x28: ffff00080b6da940 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 x23: ffff000801a5b970 x22: ffff0008048b0890 x21: ffff800009297000 x20: ffff0008048b0f70 x19: 000000aa00000064 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000014 x13: 0000000000000000 x12: ffff000802da49e8 x11: ffff000802051918 x10: ffff000802da4920 x9 : ffff000800030098 x8 : 0101010101010101 x7 : 7f7f7f7f7f7f7f7f x6 : fefefeff6364626d x5 : 8080808000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : ffffffffffffffff x1 : ffff00080b6da940 x0 : 0000000000000000 Call trace: i2c_mux_del_adapters+0x24/0xf0 max9286_remove+0x28/0xd0 [max9286] i2c_device_remove+0x40/0x110 __device_release_driver+0x188/0x234 driver_detach+0xc4/0x150 bus_remove_driver+0x60/0xe0 driver_unregister+0x34/0x64 i2c_del_driver+0x58/0xa0 max9286_i2c_driver_exit+0x1c/0x490 [max9286] __arm64_sys_delete_module+0x194/0x260 invoke_syscall+0x48/0x114 el0_svc_common.constprop.0+0xd4/0xfc do_el0_svc+0x2c/0x94 el0_svc+0x28/0x80 el0t_64_sync_handler+0xa8/0x130 el0t_64_sync+0x1a0/0x1a4 The Oops happens because the I2C client data does not point to max9286_priv anymore but to v4l2_subdev. The change happened in max9286_init() which calls v4l2_i2c_subdev_init() later on... Besides fixing the max9286_remove() function, remove the call to i2c_set_clientdata() in max9286_probe(), to avoid confusion, and make the necessary changes to max9286_init() so that it doesn't have to use i2c_get_clientdata() in order to fetch the pointer to priv.
CVE-2022-49513: In the Linux kernel, the following vulnerability has been resolved: cpufreq: governor: Use kobject release() method to free dbs_data The struct dbs_data embeds a struct gov_attr_set and the struct gov_attr_set embeds a kobject. Since every kobject must have a release() method and we can't use kfree() to free it directly, so introduce cpufreq_dbs_data_release() to release the dbs_data via the kobject::release() method. This fixes the calltrace like below: ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x34 WARNING: CPU: 12 PID: 810 at lib/debugobjects.c:505 debug_print_object+0xb8/0x100 Modules linked in: CPU: 12 PID: 810 Comm: sh Not tainted 5.16.0-next-20220120-yocto-standard+ #536 Hardware name: Marvell OcteonTX CN96XX board (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : debug_print_object+0xb8/0x100 lr : debug_print_object+0xb8/0x100 sp : ffff80001dfcf9a0 x29: ffff80001dfcf9a0 x28: 0000000000000001 x27: ffff0001464f0000 x26: 0000000000000000 x25: ffff8000090e3f00 x24: ffff80000af60210 x23: ffff8000094dfb78 x22: ffff8000090e3f00 x21: ffff0001080b7118 x20: ffff80000aeb2430 x19: ffff800009e8f5e0 x18: 0000000000000000 x17: 0000000000000002 x16: 00004d62e58be040 x15: 013590470523aff8 x14: ffff8000090e1828 x13: 0000000001359047 x12: 00000000f5257d14 x11: 0000000000040591 x10: 0000000066c1ffea x9 : ffff8000080d15e0 x8 : ffff80000a1765a8 x7 : 0000000000000000 x6 : 0000000000000001 x5 : ffff800009e8c000 x4 : ffff800009e8c760 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0001474ed040 Call trace: debug_print_object+0xb8/0x100 __debug_check_no_obj_freed+0x1d0/0x25c debug_check_no_obj_freed+0x24/0xa0 kfree+0x11c/0x440 cpufreq_dbs_governor_exit+0xa8/0xac cpufreq_exit_governor+0x44/0x90 cpufreq_set_policy+0x29c/0x570 store_scaling_governor+0x110/0x154 store+0xb0/0xe0 sysfs_kf_write+0x58/0x84 kernfs_fop_write_iter+0x12c/0x1c0 new_sync_write+0xf0/0x18c vfs_write+0x1cc/0x220 ksys_write+0x74/0x100 __arm64_sys_write+0x28/0x3c invoke_syscall.constprop.0+0x58/0xf0 do_el0_svc+0x70/0x170 el0_svc+0x54/0x190 el0t_64_sync_handler+0xa4/0x130 el0t_64_sync+0x1a0/0x1a4 irq event stamp: 189006 hardirqs last enabled at (189005): [<ffff8000080849d0>] finish_task_switch.isra.0+0xe0/0x2c0 hardirqs last disabled at (189006): [<ffff8000090667a4>] el1_dbg+0x24/0xa0 softirqs last enabled at (188966): [<ffff8000080106d0>] __do_softirq+0x4b0/0x6a0 softirqs last disabled at (188957): [<ffff80000804a618>] __irq_exit_rcu+0x108/0x1a4 [ rjw: Because can be freed by the gov_attr_set_put() in cpufreq_dbs_governor_exit() now, it is also necessary to put the invocation of the governor ->exit() callback into the new cpufreq_dbs_data_release() function. ]
CVE-2022-49528: In the Linux kernel, the following vulnerability has been resolved: media: i2c: dw9714: Disable the regulator when the driver fails to probe When the driver fails to probe, we will get the following splat: [ 59.305988] ------------[ cut here ]------------ [ 59.306417] WARNING: CPU: 2 PID: 395 at drivers/regulator/core.c:2257 _regulator_put+0x3ec/0x4e0 [ 59.310345] RIP: 0010:_regulator_put+0x3ec/0x4e0 [ 59.318362] Call Trace: [ 59.318582] <TASK> [ 59.318765] regulator_put+0x1f/0x30 [ 59.319058] devres_release_group+0x319/0x3d0 [ 59.319420] i2c_device_probe+0x766/0x940 Fix this by disabling the regulator in error handling.
CVE-2022-49531: In the Linux kernel, the following vulnerability has been resolved: loop: implement ->free_disk Ensure that the lo_device which is stored in the gendisk private data is valid until the gendisk is freed. Currently the loop driver uses a lot of effort to make sure a device is not freed when it is still in use, but to to fix a potential deadlock this will be relaxed a bit soon.
CVE-2022-49533: In the Linux kernel, the following vulnerability has been resolved: ath11k: Change max no of active probe SSID and BSSID to fw capability The maximum number of SSIDs in a for active probe requests is currently reported as 16 (WLAN_SCAN_PARAMS_MAX_SSID) when registering the driver. The scan_req_params structure only has the capacity to hold 10 SSIDs. This leads to a buffer overflow which can be triggered from wpa_supplicant in userspace. When copying the SSIDs into the scan_req_params structure in the ath11k_mac_op_hw_scan route, it can overwrite the extraie pointer. Firmware supports 16 ssid * 4 bssid, for each ssid 4 bssid combo probe request will be sent, so totally 64 probe requests supported. So set both max ssid and bssid to 16 and 4 respectively. Remove the redundant macros of ssid and bssid. Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01300-QCAHKSWPL_SILICONZ-1
CVE-2022-49534: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Protect memory leak for NPIV ports sending PLOGI_RJT There is a potential memory leak in lpfc_ignore_els_cmpl() and lpfc_els_rsp_reject() that was allocated from NPIV PLOGI_RJT (lpfc_rcv_plogi()'s login_mbox). Check if cmdiocb->context_un.mbox was allocated in lpfc_ignore_els_cmpl(), and then free it back to phba->mbox_mem_pool along with mbox->ctx_buf for service parameters. For lpfc_els_rsp_reject() failure, free both the ctx_buf for service parameters and the login_mbox.
CVE-2022-49536: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Fix SCSI I/O completion and abort handler deadlock During stress I/O tests with 500+ vports, hard LOCKUP call traces are observed. CPU A: native_queued_spin_lock_slowpath+0x192 _raw_spin_lock_irqsave+0x32 lpfc_handle_fcp_err+0x4c6 lpfc_fcp_io_cmd_wqe_cmpl+0x964 lpfc_sli4_fp_handle_cqe+0x266 __lpfc_sli4_process_cq+0x105 __lpfc_sli4_hba_process_cq+0x3c lpfc_cq_poll_hdler+0x16 irq_poll_softirq+0x76 __softirqentry_text_start+0xe4 irq_exit+0xf7 do_IRQ+0x7f CPU B: native_queued_spin_lock_slowpath+0x5b _raw_spin_lock+0x1c lpfc_abort_handler+0x13e scmd_eh_abort_handler+0x85 process_one_work+0x1a7 worker_thread+0x30 kthread+0x112 ret_from_fork+0x1f Diagram of lockup: CPUA CPUB ---- ---- lpfc_cmd->buf_lock phba->hbalock lpfc_cmd->buf_lock phba->hbalock Fix by reordering the taking of the lpfc_cmd->buf_lock and phba->hbalock in lpfc_abort_handler routine so that it tries to take the lpfc_cmd->buf_lock first before phba->hbalock.
CVE-2022-49543: In the Linux kernel, the following vulnerability has been resolved: ath11k: fix the warning of dev_wake in mhi_pm_disable_transition() When test device recovery with below command, it has warning in message as below. echo assert > /sys/kernel/debug/ath11k/wcn6855\ hw2.0/simulate_fw_crash echo assert > /sys/kernel/debug/ath11k/qca6390\ hw2.0/simulate_fw_crash warning message: [ 1965.642121] ath11k_pci 0000:06:00.0: simulating firmware assert crash [ 1968.471364] ieee80211 phy0: Hardware restart was requested [ 1968.511305] ------------[ cut here ]------------ [ 1968.511368] WARNING: CPU: 3 PID: 1546 at drivers/bus/mhi/core/pm.c:505 mhi_pm_disable_transition+0xb37/0xda0 [mhi] [ 1968.511443] Modules linked in: ath11k_pci ath11k mac80211 libarc4 cfg80211 qmi_helpers qrtr_mhi mhi qrtr nvme nvme_core [ 1968.511563] CPU: 3 PID: 1546 Comm: kworker/u17:0 Kdump: loaded Tainted: G W 5.17.0-rc3-wt-ath+ #579 [ 1968.511629] Hardware name: Intel(R) Client Systems NUC8i7HVK/NUC8i7HVB, BIOS HNKBLi70.86A.0067.2021.0528.1339 05/28/2021 [ 1968.511704] Workqueue: mhi_hiprio_wq mhi_pm_st_worker [mhi] [ 1968.511787] RIP: 0010:mhi_pm_disable_transition+0xb37/0xda0 [mhi] [ 1968.511870] Code: a9 fe ff ff 4c 89 ff 44 89 04 24 e8 03 46 f6 e5 44 8b 04 24 41 83 f8 01 0f 84 21 fe ff ff e9 4c fd ff ff 0f 0b e9 af f8 ff ff <0f> 0b e9 5c f8 ff ff 48 89 df e8 da 9e ee e3 e9 12 fd ff ff 4c 89 [ 1968.511923] RSP: 0018:ffffc900024efbf0 EFLAGS: 00010286 [ 1968.511969] RAX: 00000000ffffffff RBX: ffff88811d241250 RCX: ffffffffc0176922 [ 1968.512014] RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff888118a90a24 [ 1968.512059] RBP: ffff888118a90800 R08: 0000000000000000 R09: ffff888118a90a27 [ 1968.512102] R10: ffffed1023152144 R11: 0000000000000001 R12: ffff888118a908ac [ 1968.512229] R13: ffff888118a90928 R14: dffffc0000000000 R15: ffff888118a90a24 [ 1968.512310] FS: 0000000000000000(0000) GS:ffff888234200000(0000) knlGS:0000000000000000 [ 1968.512405] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1968.512493] CR2: 00007f5538f443a8 CR3: 000000016dc28001 CR4: 00000000003706e0 [ 1968.512587] Call Trace: [ 1968.512672] <TASK> [ 1968.512751] ? _raw_spin_unlock_irq+0x1f/0x40 [ 1968.512859] mhi_pm_st_worker+0x3ac/0x790 [mhi] [ 1968.512959] ? mhi_pm_mission_mode_transition.isra.0+0x7d0/0x7d0 [mhi] [ 1968.513063] process_one_work+0x86a/0x1400 [ 1968.513184] ? pwq_dec_nr_in_flight+0x230/0x230 [ 1968.513312] ? move_linked_works+0x125/0x290 [ 1968.513416] worker_thread+0x6db/0xf60 [ 1968.513536] ? process_one_work+0x1400/0x1400 [ 1968.513627] kthread+0x241/0x2d0 [ 1968.513733] ? kthread_complete_and_exit+0x20/0x20 [ 1968.513821] ret_from_fork+0x22/0x30 [ 1968.513924] </TASK> Reason is mhi_deassert_dev_wake() from mhi_device_put() is called but mhi_assert_dev_wake() from __mhi_device_get_sync() is not called in progress of recovery. Commit 8e0559921f9a ("bus: mhi: core: Skip device wake in error or shutdown state") add check for the pm_state of mhi in __mhi_device_get_sync(), and the pm_state is not the normal state untill recovery is completed, so it leads the dev_wake is not 0 and above warning print in mhi_pm_disable_transition() while checking mhi_cntrl->dev_wake. Add check in ath11k_pci_write32()/ath11k_pci_read32() to skip call mhi_device_put() if mhi_device_get_sync() does not really do wake, then the warning gone. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2
CVE-2022-49562: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use __try_cmpxchg_user() to update guest PTE A/D bits Use the recently introduced __try_cmpxchg_user() to update guest PTE A/D bits instead of mapping the PTE into kernel address space. The VM_PFNMAP path is broken as it assumes that vm_pgoff is the base pfn of the mapped VMA range, which is conceptually wrong as vm_pgoff is the offset relative to the file and has nothing to do with the pfn. The horrific hack worked for the original use case (backing guest memory with /dev/mem), but leads to accessing "random" pfns for pretty much any other VM_PFNMAP case.
CVE-2022-49563: In the Linux kernel, the following vulnerability has been resolved: crypto: qat - add param check for RSA Reject requests with a source buffer that is bigger than the size of the key. This is to prevent a possible integer underflow that might happen when copying the source scatterlist into a linear buffer.
CVE-2022-49564: In the Linux kernel, the following vulnerability has been resolved: crypto: qat - add param check for DH Reject requests with a source buffer that is bigger than the size of the key. This is to prevent a possible integer underflow that might happen when copying the source scatterlist into a linear buffer.
CVE-2022-49566: In the Linux kernel, the following vulnerability has been resolved: crypto: qat - fix memory leak in RSA When an RSA key represented in form 2 (as defined in PKCS #1 V2.1) is used, some components of the private key persist even after the TFM is released. Replace the explicit calls to free the buffers in qat_rsa_exit_tfm() with a call to qat_rsa_clear_ctx() which frees all buffers referenced in the TFM context.
CVE-2022-49579: In the Linux kernel, the following vulnerability has been resolved: ipv4: Fix data-races around sysctl_fib_multipath_hash_policy. While reading sysctl_fib_multipath_hash_policy, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers.
CVE-2022-49588: In the Linux kernel, the following vulnerability has been resolved: tcp: Fix data-races around sysctl_tcp_migrate_req. While reading sysctl_tcp_migrate_req, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers.
CVE-2022-49591: In the Linux kernel, the following vulnerability has been resolved: net: dsa: microchip: ksz_common: Fix refcount leak bug In ksz_switch_register(), we should call of_node_put() for the reference returned by of_get_child_by_name() which has increased the refcount.
CVE-2022-49610: In the Linux kernel, the following vulnerability has been resolved: KVM: VMX: Prevent RSB underflow before vmenter On VMX, there are some balanced returns between the time the guest's SPEC_CTRL value is written, and the vmenter. Balanced returns (matched by a preceding call) are usually ok, but it's at least theoretically possible an NMI with a deep call stack could empty the RSB before one of the returns. For maximum paranoia, don't allow *any* returns (balanced or otherwise) between the SPEC_CTRL write and the vmenter. [ bp: Fix 32-bit build. ]
CVE-2022-49616: In the Linux kernel, the following vulnerability has been resolved: ASoC: rt7*-sdw: harden jack_detect_handler Realtek headset codec drivers typically check if the card is instantiated before proceeding with the jack detection. The rt700, rt711 and rt711-sdca are however missing a check on the card pointer, which can lead to NULL dereferences encountered in driver bind/unbind tests.
CVE-2022-49617: In the Linux kernel, the following vulnerability has been resolved: ASoC: Intel: sof_sdw: handle errors on card registration If the card registration fails, typically because of deferred probes, the device properties added for headset codecs are not removed, which leads to kernel oopses in driver bind/unbind tests. We already clean-up the device properties when the card is removed, this code can be moved as a helper and called upon card registration errors.
CVE-2022-49622: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: avoid skb access on nf_stolen When verdict is NF_STOLEN, the skb might have been freed. When tracing is enabled, this can result in a use-after-free: 1. access to skb->nf_trace 2. access to skb->mark 3. computation of trace id 4. dump of packet payload To avoid 1, keep a cached copy of skb->nf_trace in the trace state struct. Refresh this copy whenever verdict is != STOLEN. Avoid 2 by skipping skb->mark access if verdict is STOLEN. 3 is avoided by precomputing the trace id. Only dump the packet when verdict is not "STOLEN".
CVE-2022-49623: In the Linux kernel, the following vulnerability has been resolved: powerpc/xive/spapr: correct bitmap allocation size kasan detects access beyond the end of the xibm->bitmap allocation: BUG: KASAN: slab-out-of-bounds in _find_first_zero_bit+0x40/0x140 Read of size 8 at addr c00000001d1d0118 by task swapper/0/1 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.19.0-rc2-00001-g90df023b36dd #28 Call Trace: [c00000001d98f770] [c0000000012baab8] dump_stack_lvl+0xac/0x108 (unreliable) [c00000001d98f7b0] [c00000000068faac] print_report+0x37c/0x710 [c00000001d98f880] [c0000000006902c0] kasan_report+0x110/0x354 [c00000001d98f950] [c000000000692324] __asan_load8+0xa4/0xe0 [c00000001d98f970] [c0000000011c6ed0] _find_first_zero_bit+0x40/0x140 [c00000001d98f9b0] [c0000000000dbfbc] xive_spapr_get_ipi+0xcc/0x260 [c00000001d98fa70] [c0000000000d6d28] xive_setup_cpu_ipi+0x1e8/0x450 [c00000001d98fb30] [c000000004032a20] pSeries_smp_probe+0x5c/0x118 [c00000001d98fb60] [c000000004018b44] smp_prepare_cpus+0x944/0x9ac [c00000001d98fc90] [c000000004009f9c] kernel_init_freeable+0x2d4/0x640 [c00000001d98fd90] [c0000000000131e8] kernel_init+0x28/0x1d0 [c00000001d98fe10] [c00000000000cd54] ret_from_kernel_thread+0x5c/0x64 Allocated by task 0: kasan_save_stack+0x34/0x70 __kasan_kmalloc+0xb4/0xf0 __kmalloc+0x268/0x540 xive_spapr_init+0x4d0/0x77c pseries_init_irq+0x40/0x27c init_IRQ+0x44/0x84 start_kernel+0x2a4/0x538 start_here_common+0x1c/0x20 The buggy address belongs to the object at c00000001d1d0118 which belongs to the cache kmalloc-8 of size 8 The buggy address is located 0 bytes inside of 8-byte region [c00000001d1d0118, c00000001d1d0120) The buggy address belongs to the physical page: page:c00c000000074740 refcount:1 mapcount:0 mapping:0000000000000000 index:0xc00000001d1d0558 pfn:0x1d1d flags: 0x7ffff000000200(slab|node=0|zone=0|lastcpupid=0x7ffff) raw: 007ffff000000200 c00000001d0003c8 c00000001d0003c8 c00000001d010480 raw: c00000001d1d0558 0000000001e1000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: c00000001d1d0000: fc 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc c00000001d1d0080: fc fc 00 fc fc fc fc fc fc fc fc fc fc fc fc fc >c00000001d1d0100: fc fc fc 02 fc fc fc fc fc fc fc fc fc fc fc fc ^ c00000001d1d0180: fc fc fc fc 04 fc fc fc fc fc fc fc fc fc fc fc c00000001d1d0200: fc fc fc fc fc 04 fc fc fc fc fc fc fc fc fc fc This happens because the allocation uses the wrong unit (bits) when it should pass (BITS_TO_LONGS(count) * sizeof(long)) or equivalent. With small numbers of bits, the allocated object can be smaller than sizeof(long), which results in invalid accesses. Use bitmap_zalloc() to allocate and initialize the irq bitmap, paired with bitmap_free() for consistency.
CVE-2022-49630: In the Linux kernel, the following vulnerability has been resolved: tcp: Fix a data-race around sysctl_tcp_ecn_fallback. While reading sysctl_tcp_ecn_fallback, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.
CVE-2022-49632: In the Linux kernel, the following vulnerability has been resolved: icmp: Fix a data-race around sysctl_icmp_errors_use_inbound_ifaddr. While reading sysctl_icmp_errors_use_inbound_ifaddr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.
CVE-2022-49635: In the Linux kernel, the following vulnerability has been resolved: drm/i915/selftests: fix subtraction overflow bug On some machines hole_end can be small enough to cause subtraction overflow. On the other side (addr + 2 * min_alignment) can overflow in case of mock tests. This patch should handle both cases. (cherry picked from commit ab3edc679c552a466e4bf0b11af3666008bd65a2)
CVE-2022-49650: In the Linux kernel, the following vulnerability has been resolved: dmaengine: qcom: bam_dma: fix runtime PM underflow Commit dbad41e7bb5f ("dmaengine: qcom: bam_dma: check if the runtime pm enabled") caused unbalanced pm_runtime_get/put() calls when the bam is controlled remotely. This commit reverts it and just enables pm_runtime in all cases, the clk_* functions already just nop when the clock is NULL. Also clean up a bit by removing unnecessary bamclk null checks.
CVE-2022-49651: In the Linux kernel, the following vulnerability has been resolved: srcu: Tighten cleanup_srcu_struct() GP checks Currently, cleanup_srcu_struct() checks for a grace period in progress, but it does not check for a grace period that has not yet started but which might start at any time. Such a situation could result in a use-after-free bug, so this commit adds a check for a grace period that is needed but not yet started to cleanup_srcu_struct().
CVE-2022-49654: In the Linux kernel, the following vulnerability has been resolved: net: dsa: qca8k: reset cpu port on MTU change It was discovered that the Documentation lacks of a fundamental detail on how to correctly change the MAX_FRAME_SIZE of the switch. In fact if the MAX_FRAME_SIZE is changed while the cpu port is on, the switch panics and cease to send any packet. This cause the mgmt ethernet system to not receive any packet (the slow fallback still works) and makes the device not reachable. To recover from this a switch reset is required. To correctly handle this, turn off the cpu ports before changing the MAX_FRAME_SIZE and turn on again after the value is applied.
CVE-2022-49666: In the Linux kernel, the following vulnerability has been resolved: powerpc/memhotplug: Add add_pages override for PPC With commit ffa0b64e3be5 ("powerpc: Fix virt_addr_valid() for 64-bit Book3E & 32-bit") the kernel now validate the addr against high_memory value. This results in the below BUG_ON with dax pfns. [ 635.798741][T26531] kernel BUG at mm/page_alloc.c:5521! 1:mon> e cpu 0x1: Vector: 700 (Program Check) at [c000000007287630] pc: c00000000055ed48: free_pages.part.0+0x48/0x110 lr: c00000000053ca70: tlb_finish_mmu+0x80/0xd0 sp: c0000000072878d0 msr: 800000000282b033 current = 0xc00000000afabe00 paca = 0xc00000037ffff300 irqmask: 0x03 irq_happened: 0x05 pid = 26531, comm = 50-landscape-sy kernel BUG at :5521! Linux version 5.19.0-rc3-14659-g4ec05be7c2e1 (kvaneesh@ltc-boston8) (gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0, GNU ld (GNU Binutils for Ubuntu) 2.34) #625 SMP Thu Jun 23 00:35:43 CDT 2022 1:mon> t [link register ] c00000000053ca70 tlb_finish_mmu+0x80/0xd0 [c0000000072878d0] c00000000053ca54 tlb_finish_mmu+0x64/0xd0 (unreliable) [c000000007287900] c000000000539424 exit_mmap+0xe4/0x2a0 [c0000000072879e0] c00000000019fc1c mmput+0xcc/0x210 [c000000007287a20] c000000000629230 begin_new_exec+0x5e0/0xf40 [c000000007287ae0] c00000000070b3cc load_elf_binary+0x3ac/0x1e00 [c000000007287c10] c000000000627af0 bprm_execve+0x3b0/0xaf0 [c000000007287cd0] c000000000628414 do_execveat_common.isra.0+0x1e4/0x310 [c000000007287d80] c00000000062858c sys_execve+0x4c/0x60 [c000000007287db0] c00000000002c1b0 system_call_exception+0x160/0x2c0 [c000000007287e10] c00000000000c53c system_call_common+0xec/0x250 The fix is to make sure we update high_memory on memory hotplug. This is similar to what x86 does in commit 3072e413e305 ("mm/memory_hotplug: introduce add_pages")
CVE-2022-49722: In the Linux kernel, the following vulnerability has been resolved: ice: Fix memory corruption in VF driver Disable VF's RX/TX queues, when it's disabled. VF can have queues enabled, when it requests a reset. If PF driver assumes that VF is disabled, while VF still has queues configured, VF may unmap DMA resources. In such scenario device still can map packets to memory, which ends up silently corrupting it. Previously, VF driver could experience memory corruption, which lead to crash: [ 5119.170157] BUG: unable to handle kernel paging request at 00001b9780003237 [ 5119.170166] PGD 0 P4D 0 [ 5119.170173] Oops: 0002 [#1] PREEMPT_RT SMP PTI [ 5119.170181] CPU: 30 PID: 427592 Comm: kworker/u96:2 Kdump: loaded Tainted: G W I --------- - - 4.18.0-372.9.1.rt7.166.el8.x86_64 #1 [ 5119.170189] Hardware name: Dell Inc. PowerEdge R740/014X06, BIOS 2.3.10 08/15/2019 [ 5119.170193] Workqueue: iavf iavf_adminq_task [iavf] [ 5119.170219] RIP: 0010:__page_frag_cache_drain+0x5/0x30 [ 5119.170238] Code: 0f 0f b6 77 51 85 f6 74 07 31 d2 e9 05 df ff ff e9 90 fe ff ff 48 8b 05 49 db 33 01 eb b4 0f 1f 80 00 00 00 00 0f 1f 44 00 00 <f0> 29 77 34 74 01 c3 48 8b 07 f6 c4 80 74 0f 0f b6 77 51 85 f6 74 [ 5119.170244] RSP: 0018:ffffa43b0bdcfd78 EFLAGS: 00010282 [ 5119.170250] RAX: ffffffff896b3e40 RBX: ffff8fb282524000 RCX: 0000000000000002 [ 5119.170254] RDX: 0000000049000000 RSI: 0000000000000000 RDI: 00001b9780003203 [ 5119.170259] RBP: ffff8fb248217b00 R08: 0000000000000022 R09: 0000000000000009 [ 5119.170262] R10: 2b849d6300000000 R11: 0000000000000020 R12: 0000000000000000 [ 5119.170265] R13: 0000000000001000 R14: 0000000000000009 R15: 0000000000000000 [ 5119.170269] FS: 0000000000000000(0000) GS:ffff8fb1201c0000(0000) knlGS:0000000000000000 [ 5119.170274] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5119.170279] CR2: 00001b9780003237 CR3: 00000008f3e1a003 CR4: 00000000007726e0 [ 5119.170283] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5119.170286] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5119.170290] PKRU: 55555554 [ 5119.170292] Call Trace: [ 5119.170298] iavf_clean_rx_ring+0xad/0x110 [iavf] [ 5119.170324] iavf_free_rx_resources+0xe/0x50 [iavf] [ 5119.170342] iavf_free_all_rx_resources.part.51+0x30/0x40 [iavf] [ 5119.170358] iavf_virtchnl_completion+0xd8a/0x15b0 [iavf] [ 5119.170377] ? iavf_clean_arq_element+0x210/0x280 [iavf] [ 5119.170397] iavf_adminq_task+0x126/0x2e0 [iavf] [ 5119.170416] process_one_work+0x18f/0x420 [ 5119.170429] worker_thread+0x30/0x370 [ 5119.170437] ? process_one_work+0x420/0x420 [ 5119.170445] kthread+0x151/0x170 [ 5119.170452] ? set_kthread_struct+0x40/0x40 [ 5119.170460] ret_from_fork+0x35/0x40 [ 5119.170477] Modules linked in: iavf sctp ip6_udp_tunnel udp_tunnel mlx4_en mlx4_core nfp tls vhost_net vhost vhost_iotlb tap tun xt_CHECKSUM ipt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink bridge stp llc rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache sunrpc intel_rapl_msr iTCO_wdt iTCO_vendor_support dell_smbios wmi_bmof dell_wmi_descriptor dcdbas kvm_intel kvm irqbypass intel_rapl_common isst_if_common skx_edac irdma nfit libnvdimm x86_pkg_temp_thermal i40e intel_powerclamp coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ib_uverbs rapl ipmi_ssif intel_cstate intel_uncore mei_me pcspkr acpi_ipmi ib_core mei lpc_ich i2c_i801 ipmi_si ipmi_devintf wmi ipmi_msghandler acpi_power_meter xfs libcrc32c sd_mod t10_pi sg mgag200 drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ice ahci drm libahci crc32c_intel libata tg3 megaraid_sas [ 5119.170613] i2c_algo_bit dm_mirror dm_region_hash dm_log dm_mod fuse [last unloaded: iavf] [ 5119.170627] CR2: 00001b9780003237
CVE-2022-49742: In the Linux kernel, the following vulnerability has been resolved: f2fs: initialize locks earlier in f2fs_fill_super() syzbot is reporting lockdep warning at f2fs_handle_error() [1], for spin_lock(&sbi->error_lock) is called before spin_lock_init() is called. For safe locking in error handling, move initialization of locks (and obvious structures) in f2fs_fill_super() to immediately after memory allocation.
CVE-2022-49758: In the Linux kernel, the following vulnerability has been resolved: reset: uniphier-glue: Fix possible null-ptr-deref It will cause null-ptr-deref when resource_size(res) invoked, if platform_get_resource() returns NULL.
CVE-2022-49764: In the Linux kernel, the following vulnerability has been resolved: bpf: Prevent bpf program recursion for raw tracepoint probes We got report from sysbot [1] about warnings that were caused by bpf program attached to contention_begin raw tracepoint triggering the same tracepoint by using bpf_trace_printk helper that takes trace_printk_lock lock. Call Trace: <TASK> ? trace_event_raw_event_bpf_trace_printk+0x5f/0x90 bpf_trace_printk+0x2b/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 bpf_trace_printk+0x3f/0xe0 bpf_prog_a9aec6167c091eef_prog+0x1f/0x24 bpf_trace_run2+0x26/0x90 native_queued_spin_lock_slowpath+0x1c6/0x2b0 _raw_spin_lock_irqsave+0x44/0x50 __unfreeze_partials+0x5b/0x160 ... The can be reproduced by attaching bpf program as raw tracepoint on contention_begin tracepoint. The bpf prog calls bpf_trace_printk helper. Then by running perf bench the spin lock code is forced to take slow path and call contention_begin tracepoint. Fixing this by skipping execution of the bpf program if it's already running, Using bpf prog 'active' field, which is being currently used by trampoline programs for the same reason. Moving bpf_prog_inc_misses_counter to syscall.c because trampoline.c is compiled in just for CONFIG_BPF_JIT option. [1] https://lore.kernel.org/bpf/YxhFe3EwqchC%2FfYf@krava/T/#t
CVE-2022-49765: In the Linux kernel, the following vulnerability has been resolved: net/9p: use a dedicated spinlock for trans_fd Shamelessly copying the explanation from Tetsuo Handa's suggested patch[1] (slightly reworded): syzbot is reporting inconsistent lock state in p9_req_put()[2], for p9_tag_remove() from p9_req_put() from IRQ context is using spin_lock_irqsave() on "struct p9_client"->lock but trans_fd (not from IRQ context) is using spin_lock(). Since the locks actually protect different things in client.c and in trans_fd.c, just replace trans_fd.c's lock by a new one specific to the transport (client.c's protect the idr for fid/tag allocations, while trans_fd.c's protects its own req list and request status field that acts as the transport's state machine)
CVE-2022-49766: In the Linux kernel, the following vulnerability has been resolved: netlink: Bounds-check struct nlmsgerr creation In preparation for FORTIFY_SOURCE doing bounds-check on memcpy(), switch from __nlmsg_put to nlmsg_put(), and explain the bounds check for dealing with the memcpy() across a composite flexible array struct. Avoids this future run-time warning: memcpy: detected field-spanning write (size 32) of single field "&errmsg->msg" at net/netlink/af_netlink.c:2447 (size 16)
CVE-2022-49801: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix memory leak in tracing_read_pipe() kmemleak reports this issue: unreferenced object 0xffff888105a18900 (size 128): comm "test_progs", pid 18933, jiffies 4336275356 (age 22801.766s) hex dump (first 32 bytes): 25 73 00 90 81 88 ff ff 26 05 00 00 42 01 58 04 %s......&...B.X. 03 00 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000560143a1>] __kmalloc_node_track_caller+0x4a/0x140 [<000000006af00822>] krealloc+0x8d/0xf0 [<00000000c309be6a>] trace_iter_expand_format+0x99/0x150 [<000000005a53bdb6>] trace_check_vprintf+0x1e0/0x11d0 [<0000000065629d9d>] trace_event_printf+0xb6/0xf0 [<000000009a690dc7>] trace_raw_output_bpf_trace_printk+0x89/0xc0 [<00000000d22db172>] print_trace_line+0x73c/0x1480 [<00000000cdba76ba>] tracing_read_pipe+0x45c/0x9f0 [<0000000015b58459>] vfs_read+0x17b/0x7c0 [<000000004aeee8ed>] ksys_read+0xed/0x1c0 [<0000000063d3d898>] do_syscall_64+0x3b/0x90 [<00000000a06dda7f>] entry_SYSCALL_64_after_hwframe+0x63/0xcd iter->fmt alloced in tracing_read_pipe() -> .. ->trace_iter_expand_format(), but not freed, to fix, add free in tracing_release_pipe()
CVE-2022-49803: In the Linux kernel, the following vulnerability has been resolved: netdevsim: Fix memory leak of nsim_dev->fa_cookie kmemleak reports this issue: unreferenced object 0xffff8881bac872d0 (size 8): comm "sh", pid 58603, jiffies 4481524462 (age 68.065s) hex dump (first 8 bytes): 04 00 00 00 de ad be ef ........ backtrace: [<00000000c80b8577>] __kmalloc+0x49/0x150 [<000000005292b8c6>] nsim_dev_trap_fa_cookie_write+0xc1/0x210 [netdevsim] [<0000000093d78e77>] full_proxy_write+0xf3/0x180 [<000000005a662c16>] vfs_write+0x1c5/0xaf0 [<000000007aabf84a>] ksys_write+0xed/0x1c0 [<000000005f1d2e47>] do_syscall_64+0x3b/0x90 [<000000006001c6ec>] entry_SYSCALL_64_after_hwframe+0x63/0xcd The issue occurs in the following scenarios: nsim_dev_trap_fa_cookie_write() kmalloc() fa_cookie nsim_dev->fa_cookie = fa_cookie .. nsim_drv_remove() The fa_cookie allocked in nsim_dev_trap_fa_cookie_write() is not freed. To fix, add kfree(nsim_dev->fa_cookie) to nsim_drv_remove().
CVE-2022-49822: In the Linux kernel, the following vulnerability has been resolved: cifs: Fix connections leak when tlink setup failed If the tlink setup failed, lost to put the connections, then the module refcnt leak since the cifsd kthread not exit. Also leak the fscache info, and for next mount with fsc, it will print the follow errors: CIFS: Cache volume key already in use (cifs,127.0.0.1:445,TEST) Let's check the result of tlink setup, and do some cleanup.
CVE-2022-49828: In the Linux kernel, the following vulnerability has been resolved: hugetlbfs: don't delete error page from pagecache This change is very similar to the change that was made for shmem [1], and it solves the same problem but for HugeTLBFS instead. Currently, when poison is found in a HugeTLB page, the page is removed from the page cache. That means that attempting to map or read that hugepage in the future will result in a new hugepage being allocated instead of notifying the user that the page was poisoned. As [1] states, this is effectively memory corruption. The fix is to leave the page in the page cache. If the user attempts to use a poisoned HugeTLB page with a syscall, the syscall will fail with EIO, the same error code that shmem uses. For attempts to map the page, the thread will get a BUS_MCEERR_AR SIGBUS. [1]: commit a76054266661 ("mm: shmem: don't truncate page if memory failure happens")
CVE-2022-49829: In the Linux kernel, the following vulnerability has been resolved: drm/scheduler: fix fence ref counting We leaked dependency fences when processes were beeing killed. Additional to that grab a reference to the last scheduled fence.
CVE-2022-49837: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix memory leaks in __check_func_call kmemleak reports this issue: unreferenced object 0xffff88817139d000 (size 2048): comm "test_progs", pid 33246, jiffies 4307381979 (age 45851.820s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000045f075f0>] kmalloc_trace+0x27/0xa0 [<0000000098b7c90a>] __check_func_call+0x316/0x1230 [<00000000b4c3c403>] check_helper_call+0x172e/0x4700 [<00000000aa3875b7>] do_check+0x21d8/0x45e0 [<000000001147357b>] do_check_common+0x767/0xaf0 [<00000000b5a595b4>] bpf_check+0x43e3/0x5bc0 [<0000000011e391b1>] bpf_prog_load+0xf26/0x1940 [<0000000007f765c0>] __sys_bpf+0xd2c/0x3650 [<00000000839815d6>] __x64_sys_bpf+0x75/0xc0 [<00000000946ee250>] do_syscall_64+0x3b/0x90 [<0000000000506b7f>] entry_SYSCALL_64_after_hwframe+0x63/0xcd The root case here is: In function prepare_func_exit(), the callee is not released in the abnormal scenario after "state->curframe--;". To fix, move "state->curframe--;" to the very bottom of the function, right when we free callee and reset frame[] pointer to NULL, as Andrii suggested. In addition, function __check_func_call() has a similar problem. In the abnormal scenario before "state->curframe++;", the callee also should be released by free_func_state().
CVE-2022-49858: In the Linux kernel, the following vulnerability has been resolved: octeontx2-pf: Fix SQE threshold checking Current way of checking available SQE count which is based on HW updated SQB count could result in driver submitting an SQE even before CQE for the previously transmitted SQE at the same index is processed in NAPI resulting losing SKB pointers, hence a leak. Fix this by checking a consumer index which is updated once CQE is processed.
CVE-2022-49898: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix tree mod log mishandling of reallocated nodes We have been seeing the following panic in production kernel BUG at fs/btrfs/tree-mod-log.c:677! invalid opcode: 0000 [#1] SMP RIP: 0010:tree_mod_log_rewind+0x1b4/0x200 RSP: 0000:ffffc9002c02f890 EFLAGS: 00010293 RAX: 0000000000000003 RBX: ffff8882b448c700 RCX: 0000000000000000 RDX: 0000000000008000 RSI: 00000000000000a7 RDI: ffff88877d831c00 RBP: 0000000000000002 R08: 000000000000009f R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000100c40 R12: 0000000000000001 R13: ffff8886c26d6a00 R14: ffff88829f5424f8 R15: ffff88877d831a00 FS: 00007fee1d80c780(0000) GS:ffff8890400c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fee1963a020 CR3: 0000000434f33002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: btrfs_get_old_root+0x12b/0x420 btrfs_search_old_slot+0x64/0x2f0 ? tree_mod_log_oldest_root+0x3d/0xf0 resolve_indirect_ref+0xfd/0x660 ? ulist_alloc+0x31/0x60 ? kmem_cache_alloc_trace+0x114/0x2c0 find_parent_nodes+0x97a/0x17e0 ? ulist_alloc+0x30/0x60 btrfs_find_all_roots_safe+0x97/0x150 iterate_extent_inodes+0x154/0x370 ? btrfs_search_path_in_tree+0x240/0x240 iterate_inodes_from_logical+0x98/0xd0 ? btrfs_search_path_in_tree+0x240/0x240 btrfs_ioctl_logical_to_ino+0xd9/0x180 btrfs_ioctl+0xe2/0x2ec0 ? __mod_memcg_lruvec_state+0x3d/0x280 ? do_sys_openat2+0x6d/0x140 ? kretprobe_dispatcher+0x47/0x70 ? kretprobe_rethook_handler+0x38/0x50 ? rethook_trampoline_handler+0x82/0x140 ? arch_rethook_trampoline_callback+0x3b/0x50 ? kmem_cache_free+0xfb/0x270 ? do_sys_openat2+0xd5/0x140 __x64_sys_ioctl+0x71/0xb0 do_syscall_64+0x2d/0x40 Which is this code in tree_mod_log_rewind() switch (tm->op) { case BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING: BUG_ON(tm->slot < n); This occurs because we replay the nodes in order that they happened, and when we do a REPLACE we will log a REMOVE_WHILE_FREEING for every slot, starting at 0. 'n' here is the number of items in this block, which in this case was 1, but we had 2 REMOVE_WHILE_FREEING operations. The actual root cause of this was that we were replaying operations for a block that shouldn't have been replayed. Consider the following sequence of events 1. We have an already modified root, and we do a btrfs_get_tree_mod_seq(). 2. We begin removing items from this root, triggering KEY_REPLACE for it's child slots. 3. We remove one of the 2 children this root node points to, thus triggering the root node promotion of the remaining child, and freeing this node. 4. We modify a new root, and re-allocate the above node to the root node of this other root. The tree mod log looks something like this logical 0 op KEY_REPLACE (slot 1) seq 2 logical 0 op KEY_REMOVE (slot 1) seq 3 logical 0 op KEY_REMOVE_WHILE_FREEING (slot 0) seq 4 logical 4096 op LOG_ROOT_REPLACE (old logical 0) seq 5 logical 8192 op KEY_REMOVE_WHILE_FREEING (slot 1) seq 6 logical 8192 op KEY_REMOVE_WHILE_FREEING (slot 0) seq 7 logical 0 op LOG_ROOT_REPLACE (old logical 8192) seq 8 >From here the bug is triggered by the following steps 1. Call btrfs_get_old_root() on the new_root. 2. We call tree_mod_log_oldest_root(btrfs_root_node(new_root)), which is currently logical 0. 3. tree_mod_log_oldest_root() calls tree_mod_log_search_oldest(), which gives us the KEY_REPLACE seq 2, and since that's not a LOG_ROOT_REPLACE we incorrectly believe that we don't have an old root, because we expect that the most recent change should be a LOG_ROOT_REPLACE. 4. Back in tree_mod_log_oldest_root() we don't have a LOG_ROOT_REPLACE, so we don't set old_root, we simply use our e ---truncated---
CVE-2022-49901: In the Linux kernel, the following vulnerability has been resolved: blk-mq: Fix kmemleak in blk_mq_init_allocated_queue There is a kmemleak caused by modprobe null_blk.ko unreferenced object 0xffff8881acb1f000 (size 1024): comm "modprobe", pid 836, jiffies 4294971190 (age 27.068s) hex dump (first 32 bytes): 00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00 .....N.......... ff ff ff ff ff ff ff ff 00 53 99 9e ff ff ff ff .........S...... backtrace: [<000000004a10c249>] kmalloc_node_trace+0x22/0x60 [<00000000648f7950>] blk_mq_alloc_and_init_hctx+0x289/0x350 [<00000000af06de0e>] blk_mq_realloc_hw_ctxs+0x2fe/0x3d0 [<00000000e00c1872>] blk_mq_init_allocated_queue+0x48c/0x1440 [<00000000d16b4e68>] __blk_mq_alloc_disk+0xc8/0x1c0 [<00000000d10c98c3>] 0xffffffffc450d69d [<00000000b9299f48>] 0xffffffffc4538392 [<0000000061c39ed6>] do_one_initcall+0xd0/0x4f0 [<00000000b389383b>] do_init_module+0x1a4/0x680 [<0000000087cf3542>] load_module+0x6249/0x7110 [<00000000beba61b8>] __do_sys_finit_module+0x140/0x200 [<00000000fdcfff51>] do_syscall_64+0x35/0x80 [<000000003c0f1f71>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 That is because q->ma_ops is set to NULL before blk_release_queue is called. blk_mq_init_queue_data blk_mq_init_allocated_queue blk_mq_realloc_hw_ctxs for (i = 0; i < set->nr_hw_queues; i++) { old_hctx = xa_load(&q->hctx_table, i); if (!blk_mq_alloc_and_init_hctx(.., i, ..)) [1] if (!old_hctx) break; xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); [2] if (!q->nr_hw_queues) [3] goto err_hctxs; err_exit: q->mq_ops = NULL; [4] blk_put_queue blk_release_queue if (queue_is_mq(q)) [5] blk_mq_release(q); [1]: blk_mq_alloc_and_init_hctx failed at i != 0. [2]: The hctxs allocated by [1] are moved to q->unused_hctx_list and will be cleaned up in blk_mq_release. [3]: q->nr_hw_queues is 0. [4]: Set q->mq_ops to NULL. [5]: queue_is_mq returns false due to [4]. And blk_mq_release will not be called. The hctxs in q->unused_hctx_list are leaked. To fix it, call blk_release_queue in exception path.
CVE-2022-49932: In the Linux kernel, the following vulnerability has been resolved: KVM: VMX: Do _all_ initialization before exposing /dev/kvm to userspace Call kvm_init() only after _all_ setup is complete, as kvm_init() exposes /dev/kvm to userspace and thus allows userspace to create VMs (and call other ioctls). E.g. KVM will encounter a NULL pointer when attempting to add a vCPU to the per-CPU loaded_vmcss_on_cpu list if userspace is able to create a VM before vmx_init() configures said list. BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP CPU: 6 PID: 1143 Comm: stable Not tainted 6.0.0-rc7+ #988 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:vmx_vcpu_load_vmcs+0x68/0x230 [kvm_intel] <TASK> vmx_vcpu_load+0x16/0x60 [kvm_intel] kvm_arch_vcpu_load+0x32/0x1f0 [kvm] vcpu_load+0x2f/0x40 [kvm] kvm_arch_vcpu_create+0x231/0x310 [kvm] kvm_vm_ioctl+0x79f/0xe10 [kvm] ? handle_mm_fault+0xb1/0x220 __x64_sys_ioctl+0x80/0xb0 do_syscall_64+0x2b/0x50 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f5a6b05743b </TASK> Modules linked in: vhost_net vhost vhost_iotlb tap kvm_intel(+) kvm irqbypass
CVE-2022-49935: In the Linux kernel, the following vulnerability has been resolved: dma-buf/dma-resv: check if the new fence is really later Previously when we added a fence to a dma_resv object we always assumed the the newer than all the existing fences. With Jason's work to add an UAPI to explicit export/import that's not necessary the case any more. So without this check we would allow userspace to force the kernel into an use after free error. Since the change is very small and defensive it's probably a good idea to backport this to stable kernels as well just in case others are using the dma_resv object in the same way.
CVE-2022-49938: In the Linux kernel, the following vulnerability has been resolved: cifs: fix small mempool leak in SMB2_negotiate() In some cases of failure (dialect mismatches) in SMB2_negotiate(), after the request is sent, the checks would return -EIO when they should be rather setting rc = -EIO and jumping to neg_exit to free the response buffer from mempool.
CVE-2022-49961: In the Linux kernel, the following vulnerability has been resolved: bpf: Do mark_chain_precision for ARG_CONST_ALLOC_SIZE_OR_ZERO Precision markers need to be propagated whenever we have an ARG_CONST_* style argument, as the verifier cannot consider imprecise scalars to be equivalent for the purposes of states_equal check when such arguments refine the return value (in this case, set mem_size for PTR_TO_MEM). The resultant mem_size for the R0 is derived from the constant value, and if the verifier incorrectly prunes states considering them equivalent where such arguments exist (by seeing that both registers have reg->precise as false in regsafe), we can end up with invalid programs passing the verifier which can do access beyond what should have been the correct mem_size in that explored state. To show a concrete example of the problem: 0000000000000000 <prog>: 0: r2 = *(u32 *)(r1 + 80) 1: r1 = *(u32 *)(r1 + 76) 2: r3 = r1 3: r3 += 4 4: if r3 > r2 goto +18 <LBB5_5> 5: w2 = 0 6: *(u32 *)(r1 + 0) = r2 7: r1 = *(u32 *)(r1 + 0) 8: r2 = 1 9: if w1 == 0 goto +1 <LBB5_3> 10: r2 = -1 0000000000000058 <LBB5_3>: 11: r1 = 0 ll 13: r3 = 0 14: call bpf_ringbuf_reserve 15: if r0 == 0 goto +7 <LBB5_5> 16: r1 = r0 17: r1 += 16777215 18: w2 = 0 19: *(u8 *)(r1 + 0) = r2 20: r1 = r0 21: r2 = 0 22: call bpf_ringbuf_submit 00000000000000b8 <LBB5_5>: 23: w0 = 0 24: exit For the first case, the single line execution's exploration will prune the search at insn 14 for the branch insn 9's second leg as it will be verified first using r2 = -1 (UINT_MAX), while as w1 at insn 9 will always be 0 so at runtime we don't get error for being greater than UINT_MAX/4 from bpf_ringbuf_reserve. The verifier during regsafe just sees reg->precise as false for both r2 registers in both states, hence considers them equal for purposes of states_equal. If we propagated precise markers using the backtracking support, we would use the precise marking to then ensure that old r2 (UINT_MAX) was within the new r2 (1) and this would never be true, so the verification would rightfully fail. The end result is that the out of bounds access at instruction 19 would be permitted without this fix. Note that reg->precise is always set to true when user does not have CAP_BPF (or when subprog count is greater than 1 (i.e. use of any static or global functions)), hence this is only a problem when precision marks need to be explicitly propagated (i.e. privileged users with CAP_BPF). A simplified test case has been included in the next patch to prevent future regressions.
CVE-2022-49967: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix a data-race around bpf_jit_limit. While reading bpf_jit_limit, it can be changed concurrently via sysctl, WRITE_ONCE() in __do_proc_doulongvec_minmax(). The size of bpf_jit_limit is long, so we need to add a paired READ_ONCE() to avoid load-tearing.
CVE-2022-49980: In the Linux kernel, the following vulnerability has been resolved: USB: gadget: Fix use-after-free Read in usb_udc_uevent() The syzbot fuzzer found a race between uevent callbacks and gadget driver unregistration that can cause a use-after-free bug: --------------------------------------------------------------- BUG: KASAN: use-after-free in usb_udc_uevent+0x11f/0x130 drivers/usb/gadget/udc/core.c:1732 Read of size 8 at addr ffff888078ce2050 by task udevd/2968 CPU: 1 PID: 2968 Comm: udevd Not tainted 5.19.0-rc4-next-20220628-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/29/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold+0x2ba/0x719 mm/kasan/report.c:433 kasan_report+0xbe/0x1f0 mm/kasan/report.c:495 usb_udc_uevent+0x11f/0x130 drivers/usb/gadget/udc/core.c:1732 dev_uevent+0x290/0x770 drivers/base/core.c:2424 --------------------------------------------------------------- The bug occurs because usb_udc_uevent() dereferences udc->driver but does so without acquiring the udc_lock mutex, which protects this field. If the gadget driver is unbound from the udc concurrently with uevent processing, the driver structure may be accessed after it has been deallocated. To prevent the race, we make sure that the routine holds the mutex around the racing accesses.
CVE-2022-49997: In the Linux kernel, the following vulnerability has been resolved: net: lantiq_xrx200: restore buffer if memory allocation failed In a situation where memory allocation fails, an invalid buffer address is stored. When this descriptor is used again, the system panics in the build_skb() function when accessing memory.
CVE-2022-50000: In the Linux kernel, the following vulnerability has been resolved: netfilter: flowtable: fix stuck flows on cleanup due to pending work To clear the flow table on flow table free, the following sequence normally happens in order: 1) gc_step work is stopped to disable any further stats/del requests. 2) All flow table entries are set to teardown state. 3) Run gc_step which will queue HW del work for each flow table entry. 4) Waiting for the above del work to finish (flush). 5) Run gc_step again, deleting all entries from the flow table. 6) Flow table is freed. But if a flow table entry already has pending HW stats or HW add work step 3 will not queue HW del work (it will be skipped), step 4 will wait for the pending add/stats to finish, and step 5 will queue HW del work which might execute after freeing of the flow table. To fix the above, this patch flushes the pending work, then it sets the teardown flag to all flows in the flowtable and it forces a garbage collector run to queue work to remove the flows from hardware, then it flushes this new pending work and (finally) it forces another garbage collector run to remove the entry from the software flowtable. Stack trace: [47773.882335] BUG: KASAN: use-after-free in down_read+0x99/0x460 [47773.883634] Write of size 8 at addr ffff888103b45aa8 by task kworker/u20:6/543704 [47773.885634] CPU: 3 PID: 543704 Comm: kworker/u20:6 Not tainted 5.12.0-rc7+ #2 [47773.886745] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009) [47773.888438] Workqueue: nf_ft_offload_del flow_offload_work_handler [nf_flow_table] [47773.889727] Call Trace: [47773.890214] dump_stack+0xbb/0x107 [47773.890818] print_address_description.constprop.0+0x18/0x140 [47773.892990] kasan_report.cold+0x7c/0xd8 [47773.894459] kasan_check_range+0x145/0x1a0 [47773.895174] down_read+0x99/0x460 [47773.899706] nf_flow_offload_tuple+0x24f/0x3c0 [nf_flow_table] [47773.907137] flow_offload_work_handler+0x72d/0xbe0 [nf_flow_table] [47773.913372] process_one_work+0x8ac/0x14e0 [47773.921325] [47773.921325] Allocated by task 592159: [47773.922031] kasan_save_stack+0x1b/0x40 [47773.922730] __kasan_kmalloc+0x7a/0x90 [47773.923411] tcf_ct_flow_table_get+0x3cb/0x1230 [act_ct] [47773.924363] tcf_ct_init+0x71c/0x1156 [act_ct] [47773.925207] tcf_action_init_1+0x45b/0x700 [47773.925987] tcf_action_init+0x453/0x6b0 [47773.926692] tcf_exts_validate+0x3d0/0x600 [47773.927419] fl_change+0x757/0x4a51 [cls_flower] [47773.928227] tc_new_tfilter+0x89a/0x2070 [47773.936652] [47773.936652] Freed by task 543704: [47773.937303] kasan_save_stack+0x1b/0x40 [47773.938039] kasan_set_track+0x1c/0x30 [47773.938731] kasan_set_free_info+0x20/0x30 [47773.939467] __kasan_slab_free+0xe7/0x120 [47773.940194] slab_free_freelist_hook+0x86/0x190 [47773.941038] kfree+0xce/0x3a0 [47773.941644] tcf_ct_flow_table_cleanup_work Original patch description and stack trace by Paul Blakey.
CVE-2022-50009: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix null-ptr-deref in f2fs_get_dnode_of_data There is issue as follows when test f2fs atomic write: F2FS-fs (loop0): Can't find valid F2FS filesystem in 2th superblock F2FS-fs (loop0): invalid crc_offset: 0 F2FS-fs (loop0): f2fs_check_nid_range: out-of-range nid=1, run fsck to fix. F2FS-fs (loop0): f2fs_check_nid_range: out-of-range nid=2, run fsck to fix. ================================================================== BUG: KASAN: null-ptr-deref in f2fs_get_dnode_of_data+0xac/0x16d0 Read of size 8 at addr 0000000000000028 by task rep/1990 CPU: 4 PID: 1990 Comm: rep Not tainted 5.19.0-rc6-next-20220715 #266 Call Trace: <TASK> dump_stack_lvl+0x6e/0x91 print_report.cold+0x49a/0x6bb kasan_report+0xa8/0x130 f2fs_get_dnode_of_data+0xac/0x16d0 f2fs_do_write_data_page+0x2a5/0x1030 move_data_page+0x3c5/0xdf0 do_garbage_collect+0x2015/0x36c0 f2fs_gc+0x554/0x1d30 f2fs_balance_fs+0x7f5/0xda0 f2fs_write_single_data_page+0xb66/0xdc0 f2fs_write_cache_pages+0x716/0x1420 f2fs_write_data_pages+0x84f/0x9a0 do_writepages+0x130/0x3a0 filemap_fdatawrite_wbc+0x87/0xa0 file_write_and_wait_range+0x157/0x1c0 f2fs_do_sync_file+0x206/0x12d0 f2fs_sync_file+0x99/0xc0 vfs_fsync_range+0x75/0x140 f2fs_file_write_iter+0xd7b/0x1850 vfs_write+0x645/0x780 ksys_write+0xf1/0x1e0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd As 3db1de0e582c commit changed atomic write way which new a cow_inode for atomic write file, and also mark cow_inode as FI_ATOMIC_FILE. When f2fs_do_write_data_page write cow_inode will use cow_inode's cow_inode which is NULL. Then will trigger null-ptr-deref. To solve above issue, introduce FI_COW_FILE flag for COW inode. Fiexes: 3db1de0e582c("f2fs: change the current atomic write way")
CVE-2022-50011: In the Linux kernel, the following vulnerability has been resolved: venus: pm_helpers: Fix warning in OPP during probe Fix the following WARN triggered during Venus driver probe on 5.19.0-rc8-next-20220728: WARNING: CPU: 7 PID: 339 at drivers/opp/core.c:2471 dev_pm_opp_set_config+0x49c/0x610 Modules linked in: qcom_spmi_adc5 rtc_pm8xxx qcom_spmi_adc_tm5 leds_qcom_lpg led_class_multicolor qcom_pon qcom_vadc_common venus_core(+) qcom_spmi_temp_alarm v4l2_mem2mem videobuf2_v4l2 msm(+) videobuf2_common crct10dif_ce spi_geni_qcom snd_soc_sm8250 i2c_qcom_geni gpu_sched snd_soc_qcom_common videodev qcom_q6v5_pas soundwire_qcom drm_dp_aux_bus qcom_stats drm_display_helper qcom_pil_info soundwire_bus snd_soc_lpass_va_macro mc qcom_q6v5 phy_qcom_snps_femto_v2 qcom_rng snd_soc_lpass_macro_common snd_soc_lpass_wsa_macro lpass_gfm_sm8250 slimbus qcom_sysmon qcom_common qcom_glink_smem qmi_helpers qcom_wdt mdt_loader socinfo icc_osm_l3 display_connector drm_kms_helper qnoc_sm8250 drm fuse ip_tables x_tables ipv6 CPU: 7 PID: 339 Comm: systemd-udevd Not tainted 5.19.0-rc8-next-20220728 #4 Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT) pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : dev_pm_opp_set_config+0x49c/0x610 lr : dev_pm_opp_set_config+0x58/0x610 sp : ffff8000093c3710 x29: ffff8000093c3710 x28: ffffbca3959d82b8 x27: ffff8000093c3d00 x26: ffffbca3959d8e08 x25: ffff4396cac98118 x24: ffff4396c0e24810 x23: ffff4396c4272c40 x22: ffff4396c0e24810 x21: ffff8000093c3810 x20: ffff4396cac36800 x19: ffff4396cac96800 x18: 0000000000000000 x17: 0000000000000003 x16: ffffbca3f4edf198 x15: 0000001cba64a858 x14: 0000000000000180 x13: 000000000000017e x12: 0000000000000000 x11: 0000000000000002 x10: 0000000000000a60 x9 : ffff8000093c35c0 x8 : ffff4396c4273700 x7 : ffff43983efca6c0 x6 : ffff43983efca640 x5 : 00000000410fd0d0 x4 : ffff4396c4272c40 x3 : ffffbca3f5d1e008 x2 : 0000000000000000 x1 : ffff4396c2421600 x0 : ffff4396cac96860 Call trace: dev_pm_opp_set_config+0x49c/0x610 devm_pm_opp_set_config+0x18/0x70 vcodec_domains_get+0xb8/0x1638 [venus_core] core_get_v4+0x1d8/0x218 [venus_core] venus_probe+0xf4/0x468 [venus_core] platform_probe+0x68/0xd8 really_probe+0xbc/0x2a8 __driver_probe_device+0x78/0xe0 driver_probe_device+0x3c/0xf0 __driver_attach+0x70/0x120 bus_for_each_dev+0x70/0xc0 driver_attach+0x24/0x30 bus_add_driver+0x150/0x200 driver_register+0x64/0x120 __platform_driver_register+0x28/0x38 qcom_venus_driver_init+0x24/0x1000 [venus_core] do_one_initcall+0x54/0x1c8 do_init_module+0x44/0x1d0 load_module+0x16c8/0x1aa0 __do_sys_finit_module+0xbc/0x110 __arm64_sys_finit_module+0x20/0x30 invoke_syscall+0x44/0x108 el0_svc_common.constprop.0+0xcc/0xf0 do_el0_svc+0x2c/0xb8 el0_svc+0x2c/0x88 el0t_64_sync_handler+0xb8/0xc0 el0t_64_sync+0x18c/0x190 qcom-venus: probe of aa00000.video-codec failed with error -16 The fix is re-ordering the code related to OPP core. The OPP core expects all configuration options to be provided before the OPP table is added.
CVE-2022-50015: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda-ipc: Do not process IPC reply before firmware boot It is not yet clear, but it is possible to create a firmware so broken that it will send a reply message before a FW_READY message (it is not yet clear if FW_READY will arrive later). Since the reply_data is allocated only after the FW_READY message, this will lead to a NULL pointer dereference if not filtered out. The issue was reported with IPC4 firmware but the same condition is present for IPC3.
CVE-2022-50016: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: cnl: Do not process IPC reply before firmware boot It is not yet clear, but it is possible to create a firmware so broken that it will send a reply message before a FW_READY message (it is not yet clear if FW_READY will arrive later). Since the reply_data is allocated only after the FW_READY message, this will lead to a NULL pointer dereference if not filtered out. The issue was reported with IPC4 firmware but the same condition is present for IPC3.
CVE-2022-50023: In the Linux kernel, the following vulnerability has been resolved: dmaengine: dw-axi-dmac: ignore interrupt if no descriptor If the channel has no descriptor and the interrupt is raised then the kernel will OOPS. Check the result of vchan_next_desc() in the handler axi_chan_block_xfer_complete() to avoid the error happening.
CVE-2022-50026: In the Linux kernel, the following vulnerability has been resolved: habanalabs/gaudi: fix shift out of bounds When validating NIC queues, queue offset calculation must be performed only for NIC queues.
CVE-2022-50050: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda: Fix potential buffer overflow by snprintf() snprintf() returns the would-be-filled size when the string overflows the given buffer size, hence using this value may result in the buffer overflow (although it's unrealistic). This patch replaces with a safer version, scnprintf() for papering over such a potential issue.
CVE-2022-50053: In the Linux kernel, the following vulnerability has been resolved: iavf: Fix reset error handling Do not call iavf_close in iavf_reset_task error handling. Doing so can lead to double call of napi_disable, which can lead to deadlock there. Removing VF would lead to iavf_remove task being stuck, because it requires crit_lock, which is held by iavf_close. Call iavf_disable_vf if reset fail, so that driver will clean up remaining invalid resources. During rapid VF resets, HW can fail to setup VF mailbox. Wrong error handling can lead to iavf_remove being stuck with: [ 5218.999087] iavf 0000:82:01.0: Failed to init adminq: -53 ... [ 5267.189211] INFO: task repro.sh:11219 blocked for more than 30 seconds. [ 5267.189520] Tainted: G S E 5.18.0-04958-ga54ce3703613-dirty #1 [ 5267.189764] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 5267.190062] task:repro.sh state:D stack: 0 pid:11219 ppid: 8162 flags:0x00000000 [ 5267.190347] Call Trace: [ 5267.190647] <TASK> [ 5267.190927] __schedule+0x460/0x9f0 [ 5267.191264] schedule+0x44/0xb0 [ 5267.191563] schedule_preempt_disabled+0x14/0x20 [ 5267.191890] __mutex_lock.isra.12+0x6e3/0xac0 [ 5267.192237] ? iavf_remove+0xf9/0x6c0 [iavf] [ 5267.192565] iavf_remove+0x12a/0x6c0 [iavf] [ 5267.192911] ? _raw_spin_unlock_irqrestore+0x1e/0x40 [ 5267.193285] pci_device_remove+0x36/0xb0 [ 5267.193619] device_release_driver_internal+0xc1/0x150 [ 5267.193974] pci_stop_bus_device+0x69/0x90 [ 5267.194361] pci_stop_and_remove_bus_device+0xe/0x20 [ 5267.194735] pci_iov_remove_virtfn+0xba/0x120 [ 5267.195130] sriov_disable+0x2f/0xe0 [ 5267.195506] ice_free_vfs+0x7d/0x2f0 [ice] [ 5267.196056] ? pci_get_device+0x4f/0x70 [ 5267.196496] ice_sriov_configure+0x78/0x1a0 [ice] [ 5267.196995] sriov_numvfs_store+0xfe/0x140 [ 5267.197466] kernfs_fop_write_iter+0x12e/0x1c0 [ 5267.197918] new_sync_write+0x10c/0x190 [ 5267.198404] vfs_write+0x24e/0x2d0 [ 5267.198886] ksys_write+0x5c/0xd0 [ 5267.199367] do_syscall_64+0x3a/0x80 [ 5267.199827] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 5267.200317] RIP: 0033:0x7f5b381205c8 [ 5267.200814] RSP: 002b:00007fff8c7e8c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 5267.201981] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f5b381205c8 [ 5267.202620] RDX: 0000000000000002 RSI: 00005569420ee900 RDI: 0000000000000001 [ 5267.203426] RBP: 00005569420ee900 R08: 000000000000000a R09: 00007f5b38180820 [ 5267.204327] R10: 000000000000000a R11: 0000000000000246 R12: 00007f5b383c06e0 [ 5267.205193] R13: 0000000000000002 R14: 00007f5b383bb880 R15: 0000000000000002 [ 5267.206041] </TASK> [ 5267.206970] Kernel panic - not syncing: hung_task: blocked tasks [ 5267.207809] CPU: 48 PID: 551 Comm: khungtaskd Kdump: loaded Tainted: G S E 5.18.0-04958-ga54ce3703613-dirty #1 [ 5267.208726] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.11.0 11/02/2019 [ 5267.209623] Call Trace: [ 5267.210569] <TASK> [ 5267.211480] dump_stack_lvl+0x33/0x42 [ 5267.212472] panic+0x107/0x294 [ 5267.213467] watchdog.cold.8+0xc/0xbb [ 5267.214413] ? proc_dohung_task_timeout_secs+0x30/0x30 [ 5267.215511] kthread+0xf4/0x120 [ 5267.216459] ? kthread_complete_and_exit+0x20/0x20 [ 5267.217505] ret_from_fork+0x22/0x30 [ 5267.218459] </TASK>
CVE-2022-50060: In the Linux kernel, the following vulnerability has been resolved: octeontx2-af: Fix mcam entry resource leak The teardown sequence in FLR handler returns if no NIX LF is attached to PF/VF because it indicates that graceful shutdown of resources already happened. But there is a chance of all allocated MCAM entries not being freed by PF/VF. Hence free mcam entries even in case of detached LF.
CVE-2022-50070: In the Linux kernel, the following vulnerability has been resolved: mptcp: do not queue data on closed subflows Dipanjan reported a syzbot splat at close time: WARNING: CPU: 1 PID: 10818 at net/ipv4/af_inet.c:153 inet_sock_destruct+0x6d0/0x8e0 net/ipv4/af_inet.c:153 Modules linked in: uio_ivshmem(OE) uio(E) CPU: 1 PID: 10818 Comm: kworker/1:16 Tainted: G OE 5.19.0-rc6-g2eae0556bb9d #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Workqueue: events mptcp_worker RIP: 0010:inet_sock_destruct+0x6d0/0x8e0 net/ipv4/af_inet.c:153 Code: 21 02 00 00 41 8b 9c 24 28 02 00 00 e9 07 ff ff ff e8 34 4d 91 f9 89 ee 4c 89 e7 e8 4a 47 60 ff e9 a6 fc ff ff e8 20 4d 91 f9 <0f> 0b e9 84 fe ff ff e8 14 4d 91 f9 0f 0b e9 d4 fd ff ff e8 08 4d RSP: 0018:ffffc9001b35fa78 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 00000000002879d0 RCX: ffff8881326f3b00 RDX: 0000000000000000 RSI: ffff8881326f3b00 RDI: 0000000000000002 RBP: ffff888179662674 R08: ffffffff87e983a0 R09: 0000000000000000 R10: 0000000000000005 R11: 00000000000004ea R12: ffff888179662400 R13: ffff888179662428 R14: 0000000000000001 R15: ffff88817e38e258 FS: 0000000000000000(0000) GS:ffff8881f5f00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020007bc0 CR3: 0000000179592000 CR4: 0000000000150ee0 Call Trace: <TASK> __sk_destruct+0x4f/0x8e0 net/core/sock.c:2067 sk_destruct+0xbd/0xe0 net/core/sock.c:2112 __sk_free+0xef/0x3d0 net/core/sock.c:2123 sk_free+0x78/0xa0 net/core/sock.c:2134 sock_put include/net/sock.h:1927 [inline] __mptcp_close_ssk+0x50f/0x780 net/mptcp/protocol.c:2351 __mptcp_destroy_sock+0x332/0x760 net/mptcp/protocol.c:2828 mptcp_worker+0x5d2/0xc90 net/mptcp/protocol.c:2586 process_one_work+0x9cc/0x1650 kernel/workqueue.c:2289 worker_thread+0x623/0x1070 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:302 </TASK> The root cause of the problem is that an mptcp-level (re)transmit can race with mptcp_close() and the packet scheduler checks the subflow state before acquiring the socket lock: we can try to (re)transmit on an already closed ssk. Fix the issue checking again the subflow socket status under the subflow socket lock protection. Additionally add the missing check for the fallback-to-tcp case.
CVE-2022-50073: In the Linux kernel, the following vulnerability has been resolved: net: tap: NULL pointer derefence in dev_parse_header_protocol when skb->dev is null Fixes a NULL pointer derefence bug triggered from tap driver. When tap_get_user calls virtio_net_hdr_to_skb the skb->dev is null (in tap.c skb->dev is set after the call to virtio_net_hdr_to_skb) virtio_net_hdr_to_skb calls dev_parse_header_protocol which needs skb->dev field to be valid. The line that trigers the bug is in dev_parse_header_protocol (dev is at offset 0x10 from skb and is stored in RAX register) if (!dev->header_ops || !dev->header_ops->parse_protocol) 22e1: mov 0x10(%rbx),%rax 22e5: mov 0x230(%rax),%rax Setting skb->dev before the call in tap.c fixes the issue. BUG: kernel NULL pointer dereference, address: 0000000000000230 RIP: 0010:virtio_net_hdr_to_skb.constprop.0+0x335/0x410 [tap] Code: c0 0f 85 b7 fd ff ff eb d4 41 39 c6 77 cf 29 c6 48 89 df 44 01 f6 e8 7a 79 83 c1 48 85 c0 0f 85 d9 fd ff ff eb b7 48 8b 43 10 <48> 8b 80 30 02 00 00 48 85 c0 74 55 48 8b 40 28 48 85 c0 74 4c 48 RSP: 0018:ffffc90005c27c38 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888298f25300 RCX: 0000000000000010 RDX: 0000000000000005 RSI: ffffc90005c27cb6 RDI: ffff888298f25300 RBP: ffffc90005c27c80 R08: 00000000ffffffea R09: 00000000000007e8 R10: ffff88858ec77458 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000014 R14: ffffc90005c27e08 R15: ffffc90005c27cb6 FS: 0000000000000000(0000) GS:ffff88858ec40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000230 CR3: 0000000281408006 CR4: 00000000003706e0 Call Trace: tap_get_user+0x3f1/0x540 [tap] tap_sendmsg+0x56/0x362 [tap] ? get_tx_bufs+0xc2/0x1e0 [vhost_net] handle_tx_copy+0x114/0x670 [vhost_net] handle_tx+0xb0/0xe0 [vhost_net] handle_tx_kick+0x15/0x20 [vhost_net] vhost_worker+0x7b/0xc0 [vhost] ? vhost_vring_call_reset+0x40/0x40 [vhost] kthread+0xfa/0x120 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30
CVE-2022-50086: In the Linux kernel, the following vulnerability has been resolved: block: don't allow the same type rq_qos add more than once In our test of iocost, we encountered some list add/del corruptions of inner_walk list in ioc_timer_fn. The reason can be described as follows: cpu 0 cpu 1 ioc_qos_write ioc_qos_write ioc = q_to_ioc(queue); if (!ioc) { ioc = kzalloc(); ioc = q_to_ioc(queue); if (!ioc) { ioc = kzalloc(); ... rq_qos_add(q, rqos); } ... rq_qos_add(q, rqos); ... } When the io.cost.qos file is written by two cpus concurrently, rq_qos may be added to one disk twice. In that case, there will be two iocs enabled and running on one disk. They own different iocgs on their active list. In the ioc_timer_fn function, because of the iocgs from two iocs have the same root iocg, the root iocg's walk_list may be overwritten by each other and this leads to list add/del corruptions in building or destroying the inner_walk list. And so far, the blk-rq-qos framework works in case that one instance for one type rq_qos per queue by default. This patch make this explicit and also fix the crash above.
CVE-2022-50098: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix crash due to stale SRB access around I/O timeouts Ensure SRB is returned during I/O timeout error escalation. If that is not possible fail the escalation path. Following crash stack was seen: BUG: unable to handle kernel paging request at 0000002f56aa90f8 IP: qla_chk_edif_rx_sa_delete_pending+0x14/0x30 [qla2xxx] Call Trace: ? qla2x00_status_entry+0x19f/0x1c50 [qla2xxx] ? qla2x00_start_sp+0x116/0x1170 [qla2xxx] ? dma_pool_alloc+0x1d6/0x210 ? mempool_alloc+0x54/0x130 ? qla24xx_process_response_queue+0x548/0x12b0 [qla2xxx] ? qla_do_work+0x2d/0x40 [qla2xxx] ? process_one_work+0x14c/0x390
CVE-2022-50100: In the Linux kernel, the following vulnerability has been resolved: sched/core: Do not requeue task on CPU excluded from cpus_mask The following warning was triggered on a large machine early in boot on a distribution kernel but the same problem should also affect mainline. WARNING: CPU: 439 PID: 10 at ../kernel/workqueue.c:2231 process_one_work+0x4d/0x440 Call Trace: <TASK> rescuer_thread+0x1f6/0x360 kthread+0x156/0x180 ret_from_fork+0x22/0x30 </TASK> Commit c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") optimises ttwu by queueing a task that is descheduling on the wakelist, but does not check if the task descheduling is still allowed to run on that CPU. In this warning, the problematic task is a workqueue rescue thread which checks if the rescue is for a per-cpu workqueue and running on the wrong CPU. While this is early in boot and it should be possible to create workers, the rescue thread may still used if the MAYDAY_INITIAL_TIMEOUT is reached or MAYDAY_INTERVAL and on a sufficiently large machine, the rescue thread is being used frequently. Tracing confirmed that the task should have migrated properly using the stopper thread to handle the migration. However, a parallel wakeup from udev running on another CPU that does not share CPU cache observes p->on_cpu and uses task_cpu(p), queues the task on the old CPU and triggers the warning. Check that the wakee task that is descheduling is still allowed to run on its current CPU and if not, wait for the descheduling to complete and select an allowed CPU.
CVE-2022-50111: In the Linux kernel, the following vulnerability has been resolved: ASoC: mt6359: Fix refcount leak bug In mt6359_parse_dt() and mt6359_accdet_parse_dt(), we should call of_node_put() for the reference returned by of_get_child_by_name() which has increased the refcount.
CVE-2022-50114: In the Linux kernel, the following vulnerability has been resolved: net: 9p: fix refcount leak in p9_read_work() error handling p9_req_put need to be called when m->rreq->rc.sdata is NULL to avoid temporary refcount leak. [Dominique: commit wording adjustments, p9_req_put argument fixes for rebase]
CVE-2022-50116: In the Linux kernel, the following vulnerability has been resolved: tty: n_gsm: fix deadlock and link starvation in outgoing data path The current implementation queues up new control and user packets as needed and processes this queue down to the ldisc in the same code path. That means that the upper and the lower layer are hard coupled in the code. Due to this deadlocks can happen as seen below while transmitting data, especially during ldisc congestion. Furthermore, the data channels starve the control channel on high transmission load on the ldisc. Introduce an additional control channel data queue to prevent timeouts and link hangups during ldisc congestion. This is being processed before the user channel data queue in gsm_data_kick(), i.e. with the highest priority. Put the queue to ldisc data path into a workqueue and trigger it whenever new data has been put into the transmission queue. Change gsm_dlci_data_sweep() accordingly to fill up the transmission queue until TX_THRESH_HI. This solves the locking issue, keeps latency low and provides good performance on high data load. Note that now all packets from a DLCI are removed from the internal queue if the associated DLCI was closed. This ensures that no data is sent by the introduced write task to an already closed DLCI. BUG: spinlock recursion on CPU#0, test_v24_loop/124 lock: serial8250_ports+0x3a8/0x7500, .magic: dead4ead, .owner: test_v24_loop/124, .owner_cpu: 0 CPU: 0 PID: 124 Comm: test_v24_loop Tainted: G O 5.18.0-rc2 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: <IRQ> dump_stack_lvl+0x34/0x44 do_raw_spin_lock+0x76/0xa0 _raw_spin_lock_irqsave+0x72/0x80 uart_write_room+0x3b/0xc0 gsm_data_kick+0x14b/0x240 [n_gsm] gsmld_write_wakeup+0x35/0x70 [n_gsm] tty_wakeup+0x53/0x60 tty_port_default_wakeup+0x1b/0x30 serial8250_tx_chars+0x12f/0x220 serial8250_handle_irq.part.0+0xfe/0x150 serial8250_default_handle_irq+0x48/0x80 serial8250_interrupt+0x56/0xa0 __handle_irq_event_percpu+0x78/0x1f0 handle_irq_event+0x34/0x70 handle_fasteoi_irq+0x90/0x1e0 __common_interrupt+0x69/0x100 common_interrupt+0x48/0xc0 asm_common_interrupt+0x1e/0x40 RIP: 0010:__do_softirq+0x83/0x34e Code: 2a 0a ff 0f b7 ed c7 44 24 10 0a 00 00 00 48 c7 c7 51 2a 64 82 e8 2d e2 d5 ff 65 66 c7 05 83 af 1e 7e 00 00 fb b8 ff ff ff ff <49> c7 c2 40 61 80 82 0f bc c5 41 89 c4 41 83 c4 01 0f 84 e6 00 00 RSP: 0018:ffffc90000003f98 EFLAGS: 00000286 RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff82642a51 RDI: ffffffff825bb5e7 RBP: 0000000000000200 R08: 00000008de3271a8 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000030 R14: 0000000000000000 R15: 0000000000000000 ? __do_softirq+0x73/0x34e irq_exit_rcu+0xb5/0x100 common_interrupt+0xa4/0xc0 </IRQ> <TASK> asm_common_interrupt+0x1e/0x40 RIP: 0010:_raw_spin_unlock_irqrestore+0x2e/0x50 Code: 00 55 48 89 fd 48 83 c7 18 53 48 89 f3 48 8b 74 24 10 e8 85 28 36 ff 48 89 ef e8 cd 58 36 ff 80 e7 02 74 01 fb bf 01 00 00 00 <e8> 3d 97 33 ff 65 8b 05 96 23 2b 7e 85 c0 74 03 5b 5d c3 0f 1f 44 RSP: 0018:ffffc9000020fd08 EFLAGS: 00000202 RAX: 0000000000000000 RBX: 0000000000000246 RCX: 0000000000000000 RDX: 0000000000000004 RSI: ffffffff8257fd74 RDI: 0000000000000001 RBP: ffff8880057de3a0 R08: 00000008de233000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000100 R14: 0000000000000202 R15: ffff8880057df0b8 ? _raw_spin_unlock_irqrestore+0x23/0x50 gsmtty_write+0x65/0x80 [n_gsm] n_tty_write+0x33f/0x530 ? swake_up_all+0xe0/0xe0 file_tty_write.constprop.0+0x1b1/0x320 ? n_tty_flush_buffer+0xb0/0xb0 new_sync_write+0x10c/0x190 vfs_write+0x282/0x310 ksys_write+0x68/0xe0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f3e5e35c15c Code: 8b 7c 24 08 89 c5 e8 c5 ff ff ff 89 ef 89 44 24 ---truncated---
CVE-2022-50120: In the Linux kernel, the following vulnerability has been resolved: remoteproc: imx_rproc: Fix refcount leak in imx_rproc_addr_init of_parse_phandle() returns a node pointer with refcount incremented, we should use of_node_put() on it when not needed anymore. This function has two paths missing of_node_put().
CVE-2022-50144: In the Linux kernel, the following vulnerability has been resolved: soundwire: revisit driver bind/unbind and callbacks In the SoundWire probe, we store a pointer from the driver ops into the 'slave' structure. This can lead to kernel oopses when unbinding codec drivers, e.g. with the following sequence to remove machine driver and codec driver. /sbin/modprobe -r snd_soc_sof_sdw /sbin/modprobe -r snd_soc_rt711 The full details can be found in the BugLink below, for reference the two following examples show different cases of driver ops/callbacks being invoked after the driver .remove(). kernel: BUG: kernel NULL pointer dereference, address: 0000000000000150 kernel: Workqueue: events cdns_update_slave_status_work [soundwire_cadence] kernel: RIP: 0010:mutex_lock+0x19/0x30 kernel: Call Trace: kernel: ? sdw_handle_slave_status+0x426/0xe00 [soundwire_bus 94ff184bf398570c3f8ff7efe9e32529f532e4ae] kernel: ? newidle_balance+0x26a/0x400 kernel: ? cdns_update_slave_status_work+0x1e9/0x200 [soundwire_cadence 1bcf98eebe5ba9833cd433323769ac923c9c6f82] kernel: BUG: unable to handle page fault for address: ffffffffc07654c8 kernel: Workqueue: pm pm_runtime_work kernel: RIP: 0010:sdw_bus_prep_clk_stop+0x6f/0x160 [soundwire_bus] kernel: Call Trace: kernel: <TASK> kernel: sdw_cdns_clock_stop+0xb5/0x1b0 [soundwire_cadence 1bcf98eebe5ba9833cd433323769ac923c9c6f82] kernel: intel_suspend_runtime+0x5f/0x120 [soundwire_intel aca858f7c87048d3152a4a41bb68abb9b663a1dd] kernel: ? dpm_sysfs_remove+0x60/0x60 This was not detected earlier in Intel tests since the tests first remove the parent PCI device and shut down the bus. The sequence above is a corner case which keeps the bus operational but without a driver bound. While trying to solve this kernel oopses, it became clear that the existing SoundWire bus does not deal well with the unbind case. Commit 528be501b7d4a ("soundwire: sdw_slave: add probe_complete structure and new fields") added a 'probed' status variable and a 'probe_complete' struct completion. This status is however not reset on remove and likewise the 'probe complete' is not re-initialized, so the bind/unbind/bind test cases would fail. The timeout used before the 'update_status' callback was also a bad idea in hindsight, there should really be no timing assumption as to if and when a driver is bound to a device. An initial draft was based on device_lock() and device_unlock() was tested. This proved too complicated, with deadlocks created during the suspend-resume sequences, which also use the same device_lock/unlock() as the bind/unbind sequences. On a CometLake device, a bad DSDT/BIOS caused spurious resumes and the use of device_lock() caused hangs during suspend. After multiple weeks or testing and painful reverse-engineering of deadlocks on different devices, we looked for alternatives that did not interfere with the device core. A bus notifier was used successfully to keep track of DRIVER_BOUND and DRIVER_UNBIND events. This solved the bind-unbind-bind case in tests, but it can still be defeated with a theoretical corner case where the memory is freed by a .remove while the callback is in use. The notifier only helps make sure the driver callbacks are valid, but not that the memory allocated in probe remains valid while the callbacks are invoked. This patch suggests the introduction of a new 'sdw_dev_lock' mutex protecting probe/remove and all driver callbacks. Since this mutex is 'local' to SoundWire only, it does not interfere with existing locks and does not create deadlocks. In addition, this patch removes the 'probe_complete' completion, instead we directly invoke the 'update_status' from the probe routine. That removes any sort of timing dependency and a much better support for the device/driver model, the driver could be bound before the bus started, or eons after the bus started and the hardware would be properly initialized in all cases. BugLink: https://github.com/thesofproject/linux/is ---truncated---
CVE-2022-50151: In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: fix random warning message when driver load Warning log: [ 4.141392] Unexpected gfp: 0x4 (GFP_DMA32). Fixing up to gfp: 0xa20 (GFP_ATOMIC). Fix your code! [ 4.150340] CPU: 1 PID: 175 Comm: 1-0050 Not tainted 5.15.5-00039-g2fd9ae1b568c #20 [ 4.158010] Hardware name: Freescale i.MX8QXP MEK (DT) [ 4.163155] Call trace: [ 4.165600] dump_backtrace+0x0/0x1b0 [ 4.169286] show_stack+0x18/0x68 [ 4.172611] dump_stack_lvl+0x68/0x84 [ 4.176286] dump_stack+0x18/0x34 [ 4.179613] kmalloc_fix_flags+0x60/0x88 [ 4.183550] new_slab+0x334/0x370 [ 4.186878] ___slab_alloc.part.108+0x4d4/0x748 [ 4.191419] __slab_alloc.isra.109+0x30/0x78 [ 4.195702] kmem_cache_alloc+0x40c/0x420 [ 4.199725] dma_pool_alloc+0xac/0x1f8 [ 4.203486] cdns3_allocate_trb_pool+0xb4/0xd0 pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) { ... page = kmalloc(sizeof(*page), mem_flags); page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); ... } kmalloc was called with mem_flags, which is passed down in cdns3_allocate_trb_pool() and have GFP_DMA32 flags. kmall_fix_flags() report warning. GFP_DMA32 is not useful at all. dma_alloc_coherent() will handle DMA memory region correctly by pool->dev. GFP_DMA32 can be removed safely.
CVE-2022-50159: In the Linux kernel, the following vulnerability has been resolved: of: check previous kernel's ima-kexec-buffer against memory bounds Presently ima_get_kexec_buffer() doesn't check if the previous kernel's ima-kexec-buffer lies outside the addressable memory range. This can result in a kernel panic if the new kernel is booted with 'mem=X' arg and the ima-kexec-buffer was allocated beyond that range by the previous kernel. The panic is usually of the form below: $ sudo kexec --initrd initrd vmlinux --append='mem=16G' <snip> BUG: Unable to handle kernel data access on read at 0xc000c01fff7f0000 Faulting instruction address: 0xc000000000837974 Oops: Kernel access of bad area, sig: 11 [#1] <snip> NIP [c000000000837974] ima_restore_measurement_list+0x94/0x6c0 LR [c00000000083b55c] ima_load_kexec_buffer+0xac/0x160 Call Trace: [c00000000371fa80] [c00000000083b55c] ima_load_kexec_buffer+0xac/0x160 [c00000000371fb00] [c0000000020512c4] ima_init+0x80/0x108 [c00000000371fb70] [c0000000020514dc] init_ima+0x4c/0x120 [c00000000371fbf0] [c000000000012240] do_one_initcall+0x60/0x2c0 [c00000000371fcc0] [c000000002004ad0] kernel_init_freeable+0x344/0x3ec [c00000000371fda0] [c0000000000128a4] kernel_init+0x34/0x1b0 [c00000000371fe10] [c00000000000ce64] ret_from_kernel_thread+0x5c/0x64 Instruction dump: f92100b8 f92100c0 90e10090 910100a0 4182050c 282a0017 3bc00000 40810330 7c0802a6 fb610198 7c9b2378 f80101d0 <a1240000> 2c090001 40820614 e9240010 ---[ end trace 0000000000000000 ]--- Fix this issue by checking returned PFN range of previous kernel's ima-kexec-buffer with page_is_ram() to ensure correct memory bounds.
CVE-2022-50163: In the Linux kernel, the following vulnerability has been resolved: ax25: fix incorrect dev_tracker usage While investigating a separate rose issue [1], and enabling CONFIG_NET_DEV_REFCNT_TRACKER=y, Bernard reported an orthogonal ax25 issue [2] An ax25_dev can be used by one (or many) struct ax25_cb. We thus need different dev_tracker, one per struct ax25_cb. After this patch is applied, we are able to focus on rose. [1] https://lore.kernel.org/netdev/fb7544a1-f42e-9254-18cc-c9b071f4ca70@free.fr/ [2] [ 205.798723] reference already released. [ 205.798732] allocated in: [ 205.798734] ax25_bind+0x1a2/0x230 [ax25] [ 205.798747] __sys_bind+0xea/0x110 [ 205.798753] __x64_sys_bind+0x18/0x20 [ 205.798758] do_syscall_64+0x5c/0x80 [ 205.798763] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 205.798768] freed in: [ 205.798770] ax25_release+0x115/0x370 [ax25] [ 205.798778] __sock_release+0x42/0xb0 [ 205.798782] sock_close+0x15/0x20 [ 205.798785] __fput+0x9f/0x260 [ 205.798789] ____fput+0xe/0x10 [ 205.798792] task_work_run+0x64/0xa0 [ 205.798798] exit_to_user_mode_prepare+0x18b/0x190 [ 205.798804] syscall_exit_to_user_mode+0x26/0x40 [ 205.798808] do_syscall_64+0x69/0x80 [ 205.798812] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 205.798827] ------------[ cut here ]------------ [ 205.798829] WARNING: CPU: 2 PID: 2605 at lib/ref_tracker.c:136 ref_tracker_free.cold+0x60/0x81 [ 205.798837] Modules linked in: rose netrom mkiss ax25 rfcomm cmac algif_hash algif_skcipher af_alg bnep snd_hda_codec_hdmi nls_iso8859_1 i915 rtw88_8821ce rtw88_8821c x86_pkg_temp_thermal rtw88_pci intel_powerclamp rtw88_core snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio coretemp snd_hda_intel kvm_intel snd_intel_dspcfg mac80211 snd_hda_codec kvm i2c_algo_bit drm_buddy drm_dp_helper btusb drm_kms_helper snd_hwdep btrtl snd_hda_core btbcm joydev crct10dif_pclmul btintel crc32_pclmul ghash_clmulni_intel mei_hdcp btmtk intel_rapl_msr aesni_intel bluetooth input_leds snd_pcm crypto_simd syscopyarea processor_thermal_device_pci_legacy sysfillrect cryptd intel_soc_dts_iosf snd_seq sysimgblt ecdh_generic fb_sys_fops rapl libarc4 processor_thermal_device intel_cstate processor_thermal_rfim cec snd_timer ecc snd_seq_device cfg80211 processor_thermal_mbox mei_me processor_thermal_rapl mei rc_core at24 snd intel_pch_thermal intel_rapl_common ttm soundcore int340x_thermal_zone video [ 205.798948] mac_hid acpi_pad sch_fq_codel ipmi_devintf ipmi_msghandler drm msr parport_pc ppdev lp parport ramoops pstore_blk reed_solomon pstore_zone efi_pstore ip_tables x_tables autofs4 hid_generic usbhid hid i2c_i801 i2c_smbus r8169 xhci_pci ahci libahci realtek lpc_ich xhci_pci_renesas [last unloaded: ax25] [ 205.798992] CPU: 2 PID: 2605 Comm: ax25ipd Not tainted 5.18.11-F6BVP #3 [ 205.798996] Hardware name: To be filled by O.E.M. To be filled by O.E.M./CK3, BIOS 5.011 09/16/2020 [ 205.798999] RIP: 0010:ref_tracker_free.cold+0x60/0x81 [ 205.799005] Code: e8 d2 01 9b ff 83 7b 18 00 74 14 48 c7 c7 2f d7 ff 98 e8 10 6e fc ff 8b 7b 18 e8 b8 01 9b ff 4c 89 ee 4c 89 e7 e8 5d fd 07 00 <0f> 0b b8 ea ff ff ff e9 30 05 9b ff 41 0f b6 f7 48 c7 c7 a0 fa 4e [ 205.799008] RSP: 0018:ffffaf5281073958 EFLAGS: 00010286 [ 205.799011] RAX: 0000000080000000 RBX: ffff9a0bd687ebe0 RCX: 0000000000000000 [ 205.799014] RDX: 0000000000000001 RSI: 0000000000000282 RDI: 00000000ffffffff [ 205.799016] RBP: ffffaf5281073a10 R08: 0000000000000003 R09: fffffffffffd5618 [ 205.799019] R10: 0000000000ffff10 R11: 000000000000000f R12: ffff9a0bc53384d0 [ 205.799022] R13: 0000000000000282 R14: 00000000ae000001 R15: 0000000000000001 [ 205.799024] FS: 0000000000000000(0000) GS:ffff9a0d0f300000(0000) knlGS:0000000000000000 [ 205.799028] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 205.799031] CR2: 00007ff6b8311554 CR3: 000000001ac10004 CR4: 00000000001706e0 [ 205.799033] Call Trace: [ 205.799035] <TASK> [ 205.799038] ? ax25_dev_device_down+0xd9/ ---truncated---
CVE-2022-50166: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: When HCI work queue is drained, only queue chained work The HCI command, event, and data packet processing workqueue is drained to avoid deadlock in commit 76727c02c1e1 ("Bluetooth: Call drain_workqueue() before resetting state"). There is another delayed work, which will queue command to this drained workqueue. Which results in the following error report: Bluetooth: hci2: command 0x040f tx timeout WARNING: CPU: 1 PID: 18374 at kernel/workqueue.c:1438 __queue_work+0xdad/0x1140 Workqueue: events hci_cmd_timeout RIP: 0010:__queue_work+0xdad/0x1140 RSP: 0000:ffffc90002cffc60 EFLAGS: 00010093 RAX: 0000000000000000 RBX: ffff8880b9d3ec00 RCX: 0000000000000000 RDX: ffff888024ba0000 RSI: ffffffff814e048d RDI: ffff8880b9d3ec08 RBP: 0000000000000008 R08: 0000000000000000 R09: 00000000b9d39700 R10: ffffffff814f73c6 R11: 0000000000000000 R12: ffff88807cce4c60 R13: 0000000000000000 R14: ffff8880796d8800 R15: ffff8880796d8800 FS: 0000000000000000(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c0174b4000 CR3: 000000007cae9000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? queue_work_on+0xcb/0x110 ? lockdep_hardirqs_off+0x90/0xd0 queue_work_on+0xee/0x110 process_one_work+0x996/0x1610 ? pwq_dec_nr_in_flight+0x2a0/0x2a0 ? rwlock_bug.part.0+0x90/0x90 ? _raw_spin_lock_irq+0x41/0x50 worker_thread+0x665/0x1080 ? process_one_work+0x1610/0x1610 kthread+0x2e9/0x3a0 ? kthread_complete_and_exit+0x40/0x40 ret_from_fork+0x1f/0x30 </TASK> To fix this, we can add a new HCI_DRAIN_WQ flag, and don't queue the timeout workqueue while command workqueue is draining.
CVE-2022-50167: In the Linux kernel, the following vulnerability has been resolved: bpf: fix potential 32-bit overflow when accessing ARRAY map element If BPF array map is bigger than 4GB, element pointer calculation can overflow because both index and elem_size are u32. Fix this everywhere by forcing 64-bit multiplication. Extract this formula into separate small helper and use it consistently in various places. Speculative-preventing formula utilizing index_mask trick is left as is, but explicit u64 casts are added in both places.
CVE-2022-50224: In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT Treat the NX bit as valid when using NPT, as KVM will set the NX bit when the NX huge page mitigation is enabled (mindblowing) and trigger the WARN that fires on reserved SPTE bits being set. KVM has required NX support for SVM since commit b26a71a1a5b9 ("KVM: SVM: Refuse to load kvm_amd if NX support is not available") for exactly this reason, but apparently it never occurred to anyone to actually test NPT with the mitigation enabled. ------------[ cut here ]------------ spte = 0x800000018a600ee7, level = 2, rsvd bits = 0x800f0000001fe000 WARNING: CPU: 152 PID: 15966 at arch/x86/kvm/mmu/spte.c:215 make_spte+0x327/0x340 [kvm] Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 10.48.0 01/27/2022 RIP: 0010:make_spte+0x327/0x340 [kvm] Call Trace: <TASK> tdp_mmu_map_handle_target_level+0xc3/0x230 [kvm] kvm_tdp_mmu_map+0x343/0x3b0 [kvm] direct_page_fault+0x1ae/0x2a0 [kvm] kvm_tdp_page_fault+0x7d/0x90 [kvm] kvm_mmu_page_fault+0xfb/0x2e0 [kvm] npf_interception+0x55/0x90 [kvm_amd] svm_invoke_exit_handler+0x31/0xf0 [kvm_amd] svm_handle_exit+0xf6/0x1d0 [kvm_amd] vcpu_enter_guest+0xb6d/0xee0 [kvm] ? kvm_pmu_trigger_event+0x6d/0x230 [kvm] vcpu_run+0x65/0x2c0 [kvm] kvm_arch_vcpu_ioctl_run+0x355/0x610 [kvm] kvm_vcpu_ioctl+0x551/0x610 [kvm] __se_sys_ioctl+0x77/0xc0 __x64_sys_ioctl+0x1d/0x20 do_syscall_64+0x44/0xa0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 </TASK> ---[ end trace 0000000000000000 ]---
CVE-2022-50233: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: eir: Fix using strlen with hdev->{dev_name,short_name} Both dev_name and short_name are not guaranteed to be NULL terminated so this instead use strnlen and then attempt to determine if the resulting string needs to be truncated or not.
CVE-2022-50236: In the Linux kernel, the following vulnerability has been resolved: iommu/mediatek: Fix crash on isr after kexec() If the system is rebooted via isr(), the IRQ handler might be triggered before the domain is initialized. Resulting on an invalid memory access error. Fix: [ 0.500930] Unable to handle kernel read from unreadable memory at virtual address 0000000000000070 [ 0.501166] Call trace: [ 0.501174] report_iommu_fault+0x28/0xfc [ 0.501180] mtk_iommu_isr+0x10c/0x1c0 [ joro: Fixed spelling in commit message ]
CVE-2022-50255: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix reading strings from synthetic events The follow commands caused a crash: # cd /sys/kernel/tracing # echo 's:open char file[]' > dynamic_events # echo 'hist:keys=common_pid:file=filename:onchange($file).trace(open,$file)' > events/syscalls/sys_enter_openat/trigger' # echo 1 > events/synthetic/open/enable BOOM! The problem is that the synthetic event field "char file[]" will read the value given to it as a string without any memory checks to make sure the address is valid. The above example will pass in the user space address and the sythetic event code will happily call strlen() on it and then strscpy() where either one will cause an oops when accessing user space addresses. Use the helper functions from trace_kprobe and trace_eprobe that can read strings safely (and actually succeed when the address is from user space and the memory is mapped in). Now the above can show: packagekitd-1721 [000] ...2. 104.597170: open: file=/usr/lib/rpm/fileattrs/cmake.attr in:imjournal-978 [006] ...2. 104.599642: open: file=/var/lib/rsyslog/imjournal.state.tmp packagekitd-1721 [000] ...2. 104.626308: open: file=/usr/lib/rpm/fileattrs/debuginfo.attr
CVE-2022-50256: In the Linux kernel, the following vulnerability has been resolved: drm/meson: remove drm bridges at aggregate driver unbind time drm bridges added by meson_encoder_hdmi_init and meson_encoder_cvbs_init were not manually removed at module unload time, which caused dangling references to freed memory to remain linked in the global bridge_list. When loading the driver modules back in, the same functions would again call drm_bridge_add, and when traversing the global bridge_list, would end up peeking into freed memory. Once again KASAN revealed the problem: [ +0.000095] ============================================================= [ +0.000008] BUG: KASAN: use-after-free in __list_add_valid+0x9c/0x120 [ +0.000018] Read of size 8 at addr ffff00003da291f0 by task modprobe/2483 [ +0.000018] CPU: 3 PID: 2483 Comm: modprobe Tainted: G C O 5.19.0-rc6-lrmbkasan+ #1 [ +0.000011] Hardware name: Hardkernel ODROID-N2Plus (DT) [ +0.000008] Call trace: [ +0.000006] dump_backtrace+0x1ec/0x280 [ +0.000012] show_stack+0x24/0x80 [ +0.000008] dump_stack_lvl+0x98/0xd4 [ +0.000011] print_address_description.constprop.0+0x80/0x520 [ +0.000011] print_report+0x128/0x260 [ +0.000008] kasan_report+0xb8/0xfc [ +0.000008] __asan_report_load8_noabort+0x3c/0x50 [ +0.000009] __list_add_valid+0x9c/0x120 [ +0.000009] drm_bridge_add+0x6c/0x104 [drm] [ +0.000165] dw_hdmi_probe+0x1900/0x2360 [dw_hdmi] [ +0.000022] meson_dw_hdmi_bind+0x520/0x814 [meson_dw_hdmi] [ +0.000014] component_bind+0x174/0x520 [ +0.000012] component_bind_all+0x1a8/0x38c [ +0.000010] meson_drv_bind_master+0x5e8/0xb74 [meson_drm] [ +0.000032] meson_drv_bind+0x20/0x2c [meson_drm] [ +0.000027] try_to_bring_up_aggregate_device+0x19c/0x390 [ +0.000010] component_master_add_with_match+0x1c8/0x284 [ +0.000009] meson_drv_probe+0x274/0x280 [meson_drm] [ +0.000026] platform_probe+0xd0/0x220 [ +0.000009] really_probe+0x3ac/0xa80 [ +0.000009] __driver_probe_device+0x1f8/0x400 [ +0.000009] driver_probe_device+0x68/0x1b0 [ +0.000009] __driver_attach+0x20c/0x480 [ +0.000008] bus_for_each_dev+0x114/0x1b0 [ +0.000009] driver_attach+0x48/0x64 [ +0.000008] bus_add_driver+0x390/0x564 [ +0.000009] driver_register+0x1a8/0x3e4 [ +0.000009] __platform_driver_register+0x6c/0x94 [ +0.000008] meson_drm_platform_driver_init+0x3c/0x1000 [meson_drm] [ +0.000027] do_one_initcall+0xc4/0x2b0 [ +0.000011] do_init_module+0x154/0x570 [ +0.000011] load_module+0x1a78/0x1ea4 [ +0.000008] __do_sys_init_module+0x184/0x1cc [ +0.000009] __arm64_sys_init_module+0x78/0xb0 [ +0.000009] invoke_syscall+0x74/0x260 [ +0.000009] el0_svc_common.constprop.0+0xcc/0x260 [ +0.000008] do_el0_svc+0x50/0x70 [ +0.000007] el0_svc+0x68/0x1a0 [ +0.000012] el0t_64_sync_handler+0x11c/0x150 [ +0.000008] el0t_64_sync+0x18c/0x190 [ +0.000016] Allocated by task 879: [ +0.000008] kasan_save_stack+0x2c/0x5c [ +0.000011] __kasan_kmalloc+0x90/0xd0 [ +0.000007] __kmalloc+0x278/0x4a0 [ +0.000011] mpi_resize+0x13c/0x1d0 [ +0.000011] mpi_powm+0xd24/0x1570 [ +0.000009] rsa_enc+0x1a4/0x30c [ +0.000009] pkcs1pad_verify+0x3f0/0x580 [ +0.000009] public_key_verify_signature+0x7a8/0xba4 [ +0.000010] public_key_verify_signature_2+0x40/0x60 [ +0.000008] verify_signature+0xb4/0x114 [ +0.000008] pkcs7_validate_trust_one.constprop.0+0x3b8/0x574 [ +0.000009] pkcs7_validate_trust+0xb8/0x15c [ +0.000008] verify_pkcs7_message_sig+0xec/0x1b0 [ +0.000012] verify_pkcs7_signature+0x78/0xac [ +0.000007] mod_verify_sig+0x110/0x190 [ +0.000009] module_sig_check+0x114/0x1e0 [ +0.000009] load_module+0xa0/0x1ea4 [ +0.000008] __do_sys_init_module+0x184/0x1cc [ +0.000008] __arm64_sys_init_module+0x78/0xb0 [ +0.000008] invoke_syscall+0x74/0x260 [ +0.000009] el0_svc_common.constprop.0+0x1a8/0x260 [ +0.000008] do_el0_svc+0x50/0x70 [ +0.000007] el0_svc+0x68/0x1a0 [ +0.000009] el0t_64_sync_handler+0x11c/0x150 [ +0.000009] el0t_64 ---truncated---
CVE-2022-50260: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Make .remove and .shutdown HW shutdown consistent Drivers' .remove and .shutdown callbacks are executed on different code paths. The former is called when a device is removed from the bus, while the latter is called at system shutdown time to quiesce the device. This means that some overlap exists between the two, because both have to take care of properly shutting down the hardware. But currently the logic used in these two callbacks isn't consistent in msm drivers, which could lead to kernel panic. For example, on .remove the component is deleted and its .unbind callback leads to the hardware being shutdown but only if the DRM device has been marked as registered. That check doesn't exist in the .shutdown logic and this can lead to the driver calling drm_atomic_helper_shutdown() for a DRM device that hasn't been properly initialized. A situation like this can happen if drivers for expected sub-devices fail to probe, since the .bind callback will never be executed. If that is the case, drm_atomic_helper_shutdown() will attempt to take mutexes that are only initialized if drm_mode_config_init() is called during a device bind. This bug was attempted to be fixed in commit 623f279c7781 ("drm/msm: fix shutdown hook in case GPU components failed to bind"), but unfortunately it still happens in some cases as the one mentioned above, i.e: systemd-shutdown[1]: Powering off. kvm: exiting hardware virtualization platform wifi-firmware.0: Removing from iommu group 12 platform video-firmware.0: Removing from iommu group 10 ------------[ cut here ]------------ WARNING: CPU: 6 PID: 1 at drivers/gpu/drm/drm_modeset_lock.c:317 drm_modeset_lock_all_ctx+0x3c4/0x3d0 ... Hardware name: Google CoachZ (rev3+) (DT) pstate: a0400009 (NzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : drm_modeset_lock_all_ctx+0x3c4/0x3d0 lr : drm_modeset_lock_all_ctx+0x48/0x3d0 sp : ffff80000805bb80 x29: ffff80000805bb80 x28: ffff327c00128000 x27: 0000000000000000 x26: 0000000000000000 x25: 0000000000000001 x24: ffffc95d820ec030 x23: ffff327c00bbd090 x22: ffffc95d8215eca0 x21: ffff327c039c5800 x20: ffff327c039c5988 x19: ffff80000805bbe8 x18: 0000000000000034 x17: 000000040044ffff x16: ffffc95d80cac920 x15: 0000000000000000 x14: 0000000000000315 x13: 0000000000000315 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : ffff80000805bc28 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : ffff327c00128000 x1 : 0000000000000000 x0 : ffff327c039c59b0 Call trace: drm_modeset_lock_all_ctx+0x3c4/0x3d0 drm_atomic_helper_shutdown+0x70/0x134 msm_drv_shutdown+0x30/0x40 platform_shutdown+0x28/0x40 device_shutdown+0x148/0x350 kernel_power_off+0x38/0x80 __do_sys_reboot+0x288/0x2c0 __arm64_sys_reboot+0x28/0x34 invoke_syscall+0x48/0x114 el0_svc_common.constprop.0+0x44/0xec do_el0_svc+0x2c/0xc0 el0_svc+0x2c/0x84 el0t_64_sync_handler+0x11c/0x150 el0t_64_sync+0x18c/0x190 ---[ end trace 0000000000000000 ]--- Unable to handle kernel NULL pointer dereference at virtual address 0000000000000018 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=000000010eab1000 [0000000000000018] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 96000004 [#1] PREEMPT SMP ... Hardware name: Google CoachZ (rev3+) (DT) pstate: a0400009 (NzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : ww_mutex_lock+0x28/0x32c lr : drm_modeset_lock_all_ctx+0x1b0/0x3d0 sp : ffff80000805bb50 x29: ffff80000805bb50 x28: ffff327c00128000 x27: 0000000000000000 x26: 00000 ---truncated---
CVE-2022-50266: In the Linux kernel, the following vulnerability has been resolved: kprobes: Fix check for probe enabled in kill_kprobe() In kill_kprobe(), the check whether disarm_kprobe_ftrace() needs to be called always fails. This is because before that we set the KPROBE_FLAG_GONE flag for kprobe so that "!kprobe_disabled(p)" is always false. The disarm_kprobe_ftrace() call introduced by commit: 0cb2f1372baa ("kprobes: Fix NULL pointer dereference at kprobe_ftrace_handler") to fix the NULL pointer reference problem. When the probe is enabled, if we do not disarm it, this problem still exists. Fix it by putting the probe enabled check before setting the KPROBE_FLAG_GONE flag.
CVE-2022-50267: In the Linux kernel, the following vulnerability has been resolved: mmc: rtsx_pci: fix return value check of mmc_add_host() mmc_add_host() may return error, if we ignore its return value, the memory that allocated in mmc_alloc_host() will be leaked and it will lead a kernel crash because of deleting not added device in the remove path. So fix this by checking the return value and calling mmc_free_host() in the error path, beside, runtime PM also needs be disabled.
CVE-2022-50293: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not BUG_ON() on ENOMEM when dropping extent items for a range If we get -ENOMEM while dropping file extent items in a given range, at btrfs_drop_extents(), due to failure to allocate memory when attempting to increment the reference count for an extent or drop the reference count, we handle it with a BUG_ON(). This is excessive, instead we can simply abort the transaction and return the error to the caller. In fact most callers of btrfs_drop_extents(), directly or indirectly, already abort the transaction if btrfs_drop_extents() returns any error. Also, we already have error paths at btrfs_drop_extents() that may return -ENOMEM and in those cases we abort the transaction, like for example anything that changes the b+tree may return -ENOMEM due to a failure to allocate a new extent buffer when COWing an existing extent buffer, such as a call to btrfs_duplicate_item() for example. So replace the BUG_ON() calls with proper logic to abort the transaction and return the error.
CVE-2022-50300: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix extent map use-after-free when handling missing device in read_one_chunk Store the error code before freeing the extent_map. Though it's reference counted structure, in that function it's the first and last allocation so this would lead to a potential use-after-free. The error can happen eg. when chunk is stored on a missing device and the degraded mount option is missing. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=216721
CVE-2022-50304: In the Linux kernel, the following vulnerability has been resolved: mtd: core: fix possible resource leak in init_mtd() I got the error report while inject fault in init_mtd(): sysfs: cannot create duplicate filename '/devices/virtual/bdi/mtd-0' Call Trace: <TASK> dump_stack_lvl+0x67/0x83 sysfs_warn_dup+0x60/0x70 sysfs_create_dir_ns+0x109/0x120 kobject_add_internal+0xce/0x2f0 kobject_add+0x98/0x110 device_add+0x179/0xc00 device_create_groups_vargs+0xf4/0x100 device_create+0x7b/0xb0 bdi_register_va.part.13+0x58/0x2d0 bdi_register+0x9b/0xb0 init_mtd+0x62/0x171 [mtd] do_one_initcall+0x6c/0x3c0 do_init_module+0x58/0x222 load_module+0x268e/0x27d0 __do_sys_finit_module+0xd5/0x140 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd </TASK> kobject_add_internal failed for mtd-0 with -EEXIST, don't try to register things with the same name in the same directory. Error registering mtd class or bdi: -17 If init_mtdchar() fails in init_mtd(), mtd_bdi will not be unregistered, as a result, we can't load the mtd module again, to fix this by calling bdi_unregister(mtd_bdi) after out_procfs label.
CVE-2022-50306: In the Linux kernel, the following vulnerability has been resolved: ext4: fix potential out of bound read in ext4_fc_replay_scan() For scan loop must ensure that at least EXT4_FC_TAG_BASE_LEN space. If remain space less than EXT4_FC_TAG_BASE_LEN which will lead to out of bound read when mounting corrupt file system image. ADD_RANGE/HEAD/TAIL is needed to add extra check when do journal scan, as this three tags will read data during scan, tag length couldn't less than data length which will read.
CVE-2022-50316: In the Linux kernel, the following vulnerability has been resolved: orangefs: Fix kmemleak in orangefs_sysfs_init() When insert and remove the orangefs module, there are kobjects memory leaked as below: unreferenced object 0xffff88810f95af00 (size 64): comm "insmod", pid 783, jiffies 4294813439 (age 65.512s) hex dump (first 32 bytes): a0 83 af 01 81 88 ff ff 08 af 95 0f 81 88 ff ff ................ 08 af 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000005a6e4dfe>] orangefs_sysfs_init+0x42/0x3a0 [<00000000722645ca>] 0xffffffffa02780fe [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/0x80 [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff88810f95ae80 (size 64): comm "insmod", pid 783, jiffies 4294813439 (age 65.512s) hex dump (first 32 bytes): c8 90 0f 02 81 88 ff ff 88 ae 95 0f 81 88 ff ff ................ 88 ae 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000001a4841fa>] orangefs_sysfs_init+0xc7/0x3a0 [<00000000722645ca>] 0xffffffffa02780fe [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/0x80 [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff88810f95ae00 (size 64): comm "insmod", pid 783, jiffies 4294813440 (age 65.511s) hex dump (first 32 bytes): 60 87 a1 00 81 88 ff ff 08 ae 95 0f 81 88 ff ff `............... 08 ae 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000005915e797>] orangefs_sysfs_init+0x12b/0x3a0 [<00000000722645ca>] 0xffffffffa02780fe [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/0x80 [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff88810f95ad80 (size 64): comm "insmod", pid 783, jiffies 4294813440 (age 65.511s) hex dump (first 32 bytes): 78 90 0f 02 81 88 ff ff 88 ad 95 0f 81 88 ff ff x............... 88 ad 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000007a14eb35>] orangefs_sysfs_init+0x1ac/0x3a0 [<00000000722645ca>] 0xffffffffa02780fe [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/0x80 [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 unreferenced object 0xffff88810f95ac00 (size 64): comm "insmod", pid 783, jiffies 4294813440 (age 65.531s) hex dump (first 32 bytes): e0 ff 67 02 81 88 ff ff 08 ac 95 0f 81 88 ff ff ..g............. 08 ac 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000031ab7788>] kmalloc_trace+0x27/0xa0 [<000000001f38adcb>] orangefs_sysfs_init+0x291/0x3a0 [<00000000722645ca>] 0xffffffffa02780fe [<000000004232d9f7>] do_one_initcall+0x87/0x2a0 [<0000000054f22384>] do_init_module+0xdf/0x320 [<000000003263bdea>] load_module+0x2f98/0x3330 [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0 [<00000000250ae02b>] do_syscall_64+0x35/ ---truncated---
CVE-2022-50335: In the Linux kernel, the following vulnerability has been resolved: 9p: set req refcount to zero to avoid uninitialized usage When a new request is allocated, the refcount will be zero if it is reused, but if the request is newly allocated from slab, it is not fully initialized before being added to idr. If the p9_read_work got a response before the refcount initiated. It will use a uninitialized req, which will result in a bad request data struct. Here is the logs from syzbot. Corrupted memory at 0xffff88807eade00b [ 0xff 0x07 0x00 0x00 0x00 0x00 0x00 0x00 . . . . . . . . ] (in kfence-#110): p9_fcall_fini net/9p/client.c:248 [inline] p9_req_put net/9p/client.c:396 [inline] p9_req_put+0x208/0x250 net/9p/client.c:390 p9_client_walk+0x247/0x540 net/9p/client.c:1165 clone_fid fs/9p/fid.h:21 [inline] v9fs_fid_xattr_set+0xe4/0x2b0 fs/9p/xattr.c:118 v9fs_xattr_set fs/9p/xattr.c:100 [inline] v9fs_xattr_handler_set+0x6f/0x120 fs/9p/xattr.c:159 __vfs_setxattr+0x119/0x180 fs/xattr.c:182 __vfs_setxattr_noperm+0x129/0x5f0 fs/xattr.c:216 __vfs_setxattr_locked+0x1d3/0x260 fs/xattr.c:277 vfs_setxattr+0x143/0x340 fs/xattr.c:309 setxattr+0x146/0x160 fs/xattr.c:617 path_setxattr+0x197/0x1c0 fs/xattr.c:636 __do_sys_setxattr fs/xattr.c:652 [inline] __se_sys_setxattr fs/xattr.c:648 [inline] __ia32_sys_setxattr+0xc0/0x160 fs/xattr.c:648 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0x65/0xf0 arch/x86/entry/common.c:178 do_fast_syscall_32+0x33/0x70 arch/x86/entry/common.c:203 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Below is a similar scenario, the scenario in the syzbot log looks more complicated than this one, but this patch can fix it. T21124 p9_read_work ======================== second trans ================================= p9_client_walk p9_client_rpc p9_client_prepare_req p9_tag_alloc req = kmem_cache_alloc(p9_req_cache, GFP_NOFS); tag = idr_alloc << preempted >> req->tc.tag = tag; /* req->[refcount/tag] == uninitialized */ m->rreq = p9_tag_lookup(m->client, m->rc.tag); /* increments uninitalized refcount */ refcount_set(&req->refcount, 2); /* cb drops one ref */ p9_client_cb(req) /* reader thread drops its ref: request is incorrectly freed */ p9_req_put(req) /* use after free and ref underflow */ p9_req_put(req) To fix it, we can initialize the refcount to zero before add to idr.
CVE-2022-50350: In the Linux kernel, the following vulnerability has been resolved: scsi: target: iscsi: Fix a race condition between login_work and the login thread In case a malicious initiator sends some random data immediately after a login PDU; the iscsi_target_sk_data_ready() callback will schedule the login_work and, at the same time, the negotiation may end without clearing the LOGIN_FLAGS_INITIAL_PDU flag (because no additional PDU exchanges are required to complete the login). The login has been completed but the login_work function will find the LOGIN_FLAGS_INITIAL_PDU flag set and will never stop from rescheduling itself; at this point, if the initiator drops the connection, the iscsit_conn structure will be freed, login_work will dereference a released socket structure and the kernel crashes. BUG: kernel NULL pointer dereference, address: 0000000000000230 PF: supervisor write access in kernel mode PF: error_code(0x0002) - not-present page Workqueue: events iscsi_target_do_login_rx [iscsi_target_mod] RIP: 0010:_raw_read_lock_bh+0x15/0x30 Call trace: iscsi_target_do_login_rx+0x75/0x3f0 [iscsi_target_mod] process_one_work+0x1e8/0x3c0 Fix this bug by forcing login_work to stop after the login has been completed and the socket callbacks have been restored. Add a comment to clearify the return values of iscsi_target_do_login()
CVE-2022-50378: In the Linux kernel, the following vulnerability has been resolved: drm/meson: reorder driver deinit sequence to fix use-after-free bug Unloading the driver triggers the following KASAN warning: [ +0.006275] ============================================================= [ +0.000029] BUG: KASAN: use-after-free in __list_del_entry_valid+0xe0/0x1a0 [ +0.000026] Read of size 8 at addr ffff000020c395e0 by task rmmod/2695 [ +0.000019] CPU: 5 PID: 2695 Comm: rmmod Tainted: G C O 5.19.0-rc6-lrmbkasan+ #1 [ +0.000013] Hardware name: Hardkernel ODROID-N2Plus (DT) [ +0.000008] Call trace: [ +0.000007] dump_backtrace+0x1ec/0x280 [ +0.000013] show_stack+0x24/0x80 [ +0.000008] dump_stack_lvl+0x98/0xd4 [ +0.000011] print_address_description.constprop.0+0x80/0x520 [ +0.000011] print_report+0x128/0x260 [ +0.000007] kasan_report+0xb8/0xfc [ +0.000008] __asan_report_load8_noabort+0x3c/0x50 [ +0.000010] __list_del_entry_valid+0xe0/0x1a0 [ +0.000009] drm_atomic_private_obj_fini+0x30/0x200 [drm] [ +0.000172] drm_bridge_detach+0x94/0x260 [drm] [ +0.000145] drm_encoder_cleanup+0xa4/0x290 [drm] [ +0.000144] drm_mode_config_cleanup+0x118/0x740 [drm] [ +0.000143] drm_mode_config_init_release+0x1c/0x2c [drm] [ +0.000144] drm_managed_release+0x170/0x414 [drm] [ +0.000142] drm_dev_put.part.0+0xc0/0x124 [drm] [ +0.000143] drm_dev_put+0x20/0x30 [drm] [ +0.000142] meson_drv_unbind+0x1d8/0x2ac [meson_drm] [ +0.000028] take_down_aggregate_device+0xb0/0x160 [ +0.000016] component_del+0x18c/0x360 [ +0.000009] meson_dw_hdmi_remove+0x28/0x40 [meson_dw_hdmi] [ +0.000015] platform_remove+0x64/0xb0 [ +0.000009] device_remove+0xb8/0x154 [ +0.000009] device_release_driver_internal+0x398/0x5b0 [ +0.000009] driver_detach+0xac/0x1b0 [ +0.000009] bus_remove_driver+0x158/0x29c [ +0.000009] driver_unregister+0x70/0xb0 [ +0.000008] platform_driver_unregister+0x20/0x2c [ +0.000008] meson_dw_hdmi_platform_driver_exit+0x1c/0x30 [meson_dw_hdmi] [ +0.000012] __do_sys_delete_module+0x288/0x400 [ +0.000011] __arm64_sys_delete_module+0x5c/0x80 [ +0.000009] invoke_syscall+0x74/0x260 [ +0.000009] el0_svc_common.constprop.0+0xcc/0x260 [ +0.000009] do_el0_svc+0x50/0x70 [ +0.000007] el0_svc+0x68/0x1a0 [ +0.000012] el0t_64_sync_handler+0x11c/0x150 [ +0.000008] el0t_64_sync+0x18c/0x190 [ +0.000018] Allocated by task 0: [ +0.000007] (stack is not available) [ +0.000011] Freed by task 2695: [ +0.000008] kasan_save_stack+0x2c/0x5c [ +0.000011] kasan_set_track+0x2c/0x40 [ +0.000008] kasan_set_free_info+0x28/0x50 [ +0.000009] ____kasan_slab_free+0x128/0x1d4 [ +0.000008] __kasan_slab_free+0x18/0x24 [ +0.000007] slab_free_freelist_hook+0x108/0x230 [ +0.000011] kfree+0x110/0x35c [ +0.000008] release_nodes+0xf0/0x16c [ +0.000009] devres_release_group+0x180/0x270 [ +0.000008] component_unbind+0x128/0x1e0 [ +0.000010] component_unbind_all+0x1b8/0x264 [ +0.000009] meson_drv_unbind+0x1a0/0x2ac [meson_drm] [ +0.000025] take_down_aggregate_device+0xb0/0x160 [ +0.000009] component_del+0x18c/0x360 [ +0.000009] meson_dw_hdmi_remove+0x28/0x40 [meson_dw_hdmi] [ +0.000012] platform_remove+0x64/0xb0 [ +0.000008] device_remove+0xb8/0x154 [ +0.000009] device_release_driver_internal+0x398/0x5b0 [ +0.000009] driver_detach+0xac/0x1b0 [ +0.000009] bus_remove_driver+0x158/0x29c [ +0.000008] driver_unregister+0x70/0xb0 [ +0.000008] platform_driver_unregister+0x20/0x2c [ +0.000008] meson_dw_hdmi_platform_driver_exit+0x1c/0x30 [meson_dw_hdmi] [ +0.000011] __do_sys_delete_module+0x288/0x400 [ +0.000010] __arm64_sys_delete_module+0x5c/0x80 [ +0.000008] invoke_syscall+0x74/0x260 [ +0.000008] el0_svc_common.constprop.0+0xcc/0x260 [ +0.000008] do_el0_svc+0x50/0x70 [ +0.000007] el0_svc+0x68/0x1a0 [ +0.000009] el0t_64_sync_handler+0x11c/0x150 [ +0.000009] el0t_64_sync+0x18c/0x190 [ +0.000014] The buggy address belongs to the object at ffff000020c39000 ---truncated---
CVE-2022-50380: In the Linux kernel, the following vulnerability has been resolved: mm: /proc/pid/smaps_rollup: fix no vma's null-deref Commit 258f669e7e88 ("mm: /proc/pid/smaps_rollup: convert to single value seq_file") introduced a null-deref if there are no vma's in the task in show_smaps_rollup.
CVE-2022-50390: In the Linux kernel, the following vulnerability has been resolved: drm/ttm: fix undefined behavior in bit shift for TTM_TT_FLAG_PRIV_POPULATED Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in ./include/drm/ttm/ttm_tt.h:122:26 left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: <TASK> dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c ttm_bo_move_memcpy+0x3b4/0x460 [ttm] bo_driver_move+0x32/0x40 [drm_vram_helper] ttm_bo_handle_move_mem+0x118/0x200 [ttm] ttm_bo_validate+0xfa/0x220 [ttm] drm_gem_vram_pin_locked+0x70/0x1b0 [drm_vram_helper] drm_gem_vram_pin+0x48/0xb0 [drm_vram_helper] drm_gem_vram_plane_helper_prepare_fb+0x53/0xe0 [drm_vram_helper] drm_gem_vram_simple_display_pipe_prepare_fb+0x26/0x30 [drm_vram_helper] drm_simple_kms_plane_prepare_fb+0x4d/0xe0 [drm_kms_helper] drm_atomic_helper_prepare_planes+0xda/0x210 [drm_kms_helper] drm_atomic_helper_commit+0xc3/0x1e0 [drm_kms_helper] drm_atomic_commit+0x9c/0x160 [drm] drm_client_modeset_commit_atomic+0x33a/0x380 [drm] drm_client_modeset_commit_locked+0x77/0x220 [drm] drm_client_modeset_commit+0x31/0x60 [drm] __drm_fb_helper_restore_fbdev_mode_unlocked+0xa7/0x170 [drm_kms_helper] drm_fb_helper_set_par+0x51/0x90 [drm_kms_helper] fbcon_init+0x316/0x790 visual_init+0x113/0x1d0 do_bind_con_driver+0x2a3/0x5c0 do_take_over_console+0xa9/0x270 do_fbcon_takeover+0xa1/0x170 do_fb_registered+0x2a8/0x340 fbcon_fb_registered+0x47/0xe0 register_framebuffer+0x294/0x4a0 __drm_fb_helper_initial_config_and_unlock+0x43c/0x880 [drm_kms_helper] drm_fb_helper_initial_config+0x52/0x80 [drm_kms_helper] drm_fbdev_client_hotplug+0x156/0x1b0 [drm_kms_helper] drm_fbdev_generic_setup+0xfc/0x290 [drm_kms_helper] bochs_pci_probe+0x6ca/0x772 [bochs] local_pci_probe+0x4d/0xb0 pci_device_probe+0x119/0x320 really_probe+0x181/0x550 __driver_probe_device+0xc6/0x220 driver_probe_device+0x32/0x100 __driver_attach+0x195/0x200 bus_for_each_dev+0xbb/0x120 driver_attach+0x27/0x30 bus_add_driver+0x22e/0x2f0 driver_register+0xa9/0x190 __pci_register_driver+0x90/0xa0 bochs_pci_driver_init+0x52/0x1000 [bochs] do_one_initcall+0x76/0x430 do_init_module+0x61/0x28a load_module+0x1f82/0x2e50 __do_sys_finit_module+0xf8/0x190 __x64_sys_finit_module+0x23/0x30 do_syscall_64+0x58/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd </TASK>
CVE-2022-50392: In the Linux kernel, the following vulnerability has been resolved: ASoC: mediatek: mt8183: fix refcount leak in mt8183_mt6358_ts3a227_max98357_dev_probe() The node returned by of_parse_phandle() with refcount incremented, of_node_put() needs be called when finish using it. So add it in the error path in mt8183_mt6358_ts3a227_max98357_dev_probe().
CVE-2022-50393: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: SDMA update use unlocked iterator SDMA update page table may be called from unlocked context, this generate below warning. Use unlocked iterator to handle this case. WARNING: CPU: 0 PID: 1475 at drivers/dma-buf/dma-resv.c:483 dma_resv_iter_next Call Trace: dma_resv_iter_first+0x43/0xa0 amdgpu_vm_sdma_update+0x69/0x2d0 [amdgpu] amdgpu_vm_ptes_update+0x29c/0x870 [amdgpu] amdgpu_vm_update_range+0x2f6/0x6c0 [amdgpu] svm_range_unmap_from_gpus+0x115/0x300 [amdgpu] svm_range_cpu_invalidate_pagetables+0x510/0x5e0 [amdgpu] __mmu_notifier_invalidate_range_start+0x1d3/0x230 unmap_vmas+0x140/0x150 unmap_region+0xa8/0x110
CVE-2022-50399: In the Linux kernel, the following vulnerability has been resolved: media: atomisp: prevent integer overflow in sh_css_set_black_frame() The "height" and "width" values come from the user so the "height * width" multiplication can overflow.
CVE-2022-50406: In the Linux kernel, the following vulnerability has been resolved: iomap: iomap: fix memory corruption when recording errors during writeback Every now and then I see this crash on arm64: Unable to handle kernel NULL pointer dereference at virtual address 00000000000000f8 Buffer I/O error on dev dm-0, logical block 8733687, async page read Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006 CM = 0, WnR = 0 user pgtable: 64k pages, 42-bit VAs, pgdp=0000000139750000 [00000000000000f8] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000, pmd=0000000000000000 Internal error: Oops: 96000006 [#1] PREEMPT SMP Buffer I/O error on dev dm-0, logical block 8733688, async page read Dumping ftrace buffer: Buffer I/O error on dev dm-0, logical block 8733689, async page read (ftrace buffer empty) XFS (dm-0): log I/O error -5 Modules linked in: dm_thin_pool dm_persistent_data XFS (dm-0): Metadata I/O Error (0x1) detected at xfs_trans_read_buf_map+0x1ec/0x590 [xfs] (fs/xfs/xfs_trans_buf.c:296). dm_bio_prison XFS (dm-0): Please unmount the filesystem and rectify the problem(s) XFS (dm-0): xfs_imap_lookup: xfs_ialloc_read_agi() returned error -5, agno 0 dm_bufio dm_log_writes xfs nft_chain_nat xt_REDIRECT nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip6t_REJECT potentially unexpected fatal signal 6. nf_reject_ipv6 potentially unexpected fatal signal 6. ipt_REJECT nf_reject_ipv4 CPU: 1 PID: 122166 Comm: fsstress Tainted: G W 6.0.0-rc5-djwa #rc5 3004c9f1de887ebae86015f2677638ce51ee7 rpcsec_gss_krb5 auth_rpcgss xt_tcpudp ip_set_hash_ip ip_set_hash_net xt_set nft_compat ip_set_hash_mac ip_set nf_tables Hardware name: QEMU KVM Virtual Machine, BIOS 1.5.1 06/16/2021 pstate: 60001000 (nZCv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--) ip_tables pc : 000003fd6d7df200 x_tables lr : 000003fd6d7df1ec overlay nfsv4 CPU: 0 PID: 54031 Comm: u4:3 Tainted: G W 6.0.0-rc5-djwa #rc5 3004c9f1de887ebae86015f2677638ce51ee7405 Hardware name: QEMU KVM Virtual Machine, BIOS 1.5.1 06/16/2021 Workqueue: writeback wb_workfn sp : 000003ffd9522fd0 (flush-253:0) pstate: 60401005 (nZCv daif +PAN -UAO -TCO -DIT +SSBS BTYPE=--) pc : errseq_set+0x1c/0x100 x29: 000003ffd9522fd0 x28: 0000000000000023 x27: 000002acefeb6780 x26: 0000000000000005 x25: 0000000000000001 x24: 0000000000000000 x23: 00000000ffffffff x22: 0000000000000005 lr : __filemap_set_wb_err+0x24/0xe0 x21: 0000000000000006 sp : fffffe000f80f760 x29: fffffe000f80f760 x28: 0000000000000003 x27: fffffe000f80f9f8 x26: 0000000002523000 x25: 00000000fffffffb x24: fffffe000f80f868 x23: fffffe000f80fbb0 x22: fffffc0180c26a78 x21: 0000000002530000 x20: 0000000000000000 x19: 0000000000000000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000001 x13: 0000000000470af3 x12: fffffc0058f70000 x11: 0000000000000040 x10: 0000000000001b20 x9 : fffffe000836b288 x8 : fffffc00eb9fd480 x7 : 0000000000f83659 x6 : 0000000000000000 x5 : 0000000000000869 x4 : 0000000000000005 x3 : 00000000000000f8 x20: 000003fd6d740020 x19: 000000000001dd36 x18: 0000000000000001 x17: 000003fd6d78704c x16: 0000000000000001 x15: 000002acfac87668 x2 : 0000000000000ffa x1 : 00000000fffffffb x0 : 00000000000000f8 Call trace: errseq_set+0x1c/0x100 __filemap_set_wb_err+0x24/0xe0 iomap_do_writepage+0x5e4/0xd5c write_cache_pages+0x208/0x674 iomap_writepages+0x34/0x60 xfs_vm_writepages+0x8c/0xcc [xfs 7a861f39c43631f15d3a5884246ba5035d4ca78b] x14: 0000000000000000 x13: 2064656e72757465 x12: 0000000000002180 x11: 000003fd6d8a82d0 x10: 0000000000000000 x9 : 000003fd6d8ae288 x8 : 0000000000000083 x7 : 00000000ffffffff x6 : 00000000ffffffee x5 : 00000000fbad2887 x4 : 000003fd6d9abb58 x3 : 000003fd6d740020 x2 : 0000000000000006 x1 : 000000000001dd36 x0 : 0000000000000000 CPU: ---truncated---
CVE-2022-50407: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/qm - increase the memory of local variables Increase the buffer to prevent stack overflow by fuzz test. The maximum length of the qos configuration buffer is 256 bytes. Currently, the value of the 'val buffer' is only 32 bytes. The sscanf does not check the dest memory length. So the 'val buffer' may stack overflow.
CVE-2022-50418: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: mhi: fix potential memory leak in ath11k_mhi_register() mhi_alloc_controller() allocates a memory space for mhi_ctrl. When gets some error, mhi_ctrl should be freed with mhi_free_controller(). But when ath11k_mhi_read_addr_from_dt() fails, the function returns without calling mhi_free_controller(), which will lead to a memory leak. We can fix it by calling mhi_free_controller() when ath11k_mhi_read_addr_from_dt() fails.
CVE-2022-50420: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/hpre - fix resource leak in remove process In hpre_remove(), when the disable operation of qm sriov failed, the following logic should continue to be executed to release the remaining resources that have been allocated, instead of returning directly, otherwise there will be resource leakage.
CVE-2022-50428: In the Linux kernel, the following vulnerability has been resolved: ext4: fix off-by-one errors in fast-commit block filling Due to several different off-by-one errors, or perhaps due to a late change in design that wasn't fully reflected in the code that was actually merged, there are several very strange constraints on how fast-commit blocks are filled with tlv entries: - tlvs must start at least 10 bytes before the end of the block, even though the minimum tlv length is 8. Otherwise, the replay code will ignore them. (BUG: ext4_fc_reserve_space() could violate this requirement if called with a len of blocksize - 9 or blocksize - 8. Fortunately, this doesn't seem to happen currently.) - tlvs must end at least 1 byte before the end of the block. Otherwise the replay code will consider them to be invalid. This quirk contributed to a bug (fixed by an earlier commit) where uninitialized memory was being leaked to disk in the last byte of blocks. Also, strangely these constraints don't apply to the replay code in e2fsprogs, which will accept any tlvs in the blocks (with no bounds checks at all, but that is a separate issue...). Given that this all seems to be a bug, let's fix it by just filling blocks with tlv entries in the natural way. Note that old kernels will be unable to replay fast-commit journals created by kernels that have this commit.
CVE-2022-50445: In the Linux kernel, the following vulnerability has been resolved: xfrm: Reinject transport-mode packets through workqueue The following warning is displayed when the tcp6-multi-diffip11 stress test case of the LTP test suite is tested: watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [ns-tcpserver:48198] CPU: 0 PID: 48198 Comm: ns-tcpserver Kdump: loaded Not tainted 6.0.0-rc6+ #39 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : des3_ede_encrypt+0x27c/0x460 [libdes] lr : 0x3f sp : ffff80000ceaa1b0 x29: ffff80000ceaa1b0 x28: ffff0000df056100 x27: ffff0000e51e5280 x26: ffff80004df75030 x25: ffff0000e51e4600 x24: 000000000000003b x23: 0000000000802080 x22: 000000000000003d x21: 0000000000000038 x20: 0000000080000020 x19: 000000000000000a x18: 0000000000000033 x17: ffff0000e51e4780 x16: ffff80004e2d1448 x15: ffff80004e2d1248 x14: ffff0000e51e4680 x13: ffff80004e2d1348 x12: ffff80004e2d1548 x11: ffff80004e2d1848 x10: ffff80004e2d1648 x9 : ffff80004e2d1748 x8 : ffff80004e2d1948 x7 : 000000000bcaf83d x6 : 000000000000001b x5 : ffff80004e2d1048 x4 : 00000000761bf3bf x3 : 000000007f1dd0a3 x2 : ffff0000e51e4780 x1 : ffff0000e3b9a2f8 x0 : 00000000db44e872 Call trace: des3_ede_encrypt+0x27c/0x460 [libdes] crypto_des3_ede_encrypt+0x1c/0x30 [des_generic] crypto_cbc_encrypt+0x148/0x190 crypto_skcipher_encrypt+0x2c/0x40 crypto_authenc_encrypt+0xc8/0xfc [authenc] crypto_aead_encrypt+0x2c/0x40 echainiv_encrypt+0x144/0x1a0 [echainiv] crypto_aead_encrypt+0x2c/0x40 esp6_output_tail+0x1c8/0x5d0 [esp6] esp6_output+0x120/0x278 [esp6] xfrm_output_one+0x458/0x4ec xfrm_output_resume+0x6c/0x1f0 xfrm_output+0xac/0x4ac __xfrm6_output+0x130/0x270 xfrm6_output+0x60/0xec ip6_xmit+0x2ec/0x5bc inet6_csk_xmit+0xbc/0x10c __tcp_transmit_skb+0x460/0x8c0 tcp_write_xmit+0x348/0x890 __tcp_push_pending_frames+0x44/0x110 tcp_rcv_established+0x3c8/0x720 tcp_v6_do_rcv+0xdc/0x4a0 tcp_v6_rcv+0xc24/0xcb0 ip6_protocol_deliver_rcu+0xf0/0x574 ip6_input_finish+0x48/0x7c ip6_input+0x48/0xc0 ip6_rcv_finish+0x80/0x9c xfrm_trans_reinject+0xb0/0xf4 tasklet_action_common.constprop.0+0xf8/0x134 tasklet_action+0x30/0x3c __do_softirq+0x128/0x368 do_softirq+0xb4/0xc0 __local_bh_enable_ip+0xb0/0xb4 put_cpu_fpsimd_context+0x40/0x70 kernel_neon_end+0x20/0x40 sha1_base_do_update.constprop.0.isra.0+0x11c/0x140 [sha1_ce] sha1_ce_finup+0x94/0x110 [sha1_ce] crypto_shash_finup+0x34/0xc0 hmac_finup+0x48/0xe0 crypto_shash_finup+0x34/0xc0 shash_digest_unaligned+0x74/0x90 crypto_shash_digest+0x4c/0x9c shash_ahash_digest+0xc8/0xf0 shash_async_digest+0x28/0x34 crypto_ahash_digest+0x48/0xcc crypto_authenc_genicv+0x88/0xcc [authenc] crypto_authenc_encrypt+0xd8/0xfc [authenc] crypto_aead_encrypt+0x2c/0x40 echainiv_encrypt+0x144/0x1a0 [echainiv] crypto_aead_encrypt+0x2c/0x40 esp6_output_tail+0x1c8/0x5d0 [esp6] esp6_output+0x120/0x278 [esp6] xfrm_output_one+0x458/0x4ec xfrm_output_resume+0x6c/0x1f0 xfrm_output+0xac/0x4ac __xfrm6_output+0x130/0x270 xfrm6_output+0x60/0xec ip6_xmit+0x2ec/0x5bc inet6_csk_xmit+0xbc/0x10c __tcp_transmit_skb+0x460/0x8c0 tcp_write_xmit+0x348/0x890 __tcp_push_pending_frames+0x44/0x110 tcp_push+0xb4/0x14c tcp_sendmsg_locked+0x71c/0xb64 tcp_sendmsg+0x40/0x6c inet6_sendmsg+0x4c/0x80 sock_sendmsg+0x5c/0x6c __sys_sendto+0x128/0x15c __arm64_sys_sendto+0x30/0x40 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0x170/0x194 do_el0_svc+0x38/0x4c el0_svc+0x28/0xe0 el0t_64_sync_handler+0xbc/0x13c el0t_64_sync+0x180/0x184 Get softirq info by bcc tool: ./softirqs -NT 10 Tracing soft irq event time... Hit Ctrl-C to end. 15:34:34 SOFTIRQ TOTAL_nsecs block 158990 timer 20030920 sched 46577080 net_rx 676746820 tasklet 9906067650 15:34:45 SOFTIRQ TOTAL_nsecs block 86100 sched 38849790 net_rx ---truncated---
CVE-2022-50461: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: ti: am65-cpsw: Fix PM runtime leakage in am65_cpsw_nuss_ndo_slave_open() Ensure pm_runtime_put() is issued in error path.
CVE-2022-50469: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: fix potential memory leak in rtw_init_drv_sw() In rtw_init_drv_sw(), there are various init functions are called to populate the padapter structure and some checks for their return value. However, except for the first one error path, the other five error paths do not properly release the previous allocated resources, which leads to various memory leaks. This patch fixes them and keeps the success and error separate. Note that these changes keep the form of `rtw_init_drv_sw()` in "drivers/staging/r8188eu/os_dep/os_intfs.c". As there is no proper device to test with, no runtime testing was performed.
CVE-2022-50472: In the Linux kernel, the following vulnerability has been resolved: IB/mad: Don't call to function that might sleep while in atomic context Tracepoints are not allowed to sleep, as such the following splat is generated due to call to ib_query_pkey() in atomic context. WARNING: CPU: 0 PID: 1888000 at kernel/trace/ring_buffer.c:2492 rb_commit+0xc1/0x220 CPU: 0 PID: 1888000 Comm: kworker/u9:0 Kdump: loaded Tainted: G OE --------- - - 4.18.0-305.3.1.el8.x86_64 #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2.module_el8.3.0+555+a55c8938 04/01/2014 Workqueue: ib-comp-unb-wq ib_cq_poll_work [ib_core] RIP: 0010:rb_commit+0xc1/0x220 RSP: 0000:ffffa8ac80f9bca0 EFLAGS: 00010202 RAX: ffff8951c7c01300 RBX: ffff8951c7c14a00 RCX: 0000000000000246 RDX: ffff8951c707c000 RSI: ffff8951c707c57c RDI: ffff8951c7c14a00 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffff8951c7c01300 R11: 0000000000000001 R12: 0000000000000246 R13: 0000000000000000 R14: ffffffff964c70c0 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8951fbc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f20e8f39010 CR3: 000000002ca10005 CR4: 0000000000170ef0 Call Trace: ring_buffer_unlock_commit+0x1d/0xa0 trace_buffer_unlock_commit_regs+0x3b/0x1b0 trace_event_buffer_commit+0x67/0x1d0 trace_event_raw_event_ib_mad_recv_done_handler+0x11c/0x160 [ib_core] ib_mad_recv_done+0x48b/0xc10 [ib_core] ? trace_event_raw_event_cq_poll+0x6f/0xb0 [ib_core] __ib_process_cq+0x91/0x1c0 [ib_core] ib_cq_poll_work+0x26/0x80 [ib_core] process_one_work+0x1a7/0x360 ? create_worker+0x1a0/0x1a0 worker_thread+0x30/0x390 ? create_worker+0x1a0/0x1a0 kthread+0x116/0x130 ? kthread_flush_work_fn+0x10/0x10 ret_from_fork+0x35/0x40 ---[ end trace 78ba8509d3830a16 ]---
CVE-2022-50492: In the Linux kernel, the following vulnerability has been resolved: drm/msm: fix use-after-free on probe deferral The bridge counter was never reset when tearing down the DRM device so that stale pointers to deallocated structures would be accessed on the next tear down (e.g. after a second late bind deferral). Given enough bridges and a few probe deferrals this could currently also lead to data beyond the bridge array being corrupted. Patchwork: https://patchwork.freedesktop.org/patch/502665/
CVE-2022-50493: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix crash when I/O abort times out While performing CPU hotplug, a crash with the following stack was seen: Call Trace: qla24xx_process_response_queue+0x42a/0x970 [qla2xxx] qla2x00_start_nvme_mq+0x3a2/0x4b0 [qla2xxx] qla_nvme_post_cmd+0x166/0x240 [qla2xxx] nvme_fc_start_fcp_op.part.0+0x119/0x2e0 [nvme_fc] blk_mq_dispatch_rq_list+0x17b/0x610 __blk_mq_sched_dispatch_requests+0xb0/0x140 blk_mq_sched_dispatch_requests+0x30/0x60 __blk_mq_run_hw_queue+0x35/0x90 __blk_mq_delay_run_hw_queue+0x161/0x180 blk_execute_rq+0xbe/0x160 __nvme_submit_sync_cmd+0x16f/0x220 [nvme_core] nvmf_connect_admin_queue+0x11a/0x170 [nvme_fabrics] nvme_fc_create_association.cold+0x50/0x3dc [nvme_fc] nvme_fc_connect_ctrl_work+0x19/0x30 [nvme_fc] process_one_work+0x1e8/0x3c0 On abort timeout, completion was called without checking if the I/O was already completed. Verify that I/O and abort request are indeed outstanding before attempting completion.
CVE-2022-50500: In the Linux kernel, the following vulnerability has been resolved: netdevsim: fix memory leak in nsim_drv_probe() when nsim_dev_resources_register() failed If some items in nsim_dev_resources_register() fail, memory leak will occur. The following is the memory leak information. unreferenced object 0xffff888074c02600 (size 128): comm "echo", pid 8159, jiffies 4294945184 (age 493.530s) hex dump (first 32 bytes): 40 47 ea 89 ff ff ff ff 01 00 00 00 00 00 00 00 @G.............. ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ backtrace: [<0000000011a31c98>] kmalloc_trace+0x22/0x60 [<0000000027384c69>] devl_resource_register+0x144/0x4e0 [<00000000a16db248>] nsim_drv_probe+0x37a/0x1260 [<000000007d1f448c>] really_probe+0x20b/0xb10 [<00000000c416848a>] __driver_probe_device+0x1b3/0x4a0 [<00000000077e0351>] driver_probe_device+0x49/0x140 [<0000000054f2465a>] __device_attach_driver+0x18c/0x2a0 [<000000008538f359>] bus_for_each_drv+0x151/0x1d0 [<0000000038e09747>] __device_attach+0x1c9/0x4e0 [<00000000dd86e533>] bus_probe_device+0x1d5/0x280 [<00000000839bea35>] device_add+0xae0/0x1cb0 [<000000009c2abf46>] new_device_store+0x3b6/0x5f0 [<00000000fb823d7f>] bus_attr_store+0x72/0xa0 [<000000007acc4295>] sysfs_kf_write+0x106/0x160 [<000000005f50cb4d>] kernfs_fop_write_iter+0x3a8/0x5a0 [<0000000075eb41bf>] vfs_write+0x8f0/0xc80
CVE-2022-50518: In the Linux kernel, the following vulnerability has been resolved: parisc: Fix locking in pdc_iodc_print() firmware call Utilize pdc_lock spinlock to protect parallel modifications of the iodc_dbuf[] buffer, check length to prevent buffer overflow of iodc_dbuf[], drop the iodc_retbuf[] buffer and fix some wrong indentings.
CVE-2022-50527: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix size validation for non-exclusive domains (v4) Fix amdgpu_bo_validate_size() to check whether the TTM domain manager for the requested memory exists, else we get a kernel oops when dereferencing "man". v2: Make the patch standalone, i.e. not dependent on local patches. v3: Preserve old behaviour and just check that the manager pointer is not NULL. v4: Complain if GTT domain requested and it is uninitialized--most likely a bug.
CVE-2022-50539: In the Linux kernel, the following vulnerability has been resolved: ARM: OMAP2+: omap4-common: Fix refcount leak bug In omap4_sram_init(), of_find_compatible_node() will return a node pointer with refcount incremented. We should use of_node_put() when it is not used anymore.
CVE-2022-50541: In the Linux kernel, the following vulnerability has been resolved: dmaengine: ti: k3-udma: Reset UDMA_CHAN_RT byte counters to prevent overflow UDMA_CHAN_RT_*BCNT_REG stores the real-time channel bytecount statistics. These registers are 32-bit hardware counters and the driver uses these counters to monitor the operational progress status for a channel, when transferring more than 4GB of data it was observed that these counters overflow and completion calculation of a operation gets affected and the transfer hangs indefinitely. This commit adds changes to decrease the byte count for every complete transaction so that these registers never overflow and the proper byte count statistics is maintained for ongoing transaction by the RT counters. Earlier uc->bcnt used to maintain a count of the completed bytes at driver side, since the RT counters maintain the statistics of current transaction now, the maintenance of uc->bcnt is not necessary.
CVE-2022-50550: In the Linux kernel, the following vulnerability has been resolved: blk-iolatency: Fix memory leak on add_disk() failures When a gendisk is successfully initialized but add_disk() fails such as when a loop device has invalid number of minor device numbers specified, blkcg_init_disk() is called during init and then blkcg_exit_disk() during error handling. Unfortunately, iolatency gets initialized in the former but doesn't get cleaned up in the latter. This is because, in non-error cases, the cleanup is performed by del_gendisk() calling rq_qos_exit(), the assumption being that rq_qos policies, iolatency being one of them, can only be activated once the disk is fully registered and visible. That assumption is true for wbt and iocost, but not so for iolatency as it gets initialized before add_disk() is called. It is desirable to lazy-init rq_qos policies because they are optional features and add to hot path overhead once initialized - each IO has to walk all the registered rq_qos policies. So, we want to switch iolatency to lazy init too. However, that's a bigger change. As a fix for the immediate problem, let's just add an extra call to rq_qos_exit() in blkcg_exit_disk(). This is safe because duplicate calls to rq_qos_exit() become noop's.
CVE-2022-50552: In the Linux kernel, the following vulnerability has been resolved: blk-mq: use quiesced elevator switch when reinitializing queues The hctx's run_work may be racing with the elevator switch when reinitializing hardware queues. The queue is merely frozen in this context, but that only prevents requests from allocating and doesn't stop the hctx work from running. The work may get an elevator pointer that's being torn down, and can result in use-after-free errors and kernel panics (example below). Use the quiesced elevator switch instead, and make the previous one static since it is now only used locally. nvme nvme0: resetting controller nvme nvme0: 32/0/0 default/read/poll queues BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 80000020c8861067 P4D 80000020c8861067 PUD 250f8c8067 PMD 0 Oops: 0000 [#1] SMP PTI Workqueue: kblockd blk_mq_run_work_fn RIP: 0010:kyber_has_work+0x29/0x70 ... Call Trace: __blk_mq_do_dispatch_sched+0x83/0x2b0 __blk_mq_sched_dispatch_requests+0x12e/0x170 blk_mq_sched_dispatch_requests+0x30/0x60 __blk_mq_run_hw_queue+0x2b/0x50 process_one_work+0x1ef/0x380 worker_thread+0x2d/0x3e0
CVE-2022-50554: In the Linux kernel, the following vulnerability has been resolved: blk-mq: avoid double ->queue_rq() because of early timeout David Jeffery found one double ->queue_rq() issue, so far it can be triggered in VM use case because of long vmexit latency or preempt latency of vCPU pthread or long page fault in vCPU pthread, then block IO req could be timed out before queuing the request to hardware but after calling blk_mq_start_request() during ->queue_rq(), then timeout handler may handle it by requeue, then double ->queue_rq() is caused, and kernel panic. So far, it is driver's responsibility to cover the race between timeout and completion, so it seems supposed to be solved in driver in theory, given driver has enough knowledge. But it is really one common problem, lots of driver could have similar issue, and could be hard to fix all affected drivers, even it isn't easy for driver to handle the race. So David suggests this patch by draining in-progress ->queue_rq() for solving this issue.
CVE-2022-50616: In the Linux kernel, the following vulnerability has been resolved: regulator: core: Use different devices for resource allocation and DT lookup Following by the below discussion, there's the potential UAF issue between regulator and mfd. https://lore.kernel.org/all/20221128143601.1698148-1-yangyingliang@huawei.com/ From the analysis of Yingliang CPU A |CPU B mt6370_probe() | devm_mfd_add_devices() | |mt6370_regulator_probe() | regulator_register() | //allocate init_data and add it to devres | regulator_of_get_init_data() i2c_unregister_device() | device_del() | devres_release_all() | // init_data is freed | release_nodes() | | // using init_data causes UAF | regulator_register() It's common to use mfd core to create child device for the regulator. In order to do the DT lookup for init data, the child that registered the regulator would pass its parent as the parameter. And this causes init data resource allocated to its parent, not itself. The issue happen when parent device is going to release and regulator core is still doing some operation of init data constraint for the regulator of child device. To fix it, this patch expand 'regulator_register' API to use the different devices for init data allocation and DT lookup.
CVE-2022-50627: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix monitor mode bringup crash When the interface is brought up in monitor mode, it leads to NULL pointer dereference crash. This crash happens when the packet type is extracted for a SKB. This extraction which is present in the received msdu delivery path,is not needed for the monitor ring packets since they are all RAW packets. Hence appending the flags with "RX_FLAG_ONLY_MONITOR" to skip that extraction. Observed calltrace: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000064 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=0000000048517000 [0000000000000064] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Modules linked in: ath11k_pci ath11k qmi_helpers CPU: 2 PID: 1781 Comm: napi/-271 Not tainted 6.1.0-rc5-wt-ath-656295-gef907406320c-dirty #6 Hardware name: Qualcomm Technologies, Inc. IPQ8074/AP-HK10-C2 (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : ath11k_hw_qcn9074_rx_desc_get_decap_type+0x34/0x60 [ath11k] lr : ath11k_hw_qcn9074_rx_desc_get_decap_type+0x5c/0x60 [ath11k] sp : ffff80000ef5bb10 x29: ffff80000ef5bb10 x28: 0000000000000000 x27: ffff000007baafa0 x26: ffff000014a91ed0 x25: 0000000000000000 x24: 0000000000000000 x23: ffff800002b77378 x22: ffff000014a91ec0 x21: ffff000006c8d600 x20: 0000000000000000 x19: ffff800002b77740 x18: 0000000000000006 x17: 736564203634343a x16: 656e694c20657079 x15: 0000000000000143 x14: 00000000ffffffea x13: ffff80000ef5b8b8 x12: ffff80000ef5b8c8 x11: ffff80000a591d30 x10: ffff80000a579d40 x9 : c0000000ffffefff x8 : 0000000000000003 x7 : 0000000000017fe8 x6 : ffff80000a579ce8 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 3a35ec12ed7f8900 x1 : 0000000000000000 x0 : 0000000000000052 Call trace: ath11k_hw_qcn9074_rx_desc_get_decap_type+0x34/0x60 [ath11k] ath11k_dp_rx_deliver_msdu.isra.42+0xa4/0x3d0 [ath11k] ath11k_dp_rx_mon_deliver.isra.43+0x2f8/0x458 [ath11k] ath11k_dp_rx_process_mon_rings+0x310/0x4c0 [ath11k] ath11k_dp_service_srng+0x234/0x338 [ath11k] ath11k_pcic_ext_grp_napi_poll+0x30/0xb8 [ath11k] __napi_poll+0x5c/0x190 napi_threaded_poll+0xf0/0x118 kthread+0xf4/0x110 ret_from_fork+0x10/0x20 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2022-50634: In the Linux kernel, the following vulnerability has been resolved: power: supply: cw2015: Fix potential null-ptr-deref in cw_bat_probe() cw_bat_probe() calls create_singlethread_workqueue() and not checked the ret value, which may return NULL. And a null-ptr-deref may happen: cw_bat_probe() create_singlethread_workqueue() # failed, cw_bat->wq is NULL queue_delayed_work() queue_delayed_work_on() __queue_delayed_work() # warning here, but continue __queue_work() # access wq->flags, null-ptr-deref Check the ret value and return -ENOMEM if it is NULL.
CVE-2022-50635: In the Linux kernel, the following vulnerability has been resolved: powerpc/kprobes: Fix null pointer reference in arch_prepare_kprobe() I found a null pointer reference in arch_prepare_kprobe(): # echo 'p cmdline_proc_show' > kprobe_events # echo 'p cmdline_proc_show+16' >> kprobe_events Kernel attempted to read user page (0) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000000 Faulting instruction address: 0xc000000000050bfc Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA PowerNV Modules linked in: CPU: 0 PID: 122 Comm: sh Not tainted 6.0.0-rc3-00007-gdcf8e5633e2e #10 NIP: c000000000050bfc LR: c000000000050bec CTR: 0000000000005bdc REGS: c0000000348475b0 TRAP: 0300 Not tainted (6.0.0-rc3-00007-gdcf8e5633e2e) MSR: 9000000000009033 <SF,HV,EE,ME,IR,DR,RI,LE> CR: 88002444 XER: 20040006 CFAR: c00000000022d100 DAR: 0000000000000000 DSISR: 40000000 IRQMASK: 0 ... NIP arch_prepare_kprobe+0x10c/0x2d0 LR arch_prepare_kprobe+0xfc/0x2d0 Call Trace: 0xc0000000012f77a0 (unreliable) register_kprobe+0x3c0/0x7a0 __register_trace_kprobe+0x140/0x1a0 __trace_kprobe_create+0x794/0x1040 trace_probe_create+0xc4/0xe0 create_or_delete_trace_kprobe+0x2c/0x80 trace_parse_run_command+0xf0/0x210 probes_write+0x20/0x40 vfs_write+0xfc/0x450 ksys_write+0x84/0x140 system_call_exception+0x17c/0x3a0 system_call_vectored_common+0xe8/0x278 --- interrupt: 3000 at 0x7fffa5682de0 NIP: 00007fffa5682de0 LR: 0000000000000000 CTR: 0000000000000000 REGS: c000000034847e80 TRAP: 3000 Not tainted (6.0.0-rc3-00007-gdcf8e5633e2e) MSR: 900000000280f033 <SF,HV,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 44002408 XER: 00000000 The address being probed has some special: cmdline_proc_show: Probe based on ftrace cmdline_proc_show+16: Probe for the next instruction at the ftrace location The ftrace-based kprobe does not generate kprobe::ainsn::insn, it gets set to NULL. In arch_prepare_kprobe() it will check for: ... prev = get_kprobe(p->addr - 1); preempt_enable_no_resched(); if (prev && ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) { ... If prev is based on ftrace, 'ppc_inst_read(prev->ainsn.insn)' will occur with a null pointer reference. At this point prev->addr will not be a prefixed instruction, so the check can be skipped. Check if prev is ftrace-based kprobe before reading 'prev->ainsn.insn' to fix this problem. [mpe: Trim oops]
CVE-2022-50642: In the Linux kernel, the following vulnerability has been resolved: platform/chrome: cros_ec_typec: zero out stale pointers `cros_typec_get_switch_handles` allocates four pointers when obtaining type-c switch handles. These pointers are all freed if failing to obtain any of them; therefore, pointers in `port` become stale. The stale pointers eventually cause use-after-free or double free in later code paths. Zeroing out all pointer fields after freeing to eliminate these stale pointers.
CVE-2022-50666: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Fix QP destroy to wait for all references dropped. Delay QP destroy completion until all siw references to QP are dropped. The calling RDMA core will free QP structure after successful return from siw_qp_destroy() call, so siw must not hold any remaining reference to the QP upon return. A use-after-free was encountered in xfstest generic/460, while testing NFSoRDMA. Here, after a TCP connection drop by peer, the triggered siw_cm_work_handler got delayed until after QP destroy call, referencing a QP which has already freed.
CVE-2022-50700: In the Linux kernel, the following vulnerability has been resolved: wifi: ath10k: Delay the unmapping of the buffer On WCN3990, we are seeing a rare scenario where copy engine hardware is sending a copy complete interrupt to the host driver while still processing the buffer that the driver has sent, this is leading into an SMMU fault triggering kernel panic. This is happening on copy engine channel 3 (CE3) where the driver normally enqueues WMI commands to the firmware. Upon receiving a copy complete interrupt, host driver will immediately unmap and frees the buffer presuming that hardware has processed the buffer. In the issue case, upon receiving copy complete interrupt, host driver will unmap and free the buffer but since hardware is still accessing the buffer (which in this case got unmapped in parallel), SMMU hardware will trigger an SMMU fault resulting in a kernel panic. In order to avoid this, as a work around, add a delay before unmapping the copy engine source DMA buffer. This is conditionally done for WCN3990 and only for the CE3 channel where issue is seen. Below is the crash signature: wifi smmu error: kernel: [ 10.120965] arm-smmu 15000000.iommu: Unhandled context fault: fsr=0x402, iova=0x7fdfd8ac0, fsynr=0x500003,cbfrsynra=0xc1, cb=6 arm-smmu 15000000.iommu: Unhandled context fault:fsr=0x402, iova=0x7fe06fdc0, fsynr=0x710003, cbfrsynra=0xc1, cb=6 qcom-q6v5-mss 4080000.remoteproc: fatal error received: err_qdi.c:1040:EF:wlan_process:0x1:WLAN RT:0x2091: cmnos_thread.c:3998:Asserted in copy_engine.c:AXI_ERROR_DETECTED:2149 remoteproc remoteproc0: crash detected in 4080000.remoteproc: type fatal error <3> remoteproc remoteproc0: handling crash #1 in 4080000.remoteproc pc : __arm_lpae_unmap+0x500/0x514 lr : __arm_lpae_unmap+0x4bc/0x514 sp : ffffffc011ffb530 x29: ffffffc011ffb590 x28: 0000000000000000 x27: 0000000000000000 x26: 0000000000000004 x25: 0000000000000003 x24: ffffffc011ffb890 x23: ffffffa762ef9be0 x22: ffffffa77244ef00 x21: 0000000000000009 x20: 00000007fff7c000 x19: 0000000000000003 x18: 0000000000000000 x17: 0000000000000004 x16: ffffffd7a357d9f0 x15: 0000000000000000 x14: 00fd5d4fa7ffffff x13: 000000000000000e x12: 0000000000000000 x11: 00000000ffffffff x10: 00000000fffffe00 x9 : 000000000000017c x8 : 000000000000000c x7 : 0000000000000000 x6 : ffffffa762ef9000 x5 : 0000000000000003 x4 : 0000000000000004 x3 : 0000000000001000 x2 : 00000007fff7c000 x1 : ffffffc011ffb890 x0 : 0000000000000000 Call trace: __arm_lpae_unmap+0x500/0x514 __arm_lpae_unmap+0x4bc/0x514 __arm_lpae_unmap+0x4bc/0x514 arm_lpae_unmap_pages+0x78/0xa4 arm_smmu_unmap_pages+0x78/0x104 __iommu_unmap+0xc8/0x1e4 iommu_unmap_fast+0x38/0x48 __iommu_dma_unmap+0x84/0x104 iommu_dma_free+0x34/0x50 dma_free_attrs+0xa4/0xd0 ath10k_htt_rx_free+0xc4/0xf4 [ath10k_core] ath10k_core_stop+0x64/0x7c [ath10k_core] ath10k_halt+0x11c/0x180 [ath10k_core] ath10k_stop+0x54/0x94 [ath10k_core] drv_stop+0x48/0x1c8 [mac80211] ieee80211_do_open+0x638/0x77c [mac80211] ieee80211_open+0x48/0x5c [mac80211] __dev_open+0xb4/0x174 __dev_change_flags+0xc4/0x1dc dev_change_flags+0x3c/0x7c devinet_ioctl+0x2b4/0x580 inet_ioctl+0xb0/0x1b4 sock_do_ioctl+0x4c/0x16c compat_ifreq_ioctl+0x1cc/0x35c compat_sock_ioctl+0x110/0x2ac __arm64_compat_sys_ioctl+0xf4/0x3e0 el0_svc_common+0xb4/0x17c el0_svc_compat_handler+0x2c/0x58 el0_svc_compat+0x8/0x2c Tested-on: WCN3990 hw1.0 SNOC WLAN.HL.2.0-01387-QCAHLSWMTPLZ-1
CVE-2022-50704: In the Linux kernel, the following vulnerability has been resolved: USB: gadget: Fix use-after-free during usb config switch In the process of switching USB config from rndis to other config, if the hardware does not support the ->pullup callback, or the hardware encounters a low probability fault, both of them may cause the ->pullup callback to fail, which will then cause a system panic (use after free). The gadget drivers sometimes need to be unloaded regardless of the hardware's behavior. Analysis as follows: ======================================================================= (1) write /config/usb_gadget/g1/UDC "none" gether_disconnect+0x2c/0x1f8 rndis_disable+0x4c/0x74 composite_disconnect+0x74/0xb0 configfs_composite_disconnect+0x60/0x7c usb_gadget_disconnect+0x70/0x124 usb_gadget_unregister_driver+0xc8/0x1d8 gadget_dev_desc_UDC_store+0xec/0x1e4 (2) rm /config/usb_gadget/g1/configs/b.1/f1 rndis_deregister+0x28/0x54 rndis_free+0x44/0x7c usb_put_function+0x14/0x1c config_usb_cfg_unlink+0xc4/0xe0 configfs_unlink+0x124/0x1c8 vfs_unlink+0x114/0x1dc (3) rmdir /config/usb_gadget/g1/functions/rndis.gs4 panic+0x1fc/0x3d0 do_page_fault+0xa8/0x46c do_mem_abort+0x3c/0xac el1_sync_handler+0x40/0x78 0xffffff801138f880 rndis_close+0x28/0x34 eth_stop+0x74/0x110 dev_close_many+0x48/0x194 rollback_registered_many+0x118/0x814 unregister_netdev+0x20/0x30 gether_cleanup+0x1c/0x38 rndis_attr_release+0xc/0x14 kref_put+0x74/0xb8 configfs_rmdir+0x314/0x374 If gadget->ops->pullup() return an error, function rndis_close() will be called, then it will causes a use-after-free problem. =======================================================================
CVE-2022-50708: In the Linux kernel, the following vulnerability has been resolved: HSI: ssi_protocol: fix potential resource leak in ssip_pn_open() ssip_pn_open() claims the HSI client's port with hsi_claim_port(). When hsi_register_port_event() gets some error and returns a negetive value, the HSI client's port should be released with hsi_release_port(). Fix it by calling hsi_release_port() when hsi_register_port_event() fails.
CVE-2022-50720: In the Linux kernel, the following vulnerability has been resolved: x86/apic: Don't disable x2APIC if locked The APIC supports two modes, legacy APIC (or xAPIC), and Extended APIC (or x2APIC). X2APIC mode is mostly compatible with legacy APIC, but it disables the memory-mapped APIC interface in favor of one that uses MSRs. The APIC mode is controlled by the EXT bit in the APIC MSR. The MMIO/xAPIC interface has some problems, most notably the APIC LEAK [1]. This bug allows an attacker to use the APIC MMIO interface to extract data from the SGX enclave. Introduce support for a new feature that will allow the BIOS to lock the APIC in x2APIC mode. If the APIC is locked in x2APIC mode and the kernel tries to disable the APIC or revert to legacy APIC mode a GP fault will occur. Introduce support for a new MSR (IA32_XAPIC_DISABLE_STATUS) and handle the new locked mode when the LEGACY_XAPIC_DISABLED bit is set by preventing the kernel from trying to disable the x2APIC. On platforms with the IA32_XAPIC_DISABLE_STATUS MSR, if SGX or TDX are enabled the LEGACY_XAPIC_DISABLED will be set by the BIOS. If legacy APIC is required, then it SGX and TDX need to be disabled in the BIOS. [1]: https://aepicleak.com/aepicleak.pdf
CVE-2022-50746: In the Linux kernel, the following vulnerability has been resolved: erofs: validate the extent length for uncompressed pclusters syzkaller reported a KASAN use-after-free: https://syzkaller.appspot.com/bug?extid=2ae90e873e97f1faf6f2 The referenced fuzzed image actually has two issues: - m_pa == 0 as a non-inlined pcluster; - The logical length is longer than its physical length. The first issue has already been addressed. This patch addresses the second issue by checking the extent length validity.
CVE-2022-50764: In the Linux kernel, the following vulnerability has been resolved: ipv6/sit: use DEV_STATS_INC() to avoid data-races syzbot/KCSAN reported that multiple cpus are updating dev->stats.tx_error concurrently. This is because sit tunnels are NETIF_F_LLTX, meaning their ndo_start_xmit() is not protected by a spinlock. While original KCSAN report was about tx path, rx path has the same issue.
CVE-2022-50766: In the Linux kernel, the following vulnerability has been resolved: btrfs: set generation before calling btrfs_clean_tree_block in btrfs_init_new_buffer syzbot is reporting uninit-value in btrfs_clean_tree_block() [1], for commit bc877d285ca3dba2 ("btrfs: Deduplicate extent_buffer init code") missed that btrfs_set_header_generation() in btrfs_init_new_buffer() must not be moved to after clean_tree_block() because clean_tree_block() is calling btrfs_header_generation() since commit 55c69072d6bd5be1 ("Btrfs: Fix extent_buffer usage when nodesize != leafsize"). Since memzero_extent_buffer() will reset "struct btrfs_header" part, we can't move btrfs_set_header_generation() to before memzero_extent_buffer(). Just re-add btrfs_set_header_generation() before btrfs_clean_tree_block().
CVE-2022-50772: In the Linux kernel, the following vulnerability has been resolved: netdevsim: fix memory leak in nsim_bus_dev_new() If device_register() failed in nsim_bus_dev_new(), the value of reference in nsim_bus_dev->dev is 1. obj->name in nsim_bus_dev->dev will not be released. unreferenced object 0xffff88810352c480 (size 16): comm "echo", pid 5691, jiffies 4294945921 (age 133.270s) hex dump (first 16 bytes): 6e 65 74 64 65 76 73 69 6d 31 00 00 00 00 00 00 netdevsim1...... backtrace: [<000000005e2e5e26>] __kmalloc_node_track_caller+0x3a/0xb0 [<0000000094ca4fc8>] kvasprintf+0xc3/0x160 [<00000000aad09bcc>] kvasprintf_const+0x55/0x180 [<000000009bac868d>] kobject_set_name_vargs+0x56/0x150 [<000000007c1a5d70>] dev_set_name+0xbb/0xf0 [<00000000ad0d126b>] device_add+0x1f8/0x1cb0 [<00000000c222ae24>] new_device_store+0x3b6/0x5e0 [<0000000043593421>] bus_attr_store+0x72/0xa0 [<00000000cbb1833a>] sysfs_kf_write+0x106/0x160 [<00000000d0dedb8a>] kernfs_fop_write_iter+0x3a8/0x5a0 [<00000000770b66e2>] vfs_write+0x8f0/0xc80 [<0000000078bb39be>] ksys_write+0x106/0x210 [<00000000005e55a4>] do_syscall_64+0x35/0x80 [<00000000eaa40bbc>] entry_SYSCALL_64_after_hwframe+0x46/0xb0
CVE-2022-50815: In the Linux kernel, the following vulnerability has been resolved: ext2: Add sanity checks for group and filesystem size Add sanity check that filesystem size does not exceed the underlying device size and that group size is big enough so that metadata can fit into it. This avoid trying to mount some crafted filesystems with extremely large group counts.
CVE-2022-50822: In the Linux kernel, the following vulnerability has been resolved: RDMA/restrack: Release MR restrack when delete The MR restrack also needs to be released when delete it, otherwise it cause memory leak as the task struct won't be released.
CVE-2022-50851: In the Linux kernel, the following vulnerability has been resolved: vhost_vdpa: fix the crash in unmap a large memory While testing in vIOMMU, sometimes Guest will unmap very large memory, which will cause the crash. To fix this, add a new function vhost_vdpa_general_unmap(). This function will only unmap the memory that saved in iotlb. Call Trace: [ 647.820144] ------------[ cut here ]------------ [ 647.820848] kernel BUG at drivers/iommu/intel/iommu.c:1174! [ 647.821486] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 647.822082] CPU: 10 PID: 1181 Comm: qemu-system-x86 Not tainted 6.0.0-rc1home_lulu_2452_lulu7_vhost+ #62 [ 647.823139] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-29-g6a62e0cb0dfe-prebuilt.qem4 [ 647.824365] RIP: 0010:domain_unmap+0x48/0x110 [ 647.825424] Code: 48 89 fb 8d 4c f6 1e 39 c1 0f 4f c8 83 e9 0c 83 f9 3f 7f 18 48 89 e8 48 d3 e8 48 85 c0 75 59 [ 647.828064] RSP: 0018:ffffae5340c0bbf0 EFLAGS: 00010202 [ 647.828973] RAX: 0000000000000001 RBX: ffff921793d10540 RCX: 000000000000001b [ 647.830083] RDX: 00000000080000ff RSI: 0000000000000001 RDI: ffff921793d10540 [ 647.831214] RBP: 0000000007fc0100 R08: ffffae5340c0bcd0 R09: 0000000000000003 [ 647.832388] R10: 0000007fc0100000 R11: 0000000000100000 R12: 00000000080000ff [ 647.833668] R13: ffffae5340c0bcd0 R14: ffff921793d10590 R15: 0000008000100000 [ 647.834782] FS: 00007f772ec90640(0000) GS:ffff921ce7a80000(0000) knlGS:0000000000000000 [ 647.836004] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 647.836990] CR2: 00007f02c27a3a20 CR3: 0000000101b0c006 CR4: 0000000000372ee0 [ 647.838107] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 647.839283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 647.840666] Call Trace: [ 647.841437] <TASK> [ 647.842107] intel_iommu_unmap_pages+0x93/0x140 [ 647.843112] __iommu_unmap+0x91/0x1b0 [ 647.844003] iommu_unmap+0x6a/0x95 [ 647.844885] vhost_vdpa_unmap+0x1de/0x1f0 [vhost_vdpa] [ 647.845985] vhost_vdpa_process_iotlb_msg+0xf0/0x90b [vhost_vdpa] [ 647.847235] ? _raw_spin_unlock+0x15/0x30 [ 647.848181] ? _copy_from_iter+0x8c/0x580 [ 647.849137] vhost_chr_write_iter+0xb3/0x430 [vhost] [ 647.850126] vfs_write+0x1e4/0x3a0 [ 647.850897] ksys_write+0x53/0xd0 [ 647.851688] do_syscall_64+0x3a/0x90 [ 647.852508] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 647.853457] RIP: 0033:0x7f7734ef9f4f [ 647.854408] Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 29 76 f8 ff 48 8b 54 24 18 48 8b 74 24 10 41 89 c8 [ 647.857217] RSP: 002b:00007f772ec8f040 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 [ 647.858486] RAX: ffffffffffffffda RBX: 00000000fef00000 RCX: 00007f7734ef9f4f [ 647.859713] RDX: 0000000000000048 RSI: 00007f772ec8f090 RDI: 0000000000000010 [ 647.860942] RBP: 00007f772ec8f1a0 R08: 0000000000000000 R09: 0000000000000000 [ 647.862206] R10: 0000000000000001 R11: 0000000000000293 R12: 0000000000000010 [ 647.863446] R13: 0000000000000002 R14: 0000000000000000 R15: ffffffff01100000 [ 647.864692] </TASK> [ 647.865458] Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs v] [ 647.874688] ---[ end trace 0000000000000000 ]---
CVE-2022-50871: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: Fix qmi_msg_handler data structure initialization qmi_msg_handler is required to be null terminated by QMI module. There might be a case where a handler for a msg id is not present in the handlers array which can lead to infinite loop while searching the handler and therefore out of bound access in qmi_invoke_handler(). Hence update the initialization in qmi_msg_handler data structure. Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1
CVE-2023-24023: Bluetooth BR/EDR devices with Secure Simple Pairing and Secure Connections pairing in Bluetooth Core Specification 4.2 through 5.4 allow certain man-in-the-middle attacks that force a short key length, and might lead to discovery of the encryption key and live injection, aka BLUFFS.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-32251: A vulnerability has been identified in the Linux kernel's ksmbd component (kernel SMB/CIFS server). A security control designed to prevent dictionary attacks, which introduces a 5-second delay during session setup, can be bypassed through the use of asynchronous requests. This bypass negates the intended anti-brute-force protection, potentially allowing attackers to conduct dictionary attacks more efficiently against user credentials or other authentication mechanisms.
CVE-2023-32253: A flaw was found in the Linux kernel's ksmbd component. A deadlock is triggered by sending multiple concurrent session setup requests, possibly leading to a denial of service.
CVE-2023-32255: A flaw was found in the Linux kernel's ksmbd component. A memory leak can occur if a client sends a session setup request with an unknown NTLMSSP message type, potentially leading to resource exhaustion.
CVE-2023-32256: A flaw was found in the Linux kernel's ksmbd component. A race condition between smb2 close operation and logoff in multichannel connections could result in a use-after-free issue.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2023-52452: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix accesses to uninit stack slots Privileged programs are supposed to be able to read uninitialized stack memory (ever since 6715df8d5) but, before this patch, these accesses were permitted inconsistently. In particular, accesses were permitted above state->allocated_stack, but not below it. In other words, if the stack was already "large enough", the access was permitted, but otherwise the access was rejected instead of being allowed to "grow the stack". This undesired rejection was happening in two places: - in check_stack_slot_within_bounds() - in check_stack_range_initialized() This patch arranges for these accesses to be permitted. A bunch of tests that were relying on the old rejection had to change; all of them were changed to add also run unprivileged, in which case the old behavior persists. One tests couldn't be updated - global_func16 - because it can't run unprivileged for other reasons. This patch also fixes the tracking of the stack size for variable-offset reads. This second fix is bundled in the same commit as the first one because they're inter-related. Before this patch, writes to the stack using registers containing a variable offset (as opposed to registers with fixed, known values) were not properly contributing to the function's needed stack size. As a result, it was possible for a program to verify, but then to attempt to read out-of-bounds data at runtime because a too small stack had been allocated for it. Each function tracks the size of the stack it needs in bpf_subprog_info.stack_depth, which is maintained by update_stack_depth(). For regular memory accesses, check_mem_access() was calling update_state_depth() but it was passing in only the fixed part of the offset register, ignoring the variable offset. This was incorrect; the minimum possible value of that register should be used instead. This tracking is now fixed by centralizing the tracking of stack size in grow_stack_state(), and by lifting the calls to grow_stack_state() to check_stack_access_within_bounds() as suggested by Andrii. The code is now simpler and more convincingly tracks the correct maximum stack size. check_stack_range_initialized() can now rely on enough stack having been allocated for the access; this helps with the fix for the first issue. A few tests were changed to also check the stack depth computation. The one that fails without this patch is verifier_var_off:stack_write_priv_vs_unpriv.
CVE-2023-52481: In the Linux kernel, the following vulnerability has been resolved: arm64: errata: Add Cortex-A520 speculative unprivileged load workaround Implement the workaround for ARM Cortex-A520 erratum 2966298. On an affected Cortex-A520 core, a speculatively executed unprivileged load might leak data from a privileged load via a cache side channel. The issue only exists for loads within a translation regime with the same translation (e.g. same ASID and VMID). Therefore, the issue only affects the return to EL0. The workaround is to execute a TLBI before returning to EL0 after all loads of privileged data. A non-shareable TLBI to any address is sufficient. The workaround isn't necessary if page table isolation (KPTI) is enabled, but for simplicity it will be. Page table isolation should normally be disabled for Cortex-A520 as it supports the CSV3 feature and the E0PD feature (used when KASLR is enabled).
CVE-2023-52485: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before sending a command [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] For functions that execute within a DC context or DC lock we can wrap the direct calls to dm_execute_dmub_cmd/list with code that exits idle power optimizations and reallows once we're done with the command submission on success. For DM direct submissions the DM will need to manage the enter/exit sequencing manually. We cannot invoke a DMCUB command directly within the DM execution helper or we can deadlock.
CVE-2023-52494: In the Linux kernel, the following vulnerability has been resolved: bus: mhi: host: Add alignment check for event ring read pointer Though we do check the event ring read pointer by "is_valid_ring_ptr" to make sure it is in the buffer range, but there is another risk the pointer may be not aligned. Since we are expecting event ring elements are 128 bits(struct mhi_ring_element) aligned, an unaligned read pointer could lead to multiple issues like DoS or ring buffer memory corruption. So add a alignment check for event ring read pointer.
CVE-2023-52531: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: Fix a memory corruption issue A few lines above, space is kzalloc()'ed for: sizeof(struct iwl_nvm_data) + sizeof(struct ieee80211_channel) + sizeof(struct ieee80211_rate) 'mvm->nvm_data' is a 'struct iwl_nvm_data', so it is fine. At the end of this structure, there is the 'channels' flex array. Each element is of type 'struct ieee80211_channel'. So only 1 element is allocated in this array. When doing: mvm->nvm_data->bands[0].channels = mvm->nvm_data->channels; We point at the first element of the 'channels' flex array. So this is fine. However, when doing: mvm->nvm_data->bands[0].bitrates = (void *)((u8 *)mvm->nvm_data->channels + 1); because of the "(u8 *)" cast, we add only 1 to the address of the beginning of the flex array. It is likely that we want point at the 'struct ieee80211_rate' allocated just after. Remove the spurious casting so that the pointer arithmetic works as expected.
CVE-2023-52561: In the Linux kernel, the following vulnerability has been resolved: arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved Adding a reserved memory region for the framebuffer memory (the splash memory region set up by the bootloader). It fixes a kernel panic (arm-smmu: Unhandled context fault at this particular memory region) reported on DB845c running v5.10.y.
CVE-2023-52586: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: Add mutex lock in control vblank irq Add a mutex lock to control vblank irq to synchronize vblank enable/disable operations happening from different threads to prevent race conditions while registering/unregistering the vblank irq callback. v4: -Removed vblank_ctl_lock from dpu_encoder_virt, so it is only a parameter of dpu_encoder_phys. -Switch from atomic refcnt to a simple int counter as mutex has now been added v3: Mistakenly did not change wording in last version. It is done now. v2: Slightly changed wording of commit message Patchwork: https://patchwork.freedesktop.org/patch/571854/
CVE-2023-52588: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to tag gcing flag on page during block migration It needs to add missing gcing flag on page during block migration, in order to garantee migrated data be persisted during checkpoint, otherwise out-of-order persistency between data and node may cause data corruption after SPOR. Similar issue was fixed by commit 2d1fe8a86bf5 ("f2fs: fix to tag gcing flag on page during file defragment").
CVE-2023-52589: In the Linux kernel, the following vulnerability has been resolved: media: rkisp1: Fix IRQ disable race issue In rkisp1_isp_stop() and rkisp1_csi_disable() the driver masks the interrupts and then apparently assumes that the interrupt handler won't be running, and proceeds in the stop procedure. This is not the case, as the interrupt handler can already be running, which would lead to the ISP being disabled while the interrupt handler handling a captured frame. This brings up two issues: 1) the ISP could be powered off while the interrupt handler is still running and accessing registers, leading to board lockup, and 2) the interrupt handler code and the code that disables the streaming might do things that conflict. It is not clear to me if 2) causes a real issue, but 1) can be seen with a suitable delay (or printk in my case) in the interrupt handler, leading to board lockup.
CVE-2023-52590: In the Linux kernel, the following vulnerability has been resolved: ocfs2: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change ocfs2 rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52591: In the Linux kernel, the following vulnerability has been resolved: reiserfs: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change reiserfs rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52593: In the Linux kernel, the following vulnerability has been resolved: wifi: wfx: fix possible NULL pointer dereference in wfx_set_mfp_ap() Since 'ieee80211_beacon_get()' can return NULL, 'wfx_set_mfp_ap()' should check the return value before examining skb data. So convert the latter to return an appropriate error code and propagate it to return from 'wfx_start_ap()' as well. Compile tested only.
CVE-2023-52608: In the Linux kernel, the following vulnerability has been resolved: firmware: arm_scmi: Check mailbox/SMT channel for consistency On reception of a completion interrupt the shared memory area is accessed to retrieve the message header at first and then, if the message sequence number identifies a transaction which is still pending, the related payload is fetched too. When an SCMI command times out the channel ownership remains with the platform until eventually a late reply is received and, as a consequence, any further transmission attempt remains pending, waiting for the channel to be relinquished by the platform. Once that late reply is received the channel ownership is given back to the agent and any pending request is then allowed to proceed and overwrite the SMT area of the just delivered late reply; then the wait for the reply to the new request starts. It has been observed that the spurious IRQ related to the late reply can be wrongly associated with the freshly enqueued request: when that happens the SCMI stack in-flight lookup procedure is fooled by the fact that the message header now present in the SMT area is related to the new pending transaction, even though the real reply has still to arrive. This race-condition on the A2P channel can be detected by looking at the channel status bits: a genuine reply from the platform will have set the channel free bit before triggering the completion IRQ. Add a consistency check to validate such condition in the A2P ISR.
CVE-2023-52610: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ct: fix skb leak and crash on ooo frags act_ct adds skb->users before defragmentation. If frags arrive in order, the last frag's reference is reset in: inet_frag_reasm_prepare skb_morph which is not straightforward. However when frags arrive out of order, nobody unref the last frag, and all frags are leaked. The situation is even worse, as initiating packet capture can lead to a crash[0] when skb has been cloned and shared at the same time. Fix the issue by removing skb_get() before defragmentation. act_ct returns TC_ACT_CONSUMED when defrag failed or in progress. [0]: [ 843.804823] ------------[ cut here ]------------ [ 843.809659] kernel BUG at net/core/skbuff.c:2091! [ 843.814516] invalid opcode: 0000 [#1] PREEMPT SMP [ 843.819296] CPU: 7 PID: 0 Comm: swapper/7 Kdump: loaded Tainted: G S 6.7.0-rc3 #2 [ 843.824107] Hardware name: XFUSION 1288H V6/BC13MBSBD, BIOS 1.29 11/25/2022 [ 843.828953] RIP: 0010:pskb_expand_head+0x2ac/0x300 [ 843.833805] Code: 8b 70 28 48 85 f6 74 82 48 83 c6 08 bf 01 00 00 00 e8 38 bd ff ff 8b 83 c0 00 00 00 48 03 83 c8 00 00 00 e9 62 ff ff ff 0f 0b <0f> 0b e8 8d d0 ff ff e9 b3 fd ff ff 81 7c 24 14 40 01 00 00 4c 89 [ 843.843698] RSP: 0018:ffffc9000cce07c0 EFLAGS: 00010202 [ 843.848524] RAX: 0000000000000002 RBX: ffff88811a211d00 RCX: 0000000000000820 [ 843.853299] RDX: 0000000000000640 RSI: 0000000000000000 RDI: ffff88811a211d00 [ 843.857974] RBP: ffff888127d39518 R08: 00000000bee97314 R09: 0000000000000000 [ 843.862584] R10: 0000000000000000 R11: ffff8881109f0000 R12: 0000000000000880 [ 843.867147] R13: ffff888127d39580 R14: 0000000000000640 R15: ffff888170f7b900 [ 843.871680] FS: 0000000000000000(0000) GS:ffff889ffffc0000(0000) knlGS:0000000000000000 [ 843.876242] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 843.880778] CR2: 00007fa42affcfb8 CR3: 000000011433a002 CR4: 0000000000770ef0 [ 843.885336] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 843.889809] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 843.894229] PKRU: 55555554 [ 843.898539] Call Trace: [ 843.902772] <IRQ> [ 843.906922] ? __die_body+0x1e/0x60 [ 843.911032] ? die+0x3c/0x60 [ 843.915037] ? do_trap+0xe2/0x110 [ 843.918911] ? pskb_expand_head+0x2ac/0x300 [ 843.922687] ? do_error_trap+0x65/0x80 [ 843.926342] ? pskb_expand_head+0x2ac/0x300 [ 843.929905] ? exc_invalid_op+0x50/0x60 [ 843.933398] ? pskb_expand_head+0x2ac/0x300 [ 843.936835] ? asm_exc_invalid_op+0x1a/0x20 [ 843.940226] ? pskb_expand_head+0x2ac/0x300 [ 843.943580] inet_frag_reasm_prepare+0xd1/0x240 [ 843.946904] ip_defrag+0x5d4/0x870 [ 843.950132] nf_ct_handle_fragments+0xec/0x130 [nf_conntrack] [ 843.953334] tcf_ct_act+0x252/0xd90 [act_ct] [ 843.956473] ? tcf_mirred_act+0x516/0x5a0 [act_mirred] [ 843.959657] tcf_action_exec+0xa1/0x160 [ 843.962823] fl_classify+0x1db/0x1f0 [cls_flower] [ 843.966010] ? skb_clone+0x53/0xc0 [ 843.969173] tcf_classify+0x24d/0x420 [ 843.972333] tc_run+0x8f/0xf0 [ 843.975465] __netif_receive_skb_core+0x67a/0x1080 [ 843.978634] ? dev_gro_receive+0x249/0x730 [ 843.981759] __netif_receive_skb_list_core+0x12d/0x260 [ 843.984869] netif_receive_skb_list_internal+0x1cb/0x2f0 [ 843.987957] ? mlx5e_handle_rx_cqe_mpwrq_rep+0xfa/0x1a0 [mlx5_core] [ 843.991170] napi_complete_done+0x72/0x1a0 [ 843.994305] mlx5e_napi_poll+0x28c/0x6d0 [mlx5_core] [ 843.997501] __napi_poll+0x25/0x1b0 [ 844.000627] net_rx_action+0x256/0x330 [ 844.003705] __do_softirq+0xb3/0x29b [ 844.006718] irq_exit_rcu+0x9e/0xc0 [ 844.009672] common_interrupt+0x86/0xa0 [ 844.012537] </IRQ> [ 844.015285] <TASK> [ 844.017937] asm_common_interrupt+0x26/0x40 [ 844.020591] RIP: 0010:acpi_safe_halt+0x1b/0x20 [ 844.023247] Code: ff 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 65 48 8b 04 25 00 18 03 00 48 8b 00 a8 08 75 0c 66 90 0f 00 2d 81 d0 44 00 fb ---truncated---
CVE-2023-52624: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before executing GPINT commands [Why] DMCUB can be in idle when we attempt to interface with the HW through the GPINT mailbox resulting in a system hang. [How] Add dc_wake_and_execute_gpint() to wrap the wake, execute, sleep sequence. If the GPINT executes successfully then DMCUB will be put back into sleep after the optional response is returned. It functions similar to the inbox command interface.
CVE-2023-52625: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Refactor DMCUB enter/exit idle interface [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] We need to exit out of the idle state prior to sending a command, but the process that performs the exit also invokes a command itself. Fixing this issue involves the following: 1. Using a software state to track whether or not we need to start the process to exit idle or notify idle. It's possible for the hardware to have exited an idle state without driver knowledge, but entering one is always restricted to a driver allow - which makes the SW state vs HW state mismatch issue purely one of optimization, which should seldomly be hit, if at all. 2. Refactor any instances of exit/notify idle to use a single wrapper that maintains this SW state. This works simialr to dc_allow_idle_optimizations, but works at the DMCUB level and makes sure the state is marked prior to any notify/exit idle so we don't enter an infinite loop. 3. Make sure we exit out of idle prior to sending any commands or waiting for DMCUB idle. This patch takes care of 1/2. A future patch will take care of wrapping DMCUB command submission with calls to this new interface.
CVE-2023-52629: In the Linux kernel, the following vulnerability has been resolved: sh: push-switch: Reorder cleanup operations to avoid use-after-free bug The original code puts flush_work() before timer_shutdown_sync() in switch_drv_remove(). Although we use flush_work() to stop the worker, it could be rescheduled in switch_timer(). As a result, a use-after-free bug can occur. The details are shown below: (cpu 0) | (cpu 1) switch_drv_remove() | flush_work() | ... | switch_timer // timer | schedule_work(&psw->work) timer_shutdown_sync() | ... | switch_work_handler // worker kfree(psw) // free | | psw->state = 0 // use This patch puts timer_shutdown_sync() before flush_work() to mitigate the bugs. As a result, the worker and timer will be stopped safely before the deallocate operations.
CVE-2023-52633: In the Linux kernel, the following vulnerability has been resolved: um: time-travel: fix time corruption In 'basic' time-travel mode (without =inf-cpu or =ext), we still get timer interrupts. These can happen at arbitrary points in time, i.e. while in timer_read(), which pushes time forward just a little bit. Then, if we happen to get the interrupt after calculating the new time to push to, but before actually finishing that, the interrupt will set the time to a value that's incompatible with the forward, and we'll crash because time goes backwards when we do the forwarding. Fix this by reading the time_travel_time, calculating the adjustment, and doing the adjustment all with interrupts disabled.
CVE-2023-52639: In the Linux kernel, the following vulnerability has been resolved: KVM: s390: vsie: fix race during shadow creation Right now it is possible to see gmap->private being zero in kvm_s390_vsie_gmap_notifier resulting in a crash. This is due to the fact that we add gmap->private == kvm after creation: static int acquire_gmap_shadow(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { [...] gmap = gmap_shadow(vcpu->arch.gmap, asce, edat); if (IS_ERR(gmap)) return PTR_ERR(gmap); gmap->private = vcpu->kvm; Let children inherit the private field of the parent.
CVE-2023-52652: In the Linux kernel, the following vulnerability has been resolved: NTB: fix possible name leak in ntb_register_device() If device_register() fails in ntb_register_device(), the device name allocated by dev_set_name() should be freed. As per the comment in device_register(), callers should use put_device() to give up the reference in the error path. So fix this by calling put_device() in the error path so that the name can be freed in kobject_cleanup(). As a result of this, put_device() in the error path of ntb_register_device() is removed and the actual error is returned. [mani: reworded commit message]
CVE-2023-52653: In the Linux kernel, the following vulnerability has been resolved: SUNRPC: fix a memleak in gss_import_v2_context The ctx->mech_used.data allocated by kmemdup is not freed in neither gss_import_v2_context nor it only caller gss_krb5_import_sec_context, which frees ctx on error. Thus, this patch reform the last call of gss_import_v2_context to the gss_krb5_import_ctx_v2, preventing the memleak while keepping the return formation.
CVE-2023-52660: In the Linux kernel, the following vulnerability has been resolved: media: rkisp1: Fix IRQ handling due to shared interrupts The driver requests the interrupts as IRQF_SHARED, so the interrupt handlers can be called at any time. If such a call happens while the ISP is powered down, the SoC will hang as the driver tries to access the ISP registers. This can be reproduced even without the platform sharing the IRQ line: Enable CONFIG_DEBUG_SHIRQ and unload the driver, and the board will hang. Fix this by adding a new field, 'irqs_enabled', which is used to bail out from the interrupt handler when the ISP is not operational.
CVE-2023-52664: In the Linux kernel, the following vulnerability has been resolved: net: atlantic: eliminate double free in error handling logic Driver has a logic leak in ring data allocation/free, where aq_ring_free could be called multiple times on same ring, if system is under stress and got memory allocation error. Ring pointer was used as an indicator of failure, but this is not correct since only ring data is allocated/deallocated. Ring itself is an array member. Changing ring allocation functions to return error code directly. This simplifies error handling and eliminates aq_ring_free on higher layer.
CVE-2023-52671: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix hang/underflow when transitioning to ODM4:1 [Why] Under some circumstances, disabling an OPTC and attempting to reclaim its OPP(s) for a different OPTC could cause a hang/underflow due to OPPs not being properly disconnected from the disabled OPTC. [How] Ensure that all OPPs are unassigned from an OPTC when it gets disabled.
CVE-2023-52674: In the Linux kernel, the following vulnerability has been resolved: ALSA: scarlett2: Add clamp() in scarlett2_mixer_ctl_put() Ensure the value passed to scarlett2_mixer_ctl_put() is between 0 and SCARLETT2_MIXER_MAX_VALUE so we don't attempt to access outside scarlett2_mixer_values[].
CVE-2023-52676: In the Linux kernel, the following vulnerability has been resolved: bpf: Guard stack limits against 32bit overflow This patch promotes the arithmetic around checking stack bounds to be done in the 64-bit domain, instead of the current 32bit. The arithmetic implies adding together a 64-bit register with a int offset. The register was checked to be below 1<<29 when it was variable, but not when it was fixed. The offset either comes from an instruction (in which case it is 16 bit), from another register (in which case the caller checked it to be below 1<<29 [1]), or from the size of an argument to a kfunc (in which case it can be a u32 [2]). Between the register being inconsistently checked to be below 1<<29, and the offset being up to an u32, it appears that we were open to overflowing the `int`s which were currently used for arithmetic. [1] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L7494-L7498 [2] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L11904
CVE-2023-52677: In the Linux kernel, the following vulnerability has been resolved: riscv: Check if the code to patch lies in the exit section Otherwise we fall through to vmalloc_to_page() which panics since the address does not lie in the vmalloc region.
CVE-2023-52680: In the Linux kernel, the following vulnerability has been resolved: ALSA: scarlett2: Add missing error checks to *_ctl_get() The *_ctl_get() functions which call scarlett2_update_*() were not checking the return value. Fix to check the return value and pass to the caller.
CVE-2023-52682: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to wait on block writeback for post_read case If inode is compressed, but not encrypted, it missed to call f2fs_wait_on_block_writeback() to wait for GCed page writeback in IPU write path. Thread A GC-Thread - f2fs_gc - do_garbage_collect - gc_data_segment - move_data_block - f2fs_submit_page_write migrate normal cluster's block via meta_inode's page cache - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_submit_page_bio IRQ - f2fs_read_end_io IRQ old data overrides new data due to out-of-order GC and common IO. - f2fs_read_end_io
CVE-2023-52700: In the Linux kernel, the following vulnerability has been resolved: tipc: fix kernel warning when sending SYN message When sending a SYN message, this kernel stack trace is observed: ... [ 13.396352] RIP: 0010:_copy_from_iter+0xb4/0x550 ... [ 13.398494] Call Trace: [ 13.398630] <TASK> [ 13.398630] ? __alloc_skb+0xed/0x1a0 [ 13.398630] tipc_msg_build+0x12c/0x670 [tipc] [ 13.398630] ? shmem_add_to_page_cache.isra.71+0x151/0x290 [ 13.398630] __tipc_sendmsg+0x2d1/0x710 [tipc] [ 13.398630] ? tipc_connect+0x1d9/0x230 [tipc] [ 13.398630] ? __local_bh_enable_ip+0x37/0x80 [ 13.398630] tipc_connect+0x1d9/0x230 [tipc] [ 13.398630] ? __sys_connect+0x9f/0xd0 [ 13.398630] __sys_connect+0x9f/0xd0 [ 13.398630] ? preempt_count_add+0x4d/0xa0 [ 13.398630] ? fpregs_assert_state_consistent+0x22/0x50 [ 13.398630] __x64_sys_connect+0x16/0x20 [ 13.398630] do_syscall_64+0x42/0x90 [ 13.398630] entry_SYSCALL_64_after_hwframe+0x63/0xcd It is because commit a41dad905e5a ("iov_iter: saner checks for attempt to copy to/from iterator") has introduced sanity check for copying from/to iov iterator. Lacking of copy direction from the iterator viewpoint would lead to kernel stack trace like above. This commit fixes this issue by initializing the iov iterator with the correct copy direction when sending SYN or ACK without data.
CVE-2023-52732: In the Linux kernel, the following vulnerability has been resolved: ceph: blocklist the kclient when receiving corrupted snap trace When received corrupted snap trace we don't know what exactly has happened in MDS side. And we shouldn't continue IOs and metadatas access to MDS, which may corrupt or get incorrect contents. This patch will just block all the further IO/MDS requests immediately and then evict the kclient itself. The reason why we still need to evict the kclient just after blocking all the further IOs is that the MDS could revoke the caps faster.
CVE-2023-52761: In the Linux kernel, the following vulnerability has been resolved: riscv: VMAP_STACK overflow detection thread-safe commit 31da94c25aea ("riscv: add VMAP_STACK overflow detection") added support for CONFIG_VMAP_STACK. If overflow is detected, CPU switches to `shadow_stack` temporarily before switching finally to per-cpu `overflow_stack`. If two CPUs/harts are racing and end up in over flowing kernel stack, one or both will end up corrupting each other state because `shadow_stack` is not per-cpu. This patch optimizes per-cpu overflow stack switch by directly picking per-cpu `overflow_stack` and gets rid of `shadow_stack`. Following are the changes in this patch - Defines an asm macro to obtain per-cpu symbols in destination register. - In entry.S, when overflow is detected, per-cpu overflow stack is located using per-cpu asm macro. Computing per-cpu symbol requires a temporary register. x31 is saved away into CSR_SCRATCH (CSR_SCRATCH is anyways zero since we're in kernel). Please see Links for additional relevant disccussion and alternative solution. Tested by `echo EXHAUST_STACK > /sys/kernel/debug/provoke-crash/DIRECT` Kernel crash log below Insufficient stack space to handle exception!/debug/provoke-crash/DIRECT Task stack: [0xff20000010a98000..0xff20000010a9c000] Overflow stack: [0xff600001f7d98370..0xff600001f7d99370] CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) epc : __memset+0x60/0xfc ra : recursive_loop+0x48/0xc6 [lkdtm] epc : ffffffff808de0e4 ra : ffffffff0163a752 sp : ff20000010a97e80 gp : ffffffff815c0330 tp : ff600000820ea280 t0 : ff20000010a97e88 t1 : 000000000000002e t2 : 3233206874706564 s0 : ff20000010a982b0 s1 : 0000000000000012 a0 : ff20000010a97e88 a1 : 0000000000000000 a2 : 0000000000000400 a3 : ff20000010a98288 a4 : 0000000000000000 a5 : 0000000000000000 a6 : fffffffffffe43f0 a7 : 00007fffffffffff s2 : ff20000010a97e88 s3 : ffffffff01644680 s4 : ff20000010a9be90 s5 : ff600000842ba6c0 s6 : 00aaaaaac29e42b0 s7 : 00fffffff0aa3684 s8 : 00aaaaaac2978040 s9 : 0000000000000065 s10: 00ffffff8a7cad10 s11: 00ffffff8a76a4e0 t3 : ffffffff815dbaf4 t4 : ffffffff815dbaf4 t5 : ffffffff815dbab8 t6 : ff20000010a9bb48 status: 0000000200000120 badaddr: ff20000010a97e88 cause: 000000000000000f Kernel panic - not syncing: Kernel stack overflow CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006754>] dump_backtrace+0x30/0x38 [<ffffffff808de798>] show_stack+0x40/0x4c [<ffffffff808ea2a8>] dump_stack_lvl+0x44/0x5c [<ffffffff808ea2d8>] dump_stack+0x18/0x20 [<ffffffff808dec06>] panic+0x126/0x2fe [<ffffffff800065ea>] walk_stackframe+0x0/0xf0 [<ffffffff0163a752>] recursive_loop+0x48/0xc6 [lkdtm] SMP: stopping secondary CPUs ---[ end Kernel panic - not syncing: Kernel stack overflow ]---
CVE-2023-52762: In the Linux kernel, the following vulnerability has been resolved: virtio-blk: fix implicit overflow on virtio_max_dma_size The following codes have an implicit conversion from size_t to u32: (u32)max_size = (size_t)virtio_max_dma_size(vdev); This may lead overflow, Ex (size_t)4G -> (u32)0. Once virtio_max_dma_size() has a larger size than U32_MAX, use U32_MAX instead.
CVE-2023-52763: In the Linux kernel, the following vulnerability has been resolved: i3c: master: mipi-i3c-hci: Fix a kernel panic for accessing DAT_data. The `i3c_master_bus_init` function may attach the I2C devices before the I3C bus initialization. In this flow, the DAT `alloc_entry`` will be used before the DAT `init`. Additionally, if the `i3c_master_bus_init` fails, the DAT `cleanup` will execute before the device is detached, which will execue DAT `free_entry` function. The above scenario can cause the driver to use DAT_data when it is NULL.
CVE-2023-52766: In the Linux kernel, the following vulnerability has been resolved: i3c: mipi-i3c-hci: Fix out of bounds access in hci_dma_irq_handler Do not loop over ring headers in hci_dma_irq_handler() that are not allocated and enabled in hci_dma_init(). Otherwise out of bounds access will occur from rings->headers[i] access when i >= number of allocated ring headers.
CVE-2023-52808: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Set debugfs_dir pointer to NULL after removing debugfs If init debugfs failed during device registration due to memory allocation failure, debugfs_remove_recursive() is called, after which debugfs_dir is not set to NULL. debugfs_remove_recursive() will be called again during device removal. As a result, illegal pointer is accessed. [ 1665.467244] hisi_sas_v3_hw 0000:b4:02.0: failed to init debugfs! ... [ 1669.836708] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0 [ 1669.872669] pc : down_write+0x24/0x70 [ 1669.876315] lr : down_write+0x1c/0x70 [ 1669.879961] sp : ffff000036f53a30 [ 1669.883260] x29: ffff000036f53a30 x28: ffffa027c31549f8 [ 1669.888547] x27: ffffa027c3140000 x26: 0000000000000000 [ 1669.893834] x25: ffffa027bf37c270 x24: ffffa027bf37c270 [ 1669.899122] x23: ffff0000095406b8 x22: ffff0000095406a8 [ 1669.904408] x21: 0000000000000000 x20: ffffa027bf37c310 [ 1669.909695] x19: 00000000000000a0 x18: ffff8027dcd86f10 [ 1669.914982] x17: 0000000000000000 x16: 0000000000000000 [ 1669.920268] x15: 0000000000000000 x14: ffffa0274014f870 [ 1669.925555] x13: 0000000000000040 x12: 0000000000000228 [ 1669.930842] x11: 0000000000000020 x10: 0000000000000bb0 [ 1669.936129] x9 : ffff000036f537f0 x8 : ffff80273088ca10 [ 1669.941416] x7 : 000000000000001d x6 : 00000000ffffffff [ 1669.946702] x5 : ffff000008a36310 x4 : ffff80273088be00 [ 1669.951989] x3 : ffff000009513e90 x2 : 0000000000000000 [ 1669.957276] x1 : 00000000000000a0 x0 : ffffffff00000001 [ 1669.962563] Call trace: [ 1669.965000] down_write+0x24/0x70 [ 1669.968301] debugfs_remove_recursive+0x5c/0x1b0 [ 1669.972905] hisi_sas_debugfs_exit+0x24/0x30 [hisi_sas_main] [ 1669.978541] hisi_sas_v3_remove+0x130/0x150 [hisi_sas_v3_hw] [ 1669.984175] pci_device_remove+0x48/0xd8 [ 1669.988082] device_release_driver_internal+0x1b4/0x250 [ 1669.993282] device_release_driver+0x28/0x38 [ 1669.997534] pci_stop_bus_device+0x84/0xb8 [ 1670.001611] pci_stop_and_remove_bus_device_locked+0x24/0x40 [ 1670.007244] remove_store+0xfc/0x140 [ 1670.010802] dev_attr_store+0x44/0x60 [ 1670.014448] sysfs_kf_write+0x58/0x80 [ 1670.018095] kernfs_fop_write+0xe8/0x1f0 [ 1670.022000] __vfs_write+0x60/0x190 [ 1670.025472] vfs_write+0xac/0x1c0 [ 1670.028771] ksys_write+0x6c/0xd8 [ 1670.032071] __arm64_sys_write+0x24/0x30 [ 1670.035977] el0_svc_common+0x78/0x130 [ 1670.039710] el0_svc_handler+0x38/0x78 [ 1670.043442] el0_svc+0x8/0xc To fix this, set debugfs_dir to NULL after debugfs_remove_recursive().
CVE-2023-52811: In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Remove BUG_ON in the case of an empty event pool In practice the driver should never send more commands than are allocated to a queue's event pool. In the unlikely event that this happens, the code asserts a BUG_ON, and in the case that the kernel is not configured to crash on panic returns a junk event pointer from the empty event list causing things to spiral from there. This BUG_ON is a historical artifact of the ibmvfc driver first being upstreamed, and it is well known now that the use of BUG_ON is bad practice except in the most unrecoverable scenario. There is nothing about this scenario that prevents the driver from recovering and carrying on. Remove the BUG_ON in question from ibmvfc_get_event() and return a NULL pointer in the case of an empty event pool. Update all call sites to ibmvfc_get_event() to check for a NULL pointer and perfrom the appropriate failure or recovery action.
CVE-2023-52815: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/vkms: fix a possible null pointer dereference In amdgpu_vkms_conn_get_modes(), the return value of drm_cvt_mode() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_cvt_mode(). Add a check to avoid null pointer dereference.
CVE-2023-52834: In the Linux kernel, the following vulnerability has been resolved: atl1c: Work around the DMA RX overflow issue This is based on alx driver commit 881d0327db37 ("net: alx: Work around the DMA RX overflow issue"). The alx and atl1c drivers had RX overflow error which was why a custom allocator was created to avoid certain addresses. The simpler workaround then created for alx driver, but not for atl1c due to lack of tester. Instead of using a custom allocator, check the allocated skb address and use skb_reserve() to move away from problematic 0x...fc0 address. Tested on AR8131 on Acer 4540.
CVE-2023-52878: In the Linux kernel, the following vulnerability has been resolved: can: dev: can_put_echo_skb(): don't crash kernel if can_priv::echo_skb is accessed out of bounds If the "struct can_priv::echoo_skb" is accessed out of bounds, this would cause a kernel crash. Instead, issue a meaningful warning message and return with an error.
CVE-2023-52888: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: Only free buffer VA that is not NULL In the MediaTek vcodec driver, while mtk_vcodec_mem_free() is mostly called only when the buffer to free exists, there are some instances that didn't do the check and triggered warnings in practice. We believe those checks were forgotten unintentionally. Add the checks back to fix the warnings.
CVE-2023-52913: In the Linux kernel, the following vulnerability has been resolved: drm/i915: Fix potential context UAFs gem_context_register() makes the context visible to userspace, and which point a separate thread can trigger the I915_GEM_CONTEXT_DESTROY ioctl. So we need to ensure that nothing uses the ctx ptr after this. And we need to ensure that adding the ctx to the xarray is the *last* thing that gem_context_register() does with the ctx pointer. [tursulin: Stable and fixes tags add/tidy.] (cherry picked from commit bed4b455cf5374e68879be56971c1da563bcd90c)
CVE-2023-52916: In the Linux kernel, the following vulnerability has been resolved: media: aspeed: Fix memory overwrite if timing is 1600x900 When capturing 1600x900, system could crash when system memory usage is tight. The way to reproduce this issue: 1. Use 1600x900 to display on host 2. Mount ISO through 'Virtual media' on OpenBMC's web 3. Run script as below on host to do sha continuously #!/bin/bash while [ [1] ]; do find /media -type f -printf '"%h/%f"\n' | xargs sha256sum done 4. Open KVM on OpenBMC's web The size of macro block captured is 8x8. Therefore, we should make sure the height of src-buf is 8 aligned to fix this issue.
CVE-2023-52918: In the Linux kernel, the following vulnerability has been resolved: media: pci: cx23885: check cx23885_vdev_init() return cx23885_vdev_init() can return a NULL pointer, but that pointer is used in the next line without a check. Add a NULL pointer check and go to the error unwind if it is NULL.
CVE-2023-52920: In the Linux kernel, the following vulnerability has been resolved: bpf: support non-r10 register spill/fill to/from stack in precision tracking Use instruction (jump) history to record instructions that performed register spill/fill to/from stack, regardless if this was done through read-only r10 register, or any other register after copying r10 into it *and* potentially adjusting offset. To make this work reliably, we push extra per-instruction flags into instruction history, encoding stack slot index (spi) and stack frame number in extra 10 bit flags we take away from prev_idx in instruction history. We don't touch idx field for maximum performance, as it's checked most frequently during backtracking. This change removes basically the last remaining practical limitation of precision backtracking logic in BPF verifier. It fixes known deficiencies, but also opens up new opportunities to reduce number of verified states, explored in the subsequent patches. There are only three differences in selftests' BPF object files according to veristat, all in the positive direction (less states). File Program Insns (A) Insns (B) Insns (DIFF) States (A) States (B) States (DIFF) -------------------------------------- ------------- --------- --------- ------------- ---------- ---------- ------------- test_cls_redirect_dynptr.bpf.linked3.o cls_redirect 2987 2864 -123 (-4.12%) 240 231 -9 (-3.75%) xdp_synproxy_kern.bpf.linked3.o syncookie_tc 82848 82661 -187 (-0.23%) 5107 5073 -34 (-0.67%) xdp_synproxy_kern.bpf.linked3.o syncookie_xdp 85116 84964 -152 (-0.18%) 5162 5130 -32 (-0.62%) Note, I avoided renaming jmp_history to more generic insn_hist to minimize number of lines changed and potential merge conflicts between bpf and bpf-next trees. Notice also cur_hist_entry pointer reset to NULL at the beginning of instruction verification loop. This pointer avoids the problem of relying on last jump history entry's insn_idx to determine whether we already have entry for current instruction or not. It can happen that we added jump history entry because current instruction is_jmp_point(), but also we need to add instruction flags for stack access. In this case, we don't want to entries, so we need to reuse last added entry, if it is present. Relying on insn_idx comparison has the same ambiguity problem as the one that was fixed recently in [0], so we avoid that. [0] https://patchwork.kernel.org/project/netdevbpf/patch/20231110002638.4168352-3-andrii@kernel.org/
CVE-2023-52926: In the Linux kernel, the following vulnerability has been resolved: IORING_OP_READ did not correctly consume the provided buffer list when read i/o returned < 0 (except for -EAGAIN and -EIOCBQUEUED return). This can lead to a potential use-after-free when the completion via io_rw_done runs at separate context.
CVE-2023-52939: In the Linux kernel, the following vulnerability has been resolved: mm: memcg: fix NULL pointer in mem_cgroup_track_foreign_dirty_slowpath() As commit 18365225f044 ("hwpoison, memcg: forcibly uncharge LRU pages"), hwpoison will forcibly uncharg a LRU hwpoisoned page, the folio_memcg could be NULl, then, mem_cgroup_track_foreign_dirty_slowpath() could occurs a NULL pointer dereference, let's do not record the foreign writebacks for folio memcg is null in mem_cgroup_track_foreign_dirty() to fix it.
CVE-2023-53002: In the Linux kernel, the following vulnerability has been resolved: drm/i915: Fix a memory leak with reused mmap_offset drm_vma_node_allow() and drm_vma_node_revoke() should be called in balanced pairs. We call drm_vma_node_allow() once per-file everytime a user calls mmap_offset, but only call drm_vma_node_revoke once per-file on each mmap_offset. As the mmap_offset is reused by the client, the per-file vm_count may remain non-zero and the rbtree leaked. Call drm_vma_node_allow_once() instead to prevent that memory leak.
CVE-2023-53008: In the Linux kernel, the following vulnerability has been resolved: cifs: fix potential memory leaks in session setup Make sure to free cifs_ses::auth_key.response before allocating it as we might end up leaking memory in reconnect or mounting.
CVE-2023-53010: In the Linux kernel, the following vulnerability has been resolved: bnxt: Do not read past the end of test names Test names were being concatenated based on a offset beyond the end of the first name, which tripped the buffer overflow detection logic: detected buffer overflow in strnlen [...] Call Trace: bnxt_ethtool_init.cold+0x18/0x18 Refactor struct hwrm_selftest_qlist_output to use an actual array, and adjust the concatenation to use snprintf() rather than a series of strncat() calls.
CVE-2023-53039: In the Linux kernel, the following vulnerability has been resolved: HID: intel-ish-hid: ipc: Fix potential use-after-free in work function When a reset notify IPC message is received, the ISR schedules a work function and passes the ISHTP device to it via a global pointer ishtp_dev. If ish_probe() fails, the devm-managed device resources including ishtp_dev are freed, but the work is not cancelled, causing a use-after-free when the work function tries to access ishtp_dev. Use devm_work_autocancel() instead, so that the work is automatically cancelled if probe fails.
CVE-2023-53042: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not set DRR on pipe Commit [WHY] Writing to DRR registers such as OTG_V_TOTAL_MIN on the same frame as a pipe commit can cause underflow.
CVE-2023-53055: In the Linux kernel, the following vulnerability has been resolved: fscrypt: destroy keyring after security_sb_delete() fscrypt_destroy_keyring() must be called after all potentially-encrypted inodes were evicted; otherwise it cannot safely destroy the keyring. Since inodes that are in-use by the Landlock LSM don't get evicted until security_sb_delete(), this means that fscrypt_destroy_keyring() must be called *after* security_sb_delete(). This fixes a WARN_ON followed by a NULL dereference, only possible if Landlock was being used on encrypted files.
CVE-2023-53068: In the Linux kernel, the following vulnerability has been resolved: net: usb: lan78xx: Limit packet length to skb->len Packet length retrieved from descriptor may be larger than the actual socket buffer length. In such case the cloned skb passed up the network stack will leak kernel memory contents. Additionally prevent integer underflow when size is less than ETH_FCS_LEN.
CVE-2023-53072: In the Linux kernel, the following vulnerability has been resolved: mptcp: use the workqueue to destroy unaccepted sockets Christoph reported a UaF at token lookup time after having refactored the passive socket initialization part: BUG: KASAN: use-after-free in __token_bucket_busy+0x253/0x260 Read of size 4 at addr ffff88810698d5b0 by task syz-executor653/3198 CPU: 1 PID: 3198 Comm: syz-executor653 Not tainted 6.2.0-rc59af4eaa31c1f6c00c8f1e448ed99a45c66340dd5 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x6e/0x91 print_report+0x16a/0x46f kasan_report+0xad/0x130 __token_bucket_busy+0x253/0x260 mptcp_token_new_connect+0x13d/0x490 mptcp_connect+0x4ed/0x860 __inet_stream_connect+0x80e/0xd90 tcp_sendmsg_fastopen+0x3ce/0x710 mptcp_sendmsg+0xff1/0x1a20 inet_sendmsg+0x11d/0x140 __sys_sendto+0x405/0x490 __x64_sys_sendto+0xdc/0x1b0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc We need to properly clean-up all the paired MPTCP-level resources and be sure to release the msk last, even when the unaccepted subflow is destroyed by the TCP internals via inet_child_forget(). We can re-use the existing MPTCP_WORK_CLOSE_SUBFLOW infra, explicitly checking that for the critical scenario: the closed subflow is the MPC one, the msk is not accepted and eventually going through full cleanup. With such change, __mptcp_destroy_sock() is always called on msk sockets, even on accepted ones. We don't need anymore to transiently drop one sk reference at msk clone time. Please note this commit depends on the parent one: mptcp: refactor passive socket initialization
CVE-2023-53074: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix ttm_bo calltrace warning in psp_hw_fini The call trace occurs when the amdgpu is removed after the mode1 reset. During mode1 reset, from suspend to resume, there is no need to reinitialize the ta firmware buffer which caused the bo pin_count increase redundantly. [ 489.885525] Call Trace: [ 489.885525] <TASK> [ 489.885526] amdttm_bo_put+0x34/0x50 [amdttm] [ 489.885529] amdgpu_bo_free_kernel+0xe8/0x130 [amdgpu] [ 489.885620] psp_free_shared_bufs+0xb7/0x150 [amdgpu] [ 489.885720] psp_hw_fini+0xce/0x170 [amdgpu] [ 489.885815] amdgpu_device_fini_hw+0x2ff/0x413 [amdgpu] [ 489.885960] ? blocking_notifier_chain_unregister+0x56/0xb0 [ 489.885962] amdgpu_driver_unload_kms+0x51/0x60 [amdgpu] [ 489.886049] amdgpu_pci_remove+0x5a/0x140 [amdgpu] [ 489.886132] ? __pm_runtime_resume+0x60/0x90 [ 489.886134] pci_device_remove+0x3e/0xb0 [ 489.886135] __device_release_driver+0x1ab/0x2a0 [ 489.886137] driver_detach+0xf3/0x140 [ 489.886138] bus_remove_driver+0x6c/0xf0 [ 489.886140] driver_unregister+0x31/0x60 [ 489.886141] pci_unregister_driver+0x40/0x90 [ 489.886142] amdgpu_exit+0x15/0x451 [amdgpu]
CVE-2023-53091: In the Linux kernel, the following vulnerability has been resolved: ext4: update s_journal_inum if it changes after journal replay When mounting a crafted ext4 image, s_journal_inum may change after journal replay, which is obviously unreasonable because we have successfully loaded and replayed the journal through the old s_journal_inum. And the new s_journal_inum bypasses some of the checks in ext4_get_journal(), which may trigger a null pointer dereference problem. So if s_journal_inum changes after the journal replay, we ignore the change, and rewrite the current journal_inum to the superblock.
CVE-2023-53093: In the Linux kernel, the following vulnerability has been resolved: tracing: Do not let histogram values have some modifiers Histogram values can not be strings, stacktraces, graphs, symbols, syscalls, or grouped in buckets or log. Give an error if a value is set to do so. Note, the histogram code was not prepared to handle these modifiers for histograms and caused a bug. Mark Rutland reported: # echo 'p:copy_to_user __arch_copy_to_user n=$arg2' >> /sys/kernel/tracing/kprobe_events # echo 'hist:keys=n:vals=hitcount.buckets=8:sort=hitcount' > /sys/kernel/tracing/events/kprobes/copy_to_user/trigger # cat /sys/kernel/tracing/events/kprobes/copy_to_user/hist [ 143.694628] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 143.695190] Mem abort info: [ 143.695362] ESR = 0x0000000096000004 [ 143.695604] EC = 0x25: DABT (current EL), IL = 32 bits [ 143.695889] SET = 0, FnV = 0 [ 143.696077] EA = 0, S1PTW = 0 [ 143.696302] FSC = 0x04: level 0 translation fault [ 143.702381] Data abort info: [ 143.702614] ISV = 0, ISS = 0x00000004 [ 143.702832] CM = 0, WnR = 0 [ 143.703087] user pgtable: 4k pages, 48-bit VAs, pgdp=00000000448f9000 [ 143.703407] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 [ 143.704137] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 143.704714] Modules linked in: [ 143.705273] CPU: 0 PID: 133 Comm: cat Not tainted 6.2.0-00003-g6fc512c10a7c #3 [ 143.706138] Hardware name: linux,dummy-virt (DT) [ 143.706723] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 143.707120] pc : hist_field_name.part.0+0x14/0x140 [ 143.707504] lr : hist_field_name.part.0+0x104/0x140 [ 143.707774] sp : ffff800008333a30 [ 143.707952] x29: ffff800008333a30 x28: 0000000000000001 x27: 0000000000400cc0 [ 143.708429] x26: ffffd7a653b20260 x25: 0000000000000000 x24: ffff10d303ee5800 [ 143.708776] x23: ffffd7a6539b27b0 x22: ffff10d303fb8c00 x21: 0000000000000001 [ 143.709127] x20: ffff10d303ec2000 x19: 0000000000000000 x18: 0000000000000000 [ 143.709478] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 [ 143.709824] x14: 0000000000000000 x13: 203a6f666e692072 x12: 6567676972742023 [ 143.710179] x11: 0a230a6d6172676f x10: 000000000000002c x9 : ffffd7a6521e018c [ 143.710584] x8 : 000000000000002c x7 : 7f7f7f7f7f7f7f7f x6 : 000000000000002c [ 143.710915] x5 : ffff10d303b0103e x4 : ffffd7a653b20261 x3 : 000000000000003d [ 143.711239] x2 : 0000000000020001 x1 : 0000000000000001 x0 : 0000000000000000 [ 143.711746] Call trace: [ 143.712115] hist_field_name.part.0+0x14/0x140 [ 143.712642] hist_field_name.part.0+0x104/0x140 [ 143.712925] hist_field_print+0x28/0x140 [ 143.713125] event_hist_trigger_print+0x174/0x4d0 [ 143.713348] hist_show+0xf8/0x980 [ 143.713521] seq_read_iter+0x1bc/0x4b0 [ 143.713711] seq_read+0x8c/0xc4 [ 143.713876] vfs_read+0xc8/0x2a4 [ 143.714043] ksys_read+0x70/0xfc [ 143.714218] __arm64_sys_read+0x24/0x30 [ 143.714400] invoke_syscall+0x50/0x120 [ 143.714587] el0_svc_common.constprop.0+0x4c/0x100 [ 143.714807] do_el0_svc+0x44/0xd0 [ 143.714970] el0_svc+0x2c/0x84 [ 143.715134] el0t_64_sync_handler+0xbc/0x140 [ 143.715334] el0t_64_sync+0x190/0x194 [ 143.715742] Code: a9bd7bfd 910003fd a90153f3 aa0003f3 (f9400000) [ 143.716510] ---[ end trace 0000000000000000 ]--- Segmentation fault
CVE-2023-53103: In the Linux kernel, the following vulnerability has been resolved: bonding: restore bond's IFF_SLAVE flag if a non-eth dev enslave fails syzbot reported a warning[1] where the bond device itself is a slave and we try to enslave a non-ethernet device as the first slave which fails but then in the error path when ether_setup() restores the bond device it also clears all flags. In my previous fix[2] I restored the IFF_MASTER flag, but I didn't consider the case that the bond device itself might also be a slave with IFF_SLAVE set, so we need to restore that flag as well. Use the bond_ether_setup helper which does the right thing and restores the bond's flags properly. Steps to reproduce using a nlmon dev: $ ip l add nlmon0 type nlmon $ ip l add bond1 type bond $ ip l add bond2 type bond $ ip l set bond1 master bond2 $ ip l set dev nlmon0 master bond1 $ ip -d l sh dev bond1 22: bond1: <BROADCAST,MULTICAST,MASTER> mtu 1500 qdisc noqueue master bond2 state DOWN mode DEFAULT group default qlen 1000 (now bond1's IFF_SLAVE flag is gone and we'll hit a warning[3] if we try to delete it) [1] https://syzkaller.appspot.com/bug?id=391c7b1f6522182899efba27d891f1743e8eb3ef [2] commit 7d5cd2ce5292 ("bonding: correctly handle bonding type change on enslave failure") [3] example warning: [ 27.008664] bond1: (slave nlmon0): The slave device specified does not support setting the MAC address [ 27.008692] bond1: (slave nlmon0): Error -95 calling set_mac_address [ 32.464639] bond1 (unregistering): Released all slaves [ 32.464685] ------------[ cut here ]------------ [ 32.464686] WARNING: CPU: 1 PID: 2004 at net/core/dev.c:10829 unregister_netdevice_many+0x72a/0x780 [ 32.464694] Modules linked in: br_netfilter bridge bonding virtio_net [ 32.464699] CPU: 1 PID: 2004 Comm: ip Kdump: loaded Not tainted 5.18.0-rc3+ #47 [ 32.464703] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.1-2.fc37 04/01/2014 [ 32.464704] RIP: 0010:unregister_netdevice_many+0x72a/0x780 [ 32.464707] Code: 99 fd ff ff ba 90 1a 00 00 48 c7 c6 f4 02 66 96 48 c7 c7 20 4d 35 96 c6 05 fa c7 2b 02 01 e8 be 6f 4a 00 0f 0b e9 73 fd ff ff <0f> 0b e9 5f fd ff ff 80 3d e3 c7 2b 02 00 0f 85 3b fd ff ff ba 59 [ 32.464710] RSP: 0018:ffffa006422d7820 EFLAGS: 00010206 [ 32.464712] RAX: ffff8f6e077140a0 RBX: ffffa006422d7888 RCX: 0000000000000000 [ 32.464714] RDX: ffff8f6e12edbe58 RSI: 0000000000000296 RDI: ffffffff96d4a520 [ 32.464716] RBP: ffff8f6e07714000 R08: ffffffff96d63600 R09: ffffa006422d7728 [ 32.464717] R10: 0000000000000ec0 R11: ffffffff9698c988 R12: ffff8f6e12edb140 [ 32.464719] R13: dead000000000122 R14: dead000000000100 R15: ffff8f6e12edb140 [ 32.464723] FS: 00007f297c2f1740(0000) GS:ffff8f6e5d900000(0000) knlGS:0000000000000000 [ 32.464725] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 32.464726] CR2: 00007f297bf1c800 CR3: 00000000115e8000 CR4: 0000000000350ee0 [ 32.464730] Call Trace: [ 32.464763] <TASK> [ 32.464767] rtnl_dellink+0x13e/0x380 [ 32.464776] ? cred_has_capability.isra.0+0x68/0x100 [ 32.464780] ? __rtnl_unlock+0x33/0x60 [ 32.464783] ? bpf_lsm_capset+0x10/0x10 [ 32.464786] ? security_capable+0x36/0x50 [ 32.464790] rtnetlink_rcv_msg+0x14e/0x3b0 [ 32.464792] ? _copy_to_iter+0xb1/0x790 [ 32.464796] ? post_alloc_hook+0xa0/0x160 [ 32.464799] ? rtnl_calcit.isra.0+0x110/0x110 [ 32.464802] netlink_rcv_skb+0x50/0xf0 [ 32.464806] netlink_unicast+0x216/0x340 [ 32.464809] netlink_sendmsg+0x23f/0x480 [ 32.464812] sock_sendmsg+0x5e/0x60 [ 32.464815] ____sys_sendmsg+0x22c/0x270 [ 32.464818] ? import_iovec+0x17/0x20 [ 32.464821] ? sendmsg_copy_msghdr+0x59/0x90 [ 32.464823] ? do_set_pte+0xa0/0xe0 [ 32.464828] ___sys_sendmsg+0x81/0xc0 [ 32.464832] ? mod_objcg_state+0xc6/0x300 [ 32.464835] ? refill_obj_stock+0xa9/0x160 [ 32.464838] ? memcg_slab_free_hook+0x1a5/0x1f0 [ 32.464842] __sys_sendm ---truncated---
CVE-2023-53105: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix cleanup null-ptr deref on encap lock During module is unloaded while a peer tc flow is still offloaded, first the peer uplink rep profile is changed to a nic profile, and so neigh encap lock is destroyed. Next during unload, the VF reps netdevs are unregistered which causes the original non-peer tc flow to be deleted, which deletes the peer flow. The peer flow deletion detaches the encap entry and try to take the already destroyed encap lock, causing the below trace. Fix this by clearing peer flows during tc eswitch cleanup (mlx5e_tc_esw_cleanup()). Relevant trace: [ 4316.837128] BUG: kernel NULL pointer dereference, address: 00000000000001d8 [ 4316.842239] RIP: 0010:__mutex_lock+0xb5/0xc40 [ 4316.851897] Call Trace: [ 4316.852481] <TASK> [ 4316.857214] mlx5e_rep_neigh_entry_release+0x93/0x790 [mlx5_core] [ 4316.858258] mlx5e_rep_encap_entry_detach+0xa7/0xf0 [mlx5_core] [ 4316.859134] mlx5e_encap_dealloc+0xa3/0xf0 [mlx5_core] [ 4316.859867] clean_encap_dests.part.0+0x5c/0xe0 [mlx5_core] [ 4316.860605] mlx5e_tc_del_fdb_flow+0x32a/0x810 [mlx5_core] [ 4316.862609] __mlx5e_tc_del_fdb_peer_flow+0x1a2/0x250 [mlx5_core] [ 4316.863394] mlx5e_tc_del_flow+0x(/0x630 [mlx5_core] [ 4316.864090] mlx5e_flow_put+0x5f/0x100 [mlx5_core] [ 4316.864771] mlx5e_delete_flower+0x4de/0xa40 [mlx5_core] [ 4316.865486] tc_setup_cb_reoffload+0x20/0x80 [ 4316.865905] fl_reoffload+0x47c/0x510 [cls_flower] [ 4316.869181] tcf_block_playback_offloads+0x91/0x1d0 [ 4316.869649] tcf_block_unbind+0xe7/0x1b0 [ 4316.870049] tcf_block_offload_cmd.isra.0+0x1ee/0x270 [ 4316.879266] tcf_block_offload_unbind+0x61/0xa0 [ 4316.879711] __tcf_block_put+0xa4/0x310
CVE-2023-53111: In the Linux kernel, the following vulnerability has been resolved: loop: Fix use-after-free issues do_req_filebacked() calls blk_mq_complete_request() synchronously or asynchronously when using asynchronous I/O unless memory allocation fails. Hence, modify loop_handle_cmd() such that it does not dereference 'cmd' nor 'rq' after do_req_filebacked() finished unless we are sure that the request has not yet been completed. This patch fixes the following kernel crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000054 Call trace: css_put.42938+0x1c/0x1ac loop_process_work+0xc8c/0xfd4 loop_rootcg_workfn+0x24/0x34 process_one_work+0x244/0x558 worker_thread+0x400/0x8fc kthread+0x16c/0x1e0 ret_from_fork+0x10/0x20
CVE-2023-53133: In the Linux kernel, the following vulnerability has been resolved: bpf, sockmap: Fix an infinite loop error when len is 0 in tcp_bpf_recvmsg_parser() When the buffer length of the recvmsg system call is 0, we got the flollowing soft lockup problem: watchdog: BUG: soft lockup - CPU#3 stuck for 27s! [a.out:6149] CPU: 3 PID: 6149 Comm: a.out Kdump: loaded Not tainted 6.2.0+ #30 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:remove_wait_queue+0xb/0xc0 Code: 5e 41 5f c3 cc cc cc cc 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 57 <41> 56 41 55 41 54 55 48 89 fd 53 48 89 f3 4c 8d 6b 18 4c 8d 73 20 RSP: 0018:ffff88811b5978b8 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff88811a7d3780 RCX: ffffffffb7a4d768 RDX: dffffc0000000000 RSI: ffff88811b597908 RDI: ffff888115408040 RBP: 1ffff110236b2f1b R08: 0000000000000000 R09: ffff88811a7d37e7 R10: ffffed10234fa6fc R11: 0000000000000001 R12: ffff88811179b800 R13: 0000000000000001 R14: ffff88811a7d38a8 R15: ffff88811a7d37e0 FS: 00007f6fb5398740(0000) GS:ffff888237180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000010b6ba002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_msg_wait_data+0x279/0x2f0 tcp_bpf_recvmsg_parser+0x3c6/0x490 inet_recvmsg+0x280/0x290 sock_recvmsg+0xfc/0x120 ____sys_recvmsg+0x160/0x3d0 ___sys_recvmsg+0xf0/0x180 __sys_recvmsg+0xea/0x1a0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The logic in tcp_bpf_recvmsg_parser is as follows: msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { wait data; goto msg_bytes_ready; } In this case, "copied" always is 0, the infinite loop occurs. According to the Linux system call man page, 0 should be returned in this case. Therefore, in tcp_bpf_recvmsg_parser(), if the length is 0, directly return. Also modify several other functions with the same problem.
CVE-2023-53149: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid deadlock in fs reclaim with page writeback Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock.
CVE-2023-53152: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix calltrace warning in amddrm_buddy_fini The following call trace is observed when removing the amdgpu driver, which is caused by that BOs allocated for psp are not freed until removing. [61811.450562] RIP: 0010:amddrm_buddy_fini.cold+0x29/0x47 [amddrm_buddy] [61811.450577] Call Trace: [61811.450577] <TASK> [61811.450579] amdgpu_vram_mgr_fini+0x135/0x1c0 [amdgpu] [61811.450728] amdgpu_ttm_fini+0x207/0x290 [amdgpu] [61811.450870] amdgpu_bo_fini+0x27/0xa0 [amdgpu] [61811.451012] gmc_v9_0_sw_fini+0x4a/0x60 [amdgpu] [61811.451166] amdgpu_device_fini_sw+0x117/0x520 [amdgpu] [61811.451306] amdgpu_driver_release_kms+0x16/0x30 [amdgpu] [61811.451447] devm_drm_dev_init_release+0x4d/0x80 [drm] [61811.451466] devm_action_release+0x15/0x20 [61811.451469] release_nodes+0x40/0xb0 [61811.451471] devres_release_all+0x9b/0xd0 [61811.451473] __device_release_driver+0x1bb/0x2a0 [61811.451476] driver_detach+0xf3/0x140 [61811.451479] bus_remove_driver+0x6c/0xf0 [61811.451481] driver_unregister+0x31/0x60 [61811.451483] pci_unregister_driver+0x40/0x90 [61811.451486] amdgpu_exit+0x15/0x447 [amdgpu] For smu v13_0_2, if the GPU supports xgmi, refer to commit f5c7e7797060 ("drm/amdgpu: Adjust removal control flow for smu v13_0_2"), it will run gpu recover in AMDGPU_RESET_FOR_DEVICE_REMOVE mode when removing, which makes all devices in hive list have hw reset but no resume except the basic ip blocks, then other ip blocks will not call .hw_fini according to ip_block.status.hw. Since psp_free_shared_bufs just includes some software operations, so move it to psp_sw_fini.
CVE-2023-53178: In the Linux kernel, the following vulnerability has been resolved: mm: fix zswap writeback race condition The zswap writeback mechanism can cause a race condition resulting in memory corruption, where a swapped out page gets swapped in with data that was written to a different page. The race unfolds like this: 1. a page with data A and swap offset X is stored in zswap 2. page A is removed off the LRU by zpool driver for writeback in zswap-shrink work, data for A is mapped by zpool driver 3. user space program faults and invalidates page entry A, offset X is considered free 4. kswapd stores page B at offset X in zswap (zswap could also be full, if so, page B would then be IOed to X, then skip step 5.) 5. entry A is replaced by B in tree->rbroot, this doesn't affect the local reference held by zswap-shrink work 6. zswap-shrink work writes back A at X, and frees zswap entry A 7. swapin of slot X brings A in memory instead of B The fix: Once the swap page cache has been allocated (case ZSWAP_SWAPCACHE_NEW), zswap-shrink work just checks that the local zswap_entry reference is still the same as the one in the tree. If it's not the same it means that it's either been invalidated or replaced, in both cases the writeback is aborted because the local entry contains stale data. Reproducer: I originally found this by running `stress` overnight to validate my work on the zswap writeback mechanism, it manifested after hours on my test machine. The key to make it happen is having zswap writebacks, so whatever setup pumps /sys/kernel/debug/zswap/written_back_pages should do the trick. In order to reproduce this faster on a vm, I setup a system with ~100M of available memory and a 500M swap file, then running `stress --vm 1 --vm-bytes 300000000 --vm-stride 4000` makes it happen in matter of tens of minutes. One can speed things up even more by swinging /sys/module/zswap/parameters/max_pool_percent up and down between, say, 20 and 1; this makes it reproduce in tens of seconds. It's crucial to set `--vm-stride` to something other than 4096 otherwise `stress` won't realize that memory has been corrupted because all pages would have the same data.
CVE-2023-53200: In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: fix percpu counter block leak on error path when creating new netns Here is the stack where we allocate percpu counter block: +-< __alloc_percpu +-< xt_percpu_counter_alloc +-< find_check_entry # {arp,ip,ip6}_tables.c +-< translate_table And it can be leaked on this code path: +-> ip6t_register_table +-> translate_table # allocates percpu counter block +-> xt_register_table # fails there is no freeing of the counter block on xt_register_table fail. Note: xt_percpu_counter_free should be called to free it like we do in do_replace through cleanup_entry helper (or in __ip6t_unregister_table). Probability of hitting this error path is low AFAICS (xt_register_table can only return ENOMEM here, as it is not replacing anything, as we are creating new netns, and it is hard to imagine that all previous allocations succeeded and after that one in xt_register_table failed). But it's worth fixing even the rare leak.
CVE-2023-53218: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Make it so that a waiting process can be aborted When sendmsg() creates an rxrpc call, it queues it to wait for a connection and channel to be assigned and then waits before it can start shovelling data as the encrypted DATA packet content includes a summary of the connection parameters. However, sendmsg() may get interrupted before a connection gets assigned and further sendmsg() calls will fail with EBUSY until an assignment is made. Fix this so that the call can at least be aborted without failing on EBUSY. We have to be careful here as sendmsg() mustn't be allowed to start the call timer if the call doesn't yet have a connection assigned as an oops may follow shortly thereafter.
CVE-2023-53221: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix memleak due to fentry attach failure If it fails to attach fentry, the allocated bpf trampoline image will be left in the system. That can be verified by checking /proc/kallsyms. This meamleak can be verified by a simple bpf program as follows: SEC("fentry/trap_init") int fentry_run() { return 0; } It will fail to attach trap_init because this function is freed after kernel init, and then we can find the trampoline image is left in the system by checking /proc/kallsyms. $ tail /proc/kallsyms ffffffffc0613000 t bpf_trampoline_6442453466_1 [bpf] ffffffffc06c3000 t bpf_trampoline_6442453466_1 [bpf] $ bpftool btf dump file /sys/kernel/btf/vmlinux | grep "FUNC 'trap_init'" [2522] FUNC 'trap_init' type_id=119 linkage=static $ echo $((6442453466 & 0x7fffffff)) 2522 Note that there are two left bpf trampoline images, that is because the libbpf will fallback to raw tracepoint if -EINVAL is returned.
CVE-2023-53231: In the Linux kernel, the following vulnerability has been resolved: erofs: Fix detection of atomic context Current check for atomic context is not sufficient as z_erofs_decompressqueue_endio can be called under rcu lock from blk_mq_flush_plug_list(). See the stacktrace [1] In such case we should hand off the decompression work for async processing rather than trying to do sync decompression in current context. Patch fixes the detection by checking for rcu_read_lock_any_held() and while at it use more appropriate !in_task() check than in_atomic(). Background: Historically erofs would always schedule a kworker for decompression which would incur the scheduling cost regardless of the context. But z_erofs_decompressqueue_endio() may not always be in atomic context and we could actually benefit from doing the decompression in z_erofs_decompressqueue_endio() if we are in thread context, for example when running with dm-verity. This optimization was later added in patch [2] which has shown improvement in performance benchmarks. ============================================== [1] Problem stacktrace [name:core&]BUG: sleeping function called from invalid context at kernel/locking/mutex.c:291 [name:core&]in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1615, name: CpuMonitorServi [name:core&]preempt_count: 0, expected: 0 [name:core&]RCU nest depth: 1, expected: 0 CPU: 7 PID: 1615 Comm: CpuMonitorServi Tainted: G S W OE 6.1.25-android14-5-maybe-dirty-mainline #1 Hardware name: MT6897 (DT) Call trace: dump_backtrace+0x108/0x15c show_stack+0x20/0x30 dump_stack_lvl+0x6c/0x8c dump_stack+0x20/0x48 __might_resched+0x1fc/0x308 __might_sleep+0x50/0x88 mutex_lock+0x2c/0x110 z_erofs_decompress_queue+0x11c/0xc10 z_erofs_decompress_kickoff+0x110/0x1a4 z_erofs_decompressqueue_endio+0x154/0x180 bio_endio+0x1b0/0x1d8 __dm_io_complete+0x22c/0x280 clone_endio+0xe4/0x280 bio_endio+0x1b0/0x1d8 blk_update_request+0x138/0x3a4 blk_mq_plug_issue_direct+0xd4/0x19c blk_mq_flush_plug_list+0x2b0/0x354 __blk_flush_plug+0x110/0x160 blk_finish_plug+0x30/0x4c read_pages+0x2fc/0x370 page_cache_ra_unbounded+0xa4/0x23c page_cache_ra_order+0x290/0x320 do_sync_mmap_readahead+0x108/0x2c0 filemap_fault+0x19c/0x52c __do_fault+0xc4/0x114 handle_mm_fault+0x5b4/0x1168 do_page_fault+0x338/0x4b4 do_translation_fault+0x40/0x60 do_mem_abort+0x60/0xc8 el0_da+0x4c/0xe0 el0t_64_sync_handler+0xd4/0xfc el0t_64_sync+0x1a0/0x1a4 [2] Link: https://lore.kernel.org/all/20210317035448.13921-1-huangjianan@oppo.com/
CVE-2023-53244: In the Linux kernel, the following vulnerability has been resolved: media: pci: tw68: Fix null-ptr-deref bug in buf prepare and finish When the driver calls tw68_risc_buffer() to prepare the buffer, the function call dma_alloc_coherent may fail, resulting in a empty buffer buf->cpu. Later when we free the buffer or access the buffer, null ptr deref is triggered. This bug is similar to the following one: https://git.linuxtv.org/media_stage.git/commit/?id=2b064d91440b33fba5b452f2d1b31f13ae911d71. We believe the bug can be also dynamically triggered from user side. Similarly, we fix this by checking the return value of tw68_risc_buffer() and the value of buf->cpu before buffer free.
CVE-2023-53248: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: install stub fence into potential unused fence pointers When using cpu to update page tables, vm update fences are unused. Install stub fence into these fence pointers instead of NULL to avoid NULL dereference when calling dma_fence_wait() on them.
CVE-2023-53250: In the Linux kernel, the following vulnerability has been resolved: firmware: dmi-sysfs: Fix null-ptr-deref in dmi_sysfs_register_handle KASAN reported a null-ptr-deref error: KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 0 PID: 1373 Comm: modprobe Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:dmi_sysfs_entry_release ... Call Trace: <TASK> kobject_put dmi_sysfs_register_handle (drivers/firmware/dmi-sysfs.c:540) dmi_sysfs dmi_decode_table (drivers/firmware/dmi_scan.c:133) dmi_walk (drivers/firmware/dmi_scan.c:1115) dmi_sysfs_init (drivers/firmware/dmi-sysfs.c:149) dmi_sysfs do_one_initcall (init/main.c:1296) ... Kernel panic - not syncing: Fatal exception Kernel Offset: 0x4000000 from 0xffffffff81000000 ---[ end Kernel panic - not syncing: Fatal exception ]--- It is because previous patch added kobject_put() to release the memory which will call dmi_sysfs_entry_release() and list_del(). However, list_add_tail(entry->list) is called after the error block, so the list_head is uninitialized and cannot be deleted. Move error handling to after list_add_tail to fix this.
CVE-2023-53254: In the Linux kernel, the following vulnerability has been resolved: cacheinfo: Fix shared_cpu_map to handle shared caches at different levels The cacheinfo sets up the shared_cpu_map by checking whether the caches with the same index are shared between CPUs. However, this will trigger slab-out-of-bounds access if the CPUs do not have the same cache hierarchy. Another problem is the mismatched shared_cpu_map when the shared cache does not have the same index between CPUs. CPU0 I D L3 index 0 1 2 x ^ ^ ^ ^ index 0 1 2 3 CPU1 I D L2 L3 This patch checks each cache is shared with all caches on other CPUs.
CVE-2023-53261: In the Linux kernel, the following vulnerability has been resolved: coresight: Fix memory leak in acpi_buffer->pointer There are memory leaks reported by kmemleak: ... unreferenced object 0xffff00213c141000 (size 1024): comm "systemd-udevd", pid 2123, jiffies 4294909467 (age 6062.160s) hex dump (first 32 bytes): 04 00 00 00 02 00 00 00 18 10 14 3c 21 00 ff ff ...........<!... 00 00 00 00 00 00 00 00 03 00 00 00 10 00 00 00 ................ backtrace: [<000000004b7c9001>] __kmem_cache_alloc_node+0x2f8/0x348 [<00000000b0fc7ceb>] __kmalloc+0x58/0x108 [<0000000064ff4695>] acpi_os_allocate+0x2c/0x68 [<000000007d57d116>] acpi_ut_initialize_buffer+0x54/0xe0 [<0000000024583908>] acpi_evaluate_object+0x388/0x438 [<0000000017b2e72b>] acpi_evaluate_object_typed+0xe8/0x240 [<000000005df0eac2>] coresight_get_platform_data+0x1b4/0x988 [coresight] ... The ACPI buffer memory (buf.pointer) should be freed. But the buffer is also used after returning from acpi_get_dsd_graph(). Move the temporary variables buf to acpi_coresight_parse_graph(), and free it before the function return to prevent memory leak.
CVE-2023-53270: In the Linux kernel, the following vulnerability has been resolved: ext4: fix i_disksize exceeding i_size problem in paritally written case It is possible for i_disksize can exceed i_size, triggering a warning. generic_perform_write copied = iov_iter_copy_from_user_atomic(len) // copied < len ext4_da_write_end | ext4_update_i_disksize | new_i_size = pos + copied; | WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize) // update i_disksize | generic_write_end | copied = block_write_end(copied, len) // copied = 0 | if (unlikely(copied < len)) | if (!PageUptodate(page)) | copied = 0; | if (pos + copied > inode->i_size) // return false if (unlikely(copied == 0)) goto again; if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } We get i_disksize greater than i_size here, which could trigger WARNING check 'i_size_read(inode) < EXT4_I(inode)->i_disksize' while doing dio: ext4_dio_write_iter iomap_dio_rw __iomap_dio_rw // return err, length is not aligned to 512 ext4_handle_inode_extension WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize) // Oops WARNING: CPU: 2 PID: 2609 at fs/ext4/file.c:319 CPU: 2 PID: 2609 Comm: aa Not tainted 6.3.0-rc2 RIP: 0010:ext4_file_write_iter+0xbc7 Call Trace: vfs_write+0x3b1 ksys_write+0x77 do_syscall_64+0x39 Fix it by updating 'copied' value before updating i_disksize just like ext4_write_inline_data_end() does. A reproducer can be found in the buganizer link below.
CVE-2023-53282: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Fix use-after-free KFENCE violation during sysfs firmware write During the sysfs firmware write process, a use-after-free read warning is logged from the lpfc_wr_object() routine: BUG: KFENCE: use-after-free read in lpfc_wr_object+0x235/0x310 [lpfc] Use-after-free read at 0x0000000000cf164d (in kfence-#111): lpfc_wr_object+0x235/0x310 [lpfc] lpfc_write_firmware.cold+0x206/0x30d [lpfc] lpfc_sli4_request_firmware_update+0xa6/0x100 [lpfc] lpfc_request_firmware_upgrade_store+0x66/0xb0 [lpfc] kernfs_fop_write_iter+0x121/0x1b0 new_sync_write+0x11c/0x1b0 vfs_write+0x1ef/0x280 ksys_write+0x5f/0xe0 do_syscall_64+0x59/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd The driver accessed wr_object pointer data, which was initialized into mailbox payload memory, after the mailbox object was released back to the mailbox pool. Fix by moving the mailbox free calls to the end of the routine ensuring that we don't reference internal mailbox memory after release.
CVE-2023-53287: In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: Put the cdns set active part outside the spin lock The device may be scheduled during the resume process, so this cannot appear in atomic operations. Since pm_runtime_set_active will resume suppliers, put set active outside the spin lock, which is only used to protect the struct cdns data structure, otherwise the kernel will report the following warning: BUG: sleeping function called from invalid context at drivers/base/power/runtime.c:1163 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 651, name: sh preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 CPU: 0 PID: 651 Comm: sh Tainted: G WC 6.1.20 #1 Hardware name: Freescale i.MX8QM MEK (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x30 dump_stack_lvl+0x64/0x80 dump_stack+0x1c/0x38 __might_resched+0x1fc/0x240 __might_sleep+0x68/0xc0 __pm_runtime_resume+0x9c/0xe0 rpm_get_suppliers+0x68/0x1b0 __pm_runtime_set_status+0x298/0x560 cdns_resume+0xb0/0x1c0 cdns3_controller_resume.isra.0+0x1e0/0x250 cdns3_plat_resume+0x28/0x40
CVE-2023-53332: In the Linux kernel, the following vulnerability has been resolved: genirq/ipi: Fix NULL pointer deref in irq_data_get_affinity_mask() If ipi_send_{mask|single}() is called with an invalid interrupt number, all the local variables there will be NULL. ipi_send_verify() which is invoked from these functions does verify its 'data' parameter, resulting in a kernel oops in irq_data_get_affinity_mask() as the passed NULL pointer gets dereferenced. Add a missing NULL pointer check in ipi_send_verify()... Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool.
CVE-2023-53335: In the Linux kernel, the following vulnerability has been resolved: RDMA/cxgb4: Fix potential null-ptr-deref in pass_establish() If get_ep_from_tid() fails to lookup non-NULL value for ep, ep is dereferenced later regardless of whether it is empty. This patch adds a simple sanity check to fix the issue. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2023-53347: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Handle pairing of E-switch via uplink un/load APIs In case user switch a device from switchdev mode to legacy mode, mlx5 first unpair the E-switch and afterwards unload the uplink vport. From the other hand, in case user remove or reload a device, mlx5 first unload the uplink vport and afterwards unpair the E-switch. The latter is causing a bug[1], hence, handle pairing of E-switch as part of uplink un/load APIs. [1] In case VF_LAG is used, every tc fdb flow is duplicated to the peer esw. However, the original esw keeps a pointer to this duplicated flow, not the peer esw. e.g.: if user create tc fdb flow over esw0, the flow is duplicated over esw1, in FW/HW, but in SW, esw0 keeps a pointer to the duplicated flow. During module unload while a peer tc fdb flow is still offloaded, in case the first device to be removed is the peer device (esw1 in the example above), the peer net-dev is destroyed, and so the mlx5e_priv is memset to 0. Afterwards, the peer device is trying to unpair himself from the original device (esw0 in the example above). Unpair API invoke the original device to clear peer flow from its eswitch (esw0), but the peer flow, which is stored over the original eswitch (esw0), is trying to use the peer mlx5e_priv, which is memset to 0 and result in bellow kernel-oops. [ 157.964081 ] BUG: unable to handle page fault for address: 000000000002ce60 [ 157.964662 ] #PF: supervisor read access in kernel mode [ 157.965123 ] #PF: error_code(0x0000) - not-present page [ 157.965582 ] PGD 0 P4D 0 [ 157.965866 ] Oops: 0000 [#1] SMP [ 157.967670 ] RIP: 0010:mlx5e_tc_del_fdb_flow+0x48/0x460 [mlx5_core] [ 157.976164 ] Call Trace: [ 157.976437 ] <TASK> [ 157.976690 ] __mlx5e_tc_del_fdb_peer_flow+0xe6/0x100 [mlx5_core] [ 157.977230 ] mlx5e_tc_clean_fdb_peer_flows+0x67/0x90 [mlx5_core] [ 157.977767 ] mlx5_esw_offloads_unpair+0x2d/0x1e0 [mlx5_core] [ 157.984653 ] mlx5_esw_offloads_devcom_event+0xbf/0x130 [mlx5_core] [ 157.985212 ] mlx5_devcom_send_event+0xa3/0xb0 [mlx5_core] [ 157.985714 ] esw_offloads_disable+0x5a/0x110 [mlx5_core] [ 157.986209 ] mlx5_eswitch_disable_locked+0x152/0x170 [mlx5_core] [ 157.986757 ] mlx5_eswitch_disable+0x51/0x80 [mlx5_core] [ 157.987248 ] mlx5_unload+0x2a/0xb0 [mlx5_core] [ 157.987678 ] mlx5_uninit_one+0x5f/0xd0 [mlx5_core] [ 157.988127 ] remove_one+0x64/0xe0 [mlx5_core] [ 157.988549 ] pci_device_remove+0x31/0xa0 [ 157.988933 ] device_release_driver_internal+0x18f/0x1f0 [ 157.989402 ] driver_detach+0x3f/0x80 [ 157.989754 ] bus_remove_driver+0x70/0xf0 [ 157.990129 ] pci_unregister_driver+0x34/0x90 [ 157.990537 ] mlx5_cleanup+0xc/0x1c [mlx5_core] [ 157.990972 ] __x64_sys_delete_module+0x15a/0x250 [ 157.991398 ] ? exit_to_user_mode_prepare+0xea/0x110 [ 157.991840 ] do_syscall_64+0x3d/0x90 [ 157.992198 ] entry_SYSCALL_64_after_hwframe+0x46/0xb0
CVE-2023-53348: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix deadlock when aborting transaction during relocation with scrub Before relocating a block group we pause scrub, then do the relocation and then unpause scrub. The relocation process requires starting and committing a transaction, and if we have a failure in the critical section of the transaction commit path (transaction state >= TRANS_STATE_COMMIT_START), we will deadlock if there is a paused scrub. That results in stack traces like the following: [42.479] BTRFS info (device sdc): relocating block group 53876686848 flags metadata|raid6 [42.936] BTRFS warning (device sdc): Skipping commit of aborted transaction. [42.936] ------------[ cut here ]------------ [42.936] BTRFS: Transaction aborted (error -28) [42.936] WARNING: CPU: 11 PID: 346822 at fs/btrfs/transaction.c:1977 btrfs_commit_transaction+0xcc8/0xeb0 [btrfs] [42.936] Modules linked in: dm_flakey dm_mod loop btrfs (...) [42.936] CPU: 11 PID: 346822 Comm: btrfs Tainted: G W 6.3.0-rc2-btrfs-next-127+ #1 [42.936] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [42.936] RIP: 0010:btrfs_commit_transaction+0xcc8/0xeb0 [btrfs] [42.936] Code: ff ff 45 8b (...) [42.936] RSP: 0018:ffffb58649633b48 EFLAGS: 00010282 [42.936] RAX: 0000000000000000 RBX: ffff8be6ef4d5bd8 RCX: 0000000000000000 [42.936] RDX: 0000000000000002 RSI: ffffffffb35e7782 RDI: 00000000ffffffff [42.936] RBP: ffff8be6ef4d5c98 R08: 0000000000000000 R09: ffffb586496339e8 [42.936] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8be6d38c7c00 [42.936] R13: 00000000ffffffe4 R14: ffff8be6c268c000 R15: ffff8be6ef4d5cf0 [42.936] FS: 00007f381a82b340(0000) GS:ffff8beddfcc0000(0000) knlGS:0000000000000000 [42.936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [42.936] CR2: 00007f1e35fb7638 CR3: 0000000117680006 CR4: 0000000000370ee0 [42.936] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [42.936] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [42.936] Call Trace: [42.936] <TASK> [42.936] ? start_transaction+0xcb/0x610 [btrfs] [42.936] prepare_to_relocate+0x111/0x1a0 [btrfs] [42.936] relocate_block_group+0x57/0x5d0 [btrfs] [42.936] ? btrfs_wait_nocow_writers+0x25/0xb0 [btrfs] [42.936] btrfs_relocate_block_group+0x248/0x3c0 [btrfs] [42.936] ? __pfx_autoremove_wake_function+0x10/0x10 [42.936] btrfs_relocate_chunk+0x3b/0x150 [btrfs] [42.936] btrfs_balance+0x8ff/0x11d0 [btrfs] [42.936] ? __kmem_cache_alloc_node+0x14a/0x410 [42.936] btrfs_ioctl+0x2334/0x32c0 [btrfs] [42.937] ? mod_objcg_state+0xd2/0x360 [42.937] ? refill_obj_stock+0xb0/0x160 [42.937] ? seq_release+0x25/0x30 [42.937] ? __rseq_handle_notify_resume+0x3b5/0x4b0 [42.937] ? percpu_counter_add_batch+0x2e/0xa0 [42.937] ? __x64_sys_ioctl+0x88/0xc0 [42.937] __x64_sys_ioctl+0x88/0xc0 [42.937] do_syscall_64+0x38/0x90 [42.937] entry_SYSCALL_64_after_hwframe+0x72/0xdc [42.937] RIP: 0033:0x7f381a6ffe9b [42.937] Code: 00 48 89 44 24 (...) [42.937] RSP: 002b:00007ffd45ecf060 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [42.937] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f381a6ffe9b [42.937] RDX: 00007ffd45ecf150 RSI: 00000000c4009420 RDI: 0000000000000003 [42.937] RBP: 0000000000000003 R08: 0000000000000013 R09: 0000000000000000 [42.937] R10: 00007f381a60c878 R11: 0000000000000246 R12: 00007ffd45ed0423 [42.937] R13: 00007ffd45ecf150 R14: 0000000000000000 R15: 00007ffd45ecf148 [42.937] </TASK> [42.937] ---[ end trace 0000000000000000 ]--- [42.937] BTRFS: error (device sdc: state A) in cleanup_transaction:1977: errno=-28 No space left [59.196] INFO: task btrfs:346772 blocked for more than 120 seconds. [59.196] Tainted: G W 6.3.0-rc2-btrfs-next-127+ #1 [59.196] "echo 0 > /proc/sys/kernel/hung_ ---truncated---
CVE-2023-53353: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: postpone mem_mgr IDR destruction to hpriv_release() The memory manager IDR is currently destroyed when user releases the file descriptor. However, at this point the user context might be still held, and memory buffers might be still in use. Later on, calls to release those buffers will fail due to not finding their handles in the IDR, leading to a memory leak. To avoid this leak, split the IDR destruction from the memory manager fini, and postpone it to hpriv_release() when there is no user context and no buffers are used.
CVE-2023-53355: In the Linux kernel, the following vulnerability has been resolved: staging: pi433: fix memory leak with using debugfs_lookup() When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. To make things simpler, just call debugfs_lookup_and_remove() instead which handles all of the logic at once. This requires saving off the root directory dentry to make creation of individual device subdirectories easier.
CVE-2023-53367: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: fix mem leak in capture user mappings This commit fixes a memory leak caused when clearing the user_mappings info when a new context is opened immediately after user_mapping is captured and a hard reset is performed.
CVE-2023-53370: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix memory leak in mes self test The fences associated with mes queue have to be freed up during amdgpu_ring_fini.
CVE-2023-53383: In the Linux kernel, the following vulnerability has been resolved: irqchip/gicv3: Workaround for NVIDIA erratum T241-FABRIC-4 The T241 platform suffers from the T241-FABRIC-4 erratum which causes unexpected behavior in the GIC when multiple transactions are received simultaneously from different sources. This hardware issue impacts NVIDIA server platforms that use more than two T241 chips interconnected. Each chip has support for 320 {E}SPIs. This issue occurs when multiple packets from different GICs are incorrectly interleaved at the target chip. The erratum text below specifies exactly what can cause multiple transfer packets susceptible to interleaving and GIC state corruption. GIC state corruption can lead to a range of problems, including kernel panics, and unexpected behavior. >From the erratum text: "In some cases, inter-socket AXI4 Stream packets with multiple transfers, may be interleaved by the fabric when presented to ARM Generic Interrupt Controller. GIC expects all transfers of a packet to be delivered without any interleaving. The following GICv3 commands may result in multiple transfer packets over inter-socket AXI4 Stream interface: - Register reads from GICD_I* and GICD_N* - Register writes to 64-bit GICD registers other than GICD_IROUTERn* - ITS command MOVALL Multiple commands in GICv4+ utilize multiple transfer packets, including VMOVP, VMOVI, VMAPP, and 64-bit register accesses." This issue impacts system configurations with more than 2 sockets, that require multi-transfer packets to be sent over inter-socket AXI4 Stream interface between GIC instances on different sockets. GICv4 cannot be supported. GICv3 SW model can only be supported with the workaround. Single and Dual socket configurations are not impacted by this issue and support GICv3 and GICv4." Writing to the chip alias region of the GICD_In{E} registers except GICD_ICENABLERn has an equivalent effect as writing to the global distributor. The SPI interrupt deactivate path is not impacted by the erratum. To fix this problem, implement a workaround that ensures read accesses to the GICD_In{E} registers are directed to the chip that owns the SPI, and disable GICv4.x features. To simplify code changes, the gic_configure_irq() function uses the same alias region for both read and write operations to GICD_ICFGR.
CVE-2023-53393: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix mlx5_ib_get_hw_stats when used for device Currently, when mlx5_ib_get_hw_stats() is used for device (port_num = 0), there is a special handling in order to use the correct counters, but, port_num is being passed down the stack without any change. Also, some functions assume that port_num >=1. As a result, the following oops can occur. BUG: unable to handle page fault for address: ffff89510294f1a8 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP CPU: 8 PID: 1382 Comm: devlink Tainted: G W 6.1.0-rc4_for_upstream_base_2022_11_10_16_12 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:_raw_spin_lock+0xc/0x20 Call Trace: <TASK> mlx5_ib_get_native_port_mdev+0x73/0xe0 [mlx5_ib] do_get_hw_stats.constprop.0+0x109/0x160 [mlx5_ib] mlx5_ib_get_hw_stats+0xad/0x180 [mlx5_ib] ib_setup_device_attrs+0xf0/0x290 [ib_core] ib_register_device+0x3bb/0x510 [ib_core] ? atomic_notifier_chain_register+0x67/0x80 __mlx5_ib_add+0x2b/0x80 [mlx5_ib] mlx5r_probe+0xb8/0x150 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x3c/0x70 ? driver_sysfs_add+0x6b/0x90 really_probe+0xcd/0x380 __driver_probe_device+0x80/0x170 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 ? driver_allows_async_probing+0x60/0x60 ? driver_allows_async_probing+0x60/0x60 bus_for_each_drv+0x7b/0xc0 __device_attach+0xbc/0x200 bus_probe_device+0x87/0xa0 device_add+0x404/0x940 ? dev_set_name+0x53/0x70 __auxiliary_device_add+0x43/0x60 add_adev+0x99/0xe0 [mlx5_core] mlx5_attach_device+0xc8/0x120 [mlx5_core] mlx5_load_one_devl_locked+0xb2/0xe0 [mlx5_core] devlink_reload+0x133/0x250 devlink_nl_cmd_reload+0x480/0x570 ? devlink_nl_pre_doit+0x44/0x2b0 genl_family_rcv_msg_doit.isra.0+0xc2/0x110 genl_rcv_msg+0x180/0x2b0 ? devlink_nl_cmd_region_read_dumpit+0x540/0x540 ? devlink_reload+0x250/0x250 ? devlink_put+0x50/0x50 ? genl_family_rcv_msg_doit.isra.0+0x110/0x110 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1f6/0x2c0 netlink_sendmsg+0x237/0x490 sock_sendmsg+0x33/0x40 __sys_sendto+0x103/0x160 ? handle_mm_fault+0x10e/0x290 ? do_user_addr_fault+0x1c0/0x5f0 __x64_sys_sendto+0x25/0x30 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fix it by setting port_num to 1 in order to get device status and remove unused variable.
CVE-2023-53401: In the Linux kernel, the following vulnerability has been resolved: mm: kmem: fix a NULL pointer dereference in obj_stock_flush_required() KCSAN found an issue in obj_stock_flush_required(): stock->cached_objcg can be reset between the check and dereference: ================================================================== BUG: KCSAN: data-race in drain_all_stock / drain_obj_stock write to 0xffff888237c2a2f8 of 8 bytes by task 19625 on cpu 0: drain_obj_stock+0x408/0x4e0 mm/memcontrol.c:3306 refill_obj_stock+0x9c/0x1e0 mm/memcontrol.c:3340 obj_cgroup_uncharge+0xe/0x10 mm/memcontrol.c:3408 memcg_slab_free_hook mm/slab.h:587 [inline] __cache_free mm/slab.c:3373 [inline] __do_kmem_cache_free mm/slab.c:3577 [inline] kmem_cache_free+0x105/0x280 mm/slab.c:3602 __d_free fs/dcache.c:298 [inline] dentry_free fs/dcache.c:375 [inline] __dentry_kill+0x422/0x4a0 fs/dcache.c:621 dentry_kill+0x8d/0x1e0 dput+0x118/0x1f0 fs/dcache.c:913 __fput+0x3bf/0x570 fs/file_table.c:329 ____fput+0x15/0x20 fs/file_table.c:349 task_work_run+0x123/0x160 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop+0xcf/0xe0 kernel/entry/common.c:171 exit_to_user_mode_prepare+0x6a/0xa0 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:296 do_syscall_64+0x4d/0xc0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888237c2a2f8 of 8 bytes by task 19632 on cpu 1: obj_stock_flush_required mm/memcontrol.c:3319 [inline] drain_all_stock+0x174/0x2a0 mm/memcontrol.c:2361 try_charge_memcg+0x6d0/0xd10 mm/memcontrol.c:2703 try_charge mm/memcontrol.c:2837 [inline] mem_cgroup_charge_skmem+0x51/0x140 mm/memcontrol.c:7290 sock_reserve_memory+0xb1/0x390 net/core/sock.c:1025 sk_setsockopt+0x800/0x1e70 net/core/sock.c:1525 udp_lib_setsockopt+0x99/0x6c0 net/ipv4/udp.c:2692 udp_setsockopt+0x73/0xa0 net/ipv4/udp.c:2817 sock_common_setsockopt+0x61/0x70 net/core/sock.c:3668 __sys_setsockopt+0x1c3/0x230 net/socket.c:2271 __do_sys_setsockopt net/socket.c:2282 [inline] __se_sys_setsockopt net/socket.c:2279 [inline] __x64_sys_setsockopt+0x66/0x80 net/socket.c:2279 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0xffff8881382d52c0 -> 0xffff888138893740 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19632 Comm: syz-executor.0 Not tainted 6.3.0-rc2-syzkaller-00387-g534293368afa #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Fix it by using READ_ONCE()/WRITE_ONCE() for all accesses to stock->cached_objcg.
CVE-2023-53415: In the Linux kernel, the following vulnerability has been resolved: USB: dwc3: fix memory leak with using debugfs_lookup() When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. To make things simpler, just call debugfs_lookup_and_remove() instead which handles all of the logic at once. Note, the root dentry for the debugfs directory for the device needs to be saved so we don't have to keep looking it up, which required a bit more refactoring to properly create and remove it when needed.
CVE-2023-53421: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Reinit blkg_iostat_set after clearing in blkcg_reset_stats() When blkg_alloc() is called to allocate a blkcg_gq structure with the associated blkg_iostat_set's, there are 2 fields within blkg_iostat_set that requires proper initialization - blkg & sync. The former field was introduced by commit 3b8cc6298724 ("blk-cgroup: Optimize blkcg_rstat_flush()") while the later one was introduced by commit f73316482977 ("blk-cgroup: reimplement basic IO stats using cgroup rstat"). Unfortunately those fields in the blkg_iostat_set's are not properly re-initialized when they are cleared in v1's blkcg_reset_stats(). This can lead to a kernel panic due to NULL pointer access of the blkg pointer. The missing initialization of sync is less problematic and can be a problem in a debug kernel due to missing lockdep initialization. Fix these problems by re-initializing them after memory clearing.
CVE-2023-53429: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't check PageError in __extent_writepage __extent_writepage currenly sets PageError whenever any error happens, and the also checks for PageError to decide if to call error handling. This leads to very unclear responsibility for cleaning up on errors. In the VM and generic writeback helpers the basic idea is that once I/O is fired off all error handling responsibility is delegated to the end I/O handler. But if that end I/O handler sets the PageError bit, and the submitter checks it, the bit could in some cases leak into the submission context for fast enough I/O. Fix this by simply not checking PageError and just using the local ret variable to check for submission errors. This also fundamentally solves the long problem documented in a comment in __extent_writepage by never leaking the error bit into the submission context.
CVE-2023-53432: In the Linux kernel, the following vulnerability has been resolved: firewire: net: fix use after free in fwnet_finish_incoming_packet() The netif_rx() function frees the skb so we can't dereference it to save the skb->len.
CVE-2023-53438: In the Linux kernel, the following vulnerability has been resolved: x86/MCE: Always save CS register on AMD Zen IF Poison errors The Instruction Fetch (IF) units on current AMD Zen-based systems do not guarantee a synchronous #MC is delivered for poison consumption errors. Therefore, MCG_STATUS[EIPV|RIPV] will not be set. However, the microarchitecture does guarantee that the exception is delivered within the same context. In other words, the exact rIP is not known, but the context is known to not have changed. There is no architecturally-defined method to determine this behavior. The Code Segment (CS) register is always valid on such IF unit poison errors regardless of the value of MCG_STATUS[EIPV|RIPV]. Add a quirk to save the CS register for poison consumption from the IF unit banks. This is needed to properly determine the context of the error. Otherwise, the severity grading function will assume the context is IN_KERNEL due to the m->cs value being 0 (the initialized value). This leads to unnecessary kernel panics on data poison errors due to the kernel believing the poison consumption occurred in kernel context.
CVE-2023-53441: In the Linux kernel, the following vulnerability has been resolved: bpf: cpumap: Fix memory leak in cpu_map_update_elem Syzkaller reported a memory leak as follows: BUG: memory leak unreferenced object 0xff110001198ef748 (size 192): comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s) hex dump (first 32 bytes): 00 00 00 00 4a 19 00 00 80 ad e3 e4 fe ff c0 00 ....J........... 00 b2 d3 0c 01 00 11 ff 28 f5 8e 19 01 00 11 ff ........(....... backtrace: [<ffffffffadd28087>] __cpu_map_entry_alloc+0xf7/0xb00 [<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0 [<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520 [<ffffffffadc7349b>] map_update_elem+0x4cb/0x720 [<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90 [<ffffffffb029cc80>] do_syscall_64+0x30/0x40 [<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6 BUG: memory leak unreferenced object 0xff110001198ef528 (size 192): comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffffadd281f0>] __cpu_map_entry_alloc+0x260/0xb00 [<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0 [<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520 [<ffffffffadc7349b>] map_update_elem+0x4cb/0x720 [<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90 [<ffffffffb029cc80>] do_syscall_64+0x30/0x40 [<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6 BUG: memory leak unreferenced object 0xff1100010fd93d68 (size 8): comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s) hex dump (first 8 bytes): 00 00 00 00 00 00 00 00 ........ backtrace: [<ffffffffade5db3e>] kvmalloc_node+0x11e/0x170 [<ffffffffadd28280>] __cpu_map_entry_alloc+0x2f0/0xb00 [<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0 [<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520 [<ffffffffadc7349b>] map_update_elem+0x4cb/0x720 [<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90 [<ffffffffb029cc80>] do_syscall_64+0x30/0x40 [<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6 In the cpu_map_update_elem flow, when kthread_stop is called before calling the threadfn of rcpu->kthread, since the KTHREAD_SHOULD_STOP bit of kthread has been set by kthread_stop, the threadfn of rcpu->kthread will never be executed, and rcpu->refcnt will never be 0, which will lead to the allocated rcpu, rcpu->queue and rcpu->queue->queue cannot be released. Calling kthread_stop before executing kthread's threadfn will return -EINTR. We can complete the release of memory resources in this state.
CVE-2023-53447: In the Linux kernel, the following vulnerability has been resolved: f2fs: don't reset unchangable mount option in f2fs_remount() syzbot reports a bug as below: general protection fault, probably for non-canonical address 0xdffffc0000000009: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:__lock_acquire+0x69/0x2000 kernel/locking/lockdep.c:4942 Call Trace: lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5691 __raw_write_lock include/linux/rwlock_api_smp.h:209 [inline] _raw_write_lock+0x2e/0x40 kernel/locking/spinlock.c:300 __drop_extent_tree+0x3ac/0x660 fs/f2fs/extent_cache.c:1100 f2fs_drop_extent_tree+0x17/0x30 fs/f2fs/extent_cache.c:1116 f2fs_insert_range+0x2d5/0x3c0 fs/f2fs/file.c:1664 f2fs_fallocate+0x4e4/0x6d0 fs/f2fs/file.c:1838 vfs_fallocate+0x54b/0x6b0 fs/open.c:324 ksys_fallocate fs/open.c:347 [inline] __do_sys_fallocate fs/open.c:355 [inline] __se_sys_fallocate fs/open.c:353 [inline] __x64_sys_fallocate+0xbd/0x100 fs/open.c:353 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is race condition as below: - since it tries to remount rw filesystem, so that do_remount won't call sb_prepare_remount_readonly to block fallocate, there may be race condition in between remount and fallocate. - in f2fs_remount(), default_options() will reset mount option to default one, and then update it based on result of parse_options(), so there is a hole which race condition can happen. Thread A Thread B - f2fs_fill_super - parse_options - clear_opt(READ_EXTENT_CACHE) - f2fs_remount - default_options - set_opt(READ_EXTENT_CACHE) - f2fs_fallocate - f2fs_insert_range - f2fs_drop_extent_tree - __drop_extent_tree - __may_extent_tree - test_opt(READ_EXTENT_CACHE) return true - write_lock(&et->lock) access NULL pointer - parse_options - clear_opt(READ_EXTENT_CACHE)
CVE-2023-53458: In the Linux kernel, the following vulnerability has been resolved: media: cx23885: Fix a null-ptr-deref bug in buffer_prepare() and buffer_finish() When the driver calls cx23885_risc_buffer() to prepare the buffer, the function call dma_alloc_coherent may fail, resulting in a empty buffer risc->cpu. Later when we free the buffer or access the buffer, null ptr deref is triggered. This bug is similar to the following one: https://git.linuxtv.org/media_stage.git/commit/?id=2b064d91440b33fba5b452f2d1b31f13ae911d71. We believe the bug can be also dynamically triggered from user side. Similarly, we fix this by checking the return value of cx23885_risc_buffer() and the value of risc->cpu before buffer free.
CVE-2023-53460: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix memory leak in rtw_usb_probe() drivers/net/wireless/realtek/rtw88/usb.c:876 rtw_usb_probe() warn: 'hw' from ieee80211_alloc_hw() not released on lines: 811 Fix this by modifying return to a goto statement.
CVE-2023-53466: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7915: fix memory leak in mt7915_mcu_exit Always purge mcu skb queues in mt7915_mcu_exit routine even if mt7915_firmware_state fails.
CVE-2023-53470: In the Linux kernel, the following vulnerability has been resolved: ionic: catch failure from devlink_alloc Add a check for NULL on the alloc return. If devlink_alloc() fails and we try to use devlink_priv() on the NULL return, the kernel gets very unhappy and panics. With this fix, the driver load will still fail, but at least it won't panic the kernel.
CVE-2023-53473: In the Linux kernel, the following vulnerability has been resolved: ext4: improve error handling from ext4_dirhash() The ext4_dirhash() will *almost* never fail, especially when the hash tree feature was first introduced. However, with the addition of support of encrypted, casefolded file names, that function can most certainly fail today. So make sure the callers of ext4_dirhash() properly check for failures, and reflect the errors back up to their callers.
CVE-2023-53476: In the Linux kernel, the following vulnerability has been resolved: iw_cxgb4: Fix potential NULL dereference in c4iw_fill_res_cm_id_entry() This condition needs to match the previous "if (epcp->state == LISTEN) {" exactly to avoid a NULL dereference of either "listen_ep" or "ep". The problem is that "epcp" has been re-assigned so just testing "if (epcp->state == LISTEN) {" a second time is not sufficient.
CVE-2023-53482: In the Linux kernel, the following vulnerability has been resolved: iommu: Fix error unwind in iommu_group_alloc() If either iommu_group_grate_file() fails then the iommu_group is leaked. Destroy it on these error paths. Found by kselftest/iommu/iommufd_fail_nth
CVE-2023-53491: In the Linux kernel, the following vulnerability has been resolved: start_kernel: Add __no_stack_protector function attribute Back during the discussion of commit a9a3ed1eff36 ("x86: Fix early boot crash on gcc-10, third try") we discussed the need for a function attribute to control the omission of stack protectors on a per-function basis; at the time Clang had support for no_stack_protector but GCC did not. This was fixed in gcc-11. Now that the function attribute is available, let's start using it. Callers of boot_init_stack_canary need to use this function attribute unless they're compiled with -fno-stack-protector, otherwise the canary stored in the stack slot of the caller will differ upon the call to boot_init_stack_canary. This will lead to a call to __stack_chk_fail() then panic.
CVE-2023-53499: In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix error unwinding of XDP initialization When initializing XDP in virtnet_open(), some rq xdp initialization may hit an error causing net device open failed. However, previous rqs have already initialized XDP and enabled NAPI, which is not the expected behavior. Need to roll back the previous rq initialization to avoid leaks in error unwinding of init code. Also extract helper functions of disable and enable queue pairs. Use newly introduced disable helper function in error unwinding and virtnet_close. Use enable helper function in virtnet_open.
CVE-2023-53509: In the Linux kernel, the following vulnerability has been resolved: qed: allow sleep in qed_mcp_trace_dump() By default, qed_mcp_cmd_and_union() delays 10us at a time in a loop that can run 500K times, so calls to qed_mcp_nvm_rd_cmd() may block the current thread for over 5s. We observed thread scheduling delays over 700ms in production, with stacktraces pointing to this code as the culprit. qed_mcp_trace_dump() is called from ethtool, so sleeping is permitted. It already can sleep in qed_mcp_halt(), which calls qed_mcp_cmd(). Add a "can sleep" parameter to qed_find_nvram_image() and qed_nvram_read() so they can sleep during qed_mcp_trace_dump(). qed_mcp_trace_get_meta_info() and qed_mcp_trace_read_meta(), called only by qed_mcp_trace_dump(), allow these functions to sleep. I can't tell if the other caller (qed_grc_dump_mcp_hw_dump()) can sleep, so keep b_can_sleep set to false when it calls these functions. An example stacktrace from a custom warning we added to the kernel showing a thread that has not scheduled despite long needing resched: [ 2745.362925,17] ------------[ cut here ]------------ [ 2745.362941,17] WARNING: CPU: 23 PID: 5640 at arch/x86/kernel/irq.c:233 do_IRQ+0x15e/0x1a0() [ 2745.362946,17] Thread not rescheduled for 744 ms after irq 99 [ 2745.362956,17] Modules linked in: ... [ 2745.363339,17] CPU: 23 PID: 5640 Comm: lldpd Tainted: P O 4.4.182+ #202104120910+6d1da174272d.61x [ 2745.363343,17] Hardware name: FOXCONN MercuryB/Quicksilver Controller, BIOS H11P1N09 07/08/2020 [ 2745.363346,17] 0000000000000000 ffff885ec07c3ed8 ffffffff8131eb2f ffff885ec07c3f20 [ 2745.363358,17] ffffffff81d14f64 ffff885ec07c3f10 ffffffff81072ac2 ffff88be98ed0000 [ 2745.363369,17] 0000000000000063 0000000000000174 0000000000000074 0000000000000000 [ 2745.363379,17] Call Trace: [ 2745.363382,17] <IRQ> [<ffffffff8131eb2f>] dump_stack+0x8e/0xcf [ 2745.363393,17] [<ffffffff81072ac2>] warn_slowpath_common+0x82/0xc0 [ 2745.363398,17] [<ffffffff81072b4c>] warn_slowpath_fmt+0x4c/0x50 [ 2745.363404,17] [<ffffffff810d5a8e>] ? rcu_irq_exit+0xae/0xc0 [ 2745.363408,17] [<ffffffff817c99fe>] do_IRQ+0x15e/0x1a0 [ 2745.363413,17] [<ffffffff817c7ac9>] common_interrupt+0x89/0x89 [ 2745.363416,17] <EOI> [<ffffffff8132aa74>] ? delay_tsc+0x24/0x50 [ 2745.363425,17] [<ffffffff8132aa04>] __udelay+0x34/0x40 [ 2745.363457,17] [<ffffffffa04d45ff>] qed_mcp_cmd_and_union+0x36f/0x7d0 [qed] [ 2745.363473,17] [<ffffffffa04d5ced>] qed_mcp_nvm_rd_cmd+0x4d/0x90 [qed] [ 2745.363490,17] [<ffffffffa04e1dc7>] qed_mcp_trace_dump+0x4a7/0x630 [qed] [ 2745.363504,17] [<ffffffffa04e2556>] ? qed_fw_asserts_dump+0x1d6/0x1f0 [qed] [ 2745.363520,17] [<ffffffffa04e4ea7>] qed_dbg_mcp_trace_get_dump_buf_size+0x37/0x80 [qed] [ 2745.363536,17] [<ffffffffa04ea881>] qed_dbg_feature_size+0x61/0xa0 [qed] [ 2745.363551,17] [<ffffffffa04eb427>] qed_dbg_all_data_size+0x247/0x260 [qed] [ 2745.363560,17] [<ffffffffa0482c10>] qede_get_regs_len+0x30/0x40 [qede] [ 2745.363566,17] [<ffffffff816c9783>] ethtool_get_drvinfo+0xe3/0x190 [ 2745.363570,17] [<ffffffff816cc152>] dev_ethtool+0x1362/0x2140 [ 2745.363575,17] [<ffffffff8109bcc6>] ? finish_task_switch+0x76/0x260 [ 2745.363580,17] [<ffffffff817c2116>] ? __schedule+0x3c6/0x9d0 [ 2745.363585,17] [<ffffffff810dbd50>] ? hrtimer_start_range_ns+0x1d0/0x370 [ 2745.363589,17] [<ffffffff816c1e5b>] ? dev_get_by_name_rcu+0x6b/0x90 [ 2745.363594,17] [<ffffffff816de6a8>] dev_ioctl+0xe8/0x710 [ 2745.363599,17] [<ffffffff816a58a8>] sock_do_ioctl+0x48/0x60 [ 2745.363603,17] [<ffffffff816a5d87>] sock_ioctl+0x1c7/0x280 [ 2745.363608,17] [<ffffffff8111f393>] ? seccomp_phase1+0x83/0x220 [ 2745.363612,17] [<ffffffff811e3503>] do_vfs_ioctl+0x2b3/0x4e0 [ 2745.363616,17] [<ffffffff811e3771>] SyS_ioctl+0x41/0x70 [ 2745.363619,17] [<ffffffff817c6ffe>] entry_SYSCALL_64_fastpath+0x1e/0x79 [ 2745.363622,17] ---[ end trace f6954aa440266421 ]---
CVE-2023-53510: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix handling of lrbp->cmd ufshcd_queuecommand() may be called two times in a row for a SCSI command before it is completed. Hence make the following changes: - In the functions that submit a command, do not check the old value of lrbp->cmd nor clear lrbp->cmd in error paths. - In ufshcd_release_scsi_cmd(), do not clear lrbp->cmd. See also scsi_send_eh_cmnd(). This commit prevents that the following appears if a command times out: WARNING: at drivers/ufs/core/ufshcd.c:2965 ufshcd_queuecommand+0x6f8/0x9a8 Call trace: ufshcd_queuecommand+0x6f8/0x9a8 scsi_send_eh_cmnd+0x2c0/0x960 scsi_eh_test_devices+0x100/0x314 scsi_eh_ready_devs+0xd90/0x114c scsi_error_handler+0x2b4/0xb70 kthread+0x16c/0x1e0
CVE-2023-53513: In the Linux kernel, the following vulnerability has been resolved: nbd: fix incomplete validation of ioctl arg We tested and found an alarm caused by nbd_ioctl arg without verification. The UBSAN warning calltrace like below: UBSAN: Undefined behaviour in fs/buffer.c:1709:35 signed integer overflow: -9223372036854775808 - 1 cannot be represented in type 'long long int' CPU: 3 PID: 2523 Comm: syz-executor.0 Not tainted 4.19.90 #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x3f0 arch/arm64/kernel/time.c:78 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:158 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x170/0x1dc lib/dump_stack.c:118 ubsan_epilogue+0x18/0xb4 lib/ubsan.c:161 handle_overflow+0x188/0x1dc lib/ubsan.c:192 __ubsan_handle_sub_overflow+0x34/0x44 lib/ubsan.c:206 __block_write_full_page+0x94c/0xa20 fs/buffer.c:1709 block_write_full_page+0x1f0/0x280 fs/buffer.c:2934 blkdev_writepage+0x34/0x40 fs/block_dev.c:607 __writepage+0x68/0xe8 mm/page-writeback.c:2305 write_cache_pages+0x44c/0xc70 mm/page-writeback.c:2240 generic_writepages+0xdc/0x148 mm/page-writeback.c:2329 blkdev_writepages+0x2c/0x38 fs/block_dev.c:2114 do_writepages+0xd4/0x250 mm/page-writeback.c:2344 The reason for triggering this warning is __block_write_full_page() -> i_size_read(inode) - 1 overflow. inode->i_size is assigned in __nbd_ioctl() -> nbd_set_size() -> bytesize. We think it is necessary to limit the size of arg to prevent errors. Moreover, __nbd_ioctl() -> nbd_add_socket(), arg will be cast to int. Assuming the value of arg is 0x80000000000000001) (on a 64-bit machine), it will become 1 after the coercion, which will return unexpected results. Fix it by adding checks to prevent passing in too large numbers.
CVE-2023-53520: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: Fix hci_suspend_sync crash If hci_unregister_dev() frees the hci_dev object but hci_suspend_notifier may still be accessing it, it can cause the program to crash. Here's the call trace: <4>[102152.653246] Call Trace: <4>[102152.653254] hci_suspend_sync+0x109/0x301 [bluetooth] <4>[102152.653259] hci_suspend_dev+0x78/0xcd [bluetooth] <4>[102152.653263] hci_suspend_notifier+0x42/0x7a [bluetooth] <4>[102152.653268] notifier_call_chain+0x43/0x6b <4>[102152.653271] __blocking_notifier_call_chain+0x48/0x69 <4>[102152.653273] __pm_notifier_call_chain+0x22/0x39 <4>[102152.653276] pm_suspend+0x287/0x57c <4>[102152.653278] state_store+0xae/0xe5 <4>[102152.653281] kernfs_fop_write+0x109/0x173 <4>[102152.653284] __vfs_write+0x16f/0x1a2 <4>[102152.653287] ? selinux_file_permission+0xca/0x16f <4>[102152.653289] ? security_file_permission+0x36/0x109 <4>[102152.653291] vfs_write+0x114/0x21d <4>[102152.653293] __x64_sys_write+0x7b/0xdb <4>[102152.653296] do_syscall_64+0x59/0x194 <4>[102152.653299] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 This patch holds the reference count of the hci_dev object while processing it in hci_suspend_notifier to avoid potential crash caused by the race condition.
CVE-2023-53529: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: Fix memory leak in rtw88_usb Kmemleak shows the following leak arising from routine in the usb probe routine: unreferenced object 0xffff895cb29bba00 (size 512): comm "(udev-worker)", pid 534, jiffies 4294903932 (age 102751.088s) hex dump (first 32 bytes): 77 30 30 30 00 00 00 00 02 2f 2d 2b 30 00 00 00 w000...../-+0... 02 00 2a 28 00 00 00 00 ff 55 ff ff ff 00 00 00 ..*(.....U...... backtrace: [<ffffffff9265fa36>] kmalloc_trace+0x26/0x90 [<ffffffffc17eec41>] rtw_usb_probe+0x2f1/0x680 [rtw_usb] [<ffffffffc03e19fd>] usb_probe_interface+0xdd/0x2e0 [usbcore] [<ffffffff92b4f2fe>] really_probe+0x18e/0x3d0 [<ffffffff92b4f5b8>] __driver_probe_device+0x78/0x160 [<ffffffff92b4f6bf>] driver_probe_device+0x1f/0x90 [<ffffffff92b4f8df>] __driver_attach+0xbf/0x1b0 [<ffffffff92b4d350>] bus_for_each_dev+0x70/0xc0 [<ffffffff92b4e51e>] bus_add_driver+0x10e/0x210 [<ffffffff92b50935>] driver_register+0x55/0xf0 [<ffffffffc03e0708>] usb_register_driver+0x88/0x140 [usbcore] [<ffffffff92401153>] do_one_initcall+0x43/0x210 [<ffffffff9254f42a>] do_init_module+0x4a/0x200 [<ffffffff92551d1c>] __do_sys_finit_module+0xac/0x120 [<ffffffff92ee6626>] do_syscall_64+0x56/0x80 [<ffffffff9300006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The leak was verified to be real by unloading the driver, which resulted in a dangling pointer to the allocation. The allocated memory is freed in rtw_usb_intf_deinit().
CVE-2023-53538: In the Linux kernel, the following vulnerability has been resolved: btrfs: insert tree mod log move in push_node_left There is a fairly unlikely race condition in tree mod log rewind that can result in a kernel panic which has the following trace: [530.569] BTRFS critical (device sda3): unable to find logical 0 length 4096 [530.585] BTRFS critical (device sda3): unable to find logical 0 length 4096 [530.602] BUG: kernel NULL pointer dereference, address: 0000000000000002 [530.618] #PF: supervisor read access in kernel mode [530.629] #PF: error_code(0x0000) - not-present page [530.641] PGD 0 P4D 0 [530.647] Oops: 0000 [#1] SMP [530.654] CPU: 30 PID: 398973 Comm: below Kdump: loaded Tainted: G S O K 5.12.0-0_fbk13_clang_7455_gb24de3bdb045 #1 [530.680] Hardware name: Quanta Mono Lake-M.2 SATA 1HY9U9Z001G/Mono Lake-M.2 SATA, BIOS F20_3A15 08/16/2017 [530.703] RIP: 0010:__btrfs_map_block+0xaa/0xd00 [530.755] RSP: 0018:ffffc9002c2f7600 EFLAGS: 00010246 [530.767] RAX: ffffffffffffffea RBX: ffff888292e41000 RCX: f2702d8b8be15100 [530.784] RDX: ffff88885fda6fb8 RSI: ffff88885fd973c8 RDI: ffff88885fd973c8 [530.800] RBP: ffff888292e410d0 R08: ffffffff82fd7fd0 R09: 00000000fffeffff [530.816] R10: ffffffff82e57fd0 R11: ffffffff82e57d70 R12: 0000000000000000 [530.832] R13: 0000000000001000 R14: 0000000000001000 R15: ffffc9002c2f76f0 [530.848] FS: 00007f38d64af000(0000) GS:ffff88885fd80000(0000) knlGS:0000000000000000 [530.866] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [530.880] CR2: 0000000000000002 CR3: 00000002b6770004 CR4: 00000000003706e0 [530.896] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [530.912] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [530.928] Call Trace: [530.934] ? btrfs_printk+0x13b/0x18c [530.943] ? btrfs_bio_counter_inc_blocked+0x3d/0x130 [530.955] btrfs_map_bio+0x75/0x330 [530.963] ? kmem_cache_alloc+0x12a/0x2d0 [530.973] ? btrfs_submit_metadata_bio+0x63/0x100 [530.984] btrfs_submit_metadata_bio+0xa4/0x100 [530.995] submit_extent_page+0x30f/0x360 [531.004] read_extent_buffer_pages+0x49e/0x6d0 [531.015] ? submit_extent_page+0x360/0x360 [531.025] btree_read_extent_buffer_pages+0x5f/0x150 [531.037] read_tree_block+0x37/0x60 [531.046] read_block_for_search+0x18b/0x410 [531.056] btrfs_search_old_slot+0x198/0x2f0 [531.066] resolve_indirect_ref+0xfe/0x6f0 [531.076] ? ulist_alloc+0x31/0x60 [531.084] ? kmem_cache_alloc_trace+0x12e/0x2b0 [531.095] find_parent_nodes+0x720/0x1830 [531.105] ? ulist_alloc+0x10/0x60 [531.113] iterate_extent_inodes+0xea/0x370 [531.123] ? btrfs_previous_extent_item+0x8f/0x110 [531.134] ? btrfs_search_path_in_tree+0x240/0x240 [531.146] iterate_inodes_from_logical+0x98/0xd0 [531.157] ? btrfs_search_path_in_tree+0x240/0x240 [531.168] btrfs_ioctl_logical_to_ino+0xd9/0x180 [531.179] btrfs_ioctl+0xe2/0x2eb0 This occurs when logical inode resolution takes a tree mod log sequence number, and then while backref walking hits a rewind on a busy node which has the following sequence of tree mod log operations (numbers filled in from a specific example, but they are somewhat arbitrary) REMOVE_WHILE_FREEING slot 532 REMOVE_WHILE_FREEING slot 531 REMOVE_WHILE_FREEING slot 530 ... REMOVE_WHILE_FREEING slot 0 REMOVE slot 455 REMOVE slot 454 REMOVE slot 453 ... REMOVE slot 0 ADD slot 455 ADD slot 454 ADD slot 453 ... ADD slot 0 MOVE src slot 0 -> dst slot 456 nritems 533 REMOVE slot 455 REMOVE slot 454 REMOVE slot 453 ... REMOVE slot 0 When this sequence gets applied via btrfs_tree_mod_log_rewind, it allocates a fresh rewind eb, and first inserts the correct key info for the 533 elements, then overwrites the first 456 of them, then decrements the count by 456 via the add ops, then rewinds the move by doing a memmove from 456:988->0:532. We have never written anything past 532, ---truncated---
CVE-2023-53539: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Fix incomplete state save in rxe_requester If a send packet is dropped by the IP layer in rxe_requester() the call to rxe_xmit_packet() can fail with err == -EAGAIN. To recover, the state of the wqe is restored to the state before the packet was sent so it can be resent. However, the routines that save and restore the state miss a significnt part of the variable state in the wqe, the dma struct which is used to process through the sge table. And, the state is not saved before the packet is built which modifies the dma struct. Under heavy stress testing with many QPs on a fast node sending large messages to a slow node dropped packets are observed and the resent packets are corrupted because the dma struct was not restored. This patch fixes this behavior and allows the test cases to succeed.
CVE-2023-53540: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: reject auth/assoc to AP with our address If the AP uses our own address as its MLD address or BSSID, then clearly something's wrong. Reject such connections so we don't try and fail later.
CVE-2023-53544: In the Linux kernel, the following vulnerability has been resolved: cpufreq: davinci: Fix clk use after free The remove function first frees the clks and only then calls cpufreq_unregister_driver(). If one of the cpufreq callbacks is called just before cpufreq_unregister_driver() is run, the freed clks might be used.
CVE-2023-53545: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: unmap and remove csa_va properly Root PD BO should be reserved before unmap and remove a bo_va from VM otherwise lockdep will complain. v2: check fpriv->csa_va is not NULL instead of amdgpu_mcbp (christian) [14616.936827] WARNING: CPU: 6 PID: 1711 at drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1762 amdgpu_vm_bo_del+0x399/0x3f0 [amdgpu] [14616.937096] Call Trace: [14616.937097] <TASK> [14616.937102] amdgpu_driver_postclose_kms+0x249/0x2f0 [amdgpu] [14616.937187] drm_file_free+0x1d6/0x300 [drm] [14616.937207] drm_close_helper.isra.0+0x62/0x70 [drm] [14616.937220] drm_release+0x5e/0x100 [drm] [14616.937234] __fput+0x9f/0x280 [14616.937239] ____fput+0xe/0x20 [14616.937241] task_work_run+0x61/0x90 [14616.937246] exit_to_user_mode_prepare+0x215/0x220 [14616.937251] syscall_exit_to_user_mode+0x2a/0x60 [14616.937254] do_syscall_64+0x48/0x90 [14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd
CVE-2023-53562: In the Linux kernel, the following vulnerability has been resolved: drm/msm: fix vram leak on bind errors Make sure to release the VRAM buffer also in a case a subcomponent fails to bind. Patchwork: https://patchwork.freedesktop.org/patch/525094/
CVE-2023-53574: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: delete timer and free skb queue when unloading Fix possible crash and memory leak on driver unload by deleting TX purge timer and freeing C2H queue in 'rtw_core_deinit()', shrink critical section in the latter by freeing COEX queue out of TX report lock scope.
CVE-2023-53577: In the Linux kernel, the following vulnerability has been resolved: bpf, cpumap: Make sure kthread is running before map update returns The following warning was reported when running stress-mode enabled xdp_redirect_cpu with some RT threads: ------------[ cut here ]------------ WARNING: CPU: 4 PID: 65 at kernel/bpf/cpumap.c:135 CPU: 4 PID: 65 Comm: kworker/4:1 Not tainted 6.5.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events cpu_map_kthread_stop RIP: 0010:put_cpu_map_entry+0xda/0x220 ...... Call Trace: <TASK> ? show_regs+0x65/0x70 ? __warn+0xa5/0x240 ...... ? put_cpu_map_entry+0xda/0x220 cpu_map_kthread_stop+0x41/0x60 process_one_work+0x6b0/0xb80 worker_thread+0x96/0x720 kthread+0x1a5/0x1f0 ret_from_fork+0x3a/0x70 ret_from_fork_asm+0x1b/0x30 </TASK> The root cause is the same as commit 436901649731 ("bpf: cpumap: Fix memory leak in cpu_map_update_elem"). The kthread is stopped prematurely by kthread_stop() in cpu_map_kthread_stop(), and kthread() doesn't call cpu_map_kthread_run() at all but XDP program has already queued some frames or skbs into ptr_ring. So when __cpu_map_ring_cleanup() checks the ptr_ring, it will find it was not emptied and report a warning. An alternative fix is to use __cpu_map_ring_cleanup() to drop these pending frames or skbs when kthread_stop() returns -EINTR, but it may confuse the user, because these frames or skbs have been handled correctly by XDP program. So instead of dropping these frames or skbs, just make sure the per-cpu kthread is running before __cpu_map_entry_alloc() returns. After apply the fix, the error handle for kthread_stop() will be unnecessary because it will always return 0, so just remove it.
CVE-2023-53579: In the Linux kernel, the following vulnerability has been resolved: gpio: mvebu: fix irq domain leak Uwe Kleine-König pointed out we still have one resource leak in the mvebu driver triggered on driver detach. Let's address it with a custom devm action.
CVE-2023-53584: In the Linux kernel, the following vulnerability has been resolved: ubifs: ubifs_releasepage: Remove ubifs_assert(0) to valid this process There are two states for ubifs writing pages: 1. Dirty, Private 2. Not Dirty, Not Private The normal process cannot go to ubifs_releasepage() which means there exists pages being private but not dirty. Reproducer[1] shows that it could occur (which maybe related to [2]) with following process: PA PB PC lock(page)[PA] ubifs_write_end attach_page_private // set Private __set_page_dirty_nobuffers // set Dirty unlock(page) write_cache_pages[PA] lock(page) clear_page_dirty_for_io(page) // clear Dirty ubifs_writepage do_truncation[PB] truncate_setsize i_size_write(inode, newsize) // newsize = 0 i_size = i_size_read(inode) // i_size = 0 end_index = i_size >> PAGE_SHIFT if (page->index > end_index) goto out // jump out: unlock(page) // Private, Not Dirty generic_fadvise[PC] lock(page) invalidate_inode_page try_to_release_page ubifs_releasepage ubifs_assert(c, 0) // bad assertion! unlock(page) truncate_pagecache[PB] Then we may get following assertion failed: UBIFS error (ubi0:0 pid 1683): ubifs_assert_failed [ubifs]: UBIFS assert failed: 0, in fs/ubifs/file.c:1513 UBIFS warning (ubi0:0 pid 1683): ubifs_ro_mode [ubifs]: switched to read-only mode, error -22 CPU: 2 PID: 1683 Comm: aa Not tainted 5.16.0-rc5-00184-g0bca5994cacc-dirty #308 Call Trace: dump_stack+0x13/0x1b ubifs_ro_mode+0x54/0x60 [ubifs] ubifs_assert_failed+0x4b/0x80 [ubifs] ubifs_releasepage+0x67/0x1d0 [ubifs] try_to_release_page+0x57/0xe0 invalidate_inode_page+0xfb/0x130 __invalidate_mapping_pages+0xb9/0x280 invalidate_mapping_pagevec+0x12/0x20 generic_fadvise+0x303/0x3c0 ksys_fadvise64_64+0x4c/0xb0 [1] https://bugzilla.kernel.org/show_bug.cgi?id=215373 [2] https://linux-mtd.infradead.narkive.com/NQoBeT1u/patch-rfc-ubifs-fix-assert-failed-in-ubifs-set-page-dirty
CVE-2023-53588: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: check for station first in client probe When probing a client, first check if we have it, and then check for the channel context, otherwise you can trigger the warning there easily by probing when the AP isn't even started yet. Since a client existing means the AP is also operating, we can then keep the warning. Also simplify the moved code a bit.
CVE-2023-53594: In the Linux kernel, the following vulnerability has been resolved: driver core: fix resource leak in device_add() When calling kobject_add() failed in device_add(), it will call cleanup_glue_dir() to free resource. But in kobject_add(), dev->kobj.parent has been set to NULL. This will cause resource leak. The process is as follows: device_add() get_device_parent() class_dir_create_and_add() kobject_add() //kobject_get() ... dev->kobj.parent = kobj; ... kobject_add() //failed, but set dev->kobj.parent = NULL ... glue_dir = get_glue_dir(dev) //glue_dir = NULL, and goto //"Error" label ... cleanup_glue_dir() //becaues glue_dir is NULL, not call //kobject_put() The preceding problem may cause insmod mac80211_hwsim.ko to failed. sysfs: cannot create duplicate filename '/devices/virtual/mac80211_hwsim' Call Trace: <TASK> dump_stack_lvl+0x8e/0xd1 sysfs_warn_dup.cold+0x1c/0x29 sysfs_create_dir_ns+0x224/0x280 kobject_add_internal+0x2aa/0x880 kobject_add+0x135/0x1a0 get_device_parent+0x3d7/0x590 device_add+0x2aa/0x1cb0 device_create_groups_vargs+0x1eb/0x260 device_create+0xdc/0x110 mac80211_hwsim_new_radio+0x31e/0x4790 [mac80211_hwsim] init_mac80211_hwsim+0x48d/0x1000 [mac80211_hwsim] do_one_initcall+0x10f/0x630 do_init_module+0x19f/0x5e0 load_module+0x64b7/0x6eb0 __do_sys_finit_module+0x140/0x200 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 </TASK> kobject_add_internal failed for mac80211_hwsim with -EEXIST, don't try to register things with the same name in the same directory.
CVE-2023-53596: In the Linux kernel, the following vulnerability has been resolved: drivers: base: Free devm resources when unregistering a device In the current code, devres_release_all() only gets called if the device has a bus and has been probed. This leads to issues when using bus-less or driver-less devices where the device might never get freed if a managed resource holds a reference to the device. This is happening in the DRM framework for example. We should thus call devres_release_all() in the device_del() function to make sure that the device-managed actions are properly executed when the device is unregistered, even if it has neither a bus nor a driver. This is effectively the same change than commit 2f8d16a996da ("devres: release resources on device_del()") that got reverted by commit a525a3ddeaca ("driver core: free devres in device_release") over memory leaks concerns. This patch effectively combines the two commits mentioned above to release the resources both on device_del() and device_release() and get the best of both worlds.
CVE-2023-53597: In the Linux kernel, the following vulnerability has been resolved: cifs: fix mid leak during reconnection after timeout threshold When the number of responses with status of STATUS_IO_TIMEOUT exceeds a specified threshold (NUM_STATUS_IO_TIMEOUT), we reconnect the connection. But we do not return the mid, or the credits returned for the mid, or reduce the number of in-flight requests. This bug could result in the server->in_flight count to go bad, and also cause a leak in the mids. This change moves the check to a few lines below where the response is decrypted, even of the response is read from the transform header. This way, the code for returning the mids can be reused. Also, the cifs_reconnect was reconnecting just the transport connection before. In case of multi-channel, this may not be what we want to do after several timeouts. Changed that to reconnect the session and the tree too. Also renamed NUM_STATUS_IO_TIMEOUT to a more appropriate name MAX_STATUS_IO_TIMEOUT.
CVE-2023-53602: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix memory leak in WMI firmware stats Memory allocated for firmware pdev, vdev and beacon statistics are not released during rmmod. Fix it by calling ath11k_fw_stats_free() function before hardware unregister. While at it, avoid calling ath11k_fw_stats_free() while processing the firmware stats received in the WMI event because the local list is getting spliced and reinitialised and hence there are no elements in the list after splicing. Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2023-53618: In the Linux kernel, the following vulnerability has been resolved: btrfs: reject invalid reloc tree root keys with stack dump [BUG] Syzbot reported a crash that an ASSERT() got triggered inside prepare_to_merge(). That ASSERT() makes sure the reloc tree is properly pointed back by its subvolume tree. [CAUSE] After more debugging output, it turns out we had an invalid reloc tree: BTRFS error (device loop1): reloc tree mismatch, root 8 has no reloc root, expect reloc root key (-8, 132, 8) gen 17 Note the above root key is (TREE_RELOC_OBJECTID, ROOT_ITEM, QUOTA_TREE_OBJECTID), meaning it's a reloc tree for quota tree. But reloc trees can only exist for subvolumes, as for non-subvolume trees, we just COW the involved tree block, no need to create a reloc tree since those tree blocks won't be shared with other trees. Only subvolumes tree can share tree blocks with other trees (thus they have BTRFS_ROOT_SHAREABLE flag). Thus this new debug output proves my previous assumption that corrupted on-disk data can trigger that ASSERT(). [FIX] Besides the dedicated fix and the graceful exit, also let tree-checker to check such root keys, to make sure reloc trees can only exist for subvolumes.
CVE-2023-53620: In the Linux kernel, the following vulnerability has been resolved: md: fix soft lockup in status_resync status_resync() will calculate 'curr_resync - recovery_active' to show user a progress bar like following: [============>........] resync = 61.4% 'curr_resync' and 'recovery_active' is updated in md_do_sync(), and status_resync() can read them concurrently, hence it's possible that 'curr_resync - recovery_active' can overflow to a huge number. In this case status_resync() will be stuck in the loop to print a large amount of '=', which will end up soft lockup. Fix the problem by setting 'resync' to MD_RESYNC_ACTIVE in this case, this way resync in progress will be reported to user.
CVE-2023-53627: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Grab sas_dev lock when traversing the members of sas_dev.list When freeing slots in function slot_complete_v3_hw(), it is possible that sas_dev.list is being traversed elsewhere, and it may trigger a NULL pointer exception, such as follows: ==>cq thread ==>scsi_eh_6 ==>scsi_error_handler() ==>sas_eh_handle_sas_errors() ==>sas_scsi_find_task() ==>lldd_abort_task() ==>slot_complete_v3_hw() ==>hisi_sas_abort_task() ==>hisi_sas_slot_task_free() ==>dereg_device_v3_hw() ==>list_del_init() ==>list_for_each_entry_safe() [ 7165.434918] sas: Enter sas_scsi_recover_host busy: 32 failed: 32 [ 7165.434926] sas: trying to find task 0x00000000769b5ba5 [ 7165.434927] sas: sas_scsi_find_task: aborting task 0x00000000769b5ba5 [ 7165.434940] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000769b5ba5) aborted [ 7165.434964] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000c9f7aa07) ignored [ 7165.434965] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000e2a1cf01) ignored [ 7165.434968] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 7165.434972] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000022d52d93) ignored [ 7165.434975] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000066a7516c) ignored [ 7165.434976] Mem abort info: [ 7165.434982] ESR = 0x96000004 [ 7165.434991] Exception class = DABT (current EL), IL = 32 bits [ 7165.434992] SET = 0, FnV = 0 [ 7165.434993] EA = 0, S1PTW = 0 [ 7165.434994] Data abort info: [ 7165.434994] ISV = 0, ISS = 0x00000004 [ 7165.434995] CM = 0, WnR = 0 [ 7165.434997] user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000f29543f2 [ 7165.434998] [0000000000000000] pgd=0000000000000000 [ 7165.435003] Internal error: Oops: 96000004 [#1] SMP [ 7165.439863] Process scsi_eh_6 (pid: 4109, stack limit = 0x00000000c43818d5) [ 7165.468862] pstate: 00c00009 (nzcv daif +PAN +UAO) [ 7165.473637] pc : dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.479443] lr : dereg_device_v3_hw+0x2c/0xa8 [hisi_sas_v3_hw] [ 7165.485247] sp : ffff00001d623bc0 [ 7165.488546] x29: ffff00001d623bc0 x28: ffffa027d03b9508 [ 7165.493835] x27: ffff80278ed50af0 x26: ffffa027dd31e0a8 [ 7165.499123] x25: ffffa027d9b27f88 x24: ffffa027d9b209f8 [ 7165.504411] x23: ffffa027c45b0d60 x22: ffff80278ec07c00 [ 7165.509700] x21: 0000000000000008 x20: ffffa027d9b209f8 [ 7165.514988] x19: ffffa027d9b27f88 x18: ffffffffffffffff [ 7165.520276] x17: 0000000000000000 x16: 0000000000000000 [ 7165.525564] x15: ffff0000091d9708 x14: ffff0000093b7dc8 [ 7165.530852] x13: ffff0000093b7a23 x12: 6e7265746e692067 [ 7165.536140] x11: 0000000000000000 x10: 0000000000000bb0 [ 7165.541429] x9 : ffff00001d6238f0 x8 : ffffa027d877af00 [ 7165.546718] x7 : ffffa027d6329600 x6 : ffff7e809f58ca00 [ 7165.552006] x5 : 0000000000001f8a x4 : 000000000000088e [ 7165.557295] x3 : ffffa027d9b27fa8 x2 : 0000000000000000 [ 7165.562583] x1 : 0000000000000000 x0 : 000000003000188e [ 7165.567872] Call trace: [ 7165.570309] dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.575775] hisi_sas_abort_task+0x248/0x358 [hisi_sas_main] [ 7165.581415] sas_eh_handle_sas_errors+0x258/0x8e0 [libsas] [ 7165.586876] sas_scsi_recover_host+0x134/0x458 [libsas] [ 7165.592082] scsi_error_handler+0xb4/0x488 [ 7165.596163] kthread+0x134/0x138 [ 7165.599380] ret_from_fork+0x10/0x18 [ 7165.602940] Code: d5033e9f b9000040 aa0103e2 eb03003f (f9400021) [ 7165.609004] kernel fault(0x1) notification starting on CPU 75 [ 7165.700728] ---[ end trace fc042cbbea224efc ]--- [ 7165.705326] Kernel panic - not syncing: Fatal exception To fix the issue, grab sas_dev lock when traversing the members of sas_dev.list in dereg_device_v3_hw() and hisi_sas_release_tasks() to avoid concurrency of adding and deleting member. When ---truncated---
CVE-2023-53635: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: fix wrong ct->timeout value (struct nf_conn)->timeout is an interval before the conntrack confirmed. After confirmed, it becomes a timestamp. It is observed that timeout of an unconfirmed conntrack: - Set by calling ctnetlink_change_timeout(). As a result, `nfct_time_stamp` was wrongly added to `ct->timeout` twice. - Get by calling ctnetlink_dump_timeout(). As a result, `nfct_time_stamp` was wrongly subtracted. Call Trace: <TASK> dump_stack_lvl ctnetlink_dump_timeout __ctnetlink_glue_build ctnetlink_glue_build __nfqnl_enqueue_packet nf_queue nf_hook_slow ip_mc_output ? __pfx_ip_finish_output ip_send_skb ? __pfx_dst_output udp_send_skb udp_sendmsg ? __pfx_ip_generic_getfrag sock_sendmsg Separate the 2 cases in: - Setting `ct->timeout` in __nf_ct_set_timeout(). - Getting `ct->timeout` in ctnetlink_dump_timeout(). Pablo appends: Update ctnetlink to set up the timeout _after_ the IPS_CONFIRMED flag is set on, otherwise conntrack creation via ctnetlink breaks. Note that the problem described in this patch occurs since the introduction of the nfnetlink_queue conntrack support, select a sufficiently old Fixes: tag for -stable kernel to pick up this fix.
CVE-2023-53647: In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Don't dereference ACPI root object handle Since the commit referenced in the Fixes: tag below the VMBus client driver is walking the ACPI namespace up from the VMBus ACPI device to the ACPI namespace root object trying to find Hyper-V MMIO ranges. However, if it is not able to find them it ends trying to walk resources of the ACPI namespace root object itself. This object has all-ones handle, which causes a NULL pointer dereference in the ACPI code (from dereferencing this pointer with an offset). This in turn causes an oops on boot with VMBus host implementations that do not provide Hyper-V MMIO ranges in their VMBus ACPI device or its ancestors. The QEMU VMBus implementation is an example of such implementation. I guess providing these ranges is optional, since all tested Windows versions seem to be able to use VMBus devices without them. Fix this by explicitly terminating the lookup at the ACPI namespace root object. Note that Linux guests under KVM/QEMU do not use the Hyper-V PV interface by default - they only do so if the KVM PV interface is missing or disabled. Example stack trace of such oops: [ 3.710827] ? __die+0x1f/0x60 [ 3.715030] ? page_fault_oops+0x159/0x460 [ 3.716008] ? exc_page_fault+0x73/0x170 [ 3.716959] ? asm_exc_page_fault+0x22/0x30 [ 3.717957] ? acpi_ns_lookup+0x7a/0x4b0 [ 3.718898] ? acpi_ns_internalize_name+0x79/0xc0 [ 3.720018] acpi_ns_get_node_unlocked+0xb5/0xe0 [ 3.721120] ? acpi_ns_check_object_type+0xfe/0x200 [ 3.722285] ? acpi_rs_convert_aml_to_resource+0x37/0x6e0 [ 3.723559] ? down_timeout+0x3a/0x60 [ 3.724455] ? acpi_ns_get_node+0x3a/0x60 [ 3.725412] acpi_ns_get_node+0x3a/0x60 [ 3.726335] acpi_ns_evaluate+0x1c3/0x2c0 [ 3.727295] acpi_ut_evaluate_object+0x64/0x1b0 [ 3.728400] acpi_rs_get_method_data+0x2b/0x70 [ 3.729476] ? vmbus_platform_driver_probe+0x1d0/0x1d0 [hv_vmbus] [ 3.730940] ? vmbus_platform_driver_probe+0x1d0/0x1d0 [hv_vmbus] [ 3.732411] acpi_walk_resources+0x78/0xd0 [ 3.733398] vmbus_platform_driver_probe+0x9f/0x1d0 [hv_vmbus] [ 3.734802] platform_probe+0x3d/0x90 [ 3.735684] really_probe+0x19b/0x400 [ 3.736570] ? __device_attach_driver+0x100/0x100 [ 3.737697] __driver_probe_device+0x78/0x160 [ 3.738746] driver_probe_device+0x1f/0x90 [ 3.739743] __driver_attach+0xc2/0x1b0 [ 3.740671] bus_for_each_dev+0x70/0xc0 [ 3.741601] bus_add_driver+0x10e/0x210 [ 3.742527] driver_register+0x55/0xf0 [ 3.744412] ? 0xffffffffc039a000 [ 3.745207] hv_acpi_init+0x3c/0x1000 [hv_vmbus]
CVE-2023-53651: In the Linux kernel, the following vulnerability has been resolved: Input: exc3000 - properly stop timer on shutdown We need to stop the timer on driver unbind or probe failures, otherwise we get UAF/Oops.
CVE-2023-53661: In the Linux kernel, the following vulnerability has been resolved: bnxt: avoid overflow in bnxt_get_nvram_directory() The value of an arithmetic expression is subject of possible overflow due to a failure to cast operands to a larger data type before performing arithmetic. Used macro for multiplication instead operator for avoiding overflow. Found by Security Code and Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2023-53673: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_event: call disconnect callback before deleting conn In hci_cs_disconnect, we do hci_conn_del even if disconnection failed. ISO, L2CAP and SCO connections refer to the hci_conn without hci_conn_get, so disconn_cfm must be called so they can clean up their conn, otherwise use-after-free occurs. ISO: ========================================================== iso_sock_connect:880: sk 00000000eabd6557 iso_connect_cis:356: 70:1a:b8:98:ff:a2 -> 28:3d:c2:4a:7e:da ... iso_conn_add:140: hcon 000000001696f1fd conn 00000000b6251073 hci_dev_put:1487: hci0 orig refcnt 17 __iso_chan_add:214: conn 00000000b6251073 iso_sock_clear_timer:117: sock 00000000eabd6557 state 3 ... hci_rx_work:4085: hci0 Event packet hci_event_packet:7601: hci0: event 0x0f hci_cmd_status_evt:4346: hci0: opcode 0x0406 hci_cs_disconnect:2760: hci0: status 0x0c hci_sent_cmd_data:3107: hci0 opcode 0x0406 hci_conn_del:1151: hci0 hcon 000000001696f1fd handle 2560 hci_conn_unlink:1102: hci0: hcon 000000001696f1fd hci_conn_drop:1451: hcon 00000000d8521aaf orig refcnt 2 hci_chan_list_flush:2780: hcon 000000001696f1fd hci_dev_put:1487: hci0 orig refcnt 21 hci_dev_put:1487: hci0 orig refcnt 20 hci_req_cmd_complete:3978: opcode 0x0406 status 0x0c ... <no iso_* activity on sk/conn> ... iso_sock_sendmsg:1098: sock 00000000dea5e2e0, sk 00000000eabd6557 BUG: kernel NULL pointer dereference, address: 0000000000000668 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 RIP: 0010:iso_sock_sendmsg (net/bluetooth/iso.c:1112) bluetooth ========================================================== L2CAP: ================================================================== hci_cmd_status_evt:4359: hci0: opcode 0x0406 hci_cs_disconnect:2760: hci0: status 0x0c hci_sent_cmd_data:3085: hci0 opcode 0x0406 hci_conn_del:1151: hci0 hcon ffff88800c999000 handle 3585 hci_conn_unlink:1102: hci0: hcon ffff88800c999000 hci_chan_list_flush:2780: hcon ffff88800c999000 hci_chan_del:2761: hci0 hcon ffff88800c999000 chan ffff888018ddd280 ... BUG: KASAN: slab-use-after-free in hci_send_acl+0x2d/0x540 [bluetooth] Read of size 8 at addr ffff888018ddd298 by task bluetoothd/1175 CPU: 0 PID: 1175 Comm: bluetoothd Tainted: G E 6.4.0-rc4+ #2 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x5b/0x90 print_report+0xcf/0x670 ? __virt_addr_valid+0xf8/0x180 ? hci_send_acl+0x2d/0x540 [bluetooth] kasan_report+0xa8/0xe0 ? hci_send_acl+0x2d/0x540 [bluetooth] hci_send_acl+0x2d/0x540 [bluetooth] ? __pfx___lock_acquire+0x10/0x10 l2cap_chan_send+0x1fd/0x1300 [bluetooth] ? l2cap_sock_sendmsg+0xf2/0x170 [bluetooth] ? __pfx_l2cap_chan_send+0x10/0x10 [bluetooth] ? lock_release+0x1d5/0x3c0 ? mark_held_locks+0x1a/0x90 l2cap_sock_sendmsg+0x100/0x170 [bluetooth] sock_write_iter+0x275/0x280 ? __pfx_sock_write_iter+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 do_iter_readv_writev+0x176/0x220 ? __pfx_do_iter_readv_writev+0x10/0x10 ? find_held_lock+0x83/0xa0 ? selinux_file_permission+0x13e/0x210 do_iter_write+0xda/0x340 vfs_writev+0x1b4/0x400 ? __pfx_vfs_writev+0x10/0x10 ? __seccomp_filter+0x112/0x750 ? populate_seccomp_data+0x182/0x220 ? __fget_light+0xdf/0x100 ? do_writev+0x19d/0x210 do_writev+0x19d/0x210 ? __pfx_do_writev+0x10/0x10 ? mark_held_locks+0x1a/0x90 do_syscall_64+0x60/0x90 ? lockdep_hardirqs_on_prepare+0x149/0x210 ? do_syscall_64+0x6c/0x90 ? lockdep_hardirqs_on_prepare+0x149/0x210 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7ff45cb23e64 Code: 15 d1 1f 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 80 3d 9d a7 0d 00 00 74 13 b8 14 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 RSP: 002b:00007fff21ae09b8 EFLAGS: 00000202 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: ---truncated---
CVE-2023-53682: In the Linux kernel, the following vulnerability has been resolved: hwmon: (xgene) Fix ioremap and memremap leak Smatch reports: drivers/hwmon/xgene-hwmon.c:757 xgene_hwmon_probe() warn: 'ctx->pcc_comm_addr' from ioremap() not released on line: 757. This is because in drivers/hwmon/xgene-hwmon.c:701 xgene_hwmon_probe(), ioremap and memremap is not released, which may cause a leak. To fix this, ioremap and memremap is modified to devm_ioremap and devm_memremap. [groeck: Fixed formatting and subject]
CVE-2023-53685: In the Linux kernel, the following vulnerability has been resolved: tun: Fix memory leak for detached NAPI queue. syzkaller reported [0] memory leaks of sk and skb related to the TUN device with no repro, but we can reproduce it easily with: struct ifreq ifr = {} int fd_tun, fd_tmp; char buf[4] = {}; fd_tun = openat(AT_FDCWD, "/dev/net/tun", O_WRONLY, 0); ifr.ifr_flags = IFF_TUN | IFF_NAPI | IFF_MULTI_QUEUE; ioctl(fd_tun, TUNSETIFF, &ifr); ifr.ifr_flags = IFF_DETACH_QUEUE; ioctl(fd_tun, TUNSETQUEUE, &ifr); fd_tmp = socket(AF_PACKET, SOCK_PACKET, 0); ifr.ifr_flags = IFF_UP; ioctl(fd_tmp, SIOCSIFFLAGS, &ifr); write(fd_tun, buf, sizeof(buf)); close(fd_tun); If we enable NAPI and multi-queue on a TUN device, we can put skb into tfile->sk.sk_write_queue after the queue is detached. We should prevent it by checking tfile->detached before queuing skb. Note this must be done under tfile->sk.sk_write_queue.lock because write() and ioctl(IFF_DETACH_QUEUE) can run concurrently. Otherwise, there would be a small race window: write() ioctl(IFF_DETACH_QUEUE) `- tun_get_user `- __tun_detach |- if (tfile->detached) |- tun_disable_queue | `-> false | `- tfile->detached = tun | `- tun_queue_purge |- spin_lock_bh(&queue->lock) `- __skb_queue_tail(queue, skb) Another solution is to call tun_queue_purge() when closing and reattaching the detached queue, but it could paper over another problems. Also, we do the same kind of test for IFF_NAPI_FRAGS. [0]: unreferenced object 0xffff88801edbc800 (size 2048): comm "syz-executor.1", pid 33269, jiffies 4295743834 (age 18.756s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<000000008c16ea3d>] __do_kmalloc_node mm/slab_common.c:965 [inline] [<000000008c16ea3d>] __kmalloc+0x4a/0x130 mm/slab_common.c:979 [<000000003addde56>] kmalloc include/linux/slab.h:563 [inline] [<000000003addde56>] sk_prot_alloc+0xef/0x1b0 net/core/sock.c:2035 [<000000003e20621f>] sk_alloc+0x36/0x2f0 net/core/sock.c:2088 [<0000000028e43843>] tun_chr_open+0x3d/0x190 drivers/net/tun.c:3438 [<000000001b0f1f28>] misc_open+0x1a6/0x1f0 drivers/char/misc.c:165 [<000000004376f706>] chrdev_open+0x111/0x300 fs/char_dev.c:414 [<00000000614d379f>] do_dentry_open+0x2f9/0x750 fs/open.c:920 [<000000008eb24774>] do_open fs/namei.c:3636 [inline] [<000000008eb24774>] path_openat+0x143f/0x1a30 fs/namei.c:3791 [<00000000955077b5>] do_filp_open+0xce/0x1c0 fs/namei.c:3818 [<00000000b78973b0>] do_sys_openat2+0xf0/0x260 fs/open.c:1356 [<00000000057be699>] do_sys_open fs/open.c:1372 [inline] [<00000000057be699>] __do_sys_openat fs/open.c:1388 [inline] [<00000000057be699>] __se_sys_openat fs/open.c:1383 [inline] [<00000000057be699>] __x64_sys_openat+0x83/0xf0 fs/open.c:1383 [<00000000a7d2182d>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000a7d2182d>] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 [<000000004cc4e8c4>] entry_SYSCALL_64_after_hwframe+0x72/0xdc unreferenced object 0xffff88802f671700 (size 240): comm "syz-executor.1", pid 33269, jiffies 4295743854 (age 18.736s) hex dump (first 32 bytes): 68 c9 db 1e 80 88 ff ff 68 c9 db 1e 80 88 ff ff h.......h....... 00 c0 7b 2f 80 88 ff ff 00 c8 db 1e 80 88 ff ff ..{/............ backtrace: [<00000000e9d9fdb6>] __alloc_skb+0x223/0x250 net/core/skbuff.c:644 [<000000002c3e4e0b>] alloc_skb include/linux/skbuff.h:1288 [inline] [<000000002c3e4e0b>] alloc_skb_with_frags+0x6f/0x350 net/core/skbuff.c:6378 [<00000000825f98d7>] sock_alloc_send_pskb+0x3ac/0x3e0 net/core/sock.c:2729 [<00000000e9eb3df3>] tun_alloc_skb drivers/net/tun.c:1529 [inline] [< ---truncated---
CVE-2023-53696: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix memory leak in qla2x00_probe_one() There is a memory leak reported by kmemleak: unreferenced object 0xffffc900003f0000 (size 12288): comm "modprobe", pid 19117, jiffies 4299751452 (age 42490.264s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000629261a8>] __vmalloc_node_range+0xe56/0x1110 [<0000000001906886>] __vmalloc_node+0xbd/0x150 [<000000005bb4dc34>] vmalloc+0x25/0x30 [<00000000a2dc1194>] qla2x00_create_host+0x7a0/0xe30 [qla2xxx] [<0000000062b14b47>] qla2x00_probe_one+0x2eb8/0xd160 [qla2xxx] [<00000000641ccc04>] local_pci_probe+0xeb/0x1a0 The root cause is traced to an error-handling path in qla2x00_probe_one() when the adapter "base_vha" initialize failed. The fab_scan_rp "scan.l" is used to record the port information and it is allocated in qla2x00_create_host(). However, it is not released in the error handling path "probe_failed". Fix this by freeing the memory of "scan.l" when an error occurs in the adapter initialization process.
CVE-2023-53699: In the Linux kernel, the following vulnerability has been resolved: riscv: move memblock_allow_resize() after linear mapping is ready The initial memblock metadata is accessed from kernel image mapping. The regions arrays need to "reallocated" from memblock and accessed through linear mapping to cover more memblock regions. So the resizing should not be allowed until linear mapping is ready. Note that there are memblock allocations when building linear mapping. This patch is similar to 24cc61d8cb5a ("arm64: memblock: don't permit memblock resizing until linear mapping is up"). In following log, many memblock regions are reserved before create_linear_mapping_page_table(). And then it triggered reallocation of memblock.reserved.regions and memcpy the old array in kernel image mapping to the new array in linear mapping which caused a page fault. [ 0.000000] memblock_reserve: [0x00000000bf01f000-0x00000000bf01ffff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf021000-0x00000000bf021fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf023000-0x00000000bf023fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf025000-0x00000000bf025fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf027000-0x00000000bf027fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf029000-0x00000000bf029fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf02b000-0x00000000bf02bfff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf02d000-0x00000000bf02dfff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf02f000-0x00000000bf02ffff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] memblock_reserve: [0x00000000bf030000-0x00000000bf030fff] early_init_fdt_scan_reserved_mem+0x28c/0x2c6 [ 0.000000] OF: reserved mem: 0x0000000080000000..0x000000008007ffff (512 KiB) map non-reusable mmode_resv0@80000000 [ 0.000000] memblock_reserve: [0x00000000bf000000-0x00000000bf001fed] paging_init+0x19a/0x5ae [ 0.000000] memblock_phys_alloc_range: 4096 bytes align=0x1000 from=0x0000000000000000 max_addr=0x0000000000000000 alloc_pmd_fixmap+0x14/0x1c [ 0.000000] memblock_reserve: [0x000000017ffff000-0x000000017fffffff] memblock_alloc_range_nid+0xb8/0x128 [ 0.000000] memblock: reserved is doubled to 256 at [0x000000017fffd000-0x000000017fffe7ff] [ 0.000000] Unable to handle kernel paging request at virtual address ff600000ffffd000 [ 0.000000] Oops [#1] [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.4.0-rc1-00011-g99a670b2069c #66 [ 0.000000] Hardware name: riscv-virtio,qemu (DT) [ 0.000000] epc : __memcpy+0x60/0xf8 [ 0.000000] ra : memblock_double_array+0x192/0x248 [ 0.000000] epc : ffffffff8081d214 ra : ffffffff80a3dfc0 sp : ffffffff81403bd0 [ 0.000000] gp : ffffffff814fbb38 tp : ffffffff8140dac0 t0 : 0000000001600000 [ 0.000000] t1 : 0000000000000000 t2 : 000000008f001000 s0 : ffffffff81403c60 [ 0.000000] s1 : ffffffff80c0bc98 a0 : ff600000ffffd000 a1 : ffffffff80c0bcd8 [ 0.000000] a2 : 0000000000000c00 a3 : ffffffff80c0c8d8 a4 : 0000000080000000 [ 0.000000] a5 : 0000000000080000 a6 : 0000000000000000 a7 : 0000000080200000 [ 0.000000] s2 : ff600000ffffd000 s3 : 0000000000002000 s4 : 0000000000000c00 [ 0.000000] s5 : ffffffff80c0bc60 s6 : ffffffff80c0bcc8 s7 : 0000000000000000 [ 0.000000] s8 : ffffffff814fd0a8 s9 : 000000017fffe7ff s10: 0000000000000000 [ 0.000000] s11: 0000000000001000 t3 : 0000000000001000 t4 : 0000000000000000 [ 0.000000] t5 : 000000008f003000 t6 : ff600000ffffd000 [ 0.000000] status: 0000000200000100 badaddr: ff600000ffffd000 cause: 000000000000000f [ 0.000000] [<fff ---truncated---
CVE-2023-53707: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix integer overflow in amdgpu_cs_pass1 The type of size is unsigned int, if size is 0x40000000, there will be an integer overflow, size will be zero after size *= sizeof(uint32_t), will cause uninitialized memory to be referenced later.
CVE-2023-53712: In the Linux kernel, the following vulnerability has been resolved: ARM: 9317/1: kexec: Make smp stop calls asynchronous If a panic is triggered by a hrtimer interrupt all online cpus will be notified and set offline. But as highlighted by commit 19dbdcb8039c ("smp: Warn on function calls from softirq context") this call should not be made synchronous with disabled interrupts: softdog: Initiating panic Kernel panic - not syncing: Software Watchdog Timer expired WARNING: CPU: 1 PID: 0 at kernel/smp.c:753 smp_call_function_many_cond unwind_backtrace: show_stack dump_stack_lvl __warn warn_slowpath_fmt smp_call_function_many_cond smp_call_function crash_smp_send_stop.part.0 machine_crash_shutdown __crash_kexec panic softdog_fire __hrtimer_run_queues hrtimer_interrupt Make the smp call for machine_crash_nonpanic_core() asynchronous.
CVE-2023-53733: In the Linux kernel, the following vulnerability has been resolved: net: sched: cls_u32: Undo tcf_bind_filter if u32_replace_hw_knode When u32_replace_hw_knode fails, we need to undo the tcf_bind_filter operation done at u32_set_parms.
CVE-2023-53742: In the Linux kernel, the following vulnerability has been resolved: kcsan: Avoid READ_ONCE() in read_instrumented_memory() Haibo Li reported: | Unable to handle kernel paging request at virtual address | ffffff802a0d8d7171 | Mem abort info:o: | ESR = 0x9600002121 | EC = 0x25: DABT (current EL), IL = 32 bitsts | SET = 0, FnV = 0 0 | EA = 0, S1PTW = 0 0 | FSC = 0x21: alignment fault | Data abort info:o: | ISV = 0, ISS = 0x0000002121 | CM = 0, WnR = 0 0 | swapper pgtable: 4k pages, 39-bit VAs, pgdp=000000002835200000 | [ffffff802a0d8d71] pgd=180000005fbf9003, p4d=180000005fbf9003, | pud=180000005fbf9003, pmd=180000005fbe8003, pte=006800002a0d8707 | Internal error: Oops: 96000021 [#1] PREEMPT SMP | Modules linked in: | CPU: 2 PID: 45 Comm: kworker/u8:2 Not tainted | 5.15.78-android13-8-g63561175bbda-dirty #1 | ... | pc : kcsan_setup_watchpoint+0x26c/0x6bc | lr : kcsan_setup_watchpoint+0x88/0x6bc | sp : ffffffc00ab4b7f0 | x29: ffffffc00ab4b800 x28: ffffff80294fe588 x27: 0000000000000001 | x26: 0000000000000019 x25: 0000000000000001 x24: ffffff80294fdb80 | x23: 0000000000000000 x22: ffffffc00a70fb68 x21: ffffff802a0d8d71 | x20: 0000000000000002 x19: 0000000000000000 x18: ffffffc00a9bd060 | x17: 0000000000000001 x16: 0000000000000000 x15: ffffffc00a59f000 | x14: 0000000000000001 x13: 0000000000000000 x12: ffffffc00a70faa0 | x11: 00000000aaaaaaab x10: 0000000000000054 x9 : ffffffc00839adf8 | x8 : ffffffc009b4cf00 x7 : 0000000000000000 x6 : 0000000000000007 | x5 : 0000000000000000 x4 : 0000000000000000 x3 : ffffffc00a70fb70 | x2 : 0005ff802a0d8d71 x1 : 0000000000000000 x0 : 0000000000000000 | Call trace: | kcsan_setup_watchpoint+0x26c/0x6bc | __tsan_read2+0x1f0/0x234 | inflate_fast+0x498/0x750 | zlib_inflate+0x1304/0x2384 | __gunzip+0x3a0/0x45c | gunzip+0x20/0x30 | unpack_to_rootfs+0x2a8/0x3fc | do_populate_rootfs+0xe8/0x11c | async_run_entry_fn+0x58/0x1bc | process_one_work+0x3ec/0x738 | worker_thread+0x4c4/0x838 | kthread+0x20c/0x258 | ret_from_fork+0x10/0x20 | Code: b8bfc2a8 2a0803f7 14000007 d503249f (78bfc2a8) ) | ---[ end trace 613a943cb0a572b6 ]----- The reason for this is that on certain arm64 configuration since e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y"), READ_ONCE() may be promoted to a full atomic acquire instruction which cannot be used on unaligned addresses. Fix it by avoiding READ_ONCE() in read_instrumented_memory(), and simply forcing the compiler to do the required access by casting to the appropriate volatile type. In terms of generated code this currently only affects architectures that do not use the default READ_ONCE() implementation. The only downside is that we are not guaranteed atomicity of the access itself, although on most architectures a plain load up to machine word size should still be atomic (a fact the default READ_ONCE() still relies on itself).
CVE-2023-53748: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: Fix potential array out-of-bounds in decoder queue_setup variable *nplanes is provided by user via system call argument. The possible value of q_data->fmt->num_planes is 1-3, while the value of *nplanes can be 1-8. The array access by index i can cause array out-of-bounds. Fix this bug by checking *nplanes against the array size.
CVE-2023-53751: In the Linux kernel, the following vulnerability has been resolved: cifs: fix potential use-after-free bugs in TCP_Server_Info::hostname TCP_Server_Info::hostname may be updated once or many times during reconnect, so protect its access outside reconnect path as well and then prevent any potential use-after-free bugs.
CVE-2023-53753: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix mapping to non-allocated address [Why] There is an issue mapping non-allocated location of memory. It would allocate gpio registers from an array out of bounds. [How] Patch correct numbers of bounds for using.
CVE-2023-53765: In the Linux kernel, the following vulnerability has been resolved: dm cache: free background tracker's queued work in btracker_destroy Otherwise the kernel can BUG with: [ 2245.426978] ============================================================================= [ 2245.435155] BUG bt_work (Tainted: G B W ): Objects remaining in bt_work on __kmem_cache_shutdown() [ 2245.445233] ----------------------------------------------------------------------------- [ 2245.445233] [ 2245.454879] Slab 0x00000000b0ce2b30 objects=64 used=2 fp=0x000000000a3c6a4e flags=0x17ffffc0000200(slab|node=0|zone=2|lastcpupid=0x1fffff) [ 2245.467300] CPU: 7 PID: 10805 Comm: lvm Kdump: loaded Tainted: G B W 6.0.0-rc2 #19 [ 2245.476078] Hardware name: Dell Inc. PowerEdge R7525/0590KW, BIOS 2.5.6 10/06/2021 [ 2245.483646] Call Trace: [ 2245.486100] <TASK> [ 2245.488206] dump_stack_lvl+0x34/0x48 [ 2245.491878] slab_err+0x95/0xcd [ 2245.495028] __kmem_cache_shutdown.cold+0x31/0x136 [ 2245.499821] kmem_cache_destroy+0x49/0x130 [ 2245.503928] btracker_destroy+0x12/0x20 [dm_cache] [ 2245.508728] smq_destroy+0x15/0x60 [dm_cache_smq] [ 2245.513435] dm_cache_policy_destroy+0x12/0x20 [dm_cache] [ 2245.518834] destroy+0xc0/0x110 [dm_cache] [ 2245.522933] dm_table_destroy+0x5c/0x120 [dm_mod] [ 2245.527649] __dm_destroy+0x10e/0x1c0 [dm_mod] [ 2245.532102] dev_remove+0x117/0x190 [dm_mod] [ 2245.536384] ctl_ioctl+0x1a2/0x290 [dm_mod] [ 2245.540579] dm_ctl_ioctl+0xa/0x20 [dm_mod] [ 2245.544773] __x64_sys_ioctl+0x8a/0xc0 [ 2245.548524] do_syscall_64+0x5c/0x90 [ 2245.552104] ? syscall_exit_to_user_mode+0x12/0x30 [ 2245.556897] ? do_syscall_64+0x69/0x90 [ 2245.560648] ? do_syscall_64+0x69/0x90 [ 2245.564394] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 2245.569447] RIP: 0033:0x7fe52583ec6b ... [ 2245.646771] ------------[ cut here ]------------ [ 2245.651395] kmem_cache_destroy bt_work: Slab cache still has objects when called from btracker_destroy+0x12/0x20 [dm_cache] [ 2245.651408] WARNING: CPU: 7 PID: 10805 at mm/slab_common.c:478 kmem_cache_destroy+0x128/0x130 Found using: lvm2-testsuite --only "cache-single-split.sh" Ben bisected and found that commit 0495e337b703 ("mm/slab_common: Deleting kobject in kmem_cache_destroy() without holding slab_mutex/cpu_hotplug_lock") first exposed dm-cache's incomplete cleanup of its background tracker work objects.
CVE-2023-53780: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix FCLK pstate change underflow [Why] Currently we set FCLK p-state change watermark calculated based on dummy p-state latency when UCLK p-state is not supported [How] Calculate FCLK p-state change watermark based on on FCLK pstate change latency in case UCLK p-state is not supported
CVE-2023-53781: In the Linux kernel, the following vulnerability has been resolved: smc: Fix use-after-free in tcp_write_timer_handler(). With Eric's ref tracker, syzbot finally found a repro for use-after-free in tcp_write_timer_handler() by kernel TCP sockets. [0] If SMC creates a kernel socket in __smc_create(), the kernel socket is supposed to be freed in smc_clcsock_release() by calling sock_release() when we close() the parent SMC socket. However, at the end of smc_clcsock_release(), the kernel socket's sk_state might not be TCP_CLOSE. This means that we have not called inet_csk_destroy_sock() in __tcp_close() and have not stopped the TCP timers. The kernel socket's TCP timers can be fired later, so we need to hold a refcnt for net as we do for MPTCP subflows in mptcp_subflow_create_socket(). [0]: leaked reference. sk_alloc (./include/net/net_namespace.h:335 net/core/sock.c:2108) inet_create (net/ipv4/af_inet.c:319 net/ipv4/af_inet.c:244) __sock_create (net/socket.c:1546) smc_create (net/smc/af_smc.c:3269 net/smc/af_smc.c:3284) __sock_create (net/socket.c:1546) __sys_socket (net/socket.c:1634 net/socket.c:1618 net/socket.c:1661) __x64_sys_socket (net/socket.c:1672) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) ================================================================== BUG: KASAN: slab-use-after-free in tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) Read of size 1 at addr ffff888052b65e0d by task syzrepro/18091 CPU: 0 PID: 18091 Comm: syzrepro Tainted: G W 6.3.0-rc4-01174-gb5d54eb5899a #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107) print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) kasan_report (mm/kasan/report.c:538) tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) tcp_write_timer (./include/linux/spinlock.h:390 net/ipv4/tcp_timer.c:643) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2022) run_timer_softirq (kernel/time/timer.c:2037) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) __irq_exit_rcu (kernel/softirq.c:445 kernel/softirq.c:650) irq_exit_rcu (kernel/softirq.c:664) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1107 (discriminator 14)) </IRQ>
CVE-2023-53794: In the Linux kernel, the following vulnerability has been resolved: cifs: fix session state check in reconnect to avoid use-after-free issue Don't collect exiting session in smb2_reconnect_server(), because it will be released soon. Note that the exiting session will stay in server->smb_ses_list until it complete the cifs_free_ipc() and logoff() and then delete itself from the list.
CVE-2023-53806: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: populate subvp cmd info only for the top pipe [Why] System restart observed while changing the display resolution to 8k with extended mode. Sytem restart was caused by a page fault. [How] When the driver populates subvp info it did it for both the pipes using vblank which caused an outof bounds array access causing the page fault. added checks to allow the top pipe only to fix this issue.
CVE-2023-53816: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: fix potential kgd_mem UAFs kgd_mem pointers returned by kfd_process_device_translate_handle are only guaranteed to be valid while p->mutex is held. As soon as the mutex is unlocked, another thread can free the BO.
CVE-2023-53822: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: Ignore frags from uninitialized peer in dp. When max virtual ap interfaces are configured in all the bands with ACS and hostapd restart is done every 60s, a crash is observed at random times. In this certain scenario, a fragmented packet is received for self peer, for which rx_tid and rx_frags are not initialized in datapath. While handling this fragment, crash is observed as the rx_frag list is uninitialised and when we walk in ath11k_dp_rx_h_sort_frags, skb null leads to exception. To address this, before processing received fragments we check dp_setup_done flag is set to ensure that peer has completed its dp peer setup for fragment queue, else ignore processing the fragments. Call trace: ath11k_dp_process_rx_err+0x550/0x1084 [ath11k] ath11k_dp_service_srng+0x70/0x370 [ath11k] 0xffffffc009693a04 __napi_poll+0x30/0xa4 net_rx_action+0x118/0x270 __do_softirq+0x10c/0x244 irq_exit+0x64/0xb4 __handle_domain_irq+0x88/0xac gic_handle_irq+0x74/0xbc el1_irq+0xf0/0x1c0 arch_cpu_idle+0x10/0x18 do_idle+0x104/0x248 cpu_startup_entry+0x20/0x64 rest_init+0xd0/0xdc arch_call_rest_init+0xc/0x14 start_kernel+0x480/0x4b8 Code: f9400281 f94066a2 91405021 b94a0023 (f9406401) Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2023-53829: In the Linux kernel, the following vulnerability has been resolved: f2fs: flush inode if atomic file is aborted Let's flush the inode being aborted atomic operation to avoid stale dirty inode during eviction in this call stack: f2fs_mark_inode_dirty_sync+0x22/0x40 [f2fs] f2fs_abort_atomic_write+0xc4/0xf0 [f2fs] f2fs_evict_inode+0x3f/0x690 [f2fs] ? sugov_start+0x140/0x140 evict+0xc3/0x1c0 evict_inodes+0x17b/0x210 generic_shutdown_super+0x32/0x120 kill_block_super+0x21/0x50 deactivate_locked_super+0x31/0x90 cleanup_mnt+0x100/0x160 task_work_run+0x59/0x90 do_exit+0x33b/0xa50 do_group_exit+0x2d/0x80 __x64_sys_exit_group+0x14/0x20 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd This triggers f2fs_bug_on() in f2fs_evict_inode: f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); This fixes the syzbot report: loop0: detected capacity change from 0 to 131072 F2FS-fs (loop0): invalid crc value F2FS-fs (loop0): Found nat_bits in checkpoint F2FS-fs (loop0): Mounted with checkpoint version = 48b305e4 ------------[ cut here ]------------ kernel BUG at fs/f2fs/inode.c:869! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 5014 Comm: syz-executor220 Not tainted 6.4.0-syzkaller-11479-g6cd06ab12d1a #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869 Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff8880273b8000 RSI: ffffffff83a2bd0d RDI: 0000000000000007 RBP: ffff888077db91b0 R08: 0000000000000007 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888029a3c000 R13: ffff888077db9660 R14: ffff888029a3c0b8 R15: ffff888077db9c50 FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1909bb9000 CR3: 00000000276a9000 CR4: 0000000000350ef0 Call Trace: <TASK> evict+0x2ed/0x6b0 fs/inode.c:665 dispose_list+0x117/0x1e0 fs/inode.c:698 evict_inodes+0x345/0x440 fs/inode.c:748 generic_shutdown_super+0xaf/0x480 fs/super.c:478 kill_block_super+0x64/0xb0 fs/super.c:1417 kill_f2fs_super+0x2af/0x3c0 fs/f2fs/super.c:4704 deactivate_locked_super+0x98/0x160 fs/super.c:330 deactivate_super+0xb1/0xd0 fs/super.c:361 cleanup_mnt+0x2ae/0x3d0 fs/namespace.c:1254 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xa9a/0x29a0 kernel/exit.c:874 do_group_exit+0xd4/0x2a0 kernel/exit.c:1024 __do_sys_exit_group kernel/exit.c:1035 [inline] __se_sys_exit_group kernel/exit.c:1033 [inline] __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1033 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f309be71a09 Code: Unable to access opcode bytes at 0x7f309be719df. RSP: 002b:00007fff171df518 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 00007f309bef7330 RCX: 00007f309be71a09 RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000001 RBP: 0000000000000001 R08: ffffffffffffffc0 R09: 00007f309bef1e40 R10: 0000000000010600 R11: 0000000000000246 R12: 00007f309bef7330 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:f2fs_evict_inode+0x172d/0x1e00 fs/f2fs/inode.c:869 Code: ff df 48 c1 ea 03 80 3c 02 00 0f 85 6a 06 00 00 8b 75 40 ba 01 00 00 00 4c 89 e7 e8 6d ce 06 00 e9 aa fc ff ff e8 63 22 e2 fd <0f> 0b e8 5c 22 e2 fd 48 c7 c0 a8 3a 18 8d 48 ba 00 00 00 00 00 fc RSP: 0018:ffffc90003a6fa00 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 0000000000 ---truncated---
CVE-2023-53834: In the Linux kernel, the following vulnerability has been resolved: iio: adc: ina2xx: avoid NULL pointer dereference on OF device match The affected lines were resulting in a NULL pointer dereference on our platform because the device tree contained the following list of compatible strings: power-sensor@40 { compatible = "ti,ina232", "ti,ina231"; ... }; Since the driver doesn't declare a compatible string "ti,ina232", the OF matching succeeds on "ti,ina231". But the I2C device ID info is populated via the first compatible string, cf. modalias population in of_i2c_get_board_info(). Since there is no "ina232" entry in the legacy I2C device ID table either, the struct i2c_device_id *id pointer in the probe function is NULL. Fix this by using the already populated type variable instead, which points to the proper driver data. Since the name is also wanted, add a generic one to the ina2xx_config table.
CVE-2023-53840: In the Linux kernel, the following vulnerability has been resolved: usb: early: xhci-dbc: Fix a potential out-of-bound memory access If xdbc_bulk_write() fails, the values in 'buf' can be anything. So the string is not guaranteed to be NULL terminated when xdbc_trace() is called. Reserve an extra byte, which will be zeroed automatically because 'buf' is a static variable, in order to avoid troubles, should it happen.
CVE-2023-53846: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on direct node in truncate_dnode() syzbot reports below bug: BUG: KASAN: slab-use-after-free in f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 Read of size 4 at addr ffff88802a25c000 by task syz-executor148/5000 CPU: 1 PID: 5000 Comm: syz-executor148 Not tainted 6.4.0-rc7-syzkaller-00041-ge660abd551f1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351 print_report mm/kasan/report.c:462 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:572 f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 truncate_dnode+0x229/0x2e0 fs/f2fs/node.c:944 f2fs_truncate_inode_blocks+0x64b/0xde0 fs/f2fs/node.c:1154 f2fs_do_truncate_blocks+0x4ac/0xf30 fs/f2fs/file.c:721 f2fs_truncate_blocks+0x7b/0x300 fs/f2fs/file.c:749 f2fs_truncate.part.0+0x4a5/0x630 fs/f2fs/file.c:799 f2fs_truncate include/linux/fs.h:825 [inline] f2fs_setattr+0x1738/0x2090 fs/f2fs/file.c:1006 notify_change+0xb2c/0x1180 fs/attr.c:483 do_truncate+0x143/0x200 fs/open.c:66 handle_truncate fs/namei.c:3295 [inline] do_open fs/namei.c:3640 [inline] path_openat+0x2083/0x2750 fs/namei.c:3791 do_filp_open+0x1ba/0x410 fs/namei.c:3818 do_sys_openat2+0x16d/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_creat fs/open.c:1448 [inline] __se_sys_creat fs/open.c:1442 [inline] __x64_sys_creat+0xcd/0x120 fs/open.c:1442 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is, inodeA references inodeB via inodeB's ino, once inodeA is truncated, it calls truncate_dnode() to truncate data blocks in inodeB's node page, it traverse mapping data from node->i.i_addr[0] to node->i.i_addr[ADDRS_PER_BLOCK() - 1], result in out-of-boundary access. This patch fixes to add sanity check on dnode page in truncate_dnode(), so that, it can help to avoid triggering such issue, and once it encounters such issue, it will record newly introduced ERROR_INVALID_NODE_REFERENCE error into superblock, later fsck can detect such issue and try repairing. Also, it removes f2fs_truncate_data_blocks() for cleanup due to the function has only one caller, and uses f2fs_truncate_data_blocks_range() instead.
CVE-2023-53849: In the Linux kernel, the following vulnerability has been resolved: drm/msm: fix workqueue leak on bind errors Make sure to destroy the workqueue also in case of early errors during bind (e.g. a subcomponent failing to bind). Since commit c3b790ea07a1 ("drm: Manage drm_mode_config_init with drmm_") the mode config will be freed when the drm device is released also when using the legacy interface, but add an explicit cleanup for consistency and to facilitate backporting. Patchwork: https://patchwork.freedesktop.org/patch/525093/
CVE-2023-53850: In the Linux kernel, the following vulnerability has been resolved: iavf: use internal state to free traffic IRQs If the system tries to close the netdev while iavf_reset_task() is running, __LINK_STATE_START will be cleared and netif_running() will return false in iavf_reinit_interrupt_scheme(). This will result in iavf_free_traffic_irqs() not being called and a leak as follows: [7632.489326] remove_proc_entry: removing non-empty directory 'irq/999', leaking at least 'iavf-enp24s0f0v0-TxRx-0' [7632.490214] WARNING: CPU: 0 PID: 10 at fs/proc/generic.c:718 remove_proc_entry+0x19b/0x1b0 is shown when pci_disable_msix() is later called. Fix by using the internal adapter state. The traffic IRQs will always exist if state == __IAVF_RUNNING.
CVE-2023-53856: In the Linux kernel, the following vulnerability has been resolved: of: overlay: Call of_changeset_init() early When of_overlay_fdt_apply() fails, the changeset may be partially applied, and the caller is still expected to call of_overlay_remove() to clean up this partial state. However, of_overlay_apply() calls of_resolve_phandles() before init_overlay_changeset(). Hence if the overlay fails to apply due to an unresolved symbol, the overlay_changeset.cset.entries list is still uninitialized, and cleanup will crash with a NULL-pointer dereference in overlay_removal_is_ok(). Fix this by moving the call to of_changeset_init() from init_overlay_changeset() to of_overlay_fdt_apply(), where all other early initialization is done.
CVE-2023-53859: In the Linux kernel, the following vulnerability has been resolved: s390/idle: mark arch_cpu_idle() noinstr linux-next commit ("cpuidle: tracing: Warn about !rcu_is_watching()") adds a new warning which hits on s390's arch_cpu_idle() function: RCU not on for: arch_cpu_idle+0x0/0x28 WARNING: CPU: 2 PID: 0 at include/linux/trace_recursion.h:162 arch_ftrace_ops_list_func+0x24c/0x258 Modules linked in: CPU: 2 PID: 0 Comm: swapper/2 Not tainted 6.2.0-rc6-next-20230202 #4 Hardware name: IBM 8561 T01 703 (z/VM 7.3.0) Krnl PSW : 0404d00180000000 00000000002b55c0 (arch_ftrace_ops_list_func+0x250/0x258) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:1 PM:0 RI:0 EA:3 Krnl GPRS: c0000000ffffbfff 0000000080000002 0000000000000026 0000000000000000 0000037ffffe3a28 0000037ffffe3a20 0000000000000000 0000000000000000 0000000000000000 0000000000f4acf6 00000000001044f0 0000037ffffe3cb0 0000000000000000 0000000000000000 00000000002b55bc 0000037ffffe3bb8 Krnl Code: 00000000002b55b0: c02000840051 larl %r2,0000000001335652 00000000002b55b6: c0e5fff512d1 brasl %r14,0000000000157b58 #00000000002b55bc: af000000 mc 0,0 >00000000002b55c0: a7f4ffe7 brc 15,00000000002b558e 00000000002b55c4: 0707 bcr 0,%r7 00000000002b55c6: 0707 bcr 0,%r7 00000000002b55c8: eb6ff0480024 stmg %r6,%r15,72(%r15) 00000000002b55ce: b90400ef lgr %r14,%r15 Call Trace: [<00000000002b55c0>] arch_ftrace_ops_list_func+0x250/0x258 ([<00000000002b55bc>] arch_ftrace_ops_list_func+0x24c/0x258) [<0000000000f5f0fc>] ftrace_common+0x1c/0x20 [<00000000001044f6>] arch_cpu_idle+0x6/0x28 [<0000000000f4acf6>] default_idle_call+0x76/0x128 [<00000000001cc374>] do_idle+0xf4/0x1b0 [<00000000001cc6ce>] cpu_startup_entry+0x36/0x40 [<0000000000119d00>] smp_start_secondary+0x140/0x150 [<0000000000f5d2ae>] restart_int_handler+0x6e/0x90 Mark arch_cpu_idle() noinstr like all other architectures with CONFIG_ARCH_WANTS_NO_INSTR (should) have it to fix this.
CVE-2023-53867: In the Linux kernel, the following vulnerability has been resolved: ceph: fix potential use-after-free bug when trimming caps When trimming the caps and just after the 'session->s_cap_lock' is released in ceph_iterate_session_caps() the cap maybe removed by another thread, and when using the stale cap memory in the callbacks it will trigger use-after-free crash. We need to check the existence of the cap just after the 'ci->i_ceph_lock' being acquired. And do nothing if it's already removed.
CVE-2023-53992: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: ocb: don't leave if not joined If there's no OCB state, don't ask the driver/mac80211 to leave, since that's just confusing. Since set/clear the chandef state, that's a simple check.
CVE-2023-54013: In the Linux kernel, the following vulnerability has been resolved: interconnect: Fix locking for runpm vs reclaim For cases where icc_bw_set() can be called in callbaths that could deadlock against shrinker/reclaim, such as runpm resume, we need to decouple the icc locking. Introduce a new icc_bw_lock for cases where we need to serialize bw aggregation and update to decouple that from paths that require memory allocation such as node/link creation/ destruction. Fixes this lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc8-debug+ #554 Not tainted ------------------------------------------------------ ring0/132 is trying to acquire lock: ffffff80871916d0 (&gmu->lock){+.+.}-{3:3}, at: a6xx_pm_resume+0xf0/0x234 but task is already holding lock: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 (dma_fence_map){++++}-{0:0}: __dma_fence_might_wait+0x74/0xc0 dma_resv_lockdep+0x1f4/0x2f4 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}: fs_reclaim_acquire+0x80/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 topology_parse_cpu_capacity+0x8c/0x178 get_cpu_for_node+0x88/0xc4 parse_cluster+0x1b0/0x28c parse_cluster+0x8c/0x28c init_cpu_topology+0x168/0x188 smp_prepare_cpus+0x24/0xf8 kernel_init_freeable+0x18c/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #2 (fs_reclaim){+.+.}-{0:0}: __fs_reclaim_acquire+0x3c/0x48 fs_reclaim_acquire+0x54/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 kzalloc.constprop.0+0x14/0x20 icc_node_create_nolock+0x4c/0xc4 icc_node_create+0x38/0x58 qcom_icc_rpmh_probe+0x1b8/0x248 platform_probe+0x70/0xc4 really_probe+0x158/0x290 __driver_probe_device+0xc8/0xe0 driver_probe_device+0x44/0x100 __driver_attach+0xf8/0x108 bus_for_each_dev+0x78/0xc4 driver_attach+0x2c/0x38 bus_add_driver+0xd0/0x1d8 driver_register+0xbc/0xf8 __platform_driver_register+0x30/0x3c qnoc_driver_init+0x24/0x30 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #1 (icc_lock){+.+.}-{3:3}: __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 icc_set_bw+0x88/0x2b4 _set_opp_bw+0x8c/0xd8 _set_opp+0x19c/0x300 dev_pm_opp_set_opp+0x84/0x94 a6xx_gmu_resume+0x18c/0x804 a6xx_pm_resume+0xf8/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc adreno_load_gpu+0xc4/0x17c msm_open+0x50/0x120 drm_file_alloc+0x17c/0x228 drm_open_helper+0x74/0x118 drm_open+0xa0/0x144 drm_stub_open+0xd4/0xe4 chrdev_open+0x1b8/0x1e4 do_dentry_open+0x2f8/0x38c vfs_open+0x34/0x40 path_openat+0x64c/0x7b4 do_filp_open+0x54/0xc4 do_sys_openat2+0x9c/0x100 do_sys_open+0x50/0x7c __arm64_sys_openat+0x28/0x34 invoke_syscall+0x8c/0x128 el0_svc_common.constprop.0+0xa0/0x11c do_el0_ ---truncated---
CVE-2023-54019: In the Linux kernel, the following vulnerability has been resolved: sched/psi: use kernfs polling functions for PSI trigger polling Destroying psi trigger in cgroup_file_release causes UAF issues when a cgroup is removed from under a polling process. This is happening because cgroup removal causes a call to cgroup_file_release while the actual file is still alive. Destroying the trigger at this point would also destroy its waitqueue head and if there is still a polling process on that file accessing the waitqueue, it will step on the freed pointer: do_select vfs_poll do_rmdir cgroup_rmdir kernfs_drain_open_files cgroup_file_release cgroup_pressure_release psi_trigger_destroy wake_up_pollfree(&t->event_wait) // vfs_poll is unblocked synchronize_rcu kfree(t) poll_freewait -> UAF access to the trigger's waitqueue head Patch [1] fixed this issue for epoll() case using wake_up_pollfree(), however the same issue exists for synchronous poll() case. The root cause of this issue is that the lifecycles of the psi trigger's waitqueue and of the file associated with the trigger are different. Fix this by using kernfs_generic_poll function when polling on cgroup-specific psi triggers. It internally uses kernfs_open_node->poll waitqueue head with its lifecycle tied to the file's lifecycle. This also renders the fix in [1] obsolete, so revert it. [1] commit c2dbe32d5db5 ("sched/psi: Fix use-after-free in ep_remove_wait_queue()")
CVE-2023-54020: In the Linux kernel, the following vulnerability has been resolved: dmaengine: sf-pdma: pdma_desc memory leak fix Commit b2cc5c465c2c ("dmaengine: sf-pdma: Add multithread support for a DMA channel") changed sf_pdma_prep_dma_memcpy() to unconditionally allocate a new sf_pdma_desc each time it is called. The driver previously recycled descs, by checking the in_use flag, only allocating additional descs if the existing one was in use. This logic was removed in commit b2cc5c465c2c ("dmaengine: sf-pdma: Add multithread support for a DMA channel"), but sf_pdma_free_desc() was not changed to handle the new behaviour. As a result, each time sf_pdma_prep_dma_memcpy() is called, the previous descriptor is leaked, over time leading to memory starvation: unreferenced object 0xffffffe008447300 (size 192): comm "irq/39-mchp_dsc", pid 343, jiffies 4294906910 (age 981.200s) hex dump (first 32 bytes): 00 00 00 ff 00 00 00 00 b8 c1 00 00 00 00 00 00 ................ 00 00 70 08 10 00 00 00 00 00 00 c0 00 00 00 00 ..p............. backtrace: [<00000000064a04f4>] kmemleak_alloc+0x1e/0x28 [<00000000018927a7>] kmem_cache_alloc+0x11e/0x178 [<000000002aea8d16>] sf_pdma_prep_dma_memcpy+0x40/0x112 Add the missing kfree() to sf_pdma_free_desc(), and remove the redundant in_use flag.
CVE-2023-54023: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix race between balance and cancel/pause Syzbot reported a panic that looks like this: assertion failed: fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED, in fs/btrfs/ioctl.c:465 ------------[ cut here ]------------ kernel BUG at fs/btrfs/messages.c:259! RIP: 0010:btrfs_assertfail+0x2c/0x30 fs/btrfs/messages.c:259 Call Trace: <TASK> btrfs_exclop_balance fs/btrfs/ioctl.c:465 [inline] btrfs_ioctl_balance fs/btrfs/ioctl.c:3564 [inline] btrfs_ioctl+0x531e/0x5b30 fs/btrfs/ioctl.c:4632 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x197/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The reproducer is running a balance and a cancel or pause in parallel. The way balance finishes is a bit wonky, if we were paused we need to save the balance_ctl in the fs_info, but clear it otherwise and cleanup. However we rely on the return values being specific errors, or having a cancel request or no pause request. If balance completes and returns 0, but we have a pause or cancel request we won't do the appropriate cleanup, and then the next time we try to start a balance we'll trip this ASSERT. The error handling is just wrong here, we always want to clean up, unless we got -ECANCELLED and we set the appropriate pause flag in the exclusive op. With this patch the reproducer ran for an hour without tripping, previously it would trip in less than a few minutes.
CVE-2023-54028: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task" In the function rxe_create_qp(), rxe_qp_from_init() is called to initialize qp, internally things like rxe_init_task are not setup until rxe_qp_init_req(). If an error occurred before this point then the unwind will call rxe_cleanup() and eventually to rxe_qp_do_cleanup()/rxe_cleanup_task() which will oops when trying to access the uninitialized spinlock. If rxe_init_task is not executed, rxe_cleanup_task will not be called.
CVE-2023-54035: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix underflow in chain reference counter Set element addition error path decrements reference counter on chains twice: once on element release and again via nft_data_release(). Then, d6b478666ffa ("netfilter: nf_tables: fix underflow in object reference counter") incorrectly fixed this by removing the stateful object reference count decrement. Restore the stateful object decrement as in b91d90368837 ("netfilter: nf_tables: fix leaking object reference count") and let nft_data_release() decrement the chain reference counter, so this is done only once.
CVE-2023-54047: In the Linux kernel, the following vulnerability has been resolved: drm/rockchip: dw_hdmi: cleanup drm encoder during unbind This fixes a use-after-free crash during rmmod. The DRM encoder is embedded inside the larger rockchip_hdmi, which is allocated with the component. The component memory gets freed before the main drm device is destroyed. Fix it by running encoder cleanup before tearing down its container. [moved encoder cleanup above clk_disable, similar to bind-error-path]
CVE-2023-54048: In the Linux kernel, the following vulnerability has been resolved: RDMA/bnxt_re: Prevent handling any completions after qp destroy HW may generate completions that indicates QP is destroyed. Driver should not be scheduling any more completion handlers for this QP, after the QP is destroyed. Since CQs are active during the QP destroy, driver may still schedule completion handlers. This can cause a race where the destroy_cq and poll_cq running simultaneously. Snippet of kernel panic while doing bnxt_re driver load unload in loop. This indicates a poll after the CQ is freed. [77786.481636] Call Trace: [77786.481640] <TASK> [77786.481644] bnxt_re_poll_cq+0x14a/0x620 [bnxt_re] [77786.481658] ? kvm_clock_read+0x14/0x30 [77786.481693] __ib_process_cq+0x57/0x190 [ib_core] [77786.481728] ib_cq_poll_work+0x26/0x80 [ib_core] [77786.481761] process_one_work+0x1e5/0x3f0 [77786.481768] worker_thread+0x50/0x3a0 [77786.481785] ? __pfx_worker_thread+0x10/0x10 [77786.481790] kthread+0xe2/0x110 [77786.481794] ? __pfx_kthread+0x10/0x10 [77786.481797] ret_from_fork+0x2c/0x50 To avoid this, complete all completion handlers before returning the destroy QP. If free_cq is called soon after destroy_qp, IB stack will cancel the CQ work before invoking the destroy_cq verb and this will prevent any race mentioned.
CVE-2023-54067: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix race when deleting free space root from the dirty cow roots list When deleting the free space tree we are deleting the free space root from the list fs_info->dirty_cowonly_roots without taking the lock that protects it, which is struct btrfs_fs_info::trans_lock. This unsynchronized list manipulation may cause chaos if there's another concurrent manipulation of this list, such as when adding a root to it with ctree.c:add_root_to_dirty_list(). This can result in all sorts of weird failures caused by a race, such as the following crash: [337571.278245] general protection fault, probably for non-canonical address 0xdead000000000108: 0000 [#1] PREEMPT SMP PTI [337571.278933] CPU: 1 PID: 115447 Comm: btrfs Tainted: G W 6.4.0-rc6-btrfs-next-134+ #1 [337571.279153] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [337571.279572] RIP: 0010:commit_cowonly_roots+0x11f/0x250 [btrfs] [337571.279928] Code: 85 38 06 00 (...) [337571.280363] RSP: 0018:ffff9f63446efba0 EFLAGS: 00010206 [337571.280582] RAX: ffff942d98ec2638 RBX: ffff9430b82b4c30 RCX: 0000000449e1c000 [337571.280798] RDX: dead000000000100 RSI: ffff9430021e4900 RDI: 0000000000036070 [337571.281015] RBP: ffff942d98ec2000 R08: ffff942d98ec2000 R09: 000000000000015b [337571.281254] R10: 0000000000000009 R11: 0000000000000001 R12: ffff942fe8fbf600 [337571.281476] R13: ffff942dabe23040 R14: ffff942dabe20800 R15: ffff942d92cf3b48 [337571.281723] FS: 00007f478adb7340(0000) GS:ffff94349fa40000(0000) knlGS:0000000000000000 [337571.281950] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [337571.282184] CR2: 00007f478ab9a3d5 CR3: 000000001e02c001 CR4: 0000000000370ee0 [337571.282416] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [337571.282647] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [337571.282874] Call Trace: [337571.283101] <TASK> [337571.283327] ? __die_body+0x1b/0x60 [337571.283570] ? die_addr+0x39/0x60 [337571.283796] ? exc_general_protection+0x22e/0x430 [337571.284022] ? asm_exc_general_protection+0x22/0x30 [337571.284251] ? commit_cowonly_roots+0x11f/0x250 [btrfs] [337571.284531] btrfs_commit_transaction+0x42e/0xf90 [btrfs] [337571.284803] ? _raw_spin_unlock+0x15/0x30 [337571.285031] ? release_extent_buffer+0x103/0x130 [btrfs] [337571.285305] reset_balance_state+0x152/0x1b0 [btrfs] [337571.285578] btrfs_balance+0xa50/0x11e0 [btrfs] [337571.285864] ? __kmem_cache_alloc_node+0x14a/0x410 [337571.286086] btrfs_ioctl+0x249a/0x3320 [btrfs] [337571.286358] ? mod_objcg_state+0xd2/0x360 [337571.286577] ? refill_obj_stock+0xb0/0x160 [337571.286798] ? seq_release+0x25/0x30 [337571.287016] ? __rseq_handle_notify_resume+0x3ba/0x4b0 [337571.287235] ? percpu_counter_add_batch+0x2e/0xa0 [337571.287455] ? __x64_sys_ioctl+0x88/0xc0 [337571.287675] __x64_sys_ioctl+0x88/0xc0 [337571.287901] do_syscall_64+0x38/0x90 [337571.288126] entry_SYSCALL_64_after_hwframe+0x72/0xdc [337571.288352] RIP: 0033:0x7f478aaffe9b So fix this by locking struct btrfs_fs_info::trans_lock before deleting the free space root from that list.
CVE-2023-54081: In the Linux kernel, the following vulnerability has been resolved: xen: speed up grant-table reclaim When a grant entry is still in use by the remote domain, Linux must put it on a deferred list. Normally, this list is very short, because the PV network and block protocols expect the backend to unmap the grant first. However, Qubes OS's GUI protocol is subject to the constraints of the X Window System, and as such winds up with the frontend unmapping the window first. As a result, the list can grow very large, resulting in a massive memory leak and eventual VM freeze. To partially solve this problem, make the number of entries that the VM will attempt to free at each iteration tunable. The default is still 10, but it can be overridden via a module parameter. This is Cc: stable because (when combined with appropriate userspace changes) it fixes a severe performance and stability problem for Qubes OS users.
CVE-2023-54121: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix incorrect splitting in btrfs_drop_extent_map_range In production we were seeing a variety of WARN_ON()'s in the extent_map code, specifically in btrfs_drop_extent_map_range() when we have to call add_extent_mapping() for our second split. Consider the following extent map layout PINNED [0 16K) [32K, 48K) and then we call btrfs_drop_extent_map_range for [0, 36K), with skip_pinned == true. The initial loop will have start = 0 end = 36K len = 36K we will find the [0, 16k) extent, but since we are pinned we will skip it, which has this code start = em_end; if (end != (u64)-1) len = start + len - em_end; em_end here is 16K, so now the values are start = 16K len = 16K + 36K - 16K = 36K len should instead be 20K. This is a problem when we find the next extent at [32K, 48K), we need to split this extent to leave [36K, 48k), however the code for the split looks like this split->start = start + len; split->len = em_end - (start + len); In this case we have em_end = 48K split->start = 16K + 36K // this should be 16K + 20K split->len = 48K - (16K + 36K) // this overflows as 16K + 36K is 52K and now we have an invalid extent_map in the tree that potentially overlaps other entries in the extent map. Even in the non-overlapping case we will have split->start set improperly, which will cause problems with any block related calculations. We don't actually need len in this loop, we can simply use end as our end point, and only adjust start up when we find a pinned extent we need to skip. Adjust the logic to do this, which keeps us from inserting an invalid extent map. We only skip_pinned in the relocation case, so this is relatively rare, except in the case where you are running relocation a lot, which can happen with auto relocation on.
CVE-2023-54129: In the Linux kernel, the following vulnerability has been resolved: octeontx2-af: Add validation for lmac type Upon physical link change, firmware reports to the kernel about the change along with the details like speed, lmac_type_id, etc. Kernel derives lmac_type based on lmac_type_id received from firmware. In a few scenarios, firmware returns an invalid lmac_type_id, which is resulting in below kernel panic. This patch adds the missing validation of the lmac_type_id field. Internal error: Oops: 96000005 [#1] PREEMPT SMP [ 35.321595] Modules linked in: [ 35.328982] CPU: 0 PID: 31 Comm: kworker/0:1 Not tainted 5.4.210-g2e3169d8e1bc-dirty #17 [ 35.337014] Hardware name: Marvell CN103XX board (DT) [ 35.344297] Workqueue: events work_for_cpu_fn [ 35.352730] pstate: 40400089 (nZcv daIf +PAN -UAO) [ 35.360267] pc : strncpy+0x10/0x30 [ 35.366595] lr : cgx_link_change_handler+0x90/0x180
CVE-2023-54145: In the Linux kernel, the following vulnerability has been resolved: bpf: drop unnecessary user-triggerable WARN_ONCE in verifierl log It's trivial for user to trigger "verifier log line truncated" warning, as verifier has a fixed-sized buffer of 1024 bytes (as of now), and there are at least two pieces of user-provided information that can be output through this buffer, and both can be arbitrarily sized by user: - BTF names; - BTF.ext source code lines strings. Verifier log buffer should be properly sized for typical verifier state output. But it's sort-of expected that this buffer won't be long enough in some circumstances. So let's drop the check. In any case code will work correctly, at worst truncating a part of a single line output.
CVE-2023-54151: In the Linux kernel, the following vulnerability has been resolved: f2fs: Fix system crash due to lack of free space in LFS When f2fs tries to checkpoint during foreground gc in LFS mode, system crash occurs due to lack of free space if the amount of dirty node and dentry pages generated by data migration exceeds free space. The reproduction sequence is as follows. - 20GiB capacity block device (null_blk) - format and mount with LFS mode - create a file and write 20,000MiB - 4k random write on full range of the file RIP: 0010:new_curseg+0x48a/0x510 [f2fs] Code: 55 e7 f5 89 c0 48 0f af c3 48 8b 5d c0 48 c1 e8 20 83 c0 01 89 43 6c 48 83 c4 28 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc <0f> 0b f0 41 80 4f 48 04 45 85 f6 0f 84 ba fd ff ff e9 ef fe ff ff RSP: 0018:ffff977bc397b218 EFLAGS: 00010246 RAX: 00000000000027b9 RBX: 0000000000000000 RCX: 00000000000027c0 RDX: 0000000000000000 RSI: 00000000000027b9 RDI: ffff8c25ab4e74f8 RBP: ffff977bc397b268 R08: 00000000000027b9 R09: ffff8c29e4a34b40 R10: 0000000000000001 R11: ffff977bc397b0d8 R12: 0000000000000000 R13: ffff8c25b4dd81a0 R14: 0000000000000000 R15: ffff8c2f667f9000 FS: 0000000000000000(0000) GS:ffff8c344ec80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c00055d000 CR3: 0000000e30810003 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> allocate_segment_by_default+0x9c/0x110 [f2fs] f2fs_allocate_data_block+0x243/0xa30 [f2fs] ? __mod_lruvec_page_state+0xa0/0x150 do_write_page+0x80/0x160 [f2fs] f2fs_do_write_node_page+0x32/0x50 [f2fs] __write_node_page+0x339/0x730 [f2fs] f2fs_sync_node_pages+0x5a6/0x780 [f2fs] block_operations+0x257/0x340 [f2fs] f2fs_write_checkpoint+0x102/0x1050 [f2fs] f2fs_gc+0x27c/0x630 [f2fs] ? folio_mark_dirty+0x36/0x70 f2fs_balance_fs+0x16f/0x180 [f2fs] This patch adds checking whether free sections are enough before checkpoint during gc. [Jaegeuk Kim: code clean-up]
CVE-2023-54153: In the Linux kernel, the following vulnerability has been resolved: ext4: turn quotas off if mount failed after enabling quotas Yi found during a review of the patch "ext4: don't BUG on inconsistent journal feature" that when ext4_mark_recovery_complete() returns an error value, the error handling path does not turn off the enabled quotas, which triggers the following kmemleak: ================================================================ unreferenced object 0xffff8cf68678e7c0 (size 64): comm "mount", pid 746, jiffies 4294871231 (age 11.540s) hex dump (first 32 bytes): 00 90 ef 82 f6 8c ff ff 00 00 00 00 41 01 00 00 ............A... c7 00 00 00 bd 00 00 00 0a 00 00 00 48 00 00 00 ............H... backtrace: [<00000000c561ef24>] __kmem_cache_alloc_node+0x4d4/0x880 [<00000000d4e621d7>] kmalloc_trace+0x39/0x140 [<00000000837eee74>] v2_read_file_info+0x18a/0x3a0 [<0000000088f6c877>] dquot_load_quota_sb+0x2ed/0x770 [<00000000340a4782>] dquot_load_quota_inode+0xc6/0x1c0 [<0000000089a18bd5>] ext4_enable_quotas+0x17e/0x3a0 [ext4] [<000000003a0268fa>] __ext4_fill_super+0x3448/0x3910 [ext4] [<00000000b0f2a8a8>] ext4_fill_super+0x13d/0x340 [ext4] [<000000004a9489c4>] get_tree_bdev+0x1dc/0x370 [<000000006e723bf1>] ext4_get_tree+0x1d/0x30 [ext4] [<00000000c7cb663d>] vfs_get_tree+0x31/0x160 [<00000000320e1bed>] do_new_mount+0x1d5/0x480 [<00000000c074654c>] path_mount+0x22e/0xbe0 [<0000000003e97a8e>] do_mount+0x95/0xc0 [<000000002f3d3736>] __x64_sys_mount+0xc4/0x160 [<0000000027d2140c>] do_syscall_64+0x3f/0x90 ================================================================ To solve this problem, we add a "failed_mount10" tag, and call ext4_quota_off_umount() in this tag to release the enabled qoutas.
CVE-2023-54157: In the Linux kernel, the following vulnerability has been resolved: binder: fix UAF of alloc->vma in race with munmap() [ cmllamas: clean forward port from commit 015ac18be7de ("binder: fix UAF of alloc->vma in race with munmap()") in 5.10 stable. It is needed in mainline after the revert of commit a43cfc87caaf ("android: binder: stop saving a pointer to the VMA") as pointed out by Liam. The commit log and tags have been tweaked to reflect this. ] In commit 720c24192404 ("ANDROID: binder: change down_write to down_read") binder assumed the mmap read lock is sufficient to protect alloc->vma inside binder_update_page_range(). This used to be accurate until commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap"), which now downgrades the mmap_lock after detaching the vma from the rbtree in munmap(). Then it proceeds to teardown and free the vma with only the read lock held. This means that accesses to alloc->vma in binder_update_page_range() now will race with vm_area_free() in munmap() and can cause a UAF as shown in the following KASAN trace: ================================================================== BUG: KASAN: use-after-free in vm_insert_page+0x7c/0x1f0 Read of size 8 at addr ffff16204ad00600 by task server/558 CPU: 3 PID: 558 Comm: server Not tainted 5.10.150-00001-gdc8dcf942daa #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x2a0 show_stack+0x18/0x2c dump_stack+0xf8/0x164 print_address_description.constprop.0+0x9c/0x538 kasan_report+0x120/0x200 __asan_load8+0xa0/0xc4 vm_insert_page+0x7c/0x1f0 binder_update_page_range+0x278/0x50c binder_alloc_new_buf+0x3f0/0xba0 binder_transaction+0x64c/0x3040 binder_thread_write+0x924/0x2020 binder_ioctl+0x1610/0x2e5c __arm64_sys_ioctl+0xd4/0x120 el0_svc_common.constprop.0+0xac/0x270 do_el0_svc+0x38/0xa0 el0_svc+0x1c/0x2c el0_sync_handler+0xe8/0x114 el0_sync+0x180/0x1c0 Allocated by task 559: kasan_save_stack+0x38/0x6c __kasan_kmalloc.constprop.0+0xe4/0xf0 kasan_slab_alloc+0x18/0x2c kmem_cache_alloc+0x1b0/0x2d0 vm_area_alloc+0x28/0x94 mmap_region+0x378/0x920 do_mmap+0x3f0/0x600 vm_mmap_pgoff+0x150/0x17c ksys_mmap_pgoff+0x284/0x2dc __arm64_sys_mmap+0x84/0xa4 el0_svc_common.constprop.0+0xac/0x270 do_el0_svc+0x38/0xa0 el0_svc+0x1c/0x2c el0_sync_handler+0xe8/0x114 el0_sync+0x180/0x1c0 Freed by task 560: kasan_save_stack+0x38/0x6c kasan_set_track+0x28/0x40 kasan_set_free_info+0x24/0x4c __kasan_slab_free+0x100/0x164 kasan_slab_free+0x14/0x20 kmem_cache_free+0xc4/0x34c vm_area_free+0x1c/0x2c remove_vma+0x7c/0x94 __do_munmap+0x358/0x710 __vm_munmap+0xbc/0x130 __arm64_sys_munmap+0x4c/0x64 el0_svc_common.constprop.0+0xac/0x270 do_el0_svc+0x38/0xa0 el0_svc+0x1c/0x2c el0_sync_handler+0xe8/0x114 el0_sync+0x180/0x1c0 [...] ================================================================== To prevent the race above, revert back to taking the mmap write lock inside binder_update_page_range(). One might expect an increase of mmap lock contention. However, binder already serializes these calls via top level alloc->mutex. Also, there was no performance impact shown when running the binder benchmark tests.
CVE-2023-54180: In the Linux kernel, the following vulnerability has been resolved: btrfs: handle case when repair happens with dev-replace [BUG] There is a bug report that a BUG_ON() in btrfs_repair_io_failure() (originally repair_io_failure() in v6.0 kernel) got triggered when replacing a unreliable disk: BTRFS warning (device sda1): csum failed root 257 ino 2397453 off 39624704 csum 0xb0d18c75 expected csum 0x4dae9c5e mirror 3 kernel BUG at fs/btrfs/extent_io.c:2380! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 9 PID: 3614331 Comm: kworker/u257:2 Tainted: G OE 6.0.0-5-amd64 #1 Debian 6.0.10-2 Hardware name: Micro-Star International Co., Ltd. MS-7C60/TRX40 PRO WIFI (MS-7C60), BIOS 2.70 07/01/2021 Workqueue: btrfs-endio btrfs_end_bio_work [btrfs] RIP: 0010:repair_io_failure+0x24a/0x260 [btrfs] Call Trace: <TASK> clean_io_failure+0x14d/0x180 [btrfs] end_bio_extent_readpage+0x412/0x6e0 [btrfs] ? __switch_to+0x106/0x420 process_one_work+0x1c7/0x380 worker_thread+0x4d/0x380 ? rescuer_thread+0x3a0/0x3a0 kthread+0xe9/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 [CAUSE] Before the BUG_ON(), we got some read errors from the replace target first, note the mirror number (3, which is beyond RAID1 duplication, thus it's read from the replace target device). Then at the BUG_ON() location, we are trying to writeback the repaired sectors back the failed device. The check looks like this: ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length, &bioc, mirror_num); if (ret) goto out_counter_dec; BUG_ON(mirror_num != bioc->mirror_num); But inside btrfs_map_block(), we can modify bioc->mirror_num especially for dev-replace: if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 && !need_full_stripe(op) && dev_replace->tgtdev != NULL) { ret = get_extra_mirror_from_replace(fs_info, logical, *length, dev_replace->srcdev->devid, &mirror_num, &physical_to_patch_in_first_stripe); patch_the_first_stripe_for_dev_replace = 1; } Thus if we're repairing the replace target device, we're going to trigger that BUG_ON(). But in reality, the read failure from the replace target device may be that, our replace hasn't reached the range we're reading, thus we're reading garbage, but with replace running, the range would be properly filled later. Thus in that case, we don't need to do anything but let the replace routine to handle it. [FIX] Instead of a BUG_ON(), just skip the repair if we're repairing the device replace target device.
CVE-2023-54181: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix issue in verifying allow_ptr_leaks After we converted the capabilities of our networking-bpf program from cap_sys_admin to cap_net_admin+cap_bpf, our networking-bpf program failed to start. Because it failed the bpf verifier, and the error log is "R3 pointer comparison prohibited". A simple reproducer as follows, SEC("cls-ingress") int ingress(struct __sk_buff *skb) { struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); if ((long)(iph + 1) > (long)skb->data_end) return TC_ACT_STOLEN; return TC_ACT_OK; } Per discussion with Yonghong and Alexei [1], comparison of two packet pointers is not a pointer leak. This patch fixes it. Our local kernel is 6.1.y and we expect this fix to be backported to 6.1.y, so stable is CCed. [1]. https://lore.kernel.org/bpf/CAADnVQ+Nmspr7Si+pxWn8zkE7hX-7s93ugwC+94aXSy4uQ9vBg@mail.gmail.com/
CVE-2023-54182: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to check readonly condition correctly With below case, it can mount multi-device image w/ rw option, however one of secondary device is set as ro, later update will cause panic, so let's introduce f2fs_dev_is_readonly(), and check multi-devices rw status in f2fs_remount() w/ it in order to avoid such inconsistent mount status. mkfs.f2fs -c /dev/zram1 /dev/zram0 -f blockdev --setro /dev/zram1 mount -t f2fs dev/zram0 /mnt/f2fs mount: /mnt/f2fs: WARNING: source write-protected, mounted read-only. mount -t f2fs -o remount,rw mnt/f2fs dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=8192 kernel BUG at fs/f2fs/inline.c:258! RIP: 0010:f2fs_write_inline_data+0x23e/0x2d0 [f2fs] Call Trace: f2fs_write_single_data_page+0x26b/0x9f0 [f2fs] f2fs_write_cache_pages+0x389/0xa60 [f2fs] __f2fs_write_data_pages+0x26b/0x2d0 [f2fs] f2fs_write_data_pages+0x2e/0x40 [f2fs] do_writepages+0xd3/0x1b0 __writeback_single_inode+0x5b/0x420 writeback_sb_inodes+0x236/0x5a0 __writeback_inodes_wb+0x56/0xf0 wb_writeback+0x2a3/0x490 wb_do_writeback+0x2b2/0x330 wb_workfn+0x6a/0x260 process_one_work+0x270/0x5e0 worker_thread+0x52/0x3e0 kthread+0xf4/0x120 ret_from_fork+0x29/0x50
CVE-2023-54185: In the Linux kernel, the following vulnerability has been resolved: btrfs: remove BUG_ON()'s in add_new_free_space() At add_new_free_space() we have these BUG_ON()'s that are there to deal with any failure to add free space to the in memory free space cache. Such failures are mostly -ENOMEM that should be very rare. However there's no need to have these BUG_ON()'s, we can just return any error to the caller and all callers and their upper call chain are already dealing with errors. So just make add_new_free_space() return any errors, while removing the BUG_ON()'s, and returning the total amount of added free space to an optional u64 pointer argument.
CVE-2023-54201: In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix wrong resources deallocation order When trying to destroy QP or CQ, we first decrease the refcount and potentially free memory regions allocated for the object and then request the device to destroy the object. If the device fails, the object isn't fully destroyed so the user/IB core can try to destroy the object again which will lead to underflow when trying to decrease an already zeroed refcount. Deallocate resources in reverse order of allocating them to safely free them.
CVE-2023-54202: In the Linux kernel, the following vulnerability has been resolved: drm/i915: fix race condition UAF in i915_perf_add_config_ioctl Userspace can guess the id value and try to race oa_config object creation with config remove, resulting in a use-after-free if we dereference the object after unlocking the metrics_lock. For that reason, unlocking the metrics_lock must be done after we are done dereferencing the object. [tursulin: Manually added stable tag.] (cherry picked from commit 49f6f6483b652108bcb73accd0204a464b922395)
CVE-2023-54237: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix potential panic dues to unprotected smc_llc_srv_add_link() There is a certain chance to trigger the following panic: PID: 5900 TASK: ffff88c1c8af4100 CPU: 1 COMMAND: "kworker/1:48" #0 [ffff9456c1cc79a0] machine_kexec at ffffffff870665b7 #1 [ffff9456c1cc79f0] __crash_kexec at ffffffff871b4c7a #2 [ffff9456c1cc7ab0] crash_kexec at ffffffff871b5b60 #3 [ffff9456c1cc7ac0] oops_end at ffffffff87026ce7 #4 [ffff9456c1cc7ae0] page_fault_oops at ffffffff87075715 #5 [ffff9456c1cc7b58] exc_page_fault at ffffffff87ad0654 #6 [ffff9456c1cc7b80] asm_exc_page_fault at ffffffff87c00b62 [exception RIP: ib_alloc_mr+19] RIP: ffffffffc0c9cce3 RSP: ffff9456c1cc7c38 RFLAGS: 00010202 RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000004 RDX: 0000000000000010 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff88c1ea281d00 R8: 000000020a34ffff R9: ffff88c1350bbb20 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000010 R14: ffff88c1ab040a50 R15: ffff88c1ea281d00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffff9456c1cc7c60] smc_ib_get_memory_region at ffffffffc0aff6df [smc] #8 [ffff9456c1cc7c88] smcr_buf_map_link at ffffffffc0b0278c [smc] #9 [ffff9456c1cc7ce0] __smc_buf_create at ffffffffc0b03586 [smc] The reason here is that when the server tries to create a second link, smc_llc_srv_add_link() has no protection and may add a new link to link group. This breaks the security environment protected by llc_conf_mutex.
CVE-2023-54251: In the Linux kernel, the following vulnerability has been resolved: net/sched: taprio: Limit TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME to INT_MAX. syzkaller found zero division error [0] in div_s64_rem() called from get_cycle_time_elapsed(), where sched->cycle_time is the divisor. We have tests in parse_taprio_schedule() so that cycle_time will never be 0, and actually cycle_time is not 0 in get_cycle_time_elapsed(). The problem is that the types of divisor are different; cycle_time is s64, but the argument of div_s64_rem() is s32. syzkaller fed this input and 0x100000000 is cast to s32 to be 0. @TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME={0xc, 0x8, 0x100000000} We use s64 for cycle_time to cast it to ktime_t, so let's keep it and set max for cycle_time. While at it, we prevent overflow in setup_txtime() and add another test in parse_taprio_schedule() to check if cycle_time overflows. Also, we add a new tdc test case for this issue. [0]: divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 1 PID: 103 Comm: kworker/1:3 Not tainted 6.5.0-rc1-00330-g60cc1f7d0605 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:div_s64_rem include/linux/math64.h:42 [inline] RIP: 0010:get_cycle_time_elapsed net/sched/sch_taprio.c:223 [inline] RIP: 0010:find_entry_to_transmit+0x252/0x7e0 net/sched/sch_taprio.c:344 Code: 3c 02 00 0f 85 5e 05 00 00 48 8b 4c 24 08 4d 8b bd 40 01 00 00 48 8b 7c 24 48 48 89 c8 4c 29 f8 48 63 f7 48 99 48 89 74 24 70 <48> f7 fe 48 29 d1 48 8d 04 0f 49 89 cc 48 89 44 24 20 49 8d 85 10 RSP: 0018:ffffc90000acf260 EFLAGS: 00010206 RAX: 177450e0347560cf RBX: 0000000000000000 RCX: 177450e0347560cf RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000100000000 RBP: 0000000000000056 R08: 0000000000000000 R09: ffffed10020a0934 R10: ffff8880105049a7 R11: ffff88806cf3a520 R12: ffff888010504800 R13: ffff88800c00d800 R14: ffff8880105049a0 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88806cf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0edf84f0e8 CR3: 000000000d73c002 CR4: 0000000000770ee0 PKRU: 55555554 Call Trace: <TASK> get_packet_txtime net/sched/sch_taprio.c:508 [inline] taprio_enqueue_one+0x900/0xff0 net/sched/sch_taprio.c:577 taprio_enqueue+0x378/0xae0 net/sched/sch_taprio.c:658 dev_qdisc_enqueue+0x46/0x170 net/core/dev.c:3732 __dev_xmit_skb net/core/dev.c:3821 [inline] __dev_queue_xmit+0x1b2f/0x3000 net/core/dev.c:4169 dev_queue_xmit include/linux/netdevice.h:3088 [inline] neigh_resolve_output net/core/neighbour.c:1552 [inline] neigh_resolve_output+0x4a7/0x780 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:544 [inline] ip6_finish_output2+0x924/0x17d0 net/ipv6/ip6_output.c:135 __ip6_finish_output+0x620/0xaa0 net/ipv6/ip6_output.c:196 ip6_finish_output net/ipv6/ip6_output.c:207 [inline] NF_HOOK_COND include/linux/netfilter.h:292 [inline] ip6_output+0x206/0x410 net/ipv6/ip6_output.c:228 dst_output include/net/dst.h:458 [inline] NF_HOOK.constprop.0+0xea/0x260 include/linux/netfilter.h:303 ndisc_send_skb+0x872/0xe80 net/ipv6/ndisc.c:508 ndisc_send_ns+0xb5/0x130 net/ipv6/ndisc.c:666 addrconf_dad_work+0xc14/0x13f0 net/ipv6/addrconf.c:4175 process_one_work+0x92c/0x13a0 kernel/workqueue.c:2597 worker_thread+0x60f/0x1240 kernel/workqueue.c:2748 kthread+0x2fe/0x3f0 kernel/kthread.c:389 ret_from_fork+0x2c/0x50 arch/x86/entry/entry_64.S:308 </TASK> Modules linked in:
CVE-2023-54263: In the Linux kernel, the following vulnerability has been resolved: drm/nouveau/kms/nv50-: init hpd_irq_lock for PIOR DP Fixes OOPS on boards with ANX9805 DP encoders.
CVE-2023-54271: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:_raw_spin_lock+0x17/0x30 Code: be 01 02 00 00 e8 79 38 39 ff 31 d2 89 d0 5d c3 0f 1f 00 0f 1f 44 00 00 55 48 89 e5 65 ff 05 48 d0 34 7e b9 01 00 00 00 31 c0 <f0> 0f b1 0f 75 02 5d c3 89 c6 e8 ea 04 00 00 5d c3 0f 1f 84 00 00 RSP: 0018:ffffc900023b3d40 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 00000000000000e0 RCX: 0000000000000001 RDX: ffffc900023b3d20 RSI: ffffc900023b3cf0 RDI: 00000000000000e0 RBP: ffffc900023b3d40 R08: ffffc900023b3c10 R09: 0000000000000003 R10: 0000000000000064 R11: 000000000000000a R12: ffff888102337000 R13: fffffffffffffff2 R14: ffff88810af408c8 R15: ffff8881070c3600 FS: 00007faaaf364fc0(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e0 CR3: 00000001097b1000 CR4: 0000000000350ea0 Call Trace: <TASK> ioc_weight_write+0x13d/0x410 cgroup_file_write+0x7a/0x130 kernfs_fop_write_iter+0xf5/0x170 vfs_write+0x298/0x370 ksys_write+0x5f/0xb0 __x64_sys_write+0x1b/0x20 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 This happens because iocg->ioc is NULL. The field is initialized by ioc_pd_init() and never cleared. The NULL deref is caused by blkcg_activate_policy() installing blkg_policy_data before initializing it. blkcg_activate_policy() was doing the following: 1. Allocate pd's for all existing blkg's and install them in blkg->pd[]. 2. Initialize all pd's. 3. Online all pd's. blkcg_activate_policy() only grabs the queue_lock and may release and re-acquire the lock as allocation may need to sleep. ioc_weight_write() grabs blkcg->lock and iterates all its blkg's. The two can race and if ioc_weight_write() runs during #1 or between #1 and #2, it can encounter a pd which is not initialized yet, leading to crash. The crash can be reproduced with the following script: #!/bin/bash echo +io > /sys/fs/cgroup/cgroup.subtree_control systemd-run --unit touch-sda --scope dd if=/dev/sda of=/dev/null bs=1M count=1 iflag=direct echo 100 > /sys/fs/cgroup/system.slice/io.weight bash -c "echo '8:0 enable=1' > /sys/fs/cgroup/io.cost.qos" & sleep .2 echo 100 > /sys/fs/cgroup/system.slice/io.weight with the following patch applied: > diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c > index fc49be622e05..38d671d5e10c 100644 > --- a/block/blk-cgroup.c > +++ b/block/blk-cgroup.c > @@ -1553,6 +1553,12 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) > pd->online = false; > } > > + if (system_state == SYSTEM_RUNNING) { > + spin_unlock_irq(&q->queue_lock); > + ssleep(1); > + spin_lock_irq(&q->queue_lock); > + } > + > /* all allocated, init in the same order */ > if (pol->pd_init_fn) > list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) I don't see a reason why all pd's should be allocated, initialized and onlined together. The only ordering requirement is that parent blkgs to be initialized and onlined before children, which is guaranteed from the walking order. Let's fix the bug by allocating, initializing and onlining pd for each blkg and holding blkcg->lock over initialization and onlining. This ensures that an installed blkg is always fully initialized and onlined removing the the race window.
CVE-2023-54287: In the Linux kernel, the following vulnerability has been resolved: tty: serial: imx: disable Ageing Timer interrupt request irq There maybe pending USR interrupt before requesting irq, however uart_add_one_port has not executed, so there will be kernel panic: [ 0.795668] Unable to handle kernel NULL pointer dereference at virtual addre ss 0000000000000080 [ 0.802701] Mem abort info: [ 0.805367] ESR = 0x0000000096000004 [ 0.808950] EC = 0x25: DABT (current EL), IL = 32 bits [ 0.814033] SET = 0, FnV = 0 [ 0.816950] EA = 0, S1PTW = 0 [ 0.819950] FSC = 0x04: level 0 translation fault [ 0.824617] Data abort info: [ 0.827367] ISV = 0, ISS = 0x00000004 [ 0.831033] CM = 0, WnR = 0 [ 0.833866] [0000000000000080] user address but active_mm is swapper [ 0.839951] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [ 0.845953] Modules linked in: [ 0.848869] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.1.1+g56321e101aca #1 [ 0.855617] Hardware name: Freescale i.MX8MP EVK (DT) [ 0.860452] pstate: 000000c5 (nzcv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 0.867117] pc : __imx_uart_rxint.constprop.0+0x11c/0x2c0 [ 0.872283] lr : imx_uart_int+0xf8/0x1ec The issue only happends in the inmate linux when Jailhouse hypervisor enabled. The test procedure is: while true; do jailhouse enable imx8mp.cell jailhouse cell linux xxxx sleep 10 jailhouse cell destroy 1 jailhouse disable sleep 5 done And during the upper test, press keys to the 2nd linux console. When `jailhouse cell destroy 1`, the 2nd linux has no chance to put the uart to a quiese state, so USR1/2 may has pending interrupts. Then when `jailhosue cell linux xx` to start 2nd linux again, the issue trigger. In order to disable irqs before requesting them, both UCR1 and UCR2 irqs should be disabled, so here fix that, disable the Ageing Timer interrupt in UCR2 as UCR1 does.
CVE-2023-54324: In the Linux kernel, the following vulnerability has been resolved: dm: fix a race condition in retrieve_deps There's a race condition in the multipath target when retrieve_deps races with multipath_message calling dm_get_device and dm_put_device. retrieve_deps walks the list of open devices without holding any lock but multipath may add or remove devices to the list while it is running. The end result may be memory corruption or use-after-free memory access. See this description of a UAF with multipath_message(): https://listman.redhat.com/archives/dm-devel/2022-October/052373.html Fix this bug by introducing a new rw semaphore "devices_lock". We grab devices_lock for read in retrieve_deps and we grab it for write in dm_get_device and dm_put_device.
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-21823: Hardware logic with insecure de-synchronization in Intel(R) DSA and Intel(R) IAA for some Intel(R) 4th or 5th generation Xeon(R) processors may allow an authorized user to potentially enable escalation of privilege local access
CVE-2024-23307: Integer Overflow or Wraparound vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (md, raid, raid5 modules) allows Forced Integer Overflow.
CVE-2024-24855: A race condition was found in the Linux kernel's scsi device driver in lpfc_unregister_fcf_rescan() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-25740: A memory leak flaw was found in the UBI driver in drivers/mtd/ubi/attach.c in the Linux kernel through 6.7.4 for UBI_IOCATT, because kobj->name is not released.
CVE-2024-26583: In the Linux kernel, the following vulnerability has been resolved: tls: fix race between async notify and socket close The submitting thread (one which called recvmsg/sendmsg) may exit as soon as the async crypto handler calls complete() so any code past that point risks touching already freed data. Try to avoid the locking and extra flags altogether. Have the main thread hold an extra reference, this way we can depend solely on the atomic ref counter for synchronization. Don't futz with reiniting the completion, either, we are now tightly controlling when completion fires.
CVE-2024-26584: In the Linux kernel, the following vulnerability has been resolved: net: tls: handle backlogging of crypto requests Since we're setting the CRYPTO_TFM_REQ_MAY_BACKLOG flag on our requests to the crypto API, crypto_aead_{encrypt,decrypt} can return -EBUSY instead of -EINPROGRESS in valid situations. For example, when the cryptd queue for AESNI is full (easy to trigger with an artificially low cryptd.cryptd_max_cpu_qlen), requests will be enqueued to the backlog but still processed. In that case, the async callback will also be called twice: first with err == -EINPROGRESS, which it seems we can just ignore, then with err == 0. Compared to Sabrina's original patch this version uses the new tls_*crypt_async_wait() helpers and converts the EBUSY to EINPROGRESS to avoid having to modify all the error handling paths. The handling is identical.
CVE-2024-26585: In the Linux kernel, the following vulnerability has been resolved: tls: fix race between tx work scheduling and socket close Similarly to previous commit, the submitting thread (recvmsg/sendmsg) may exit as soon as the async crypto handler calls complete(). Reorder scheduling the work before calling complete(). This seems more logical in the first place, as it's the inverse order of what the submitting thread will do.
CVE-2024-26589: In the Linux kernel, the following vulnerability has been resolved: bpf: Reject variable offset alu on PTR_TO_FLOW_KEYS For PTR_TO_FLOW_KEYS, check_flow_keys_access() only uses fixed off for validation. However, variable offset ptr alu is not prohibited for this ptr kind. So the variable offset is not checked. The following prog is accepted: func#0 @0 0: R1=ctx() R10=fp0 0: (bf) r6 = r1 ; R1=ctx() R6_w=ctx() 1: (79) r7 = *(u64 *)(r6 +144) ; R6_w=ctx() R7_w=flow_keys() 2: (b7) r8 = 1024 ; R8_w=1024 3: (37) r8 /= 1 ; R8_w=scalar() 4: (57) r8 &= 1024 ; R8_w=scalar(smin=smin32=0, smax=umax=smax32=umax32=1024,var_off=(0x0; 0x400)) 5: (0f) r7 += r8 mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1 mark_precise: frame0: regs=r8 stack= before 4: (57) r8 &= 1024 mark_precise: frame0: regs=r8 stack= before 3: (37) r8 /= 1 mark_precise: frame0: regs=r8 stack= before 2: (b7) r8 = 1024 6: R7_w=flow_keys(smin=smin32=0,smax=umax=smax32=umax32=1024,var_off =(0x0; 0x400)) R8_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=1024, var_off=(0x0; 0x400)) 6: (79) r0 = *(u64 *)(r7 +0) ; R0_w=scalar() 7: (95) exit This prog loads flow_keys to r7, and adds the variable offset r8 to r7, and finally causes out-of-bounds access: BUG: unable to handle page fault for address: ffffc90014c80038 [...] Call Trace: <TASK> bpf_dispatcher_nop_func include/linux/bpf.h:1231 [inline] __bpf_prog_run include/linux/filter.h:651 [inline] bpf_prog_run include/linux/filter.h:658 [inline] bpf_prog_run_pin_on_cpu include/linux/filter.h:675 [inline] bpf_flow_dissect+0x15f/0x350 net/core/flow_dissector.c:991 bpf_prog_test_run_flow_dissector+0x39d/0x620 net/bpf/test_run.c:1359 bpf_prog_test_run kernel/bpf/syscall.c:4107 [inline] __sys_bpf+0xf8f/0x4560 kernel/bpf/syscall.c:5475 __do_sys_bpf kernel/bpf/syscall.c:5561 [inline] __se_sys_bpf kernel/bpf/syscall.c:5559 [inline] __x64_sys_bpf+0x73/0xb0 kernel/bpf/syscall.c:5559 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b Fix this by rejecting ptr alu with variable offset on flow_keys. Applying the patch rejects the program with "R7 pointer arithmetic on flow_keys prohibited".
CVE-2024-26595: In the Linux kernel, the following vulnerability has been resolved: mlxsw: spectrum_acl_tcam: Fix NULL pointer dereference in error path When calling mlxsw_sp_acl_tcam_region_destroy() from an error path after failing to attach the region to an ACL group, we hit a NULL pointer dereference upon 'region->group->tcam' [1]. Fix by retrieving the 'tcam' pointer using mlxsw_sp_acl_to_tcam(). [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] RIP: 0010:mlxsw_sp_acl_tcam_region_destroy+0xa0/0xd0 [...] Call Trace: mlxsw_sp_acl_tcam_vchunk_get+0x88b/0xa20 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0 mlxsw_sp_acl_rule_add+0x47/0x240 mlxsw_sp_flower_replace+0x1a9/0x1d0 tc_setup_cb_add+0xdc/0x1c0 fl_hw_replace_filter+0x146/0x1f0 fl_change+0xc17/0x1360 tc_new_tfilter+0x472/0xb90 rtnetlink_rcv_msg+0x313/0x3b0 netlink_rcv_skb+0x58/0x100 netlink_unicast+0x244/0x390 netlink_sendmsg+0x1e4/0x440 ____sys_sendmsg+0x164/0x260 ___sys_sendmsg+0x9a/0xe0 __sys_sendmsg+0x7a/0xc0 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0x6b
CVE-2024-26607: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: sii902x: Fix probing race issue A null pointer dereference crash has been observed rarely on TI platforms using sii9022 bridge: [ 53.271356] sii902x_get_edid+0x34/0x70 [sii902x] [ 53.276066] sii902x_bridge_get_edid+0x14/0x20 [sii902x] [ 53.281381] drm_bridge_get_edid+0x20/0x34 [drm] [ 53.286305] drm_bridge_connector_get_modes+0x8c/0xcc [drm_kms_helper] [ 53.292955] drm_helper_probe_single_connector_modes+0x190/0x538 [drm_kms_helper] [ 53.300510] drm_client_modeset_probe+0x1f0/0xbd4 [drm] [ 53.305958] __drm_fb_helper_initial_config_and_unlock+0x50/0x510 [drm_kms_helper] [ 53.313611] drm_fb_helper_initial_config+0x48/0x58 [drm_kms_helper] [ 53.320039] drm_fbdev_dma_client_hotplug+0x84/0xd4 [drm_dma_helper] [ 53.326401] drm_client_register+0x5c/0xa0 [drm] [ 53.331216] drm_fbdev_dma_setup+0xc8/0x13c [drm_dma_helper] [ 53.336881] tidss_probe+0x128/0x264 [tidss] [ 53.341174] platform_probe+0x68/0xc4 [ 53.344841] really_probe+0x188/0x3c4 [ 53.348501] __driver_probe_device+0x7c/0x16c [ 53.352854] driver_probe_device+0x3c/0x10c [ 53.357033] __device_attach_driver+0xbc/0x158 [ 53.361472] bus_for_each_drv+0x88/0xe8 [ 53.365303] __device_attach+0xa0/0x1b4 [ 53.369135] device_initial_probe+0x14/0x20 [ 53.373314] bus_probe_device+0xb0/0xb4 [ 53.377145] deferred_probe_work_func+0xcc/0x124 [ 53.381757] process_one_work+0x1f0/0x518 [ 53.385770] worker_thread+0x1e8/0x3dc [ 53.389519] kthread+0x11c/0x120 [ 53.392750] ret_from_fork+0x10/0x20 The issue here is as follows: - tidss probes, but is deferred as sii902x is still missing. - sii902x starts probing and enters sii902x_init(). - sii902x calls drm_bridge_add(). Now the sii902x bridge is ready from DRM's perspective. - sii902x calls sii902x_audio_codec_init() and platform_device_register_data() - The registration of the audio platform device causes probing of the deferred devices. - tidss probes, which eventually causes sii902x_bridge_get_edid() to be called. - sii902x_bridge_get_edid() tries to use the i2c to read the edid. However, the sii902x driver has not set up the i2c part yet, leading to the crash. Fix this by moving the drm_bridge_add() to the end of the sii902x_init(), which is also at the very end of sii902x_probe().
CVE-2024-26656: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix use-after-free bug The bug can be triggered by sending a single amdgpu_gem_userptr_ioctl to the AMDGPU DRM driver on any ASICs with an invalid address and size. The bug was reported by Joonkyo Jung <joonkyoj@yonsei.ac.kr>. For example the following code: static void Syzkaller1(int fd) { struct drm_amdgpu_gem_userptr arg; int ret; arg.addr = 0xffffffffffff0000; arg.size = 0x80000000; /*2 Gb*/ arg.flags = 0x7; ret = drmIoctl(fd, 0xc1186451/*amdgpu_gem_userptr_ioctl*/, &arg); } Due to the address and size are not valid there is a failure in amdgpu_hmm_register->mmu_interval_notifier_insert->__mmu_interval_notifier_insert-> check_shl_overflow, but we even the amdgpu_hmm_register failure we still call amdgpu_hmm_unregister into amdgpu_gem_object_free which causes access to a bad address. The following stack is below when the issue is reproduced when Kazan is enabled: [ +0.000014] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.000009] RIP: 0010:mmu_interval_notifier_remove+0x327/0x340 [ +0.000017] Code: ff ff 49 89 44 24 08 48 b8 00 01 00 00 00 00 ad de 4c 89 f7 49 89 47 40 48 83 c0 22 49 89 47 48 e8 ce d1 2d 01 e9 32 ff ff ff <0f> 0b e9 16 ff ff ff 4c 89 ef e8 fa 14 b3 ff e9 36 ff ff ff e8 80 [ +0.000014] RSP: 0018:ffffc90002657988 EFLAGS: 00010246 [ +0.000013] RAX: 0000000000000000 RBX: 1ffff920004caf35 RCX: ffffffff8160565b [ +0.000011] RDX: dffffc0000000000 RSI: 0000000000000004 RDI: ffff8881a9f78260 [ +0.000010] RBP: ffffc90002657a70 R08: 0000000000000001 R09: fffff520004caf25 [ +0.000010] R10: 0000000000000003 R11: ffffffff8161d1d6 R12: ffff88810e988c00 [ +0.000010] R13: ffff888126fb5a00 R14: ffff88810e988c0c R15: ffff8881a9f78260 [ +0.000011] FS: 00007ff9ec848540(0000) GS:ffff8883cc880000(0000) knlGS:0000000000000000 [ +0.000012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000010] CR2: 000055b3f7e14328 CR3: 00000001b5770000 CR4: 0000000000350ef0 [ +0.000010] Call Trace: [ +0.000006] <TASK> [ +0.000007] ? show_regs+0x6a/0x80 [ +0.000018] ? __warn+0xa5/0x1b0 [ +0.000019] ? mmu_interval_notifier_remove+0x327/0x340 [ +0.000018] ? report_bug+0x24a/0x290 [ +0.000022] ? handle_bug+0x46/0x90 [ +0.000015] ? exc_invalid_op+0x19/0x50 [ +0.000016] ? asm_exc_invalid_op+0x1b/0x20 [ +0.000017] ? kasan_save_stack+0x26/0x50 [ +0.000017] ? mmu_interval_notifier_remove+0x23b/0x340 [ +0.000019] ? mmu_interval_notifier_remove+0x327/0x340 [ +0.000019] ? mmu_interval_notifier_remove+0x23b/0x340 [ +0.000020] ? __pfx_mmu_interval_notifier_remove+0x10/0x10 [ +0.000017] ? kasan_save_alloc_info+0x1e/0x30 [ +0.000018] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? __kasan_kmalloc+0xb1/0xc0 [ +0.000018] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? __kasan_check_read+0x11/0x20 [ +0.000020] amdgpu_hmm_unregister+0x34/0x50 [amdgpu] [ +0.004695] amdgpu_gem_object_free+0x66/0xa0 [amdgpu] [ +0.004534] ? __pfx_amdgpu_gem_object_free+0x10/0x10 [amdgpu] [ +0.004291] ? do_syscall_64+0x5f/0xe0 [ +0.000023] ? srso_return_thunk+0x5/0x5f [ +0.000017] drm_gem_object_free+0x3b/0x50 [drm] [ +0.000489] amdgpu_gem_userptr_ioctl+0x306/0x500 [amdgpu] [ +0.004295] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004270] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? __this_cpu_preempt_check+0x13/0x20 [ +0.000015] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? sysvec_apic_timer_interrupt+0x57/0xc0 [ +0.000020] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 [ +0.000022] ? drm_ioctl_kernel+0x17b/0x1f0 [drm] [ +0.000496] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004272] ? drm_ioctl_kernel+0x190/0x1f0 [drm] [ +0.000492] drm_ioctl_kernel+0x140/0x1f0 [drm] [ +0.000497] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004297] ? __pfx_drm_ioctl_kernel+0x10/0x10 [d ---truncated---
CVE-2024-26661: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL test for 'timing generator' in 'dcn21_set_pipe()' In "u32 otg_inst = pipe_ctx->stream_res.tg->inst;" pipe_ctx->stream_res.tg could be NULL, it is relying on the caller to ensure the tg is not NULL.
CVE-2024-26662: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix 'panel_cntl' could be null in 'dcn21_set_backlight_level()' 'panel_cntl' structure used to control the display panel could be null, dereferencing it could lead to a null pointer access. Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn21/dcn21_hwseq.c:269 dcn21_set_backlight_level() error: we previously assumed 'panel_cntl' could be null (see line 250)
CVE-2024-26668: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_limit: reject configurations that cause integer overflow Reject bogus configs where internal token counter wraps around. This only occurs with very very large requests, such as 17gbyte/s. Its better to reject this rather than having incorrect ratelimit.
CVE-2024-26669: In the Linux kernel, the following vulnerability has been resolved: net/sched: flower: Fix chain template offload When a qdisc is deleted from a net device the stack instructs the underlying driver to remove its flow offload callback from the associated filter block using the 'FLOW_BLOCK_UNBIND' command. The stack then continues to replay the removal of the filters in the block for this driver by iterating over the chains in the block and invoking the 'reoffload' operation of the classifier being used. In turn, the classifier in its 'reoffload' operation prepares and emits a 'FLOW_CLS_DESTROY' command for each filter. However, the stack does not do the same for chain templates and the underlying driver never receives a 'FLOW_CLS_TMPLT_DESTROY' command when a qdisc is deleted. This results in a memory leak [1] which can be reproduced using [2]. Fix by introducing a 'tmplt_reoffload' operation and have the stack invoke it with the appropriate arguments as part of the replay. Implement the operation in the sole classifier that supports chain templates (flower) by emitting the 'FLOW_CLS_TMPLT_{CREATE,DESTROY}' command based on whether a flow offload callback is being bound to a filter block or being unbound from one. As far as I can tell, the issue happens since cited commit which reordered tcf_block_offload_unbind() before tcf_block_flush_all_chains() in __tcf_block_put(). The order cannot be reversed as the filter block is expected to be freed after flushing all the chains. [1] unreferenced object 0xffff888107e28800 (size 2048): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): b1 a6 7c 11 81 88 ff ff e0 5b b3 10 81 88 ff ff ..|......[...... 01 00 00 00 00 00 00 00 e0 aa b0 84 ff ff ff ff ................ backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab374e>] __kmalloc+0x4e/0x90 [<ffffffff832aec6d>] mlxsw_sp_acl_ruleset_get+0x34d/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80 [<ffffffff8379d29a>] ___sys_sendmsg+0x13a/0x1e0 [<ffffffff8379d50c>] __sys_sendmsg+0x11c/0x1f0 [<ffffffff843b9ce0>] do_syscall_64+0x40/0xe0 unreferenced object 0xffff88816d2c0400 (size 1024): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): 40 00 00 00 00 00 00 00 57 f6 38 be 00 00 00 00 @.......W.8..... 10 04 2c 6d 81 88 ff ff 10 04 2c 6d 81 88 ff ff ..,m......,m.... backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab36c1>] __kmalloc_node+0x51/0x90 [<ffffffff81a8ed96>] kvmalloc_node+0xa6/0x1f0 [<ffffffff82827d03>] bucket_table_alloc.isra.0+0x83/0x460 [<ffffffff82828d2b>] rhashtable_init+0x43b/0x7c0 [<ffffffff832aed48>] mlxsw_sp_acl_ruleset_get+0x428/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80 [2] # tc qdisc add dev swp1 clsact # tc chain add dev swp1 ingress proto ip chain 1 flower dst_ip 0.0.0.0/32 # tc qdisc del dev ---truncated---
CVE-2024-26672: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix variable 'mca_funcs' dereferenced before NULL check in 'amdgpu_mca_smu_get_mca_entry()' Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c:377 amdgpu_mca_smu_get_mca_entry() warn: variable dereferenced before check 'mca_funcs' (see line 368) 357 int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, 358 int idx, struct mca_bank_entry *entry) 359 { 360 const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; 361 int count; 362 363 switch (type) { 364 case AMDGPU_MCA_ERROR_TYPE_UE: 365 count = mca_funcs->max_ue_count; mca_funcs is dereferenced here. 366 break; 367 case AMDGPU_MCA_ERROR_TYPE_CE: 368 count = mca_funcs->max_ce_count; mca_funcs is dereferenced here. 369 break; 370 default: 371 return -EINVAL; 372 } 373 374 if (idx >= count) 375 return -EINVAL; 376 377 if (mca_funcs && mca_funcs->mca_get_mca_entry) ^^^^^^^^^ Checked too late!
CVE-2024-26677: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix delayed ACKs to not set the reference serial number Fix the construction of delayed ACKs to not set the reference serial number as they can't be used as an RTT reference.
CVE-2024-26680: In the Linux kernel, the following vulnerability has been resolved: net: atlantic: Fix DMA mapping for PTP hwts ring Function aq_ring_hwts_rx_alloc() maps extra AQ_CFG_RXDS_DEF bytes for PTP HWTS ring but then generic aq_ring_free() does not take this into account. Create and use a specific function to free HWTS ring to fix this issue. Trace: [ 215.351607] ------------[ cut here ]------------ [ 215.351612] DMA-API: atlantic 0000:4b:00.0: device driver frees DMA memory with different size [device address=0x00000000fbdd0000] [map size=34816 bytes] [unmap size=32768 bytes] [ 215.351635] WARNING: CPU: 33 PID: 10759 at kernel/dma/debug.c:988 check_unmap+0xa6f/0x2360 ... [ 215.581176] Call Trace: [ 215.583632] <TASK> [ 215.585745] ? show_trace_log_lvl+0x1c4/0x2df [ 215.590114] ? show_trace_log_lvl+0x1c4/0x2df [ 215.594497] ? debug_dma_free_coherent+0x196/0x210 [ 215.599305] ? check_unmap+0xa6f/0x2360 [ 215.603147] ? __warn+0xca/0x1d0 [ 215.606391] ? check_unmap+0xa6f/0x2360 [ 215.610237] ? report_bug+0x1ef/0x370 [ 215.613921] ? handle_bug+0x3c/0x70 [ 215.617423] ? exc_invalid_op+0x14/0x50 [ 215.621269] ? asm_exc_invalid_op+0x16/0x20 [ 215.625480] ? check_unmap+0xa6f/0x2360 [ 215.629331] ? mark_lock.part.0+0xca/0xa40 [ 215.633445] debug_dma_free_coherent+0x196/0x210 [ 215.638079] ? __pfx_debug_dma_free_coherent+0x10/0x10 [ 215.643242] ? slab_free_freelist_hook+0x11d/0x1d0 [ 215.648060] dma_free_attrs+0x6d/0x130 [ 215.651834] aq_ring_free+0x193/0x290 [atlantic] [ 215.656487] aq_ptp_ring_free+0x67/0x110 [atlantic] ... [ 216.127540] ---[ end trace 6467e5964dd2640b ]--- [ 216.132160] DMA-API: Mapped at: [ 216.132162] debug_dma_alloc_coherent+0x66/0x2f0 [ 216.132165] dma_alloc_attrs+0xf5/0x1b0 [ 216.132168] aq_ring_hwts_rx_alloc+0x150/0x1f0 [atlantic] [ 216.132193] aq_ptp_ring_alloc+0x1bb/0x540 [atlantic] [ 216.132213] aq_nic_init+0x4a1/0x760 [atlantic]
CVE-2024-26691: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Fix circular locking dependency The rule inside kvm enforces that the vcpu->mutex is taken *inside* kvm->lock. The rule is violated by the pkvm_create_hyp_vm() which acquires the kvm->lock while already holding the vcpu->mutex lock from kvm_vcpu_ioctl(). Avoid the circular locking dependency altogether by protecting the hyp vm handle with the config_lock, much like we already do for other forms of VM-scoped data.
CVE-2024-26700: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix MST Null Ptr for RV The change try to fix below error specific to RV platform: BUG: kernel NULL pointer dereference, address: 0000000000000008 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2 Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022 RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? plist_add+0xbe/0x100 ? exc_page_fault+0x7c/0x180 ? asm_exc_page_fault+0x26/0x30 ? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] ? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] ? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] drm_atomic_check_only+0x5c5/0xa40 drm_mode_atomic_ioctl+0x76e/0xbc0 ? _copy_to_user+0x25/0x30 ? drm_ioctl+0x296/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 drm_ioctl_kernel+0xcd/0x170 drm_ioctl+0x26d/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 amdgpu_drm_ioctl+0x4e/0x90 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] __x64_sys_ioctl+0x94/0xd0 do_syscall_64+0x60/0x90 ? do_syscall_64+0x6c/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f4dad17f76f Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c> RSP: 002b:00007ffd9ae859f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 000055e255a55900 RCX: 00007f4dad17f76f RDX: 00007ffd9ae85a90 RSI: 00000000c03864bc RDI: 000000000000000b RBP: 00007ffd9ae85a90 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c03864bc R13: 000000000000000b R14: 000055e255a7fc60 R15: 000055e255a01eb0 </TASK> Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device ccm cmac algif_hash algif_skcipher af_alg joydev mousedev bnep > typec libphy k10temp ipmi_msghandler roles i2c_scmi acpi_cpufreq mac_hid nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_mas> CR2: 0000000000000008 ---[ end trace 0000000000000000 ]--- RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000 ---truncated---
CVE-2024-26715: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: gadget: Fix NULL pointer dereference in dwc3_gadget_suspend In current scenario if Plug-out and Plug-In performed continuously there could be a chance while checking for dwc->gadget_driver in dwc3_gadget_suspend, a NULL pointer dereference may occur. Call Stack: CPU1: CPU2: gadget_unbind_driver dwc3_suspend_common dwc3_gadget_stop dwc3_gadget_suspend dwc3_disconnect_gadget CPU1 basically clears the variable and CPU2 checks the variable. Consider CPU1 is running and right before gadget_driver is cleared and in parallel CPU2 executes dwc3_gadget_suspend where it finds dwc->gadget_driver which is not NULL and resumes execution and then CPU1 completes execution. CPU2 executes dwc3_disconnect_gadget where it checks dwc->gadget_driver is already NULL because of which the NULL pointer deference occur.
CVE-2024-26718: In the Linux kernel, the following vulnerability has been resolved: dm-crypt, dm-verity: disable tasklets Tasklets have an inherent problem with memory corruption. The function tasklet_action_common calls tasklet_trylock, then it calls the tasklet callback and then it calls tasklet_unlock. If the tasklet callback frees the structure that contains the tasklet or if it calls some code that may free it, tasklet_unlock will write into free memory. The commits 8e14f610159d and d9a02e016aaf try to fix it for dm-crypt, but it is not a sufficient fix and the data corruption can still happen [1]. There is no fix for dm-verity and dm-verity will write into free memory with every tasklet-processed bio. There will be atomic workqueues implemented in the kernel 6.9 [2]. They will have better interface and they will not suffer from the memory corruption problem. But we need something that stops the memory corruption now and that can be backported to the stable kernels. So, I'm proposing this commit that disables tasklets in both dm-crypt and dm-verity. This commit doesn't remove the tasklet support, because the tasklet code will be reused when atomic workqueues will be implemented. [1] https://lore.kernel.org/all/d390d7ee-f142-44d3-822a-87949e14608b@suse.de/T/ [2] https://lore.kernel.org/lkml/20240130091300.2968534-1-tj@kernel.org/
CVE-2024-26726: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't drop extent_map for free space inode on write error While running the CI for an unrelated change I hit the following panic with generic/648 on btrfs_holes_spacecache. assertion failed: block_start != EXTENT_MAP_HOLE, in fs/btrfs/extent_io.c:1385 ------------[ cut here ]------------ kernel BUG at fs/btrfs/extent_io.c:1385! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 2695096 Comm: fsstress Kdump: loaded Tainted: G W 6.8.0-rc2+ #1 RIP: 0010:__extent_writepage_io.constprop.0+0x4c1/0x5c0 Call Trace: <TASK> extent_write_cache_pages+0x2ac/0x8f0 extent_writepages+0x87/0x110 do_writepages+0xd5/0x1f0 filemap_fdatawrite_wbc+0x63/0x90 __filemap_fdatawrite_range+0x5c/0x80 btrfs_fdatawrite_range+0x1f/0x50 btrfs_write_out_cache+0x507/0x560 btrfs_write_dirty_block_groups+0x32a/0x420 commit_cowonly_roots+0x21b/0x290 btrfs_commit_transaction+0x813/0x1360 btrfs_sync_file+0x51a/0x640 __x64_sys_fdatasync+0x52/0x90 do_syscall_64+0x9c/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 This happens because we fail to write out the free space cache in one instance, come back around and attempt to write it again. However on the second pass through we go to call btrfs_get_extent() on the inode to get the extent mapping. Because this is a new block group, and with the free space inode we always search the commit root to avoid deadlocking with the tree, we find nothing and return a EXTENT_MAP_HOLE for the requested range. This happens because the first time we try to write the space cache out we hit an error, and on an error we drop the extent mapping. This is normal for normal files, but the free space cache inode is special. We always expect the extent map to be correct. Thus the second time through we end up with a bogus extent map. Since we're deprecating this feature, the most straightforward way to fix this is to simply skip dropping the extent map range for this failed range. I shortened the test by using error injection to stress the area to make it easier to reproduce. With this patch in place we no longer panic with my error injection test.
CVE-2024-26740: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_mirred: use the backlog for mirred ingress The test Davide added in commit ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") hangs our testing VMs every 10 or so runs, with the familiar tcp_v4_rcv -> tcp_v4_rcv deadlock reported by lockdep. The problem as previously described by Davide (see Link) is that if we reverse flow of traffic with the redirect (egress -> ingress) we may reach the same socket which generated the packet. And we may still be holding its socket lock. The common solution to such deadlocks is to put the packet in the Rx backlog, rather than run the Rx path inline. Do that for all egress -> ingress reversals, not just once we started to nest mirred calls. In the past there was a concern that the backlog indirection will lead to loss of error reporting / less accurate stats. But the current workaround does not seem to address the issue.
CVE-2024-26756: In the Linux kernel, the following vulnerability has been resolved: md: Don't register sync_thread for reshape directly Currently, if reshape is interrupted, then reassemble the array will register sync_thread directly from pers->run(), in this case 'MD_RECOVERY_RUNNING' is set directly, however, there is no guarantee that md_do_sync() will be executed, hence stop_sync_thread() will hang because 'MD_RECOVERY_RUNNING' can't be cleared. Last patch make sure that md_do_sync() will set MD_RECOVERY_DONE, however, following hang can still be triggered by dm-raid test shell/lvconvert-raid-reshape.sh occasionally: [root@fedora ~]# cat /proc/1982/stack [<0>] stop_sync_thread+0x1ab/0x270 [md_mod] [<0>] md_frozen_sync_thread+0x5c/0xa0 [md_mod] [<0>] raid_presuspend+0x1e/0x70 [dm_raid] [<0>] dm_table_presuspend_targets+0x40/0xb0 [dm_mod] [<0>] __dm_destroy+0x2a5/0x310 [dm_mod] [<0>] dm_destroy+0x16/0x30 [dm_mod] [<0>] dev_remove+0x165/0x290 [dm_mod] [<0>] ctl_ioctl+0x4bb/0x7b0 [dm_mod] [<0>] dm_ctl_ioctl+0x11/0x20 [dm_mod] [<0>] vfs_ioctl+0x21/0x60 [<0>] __x64_sys_ioctl+0xb9/0xe0 [<0>] do_syscall_64+0xc6/0x230 [<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74 Meanwhile mddev->recovery is: MD_RECOVERY_RUNNING | MD_RECOVERY_INTR | MD_RECOVERY_RESHAPE | MD_RECOVERY_FROZEN Fix this problem by remove the code to register sync_thread directly from raid10 and raid5. And let md_check_recovery() to register sync_thread.
CVE-2024-26757: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore read-only array in md_check_recovery() Usually if the array is not read-write, md_check_recovery() won't register new sync_thread in the first place. And if the array is read-write and sync_thread is registered, md_set_readonly() will unregister sync_thread before setting the array read-only. md/raid follow this behavior hence there is no problem. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) array is read-only. dm-raid update super block: rs_update_sbs ro = mddev->ro mddev->ro = 0 -> set array read-write md_update_sb 2) register new sync thread concurrently. 3) dm-raid set array back to read-only: rs_update_sbs mddev->ro = ro 4) stop the array: raid_dtr md_stop stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 5) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 6) daemon thread can't unregister sync thread: md_check_recovery if (!md_is_rdwr(mddev) && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return; -> -> MD_RECOVERY_RUNNING can't be cleared, hence step 4 hang; The root cause is that dm-raid manipulate 'mddev->ro' by itself, however, dm-raid really should stop sync thread before setting the array read-only. Unfortunately, I need to read more code before I can refacter the handler of 'mddev->ro' in dm-raid, hence let's fix the problem the easy way for now to prevent dm-raid regression.
CVE-2024-26758: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore suspended array in md_check_recovery() mddev_suspend() never stop sync_thread, hence it doesn't make sense to ignore suspended array in md_check_recovery(), which might cause sync_thread can't be unregistered. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) suspend the array: raid_postsuspend mddev_suspend 2) stop the array: raid_dtr md_stop __md_stop_writes stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 3) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 4) daemon thread can't unregister sync thread: md_check_recovery if (mddev->suspended) return; -> return directly md_read_sync_thread clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); -> MD_RECOVERY_RUNNING can't be cleared, hence step 2 hang; This problem is not just related to dm-raid, fix it by ignoring suspended array in md_check_recovery(). And follow up patches will improve dm-raid better to frozen sync thread during suspend.
CVE-2024-26759: In the Linux kernel, the following vulnerability has been resolved: mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong@tencent.com: v4]
CVE-2024-26769: In the Linux kernel, the following vulnerability has been resolved: nvmet-fc: avoid deadlock on delete association path When deleting an association the shutdown path is deadlocking because we try to flush the nvmet_wq nested. Avoid this by deadlock by deferring the put work into its own work item.
CVE-2024-26792: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double free of anonymous device after snapshot creation failure When creating a snapshot we may do a double free of an anonymous device in case there's an error committing the transaction. The second free may result in freeing an anonymous device number that was allocated by some other subsystem in the kernel or another btrfs filesystem. The steps that lead to this: 1) At ioctl.c:create_snapshot() we allocate an anonymous device number and assign it to pending_snapshot->anon_dev; 2) Then we call btrfs_commit_transaction() and end up at transaction.c:create_pending_snapshot(); 3) There we call btrfs_get_new_fs_root() and pass it the anonymous device number stored in pending_snapshot->anon_dev; 4) btrfs_get_new_fs_root() frees that anonymous device number because btrfs_lookup_fs_root() returned a root - someone else did a lookup of the new root already, which could some task doing backref walking; 5) After that some error happens in the transaction commit path, and at ioctl.c:create_snapshot() we jump to the 'fail' label, and after that we free again the same anonymous device number, which in the meanwhile may have been reallocated somewhere else, because pending_snapshot->anon_dev still has the same value as in step 1. Recently syzbot ran into this and reported the following trace: ------------[ cut here ]------------ ida_free called for id=51 which is not allocated. WARNING: CPU: 1 PID: 31038 at lib/idr.c:525 ida_free+0x370/0x420 lib/idr.c:525 Modules linked in: CPU: 1 PID: 31038 Comm: syz-executor.2 Not tainted 6.8.0-rc4-syzkaller-00410-gc02197fc9076 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 RIP: 0010:ida_free+0x370/0x420 lib/idr.c:525 Code: 10 42 80 3c 28 (...) RSP: 0018:ffffc90015a67300 EFLAGS: 00010246 RAX: be5130472f5dd000 RBX: 0000000000000033 RCX: 0000000000040000 RDX: ffffc90009a7a000 RSI: 000000000003ffff RDI: 0000000000040000 RBP: ffffc90015a673f0 R08: ffffffff81577992 R09: 1ffff92002b4cdb4 R10: dffffc0000000000 R11: fffff52002b4cdb5 R12: 0000000000000246 R13: dffffc0000000000 R14: ffffffff8e256b80 R15: 0000000000000246 FS: 00007fca3f4b46c0(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f167a17b978 CR3: 000000001ed26000 CR4: 0000000000350ef0 Call Trace: <TASK> btrfs_get_root_ref+0xa48/0xaf0 fs/btrfs/disk-io.c:1346 create_pending_snapshot+0xff2/0x2bc0 fs/btrfs/transaction.c:1837 create_pending_snapshots+0x195/0x1d0 fs/btrfs/transaction.c:1931 btrfs_commit_transaction+0xf1c/0x3740 fs/btrfs/transaction.c:2404 create_snapshot+0x507/0x880 fs/btrfs/ioctl.c:848 btrfs_mksubvol+0x5d0/0x750 fs/btrfs/ioctl.c:998 btrfs_mksnapshot+0xb5/0xf0 fs/btrfs/ioctl.c:1044 __btrfs_ioctl_snap_create+0x387/0x4b0 fs/btrfs/ioctl.c:1306 btrfs_ioctl_snap_create_v2+0x1ca/0x400 fs/btrfs/ioctl.c:1393 btrfs_ioctl+0xa74/0xd40 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0xfe/0x170 fs/ioctl.c:857 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7fca3e67dda9 Code: 28 00 00 00 (...) RSP: 002b:00007fca3f4b40c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fca3e7abf80 RCX: 00007fca3e67dda9 RDX: 00000000200005c0 RSI: 0000000050009417 RDI: 0000000000000003 RBP: 00007fca3e6ca47a R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fca3e7abf80 R15: 00007fff6bf95658 </TASK> Where we get an explicit message where we attempt to free an anonymous device number that is not currently allocated. It happens in a different code path from the example below, at btrfs_get_root_ref(), so this change may not fix the case triggered by sy ---truncated---
CVE-2024-26807: In the Linux kernel, the following vulnerability has been resolved: Both cadence-quadspi ->runtime_suspend() and ->runtime_resume() implementations start with: struct cqspi_st *cqspi = dev_get_drvdata(dev); struct spi_controller *host = dev_get_drvdata(dev); This obviously cannot be correct, unless "struct cqspi_st" is the first member of " struct spi_controller", or the other way around, but it is not the case. "struct spi_controller" is allocated by devm_spi_alloc_host(), which allocates an extra amount of memory for private data, used to store "struct cqspi_st". The ->probe() function of the cadence-quadspi driver then sets the device drvdata to store the address of the "struct cqspi_st" structure. Therefore: struct cqspi_st *cqspi = dev_get_drvdata(dev); is correct, but: struct spi_controller *host = dev_get_drvdata(dev); is not, as it makes "host" point not to a "struct spi_controller" but to the same "struct cqspi_st" structure as above. This obviously leads to bad things (memory corruption, kernel crashes) directly during ->probe(), as ->probe() enables the device using PM runtime, leading the ->runtime_resume() hook being called, which in turns calls spi_controller_resume() with the wrong pointer. This has at least been reported [0] to cause a kernel crash, but the exact behavior will depend on the memory contents. [0] https://lore.kernel.org/all/20240226121803.5a7r5wkpbbowcxgx@dhruva/ This issue potentially affects all platforms that are currently using the cadence-quadspi driver.
CVE-2024-26828: In the Linux kernel, the following vulnerability has been resolved: cifs: fix underflow in parse_server_interfaces() In this loop, we step through the buffer and after each item we check if the size_left is greater than the minimum size we need. However, the problem is that "bytes_left" is type ssize_t while sizeof() is type size_t. That means that because of type promotion, the comparison is done as an unsigned and if we have negative bytes left the loop continues instead of ending.
CVE-2024-26830: In the Linux kernel, the following vulnerability has been resolved: i40e: Do not allow untrusted VF to remove administratively set MAC Currently when PF administratively sets VF's MAC address and the VF is put down (VF tries to delete all MACs) then the MAC is removed from MAC filters and primary VF MAC is zeroed. Do not allow untrusted VF to remove primary MAC when it was set administratively by PF. Reproducer: 1) Create VF 2) Set VF interface up 3) Administratively set the VF's MAC 4) Put VF interface down [root@host ~]# echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs [root@host ~]# ip link set enp2s0f0v0 up [root@host ~]# ip link set enp2s0f0 vf 0 mac fe:6c:b5:da:c7:7d [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether fe:6c:b5:da:c7:7d brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off [root@host ~]# ip link set enp2s0f0v0 down [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
CVE-2024-26844: In the Linux kernel, the following vulnerability has been resolved: block: Fix WARNING in _copy_from_iter Syzkaller reports a warning in _copy_from_iter because an iov_iter is supposedly used in the wrong direction. The reason is that syzcaller managed to generate a request with a transfer direction of SG_DXFER_TO_FROM_DEV. This instructs the kernel to copy user buffers into the kernel, read into the copied buffers and then copy the data back to user space. Thus the iovec is used in both directions. Detect this situation in the block layer and construct a new iterator with the correct direction for the copy-in.
CVE-2024-26865: In the Linux kernel, the following vulnerability has been resolved: rds: tcp: Fix use-after-free of net in reqsk_timer_handler(). syzkaller reported a warning of netns tracker [0] followed by KASAN splat [1] and another ref tracker warning [1]. syzkaller could not find a repro, but in the log, the only suspicious sequence was as follows: 18:26:22 executing program 1: r0 = socket$inet6_mptcp(0xa, 0x1, 0x106) ... connect$inet6(r0, &(0x7f0000000080)={0xa, 0x4001, 0x0, @loopback}, 0x1c) (async) The notable thing here is 0x4001 in connect(), which is RDS_TCP_PORT. So, the scenario would be: 1. unshare(CLONE_NEWNET) creates a per netns tcp listener in rds_tcp_listen_init(). 2. syz-executor connect()s to it and creates a reqsk. 3. syz-executor exit()s immediately. 4. netns is dismantled. [0] 5. reqsk timer is fired, and UAF happens while freeing reqsk. [1] 6. listener is freed after RCU grace period. [2] Basically, reqsk assumes that the listener guarantees netns safety until all reqsk timers are expired by holding the listener's refcount. However, this was not the case for kernel sockets. Commit 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()") fixed this issue only for per-netns ehash. Let's apply the same fix for the global ehash. [0]: ref_tracker: net notrefcnt@0000000065449cc3 has 1/1 users at sk_alloc (./include/net/net_namespace.h:337 net/core/sock.c:2146) inet6_create (net/ipv6/af_inet6.c:192 net/ipv6/af_inet6.c:119) __sock_create (net/socket.c:1572) rds_tcp_listen_init (net/rds/tcp_listen.c:279) rds_tcp_init_net (net/rds/tcp.c:577) ops_init (net/core/net_namespace.c:137) setup_net (net/core/net_namespace.c:340) copy_net_ns (net/core/net_namespace.c:497) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3429) __x64_sys_unshare (kernel/fork.c:3496) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129) ... WARNING: CPU: 0 PID: 27 at lib/ref_tracker.c:179 ref_tracker_dir_exit (lib/ref_tracker.c:179) [1]: BUG: KASAN: slab-use-after-free in inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) Read of size 8 at addr ffff88801b370400 by task swapper/0/0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107 (discriminator 1)) print_report (mm/kasan/report.c:378 mm/kasan/report.c:488) kasan_report (mm/kasan/report.c:603) inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) reqsk_timer_handler (net/ipv4/inet_connection_sock.c:979 net/ipv4/inet_connection_sock.c:1092) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2038) run_timer_softirq (kernel/time/timer.c:2053) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:554) irq_exit_rcu (kernel/softirq.c:427 kernel/softirq.c:632 kernel/softirq.c:644) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1076 (discriminator 14)) </IRQ> Allocated by task 258 on cpu 0 at 83.612050s: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (mm/kasan/common.c:68) __kasan_slab_alloc (mm/kasan/common.c:343) kmem_cache_alloc (mm/slub.c:3813 mm/slub.c:3860 mm/slub.c:3867) copy_net_ns (./include/linux/slab.h:701 net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_name ---truncated---
CVE-2024-26866: In the Linux kernel, the following vulnerability has been resolved: spi: lpspi: Avoid potential use-after-free in probe() fsl_lpspi_probe() is allocating/disposing memory manually with spi_alloc_host()/spi_alloc_target(), but uses devm_spi_register_controller(). In case of error after the latter call the memory will be explicitly freed in the probe function by spi_controller_put() call, but used afterwards by "devm" management outside probe() (spi_unregister_controller() <- devm_spi_unregister() below). Unable to handle kernel NULL pointer dereference at virtual address 0000000000000070 ... Call trace: kernfs_find_ns kernfs_find_and_get_ns sysfs_remove_group sysfs_remove_groups device_remove_attrs device_del spi_unregister_controller devm_spi_unregister release_nodes devres_release_all really_probe driver_probe_device __device_attach_driver bus_for_each_drv __device_attach device_initial_probe bus_probe_device deferred_probe_work_func process_one_work worker_thread kthread ret_from_fork
CVE-2024-26869: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to truncate meta inode pages forcely Below race case can cause data corruption: Thread A GC thread - gc_data_segment - ra_data_block - locked meta_inode page - f2fs_inplace_write_data - invalidate_mapping_pages : fail to invalidate meta_inode page due to lock failure or dirty|writeback status - f2fs_submit_page_bio : write last dirty data to old blkaddr - move_data_block - load old data from meta_inode page - f2fs_submit_page_write : write old data to new blkaddr Because invalidate_mapping_pages() will skip invalidating page which has unclear status including locked, dirty, writeback and so on, so we need to use truncate_inode_pages_range() instead of invalidate_mapping_pages() to make sure meta_inode page will be dropped.
CVE-2024-26876: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: adv7511: fix crash on irq during probe Moved IRQ registration down to end of adv7511_probe(). If an IRQ already is pending during adv7511_probe (before adv7511_cec_init) then cec_received_msg_ts could crash using uninitialized data: Unable to handle kernel read from unreadable memory at virtual address 00000000000003d5 Internal error: Oops: 96000004 [#1] PREEMPT_RT SMP Call trace: cec_received_msg_ts+0x48/0x990 [cec] adv7511_cec_irq_process+0x1cc/0x308 [adv7511] adv7511_irq_process+0xd8/0x120 [adv7511] adv7511_irq_handler+0x1c/0x30 [adv7511] irq_thread_fn+0x30/0xa0 irq_thread+0x14c/0x238 kthread+0x190/0x1a8
CVE-2024-26886: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: af_bluetooth: Fix deadlock Attemting to do sock_lock on .recvmsg may cause a deadlock as shown bellow, so instead of using sock_sock this uses sk_receive_queue.lock on bt_sock_ioctl to avoid the UAF: INFO: task kworker/u9:1:121 blocked for more than 30 seconds. Not tainted 6.7.6-lemon #183 Workqueue: hci0 hci_rx_work Call Trace: <TASK> __schedule+0x37d/0xa00 schedule+0x32/0xe0 __lock_sock+0x68/0xa0 ? __pfx_autoremove_wake_function+0x10/0x10 lock_sock_nested+0x43/0x50 l2cap_sock_recv_cb+0x21/0xa0 l2cap_recv_frame+0x55b/0x30a0 ? psi_task_switch+0xeb/0x270 ? finish_task_switch.isra.0+0x93/0x2a0 hci_rx_work+0x33a/0x3f0 process_one_work+0x13a/0x2f0 worker_thread+0x2f0/0x410 ? __pfx_worker_thread+0x10/0x10 kthread+0xe0/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK>
CVE-2024-26893: In the Linux kernel, the following vulnerability has been resolved: firmware: arm_scmi: Fix double free in SMC transport cleanup path When the generic SCMI code tears down a channel, it calls the chan_free callback function, defined by each transport. Since multiple protocols might share the same transport_info member, chan_free() might want to clean up the same member multiple times within the given SCMI transport implementation. In this case, it is SMC transport. This will lead to a NULL pointer dereference at the second time: | scmi_protocol scmi_dev.1: Enabled polling mode TX channel - prot_id:16 | arm-scmi firmware:scmi: SCMI Notifications - Core Enabled. | arm-scmi firmware:scmi: unable to communicate with SCMI | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 | Mem abort info: | ESR = 0x0000000096000004 | EC = 0x25: DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | FSC = 0x04: level 0 translation fault | Data abort info: | ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 | CM = 0, WnR = 0, TnD = 0, TagAccess = 0 | GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 | user pgtable: 4k pages, 48-bit VAs, pgdp=0000000881ef8000 | [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 | Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP | Modules linked in: | CPU: 4 PID: 1 Comm: swapper/0 Not tainted 6.7.0-rc2-00124-g455ef3d016c9-dirty #793 | Hardware name: FVP Base RevC (DT) | pstate: 61400009 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) | pc : smc_chan_free+0x3c/0x6c | lr : smc_chan_free+0x3c/0x6c | Call trace: | smc_chan_free+0x3c/0x6c | idr_for_each+0x68/0xf8 | scmi_cleanup_channels.isra.0+0x2c/0x58 | scmi_probe+0x434/0x734 | platform_probe+0x68/0xd8 | really_probe+0x110/0x27c | __driver_probe_device+0x78/0x12c | driver_probe_device+0x3c/0x118 | __driver_attach+0x74/0x128 | bus_for_each_dev+0x78/0xe0 | driver_attach+0x24/0x30 | bus_add_driver+0xe4/0x1e8 | driver_register+0x60/0x128 | __platform_driver_register+0x28/0x34 | scmi_driver_init+0x84/0xc0 | do_one_initcall+0x78/0x33c | kernel_init_freeable+0x2b8/0x51c | kernel_init+0x24/0x130 | ret_from_fork+0x10/0x20 | Code: f0004701 910a0021 aa1403e5 97b91c70 (b9400280) | ---[ end trace 0000000000000000 ]--- Simply check for the struct pointer being NULL before trying to access its members, to avoid this situation. This was found when a transport doesn't really work (for instance no SMC service), the probe routines then tries to clean up, and triggers a crash.
CVE-2024-26896: In the Linux kernel, the following vulnerability has been resolved: wifi: wfx: fix memory leak when starting AP Kmemleak reported this error: unreferenced object 0xd73d1180 (size 184): comm "wpa_supplicant", pid 1559, jiffies 13006305 (age 964.245s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 1e 00 01 00 00 00 00 00 ................ backtrace: [<5ca11420>] kmem_cache_alloc+0x20c/0x5ac [<127bdd74>] __alloc_skb+0x144/0x170 [<fb8a5e38>] __netdev_alloc_skb+0x50/0x180 [<0f9fa1d5>] __ieee80211_beacon_get+0x290/0x4d4 [mac80211] [<7accd02d>] ieee80211_beacon_get_tim+0x54/0x18c [mac80211] [<41e25cc3>] wfx_start_ap+0xc8/0x234 [wfx] [<93a70356>] ieee80211_start_ap+0x404/0x6b4 [mac80211] [<a4a661cd>] nl80211_start_ap+0x76c/0x9e0 [cfg80211] [<47bd8b68>] genl_rcv_msg+0x198/0x378 [<453ef796>] netlink_rcv_skb+0xd0/0x130 [<6b7c977a>] genl_rcv+0x34/0x44 [<66b2d04d>] netlink_unicast+0x1b4/0x258 [<f965b9b6>] netlink_sendmsg+0x1e8/0x428 [<aadb8231>] ____sys_sendmsg+0x1e0/0x274 [<d2b5212d>] ___sys_sendmsg+0x80/0xb4 [<69954f45>] __sys_sendmsg+0x64/0xa8 unreferenced object 0xce087000 (size 1024): comm "wpa_supplicant", pid 1559, jiffies 13006305 (age 964.246s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 10 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<9a993714>] __kmalloc_track_caller+0x230/0x600 [<f83ea192>] kmalloc_reserve.constprop.0+0x30/0x74 [<a2c61343>] __alloc_skb+0xa0/0x170 [<fb8a5e38>] __netdev_alloc_skb+0x50/0x180 [<0f9fa1d5>] __ieee80211_beacon_get+0x290/0x4d4 [mac80211] [<7accd02d>] ieee80211_beacon_get_tim+0x54/0x18c [mac80211] [<41e25cc3>] wfx_start_ap+0xc8/0x234 [wfx] [<93a70356>] ieee80211_start_ap+0x404/0x6b4 [mac80211] [<a4a661cd>] nl80211_start_ap+0x76c/0x9e0 [cfg80211] [<47bd8b68>] genl_rcv_msg+0x198/0x378 [<453ef796>] netlink_rcv_skb+0xd0/0x130 [<6b7c977a>] genl_rcv+0x34/0x44 [<66b2d04d>] netlink_unicast+0x1b4/0x258 [<f965b9b6>] netlink_sendmsg+0x1e8/0x428 [<aadb8231>] ____sys_sendmsg+0x1e0/0x274 [<d2b5212d>] ___sys_sendmsg+0x80/0xb4 However, since the kernel is build optimized, it seems the stack is not accurate. It appears the issue is related to wfx_set_mfp_ap(). The issue is obvious in this function: memory allocated by ieee80211_beacon_get() is never released. Fixing this leak makes kmemleak happy.
CVE-2024-26913: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix dcn35 8k30 Underflow/Corruption Issue [why] odm calculation is missing for pipe split policy determination and cause Underflow/Corruption issue. [how] Add the odm calculation.
CVE-2024-26914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix incorrect mpc_combine array size [why] MAX_SURFACES is per stream, while MAX_PLANES is per asic. The mpc_combine is an array that records all the planes per asic. Therefore MAX_PLANES should be used as the array size. Using MAX_SURFACES causes array overflow when there are more than 3 planes. [how] Use the MAX_PLANES for the mpc_combine array size.
CVE-2024-26915: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Reset IH OVERFLOW_CLEAR bit Allows us to detect subsequent IH ring buffer overflows as well.
CVE-2024-26920: In the Linux kernel, the following vulnerability has been resolved: tracing/trigger: Fix to return error if failed to alloc snapshot Fix register_snapshot_trigger() to return error code if it failed to allocate a snapshot instead of 0 (success). Unless that, it will register snapshot trigger without an error.
CVE-2024-26947: In the Linux kernel, the following vulnerability has been resolved: ARM: 9359/1: flush: check if the folio is reserved for no-mapping addresses Since commit a4d5613c4dc6 ("arm: extend pfn_valid to take into account freed memory map alignment") changes the semantics of pfn_valid() to check presence of the memory map for a PFN. A valid page for an address which is reserved but not mapped by the kernel[1], the system crashed during some uio test with the following memory layout: node 0: [mem 0x00000000c0a00000-0x00000000cc8fffff] node 0: [mem 0x00000000d0000000-0x00000000da1fffff] the uio layout is：0xc0900000, 0x100000 the crash backtrace like: Unable to handle kernel paging request at virtual address bff00000 [...] CPU: 1 PID: 465 Comm: startapp.bin Tainted: G O 5.10.0 #1 Hardware name: Generic DT based system PC is at b15_flush_kern_dcache_area+0x24/0x3c LR is at __sync_icache_dcache+0x6c/0x98 [...] (b15_flush_kern_dcache_area) from (__sync_icache_dcache+0x6c/0x98) (__sync_icache_dcache) from (set_pte_at+0x28/0x54) (set_pte_at) from (remap_pfn_range+0x1a0/0x274) (remap_pfn_range) from (uio_mmap+0x184/0x1b8 [uio]) (uio_mmap [uio]) from (__mmap_region+0x264/0x5f4) (__mmap_region) from (__do_mmap_mm+0x3ec/0x440) (__do_mmap_mm) from (do_mmap+0x50/0x58) (do_mmap) from (vm_mmap_pgoff+0xfc/0x188) (vm_mmap_pgoff) from (ksys_mmap_pgoff+0xac/0xc4) (ksys_mmap_pgoff) from (ret_fast_syscall+0x0/0x5c) Code: e0801001 e2423001 e1c00003 f57ff04f (ee070f3e) ---[ end trace 09cf0734c3805d52 ]--- Kernel panic - not syncing: Fatal exception So check if PG_reserved was set to solve this issue. [1]: https://lore.kernel.org/lkml/Zbtdue57RO0QScJM@linux.ibm.com/
CVE-2024-26948: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add a dc_state NULL check in dc_state_release [How] Check wheather state is NULL before releasing it.
CVE-2024-26996: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: Fix UAF ncm object at re-bind after usb ep transport error When ncm function is working and then stop usb0 interface for link down, eth_stop() is called. At this piont, accidentally if usb transport error should happen in usb_ep_enable(), 'in_ep' and/or 'out_ep' may not be enabled. After that, ncm_disable() is called to disable for ncm unbind but gether_disconnect() is never called since 'in_ep' is not enabled. As the result, ncm object is released in ncm unbind but 'dev->port_usb' associated to 'ncm->port' is not NULL. And when ncm bind again to recover netdev, ncm object is reallocated but usb0 interface is already associated to previous released ncm object. Therefore, once usb0 interface is up and eth_start_xmit() is called, released ncm object is dereferrenced and it might cause use-after-free memory. [function unlink via configfs] usb0: eth_stop dev->port_usb=ffffff9b179c3200 --> error happens in usb_ep_enable(). NCM: ncm_disable: ncm=ffffff9b179c3200 --> no gether_disconnect() since ncm->port.in_ep->enabled is false. NCM: ncm_unbind: ncm unbind ncm=ffffff9b179c3200 NCM: ncm_free: ncm free ncm=ffffff9b179c3200 <-- released ncm [function link via configfs] NCM: ncm_alloc: ncm alloc ncm=ffffff9ac4f8a000 NCM: ncm_bind: ncm bind ncm=ffffff9ac4f8a000 NCM: ncm_set_alt: ncm=ffffff9ac4f8a000 alt=0 usb0: eth_open dev->port_usb=ffffff9b179c3200 <-- previous released ncm usb0: eth_start dev->port_usb=ffffff9b179c3200 <-- eth_start_xmit() --> dev->wrap() Unable to handle kernel paging request at virtual address dead00000000014f This patch addresses the issue by checking if 'ncm->netdev' is not NULL at ncm_disable() to call gether_disconnect() to deassociate 'dev->port_usb'. It's more reasonable to check 'ncm->netdev' to call gether_connect/disconnect rather than check 'ncm->port.in_ep->enabled' since it might not be enabled but the gether connection might be established.
CVE-2024-27002: In the Linux kernel, the following vulnerability has been resolved: clk: mediatek: Do a runtime PM get on controllers during probe mt8183-mfgcfg has a mutual dependency with genpd during the probing stage, which leads to a deadlock in the following call stack: CPU0: genpd_lock --> clk_prepare_lock genpd_power_off_work_fn() genpd_lock() generic_pm_domain::power_off() clk_unprepare() clk_prepare_lock() CPU1: clk_prepare_lock --> genpd_lock clk_register() __clk_core_init() clk_prepare_lock() clk_pm_runtime_get() genpd_lock() Do a runtime PM get at the probe function to make sure clk_register() won't acquire the genpd lock. Instead of only modifying mt8183-mfgcfg, do this on all mediatek clock controller probings because we don't believe this would cause any regression. Verified on MT8183 and MT8192 Chromebooks.
CVE-2024-27010: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix mirred deadlock on device recursion When the mirred action is used on a classful egress qdisc and a packet is mirrored or redirected to self we hit a qdisc lock deadlock. See trace below. [..... other info removed for brevity....] [ 82.890906] [ 82.890906] ============================================ [ 82.890906] WARNING: possible recursive locking detected [ 82.890906] 6.8.0-05205-g77fadd89fe2d-dirty #213 Tainted: G W [ 82.890906] -------------------------------------------- [ 82.890906] ping/418 is trying to acquire lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] but task is already holding lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] other info that might help us debug this: [ 82.890906] Possible unsafe locking scenario: [ 82.890906] [ 82.890906] CPU0 [ 82.890906] ---- [ 82.890906] lock(&sch->q.lock); [ 82.890906] lock(&sch->q.lock); [ 82.890906] [ 82.890906] *** DEADLOCK *** [ 82.890906] [..... other info removed for brevity....] Example setup (eth0->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 Another example(eth0->eth1->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth1 tc qdisc add dev eth1 root handle 1: htb default 30 tc filter add dev eth1 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 We fix this by adding an owner field (CPU id) to struct Qdisc set after root qdisc is entered. When the softirq enters it a second time, if the qdisc owner is the same CPU, the packet is dropped to break the loop.
CVE-2024-27011: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix memleak in map from abort path The delete set command does not rely on the transaction object for element removal, therefore, a combination of delete element + delete set from the abort path could result in restoring twice the refcount of the mapping. Check for inactive element in the next generation for the delete element command in the abort path, skip restoring state if next generation bit has been already cleared. This is similar to the activate logic using the set walk iterator. [ 6170.286929] ------------[ cut here ]------------ [ 6170.286939] WARNING: CPU: 6 PID: 790302 at net/netfilter/nf_tables_api.c:2086 nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287071] Modules linked in: [...] [ 6170.287633] CPU: 6 PID: 790302 Comm: kworker/6:2 Not tainted 6.9.0-rc3+ #365 [ 6170.287768] RIP: 0010:nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287886] Code: df 48 8d 7d 58 e8 69 2e 3b df 48 8b 7d 58 e8 80 1b 37 df 48 8d 7d 68 e8 57 2e 3b df 48 8b 7d 68 e8 6e 1b 37 df 48 89 ef eb c4 <0f> 0b 48 83 c4 08 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 0f [ 6170.287895] RSP: 0018:ffff888134b8fd08 EFLAGS: 00010202 [ 6170.287904] RAX: 0000000000000001 RBX: ffff888125bffb28 RCX: dffffc0000000000 [ 6170.287912] RDX: 0000000000000003 RSI: ffffffffa20298ab RDI: ffff88811ebe4750 [ 6170.287919] RBP: ffff88811ebe4700 R08: ffff88838e812650 R09: fffffbfff0623a55 [ 6170.287926] R10: ffffffff8311d2af R11: 0000000000000001 R12: ffff888125bffb10 [ 6170.287933] R13: ffff888125bffb10 R14: dead000000000122 R15: dead000000000100 [ 6170.287940] FS: 0000000000000000(0000) GS:ffff888390b00000(0000) knlGS:0000000000000000 [ 6170.287948] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6170.287955] CR2: 00007fd31fc00710 CR3: 0000000133f60004 CR4: 00000000001706f0 [ 6170.287962] Call Trace: [ 6170.287967] <TASK> [ 6170.287973] ? __warn+0x9f/0x1a0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.288104] ? handle_bug+0x3c/0x70 [ 6170.288112] ? exc_invalid_op+0x17/0x40 [ 6170.288120] ? asm_exc_invalid_op+0x1a/0x20 [ 6170.288132] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288243] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288366] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288483] nf_tables_trans_destroy_work+0x588/0x590 [nf_tables]
CVE-2024-27012: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: restore set elements when delete set fails From abort path, nft_mapelem_activate() needs to restore refcounters to the original state. Currently, it uses the set->ops->walk() to iterate over these set elements. The existing set iterator skips inactive elements in the next generation, this does not work from the abort path to restore the original state since it has to skip active elements instead (not inactive ones). This patch moves the check for inactive elements to the set iterator callback, then it reverses the logic for the .activate case which needs to skip active elements. Toggle next generation bit for elements when delete set command is invoked and call nft_clear() from .activate (abort) path to restore the next generation bit. The splat below shows an object in mappings memleak: [43929.457523] ------------[ cut here ]------------ [43929.457532] WARNING: CPU: 0 PID: 1139 at include/net/netfilter/nf_tables.h:1237 nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [...] [43929.458014] RIP: 0010:nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458076] Code: 83 f8 01 77 ab 49 8d 7c 24 08 e8 37 5e d0 de 49 8b 6c 24 08 48 8d 7d 50 e8 e9 5c d0 de 8b 45 50 8d 50 ff 89 55 50 85 c0 75 86 <0f> 0b eb 82 0f 0b eb b3 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 [43929.458081] RSP: 0018:ffff888140f9f4b0 EFLAGS: 00010246 [43929.458086] RAX: 0000000000000000 RBX: ffff8881434f5288 RCX: dffffc0000000000 [43929.458090] RDX: 00000000ffffffff RSI: ffffffffa26d28a7 RDI: ffff88810ecc9550 [43929.458093] RBP: ffff88810ecc9500 R08: 0000000000000001 R09: ffffed10281f3e8f [43929.458096] R10: 0000000000000003 R11: ffff0000ffff0000 R12: ffff8881434f52a0 [43929.458100] R13: ffff888140f9f5f4 R14: ffff888151c7a800 R15: 0000000000000002 [43929.458103] FS: 00007f0c687c4740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000 [43929.458107] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [43929.458111] CR2: 00007f58dbe5b008 CR3: 0000000123602005 CR4: 00000000001706f0 [43929.458114] Call Trace: [43929.458118] <TASK> [43929.458121] ? __warn+0x9f/0x1a0 [43929.458127] ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458188] ? report_bug+0x1b1/0x1e0 [43929.458196] ? handle_bug+0x3c/0x70 [43929.458200] ? exc_invalid_op+0x17/0x40 [43929.458211] ? nft_setelem_data_deactivate+0xd7/0xf0 [nf_tables] [43929.458271] ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458332] nft_mapelem_deactivate+0x24/0x30 [nf_tables] [43929.458392] nft_rhash_walk+0xdd/0x180 [nf_tables] [43929.458453] ? __pfx_nft_rhash_walk+0x10/0x10 [nf_tables] [43929.458512] ? rb_insert_color+0x2e/0x280 [43929.458520] nft_map_deactivate+0xdc/0x1e0 [nf_tables] [43929.458582] ? __pfx_nft_map_deactivate+0x10/0x10 [nf_tables] [43929.458642] ? __pfx_nft_mapelem_deactivate+0x10/0x10 [nf_tables] [43929.458701] ? __rcu_read_unlock+0x46/0x70 [43929.458709] nft_delset+0xff/0x110 [nf_tables] [43929.458769] nft_flush_table+0x16f/0x460 [nf_tables] [43929.458830] nf_tables_deltable+0x501/0x580 [nf_tables]
CVE-2024-27014: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Prevent deadlock while disabling aRFS When disabling aRFS under the `priv->state_lock`, any scheduled aRFS works are canceled using the `cancel_work_sync` function, which waits for the work to end if it has already started. However, while waiting for the work handler, the handler will try to acquire the `state_lock` which is already acquired. The worker acquires the lock to delete the rules if the state is down, which is not the worker's responsibility since disabling aRFS deletes the rules. Add an aRFS state variable, which indicates whether the aRFS is enabled and prevent adding rules when the aRFS is disabled. Kernel log: ====================================================== WARNING: possible circular locking dependency detected 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Tainted: G I ------------------------------------------------------ ethtool/386089 is trying to acquire lock: ffff88810f21ce68 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}, at: __flush_work+0x74/0x4e0 but task is already holding lock: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&priv->state_lock){+.+.}-{3:3}: __mutex_lock+0x80/0xc90 arfs_handle_work+0x4b/0x3b0 [mlx5_core] process_one_work+0x1dc/0x4a0 worker_thread+0x1bf/0x3c0 kthread+0xd7/0x100 ret_from_fork+0x2d/0x50 ret_from_fork_asm+0x11/0x20 -> #0 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}: __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 __flush_work+0x7a/0x4e0 __cancel_work_timer+0x131/0x1c0 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1a1/0x270 netlink_sendmsg+0x214/0x460 __sock_sendmsg+0x38/0x60 __sys_sendto+0x113/0x170 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x46/0x4e other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work)); lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work)); *** DEADLOCK *** 3 locks held by ethtool/386089: #0: ffffffff82ea7210 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 #1: ffffffff82e94c88 (rtnl_mutex){+.+.}-{3:3}, at: ethnl_default_set_doit+0xd3/0x240 #2: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core] stack backtrace: CPU: 15 PID: 386089 Comm: ethtool Tainted: G I 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x60/0xa0 check_noncircular+0x144/0x160 __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 ? __flush_work+0x74/0x4e0 ? save_trace+0x3e/0x360 ? __flush_work+0x74/0x4e0 __flush_work+0x7a/0x4e0 ? __flush_work+0x74/0x4e0 ? __lock_acquire+0xa78/0x2c80 ? lock_acquire+0xd0/0x2b0 ? mark_held_locks+0x49/0x70 __cancel_work_timer+0x131/0x1c0 ? mark_held_locks+0x49/0x70 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 ? ethn ---truncated---
CVE-2024-27032: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid potential panic during recovery During recovery, if FAULT_BLOCK is on, it is possible that f2fs_reserve_new_block() will return -ENOSPC during recovery, then it may trigger panic. Also, if fault injection rate is 1 and only FAULT_BLOCK fault type is on, it may encounter deadloop in loop of block reservation. Let's change as below to fix these issues: - remove bug_on() to avoid panic. - limit the loop count of block reservation to avoid potential deadloop.
CVE-2024-27034: In the Linux kernel, the following vulnerability has been resolved: f2fs: compress: fix to cover normal cluster write with cp_rwsem When we overwrite compressed cluster w/ normal cluster, we should not unlock cp_rwsem during f2fs_write_raw_pages(), otherwise data will be corrupted if partial blocks were persisted before CP & SPOR, due to cluster metadata wasn't updated atomically.
CVE-2024-27035: In the Linux kernel, the following vulnerability has been resolved: f2fs: compress: fix to guarantee persisting compressed blocks by CP If data block in compressed cluster is not persisted with metadata during checkpoint, after SPOR, the data may be corrupted, let's guarantee to write compressed page by checkpoint.
CVE-2024-27037: In the Linux kernel, the following vulnerability has been resolved: clk: zynq: Prevent null pointer dereference caused by kmalloc failure The kmalloc() in zynq_clk_setup() will return null if the physical memory has run out. As a result, if we use snprintf() to write data to the null address, the null pointer dereference bug will happen. This patch uses a stack variable to replace the kmalloc().
CVE-2024-27056: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: ensure offloading TID queue exists The resume code path assumes that the TX queue for the offloading TID has been configured. At resume time it then tries to sync the write pointer as it may have been updated by the firmware. In the unusual event that no packets have been send on TID 0, the queue will not have been allocated and this causes a crash. Fix this by ensuring the queue exist at suspend time.
CVE-2024-27062: In the Linux kernel, the following vulnerability has been resolved: nouveau: lock the client object tree. It appears the client object tree has no locking unless I've missed something else. Fix races around adding/removing client objects, mostly vram bar mappings. 4562.099306] general protection fault, probably for non-canonical address 0x6677ed422bceb80c: 0000 [#1] PREEMPT SMP PTI [ 4562.099314] CPU: 2 PID: 23171 Comm: deqp-vk Not tainted 6.8.0-rc6+ #27 [ 4562.099324] Hardware name: Gigabyte Technology Co., Ltd. Z390 I AORUS PRO WIFI/Z390 I AORUS PRO WIFI-CF, BIOS F8 11/05/2021 [ 4562.099330] RIP: 0010:nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099503] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 48 89 f8 48 85 f6 74 39 48 8b 87 a0 00 00 00 48 85 c0 74 12 <48> 8b 48 f8 48 39 ce 73 15 48 8b 40 10 48 85 c0 75 ee 48 c7 c0 fe [ 4562.099506] RSP: 0000:ffffa94cc420bbf8 EFLAGS: 00010206 [ 4562.099512] RAX: 6677ed422bceb814 RBX: ffff98108791f400 RCX: ffff9810f26b8f58 [ 4562.099517] RDX: 0000000000000000 RSI: ffff9810f26b9158 RDI: ffff98108791f400 [ 4562.099519] RBP: ffff9810f26b9158 R08: 0000000000000000 R09: 0000000000000000 [ 4562.099521] R10: ffffa94cc420bc48 R11: 0000000000000001 R12: ffff9810f02a7cc0 [ 4562.099526] R13: 0000000000000000 R14: 00000000000000ff R15: 0000000000000007 [ 4562.099528] FS: 00007f629c5017c0(0000) GS:ffff98142c700000(0000) knlGS:0000000000000000 [ 4562.099534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4562.099536] CR2: 00007f629a882000 CR3: 000000017019e004 CR4: 00000000003706f0 [ 4562.099541] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4562.099542] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4562.099544] Call Trace: [ 4562.099555] <TASK> [ 4562.099573] ? die_addr+0x36/0x90 [ 4562.099583] ? exc_general_protection+0x246/0x4a0 [ 4562.099593] ? asm_exc_general_protection+0x26/0x30 [ 4562.099600] ? nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099730] nvkm_ioctl+0xa1/0x250 [nouveau] [ 4562.099861] nvif_object_map_handle+0xc8/0x180 [nouveau] [ 4562.099986] nouveau_ttm_io_mem_reserve+0x122/0x270 [nouveau] [ 4562.100156] ? dma_resv_test_signaled+0x26/0xb0 [ 4562.100163] ttm_bo_vm_fault_reserved+0x97/0x3c0 [ttm] [ 4562.100182] ? __mutex_unlock_slowpath+0x2a/0x270 [ 4562.100189] nouveau_ttm_fault+0x69/0xb0 [nouveau] [ 4562.100356] __do_fault+0x32/0x150 [ 4562.100362] do_fault+0x7c/0x560 [ 4562.100369] __handle_mm_fault+0x800/0xc10 [ 4562.100382] handle_mm_fault+0x17c/0x3e0 [ 4562.100388] do_user_addr_fault+0x208/0x860 [ 4562.100395] exc_page_fault+0x7f/0x200 [ 4562.100402] asm_exc_page_fault+0x26/0x30 [ 4562.100412] RIP: 0033:0x9b9870 [ 4562.100419] Code: 85 a8 f7 ff ff 8b 8d 80 f7 ff ff 89 08 e9 18 f2 ff ff 0f 1f 84 00 00 00 00 00 44 89 32 e9 90 fa ff ff 0f 1f 84 00 00 00 00 00 <44> 89 32 e9 f8 f1 ff ff 0f 1f 84 00 00 00 00 00 66 44 89 32 e9 e7 [ 4562.100422] RSP: 002b:00007fff9ba2dc70 EFLAGS: 00010246 [ 4562.100426] RAX: 0000000000000004 RBX: 000000000dd65e10 RCX: 000000fff0000000 [ 4562.100428] RDX: 00007f629a882000 RSI: 00007f629a882000 RDI: 0000000000000066 [ 4562.100432] RBP: 00007fff9ba2e570 R08: 0000000000000000 R09: 0000000123ddf000 [ 4562.100434] R10: 0000000000000001 R11: 0000000000000246 R12: 000000007fffffff [ 4562.100436] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 4562.100446] </TASK> [ 4562.100448] Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink cmac bnep sunrpc iwlmvm intel_rapl_msr intel_rapl_common snd_sof_pci_intel_cnl x86_pkg_temp_thermal intel_powerclamp snd_sof_intel_hda_common mac80211 coretemp snd_soc_acpi_intel_match kvm_intel snd_soc_acpi snd_soc_hdac_hda snd_sof_pci snd_sof_xtensa_dsp snd_sof_intel_hda_mlink ---truncated---
CVE-2024-27389: In the Linux kernel, the following vulnerability has been resolved: pstore: inode: Only d_invalidate() is needed Unloading a modular pstore backend with records in pstorefs would trigger the dput() double-drop warning: WARNING: CPU: 0 PID: 2569 at fs/dcache.c:762 dput.part.0+0x3f3/0x410 Using the combo of d_drop()/dput() (as mentioned in Documentation/filesystems/vfs.rst) isn't the right approach here, and leads to the reference counting problem seen above. Use d_invalidate() and update the code to not bother checking for error codes that can never happen. ---
CVE-2024-27393: In the Linux kernel, the following vulnerability has been resolved: xen-netfront: Add missing skb_mark_for_recycle Notice that skb_mark_for_recycle() is introduced later than fixes tag in commit 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling"). It is believed that fixes tag were missing a call to page_pool_release_page() between v5.9 to v5.14, after which is should have used skb_mark_for_recycle(). Since v6.6 the call page_pool_release_page() were removed (in commit 535b9c61bdef ("net: page_pool: hide page_pool_release_page()") and remaining callers converted (in commit 6bfef2ec0172 ("Merge branch 'net-page_pool-remove-page_pool_release_page'")). This leak became visible in v6.8 via commit dba1b8a7ab68 ("mm/page_pool: catch page_pool memory leaks").
CVE-2024-27402: In the Linux kernel, the following vulnerability has been resolved: phonet/pep: fix racy skb_queue_empty() use The receive queues are protected by their respective spin-lock, not the socket lock. This could lead to skb_peek() unexpectedly returning NULL or a pointer to an already dequeued socket buffer.
CVE-2024-27403: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_flow_offload: reset dst in route object after setting up flow dst is transferred to the flow object, route object does not own it anymore. Reset dst in route object, otherwise if flow_offload_add() fails, error path releases dst twice, leading to a refcount underflow.
CVE-2024-27408: In the Linux kernel, the following vulnerability has been resolved: dmaengine: dw-edma: eDMA: Add sync read before starting the DMA transfer in remote setup The Linked list element and pointer are not stored in the same memory as the eDMA controller register. If the doorbell register is toggled before the full write of the linked list a race condition error will occur. In remote setup we can only use a readl to the memory to assure the full write has occurred.
CVE-2024-27415: In the Linux kernel, the following vulnerability has been resolved: netfilter: bridge: confirm multicast packets before passing them up the stack conntrack nf_confirm logic cannot handle cloned skbs referencing the same nf_conn entry, which will happen for multicast (broadcast) frames on bridges. Example: macvlan0 | br0 / \ ethX ethY ethX (or Y) receives a L2 multicast or broadcast packet containing an IP packet, flow is not yet in conntrack table. 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. -> skb->_nfct now references a unconfirmed entry 2. skb is broad/mcast packet. bridge now passes clones out on each bridge interface. 3. skb gets passed up the stack. 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb and schedules a work queue to send them out on the lower devices. The clone skb->_nfct is not a copy, it is the same entry as the original skb. The macvlan rx handler then returns RX_HANDLER_PASS. 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. The Macvlan broadcast worker and normal confirm path will race. This race will not happen if step 2 already confirmed a clone. In that case later steps perform skb_clone() with skb->_nfct already confirmed (in hash table). This works fine. But such confirmation won't happen when eb/ip/nftables rules dropped the packets before they reached the nf_confirm step in postrouting. Pablo points out that nf_conntrack_bridge doesn't allow use of stateful nat, so we can safely discard the nf_conn entry and let inet call conntrack again. This doesn't work for bridge netfilter: skb could have a nat transformation. Also bridge nf prevents re-invocation of inet prerouting via 'sabotage_in' hook. Work around this problem by explicit confirmation of the entry at LOCAL_IN time, before upper layer has a chance to clone the unconfirmed entry. The downside is that this disables NAT and conntrack helpers. Alternative fix would be to add locking to all code parts that deal with unconfirmed packets, but even if that could be done in a sane way this opens up other problems, for example: -m physdev --physdev-out eth0 -j SNAT --snat-to 1.2.3.4 -m physdev --physdev-out eth1 -j SNAT --snat-to 1.2.3.5 For multicast case, only one of such conflicting mappings will be created, conntrack only handles 1:1 NAT mappings. Users should set create a setup that explicitly marks such traffic NOTRACK (conntrack bypass) to avoid this, but we cannot auto-bypass them, ruleset might have accept rules for untracked traffic already, so user-visible behaviour would change.
CVE-2024-35784: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix deadlock with fiemap and extent locking While working on the patchset to remove extent locking I got a lockdep splat with fiemap and pagefaulting with my new extent lock replacement lock. This deadlock exists with our normal code, we just don't have lockdep annotations with the extent locking so we've never noticed it. Since we're copying the fiemap extent to user space on every iteration we have the chance of pagefaulting. Because we hold the extent lock for the entire range we could mkwrite into a range in the file that we have mmap'ed. This would deadlock with the following stack trace [<0>] lock_extent+0x28d/0x2f0 [<0>] btrfs_page_mkwrite+0x273/0x8a0 [<0>] do_page_mkwrite+0x50/0xb0 [<0>] do_fault+0xc1/0x7b0 [<0>] __handle_mm_fault+0x2fa/0x460 [<0>] handle_mm_fault+0xa4/0x330 [<0>] do_user_addr_fault+0x1f4/0x800 [<0>] exc_page_fault+0x7c/0x1e0 [<0>] asm_exc_page_fault+0x26/0x30 [<0>] rep_movs_alternative+0x33/0x70 [<0>] _copy_to_user+0x49/0x70 [<0>] fiemap_fill_next_extent+0xc8/0x120 [<0>] emit_fiemap_extent+0x4d/0xa0 [<0>] extent_fiemap+0x7f8/0xad0 [<0>] btrfs_fiemap+0x49/0x80 [<0>] __x64_sys_ioctl+0x3e1/0xb50 [<0>] do_syscall_64+0x94/0x1a0 [<0>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 I wrote an fstest to reproduce this deadlock without my replacement lock and verified that the deadlock exists with our existing locking. To fix this simply don't take the extent lock for the entire duration of the fiemap. This is safe in general because we keep track of where we are when we're searching the tree, so if an ordered extent updates in the middle of our fiemap call we'll still emit the correct extents because we know what offset we were on before. The only place we maintain the lock is searching delalloc. Since the delalloc stuff can change during writeback we want to lock the extent range so we have a consistent view of delalloc at the time we're checking to see if we need to set the delalloc flag. With this patch applied we no longer deadlock with my testcase.
CVE-2024-35794: In the Linux kernel, the following vulnerability has been resolved: dm-raid: really frozen sync_thread during suspend 1) commit f52f5c71f3d4 ("md: fix stopping sync thread") remove MD_RECOVERY_FROZEN from __md_stop_writes() and doesn't realize that dm-raid relies on __md_stop_writes() to frozen sync_thread indirectly. Fix this problem by adding MD_RECOVERY_FROZEN in md_stop_writes(), and since stop_sync_thread() is only used for dm-raid in this case, also move stop_sync_thread() to md_stop_writes(). 2) The flag MD_RECOVERY_FROZEN doesn't mean that sync thread is frozen, it only prevent new sync_thread to start, and it can't stop the running sync thread; In order to frozen sync_thread, after seting the flag, stop_sync_thread() should be used. 3) The flag MD_RECOVERY_FROZEN doesn't mean that writes are stopped, use it as condition for md_stop_writes() in raid_postsuspend() doesn't look correct. Consider that reentrant stop_sync_thread() do nothing, always call md_stop_writes() in raid_postsuspend(). 4) raid_message can set/clear the flag MD_RECOVERY_FROZEN at anytime, and if MD_RECOVERY_FROZEN is cleared while the array is suspended, new sync_thread can start unexpected. Fix this by disallow raid_message() to change sync_thread status during suspend. Note that after commit f52f5c71f3d4 ("md: fix stopping sync thread"), the test shell/lvconvert-raid-reshape.sh start to hang in stop_sync_thread(), and with previous fixes, the test won't hang there anymore, however, the test will still fail and complain that ext4 is corrupted. And with this patch, the test won't hang due to stop_sync_thread() or fail due to ext4 is corrupted anymore. However, there is still a deadlock related to dm-raid456 that will be fixed in following patches.
CVE-2024-35799: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Prevent crash when disable stream [Why] Disabling stream encoder invokes a function that no longer exists. [How] Check if the function declaration is NULL in disable stream encoder.
CVE-2024-35803: In the Linux kernel, the following vulnerability has been resolved: x86/efistub: Call mixed mode boot services on the firmware's stack Normally, the EFI stub calls into the EFI boot services using the stack that was live when the stub was entered. According to the UEFI spec, this stack needs to be at least 128k in size - this might seem large but all asynchronous processing and event handling in EFI runs from the same stack and so quite a lot of space may be used in practice. In mixed mode, the situation is a bit different: the bootloader calls the 32-bit EFI stub entry point, which calls the decompressor's 32-bit entry point, where the boot stack is set up, using a fixed allocation of 16k. This stack is still in use when the EFI stub is started in 64-bit mode, and so all calls back into the EFI firmware will be using the decompressor's limited boot stack. Due to the placement of the boot stack right after the boot heap, any stack overruns have gone unnoticed. However, commit 5c4feadb0011983b ("x86/decompressor: Move global symbol references to C code") moved the definition of the boot heap into C code, and now the boot stack is placed right at the base of BSS, where any overruns will corrupt the end of the .data section. While it would be possible to work around this by increasing the size of the boot stack, doing so would affect all x86 systems, and mixed mode systems are a tiny (and shrinking) fraction of the x86 installed base. So instead, record the firmware stack pointer value when entering from the 32-bit firmware, and switch to this stack every time a EFI boot service call is made.
CVE-2024-35808: In the Linux kernel, the following vulnerability has been resolved: md/dm-raid: don't call md_reap_sync_thread() directly Currently md_reap_sync_thread() is called from raid_message() directly without holding 'reconfig_mutex', this is definitely unsafe because md_reap_sync_thread() can change many fields that is protected by 'reconfig_mutex'. However, hold 'reconfig_mutex' here is still problematic because this will cause deadlock, for example, commit 130443d60b1b ("md: refactor idle/frozen_sync_thread() to fix deadlock"). Fix this problem by using stop_sync_thread() to unregister sync_thread, like md/raid did.
CVE-2024-35817: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: amdgpu_ttm_gart_bind set gtt bound flag Otherwise after the GTT bo is released, the GTT and gart space is freed but amdgpu_ttm_backend_unbind will not clear the gart page table entry and leave valid mapping entry pointing to the stale system page. Then if GPU access the gart address mistakely, it will read undefined value instead page fault, harder to debug and reproduce the real issue.
CVE-2024-35826: In the Linux kernel, the following vulnerability has been resolved: block: Fix page refcounts for unaligned buffers in __bio_release_pages() Fix an incorrect number of pages being released for buffers that do not start at the beginning of a page.
CVE-2024-35839: In the Linux kernel, the following vulnerability has been resolved: netfilter: bridge: replace physindev with physinif in nf_bridge_info An skb can be added to a neigh->arp_queue while waiting for an arp reply. Where original skb's skb->dev can be different to neigh's neigh->dev. For instance in case of bridging dnated skb from one veth to another, the skb would be added to a neigh->arp_queue of the bridge. As skb->dev can be reset back to nf_bridge->physindev and used, and as there is no explicit mechanism that prevents this physindev from been freed under us (for instance neigh_flush_dev doesn't cleanup skbs from different device's neigh queue) we can crash on e.g. this stack: arp_process neigh_update skb = __skb_dequeue(&neigh->arp_queue) neigh_resolve_output(..., skb) ... br_nf_dev_xmit br_nf_pre_routing_finish_bridge_slow skb->dev = nf_bridge->physindev br_handle_frame_finish Let's use plain ifindex instead of net_device link. To peek into the original net_device we will use dev_get_by_index_rcu(). Thus either we get device and are safe to use it or we don't get it and drop skb.
CVE-2024-35840: In the Linux kernel, the following vulnerability has been resolved: mptcp: use OPTION_MPTCP_MPJ_SYNACK in subflow_finish_connect() subflow_finish_connect() uses four fields (backup, join_id, thmac, none) that may contain garbage unless OPTION_MPTCP_MPJ_SYNACK has been set in mptcp_parse_option()
CVE-2024-35844: In the Linux kernel, the following vulnerability has been resolved: f2fs: compress: fix reserve_cblocks counting error when out of space When a file only needs one direct_node, performing the following operations will cause the file to be unrepairable: unisoc # ./f2fs_io compress test.apk unisoc #df -h | grep dm-48 /dev/block/dm-48 112G 112G 1.2M 100% /data unisoc # ./f2fs_io release_cblocks test.apk 924 unisoc # df -h | grep dm-48 /dev/block/dm-48 112G 112G 4.8M 100% /data unisoc # dd if=/dev/random of=file4 bs=1M count=3 3145728 bytes (3.0 M) copied, 0.025 s, 120 M/s unisoc # df -h | grep dm-48 /dev/block/dm-48 112G 112G 1.8M 100% /data unisoc # ./f2fs_io reserve_cblocks test.apk F2FS_IOC_RESERVE_COMPRESS_BLOCKS failed: No space left on device adb reboot unisoc # df -h | grep dm-48 /dev/block/dm-48 112G 112G 11M 100% /data unisoc # ./f2fs_io reserve_cblocks test.apk 0 This is because the file has only one direct_node. After returning to -ENOSPC, reserved_blocks += ret will not be executed. As a result, the reserved_blocks at this time is still 0, which is not the real number of reserved blocks. Therefore, fsck cannot be set to repair the file. After this patch, the fsck flag will be set to fix this problem. unisoc # df -h | grep dm-48 /dev/block/dm-48 112G 112G 1.8M 100% /data unisoc # ./f2fs_io reserve_cblocks test.apk F2FS_IOC_RESERVE_COMPRESS_BLOCKS failed: No space left on device adb reboot then fsck will be executed unisoc # df -h | grep dm-48 /dev/block/dm-48 112G 112G 11M 100% /data unisoc # ./f2fs_io reserve_cblocks test.apk 924
CVE-2024-35863: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in is_valid_oplock_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35864: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_is_valid_lease_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35865: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_is_valid_oplock_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35868: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_stats_proc_write() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35870: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix UAF in smb2_reconnect_server() The UAF bug is due to smb2_reconnect_server() accessing a session that is already being teared down by another thread that is executing __cifs_put_smb_ses(). This can happen when (a) the client has connection to the server but no session or (b) another thread ends up setting @ses->ses_status again to something different than SES_EXITING. To fix this, we need to make sure to unconditionally set @ses->ses_status to SES_EXITING and prevent any other threads from setting a new status while we're still tearing it down. The following can be reproduced by adding some delay to right after the ipc is freed in __cifs_put_smb_ses() - which will give smb2_reconnect_server() worker a chance to run and then accessing @ses->ipc: kinit ... mount.cifs //srv/share /mnt/1 -o sec=krb5,nohandlecache,echo_interval=10 [disconnect srv] ls /mnt/1 &>/dev/null sleep 30 kdestroy [reconnect srv] sleep 10 umount /mnt/1 ... CIFS: VFS: Verify user has a krb5 ticket and keyutils is installed CIFS: VFS: \\srv Send error in SessSetup = -126 CIFS: VFS: Verify user has a krb5 ticket and keyutils is installed CIFS: VFS: \\srv Send error in SessSetup = -126 general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 50 Comm: kworker/3:1 Not tainted 6.9.0-rc2 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39 04/01/2014 Workqueue: cifsiod smb2_reconnect_server [cifs] RIP: 0010:__list_del_entry_valid_or_report+0x33/0xf0 Code: 4f 08 48 85 d2 74 42 48 85 c9 74 59 48 b8 00 01 00 00 00 00 ad de 48 39 c2 74 61 48 b8 22 01 00 00 00 00 74 69 <48> 8b 01 48 39 f8 75 7b 48 8b 72 08 48 39 c6 0f 85 88 00 00 00 b8 RSP: 0018:ffffc900001bfd70 EFLAGS: 00010a83 RAX: dead000000000122 RBX: ffff88810da53838 RCX: 6b6b6b6b6b6b6b6b RDX: 6b6b6b6b6b6b6b6b RSI: ffffffffc02f6878 RDI: ffff88810da53800 RBP: ffff88810da53800 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: ffff88810c064000 R13: 0000000000000001 R14: ffff88810c064000 R15: ffff8881039cc000 FS: 0000000000000000(0000) GS:ffff888157c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe3728b1000 CR3: 000000010caa4000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> ? die_addr+0x36/0x90 ? exc_general_protection+0x1c1/0x3f0 ? asm_exc_general_protection+0x26/0x30 ? __list_del_entry_valid_or_report+0x33/0xf0 __cifs_put_smb_ses+0x1ae/0x500 [cifs] smb2_reconnect_server+0x4ed/0x710 [cifs] process_one_work+0x205/0x6b0 worker_thread+0x191/0x360 ? __pfx_worker_thread+0x10/0x10 kthread+0xe2/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2024-35875: In the Linux kernel, the following vulnerability has been resolved: x86/coco: Require seeding RNG with RDRAND on CoCo systems There are few uses of CoCo that don't rely on working cryptography and hence a working RNG. Unfortunately, the CoCo threat model means that the VM host cannot be trusted and may actively work against guests to extract secrets or manipulate computation. Since a malicious host can modify or observe nearly all inputs to guests, the only remaining source of entropy for CoCo guests is RDRAND. If RDRAND is broken -- due to CPU hardware fault -- the RNG as a whole is meant to gracefully continue on gathering entropy from other sources, but since there aren't other sources on CoCo, this is catastrophic. This is mostly a concern at boot time when initially seeding the RNG, as after that the consequences of a broken RDRAND are much more theoretical. So, try at boot to seed the RNG using 256 bits of RDRAND output. If this fails, panic(). This will also trigger if the system is booted without RDRAND, as RDRAND is essential for a safe CoCo boot. Add this deliberately to be "just a CoCo x86 driver feature" and not part of the RNG itself. Many device drivers and platforms have some desire to contribute something to the RNG, and add_device_randomness() is specifically meant for this purpose. Any driver can call it with seed data of any quality, or even garbage quality, and it can only possibly make the quality of the RNG better or have no effect, but can never make it worse. Rather than trying to build something into the core of the RNG, consider the particular CoCo issue just a CoCo issue, and therefore separate it all out into driver (well, arch/platform) code. [ bp: Massage commit message. ]
CVE-2024-35887: In the Linux kernel, the following vulnerability has been resolved: ax25: fix use-after-free bugs caused by ax25_ds_del_timer When the ax25 device is detaching, the ax25_dev_device_down() calls ax25_ds_del_timer() to cleanup the slave_timer. When the timer handler is running, the ax25_ds_del_timer() that calls del_timer() in it will return directly. As a result, the use-after-free bugs could happen, one of the scenarios is shown below: (Thread 1) | (Thread 2) | ax25_ds_timeout() ax25_dev_device_down() | ax25_ds_del_timer() | del_timer() | ax25_dev_put() //FREE | | ax25_dev-> //USE In order to mitigate bugs, when the device is detaching, use timer_shutdown_sync() to stop the timer.
CVE-2024-35904: In the Linux kernel, the following vulnerability has been resolved: selinux: avoid dereference of garbage after mount failure In case kern_mount() fails and returns an error pointer return in the error branch instead of continuing and dereferencing the error pointer. While on it drop the never read static variable selinuxfs_mount.
CVE-2024-35924: In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: Limit read size on v1.2 Between UCSI 1.2 and UCSI 2.0, the size of the MESSAGE_IN region was increased from 16 to 256. In order to avoid overflowing reads for older systems, add a mechanism to use the read UCSI version to truncate read sizes on UCSI v1.2.
CVE-2024-35931: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Skip do PCI error slot reset during RAS recovery Why: The PCI error slot reset maybe triggered after inject ue to UMC multi times, this caused system hang. [ 557.371857] amdgpu 0000:af:00.0: amdgpu: GPU reset succeeded, trying to resume [ 557.373718] [drm] PCIE GART of 512M enabled. [ 557.373722] [drm] PTB located at 0x0000031FED700000 [ 557.373788] [drm] VRAM is lost due to GPU reset! [ 557.373789] [drm] PSP is resuming... [ 557.547012] mlx5_core 0000:55:00.0: mlx5_pci_err_detected Device state = 1 pci_status: 0. Exit, result = 3, need reset [ 557.547067] [drm] PCI error: detected callback, state(1)!! [ 557.547069] [drm] No support for XGMI hive yet... [ 557.548125] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 0. Enter [ 557.607763] mlx5_core 0000:55:00.0: wait vital counter value 0x16b5b after 1 iterations [ 557.607777] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 1. Exit, err = 0, result = 5, recovered [ 557.610492] [drm] PCI error: slot reset callback!! ... [ 560.689382] amdgpu 0000:3f:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689546] amdgpu 0000:5a:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689562] general protection fault, probably for non-canonical address 0x5f080b54534f611f: 0000 [#1] SMP NOPTI [ 560.701008] CPU: 16 PID: 2361 Comm: kworker/u448:9 Tainted: G OE 5.15.0-91-generic #101-Ubuntu [ 560.712057] Hardware name: Microsoft C278A/C278A, BIOS C2789.5.BS.1C11.AG.1 11/08/2023 [ 560.720959] Workqueue: amdgpu-reset-hive amdgpu_ras_do_recovery [amdgpu] [ 560.728887] RIP: 0010:amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.736891] Code: ff 41 89 c6 e9 1b ff ff ff 44 0f b6 45 b0 e9 4f ff ff ff be 01 00 00 00 4c 89 e7 e8 76 c9 8b ff 44 0f b6 45 b0 e9 3c fd ff ff <48> 83 ba 18 02 00 00 00 0f 84 6a f8 ff ff 48 8d 7a 78 be 01 00 00 [ 560.757967] RSP: 0018:ffa0000032e53d80 EFLAGS: 00010202 [ 560.763848] RAX: ffa00000001dfd10 RBX: ffa0000000197090 RCX: ffa0000032e53db0 [ 560.771856] RDX: 5f080b54534f5f07 RSI: 0000000000000000 RDI: ff11000128100010 [ 560.779867] RBP: ffa0000032e53df0 R08: 0000000000000000 R09: ffffffffffe77f08 [ 560.787879] R10: 0000000000ffff0a R11: 0000000000000001 R12: 0000000000000000 [ 560.795889] R13: ffa0000032e53e00 R14: 0000000000000000 R15: 0000000000000000 [ 560.803889] FS: 0000000000000000(0000) GS:ff11007e7e800000(0000) knlGS:0000000000000000 [ 560.812973] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 560.819422] CR2: 000055a04c118e68 CR3: 0000000007410005 CR4: 0000000000771ee0 [ 560.827433] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 560.835433] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 560.843444] PKRU: 55555554 [ 560.846480] Call Trace: [ 560.849225] <TASK> [ 560.851580] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.856488] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.861379] ? amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.867778] ? show_regs.part.0+0x23/0x29 [ 560.872293] ? __die_body.cold+0x8/0xd [ 560.876502] ? die_addr+0x3e/0x60 [ 560.880238] ? exc_general_protection+0x1c5/0x410 [ 560.885532] ? asm_exc_general_protection+0x27/0x30 [ 560.891025] ? amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.898323] amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.904520] process_one_work+0x228/0x3d0 How: In RAS recovery, mode-1 reset is issued from RAS fatal error handling and expected all the nodes in a hive to be reset. no need to issue another mode-1 during this procedure.
CVE-2024-35932: In the Linux kernel, the following vulnerability has been resolved: drm/vc4: don't check if plane->state->fb == state->fb Currently, when using non-blocking commits, we can see the following kernel warning: [ 110.908514] ------------[ cut here ]------------ [ 110.908529] refcount_t: underflow; use-after-free. [ 110.908620] WARNING: CPU: 0 PID: 1866 at lib/refcount.c:87 refcount_dec_not_one+0xb8/0xc0 [ 110.908664] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device cmac algif_hash aes_arm64 aes_generic algif_skcipher af_alg bnep hid_logitech_hidpp vc4 brcmfmac hci_uart btbcm brcmutil bluetooth snd_soc_hdmi_codec cfg80211 cec drm_display_helper drm_dma_helper drm_kms_helper snd_soc_core snd_compress snd_pcm_dmaengine fb_sys_fops sysimgblt syscopyarea sysfillrect raspberrypi_hwmon ecdh_generic ecc rfkill libaes i2c_bcm2835 binfmt_misc joydev snd_bcm2835(C) bcm2835_codec(C) bcm2835_isp(C) v4l2_mem2mem videobuf2_dma_contig snd_pcm bcm2835_v4l2(C) raspberrypi_gpiomem bcm2835_mmal_vchiq(C) videobuf2_v4l2 snd_timer videobuf2_vmalloc videobuf2_memops videobuf2_common snd videodev vc_sm_cma(C) mc hid_logitech_dj uio_pdrv_genirq uio i2c_dev drm fuse dm_mod drm_panel_orientation_quirks backlight ip_tables x_tables ipv6 [ 110.909086] CPU: 0 PID: 1866 Comm: kodi.bin Tainted: G C 6.1.66-v8+ #32 [ 110.909104] Hardware name: Raspberry Pi 3 Model B Rev 1.2 (DT) [ 110.909114] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 110.909132] pc : refcount_dec_not_one+0xb8/0xc0 [ 110.909152] lr : refcount_dec_not_one+0xb4/0xc0 [ 110.909170] sp : ffffffc00913b9c0 [ 110.909177] x29: ffffffc00913b9c0 x28: 000000556969bbb0 x27: 000000556990df60 [ 110.909205] x26: 0000000000000002 x25: 0000000000000004 x24: ffffff8004448480 [ 110.909230] x23: ffffff800570b500 x22: ffffff802e03a7bc x21: ffffffecfca68c78 [ 110.909257] x20: ffffff8002b42000 x19: ffffff802e03a600 x18: 0000000000000000 [ 110.909283] x17: 0000000000000011 x16: ffffffffffffffff x15: 0000000000000004 [ 110.909308] x14: 0000000000000fff x13: ffffffed577e47e0 x12: 0000000000000003 [ 110.909333] x11: 0000000000000000 x10: 0000000000000027 x9 : c912d0d083728c00 [ 110.909359] x8 : c912d0d083728c00 x7 : 65646e75203a745f x6 : 746e756f63666572 [ 110.909384] x5 : ffffffed579f62ee x4 : ffffffed579eb01e x3 : 0000000000000000 [ 110.909409] x2 : 0000000000000000 x1 : ffffffc00913b750 x0 : 0000000000000001 [ 110.909434] Call trace: [ 110.909441] refcount_dec_not_one+0xb8/0xc0 [ 110.909461] vc4_bo_dec_usecnt+0x4c/0x1b0 [vc4] [ 110.909903] vc4_cleanup_fb+0x44/0x50 [vc4] [ 110.910315] drm_atomic_helper_cleanup_planes+0x88/0xa4 [drm_kms_helper] [ 110.910669] vc4_atomic_commit_tail+0x390/0x9dc [vc4] [ 110.911079] commit_tail+0xb0/0x164 [drm_kms_helper] [ 110.911397] drm_atomic_helper_commit+0x1d0/0x1f0 [drm_kms_helper] [ 110.911716] drm_atomic_commit+0xb0/0xdc [drm] [ 110.912569] drm_mode_atomic_ioctl+0x348/0x4b8 [drm] [ 110.913330] drm_ioctl_kernel+0xec/0x15c [drm] [ 110.914091] drm_ioctl+0x24c/0x3b0 [drm] [ 110.914850] __arm64_sys_ioctl+0x9c/0xd4 [ 110.914873] invoke_syscall+0x4c/0x114 [ 110.914897] el0_svc_common+0xd0/0x118 [ 110.914917] do_el0_svc+0x38/0xd0 [ 110.914936] el0_svc+0x30/0x8c [ 110.914958] el0t_64_sync_handler+0x84/0xf0 [ 110.914979] el0t_64_sync+0x18c/0x190 [ 110.914996] ---[ end trace 0000000000000000 ]--- This happens because, although `prepare_fb` and `cleanup_fb` are perfectly balanced, we cannot guarantee consistency in the check plane->state->fb == state->fb. This means that sometimes we can increase the refcount in `prepare_fb` and don't decrease it in `cleanup_fb`. The opposite can also be true. In fact, the struct drm_plane .state shouldn't be accessed directly but instead, the `drm_atomic_get_new_plane_state()` helper function should be used. So, we could stick to this check, but using `drm_atomic_get_new_plane_state()`. But actually, this check is not re ---truncated---
CVE-2024-35938: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: decrease MHI channel buffer length to 8KB Currently buf_len field of ath11k_mhi_config_qca6390 is assigned with 0, making MHI use a default size, 64KB, to allocate channel buffers. This is likely to fail in some scenarios where system memory is highly fragmented and memory compaction or reclaim is not allowed. There is a fail report which is caused by it: kworker/u32:45: page allocation failure: order:4, mode:0x40c00(GFP_NOIO|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 CPU: 0 PID: 19318 Comm: kworker/u32:45 Not tainted 6.8.0-rc3-1.gae4495f-default #1 openSUSE Tumbleweed (unreleased) 493b6d5b382c603654d7a81fc3c144d59a1dfceb Workqueue: events_unbound async_run_entry_fn Call Trace: <TASK> dump_stack_lvl+0x47/0x60 warn_alloc+0x13a/0x1b0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __alloc_pages_direct_compact+0xab/0x210 __alloc_pages_slowpath.constprop.0+0xd3e/0xda0 __alloc_pages+0x32d/0x350 ? mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] __kmalloc_large_node+0x72/0x110 __kmalloc+0x37c/0x480 ? mhi_map_single_no_bb+0x77/0xf0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] ? mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] __mhi_prepare_for_transfer+0x44/0x80 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] ? __pfx_____mhi_prepare_for_transfer+0x10/0x10 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] device_for_each_child+0x5c/0xa0 ? __pfx_pci_pm_resume+0x10/0x10 ath11k_core_resume+0x65/0x100 [ath11k a5094e22d7223135c40d93c8f5321cf09fd85e4e] ? srso_alias_return_thunk+0x5/0xfbef5 ath11k_pci_pm_resume+0x32/0x60 [ath11k_pci 830b7bfc3ea80ebef32e563cafe2cb55e9cc73ec] ? srso_alias_return_thunk+0x5/0xfbef5 dpm_run_callback+0x8c/0x1e0 device_resume+0x104/0x340 ? __pfx_dpm_watchdog_handler+0x10/0x10 async_resume+0x1d/0x30 async_run_entry_fn+0x32/0x120 process_one_work+0x168/0x330 worker_thread+0x2f5/0x410 ? __pfx_worker_thread+0x10/0x10 kthread+0xe8/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Actually those buffers are used only by QMI target -> host communication. And for WCN6855 and QCA6390, the largest packet size for that is less than 6KB. So change buf_len field to 8KB, which results in order 1 allocation if page size is 4KB. In this way, we can at least save some memory, and as well as decrease the possibility of allocation failure in those scenarios. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
CVE-2024-35939: In the Linux kernel, the following vulnerability has been resolved: dma-direct: Leak pages on dma_set_decrypted() failure On TDX it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. DMA could free decrypted/shared pages if dma_set_decrypted() fails. This should be a rare case. Just leak the pages in this case instead of freeing them.
CVE-2024-35945: In the Linux kernel, the following vulnerability has been resolved: net: phy: phy_device: Prevent nullptr exceptions on ISR If phydev->irq is set unconditionally, check for valid interrupt handler or fall back to polling mode to prevent nullptr exceptions in interrupt service routine.
CVE-2024-35951: In the Linux kernel, the following vulnerability has been resolved: drm/panfrost: Fix the error path in panfrost_mmu_map_fault_addr() Subject: [PATCH] drm/panfrost: Fix the error path in panfrost_mmu_map_fault_addr() If some the pages or sgt allocation failed, we shouldn't release the pages ref we got earlier, otherwise we will end up with unbalanced get/put_pages() calls. We should instead leave everything in place and let the BO release function deal with extra cleanup when the object is destroyed, or let the fault handler try again next time it's called.
CVE-2024-35956: In the Linux kernel, the following vulnerability has been resolved: btrfs: qgroup: fix qgroup prealloc rsv leak in subvolume operations Create subvolume, create snapshot and delete subvolume all use btrfs_subvolume_reserve_metadata() to reserve metadata for the changes done to the parent subvolume's fs tree, which cannot be mediated in the normal way via start_transaction. When quota groups (squota or qgroups) are enabled, this reserves qgroup metadata of type PREALLOC. Once the operation is associated to a transaction, we convert PREALLOC to PERTRANS, which gets cleared in bulk at the end of the transaction. However, the error paths of these three operations were not implementing this lifecycle correctly. They unconditionally converted the PREALLOC to PERTRANS in a generic cleanup step regardless of errors or whether the operation was fully associated to a transaction or not. This resulted in error paths occasionally converting this rsv to PERTRANS without calling record_root_in_trans successfully, which meant that unless that root got recorded in the transaction by some other thread, the end of the transaction would not free that root's PERTRANS, leaking it. Ultimately, this resulted in hitting a WARN in CONFIG_BTRFS_DEBUG builds at unmount for the leaked reservation. The fix is to ensure that every qgroup PREALLOC reservation observes the following properties: 1. any failure before record_root_in_trans is called successfully results in freeing the PREALLOC reservation. 2. after record_root_in_trans, we convert to PERTRANS, and now the transaction owns freeing the reservation. This patch enforces those properties on the three operations. Without it, generic/269 with squotas enabled at mkfs time would fail in ~5-10 runs on my system. With this patch, it ran successfully 1000 times in a row.
CVE-2024-35971: In the Linux kernel, the following vulnerability has been resolved: net: ks8851: Handle softirqs at the end of IRQ thread to fix hang The ks8851_irq() thread may call ks8851_rx_pkts() in case there are any packets in the MAC FIFO, which calls netif_rx(). This netif_rx() implementation is guarded by local_bh_disable() and local_bh_enable(). The local_bh_enable() may call do_softirq() to run softirqs in case any are pending. One of the softirqs is net_rx_action, which ultimately reaches the driver .start_xmit callback. If that happens, the system hangs. The entire call chain is below: ks8851_start_xmit_par from netdev_start_xmit netdev_start_xmit from dev_hard_start_xmit dev_hard_start_xmit from sch_direct_xmit sch_direct_xmit from __dev_queue_xmit __dev_queue_xmit from __neigh_update __neigh_update from neigh_update neigh_update from arp_process.constprop.0 arp_process.constprop.0 from __netif_receive_skb_one_core __netif_receive_skb_one_core from process_backlog process_backlog from __napi_poll.constprop.0 __napi_poll.constprop.0 from net_rx_action net_rx_action from __do_softirq __do_softirq from call_with_stack call_with_stack from do_softirq do_softirq from __local_bh_enable_ip __local_bh_enable_ip from netif_rx netif_rx from ks8851_irq ks8851_irq from irq_thread_fn irq_thread_fn from irq_thread irq_thread from kthread kthread from ret_from_fork The hang happens because ks8851_irq() first locks a spinlock in ks8851_par.c ks8851_lock_par() spin_lock_irqsave(&ksp->lock, ...) and with that spinlock locked, calls netif_rx(). Once the execution reaches ks8851_start_xmit_par(), it calls ks8851_lock_par() again which attempts to claim the already locked spinlock again, and the hang happens. Move the do_softirq() call outside of the spinlock protected section of ks8851_irq() by disabling BHs around the entire spinlock protected section of ks8851_irq() handler. Place local_bh_enable() outside of the spinlock protected section, so that it can trigger do_softirq() without the ks8851_par.c ks8851_lock_par() spinlock being held, and safely call ks8851_start_xmit_par() without attempting to lock the already locked spinlock. Since ks8851_irq() is protected by local_bh_disable()/local_bh_enable() now, replace netif_rx() with __netif_rx() which is not duplicating the local_bh_disable()/local_bh_enable() calls.
CVE-2024-35995: In the Linux kernel, the following vulnerability has been resolved: ACPI: CPPC: Use access_width over bit_width for system memory accesses To align with ACPI 6.3+, since bit_width can be any 8-bit value, it cannot be depended on to be always on a clean 8b boundary. This was uncovered on the Cobalt 100 platform. SError Interrupt on CPU26, code 0xbe000011 -- SError CPU: 26 PID: 1510 Comm: systemd-udevd Not tainted 5.15.2.1-13 #1 Hardware name: MICROSOFT CORPORATION, BIOS MICROSOFT CORPORATION pstate: 62400009 (nZCv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--) pc : cppc_get_perf_caps+0xec/0x410 lr : cppc_get_perf_caps+0xe8/0x410 sp : ffff8000155ab730 x29: ffff8000155ab730 x28: ffff0080139d0038 x27: ffff0080139d0078 x26: 0000000000000000 x25: ffff0080139d0058 x24: 00000000ffffffff x23: ffff0080139d0298 x22: ffff0080139d0278 x21: 0000000000000000 x20: ffff00802b251910 x19: ffff0080139d0000 x18: ffffffffffffffff x17: 0000000000000000 x16: ffffdc7e111bad04 x15: ffff00802b251008 x14: ffffffffffffffff x13: ffff013f1fd63300 x12: 0000000000000006 x11: ffffdc7e128f4420 x10: 0000000000000000 x9 : ffffdc7e111badec x8 : ffff00802b251980 x7 : 0000000000000000 x6 : ffff0080139d0028 x5 : 0000000000000000 x4 : ffff0080139d0018 x3 : 00000000ffffffff x2 : 0000000000000008 x1 : ffff8000155ab7a0 x0 : 0000000000000000 Kernel panic - not syncing: Asynchronous SError Interrupt CPU: 26 PID: 1510 Comm: systemd-udevd Not tainted 5.15.2.1-13 #1 Hardware name: MICROSOFT CORPORATION, BIOS MICROSOFT CORPORATION Call trace: dump_backtrace+0x0/0x1e0 show_stack+0x24/0x30 dump_stack_lvl+0x8c/0xb8 dump_stack+0x18/0x34 panic+0x16c/0x384 add_taint+0x0/0xc0 arm64_serror_panic+0x7c/0x90 arm64_is_fatal_ras_serror+0x34/0xa4 do_serror+0x50/0x6c el1h_64_error_handler+0x40/0x74 el1h_64_error+0x7c/0x80 cppc_get_perf_caps+0xec/0x410 cppc_cpufreq_cpu_init+0x74/0x400 [cppc_cpufreq] cpufreq_online+0x2dc/0xa30 cpufreq_add_dev+0xc0/0xd4 subsys_interface_register+0x134/0x14c cpufreq_register_driver+0x1b0/0x354 cppc_cpufreq_init+0x1a8/0x1000 [cppc_cpufreq] do_one_initcall+0x50/0x250 do_init_module+0x60/0x27c load_module+0x2300/0x2570 __do_sys_finit_module+0xa8/0x114 __arm64_sys_finit_module+0x2c/0x3c invoke_syscall+0x78/0x100 el0_svc_common.constprop.0+0x180/0x1a0 do_el0_svc+0x84/0xa0 el0_svc+0x2c/0xc0 el0t_64_sync_handler+0xa4/0x12c el0t_64_sync+0x1a4/0x1a8 Instead, use access_width to determine the size and use the offset and width to shift and mask the bits to read/write out. Make sure to add a check for system memory since pcc redefines the access_width to subspace id. If access_width is not set, then fall back to using bit_width. [ rjw: Subject and changelog edits, comment adjustments ]
CVE-2024-36000: In the Linux kernel, the following vulnerability has been resolved: mm/hugetlb: fix missing hugetlb_lock for resv uncharge There is a recent report on UFFDIO_COPY over hugetlb: https://lore.kernel.org/all/000000000000ee06de0616177560@google.com/ 350: lockdep_assert_held(&hugetlb_lock); Should be an issue in hugetlb but triggered in an userfault context, where it goes into the unlikely path where two threads modifying the resv map together. Mike has a fix in that path for resv uncharge but it looks like the locking criteria was overlooked: hugetlb_cgroup_uncharge_folio_rsvd() will update the cgroup pointer, so it requires to be called with the lock held.
CVE-2024-36009: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix netdev refcount issue The dev_tracker is added to ax25_cb in ax25_bind(). When the ax25 device is detaching, the dev_tracker of ax25_cb should be deallocated in ax25_kill_by_device() instead of the dev_tracker of ax25_dev. The log reported by ref_tracker is shown below: [ 80.884935] ref_tracker: reference already released. [ 80.885150] ref_tracker: allocated in: [ 80.885349] ax25_dev_device_up+0x105/0x540 [ 80.885730] ax25_device_event+0xa4/0x420 [ 80.885730] notifier_call_chain+0xc9/0x1e0 [ 80.885730] __dev_notify_flags+0x138/0x280 [ 80.885730] dev_change_flags+0xd7/0x180 [ 80.885730] dev_ifsioc+0x6a9/0xa30 [ 80.885730] dev_ioctl+0x4d8/0xd90 [ 80.885730] sock_do_ioctl+0x1c2/0x2d0 [ 80.885730] sock_ioctl+0x38b/0x4f0 [ 80.885730] __se_sys_ioctl+0xad/0xf0 [ 80.885730] do_syscall_64+0xc4/0x1b0 [ 80.885730] entry_SYSCALL_64_after_hwframe+0x67/0x6f [ 80.885730] ref_tracker: freed in: [ 80.885730] ax25_device_event+0x272/0x420 [ 80.885730] notifier_call_chain+0xc9/0x1e0 [ 80.885730] dev_close_many+0x272/0x370 [ 80.885730] unregister_netdevice_many_notify+0x3b5/0x1180 [ 80.885730] unregister_netdev+0xcf/0x120 [ 80.885730] sixpack_close+0x11f/0x1b0 [ 80.885730] tty_ldisc_kill+0xcb/0x190 [ 80.885730] tty_ldisc_hangup+0x338/0x3d0 [ 80.885730] __tty_hangup+0x504/0x740 [ 80.885730] tty_release+0x46e/0xd80 [ 80.885730] __fput+0x37f/0x770 [ 80.885730] __x64_sys_close+0x7b/0xb0 [ 80.885730] do_syscall_64+0xc4/0x1b0 [ 80.885730] entry_SYSCALL_64_after_hwframe+0x67/0x6f [ 80.893739] ------------[ cut here ]------------ [ 80.894030] WARNING: CPU: 2 PID: 140 at lib/ref_tracker.c:255 ref_tracker_free+0x47b/0x6b0 [ 80.894297] Modules linked in: [ 80.894929] CPU: 2 PID: 140 Comm: ax25_conn_rel_6 Not tainted 6.9.0-rc4-g8cd26fd90c1a #11 [ 80.895190] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qem4 [ 80.895514] RIP: 0010:ref_tracker_free+0x47b/0x6b0 [ 80.895808] Code: 83 c5 18 4c 89 eb 48 c1 eb 03 8a 04 13 84 c0 0f 85 df 01 00 00 41 83 7d 00 00 75 4b 4c 89 ff 9 [ 80.896171] RSP: 0018:ffff888009edf8c0 EFLAGS: 00000286 [ 80.896339] RAX: 1ffff1100141ac00 RBX: 1ffff1100149463b RCX: dffffc0000000000 [ 80.896502] RDX: 0000000000000001 RSI: 0000000000000246 RDI: ffff88800a0d6518 [ 80.896925] RBP: ffff888009edf9b0 R08: ffff88806d3288d3 R09: 1ffff1100da6511a [ 80.897212] R10: dffffc0000000000 R11: ffffed100da6511b R12: ffff88800a4a31d4 [ 80.897859] R13: ffff88800a4a31d8 R14: dffffc0000000000 R15: ffff88800a0d6518 [ 80.898279] FS: 00007fd88b7fe700(0000) GS:ffff88806d300000(0000) knlGS:0000000000000000 [ 80.899436] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 80.900181] CR2: 00007fd88c001d48 CR3: 000000000993e000 CR4: 00000000000006f0 ... [ 80.935774] ref_tracker: sp%d@000000000bb9df3d has 1/1 users at [ 80.935774] ax25_bind+0x424/0x4e0 [ 80.935774] __sys_bind+0x1d9/0x270 [ 80.935774] __x64_sys_bind+0x75/0x80 [ 80.935774] do_syscall_64+0xc4/0x1b0 [ 80.935774] entry_SYSCALL_64_after_hwframe+0x67/0x6f Change ax25_dev->dev_tracker to the dev_tracker of ax25_cb in order to mitigate the bug.
CVE-2024-36013: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix slab-use-after-free in l2cap_connect() Extend a critical section to prevent chan from early freeing. Also make the l2cap_connect() return type void. Nothing is using the returned value but it is ugly to return a potentially freed pointer. Making it void will help with backports because earlier kernels did use the return value. Now the compile will break for kernels where this patch is not a complete fix. Call stack summary: [use] l2cap_bredr_sig_cmd l2cap_connect ┌ mutex_lock(&conn->chan_lock); │ chan = pchan->ops->new_connection(pchan); <- alloc chan │ __l2cap_chan_add(conn, chan); │ l2cap_chan_hold(chan); │ list_add(&chan->list, &conn->chan_l); ... (1) └ mutex_unlock(&conn->chan_lock); chan->conf_state ... (4) <- use after free [free] l2cap_conn_del ┌ mutex_lock(&conn->chan_lock); │ foreach chan in conn->chan_l: ... (2) │ l2cap_chan_put(chan); │ l2cap_chan_destroy │ kfree(chan) ... (3) <- chan freed └ mutex_unlock(&conn->chan_lock); ================================================================== BUG: KASAN: slab-use-after-free in instrument_atomic_read include/linux/instrumented.h:68 [inline] BUG: KASAN: slab-use-after-free in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline] BUG: KASAN: slab-use-after-free in l2cap_connect+0xa67/0x11a0 net/bluetooth/l2cap_core.c:4260 Read of size 8 at addr ffff88810bf040a0 by task kworker/u3:1/311
CVE-2024-36023: In the Linux kernel, the following vulnerability has been resolved: Julia Lawall reported this null pointer dereference, this should fix it.
CVE-2024-36024: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Disable idle reallow as part of command/gpint execution [Why] Workaroud for a race condition where DMCUB is in the process of committing to IPS1 during the handshake causing us to miss the transition into IPS2 and touch the INBOX1 RPTR causing a HW hang. [How] Disable the reallow to ensure that we have enough of a gap between entry and exit and we're not seeing back-to-back wake_and_executes.
CVE-2024-36029: In the Linux kernel, the following vulnerability has been resolved: mmc: sdhci-msm: pervent access to suspended controller Generic sdhci code registers LED device and uses host->runtime_suspended flag to protect access to it. The sdhci-msm driver doesn't set this flag, which causes a crash when LED is accessed while controller is runtime suspended. Fix this by setting the flag correctly.
CVE-2024-36244: In the Linux kernel, the following vulnerability has been resolved: net/sched: taprio: extend minimum interval restriction to entire cycle too It is possible for syzbot to side-step the restriction imposed by the blamed commit in the Fixes: tag, because the taprio UAPI permits a cycle-time different from (and potentially shorter than) the sum of entry intervals. We need one more restriction, which is that the cycle time itself must be larger than N * ETH_ZLEN bit times, where N is the number of schedule entries. This restriction needs to apply regardless of whether the cycle time came from the user or was the implicit, auto-calculated value, so we move the existing "cycle == 0" check outside the "if "(!new->cycle_time)" branch. This way covers both conditions and scenarios. Add a selftest which illustrates the issue triggered by syzbot.
CVE-2024-36331: Improper initialization of CPU cache memory could allow a privileged attacker with hypervisor access to overwrite SEV-SNP guest memory resulting in loss of data integrity.
CVE-2024-36478: In the Linux kernel, the following vulnerability has been resolved: null_blk: fix null-ptr-dereference while configuring 'power' and 'submit_queues' Writing 'power' and 'submit_queues' concurrently will trigger kernel panic: Test script: modprobe null_blk nr_devices=0 mkdir -p /sys/kernel/config/nullb/nullb0 while true; do echo 1 > submit_queues; echo 4 > submit_queues; done & while true; do echo 1 > power; echo 0 > power; done Test result: BUG: kernel NULL pointer dereference, address: 0000000000000148 Oops: 0000 [#1] PREEMPT SMP RIP: 0010:__lock_acquire+0x41d/0x28f0 Call Trace: <TASK> lock_acquire+0x121/0x450 down_write+0x5f/0x1d0 simple_recursive_removal+0x12f/0x5c0 blk_mq_debugfs_unregister_hctxs+0x7c/0x100 blk_mq_update_nr_hw_queues+0x4a3/0x720 nullb_update_nr_hw_queues+0x71/0xf0 [null_blk] nullb_device_submit_queues_store+0x79/0xf0 [null_blk] configfs_write_iter+0x119/0x1e0 vfs_write+0x326/0x730 ksys_write+0x74/0x150 This is because del_gendisk() can concurrent with blk_mq_update_nr_hw_queues(): nullb_device_power_store nullb_apply_submit_queues null_del_dev del_gendisk nullb_update_nr_hw_queues if (!dev->nullb) // still set while gendisk is deleted return 0 blk_mq_update_nr_hw_queues dev->nullb = NULL Fix this problem by resuing the global mutex to protect nullb_device_power_store() and nullb_update_nr_hw_queues() from configfs.
CVE-2024-36479: In the Linux kernel, the following vulnerability has been resolved: fpga: bridge: add owner module and take its refcount The current implementation of the fpga bridge assumes that the low-level module registers a driver for the parent device and uses its owner pointer to take the module's refcount. This approach is problematic since it can lead to a null pointer dereference while attempting to get the bridge if the parent device does not have a driver. To address this problem, add a module owner pointer to the fpga_bridge struct and use it to take the module's refcount. Modify the function for registering a bridge to take an additional owner module parameter and rename it to avoid conflicts. Use the old function name for a helper macro that automatically sets the module that registers the bridge as the owner. This ensures compatibility with existing low-level control modules and reduces the chances of registering a bridge without setting the owner. Also, update the documentation to keep it consistent with the new interface for registering an fpga bridge. Other changes: opportunistically move put_device() from __fpga_bridge_get() to fpga_bridge_get() and of_fpga_bridge_get() to improve code clarity since the bridge device is taken in these functions.
CVE-2024-36880: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: qca: add missing firmware sanity checks Add the missing sanity checks when parsing the firmware files before downloading them to avoid accessing and corrupting memory beyond the vmalloced buffer.
CVE-2024-36897: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Atom Integrated System Info v2_2 for DCN35 New request from KMD/VBIOS in order to support new UMA carveout model. This fixes a null dereference from accessing Ctx->dc_bios->integrated_info while it was NULL. DAL parses through the BIOS and extracts the necessary integrated_info but was missing a case for the new BIOS version 2.3.
CVE-2024-36898: In the Linux kernel, the following vulnerability has been resolved: gpiolib: cdev: fix uninitialised kfifo If a line is requested with debounce, and that results in debouncing in software, and the line is subsequently reconfigured to enable edge detection then the allocation of the kfifo to contain edge events is overlooked. This results in events being written to and read from an uninitialised kfifo. Read events are returned to userspace. Initialise the kfifo in the case where the software debounce is already active.
CVE-2024-36914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Skip on writeback when it's not applicable [WHY] dynamic memory safety error detector (KASAN) catches and generates error messages "BUG: KASAN: slab-out-of-bounds" as writeback connector does not support certain features which are not initialized. [HOW] Skip them when connector type is DRM_MODE_CONNECTOR_WRITEBACK.
CVE-2024-36915: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: fix nfc_llcp_setsockopt() unsafe copies syzbot reported unsafe calls to copy_from_sockptr() [1] Use copy_safe_from_sockptr() instead. [1] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in nfc_llcp_setsockopt+0x6c2/0x850 net/nfc/llcp_sock.c:255 Read of size 4 at addr ffff88801caa1ec3 by task syz-executor459/5078 CPU: 0 PID: 5078 Comm: syz-executor459 Not tainted 6.8.0-syzkaller-08951-gfe46a7dd189e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] copy_from_sockptr include/linux/sockptr.h:55 [inline] nfc_llcp_setsockopt+0x6c2/0x850 net/nfc/llcp_sock.c:255 do_sock_setsockopt+0x3b1/0x720 net/socket.c:2311 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfd/0x240 entry_SYSCALL_64_after_hwframe+0x6d/0x75 RIP: 0033:0x7f7fac07fd89 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 91 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fff660eb788 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f7fac07fd89 RDX: 0000000000000000 RSI: 0000000000000118 RDI: 0000000000000004 RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000000 R10: 0000000020000a80 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
CVE-2024-36917: In the Linux kernel, the following vulnerability has been resolved: block: fix overflow in blk_ioctl_discard() There is no check for overflow of 'start + len' in blk_ioctl_discard(). Hung task occurs if submit an discard ioctl with the following param: start = 0x80000000000ff000, len = 0x8000000000fff000; Add the overflow validation now.
CVE-2024-36922: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: read txq->read_ptr under lock If we read txq->read_ptr without lock, we can read the same value twice, then obtain the lock, and reclaim from there to two different places, but crucially reclaim the same entry twice, resulting in the WARN_ONCE() a little later. Fix that by reading txq->read_ptr under lock.
CVE-2024-36924: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Release hbalock before calling lpfc_worker_wake_up() lpfc_worker_wake_up() calls the lpfc_work_done() routine, which takes the hbalock. Thus, lpfc_worker_wake_up() should not be called while holding the hbalock to avoid potential deadlock.
CVE-2024-36928: In the Linux kernel, the following vulnerability has been resolved: s390/qeth: Fix kernel panic after setting hsuid Symptom: When the hsuid attribute is set for the first time on an IQD Layer3 device while the corresponding network interface is already UP, the kernel will try to execute a napi function pointer that is NULL. Example: --------------------------------------------------------------------------- [ 2057.572696] illegal operation: 0001 ilc:1 [#1] SMP [ 2057.572702] Modules linked in: af_iucv qeth_l3 zfcp scsi_transport_fc sunrpc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nf_tables_set nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink ghash_s390 prng xts aes_s390 des_s390 de s_generic sha3_512_s390 sha3_256_s390 sha512_s390 vfio_ccw vfio_mdev mdev vfio_iommu_type1 eadm_sch vfio ext4 mbcache jbd2 qeth_l2 bridge stp llc dasd_eckd_mod qeth dasd_mod qdio ccwgroup pkey zcrypt [ 2057.572739] CPU: 6 PID: 60182 Comm: stress_client Kdump: loaded Not tainted 4.18.0-541.el8.s390x #1 [ 2057.572742] Hardware name: IBM 3931 A01 704 (LPAR) [ 2057.572744] Krnl PSW : 0704f00180000000 0000000000000002 (0x2) [ 2057.572748] R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:3 PM:0 RI:0 EA:3 [ 2057.572751] Krnl GPRS: 0000000000000004 0000000000000000 00000000a3b008d8 0000000000000000 [ 2057.572754] 00000000a3b008d8 cb923a29c779abc5 0000000000000000 00000000814cfd80 [ 2057.572756] 000000000000012c 0000000000000000 00000000a3b008d8 00000000a3b008d8 [ 2057.572758] 00000000bab6d500 00000000814cfd80 0000000091317e46 00000000814cfc68 [ 2057.572762] Krnl Code:#0000000000000000: 0000 illegal >0000000000000002: 0000 illegal 0000000000000004: 0000 illegal 0000000000000006: 0000 illegal 0000000000000008: 0000 illegal 000000000000000a: 0000 illegal 000000000000000c: 0000 illegal 000000000000000e: 0000 illegal [ 2057.572800] Call Trace: [ 2057.572801] ([<00000000ec639700>] 0xec639700) [ 2057.572803] [<00000000913183e2>] net_rx_action+0x2ba/0x398 [ 2057.572809] [<0000000091515f76>] __do_softirq+0x11e/0x3a0 [ 2057.572813] [<0000000090ce160c>] do_softirq_own_stack+0x3c/0x58 [ 2057.572817] ([<0000000090d2cbd6>] do_softirq.part.1+0x56/0x60) [ 2057.572822] [<0000000090d2cc60>] __local_bh_enable_ip+0x80/0x98 [ 2057.572825] [<0000000091314706>] __dev_queue_xmit+0x2be/0xd70 [ 2057.572827] [<000003ff803dd6d6>] afiucv_hs_send+0x24e/0x300 [af_iucv] [ 2057.572830] [<000003ff803dd88a>] iucv_send_ctrl+0x102/0x138 [af_iucv] [ 2057.572833] [<000003ff803de72a>] iucv_sock_connect+0x37a/0x468 [af_iucv] [ 2057.572835] [<00000000912e7e90>] __sys_connect+0xa0/0xd8 [ 2057.572839] [<00000000912e9580>] sys_socketcall+0x228/0x348 [ 2057.572841] [<0000000091514e1a>] system_call+0x2a6/0x2c8 [ 2057.572843] Last Breaking-Event-Address: [ 2057.572844] [<0000000091317e44>] __napi_poll+0x4c/0x1d8 [ 2057.572846] [ 2057.572847] Kernel panic - not syncing: Fatal exception in interrupt ------------------------------------------------------------------------------------------- Analysis: There is one napi structure per out_q: card->qdio.out_qs[i].napi The napi.poll functions are set during qeth_open(). Since commit 1cfef80d4c2b ("s390/qeth: Don't call dev_close/dev_open (DOWN/UP)") qeth_set_offline()/qeth_set_online() no longer call dev_close()/ dev_open(). So if qeth_free_qdio_queues() cleared card->qdio.out_qs[i].napi.poll while the network interface was UP and the card was offline, they are not set again. Reproduction: chzdev -e $devno layer2=0 ip link set dev $network_interface up echo 0 > /sys/bus/ccw ---truncated---
CVE-2024-36949: In the Linux kernel, the following vulnerability has been resolved: amd/amdkfd: sync all devices to wait all processes being evicted If there are more than one device doing reset in parallel, the first device will call kfd_suspend_all_processes() to evict all processes on all devices, this call takes time to finish. other device will start reset and recover without waiting. if the process has not been evicted before doing recover, it will be restored, then caused page fault.
CVE-2024-36951: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: range check cp bad op exception interrupts Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well.
CVE-2024-36952: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Move NPIV's transport unregistration to after resource clean up There are cases after NPIV deletion where the fabric switch still believes the NPIV is logged into the fabric. This occurs when a vport is unregistered before the Remove All DA_ID CT and LOGO ELS are sent to the fabric. Currently fc_remove_host(), which calls dev_loss_tmo for all D_IDs including the fabric D_ID, removes the last ndlp reference and frees the ndlp rport object. This sometimes causes the race condition where the final DA_ID and LOGO are skipped from being sent to the fabric switch. Fix by moving the fc_remove_host() and scsi_remove_host() calls after DA_ID and LOGO are sent.
CVE-2024-36968: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() l2cap_le_flowctl_init() can cause both div-by-zero and an integer overflow since hdev->le_mtu may not fall in the valid range. Move MTU from hci_dev to hci_conn to validate MTU and stop the connection process earlier if MTU is invalid. Also, add a missing validation in read_buffer_size() and make it return an error value if the validation fails. Now hci_conn_add() returns ERR_PTR() as it can fail due to the both a kzalloc failure and invalid MTU value. divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 67 Comm: kworker/u5:0 Tainted: G W 6.9.0-rc5+ #20 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: hci0 hci_rx_work RIP: 0010:l2cap_le_flowctl_init+0x19e/0x3f0 net/bluetooth/l2cap_core.c:547 Code: e8 17 17 0c 00 66 41 89 9f 84 00 00 00 bf 01 00 00 00 41 b8 02 00 00 00 4c 89 fe 4c 89 e2 89 d9 e8 27 17 0c 00 44 89 f0 31 d2 <66> f7 f3 89 c3 ff c3 4d 8d b7 88 00 00 00 4c 89 f0 48 c1 e8 03 42 RSP: 0018:ffff88810bc0f858 EFLAGS: 00010246 RAX: 00000000000002a0 RBX: 0000000000000000 RCX: dffffc0000000000 RDX: 0000000000000000 RSI: ffff88810bc0f7c0 RDI: ffffc90002dcb66f RBP: ffff88810bc0f880 R08: aa69db2dda70ff01 R09: 0000ffaaaaaaaaaa R10: 0084000000ffaaaa R11: 0000000000000000 R12: ffff88810d65a084 R13: dffffc0000000000 R14: 00000000000002a0 R15: ffff88810d65a000 FS: 0000000000000000(0000) GS:ffff88811ac00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000100 CR3: 0000000103268003 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: <TASK> l2cap_le_connect_req net/bluetooth/l2cap_core.c:4902 [inline] l2cap_le_sig_cmd net/bluetooth/l2cap_core.c:5420 [inline] l2cap_le_sig_channel net/bluetooth/l2cap_core.c:5486 [inline] l2cap_recv_frame+0xe59d/0x11710 net/bluetooth/l2cap_core.c:6809 l2cap_recv_acldata+0x544/0x10a0 net/bluetooth/l2cap_core.c:7506 hci_acldata_packet net/bluetooth/hci_core.c:3939 [inline] hci_rx_work+0x5e5/0xb20 net/bluetooth/hci_core.c:4176 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0x90f/0x1530 kernel/workqueue.c:3335 worker_thread+0x926/0xe70 kernel/workqueue.c:3416 kthread+0x2e3/0x380 kernel/kthread.c:388 ret_from_fork+0x5c/0x90 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]---
CVE-2024-36969: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix division by zero in setup_dsc_config When slice_height is 0, the division by slice_height in the calculation of the number of slices will cause a division by zero driver crash. This leaves the kernel in a state that requires a reboot. This patch adds a check to avoid the division by zero. The stack trace below is for the 6.8.4 Kernel. I reproduced the issue on a Z16 Gen 2 Lenovo Thinkpad with a Apple Studio Display monitor connected via Thunderbolt. The amdgpu driver crashed with this exception when I rebooted the system with the monitor connected. kernel: ? die (arch/x86/kernel/dumpstack.c:421 arch/x86/kernel/dumpstack.c:434 arch/x86/kernel/dumpstack.c:447) kernel: ? do_trap (arch/x86/kernel/traps.c:113 arch/x86/kernel/traps.c:154) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? do_error_trap (./arch/x86/include/asm/traps.h:58 arch/x86/kernel/traps.c:175) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? exc_divide_error (arch/x86/kernel/traps.c:194 (discriminator 2)) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? asm_exc_divide_error (./arch/x86/include/asm/idtentry.h:548) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: dc_dsc_compute_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1109) amdgpu After applying this patch, the driver no longer crashes when the monitor is connected and the system is rebooted. I believe this is the same issue reported for 3113.
CVE-2024-37021: In the Linux kernel, the following vulnerability has been resolved: fpga: manager: add owner module and take its refcount The current implementation of the fpga manager assumes that the low-level module registers a driver for the parent device and uses its owner pointer to take the module's refcount. This approach is problematic since it can lead to a null pointer dereference while attempting to get the manager if the parent device does not have a driver. To address this problem, add a module owner pointer to the fpga_manager struct and use it to take the module's refcount. Modify the functions for registering the manager to take an additional owner module parameter and rename them to avoid conflicts. Use the old function names for helper macros that automatically set the module that registers the manager as the owner. This ensures compatibility with existing low-level control modules and reduces the chances of registering a manager without setting the owner. Also, update the documentation to keep it consistent with the new interface for registering an fpga manager. Other changes: opportunistically move put_device() from __fpga_mgr_get() to fpga_mgr_get() and of_fpga_mgr_get() to improve code clarity since the manager device is taken in these functions.
CVE-2024-37354: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix crash on racing fsync and size-extending write into prealloc We have been seeing crashes on duplicate keys in btrfs_set_item_key_safe(): BTRFS critical (device vdb): slot 4 key (450 108 8192) new key (450 108 8192) ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:2620! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 3139 Comm: xfs_io Kdump: loaded Not tainted 6.9.0 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:btrfs_set_item_key_safe+0x11f/0x290 [btrfs] With the following stack trace: #0 btrfs_set_item_key_safe (fs/btrfs/ctree.c:2620:4) #1 btrfs_drop_extents (fs/btrfs/file.c:411:4) #2 log_one_extent (fs/btrfs/tree-log.c:4732:9) #3 btrfs_log_changed_extents (fs/btrfs/tree-log.c:4955:9) #4 btrfs_log_inode (fs/btrfs/tree-log.c:6626:9) #5 btrfs_log_inode_parent (fs/btrfs/tree-log.c:7070:8) #6 btrfs_log_dentry_safe (fs/btrfs/tree-log.c:7171:8) #7 btrfs_sync_file (fs/btrfs/file.c:1933:8) #8 vfs_fsync_range (fs/sync.c:188:9) #9 vfs_fsync (fs/sync.c:202:9) #10 do_fsync (fs/sync.c:212:9) #11 __do_sys_fdatasync (fs/sync.c:225:9) #12 __se_sys_fdatasync (fs/sync.c:223:1) #13 __x64_sys_fdatasync (fs/sync.c:223:1) #14 do_syscall_x64 (arch/x86/entry/common.c:52:14) #15 do_syscall_64 (arch/x86/entry/common.c:83:7) #16 entry_SYSCALL_64+0xaf/0x14c (arch/x86/entry/entry_64.S:121) So we're logging a changed extent from fsync, which is splitting an extent in the log tree. But this split part already exists in the tree, triggering the BUG(). This is the state of the log tree at the time of the crash, dumped with drgn (https://github.com/osandov/drgn/blob/main/contrib/btrfs_tree.py) to get more details than btrfs_print_leaf() gives us: >>> print_extent_buffer(prog.crashed_thread().stack_trace()[0]["eb"]) leaf 33439744 level 0 items 72 generation 9 owner 18446744073709551610 leaf 33439744 flags 0x100000000000000 fs uuid e5bd3946-400c-4223-8923-190ef1f18677 chunk uuid d58cb17e-6d02-494a-829a-18b7d8a399da item 0 key (450 INODE_ITEM 0) itemoff 16123 itemsize 160 generation 7 transid 9 size 8192 nbytes 8473563889606862198 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 sequence 204 flags 0x10(PREALLOC) atime 1716417703.220000000 (2024-05-22 15:41:43) ctime 1716417704.983333333 (2024-05-22 15:41:44) mtime 1716417704.983333333 (2024-05-22 15:41:44) otime 17592186044416.000000000 (559444-03-08 01:40:16) item 1 key (450 INODE_REF 256) itemoff 16110 itemsize 13 index 195 namelen 3 name: 193 item 2 key (450 XATTR_ITEM 1640047104) itemoff 16073 itemsize 37 location key (0 UNKNOWN.0 0) type XATTR transid 7 data_len 1 name_len 6 name: user.a data a item 3 key (450 EXTENT_DATA 0) itemoff 16020 itemsize 53 generation 9 type 1 (regular) extent data disk byte 303144960 nr 12288 extent data offset 0 nr 4096 ram 12288 extent compression 0 (none) item 4 key (450 EXTENT_DATA 4096) itemoff 15967 itemsize 53 generation 9 type 2 (prealloc) prealloc data disk byte 303144960 nr 12288 prealloc data offset 4096 nr 8192 item 5 key (450 EXTENT_DATA 8192) itemoff 15914 itemsize 53 generation 9 type 2 (prealloc) prealloc data disk byte 303144960 nr 12288 prealloc data offset 8192 nr 4096 ... So the real problem happened earlier: notice that items 4 (4k-12k) and 5 (8k-12k) overlap. Both are prealloc extents. Item 4 straddles i_size and item 5 starts at i_size. Here is the state of ---truncated---
CVE-2024-38540: In the Linux kernel, the following vulnerability has been resolved: bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq Undefined behavior is triggered when bnxt_qplib_alloc_init_hwq is called with hwq_attr->aux_depth != 0 and hwq_attr->aux_stride == 0. In that case, "roundup_pow_of_two(hwq_attr->aux_stride)" gets called. roundup_pow_of_two is documented as undefined for 0. Fix it in the one caller that had this combination. The undefined behavior was detected by UBSAN: UBSAN: shift-out-of-bounds in ./include/linux/log2.h:57:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 24 PID: 1075 Comm: (udev-worker) Not tainted 6.9.0-rc6+ #4 Hardware name: Abacus electric, s.r.o. - servis@abacus.cz Super Server/H12SSW-iN, BIOS 2.7 10/25/2023 Call Trace: <TASK> dump_stack_lvl+0x5d/0x80 ubsan_epilogue+0x5/0x30 __ubsan_handle_shift_out_of_bounds.cold+0x61/0xec __roundup_pow_of_two+0x25/0x35 [bnxt_re] bnxt_qplib_alloc_init_hwq+0xa1/0x470 [bnxt_re] bnxt_qplib_create_qp+0x19e/0x840 [bnxt_re] bnxt_re_create_qp+0x9b1/0xcd0 [bnxt_re] ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? __kmalloc+0x1b6/0x4f0 ? create_qp.part.0+0x128/0x1c0 [ib_core] ? __pfx_bnxt_re_create_qp+0x10/0x10 [bnxt_re] create_qp.part.0+0x128/0x1c0 [ib_core] ib_create_qp_kernel+0x50/0xd0 [ib_core] create_mad_qp+0x8e/0xe0 [ib_core] ? __pfx_qp_event_handler+0x10/0x10 [ib_core] ib_mad_init_device+0x2be/0x680 [ib_core] add_client_context+0x10d/0x1a0 [ib_core] enable_device_and_get+0xe0/0x1d0 [ib_core] ib_register_device+0x53c/0x630 [ib_core] ? srso_alias_return_thunk+0x5/0xfbef5 bnxt_re_probe+0xbd8/0xe50 [bnxt_re] ? __pfx_bnxt_re_probe+0x10/0x10 [bnxt_re] auxiliary_bus_probe+0x49/0x80 ? driver_sysfs_add+0x57/0xc0 really_probe+0xde/0x340 ? pm_runtime_barrier+0x54/0x90 ? __pfx___driver_attach+0x10/0x10 __driver_probe_device+0x78/0x110 driver_probe_device+0x1f/0xa0 __driver_attach+0xba/0x1c0 bus_for_each_dev+0x8f/0xe0 bus_add_driver+0x146/0x220 driver_register+0x72/0xd0 __auxiliary_driver_register+0x6e/0xd0 ? __pfx_bnxt_re_mod_init+0x10/0x10 [bnxt_re] bnxt_re_mod_init+0x3e/0xff0 [bnxt_re] ? __pfx_bnxt_re_mod_init+0x10/0x10 [bnxt_re] do_one_initcall+0x5b/0x310 do_init_module+0x90/0x250 init_module_from_file+0x86/0xc0 idempotent_init_module+0x121/0x2b0 __x64_sys_finit_module+0x5e/0xb0 do_syscall_64+0x82/0x160 ? srso_alias_return_thunk+0x5/0xfbef5 ? syscall_exit_to_user_mode_prepare+0x149/0x170 ? srso_alias_return_thunk+0x5/0xfbef5 ? syscall_exit_to_user_mode+0x75/0x230 ? srso_alias_return_thunk+0x5/0xfbef5 ? do_syscall_64+0x8e/0x160 ? srso_alias_return_thunk+0x5/0xfbef5 ? __count_memcg_events+0x69/0x100 ? srso_alias_return_thunk+0x5/0xfbef5 ? count_memcg_events.constprop.0+0x1a/0x30 ? srso_alias_return_thunk+0x5/0xfbef5 ? handle_mm_fault+0x1f0/0x300 ? srso_alias_return_thunk+0x5/0xfbef5 ? do_user_addr_fault+0x34e/0x640 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f4e5132821d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d e3 db 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffca9c906a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 0000563ec8a8f130 RCX: 00007f4e5132821d RDX: 0000000000000000 RSI: 00007f4e518fa07d RDI: 000000000000003b RBP: 00007ffca9c90760 R08: 00007f4e513f6b20 R09: 00007ffca9c906f0 R10: 0000563ec8a8faa0 R11: 0000000000000246 R12: 00007f4e518fa07d R13: 0000000000020000 R14: 0000563ec8409e90 R15: 0000563ec8a8fa60 </TASK> ---[ end trace ]---
CVE-2024-38543: In the Linux kernel, the following vulnerability has been resolved: lib/test_hmm.c: handle src_pfns and dst_pfns allocation failure The kcalloc() in dmirror_device_evict_chunk() will return null if the physical memory has run out. As a result, if src_pfns or dst_pfns is dereferenced, the null pointer dereference bug will happen. Moreover, the device is going away. If the kcalloc() fails, the pages mapping a chunk could not be evicted. So add a __GFP_NOFAIL flag in kcalloc(). Finally, as there is no need to have physically contiguous memory, Switch kcalloc() to kvcalloc() in order to avoid failing allocations.
CVE-2024-38545: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix UAF for cq async event The refcount of CQ is not protected by locks. When CQ asynchronous events and CQ destruction are concurrent, CQ may have been released, which will cause UAF. Use the xa_lock() to protect the CQ refcount.
CVE-2024-38553: In the Linux kernel, the following vulnerability has been resolved: net: fec: remove .ndo_poll_controller to avoid deadlocks There is a deadlock issue found in sungem driver, please refer to the commit ac0a230f719b ("eth: sungem: remove .ndo_poll_controller to avoid deadlocks"). The root cause of the issue is that netpoll is in atomic context and disable_irq() is called by .ndo_poll_controller interface of sungem driver, however, disable_irq() might sleep. After analyzing the implementation of fec_poll_controller(), the fec driver should have the same issue. Due to the fec driver uses NAPI for TX completions, the .ndo_poll_controller is unnecessary to be implemented in the fec driver, so fec_poll_controller() can be safely removed.
CVE-2024-38554: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix reference count leak issue of net_device There is a reference count leak issue of the object "net_device" in ax25_dev_device_down(). When the ax25 device is shutting down, the ax25_dev_device_down() drops the reference count of net_device one or zero times depending on if we goto unlock_put or not, which will cause memory leak. In order to solve the above issue, decrease the reference count of net_device after dev->ax25_ptr is set to null.
CVE-2024-38556: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Add a timeout to acquire the command queue semaphore Prevent forced completion handling on an entry that has not yet been assigned an index, causing an out of bounds access on idx = -22. Instead of waiting indefinitely for the sem, blocking flow now waits for index to be allocated or a sem acquisition timeout before beginning the timer for FW completion. Kernel log example: mlx5_core 0000:06:00.0: wait_func_handle_exec_timeout:1128:(pid 185911): cmd[-22]: CREATE_UCTX(0xa04) No done completion
CVE-2024-38564: In the Linux kernel, the following vulnerability has been resolved: bpf: Add BPF_PROG_TYPE_CGROUP_SKB attach type enforcement in BPF_LINK_CREATE bpf_prog_attach uses attach_type_to_prog_type to enforce proper attach type for BPF_PROG_TYPE_CGROUP_SKB. link_create uses bpf_prog_get and relies on bpf_prog_attach_check_attach_type to properly verify prog_type <> attach_type association. Add missing attach_type enforcement for the link_create case. Otherwise, it's currently possible to attach cgroup_skb prog types to other cgroup hooks.
CVE-2024-38570: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix potential glock use-after-free on unmount When a DLM lockspace is released and there ares still locks in that lockspace, DLM will unlock those locks automatically. Commit fb6791d100d1b started exploiting this behavior to speed up filesystem unmount: gfs2 would simply free glocks it didn't want to unlock and then release the lockspace. This didn't take the bast callbacks for asynchronous lock contention notifications into account, which remain active until until a lock is unlocked or its lockspace is released. To prevent those callbacks from accessing deallocated objects, put the glocks that should not be unlocked on the sd_dead_glocks list, release the lockspace, and only then free those glocks. As an additional measure, ignore unexpected ast and bast callbacks if the receiving glock is dead.
CVE-2024-38580: In the Linux kernel, the following vulnerability has been resolved: epoll: be better about file lifetimes epoll can call out to vfs_poll() with a file pointer that may race with the last 'fput()'. That would make f_count go down to zero, and while the ep->mtx locking means that the resulting file pointer tear-down will be blocked until the poll returns, it means that f_count is already dead, and any use of it won't actually get a reference to the file any more: it's dead regardless. Make sure we have a valid ref on the file pointer before we call down to vfs_poll() from the epoll routines.
CVE-2024-38581: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/mes: fix use-after-free issue Delete fence fallback timer to fix the ramdom use-after-free issue. v2: move to amdgpu_mes.c
CVE-2024-38594: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: move the EST lock to struct stmmac_priv Reinitialize the whole EST structure would also reset the mutex lock which is embedded in the EST structure, and then trigger the following warning. To address this, move the lock to struct stmmac_priv. We also need to reacquire the mutex lock when doing this initialization. DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 505 at kernel/locking/mutex.c:587 __mutex_lock+0xd84/0x1068 Modules linked in: CPU: 3 PID: 505 Comm: tc Not tainted 6.9.0-rc6-00053-g0106679839f7-dirty #29 Hardware name: NXP i.MX8MPlus EVK board (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __mutex_lock+0xd84/0x1068 lr : __mutex_lock+0xd84/0x1068 sp : ffffffc0864e3570 x29: ffffffc0864e3570 x28: ffffffc0817bdc78 x27: 0000000000000003 x26: ffffff80c54f1808 x25: ffffff80c9164080 x24: ffffffc080d723ac x23: 0000000000000000 x22: 0000000000000002 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffc083bc3000 x18: ffffffffffffffff x17: ffffffc08117b080 x16: 0000000000000002 x15: ffffff80d2d40000 x14: 00000000000002da x13: ffffff80d2d404b8 x12: ffffffc082b5a5c8 x11: ffffffc082bca680 x10: ffffffc082bb2640 x9 : ffffffc082bb2698 x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001 x5 : ffffff8178fe0d48 x4 : 0000000000000000 x3 : 0000000000000027 x2 : ffffff8178fe0d50 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: __mutex_lock+0xd84/0x1068 mutex_lock_nested+0x28/0x34 tc_setup_taprio+0x118/0x68c stmmac_setup_tc+0x50/0xf0 taprio_change+0x868/0xc9c
CVE-2024-38602: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix reference count leak issues of ax25_dev The ax25_addr_ax25dev() and ax25_dev_device_down() exist a reference count leak issue of the object "ax25_dev". Memory leak issue in ax25_addr_ax25dev(): The reference count of the object "ax25_dev" can be increased multiple times in ax25_addr_ax25dev(). This will cause a memory leak. Memory leak issues in ax25_dev_device_down(): The reference count of ax25_dev is set to 1 in ax25_dev_device_up() and then increase the reference count when ax25_dev is added to ax25_dev_list. As a result, the reference count of ax25_dev is 2. But when the device is shutting down. The ax25_dev_device_down() drops the reference count once or twice depending on if we goto unlock_put or not, which will cause memory leak. As for the issue of ax25_addr_ax25dev(), it is impossible for one pointer to be on a list twice. So add a break in ax25_addr_ax25dev(). As for the issue of ax25_dev_device_down(), increase the reference count of ax25_dev once in ax25_dev_device_up() and decrease the reference count of ax25_dev after it is removed from the ax25_dev_list.
CVE-2024-38608: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix netif state handling mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]---
CVE-2024-38620: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HCI: Remove HCI_AMP support Since BT_HS has been remove HCI_AMP controllers no longer has any use so remove it along with the capability of creating AMP controllers. Since we no longer need to differentiate between AMP and Primary controllers, as only HCI_PRIMARY is left, this also remove hdev->dev_type altogether.
CVE-2024-38630: In the Linux kernel, the following vulnerability has been resolved: watchdog: cpu5wdt.c: Fix use-after-free bug caused by cpu5wdt_trigger When the cpu5wdt module is removing, the origin code uses del_timer() to de-activate the timer. If the timer handler is running, del_timer() could not stop it and will return directly. If the port region is released by release_region() and then the timer handler cpu5wdt_trigger() calls outb() to write into the region that is released, the use-after-free bug will happen. Change del_timer() to timer_shutdown_sync() in order that the timer handler could be finished before the port region is released.
CVE-2024-38632: In the Linux kernel, the following vulnerability has been resolved: vfio/pci: fix potential memory leak in vfio_intx_enable() If vfio_irq_ctx_alloc() failed will lead to 'name' memory leak.
CVE-2024-38667: In the Linux kernel, the following vulnerability has been resolved: riscv: prevent pt_regs corruption for secondary idle threads Top of the kernel thread stack should be reserved for pt_regs. However this is not the case for the idle threads of the secondary boot harts. Their stacks overlap with their pt_regs, so both may get corrupted. Similar issue has been fixed for the primary hart, see c7cdd96eca28 ("riscv: prevent stack corruption by reserving task_pt_regs(p) early"). However that fix was not propagated to the secondary harts. The problem has been noticed in some CPU hotplug tests with V enabled. The function smp_callin stored several registers on stack, corrupting top of pt_regs structure including status field. As a result, kernel attempted to save or restore inexistent V context.
CVE-2024-39472: In the Linux kernel, the following vulnerability has been resolved: xfs: fix log recovery buffer allocation for the legacy h_size fixup Commit a70f9fe52daa ("xfs: detect and handle invalid iclog size set by mkfs") added a fixup for incorrect h_size values used for the initial umount record in old xfsprogs versions. Later commit 0c771b99d6c9 ("xfs: clean up calculation of LR header blocks") cleaned up the log reover buffer calculation, but stoped using the fixed up h_size value to size the log recovery buffer, which can lead to an out of bounds access when the incorrect h_size does not come from the old mkfs tool, but a fuzzer. Fix this by open coding xlog_logrec_hblks and taking the fixed h_size into account for this calculation.
CVE-2024-39490: In the Linux kernel, the following vulnerability has been resolved: ipv6: sr: fix missing sk_buff release in seg6_input_core The seg6_input() function is responsible for adding the SRH into a packet, delegating the operation to the seg6_input_core(). This function uses the skb_cow_head() to ensure that there is sufficient headroom in the sk_buff for accommodating the link-layer header. In the event that the skb_cow_header() function fails, the seg6_input_core() catches the error but it does not release the sk_buff, which will result in a memory leak. This issue was introduced in commit af3b5158b89d ("ipv6: sr: fix BUG due to headroom too small after SRH push") and persists even after commit 7a3f5b0de364 ("netfilter: add netfilter hooks to SRv6 data plane"), where the entire seg6_input() code was refactored to deal with netfilter hooks. The proposed patch addresses the identified memory leak by requiring the seg6_input_core() function to release the sk_buff in the event that skb_cow_head() fails.
CVE-2024-39500: In the Linux kernel, the following vulnerability has been resolved: sock_map: avoid race between sock_map_close and sk_psock_put sk_psock_get will return NULL if the refcount of psock has gone to 0, which will happen when the last call of sk_psock_put is done. However, sk_psock_drop may not have finished yet, so the close callback will still point to sock_map_close despite psock being NULL. This can be reproduced with a thread deleting an element from the sock map, while the second one creates a socket, adds it to the map and closes it. That will trigger the WARN_ON_ONCE: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 7220 at net/core/sock_map.c:1701 sock_map_close+0x2a2/0x2d0 net/core/sock_map.c:1701 Modules linked in: CPU: 1 PID: 7220 Comm: syz-executor380 Not tainted 6.9.0-syzkaller-07726-g3c999d1ae3c7 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 RIP: 0010:sock_map_close+0x2a2/0x2d0 net/core/sock_map.c:1701 Code: df e8 92 29 88 f8 48 8b 1b 48 89 d8 48 c1 e8 03 42 80 3c 20 00 74 08 48 89 df e8 79 29 88 f8 4c 8b 23 eb 89 e8 4f 15 23 f8 90 <0f> 0b 90 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d e9 13 26 3d 02 RSP: 0018:ffffc9000441fda8 EFLAGS: 00010293 RAX: ffffffff89731ae1 RBX: ffffffff94b87540 RCX: ffff888029470000 RDX: 0000000000000000 RSI: ffffffff8bcab5c0 RDI: ffffffff8c1faba0 RBP: 0000000000000000 R08: ffffffff92f9b61f R09: 1ffffffff25f36c3 R10: dffffc0000000000 R11: fffffbfff25f36c4 R12: ffffffff89731840 R13: ffff88804b587000 R14: ffff88804b587000 R15: ffffffff89731870 FS: 000055555e080380(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 00000000207d4000 CR4: 0000000000350ef0 Call Trace: <TASK> unix_release+0x87/0xc0 net/unix/af_unix.c:1048 __sock_release net/socket.c:659 [inline] sock_close+0xbe/0x240 net/socket.c:1421 __fput+0x42b/0x8a0 fs/file_table.c:422 __do_sys_close fs/open.c:1556 [inline] __se_sys_close fs/open.c:1541 [inline] __x64_sys_close+0x7f/0x110 fs/open.c:1541 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fb37d618070 Code: 00 00 48 c7 c2 b8 ff ff ff f7 d8 64 89 02 b8 ff ff ff ff eb d4 e8 10 2c 00 00 80 3d 31 f0 07 00 00 74 17 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 48 c3 0f 1f 80 00 00 00 00 48 83 ec 18 89 7c RSP: 002b:00007ffcd4a525d8 EFLAGS: 00000202 ORIG_RAX: 0000000000000003 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00007fb37d618070 RDX: 0000000000000010 RSI: 00000000200001c0 RDI: 0000000000000004 RBP: 0000000000000000 R08: 0000000100000000 R09: 0000000100000000 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK> Use sk_psock, which will only check that the pointer is not been set to NULL yet, which should only happen after the callbacks are restored. If, then, a reference can still be gotten, we may call sk_psock_stop and cancel psock->work. As suggested by Paolo Abeni, reorder the condition so the control flow is less convoluted. After that change, the reproducer does not trigger the WARN_ON_ONCE anymore.
CVE-2024-39507: In the Linux kernel, the following vulnerability has been resolved: net: hns3: fix kernel crash problem in concurrent scenario When link status change, the nic driver need to notify the roce driver to handle this event, but at this time, the roce driver may uninit, then cause kernel crash. To fix the problem, when link status change, need to check whether the roce registered, and when uninit, need to wait link update finish.
CVE-2024-39508: In the Linux kernel, the following vulnerability has been resolved: io_uring/io-wq: Use set_bit() and test_bit() at worker->flags Utilize set_bit() and test_bit() on worker->flags within io_uring/io-wq to address potential data races. The structure io_worker->flags may be accessed through various data paths, leading to concurrency issues. When KCSAN is enabled, it reveals data races occurring in io_worker_handle_work and io_wq_activate_free_worker functions. BUG: KCSAN: data-race in io_worker_handle_work / io_wq_activate_free_worker write to 0xffff8885c4246404 of 4 bytes by task 49071 on cpu 28: io_worker_handle_work (io_uring/io-wq.c:434 io_uring/io-wq.c:569) io_wq_worker (io_uring/io-wq.c:?) <snip> read to 0xffff8885c4246404 of 4 bytes by task 49024 on cpu 5: io_wq_activate_free_worker (io_uring/io-wq.c:? io_uring/io-wq.c:285) io_wq_enqueue (io_uring/io-wq.c:947) io_queue_iowq (io_uring/io_uring.c:524) io_req_task_submit (io_uring/io_uring.c:1511) io_handle_tw_list (io_uring/io_uring.c:1198) <snip> Line numbers against commit 18daea77cca6 ("Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm"). These races involve writes and reads to the same memory location by different tasks running on different CPUs. To mitigate this, refactor the code to use atomic operations such as set_bit(), test_bit(), and clear_bit() instead of basic "and" and "or" operations. This ensures thread-safe manipulation of worker flags. Also, move `create_index` to avoid holes in the structure.
CVE-2024-40910: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix refcount imbalance on inbound connections When releasing a socket in ax25_release(), we call netdev_put() to decrease the refcount on the associated ax.25 device. However, the execution path for accepting an incoming connection never calls netdev_hold(). This imbalance leads to refcount errors, and ultimately to kernel crashes. A typical call trace for the above situation will start with one of the following errors: refcount_t: decrement hit 0; leaking memory. refcount_t: underflow; use-after-free. And will then have a trace like: Call Trace: <TASK> ? show_regs+0x64/0x70 ? __warn+0x83/0x120 ? refcount_warn_saturate+0xb2/0x100 ? report_bug+0x158/0x190 ? prb_read_valid+0x20/0x30 ? handle_bug+0x3e/0x70 ? exc_invalid_op+0x1c/0x70 ? asm_exc_invalid_op+0x1f/0x30 ? refcount_warn_saturate+0xb2/0x100 ? refcount_warn_saturate+0xb2/0x100 ax25_release+0x2ad/0x360 __sock_release+0x35/0xa0 sock_close+0x19/0x20 [...] On reboot (or any attempt to remove the interface), the kernel gets stuck in an infinite loop: unregister_netdevice: waiting for ax0 to become free. Usage count = 0 This patch corrects these issues by ensuring that we call netdev_hold() and ax25_dev_hold() for new connections in ax25_accept(). This makes the logic leading to ax25_accept() match the logic for ax25_bind(): in both cases we increment the refcount, which is ultimately decremented in ax25_release().
CVE-2024-40911: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: Lock wiphy in cfg80211_get_station Wiphy should be locked before calling rdev_get_station() (see lockdep assert in ieee80211_get_station()). This fixes the following kernel NULL dereference: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000050 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=0000000003001000 [0000000000000050] pgd=0800000002dca003, p4d=0800000002dca003, pud=08000000028e9003, pmd=0000000000000000 Internal error: Oops: 0000000096000006 [#1] SMP Modules linked in: netconsole dwc3_meson_g12a dwc3_of_simple dwc3 ip_gre gre ath10k_pci ath10k_core ath9k ath9k_common ath9k_hw ath CPU: 0 PID: 1091 Comm: kworker/u8:0 Not tainted 6.4.0-02144-g565f9a3a7911-dirty #705 Hardware name: RPT (r1) (DT) Workqueue: bat_events batadv_v_elp_throughput_metric_update pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : ath10k_sta_statistics+0x10/0x2dc [ath10k_core] lr : sta_set_sinfo+0xcc/0xbd4 sp : ffff000007b43ad0 x29: ffff000007b43ad0 x28: ffff0000071fa900 x27: ffff00000294ca98 x26: ffff000006830880 x25: ffff000006830880 x24: ffff00000294c000 x23: 0000000000000001 x22: ffff000007b43c90 x21: ffff800008898acc x20: ffff00000294c6e8 x19: ffff000007b43c90 x18: 0000000000000000 x17: 445946354d552d78 x16: 62661f7200000000 x15: 57464f445946354d x14: 0000000000000000 x13: 00000000000000e3 x12: d5f0acbcebea978e x11: 00000000000000e3 x10: 000000010048fe41 x9 : 0000000000000000 x8 : ffff000007b43d90 x7 : 000000007a1e2125 x6 : 0000000000000000 x5 : ffff0000024e0900 x4 : ffff800000a0250c x3 : ffff000007b43c90 x2 : ffff00000294ca98 x1 : ffff000006831920 x0 : 0000000000000000 Call trace: ath10k_sta_statistics+0x10/0x2dc [ath10k_core] sta_set_sinfo+0xcc/0xbd4 ieee80211_get_station+0x2c/0x44 cfg80211_get_station+0x80/0x154 batadv_v_elp_get_throughput+0x138/0x1fc batadv_v_elp_throughput_metric_update+0x1c/0xa4 process_one_work+0x1ec/0x414 worker_thread+0x70/0x46c kthread+0xdc/0xe0 ret_from_fork+0x10/0x20 Code: a9bb7bfd 910003fd a90153f3 f9411c40 (f9402814) This happens because STA has time to disconnect and reconnect before batadv_v_elp_throughput_metric_update() delayed work gets scheduled. In this situation, ath10k_sta_state() can be in the middle of resetting arsta data when the work queue get chance to be scheduled and ends up accessing it. Locking wiphy prevents that.
CVE-2024-40915: In the Linux kernel, the following vulnerability has been resolved: riscv: rewrite __kernel_map_pages() to fix sleeping in invalid context __kernel_map_pages() is a debug function which clears the valid bit in page table entry for deallocated pages to detect illegal memory accesses to freed pages. This function set/clear the valid bit using __set_memory(). __set_memory() acquires init_mm's semaphore, and this operation may sleep. This is problematic, because __kernel_map_pages() can be called in atomic context, and thus is illegal to sleep. An example warning that this causes: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1578 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd preempt_count: 2, expected: 0 CPU: 0 PID: 2 Comm: kthreadd Not tainted 6.9.0-g1d4c6d784ef6 #37 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff800060dc>] dump_backtrace+0x1c/0x24 [<ffffffff8091ef6e>] show_stack+0x2c/0x38 [<ffffffff8092baf8>] dump_stack_lvl+0x5a/0x72 [<ffffffff8092bb24>] dump_stack+0x14/0x1c [<ffffffff8003b7ac>] __might_resched+0x104/0x10e [<ffffffff8003b7f4>] __might_sleep+0x3e/0x62 [<ffffffff8093276a>] down_write+0x20/0x72 [<ffffffff8000cf00>] __set_memory+0x82/0x2fa [<ffffffff8000d324>] __kernel_map_pages+0x5a/0xd4 [<ffffffff80196cca>] __alloc_pages_bulk+0x3b2/0x43a [<ffffffff8018ee82>] __vmalloc_node_range+0x196/0x6ba [<ffffffff80011904>] copy_process+0x72c/0x17ec [<ffffffff80012ab4>] kernel_clone+0x60/0x2fe [<ffffffff80012f62>] kernel_thread+0x82/0xa0 [<ffffffff8003552c>] kthreadd+0x14a/0x1be [<ffffffff809357de>] ret_from_fork+0xe/0x1c Rewrite this function with apply_to_existing_page_range(). It is fine to not have any locking, because __kernel_map_pages() works with pages being allocated/deallocated and those pages are not changed by anyone else in the meantime.
CVE-2024-40927: In the Linux kernel, the following vulnerability has been resolved: xhci: Handle TD clearing for multiple streams case When multiple streams are in use, multiple TDs might be in flight when an endpoint is stopped. We need to issue a Set TR Dequeue Pointer for each, to ensure everything is reset properly and the caches cleared. Change the logic so that any N>1 TDs found active for different streams are deferred until after the first one is processed, calling xhci_invalidate_cancelled_tds() again from xhci_handle_cmd_set_deq() to queue another command until we are done with all of them. Also change the error/"should never happen" paths to ensure we at least clear any affected TDs, even if we can't issue a command to clear the hardware cache, and complain loudly with an xhci_warn() if this ever happens. This problem case dates back to commit e9df17eb1408 ("USB: xhci: Correct assumptions about number of rings per endpoint.") early on in the XHCI driver's life, when stream support was first added. It was then identified but not fixed nor made into a warning in commit 674f8438c121 ("xhci: split handling halted endpoints into two steps"), which added a FIXME comment for the problem case (without materially changing the behavior as far as I can tell, though the new logic made the problem more obvious). Then later, in commit 94f339147fc3 ("xhci: Fix failure to give back some cached cancelled URBs."), it was acknowledged again. [Mathias: commit 94f339147fc3 ("xhci: Fix failure to give back some cached cancelled URBs.") was a targeted regression fix to the previously mentioned patch. Users reported issues with usb stuck after unmounting/disconnecting UAS devices. This rolled back the TD clearing of multiple streams to its original state.] Apparently the commit author was aware of the problem (yet still chose to submit it): It was still mentioned as a FIXME, an xhci_dbg() was added to log the problem condition, and the remaining issue was mentioned in the commit description. The choice of making the log type xhci_dbg() for what is, at this point, a completely unhandled and known broken condition is puzzling and unfortunate, as it guarantees that no actual users would see the log in production, thereby making it nigh undebuggable (indeed, even if you turn on DEBUG, the message doesn't really hint at there being a problem at all). It took me *months* of random xHC crashes to finally find a reliable repro and be able to do a deep dive debug session, which could all have been avoided had this unhandled, broken condition been actually reported with a warning, as it should have been as a bug intentionally left in unfixed (never mind that it shouldn't have been left in at all). > Another fix to solve clearing the caches of all stream rings with > cancelled TDs is needed, but not as urgent. 3 years after that statement and 14 years after the original bug was introduced, I think it's finally time to fix it. And maybe next time let's not leave bugs unfixed (that are actually worse than the original bug), and let's actually get people to review kernel commits please. Fixes xHC crashes and IOMMU faults with UAS devices when handling errors/faults. Easiest repro is to use `hdparm` to mark an early sector (e.g. 1024) on a disk as bad, then `cat /dev/sdX > /dev/null` in a loop. At least in the case of JMicron controllers, the read errors end up having to cancel two TDs (for two queued requests to different streams) and the one that didn't get cleared properly ends up faulting the xHC entirely when it tries to access DMA pages that have since been unmapped, referred to by the stale TDs. This normally happens quickly (after two or three loops). After this fix, I left the `cat` in a loop running overnight and experienced no xHC failures, with all read errors recovered properly. Repro'd and tested on an Apple M1 Mac Mini (dwc3 host). On systems without an IOMMU, this bug would instead silently corrupt freed memory, making this a ---truncated---
CVE-2024-40965: In the Linux kernel, the following vulnerability has been resolved: i2c: lpi2c: Avoid calling clk_get_rate during transfer Instead of repeatedly calling clk_get_rate for each transfer, lock the clock rate and cache the value. A deadlock has been observed while adding tlv320aic32x4 audio codec to the system. When this clock provider adds its clock, the clk mutex is locked already, it needs to access i2c, which in return needs the mutex for clk_get_rate as well.
CVE-2024-40966: In the Linux kernel, the following vulnerability has been resolved: tty: add the option to have a tty reject a new ldisc ... and use it to limit the virtual terminals to just N_TTY. They are kind of special, and in particular, the "con_write()" routine violates the "writes cannot sleep" rule that some ldiscs rely on. This avoids the BUG: sleeping function called from invalid context at kernel/printk/printk.c:2659 when N_GSM has been attached to a virtual console, and gsmld_write() calls con_write() while holding a spinlock, and con_write() then tries to get the console lock.
CVE-2024-40967: In the Linux kernel, the following vulnerability has been resolved: serial: imx: Introduce timeout when waiting on transmitter empty By waiting at most 1 second for USR2_TXDC to be set, we avoid a potential deadlock. In case of the timeout, there is not much we can do, so we simply ignore the transmitter state and optimistically try to continue.
CVE-2024-40969: In the Linux kernel, the following vulnerability has been resolved: f2fs: don't set RO when shutting down f2fs Shutdown does not check the error of thaw_super due to readonly, which causes a deadlock like below. f2fs_ioc_shutdown(F2FS_GOING_DOWN_FULLSYNC) issue_discard_thread - bdev_freeze - freeze_super - f2fs_stop_checkpoint() - f2fs_handle_critical_error - sb_start_write - set RO - waiting - bdev_thaw - thaw_super_locked - return -EINVAL, if sb_rdonly() - f2fs_stop_discard_thread -> wait for kthread_stop(discard_thread);
CVE-2024-40972: In the Linux kernel, the following vulnerability has been resolved: ext4: do not create EA inode under buffer lock ext4_xattr_set_entry() creates new EA inodes while holding buffer lock on the external xattr block. This is problematic as it nests all the allocation locking (which acquires locks on other buffers) under the buffer lock. This can even deadlock when the filesystem is corrupted and e.g. quota file is setup to contain xattr block as data block. Move the allocation of EA inode out of ext4_xattr_set_entry() into the callers.
CVE-2024-40973: In the Linux kernel, the following vulnerability has been resolved: media: mtk-vcodec: potential null pointer deference in SCP The return value of devm_kzalloc() needs to be checked to avoid NULL pointer deference. This is similar to CVE-2022-3113.
CVE-2024-40977: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7921s: fix potential hung tasks during chip recovery During chip recovery (e.g. chip reset), there is a possible situation that kernel worker reset_work is holding the lock and waiting for kernel thread stat_worker to be parked, while stat_worker is waiting for the release of the same lock. It causes a deadlock resulting in the dumping of hung tasks messages and possible rebooting of the device. This patch prevents the execution of stat_worker during the chip recovery.
CVE-2024-40998: In the Linux kernel, the following vulnerability has been resolved: ext4: fix uninitialized ratelimit_state->lock access in __ext4_fill_super() In the following concurrency we will access the uninitialized rs->lock: ext4_fill_super ext4_register_sysfs // sysfs registered msg_ratelimit_interval_ms // Other processes modify rs->interval to // non-zero via msg_ratelimit_interval_ms ext4_orphan_cleanup ext4_msg(sb, KERN_INFO, "Errors on filesystem, " __ext4_msg ___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state) if (!rs->interval) // do nothing if interval is 0 return 1; raw_spin_trylock_irqsave(&rs->lock, flags) raw_spin_trylock(lock) _raw_spin_trylock __raw_spin_trylock spin_acquire(&lock->dep_map, 0, 1, _RET_IP_) lock_acquire __lock_acquire register_lock_class assign_lock_key dump_stack(); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); raw_spin_lock_init(&rs->lock); // init rs->lock here and get the following dump_stack: ========================================================= INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 12 PID: 753 Comm: mount Tainted: G E 6.7.0-rc6-next-20231222 #504 [...] Call Trace: dump_stack_lvl+0xc5/0x170 dump_stack+0x18/0x30 register_lock_class+0x740/0x7c0 __lock_acquire+0x69/0x13a0 lock_acquire+0x120/0x450 _raw_spin_trylock+0x98/0xd0 ___ratelimit+0xf6/0x220 __ext4_msg+0x7f/0x160 [ext4] ext4_orphan_cleanup+0x665/0x740 [ext4] __ext4_fill_super+0x21ea/0x2b10 [ext4] ext4_fill_super+0x14d/0x360 [ext4] [...] ========================================================= Normally interval is 0 until s_msg_ratelimit_state is initialized, so ___ratelimit() does nothing. But registering sysfs precedes initializing rs->lock, so it is possible to change rs->interval to a non-zero value via the msg_ratelimit_interval_ms interface of sysfs while rs->lock is uninitialized, and then a call to ext4_msg triggers the problem by accessing an uninitialized rs->lock. Therefore register sysfs after all initializations are complete to avoid such problems.
CVE-2024-40999: In the Linux kernel, the following vulnerability has been resolved: net: ena: Add validation for completion descriptors consistency Validate that `first` flag is set only for the first descriptor in multi-buffer packets. In case of an invalid descriptor, a reset will occur. A new reset reason for RX data corruption has been added.
CVE-2024-41001: In the Linux kernel, the following vulnerability has been resolved: io_uring/sqpoll: work around a potential audit memory leak kmemleak complains that there's a memory leak related to connect handling: unreferenced object 0xffff0001093bdf00 (size 128): comm "iou-sqp-455", pid 457, jiffies 4294894164 hex dump (first 32 bytes): 02 00 fa ea 7f 00 00 01 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc 2e481b1a): [<00000000c0a26af4>] kmemleak_alloc+0x30/0x38 [<000000009c30bb45>] kmalloc_trace+0x228/0x358 [<000000009da9d39f>] __audit_sockaddr+0xd0/0x138 [<0000000089a93e34>] move_addr_to_kernel+0x1a0/0x1f8 [<000000000b4e80e6>] io_connect_prep+0x1ec/0x2d4 [<00000000abfbcd99>] io_submit_sqes+0x588/0x1e48 [<00000000e7c25e07>] io_sq_thread+0x8a4/0x10e4 [<00000000d999b491>] ret_from_fork+0x10/0x20 which can can happen if: 1) The command type does something on the prep side that triggers an audit call. 2) The thread hasn't done any operations before this that triggered an audit call inside ->issue(), where we have audit_uring_entry() and audit_uring_exit(). Work around this by issuing a blanket NOP operation before the SQPOLL does anything.
CVE-2024-41002: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/sec - Fix memory leak for sec resource release The AIV is one of the SEC resources. When releasing resources, it need to release the AIV resources at the same time. Otherwise, memory leakage occurs. The aiv resource release is added to the sec resource release function.
CVE-2024-41008: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: change vm->task_info handling This patch changes the handling and lifecycle of vm->task_info object. The major changes are: - vm->task_info is a dynamically allocated ptr now, and its uasge is reference counted. - introducing two new helper funcs for task_info lifecycle management - amdgpu_vm_get_task_info: reference counts up task_info before returning this info - amdgpu_vm_put_task_info: reference counts down task_info - last put to task_info() frees task_info from the vm. This patch also does logistical changes required for existing usage of vm->task_info. V2: Do not block all the prints when task_info not found (Felix) V3: Fixed review comments from Felix - Fix wrong indentation - No debug message for -ENOMEM - Add NULL check for task_info - Do not duplicate the debug messages (ti vs no ti) - Get first reference of task_info in vm_init(), put last in vm_fini() V4: Fixed review comments from Felix - fix double reference increment in create_task_info - change amdgpu_vm_get_task_info_pasid - additional changes in amdgpu_gem.c while porting
CVE-2024-41013: In the Linux kernel, the following vulnerability has been resolved: xfs: don't walk off the end of a directory data block This adds sanity checks for xfs_dir2_data_unused and xfs_dir2_data_entry to make sure don't stray beyond valid memory region. Before patching, the loop simply checks that the start offset of the dup and dep is within the range. So in a crafted image, if last entry is xfs_dir2_data_unused, we can change dup->length to dup->length-1 and leave 1 byte of space. In the next traversal, this space will be considered as dup or dep. We may encounter an out of bound read when accessing the fixed members. In the patch, we make sure that the remaining bytes large enough to hold an unused entry before accessing xfs_dir2_data_unused and xfs_dir2_data_unused is XFS_DIR2_DATA_ALIGN byte aligned. We also make sure that the remaining bytes large enough to hold a dirent with a single-byte name before accessing xfs_dir2_data_entry.
CVE-2024-41014: In the Linux kernel, the following vulnerability has been resolved: xfs: add bounds checking to xlog_recover_process_data There is a lack of verification of the space occupied by fixed members of xlog_op_header in the xlog_recover_process_data. We can create a crafted image to trigger an out of bounds read by following these steps: 1) Mount an image of xfs, and do some file operations to leave records 2) Before umounting, copy the image for subsequent steps to simulate abnormal exit. Because umount will ensure that tail_blk and head_blk are the same, which will result in the inability to enter xlog_recover_process_data 3) Write a tool to parse and modify the copied image in step 2 4) Make the end of the xlog_op_header entries only 1 byte away from xlog_rec_header->h_size 5) xlog_rec_header->h_num_logops++ 6) Modify xlog_rec_header->h_crc Fix: Add a check to make sure there is sufficient space to access fixed members of xlog_op_header.
CVE-2024-41023: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix task_struct reference leak During the execution of the following stress test with linux-rt: stress-ng --cyclic 30 --timeout 30 --minimize --quiet kmemleak frequently reported a memory leak concerning the task_struct: unreferenced object 0xffff8881305b8000 (size 16136): comm "stress-ng", pid 614, jiffies 4294883961 (age 286.412s) object hex dump (first 32 bytes): 02 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 .@.............. 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ debug hex dump (first 16 bytes): 53 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 S............... backtrace: [<00000000046b6790>] dup_task_struct+0x30/0x540 [<00000000c5ca0f0b>] copy_process+0x3d9/0x50e0 [<00000000ced59777>] kernel_clone+0xb0/0x770 [<00000000a50befdc>] __do_sys_clone+0xb6/0xf0 [<000000001dbf2008>] do_syscall_64+0x5d/0xf0 [<00000000552900ff>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 The issue occurs in start_dl_timer(), which increments the task_struct reference count and sets a timer. The timer callback, dl_task_timer, is supposed to decrement the reference count upon expiration. However, if enqueue_task_dl() is called before the timer expires and cancels it, the reference count is not decremented, leading to the leak. This patch fixes the reference leak by ensuring the task_struct reference count is properly decremented when the timer is canceled.
CVE-2024-41027: In the Linux kernel, the following vulnerability has been resolved: Fix userfaultfd_api to return EINVAL as expected Currently if we request a feature that is not set in the Kernel config we fail silently and return all the available features. However, the man page indicates we should return an EINVAL. We need to fix this issue since we can end up with a Kernel warning should a program request the feature UFFD_FEATURE_WP_UNPOPULATED on a kernel with the config not set with this feature. [ 200.812896] WARNING: CPU: 91 PID: 13634 at mm/memory.c:1660 zap_pte_range+0x43d/0x660 [ 200.820738] Modules linked in: [ 200.869387] CPU: 91 PID: 13634 Comm: userfaultfd Kdump: loaded Not tainted 6.9.0-rc5+ #8 [ 200.877477] Hardware name: Dell Inc. PowerEdge R6525/0N7YGH, BIOS 2.7.3 03/30/2022 [ 200.885052] RIP: 0010:zap_pte_range+0x43d/0x660
CVE-2024-41036: In the Linux kernel, the following vulnerability has been resolved: net: ks8851: Fix deadlock with the SPI chip variant When SMP is enabled and spinlocks are actually functional then there is a deadlock with the 'statelock' spinlock between ks8851_start_xmit_spi and ks8851_irq: watchdog: BUG: soft lockup - CPU#0 stuck for 27s! call trace: queued_spin_lock_slowpath+0x100/0x284 do_raw_spin_lock+0x34/0x44 ks8851_start_xmit_spi+0x30/0xb8 ks8851_start_xmit+0x14/0x20 netdev_start_xmit+0x40/0x6c dev_hard_start_xmit+0x6c/0xbc sch_direct_xmit+0xa4/0x22c __qdisc_run+0x138/0x3fc qdisc_run+0x24/0x3c net_tx_action+0xf8/0x130 handle_softirqs+0x1ac/0x1f0 __do_softirq+0x14/0x20 ____do_softirq+0x10/0x1c call_on_irq_stack+0x3c/0x58 do_softirq_own_stack+0x1c/0x28 __irq_exit_rcu+0x54/0x9c irq_exit_rcu+0x10/0x1c el1_interrupt+0x38/0x50 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x64/0x68 __netif_schedule+0x6c/0x80 netif_tx_wake_queue+0x38/0x48 ks8851_irq+0xb8/0x2c8 irq_thread_fn+0x2c/0x74 irq_thread+0x10c/0x1b0 kthread+0xc8/0xd8 ret_from_fork+0x10/0x20 This issue has not been identified earlier because tests were done on a device with SMP disabled and so spinlocks were actually NOPs. Now use spin_(un)lock_bh for TX queue related locking to avoid execution of softirq work synchronously that would lead to a deadlock.
CVE-2024-41048: In the Linux kernel, the following vulnerability has been resolved: skmsg: Skip zero length skb in sk_msg_recvmsg When running BPF selftests (./test_progs -t sockmap_basic) on a Loongarch platform, the following kernel panic occurs: [...] Oops[#1]: CPU: 22 PID: 2824 Comm: test_progs Tainted: G OE 6.10.0-rc2+ #18 Hardware name: LOONGSON Dabieshan/Loongson-TC542F0, BIOS Loongson-UDK2018 ... ... ra: 90000000048bf6c0 sk_msg_recvmsg+0x120/0x560 ERA: 9000000004162774 copy_page_to_iter+0x74/0x1c0 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 0000000c (PPLV0 +PIE +PWE) EUEN: 00000007 (+FPE +SXE +ASXE -BTE) ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) BADV: 0000000000000040 PRID: 0014c011 (Loongson-64bit, Loongson-3C5000) Modules linked in: bpf_testmod(OE) xt_CHECKSUM xt_MASQUERADE xt_conntrack Process test_progs (pid: 2824, threadinfo=0000000000863a31, task=...) Stack : ... Call Trace: [<9000000004162774>] copy_page_to_iter+0x74/0x1c0 [<90000000048bf6c0>] sk_msg_recvmsg+0x120/0x560 [<90000000049f2b90>] tcp_bpf_recvmsg_parser+0x170/0x4e0 [<90000000049aae34>] inet_recvmsg+0x54/0x100 [<900000000481ad5c>] sock_recvmsg+0x7c/0xe0 [<900000000481e1a8>] __sys_recvfrom+0x108/0x1c0 [<900000000481e27c>] sys_recvfrom+0x1c/0x40 [<9000000004c076ec>] do_syscall+0x8c/0xc0 [<9000000003731da4>] handle_syscall+0xc4/0x160 Code: ... ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Fatal exception Kernel relocated by 0x3510000 .text @ 0x9000000003710000 .data @ 0x9000000004d70000 .bss @ 0x9000000006469400 ---[ end Kernel panic - not syncing: Fatal exception ]--- [...] This crash happens every time when running sockmap_skb_verdict_shutdown subtest in sockmap_basic. This crash is because a NULL pointer is passed to page_address() in the sk_msg_recvmsg(). Due to the different implementations depending on the architecture, page_address(NULL) will trigger a panic on Loongarch platform but not on x86 platform. So this bug was hidden on x86 platform for a while, but now it is exposed on Loongarch platform. The root cause is that a zero length skb (skb->len == 0) was put on the queue. This zero length skb is a TCP FIN packet, which was sent by shutdown(), invoked in test_sockmap_skb_verdict_shutdown(): shutdown(p1, SHUT_WR); In this case, in sk_psock_skb_ingress_enqueue(), num_sge is zero, and no page is put to this sge (see sg_set_page in sg_set_page), but this empty sge is queued into ingress_msg list. And in sk_msg_recvmsg(), this empty sge is used, and a NULL page is got by sg_page(sge). Pass this NULL page to copy_page_to_iter(), which passes it to kmap_local_page() and to page_address(), then kernel panics. To solve this, we should skip this zero length skb. So in sk_msg_recvmsg(), if copy is zero, that means it's a zero length skb, skip invoking copy_page_to_iter(). We are using the EFAULT return triggered by copy_page_to_iter to check for is_fin in tcp_bpf.c.
CVE-2024-41062: In the Linux kernel, the following vulnerability has been resolved: bluetooth/l2cap: sync sock recv cb and release The problem occurs between the system call to close the sock and hci_rx_work, where the former releases the sock and the latter accesses it without lock protection. CPU0 CPU1 ---- ---- sock_close hci_rx_work l2cap_sock_release hci_acldata_packet l2cap_sock_kill l2cap_recv_frame sk_free l2cap_conless_channel l2cap_sock_recv_cb If hci_rx_work processes the data that needs to be received before the sock is closed, then everything is normal; Otherwise, the work thread may access the released sock when receiving data. Add a chan mutex in the rx callback of the sock to achieve synchronization between the sock release and recv cb. Sock is dead, so set chan data to NULL, avoid others use invalid sock pointer.
CVE-2024-41069: In the Linux kernel, the following vulnerability has been resolved: ASoC: topology: Fix references to freed memory Most users after parsing a topology file, release memory used by it, so having pointer references directly into topology file contents is wrong. Use devm_kmemdup(), to allocate memory as needed.
CVE-2024-41079: In the Linux kernel, the following vulnerability has been resolved: nvmet: always initialize cqe.result The spec doesn't mandate that the first two double words (aka results) for the command queue entry need to be set to 0 when they are not used (not specified). Though, the target implemention returns 0 for TCP and FC but not for RDMA. Let's make RDMA behave the same and thus explicitly initializing the result field. This prevents leaking any data from the stack.
CVE-2024-41082: In the Linux kernel, the following vulnerability has been resolved: nvme-fabrics: use reserved tag for reg read/write command In some scenarios, if too many commands are issued by nvme command in the same time by user tasks, this may exhaust all tags of admin_q. If a reset (nvme reset or IO timeout) occurs before these commands finish, reconnect routine may fail to update nvme regs due to insufficient tags, which will cause kernel hang forever. In order to workaround this issue, maybe we can let reg_read32()/reg_read64()/reg_write32() use reserved tags. This maybe safe for nvmf: 1. For the disable ctrl path, we will not issue connect command 2. For the enable ctrl / fw activate path, since connect and reg_xx() are called serially. So the reserved tags may still be enough while reg_xx() use reserved tags.
CVE-2024-41088: In the Linux kernel, the following vulnerability has been resolved: can: mcp251xfd: fix infinite loop when xmit fails When the mcp251xfd_start_xmit() function fails, the driver stops processing messages, and the interrupt routine does not return, running indefinitely even after killing the running application. Error messages: [ 441.298819] mcp251xfd spi2.0 can0: ERROR in mcp251xfd_start_xmit: -16 [ 441.306498] mcp251xfd spi2.0 can0: Transmit Event FIFO buffer not empty. (seq=0x000017c7, tef_tail=0x000017cf, tef_head=0x000017d0, tx_head=0x000017d3). ... and repeat forever. The issue can be triggered when multiple devices share the same SPI interface. And there is concurrent access to the bus. The problem occurs because tx_ring->head increments even if mcp251xfd_start_xmit() fails. Consequently, the driver skips one TX package while still expecting a response in mcp251xfd_handle_tefif_one(). Resolve the issue by starting a workqueue to write the tx obj synchronously if err = -EBUSY. In case of another error, decrement tx_ring->head, remove skb from the echo stack, and drop the message. [mkl: use more imperative wording in patch description]
CVE-2024-41093: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: avoid using null object of framebuffer Instead of using state->fb->obj[0] directly, get object from framebuffer by calling drm_gem_fb_get_obj() and return error code when object is null to avoid using null object of framebuffer.
CVE-2024-41935: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to shrink read extent node in batches We use rwlock to protect core structure data of extent tree during its shrink, however, if there is a huge number of extent nodes in extent tree, during shrink of extent tree, it may hold rwlock for a very long time, which may trigger kernel hang issue. This patch fixes to shrink read extent node in batches, so that, critical region of the rwlock can be shrunk to avoid its extreme long time hold.
CVE-2024-42063: In the Linux kernel, the following vulnerability has been resolved: bpf: Mark bpf prog stack with kmsan_unposion_memory in interpreter mode syzbot reported uninit memory usages during map_{lookup,delete}_elem. ========== BUG: KMSAN: uninit-value in __dev_map_lookup_elem kernel/bpf/devmap.c:441 [inline] BUG: KMSAN: uninit-value in dev_map_lookup_elem+0xf3/0x170 kernel/bpf/devmap.c:796 __dev_map_lookup_elem kernel/bpf/devmap.c:441 [inline] dev_map_lookup_elem+0xf3/0x170 kernel/bpf/devmap.c:796 ____bpf_map_lookup_elem kernel/bpf/helpers.c:42 [inline] bpf_map_lookup_elem+0x5c/0x80 kernel/bpf/helpers.c:38 ___bpf_prog_run+0x13fe/0xe0f0 kernel/bpf/core.c:1997 __bpf_prog_run256+0xb5/0xe0 kernel/bpf/core.c:2237 ========== The reproducer should be in the interpreter mode. The C reproducer is trying to run the following bpf prog: 0: (18) r0 = 0x0 2: (18) r1 = map[id:49] 4: (b7) r8 = 16777216 5: (7b) *(u64 *)(r10 -8) = r8 6: (bf) r2 = r10 7: (07) r2 += -229 ^^^^^^^^^^ 8: (b7) r3 = 8 9: (b7) r4 = 0 10: (85) call dev_map_lookup_elem#1543472 11: (95) exit It is due to the "void *key" (r2) passed to the helper. bpf allows uninit stack memory access for bpf prog with the right privileges. This patch uses kmsan_unpoison_memory() to mark the stack as initialized. This should address different syzbot reports on the uninit "void *key" argument during map_{lookup,delete}_elem.
CVE-2024-42068: In the Linux kernel, the following vulnerability has been resolved: bpf: Take return from set_memory_ro() into account with bpf_prog_lock_ro() set_memory_ro() can fail, leaving memory unprotected. Check its return and take it into account as an error.
CVE-2024-42080: In the Linux kernel, the following vulnerability has been resolved: RDMA/restrack: Fix potential invalid address access struct rdma_restrack_entry's kern_name was set to KBUILD_MODNAME in ib_create_cq(), while if the module exited but forgot del this rdma_restrack_entry, it would cause a invalid address access in rdma_restrack_clean() when print the owner of this rdma_restrack_entry. These code is used to help find one forgotten PD release in one of the ULPs. But it is not needed anymore, so delete them.
CVE-2024-42098: In the Linux kernel, the following vulnerability has been resolved: crypto: ecdh - explicitly zeroize private_key private_key is overwritten with the key parameter passed in by the caller (if present), or alternatively a newly generated private key. However, it is possible that the caller provides a key (or the newly generated key) which is shorter than the previous key. In that scenario, some key material from the previous key would not be overwritten. The easiest solution is to explicitly zeroize the entire private_key array first. Note that this patch slightly changes the behavior of this function: previously, if the ecc_gen_privkey failed, the old private_key would remain. Now, the private_key is always zeroized. This behavior is consistent with the case where params.key is set and ecc_is_key_valid fails.
CVE-2024-42110: In the Linux kernel, the following vulnerability has been resolved: net: ntb_netdev: Move ntb_netdev_rx_handler() to call netif_rx() from __netif_rx() The following is emitted when using idxd (DSA) dmanegine as the data mover for ntb_transport that ntb_netdev uses. [74412.546922] BUG: using smp_processor_id() in preemptible [00000000] code: irq/52-idxd-por/14526 [74412.556784] caller is netif_rx_internal+0x42/0x130 [74412.562282] CPU: 6 PID: 14526 Comm: irq/52-idxd-por Not tainted 6.9.5 #5 [74412.569870] Hardware name: Intel Corporation ArcherCity/ArcherCity, BIOS EGSDCRB1.E9I.1752.P05.2402080856 02/08/2024 [74412.581699] Call Trace: [74412.584514] <TASK> [74412.586933] dump_stack_lvl+0x55/0x70 [74412.591129] check_preemption_disabled+0xc8/0xf0 [74412.596374] netif_rx_internal+0x42/0x130 [74412.600957] __netif_rx+0x20/0xd0 [74412.604743] ntb_netdev_rx_handler+0x66/0x150 [ntb_netdev] [74412.610985] ntb_complete_rxc+0xed/0x140 [ntb_transport] [74412.617010] ntb_rx_copy_callback+0x53/0x80 [ntb_transport] [74412.623332] idxd_dma_complete_txd+0xe3/0x160 [idxd] [74412.628963] idxd_wq_thread+0x1a6/0x2b0 [idxd] [74412.634046] irq_thread_fn+0x21/0x60 [74412.638134] ? irq_thread+0xa8/0x290 [74412.642218] irq_thread+0x1a0/0x290 [74412.646212] ? __pfx_irq_thread_fn+0x10/0x10 [74412.651071] ? __pfx_irq_thread_dtor+0x10/0x10 [74412.656117] ? __pfx_irq_thread+0x10/0x10 [74412.660686] kthread+0x100/0x130 [74412.664384] ? __pfx_kthread+0x10/0x10 [74412.668639] ret_from_fork+0x31/0x50 [74412.672716] ? __pfx_kthread+0x10/0x10 [74412.676978] ret_from_fork_asm+0x1a/0x30 [74412.681457] </TASK> The cause is due to the idxd driver interrupt completion handler uses threaded interrupt and the threaded handler is not hard or soft interrupt context. However __netif_rx() can only be called from interrupt context. Change the call to netif_rx() in order to allow completion via normal context for dmaengine drivers that utilize threaded irq handling. While the following commit changed from netif_rx() to __netif_rx(), baebdf48c360 ("net: dev: Makes sure netif_rx() can be invoked in any context."), the change should've been a noop instead. However, the code precedes this fix should've been using netif_rx_ni() or netif_rx_any_context().
CVE-2024-42118: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not return negative stream id for array [WHY] resource_stream_to_stream_idx returns an array index and it return -1 when not found; however, -1 is not a valid array index number. [HOW] When this happens, call ASSERT(), and return a zero instead. This fixes an OVERRUN and an NEGATIVE_RETURNS issues reported by Coverity.
CVE-2024-42122: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL pointer check for kzalloc [Why & How] Check return pointer of kzalloc before using it.
CVE-2024-42123: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix double free err_addr pointer warnings In amdgpu_umc_bad_page_polling_timeout, the amdgpu_umc_handle_bad_pages will be run many times so that double free err_addr in some special case. So set the err_addr to NULL to avoid the warnings.
CVE-2024-42128: In the Linux kernel, the following vulnerability has been resolved: leds: an30259a: Use devm_mutex_init() for mutex initialization In this driver LEDs are registered using devm_led_classdev_register() so they are automatically unregistered after module's remove() is done. led_classdev_unregister() calls module's led_set_brightness() to turn off the LEDs and that callback uses mutex which was destroyed already in module's remove() so use devm API instead.
CVE-2024-42129: In the Linux kernel, the following vulnerability has been resolved: leds: mlxreg: Use devm_mutex_init() for mutex initialization In this driver LEDs are registered using devm_led_classdev_register() so they are automatically unregistered after module's remove() is done. led_classdev_unregister() calls module's led_set_brightness() to turn off the LEDs and that callback uses mutex which was destroyed already in module's remove() so use devm API instead.
CVE-2024-42147: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/debugfs - Fix debugfs uninit process issue During the zip probe process, the debugfs failure does not stop the probe. When debugfs initialization fails, jumping to the error branch will also release regs, in addition to its own rollback operation. As a result, it may be released repeatedly during the regs uninit process. Therefore, the null check needs to be added to the regs uninit process.
CVE-2024-42155: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Wipe copies of protected- and secure-keys Although the clear-key of neither protected- nor secure-keys is accessible, this key material should only be visible to the calling process. So wipe all copies of protected- or secure-keys from stack, even in case of an error.
CVE-2024-42156: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Wipe copies of clear-key structures on failure Wipe all sensitive data from stack for all IOCTLs, which convert a clear-key into a protected- or secure-key.
CVE-2024-42158: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Use kfree_sensitive() to fix Coccinelle warnings Replace memzero_explicit() and kfree() with kfree_sensitive() to fix warnings reported by Coccinelle: WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1506) WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1643) WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1770)
CVE-2024-42160: In the Linux kernel, the following vulnerability has been resolved: f2fs: check validation of fault attrs in f2fs_build_fault_attr() - It missed to check validation of fault attrs in parse_options(), let's fix to add check condition in f2fs_build_fault_attr(). - Use f2fs_build_fault_attr() in __sbi_store() to clean up code.
CVE-2024-42162: In the Linux kernel, the following vulnerability has been resolved: gve: Account for stopped queues when reading NIC stats We now account for the fact that the NIC might send us stats for a subset of queues. Without this change, gve_get_ethtool_stats might make an invalid access on the priv->stats_report->stats array.
CVE-2024-42225: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: replace skb_put with skb_put_zero Avoid potentially reusing uninitialized data
CVE-2024-42230: In the Linux kernel, the following vulnerability has been resolved: powerpc/pseries: Fix scv instruction crash with kexec kexec on pseries disables AIL (reloc_on_exc), required for scv instruction support, before other CPUs have been shut down. This means they can execute scv instructions after AIL is disabled, which causes an interrupt at an unexpected entry location that crashes the kernel. Change the kexec sequence to disable AIL after other CPUs have been brought down. As a refresher, the real-mode scv interrupt vector is 0x17000, and the fixed-location head code probably couldn't easily deal with implementing such high addresses so it was just decided not to support that interrupt at all.
CVE-2024-42252: In the Linux kernel, the following vulnerability has been resolved: closures: Change BUG_ON() to WARN_ON() If a BUG_ON() can be hit in the wild, it shouldn't be a BUG_ON() For reference, this has popped up once in the CI, and we'll need more info to debug it: 03240 ------------[ cut here ]------------ 03240 kernel BUG at lib/closure.c:21! 03240 kernel BUG at lib/closure.c:21! 03240 Internal error: Oops - BUG: 00000000f2000800 [#1] SMP 03240 Modules linked in: 03240 CPU: 15 PID: 40534 Comm: kworker/u80:1 Not tainted 6.10.0-rc4-ktest-ga56da69799bd #25570 03240 Hardware name: linux,dummy-virt (DT) 03240 Workqueue: btree_update btree_interior_update_work 03240 pstate: 00001005 (nzcv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--) 03240 pc : closure_put+0x224/0x2a0 03240 lr : closure_put+0x24/0x2a0 03240 sp : ffff0000d12071c0 03240 x29: ffff0000d12071c0 x28: dfff800000000000 x27: ffff0000d1207360 03240 x26: 0000000000000040 x25: 0000000000000040 x24: 0000000000000040 03240 x23: ffff0000c1f20180 x22: 0000000000000000 x21: ffff0000c1f20168 03240 x20: 0000000040000000 x19: ffff0000c1f20140 x18: 0000000000000001 03240 x17: 0000000000003aa0 x16: 0000000000003ad0 x15: 1fffe0001c326974 03240 x14: 0000000000000a1e x13: 0000000000000000 x12: 1fffe000183e402d 03240 x11: ffff6000183e402d x10: dfff800000000000 x9 : ffff6000183e402e 03240 x8 : 0000000000000001 x7 : 00009fffe7c1bfd3 x6 : ffff0000c1f2016b 03240 x5 : ffff0000c1f20168 x4 : ffff6000183e402e x3 : ffff800081391954 03240 x2 : 0000000000000001 x1 : 0000000000000000 x0 : 00000000a8000000 03240 Call trace: 03240 closure_put+0x224/0x2a0 03240 bch2_check_for_deadlock+0x910/0x1028 03240 bch2_six_check_for_deadlock+0x1c/0x30 03240 six_lock_slowpath.isra.0+0x29c/0xed0 03240 six_lock_ip_waiter+0xa8/0xf8 03240 __bch2_btree_node_lock_write+0x14c/0x298 03240 bch2_trans_lock_write+0x6d4/0xb10 03240 __bch2_trans_commit+0x135c/0x5520 03240 btree_interior_update_work+0x1248/0x1c10 03240 process_scheduled_works+0x53c/0xd90 03240 worker_thread+0x370/0x8c8 03240 kthread+0x258/0x2e8 03240 ret_from_fork+0x10/0x20 03240 Code: aa1303e0 d63f0020 a94363f7 17ffff8c (d4210000) 03240 ---[ end trace 0000000000000000 ]--- 03240 Kernel panic - not syncing: Oops - BUG: Fatal exception 03240 SMP: stopping secondary CPUs 03241 SMP: failed to stop secondary CPUs 13,15 03241 Kernel Offset: disabled 03241 CPU features: 0x00,00000003,80000008,4240500b 03241 Memory Limit: none 03241 ---[ end Kernel panic - not syncing: Oops - BUG: Fatal exception ]--- 03246 ========= FAILED TIMEOUT copygc_torture_no_checksum in 7200s
CVE-2024-42253: In the Linux kernel, the following vulnerability has been resolved: gpio: pca953x: fix pca953x_irq_bus_sync_unlock race Ensure that `i2c_lock' is held when setting interrupt latch and mask in pca953x_irq_bus_sync_unlock() in order to avoid races. The other (non-probe) call site pca953x_gpio_set_multiple() ensures the lock is held before calling pca953x_write_regs(). The problem occurred when a request raced against irq_bus_sync_unlock() approximately once per thousand reboots on an i.MX8MP based system. * Normal case 0-0022: write register AI|3a {03,02,00,00,01} Input latch P0 0-0022: write register AI|49 {fc,fd,ff,ff,fe} Interrupt mask P0 0-0022: write register AI|08 {ff,00,00,00,00} Output P3 0-0022: write register AI|12 {fc,00,00,00,00} Config P3 * Race case 0-0022: write register AI|08 {ff,00,00,00,00} Output P3 0-0022: write register AI|08 {03,02,00,00,01} *** Wrong register *** 0-0022: write register AI|12 {fc,00,00,00,00} Config P3 0-0022: write register AI|49 {fc,fd,ff,ff,fe} Interrupt mask P0
CVE-2024-42296: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix return value of f2fs_convert_inline_inode() If device is readonly, make f2fs_convert_inline_inode() return EROFS instead of zero, otherwise it may trigger panic during writeback of inline inode's dirty page as below: f2fs_write_single_data_page+0xbb6/0x1e90 fs/f2fs/data.c:2888 f2fs_write_cache_pages fs/f2fs/data.c:3187 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3342 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3369 do_writepages+0x359/0x870 mm/page-writeback.c:2634 filemap_fdatawrite_wbc+0x125/0x180 mm/filemap.c:397 __filemap_fdatawrite_range mm/filemap.c:430 [inline] file_write_and_wait_range+0x1aa/0x290 mm/filemap.c:788 f2fs_do_sync_file+0x68a/0x1ae0 fs/f2fs/file.c:276 generic_write_sync include/linux/fs.h:2806 [inline] f2fs_file_write_iter+0x7bd/0x24e0 fs/f2fs/file.c:4977 call_write_iter include/linux/fs.h:2114 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0xa72/0xc90 fs/read_write.c:590 ksys_write+0x1a0/0x2c0 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
CVE-2024-42319: In the Linux kernel, the following vulnerability has been resolved: mailbox: mtk-cmdq: Move devm_mbox_controller_register() after devm_pm_runtime_enable() When mtk-cmdq unbinds, a WARN_ON message with condition pm_runtime_get_sync() < 0 occurs. According to the call tracei below: cmdq_mbox_shutdown mbox_free_channel mbox_controller_unregister __devm_mbox_controller_unregister ... The root cause can be deduced to be calling pm_runtime_get_sync() after calling pm_runtime_disable() as observed below: 1. CMDQ driver uses devm_mbox_controller_register() in cmdq_probe() to bind the cmdq device to the mbox_controller, so devm_mbox_controller_unregister() will automatically unregister the device bound to the mailbox controller when the device-managed resource is removed. That means devm_mbox_controller_unregister() and cmdq_mbox_shoutdown() will be called after cmdq_remove(). 2. CMDQ driver also uses devm_pm_runtime_enable() in cmdq_probe() after devm_mbox_controller_register(), so that devm_pm_runtime_disable() will be called after cmdq_remove(), but before devm_mbox_controller_unregister(). To fix this problem, cmdq_probe() needs to move devm_mbox_controller_register() after devm_pm_runtime_enable() to make devm_pm_runtime_disable() be called after devm_mbox_controller_unregister().
CVE-2024-42321: In the Linux kernel, the following vulnerability has been resolved: net: flow_dissector: use DEBUG_NET_WARN_ON_ONCE The following splat is easy to reproduce upstream as well as in -stable kernels. Florian Westphal provided the following commit: d1dab4f71d37 ("net: add and use __skb_get_hash_symmetric_net") but this complementary fix has been also suggested by Willem de Bruijn and it can be easily backported to -stable kernel which consists in using DEBUG_NET_WARN_ON_ONCE instead to silence the following splat given __skb_get_hash() is used by the nftables tracing infrastructure to to identify packets in traces. [69133.561393] ------------[ cut here ]------------ [69133.561404] WARNING: CPU: 0 PID: 43576 at net/core/flow_dissector.c:1104 __skb_flow_dissect+0x134f/ [...] [69133.561944] CPU: 0 PID: 43576 Comm: socat Not tainted 6.10.0-rc7+ #379 [69133.561959] RIP: 0010:__skb_flow_dissect+0x134f/0x2ad0 [69133.561970] Code: 83 f9 04 0f 84 b3 00 00 00 45 85 c9 0f 84 aa 00 00 00 41 83 f9 02 0f 84 81 fc ff ff 44 0f b7 b4 24 80 00 00 00 e9 8b f9 ff ff <0f> 0b e9 20 f3 ff ff 41 f6 c6 20 0f 84 e4 ef ff ff 48 8d 7b 12 e8 [69133.561979] RSP: 0018:ffffc90000006fc0 EFLAGS: 00010246 [69133.561988] RAX: 0000000000000000 RBX: ffffffff82f33e20 RCX: ffffffff81ab7e19 [69133.561994] RDX: dffffc0000000000 RSI: ffffc90000007388 RDI: ffff888103a1b418 [69133.562001] RBP: ffffc90000007310 R08: 0000000000000000 R09: 0000000000000000 [69133.562007] R10: ffffc90000007388 R11: ffffffff810cface R12: ffff888103a1b400 [69133.562013] R13: 0000000000000000 R14: ffffffff82f33e2a R15: ffffffff82f33e28 [69133.562020] FS: 00007f40f7131740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000 [69133.562027] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [69133.562033] CR2: 00007f40f7346ee0 CR3: 000000015d200001 CR4: 00000000001706f0 [69133.562040] Call Trace: [69133.562044] <IRQ> [69133.562049] ? __warn+0x9f/0x1a0 [ 1211.841384] ? __skb_flow_dissect+0x107e/0x2860 [...] [ 1211.841496] ? bpf_flow_dissect+0x160/0x160 [ 1211.841753] __skb_get_hash+0x97/0x280 [ 1211.841765] ? __skb_get_hash_symmetric+0x230/0x230 [ 1211.841776] ? mod_find+0xbf/0xe0 [ 1211.841786] ? get_stack_info_noinstr+0x12/0xe0 [ 1211.841798] ? bpf_ksym_find+0x56/0xe0 [ 1211.841807] ? __rcu_read_unlock+0x2a/0x70 [ 1211.841819] nft_trace_init+0x1b9/0x1c0 [nf_tables] [ 1211.841895] ? nft_trace_notify+0x830/0x830 [nf_tables] [ 1211.841964] ? get_stack_info+0x2b/0x80 [ 1211.841975] ? nft_do_chain_arp+0x80/0x80 [nf_tables] [ 1211.842044] nft_do_chain+0x79c/0x850 [nf_tables]
CVE-2024-43817: In the Linux kernel, the following vulnerability has been resolved: net: missing check virtio Two missing check in virtio_net_hdr_to_skb() allowed syzbot to crash kernels again 1. After the skb_segment function the buffer may become non-linear (nr_frags != 0), but since the SKBTX_SHARED_FRAG flag is not set anywhere the __skb_linearize function will not be executed, then the buffer will remain non-linear. Then the condition (offset >= skb_headlen(skb)) becomes true, which causes WARN_ON_ONCE in skb_checksum_help. 2. The struct sk_buff and struct virtio_net_hdr members must be mathematically related. (gso_size) must be greater than (needed) otherwise WARN_ON_ONCE. (remainder) must be greater than (needed) otherwise WARN_ON_ONCE. (remainder) may be 0 if division is without remainder. offset+2 (4191) > skb_headlen() (1116) WARNING: CPU: 1 PID: 5084 at net/core/dev.c:3303 skb_checksum_help+0x5e2/0x740 net/core/dev.c:3303 Modules linked in: CPU: 1 PID: 5084 Comm: syz-executor336 Not tainted 6.7.0-rc3-syzkaller-00014-gdf60cee26a2e #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023 RIP: 0010:skb_checksum_help+0x5e2/0x740 net/core/dev.c:3303 Code: 89 e8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 52 01 00 00 44 89 e2 2b 53 74 4c 89 ee 48 c7 c7 40 57 e9 8b e8 af 8f dd f8 90 <0f> 0b 90 90 e9 87 fe ff ff e8 40 0f 6e f9 e9 4b fa ff ff 48 89 ef RSP: 0018:ffffc90003a9f338 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff888025125780 RCX: ffffffff814db209 RDX: ffff888015393b80 RSI: ffffffff814db216 RDI: 0000000000000001 RBP: ffff8880251257f4 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: 000000000000045c R13: 000000000000105f R14: ffff8880251257f0 R15: 000000000000105d FS: 0000555555c24380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000002000f000 CR3: 0000000023151000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ip_do_fragment+0xa1b/0x18b0 net/ipv4/ip_output.c:777 ip_fragment.constprop.0+0x161/0x230 net/ipv4/ip_output.c:584 ip_finish_output_gso net/ipv4/ip_output.c:286 [inline] __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x49c/0x650 net/ipv4/ip_output.c:295 ip_finish_output+0x31/0x310 net/ipv4/ip_output.c:323 NF_HOOK_COND include/linux/netfilter.h:303 [inline] ip_output+0x13b/0x2a0 net/ipv4/ip_output.c:433 dst_output include/net/dst.h:451 [inline] ip_local_out+0xaf/0x1a0 net/ipv4/ip_output.c:129 iptunnel_xmit+0x5b4/0x9b0 net/ipv4/ip_tunnel_core.c:82 ipip6_tunnel_xmit net/ipv6/sit.c:1034 [inline] sit_tunnel_xmit+0xed2/0x28f0 net/ipv6/sit.c:1076 __netdev_start_xmit include/linux/netdevice.h:4940 [inline] netdev_start_xmit include/linux/netdevice.h:4954 [inline] xmit_one net/core/dev.c:3545 [inline] dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3561 __dev_queue_xmit+0x7c1/0x3d60 net/core/dev.c:4346 dev_queue_xmit include/linux/netdevice.h:3134 [inline] packet_xmit+0x257/0x380 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3087 [inline] packet_sendmsg+0x24ca/0x5240 net/packet/af_packet.c:3119 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xd5/0x180 net/socket.c:745 __sys_sendto+0x255/0x340 net/socket.c:2190 __do_sys_sendto net/socket.c:2202 [inline] __se_sys_sendto net/socket.c:2198 [inline] __x64_sys_sendto+0xe0/0x1b0 net/socket.c:2198 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b Found by Linux Verification Center (linuxtesting.org) with Syzkaller
CVE-2024-43819: In the Linux kernel, the following vulnerability has been resolved: kvm: s390: Reject memory region operations for ucontrol VMs This change rejects the KVM_SET_USER_MEMORY_REGION and KVM_SET_USER_MEMORY_REGION2 ioctls when called on a ucontrol VM. This is necessary since ucontrol VMs have kvm->arch.gmap set to 0 and would thus result in a null pointer dereference further in. Memory management needs to be performed in userspace and using the ioctls KVM_S390_UCAS_MAP and KVM_S390_UCAS_UNMAP. Also improve s390 specific documentation for KVM_SET_USER_MEMORY_REGION and KVM_SET_USER_MEMORY_REGION2. [frankja@linux.ibm.com: commit message spelling fix, subject prefix fix]
CVE-2024-43823: In the Linux kernel, the following vulnerability has been resolved: PCI: keystone: Fix NULL pointer dereference in case of DT error in ks_pcie_setup_rc_app_regs() If IORESOURCE_MEM is not provided in Device Tree due to any error, resource_list_first_type() will return NULL and pci_parse_request_of_pci_ranges() will just emit a warning. This will cause a NULL pointer dereference. Fix this bug by adding NULL return check. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2024-43824: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-test: Make use of cached 'epc_features' in pci_epf_test_core_init() Instead of getting the epc_features from pci_epc_get_features() API, use the cached pci_epf_test::epc_features value to avoid the NULL check. Since the NULL check is already performed in pci_epf_test_bind(), having one more check in pci_epf_test_core_init() is redundant and it is not possible to hit the NULL pointer dereference. Also with commit a01e7214bef9 ("PCI: endpoint: Remove "core_init_notifier" flag"), 'epc_features' got dereferenced without the NULL check, leading to the following false positive Smatch warning: drivers/pci/endpoint/functions/pci-epf-test.c:784 pci_epf_test_core_init() error: we previously assumed 'epc_features' could be null (see line 747) Thus, remove the redundant NULL check and also use the epc_features:: {msix_capable/msi_capable} flags directly to avoid local variables. [kwilczynski: commit log]
CVE-2024-43831: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: Handle invalid decoder vsi Handle an invalid decoder vsi in vpu_dec_init to ensure the decoder vsi is valid for future use.
CVE-2024-43832: In the Linux kernel, the following vulnerability has been resolved: s390/uv: Don't call folio_wait_writeback() without a folio reference folio_wait_writeback() requires that no spinlocks are held and that a folio reference is held, as documented. After we dropped the PTL, the folio could get freed concurrently. So grab a temporary reference.
CVE-2024-43866: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Always drain health in shutdown callback There is no point in recovery during device shutdown. if health work started need to wait for it to avoid races and NULL pointer access. Hence, drain health WQ on shutdown callback.
CVE-2024-43872: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix soft lockup under heavy CEQE load CEQEs are handled in interrupt handler currently. This may cause the CPU core staying in interrupt context too long and lead to soft lockup under heavy load. Handle CEQEs in BH workqueue and set an upper limit for the number of CEQE handled by a single call of work handler.
CVE-2024-43899: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix null pointer deref in dcn20_resource.c Fixes a hang thats triggered when MPV is run on a DCN401 dGPU: mpv --hwdec=vaapi --vo=gpu --hwdec-codecs=all and then enabling fullscreen playback (double click on the video) The following calltrace will be seen: [ 181.843989] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 181.843997] #PF: supervisor instruction fetch in kernel mode [ 181.844003] #PF: error_code(0x0010) - not-present page [ 181.844009] PGD 0 P4D 0 [ 181.844020] Oops: 0010 [#1] PREEMPT SMP NOPTI [ 181.844028] CPU: 6 PID: 1892 Comm: gnome-shell Tainted: G W OE 6.5.0-41-generic #41~22.04.2-Ubuntu [ 181.844038] Hardware name: System manufacturer System Product Name/CROSSHAIR VI HERO, BIOS 6302 10/23/2018 [ 181.844044] RIP: 0010:0x0 [ 181.844079] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 181.844084] RSP: 0018:ffffb593c2b8f7b0 EFLAGS: 00010246 [ 181.844093] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000004 [ 181.844099] RDX: ffffb593c2b8f804 RSI: ffffb593c2b8f7e0 RDI: ffff9e3c8e758400 [ 181.844105] RBP: ffffb593c2b8f7b8 R08: ffffb593c2b8f9c8 R09: ffffb593c2b8f96c [ 181.844110] R10: 0000000000000000 R11: 0000000000000000 R12: ffffb593c2b8f9c8 [ 181.844115] R13: 0000000000000001 R14: ffff9e3c88000000 R15: 0000000000000005 [ 181.844121] FS: 00007c6e323bb5c0(0000) GS:ffff9e3f85f80000(0000) knlGS:0000000000000000 [ 181.844128] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 181.844134] CR2: ffffffffffffffd6 CR3: 0000000140fbe000 CR4: 00000000003506e0 [ 181.844141] Call Trace: [ 181.844146] <TASK> [ 181.844153] ? show_regs+0x6d/0x80 [ 181.844167] ? __die+0x24/0x80 [ 181.844179] ? page_fault_oops+0x99/0x1b0 [ 181.844192] ? do_user_addr_fault+0x31d/0x6b0 [ 181.844204] ? exc_page_fault+0x83/0x1b0 [ 181.844216] ? asm_exc_page_fault+0x27/0x30 [ 181.844237] dcn20_get_dcc_compression_cap+0x23/0x30 [amdgpu] [ 181.845115] amdgpu_dm_plane_validate_dcc.constprop.0+0xe5/0x180 [amdgpu] [ 181.845985] amdgpu_dm_plane_fill_plane_buffer_attributes+0x300/0x580 [amdgpu] [ 181.846848] fill_dc_plane_info_and_addr+0x258/0x350 [amdgpu] [ 181.847734] fill_dc_plane_attributes+0x162/0x350 [amdgpu] [ 181.848748] dm_update_plane_state.constprop.0+0x4e3/0x6b0 [amdgpu] [ 181.849791] ? dm_update_plane_state.constprop.0+0x4e3/0x6b0 [amdgpu] [ 181.850840] amdgpu_dm_atomic_check+0xdfe/0x1760 [amdgpu]
CVE-2024-43900: In the Linux kernel, the following vulnerability has been resolved: media: xc2028: avoid use-after-free in load_firmware_cb() syzkaller reported use-after-free in load_firmware_cb() [1]. The reason is because the module allocated a struct tuner in tuner_probe(), and then the module initialization failed, the struct tuner was released. A worker which created during module initialization accesses this struct tuner later, it caused use-after-free. The process is as follows: task-6504 worker_thread tuner_probe <= alloc dvb_frontend [2] ... request_firmware_nowait <= create a worker ... tuner_remove <= free dvb_frontend ... request_firmware_work_func <= the firmware is ready load_firmware_cb <= but now the dvb_frontend has been freed To fix the issue, check the dvd_frontend in load_firmware_cb(), if it is null, report a warning and just return. [1]: ================================================================== BUG: KASAN: use-after-free in load_firmware_cb+0x1310/0x17a0 Read of size 8 at addr ffff8000d7ca2308 by task kworker/2:3/6504 Call trace: load_firmware_cb+0x1310/0x17a0 request_firmware_work_func+0x128/0x220 process_one_work+0x770/0x1824 worker_thread+0x488/0xea0 kthread+0x300/0x430 ret_from_fork+0x10/0x20 Allocated by task 6504: kzalloc tuner_probe+0xb0/0x1430 i2c_device_probe+0x92c/0xaf0 really_probe+0x678/0xcd0 driver_probe_device+0x280/0x370 __device_attach_driver+0x220/0x330 bus_for_each_drv+0x134/0x1c0 __device_attach+0x1f4/0x410 device_initial_probe+0x20/0x30 bus_probe_device+0x184/0x200 device_add+0x924/0x12c0 device_register+0x24/0x30 i2c_new_device+0x4e0/0xc44 v4l2_i2c_new_subdev_board+0xbc/0x290 v4l2_i2c_new_subdev+0xc8/0x104 em28xx_v4l2_init+0x1dd0/0x3770 Freed by task 6504: kfree+0x238/0x4e4 tuner_remove+0x144/0x1c0 i2c_device_remove+0xc8/0x290 __device_release_driver+0x314/0x5fc device_release_driver+0x30/0x44 bus_remove_device+0x244/0x490 device_del+0x350/0x900 device_unregister+0x28/0xd0 i2c_unregister_device+0x174/0x1d0 v4l2_device_unregister+0x224/0x380 em28xx_v4l2_init+0x1d90/0x3770 The buggy address belongs to the object at ffff8000d7ca2000 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 776 bytes inside of 2048-byte region [ffff8000d7ca2000, ffff8000d7ca2800) The buggy address belongs to the page: page:ffff7fe00035f280 count:1 mapcount:0 mapping:ffff8000c001f000 index:0x0 flags: 0x7ff800000000100(slab) raw: 07ff800000000100 ffff7fe00049d880 0000000300000003 ffff8000c001f000 raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8000d7ca2200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8000d7ca2280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8000d7ca2300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8000d7ca2380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8000d7ca2400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== [2] Actually, it is allocated for struct tuner, and dvb_frontend is inside.
CVE-2024-43901: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix NULL pointer dereference for DTN log in DCN401 When users run the command: cat /sys/kernel/debug/dri/0/amdgpu_dm_dtn_log The following NULL pointer dereference happens: [ +0.000003] BUG: kernel NULL pointer dereference, address: NULL [ +0.000005] #PF: supervisor instruction fetch in kernel mode [ +0.000002] #PF: error_code(0x0010) - not-present page [ +0.000002] PGD 0 P4D 0 [ +0.000004] Oops: 0010 [#1] PREEMPT SMP NOPTI [ +0.000003] RIP: 0010:0x0 [ +0.000008] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [...] [ +0.000002] PKRU: 55555554 [ +0.000002] Call Trace: [ +0.000002] <TASK> [ +0.000003] ? show_regs+0x65/0x70 [ +0.000006] ? __die+0x24/0x70 [ +0.000004] ? page_fault_oops+0x160/0x470 [ +0.000006] ? do_user_addr_fault+0x2b5/0x690 [ +0.000003] ? prb_read_valid+0x1c/0x30 [ +0.000005] ? exc_page_fault+0x8c/0x1a0 [ +0.000005] ? asm_exc_page_fault+0x27/0x30 [ +0.000012] dcn10_log_color_state+0xf9/0x510 [amdgpu] [ +0.000306] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000003] ? vsnprintf+0x2fb/0x600 [ +0.000009] dcn10_log_hw_state+0xfd0/0xfe0 [amdgpu] [ +0.000218] ? __mod_memcg_lruvec_state+0xe8/0x170 [ +0.000008] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? debug_smp_processor_id+0x17/0x20 [ +0.000003] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? set_ptes.isra.0+0x2b/0x90 [ +0.000004] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? _raw_spin_unlock+0x19/0x40 [ +0.000004] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? do_anonymous_page+0x337/0x700 [ +0.000004] dtn_log_read+0x82/0x120 [amdgpu] [ +0.000207] full_proxy_read+0x66/0x90 [ +0.000007] vfs_read+0xb0/0x340 [ +0.000005] ? __count_memcg_events+0x79/0xe0 [ +0.000002] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000003] ? count_memcg_events.constprop.0+0x1e/0x40 [ +0.000003] ? handle_mm_fault+0xb2/0x370 [ +0.000003] ksys_read+0x6b/0xf0 [ +0.000004] __x64_sys_read+0x19/0x20 [ +0.000003] do_syscall_64+0x60/0x130 [ +0.000004] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ +0.000003] RIP: 0033:0x7fdf32f147e2 [...] This error happens when the color log tries to read the gamut remap information from DCN401 which is not initialized in the dcn401_dpp_funcs which leads to a null pointer dereference. This commit addresses this issue by adding a proper guard to access the gamut_remap callback in case the specific ASIC did not implement this function.
CVE-2024-43902: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null checker before passing variables Checks null pointer before passing variables to functions. This fixes 3 NULL_RETURNS issues reported by Coverity.
CVE-2024-43904: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null checks for 'stream' and 'plane' before dereferencing This commit adds null checks for the 'stream' and 'plane' variables in the dcn30_apply_idle_power_optimizations function. These variables were previously assumed to be null at line 922, but they were used later in the code without checking if they were null. This could potentially lead to a null pointer dereference, which would cause a crash. The null checks ensure that 'stream' and 'plane' are not null before they are used, preventing potential crashes. Fixes the below static smatch checker: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn30/dcn30_hwseq.c:938 dcn30_apply_idle_power_optimizations() error: we previously assumed 'stream' could be null (see line 922) drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn30/dcn30_hwseq.c:940 dcn30_apply_idle_power_optimizations() error: we previously assumed 'plane' could be null (see line 922)
CVE-2024-43909: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/pm: Fix the null pointer dereference for smu7 optimize the code to avoid pass a null pointer (hwmgr->backend) to function smu7_update_edc_leakage_table.
CVE-2024-43912: In the Linux kernel, the following vulnerability has been resolved: wifi: nl80211: disallow setting special AP channel widths Setting the AP channel width is meant for use with the normal 20/40/... MHz channel width progression, and switching around in S1G or narrow channels isn't supported. Disallow that.
CVE-2024-44934: In the Linux kernel, the following vulnerability has been resolved: net: bridge: mcast: wait for previous gc cycles when removing port syzbot hit a use-after-free[1] which is caused because the bridge doesn't make sure that all previous garbage has been collected when removing a port. What happens is: CPU 1 CPU 2 start gc cycle remove port acquire gc lock first wait for lock call br_multicasg_gc() directly acquire lock now but free port the port can be freed while grp timers still running Make sure all previous gc cycles have finished by using flush_work before freeing the port. [1] BUG: KASAN: slab-use-after-free in br_multicast_port_group_expired+0x4c0/0x550 net/bridge/br_multicast.c:861 Read of size 8 at addr ffff888071d6d000 by task syz.5.1232/9699 CPU: 1 PID: 9699 Comm: syz.5.1232 Not tainted 6.10.0-rc5-syzkaller-00021-g24ca36a562d6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/07/2024 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0xc3/0x620 mm/kasan/report.c:488 kasan_report+0xd9/0x110 mm/kasan/report.c:601 br_multicast_port_group_expired+0x4c0/0x550 net/bridge/br_multicast.c:861 call_timer_fn+0x1a3/0x610 kernel/time/timer.c:1792 expire_timers kernel/time/timer.c:1843 [inline] __run_timers+0x74b/0xaf0 kernel/time/timer.c:2417 __run_timer_base kernel/time/timer.c:2428 [inline] __run_timer_base kernel/time/timer.c:2421 [inline] run_timer_base+0x111/0x190 kernel/time/timer.c:2437
CVE-2024-44939: In the Linux kernel, the following vulnerability has been resolved: jfs: fix null ptr deref in dtInsertEntry [syzbot reported] general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 0 PID: 5061 Comm: syz-executor404 Not tainted 6.8.0-syzkaller-08951-gfe46a7dd189e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 RIP: 0010:dtInsertEntry+0xd0c/0x1780 fs/jfs/jfs_dtree.c:3713 ... [Analyze] In dtInsertEntry(), when the pointer h has the same value as p, after writing name in UniStrncpy_to_le(), p->header.flag will be cleared. This will cause the previously true judgment "p->header.flag & BT-LEAF" to change to no after writing the name operation, this leads to entering an incorrect branch and accessing the uninitialized object ih when judging this condition for the second time. [Fix] After got the page, check freelist first, if freelist == 0 then exit dtInsert() and return -EINVAL.
CVE-2024-44941: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to cover read extent cache access with lock syzbot reports a f2fs bug as below: BUG: KASAN: slab-use-after-free in sanity_check_extent_cache+0x370/0x410 fs/f2fs/extent_cache.c:46 Read of size 4 at addr ffff8880739ab220 by task syz-executor200/5097 CPU: 0 PID: 5097 Comm: syz-executor200 Not tainted 6.9.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 sanity_check_extent_cache+0x370/0x410 fs/f2fs/extent_cache.c:46 do_read_inode fs/f2fs/inode.c:509 [inline] f2fs_iget+0x33e1/0x46e0 fs/f2fs/inode.c:560 f2fs_nfs_get_inode+0x74/0x100 fs/f2fs/super.c:3237 generic_fh_to_dentry+0x9f/0xf0 fs/libfs.c:1413 exportfs_decode_fh_raw+0x152/0x5f0 fs/exportfs/expfs.c:444 exportfs_decode_fh+0x3c/0x80 fs/exportfs/expfs.c:584 do_handle_to_path fs/fhandle.c:155 [inline] handle_to_path fs/fhandle.c:210 [inline] do_handle_open+0x495/0x650 fs/fhandle.c:226 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f We missed to cover sanity_check_extent_cache() w/ extent cache lock, so, below race case may happen, result in use after free issue. - f2fs_iget - do_read_inode - f2fs_init_read_extent_tree : add largest extent entry in to cache - shrink - f2fs_shrink_read_extent_tree - __shrink_extent_tree - __detach_extent_node : drop largest extent entry - sanity_check_extent_cache : access et->largest w/o lock let's refactor sanity_check_extent_cache() to avoid extent cache access and call it before f2fs_init_read_extent_tree() to fix this issue.
CVE-2024-44942: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing.
CVE-2024-44950: In the Linux kernel, the following vulnerability has been resolved: serial: sc16is7xx: fix invalid FIFO access with special register set When enabling access to the special register set, Receiver time-out and RHR interrupts can happen. In this case, the IRQ handler will try to read from the FIFO thru the RHR register at address 0x00, but address 0x00 is mapped to DLL register, resulting in erroneous FIFO reading. Call graph example: sc16is7xx_startup(): entry sc16is7xx_ms_proc(): entry sc16is7xx_set_termios(): entry sc16is7xx_set_baud(): DLH/DLL = $009C --> access special register set sc16is7xx_port_irq() entry --> IIR is 0x0C sc16is7xx_handle_rx() entry sc16is7xx_fifo_read(): --> unable to access FIFO (RHR) because it is mapped to DLL (LCR=LCR_CONF_MODE_A) sc16is7xx_set_baud(): exit --> Restore access to general register set Fix the problem by claiming the efr_lock mutex when accessing the Special register set.
CVE-2024-44958: In the Linux kernel, the following vulnerability has been resolved: sched/smt: Fix unbalance sched_smt_present dec/inc I got the following warn report while doing stress test: jump label: negative count! WARNING: CPU: 3 PID: 38 at kernel/jump_label.c:263 static_key_slow_try_dec+0x9d/0xb0 Call Trace: <TASK> __static_key_slow_dec_cpuslocked+0x16/0x70 sched_cpu_deactivate+0x26e/0x2a0 cpuhp_invoke_callback+0x3ad/0x10d0 cpuhp_thread_fun+0x3f5/0x680 smpboot_thread_fn+0x56d/0x8d0 kthread+0x309/0x400 ret_from_fork+0x41/0x70 ret_from_fork_asm+0x1b/0x30 </TASK> Because when cpuset_cpu_inactive() fails in sched_cpu_deactivate(), the cpu offline failed, but sched_smt_present is decremented before calling sched_cpu_deactivate(), it leads to unbalanced dec/inc, so fix it by incrementing sched_smt_present in the error path.
CVE-2024-44963: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not BUG_ON() when freeing tree block after error When freeing a tree block, at btrfs_free_tree_block(), if we fail to create a delayed reference we don't deal with the error and just do a BUG_ON(). The error most likely to happen is -ENOMEM, and we have a comment mentioning that only -ENOMEM can happen, but that is not true, because in case qgroups are enabled any error returned from btrfs_qgroup_trace_extent_post() (can be -EUCLEAN or anything returned from btrfs_search_slot() for example) can be propagated back to btrfs_free_tree_block(). So stop doing a BUG_ON() and return the error to the callers and make them abort the transaction to prevent leaking space. Syzbot was triggering this, likely due to memory allocation failure injection.
CVE-2024-44969: In the Linux kernel, the following vulnerability has been resolved: s390/sclp: Prevent release of buffer in I/O When a task waiting for completion of a Store Data operation is interrupted, an attempt is made to halt this operation. If this attempt fails due to a hardware or firmware problem, there is a chance that the SCLP facility might store data into buffers referenced by the original operation at a later time. Handle this situation by not releasing the referenced data buffers if the halt attempt fails. For current use cases, this might result in a leak of few pages of memory in case of a rare hardware/firmware malfunction.
CVE-2024-44982: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: cleanup FB if dpu_format_populate_layout fails If the dpu_format_populate_layout() fails, then FB is prepared, but not cleaned up. This ends up leaking the pin_count on the GEM object and causes a splat during DRM file closure: msm_obj->pin_count WARNING: CPU: 2 PID: 569 at drivers/gpu/drm/msm/msm_gem.c:121 update_lru_locked+0xc4/0xcc [...] Call trace: update_lru_locked+0xc4/0xcc put_pages+0xac/0x100 msm_gem_free_object+0x138/0x180 drm_gem_object_free+0x1c/0x30 drm_gem_object_handle_put_unlocked+0x108/0x10c drm_gem_object_release_handle+0x58/0x70 idr_for_each+0x68/0xec drm_gem_release+0x28/0x40 drm_file_free+0x174/0x234 drm_release+0xb0/0x160 __fput+0xc0/0x2c8 __fput_sync+0x50/0x5c __arm64_sys_close+0x38/0x7c invoke_syscall+0x48/0x118 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x4c/0x120 el0t_64_sync_handler+0x100/0x12c el0t_64_sync+0x190/0x194 irq event stamp: 129818 hardirqs last enabled at (129817): [<ffffa5f6d953fcc0>] console_unlock+0x118/0x124 hardirqs last disabled at (129818): [<ffffa5f6da7dcf04>] el1_dbg+0x24/0x8c softirqs last enabled at (129808): [<ffffa5f6d94afc18>] handle_softirqs+0x4c8/0x4e8 softirqs last disabled at (129785): [<ffffa5f6d94105e4>] __do_softirq+0x14/0x20 Patchwork: https://patchwork.freedesktop.org/patch/600714/
CVE-2024-44986: In the Linux kernel, the following vulnerability has been resolved: ipv6: fix possible UAF in ip6_finish_output2() If skb_expand_head() returns NULL, skb has been freed and associated dst/idev could also have been freed. We need to hold rcu_read_lock() to make sure the dst and associated idev are alive.
CVE-2024-45009: In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: only decrement add_addr_accepted for MPJ req Adding the following warning ... WARN_ON_ONCE(msk->pm.add_addr_accepted == 0) ... before decrementing the add_addr_accepted counter helped to find a bug when running the "remove single subflow" subtest from the mptcp_join.sh selftest. Removing a 'subflow' endpoint will first trigger a RM_ADDR, then the subflow closure. Before this patch, and upon the reception of the RM_ADDR, the other peer will then try to decrement this add_addr_accepted. That's not correct because the attached subflows have not been created upon the reception of an ADD_ADDR. A way to solve that is to decrement the counter only if the attached subflow was an MP_JOIN to a remote id that was not 0, and initiated by the host receiving the RM_ADDR.
CVE-2024-45015: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: move dpu_encoder's connector assignment to atomic_enable() For cases where the crtc's connectors_changed was set without enable/active getting toggled , there is an atomic_enable() call followed by an atomic_disable() but without an atomic_mode_set(). This results in a NULL ptr access for the dpu_encoder_get_drm_fmt() call in the atomic_enable() as the dpu_encoder's connector was cleared in the atomic_disable() but not re-assigned as there was no atomic_mode_set() call. Fix the NULL ptr access by moving the assignment for atomic_enable() and also use drm_atomic_get_new_connector_for_encoder() to get the connector from the atomic_state. Patchwork: https://patchwork.freedesktop.org/patch/606729/
CVE-2024-45026: In the Linux kernel, the following vulnerability has been resolved: s390/dasd: fix error recovery leading to data corruption on ESE devices Extent Space Efficient (ESE) or thin provisioned volumes need to be formatted on demand during usual IO processing. The dasd_ese_needs_format function checks for error codes that signal the non existence of a proper track format. The check for incorrect length is to imprecise since other error cases leading to transport of insufficient data also have this flag set. This might lead to data corruption in certain error cases for example during a storage server warmstart. Fix by removing the check for incorrect length and replacing by explicitly checking for invalid track format in transport mode. Also remove the check for file protected since this is not a valid ESE handling case.
CVE-2024-45828: In the Linux kernel, the following vulnerability has been resolved: i3c: mipi-i3c-hci: Mask ring interrupts before ring stop request Bus cleanup path in DMA mode may trigger a RING_OP_STAT interrupt when the ring is being stopped. Depending on timing between ring stop request completion, interrupt handler removal and code execution this may lead to a NULL pointer dereference in hci_dma_irq_handler() if it gets to run after the io_data pointer is set to NULL in hci_dma_cleanup(). Prevent this my masking the ring interrupts before ring stop request.
CVE-2024-46678: In the Linux kernel, the following vulnerability has been resolved: bonding: change ipsec_lock from spin lock to mutex In the cited commit, bond->ipsec_lock is added to protect ipsec_list, hence xdo_dev_state_add and xdo_dev_state_delete are called inside this lock. As ipsec_lock is a spin lock and such xfrmdev ops may sleep, "scheduling while atomic" will be triggered when changing bond's active slave. [ 101.055189] BUG: scheduling while atomic: bash/902/0x00000200 [ 101.055726] Modules linked in: [ 101.058211] CPU: 3 PID: 902 Comm: bash Not tainted 6.9.0-rc4+ #1 [ 101.058760] Hardware name: [ 101.059434] Call Trace: [ 101.059436] <TASK> [ 101.060873] dump_stack_lvl+0x51/0x60 [ 101.061275] __schedule_bug+0x4e/0x60 [ 101.061682] __schedule+0x612/0x7c0 [ 101.062078] ? __mod_timer+0x25c/0x370 [ 101.062486] schedule+0x25/0xd0 [ 101.062845] schedule_timeout+0x77/0xf0 [ 101.063265] ? asm_common_interrupt+0x22/0x40 [ 101.063724] ? __bpf_trace_itimer_state+0x10/0x10 [ 101.064215] __wait_for_common+0x87/0x190 [ 101.064648] ? usleep_range_state+0x90/0x90 [ 101.065091] cmd_exec+0x437/0xb20 [mlx5_core] [ 101.065569] mlx5_cmd_do+0x1e/0x40 [mlx5_core] [ 101.066051] mlx5_cmd_exec+0x18/0x30 [mlx5_core] [ 101.066552] mlx5_crypto_create_dek_key+0xea/0x120 [mlx5_core] [ 101.067163] ? bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.067738] ? kmalloc_trace+0x4d/0x350 [ 101.068156] mlx5_ipsec_create_sa_ctx+0x33/0x100 [mlx5_core] [ 101.068747] mlx5e_xfrm_add_state+0x47b/0xaa0 [mlx5_core] [ 101.069312] bond_change_active_slave+0x392/0x900 [bonding] [ 101.069868] bond_option_active_slave_set+0x1c2/0x240 [bonding] [ 101.070454] __bond_opt_set+0xa6/0x430 [bonding] [ 101.070935] __bond_opt_set_notify+0x2f/0x90 [bonding] [ 101.071453] bond_opt_tryset_rtnl+0x72/0xb0 [bonding] [ 101.071965] bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.072567] kernfs_fop_write_iter+0x10c/0x1a0 [ 101.073033] vfs_write+0x2d8/0x400 [ 101.073416] ? alloc_fd+0x48/0x180 [ 101.073798] ksys_write+0x5f/0xe0 [ 101.074175] do_syscall_64+0x52/0x110 [ 101.074576] entry_SYSCALL_64_after_hwframe+0x4b/0x53 As bond_ipsec_add_sa_all and bond_ipsec_del_sa_all are only called from bond_change_active_slave, which requires holding the RTNL lock. And bond_ipsec_add_sa and bond_ipsec_del_sa are xfrm state xdo_dev_state_add and xdo_dev_state_delete APIs, which are in user context. So ipsec_lock doesn't have to be spin lock, change it to mutex, and thus the above issue can be resolved.
CVE-2024-46681: In the Linux kernel, the following vulnerability has been resolved: pktgen: use cpus_read_lock() in pg_net_init() I have seen the WARN_ON(smp_processor_id() != cpu) firing in pktgen_thread_worker() during tests. We must use cpus_read_lock()/cpus_read_unlock() around the for_each_online_cpu(cpu) loop. While we are at it use WARN_ON_ONCE() to avoid a possible syslog flood.
CVE-2024-46715: In the Linux kernel, the following vulnerability has been resolved: driver: iio: add missing checks on iio_info's callback access Some callbacks from iio_info structure are accessed without any check, so if a driver doesn't implement them trying to access the corresponding sysfs entries produce a kernel oops such as: [ 2203.527791] Unable to handle kernel NULL pointer dereference at virtual address 00000000 when execute [...] [ 2203.783416] Call trace: [ 2203.783429] iio_read_channel_info_avail from dev_attr_show+0x18/0x48 [ 2203.789807] dev_attr_show from sysfs_kf_seq_show+0x90/0x120 [ 2203.794181] sysfs_kf_seq_show from seq_read_iter+0xd0/0x4e4 [ 2203.798555] seq_read_iter from vfs_read+0x238/0x2a0 [ 2203.802236] vfs_read from ksys_read+0xa4/0xd4 [ 2203.805385] ksys_read from ret_fast_syscall+0x0/0x54 [ 2203.809135] Exception stack(0xe0badfa8 to 0xe0badff0) [ 2203.812880] dfa0: 00000003 b6f10f80 00000003 b6eab000 00020000 00000000 [ 2203.819746] dfc0: 00000003 b6f10f80 7ff00000 00000003 00000003 00000000 00020000 00000000 [ 2203.826619] dfe0: b6e1bc88 bed80958 b6e1bc94 b6e1bcb0 [ 2203.830363] Code: bad PC value [ 2203.832695] ---[ end trace 0000000000000000 ]---
CVE-2024-46716: In the Linux kernel, the following vulnerability has been resolved: dmaengine: altera-msgdma: properly free descriptor in msgdma_free_descriptor Remove list_del call in msgdma_chan_desc_cleanup, this should be the role of msgdma_free_descriptor. In consequence replace list_add_tail with list_move_tail in msgdma_free_descriptor. This fixes the path: msgdma_free_chan_resources -> msgdma_free_descriptors -> msgdma_free_desc_list -> msgdma_free_descriptor which does not correctly free the descriptors as first nodes were not removed from the list.
CVE-2024-46720: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix dereference after null check check the pointer hive before use.
CVE-2024-46726: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Ensure index calculation will not overflow [WHY & HOW] Make sure vmid0p72_idx, vnom0p8_idx and vmax0p9_idx calculation will never overflow and exceess array size. This fixes 3 OVERRUN and 1 INTEGER_OVERFLOW issues reported by Coverity.
CVE-2024-46727: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add otg_master NULL check within resource_log_pipe_topology_update [Why] Coverity reports NULL_RETURN warning. [How] Add otg_master NULL check.
CVE-2024-46728: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check index for aux_rd_interval before using aux_rd_interval has size of 7 and should be checked. This fixes 3 OVERRUN and 1 INTEGER_OVERFLOW issues reported by Coverity.
CVE-2024-46729: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix incorrect size calculation for loop [WHY] fe_clk_en has size of 5 but sizeof(fe_clk_en) has byte size 20 which is lager than the array size. [HOW] Divide byte size 20 by its element size. This fixes 2 OVERRUN issues reported by Coverity.
CVE-2024-46730: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Ensure array index tg_inst won't be -1 [WHY & HOW] tg_inst will be a negative if timing_generator_count equals 0, which should be checked before used. This fixes 2 OVERRUN issues reported by Coverity.
CVE-2024-46732: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Assign linear_pitch_alignment even for VM [Description] Assign linear_pitch_alignment so we don't cause a divide by 0 error in VM environments
CVE-2024-46733: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix qgroup reserve leaks in cow_file_range In the buffered write path, the dirty page owns the qgroup reserve until it creates an ordered_extent. Therefore, any errors that occur before the ordered_extent is created must free that reservation, or else the space is leaked. The fstest generic/475 exercises various IO error paths, and is able to trigger errors in cow_file_range where we fail to get to allocating the ordered extent. Note that because we *do* clear delalloc, we are likely to remove the inode from the delalloc list, so the inodes/pages to not have invalidate/launder called on them in the commit abort path. This results in failures at the unmount stage of the test that look like: BTRFS: error (device dm-8 state EA) in cleanup_transaction:2018: errno=-5 IO failure BTRFS: error (device dm-8 state EA) in btrfs_replace_file_extents:2416: errno=-5 IO failure BTRFS warning (device dm-8 state EA): qgroup 0/5 has unreleased space, type 0 rsv 28672 ------------[ cut here ]------------ WARNING: CPU: 3 PID: 22588 at fs/btrfs/disk-io.c:4333 close_ctree+0x222/0x4d0 [btrfs] Modules linked in: btrfs blake2b_generic libcrc32c xor zstd_compress raid6_pq CPU: 3 PID: 22588 Comm: umount Kdump: loaded Tainted: G W 6.10.0-rc7-gab56fde445b8 #21 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014 RIP: 0010:close_ctree+0x222/0x4d0 [btrfs] RSP: 0018:ffffb4465283be00 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffffa1a1818e1000 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffffb4465283bbe0 RDI: ffffa1a19374fcb8 RBP: ffffa1a1818e13c0 R08: 0000000100028b16 R09: 0000000000000000 R10: 0000000000000003 R11: 0000000000000003 R12: ffffa1a18ad7972c R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f9168312b80(0000) GS:ffffa1a4afcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f91683c9140 CR3: 000000010acaa000 CR4: 00000000000006f0 Call Trace: <TASK> ? close_ctree+0x222/0x4d0 [btrfs] ? __warn.cold+0x8e/0xea ? close_ctree+0x222/0x4d0 [btrfs] ? report_bug+0xff/0x140 ? handle_bug+0x3b/0x70 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? close_ctree+0x222/0x4d0 [btrfs] generic_shutdown_super+0x70/0x160 kill_anon_super+0x11/0x40 btrfs_kill_super+0x11/0x20 [btrfs] deactivate_locked_super+0x2e/0xa0 cleanup_mnt+0xb5/0x150 task_work_run+0x57/0x80 syscall_exit_to_user_mode+0x121/0x130 do_syscall_64+0xab/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f916847a887 ---[ end trace 0000000000000000 ]--- BTRFS error (device dm-8 state EA): qgroup reserved space leaked Cases 2 and 3 in the out_reserve path both pertain to this type of leak and must free the reserved qgroup data. Because it is already an error path, I opted not to handle the possible errors in btrfs_free_qgroup_data.
CVE-2024-46752: In the Linux kernel, the following vulnerability has been resolved: btrfs: replace BUG_ON() with error handling at update_ref_for_cow() Instead of a BUG_ON() just return an error, log an error message and abort the transaction in case we find an extent buffer belonging to the relocation tree that doesn't have the full backref flag set. This is unexpected and should never happen (save for bugs or a potential bad memory).
CVE-2024-46754: In the Linux kernel, the following vulnerability has been resolved: bpf: Remove tst_run from lwt_seg6local_prog_ops. The syzbot reported that the lwt_seg6 related BPF ops can be invoked via bpf_test_run() without without entering input_action_end_bpf() first. Martin KaFai Lau said that self test for BPF_PROG_TYPE_LWT_SEG6LOCAL probably didn't work since it was introduced in commit 04d4b274e2a ("ipv6: sr: Add seg6local action End.BPF"). The reason is that the per-CPU variable seg6_bpf_srh_states::srh is never assigned in the self test case but each BPF function expects it. Remove test_run for BPF_PROG_TYPE_LWT_SEG6LOCAL.
CVE-2024-46760: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: usb: schedule rx work after everything is set up Right now it's possible to hit NULL pointer dereference in rtw_rx_fill_rx_status on hw object and/or its fields because initialization routine can start getting USB replies before rtw_dev is fully setup. The stack trace looks like this: rtw_rx_fill_rx_status rtw8821c_query_rx_desc rtw_usb_rx_handler ... queue_work rtw_usb_read_port_complete ... usb_submit_urb rtw_usb_rx_resubmit rtw_usb_init_rx rtw_usb_probe So while we do the async stuff rtw_usb_probe continues and calls rtw_register_hw, which does all kinds of initialization (e.g. via ieee80211_register_hw) that rtw_rx_fill_rx_status relies on. Fix this by moving the first usb_submit_urb after everything is set up. For me, this bug manifested as: [ 8.893177] rtw_8821cu 1-1:1.2: band wrong, packet dropped [ 8.910904] rtw_8821cu 1-1:1.2: hw->conf.chandef.chan NULL in rtw_rx_fill_rx_status because I'm using Larry's backport of rtw88 driver with the NULL checks in rtw_rx_fill_rx_status.
CVE-2024-46765: In the Linux kernel, the following vulnerability has been resolved: ice: protect XDP configuration with a mutex The main threat to data consistency in ice_xdp() is a possible asynchronous PF reset. It can be triggered by a user or by TX timeout handler. XDP setup and PF reset code access the same resources in the following sections: * ice_vsi_close() in ice_prepare_for_reset() - already rtnl-locked * ice_vsi_rebuild() for the PF VSI - not protected * ice_vsi_open() - already rtnl-locked With an unfortunate timing, such accesses can result in a crash such as the one below: [ +1.999878] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 14 [ +2.002992] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 18 [Mar15 18:17] ice 0000:b1:00.0 ens801f0np0: NETDEV WATCHDOG: CPU: 38: transmit queue 14 timed out 80692736 ms [ +0.000093] ice 0000:b1:00.0 ens801f0np0: tx_timeout: VSI_num: 6, Q 14, NTC: 0x0, HW_HEAD: 0x0, NTU: 0x0, INT: 0x4000001 [ +0.000012] ice 0000:b1:00.0 ens801f0np0: tx_timeout recovery level 1, txqueue 14 [ +0.394718] ice 0000:b1:00.0: PTP reset successful [ +0.006184] BUG: kernel NULL pointer dereference, address: 0000000000000098 [ +0.000045] #PF: supervisor read access in kernel mode [ +0.000023] #PF: error_code(0x0000) - not-present page [ +0.000023] PGD 0 P4D 0 [ +0.000018] Oops: 0000 [#1] PREEMPT SMP NOPTI [ +0.000023] CPU: 38 PID: 7540 Comm: kworker/38:1 Not tainted 6.8.0-rc7 #1 [ +0.000031] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021 [ +0.000036] Workqueue: ice ice_service_task [ice] [ +0.000183] RIP: 0010:ice_clean_tx_ring+0xa/0xd0 [ice] [...] [ +0.000013] Call Trace: [ +0.000016] <TASK> [ +0.000014] ? __die+0x1f/0x70 [ +0.000029] ? page_fault_oops+0x171/0x4f0 [ +0.000029] ? schedule+0x3b/0xd0 [ +0.000027] ? exc_page_fault+0x7b/0x180 [ +0.000022] ? asm_exc_page_fault+0x22/0x30 [ +0.000031] ? ice_clean_tx_ring+0xa/0xd0 [ice] [ +0.000194] ice_free_tx_ring+0xe/0x60 [ice] [ +0.000186] ice_destroy_xdp_rings+0x157/0x310 [ice] [ +0.000151] ice_vsi_decfg+0x53/0xe0 [ice] [ +0.000180] ice_vsi_rebuild+0x239/0x540 [ice] [ +0.000186] ice_vsi_rebuild_by_type+0x76/0x180 [ice] [ +0.000145] ice_rebuild+0x18c/0x840 [ice] [ +0.000145] ? delay_tsc+0x4a/0xc0 [ +0.000022] ? delay_tsc+0x92/0xc0 [ +0.000020] ice_do_reset+0x140/0x180 [ice] [ +0.000886] ice_service_task+0x404/0x1030 [ice] [ +0.000824] process_one_work+0x171/0x340 [ +0.000685] worker_thread+0x277/0x3a0 [ +0.000675] ? preempt_count_add+0x6a/0xa0 [ +0.000677] ? _raw_spin_lock_irqsave+0x23/0x50 [ +0.000679] ? __pfx_worker_thread+0x10/0x10 [ +0.000653] kthread+0xf0/0x120 [ +0.000635] ? __pfx_kthread+0x10/0x10 [ +0.000616] ret_from_fork+0x2d/0x50 [ +0.000612] ? __pfx_kthread+0x10/0x10 [ +0.000604] ret_from_fork_asm+0x1b/0x30 [ +0.000604] </TASK> The previous way of handling this through returning -EBUSY is not viable, particularly when destroying AF_XDP socket, because the kernel proceeds with removal anyway. There is plenty of code between those calls and there is no need to create a large critical section that covers all of them, same as there is no need to protect ice_vsi_rebuild() with rtnl_lock(). Add xdp_state_lock mutex to protect ice_vsi_rebuild() and ice_xdp(). Leaving unprotected sections in between would result in two states that have to be considered: 1. when the VSI is closed, but not yet rebuild 2. when VSI is already rebuild, but not yet open The latter case is actually already handled through !netif_running() case, we just need to adjust flag checking a little. The former one is not as trivial, because between ice_vsi_close() and ice_vsi_rebuild(), a lot of hardware interaction happens, this can make adding/deleting rings exit with an error. Luckily, VSI rebuild is pending and can apply new configuration for us in a managed fashion. Therefore, add an additional VSI state flag ICE_VSI_REBUILD_PENDING to indicate that ice_x ---truncated---
CVE-2024-46770: In the Linux kernel, the following vulnerability has been resolved: ice: Add netif_device_attach/detach into PF reset flow Ethtool callbacks can be executed while reset is in progress and try to access deleted resources, e.g. getting coalesce settings can result in a NULL pointer dereference seen below. Reproduction steps: Once the driver is fully initialized, trigger reset: # echo 1 > /sys/class/net/<interface>/device/reset when reset is in progress try to get coalesce settings using ethtool: # ethtool -c <interface> BUG: kernel NULL pointer dereference, address: 0000000000000020 PGD 0 P4D 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 11 PID: 19713 Comm: ethtool Tainted: G S 6.10.0-rc7+ #7 RIP: 0010:ice_get_q_coalesce+0x2e/0xa0 [ice] RSP: 0018:ffffbab1e9bcf6a8 EFLAGS: 00010206 RAX: 000000000000000c RBX: ffff94512305b028 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9451c3f2e588 RDI: ffff9451c3f2e588 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffff9451c3f2e580 R11: 000000000000001f R12: ffff945121fa9000 R13: ffffbab1e9bcf760 R14: 0000000000000013 R15: ffffffff9e65dd40 FS: 00007faee5fbe740(0000) GS:ffff94546fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000020 CR3: 0000000106c2e005 CR4: 00000000001706f0 Call Trace: <TASK> ice_get_coalesce+0x17/0x30 [ice] coalesce_prepare_data+0x61/0x80 ethnl_default_doit+0xde/0x340 genl_family_rcv_msg_doit+0xf2/0x150 genl_rcv_msg+0x1b3/0x2c0 netlink_rcv_skb+0x5b/0x110 genl_rcv+0x28/0x40 netlink_unicast+0x19c/0x290 netlink_sendmsg+0x222/0x490 __sys_sendto+0x1df/0x1f0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x82/0x160 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7faee60d8e27 Calling netif_device_detach() before reset makes the net core not call the driver when ethtool command is issued, the attempt to execute an ethtool command during reset will result in the following message: netlink error: No such device instead of NULL pointer dereference. Once reset is done and ice_rebuild() is executing, the netif_device_attach() is called to allow for ethtool operations to occur again in a safe manner.
CVE-2024-46772: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check denominator crb_pipes before used [WHAT & HOW] A denominator cannot be 0, and is checked before used. This fixes 2 DIVIDE_BY_ZERO issues reported by Coverity.
CVE-2024-46773: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check denominator pbn_div before used [WHAT & HOW] A denominator cannot be 0, and is checked before used. This fixes 1 DIVIDE_BY_ZERO issue reported by Coverity.
CVE-2024-46775: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Validate function returns [WHAT & HOW] Function return values must be checked before data can be used in subsequent functions. This fixes 4 CHECKED_RETURN issues reported by Coverity.
CVE-2024-46776: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Run DC_LOG_DC after checking link->link_enc [WHAT] The DC_LOG_DC should be run after link->link_enc is checked, not before. This fixes 1 REVERSE_INULL issue reported by Coverity.
CVE-2024-46787: In the Linux kernel, the following vulnerability has been resolved: userfaultfd: fix checks for huge PMDs Patch series "userfaultfd: fix races around pmd_trans_huge() check", v2. The pmd_trans_huge() code in mfill_atomic() is wrong in three different ways depending on kernel version: 1. The pmd_trans_huge() check is racy and can lead to a BUG_ON() (if you hit the right two race windows) - I've tested this in a kernel build with some extra mdelay() calls. See the commit message for a description of the race scenario. On older kernels (before 6.5), I think the same bug can even theoretically lead to accessing transhuge page contents as a page table if you hit the right 5 narrow race windows (I haven't tested this case). 2. As pointed out by Qi Zheng, pmd_trans_huge() is not sufficient for detecting PMDs that don't point to page tables. On older kernels (before 6.5), you'd just have to win a single fairly wide race to hit this. I've tested this on 6.1 stable by racing migration (with a mdelay() patched into try_to_migrate()) against UFFDIO_ZEROPAGE - on my x86 VM, that causes a kernel oops in ptlock_ptr(). 3. On newer kernels (>=6.5), for shmem mappings, khugepaged is allowed to yank page tables out from under us (though I haven't tested that), so I think the BUG_ON() checks in mfill_atomic() are just wrong. I decided to write two separate fixes for these (one fix for bugs 1+2, one fix for bug 3), so that the first fix can be backported to kernels affected by bugs 1+2. This patch (of 2): This fixes two issues. I discovered that the following race can occur: mfill_atomic other thread ============ ============ <zap PMD> pmdp_get_lockless() [reads none pmd] <bail if trans_huge> <if none:> <pagefault creates transhuge zeropage> __pte_alloc [no-op] <zap PMD> <bail if pmd_trans_huge(*dst_pmd)> BUG_ON(pmd_none(*dst_pmd)) I have experimentally verified this in a kernel with extra mdelay() calls; the BUG_ON(pmd_none(*dst_pmd)) triggers. On kernels newer than commit 0d940a9b270b ("mm/pgtable: allow pte_offset_map[_lock]() to fail"), this can't lead to anything worse than a BUG_ON(), since the page table access helpers are actually designed to deal with page tables concurrently disappearing; but on older kernels (<=6.4), I think we could probably theoretically race past the two BUG_ON() checks and end up treating a hugepage as a page table. The second issue is that, as Qi Zheng pointed out, there are other types of huge PMDs that pmd_trans_huge() can't catch: devmap PMDs and swap PMDs (in particular, migration PMDs). On <=6.4, this is worse than the first issue: If mfill_atomic() runs on a PMD that contains a migration entry (which just requires winning a single, fairly wide race), it will pass the PMD to pte_offset_map_lock(), which assumes that the PMD points to a page table. Breakage follows: First, the kernel tries to take the PTE lock (which will crash or maybe worse if there is no "struct page" for the address bits in the migration entry PMD - I think at least on X86 there usually is no corresponding "struct page" thanks to the PTE inversion mitigation, amd64 looks different). If that didn't crash, the kernel would next try to write a PTE into what it wrongly thinks is a page table. As part of fixing these issues, get rid of the check for pmd_trans_huge() before __pte_alloc() - that's redundant, we're going to have to check for that after the __pte_alloc() anyway. Backport note: pmdp_get_lockless() is pmd_read_atomic() in older kernels.
CVE-2024-46802: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: added NULL check at start of dc_validate_stream [Why] prevent invalid memory access [How] check if dc and stream are NULL
CVE-2024-46806: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix the warning division or modulo by zero Checks the partition mode and returns an error for an invalid mode.
CVE-2024-46807: In the Linux kernel, the following vulnerability has been resolved: drm/amd/amdgpu: Check tbo resource pointer Validate tbo resource pointer, skip if NULL
CVE-2024-46808: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add missing NULL pointer check within dpcd_extend_address_range [Why & How] ASSERT if return NULL from kcalloc.
CVE-2024-46810: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: tc358767: Check if fully initialized before signalling HPD event via IRQ Make sure the connector is fully initialized before signalling any HPD events via drm_kms_helper_hotplug_event(), otherwise this may lead to NULL pointer dereference.
CVE-2024-46811: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix index may exceed array range within fpu_update_bw_bounding_box [Why] Coverity reports OVERRUN warning. soc.num_states could be 40. But array range of bw_params->clk_table.entries is 8. [How] Assert if soc.num_states greater than 8.
CVE-2024-46813: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check link_index before accessing dc->links[] [WHY & HOW] dc->links[] has max size of MAX_LINKS and NULL is return when trying to access with out-of-bound index. This fixes 3 OVERRUN and 1 RESOURCE_LEAK issues reported by Coverity.
CVE-2024-46826: In the Linux kernel, the following vulnerability has been resolved: ELF: fix kernel.randomize_va_space double read ELF loader uses "randomize_va_space" twice. It is sysctl and can change at any moment, so 2 loads could see 2 different values in theory with unpredictable consequences. Issue exactly one load for consistent value across one exec.
CVE-2024-46830: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Acquire kvm->srcu when handling KVM_SET_VCPU_EVENTS Grab kvm->srcu when processing KVM_SET_VCPU_EVENTS, as KVM will forcibly leave nested VMX/SVM if SMM mode is being toggled, and leaving nested VMX reads guest memory. Note, kvm_vcpu_ioctl_x86_set_vcpu_events() can also be called from KVM_RUN via sync_regs(), which already holds SRCU. I.e. trying to precisely use kvm_vcpu_srcu_read_lock() around the problematic SMM code would cause problems. Acquiring SRCU isn't all that expensive, so for simplicity, grab it unconditionally for KVM_SET_VCPU_EVENTS. ============================= WARNING: suspicious RCU usage 6.10.0-rc7-332d2c1d713e-next-vm #552 Not tainted ----------------------------- include/linux/kvm_host.h:1027 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by repro/1071: #0: ffff88811e424430 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x7d/0x970 [kvm] stack backtrace: CPU: 15 PID: 1071 Comm: repro Not tainted 6.10.0-rc7-332d2c1d713e-next-vm #552 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Call Trace: <TASK> dump_stack_lvl+0x7f/0x90 lockdep_rcu_suspicious+0x13f/0x1a0 kvm_vcpu_gfn_to_memslot+0x168/0x190 [kvm] kvm_vcpu_read_guest+0x3e/0x90 [kvm] nested_vmx_load_msr+0x6b/0x1d0 [kvm_intel] load_vmcs12_host_state+0x432/0xb40 [kvm_intel] vmx_leave_nested+0x30/0x40 [kvm_intel] kvm_vcpu_ioctl_x86_set_vcpu_events+0x15d/0x2b0 [kvm] kvm_arch_vcpu_ioctl+0x1107/0x1750 [kvm] ? mark_held_locks+0x49/0x70 ? kvm_vcpu_ioctl+0x7d/0x970 [kvm] ? kvm_vcpu_ioctl+0x497/0x970 [kvm] kvm_vcpu_ioctl+0x497/0x970 [kvm] ? lock_acquire+0xba/0x2d0 ? find_held_lock+0x2b/0x80 ? do_user_addr_fault+0x40c/0x6f0 ? lock_release+0xb7/0x270 __x64_sys_ioctl+0x82/0xb0 do_syscall_64+0x6c/0x170 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7ff11eb1b539 </TASK>
CVE-2024-46834: In the Linux kernel, the following vulnerability has been resolved: ethtool: fail closed if we can't get max channel used in indirection tables Commit 0d1b7d6c9274 ("bnxt: fix crashes when reducing ring count with active RSS contexts") proves that allowing indirection table to contain channels with out of bounds IDs may lead to crashes. Currently the max channel check in the core gets skipped if driver can't fetch the indirection table or when we can't allocate memory. Both of those conditions should be extremely rare but if they do happen we should try to be safe and fail the channel change.
CVE-2024-46848: In the Linux kernel, the following vulnerability has been resolved: perf/x86/intel: Limit the period on Haswell Running the ltp test cve-2015-3290 concurrently reports the following warnings. perfevents: irq loop stuck! WARNING: CPU: 31 PID: 32438 at arch/x86/events/intel/core.c:3174 intel_pmu_handle_irq+0x285/0x370 Call Trace: <NMI> ? __warn+0xa4/0x220 ? intel_pmu_handle_irq+0x285/0x370 ? __report_bug+0x123/0x130 ? intel_pmu_handle_irq+0x285/0x370 ? __report_bug+0x123/0x130 ? intel_pmu_handle_irq+0x285/0x370 ? report_bug+0x3e/0xa0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x18/0x50 ? asm_exc_invalid_op+0x1a/0x20 ? irq_work_claim+0x1e/0x40 ? intel_pmu_handle_irq+0x285/0x370 perf_event_nmi_handler+0x3d/0x60 nmi_handle+0x104/0x330 Thanks to Thomas Gleixner's analysis, the issue is caused by the low initial period (1) of the frequency estimation algorithm, which triggers the defects of the HW, specifically erratum HSW11 and HSW143. (For the details, please refer https://lore.kernel.org/lkml/87plq9l5d2.ffs@tglx/) The HSW11 requires a period larger than 100 for the INST_RETIRED.ALL event, but the initial period in the freq mode is 1. The erratum is the same as the BDM11, which has been supported in the kernel. A minimum period of 128 is enforced as well on HSW. HSW143 is regarding that the fixed counter 1 may overcount 32 with the Hyper-Threading is enabled. However, based on the test, the hardware has more issues than it tells. Besides the fixed counter 1, the message 'interrupt took too long' can be observed on any counter which was armed with a period < 32 and two events expired in the same NMI. A minimum period of 32 is enforced for the rest of the events. The recommended workaround code of the HSW143 is not implemented. Because it only addresses the issue for the fixed counter. It brings extra overhead through extra MSR writing. No related overcounting issue has been reported so far.
CVE-2024-46857: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix bridge mode operations when there are no VFs Currently, trying to set the bridge mode attribute when numvfs=0 leads to a crash: bridge link set dev eth2 hwmode vepa [ 168.967392] BUG: kernel NULL pointer dereference, address: 0000000000000030 [...] [ 168.969989] RIP: 0010:mlx5_add_flow_rules+0x1f/0x300 [mlx5_core] [...] [ 168.976037] Call Trace: [ 168.976188] <TASK> [ 168.978620] _mlx5_eswitch_set_vepa_locked+0x113/0x230 [mlx5_core] [ 168.979074] mlx5_eswitch_set_vepa+0x7f/0xa0 [mlx5_core] [ 168.979471] rtnl_bridge_setlink+0xe9/0x1f0 [ 168.979714] rtnetlink_rcv_msg+0x159/0x400 [ 168.980451] netlink_rcv_skb+0x54/0x100 [ 168.980675] netlink_unicast+0x241/0x360 [ 168.980918] netlink_sendmsg+0x1f6/0x430 [ 168.981162] ____sys_sendmsg+0x3bb/0x3f0 [ 168.982155] ___sys_sendmsg+0x88/0xd0 [ 168.985036] __sys_sendmsg+0x59/0xa0 [ 168.985477] do_syscall_64+0x79/0x150 [ 168.987273] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 168.987773] RIP: 0033:0x7f8f7950f917 (esw->fdb_table.legacy.vepa_fdb is null) The bridge mode is only relevant when there are multiple functions per port. Therefore, prevent setting and getting this setting when there are no VFs. Note that after this change, there are no settings to change on the PF interface using `bridge link` when there are no VFs, so the interface no longer appears in the `bridge link` output.
CVE-2024-46859: In the Linux kernel, the following vulnerability has been resolved: platform/x86: panasonic-laptop: Fix SINF array out of bounds accesses The panasonic laptop code in various places uses the SINF array with index values of 0 - SINF_CUR_BRIGHT(0x0d) without checking that the SINF array is big enough. Not all panasonic laptops have this many SINF array entries, for example the Toughbook CF-18 model only has 10 SINF array entries. So it only supports the AC+DC brightness entries and mute. Check that the SINF array has a minimum size which covers all AC+DC brightness entries and refuse to load if the SINF array is smaller. For higher SINF indexes hide the sysfs attributes when the SINF array does not contain an entry for that attribute, avoiding show()/store() accessing the array out of bounds and add bounds checking to the probe() and resume() code accessing these.
CVE-2024-46860: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change When disabling wifi mt7921_ipv6_addr_change() is called as a notifier. At this point mvif->phy is already NULL so we cannot use it here.
CVE-2024-46870: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Disable DMCUB timeout for DCN35 [Why] DMCUB can intermittently take longer than expected to process commands. Old ASIC policy was to continue while logging a diagnostic error - which works fine for ASIC without IPS, but with IPS this could lead to a race condition where we attempt to access DCN state while it's inaccessible, leading to a system hang when the NIU port is not disabled or register accesses that timeout and the display configuration in an undefined state. [How] We need to investigate why these accesses take longer than expected, but for now we should disable the timeout on DCN35 to avoid this race condition. Since the waits happen only at lower interrupt levels the risk of taking too long at higher IRQ and causing a system watchdog timeout are minimal.
CVE-2024-46871: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Correct the defined value for AMDGPU_DMUB_NOTIFICATION_MAX [Why & How] It actually exposes '6' types in enum dmub_notification_type. Not 5. Using smaller number to create array dmub_callback & dmub_thread_offload has potential to access item out of array bound. Fix it.
CVE-2024-47141: In the Linux kernel, the following vulnerability has been resolved: pinmux: Use sequential access to access desc->pinmux data When two client of the same gpio call pinctrl_select_state() for the same functionality, we are seeing NULL pointer issue while accessing desc->mux_owner. Let's say two processes A, B executing in pin_request() for the same pin and process A updates the desc->mux_usecount but not yet updated the desc->mux_owner while process B see the desc->mux_usecount which got updated by A path and further executes strcmp and while accessing desc->mux_owner it crashes with NULL pointer. Serialize the access to mux related setting with a mutex lock. cpu0 (process A) cpu1(process B) pinctrl_select_state() { pinctrl_select_state() { pin_request() { pin_request() { ... .... } else { desc->mux_usecount++; desc->mux_usecount && strcmp(desc->mux_owner, owner)) { if (desc->mux_usecount > 1) return 0; desc->mux_owner = owner; } }
CVE-2024-47408: In the Linux kernel, the following vulnerability has been resolved: net/smc: check smcd_v2_ext_offset when receiving proposal msg When receiving proposal msg in server, the field smcd_v2_ext_offset in proposal msg is from the remote client and can not be fully trusted. Once the value of smcd_v2_ext_offset exceed the max value, there has the chance to access wrong address, and crash may happen. This patch checks the value of smcd_v2_ext_offset before using it.
CVE-2024-47658: In the Linux kernel, the following vulnerability has been resolved: crypto: stm32/cryp - call finalize with bh disabled The finalize operation in interrupt mode produce a produces a spinlock recursion warning. The reason is the fact that BH must be disabled during this process.
CVE-2024-47659: In the Linux kernel, the following vulnerability has been resolved: smack: tcp: ipv4, fix incorrect labeling Currently, Smack mirrors the label of incoming tcp/ipv4 connections: when a label 'foo' connects to a label 'bar' with tcp/ipv4, 'foo' always gets 'foo' in returned ipv4 packets. So, 1) returned packets are incorrectly labeled ('foo' instead of 'bar') 2) 'bar' can write to 'foo' without being authorized to write. Here is a scenario how to see this: * Take two machines, let's call them C and S, with active Smack in the default state (no settings, no rules, no labeled hosts, only builtin labels) * At S, add Smack rule 'foo bar w' (labels 'foo' and 'bar' are instantiated at S at this moment) * At S, at label 'bar', launch a program that listens for incoming tcp/ipv4 connections * From C, at label 'foo', connect to the listener at S. (label 'foo' is instantiated at C at this moment) Connection succeedes and works. * Send some data in both directions. * Collect network traffic of this connection. All packets in both directions are labeled with the CIPSO of the label 'foo'. Hence, label 'bar' writes to 'foo' without being authorized, and even without ever being known at C. If anybody cares: exactly the same happens with DCCP. This behavior 1st manifested in release 2.6.29.4 (see Fixes below) and it looks unintentional. At least, no explanation was provided. I changed returned packes label into the 'bar', to bring it into line with the Smack documentation claims.
CVE-2024-47660: In the Linux kernel, the following vulnerability has been resolved: fsnotify: clear PARENT_WATCHED flags lazily In some setups directories can have many (usually negative) dentries. Hence __fsnotify_update_child_dentry_flags() function can take a significant amount of time. Since the bulk of this function happens under inode->i_lock this causes a significant contention on the lock when we remove the watch from the directory as the __fsnotify_update_child_dentry_flags() call from fsnotify_recalc_mask() races with __fsnotify_update_child_dentry_flags() calls from __fsnotify_parent() happening on children. This can lead upto softlockup reports reported by users. Fix the problem by calling fsnotify_update_children_dentry_flags() to set PARENT_WATCHED flags only when parent starts watching children. When parent stops watching children, clear false positive PARENT_WATCHED flags lazily in __fsnotify_parent() for each accessed child.
CVE-2024-47661: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Avoid overflow from uint32_t to uint8_t [WHAT & HOW] dmub_rb_cmd's ramping_boundary has size of uint8_t and it is assigned 0xFFFF. Fix it by changing it to uint8_t with value of 0xFF. This fixes 2 INTEGER_OVERFLOW issues reported by Coverity.
CVE-2024-47662: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Remove register from DCN35 DMCUB diagnostic collection [Why] These registers should not be read from driver and triggering the security violation when DMCUB work times out and diagnostics are collected blocks Z8 entry. [How] Remove the register read from DCN35.
CVE-2024-47665: In the Linux kernel, the following vulnerability has been resolved: i3c: mipi-i3c-hci: Error out instead on BUG_ON() in IBI DMA setup Definitely condition dma_get_cache_alignment * defined value > 256 during driver initialization is not reason to BUG_ON(). Turn that to graceful error out with -EINVAL.
CVE-2024-47667: In the Linux kernel, the following vulnerability has been resolved: PCI: keystone: Add workaround for Errata #i2037 (AM65x SR 1.0) Errata #i2037 in AM65x/DRA80xM Processors Silicon Revision 1.0 (SPRZ452D_July 2018_Revised December 2019 [1]) mentions when an inbound PCIe TLP spans more than two internal AXI 128-byte bursts, the bus may corrupt the packet payload and the corrupt data may cause associated applications or the processor to hang. The workaround for Errata #i2037 is to limit the maximum read request size and maximum payload size to 128 bytes. Add workaround for Errata #i2037 here. The errata and workaround is applicable only to AM65x SR 1.0 and later versions of the silicon will have this fixed. [1] -> https://www.ti.com/lit/er/sprz452i/sprz452i.pdf
CVE-2024-47668: In the Linux kernel, the following vulnerability has been resolved: lib/generic-radix-tree.c: Fix rare race in __genradix_ptr_alloc() If we need to increase the tree depth, allocate a new node, and then race with another thread that increased the tree depth before us, we'll still have a preallocated node that might be used later. If we then use that node for a new non-root node, it'll still have a pointer to the old root instead of being zeroed - fix this by zeroing it in the cmpxchg failure path.
CVE-2024-47669: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix state management in error path of log writing function After commit a694291a6211 ("nilfs2: separate wait function from nilfs_segctor_write") was applied, the log writing function nilfs_segctor_do_construct() was able to issue I/O requests continuously even if user data blocks were split into multiple logs across segments, but two potential flaws were introduced in its error handling. First, if nilfs_segctor_begin_construction() fails while creating the second or subsequent logs, the log writing function returns without calling nilfs_segctor_abort_construction(), so the writeback flag set on pages/folios will remain uncleared. This causes page cache operations to hang waiting for the writeback flag. For example, truncate_inode_pages_final(), which is called via nilfs_evict_inode() when an inode is evicted from memory, will hang. Second, the NILFS_I_COLLECTED flag set on normal inodes remain uncleared. As a result, if the next log write involves checkpoint creation, that's fine, but if a partial log write is performed that does not, inodes with NILFS_I_COLLECTED set are erroneously removed from the "sc_dirty_files" list, and their data and b-tree blocks may not be written to the device, corrupting the block mapping. Fix these issues by uniformly calling nilfs_segctor_abort_construction() on failure of each step in the loop in nilfs_segctor_do_construct(), having it clean up logs and segment usages according to progress, and correcting the conditions for calling nilfs_redirty_inodes() to ensure that the NILFS_I_COLLECTED flag is cleared.
CVE-2024-47673: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: pause TCM when the firmware is stopped Not doing so will make us send a host command to the transport while the firmware is not alive, which will trigger a WARNING. bad state = 0 WARNING: CPU: 2 PID: 17434 at drivers/net/wireless/intel/iwlwifi/iwl-trans.c:115 iwl_trans_send_cmd+0x1cb/0x1e0 [iwlwifi] RIP: 0010:iwl_trans_send_cmd+0x1cb/0x1e0 [iwlwifi] Call Trace: <TASK> iwl_mvm_send_cmd+0x40/0xc0 [iwlmvm] iwl_mvm_config_scan+0x198/0x260 [iwlmvm] iwl_mvm_recalc_tcm+0x730/0x11d0 [iwlmvm] iwl_mvm_tcm_work+0x1d/0x30 [iwlmvm] process_one_work+0x29e/0x640 worker_thread+0x2df/0x690 ? rescuer_thread+0x540/0x540 kthread+0x192/0x1e0 ? set_kthread_struct+0x90/0x90 ret_from_fork+0x22/0x30
CVE-2024-47678: In the Linux kernel, the following vulnerability has been resolved: icmp: change the order of rate limits ICMP messages are ratelimited : After the blamed commits, the two rate limiters are applied in this order: 1) host wide ratelimit (icmp_global_allow()) 2) Per destination ratelimit (inetpeer based) In order to avoid side-channels attacks, we need to apply the per destination check first. This patch makes the following change : 1) icmp_global_allow() checks if the host wide limit is reached. But credits are not yet consumed. This is deferred to 3) 2) The per destination limit is checked/updated. This might add a new node in inetpeer tree. 3) icmp_global_consume() consumes tokens if prior operations succeeded. This means that host wide ratelimit is still effective in keeping inetpeer tree small even under DDOS. As a bonus, I removed icmp_global.lock as the fast path can use a lock-free operation.
CVE-2024-47683: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Skip Recompute DSC Params if no Stream on Link [why] Encounter NULL pointer dereference uner mst + dsc setup. BUG: kernel NULL pointer dereference, address: 0000000000000008 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2 Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022 RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? plist_add+0xbe/0x100 ? exc_page_fault+0x7c/0x180 ? asm_exc_page_fault+0x26/0x30 ? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] ? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] ? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] drm_atomic_check_only+0x5c5/0xa40 drm_mode_atomic_ioctl+0x76e/0xbc0 [how] dsc recompute should be skipped if no mode change detected on the new request. If detected, keep checking whether the stream is already on current state or not.
CVE-2024-47690: In the Linux kernel, the following vulnerability has been resolved: f2fs: get rid of online repaire on corrupted directory syzbot reports a f2fs bug as below: kernel BUG at fs/f2fs/inode.c:896! RIP: 0010:f2fs_evict_inode+0x1598/0x15c0 fs/f2fs/inode.c:896 Call Trace: evict+0x532/0x950 fs/inode.c:704 dispose_list fs/inode.c:747 [inline] evict_inodes+0x5f9/0x690 fs/inode.c:797 generic_shutdown_super+0x9d/0x2d0 fs/super.c:627 kill_block_super+0x44/0x90 fs/super.c:1696 kill_f2fs_super+0x344/0x690 fs/f2fs/super.c:4898 deactivate_locked_super+0xc4/0x130 fs/super.c:473 cleanup_mnt+0x41f/0x4b0 fs/namespace.c:1373 task_work_run+0x24f/0x310 kernel/task_work.c:228 ptrace_notify+0x2d2/0x380 kernel/signal.c:2402 ptrace_report_syscall include/linux/ptrace.h:415 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:477 [inline] syscall_exit_work+0xc6/0x190 kernel/entry/common.c:173 syscall_exit_to_user_mode_prepare kernel/entry/common.c:200 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:205 [inline] syscall_exit_to_user_mode+0x279/0x370 kernel/entry/common.c:218 do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0010:f2fs_evict_inode+0x1598/0x15c0 fs/f2fs/inode.c:896 Online repaire on corrupted directory in f2fs_lookup() can generate dirty data/meta while racing w/ readonly remount, it may leave dirty inode after filesystem becomes readonly, however, checkpoint() will skips flushing dirty inode in a state of readonly mode, result in above panic. Let's get rid of online repaire in f2fs_lookup(), and leave the work to fsck.f2fs.
CVE-2024-47691: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid use-after-free in f2fs_stop_gc_thread() syzbot reports a f2fs bug as below: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_report+0xe8/0x550 mm/kasan/report.c:491 kasan_report+0x143/0x180 mm/kasan/report.c:601 kasan_check_range+0x282/0x290 mm/kasan/generic.c:189 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_fetch_add_relaxed include/linux/atomic/atomic-instrumented.h:252 [inline] __refcount_add include/linux/refcount.h:184 [inline] __refcount_inc include/linux/refcount.h:241 [inline] refcount_inc include/linux/refcount.h:258 [inline] get_task_struct include/linux/sched/task.h:118 [inline] kthread_stop+0xca/0x630 kernel/kthread.c:704 f2fs_stop_gc_thread+0x65/0xb0 fs/f2fs/gc.c:210 f2fs_do_shutdown+0x192/0x540 fs/f2fs/file.c:2283 f2fs_ioc_shutdown fs/f2fs/file.c:2325 [inline] __f2fs_ioctl+0x443a/0xbe60 fs/f2fs/file.c:4325 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is below race condition, it may cause use-after-free issue in sbi->gc_th pointer. - remount - f2fs_remount - f2fs_stop_gc_thread - kfree(gc_th) - f2fs_ioc_shutdown - f2fs_do_shutdown - f2fs_stop_gc_thread - kthread_stop(gc_th->f2fs_gc_task) : sbi->gc_thread = NULL; We will call f2fs_do_shutdown() in two paths: - for f2fs_ioc_shutdown() path, we should grab sb->s_umount semaphore for fixing. - for f2fs_shutdown() path, it's safe since caller has already grabbed sb->s_umount semaphore.
CVE-2024-47693: In the Linux kernel, the following vulnerability has been resolved: IB/core: Fix ib_cache_setup_one error flow cleanup When ib_cache_update return an error, we exit ib_cache_setup_one instantly with no proper cleanup, even though before this we had already successfully done gid_table_setup_one, that results in the kernel WARN below. Do proper cleanup using gid_table_cleanup_one before returning the err in order to fix the issue. WARNING: CPU: 4 PID: 922 at drivers/infiniband/core/cache.c:806 gid_table_release_one+0x181/0x1a0 Modules linked in: CPU: 4 UID: 0 PID: 922 Comm: c_repro Not tainted 6.11.0-rc1+ #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:gid_table_release_one+0x181/0x1a0 Code: 44 8b 38 75 0c e8 2f cb 34 ff 4d 8b b5 28 05 00 00 e8 23 cb 34 ff 44 89 f9 89 da 4c 89 f6 48 c7 c7 d0 58 14 83 e8 4f de 21 ff <0f> 0b 4c 8b 75 30 e9 54 ff ff ff 48 8 3 c4 10 5b 5d 41 5c 41 5d 41 RSP: 0018:ffffc90002b835b0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff811c8527 RDX: 0000000000000000 RSI: ffffffff811c8534 RDI: 0000000000000001 RBP: ffff8881011b3d00 R08: ffff88810b3abe00 R09: 205d303839303631 R10: 666572207972746e R11: 72746e6520444947 R12: 0000000000000001 R13: ffff888106390000 R14: ffff8881011f2110 R15: 0000000000000001 FS: 00007fecc3b70800(0000) GS:ffff88813bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000340 CR3: 000000010435a001 CR4: 00000000003706b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? show_regs+0x94/0xa0 ? __warn+0x9e/0x1c0 ? gid_table_release_one+0x181/0x1a0 ? report_bug+0x1f9/0x340 ? gid_table_release_one+0x181/0x1a0 ? handle_bug+0xa2/0x110 ? exc_invalid_op+0x31/0xa0 ? asm_exc_invalid_op+0x16/0x20 ? __warn_printk+0xc7/0x180 ? __warn_printk+0xd4/0x180 ? gid_table_release_one+0x181/0x1a0 ib_device_release+0x71/0xe0 ? __pfx_ib_device_release+0x10/0x10 device_release+0x44/0xd0 kobject_put+0x135/0x3d0 put_device+0x20/0x30 rxe_net_add+0x7d/0xa0 rxe_newlink+0xd7/0x190 nldev_newlink+0x1b0/0x2a0 ? __pfx_nldev_newlink+0x10/0x10 rdma_nl_rcv_msg+0x1ad/0x2e0 rdma_nl_rcv_skb.constprop.0+0x176/0x210 netlink_unicast+0x2de/0x400 netlink_sendmsg+0x306/0x660 __sock_sendmsg+0x110/0x120 ____sys_sendmsg+0x30e/0x390 ___sys_sendmsg+0x9b/0xf0 ? kstrtouint+0x6e/0xa0 ? kstrtouint_from_user+0x7c/0xb0 ? get_pid_task+0xb0/0xd0 ? proc_fail_nth_write+0x5b/0x140 ? __fget_light+0x9a/0x200 ? preempt_count_add+0x47/0xa0 __sys_sendmsg+0x61/0xd0 do_syscall_64+0x50/0x110 entry_SYSCALL_64_after_hwframe+0x76/0x7e
CVE-2024-47695: In the Linux kernel, the following vulnerability has been resolved: RDMA/rtrs-clt: Reset cid to con_num - 1 to stay in bounds In the function init_conns(), after the create_con() and create_cm() for loop if something fails. In the cleanup for loop after the destroy tag, we access out of bound memory because cid is set to clt_path->s.con_num. This commits resets the cid to clt_path->s.con_num - 1, to stay in bounds in the cleanup loop later.
CVE-2024-47703: In the Linux kernel, the following vulnerability has been resolved: bpf, lsm: Add check for BPF LSM return value A bpf prog returning a positive number attached to file_alloc_security hook makes kernel panic. This happens because file system can not filter out the positive number returned by the LSM prog using IS_ERR, and misinterprets this positive number as a file pointer. Given that hook file_alloc_security never returned positive number before the introduction of BPF LSM, and other BPF LSM hooks may encounter similar issues, this patch adds LSM return value check in verifier, to ensure no unexpected value is returned.
CVE-2024-47704: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check link_res->hpo_dp_link_enc before using it [WHAT & HOW] Functions dp_enable_link_phy and dp_disable_link_phy can pass link_res without initializing hpo_dp_link_enc and it is necessary to check for null before dereferencing. This fixes 2 FORWARD_NULL issues reported by Coverity.
CVE-2024-47720: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for set_output_gamma in dcn30_set_output_transfer_func This commit adds a null check for the set_output_gamma function pointer in the dcn30_set_output_transfer_func function. Previously, set_output_gamma was being checked for nullity at line 386, but then it was being dereferenced without any nullity check at line 401. This could potentially lead to a null pointer dereference error if set_output_gamma is indeed null. To fix this, we now ensure that set_output_gamma is not null before dereferencing it. We do this by adding a nullity check for set_output_gamma before the call to set_output_gamma at line 401. If set_output_gamma is null, we log an error message and do not call the function. This fix prevents a potential null pointer dereference error. drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn30/dcn30_hwseq.c:401 dcn30_set_output_transfer_func() error: we previously assumed 'mpc->funcs->set_output_gamma' could be null (see line 386) drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn30/dcn30_hwseq.c 373 bool dcn30_set_output_transfer_func(struct dc *dc, 374 struct pipe_ctx *pipe_ctx, 375 const struct dc_stream_state *stream) 376 { 377 int mpcc_id = pipe_ctx->plane_res.hubp->inst; 378 struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc; 379 const struct pwl_params *params = NULL; 380 bool ret = false; 381 382 /* program OGAM or 3DLUT only for the top pipe*/ 383 if (pipe_ctx->top_pipe == NULL) { 384 /*program rmu shaper and 3dlut in MPC*/ 385 ret = dcn30_set_mpc_shaper_3dlut(pipe_ctx, stream); 386 if (ret == false && mpc->funcs->set_output_gamma) { ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ If this is NULL 387 if (stream->out_transfer_func.type == TF_TYPE_HWPWL) 388 params = &stream->out_transfer_func.pwl; 389 else if (pipe_ctx->stream->out_transfer_func.type == 390 TF_TYPE_DISTRIBUTED_POINTS && 391 cm3_helper_translate_curve_to_hw_format( 392 &stream->out_transfer_func, 393 &mpc->blender_params, false)) 394 params = &mpc->blender_params; 395 /* there are no ROM LUTs in OUTGAM */ 396 if (stream->out_transfer_func.type == TF_TYPE_PREDEFINED) 397 BREAK_TO_DEBUGGER(); 398 } 399 } 400 --> 401 mpc->funcs->set_output_gamma(mpc, mpcc_id, params); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Then it will crash 402 return ret; 403 }
CVE-2024-47728: In the Linux kernel, the following vulnerability has been resolved: bpf: Zero former ARG_PTR_TO_{LONG,INT} args in case of error For all non-tracing helpers which formerly had ARG_PTR_TO_{LONG,INT} as input arguments, zero the value for the case of an error as otherwise it could leak memory. For tracing, it is not needed given CAP_PERFMON can already read all kernel memory anyway hence bpf_get_func_arg() and bpf_get_func_ret() is skipped in here. Also, the MTU helpers mtu_len pointer value is being written but also read. Technically, the MEM_UNINIT should not be there in order to always force init. Removing MEM_UNINIT needs more verifier rework though: MEM_UNINIT right now implies two things actually: i) write into memory, ii) memory does not have to be initialized. If we lift MEM_UNINIT, it then becomes: i) read into memory, ii) memory must be initialized. This means that for bpf_*_check_mtu() we're readding the issue we're trying to fix, that is, it would then be able to write back into things like .rodata BPF maps. Follow-up work will rework the MEM_UNINIT semantics such that the intent can be better expressed. For now just clear the *mtu_len on error path which can be lifted later again.
CVE-2024-47738: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: don't use rate mask for offchannel TX either Like the commit ab9177d83c04 ("wifi: mac80211: don't use rate mask for scanning"), ignore incorrect settings to avoid no supported rate warning reported by syzbot. The syzbot did bisect and found cause is commit 9df66d5b9f45 ("cfg80211: fix default HE tx bitrate mask in 2G band"), which however corrects bitmask of HE MCS and recognizes correctly settings of empty legacy rate plus HE MCS rate instead of returning -EINVAL. As suggestions [1], follow the change of SCAN TX to consider this case of offchannel TX as well. [1] https://lore.kernel.org/linux-wireless/6ab2dc9c3afe753ca6fdcdd1421e7a1f47e87b84.camel@sipsolutions.net/T/#m2ac2a6d2be06a37c9c47a3d8a44b4f647ed4f024
CVE-2024-47745: In the Linux kernel, the following vulnerability has been resolved: mm: call the security_mmap_file() LSM hook in remap_file_pages() The remap_file_pages syscall handler calls do_mmap() directly, which doesn't contain the LSM security check. And if the process has called personality(READ_IMPLIES_EXEC) before and remap_file_pages() is called for RW pages, this will actually result in remapping the pages to RWX, bypassing a W^X policy enforced by SELinux. So we should check prot by security_mmap_file LSM hook in the remap_file_pages syscall handler before do_mmap() is called. Otherwise, it potentially permits an attacker to bypass a W^X policy enforced by SELinux. The bypass is similar to CVE-2016-10044, which bypass the same thing via AIO and can be found in [1]. The PoC: $ cat > test.c int main(void) { size_t pagesz = sysconf(_SC_PAGE_SIZE); int mfd = syscall(SYS_memfd_create, "test", 0); const char *buf = mmap(NULL, 4 * pagesz, PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0); unsigned int old = syscall(SYS_personality, 0xffffffff); syscall(SYS_personality, READ_IMPLIES_EXEC | old); syscall(SYS_remap_file_pages, buf, pagesz, 0, 2, 0); syscall(SYS_personality, old); // show the RWX page exists even if W^X policy is enforced int fd = open("/proc/self/maps", O_RDONLY); unsigned char buf2[1024]; while (1) { int ret = read(fd, buf2, 1024); if (ret <= 0) break; write(1, buf2, ret); } close(fd); } $ gcc test.c -o test $ ./test | grep rwx 7f1836c34000-7f1836c35000 rwxs 00002000 00:01 2050 /memfd:test (deleted) [PM: subject line tweaks]
CVE-2024-47794: In the Linux kernel, the following vulnerability has been resolved: bpf: Prevent tailcall infinite loop caused by freplace There is a potential infinite loop issue that can occur when using a combination of tail calls and freplace. In an upcoming selftest, the attach target for entry_freplace of tailcall_freplace.c is subprog_tc of tc_bpf2bpf.c, while the tail call in entry_freplace leads to entry_tc. This results in an infinite loop: entry_tc -> subprog_tc -> entry_freplace --tailcall-> entry_tc. The problem arises because the tail_call_cnt in entry_freplace resets to zero each time entry_freplace is executed, causing the tail call mechanism to never terminate, eventually leading to a kernel panic. To fix this issue, the solution is twofold: 1. Prevent updating a program extended by an freplace program to a prog_array map. 2. Prevent extending a program that is already part of a prog_array map with an freplace program. This ensures that: * If a program or its subprogram has been extended by an freplace program, it can no longer be updated to a prog_array map. * If a program has been added to a prog_array map, neither it nor its subprograms can be extended by an freplace program. Moreover, an extension program should not be tailcalled. As such, return -EINVAL if the program has a type of BPF_PROG_TYPE_EXT when adding it to a prog_array map. Additionally, fix a minor code style issue by replacing eight spaces with a tab for proper formatting.
CVE-2024-47809: In the Linux kernel, the following vulnerability has been resolved: dlm: fix possible lkb_resource null dereference This patch fixes a possible null pointer dereference when this function is called from request_lock() as lkb->lkb_resource is not assigned yet, only after validate_lock_args() by calling attach_lkb(). Another issue is that a resource name could be a non printable bytearray and we cannot assume to be ASCII coded. The log functionality is probably never being hit when DLM is used in normal way and no debug logging is enabled. The null pointer dereference can only occur on a new created lkb that does not have the resource assigned yet, it probably never hits the null pointer dereference but we should be sure that other changes might not change this behaviour and we actually can hit the mentioned null pointer dereference. In this patch we just drop the printout of the resource name, the lkb id is enough to make a possible connection to a resource name if this exists.
CVE-2024-49568: In the Linux kernel, the following vulnerability has been resolved: net/smc: check v2_ext_offset/eid_cnt/ism_gid_cnt when receiving proposal msg When receiving proposal msg in server, the fields v2_ext_offset/ eid_cnt/ism_gid_cnt in proposal msg are from the remote client and can not be fully trusted. Especially the field v2_ext_offset, once exceed the max value, there has the chance to access wrong address, and crash may happen. This patch checks the fields v2_ext_offset/eid_cnt/ism_gid_cnt before using them.
CVE-2024-49569: In the Linux kernel, the following vulnerability has been resolved: nvme-rdma: unquiesce admin_q before destroy it Kernel will hang on destroy admin_q while we create ctrl failed, such as following calltrace: PID: 23644 TASK: ff2d52b40f439fc0 CPU: 2 COMMAND: "nvme" #0 [ff61d23de260fb78] __schedule at ffffffff8323bc15 #1 [ff61d23de260fc08] schedule at ffffffff8323c014 #2 [ff61d23de260fc28] blk_mq_freeze_queue_wait at ffffffff82a3dba1 #3 [ff61d23de260fc78] blk_freeze_queue at ffffffff82a4113a #4 [ff61d23de260fc90] blk_cleanup_queue at ffffffff82a33006 #5 [ff61d23de260fcb0] nvme_rdma_destroy_admin_queue at ffffffffc12686ce #6 [ff61d23de260fcc8] nvme_rdma_setup_ctrl at ffffffffc1268ced #7 [ff61d23de260fd28] nvme_rdma_create_ctrl at ffffffffc126919b #8 [ff61d23de260fd68] nvmf_dev_write at ffffffffc024f362 #9 [ff61d23de260fe38] vfs_write at ffffffff827d5f25 RIP: 00007fda7891d574 RSP: 00007ffe2ef06958 RFLAGS: 00000202 RAX: ffffffffffffffda RBX: 000055e8122a4d90 RCX: 00007fda7891d574 RDX: 000000000000012b RSI: 000055e8122a4d90 RDI: 0000000000000004 RBP: 00007ffe2ef079c0 R8: 000000000000012b R9: 000055e8122a4d90 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000004 R13: 000055e8122923c0 R14: 000000000000012b R15: 00007fda78a54500 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b This due to we have quiesced admi_q before cancel requests, but forgot to unquiesce before destroy it, as a result we fail to drain the pending requests, and hang on blk_mq_freeze_queue_wait() forever. Here try to reuse nvme_rdma_teardown_admin_queue() to fix this issue and simplify the code.
CVE-2024-49859: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to check atomic_file in f2fs ioctl interfaces Some f2fs ioctl interfaces like f2fs_ioc_set_pin_file(), f2fs_move_file_range(), and f2fs_defragment_range() missed to check atomic_write status, which may cause potential race issue, fix it.
CVE-2024-49861: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix helper writes to read-only maps Lonial found an issue that despite user- and BPF-side frozen BPF map (like in case of .rodata), it was still possible to write into it from a BPF program side through specific helpers having ARG_PTR_TO_{LONG,INT} as arguments. In check_func_arg() when the argument is as mentioned, the meta->raw_mode is never set. Later, check_helper_mem_access(), under the case of PTR_TO_MAP_VALUE as register base type, it assumes BPF_READ for the subsequent call to check_map_access_type() and given the BPF map is read-only it succeeds. The helpers really need to be annotated as ARG_PTR_TO_{LONG,INT} | MEM_UNINIT when results are written into them as opposed to read out of them. The latter indicates that it's okay to pass a pointer to uninitialized memory as the memory is written to anyway. However, ARG_PTR_TO_{LONG,INT} is a special case of ARG_PTR_TO_FIXED_SIZE_MEM just with additional alignment requirement. So it is better to just get rid of the ARG_PTR_TO_{LONG,INT} special cases altogether and reuse the fixed size memory types. For this, add MEM_ALIGNED to additionally ensure alignment given these helpers write directly into the args via *<ptr> = val. The .arg*_size has been initialized reflecting the actual sizeof(*<ptr>). MEM_ALIGNED can only be used in combination with MEM_FIXED_SIZE annotated argument types, since in !MEM_FIXED_SIZE cases the verifier does not know the buffer size a priori and therefore cannot blindly write *<ptr> = val.
CVE-2024-49891: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Validate hdwq pointers before dereferencing in reset/errata paths When the HBA is undergoing a reset or is handling an errata event, NULL ptr dereference crashes may occur in routines such as lpfc_sli_flush_io_rings(), lpfc_dev_loss_tmo_callbk(), or lpfc_abort_handler(). Add NULL ptr checks before dereferencing hdwq pointers that may have been freed due to operations colliding with a reset or errata event handler.
CVE-2024-49893: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check stream_status before it is used [WHAT & HOW] dc_state_get_stream_status can return null, and therefore null must be checked before stream_status is used. This fixes 1 NULL_RETURNS issue reported by Coverity.
CVE-2024-49897: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check phantom_stream before it is used dcn32_enable_phantom_stream can return null, so returned value must be checked before used. This fixes 1 NULL_RETURNS issue reported by Coverity.
CVE-2024-49898: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null-initialized variables [WHAT & HOW] drr_timing and subvp_pipe are initialized to null and they are not always assigned new values. It is necessary to check for null before dereferencing. This fixes 2 FORWARD_NULL issues reported by Coverity.
CVE-2024-49899: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Initialize denominators' default to 1 [WHAT & HOW] Variables used as denominators and maybe not assigned to other values, should not be 0. Change their default to 1 so they are never 0. This fixes 10 DIVIDE_BY_ZERO issues reported by Coverity.
CVE-2024-49901: In the Linux kernel, the following vulnerability has been resolved: drm/msm/adreno: Assign msm_gpu->pdev earlier to avoid nullptrs There are some cases, such as the one uncovered by Commit 46d4efcccc68 ("drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails") where msm_gpu_cleanup() : platform_set_drvdata(gpu->pdev, NULL); is called on gpu->pdev == NULL, as the GPU device has not been fully initialized yet. Turns out that there's more than just the aforementioned path that causes this to happen (e.g. the case when there's speedbin data in the catalog, but opp-supported-hw is missing in DT). Assigning msm_gpu->pdev earlier seems like the least painful solution to this, therefore do so. Patchwork: https://patchwork.freedesktop.org/patch/602742/
CVE-2024-49905: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for 'afb' in amdgpu_dm_plane_handle_cursor_update (v2) This commit adds a null check for the 'afb' variable in the amdgpu_dm_plane_handle_cursor_update function. Previously, 'afb' was assumed to be null, but was used later in the code without a null check. This could potentially lead to a null pointer dereference. Changes since v1: - Moved the null check for 'afb' to the line where 'afb' is used. (Alex) Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_plane.c:1298 amdgpu_dm_plane_handle_cursor_update() error: we previously assumed 'afb' could be null (see line 1252)
CVE-2024-49906: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointer before try to access it [why & how] Change the order of the pipe_ctx->plane_state check to ensure that plane_state is not null before accessing it.
CVE-2024-49908: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for 'afb' in amdgpu_dm_update_cursor (v2) This commit adds a null check for the 'afb' variable in the amdgpu_dm_update_cursor function. Previously, 'afb' was assumed to be null at line 8388, but was used later in the code without a null check. This could potentially lead to a null pointer dereference. Changes since v1: - Moved the null check for 'afb' to the line where 'afb' is used. (Alex) Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:8433 amdgpu_dm_update_cursor() error: we previously assumed 'afb' could be null (see line 8388)
CVE-2024-49910: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for function pointer in dcn401_set_output_transfer_func This commit adds a null check for the set_output_gamma function pointer in the dcn401_set_output_transfer_func function. Previously, set_output_gamma was being checked for null, but then it was being dereferenced without any null check. This could lead to a null pointer dereference if set_output_gamma is null. To fix this, we now ensure that set_output_gamma is not null before dereferencing it. We do this by adding a null check for set_output_gamma before the call to set_output_gamma.
CVE-2024-49911: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for function pointer in dcn20_set_output_transfer_func This commit adds a null check for the set_output_gamma function pointer in the dcn20_set_output_transfer_func function. Previously, set_output_gamma was being checked for null at line 1030, but then it was being dereferenced without any null check at line 1048. This could potentially lead to a null pointer dereference error if set_output_gamma is null. To fix this, we now ensure that set_output_gamma is not null before dereferencing it. We do this by adding a null check for set_output_gamma before the call to set_output_gamma at line 1048.
CVE-2024-49912: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Handle null 'stream_status' in 'planes_changed_for_existing_stream' This commit adds a null check for 'stream_status' in the function 'planes_changed_for_existing_stream'. Previously, the code assumed 'stream_status' could be null, but did not handle the case where it was actually null. This could lead to a null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_resource.c:3784 planes_changed_for_existing_stream() error: we previously assumed 'stream_status' could be null (see line 3774)
CVE-2024-49914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe This commit addresses a null pointer dereference issue in the `dcn20_program_pipe` function. The issue could occur when `pipe_ctx->plane_state` is null. The fix adds a check to ensure `pipe_ctx->plane_state` is not null before accessing. This prevents a null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn20/dcn20_hwseq.c:1925 dcn20_program_pipe() error: we previously assumed 'pipe_ctx->plane_state' could be null (see line 1877)
CVE-2024-49915: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for clk_mgr in dcn32_init_hw This commit addresses a potential null pointer dereference issue in the `dcn32_init_hw` function. The issue could occur when `dc->clk_mgr` is null. The fix adds a check to ensure `dc->clk_mgr` is not null before accessing its functions. This prevents a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn32/dcn32_hwseq.c:961 dcn32_init_hw() error: we previously assumed 'dc->clk_mgr' could be null (see line 782)
CVE-2024-49916: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for clk_mgr and clk_mgr->funcs in dcn401_init_hw This commit addresses a potential null pointer dereference issue in the `dcn401_init_hw` function. The issue could occur when `dc->clk_mgr` or `dc->clk_mgr->funcs` is null. The fix adds a check to ensure `dc->clk_mgr` and `dc->clk_mgr->funcs` is not null before accessing its functions. This prevents a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn401/dcn401_hwseq.c:416 dcn401_init_hw() error: we previously assumed 'dc->clk_mgr' could be null (see line 225)
CVE-2024-49917: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for clk_mgr and clk_mgr->funcs in dcn30_init_hw This commit addresses a potential null pointer dereference issue in the `dcn30_init_hw` function. The issue could occur when `dc->clk_mgr` or `dc->clk_mgr->funcs` is null. The fix adds a check to ensure `dc->clk_mgr` and `dc->clk_mgr->funcs` is not null before accessing its functions. This prevents a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn30/dcn30_hwseq.c:789 dcn30_init_hw() error: we previously assumed 'dc->clk_mgr' could be null (see line 628)
CVE-2024-49918: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for head_pipe in dcn32_acquire_idle_pipe_for_head_pipe_in_layer This commit addresses a potential null pointer dereference issue in the `dcn32_acquire_idle_pipe_for_head_pipe_in_layer` function. The issue could occur when `head_pipe` is null. The fix adds a check to ensure `head_pipe` is not null before asserting it. If `head_pipe` is null, the function returns NULL to prevent a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn32/dcn32_resource.c:2690 dcn32_acquire_idle_pipe_for_head_pipe_in_layer() error: we previously assumed 'head_pipe' could be null (see line 2681)
CVE-2024-49919: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for head_pipe in dcn201_acquire_free_pipe_for_layer This commit addresses a potential null pointer dereference issue in the `dcn201_acquire_free_pipe_for_layer` function. The issue could occur when `head_pipe` is null. The fix adds a check to ensure `head_pipe` is not null before asserting it. If `head_pipe` is null, the function returns NULL to prevent a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn201/dcn201_resource.c:1016 dcn201_acquire_free_pipe_for_layer() error: we previously assumed 'head_pipe' could be null (see line 1010)
CVE-2024-49920: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before multiple uses [WHAT & HOW] Poniters, such as stream_enc and dc->bw_vbios, are null checked previously in the same function, so Coverity warns "implies that stream_enc and dc->bw_vbios might be null". They are used multiple times in the subsequent code and need to be checked. This fixes 10 FORWARD_NULL issues reported by Coverity.
CVE-2024-49921: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before used [WHAT & HOW] Poniters, such as dc->clk_mgr, are null checked previously in the same function, so Coverity warns "implies that "dc->clk_mgr" might be null". As a result, these pointers need to be checked when used again. This fixes 10 FORWARD_NULL issues reported by Coverity.
CVE-2024-49922: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before using them [WHAT & HOW] These pointers are null checked previously in the same function, indicating they might be null as reported by Coverity. As a result, they need to be checked when used again. This fixes 3 FORWARD_NULL issue reported by Coverity.
CVE-2024-49923: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Pass non-null to dcn20_validate_apply_pipe_split_flags [WHAT & HOW] "dcn20_validate_apply_pipe_split_flags" dereferences merge, and thus it cannot be a null pointer. Let's pass a valid pointer to avoid null dereference. This fixes 2 FORWARD_NULL issues reported by Coverity.
CVE-2024-49925: In the Linux kernel, the following vulnerability has been resolved: fbdev: efifb: Register sysfs groups through driver core The driver core can register and cleanup sysfs groups already. Make use of that functionality to simplify the error handling and cleanup. Also avoid a UAF race during unregistering where the sysctl attributes were usable after the info struct was freed.
CVE-2024-49927: In the Linux kernel, the following vulnerability has been resolved: x86/ioapic: Handle allocation failures gracefully Breno observed panics when using failslab under certain conditions during runtime: can not alloc irq_pin_list (-1,0,20) Kernel panic - not syncing: IO-APIC: failed to add irq-pin. Can not proceed panic+0x4e9/0x590 mp_irqdomain_alloc+0x9ab/0xa80 irq_domain_alloc_irqs_locked+0x25d/0x8d0 __irq_domain_alloc_irqs+0x80/0x110 mp_map_pin_to_irq+0x645/0x890 acpi_register_gsi_ioapic+0xe6/0x150 hpet_open+0x313/0x480 That's a pointless panic which is a leftover of the historic IO/APIC code which panic'ed during early boot when the interrupt allocation failed. The only place which might justify panic is the PIT/HPET timer_check() code which tries to figure out whether the timer interrupt is delivered through the IO/APIC. But that code does not require to handle interrupt allocation failures. If the interrupt cannot be allocated then timer delivery fails and it either panics due to that or falls back to legacy mode. Cure this by removing the panic wrapper around __add_pin_to_irq_node() and making mp_irqdomain_alloc() aware of the failure condition and handle it as any other failure in this function gracefully.
CVE-2024-49929: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: avoid NULL pointer dereference iwl_mvm_tx_skb_sta() and iwl_mvm_tx_mpdu() verify that the mvmvsta pointer is not NULL. It retrieves this pointer using iwl_mvm_sta_from_mac80211, which is dereferencing the ieee80211_sta pointer. If sta is NULL, iwl_mvm_sta_from_mac80211 will dereference a NULL pointer. Fix this by checking the sta pointer before retrieving the mvmsta from it. If sta is not NULL, then mvmsta isn't either.
CVE-2024-49934: In the Linux kernel, the following vulnerability has been resolved: fs/inode: Prevent dump_mapping() accessing invalid dentry.d_name.name It's observed that a crash occurs during hot-remove a memory device, in which user is accessing the hugetlb. See calltrace as following: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 14045 at arch/x86/mm/fault.c:1278 do_user_addr_fault+0x2a0/0x790 Modules linked in: kmem device_dax cxl_mem cxl_pmem cxl_port cxl_pci dax_hmem dax_pmem nd_pmem cxl_acpi nd_btt cxl_core crc32c_intel nvme virtiofs fuse nvme_core nfit libnvdimm dm_multipath scsi_dh_rdac scsi_dh_emc s mirror dm_region_hash dm_log dm_mod CPU: 1 PID: 14045 Comm: daxctl Not tainted 6.10.0-rc2-lizhijian+ #492 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:do_user_addr_fault+0x2a0/0x790 Code: 48 8b 00 a8 04 0f 84 b5 fe ff ff e9 1c ff ff ff 4c 89 e9 4c 89 e2 be 01 00 00 00 bf 02 00 00 00 e8 b5 ef 24 00 e9 42 fe ff ff <0f> 0b 48 83 c4 08 4c 89 ea 48 89 ee 4c 89 e7 5b 5d 41 5c 41 5d 41 RSP: 0000:ffffc90000a575f0 EFLAGS: 00010046 RAX: ffff88800c303600 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000001000 RSI: ffffffff82504162 RDI: ffffffff824b2c36 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffc90000a57658 R13: 0000000000001000 R14: ffff88800bc2e040 R15: 0000000000000000 FS: 00007f51cb57d880(0000) GS:ffff88807fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000001000 CR3: 00000000072e2004 CR4: 00000000001706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __warn+0x8d/0x190 ? do_user_addr_fault+0x2a0/0x790 ? report_bug+0x1c3/0x1d0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? do_user_addr_fault+0x2a0/0x790 ? exc_page_fault+0x31/0x200 exc_page_fault+0x68/0x200 <...snip...> BUG: unable to handle page fault for address: 0000000000001000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 800000000ad92067 P4D 800000000ad92067 PUD 7677067 PMD 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI ---[ end trace 0000000000000000 ]--- BUG: unable to handle page fault for address: 0000000000001000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 800000000ad92067 P4D 800000000ad92067 PUD 7677067 PMD 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 14045 Comm: daxctl Kdump: loaded Tainted: G W 6.10.0-rc2-lizhijian+ #492 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:dentry_name+0x1f4/0x440 <...snip...> ? dentry_name+0x2fa/0x440 vsnprintf+0x1f3/0x4f0 vprintk_store+0x23a/0x540 vprintk_emit+0x6d/0x330 _printk+0x58/0x80 dump_mapping+0x10b/0x1a0 ? __pfx_free_object_rcu+0x10/0x10 __dump_page+0x26b/0x3e0 ? vprintk_emit+0xe0/0x330 ? _printk+0x58/0x80 ? dump_page+0x17/0x50 dump_page+0x17/0x50 do_migrate_range+0x2f7/0x7f0 ? do_migrate_range+0x42/0x7f0 ? offline_pages+0x2f4/0x8c0 offline_pages+0x60a/0x8c0 memory_subsys_offline+0x9f/0x1c0 ? lockdep_hardirqs_on+0x77/0x100 ? _raw_spin_unlock_irqrestore+0x38/0x60 device_offline+0xe3/0x110 state_store+0x6e/0xc0 kernfs_fop_write_iter+0x143/0x200 vfs_write+0x39f/0x560 ksys_write+0x65/0xf0 do_syscall_64+0x62/0x130 Previously, some sanity check have been done in dump_mapping() before the print facility parsing '%pd' though, it's still possible to run into an invalid dentry.d_name.name. Since dump_mapping() only needs to dump the filename only, retrieve it by itself in a safer way to prevent an unnecessary crash. Note that either retrieving the filename with '%pd' or strncpy_from_kernel_nofault(), the filename could be unreliable.
CVE-2024-49940: In the Linux kernel, the following vulnerability has been resolved: l2tp: prevent possible tunnel refcount underflow When a session is created, it sets a backpointer to its tunnel. When the session refcount drops to 0, l2tp_session_free drops the tunnel refcount if session->tunnel is non-NULL. However, session->tunnel is set in l2tp_session_create, before the tunnel refcount is incremented by l2tp_session_register, which leaves a small window where session->tunnel is non-NULL when the tunnel refcount hasn't been bumped. Moving the assignment to l2tp_session_register is trivial but l2tp_session_create calls l2tp_session_set_header_len which uses session->tunnel to get the tunnel's encap. Add an encap arg to l2tp_session_set_header_len to avoid using session->tunnel. If l2tpv3 sessions have colliding IDs, it is possible for l2tp_v3_session_get to race with l2tp_session_register and fetch a session which doesn't yet have session->tunnel set. Add a check for this case.
CVE-2024-49945: In the Linux kernel, the following vulnerability has been resolved: net/ncsi: Disable the ncsi work before freeing the associated structure The work function can run after the ncsi device is freed, resulting in use-after-free bugs or kernel panic.
CVE-2024-49950: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix uaf in l2cap_connect [Syzbot reported] BUG: KASAN: slab-use-after-free in l2cap_connect.constprop.0+0x10d8/0x1270 net/bluetooth/l2cap_core.c:3949 Read of size 8 at addr ffff8880241e9800 by task kworker/u9:0/54 CPU: 0 UID: 0 PID: 54 Comm: kworker/u9:0 Not tainted 6.11.0-rc6-syzkaller-00268-g788220eee30d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024 Workqueue: hci2 hci_rx_work Call Trace: <TASK> __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:119 print_address_description mm/kasan/report.c:377 [inline] print_report+0xc3/0x620 mm/kasan/report.c:488 kasan_report+0xd9/0x110 mm/kasan/report.c:601 l2cap_connect.constprop.0+0x10d8/0x1270 net/bluetooth/l2cap_core.c:3949 l2cap_connect_req net/bluetooth/l2cap_core.c:4080 [inline] l2cap_bredr_sig_cmd net/bluetooth/l2cap_core.c:4772 [inline] l2cap_sig_channel net/bluetooth/l2cap_core.c:5543 [inline] l2cap_recv_frame+0xf0b/0x8eb0 net/bluetooth/l2cap_core.c:6825 l2cap_recv_acldata+0x9b4/0xb70 net/bluetooth/l2cap_core.c:7514 hci_acldata_packet net/bluetooth/hci_core.c:3791 [inline] hci_rx_work+0xaab/0x1610 net/bluetooth/hci_core.c:4028 process_one_work+0x9c5/0x1b40 kernel/workqueue.c:3231 process_scheduled_works kernel/workqueue.c:3312 [inline] worker_thread+0x6c8/0xed0 kernel/workqueue.c:3389 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 ... Freed by task 5245: kasan_save_stack+0x33/0x60 mm/kasan/common.c:47 kasan_save_track+0x14/0x30 mm/kasan/common.c:68 kasan_save_free_info+0x3b/0x60 mm/kasan/generic.c:579 poison_slab_object+0xf7/0x160 mm/kasan/common.c:240 __kasan_slab_free+0x32/0x50 mm/kasan/common.c:256 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2256 [inline] slab_free mm/slub.c:4477 [inline] kfree+0x12a/0x3b0 mm/slub.c:4598 l2cap_conn_free net/bluetooth/l2cap_core.c:1810 [inline] kref_put include/linux/kref.h:65 [inline] l2cap_conn_put net/bluetooth/l2cap_core.c:1822 [inline] l2cap_conn_del+0x59d/0x730 net/bluetooth/l2cap_core.c:1802 l2cap_connect_cfm+0x9e6/0xf80 net/bluetooth/l2cap_core.c:7241 hci_connect_cfm include/net/bluetooth/hci_core.h:1960 [inline] hci_conn_failed+0x1c3/0x370 net/bluetooth/hci_conn.c:1265 hci_abort_conn_sync+0x75a/0xb50 net/bluetooth/hci_sync.c:5583 abort_conn_sync+0x197/0x360 net/bluetooth/hci_conn.c:2917 hci_cmd_sync_work+0x1a4/0x410 net/bluetooth/hci_sync.c:328 process_one_work+0x9c5/0x1b40 kernel/workqueue.c:3231 process_scheduled_works kernel/workqueue.c:3312 [inline] worker_thread+0x6c8/0xed0 kernel/workqueue.c:3389 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
CVE-2024-49954: In the Linux kernel, the following vulnerability has been resolved: static_call: Replace pointless WARN_ON() in static_call_module_notify() static_call_module_notify() triggers a WARN_ON(), when memory allocation fails in __static_call_add_module(). That's not really justified, because the failure case must be correctly handled by the well known call chain and the error code is passed through to the initiating userspace application. A memory allocation fail is not a fatal problem, but the WARN_ON() takes the machine out when panic_on_warn is set. Replace it with a pr_warn().
CVE-2024-49970: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Implement bounds check for stream encoder creation in DCN401 'stream_enc_regs' array is an array of dcn10_stream_enc_registers structures. The array is initialized with four elements, corresponding to the four calls to stream_enc_regs() in the array initializer. This means that valid indices for this array are 0, 1, 2, and 3. The error message 'stream_enc_regs' 4 <= 5 below, is indicating that there is an attempt to access this array with an index of 5, which is out of bounds. This could lead to undefined behavior Here, eng_id is used as an index to access the stream_enc_regs array. If eng_id is 5, this would result in an out-of-bounds access on the stream_enc_regs array. Thus fixing Buffer overflow error in dcn401_stream_encoder_create Found by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn401/dcn401_resource.c:1209 dcn401_stream_encoder_create() error: buffer overflow 'stream_enc_regs' 4 <= 5
CVE-2024-49978: In the Linux kernel, the following vulnerability has been resolved: gso: fix udp gso fraglist segmentation after pull from frag_list Detect gso fraglist skbs with corrupted geometry (see below) and pass these to skb_segment instead of skb_segment_list, as the first can segment them correctly. Valid SKB_GSO_FRAGLIST skbs - consist of two or more segments - the head_skb holds the protocol headers plus first gso_size - one or more frag_list skbs hold exactly one segment - all but the last must be gso_size Optional datapath hooks such as NAT and BPF (bpf_skb_pull_data) can modify these skbs, breaking these invariants. In extreme cases they pull all data into skb linear. For UDP, this causes a NULL ptr deref in __udpv4_gso_segment_list_csum at udp_hdr(seg->next)->dest. Detect invalid geometry due to pull, by checking head_skb size. Don't just drop, as this may blackhole a destination. Convert to be able to pass to regular skb_segment.
CVE-2024-49989: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix double free issue during amdgpu module unload Flexible endpoints use DIGs from available inflexible endpoints, so only the encoders of inflexible links need to be freed. Otherwise, a double free issue may occur when unloading the amdgpu module. [ 279.190523] RIP: 0010:__slab_free+0x152/0x2f0 [ 279.190577] Call Trace: [ 279.190580] <TASK> [ 279.190582] ? show_regs+0x69/0x80 [ 279.190590] ? die+0x3b/0x90 [ 279.190595] ? do_trap+0xc8/0xe0 [ 279.190601] ? do_error_trap+0x73/0xa0 [ 279.190605] ? __slab_free+0x152/0x2f0 [ 279.190609] ? exc_invalid_op+0x56/0x70 [ 279.190616] ? __slab_free+0x152/0x2f0 [ 279.190642] ? asm_exc_invalid_op+0x1f/0x30 [ 279.190648] ? dcn10_link_encoder_destroy+0x19/0x30 [amdgpu] [ 279.191096] ? __slab_free+0x152/0x2f0 [ 279.191102] ? dcn10_link_encoder_destroy+0x19/0x30 [amdgpu] [ 279.191469] kfree+0x260/0x2b0 [ 279.191474] dcn10_link_encoder_destroy+0x19/0x30 [amdgpu] [ 279.191821] link_destroy+0xd7/0x130 [amdgpu] [ 279.192248] dc_destruct+0x90/0x270 [amdgpu] [ 279.192666] dc_destroy+0x19/0x40 [amdgpu] [ 279.193020] amdgpu_dm_fini+0x16e/0x200 [amdgpu] [ 279.193432] dm_hw_fini+0x26/0x40 [amdgpu] [ 279.193795] amdgpu_device_fini_hw+0x24c/0x400 [amdgpu] [ 279.194108] amdgpu_driver_unload_kms+0x4f/0x70 [amdgpu] [ 279.194436] amdgpu_pci_remove+0x40/0x80 [amdgpu] [ 279.194632] pci_device_remove+0x3a/0xa0 [ 279.194638] device_remove+0x40/0x70 [ 279.194642] device_release_driver_internal+0x1ad/0x210 [ 279.194647] driver_detach+0x4e/0xa0 [ 279.194650] bus_remove_driver+0x6f/0xf0 [ 279.194653] driver_unregister+0x33/0x60 [ 279.194657] pci_unregister_driver+0x44/0x90 [ 279.194662] amdgpu_exit+0x19/0x1f0 [amdgpu] [ 279.194939] __do_sys_delete_module.isra.0+0x198/0x2f0 [ 279.194946] __x64_sys_delete_module+0x16/0x20 [ 279.194950] do_syscall_64+0x58/0x120 [ 279.194954] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 279.194980] </TASK>
CVE-2024-49991: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: amdkfd_free_gtt_mem clear the correct pointer Pass pointer reference to amdgpu_bo_unref to clear the correct pointer, otherwise amdgpu_bo_unref clear the local variable, the original pointer not set to NULL, this could cause use-after-free bug.
CVE-2024-49992: In the Linux kernel, the following vulnerability has been resolved: drm/stm: Avoid use-after-free issues with crtc and plane ltdc_load() calls functions drm_crtc_init_with_planes(), drm_universal_plane_init() and drm_encoder_init(). These functions should not be called with parameters allocated with devm_kzalloc() to avoid use-after-free issues [1]. Use allocations managed by the DRM framework. Found by Linux Verification Center (linuxtesting.org). [1] https://lore.kernel.org/lkml/u366i76e3qhh3ra5oxrtngjtm2u5lterkekcz6y2jkndhuxzli@diujon4h7qwb/
CVE-2024-50002: In the Linux kernel, the following vulnerability has been resolved: static_call: Handle module init failure correctly in static_call_del_module() Module insertion invokes static_call_add_module() to initialize the static calls in a module. static_call_add_module() invokes __static_call_init(), which allocates a struct static_call_mod to either encapsulate the built-in static call sites of the associated key into it so further modules can be added or to append the module to the module chain. If that allocation fails the function returns with an error code and the module core invokes static_call_del_module() to clean up eventually added static_call_mod entries. This works correctly, when all keys used by the module were converted over to a module chain before the failure. If not then static_call_del_module() causes a #GP as it blindly assumes that key::mods points to a valid struct static_call_mod. The problem is that key::mods is not a individual struct member of struct static_call_key, it's part of a union to save space: union { /* bit 0: 0 = mods, 1 = sites */ unsigned long type; struct static_call_mod *mods; struct static_call_site *sites; }; key::sites is a pointer to the list of built-in usage sites of the static call. The type of the pointer is differentiated by bit 0. A mods pointer has the bit clear, the sites pointer has the bit set. As static_call_del_module() blidly assumes that the pointer is a valid static_call_mod type, it fails to check for this failure case and dereferences the pointer to the list of built-in call sites, which is obviously bogus. Cure it by checking whether the key has a sites or a mods pointer. If it's a sites pointer then the key is not to be touched. As the sites are walked in the same order as in __static_call_init() the site walk can be terminated because all subsequent sites have not been touched by the init code due to the error exit. If it was converted before the allocation fail, then the inner loop which searches for a module match will find nothing. A fail in the second allocation in __static_call_init() is harmless and does not require special treatment. The first allocation succeeded and converted the key to a module chain. That first entry has mod::mod == NULL and mod::next == NULL, so the inner loop of static_call_del_module() will neither find a module match nor a module chain. The next site in the walk was either already converted, but can't match the module, or it will exit the outer loop because it has a static_call_site pointer and not a static_call_mod pointer.
CVE-2024-50003: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix system hang while resume with TBT monitor [Why] Connected with a Thunderbolt monitor and do the suspend and the system may hang while resume. The TBT monitor HPD will be triggered during the resume procedure and call the drm_client_modeset_probe() while struct drm_connector connector->dev->master is NULL. It will mess up the pipe topology after resume. [How] Skip the TBT monitor HPD during the resume procedure because we currently will probe the connectors after resume by default. (cherry picked from commit 453f86a26945207a16b8f66aaed5962dc2b95b85)
CVE-2024-50017: In the Linux kernel, the following vulnerability has been resolved: x86/mm/ident_map: Use gbpages only where full GB page should be mapped. When ident_pud_init() uses only GB pages to create identity maps, large ranges of addresses not actually requested can be included in the resulting table; a 4K request will map a full GB. This can include a lot of extra address space past that requested, including areas marked reserved by the BIOS. That allows processor speculation into reserved regions, that on UV systems can cause system halts. Only use GB pages when map creation requests include the full GB page of space. Fall back to using smaller 2M pages when only portions of a GB page are included in the request. No attempt is made to coalesce mapping requests. If a request requires a map entry at the 2M (pmd) level, subsequent mapping requests within the same 1G region will also be at the pmd level, even if adjacent or overlapping such requests could have been combined to map a full GB page. Existing usage starts with larger regions and then adds smaller regions, so this should not have any great consequence.
CVE-2024-50028: In the Linux kernel, the following vulnerability has been resolved: thermal: core: Reference count the zone in thermal_zone_get_by_id() There are places in the thermal netlink code where nothing prevents the thermal zone object from going away while being accessed after it has been returned by thermal_zone_get_by_id(). To address this, make thermal_zone_get_by_id() get a reference on the thermal zone device object to be returned with the help of get_device(), under thermal_list_lock, and adjust all of its callers to this change with the help of the cleanup.h infrastructure.
CVE-2024-50038: In the Linux kernel, the following vulnerability has been resolved: netfilter: xtables: avoid NFPROTO_UNSPEC where needed syzbot managed to call xt_cluster match via ebtables: WARNING: CPU: 0 PID: 11 at net/netfilter/xt_cluster.c:72 xt_cluster_mt+0x196/0x780 [..] ebt_do_table+0x174b/0x2a40 Module registers to NFPROTO_UNSPEC, but it assumes ipv4/ipv6 packet processing. As this is only useful to restrict locally terminating TCP/UDP traffic, register this for ipv4 and ipv6 family only. Pablo points out that this is a general issue, direct users of the set/getsockopt interface can call into targets/matches that were only intended for use with ip(6)tables. Check all UNSPEC matches and targets for similar issues: - matches and targets are fine except if they assume skb_network_header() is valid -- this is only true when called from inet layer: ip(6) stack pulls the ip/ipv6 header into linear data area. - targets that return XT_CONTINUE or other xtables verdicts must be restricted too, they are incompatbile with the ebtables traverser, e.g. EBT_CONTINUE is a completely different value than XT_CONTINUE. Most matches/targets are changed to register for NFPROTO_IPV4/IPV6, as they are provided for use by ip(6)tables. The MARK target is also used by arptables, so register for NFPROTO_ARP too. While at it, bail out if connbytes fails to enable the corresponding conntrack family. This change passes the selftests in iptables.git.
CVE-2024-50057: In the Linux kernel, the following vulnerability has been resolved: usb: typec: tipd: Free IRQ only if it was requested before In polling mode, if no IRQ was requested there is no need to free it. Call devm_free_irq() only if client->irq is set. This fixes the warning caused by the tps6598x module removal: WARNING: CPU: 2 PID: 333 at kernel/irq/devres.c:144 devm_free_irq+0x80/0x8c ... ... Call trace: devm_free_irq+0x80/0x8c tps6598x_remove+0x28/0x88 [tps6598x] i2c_device_remove+0x2c/0x9c device_remove+0x4c/0x80 device_release_driver_internal+0x1cc/0x228 driver_detach+0x50/0x98 bus_remove_driver+0x6c/0xbc driver_unregister+0x30/0x60 i2c_del_driver+0x54/0x64 tps6598x_i2c_driver_exit+0x18/0xc3c [tps6598x] __arm64_sys_delete_module+0x184/0x264 invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0xc8/0xe8 do_el0_svc+0x20/0x2c el0_svc+0x28/0x98 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194
CVE-2024-50060: In the Linux kernel, the following vulnerability has been resolved: io_uring: check if we need to reschedule during overflow flush In terms of normal application usage, this list will always be empty. And if an application does overflow a bit, it'll have a few entries. However, nothing obviously prevents syzbot from running a test case that generates a ton of overflow entries, and then flushing them can take quite a while. Check for needing to reschedule while flushing, and drop our locks and do so if necessary. There's no state to maintain here as overflows always prune from head-of-list, hence it's fine to drop and reacquire the locks at the end of the loop.
CVE-2024-50061: In the Linux kernel, the following vulnerability has been resolved: i3c: master: cdns: Fix use after free vulnerability in cdns_i3c_master Driver Due to Race Condition In the cdns_i3c_master_probe function, &master->hj_work is bound with cdns_i3c_master_hj. And cdns_i3c_master_interrupt can call cnds_i3c_master_demux_ibis function to start the work. If we remove the module which will call cdns_i3c_master_remove to make cleanup, it will free master->base through i3c_master_unregister while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | cdns_i3c_master_hj cdns_i3c_master_remove | i3c_master_unregister(&master->base) | device_unregister(&master->dev) | device_release | //free master->base | | i3c_master_do_daa(&master->base) | //use master->base Fix it by ensuring that the work is canceled before proceeding with the cleanup in cdns_i3c_master_remove.
CVE-2024-50062: In the Linux kernel, the following vulnerability has been resolved: RDMA/rtrs-srv: Avoid null pointer deref during path establishment For RTRS path establishment, RTRS client initiates and completes con_num of connections. After establishing all its connections, the information is exchanged between the client and server through the info_req message. During this exchange, it is essential that all connections have been established, and the state of the RTRS srv path is CONNECTED. So add these sanity checks, to make sure we detect and abort process in error scenarios to avoid null pointer deref.
CVE-2024-50063: In the Linux kernel, the following vulnerability has been resolved: bpf: Prevent tail call between progs attached to different hooks bpf progs can be attached to kernel functions, and the attached functions can take different parameters or return different return values. If prog attached to one kernel function tail calls prog attached to another kernel function, the ctx access or return value verification could be bypassed. For example, if prog1 is attached to func1 which takes only 1 parameter and prog2 is attached to func2 which takes two parameters. Since verifier assumes the bpf ctx passed to prog2 is constructed based on func2's prototype, verifier allows prog2 to access the second parameter from the bpf ctx passed to it. The problem is that verifier does not prevent prog1 from passing its bpf ctx to prog2 via tail call. In this case, the bpf ctx passed to prog2 is constructed from func1 instead of func2, that is, the assumption for ctx access verification is bypassed. Another example, if BPF LSM prog1 is attached to hook file_alloc_security, and BPF LSM prog2 is attached to hook bpf_lsm_audit_rule_known. Verifier knows the return value rules for these two hooks, e.g. it is legal for bpf_lsm_audit_rule_known to return positive number 1, and it is illegal for file_alloc_security to return positive number. So verifier allows prog2 to return positive number 1, but does not allow prog1 to return positive number. The problem is that verifier does not prevent prog1 from calling prog2 via tail call. In this case, prog2's return value 1 will be used as the return value for prog1's hook file_alloc_security. That is, the return value rule is bypassed. This patch adds restriction for tail call to prevent such bypasses.
CVE-2024-50067: In the Linux kernel, the following vulnerability has been resolved: uprobe: avoid out-of-bounds memory access of fetching args Uprobe needs to fetch args into a percpu buffer, and then copy to ring buffer to avoid non-atomic context problem. Sometimes user-space strings, arrays can be very large, but the size of percpu buffer is only page size. And store_trace_args() won't check whether these data exceeds a single page or not, caused out-of-bounds memory access. It could be reproduced by following steps: 1. build kernel with CONFIG_KASAN enabled 2. save follow program as test.c ``` \#include <stdio.h> \#include <stdlib.h> \#include <string.h> // If string length large than MAX_STRING_SIZE, the fetch_store_strlen() // will return 0, cause __get_data_size() return shorter size, and // store_trace_args() will not trigger out-of-bounds access. // So make string length less than 4096. \#define STRLEN 4093 void generate_string(char *str, int n) { int i; for (i = 0; i < n; ++i) { char c = i % 26 + 'a'; str[i] = c; } str[n-1] = '\0'; } void print_string(char *str) { printf("%s\n", str); } int main() { char tmp[STRLEN]; generate_string(tmp, STRLEN); print_string(tmp); return 0; } ``` 3. compile program `gcc -o test test.c` 4. get the offset of `print_string()` ``` objdump -t test | grep -w print_string 0000000000401199 g F .text 000000000000001b print_string ``` 5. configure uprobe with offset 0x1199 ``` off=0x1199 cd /sys/kernel/debug/tracing/ echo "p /root/test:${off} arg1=+0(%di):ustring arg2=\$comm arg3=+0(%di):ustring" > uprobe_events echo 1 > events/uprobes/enable echo 1 > tracing_on ``` 6. run `test`, and kasan will report error. ================================================================== BUG: KASAN: use-after-free in strncpy_from_user+0x1d6/0x1f0 Write of size 8 at addr ffff88812311c004 by task test/499CPU: 0 UID: 0 PID: 499 Comm: test Not tainted 6.12.0-rc3+ #18 Hardware name: Red Hat KVM, BIOS 1.16.0-4.al8 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x55/0x70 print_address_description.constprop.0+0x27/0x310 kasan_report+0x10f/0x120 ? strncpy_from_user+0x1d6/0x1f0 strncpy_from_user+0x1d6/0x1f0 ? rmqueue.constprop.0+0x70d/0x2ad0 process_fetch_insn+0xb26/0x1470 ? __pfx_process_fetch_insn+0x10/0x10 ? _raw_spin_lock+0x85/0xe0 ? __pfx__raw_spin_lock+0x10/0x10 ? __pte_offset_map+0x1f/0x2d0 ? unwind_next_frame+0xc5f/0x1f80 ? arch_stack_walk+0x68/0xf0 ? is_bpf_text_address+0x23/0x30 ? kernel_text_address.part.0+0xbb/0xd0 ? __kernel_text_address+0x66/0xb0 ? unwind_get_return_address+0x5e/0xa0 ? __pfx_stack_trace_consume_entry+0x10/0x10 ? arch_stack_walk+0xa2/0xf0 ? _raw_spin_lock_irqsave+0x8b/0xf0 ? __pfx__raw_spin_lock_irqsave+0x10/0x10 ? depot_alloc_stack+0x4c/0x1f0 ? _raw_spin_unlock_irqrestore+0xe/0x30 ? stack_depot_save_flags+0x35d/0x4f0 ? kasan_save_stack+0x34/0x50 ? kasan_save_stack+0x24/0x50 ? mutex_lock+0x91/0xe0 ? __pfx_mutex_lock+0x10/0x10 prepare_uprobe_buffer.part.0+0x2cd/0x500 uprobe_dispatcher+0x2c3/0x6a0 ? __pfx_uprobe_dispatcher+0x10/0x10 ? __kasan_slab_alloc+0x4d/0x90 handler_chain+0xdd/0x3e0 handle_swbp+0x26e/0x3d0 ? __pfx_handle_swbp+0x10/0x10 ? uprobe_pre_sstep_notifier+0x151/0x1b0 irqentry_exit_to_user_mode+0xe2/0x1b0 asm_exc_int3+0x39/0x40 RIP: 0033:0x401199 Code: 01 c2 0f b6 45 fb 88 02 83 45 fc 01 8b 45 fc 3b 45 e4 7c b7 8b 45 e4 48 98 48 8d 50 ff 48 8b 45 e8 48 01 d0 ce RSP: 002b:00007ffdf00576a8 EFLAGS: 00000206 RAX: 00007ffdf00576b0 RBX: 0000000000000000 RCX: 0000000000000ff2 RDX: 0000000000000ffc RSI: 0000000000000ffd RDI: 00007ffdf00576b0 RBP: 00007ffdf00586b0 R08: 00007feb2f9c0d20 R09: 00007feb2f9c0d20 R10: 0000000000000001 R11: 0000000000000202 R12: 0000000000401040 R13: 00007ffdf0058780 R14: 0000000000000000 R15: 0000000000000000 </TASK> This commit enforces the buffer's maxlen less than a page-size to avoid store_trace_args() out-of-memory access.
CVE-2024-50125: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix UAF on sco_sock_timeout conn->sk maybe have been unlinked/freed while waiting for sco_conn_lock so this checks if the conn->sk is still valid by checking if it part of sco_sk_list.
CVE-2024-50135: In the Linux kernel, the following vulnerability has been resolved: nvme-pci: fix race condition between reset and nvme_dev_disable() nvme_dev_disable() modifies the dev->online_queues field, therefore nvme_pci_update_nr_queues() should avoid racing against it, otherwise we could end up passing invalid values to blk_mq_update_nr_hw_queues(). WARNING: CPU: 39 PID: 61303 at drivers/pci/msi/api.c:347 pci_irq_get_affinity+0x187/0x210 Workqueue: nvme-reset-wq nvme_reset_work [nvme] RIP: 0010:pci_irq_get_affinity+0x187/0x210 Call Trace: <TASK> ? blk_mq_pci_map_queues+0x87/0x3c0 ? pci_irq_get_affinity+0x187/0x210 blk_mq_pci_map_queues+0x87/0x3c0 nvme_pci_map_queues+0x189/0x460 [nvme] blk_mq_update_nr_hw_queues+0x2a/0x40 nvme_reset_work+0x1be/0x2a0 [nvme] Fix the bug by locking the shutdown_lock mutex before using dev->online_queues. Give up if nvme_dev_disable() is running or if it has been executed already.
CVE-2024-50138: In the Linux kernel, the following vulnerability has been resolved: bpf: Use raw_spinlock_t in ringbuf The function __bpf_ringbuf_reserve is invoked from a tracepoint, which disables preemption. Using spinlock_t in this context can lead to a "sleep in atomic" warning in the RT variant. This issue is illustrated in the example below: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 556208, name: test_progs preempt_count: 1, expected: 0 RCU nest depth: 1, expected: 1 INFO: lockdep is turned off. Preemption disabled at: [<ffffd33a5c88ea44>] migrate_enable+0xc0/0x39c CPU: 7 PID: 556208 Comm: test_progs Tainted: G Hardware name: Qualcomm SA8775P Ride (DT) Call trace: dump_backtrace+0xac/0x130 show_stack+0x1c/0x30 dump_stack_lvl+0xac/0xe8 dump_stack+0x18/0x30 __might_resched+0x3bc/0x4fc rt_spin_lock+0x8c/0x1a4 __bpf_ringbuf_reserve+0xc4/0x254 bpf_ringbuf_reserve_dynptr+0x5c/0xdc bpf_prog_ac3d15160d62622a_test_read_write+0x104/0x238 trace_call_bpf+0x238/0x774 perf_call_bpf_enter.isra.0+0x104/0x194 perf_syscall_enter+0x2f8/0x510 trace_sys_enter+0x39c/0x564 syscall_trace_enter+0x220/0x3c0 do_el0_svc+0x138/0x1dc el0_svc+0x54/0x130 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Switch the spinlock to raw_spinlock_t to avoid this error.
CVE-2024-50166: In the Linux kernel, the following vulnerability has been resolved: fsl/fman: Fix refcount handling of fman-related devices In mac_probe() there are multiple calls to of_find_device_by_node(), fman_bind() and fman_port_bind() which takes references to of_dev->dev. Not all references taken by these calls are released later on error path in mac_probe() and in mac_remove() which lead to reference leaks. Add references release.
CVE-2024-50187: In the Linux kernel, the following vulnerability has been resolved: drm/vc4: Stop the active perfmon before being destroyed Upon closing the file descriptor, the active performance monitor is not stopped. Although all perfmons are destroyed in `vc4_perfmon_close_file()`, the active performance monitor's pointer (`vc4->active_perfmon`) is still retained. If we open a new file descriptor and submit a few jobs with performance monitors, the driver will attempt to stop the active performance monitor using the stale pointer in `vc4->active_perfmon`. However, this pointer is no longer valid because the previous process has already terminated, and all performance monitors associated with it have been destroyed and freed. To fix this, when the active performance monitor belongs to a given process, explicitly stop it before destroying and freeing it.
CVE-2024-50196: In the Linux kernel, the following vulnerability has been resolved: pinctrl: ocelot: fix system hang on level based interrupts The current implementation only calls chained_irq_enter() and chained_irq_exit() if it detects pending interrupts. ``` for (i = 0; i < info->stride; i++) { uregmap_read(info->map, id_reg + 4 * i, &reg); if (!reg) continue; chained_irq_enter(parent_chip, desc); ``` However, in case of GPIO pin configured in level mode and the parent controller configured in edge mode, GPIO interrupt might be lowered by the hardware. In the result, if the interrupt is short enough, the parent interrupt is still pending while the GPIO interrupt is cleared; chained_irq_enter() never gets called and the system hangs trying to service the parent interrupt. Moving chained_irq_enter() and chained_irq_exit() outside the for loop ensures that they are called even when GPIO interrupt is lowered by the hardware. The similar code with chained_irq_enter() / chained_irq_exit() functions wrapping interrupt checking loop may be found in many other drivers: ``` grep -r -A 10 chained_irq_enter drivers/pinctrl ```
CVE-2024-50211: In the Linux kernel, the following vulnerability has been resolved: udf: refactor inode_bmap() to handle error Refactor inode_bmap() to handle error since udf_next_aext() can return error now. On situations like ftruncate, udf_extend_file() can now detect errors and bail out early without resorting to checking for particular offsets and assuming internal behavior of these functions.
CVE-2024-50217: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix use-after-free of block device file in __btrfs_free_extra_devids() Mounting btrfs from two images (which have the same one fsid and two different dev_uuids) in certain executing order may trigger an UAF for variable 'device->bdev_file' in __btrfs_free_extra_devids(). And following are the details: 1. Attach image_1 to loop0, attach image_2 to loop1, and scan btrfs devices by ioctl(BTRFS_IOC_SCAN_DEV): / btrfs_device_1 → loop0 fs_device \ btrfs_device_2 → loop1 2. mount /dev/loop0 /mnt btrfs_open_devices btrfs_device_1->bdev_file = btrfs_get_bdev_and_sb(loop0) btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1) btrfs_fill_super open_ctree fail: btrfs_close_devices // -ENOMEM btrfs_close_bdev(btrfs_device_1) fput(btrfs_device_1->bdev_file) // btrfs_device_1->bdev_file is freed btrfs_close_bdev(btrfs_device_2) fput(btrfs_device_2->bdev_file) 3. mount /dev/loop1 /mnt btrfs_open_devices btrfs_get_bdev_and_sb(&bdev_file) // EIO, btrfs_device_1->bdev_file is not assigned, // which points to a freed memory area btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1) btrfs_fill_super open_ctree btrfs_free_extra_devids if (btrfs_device_1->bdev_file) fput(btrfs_device_1->bdev_file) // UAF ! Fix it by setting 'device->bdev_file' as 'NULL' after closing the btrfs_device in btrfs_close_one_device().
CVE-2024-50256: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_reject_ipv6: fix potential crash in nf_send_reset6() I got a syzbot report without a repro [1] crashing in nf_send_reset6() I think the issue is that dev->hard_header_len is zero, and we attempt later to push an Ethernet header. Use LL_MAX_HEADER, as other functions in net/ipv6/netfilter/nf_reject_ipv6.c. [1] skbuff: skb_under_panic: text:ffffffff89b1d008 len:74 put:14 head:ffff88803123aa00 data:ffff88803123a9f2 tail:0x3c end:0x140 dev:syz_tun kernel BUG at net/core/skbuff.c:206 ! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 0 UID: 0 PID: 7373 Comm: syz.1.568 Not tainted 6.12.0-rc2-syzkaller-00631-g6d858708d465 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 RIP: 0010:skb_panic net/core/skbuff.c:206 [inline] RIP: 0010:skb_under_panic+0x14b/0x150 net/core/skbuff.c:216 Code: 0d 8d 48 c7 c6 60 a6 29 8e 48 8b 54 24 08 8b 0c 24 44 8b 44 24 04 4d 89 e9 50 41 54 41 57 41 56 e8 ba 30 38 02 48 83 c4 20 90 <0f> 0b 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 RSP: 0018:ffffc900045269b0 EFLAGS: 00010282 RAX: 0000000000000088 RBX: dffffc0000000000 RCX: cd66dacdc5d8e800 RDX: 0000000000000000 RSI: 0000000000000200 RDI: 0000000000000000 RBP: ffff88802d39a3d0 R08: ffffffff8174afec R09: 1ffff920008a4ccc R10: dffffc0000000000 R11: fffff520008a4ccd R12: 0000000000000140 R13: ffff88803123aa00 R14: ffff88803123a9f2 R15: 000000000000003c FS: 00007fdbee5ff6c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000005d322000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> skb_push+0xe5/0x100 net/core/skbuff.c:2636 eth_header+0x38/0x1f0 net/ethernet/eth.c:83 dev_hard_header include/linux/netdevice.h:3208 [inline] nf_send_reset6+0xce6/0x1270 net/ipv6/netfilter/nf_reject_ipv6.c:358 nft_reject_inet_eval+0x3b9/0x690 net/netfilter/nft_reject_inet.c:48 expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline] nft_do_chain+0x4ad/0x1da0 net/netfilter/nf_tables_core.c:288 nft_do_chain_inet+0x418/0x6b0 net/netfilter/nft_chain_filter.c:161 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xc3/0x220 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] NF_HOOK include/linux/netfilter.h:312 [inline] br_nf_pre_routing_ipv6+0x63e/0x770 net/bridge/br_netfilter_ipv6.c:184 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_bridge_pre net/bridge/br_input.c:277 [inline] br_handle_frame+0x9fd/0x1530 net/bridge/br_input.c:424 __netif_receive_skb_core+0x13e8/0x4570 net/core/dev.c:5562 __netif_receive_skb_one_core net/core/dev.c:5666 [inline] __netif_receive_skb+0x12f/0x650 net/core/dev.c:5781 netif_receive_skb_internal net/core/dev.c:5867 [inline] netif_receive_skb+0x1e8/0x890 net/core/dev.c:5926 tun_rx_batched+0x1b7/0x8f0 drivers/net/tun.c:1550 tun_get_user+0x3056/0x47e0 drivers/net/tun.c:2007 tun_chr_write_iter+0x10d/0x1f0 drivers/net/tun.c:2053 new_sync_write fs/read_write.c:590 [inline] vfs_write+0xa6d/0xc90 fs/read_write.c:683 ksys_write+0x183/0x2b0 fs/read_write.c:736 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fdbeeb7d1ff Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 c9 8d 02 00 48 8b 54 24 18 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 1c 8e 02 00 48 RSP: 002b:00007fdbee5ff000 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007fdbeed36058 RCX: 00007fdbeeb7d1ff RDX: 000000000000008e RSI: 0000000020000040 RDI: 00000000000000c8 RBP: 00007fdbeebf12be R08: 0000000 ---truncated---
CVE-2024-50258: In the Linux kernel, the following vulnerability has been resolved: net: fix crash when config small gso_max_size/gso_ipv4_max_size Config a small gso_max_size/gso_ipv4_max_size will lead to an underflow in sk_dst_gso_max_size(), which may trigger a BUG_ON crash, because sk->sk_gso_max_size would be much bigger than device limits. Call Trace: tcp_write_xmit tso_segs = tcp_init_tso_segs(skb, mss_now); tcp_set_skb_tso_segs tcp_skb_pcount_set // skb->len = 524288, mss_now = 8 // u16 tso_segs = 524288/8 = 65535 -> 0 tso_segs = DIV_ROUND_UP(skb->len, mss_now) BUG_ON(!tso_segs) Add check for the minimum value of gso_max_size and gso_ipv4_max_size.
CVE-2024-50272: In the Linux kernel, the following vulnerability has been resolved: filemap: Fix bounds checking in filemap_read() If the caller supplies an iocb->ki_pos value that is close to the filesystem upper limit, and an iterator with a count that causes us to overflow that limit, then filemap_read() enters an infinite loop. This behaviour was discovered when testing xfstests generic/525 with the "localio" optimisation for loopback NFS mounts.
CVE-2024-50282: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: add missing size check in amdgpu_debugfs_gprwave_read() Avoid a possible buffer overflow if size is larger than 4K. (cherry picked from commit f5d873f5825b40d886d03bd2aede91d4cf002434)
CVE-2024-50289: In the Linux kernel, the following vulnerability has been resolved: media: av7110: fix a spectre vulnerability As warned by smatch: drivers/staging/media/av7110/av7110_ca.c:270 dvb_ca_ioctl() warn: potential spectre issue 'av7110->ci_slot' [w] (local cap) There is a spectre-related vulnerability at the code. Fix it.
CVE-2024-50298: In the Linux kernel, the following vulnerability has been resolved: net: enetc: allocate vf_state during PF probes In the previous implementation, vf_state is allocated memory only when VF is enabled. However, net_device_ops::ndo_set_vf_mac() may be called before VF is enabled to configure the MAC address of VF. If this is the case, enetc_pf_set_vf_mac() will access vf_state, resulting in access to a null pointer. The simplified error log is as follows. root@ls1028ardb:~# ip link set eno0 vf 1 mac 00:0c:e7:66:77:89 [ 173.543315] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004 [ 173.637254] pc : enetc_pf_set_vf_mac+0x3c/0x80 Message from sy [ 173.641973] lr : do_setlink+0x4a8/0xec8 [ 173.732292] Call trace: [ 173.734740] enetc_pf_set_vf_mac+0x3c/0x80 [ 173.738847] __rtnl_newlink+0x530/0x89c [ 173.742692] rtnl_newlink+0x50/0x7c [ 173.746189] rtnetlink_rcv_msg+0x128/0x390 [ 173.750298] netlink_rcv_skb+0x60/0x130 [ 173.754145] rtnetlink_rcv+0x18/0x24 [ 173.757731] netlink_unicast+0x318/0x380 [ 173.761665] netlink_sendmsg+0x17c/0x3c8
CVE-2024-52559: In the Linux kernel, the following vulnerability has been resolved: drm/msm/gem: prevent integer overflow in msm_ioctl_gem_submit() The "submit->cmd[i].size" and "submit->cmd[i].offset" variables are u32 values that come from the user via the submit_lookup_cmds() function. This addition could lead to an integer wrapping bug so use size_add() to prevent that. Patchwork: https://patchwork.freedesktop.org/patch/624696/
CVE-2024-53051: In the Linux kernel, the following vulnerability has been resolved: drm/i915/hdcp: Add encoder check in intel_hdcp_get_capability Sometimes during hotplug scenario or suspend/resume scenario encoder is not always initialized when intel_hdcp_get_capability add a check to avoid kernel null pointer dereference.
CVE-2024-53058: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: TSO: Fix unbalanced DMA map/unmap for non-paged SKB data In case the non-paged data of a SKB carries protocol header and protocol payload to be transmitted on a certain platform that the DMA AXI address width is configured to 40-bit/48-bit, or the size of the non-paged data is bigger than TSO_MAX_BUFF_SIZE on a certain platform that the DMA AXI address width is configured to 32-bit, then this SKB requires at least two DMA transmit descriptors to serve it. For example, three descriptors are allocated to split one DMA buffer mapped from one piece of non-paged data: dma_desc[N + 0], dma_desc[N + 1], dma_desc[N + 2]. Then three elements of tx_q->tx_skbuff_dma[] will be allocated to hold extra information to be reused in stmmac_tx_clean(): tx_q->tx_skbuff_dma[N + 0], tx_q->tx_skbuff_dma[N + 1], tx_q->tx_skbuff_dma[N + 2]. Now we focus on tx_q->tx_skbuff_dma[entry].buf, which is the DMA buffer address returned by DMA mapping call. stmmac_tx_clean() will try to unmap the DMA buffer _ONLY_IF_ tx_q->tx_skbuff_dma[entry].buf is a valid buffer address. The expected behavior that saves DMA buffer address of this non-paged data to tx_q->tx_skbuff_dma[entry].buf is: tx_q->tx_skbuff_dma[N + 0].buf = NULL; tx_q->tx_skbuff_dma[N + 1].buf = NULL; tx_q->tx_skbuff_dma[N + 2].buf = dma_map_single(); Unfortunately, the current code misbehaves like this: tx_q->tx_skbuff_dma[N + 0].buf = dma_map_single(); tx_q->tx_skbuff_dma[N + 1].buf = NULL; tx_q->tx_skbuff_dma[N + 2].buf = NULL; On the stmmac_tx_clean() side, when dma_desc[N + 0] is closed by the DMA engine, tx_q->tx_skbuff_dma[N + 0].buf is a valid buffer address obviously, then the DMA buffer will be unmapped immediately. There may be a rare case that the DMA engine does not finish the pending dma_desc[N + 1], dma_desc[N + 2] yet. Now things will go horribly wrong, DMA is going to access a unmapped/unreferenced memory region, corrupted data will be transmited or iommu fault will be triggered :( In contrast, the for-loop that maps SKB fragments behaves perfectly as expected, and that is how the driver should do for both non-paged data and paged frags actually. This patch corrects DMA map/unmap sequences by fixing the array index for tx_q->tx_skbuff_dma[entry].buf when assigning DMA buffer address. Tested and verified on DWXGMAC CORE 3.20a
CVE-2024-53068: In the Linux kernel, the following vulnerability has been resolved: firmware: arm_scmi: Fix slab-use-after-free in scmi_bus_notifier() The scmi_dev->name is released prematurely in __scmi_device_destroy(), which causes slab-use-after-free when accessing scmi_dev->name in scmi_bus_notifier(). So move the release of scmi_dev->name to scmi_device_release() to avoid slab-use-after-free. | BUG: KASAN: slab-use-after-free in strncmp+0xe4/0xec | Read of size 1 at addr ffffff80a482bcc0 by task swapper/0/1 | | CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.6.38-debug #1 | Hardware name: Qualcomm Technologies, Inc. SA8775P Ride (DT) | Call trace: | dump_backtrace+0x94/0x114 | show_stack+0x18/0x24 | dump_stack_lvl+0x48/0x60 | print_report+0xf4/0x5b0 | kasan_report+0xa4/0xec | __asan_report_load1_noabort+0x20/0x2c | strncmp+0xe4/0xec | scmi_bus_notifier+0x5c/0x54c | notifier_call_chain+0xb4/0x31c | blocking_notifier_call_chain+0x68/0x9c | bus_notify+0x54/0x78 | device_del+0x1bc/0x840 | device_unregister+0x20/0xb4 | __scmi_device_destroy+0xac/0x280 | scmi_device_destroy+0x94/0xd0 | scmi_chan_setup+0x524/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20 | | Allocated by task 1: | kasan_save_stack+0x2c/0x54 | kasan_set_track+0x2c/0x40 | kasan_save_alloc_info+0x24/0x34 | __kasan_kmalloc+0xa0/0xb8 | __kmalloc_node_track_caller+0x6c/0x104 | kstrdup+0x48/0x84 | kstrdup_const+0x34/0x40 | __scmi_device_create.part.0+0x8c/0x408 | scmi_device_create+0x104/0x370 | scmi_chan_setup+0x2a0/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20 | | Freed by task 1: | kasan_save_stack+0x2c/0x54 | kasan_set_track+0x2c/0x40 | kasan_save_free_info+0x38/0x5c | __kasan_slab_free+0xe8/0x164 | __kmem_cache_free+0x11c/0x230 | kfree+0x70/0x130 | kfree_const+0x20/0x40 | __scmi_device_destroy+0x70/0x280 | scmi_device_destroy+0x94/0xd0 | scmi_chan_setup+0x524/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20
CVE-2024-53079: In the Linux kernel, the following vulnerability has been resolved: mm/thp: fix deferred split unqueue naming and locking Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. Before fixing locking: rename misleading folio_undo_large_rmappable(), which does not undo large_rmappable, to folio_unqueue_deferred_split(), which is what it does. But that and its out-of-line __callee are mm internals of very limited usability: add comment and WARN_ON_ONCEs to check usage; and return a bool to say if a deferred split was unqueued, which can then be used in WARN_ON_ONCEs around safety checks (sparing callers the arcane conditionals in __folio_unqueue_deferred_split()). Just omit the folio_unqueue_deferred_split() from free_unref_folios(), all of whose callers now call it beforehand (and if any forget then bad_page() will tell) - except for its caller put_pages_list(), which itself no longer has any callers (and will be deleted separately). Swapout: mem_cgroup_swapout() has been resetting folio->memcg_data 0 without checking and unqueueing a THP folio from deferred split list; which is unfortunate, since the split_queue_lock depends on the memcg (when memcg is enabled); so swapout has been unqueueing such THPs later, when freeing the folio, using the pgdat's lock instead: potentially corrupting the memcg's list. __remove_mapping() has frozen refcount to 0 here, so no problem with calling folio_unqueue_deferred_split() before resetting memcg_data. That goes back to 5.4 commit 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware"): which included a check on swapcache before adding to deferred queue, but no check on deferred queue before adding THP to swapcache. That worked fine with the usual sequence of events in reclaim (though there were a couple of rare ways in which a THP on deferred queue could have been swapped out), but 6.12 commit dafff3f4c850 ("mm: split underused THPs") avoids splitting underused THPs in reclaim, which makes swapcache THPs on deferred queue commonplace. Keep the check on swapcache before adding to deferred queue? Yes: it is no longer essential, but preserves the existing behaviour, and is likely to be a worthwhile optimization (vmstat showed much more traffic on the queue under swapping load if the check was removed); update its comment. Memcg-v1 move (deprecated): mem_cgroup_move_account() has been changing folio->memcg_data without checking and unqueueing a THP folio from the deferred list, sometimes corrupting "from" memcg's list, like swapout. Refcount is non-zero here, so folio_unqueue_deferred_split() can only be used in a WARN_ON_ONCE to validate the fix, which must be done earlier: mem_cgroup_move_charge_pte_range() first try to split the THP (splitting of course unqueues), or skip it if that fails. Not ideal, but moving charge has been requested, and khugepaged should repair the THP later: nobody wants new custom unqueueing code just for this deprecated case. The 87eaceb3faa5 commit did have the code to move from one deferred list to another (but was not conscious of its unsafety while refcount non-0); but that was removed by 5.6 commit fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path"), which argued that the existence of a PMD mapping guarantees that the THP cannot be on a deferred list. As above, false in rare cases, and now commonly false. Backport to 6.11 should be straightforward. Earlier backports must take care that other _deferred_list fixes and dependencies are included. There is not a strong case for backports, but they can fix cornercases.
CVE-2024-53088: In the Linux kernel, the following vulnerability has been resolved: i40e: fix race condition by adding filter's intermediate sync state Fix a race condition in the i40e driver that leads to MAC/VLAN filters becoming corrupted and leaking. Address the issue that occurs under heavy load when multiple threads are concurrently modifying MAC/VLAN filters by setting mac and port VLAN. 1. Thread T0 allocates a filter in i40e_add_filter() within i40e_ndo_set_vf_port_vlan(). 2. Thread T1 concurrently frees the filter in __i40e_del_filter() within i40e_ndo_set_vf_mac(). 3. Subsequently, i40e_service_task() calls i40e_sync_vsi_filters(), which refers to the already freed filter memory, causing corruption. Reproduction steps: 1. Spawn multiple VFs. 2. Apply a concurrent heavy load by running parallel operations to change MAC addresses on the VFs and change port VLANs on the host. 3. Observe errors in dmesg: "Error I40E_AQ_RC_ENOSPC adding RX filters on VF XX, please set promiscuous on manually for VF XX". Exact code for stable reproduction Intel can't open-source now. The fix involves implementing a new intermediate filter state, I40E_FILTER_NEW_SYNC, for the time when a filter is on a tmp_add_list. These filters cannot be deleted from the hash list directly but must be removed using the full process.
CVE-2024-53090: In the Linux kernel, the following vulnerability has been resolved: afs: Fix lock recursion afs_wake_up_async_call() can incur lock recursion. The problem is that it is called from AF_RXRPC whilst holding the ->notify_lock, but it tries to take a ref on the afs_call struct in order to pass it to a work queue - but if the afs_call is already queued, we then have an extraneous ref that must be put... calling afs_put_call() may call back down into AF_RXRPC through rxrpc_kernel_shutdown_call(), however, which might try taking the ->notify_lock again. This case isn't very common, however, so defer it to a workqueue. The oops looks something like: BUG: spinlock recursion on CPU#0, krxrpcio/7001/1646 lock: 0xffff888141399b30, .magic: dead4ead, .owner: krxrpcio/7001/1646, .owner_cpu: 0 CPU: 0 UID: 0 PID: 1646 Comm: krxrpcio/7001 Not tainted 6.12.0-rc2-build3+ #4351 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Call Trace: <TASK> dump_stack_lvl+0x47/0x70 do_raw_spin_lock+0x3c/0x90 rxrpc_kernel_shutdown_call+0x83/0xb0 afs_put_call+0xd7/0x180 rxrpc_notify_socket+0xa0/0x190 rxrpc_input_split_jumbo+0x198/0x1d0 rxrpc_input_data+0x14b/0x1e0 ? rxrpc_input_call_packet+0xc2/0x1f0 rxrpc_input_call_event+0xad/0x6b0 rxrpc_input_packet_on_conn+0x1e1/0x210 rxrpc_input_packet+0x3f2/0x4d0 rxrpc_io_thread+0x243/0x410 ? __pfx_rxrpc_io_thread+0x10/0x10 kthread+0xcf/0xe0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x24/0x40 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2024-53093: In the Linux kernel, the following vulnerability has been resolved: nvme-multipath: defer partition scanning We need to suppress the partition scan from occuring within the controller's scan_work context. If a path error occurs here, the IO will wait until a path becomes available or all paths are torn down, but that action also occurs within scan_work, so it would deadlock. Defer the partion scan to a different context that does not block scan_work.
CVE-2024-53094: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Add sendpage_ok() check to disable MSG_SPLICE_PAGES While running ISER over SIW, the initiator machine encounters a warning from skb_splice_from_iter() indicating that a slab page is being used in send_page. To address this, it is better to add a sendpage_ok() check within the driver itself, and if it returns 0, then MSG_SPLICE_PAGES flag should be disabled before entering the network stack. A similar issue has been discussed for NVMe in this thread: https://lore.kernel.org/all/20240530142417.146696-1-ofir.gal@volumez.com/ WARNING: CPU: 0 PID: 5342 at net/core/skbuff.c:7140 skb_splice_from_iter+0x173/0x320 Call Trace: tcp_sendmsg_locked+0x368/0xe40 siw_tx_hdt+0x695/0xa40 [siw] siw_qp_sq_process+0x102/0xb00 [siw] siw_sq_resume+0x39/0x110 [siw] siw_run_sq+0x74/0x160 [siw] kthread+0xd2/0x100 ret_from_fork+0x34/0x40 ret_from_fork_asm+0x1a/0x30
CVE-2024-53095: In the Linux kernel, the following vulnerability has been resolved: smb: client: Fix use-after-free of network namespace. Recently, we got a customer report that CIFS triggers oops while reconnecting to a server. [0] The workload runs on Kubernetes, and some pods mount CIFS servers in non-root network namespaces. The problem rarely happened, but it was always while the pod was dying. The root cause is wrong reference counting for network namespace. CIFS uses kernel sockets, which do not hold refcnt of the netns that the socket belongs to. That means CIFS must ensure the socket is always freed before its netns; otherwise, use-after-free happens. The repro steps are roughly: 1. mount CIFS in a non-root netns 2. drop packets from the netns 3. destroy the netns 4. unmount CIFS We can reproduce the issue quickly with the script [1] below and see the splat [2] if CONFIG_NET_NS_REFCNT_TRACKER is enabled. When the socket is TCP, it is hard to guarantee the netns lifetime without holding refcnt due to async timers. Let's hold netns refcnt for each socket as done for SMC in commit 9744d2bf1976 ("smc: Fix use-after-free in tcp_write_timer_handler()."). Note that we need to move put_net() from cifs_put_tcp_session() to clean_demultiplex_info(); otherwise, __sock_create() still could touch a freed netns while cifsd tries to reconnect from cifs_demultiplex_thread(). Also, maybe_get_net() cannot be put just before __sock_create() because the code is not under RCU and there is a small chance that the same address happened to be reallocated to another netns. [0]: CIFS: VFS: \\XXXXXXXXXXX has not responded in 15 seconds. Reconnecting... CIFS: Serverclose failed 4 times, giving up Unable to handle kernel paging request at virtual address 14de99e461f84a07 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [14de99e461f84a07] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] SMP Modules linked in: cls_bpf sch_ingress nls_utf8 cifs cifs_arc4 cifs_md4 dns_resolver tcp_diag inet_diag veth xt_state xt_connmark nf_conntrack_netlink xt_nat xt_statistic xt_MASQUERADE xt_mark xt_addrtype ipt_REJECT nf_reject_ipv4 nft_chain_nat nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_comment nft_compat nf_tables nfnetlink overlay nls_ascii nls_cp437 sunrpc vfat fat aes_ce_blk aes_ce_cipher ghash_ce sm4_ce_cipher sm4 sm3_ce sm3 sha3_ce sha512_ce sha512_arm64 sha1_ce ena button sch_fq_codel loop fuse configfs dmi_sysfs sha2_ce sha256_arm64 dm_mirror dm_region_hash dm_log dm_mod dax efivarfs CPU: 5 PID: 2690970 Comm: cifsd Not tainted 6.1.103-109.184.amzn2023.aarch64 #1 Hardware name: Amazon EC2 r7g.4xlarge/, BIOS 1.0 11/1/2018 pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : fib_rules_lookup+0x44/0x238 lr : __fib_lookup+0x64/0xbc sp : ffff8000265db790 x29: ffff8000265db790 x28: 0000000000000000 x27: 000000000000bd01 x26: 0000000000000000 x25: ffff000b4baf8000 x24: ffff00047b5e4580 x23: ffff8000265db7e0 x22: 0000000000000000 x21: ffff00047b5e4500 x20: ffff0010e3f694f8 x19: 14de99e461f849f7 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 3f92800abd010002 x11: 0000000000000001 x10: ffff0010e3f69420 x9 : ffff800008a6f294 x8 : 0000000000000000 x7 : 0000000000000006 x6 : 0000000000000000 x5 : 0000000000000001 x4 : ffff001924354280 x3 : ffff8000265db7e0 x2 : 0000000000000000 x1 : ffff0010e3f694f8 x0 : ffff00047b5e4500 Call trace: fib_rules_lookup+0x44/0x238 __fib_lookup+0x64/0xbc ip_route_output_key_hash_rcu+0x2c4/0x398 ip_route_output_key_hash+0x60/0x8c tcp_v4_connect+0x290/0x488 __inet_stream_connect+0x108/0x3d0 inet_stream_connect+0x50/0x78 kernel_connect+0x6c/0xac generic_ip_conne ---truncated---
CVE-2024-53100: In the Linux kernel, the following vulnerability has been resolved: nvme: tcp: avoid race between queue_lock lock and destroy Commit 76d54bf20cdc ("nvme-tcp: don't access released socket during error recovery") added a mutex_lock() call for the queue->queue_lock in nvme_tcp_get_address(). However, the mutex_lock() races with mutex_destroy() in nvme_tcp_free_queue(), and causes the WARN below. DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 34077 at kernel/locking/mutex.c:587 __mutex_lock+0xcf0/0x1220 Modules linked in: nvmet_tcp nvmet nvme_tcp nvme_fabrics iw_cm ib_cm ib_core pktcdvd nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables qrtr sunrpc ppdev 9pnet_virtio 9pnet pcspkr netfs parport_pc parport e1000 i2c_piix4 i2c_smbus loop fuse nfnetlink zram bochs drm_vram_helper drm_ttm_helper ttm drm_kms_helper xfs drm sym53c8xx floppy nvme scsi_transport_spi nvme_core nvme_auth serio_raw ata_generic pata_acpi dm_multipath qemu_fw_cfg [last unloaded: ib_uverbs] CPU: 3 UID: 0 PID: 34077 Comm: udisksd Not tainted 6.11.0-rc7 #319 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:__mutex_lock+0xcf0/0x1220 Code: 08 84 d2 0f 85 c8 04 00 00 8b 15 ef b6 c8 01 85 d2 0f 85 78 f4 ff ff 48 c7 c6 20 93 ee af 48 c7 c7 60 91 ee af e8 f0 a7 6d fd <0f> 0b e9 5e f4 ff ff 48 b8 00 00 00 00 00 fc ff df 4c 89 f2 48 c1 RSP: 0018:ffff88811305f760 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff88812c652058 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000001 RBP: ffff88811305f8b0 R08: 0000000000000001 R09: ffffed1075c36341 R10: ffff8883ae1b1a0b R11: 0000000000010498 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88812c652058 FS: 00007f9713ae4980(0000) GS:ffff8883ae180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fcd78483c7c CR3: 0000000122c38000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __warn.cold+0x5b/0x1af ? __mutex_lock+0xcf0/0x1220 ? report_bug+0x1ec/0x390 ? handle_bug+0x3c/0x80 ? exc_invalid_op+0x13/0x40 ? asm_exc_invalid_op+0x16/0x20 ? __mutex_lock+0xcf0/0x1220 ? nvme_tcp_get_address+0xc2/0x1e0 [nvme_tcp] ? __pfx___mutex_lock+0x10/0x10 ? __lock_acquire+0xd6a/0x59e0 ? nvme_tcp_get_address+0xc2/0x1e0 [nvme_tcp] nvme_tcp_get_address+0xc2/0x1e0 [nvme_tcp] ? __pfx_nvme_tcp_get_address+0x10/0x10 [nvme_tcp] nvme_sysfs_show_address+0x81/0xc0 [nvme_core] dev_attr_show+0x42/0x80 ? __asan_memset+0x1f/0x40 sysfs_kf_seq_show+0x1f0/0x370 seq_read_iter+0x2cb/0x1130 ? rw_verify_area+0x3b1/0x590 ? __mutex_lock+0x433/0x1220 vfs_read+0x6a6/0xa20 ? lockdep_hardirqs_on+0x78/0x100 ? __pfx_vfs_read+0x10/0x10 ksys_read+0xf7/0x1d0 ? __pfx_ksys_read+0x10/0x10 ? __x64_sys_openat+0x105/0x1d0 do_syscall_64+0x93/0x180 ? lockdep_hardirqs_on_prepare+0x16d/0x400 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on+0x78/0x100 ? do_syscall_64+0x9f/0x180 ? __pfx_ksys_read+0x10/0x10 ? lockdep_hardirqs_on_prepare+0x16d/0x400 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on+0x78/0x100 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on_prepare+0x16d/0x400 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on+0x78/0x100 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on_prepare+0x16d/0x400 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on+0x78/0x100 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on_prepare+0x16d/0x400 ? do_syscall_64+0x9f/0x180 ? lockdep_hardirqs_on+0x78/0x100 ? do_syscall_64+0x9f/0x180 ? do_syscall_64+0x9f/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f9713f55cfa Code: 55 48 89 e5 48 83 ec 20 48 89 55 e8 48 89 75 f0 89 7d f8 e8 e8 74 f8 ff 48 8b 55 e8 48 8b 75 f0 4 ---truncated---
CVE-2024-53114: In the Linux kernel, the following vulnerability has been resolved: x86/CPU/AMD: Clear virtualized VMLOAD/VMSAVE on Zen4 client A number of Zen4 client SoCs advertise the ability to use virtualized VMLOAD/VMSAVE, but using these instructions is reported to be a cause of a random host reboot. These instructions aren't intended to be advertised on Zen4 client so clear the capability.
CVE-2024-53122: In the Linux kernel, the following vulnerability has been resolved: mptcp: cope racing subflow creation in mptcp_rcv_space_adjust Additional active subflows - i.e. created by the in kernel path manager - are included into the subflow list before starting the 3whs. A racing recvmsg() spooling data received on an already established subflow would unconditionally call tcp_cleanup_rbuf() on all the current subflows, potentially hitting a divide by zero error on the newly created ones. Explicitly check that the subflow is in a suitable state before invoking tcp_cleanup_rbuf().
CVE-2024-53128: In the Linux kernel, the following vulnerability has been resolved: sched/task_stack: fix object_is_on_stack() for KASAN tagged pointers When CONFIG_KASAN_SW_TAGS and CONFIG_KASAN_STACK are enabled, the object_is_on_stack() function may produce incorrect results due to the presence of tags in the obj pointer, while the stack pointer does not have tags. This discrepancy can lead to incorrect stack object detection and subsequently trigger warnings if CONFIG_DEBUG_OBJECTS is also enabled. Example of the warning: ODEBUG: object 3eff800082ea7bb0 is NOT on stack ffff800082ea0000, but annotated. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at lib/debugobjects.c:557 __debug_object_init+0x330/0x364 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-rc5 #4 Hardware name: linux,dummy-virt (DT) pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __debug_object_init+0x330/0x364 lr : __debug_object_init+0x330/0x364 sp : ffff800082ea7b40 x29: ffff800082ea7b40 x28: 98ff0000c0164518 x27: 98ff0000c0164534 x26: ffff800082d93ec8 x25: 0000000000000001 x24: 1cff0000c00172a0 x23: 0000000000000000 x22: ffff800082d93ed0 x21: ffff800081a24418 x20: 3eff800082ea7bb0 x19: efff800000000000 x18: 0000000000000000 x17: 00000000000000ff x16: 0000000000000047 x15: 206b63617473206e x14: 0000000000000018 x13: ffff800082ea7780 x12: 0ffff800082ea78e x11: 0ffff800082ea790 x10: 0ffff800082ea79d x9 : 34d77febe173e800 x8 : 34d77febe173e800 x7 : 0000000000000001 x6 : 0000000000000001 x5 : feff800082ea74b8 x4 : ffff800082870a90 x3 : ffff80008018d3c4 x2 : 0000000000000001 x1 : ffff800082858810 x0 : 0000000000000050 Call trace: __debug_object_init+0x330/0x364 debug_object_init_on_stack+0x30/0x3c schedule_hrtimeout_range_clock+0xac/0x26c schedule_hrtimeout+0x1c/0x30 wait_task_inactive+0x1d4/0x25c kthread_bind_mask+0x28/0x98 init_rescuer+0x1e8/0x280 workqueue_init+0x1a0/0x3cc kernel_init_freeable+0x118/0x200 kernel_init+0x28/0x1f0 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- ODEBUG: object 3eff800082ea7bb0 is NOT on stack ffff800082ea0000, but annotated. ------------[ cut here ]------------
CVE-2024-53147: In the Linux kernel, the following vulnerability has been resolved: exfat: fix out-of-bounds access of directory entries In the case of the directory size is greater than or equal to the cluster size, if start_clu becomes an EOF cluster(an invalid cluster) due to file system corruption, then the directory entry where ei->hint_femp.eidx hint is outside the directory, resulting in an out-of-bounds access, which may cause further file system corruption. This commit adds a check for start_clu, if it is an invalid cluster, the file or directory will be treated as empty.
CVE-2024-53168: In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix one UAF issue caused by sunrpc kernel tcp socket BUG: KASAN: slab-use-after-free in tcp_write_timer_handler+0x156/0x3e0 Read of size 1 at addr ffff888111f322cd by task swapper/0/0 CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc4-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 Call Trace: <IRQ> dump_stack_lvl+0x68/0xa0 print_address_description.constprop.0+0x2c/0x3d0 print_report+0xb4/0x270 kasan_report+0xbd/0xf0 tcp_write_timer_handler+0x156/0x3e0 tcp_write_timer+0x66/0x170 call_timer_fn+0xfb/0x1d0 __run_timers+0x3f8/0x480 run_timer_softirq+0x9b/0x100 handle_softirqs+0x153/0x390 __irq_exit_rcu+0x103/0x120 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x76/0x90 </IRQ> <TASK> asm_sysvec_apic_timer_interrupt+0x1a/0x20 RIP: 0010:default_idle+0xf/0x20 Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 66 90 0f 00 2d 33 f8 25 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 RSP: 0018:ffffffffa2007e28 EFLAGS: 00000242 RAX: 00000000000f3b31 RBX: 1ffffffff4400fc7 RCX: ffffffffa09c3196 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff9f00590f RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed102360835d R10: ffff88811b041aeb R11: 0000000000000001 R12: 0000000000000000 R13: ffffffffa202d7c0 R14: 0000000000000000 R15: 00000000000147d0 default_idle_call+0x6b/0xa0 cpuidle_idle_call+0x1af/0x1f0 do_idle+0xbc/0x130 cpu_startup_entry+0x33/0x40 rest_init+0x11f/0x210 start_kernel+0x39a/0x420 x86_64_start_reservations+0x18/0x30 x86_64_start_kernel+0x97/0xa0 common_startup_64+0x13e/0x141 </TASK> Allocated by task 595: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 __kasan_slab_alloc+0x87/0x90 kmem_cache_alloc_noprof+0x12b/0x3f0 copy_net_ns+0x94/0x380 create_new_namespaces+0x24c/0x500 unshare_nsproxy_namespaces+0x75/0xf0 ksys_unshare+0x24e/0x4f0 __x64_sys_unshare+0x1f/0x30 do_syscall_64+0x70/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 100: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x54/0x70 kmem_cache_free+0x156/0x5d0 cleanup_net+0x5d3/0x670 process_one_work+0x776/0xa90 worker_thread+0x2e2/0x560 kthread+0x1a8/0x1f0 ret_from_fork+0x34/0x60 ret_from_fork_asm+0x1a/0x30 Reproduction script: mkdir -p /mnt/nfsshare mkdir -p /mnt/nfs/netns_1 mkfs.ext4 /dev/sdb mount /dev/sdb /mnt/nfsshare systemctl restart nfs-server chmod 777 /mnt/nfsshare exportfs -i -o rw,no_root_squash *:/mnt/nfsshare ip netns add netns_1 ip link add name veth_1_peer type veth peer veth_1 ifconfig veth_1_peer 11.11.0.254 up ip link set veth_1 netns netns_1 ip netns exec netns_1 ifconfig veth_1 11.11.0.1 ip netns exec netns_1 /root/iptables -A OUTPUT -d 11.11.0.254 -p tcp \ --tcp-flags FIN FIN -j DROP (note: In my environment, a DESTROY_CLIENTID operation is always sent immediately, breaking the nfs tcp connection.) ip netns exec netns_1 timeout -s 9 300 mount -t nfs -o proto=tcp,vers=4.1 \ 11.11.0.254:/mnt/nfsshare /mnt/nfs/netns_1 ip netns del netns_1 The reason here is that the tcp socket in netns_1 (nfs side) has been shutdown and closed (done in xs_destroy), but the FIN message (with ack) is discarded, and the nfsd side keeps sending retransmission messages. As a result, when the tcp sock in netns_1 processes the received message, it sends the message (FIN message) in the sending queue, and the tcp timer is re-established. When the network namespace is deleted, the net structure accessed by tcp's timer handler function causes problems. To fix this problem, let's hold netns refcnt for the tcp kernel socket as done in other modules. This is an ugly hack which can easily be backported to earlier kernels. A proper fix which cleans up the interfaces will follow, but may not be so easy to backport.
CVE-2024-53179: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free of signing key Customers have reported use-after-free in @ses->auth_key.response with SMB2.1 + sign mounts which occurs due to following race: task A task B cifs_mount() dfs_mount_share() get_session() cifs_mount_get_session() cifs_send_recv() cifs_get_smb_ses() compound_send_recv() cifs_setup_session() smb2_setup_request() kfree_sensitive() smb2_calc_signature() crypto_shash_setkey() *UAF* Fix this by ensuring that we have a valid @ses->auth_key.response by checking whether @ses->ses_status is SES_GOOD or SES_EXITING with @ses->ses_lock held. After commit 24a9799aa8ef ("smb: client: fix UAF in smb2_reconnect_server()"), we made sure to call ->logoff() only when @ses was known to be good (e.g. valid ->auth_key.response), so it's safe to access signing key when @ses->ses_status == SES_EXITING.
CVE-2024-53187: In the Linux kernel, the following vulnerability has been resolved: io_uring: check for overflows in io_pin_pages WARNING: CPU: 0 PID: 5834 at io_uring/memmap.c:144 io_pin_pages+0x149/0x180 io_uring/memmap.c:144 CPU: 0 UID: 0 PID: 5834 Comm: syz-executor825 Not tainted 6.12.0-next-20241118-syzkaller #0 Call Trace: <TASK> __io_uaddr_map+0xfb/0x2d0 io_uring/memmap.c:183 io_rings_map io_uring/io_uring.c:2611 [inline] io_allocate_scq_urings+0x1c0/0x650 io_uring/io_uring.c:3470 io_uring_create+0x5b5/0xc00 io_uring/io_uring.c:3692 io_uring_setup io_uring/io_uring.c:3781 [inline] ... </TASK> io_pin_pages()'s uaddr parameter came directly from the user and can be garbage. Don't just add size to it as it can overflow.
CVE-2024-53190: In the Linux kernel, the following vulnerability has been resolved: wifi: rtlwifi: Drastically reduce the attempts to read efuse in case of failures Syzkaller reported a hung task with uevent_show() on stack trace. That specific issue was addressed by another commit [0], but even with that fix applied (for example, running v6.12-rc5) we face another type of hung task that comes from the same reproducer [1]. By investigating that, we could narrow it to the following path: (a) Syzkaller emulates a Realtek USB WiFi adapter using raw-gadget and dummy_hcd infrastructure. (b) During the probe of rtl8192cu, the driver ends-up performing an efuse read procedure (which is related to EEPROM load IIUC), and here lies the issue: the function read_efuse() calls read_efuse_byte() many times, as loop iterations depending on the efuse size (in our example, 512 in total). This procedure for reading efuse bytes relies in a loop that performs an I/O read up to *10k* times in case of failures. We measured the time of the loop inside read_efuse_byte() alone, and in this reproducer (which involves the dummy_hcd emulation layer), it takes 15 seconds each. As a consequence, we have the driver stuck in its probe routine for big time, exposing a stack trace like below if we attempt to reboot the system, for example: task:kworker/0:3 state:D stack:0 pid:662 tgid:662 ppid:2 flags:0x00004000 Workqueue: usb_hub_wq hub_event Call Trace: __schedule+0xe22/0xeb6 schedule_timeout+0xe7/0x132 __wait_for_common+0xb5/0x12e usb_start_wait_urb+0xc5/0x1ef ? usb_alloc_urb+0x95/0xa4 usb_control_msg+0xff/0x184 _usbctrl_vendorreq_sync+0xa0/0x161 _usb_read_sync+0xb3/0xc5 read_efuse_byte+0x13c/0x146 read_efuse+0x351/0x5f0 efuse_read_all_map+0x42/0x52 rtl_efuse_shadow_map_update+0x60/0xef rtl_get_hwinfo+0x5d/0x1c2 rtl92cu_read_eeprom_info+0x10a/0x8d5 ? rtl92c_read_chip_version+0x14f/0x17e rtl_usb_probe+0x323/0x851 usb_probe_interface+0x278/0x34b really_probe+0x202/0x4a4 __driver_probe_device+0x166/0x1b2 driver_probe_device+0x2f/0xd8 [...] We propose hereby to drastically reduce the attempts of doing the I/O reads in case of failures, restricted to USB devices (given that they're inherently slower than PCIe ones). By retrying up to 10 times (instead of 10000), we got reponsiveness in the reproducer, while seems reasonable to believe that there's no sane USB device implementation in the field requiring this amount of retries at every I/O read in order to properly work. Based on that assumption, it'd be good to have it backported to stable but maybe not since driver implementation (the 10k number comes from day 0), perhaps up to 6.x series makes sense. [0] Commit 15fffc6a5624 ("driver core: Fix uevent_show() vs driver detach race") [1] A note about that: this syzkaller report presents multiple reproducers that differs by the type of emulated USB device. For this specific case, check the entry from 2024/08/08 06:23 in the list of crashes; the C repro is available at https://syzkaller.appspot.com/text?tag=ReproC&x=1521fc83980000.
CVE-2024-53195: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Get rid of userspace_irqchip_in_use Improper use of userspace_irqchip_in_use led to syzbot hitting the following WARN_ON() in kvm_timer_update_irq(): WARNING: CPU: 0 PID: 3281 at arch/arm64/kvm/arch_timer.c:459 kvm_timer_update_irq+0x21c/0x394 Call trace: kvm_timer_update_irq+0x21c/0x394 arch/arm64/kvm/arch_timer.c:459 kvm_timer_vcpu_reset+0x158/0x684 arch/arm64/kvm/arch_timer.c:968 kvm_reset_vcpu+0x3b4/0x560 arch/arm64/kvm/reset.c:264 kvm_vcpu_set_target arch/arm64/kvm/arm.c:1553 [inline] kvm_arch_vcpu_ioctl_vcpu_init arch/arm64/kvm/arm.c:1573 [inline] kvm_arch_vcpu_ioctl+0x112c/0x1b3c arch/arm64/kvm/arm.c:1695 kvm_vcpu_ioctl+0x4ec/0xf74 virt/kvm/kvm_main.c:4658 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x108/0x184 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x78/0x1b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0xe8/0x1b0 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x40/0x50 arch/arm64/kernel/syscall.c:151 el0_svc+0x54/0x14c arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The following sequence led to the scenario: - Userspace creates a VM and a vCPU. - The vCPU is initialized with KVM_ARM_VCPU_PMU_V3 during KVM_ARM_VCPU_INIT. - Without any other setup, such as vGIC or vPMU, userspace issues KVM_RUN on the vCPU. Since the vPMU is requested, but not setup, kvm_arm_pmu_v3_enable() fails in kvm_arch_vcpu_run_pid_change(). As a result, KVM_RUN returns after enabling the timer, but before incrementing 'userspace_irqchip_in_use': kvm_arch_vcpu_run_pid_change() ret = kvm_arm_pmu_v3_enable() if (!vcpu->arch.pmu.created) return -EINVAL; if (ret) return ret; [...] if (!irqchip_in_kernel(kvm)) static_branch_inc(&userspace_irqchip_in_use); - Userspace ignores the error and issues KVM_ARM_VCPU_INIT again. Since the timer is already enabled, control moves through the following flow, ultimately hitting the WARN_ON(): kvm_timer_vcpu_reset() if (timer->enabled) kvm_timer_update_irq() if (!userspace_irqchip()) ret = kvm_vgic_inject_irq() ret = vgic_lazy_init() if (unlikely(!vgic_initialized(kvm))) if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; WARN_ON(ret); Theoretically, since userspace_irqchip_in_use's functionality can be simply replaced by '!irqchip_in_kernel()', get rid of the static key to avoid the mismanagement, which also helps with the syzbot issue.
CVE-2024-53196: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Don't retire aborted MMIO instruction Returning an abort to the guest for an unsupported MMIO access is a documented feature of the KVM UAPI. Nevertheless, it's clear that this plumbing has seen limited testing, since userspace can trivially cause a WARN in the MMIO return: WARNING: CPU: 0 PID: 30558 at arch/arm64/include/asm/kvm_emulate.h:536 kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 Call trace: kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 kvm_arch_vcpu_ioctl_run+0x98/0x15b4 arch/arm64/kvm/arm.c:1133 kvm_vcpu_ioctl+0x75c/0xa78 virt/kvm/kvm_main.c:4487 __do_sys_ioctl fs/ioctl.c:51 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x14c/0x1c8 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x1e0/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x38/0x68 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x90/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The splat is complaining that KVM is advancing PC while an exception is pending, i.e. that KVM is retiring the MMIO instruction despite a pending synchronous external abort. Womp womp. Fix the glaring UAPI bug by skipping over all the MMIO emulation in case there is a pending synchronous exception. Note that while userspace is capable of pending an asynchronous exception (SError, IRQ, or FIQ), it is still safe to retire the MMIO instruction in this case as (1) they are by definition asynchronous, and (2) KVM relies on hardware support for pending/delivering these exceptions instead of the software state machine for advancing PC.
CVE-2024-53210: In the Linux kernel, the following vulnerability has been resolved: s390/iucv: MSG_PEEK causes memory leak in iucv_sock_destruct() Passing MSG_PEEK flag to skb_recv_datagram() increments skb refcount (skb->users) and iucv_sock_recvmsg() does not decrement skb refcount at exit. This results in skb memory leak in skb_queue_purge() and WARN_ON in iucv_sock_destruct() during socket close. To fix this decrease skb refcount by one if MSG_PEEK is set in order to prevent memory leak and WARN_ON. WARNING: CPU: 2 PID: 6292 at net/iucv/af_iucv.c:286 iucv_sock_destruct+0x144/0x1a0 [af_iucv] CPU: 2 PID: 6292 Comm: afiucv_test_msg Kdump: loaded Tainted: G W 6.10.0-rc7 #1 Hardware name: IBM 3931 A01 704 (z/VM 7.3.0) Call Trace: [<001587c682c4aa98>] iucv_sock_destruct+0x148/0x1a0 [af_iucv] [<001587c682c4a9d0>] iucv_sock_destruct+0x80/0x1a0 [af_iucv] [<001587c704117a32>] __sk_destruct+0x52/0x550 [<001587c704104a54>] __sock_release+0xa4/0x230 [<001587c704104c0c>] sock_close+0x2c/0x40 [<001587c702c5f5a8>] __fput+0x2e8/0x970 [<001587c7024148c4>] task_work_run+0x1c4/0x2c0 [<001587c7023b0716>] do_exit+0x996/0x1050 [<001587c7023b13aa>] do_group_exit+0x13a/0x360 [<001587c7023b1626>] __s390x_sys_exit_group+0x56/0x60 [<001587c7022bccca>] do_syscall+0x27a/0x380 [<001587c7049a6a0c>] __do_syscall+0x9c/0x160 [<001587c7049ce8a8>] system_call+0x70/0x98 Last Breaking-Event-Address: [<001587c682c4a9d4>] iucv_sock_destruct+0x84/0x1a0 [af_iucv]
CVE-2024-53213: In the Linux kernel, the following vulnerability has been resolved: net: usb: lan78xx: Fix double free issue with interrupt buffer allocation In lan78xx_probe(), the buffer `buf` was being freed twice: once implicitly through `usb_free_urb(dev->urb_intr)` with the `URB_FREE_BUFFER` flag and again explicitly by `kfree(buf)`. This caused a double free issue. To resolve this, reordered `kmalloc()` and `usb_alloc_urb()` calls to simplify the initialization sequence and removed the redundant `kfree(buf)`. Now, `buf` is allocated after `usb_alloc_urb()`, ensuring it is correctly managed by `usb_fill_int_urb()` and freed by `usb_free_urb()` as intended.
CVE-2024-53216: In the Linux kernel, the following vulnerability has been resolved: nfsd: release svc_expkey/svc_export with rcu_work The last reference for `cache_head` can be reduced to zero in `c_show` and `e_show`(using `rcu_read_lock` and `rcu_read_unlock`). Consequently, `svc_export_put` and `expkey_put` will be invoked, leading to two issues: 1. The `svc_export_put` will directly free ex_uuid. However, `e_show`/`c_show` will access `ex_uuid` after `cache_put`, which can trigger a use-after-free issue, shown below. ================================================================== BUG: KASAN: slab-use-after-free in svc_export_show+0x362/0x430 [nfsd] Read of size 1 at addr ff11000010fdc120 by task cat/870 CPU: 1 UID: 0 PID: 870 Comm: cat Not tainted 6.12.0-rc3+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x2c/0x3a0 print_report+0xb9/0x280 kasan_report+0xae/0xe0 svc_export_show+0x362/0x430 [nfsd] c_show+0x161/0x390 [sunrpc] seq_read_iter+0x589/0x770 seq_read+0x1e5/0x270 proc_reg_read+0xe1/0x140 vfs_read+0x125/0x530 ksys_read+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 830: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 __kmalloc_node_track_caller_noprof+0x1bc/0x400 kmemdup_noprof+0x22/0x50 svc_export_parse+0x8a9/0xb80 [nfsd] cache_do_downcall+0x71/0xa0 [sunrpc] cache_write_procfs+0x8e/0xd0 [sunrpc] proc_reg_write+0xe1/0x140 vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 868: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x37/0x50 kfree+0xf3/0x3e0 svc_export_put+0x87/0xb0 [nfsd] cache_purge+0x17f/0x1f0 [sunrpc] nfsd_destroy_serv+0x226/0x2d0 [nfsd] nfsd_svc+0x125/0x1e0 [nfsd] write_threads+0x16a/0x2a0 [nfsd] nfsctl_transaction_write+0x74/0xa0 [nfsd] vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e 2. We cannot sleep while using `rcu_read_lock`/`rcu_read_unlock`. However, `svc_export_put`/`expkey_put` will call path_put, which subsequently triggers a sleeping operation due to the following `dput`. ============================= WARNING: suspicious RCU usage 5.10.0-dirty #141 Not tainted ----------------------------- ... Call Trace: dump_stack+0x9a/0xd0 ___might_sleep+0x231/0x240 dput+0x39/0x600 path_put+0x1b/0x30 svc_export_put+0x17/0x80 e_show+0x1c9/0x200 seq_read_iter+0x63f/0x7c0 seq_read+0x226/0x2d0 vfs_read+0x113/0x2c0 ksys_read+0xc9/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 Fix these issues by using `rcu_work` to help release `svc_expkey`/`svc_export`. This approach allows for an asynchronous context to invoke `path_put` and also facilitates the freeing of `uuid/exp/key` after an RCU grace period.
CVE-2024-53218: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix race in concurrent f2fs_stop_gc_thread In my test case, concurrent calls to f2fs shutdown report the following stack trace: Oops: general protection fault, probably for non-canonical address 0xc6cfff63bb5513fc: 0000 [#1] PREEMPT SMP PTI CPU: 0 UID: 0 PID: 678 Comm: f2fs_rep_shutdo Not tainted 6.12.0-rc5-next-20241029-g6fb2fa9805c5-dirty #85 Call Trace: <TASK> ? show_regs+0x8b/0xa0 ? __die_body+0x26/0xa0 ? die_addr+0x54/0x90 ? exc_general_protection+0x24b/0x5c0 ? asm_exc_general_protection+0x26/0x30 ? kthread_stop+0x46/0x390 f2fs_stop_gc_thread+0x6c/0x110 f2fs_do_shutdown+0x309/0x3a0 f2fs_ioc_shutdown+0x150/0x1c0 __f2fs_ioctl+0xffd/0x2ac0 f2fs_ioctl+0x76/0xe0 vfs_ioctl+0x23/0x60 __x64_sys_ioctl+0xce/0xf0 x64_sys_call+0x2b1b/0x4540 do_syscall_64+0xa7/0x240 entry_SYSCALL_64_after_hwframe+0x76/0x7e The root cause is a race condition in f2fs_stop_gc_thread() called from different f2fs shutdown paths: [CPU0] [CPU1] ---------------------- ----------------------- f2fs_stop_gc_thread f2fs_stop_gc_thread gc_th = sbi->gc_thread gc_th = sbi->gc_thread kfree(gc_th) sbi->gc_thread = NULL < gc_th != NULL > kthread_stop(gc_th->f2fs_gc_task) //UAF The commit c7f114d864ac ("f2fs: fix to avoid use-after-free in f2fs_stop_gc_thread()") attempted to fix this issue by using a read semaphore to prevent races between shutdown and remount threads, but it fails to prevent all race conditions. Fix it by converting to write lock of s_umount in f2fs_do_shutdown().
CVE-2024-53219: In the Linux kernel, the following vulnerability has been resolved: virtiofs: use pages instead of pointer for kernel direct IO When trying to insert a 10MB kernel module kept in a virtio-fs with cache disabled, the following warning was reported: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 404 at mm/page_alloc.c:4551 ...... Modules linked in: CPU: 1 PID: 404 Comm: insmod Not tainted 6.9.0-rc5+ #123 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ...... RIP: 0010:__alloc_pages+0x2bf/0x380 ...... Call Trace: <TASK> ? __warn+0x8e/0x150 ? __alloc_pages+0x2bf/0x380 __kmalloc_large_node+0x86/0x160 __kmalloc+0x33c/0x480 virtio_fs_enqueue_req+0x240/0x6d0 virtio_fs_wake_pending_and_unlock+0x7f/0x190 queue_request_and_unlock+0x55/0x60 fuse_simple_request+0x152/0x2b0 fuse_direct_io+0x5d2/0x8c0 fuse_file_read_iter+0x121/0x160 __kernel_read+0x151/0x2d0 kernel_read+0x45/0x50 kernel_read_file+0x1a9/0x2a0 init_module_from_file+0x6a/0xe0 idempotent_init_module+0x175/0x230 __x64_sys_finit_module+0x5d/0xb0 x64_sys_call+0x1c3/0x9e0 do_syscall_64+0x3d/0xc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ...... </TASK> ---[ end trace 0000000000000000 ]--- The warning is triggered as follows: 1) syscall finit_module() handles the module insertion and it invokes kernel_read_file() to read the content of the module first. 2) kernel_read_file() allocates a 10MB buffer by using vmalloc() and passes it to kernel_read(). kernel_read() constructs a kvec iter by using iov_iter_kvec() and passes it to fuse_file_read_iter(). 3) virtio-fs disables the cache, so fuse_file_read_iter() invokes fuse_direct_io(). As for now, the maximal read size for kvec iter is only limited by fc->max_read. For virtio-fs, max_read is UINT_MAX, so fuse_direct_io() doesn't split the 10MB buffer. It saves the address and the size of the 10MB-sized buffer in out_args[0] of a fuse request and passes the fuse request to virtio_fs_wake_pending_and_unlock(). 4) virtio_fs_wake_pending_and_unlock() uses virtio_fs_enqueue_req() to queue the request. Because virtiofs need DMA-able address, so virtio_fs_enqueue_req() uses kmalloc() to allocate a bounce buffer for all fuse args, copies these args into the bounce buffer and passed the physical address of the bounce buffer to virtiofsd. The total length of these fuse args for the passed fuse request is about 10MB, so copy_args_to_argbuf() invokes kmalloc() with a 10MB size parameter and it triggers the warning in __alloc_pages(): if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)) return NULL; 5) virtio_fs_enqueue_req() will retry the memory allocation in a kworker, but it won't help, because kmalloc() will always return NULL due to the abnormal size and finit_module() will hang forever. A feasible solution is to limit the value of max_read for virtio-fs, so the length passed to kmalloc() will be limited. However it will affect the maximal read size for normal read. And for virtio-fs write initiated from kernel, it has the similar problem but now there is no way to limit fc->max_write in kernel. So instead of limiting both the values of max_read and max_write in kernel, introducing use_pages_for_kvec_io in fuse_conn and setting it as true in virtiofs. When use_pages_for_kvec_io is enabled, fuse will use pages instead of pointer to pass the KVEC_IO data. After switching to pages for KVEC_IO data, these pages will be used for DMA through virtio-fs. If these pages are backed by vmalloc(), {flush|invalidate}_kernel_vmap_range() are necessary to flush or invalidate the cache before the DMA operation. So add two new fields in fuse_args_pages to record the base address of vmalloc area and the condition indicating whether invalidation is needed. Perform the flush in fuse_get_user_pages() for write operations and the invalidation in fuse_release_user_pages() for read operations. It may seem necessary to introduce another fie ---truncated---
CVE-2024-53220: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to account dirty data in __get_secs_required() It will trigger system panic w/ testcase in [1]: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2752! RIP: 0010:new_curseg+0xc81/0x2110 Call Trace: f2fs_allocate_data_block+0x1c91/0x4540 do_write_page+0x163/0xdf0 f2fs_outplace_write_data+0x1aa/0x340 f2fs_do_write_data_page+0x797/0x2280 f2fs_write_single_data_page+0x16cd/0x2190 f2fs_write_cache_pages+0x994/0x1c80 f2fs_write_data_pages+0x9cc/0xea0 do_writepages+0x194/0x7a0 filemap_fdatawrite_wbc+0x12b/0x1a0 __filemap_fdatawrite_range+0xbb/0xf0 file_write_and_wait_range+0xa1/0x110 f2fs_do_sync_file+0x26f/0x1c50 f2fs_sync_file+0x12b/0x1d0 vfs_fsync_range+0xfa/0x230 do_fsync+0x3d/0x80 __x64_sys_fsync+0x37/0x50 x64_sys_call+0x1e88/0x20d0 do_syscall_64+0x4b/0x110 entry_SYSCALL_64_after_hwframe+0x76/0x7e The root cause is if checkpoint_disabling and lfs_mode are both on, it will trigger OPU for all overwritten data, it may cost more free segment than expected, so f2fs must account those data correctly to calculate cosumed free segments later, and return ENOSPC earlier to avoid run out of free segment during block allocation. [1] https://lore.kernel.org/fstests/20241015025106.3203676-1-chao@kernel.org/
CVE-2024-53221: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix null-ptr-deref in f2fs_submit_page_bio() There's issue as follows when concurrently installing the f2fs.ko module and mounting the f2fs file system: KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] RIP: 0010:__bio_alloc+0x2fb/0x6c0 [f2fs] Call Trace: <TASK> f2fs_submit_page_bio+0x126/0x8b0 [f2fs] __get_meta_page+0x1d4/0x920 [f2fs] get_checkpoint_version.constprop.0+0x2b/0x3c0 [f2fs] validate_checkpoint+0xac/0x290 [f2fs] f2fs_get_valid_checkpoint+0x207/0x950 [f2fs] f2fs_fill_super+0x1007/0x39b0 [f2fs] mount_bdev+0x183/0x250 legacy_get_tree+0xf4/0x1e0 vfs_get_tree+0x88/0x340 do_new_mount+0x283/0x5e0 path_mount+0x2b2/0x15b0 __x64_sys_mount+0x1fe/0x270 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Above issue happens as the biset of the f2fs file system is not initialized before register "f2fs_fs_type". To address above issue just register "f2fs_fs_type" at the last in init_f2fs_fs(). Ensure that all f2fs file system resources are initialized.
CVE-2024-53224: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Move events notifier registration to be after device registration Move pkey change work initialization and cleanup from device resources stage to notifier stage, since this is the stage which handles this work events. Fix a race between the device deregistration and pkey change work by moving MLX5_IB_STAGE_DEVICE_NOTIFIER to be after MLX5_IB_STAGE_IB_REG in order to ensure that the notifier is deregistered before the device during cleanup. Which ensures there are no works that are being executed after the device has already unregistered which can cause the panic below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 630071 Comm: kworker/1:2 Kdump: loaded Tainted: G W OE --------- --- 5.14.0-162.6.1.el9_1.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 02/27/2023 Workqueue: events pkey_change_handler [mlx5_ib] RIP: 0010:setup_qp+0x38/0x1f0 [mlx5_ib] Code: ee 41 54 45 31 e4 55 89 f5 53 48 89 fb 48 83 ec 20 8b 77 08 65 48 8b 04 25 28 00 00 00 48 89 44 24 18 48 8b 07 48 8d 4c 24 16 <4c> 8b 38 49 8b 87 80 0b 00 00 4c 89 ff 48 8b 80 08 05 00 00 8b 40 RSP: 0018:ffffbcc54068be20 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff954054494128 RCX: ffffbcc54068be36 RDX: ffff954004934000 RSI: 0000000000000001 RDI: ffff954054494128 RBP: 0000000000000023 R08: ffff954001be2c20 R09: 0000000000000001 R10: ffff954001be2c20 R11: ffff9540260133c0 R12: 0000000000000000 R13: 0000000000000023 R14: 0000000000000000 R15: ffff9540ffcb0905 FS: 0000000000000000(0000) GS:ffff9540ffc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000010625c001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_ib_gsi_pkey_change+0x20/0x40 [mlx5_ib] process_one_work+0x1e8/0x3c0 worker_thread+0x50/0x3b0 ? rescuer_thread+0x380/0x380 kthread+0x149/0x170 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Modules linked in: rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) mlx5_fwctl(OE) fwctl(OE) ib_uverbs(OE) mlx5_core(OE) mlxdevm(OE) ib_core(OE) mlx_compat(OE) psample mlxfw(OE) tls knem(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache netfs qrtr rfkill sunrpc intel_rapl_msr intel_rapl_common rapl hv_balloon hv_utils i2c_piix4 pcspkr joydev fuse ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ata_generic pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper drm_kms_helper hv_storvsc syscopyarea hv_netvsc sysfillrect sysimgblt hid_hyperv fb_sys_fops scsi_transport_fc hyperv_keyboard drm ata_piix crct10dif_pclmul crc32_pclmul crc32c_intel libata ghash_clmulni_intel hv_vmbus serio_raw [last unloaded: ib_core] CR2: 0000000000000000 ---[ end trace f6f8be4eae12f7bc ]---
CVE-2024-53234: In the Linux kernel, the following vulnerability has been resolved: erofs: handle NONHEAD !delta[1] lclusters gracefully syzbot reported a WARNING in iomap_iter_done: iomap_fiemap+0x73b/0x9b0 fs/iomap/fiemap.c:80 ioctl_fiemap fs/ioctl.c:220 [inline] Generally, NONHEAD lclusters won't have delta[1]==0, except for crafted images and filesystems created by pre-1.0 mkfs versions. Previously, it would immediately bail out if delta[1]==0, which led to inadequate decompressed lengths (thus FIEMAP is impacted). Treat it as delta[1]=1 to work around these legacy mkfs versions. `lclusterbits > 14` is illegal for compact indexes, error out too.
CVE-2024-54683: In the Linux kernel, the following vulnerability has been resolved: netfilter: IDLETIMER: Fix for possible ABBA deadlock Deletion of the last rule referencing a given idletimer may happen at the same time as a read of its file in sysfs: | ====================================================== | WARNING: possible circular locking dependency detected | 6.12.0-rc7-01692-g5e9a28f41134-dirty #594 Not tainted | ------------------------------------------------------ | iptables/3303 is trying to acquire lock: | ffff8881057e04b8 (kn->active#48){++++}-{0:0}, at: __kernfs_remove+0x20 | | but task is already holding lock: | ffffffffa0249068 (list_mutex){+.+.}-{3:3}, at: idletimer_tg_destroy_v] | | which lock already depends on the new lock. A simple reproducer is: | #!/bin/bash | | while true; do | iptables -A INPUT -i foo -j IDLETIMER --timeout 10 --label "testme" | iptables -D INPUT -i foo -j IDLETIMER --timeout 10 --label "testme" | done & | while true; do | cat /sys/class/xt_idletimer/timers/testme >/dev/null | done Avoid this by freeing list_mutex right after deleting the element from the list, then continuing with the teardown.
CVE-2024-56369: In the Linux kernel, the following vulnerability has been resolved: drm/modes: Avoid divide by zero harder in drm_mode_vrefresh() drm_mode_vrefresh() is trying to avoid divide by zero by checking whether htotal or vtotal are zero. But we may still end up with a div-by-zero of vtotal*htotal*...
CVE-2024-56538: In the Linux kernel, the following vulnerability has been resolved: drm: zynqmp_kms: Unplug DRM device before removal Prevent userspace accesses to the DRM device from causing use-after-frees by unplugging the device before we remove it. This causes any further userspace accesses to result in an error without further calls into this driver's internals.
CVE-2024-56544: In the Linux kernel, the following vulnerability has been resolved: udmabuf: change folios array from kmalloc to kvmalloc When PAGE_SIZE 4096, MAX_PAGE_ORDER 10, 64bit machine, page_alloc only support 4MB. If above this, trigger this warn and return NULL. udmabuf can change size limit, if change it to 3072(3GB), and then alloc 3GB udmabuf, will fail create. [ 4080.876581] ------------[ cut here ]------------ [ 4080.876843] WARNING: CPU: 3 PID: 2015 at mm/page_alloc.c:4556 __alloc_pages+0x2c8/0x350 [ 4080.878839] RIP: 0010:__alloc_pages+0x2c8/0x350 [ 4080.879470] Call Trace: [ 4080.879473] <TASK> [ 4080.879473] ? __alloc_pages+0x2c8/0x350 [ 4080.879475] ? __warn.cold+0x8e/0xe8 [ 4080.880647] ? __alloc_pages+0x2c8/0x350 [ 4080.880909] ? report_bug+0xff/0x140 [ 4080.881175] ? handle_bug+0x3c/0x80 [ 4080.881556] ? exc_invalid_op+0x17/0x70 [ 4080.881559] ? asm_exc_invalid_op+0x1a/0x20 [ 4080.882077] ? udmabuf_create+0x131/0x400 Because MAX_PAGE_ORDER, kmalloc can max alloc 4096 * (1 << 10), 4MB memory, each array entry is pointer(8byte), so can save 524288 pages(2GB). Further more, costly order(order 3) may not be guaranteed that it can be applied for, due to fragmentation. This patch change udmabuf array use kvmalloc_array, this can fallback alloc into vmalloc, which can guarantee allocation for any size and does not affect the performance of kmalloc allocations.
CVE-2024-56551: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix usage slab after free [ +0.000021] BUG: KASAN: slab-use-after-free in drm_sched_entity_flush+0x6cb/0x7a0 [gpu_sched] [ +0.000027] Read of size 8 at addr ffff8881b8605f88 by task amd_pci_unplug/2147 [ +0.000023] CPU: 6 PID: 2147 Comm: amd_pci_unplug Not tainted 6.10.0+ #1 [ +0.000016] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.000016] Call Trace: [ +0.000008] <TASK> [ +0.000009] dump_stack_lvl+0x76/0xa0 [ +0.000017] print_report+0xce/0x5f0 [ +0.000017] ? drm_sched_entity_flush+0x6cb/0x7a0 [gpu_sched] [ +0.000019] ? srso_return_thunk+0x5/0x5f [ +0.000015] ? kasan_complete_mode_report_info+0x72/0x200 [ +0.000016] ? drm_sched_entity_flush+0x6cb/0x7a0 [gpu_sched] [ +0.000019] kasan_report+0xbe/0x110 [ +0.000015] ? drm_sched_entity_flush+0x6cb/0x7a0 [gpu_sched] [ +0.000023] __asan_report_load8_noabort+0x14/0x30 [ +0.000014] drm_sched_entity_flush+0x6cb/0x7a0 [gpu_sched] [ +0.000020] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? __kasan_check_write+0x14/0x30 [ +0.000016] ? __pfx_drm_sched_entity_flush+0x10/0x10 [gpu_sched] [ +0.000020] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? __kasan_check_write+0x14/0x30 [ +0.000013] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? enable_work+0x124/0x220 [ +0.000015] ? __pfx_enable_work+0x10/0x10 [ +0.000013] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? free_large_kmalloc+0x85/0xf0 [ +0.000016] drm_sched_entity_destroy+0x18/0x30 [gpu_sched] [ +0.000020] amdgpu_vce_sw_fini+0x55/0x170 [amdgpu] [ +0.000735] ? __kasan_check_read+0x11/0x20 [ +0.000016] vce_v4_0_sw_fini+0x80/0x110 [amdgpu] [ +0.000726] amdgpu_device_fini_sw+0x331/0xfc0 [amdgpu] [ +0.000679] ? mutex_unlock+0x80/0xe0 [ +0.000017] ? __pfx_amdgpu_device_fini_sw+0x10/0x10 [amdgpu] [ +0.000662] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? __kasan_check_write+0x14/0x30 [ +0.000013] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? mutex_unlock+0x80/0xe0 [ +0.000016] amdgpu_driver_release_kms+0x16/0x80 [amdgpu] [ +0.000663] drm_minor_release+0xc9/0x140 [drm] [ +0.000081] drm_release+0x1fd/0x390 [drm] [ +0.000082] __fput+0x36c/0xad0 [ +0.000018] __fput_sync+0x3c/0x50 [ +0.000014] __x64_sys_close+0x7d/0xe0 [ +0.000014] x64_sys_call+0x1bc6/0x2680 [ +0.000014] do_syscall_64+0x70/0x130 [ +0.000014] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? irqentry_exit_to_user_mode+0x60/0x190 [ +0.000015] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? irqentry_exit+0x43/0x50 [ +0.000012] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? exc_page_fault+0x7c/0x110 [ +0.000015] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ +0.000014] RIP: 0033:0x7ffff7b14f67 [ +0.000013] Code: ff e8 0d 16 02 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 73 ba f7 ff [ +0.000026] RSP: 002b:00007fffffffe378 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 [ +0.000019] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffff7b14f67 [ +0.000014] RDX: 0000000000000000 RSI: 00007ffff7f6f47a RDI: 0000000000000003 [ +0.000014] RBP: 00007fffffffe3a0 R08: 0000555555569890 R09: 0000000000000000 [ +0.000014] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fffffffe5c8 [ +0.000013] R13: 00005555555552a9 R14: 0000555555557d48 R15: 00007ffff7ffd040 [ +0.000020] </TASK> [ +0.000016] Allocated by task 383 on cpu 7 at 26.880319s: [ +0.000014] kasan_save_stack+0x28/0x60 [ +0.000008] kasan_save_track+0x18/0x70 [ +0.000007] kasan_save_alloc_info+0x38/0x60 [ +0.000007] __kasan_kmalloc+0xc1/0xd0 [ +0.000007] kmalloc_trace_noprof+0x180/0x380 [ +0.000007] drm_sched_init+0x411/0xec0 [gpu_sched] [ +0.000012] amdgpu_device_init+0x695f/0xa610 [amdgpu] [ +0.000658] amdgpu_driver_load_kms+0x1a/0x120 [amdgpu] [ +0.000662] amdgpu_pci_p ---truncated---
CVE-2024-56557: In the Linux kernel, the following vulnerability has been resolved: iio: adc: ad7923: Fix buffer overflow for tx_buf and ring_xfer The AD7923 was updated to support devices with 8 channels, but the size of tx_buf and ring_xfer was not increased accordingly, leading to a potential buffer overflow in ad7923_update_scan_mode().
CVE-2024-56565: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to drop all discards after creating snapshot on lvm device Piergiorgio reported a bug in bugzilla as below: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 969 at fs/f2fs/segment.c:1330 RIP: 0010:__submit_discard_cmd+0x27d/0x400 [f2fs] Call Trace: __issue_discard_cmd+0x1ca/0x350 [f2fs] issue_discard_thread+0x191/0x480 [f2fs] kthread+0xcf/0x100 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x1a/0x30 w/ below testcase, it can reproduce this bug quickly: - pvcreate /dev/vdb - vgcreate myvg1 /dev/vdb - lvcreate -L 1024m -n mylv1 myvg1 - mount /dev/myvg1/mylv1 /mnt/f2fs - dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=20 - sync - rm /mnt/f2fs/file - sync - lvcreate -L 1024m -s -n mylv1-snapshot /dev/myvg1/mylv1 - umount /mnt/f2fs The root cause is: it will update discard_max_bytes of mounted lvm device to zero after creating snapshot on this lvm device, then, __submit_discard_cmd() will pass parameter @nr_sects w/ zero value to __blkdev_issue_discard(), it returns a NULL bio pointer, result in panic. This patch changes as below for fixing: 1. Let's drop all remained discards in f2fs_unfreeze() if snapshot of lvm device is created. 2. Checking discard_max_bytes before submitting discard during __submit_discard_cmd().
CVE-2024-56566: In the Linux kernel, the following vulnerability has been resolved: mm/slub: Avoid list corruption when removing a slab from the full list Boot with slub_debug=UFPZ. If allocated object failed in alloc_consistency_checks, all objects of the slab will be marked as used, and then the slab will be removed from the partial list. When an object belonging to the slab got freed later, the remove_full() function is called. Because the slab is neither on the partial list nor on the full list, it eventually lead to a list corruption (actually a list poison being detected). So we need to mark and isolate the slab page with metadata corruption, do not put it back in circulation. Because the debug caches avoid all the fastpaths, reusing the frozen bit to mark slab page with metadata corruption seems to be fine. [ 4277.385669] list_del corruption, ffffea00044b3e50->next is LIST_POISON1 (dead000000000100) [ 4277.387023] ------------[ cut here ]------------ [ 4277.387880] kernel BUG at lib/list_debug.c:56! [ 4277.388680] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 4277.389562] CPU: 5 PID: 90 Comm: kworker/5:1 Kdump: loaded Tainted: G OE 6.6.1-1 #1 [ 4277.392113] Workqueue: xfs-inodegc/vda1 xfs_inodegc_worker [xfs] [ 4277.393551] RIP: 0010:__list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.394518] Code: 48 91 82 e8 37 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 28 49 91 82 e8 26 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 58 49 91 [ 4277.397292] RSP: 0018:ffffc90000333b38 EFLAGS: 00010082 [ 4277.398202] RAX: 000000000000004e RBX: ffffea00044b3e50 RCX: 0000000000000000 [ 4277.399340] RDX: 0000000000000002 RSI: ffffffff828f8715 RDI: 00000000ffffffff [ 4277.400545] RBP: ffffea00044b3e40 R08: 0000000000000000 R09: ffffc900003339f0 [ 4277.401710] R10: 0000000000000003 R11: ffffffff82d44088 R12: ffff888112cf9910 [ 4277.402887] R13: 0000000000000001 R14: 0000000000000001 R15: ffff8881000424c0 [ 4277.404049] FS: 0000000000000000(0000) GS:ffff88842fd40000(0000) knlGS:0000000000000000 [ 4277.405357] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4277.406389] CR2: 00007f2ad0b24000 CR3: 0000000102a3a006 CR4: 00000000007706e0 [ 4277.407589] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4277.408780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4277.410000] PKRU: 55555554 [ 4277.410645] Call Trace: [ 4277.411234] <TASK> [ 4277.411777] ? die+0x32/0x80 [ 4277.412439] ? do_trap+0xd6/0x100 [ 4277.413150] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.414158] ? do_error_trap+0x6a/0x90 [ 4277.414948] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.415915] ? exc_invalid_op+0x4c/0x60 [ 4277.416710] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.417675] ? asm_exc_invalid_op+0x16/0x20 [ 4277.418482] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.419466] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.420410] free_to_partial_list+0x515/0x5e0 [ 4277.421242] ? xfs_iext_remove+0x41a/0xa10 [xfs] [ 4277.422298] xfs_iext_remove+0x41a/0xa10 [xfs] [ 4277.423316] ? xfs_inodegc_worker+0xb4/0x1a0 [xfs] [ 4277.424383] xfs_bmap_del_extent_delay+0x4fe/0x7d0 [xfs] [ 4277.425490] __xfs_bunmapi+0x50d/0x840 [xfs] [ 4277.426445] xfs_itruncate_extents_flags+0x13a/0x490 [xfs] [ 4277.427553] xfs_inactive_truncate+0xa3/0x120 [xfs] [ 4277.428567] xfs_inactive+0x22d/0x290 [xfs] [ 4277.429500] xfs_inodegc_worker+0xb4/0x1a0 [xfs] [ 4277.430479] process_one_work+0x171/0x340 [ 4277.431227] worker_thread+0x277/0x390 [ 4277.431962] ? __pfx_worker_thread+0x10/0x10 [ 4277.432752] kthread+0xf0/0x120 [ 4277.433382] ? __pfx_kthread+0x10/0x10 [ 4277.434134] ret_from_fork+0x2d/0x50 [ 4277.434837] ? __pfx_kthread+0x10/0x10 [ 4277.435566] ret_from_fork_asm+0x1b/0x30 [ 4277.436280] </TASK>
CVE-2024-56583: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix warning in migrate_enable for boosted tasks When running the following command: while true; do stress-ng --cyclic 30 --timeout 30s --minimize --quiet done a warning is eventually triggered: WARNING: CPU: 43 PID: 2848 at kernel/sched/deadline.c:794 setup_new_dl_entity+0x13e/0x180 ... Call Trace: <TASK> ? show_trace_log_lvl+0x1c4/0x2df ? enqueue_dl_entity+0x631/0x6e0 ? setup_new_dl_entity+0x13e/0x180 ? __warn+0x7e/0xd0 ? report_bug+0x11a/0x1a0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 enqueue_dl_entity+0x631/0x6e0 enqueue_task_dl+0x7d/0x120 __do_set_cpus_allowed+0xe3/0x280 __set_cpus_allowed_ptr_locked+0x140/0x1d0 __set_cpus_allowed_ptr+0x54/0xa0 migrate_enable+0x7e/0x150 rt_spin_unlock+0x1c/0x90 group_send_sig_info+0xf7/0x1a0 ? kill_pid_info+0x1f/0x1d0 kill_pid_info+0x78/0x1d0 kill_proc_info+0x5b/0x110 __x64_sys_kill+0x93/0xc0 do_syscall_64+0x5c/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7f0dab31f92b This warning occurs because set_cpus_allowed dequeues and enqueues tasks with the ENQUEUE_RESTORE flag set. If the task is boosted, the warning is triggered. A boosted task already had its parameters set by rt_mutex_setprio, and a new call to setup_new_dl_entity is unnecessary, hence the WARN_ON call. Check if we are requeueing a boosted task and avoid calling setup_new_dl_entity if that's the case.
CVE-2024-56584: In the Linux kernel, the following vulnerability has been resolved: io_uring/tctx: work around xa_store() allocation error issue syzbot triggered the following WARN_ON: WARNING: CPU: 0 PID: 16 at io_uring/tctx.c:51 __io_uring_free+0xfa/0x140 io_uring/tctx.c:51 which is the WARN_ON_ONCE(!xa_empty(&tctx->xa)); sanity check in __io_uring_free() when a io_uring_task is going through its final put. The syzbot test case includes injecting memory allocation failures, and it very much looks like xa_store() can fail one of its memory allocations and end up with ->head being non-NULL even though no entries exist in the xarray. Until this issue gets sorted out, work around it by attempting to iterate entries in our xarray, and WARN_ON_ONCE() if one is found.
CVE-2024-56588: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Create all dump files during debugfs initialization For the current debugfs of hisi_sas, after user triggers dump, the driver allocate memory space to save the register information and create debugfs files to display the saved information. In this process, the debugfs files created after each dump. Therefore, when the dump is triggered while the driver is unbind, the following hang occurs: [67840.853907] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0 [67840.862947] Mem abort info: [67840.865855] ESR = 0x0000000096000004 [67840.869713] EC = 0x25: DABT (current EL), IL = 32 bits [67840.875125] SET = 0, FnV = 0 [67840.878291] EA = 0, S1PTW = 0 [67840.881545] FSC = 0x04: level 0 translation fault [67840.886528] Data abort info: [67840.889524] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [67840.895117] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [67840.900284] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [67840.905709] user pgtable: 4k pages, 48-bit VAs, pgdp=0000002803a1f000 [67840.912263] [00000000000000a0] pgd=0000000000000000, p4d=0000000000000000 [67840.919177] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [67840.996435] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [67841.003628] pc : down_write+0x30/0x98 [67841.007546] lr : start_creating.part.0+0x60/0x198 [67841.012495] sp : ffff8000b979ba20 [67841.016046] x29: ffff8000b979ba20 x28: 0000000000000010 x27: 0000000000024b40 [67841.023412] x26: 0000000000000012 x25: ffff20202b355ae8 x24: ffff20202b35a8c8 [67841.030779] x23: ffffa36877928208 x22: ffffa368b4972240 x21: ffff8000b979bb18 [67841.038147] x20: ffff00281dc1e3c0 x19: fffffffffffffffe x18: 0000000000000020 [67841.045515] x17: 0000000000000000 x16: ffffa368b128a530 x15: ffffffffffffffff [67841.052888] x14: ffff8000b979bc18 x13: ffffffffffffffff x12: ffff8000b979bb18 [67841.060263] x11: 0000000000000000 x10: 0000000000000000 x9 : ffffa368b1289b18 [67841.067640] x8 : 0000000000000012 x7 : 0000000000000000 x6 : 00000000000003a9 [67841.075014] x5 : 0000000000000000 x4 : ffff002818c5cb00 x3 : 0000000000000001 [67841.082388] x2 : 0000000000000000 x1 : ffff002818c5cb00 x0 : 00000000000000a0 [67841.089759] Call trace: [67841.092456] down_write+0x30/0x98 [67841.096017] start_creating.part.0+0x60/0x198 [67841.100613] debugfs_create_dir+0x48/0x1f8 [67841.104950] debugfs_create_files_v3_hw+0x88/0x348 [hisi_sas_v3_hw] [67841.111447] debugfs_snapshot_regs_v3_hw+0x708/0x798 [hisi_sas_v3_hw] [67841.118111] debugfs_trigger_dump_v3_hw_write+0x9c/0x120 [hisi_sas_v3_hw] [67841.125115] full_proxy_write+0x68/0xc8 [67841.129175] vfs_write+0xd8/0x3f0 [67841.132708] ksys_write+0x70/0x108 [67841.136317] __arm64_sys_write+0x24/0x38 [67841.140440] invoke_syscall+0x50/0x128 [67841.144385] el0_svc_common.constprop.0+0xc8/0xf0 [67841.149273] do_el0_svc+0x24/0x38 [67841.152773] el0_svc+0x38/0xd8 [67841.156009] el0t_64_sync_handler+0xc0/0xc8 [67841.160361] el0t_64_sync+0x1a4/0x1a8 [67841.164189] Code: b9000882 d2800002 d2800023 f9800011 (c85ffc05) [67841.170443] ---[ end trace 0000000000000000 ]--- To fix this issue, create all directories and files during debugfs initialization. In this way, the driver only needs to allocate memory space to save information each time the user triggers dumping.
CVE-2024-56590: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: Fix not checking skb length on hci_acldata_packet This fixes not checking if skb really contains an ACL header otherwise the code may attempt to access some uninitilized/invalid memory past the valid skb->data.
CVE-2024-56591: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: Use disable_delayed_work_sync This makes use of disable_delayed_work_sync instead cancel_delayed_work_sync as it not only cancel the ongoing work but also disables new submit which is disarable since the object holding the work is about to be freed.
CVE-2024-56592: In the Linux kernel, the following vulnerability has been resolved: bpf: Call free_htab_elem() after htab_unlock_bucket() For htab of maps, when the map is removed from the htab, it may hold the last reference of the map. bpf_map_fd_put_ptr() will invoke bpf_map_free_id() to free the id of the removed map element. However, bpf_map_fd_put_ptr() is invoked while holding a bucket lock (raw_spin_lock_t), and bpf_map_free_id() attempts to acquire map_idr_lock (spinlock_t), triggering the following lockdep warning: ============================= [ BUG: Invalid wait context ] 6.11.0-rc4+ #49 Not tainted ----------------------------- test_maps/4881 is trying to lock: ffffffff84884578 (map_idr_lock){+...}-{3:3}, at: bpf_map_free_id.part.0+0x21/0x70 other info that might help us debug this: context-{5:5} 2 locks held by test_maps/4881: #0: ffffffff846caf60 (rcu_read_lock){....}-{1:3}, at: bpf_fd_htab_map_update_elem+0xf9/0x270 #1: ffff888149ced148 (&htab->lockdep_key#2){....}-{2:2}, at: htab_map_update_elem+0x178/0xa80 stack backtrace: CPU: 0 UID: 0 PID: 4881 Comm: test_maps Not tainted 6.11.0-rc4+ #49 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ... Call Trace: <TASK> dump_stack_lvl+0x6e/0xb0 dump_stack+0x10/0x20 __lock_acquire+0x73e/0x36c0 lock_acquire+0x182/0x450 _raw_spin_lock_irqsave+0x43/0x70 bpf_map_free_id.part.0+0x21/0x70 bpf_map_put+0xcf/0x110 bpf_map_fd_put_ptr+0x9a/0xb0 free_htab_elem+0x69/0xe0 htab_map_update_elem+0x50f/0xa80 bpf_fd_htab_map_update_elem+0x131/0x270 htab_map_update_elem+0x50f/0xa80 bpf_fd_htab_map_update_elem+0x131/0x270 bpf_map_update_value+0x266/0x380 __sys_bpf+0x21bb/0x36b0 __x64_sys_bpf+0x45/0x60 x64_sys_call+0x1b2a/0x20d0 do_syscall_64+0x5d/0x100 entry_SYSCALL_64_after_hwframe+0x76/0x7e One way to fix the lockdep warning is using raw_spinlock_t for map_idr_lock as well. However, bpf_map_alloc_id() invokes idr_alloc_cyclic() after acquiring map_idr_lock, it will trigger a similar lockdep warning because the slab's lock (s->cpu_slab->lock) is still a spinlock. Instead of changing map_idr_lock's type, fix the issue by invoking htab_put_fd_value() after htab_unlock_bucket(). However, only deferring the invocation of htab_put_fd_value() is not enough, because the old map pointers in htab of maps can not be saved during batched deletion. Therefore, also defer the invocation of free_htab_elem(), so these to-be-freed elements could be linked together similar to lru map. There are four callers for ->map_fd_put_ptr: (1) alloc_htab_elem() (through htab_put_fd_value()) It invokes ->map_fd_put_ptr() under a raw_spinlock_t. The invocation of htab_put_fd_value() can not simply move after htab_unlock_bucket(), because the old element has already been stashed in htab->extra_elems. It may be reused immediately after htab_unlock_bucket() and the invocation of htab_put_fd_value() after htab_unlock_bucket() may release the newly-added element incorrectly. Therefore, saving the map pointer of the old element for htab of maps before unlocking the bucket and releasing the map_ptr after unlock. Beside the map pointer in the old element, should do the same thing for the special fields in the old element as well. (2) free_htab_elem() (through htab_put_fd_value()) Its caller includes __htab_map_lookup_and_delete_elem(), htab_map_delete_elem() and __htab_map_lookup_and_delete_batch(). For htab_map_delete_elem(), simply invoke free_htab_elem() after htab_unlock_bucket(). For __htab_map_lookup_and_delete_batch(), just like lru map, linking the to-be-freed element into node_to_free list and invoking free_htab_elem() for these element after unlock. It is safe to reuse batch_flink as the link for node_to_free, because these elements have been removed from the hash llist. Because htab of maps doesn't support lookup_and_delete operation, __htab_map_lookup_and_delete_elem() doesn't have the problem, so kept it as ---truncated---
CVE-2024-56604: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: RFCOMM: avoid leaving dangling sk pointer in rfcomm_sock_alloc() bt_sock_alloc() attaches allocated sk object to the provided sock object. If rfcomm_dlc_alloc() fails, we release the sk object, but leave the dangling pointer in the sock object, which may cause use-after-free. Fix this by swapping calls to bt_sock_alloc() and rfcomm_dlc_alloc().
CVE-2024-56609: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: use ieee80211_purge_tx_queue() to purge TX skb When removing kernel modules by: rmmod rtw88_8723cs rtw88_8703b rtw88_8723x rtw88_sdio rtw88_core Driver uses skb_queue_purge() to purge TX skb, but not report tx status causing "Have pending ack frames!" warning. Use ieee80211_purge_tx_queue() to correct this. Since ieee80211_purge_tx_queue() doesn't take locks, to prevent racing between TX work and purge TX queue, flush and destroy TX work in advance. wlan0: deauthenticating from aa:f5:fd:60:4c:a8 by local choice (Reason: 3=DEAUTH_LEAVING) ------------[ cut here ]------------ Have pending ack frames! WARNING: CPU: 3 PID: 9232 at net/mac80211/main.c:1691 ieee80211_free_ack_frame+0x5c/0x90 [mac80211] CPU: 3 PID: 9232 Comm: rmmod Tainted: G C 6.10.1-200.fc40.aarch64 #1 Hardware name: pine64 Pine64 PinePhone Braveheart (1.1)/Pine64 PinePhone Braveheart (1.1), BIOS 2024.01 01/01/2024 pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : ieee80211_free_ack_frame+0x5c/0x90 [mac80211] lr : ieee80211_free_ack_frame+0x5c/0x90 [mac80211] sp : ffff80008c1b37b0 x29: ffff80008c1b37b0 x28: ffff000003be8000 x27: 0000000000000000 x26: 0000000000000000 x25: ffff000003dc14b8 x24: ffff80008c1b37d0 x23: ffff000000ff9f80 x22: 0000000000000000 x21: 000000007fffffff x20: ffff80007c7e93d8 x19: ffff00006e66f400 x18: 0000000000000000 x17: ffff7ffffd2b3000 x16: ffff800083fc0000 x15: 0000000000000000 x14: 0000000000000000 x13: 2173656d61726620 x12: 6b636120676e6964 x11: 0000000000000000 x10: 000000000000005d x9 : ffff8000802af2b0 x8 : ffff80008c1b3430 x7 : 0000000000000001 x6 : 0000000000000001 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff000003be8000 Call trace: ieee80211_free_ack_frame+0x5c/0x90 [mac80211] idr_for_each+0x74/0x110 ieee80211_free_hw+0x44/0xe8 [mac80211] rtw_sdio_remove+0x9c/0xc0 [rtw88_sdio] sdio_bus_remove+0x44/0x180 device_remove+0x54/0x90 device_release_driver_internal+0x1d4/0x238 driver_detach+0x54/0xc0 bus_remove_driver+0x78/0x108 driver_unregister+0x38/0x78 sdio_unregister_driver+0x2c/0x40 rtw_8723cs_driver_exit+0x18/0x1000 [rtw88_8723cs] __do_sys_delete_module.isra.0+0x190/0x338 __arm64_sys_delete_module+0x1c/0x30 invoke_syscall+0x74/0x100 el0_svc_common.constprop.0+0x48/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x3c/0x158 el0t_64_sync_handler+0x120/0x138 el0t_64_sync+0x194/0x198 ---[ end trace 0000000000000000 ]---
CVE-2024-56611: In the Linux kernel, the following vulnerability has been resolved: mm/mempolicy: fix migrate_to_node() assuming there is at least one VMA in a MM We currently assume that there is at least one VMA in a MM, which isn't true. So we might end up having find_vma() return NULL, to then de-reference NULL. So properly handle find_vma() returning NULL. This fixes the report: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 UID: 0 PID: 6021 Comm: syz-executor284 Not tainted 6.12.0-rc7-syzkaller-00187-gf868cd251776 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/30/2024 RIP: 0010:migrate_to_node mm/mempolicy.c:1090 [inline] RIP: 0010:do_migrate_pages+0x403/0x6f0 mm/mempolicy.c:1194 Code: ... RSP: 0018:ffffc9000375fd08 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffc9000375fd78 RCX: 0000000000000000 RDX: ffff88807e171300 RSI: dffffc0000000000 RDI: ffff88803390c044 RBP: ffff88807e171428 R08: 0000000000000014 R09: fffffbfff2039ef1 R10: ffffffff901cf78f R11: 0000000000000000 R12: 0000000000000003 R13: ffffc9000375fe90 R14: ffffc9000375fe98 R15: ffffc9000375fdf8 FS: 00005555919e1380(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005555919e1ca8 CR3: 000000007f12a000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> kernel_migrate_pages+0x5b2/0x750 mm/mempolicy.c:1709 __do_sys_migrate_pages mm/mempolicy.c:1727 [inline] __se_sys_migrate_pages mm/mempolicy.c:1723 [inline] __x64_sys_migrate_pages+0x96/0x100 mm/mempolicy.c:1723 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [akpm@linux-foundation.org: add unlikely()]
CVE-2024-56614: In the Linux kernel, the following vulnerability has been resolved: xsk: fix OOB map writes when deleting elements Jordy says: " In the xsk_map_delete_elem function an unsigned integer (map->max_entries) is compared with a user-controlled signed integer (k). Due to implicit type conversion, a large unsigned value for map->max_entries can bypass the intended bounds check: if (k >= map->max_entries) return -EINVAL; This allows k to hold a negative value (between -2147483648 and -2), which is then used as an array index in m->xsk_map[k], which results in an out-of-bounds access. spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; // Out-of-bounds map_entry old_xs = unrcu_pointer(xchg(map_entry, NULL)); // Oob write if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); The xchg operation can then be used to cause an out-of-bounds write. Moreover, the invalid map_entry passed to xsk_map_sock_delete can lead to further memory corruption. " It indeed results in following splat: [76612.897343] BUG: unable to handle page fault for address: ffffc8fc2e461108 [76612.904330] #PF: supervisor write access in kernel mode [76612.909639] #PF: error_code(0x0002) - not-present page [76612.914855] PGD 0 P4D 0 [76612.917431] Oops: Oops: 0002 [#1] PREEMPT SMP [76612.921859] CPU: 11 UID: 0 PID: 10318 Comm: a.out Not tainted 6.12.0-rc1+ #470 [76612.929189] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0008.031920191559 03/19/2019 [76612.939781] RIP: 0010:xsk_map_delete_elem+0x2d/0x60 [76612.944738] Code: 00 00 41 54 55 53 48 63 2e 3b 6f 24 73 38 4c 8d a7 f8 00 00 00 48 89 fb 4c 89 e7 e8 2d bf 05 00 48 8d b4 eb 00 01 00 00 31 ff <48> 87 3e 48 85 ff 74 05 e8 16 ff ff ff 4c 89 e7 e8 3e bc 05 00 31 [76612.963774] RSP: 0018:ffffc9002e407df8 EFLAGS: 00010246 [76612.969079] RAX: 0000000000000000 RBX: ffffc9002e461000 RCX: 0000000000000000 [76612.976323] RDX: 0000000000000001 RSI: ffffc8fc2e461108 RDI: 0000000000000000 [76612.983569] RBP: ffffffff80000001 R08: 0000000000000000 R09: 0000000000000007 [76612.990812] R10: ffffc9002e407e18 R11: ffff888108a38858 R12: ffffc9002e4610f8 [76612.998060] R13: ffff888108a38858 R14: 00007ffd1ae0ac78 R15: ffffc9002e4610c0 [76613.005303] FS: 00007f80b6f59740(0000) GS:ffff8897e0ec0000(0000) knlGS:0000000000000000 [76613.013517] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [76613.019349] CR2: ffffc8fc2e461108 CR3: 000000011e3ef001 CR4: 00000000007726f0 [76613.026595] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [76613.033841] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [76613.041086] PKRU: 55555554 [76613.043842] Call Trace: [76613.046331] <TASK> [76613.048468] ? __die+0x20/0x60 [76613.051581] ? page_fault_oops+0x15a/0x450 [76613.055747] ? search_extable+0x22/0x30 [76613.059649] ? search_bpf_extables+0x5f/0x80 [76613.063988] ? exc_page_fault+0xa9/0x140 [76613.067975] ? asm_exc_page_fault+0x22/0x30 [76613.072229] ? xsk_map_delete_elem+0x2d/0x60 [76613.076573] ? xsk_map_delete_elem+0x23/0x60 [76613.080914] __sys_bpf+0x19b7/0x23c0 [76613.084555] __x64_sys_bpf+0x1a/0x20 [76613.088194] do_syscall_64+0x37/0xb0 [76613.091832] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [76613.096962] RIP: 0033:0x7f80b6d1e88d [76613.100592] Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 b5 0f 00 f7 d8 64 89 01 48 [76613.119631] RSP: 002b:00007ffd1ae0ac68 EFLAGS: 00000206 ORIG_RAX: 0000000000000141 [76613.131330] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f80b6d1e88d [76613.142632] RDX: 0000000000000098 RSI: 00007ffd1ae0ad20 RDI: 0000000000000003 [76613.153967] RBP: 00007ffd1ae0adc0 R08: 0000000000000000 R09: 0000000000000000 [76613.166030] R10: 00007f80b6f77040 R11: 0000000000000206 R12: 00007ffd1ae0aed8 [76613.177130] R13: 000055ddf42ce1e9 R14: 000055ddf42d0d98 R15: 00 ---truncated---
CVE-2024-56640: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix LGR and link use-after-free issue We encountered a LGR/link use-after-free issue, which manifested as the LGR/link refcnt reaching 0 early and entering the clear process, making resource access unsafe. refcount_t: addition on 0; use-after-free. WARNING: CPU: 14 PID: 107447 at lib/refcount.c:25 refcount_warn_saturate+0x9c/0x140 Workqueue: events smc_lgr_terminate_work [smc] Call trace: refcount_warn_saturate+0x9c/0x140 __smc_lgr_terminate.part.45+0x2a8/0x370 [smc] smc_lgr_terminate_work+0x28/0x30 [smc] process_one_work+0x1b8/0x420 worker_thread+0x158/0x510 kthread+0x114/0x118 or refcount_t: underflow; use-after-free. WARNING: CPU: 6 PID: 93140 at lib/refcount.c:28 refcount_warn_saturate+0xf0/0x140 Workqueue: smc_hs_wq smc_listen_work [smc] Call trace: refcount_warn_saturate+0xf0/0x140 smcr_link_put+0x1cc/0x1d8 [smc] smc_conn_free+0x110/0x1b0 [smc] smc_conn_abort+0x50/0x60 [smc] smc_listen_find_device+0x75c/0x790 [smc] smc_listen_work+0x368/0x8a0 [smc] process_one_work+0x1b8/0x420 worker_thread+0x158/0x510 kthread+0x114/0x118 It is caused by repeated release of LGR/link refcnt. One suspect is that smc_conn_free() is called repeatedly because some smc_conn_free() from server listening path are not protected by sock lock. e.g. Calls under socklock | smc_listen_work ------------------------------------------------------- lock_sock(sk) | smc_conn_abort smc_conn_free | \- smc_conn_free \- smcr_link_put | \- smcr_link_put (duplicated) release_sock(sk) So here add sock lock protection in smc_listen_work() path, making it exclusive with other connection operations.
CVE-2024-56641: In the Linux kernel, the following vulnerability has been resolved: net/smc: initialize close_work early to avoid warning We encountered a warning that close_work was canceled before initialization. WARNING: CPU: 7 PID: 111103 at kernel/workqueue.c:3047 __flush_work+0x19e/0x1b0 Workqueue: events smc_lgr_terminate_work [smc] RIP: 0010:__flush_work+0x19e/0x1b0 Call Trace: ? __wake_up_common+0x7a/0x190 ? work_busy+0x80/0x80 __cancel_work_timer+0xe3/0x160 smc_close_cancel_work+0x1a/0x70 [smc] smc_close_active_abort+0x207/0x360 [smc] __smc_lgr_terminate.part.38+0xc8/0x180 [smc] process_one_work+0x19e/0x340 worker_thread+0x30/0x370 ? process_one_work+0x340/0x340 kthread+0x117/0x130 ? __kthread_cancel_work+0x50/0x50 ret_from_fork+0x22/0x30 This is because when smc_close_cancel_work is triggered, e.g. the RDMA driver is rmmod and the LGR is terminated, the conn->close_work is flushed before initialization, resulting in WARN_ON(!work->func). __smc_lgr_terminate | smc_connect_{rdma|ism} ------------------------------------------------------------- | smc_conn_create | \- smc_lgr_register_conn for conn in lgr->conns_all | \- smc_conn_kill | \- smc_close_active_abort | \- smc_close_cancel_work | \- cancel_work_sync | \- __flush_work | (close_work) | | smc_close_init | \- INIT_WORK(&close_work) So fix this by initializing close_work before establishing the connection.
CVE-2024-56647: In the Linux kernel, the following vulnerability has been resolved: net: Fix icmp host relookup triggering ip_rt_bug arp link failure may trigger ip_rt_bug while xfrm enabled, call trace is: WARNING: CPU: 0 PID: 0 at net/ipv4/route.c:1241 ip_rt_bug+0x14/0x20 Modules linked in: CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc6-00077-g2e1b3cc9d7f7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:ip_rt_bug+0x14/0x20 Call Trace: <IRQ> ip_send_skb+0x14/0x40 __icmp_send+0x42d/0x6a0 ipv4_link_failure+0xe2/0x1d0 arp_error_report+0x3c/0x50 neigh_invalidate+0x8d/0x100 neigh_timer_handler+0x2e1/0x330 call_timer_fn+0x21/0x120 __run_timer_base.part.0+0x1c9/0x270 run_timer_softirq+0x4c/0x80 handle_softirqs+0xac/0x280 irq_exit_rcu+0x62/0x80 sysvec_apic_timer_interrupt+0x77/0x90 The script below reproduces this scenario: ip xfrm policy add src 0.0.0.0/0 dst 0.0.0.0/0 \ dir out priority 0 ptype main flag localok icmp ip l a veth1 type veth ip a a 192.168.141.111/24 dev veth0 ip l s veth0 up ping 192.168.141.155 -c 1 icmp_route_lookup() create input routes for locally generated packets while xfrm relookup ICMP traffic.Then it will set input route (dst->out = ip_rt_bug) to skb for DESTUNREACH. For ICMP err triggered by locally generated packets, dst->dev of output route is loopback. Generally, xfrm relookup verification is not required on loopback interfaces (net.ipv4.conf.lo.disable_xfrm = 1). Skip icmp relookup for locally generated packets to fix it.
CVE-2024-56651: In the Linux kernel, the following vulnerability has been resolved: can: hi311x: hi3110_can_ist(): fix potential use-after-free The commit a22bd630cfff ("can: hi311x: do not report txerr and rxerr during bus-off") removed the reporting of rxerr and txerr even in case of correct operation (i. e. not bus-off). The error count information added to the CAN frame after netif_rx() is a potential use after free, since there is no guarantee that the skb is in the same state. It might be freed or reused. Fix the issue by postponing the netif_rx() call in case of txerr and rxerr reporting.
CVE-2024-56692: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node blkaddr in truncate_node() syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2534! RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 Call Trace: truncate_node+0x1ae/0x8c0 fs/f2fs/node.c:909 f2fs_remove_inode_page+0x5c2/0x870 fs/f2fs/node.c:1288 f2fs_evict_inode+0x879/0x15c0 fs/f2fs/inode.c:856 evict+0x4e8/0x9b0 fs/inode.c:723 f2fs_handle_failed_inode+0x271/0x2e0 fs/f2fs/inode.c:986 f2fs_create+0x357/0x530 fs/f2fs/namei.c:394 lookup_open fs/namei.c:3595 [inline] open_last_lookups fs/namei.c:3694 [inline] path_openat+0x1c03/0x3590 fs/namei.c:3930 do_filp_open+0x235/0x490 fs/namei.c:3960 do_sys_openat2+0x13e/0x1d0 fs/open.c:1415 do_sys_open fs/open.c:1430 [inline] __do_sys_openat fs/open.c:1446 [inline] __se_sys_openat fs/open.c:1441 [inline] __x64_sys_openat+0x247/0x2a0 fs/open.c:1441 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 The root cause is: on a fuzzed image, blkaddr in nat entry may be corrupted, then it will cause system panic when using it in f2fs_invalidate_blocks(), to avoid this, let's add sanity check on nat blkaddr in truncate_node().
CVE-2024-56703: In the Linux kernel, the following vulnerability has been resolved: ipv6: Fix soft lockups in fib6_select_path under high next hop churn Soft lockups have been observed on a cluster of Linux-based edge routers located in a highly dynamic environment. Using the `bird` service, these routers continuously update BGP-advertised routes due to frequently changing nexthop destinations, while also managing significant IPv6 traffic. The lockups occur during the traversal of the multipath circular linked-list in the `fib6_select_path` function, particularly while iterating through the siblings in the list. The issue typically arises when the nodes of the linked list are unexpectedly deleted concurrently on a different core—indicated by their 'next' and 'previous' elements pointing back to the node itself and their reference count dropping to zero. This results in an infinite loop, leading to a soft lockup that triggers a system panic via the watchdog timer. Apply RCU primitives in the problematic code sections to resolve the issue. Where necessary, update the references to fib6_siblings to annotate or use the RCU APIs. Include a test script that reproduces the issue. The script periodically updates the routing table while generating a heavy load of outgoing IPv6 traffic through multiple iperf3 clients. It consistently induces infinite soft lockups within a couple of minutes. Kernel log: 0 [ffffbd13003e8d30] machine_kexec at ffffffff8ceaf3eb 1 [ffffbd13003e8d90] __crash_kexec at ffffffff8d0120e3 2 [ffffbd13003e8e58] panic at ffffffff8cef65d4 3 [ffffbd13003e8ed8] watchdog_timer_fn at ffffffff8d05cb03 4 [ffffbd13003e8f08] __hrtimer_run_queues at ffffffff8cfec62f 5 [ffffbd13003e8f70] hrtimer_interrupt at ffffffff8cfed756 6 [ffffbd13003e8fd0] __sysvec_apic_timer_interrupt at ffffffff8cea01af 7 [ffffbd13003e8ff0] sysvec_apic_timer_interrupt at ffffffff8df1b83d -- <IRQ stack> -- 8 [ffffbd13003d3708] asm_sysvec_apic_timer_interrupt at ffffffff8e000ecb [exception RIP: fib6_select_path+299] RIP: ffffffff8ddafe7b RSP: ffffbd13003d37b8 RFLAGS: 00000287 RAX: ffff975850b43600 RBX: ffff975850b40200 RCX: 0000000000000000 RDX: 000000003fffffff RSI: 0000000051d383e4 RDI: ffff975850b43618 RBP: ffffbd13003d3800 R8: 0000000000000000 R9: ffff975850b40200 R10: 0000000000000000 R11: 0000000000000000 R12: ffffbd13003d3830 R13: ffff975850b436a8 R14: ffff975850b43600 R15: 0000000000000007 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 9 [ffffbd13003d3808] ip6_pol_route at ffffffff8ddb030c 10 [ffffbd13003d3888] ip6_pol_route_input at ffffffff8ddb068c 11 [ffffbd13003d3898] fib6_rule_lookup at ffffffff8ddf02b5 12 [ffffbd13003d3928] ip6_route_input at ffffffff8ddb0f47 13 [ffffbd13003d3a18] ip6_rcv_finish_core.constprop.0 at ffffffff8dd950d0 14 [ffffbd13003d3a30] ip6_list_rcv_finish.constprop.0 at ffffffff8dd96274 15 [ffffbd13003d3a98] ip6_sublist_rcv at ffffffff8dd96474 16 [ffffbd13003d3af8] ipv6_list_rcv at ffffffff8dd96615 17 [ffffbd13003d3b60] __netif_receive_skb_list_core at ffffffff8dc16fec 18 [ffffbd13003d3be0] netif_receive_skb_list_internal at ffffffff8dc176b3 19 [ffffbd13003d3c50] napi_gro_receive at ffffffff8dc565b9 20 [ffffbd13003d3c80] ice_receive_skb at ffffffffc087e4f5 [ice] 21 [ffffbd13003d3c90] ice_clean_rx_irq at ffffffffc0881b80 [ice] 22 [ffffbd13003d3d20] ice_napi_poll at ffffffffc088232f [ice] 23 [ffffbd13003d3d80] __napi_poll at ffffffff8dc18000 24 [ffffbd13003d3db8] net_rx_action at ffffffff8dc18581 25 [ffffbd13003d3e40] __do_softirq at ffffffff8df352e9 26 [ffffbd13003d3eb0] run_ksoftirqd at ffffffff8ceffe47 27 [ffffbd13003d3ec0] smpboot_thread_fn at ffffffff8cf36a30 28 [ffffbd13003d3ee8] kthread at ffffffff8cf2b39f 29 [ffffbd13003d3f28] ret_from_fork at ffffffff8ce5fa64 30 [ffffbd13003d3f50] ret_from_fork_asm at ffffffff8ce03cbb
CVE-2024-56712: In the Linux kernel, the following vulnerability has been resolved: udmabuf: fix memory leak on last export_udmabuf() error path In export_udmabuf(), if dma_buf_fd() fails because the FD table is full, a dma_buf owning the udmabuf has already been created; but the error handling in udmabuf_create() will tear down the udmabuf without doing anything about the containing dma_buf. This leaves a dma_buf in memory that contains a dangling pointer; though that doesn't seem to lead to anything bad except a memory leak. Fix it by moving the dma_buf_fd() call out of export_udmabuf() so that we can give it different error handling. Note that the shape of this code changed a lot in commit 5e72b2b41a21 ("udmabuf: convert udmabuf driver to use folios"); but the memory leak seems to have existed since the introduction of udmabuf.
CVE-2024-56715: In the Linux kernel, the following vulnerability has been resolved: ionic: Fix netdev notifier unregister on failure If register_netdev() fails, then the driver leaks the netdev notifier. Fix this by calling ionic_lif_unregister() on register_netdev() failure. This will also call ionic_lif_unregister_phc() if it has already been registered.
CVE-2024-56718: In the Linux kernel, the following vulnerability has been resolved: net/smc: protect link down work from execute after lgr freed link down work may be scheduled before lgr freed but execute after lgr freed, which may result in crash. So it is need to hold a reference before shedule link down work, and put the reference after work executed or canceled. The relevant crash call stack as follows: list_del corruption. prev->next should be ffffb638c9c0fe20, but was 0000000000000000 ------------[ cut here ]------------ kernel BUG at lib/list_debug.c:51! invalid opcode: 0000 [#1] SMP NOPTI CPU: 6 PID: 978112 Comm: kworker/6:119 Kdump: loaded Tainted: G #1 Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 2221b89 04/01/2014 Workqueue: events smc_link_down_work [smc] RIP: 0010:__list_del_entry_valid.cold+0x31/0x47 RSP: 0018:ffffb638c9c0fdd8 EFLAGS: 00010086 RAX: 0000000000000054 RBX: ffff942fb75e5128 RCX: 0000000000000000 RDX: ffff943520930aa0 RSI: ffff94352091fc80 RDI: ffff94352091fc80 RBP: 0000000000000000 R08: 0000000000000000 R09: ffffb638c9c0fc38 R10: ffffb638c9c0fc30 R11: ffffffffa015eb28 R12: 0000000000000002 R13: ffffb638c9c0fe20 R14: 0000000000000001 R15: ffff942f9cd051c0 FS: 0000000000000000(0000) GS:ffff943520900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4f25214000 CR3: 000000025fbae004 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: rwsem_down_write_slowpath+0x17e/0x470 smc_link_down_work+0x3c/0x60 [smc] process_one_work+0x1ac/0x350 worker_thread+0x49/0x2f0 ? rescuer_thread+0x360/0x360 kthread+0x118/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x1f/0x30
CVE-2024-56722: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix cpu stuck caused by printings during reset During reset, cmd to destroy resources such as qp, cq, and mr may fail, and error logs will be printed. When a large number of resources are destroyed, there will be lots of printings, and it may lead to a cpu stuck. Delete some unnecessary printings and replace other printing functions in these paths with the ratelimited version.
CVE-2024-56775: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix handling of plane refcount [Why] The mechanism to backup and restore plane states doesn't maintain refcount, which can cause issues if the refcount of the plane changes in between backup and restore operations, such as memory leaks if the refcount was supposed to go down, or double frees / invalid memory accesses if the refcount was supposed to go up. [How] Cache and re-apply current refcount when restoring plane states.
CVE-2024-56776: In the Linux kernel, the following vulnerability has been resolved: drm/sti: avoid potential dereference of error pointers The return value of drm_atomic_get_crtc_state() needs to be checked. To avoid use of error pointer 'crtc_state' in case of the failure.
CVE-2024-56777: In the Linux kernel, the following vulnerability has been resolved: drm/sti: avoid potential dereference of error pointers in sti_gdp_atomic_check The return value of drm_atomic_get_crtc_state() needs to be checked. To avoid use of error pointer 'crtc_state' in case of the failure.
CVE-2024-56778: In the Linux kernel, the following vulnerability has been resolved: drm/sti: avoid potential dereference of error pointers in sti_hqvdp_atomic_check The return value of drm_atomic_get_crtc_state() needs to be checked. To avoid use of error pointer 'crtc_state' in case of the failure.
CVE-2024-56787: In the Linux kernel, the following vulnerability has been resolved: soc: imx8m: Probe the SoC driver as platform driver With driver_async_probe=* on kernel command line, the following trace is produced because on i.MX8M Plus hardware because the soc-imx8m.c driver calls of_clk_get_by_name() which returns -EPROBE_DEFER because the clock driver is not yet probed. This was not detected during regular testing without driver_async_probe. Convert the SoC code to platform driver and instantiate a platform device in its current device_initcall() to probe the platform driver. Rework .soc_revision callback to always return valid error code and return SoC revision via parameter. This way, if anything in the .soc_revision callback return -EPROBE_DEFER, it gets propagated to .probe and the .probe will get retried later. " ------------[ cut here ]------------ WARNING: CPU: 1 PID: 1 at drivers/soc/imx/soc-imx8m.c:115 imx8mm_soc_revision+0xdc/0x180 CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.11.0-next-20240924-00002-g2062bb554dea #603 Hardware name: DH electronics i.MX8M Plus DHCOM Premium Developer Kit (3) (DT) pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : imx8mm_soc_revision+0xdc/0x180 lr : imx8mm_soc_revision+0xd0/0x180 sp : ffff8000821fbcc0 x29: ffff8000821fbce0 x28: 0000000000000000 x27: ffff800081810120 x26: ffff8000818a9970 x25: 0000000000000006 x24: 0000000000824311 x23: ffff8000817f42c8 x22: ffff0000df8be210 x21: fffffffffffffdfb x20: ffff800082780000 x19: 0000000000000001 x18: ffffffffffffffff x17: ffff800081fff418 x16: ffff8000823e1000 x15: ffff0000c03b65e8 x14: ffff0000c00051b0 x13: ffff800082790000 x12: 0000000000000801 x11: ffff80008278ffff x10: ffff80008209d3a6 x9 : ffff80008062e95c x8 : ffff8000821fb9a0 x7 : 0000000000000000 x6 : 00000000000080e3 x5 : ffff0000df8c03d8 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : fffffffffffffdfb x0 : fffffffffffffdfb Call trace: imx8mm_soc_revision+0xdc/0x180 imx8_soc_init+0xb0/0x1e0 do_one_initcall+0x94/0x1a8 kernel_init_freeable+0x240/0x2a8 kernel_init+0x28/0x140 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- SoC: i.MX8MP revision 1.1 "
CVE-2024-57795: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Remove the direct link to net_device The similar patch in siw is in the link: https://git.kernel.org/rdma/rdma/c/16b87037b48889 This problem also occurred in RXE. The following analyze this problem. In the following Call Traces: " BUG: KASAN: slab-use-after-free in dev_get_flags+0x188/0x1d0 net/core/dev.c:8782 Read of size 4 at addr ffff8880554640b0 by task kworker/1:4/5295 CPU: 1 UID: 0 PID: 5295 Comm: kworker/1:4 Not tainted 6.12.0-rc3-syzkaller-00399-g9197b73fd7bb #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: infiniband ib_cache_event_task Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 dev_get_flags+0x188/0x1d0 net/core/dev.c:8782 rxe_query_port+0x12d/0x260 drivers/infiniband/sw/rxe/rxe_verbs.c:60 __ib_query_port drivers/infiniband/core/device.c:2111 [inline] ib_query_port+0x168/0x7d0 drivers/infiniband/core/device.c:2143 ib_cache_update+0x1a9/0xb80 drivers/infiniband/core/cache.c:1494 ib_cache_event_task+0xf3/0x1e0 drivers/infiniband/core/cache.c:1568 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa65/0x1850 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f2/0x390 kernel/kthread.c:389 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> " 1). In the link [1], " infiniband syz2: set down " This means that on 839.350575, the event ib_cache_event_task was sent andi queued in ib_wq. 2). In the link [1], " team0 (unregistering): Port device team_slave_0 removed " It indicates that before 843.251853, the net device should be freed. 3). In the link [1], " BUG: KASAN: slab-use-after-free in dev_get_flags+0x188/0x1d0 " This means that on 850.559070, this slab-use-after-free problem occurred. In all, on 839.350575, the event ib_cache_event_task was sent and queued in ib_wq, before 843.251853, the net device veth was freed. on 850.559070, this event was executed, and the mentioned freed net device was called. Thus, the above call trace occurred. [1] https://syzkaller.appspot.com/x/log.txt?x=12e7025f980000
CVE-2024-57798: In the Linux kernel, the following vulnerability has been resolved: drm/dp_mst: Ensure mst_primary pointer is valid in drm_dp_mst_handle_up_req() While receiving an MST up request message from one thread in drm_dp_mst_handle_up_req(), the MST topology could be removed from another thread via drm_dp_mst_topology_mgr_set_mst(false), freeing mst_primary and setting drm_dp_mst_topology_mgr::mst_primary to NULL. This could lead to a NULL deref/use-after-free of mst_primary in drm_dp_mst_handle_up_req(). Avoid the above by holding a reference for mst_primary in drm_dp_mst_handle_up_req() while it's used. v2: Fix kfreeing the request if getting an mst_primary reference fails.
CVE-2024-57809: In the Linux kernel, the following vulnerability has been resolved: PCI: imx6: Fix suspend/resume support on i.MX6QDL The suspend/resume functionality is currently broken on the i.MX6QDL platform, as documented in the NXP errata (ERR005723): https://www.nxp.com/docs/en/errata/IMX6DQCE.pdf This patch addresses the issue by sharing most of the suspend/resume sequences used by other i.MX devices, while avoiding modifications to critical registers that disrupt the PCIe functionality. It targets the same problem as the following downstream commit: https://github.com/nxp-imx/linux-imx/commit/4e92355e1f79d225ea842511fcfd42b343b32995 Unlike the downstream commit, this patch also resets the connected PCIe device if possible. Without this reset, certain drivers, such as ath10k or iwlwifi, will crash on resume. The device reset is also done by the driver on other i.MX platforms, making this patch consistent with existing practices. Upon resuming, the kernel will hang and display an error. Here's an example of the error encountered with the ath10k driver: ath10k_pci 0000:01:00.0: Unable to change power state from D3hot to D0, device inaccessible Unhandled fault: imprecise external abort (0x1406) at 0x0106f944 Without this patch, suspend/resume will fail on i.MX6QDL devices if a PCIe device is connected. [kwilczynski: commit log, added tag for stable releases]
CVE-2024-57857: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Remove direct link to net_device Do not manage a per device direct link to net_device. Rely on associated ib_devices net_device management, not doubling the effort locally. A badly managed local link to net_device was causing a 'KASAN: slab-use-after-free' exception during siw_query_port() call.
CVE-2024-57872: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: pltfrm: Dellocate HBA during ufshcd_pltfrm_remove() This will ensure that the scsi host is cleaned up properly using scsi_host_dev_release(). Otherwise, it may lead to memory leaks.
CVE-2024-57876: In the Linux kernel, the following vulnerability has been resolved: drm/dp_mst: Fix resetting msg rx state after topology removal If the MST topology is removed during the reception of an MST down reply or MST up request sideband message, the drm_dp_mst_topology_mgr::up_req_recv/down_rep_recv states could be reset from one thread via drm_dp_mst_topology_mgr_set_mst(false), racing with the reading/parsing of the message from another thread via drm_dp_mst_handle_down_rep() or drm_dp_mst_handle_up_req(). The race is possible since the reader/parser doesn't hold any lock while accessing the reception state. This in turn can lead to a memory corruption in the reader/parser as described by commit bd2fccac61b4 ("drm/dp_mst: Fix MST sideband message body length check"). Fix the above by resetting the message reception state if needed before reading/parsing a message. Another solution would be to hold the drm_dp_mst_topology_mgr::lock for the whole duration of the message reception/parsing in drm_dp_mst_handle_down_rep() and drm_dp_mst_handle_up_req(), however this would require a bigger change. Since the fix is also needed for stable, opting for the simpler solution in this patch.
CVE-2024-57888: In the Linux kernel, the following vulnerability has been resolved: workqueue: Do not warn when cancelling WQ_MEM_RECLAIM work from !WQ_MEM_RECLAIM worker After commit 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM") amdgpu started seeing the following warning: [ ] workqueue: WQ_MEM_RECLAIM sdma0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_device_delay_enable_gfx_off [amdgpu] ... [ ] Workqueue: sdma0 drm_sched_run_job_work [gpu_sched] ... [ ] Call Trace: [ ] <TASK> ... [ ] ? check_flush_dependency+0xf5/0x110 ... [ ] cancel_delayed_work_sync+0x6e/0x80 [ ] amdgpu_gfx_off_ctrl+0xab/0x140 [amdgpu] [ ] amdgpu_ring_alloc+0x40/0x50 [amdgpu] [ ] amdgpu_ib_schedule+0xf4/0x810 [amdgpu] [ ] ? drm_sched_run_job_work+0x22c/0x430 [gpu_sched] [ ] amdgpu_job_run+0xaa/0x1f0 [amdgpu] [ ] drm_sched_run_job_work+0x257/0x430 [gpu_sched] [ ] process_one_work+0x217/0x720 ... [ ] </TASK> The intent of the verifcation done in check_flush_depedency is to ensure forward progress during memory reclaim, by flagging cases when either a memory reclaim process, or a memory reclaim work item is flushed from a context not marked as memory reclaim safe. This is correct when flushing, but when called from the cancel(_delayed)_work_sync() paths it is a false positive because work is either already running, or will not be running at all. Therefore cancelling it is safe and we can relax the warning criteria by letting the helper know of the calling context. References: 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
CVE-2024-57893: In the Linux kernel, the following vulnerability has been resolved: ALSA: seq: oss: Fix races at processing SysEx messages OSS sequencer handles the SysEx messages split in 6 bytes packets, and ALSA sequencer OSS layer tries to combine those. It stores the data in the internal buffer and this access is racy as of now, which may lead to the out-of-bounds access. As a temporary band-aid fix, introduce a mutex for serializing the process of the SysEx message packets.
CVE-2024-57897: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Correct the migration DMA map direction The SVM DMA device map direction should be set the same as the DMA unmap setting, otherwise the DMA core will report the following warning. Before finialize this solution, there're some discussion on the DMA mapping type(stream-based or coherent) in this KFD migration case, followed by https://lore.kernel.org/all/04d4ab32 -45a1-4b88-86ee-fb0f35a0ca40@amd.com/T/. As there's no dma_sync_single_for_*() in the DMA buffer accessed that because this migration operation should be sync properly and automatically. Give that there's might not be a performance problem in various cache sync policy of DMA sync. Therefore, in order to simplify the DMA direction setting alignment, let's set the DMA map direction as BIDIRECTIONAL. [ 150.834218] WARNING: CPU: 8 PID: 1812 at kernel/dma/debug.c:1028 check_unmap+0x1cc/0x930 [ 150.834225] Modules linked in: amdgpu(OE) amdxcp drm_exec(OE) gpu_sched drm_buddy(OE) drm_ttm_helper(OE) ttm(OE) drm_suballoc_helper(OE) drm_display_helper(OE) drm_kms_helper(OE) i2c_algo_bit rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs lockd grace netfs xt_conntrack xt_MASQUERADE nf_conntrack_netlink xfrm_user xfrm_algo iptable_nat xt_addrtype iptable_filter br_netfilter nvme_fabrics overlay nfnetlink_cttimeout nfnetlink openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c bridge stp llc sch_fq_codel intel_rapl_msr amd_atl intel_rapl_common snd_hda_codec_realtek snd_hda_codec_generic snd_hda_scodec_component snd_hda_codec_hdmi snd_hda_intel snd_intel_dspcfg edac_mce_amd snd_pci_acp6x snd_hda_codec snd_acp_config snd_hda_core snd_hwdep snd_soc_acpi kvm_amd sunrpc snd_pcm kvm binfmt_misc snd_seq_midi crct10dif_pclmul snd_seq_midi_event ghash_clmulni_intel sha512_ssse3 snd_rawmidi nls_iso8859_1 sha256_ssse3 sha1_ssse3 snd_seq aesni_intel snd_seq_device crypto_simd snd_timer cryptd input_leds [ 150.834310] wmi_bmof serio_raw k10temp rapl snd sp5100_tco ipmi_devintf soundcore ccp ipmi_msghandler cm32181 industrialio mac_hid msr parport_pc ppdev lp parport efi_pstore drm(OE) ip_tables x_tables pci_stub crc32_pclmul nvme ahci libahci i2c_piix4 r8169 nvme_core i2c_designware_pci realtek i2c_ccgx_ucsi video wmi hid_generic cdc_ether usbnet usbhid hid r8152 mii [ 150.834354] CPU: 8 PID: 1812 Comm: rocrtst64 Tainted: G OE 6.10.0-custom #492 [ 150.834358] Hardware name: AMD Majolica-RN/Majolica-RN, BIOS RMJ1009A 06/13/2021 [ 150.834360] RIP: 0010:check_unmap+0x1cc/0x930 [ 150.834363] Code: c0 4c 89 4d c8 e8 34 bf 86 00 4c 8b 4d c8 4c 8b 45 c0 48 8b 4d b8 48 89 c6 41 57 4c 89 ea 48 c7 c7 80 49 b4 84 e8 b4 81 f3 ff <0f> 0b 48 c7 c7 04 83 ac 84 e8 76 ba fc ff 41 8b 76 4c 49 8d 7e 50 [ 150.834365] RSP: 0018:ffffaac5023739e0 EFLAGS: 00010086 [ 150.834368] RAX: 0000000000000000 RBX: ffffffff8566a2e0 RCX: 0000000000000027 [ 150.834370] RDX: ffff8f6a8f621688 RSI: 0000000000000001 RDI: ffff8f6a8f621680 [ 150.834372] RBP: ffffaac502373a30 R08: 00000000000000c9 R09: ffffaac502373850 [ 150.834373] R10: ffffaac502373848 R11: ffffffff84f46328 R12: ffffaac502373a40 [ 150.834375] R13: ffff8f6741045330 R14: ffff8f6741a77700 R15: ffffffff84ac831b [ 150.834377] FS: 00007faf0fc94c00(0000) GS:ffff8f6a8f600000(0000) knlGS:0000000000000000 [ 150.834379] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 150.834381] CR2: 00007faf0b600020 CR3: 000000010a52e000 CR4: 0000000000350ef0 [ 150.834383] Call Trace: [ 150.834385] <TASK> [ 150.834387] ? show_regs+0x6d/0x80 [ 150.834393] ? __warn+0x8c/0x140 [ 150.834397] ? check_unmap+0x1cc/0x930 [ 150.834400] ? report_bug+0x193/0x1a0 [ 150.834406] ? handle_bug+0x46/0x80 [ 150.834410] ? exc_invalid_op+0x1d/0x80 [ 150.834413] ? asm_exc_invalid_op+0x1f/0x30 [ 150.834420] ? check_unmap+0x1cc/0x930 [ 150.834425] debug_dma_unmap_page+0x86/0x90 [ 150.834431] ? srso_return_thunk+0x5/0x5f [ 150.834435] ---truncated---
CVE-2024-57903: In the Linux kernel, the following vulnerability has been resolved: net: restrict SO_REUSEPORT to inet sockets After blamed commit, crypto sockets could accidentally be destroyed from RCU call back, as spotted by zyzbot [1]. Trying to acquire a mutex in RCU callback is not allowed. Restrict SO_REUSEPORT socket option to inet sockets. v1 of this patch supported TCP, UDP and SCTP sockets, but fcnal-test.sh test needed RAW and ICMP support. [1] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:562 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 24, name: ksoftirqd/1 preempt_count: 100, expected: 0 RCU nest depth: 0, expected: 0 1 lock held by ksoftirqd/1/24: #0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire include/linux/rcupdate.h:337 [inline] #0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_do_batch kernel/rcu/tree.c:2561 [inline] #0: ffffffff8e937ba0 (rcu_callback){....}-{0:0}, at: rcu_core+0xa37/0x17a0 kernel/rcu/tree.c:2823 Preemption disabled at: [<ffffffff8161c8c8>] softirq_handle_begin kernel/softirq.c:402 [inline] [<ffffffff8161c8c8>] handle_softirqs+0x128/0x9b0 kernel/softirq.c:537 CPU: 1 UID: 0 PID: 24 Comm: ksoftirqd/1 Not tainted 6.13.0-rc3-syzkaller-00174-ga024e377efed #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 __might_resched+0x5d4/0x780 kernel/sched/core.c:8758 __mutex_lock_common kernel/locking/mutex.c:562 [inline] __mutex_lock+0x131/0xee0 kernel/locking/mutex.c:735 crypto_put_default_null_skcipher+0x18/0x70 crypto/crypto_null.c:179 aead_release+0x3d/0x50 crypto/algif_aead.c:489 alg_do_release crypto/af_alg.c:118 [inline] alg_sock_destruct+0x86/0xc0 crypto/af_alg.c:502 __sk_destruct+0x58/0x5f0 net/core/sock.c:2260 rcu_do_batch kernel/rcu/tree.c:2567 [inline] rcu_core+0xaaa/0x17a0 kernel/rcu/tree.c:2823 handle_softirqs+0x2d4/0x9b0 kernel/softirq.c:561 run_ksoftirqd+0xca/0x130 kernel/softirq.c:950 smpboot_thread_fn+0x544/0xa30 kernel/smpboot.c:164 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK>
CVE-2024-57924: In the Linux kernel, the following vulnerability has been resolved: fs: relax assertions on failure to encode file handles Encoding file handles is usually performed by a filesystem >encode_fh() method that may fail for various reasons. The legacy users of exportfs_encode_fh(), namely, nfsd and name_to_handle_at(2) syscall are ready to cope with the possibility of failure to encode a file handle. There are a few other users of exportfs_encode_{fh,fid}() that currently have a WARN_ON() assertion when ->encode_fh() fails. Relax those assertions because they are wrong. The second linked bug report states commit 16aac5ad1fa9 ("ovl: support encoding non-decodable file handles") in v6.6 as the regressing commit, but this is not accurate. The aforementioned commit only increases the chances of the assertion and allows triggering the assertion with the reproducer using overlayfs, inotify and drop_caches. Triggering this assertion was always possible with other filesystems and other reasons of ->encode_fh() failures and more particularly, it was also possible with the exact same reproducer using overlayfs that is mounted with options index=on,nfs_export=on also on kernels < v6.6. Therefore, I am not listing the aforementioned commit as a Fixes commit. Backport hint: this patch will have a trivial conflict applying to v6.6.y, and other trivial conflicts applying to stable kernels < v6.6.
CVE-2024-57945: In the Linux kernel, the following vulnerability has been resolved: riscv: mm: Fix the out of bound issue of vmemmap address In sparse vmemmap model, the virtual address of vmemmap is calculated as: ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)). And the struct page's va can be calculated with an offset: (vmemmap + (pfn)). However, when initializing struct pages, kernel actually starts from the first page from the same section that phys_ram_base belongs to. If the first page's physical address is not (phys_ram_base >> PAGE_SHIFT), then we get an va below VMEMMAP_START when calculating va for it's struct page. For example, if phys_ram_base starts from 0x82000000 with pfn 0x82000, the first page in the same section is actually pfn 0x80000. During init_unavailable_range(), we will initialize struct page for pfn 0x80000 with virtual address ((struct page *)VMEMMAP_START - 0x2000), which is below VMEMMAP_START as well as PCI_IO_END. This commit fixes this bug by introducing a new variable 'vmemmap_start_pfn' which is aligned with memory section size and using it to calculate vmemmap address instead of phys_ram_base.
CVE-2024-57974: In the Linux kernel, the following vulnerability has been resolved: udp: Deal with race between UDP socket address change and rehash If a UDP socket changes its local address while it's receiving datagrams, as a result of connect(), there is a period during which a lookup operation might fail to find it, after the address is changed but before the secondary hash (port and address) and the four-tuple hash (local and remote ports and addresses) are updated. Secondary hash chains were introduced by commit 30fff9231fad ("udp: bind() optimisation") and, as a result, a rehash operation became needed to make a bound socket reachable again after a connect(). This operation was introduced by commit 719f835853a9 ("udp: add rehash on connect()") which isn't however a complete fix: the socket will be found once the rehashing completes, but not while it's pending. This is noticeable with a socat(1) server in UDP4-LISTEN mode, and a client sending datagrams to it. After the server receives the first datagram (cf. _xioopen_ipdgram_listen()), it issues a connect() to the address of the sender, in order to set up a directed flow. Now, if the client, running on a different CPU thread, happens to send a (subsequent) datagram while the server's socket changes its address, but is not rehashed yet, this will result in a failed lookup and a port unreachable error delivered to the client, as apparent from the following reproducer: LEN=$(($(cat /proc/sys/net/core/wmem_default) / 4)) dd if=/dev/urandom bs=1 count=${LEN} of=tmp.in while :; do taskset -c 1 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,trunc & sleep 0.1 || sleep 1 taskset -c 2 socat OPEN:tmp.in UDP4:localhost:1337,shut-null wait done where the client will eventually get ECONNREFUSED on a write() (typically the second or third one of a given iteration): 2024/11/13 21:28:23 socat[46901] E write(6, 0x556db2e3c000, 8192): Connection refused This issue was first observed as a seldom failure in Podman's tests checking UDP functionality while using pasta(1) to connect the container's network namespace, which leads us to a reproducer with the lookup error resulting in an ICMP packet on a tap device: LOCAL_ADDR="$(ip -j -4 addr show|jq -rM '.[] | .addr_info[0] | select(.scope == "global").local')" while :; do ./pasta --config-net -p pasta.pcap -u 1337 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,trunc & sleep 0.2 || sleep 1 socat OPEN:tmp.in UDP4:${LOCAL_ADDR}:1337,shut-null wait cmp tmp.in tmp.out done Once this fails: tmp.in tmp.out differ: char 8193, line 29 we can finally have a look at what's going on: $ tshark -r pasta.pcap 1 0.000000 :: ? ff02::16 ICMPv6 110 Multicast Listener Report Message v2 2 0.168690 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 3 0.168767 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 4 0.168806 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 5 0.168827 c6:47:05:8d:dc:04 ? Broadcast ARP 42 Who has 88.198.0.161? Tell 88.198.0.164 6 0.168851 9a:55:9a:55:9a:55 ? c6:47:05:8d:dc:04 ARP 42 88.198.0.161 is at 9a:55:9a:55:9a:55 7 0.168875 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 8 0.168896 88.198.0.164 ? 88.198.0.161 ICMP 590 Destination unreachable (Port unreachable) 9 0.168926 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 10 0.168959 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 11 0.168989 88.198.0.161 ? 88.198.0.164 UDP 4138 60260 ? 1337 Len=4096 12 0.169010 88.198.0.161 ? 88.198.0.164 UDP 42 60260 ? 1337 Len=0 On the third datagram received, the network namespace of the container initiates an ARP lookup to deliver the ICMP message. In another variant of this reproducer, starting the client with: strace -f pasta --config-net -u 1337 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,tru ---truncated---
CVE-2024-57975: In the Linux kernel, the following vulnerability has been resolved: btrfs: do proper folio cleanup when run_delalloc_nocow() failed [BUG] With CONFIG_DEBUG_VM set, test case generic/476 has some chance to crash with the following VM_BUG_ON_FOLIO(): BTRFS error (device dm-3): cow_file_range failed, start 1146880 end 1253375 len 106496 ret -28 BTRFS error (device dm-3): run_delalloc_nocow failed, start 1146880 end 1253375 len 106496 ret -28 page: refcount:4 mapcount:0 mapping:00000000592787cc index:0x12 pfn:0x10664 aops:btrfs_aops [btrfs] ino:101 dentry name(?):"f1774" flags: 0x2fffff80004028(uptodate|lru|private|node=0|zone=2|lastcpupid=0xfffff) page dumped because: VM_BUG_ON_FOLIO(!folio_test_locked(folio)) ------------[ cut here ]------------ kernel BUG at mm/page-writeback.c:2992! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 2 UID: 0 PID: 3943513 Comm: kworker/u24:15 Tainted: G OE 6.12.0-rc7-custom+ #87 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : folio_clear_dirty_for_io+0x128/0x258 lr : folio_clear_dirty_for_io+0x128/0x258 Call trace: folio_clear_dirty_for_io+0x128/0x258 btrfs_folio_clamp_clear_dirty+0x80/0xd0 [btrfs] __process_folios_contig+0x154/0x268 [btrfs] extent_clear_unlock_delalloc+0x5c/0x80 [btrfs] run_delalloc_nocow+0x5f8/0x760 [btrfs] btrfs_run_delalloc_range+0xa8/0x220 [btrfs] writepage_delalloc+0x230/0x4c8 [btrfs] extent_writepage+0xb8/0x358 [btrfs] extent_write_cache_pages+0x21c/0x4e8 [btrfs] btrfs_writepages+0x94/0x150 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x88/0xc8 start_delalloc_inodes+0x178/0x3a8 [btrfs] btrfs_start_delalloc_roots+0x174/0x280 [btrfs] shrink_delalloc+0x114/0x280 [btrfs] flush_space+0x250/0x2f8 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x164/0x408 worker_thread+0x25c/0x388 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: 910a8021 a90363f7 a9046bf9 94012379 (d4210000) ---[ end trace 0000000000000000 ]--- [CAUSE] The first two lines of extra debug messages show the problem is caused by the error handling of run_delalloc_nocow(). E.g. we have the following dirtied range (4K blocksize 4K page size): 0 16K 32K |//////////////////////////////////////| | Pre-allocated | And the range [0, 16K) has a preallocated extent. - Enter run_delalloc_nocow() for range [0, 16K) Which found range [0, 16K) is preallocated, can do the proper NOCOW write. - Enter fallback_to_fow() for range [16K, 32K) Since the range [16K, 32K) is not backed by preallocated extent, we have to go COW. - cow_file_range() failed for range [16K, 32K) So cow_file_range() will do the clean up by clearing folio dirty, unlock the folios. Now the folios in range [16K, 32K) is unlocked. - Enter extent_clear_unlock_delalloc() from run_delalloc_nocow() Which is called with PAGE_START_WRITEBACK to start page writeback. But folios can only be marked writeback when it's properly locked, thus this triggered the VM_BUG_ON_FOLIO(). Furthermore there is another hidden but common bug that run_delalloc_nocow() is not clearing the folio dirty flags in its error handling path. This is the common bug shared between run_delalloc_nocow() and cow_file_range(). [FIX] - Clear folio dirty for range [@start, @cur_offset) Introduce a helper, cleanup_dirty_folios(), which will find and lock the folio in the range, clear the dirty flag and start/end the writeback, with the extra handling for the @locked_folio. - Introduce a helper to clear folio dirty, start and end writeback - Introduce a helper to record the last failed COW range end This is to trace which range we should skip, to avoid double unlocking. - Skip the failed COW range for the e ---truncated---
CVE-2024-57976: In the Linux kernel, the following vulnerability has been resolved: btrfs: do proper folio cleanup when cow_file_range() failed [BUG] When testing with COW fixup marked as BUG_ON() (this is involved with the new pin_user_pages*() change, which should not result new out-of-band dirty pages), I hit a crash triggered by the BUG_ON() from hitting COW fixup path. This BUG_ON() happens just after a failed btrfs_run_delalloc_range(): BTRFS error (device dm-2): failed to run delalloc range, root 348 ino 405 folio 65536 submit_bitmap 6-15 start 90112 len 106496: -28 ------------[ cut here ]------------ kernel BUG at fs/btrfs/extent_io.c:1444! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 0 UID: 0 PID: 434621 Comm: kworker/u24:8 Tainted: G OE 6.12.0-rc7-custom+ #86 Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : extent_writepage_io+0x2d4/0x308 [btrfs] lr : extent_writepage_io+0x2d4/0x308 [btrfs] Call trace: extent_writepage_io+0x2d4/0x308 [btrfs] extent_writepage+0x218/0x330 [btrfs] extent_write_cache_pages+0x1d4/0x4b0 [btrfs] btrfs_writepages+0x94/0x150 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x88/0xc8 start_delalloc_inodes+0x180/0x3b0 [btrfs] btrfs_start_delalloc_roots+0x174/0x280 [btrfs] shrink_delalloc+0x114/0x280 [btrfs] flush_space+0x250/0x2f8 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x164/0x408 worker_thread+0x25c/0x388 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: aa1403e1 9402f3ef aa1403e0 9402f36f (d4210000) ---[ end trace 0000000000000000 ]--- [CAUSE] That failure is mostly from cow_file_range(), where we can hit -ENOSPC. Although the -ENOSPC is already a bug related to our space reservation code, let's just focus on the error handling. For example, we have the following dirty range [0, 64K) of an inode, with 4K sector size and 4K page size: 0 16K 32K 48K 64K |///////////////////////////////////////| |#######################################| Where |///| means page are still dirty, and |###| means the extent io tree has EXTENT_DELALLOC flag. - Enter extent_writepage() for page 0 - Enter btrfs_run_delalloc_range() for range [0, 64K) - Enter cow_file_range() for range [0, 64K) - Function btrfs_reserve_extent() only reserved one 16K extent So we created extent map and ordered extent for range [0, 16K) 0 16K 32K 48K 64K |////////|//////////////////////////////| |<- OE ->|##############################| And range [0, 16K) has its delalloc flag cleared. But since we haven't yet submit any bio, involved 4 pages are still dirty. - Function btrfs_reserve_extent() returns with -ENOSPC Now we have to run error cleanup, which will clear all EXTENT_DELALLOC* flags and clear the dirty flags for the remaining ranges: 0 16K 32K 48K 64K |////////| | | | | Note that range [0, 16K) still has its pages dirty. - Some time later, writeback is triggered again for the range [0, 16K) since the page range still has dirty flags. - btrfs_run_delalloc_range() will do nothing because there is no EXTENT_DELALLOC flag. - extent_writepage_io() finds page 0 has no ordered flag Which falls into the COW fixup path, triggering the BUG_ON(). Unfortunately this error handling bug dates back to the introduction of btrfs. Thankfully with the abuse of COW fixup, at least it won't crash the kernel. [FIX] Instead of immediately unlocking the extent and folios, we keep the extent and folios locked until either erroring out or the whole delalloc range finished. When the whole delalloc range finished without error, we just unlock the whole range with PAGE_SET_ORDERED (and PAGE_UNLOCK for !keep_locked cases) ---truncated---
CVE-2024-57982: In the Linux kernel, the following vulnerability has been resolved: xfrm: state: fix out-of-bounds read during lookup lookup and resize can run in parallel. The xfrm_state_hash_generation seqlock ensures a retry, but the hash functions can observe a hmask value that is too large for the new hlist array. rehash does: rcu_assign_pointer(net->xfrm.state_bydst, ndst) [..] net->xfrm.state_hmask = nhashmask; While state lookup does: h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { This is only safe in case the update to state_bydst is larger than net->xfrm.xfrm_state_hmask (or if the lookup function gets serialized via state spinlock again). Fix this by prefetching state_hmask and the associated pointers. The xfrm_state_hash_generation seqlock retry will ensure that the pointer and the hmask will be consistent. The existing helpers, like xfrm_dst_hash(), are now unsafe for RCU side, add lockdep assertions to document that they are only safe for insert side. xfrm_state_lookup_byaddr() uses the spinlock rather than RCU. AFAICS this is an oversight from back when state lookup was converted to RCU, this lock should be replaced with RCU in a future patch.
CVE-2024-57984: In the Linux kernel, the following vulnerability has been resolved: i3c: dw: Fix use-after-free in dw_i3c_master driver due to race condition In dw_i3c_common_probe, &master->hj_work is bound with dw_i3c_hj_work. And dw_i3c_master_irq_handler can call dw_i3c_master_irq_handle_ibis function to start the work. If we remove the module which will call dw_i3c_common_remove to make cleanup, it will free master->base through i3c_master_unregister while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | dw_i3c_hj_work dw_i3c_common_remove | i3c_master_unregister(&master->base) | device_unregister(&master->dev) | device_release | //free master->base | | i3c_master_do_daa(&master->base) | //use master->base Fix it by ensuring that the work is canceled before proceeding with the cleanup in dw_i3c_common_remove.
CVE-2024-58012: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda-dai: Ensure DAI widget is valid during params Each cpu DAI should associate with a widget. However, the topology might not create the right number of DAI widgets for aggregated amps. And it will cause NULL pointer deference. Check that the DAI widget associated with the CPU DAI is valid to prevent NULL pointer deference due to missing DAI widgets in topologies with aggregated amps.
CVE-2024-58034: In the Linux kernel, the following vulnerability has been resolved: memory: tegra20-emc: fix an OF node reference bug in tegra_emc_find_node_by_ram_code() As of_find_node_by_name() release the reference of the argument device node, tegra_emc_find_node_by_ram_code() releases some device nodes while still in use, resulting in possible UAFs. According to the bindings and the in-tree DTS files, the "emc-tables" node is always device's child node with the property "nvidia,use-ram-code", and the "lpddr2" node is a child of the "emc-tables" node. Thus utilize the for_each_child_of_node() macro and of_get_child_by_name() instead of of_find_node_by_name() to simplify the code. This bug was found by an experimental verification tool that I am developing. [krzysztof: applied v1, adjust the commit msg to incorporate v2 parts]
CVE-2024-58053: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix handling of received connection abort Fix the handling of a connection abort that we've received. Though the abort is at the connection level, it needs propagating to the calls on that connection. Whilst the propagation bit is performed, the calls aren't then woken up to go and process their termination, and as no further input is forthcoming, they just hang. Also add some tracing for the logging of connection aborts.
CVE-2024-58089: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double accounting race when btrfs_run_delalloc_range() failed [BUG] When running btrfs with block size (4K) smaller than page size (64K, aarch64), there is a very high chance to crash the kernel at generic/750, with the following messages: (before the call traces, there are 3 extra debug messages added) BTRFS warning (device dm-3): read-write for sector size 4096 with page size 65536 is experimental BTRFS info (device dm-3): checking UUID tree hrtimer: interrupt took 5451385 ns BTRFS error (device dm-3): cow_file_range failed, root=4957 inode=257 start=1605632 len=69632: -28 BTRFS error (device dm-3): run_delalloc_nocow failed, root=4957 inode=257 start=1605632 len=69632: -28 BTRFS error (device dm-3): failed to run delalloc range, root=4957 ino=257 folio=1572864 submit_bitmap=8-15 start=1605632 len=69632: -28 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 3020984 at ordered-data.c:360 can_finish_ordered_extent+0x370/0x3b8 [btrfs] CPU: 2 UID: 0 PID: 3020984 Comm: kworker/u24:1 Tainted: G OE 6.13.0-rc1-custom+ #89 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : can_finish_ordered_extent+0x370/0x3b8 [btrfs] lr : can_finish_ordered_extent+0x1ec/0x3b8 [btrfs] Call trace: can_finish_ordered_extent+0x370/0x3b8 [btrfs] (P) can_finish_ordered_extent+0x1ec/0x3b8 [btrfs] (L) btrfs_mark_ordered_io_finished+0x130/0x2b8 [btrfs] extent_writepage+0x10c/0x3b8 [btrfs] extent_write_cache_pages+0x21c/0x4e8 [btrfs] btrfs_writepages+0x94/0x160 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x74/0xa0 start_delalloc_inodes+0x17c/0x3b0 [btrfs] btrfs_start_delalloc_roots+0x17c/0x288 [btrfs] shrink_delalloc+0x11c/0x280 [btrfs] flush_space+0x288/0x328 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x228/0x680 worker_thread+0x1bc/0x360 kthread+0x100/0x118 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1605632 OE len=16384 to_dec=16384 left=0 BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1622016 OE len=12288 to_dec=12288 left=0 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1634304 OE len=8192 to_dec=4096 left=0 CPU: 1 UID: 0 PID: 3286940 Comm: kworker/u24:3 Tainted: G W OE 6.13.0-rc1-custom+ #89 Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: btrfs_work_helper [btrfs] (btrfs-endio-write) pstate: 404000c5 (nZcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : process_one_work+0x110/0x680 lr : worker_thread+0x1bc/0x360 Call trace: process_one_work+0x110/0x680 (P) worker_thread+0x1bc/0x360 (L) worker_thread+0x1bc/0x360 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: f84086a1 f9000fe1 53041c21 b9003361 (f9400661) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs SMP: failed to stop secondary CPUs 2-3 Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: 0x275bb9540000 from 0xffff800080000000 PHYS_OFFSET: 0xffff8fbba0000000 CPU features: 0x100,00000070,00801250,8201720b [CAUSE] The above warning is triggered immediately after the delalloc range failure, this happens in the following sequence: - Range [1568K, 1636K) is dirty 1536K 1568K 1600K 1636K 1664K | |/////////|////////| | Where 1536K, 1600K and 1664K are page boundaries (64K page size) - Enter extent_writepage() for page 1536K - Enter run_delalloc_nocow() with locke ---truncated---
CVE-2024-58093: In the Linux kernel, the following vulnerability has been resolved: PCI/ASPM: Fix link state exit during switch upstream function removal Before 456d8aa37d0f ("PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free"), we would free the ASPM link only after the last function on the bus pertaining to the given link was removed. That was too late. If function 0 is removed before sibling function, link->downstream would point to free'd memory after. After above change, we freed the ASPM parent link state upon any function removal on the bus pertaining to a given link. That is too early. If the link is to a PCIe switch with MFD on the upstream port, then removing functions other than 0 first would free a link which still remains parent_link to the remaining downstream ports. The resulting GPFs are especially frequent during hot-unplug, because pciehp removes devices on the link bus in reverse order. On that switch, function 0 is the virtual P2P bridge to the internal bus. Free exactly when function 0 is removed -- before the parent link is obsolete, but after all subordinate links are gone. [kwilczynski: commit log]
CVE-2024-58094: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before truncation in jfs_truncate_nolock() Added a check for "read-only" mode in the `jfs_truncate_nolock` function to avoid errors related to writing to a read-only filesystem. Call stack: block_write_begin() { jfs_write_failed() { jfs_truncate() { jfs_truncate_nolock() { txEnd() { ... log = JFS_SBI(tblk->sb)->log; // (log == NULL) If the `isReadOnly(ip)` condition is triggered in `jfs_truncate_nolock`, the function execution will stop, and no further data modification will occur. Instead, the `xtTruncate` function will be called with the "COMMIT_WMAP" flag, preventing modifications in "read-only" mode.
CVE-2024-58095: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before txBeginAnon() call Added a read-only check before calling `txBeginAnon` in `extAlloc` and `extRecord`. This prevents modification attempts on a read-only mounted filesystem, avoiding potential errors or crashes. Call trace: txBeginAnon+0xac/0x154 extAlloc+0xe8/0xdec fs/jfs/jfs_extent.c:78 jfs_get_block+0x340/0xb98 fs/jfs/inode.c:248 __block_write_begin_int+0x580/0x166c fs/buffer.c:2128 __block_write_begin fs/buffer.c:2177 [inline] block_write_begin+0x98/0x11c fs/buffer.c:2236 jfs_write_begin+0x44/0x88 fs/jfs/inode.c:299
CVE-2024-58096: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: add srng->lock for ath11k_hal_srng_* in monitor mode ath11k_hal_srng_* should be used with srng->lock to protect srng data. For ath11k_dp_rx_mon_dest_process() and ath11k_dp_full_mon_process_rx(), they use ath11k_hal_srng_* for many times but never call srng->lock. So when running (full) monitor mode, warning will occur: RIP: 0010:ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k] Call Trace: ? ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k] ath11k_dp_rx_process_mon_status+0xc45/0x1190 [ath11k] ? idr_alloc_u32+0x97/0xd0 ath11k_dp_rx_process_mon_rings+0x32a/0x550 [ath11k] ath11k_dp_service_srng+0x289/0x5a0 [ath11k] ath11k_pcic_ext_grp_napi_poll+0x30/0xd0 [ath11k] __napi_poll+0x30/0x1f0 net_rx_action+0x198/0x320 __do_softirq+0xdd/0x319 So add srng->lock for them to avoid such warnings. Inorder to fetch the srng->lock, should change srng's definition from 'void' to 'struct hal_srng'. And initialize them elsewhere to prevent one line of code from being too long. This is consistent with other ring process functions, such as ath11k_dp_process_rx(). Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2024-58097: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix RCU stall while reaping monitor destination ring While processing the monitor destination ring, MSDUs are reaped from the link descriptor based on the corresponding buf_id. However, sometimes the driver cannot obtain a valid buffer corresponding to the buf_id received from the hardware. This causes an infinite loop in the destination processing, resulting in a kernel crash. kernel log: ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309 ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309 ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed Fix this by skipping the problematic buf_id and reaping the next entry, replacing the break with the next MSDU processing. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2024-58098: In the Linux kernel, the following vulnerability has been resolved: bpf: track changes_pkt_data property for global functions When processing calls to certain helpers, verifier invalidates all packet pointers in a current state. For example, consider the following program: __attribute__((__noinline__)) long skb_pull_data(struct __sk_buff *sk, __u32 len) { return bpf_skb_pull_data(sk, len); } SEC("tc") int test_invalidate_checks(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP; skb_pull_data(sk, 0); *p = 42; return TCX_PASS; } After a call to bpf_skb_pull_data() the pointer 'p' can't be used safely. See function filter.c:bpf_helper_changes_pkt_data() for a list of such helpers. At the moment verifier invalidates packet pointers when processing helper function calls, and does not traverse global sub-programs when processing calls to global sub-programs. This means that calls to helpers done from global sub-programs do not invalidate pointers in the caller state. E.g. the program above is unsafe, but is not rejected by verifier. This commit fixes the omission by computing field bpf_subprog_info->changes_pkt_data for each sub-program before main verification pass. changes_pkt_data should be set if: - subprogram calls helper for which bpf_helper_changes_pkt_data returns true; - subprogram calls a global function, for which bpf_subprog_info->changes_pkt_data should be set. The verifier.c:check_cfg() pass is modified to compute this information. The commit relies on depth first instruction traversal done by check_cfg() and absence of recursive function calls: - check_cfg() would eventually visit every call to subprogram S in a state when S is fully explored; - when S is fully explored: - every direct helper call within S is explored (and thus changes_pkt_data is set if needed); - every call to subprogram S1 called by S was visited with S1 fully explored (and thus S inherits changes_pkt_data from S1). The downside of such approach is that dead code elimination is not taken into account: if a helper call inside global function is dead because of current configuration, verifier would conservatively assume that the call occurs for the purpose of the changes_pkt_data computation.
CVE-2024-58100: In the Linux kernel, the following vulnerability has been resolved: bpf: check changes_pkt_data property for extension programs When processing calls to global sub-programs, verifier decides whether to invalidate all packet pointers in current state depending on the changes_pkt_data property of the global sub-program. Because of this, an extension program replacing a global sub-program must be compatible with changes_pkt_data property of the sub-program being replaced. This commit: - adds changes_pkt_data flag to struct bpf_prog_aux: - this flag is set in check_cfg() for main sub-program; - in jit_subprogs() for other sub-programs; - modifies bpf_check_attach_btf_id() to check changes_pkt_data flag; - moves call to check_attach_btf_id() after the call to check_cfg(), because it needs changes_pkt_data flag to be set: bpf_check: ... ... - check_attach_btf_id resolve_pseudo_ldimm64 resolve_pseudo_ldimm64 --> bpf_prog_is_offloaded bpf_prog_is_offloaded check_cfg check_cfg + check_attach_btf_id ... ... The following fields are set by check_attach_btf_id(): - env->ops - prog->aux->attach_btf_trace - prog->aux->attach_func_name - prog->aux->attach_func_proto - prog->aux->dst_trampoline - prog->aux->mod - prog->aux->saved_dst_attach_type - prog->aux->saved_dst_prog_type - prog->expected_attach_type Neither of these fields are used by resolve_pseudo_ldimm64() or bpf_prog_offload_verifier_prep() (for netronome and netdevsim drivers), so the reordering is safe.
CVE-2024-58237: In the Linux kernel, the following vulnerability has been resolved: bpf: consider that tail calls invalidate packet pointers Tail-called programs could execute any of the helpers that invalidate packet pointers. Hence, conservatively assume that each tail call invalidates packet pointers. Making the change in bpf_helper_changes_pkt_data() automatically makes use of check_cfg() logic that computes 'changes_pkt_data' effect for global sub-programs, such that the following program could be rejected: int tail_call(struct __sk_buff *sk) { bpf_tail_call_static(sk, &jmp_table, 0); return 0; } SEC("tc") int not_safe(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; ... make p valid ... tail_call(sk); *p = 42; /* this is unsafe */ ... } The tc_bpf2bpf.c:subprog_tc() needs change: mark it as a function that can invalidate packet pointers. Otherwise, it can't be freplaced with tailcall_freplace.c:entry_freplace() that does a tail call.
CVE-2024-58240: In the Linux kernel, the following vulnerability has been resolved: tls: separate no-async decryption request handling from async If we're not doing async, the handling is much simpler. There's no reference counting, we just need to wait for the completion to wake us up and return its result. We should preferably also use a separate crypto_wait. I'm not seeing a UAF as I did in the past, I think aec7961916f3 ("tls: fix race between async notify and socket close") took care of it. This will make the next fix easier.
CVE-2024-58241: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: Disable works on hci_unregister_dev This make use of disable_work_* on hci_unregister_dev since the hci_dev is about to be freed new submissions are not disarable.
CVE-2025-21629: In the Linux kernel, the following vulnerability has been resolved: net: reenable NETIF_F_IPV6_CSUM offload for BIG TCP packets The blamed commit disabled hardware offoad of IPv6 packets with extension headers on devices that advertise NETIF_F_IPV6_CSUM, based on the definition of that feature in skbuff.h: * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). The change causes skb_warn_bad_offload to fire for BIG TCP packets. [ 496.310233] WARNING: CPU: 13 PID: 23472 at net/core/dev.c:3129 skb_warn_bad_offload+0xc4/0xe0 [ 496.310297] ? skb_warn_bad_offload+0xc4/0xe0 [ 496.310300] skb_checksum_help+0x129/0x1f0 [ 496.310303] skb_csum_hwoffload_help+0x150/0x1b0 [ 496.310306] validate_xmit_skb+0x159/0x270 [ 496.310309] validate_xmit_skb_list+0x41/0x70 [ 496.310312] sch_direct_xmit+0x5c/0x250 [ 496.310317] __qdisc_run+0x388/0x620 BIG TCP introduced an IPV6_TLV_JUMBO IPv6 extension header to communicate packet length, as this is an IPv6 jumbogram. But, the feature is only enabled on devices that support BIG TCP TSO. The header is only present for PF_PACKET taps like tcpdump, and not transmitted by physical devices. For this specific case of extension headers that are not transmitted, return to the situation before the blamed commit and support hardware offload. ipv6_has_hopopt_jumbo() tests not only whether this header is present, but also that it is the only extension header before a terminal (L4) header.
CVE-2025-21634: In the Linux kernel, the following vulnerability has been resolved: cgroup/cpuset: remove kernfs active break A warning was found: WARNING: CPU: 10 PID: 3486953 at fs/kernfs/file.c:828 CPU: 10 PID: 3486953 Comm: rmdir Kdump: loaded Tainted: G RIP: 0010:kernfs_should_drain_open_files+0x1a1/0x1b0 RSP: 0018:ffff8881107ef9e0 EFLAGS: 00010202 RAX: 0000000080000002 RBX: ffff888154738c00 RCX: dffffc0000000000 RDX: 0000000000000007 RSI: 0000000000000004 RDI: ffff888154738c04 RBP: ffff888154738c04 R08: ffffffffaf27fa15 R09: ffffed102a8e7180 R10: ffff888154738c07 R11: 0000000000000000 R12: ffff888154738c08 R13: ffff888750f8c000 R14: ffff888750f8c0e8 R15: ffff888154738ca0 FS: 00007f84cd0be740(0000) GS:ffff8887ddc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555f9fbe00c8 CR3: 0000000153eec001 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: kernfs_drain+0x15e/0x2f0 __kernfs_remove+0x165/0x300 kernfs_remove_by_name_ns+0x7b/0xc0 cgroup_rm_file+0x154/0x1c0 cgroup_addrm_files+0x1c2/0x1f0 css_clear_dir+0x77/0x110 kill_css+0x4c/0x1b0 cgroup_destroy_locked+0x194/0x380 cgroup_rmdir+0x2a/0x140 It can be explained by: rmdir echo 1 > cpuset.cpus kernfs_fop_write_iter // active=0 cgroup_rm_file kernfs_remove_by_name_ns kernfs_get_active // active=1 __kernfs_remove // active=0x80000002 kernfs_drain cpuset_write_resmask wait_event //waiting (active == 0x80000001) kernfs_break_active_protection // active = 0x80000001 // continue kernfs_unbreak_active_protection // active = 0x80000002 ... kernfs_should_drain_open_files // warning occurs kernfs_put_active This warning is caused by 'kernfs_break_active_protection' when it is writing to cpuset.cpus, and the cgroup is removed concurrently. The commit 3a5a6d0c2b03 ("cpuset: don't nest cgroup_mutex inside get_online_cpus()") made cpuset_hotplug_workfn asynchronous, This change involves calling flush_work(), which can create a multiple processes circular locking dependency that involve cgroup_mutex, potentially leading to a deadlock. To avoid deadlock. the commit 76bb5ab8f6e3 ("cpuset: break kernfs active protection in cpuset_write_resmask()") added 'kernfs_break_active_protection' in the cpuset_write_resmask. This could lead to this warning. After the commit 2125c0034c5d ("cgroup/cpuset: Make cpuset hotplug processing synchronous"), the cpuset_write_resmask no longer needs to wait the hotplug to finish, which means that concurrent hotplug and cpuset operations are no longer possible. Therefore, the deadlock doesn't exist anymore and it does not have to 'break active protection' now. To fix this warning, just remove kernfs_break_active_protection operation in the 'cpuset_write_resmask'.
CVE-2025-21635: In the Linux kernel, the following vulnerability has been resolved: rds: sysctl: rds_tcp_{rcv,snd}buf: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The per-netns structure can be obtained from the table->data using container_of(), then the 'net' one can be retrieved from the listen socket (if available).
CVE-2025-21651: In the Linux kernel, the following vulnerability has been resolved: net: hns3: don't auto enable misc vector Currently, there is a time window between misc irq enabled and service task inited. If an interrupte is reported at this time, it will cause warning like below: [ 16.324639] Call trace: [ 16.324641] __queue_delayed_work+0xb8/0xe0 [ 16.324643] mod_delayed_work_on+0x78/0xd0 [ 16.324655] hclge_errhand_task_schedule+0x58/0x90 [hclge] [ 16.324662] hclge_misc_irq_handle+0x168/0x240 [hclge] [ 16.324666] __handle_irq_event_percpu+0x64/0x1e0 [ 16.324667] handle_irq_event+0x80/0x170 [ 16.324670] handle_fasteoi_edge_irq+0x110/0x2bc [ 16.324671] __handle_domain_irq+0x84/0xfc [ 16.324673] gic_handle_irq+0x88/0x2c0 [ 16.324674] el1_irq+0xb8/0x140 [ 16.324677] arch_cpu_idle+0x18/0x40 [ 16.324679] default_idle_call+0x5c/0x1bc [ 16.324682] cpuidle_idle_call+0x18c/0x1c4 [ 16.324684] do_idle+0x174/0x17c [ 16.324685] cpu_startup_entry+0x30/0x6c [ 16.324687] secondary_start_kernel+0x1a4/0x280 [ 16.324688] ---[ end trace 6aa0bff672a964aa ]--- So don't auto enable misc vector when request irq..
CVE-2025-21656: In the Linux kernel, the following vulnerability has been resolved: hwmon: (drivetemp) Fix driver producing garbage data when SCSI errors occur scsi_execute_cmd() function can return both negative (linux codes) and positive (scsi_cmnd result field) error codes. Currently the driver just passes error codes of scsi_execute_cmd() to hwmon core, which is incorrect because hwmon only checks for negative error codes. This leads to hwmon reporting uninitialized data to userspace in case of SCSI errors (for example if the disk drive was disconnected). This patch checks scsi_execute_cmd() output and returns -EIO if it's error code is positive. [groeck: Avoid inline variable declaration for portability]
CVE-2025-21682: In the Linux kernel, the following vulnerability has been resolved: eth: bnxt: always recalculate features after XDP clearing, fix null-deref Recalculate features when XDP is detached. Before: # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp # ip li set dev eth0 xdp off # ethtool -k eth0 | grep gro rx-gro-hw: off [requested on] After: # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp # ip li set dev eth0 xdp off # ethtool -k eth0 | grep gro rx-gro-hw: on The fact that HW-GRO doesn't get re-enabled automatically is just a minor annoyance. The real issue is that the features will randomly come back during another reconfiguration which just happens to invoke netdev_update_features(). The driver doesn't handle reconfiguring two things at a time very robustly. Starting with commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in __bnxt_reserve_rings()") we only reconfigure the RSS hash table if the "effective" number of Rx rings has changed. If HW-GRO is enabled "effective" number of rings is 2x what user sees. So if we are in the bad state, with HW-GRO re-enablement "pending" after XDP off, and we lower the rings by / 2 - the HW-GRO rings doing 2x and the ethtool -L doing / 2 may cancel each other out, and the: if (old_rx_rings != bp->hw_resc.resv_rx_rings && condition in __bnxt_reserve_rings() will be false. The RSS map won't get updated, and we'll crash with: BUG: kernel NULL pointer dereference, address: 0000000000000168 RIP: 0010:__bnxt_hwrm_vnic_set_rss+0x13a/0x1a0 bnxt_hwrm_vnic_rss_cfg_p5+0x47/0x180 __bnxt_setup_vnic_p5+0x58/0x110 bnxt_init_nic+0xb72/0xf50 __bnxt_open_nic+0x40d/0xab0 bnxt_open_nic+0x2b/0x60 ethtool_set_channels+0x18c/0x1d0 As we try to access a freed ring. The issue is present since XDP support was added, really, but prior to commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in __bnxt_reserve_rings()") it wasn't causing major issues.
CVE-2025-21690: In the Linux kernel, the following vulnerability has been resolved: scsi: storvsc: Ratelimit warning logs to prevent VM denial of service If there's a persistent error in the hypervisor, the SCSI warning for failed I/O can flood the kernel log and max out CPU utilization, preventing troubleshooting from the VM side. Ratelimit the warning so it doesn't DoS the VM.
CVE-2025-21696: In the Linux kernel, the following vulnerability has been resolved: mm: clear uffd-wp PTE/PMD state on mremap() When mremap()ing a memory region previously registered with userfaultfd as write-protected but without UFFD_FEATURE_EVENT_REMAP, an inconsistency in flag clearing leads to a mismatch between the vma flags (which have uffd-wp cleared) and the pte/pmd flags (which do not have uffd-wp cleared). This mismatch causes a subsequent mprotect(PROT_WRITE) to trigger a warning in page_table_check_pte_flags() due to setting the pte to writable while uffd-wp is still set. Fix this by always explicitly clearing the uffd-wp pte/pmd flags on any such mremap() so that the values are consistent with the existing clearing of VM_UFFD_WP. Be careful to clear the logical flag regardless of its physical form; a PTE bit, a swap PTE bit, or a PTE marker. Cover PTE, huge PMD and hugetlb paths.
CVE-2025-21701: In the Linux kernel, the following vulnerability has been resolved: net: avoid race between device unregistration and ethnl ops The following trace can be seen if a device is being unregistered while its number of channels are being modified. DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 3754 at kernel/locking/mutex.c:564 __mutex_lock+0xc8a/0x1120 CPU: 3 UID: 0 PID: 3754 Comm: ethtool Not tainted 6.13.0-rc6+ #771 RIP: 0010:__mutex_lock+0xc8a/0x1120 Call Trace: <TASK> ethtool_check_max_channel+0x1ea/0x880 ethnl_set_channels+0x3c3/0xb10 ethnl_default_set_doit+0x306/0x650 genl_family_rcv_msg_doit+0x1e3/0x2c0 genl_rcv_msg+0x432/0x6f0 netlink_rcv_skb+0x13d/0x3b0 genl_rcv+0x28/0x40 netlink_unicast+0x42e/0x720 netlink_sendmsg+0x765/0xc20 __sys_sendto+0x3ac/0x420 __x64_sys_sendto+0xe0/0x1c0 do_syscall_64+0x95/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e This is because unregister_netdevice_many_notify might run before the rtnl lock section of ethnl operations, eg. set_channels in the above example. In this example the rss lock would be destroyed by the device unregistration path before being used again, but in general running ethnl operations while dismantle has started is not a good idea. Fix this by denying any operation on devices being unregistered. A check was already there in ethnl_ops_begin, but not wide enough. Note that the same issue cannot be seen on the ioctl version (__dev_ethtool) because the device reference is retrieved from within the rtnl lock section there. Once dismantle started, the net device is unlisted and no reference will be found.
CVE-2025-21712: In the Linux kernel, the following vulnerability has been resolved: md/md-bitmap: Synchronize bitmap_get_stats() with bitmap lifetime After commit ec6bb299c7c3 ("md/md-bitmap: add 'sync_size' into struct md_bitmap_stats"), following panic is reported: Oops: general protection fault, probably for non-canonical address RIP: 0010:bitmap_get_stats+0x2b/0xa0 Call Trace: <TASK> md_seq_show+0x2d2/0x5b0 seq_read_iter+0x2b9/0x470 seq_read+0x12f/0x180 proc_reg_read+0x57/0xb0 vfs_read+0xf6/0x380 ksys_read+0x6c/0xf0 do_syscall_64+0x82/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Root cause is that bitmap_get_stats() can be called at anytime if mddev is still there, even if bitmap is destroyed, or not fully initialized. Deferenceing bitmap in this case can crash the kernel. Meanwhile, the above commit start to deferencing bitmap->storage, make the problem easier to trigger. Fix the problem by protecting bitmap_get_stats() with bitmap_info.mutex.
CVE-2025-21714: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix implicit ODP use after free Prevent double queueing of implicit ODP mr destroy work by using __xa_cmpxchg() to make sure this is the only time we are destroying this specific mr. Without this change, we could try to invalidate this mr twice, which in turn could result in queuing a MR work destroy twice, and eventually the second work could execute after the MR was freed due to the first work, causing a user after free and trace below. refcount_t: underflow; use-after-free. WARNING: CPU: 2 PID: 12178 at lib/refcount.c:28 refcount_warn_saturate+0x12b/0x130 Modules linked in: bonding ib_ipoib vfio_pci ip_gre geneve nf_tables ip6_gre gre ip6_tunnel tunnel6 ipip tunnel4 ib_umad rdma_ucm mlx5_vfio_pci vfio_pci_core vfio_iommu_type1 mlx5_ib vfio ib_uverbs mlx5_core iptable_raw openvswitch nsh rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay zram zsmalloc fuse [last unloaded: ib_uverbs] CPU: 2 PID: 12178 Comm: kworker/u20:5 Not tainted 6.5.0-rc1_net_next_mlx5_58c644e #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: events_unbound free_implicit_child_mr_work [mlx5_ib] RIP: 0010:refcount_warn_saturate+0x12b/0x130 Code: 48 c7 c7 38 95 2a 82 c6 05 bc c6 fe 00 01 e8 0c 66 aa ff 0f 0b 5b c3 48 c7 c7 e0 94 2a 82 c6 05 a7 c6 fe 00 01 e8 f5 65 aa ff <0f> 0b 5b c3 90 8b 07 3d 00 00 00 c0 74 12 83 f8 01 74 13 8d 50 ff RSP: 0018:ffff8881008e3e40 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000027 RDX: ffff88852c91b5c8 RSI: 0000000000000001 RDI: ffff88852c91b5c0 RBP: ffff8881dacd4e00 R08: 00000000ffffffff R09: 0000000000000019 R10: 000000000000072e R11: 0000000063666572 R12: ffff88812bfd9e00 R13: ffff8881c792d200 R14: ffff88810011c005 R15: ffff8881002099c0 FS: 0000000000000000(0000) GS:ffff88852c900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f5694b5e000 CR3: 00000001153f6003 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? refcount_warn_saturate+0x12b/0x130 free_implicit_child_mr_work+0x180/0x1b0 [mlx5_ib] process_one_work+0x1cc/0x3c0 worker_thread+0x218/0x3c0 kthread+0xc6/0xf0 ret_from_fork+0x1f/0x30 </TASK>
CVE-2025-21734: In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: Fix copy buffer page size For non-registered buffer, fastrpc driver copies the buffer and pass it to the remote subsystem. There is a problem with current implementation of page size calculation which is not considering the offset in the calculation. This might lead to passing of improper and out-of-bounds page size which could result in memory issue. Calculate page start and page end using the offset adjusted address instead of absolute address.
CVE-2025-21738: In the Linux kernel, the following vulnerability has been resolved: ata: libata-sff: Ensure that we cannot write outside the allocated buffer reveliofuzzing reported that a SCSI_IOCTL_SEND_COMMAND ioctl with out_len set to 0xd42, SCSI command set to ATA_16 PASS-THROUGH, ATA command set to ATA_NOP, and protocol set to ATA_PROT_PIO, can cause ata_pio_sector() to write outside the allocated buffer, overwriting random memory. While a ATA device is supposed to abort a ATA_NOP command, there does seem to be a bug either in libata-sff or QEMU, where either this status is not set, or the status is cleared before read by ata_sff_hsm_move(). Anyway, that is most likely a separate bug. Looking at __atapi_pio_bytes(), it already has a safety check to ensure that __atapi_pio_bytes() cannot write outside the allocated buffer. Add a similar check to ata_pio_sector(), such that also ata_pio_sector() cannot write outside the allocated buffer.
CVE-2025-21750: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmfmac: Check the return value of of_property_read_string_index() Somewhen between 6.10 and 6.11 the driver started to crash on my MacBookPro14,3. The property doesn't exist and 'tmp' remains uninitialized, so we pass a random pointer to devm_kstrdup(). The crash I am getting looks like this: BUG: unable to handle page fault for address: 00007f033c669379 PF: supervisor read access in kernel mode PF: error_code(0x0001) - permissions violation PGD 8000000101341067 P4D 8000000101341067 PUD 101340067 PMD 1013bb067 PTE 800000010aee9025 Oops: Oops: 0001 [#1] SMP PTI CPU: 4 UID: 0 PID: 827 Comm: (udev-worker) Not tainted 6.11.8-gentoo #1 Hardware name: Apple Inc. MacBookPro14,3/Mac-551B86E5744E2388, BIOS 529.140.2.0.0 06/23/2024 RIP: 0010:strlen+0x4/0x30 Code: f7 75 ec 31 c0 c3 cc cc cc cc 48 89 f8 c3 cc cc cc cc 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa <80> 3f 00 74 14 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 cc RSP: 0018:ffffb4aac0683ad8 EFLAGS: 00010202 RAX: 00000000ffffffea RBX: 00007f033c669379 RCX: 0000000000000001 RDX: 0000000000000cc0 RSI: 00007f033c669379 RDI: 00007f033c669379 RBP: 00000000ffffffea R08: 0000000000000000 R09: 00000000c0ba916a R10: ffffffffffffffff R11: ffffffffb61ea260 R12: ffff91f7815b50c8 R13: 0000000000000cc0 R14: ffff91fafefffe30 R15: ffffb4aac0683b30 FS: 00007f033ccbe8c0(0000) GS:ffff91faeed00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f033c669379 CR3: 0000000107b1e004 CR4: 00000000003706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x149/0x4c0 ? raw_spin_rq_lock_nested+0xe/0x20 ? sched_balance_newidle+0x22b/0x3c0 ? update_load_avg+0x78/0x770 ? exc_page_fault+0x6f/0x150 ? asm_exc_page_fault+0x26/0x30 ? __pfx_pci_conf1_write+0x10/0x10 ? strlen+0x4/0x30 devm_kstrdup+0x25/0x70 brcmf_of_probe+0x273/0x350 [brcmfmac]
CVE-2025-21758: In the Linux kernel, the following vulnerability has been resolved: ipv6: mcast: add RCU protection to mld_newpack() mld_newpack() can be called without RTNL or RCU being held. Note that we no longer can use sock_alloc_send_skb() because ipv6.igmp_sk uses GFP_KERNEL allocations which can sleep. Instead use alloc_skb() and charge the net->ipv6.igmp_sk socket under RCU protection.
CVE-2025-21759: In the Linux kernel, the following vulnerability has been resolved: ipv6: mcast: extend RCU protection in igmp6_send() igmp6_send() can be called without RTNL or RCU being held. Extend RCU protection so that we can safely fetch the net pointer and avoid a potential UAF. Note that we no longer can use sock_alloc_send_skb() because ipv6.igmp_sk uses GFP_KERNEL allocations which can sleep. Instead use alloc_skb() and charge the net->ipv6.igmp_sk socket under RCU protection.
CVE-2025-21766: In the Linux kernel, the following vulnerability has been resolved: ipv4: use RCU protection in __ip_rt_update_pmtu() __ip_rt_update_pmtu() must use RCU protection to make sure the net structure it reads does not disappear.
CVE-2025-21768: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix dst ref loops in rpl, seg6 and ioam6 lwtunnels Some lwtunnels have a dst cache for post-transformation dst. If the packet destination did not change we may end up recording a reference to the lwtunnel in its own cache, and the lwtunnel state will never be freed. Discovered by the ioam6.sh test, kmemleak was recently fixed to catch per-cpu memory leaks. I'm not sure if rpl and seg6 can actually hit this, but in principle I don't see why not.
CVE-2025-21780: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: avoid buffer overflow attach in smu_sys_set_pp_table() It malicious user provides a small pptable through sysfs and then a bigger pptable, it may cause buffer overflow attack in function smu_sys_set_pp_table().
CVE-2025-21792: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix refcount leak caused by setting SO_BINDTODEVICE sockopt If an AX25 device is bound to a socket by setting the SO_BINDTODEVICE socket option, a refcount leak will occur in ax25_release(). Commit 9fd75b66b8f6 ("ax25: Fix refcount leaks caused by ax25_cb_del()") added decrement of device refcounts in ax25_release(). In order for that to work correctly the refcounts must already be incremented when the device is bound to the socket. An AX25 device can be bound to a socket by either calling ax25_bind() or setting SO_BINDTODEVICE socket option. In both cases the refcounts should be incremented, but in fact it is done only in ax25_bind(). This bug leads to the following issue reported by Syzkaller: ================================================================ refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 1 PID: 5932 at lib/refcount.c:31 refcount_warn_saturate+0x1ed/0x210 lib/refcount.c:31 Modules linked in: CPU: 1 UID: 0 PID: 5932 Comm: syz-executor424 Not tainted 6.13.0-rc4-syzkaller-00110-g4099a71718b0 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:refcount_warn_saturate+0x1ed/0x210 lib/refcount.c:31 Call Trace: <TASK> __refcount_dec include/linux/refcount.h:336 [inline] refcount_dec include/linux/refcount.h:351 [inline] ref_tracker_free+0x710/0x820 lib/ref_tracker.c:236 netdev_tracker_free include/linux/netdevice.h:4156 [inline] netdev_put include/linux/netdevice.h:4173 [inline] netdev_put include/linux/netdevice.h:4169 [inline] ax25_release+0x33f/0xa10 net/ax25/af_ax25.c:1069 __sock_release+0xb0/0x270 net/socket.c:640 sock_close+0x1c/0x30 net/socket.c:1408 ... do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f ... </TASK> ================================================================ Fix the implementation of ax25_setsockopt() by adding increment of refcounts for the new device bound, and decrement of refcounts for the old unbound device.
CVE-2025-21801: In the Linux kernel, the following vulnerability has been resolved: net: ravb: Fix missing rtnl lock in suspend/resume path Fix the suspend/resume path by ensuring the rtnl lock is held where required. Calls to ravb_open, ravb_close and wol operations must be performed under the rtnl lock to prevent conflicts with ongoing ndo operations. Without this fix, the following warning is triggered: [ 39.032969] ============================= [ 39.032983] WARNING: suspicious RCU usage [ 39.033019] ----------------------------- [ 39.033033] drivers/net/phy/phy_device.c:2004 suspicious rcu_dereference_protected() usage! ... [ 39.033597] stack backtrace: [ 39.033613] CPU: 0 UID: 0 PID: 174 Comm: python3 Not tainted 6.13.0-rc7-next-20250116-arm64-renesas-00002-g35245dfdc62c #7 [ 39.033623] Hardware name: Renesas SMARC EVK version 2 based on r9a08g045s33 (DT) [ 39.033628] Call trace: [ 39.033633] show_stack+0x14/0x1c (C) [ 39.033652] dump_stack_lvl+0xb4/0xc4 [ 39.033664] dump_stack+0x14/0x1c [ 39.033671] lockdep_rcu_suspicious+0x16c/0x22c [ 39.033682] phy_detach+0x160/0x190 [ 39.033694] phy_disconnect+0x40/0x54 [ 39.033703] ravb_close+0x6c/0x1cc [ 39.033714] ravb_suspend+0x48/0x120 [ 39.033721] dpm_run_callback+0x4c/0x14c [ 39.033731] device_suspend+0x11c/0x4dc [ 39.033740] dpm_suspend+0xdc/0x214 [ 39.033748] dpm_suspend_start+0x48/0x60 [ 39.033758] suspend_devices_and_enter+0x124/0x574 [ 39.033769] pm_suspend+0x1ac/0x274 [ 39.033778] state_store+0x88/0x124 [ 39.033788] kobj_attr_store+0x14/0x24 [ 39.033798] sysfs_kf_write+0x48/0x6c [ 39.033808] kernfs_fop_write_iter+0x118/0x1a8 [ 39.033817] vfs_write+0x27c/0x378 [ 39.033825] ksys_write+0x64/0xf4 [ 39.033833] __arm64_sys_write+0x18/0x20 [ 39.033841] invoke_syscall+0x44/0x104 [ 39.033852] el0_svc_common.constprop.0+0xb4/0xd4 [ 39.033862] do_el0_svc+0x18/0x20 [ 39.033870] el0_svc+0x3c/0xf0 [ 39.033880] el0t_64_sync_handler+0xc0/0xc4 [ 39.033888] el0t_64_sync+0x154/0x158 [ 39.041274] ravb 11c30000.ethernet eth0: Link is Down
CVE-2025-21812: In the Linux kernel, the following vulnerability has been resolved: ax25: rcu protect dev->ax25_ptr syzbot found a lockdep issue [1]. We should remove ax25 RTNL dependency in ax25_setsockopt() This should also fix a variety of possible UAF in ax25. [1] WARNING: possible circular locking dependency detected 6.13.0-rc3-syzkaller-00762-g9268abe611b0 #0 Not tainted ------------------------------------------------------ syz.5.1818/12806 is trying to acquire lock: ffffffff8fcb3988 (rtnl_mutex){+.+.}-{4:4}, at: ax25_setsockopt+0xa55/0xe90 net/ax25/af_ax25.c:680 but task is already holding lock: ffff8880617ac258 (sk_lock-AF_AX25){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1618 [inline] ffff8880617ac258 (sk_lock-AF_AX25){+.+.}-{0:0}, at: ax25_setsockopt+0x209/0xe90 net/ax25/af_ax25.c:574 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (sk_lock-AF_AX25){+.+.}-{0:0}: lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5849 lock_sock_nested+0x48/0x100 net/core/sock.c:3642 lock_sock include/net/sock.h:1618 [inline] ax25_kill_by_device net/ax25/af_ax25.c:101 [inline] ax25_device_event+0x24d/0x580 net/ax25/af_ax25.c:146 notifier_call_chain+0x1a5/0x3f0 kernel/notifier.c:85 __dev_notify_flags+0x207/0x400 dev_change_flags+0xf0/0x1a0 net/core/dev.c:9026 dev_ifsioc+0x7c8/0xe70 net/core/dev_ioctl.c:563 dev_ioctl+0x719/0x1340 net/core/dev_ioctl.c:820 sock_do_ioctl+0x240/0x460 net/socket.c:1234 sock_ioctl+0x626/0x8e0 net/socket.c:1339 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf5/0x170 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #0 (rtnl_mutex){+.+.}-{4:4}: check_prev_add kernel/locking/lockdep.c:3161 [inline] check_prevs_add kernel/locking/lockdep.c:3280 [inline] validate_chain+0x18ef/0x5920 kernel/locking/lockdep.c:3904 __lock_acquire+0x1397/0x2100 kernel/locking/lockdep.c:5226 lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5849 __mutex_lock_common kernel/locking/mutex.c:585 [inline] __mutex_lock+0x1ac/0xee0 kernel/locking/mutex.c:735 ax25_setsockopt+0xa55/0xe90 net/ax25/af_ax25.c:680 do_sock_setsockopt+0x3af/0x720 net/socket.c:2324 __sys_setsockopt net/socket.c:2349 [inline] __do_sys_setsockopt net/socket.c:2355 [inline] __se_sys_setsockopt net/socket.c:2352 [inline] __x64_sys_setsockopt+0x1ee/0x280 net/socket.c:2352 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(sk_lock-AF_AX25); lock(rtnl_mutex); lock(sk_lock-AF_AX25); lock(rtnl_mutex); *** DEADLOCK *** 1 lock held by syz.5.1818/12806: #0: ffff8880617ac258 (sk_lock-AF_AX25){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1618 [inline] #0: ffff8880617ac258 (sk_lock-AF_AX25){+.+.}-{0:0}, at: ax25_setsockopt+0x209/0xe90 net/ax25/af_ax25.c:574 stack backtrace: CPU: 1 UID: 0 PID: 12806 Comm: syz.5.1818 Not tainted 6.13.0-rc3-syzkaller-00762-g9268abe611b0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_circular_bug+0x13a/0x1b0 kernel/locking/lockdep.c:2074 check_noncircular+0x36a/0x4a0 kernel/locking/lockdep.c:2206 check_prev_add kernel/locking/lockdep.c:3161 [inline] check_prevs_add kernel/lockin ---truncated---
CVE-2025-21816: In the Linux kernel, the following vulnerability has been resolved: hrtimers: Force migrate away hrtimers queued after CPUHP_AP_HRTIMERS_DYING hrtimers are migrated away from the dying CPU to any online target at the CPUHP_AP_HRTIMERS_DYING stage in order not to delay bandwidth timers handling tasks involved in the CPU hotplug forward progress. However wakeups can still be performed by the outgoing CPU after CPUHP_AP_HRTIMERS_DYING. Those can result again in bandwidth timers being armed. Depending on several considerations (crystal ball power management based election, earliest timer already enqueued, timer migration enabled or not), the target may eventually be the current CPU even if offline. If that happens, the timer is eventually ignored. The most notable example is RCU which had to deal with each and every of those wake-ups by deferring them to an online CPU, along with related workarounds: _ e787644caf76 (rcu: Defer RCU kthreads wakeup when CPU is dying) _ 9139f93209d1 (rcu/nocb: Fix RT throttling hrtimer armed from offline CPU) _ f7345ccc62a4 (rcu/nocb: Fix rcuog wake-up from offline softirq) The problem isn't confined to RCU though as the stop machine kthread (which runs CPUHP_AP_HRTIMERS_DYING) reports its completion at the end of its work through cpu_stop_signal_done() and performs a wake up that eventually arms the deadline server timer: WARNING: CPU: 94 PID: 588 at kernel/time/hrtimer.c:1086 hrtimer_start_range_ns+0x289/0x2d0 CPU: 94 UID: 0 PID: 588 Comm: migration/94 Not tainted Stopper: multi_cpu_stop+0x0/0x120 <- stop_machine_cpuslocked+0x66/0xc0 RIP: 0010:hrtimer_start_range_ns+0x289/0x2d0 Call Trace: <TASK> start_dl_timer enqueue_dl_entity dl_server_start enqueue_task_fair enqueue_task ttwu_do_activate try_to_wake_up complete cpu_stopper_thread Instead of providing yet another bandaid to work around the situation, fix it in the hrtimers infrastructure instead: always migrate away a timer to an online target whenever it is enqueued from an offline CPU. This will also allow to revert all the above RCU disgraceful hacks.
CVE-2025-21820: In the Linux kernel, the following vulnerability has been resolved: tty: xilinx_uartps: split sysrq handling lockdep detects the following circular locking dependency: CPU 0 CPU 1 ========================== ============================ cdns_uart_isr() printk() uart_port_lock(port) console_lock() cdns_uart_console_write() if (!port->sysrq) uart_port_lock(port) uart_handle_break() port->sysrq = ... uart_handle_sysrq_char() printk() console_lock() The fixed commit attempts to avoid this situation by only taking the port lock in cdns_uart_console_write if port->sysrq unset. However, if (as shown above) cdns_uart_console_write runs before port->sysrq is set, then it will try to take the port lock anyway. This may result in a deadlock. Fix this by splitting sysrq handling into two parts. We use the prepare helper under the port lock and defer handling until we release the lock.
CVE-2025-21831: In the Linux kernel, the following vulnerability has been resolved: PCI: Avoid putting some root ports into D3 on TUXEDO Sirius Gen1 commit 9d26d3a8f1b0 ("PCI: Put PCIe ports into D3 during suspend") sets the policy that all PCIe ports are allowed to use D3. When the system is suspended if the port is not power manageable by the platform and won't be used for wakeup via a PME this sets up the policy for these ports to go into D3hot. This policy generally makes sense from an OSPM perspective but it leads to problems with wakeup from suspend on the TUXEDO Sirius 16 Gen 1 with a specific old BIOS. This manifests as a system hang. On the affected Device + BIOS combination, add a quirk for the root port of the problematic controller to ensure that these root ports are not put into D3hot at suspend. This patch is based on https://lore.kernel.org/linux-pci/20230708214457.1229-2-mario.limonciello@amd.com but with the added condition both in the documentation and in the code to apply only to the TUXEDO Sirius 16 Gen 1 with a specific old BIOS and only the affected root ports.
CVE-2025-21838: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: core: flush gadget workqueue after device removal device_del() can lead to new work being scheduled in gadget->work workqueue. This is observed, for example, with the dwc3 driver with the following call stack: device_del() gadget_unbind_driver() usb_gadget_disconnect_locked() dwc3_gadget_pullup() dwc3_gadget_soft_disconnect() usb_gadget_set_state() schedule_work(&gadget->work) Move flush_work() after device_del() to ensure the workqueue is cleaned up.
CVE-2025-21839: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Load DR6 with guest value only before entering .vcpu_run() loop Move the conditional loading of hardware DR6 with the guest's DR6 value out of the core .vcpu_run() loop to fix a bug where KVM can load hardware with a stale vcpu->arch.dr6. When the guest accesses a DR and host userspace isn't debugging the guest, KVM disables DR interception and loads the guest's values into hardware on VM-Enter and saves them on VM-Exit. This allows the guest to access DRs at will, e.g. so that a sequence of DR accesses to configure a breakpoint only generates one VM-Exit. For DR0-DR3, the logic/behavior is identical between VMX and SVM, and also identical between KVM_DEBUGREG_BP_ENABLED (userspace debugging the guest) and KVM_DEBUGREG_WONT_EXIT (guest using DRs), and so KVM handles loading DR0-DR3 in common code, _outside_ of the core kvm_x86_ops.vcpu_run() loop. But for DR6, the guest's value doesn't need to be loaded into hardware for KVM_DEBUGREG_BP_ENABLED, and SVM provides a dedicated VMCB field whereas VMX requires software to manually load the guest value, and so loading the guest's value into DR6 is handled by {svm,vmx}_vcpu_run(), i.e. is done _inside_ the core run loop. Unfortunately, saving the guest values on VM-Exit is initiated by common x86, again outside of the core run loop. If the guest modifies DR6 (in hardware, when DR interception is disabled), and then the next VM-Exit is a fastpath VM-Exit, KVM will reload hardware DR6 with vcpu->arch.dr6 and clobber the guest's actual value. The bug shows up primarily with nested VMX because KVM handles the VMX preemption timer in the fastpath, and the window between hardware DR6 being modified (in guest context) and DR6 being read by guest software is orders of magnitude larger in a nested setup. E.g. in non-nested, the VMX preemption timer would need to fire precisely between #DB injection and the #DB handler's read of DR6, whereas with a KVM-on-KVM setup, the window where hardware DR6 is "dirty" extends all the way from L1 writing DR6 to VMRESUME (in L1). L1's view: ========== <L1 disables DR interception> CPU 0/KVM-7289 [023] d.... 2925.640961: kvm_entry: vcpu 0 A: L1 Writes DR6 CPU 0/KVM-7289 [023] d.... 2925.640963: <hack>: Set DRs, DR6 = 0xffff0ff1 B: CPU 0/KVM-7289 [023] d.... 2925.640967: kvm_exit: vcpu 0 reason EXTERNAL_INTERRUPT intr_info 0x800000ec D: L1 reads DR6, arch.dr6 = 0 CPU 0/KVM-7289 [023] d.... 2925.640969: <hack>: Sync DRs, DR6 = 0xffff0ff0 CPU 0/KVM-7289 [023] d.... 2925.640976: kvm_entry: vcpu 0 L2 reads DR6, L1 disables DR interception CPU 0/KVM-7289 [023] d.... 2925.640980: kvm_exit: vcpu 0 reason DR_ACCESS info1 0x0000000000000216 CPU 0/KVM-7289 [023] d.... 2925.640983: kvm_entry: vcpu 0 CPU 0/KVM-7289 [023] d.... 2925.640983: <hack>: Set DRs, DR6 = 0xffff0ff0 L2 detects failure CPU 0/KVM-7289 [023] d.... 2925.640987: kvm_exit: vcpu 0 reason HLT L1 reads DR6 (confirms failure) CPU 0/KVM-7289 [023] d.... 2925.640990: <hack>: Sync DRs, DR6 = 0xffff0ff0 L0's view: ========== L2 reads DR6, arch.dr6 = 0 CPU 23/KVM-5046 [001] d.... 3410.005610: kvm_exit: vcpu 23 reason DR_ACCESS info1 0x0000000000000216 CPU 23/KVM-5046 [001] ..... 3410.005610: kvm_nested_vmexit: vcpu 23 reason DR_ACCESS info1 0x0000000000000216 L2 => L1 nested VM-Exit CPU 23/KVM-5046 [001] ..... 3410.005610: kvm_nested_vmexit_inject: reason: DR_ACCESS ext_inf1: 0x0000000000000216 CPU 23/KVM-5046 [001] d.... 3410.005610: kvm_entry: vcpu 23 CPU 23/KVM-5046 [001] d.... 3410.005611: kvm_exit: vcpu 23 reason VMREAD CPU 23/KVM-5046 [001] d.... 3410.005611: kvm_entry: vcpu 23 CPU 23/KVM-5046 [001] d.... 3410. ---truncated---
CVE-2025-21855: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Don't reference skb after sending to VIOS Previously, after successfully flushing the xmit buffer to VIOS, the tx_bytes stat was incremented by the length of the skb. It is invalid to access the skb memory after sending the buffer to the VIOS because, at any point after sending, the VIOS can trigger an interrupt to free this memory. A race between reading skb->len and freeing the skb is possible (especially during LPM) and will result in use-after-free: ================================================================== BUG: KASAN: slab-use-after-free in ibmvnic_xmit+0x75c/0x1808 [ibmvnic] Read of size 4 at addr c00000024eb48a70 by task hxecom/14495 <...> Call Trace: [c000000118f66cf0] [c0000000018cba6c] dump_stack_lvl+0x84/0xe8 (unreliable) [c000000118f66d20] [c0000000006f0080] print_report+0x1a8/0x7f0 [c000000118f66df0] [c0000000006f08f0] kasan_report+0x128/0x1f8 [c000000118f66f00] [c0000000006f2868] __asan_load4+0xac/0xe0 [c000000118f66f20] [c0080000046eac84] ibmvnic_xmit+0x75c/0x1808 [ibmvnic] [c000000118f67340] [c0000000014be168] dev_hard_start_xmit+0x150/0x358 <...> Freed by task 0: kasan_save_stack+0x34/0x68 kasan_save_track+0x2c/0x50 kasan_save_free_info+0x64/0x108 __kasan_mempool_poison_object+0x148/0x2d4 napi_skb_cache_put+0x5c/0x194 net_tx_action+0x154/0x5b8 handle_softirqs+0x20c/0x60c do_softirq_own_stack+0x6c/0x88 <...> The buggy address belongs to the object at c00000024eb48a00 which belongs to the cache skbuff_head_cache of size 224 ==================================================================
CVE-2025-21863: In the Linux kernel, the following vulnerability has been resolved: io_uring: prevent opcode speculation sqe->opcode is used for different tables, make sure we santitise it against speculations.
CVE-2025-21881: In the Linux kernel, the following vulnerability has been resolved: uprobes: Reject the shared zeropage in uprobe_write_opcode() We triggered the following crash in syzkaller tests: BUG: Bad page state in process syz.7.38 pfn:1eff3 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1eff3 flags: 0x3fffff00004004(referenced|reserved|node=0|zone=1|lastcpupid=0x1fffff) raw: 003fffff00004004 ffffe6c6c07bfcc8 ffffe6c6c07bfcc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000fffffffe 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x32/0x50 bad_page+0x69/0xf0 free_unref_page_prepare+0x401/0x500 free_unref_page+0x6d/0x1b0 uprobe_write_opcode+0x460/0x8e0 install_breakpoint.part.0+0x51/0x80 register_for_each_vma+0x1d9/0x2b0 __uprobe_register+0x245/0x300 bpf_uprobe_multi_link_attach+0x29b/0x4f0 link_create+0x1e2/0x280 __sys_bpf+0x75f/0xac0 __x64_sys_bpf+0x1a/0x30 do_syscall_64+0x56/0x100 entry_SYSCALL_64_after_hwframe+0x78/0xe2 BUG: Bad rss-counter state mm:00000000452453e0 type:MM_FILEPAGES val:-1 The following syzkaller test case can be used to reproduce: r2 = creat(&(0x7f0000000000)='./file0\x00', 0x8) write$nbd(r2, &(0x7f0000000580)=ANY=[], 0x10) r4 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x42, 0x0) mmap$IORING_OFF_SQ_RING(&(0x7f0000ffd000/0x3000)=nil, 0x3000, 0x0, 0x12, r4, 0x0) r5 = userfaultfd(0x80801) ioctl$UFFDIO_API(r5, 0xc018aa3f, &(0x7f0000000040)={0xaa, 0x20}) r6 = userfaultfd(0x80801) ioctl$UFFDIO_API(r6, 0xc018aa3f, &(0x7f0000000140)) ioctl$UFFDIO_REGISTER(r6, 0xc020aa00, &(0x7f0000000100)={{&(0x7f0000ffc000/0x4000)=nil, 0x4000}, 0x2}) ioctl$UFFDIO_ZEROPAGE(r5, 0xc020aa04, &(0x7f0000000000)={{&(0x7f0000ffd000/0x1000)=nil, 0x1000}}) r7 = bpf$PROG_LOAD(0x5, &(0x7f0000000140)={0x2, 0x3, &(0x7f0000000200)=ANY=[@ANYBLOB="1800000000120000000000000000000095"], &(0x7f0000000000)='GPL\x00', 0x7, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x0, @void, @value}, 0x94) bpf$BPF_LINK_CREATE_XDP(0x1c, &(0x7f0000000040)={r7, 0x0, 0x30, 0x1e, @val=@uprobe_multi={&(0x7f0000000080)='./file0\x00', &(0x7f0000000100)=[0x2], 0x0, 0x0, 0x1}}, 0x40) The cause is that zero pfn is set to the PTE without increasing the RSS count in mfill_atomic_pte_zeropage() and the refcount of zero folio does not increase accordingly. Then, the operation on the same pfn is performed in uprobe_write_opcode()->__replace_page() to unconditional decrease the RSS count and old_folio's refcount. Therefore, two bugs are introduced: 1. The RSS count is incorrect, when process exit, the check_mm() report error "Bad rss-count". 2. The reserved folio (zero folio) is freed when folio->refcount is zero, then free_pages_prepare->free_page_is_bad() report error "Bad page state". There is more, the following warning could also theoretically be triggered: __replace_page() -> ... -> folio_remove_rmap_pte() -> VM_WARN_ON_FOLIO(is_zero_folio(folio), folio) Considering that uprobe hit on the zero folio is a very rare case, just reject zero old folio immediately after get_user_page_vma_remote(). [ mingo: Cleaned up the changelog ]
CVE-2025-21885: In the Linux kernel, the following vulnerability has been resolved: RDMA/bnxt_re: Fix the page details for the srq created by kernel consumers While using nvme target with use_srq on, below kernel panic is noticed. [ 549.698111] bnxt_en 0000:41:00.0 enp65s0np0: FEC autoneg off encoding: Clause 91 RS(544,514) [ 566.393619] Oops: divide error: 0000 [#1] PREEMPT SMP NOPTI .. [ 566.393799] <TASK> [ 566.393807] ? __die_body+0x1a/0x60 [ 566.393823] ? die+0x38/0x60 [ 566.393835] ? do_trap+0xe4/0x110 [ 566.393847] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393867] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393881] ? do_error_trap+0x7c/0x120 [ 566.393890] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393911] ? exc_divide_error+0x34/0x50 [ 566.393923] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393939] ? asm_exc_divide_error+0x16/0x20 [ 566.393966] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393997] bnxt_qplib_create_srq+0xc9/0x340 [bnxt_re] [ 566.394040] bnxt_re_create_srq+0x335/0x3b0 [bnxt_re] [ 566.394057] ? srso_return_thunk+0x5/0x5f [ 566.394068] ? __init_swait_queue_head+0x4a/0x60 [ 566.394090] ib_create_srq_user+0xa7/0x150 [ib_core] [ 566.394147] nvmet_rdma_queue_connect+0x7d0/0xbe0 [nvmet_rdma] [ 566.394174] ? lock_release+0x22c/0x3f0 [ 566.394187] ? srso_return_thunk+0x5/0x5f Page size and shift info is set only for the user space SRQs. Set page size and page shift for kernel space SRQs also.
CVE-2025-21891: In the Linux kernel, the following vulnerability has been resolved: ipvlan: ensure network headers are in skb linear part syzbot found that ipvlan_process_v6_outbound() was assuming the IPv6 network header isis present in skb->head [1] Add the needed pskb_network_may_pull() calls for both IPv4 and IPv6 handlers. [1] BUG: KMSAN: uninit-value in __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 ipv6_addr_type include/net/ipv6.h:555 [inline] ip6_route_output_flags_noref net/ipv6/route.c:2616 [inline] ip6_route_output_flags+0x51/0x720 net/ipv6/route.c:2651 ip6_route_output include/net/ip6_route.h:93 [inline] ipvlan_route_v6_outbound+0x24e/0x520 drivers/net/ipvlan/ipvlan_core.c:476 ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:491 [inline] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:541 [inline] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:605 [inline] ipvlan_queue_xmit+0xd72/0x1780 drivers/net/ipvlan/ipvlan_core.c:671 ipvlan_start_xmit+0x5b/0x210 drivers/net/ipvlan/ipvlan_main.c:223 __netdev_start_xmit include/linux/netdevice.h:5150 [inline] netdev_start_xmit include/linux/netdevice.h:5159 [inline] xmit_one net/core/dev.c:3735 [inline] dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3751 sch_direct_xmit+0x399/0xd40 net/sched/sch_generic.c:343 qdisc_restart net/sched/sch_generic.c:408 [inline] __qdisc_run+0x14da/0x35d0 net/sched/sch_generic.c:416 qdisc_run+0x141/0x4d0 include/net/pkt_sched.h:127 net_tx_action+0x78b/0x940 net/core/dev.c:5484 handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:561 __do_softirq+0x14/0x1a kernel/softirq.c:595 do_softirq+0x9a/0x100 kernel/softirq.c:462 __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:389 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline] __dev_queue_xmit+0x2758/0x57d0 net/core/dev.c:4611 dev_queue_xmit include/linux/netdevice.h:3311 [inline] packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3132 [inline] packet_sendmsg+0x93e0/0xa7e0 net/packet/af_packet.c:3164 sock_sendmsg_nosec net/socket.c:718 [inline]
CVE-2025-21894: In the Linux kernel, the following vulnerability has been resolved: net: enetc: VFs do not support HWTSTAMP_TX_ONESTEP_SYNC Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash if VFs are used to test one-step timestamp, the crash log as follows. [ 129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0 [ 129.287769] Call trace: [ 129.290219] enetc_port_mac_wr+0x30/0xec (P) [ 129.294504] enetc_start_xmit+0xda4/0xe74 [ 129.298525] enetc_xmit+0x70/0xec [ 129.301848] dev_hard_start_xmit+0x98/0x118
CVE-2025-21899: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix bad hist from corrupting named_triggers list The following commands causes a crash: ~# cd /sys/kernel/tracing/events/rcu/rcu_callback ~# echo 'hist:name=bad:keys=common_pid:onmax(bogus).save(common_pid)' > trigger bash: echo: write error: Invalid argument ~# echo 'hist:name=bad:keys=common_pid' > trigger Because the following occurs: event_trigger_write() { trigger_process_regex() { event_hist_trigger_parse() { data = event_trigger_alloc(..); event_trigger_register(.., data) { cmd_ops->reg(.., data, ..) [hist_register_trigger()] { data->ops->init() [event_hist_trigger_init()] { save_named_trigger(name, data) { list_add(&data->named_list, &named_triggers); } } } } ret = create_actions(); (return -EINVAL) if (ret) goto out_unreg; [..] ret = hist_trigger_enable(data, ...) { list_add_tail_rcu(&data->list, &file->triggers); <<<---- SKIPPED!!! (this is important!) [..] out_unreg: event_hist_unregister(.., data) { cmd_ops->unreg(.., data, ..) [hist_unregister_trigger()] { list_for_each_entry(iter, &file->triggers, list) { if (!hist_trigger_match(data, iter, named_data, false)) <- never matches continue; [..] test = iter; } if (test && test->ops->free) <<<-- test is NULL test->ops->free(test) [event_hist_trigger_free()] { [..] if (data->name) del_named_trigger(data) { list_del(&data->named_list); <<<<-- NEVER gets removed! } } } } [..] kfree(data); <<<-- frees item but it is still on list The next time a hist with name is registered, it causes an u-a-f bug and the kernel can crash. Move the code around such that if event_trigger_register() succeeds, the next thing called is hist_trigger_enable() which adds it to the list. A bunch of actions is called if get_named_trigger_data() returns false. But that doesn't need to be called after event_trigger_register(), so it can be moved up, allowing event_trigger_register() to be called just before hist_trigger_enable() keeping them together and allowing the file->triggers to be properly populated.
CVE-2025-21927: In the Linux kernel, the following vulnerability has been resolved: nvme-tcp: fix potential memory corruption in nvme_tcp_recv_pdu() nvme_tcp_recv_pdu() doesn't check the validity of the header length. When header digests are enabled, a target might send a packet with an invalid header length (e.g. 255), causing nvme_tcp_verify_hdgst() to access memory outside the allocated area and cause memory corruptions by overwriting it with the calculated digest. Fix this by rejecting packets with an unexpected header length.
CVE-2025-21931: In the Linux kernel, the following vulnerability has been resolved: hwpoison, memory_hotplug: lock folio before unmap hwpoisoned folio Commit b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined) add page poison checks in do_migrate_range in order to make offline hwpoisoned page possible by introducing isolate_lru_page and try_to_unmap for hwpoisoned page. However folio lock must be held before calling try_to_unmap. Add it to fix this problem. Warning will be produced if folio is not locked during unmap: ------------[ cut here ]------------ kernel BUG at ./include/linux/swapops.h:400! Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP Modules linked in: CPU: 4 UID: 0 PID: 411 Comm: bash Tainted: G W 6.13.0-rc1-00016-g3c434c7ee82a-dirty #41 Tainted: [W]=WARN Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : try_to_unmap_one+0xb08/0xd3c lr : try_to_unmap_one+0x3dc/0xd3c Call trace: try_to_unmap_one+0xb08/0xd3c (P) try_to_unmap_one+0x3dc/0xd3c (L) rmap_walk_anon+0xdc/0x1f8 rmap_walk+0x3c/0x58 try_to_unmap+0x88/0x90 unmap_poisoned_folio+0x30/0xa8 do_migrate_range+0x4a0/0x568 offline_pages+0x5a4/0x670 memory_block_action+0x17c/0x374 memory_subsys_offline+0x3c/0x78 device_offline+0xa4/0xd0 state_store+0x8c/0xf0 dev_attr_store+0x18/0x2c sysfs_kf_write+0x44/0x54 kernfs_fop_write_iter+0x118/0x1a8 vfs_write+0x3a8/0x4bc ksys_write+0x6c/0xf8 __arm64_sys_write+0x1c/0x28 invoke_syscall+0x44/0x100 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x30/0xd0 el0t_64_sync_handler+0xc8/0xcc el0t_64_sync+0x198/0x19c Code: f9407be0 b5fff320 d4210000 17ffff97 (d4210000) ---[ end trace 0000000000000000 ]---
CVE-2025-21976: In the Linux kernel, the following vulnerability has been resolved: fbdev: hyperv_fb: Allow graceful removal of framebuffer When a Hyper-V framebuffer device is unbind, hyperv_fb driver tries to release the framebuffer forcefully. If this framebuffer is in use it produce the following WARN and hence this framebuffer is never released. [ 44.111220] WARNING: CPU: 35 PID: 1882 at drivers/video/fbdev/core/fb_info.c:70 framebuffer_release+0x2c/0x40 < snip > [ 44.111289] Call Trace: [ 44.111290] <TASK> [ 44.111291] ? show_regs+0x6c/0x80 [ 44.111295] ? __warn+0x8d/0x150 [ 44.111298] ? framebuffer_release+0x2c/0x40 [ 44.111300] ? report_bug+0x182/0x1b0 [ 44.111303] ? handle_bug+0x6e/0xb0 [ 44.111306] ? exc_invalid_op+0x18/0x80 [ 44.111308] ? asm_exc_invalid_op+0x1b/0x20 [ 44.111311] ? framebuffer_release+0x2c/0x40 [ 44.111313] ? hvfb_remove+0x86/0xa0 [hyperv_fb] [ 44.111315] vmbus_remove+0x24/0x40 [hv_vmbus] [ 44.111323] device_remove+0x40/0x80 [ 44.111325] device_release_driver_internal+0x20b/0x270 [ 44.111327] ? bus_find_device+0xb3/0xf0 Fix this by moving the release of framebuffer and assosiated memory to fb_ops.fb_destroy function, so that framebuffer framework handles it gracefully. While we fix this, also replace manual registrations/unregistration of framebuffer with devm_register_framebuffer.
CVE-2025-21985: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix out-of-bound accesses [WHAT & HOW] hpo_stream_to_link_encoder_mapping has size MAX_HPO_DP2_ENCODERS(=4), but location can have size up to 6. As a result, it is necessary to check location against MAX_HPO_DP2_ENCODERS. Similiarly, disp_cfg_stream_location can be used as an array index which should be 0..5, so the ASSERT's conditions should be less without equal.
CVE-2025-22026: In the Linux kernel, the following vulnerability has been resolved: nfsd: don't ignore the return code of svc_proc_register() Currently, nfsd_proc_stat_init() ignores the return value of svc_proc_register(). If the procfile creation fails, then the kernel will WARN when it tries to remove the entry later. Fix nfsd_proc_stat_init() to return the same type of pointer as svc_proc_register(), and fix up nfsd_net_init() to check that and fail the nfsd_net construction if it occurs. svc_proc_register() can fail if the dentry can't be allocated, or if an identical dentry already exists. The second case is pretty unlikely in the nfsd_net construction codepath, so if this happens, return -ENOMEM.
CVE-2025-22028: In the Linux kernel, the following vulnerability has been resolved: media: vimc: skip .s_stream() for stopped entities Syzbot reported [1] a warning prompted by a check in call_s_stream() that checks whether .s_stream() operation is warranted for unstarted or stopped subdevs. Add a simple fix in vimc_streamer_pipeline_terminate() ensuring that entities skip a call to .s_stream() unless they have been previously properly started. [1] Syzbot report: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 5933 at drivers/media/v4l2-core/v4l2-subdev.c:460 call_s_stream+0x2df/0x350 drivers/media/v4l2-core/v4l2-subdev.c:460 Modules linked in: CPU: 0 UID: 0 PID: 5933 Comm: syz-executor330 Not tainted 6.13.0-rc2-syzkaller-00362-g2d8308bf5b67 #0 ... Call Trace: <TASK> vimc_streamer_pipeline_terminate+0x218/0x320 drivers/media/test-drivers/vimc/vimc-streamer.c:62 vimc_streamer_pipeline_init drivers/media/test-drivers/vimc/vimc-streamer.c:101 [inline] vimc_streamer_s_stream+0x650/0x9a0 drivers/media/test-drivers/vimc/vimc-streamer.c:203 vimc_capture_start_streaming+0xa1/0x130 drivers/media/test-drivers/vimc/vimc-capture.c:256 vb2_start_streaming+0x15f/0x5a0 drivers/media/common/videobuf2/videobuf2-core.c:1789 vb2_core_streamon+0x2a7/0x450 drivers/media/common/videobuf2/videobuf2-core.c:2348 vb2_streamon drivers/media/common/videobuf2/videobuf2-v4l2.c:875 [inline] vb2_ioctl_streamon+0xf4/0x170 drivers/media/common/videobuf2/videobuf2-v4l2.c:1118 __video_do_ioctl+0xaf0/0xf00 drivers/media/v4l2-core/v4l2-ioctl.c:3122 video_usercopy+0x4d2/0x1620 drivers/media/v4l2-core/v4l2-ioctl.c:3463 v4l2_ioctl+0x1ba/0x250 drivers/media/v4l2-core/v4l2-dev.c:366 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl fs/ioctl.c:892 [inline] __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f2b85c01b19 ...
CVE-2025-22053: In the Linux kernel, the following vulnerability has been resolved: net: ibmveth: make veth_pool_store stop hanging v2: - Created a single error handling unlock and exit in veth_pool_store - Greatly expanded commit message with previous explanatory-only text Summary: Use rtnl_mutex to synchronize veth_pool_store with itself, ibmveth_close and ibmveth_open, preventing multiple calls in a row to napi_disable. Background: Two (or more) threads could call veth_pool_store through writing to /sys/devices/vio/30000002/pool*/*. You can do this easily with a little shell script. This causes a hang. I configured LOCKDEP, compiled ibmveth.c with DEBUG, and built a new kernel. I ran this test again and saw: Setting pool0/active to 0 Setting pool1/active to 1 [ 73.911067][ T4365] ibmveth 30000002 eth0: close starting Setting pool1/active to 1 Setting pool1/active to 0 [ 73.911367][ T4366] ibmveth 30000002 eth0: close starting [ 73.916056][ T4365] ibmveth 30000002 eth0: close complete [ 73.916064][ T4365] ibmveth 30000002 eth0: open starting [ 110.808564][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 230.808495][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 243.683786][ T123] INFO: task stress.sh:4365 blocked for more than 122 seconds. [ 243.683827][ T123] Not tainted 6.14.0-01103-g2df0c02dab82-dirty #8 [ 243.683833][ T123] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 243.683838][ T123] task:stress.sh state:D stack:28096 pid:4365 tgid:4365 ppid:4364 task_flags:0x400040 flags:0x00042000 [ 243.683852][ T123] Call Trace: [ 243.683857][ T123] [c00000000c38f690] [0000000000000001] 0x1 (unreliable) [ 243.683868][ T123] [c00000000c38f840] [c00000000001f908] __switch_to+0x318/0x4e0 [ 243.683878][ T123] [c00000000c38f8a0] [c000000001549a70] __schedule+0x500/0x12a0 [ 243.683888][ T123] [c00000000c38f9a0] [c00000000154a878] schedule+0x68/0x210 [ 243.683896][ T123] [c00000000c38f9d0] [c00000000154ac80] schedule_preempt_disabled+0x30/0x50 [ 243.683904][ T123] [c00000000c38fa00] [c00000000154dbb0] __mutex_lock+0x730/0x10f0 [ 243.683913][ T123] [c00000000c38fb10] [c000000001154d40] napi_enable+0x30/0x60 [ 243.683921][ T123] [c00000000c38fb40] [c000000000f4ae94] ibmveth_open+0x68/0x5dc [ 243.683928][ T123] [c00000000c38fbe0] [c000000000f4aa20] veth_pool_store+0x220/0x270 [ 243.683936][ T123] [c00000000c38fc70] [c000000000826278] sysfs_kf_write+0x68/0xb0 [ 243.683944][ T123] [c00000000c38fcb0] [c0000000008240b8] kernfs_fop_write_iter+0x198/0x2d0 [ 243.683951][ T123] [c00000000c38fd00] [c00000000071b9ac] vfs_write+0x34c/0x650 [ 243.683958][ T123] [c00000000c38fdc0] [c00000000071bea8] ksys_write+0x88/0x150 [ 243.683966][ T123] [c00000000c38fe10] [c0000000000317f4] system_call_exception+0x124/0x340 [ 243.683973][ T123] [c00000000c38fe50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec ... [ 243.684087][ T123] Showing all locks held in the system: [ 243.684095][ T123] 1 lock held by khungtaskd/123: [ 243.684099][ T123] #0: c00000000278e370 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x50/0x248 [ 243.684114][ T123] 4 locks held by stress.sh/4365: [ 243.684119][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243.684132][ T123] #1: c000000041aea888 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0 [ 243.684143][ T123] #2: c0000000366fb9a8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0 [ 243.684155][ T123] #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_enable+0x30/0x60 [ 243.684166][ T123] 5 locks held by stress.sh/4366: [ 243.684170][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243. ---truncated---
CVE-2025-22057: In the Linux kernel, the following vulnerability has been resolved: net: decrease cached dst counters in dst_release Upstream fix ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") moved decrementing the dst count from dst_destroy to dst_release to avoid accessing already freed data in case of netns dismantle. However in case CONFIG_DST_CACHE is enabled and OvS+tunnels are used, this fix is incomplete as the same issue will be seen for cached dsts: Unable to handle kernel paging request at virtual address ffff5aabf6b5c000 Call trace: percpu_counter_add_batch+0x3c/0x160 (P) dst_release+0xec/0x108 dst_cache_destroy+0x68/0xd8 dst_destroy+0x13c/0x168 dst_destroy_rcu+0x1c/0xb0 rcu_do_batch+0x18c/0x7d0 rcu_core+0x174/0x378 rcu_core_si+0x18/0x30 Fix this by invalidating the cache, and thus decrementing cached dst counters, in dst_release too.
CVE-2025-22060: In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: Prevent parser TCAM memory corruption Protect the parser TCAM/SRAM memory, and the cached (shadow) SRAM information, from concurrent modifications. Both the TCAM and SRAM tables are indirectly accessed by configuring an index register that selects the row to read or write to. This means that operations must be atomic in order to, e.g., avoid spreading writes across multiple rows. Since the shadow SRAM array is used to find free rows in the hardware table, it must also be protected in order to avoid TOCTOU errors where multiple cores allocate the same row. This issue was detected in a situation where `mvpp2_set_rx_mode()` ran concurrently on two CPUs. In this particular case the MVPP2_PE_MAC_UC_PROMISCUOUS entry was corrupted, causing the classifier unit to drop all incoming unicast - indicated by the `rx_classifier_drops` counter.
CVE-2025-22072: In the Linux kernel, the following vulnerability has been resolved: spufs: fix gang directory lifetimes prior to "[POWERPC] spufs: Fix gang destroy leaks" we used to have a problem with gang lifetimes - creation of a gang returns opened gang directory, which normally gets removed when that gets closed, but if somebody has created a context belonging to that gang and kept it alive until the gang got closed, removal failed and we ended up with a leak. Unfortunately, it had been fixed the wrong way. Dentry of gang directory was no longer pinned, and rmdir on close was gone. One problem was that failure of open kept calling simple_rmdir() as cleanup, which meant an unbalanced dput(). Another bug was in the success case - gang creation incremented link count on root directory, but that was no longer undone when gang got destroyed. Fix consists of * reverting the commit in question * adding a counter to gang, protected by ->i_rwsem of gang directory inode. * having it set to 1 at creation time, dropped in both spufs_dir_close() and spufs_gang_close() and bumped in spufs_create_context(), provided that it's not 0. * using simple_recursive_removal() to take the gang directory out when counter reaches zero.
CVE-2025-22083: In the Linux kernel, the following vulnerability has been resolved: vhost-scsi: Fix handling of multiple calls to vhost_scsi_set_endpoint If vhost_scsi_set_endpoint is called multiple times without a vhost_scsi_clear_endpoint between them, we can hit multiple bugs found by Haoran Zhang: 1. Use-after-free when no tpgs are found: This fixes a use after free that occurs when vhost_scsi_set_endpoint is called more than once and calls after the first call do not find any tpgs to add to the vs_tpg. When vhost_scsi_set_endpoint first finds tpgs to add to the vs_tpg array match=true, so we will do: vhost_vq_set_backend(vq, vs_tpg); ... kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; If vhost_scsi_set_endpoint is called again and no tpgs are found match=false so we skip the vhost_vq_set_backend call leaving the pointer to the vs_tpg we then free via: kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; If a scsi request is then sent we do: vhost_scsi_handle_vq -> vhost_scsi_get_req -> vhost_vq_get_backend which sees the vs_tpg we just did a kfree on. 2. Tpg dir removal hang: This patch fixes an issue where we cannot remove a LIO/target layer tpg (and structs above it like the target) dir due to the refcount dropping to -1. The problem is that if vhost_scsi_set_endpoint detects a tpg is already in the vs->vs_tpg array or if the tpg has been removed so target_depend_item fails, the undepend goto handler will do target_undepend_item on all tpgs in the vs_tpg array dropping their refcount to 0. At this time vs_tpg contains both the tpgs we have added in the current vhost_scsi_set_endpoint call as well as tpgs we added in previous calls which are also in vs->vs_tpg. Later, when vhost_scsi_clear_endpoint runs it will do target_undepend_item on all the tpgs in the vs->vs_tpg which will drop their refcount to -1. Userspace will then not be able to remove the tpg and will hang when it tries to do rmdir on the tpg dir. 3. Tpg leak: This fixes a bug where we can leak tpgs and cause them to be un-removable because the target name is overwritten when vhost_scsi_set_endpoint is called multiple times but with different target names. The bug occurs if a user has called VHOST_SCSI_SET_ENDPOINT and setup a vhost-scsi device to target/tpg mapping, then calls VHOST_SCSI_SET_ENDPOINT again with a new target name that has tpgs we haven't seen before (target1 has tpg1 but target2 has tpg2). When this happens we don't teardown the old target tpg mapping and just overwrite the target name and the vs->vs_tpg array. Later when we do vhost_scsi_clear_endpoint, we are passed in either target1 or target2's name and we will only match that target's tpgs when we loop over the vs->vs_tpg. We will then return from the function without doing target_undepend_item on the tpgs. Because of all these bugs, it looks like being able to call vhost_scsi_set_endpoint multiple times was never supported. The major user, QEMU, already has checks to prevent this use case. So to fix the issues, this patch prevents vhost_scsi_set_endpoint from being called if it's already successfully added tpgs. To add, remove or change the tpg config or target name, you must do a vhost_scsi_clear_endpoint first.
CVE-2025-22090: In the Linux kernel, the following vulnerability has been resolved: x86/mm/pat: Fix VM_PAT handling when fork() fails in copy_page_range() If track_pfn_copy() fails, we already added the dst VMA to the maple tree. As fork() fails, we'll cleanup the maple tree, and stumble over the dst VMA for which we neither performed any reservation nor copied any page tables. Consequently untrack_pfn() will see VM_PAT and try obtaining the PAT information from the page table -- which fails because the page table was not copied. The easiest fix would be to simply clear the VM_PAT flag of the dst VMA if track_pfn_copy() fails. However, the whole thing is about "simply" clearing the VM_PAT flag is shaky as well: if we passed track_pfn_copy() and performed a reservation, but copying the page tables fails, we'll simply clear the VM_PAT flag, not properly undoing the reservation ... which is also wrong. So let's fix it properly: set the VM_PAT flag only if the reservation succeeded (leaving it clear initially), and undo the reservation if anything goes wrong while copying the page tables: clearing the VM_PAT flag after undoing the reservation. Note that any copied page table entries will get zapped when the VMA will get removed later, after copy_page_range() succeeded; as VM_PAT is not set then, we won't try cleaning VM_PAT up once more and untrack_pfn() will be happy. Note that leaving these page tables in place without a reservation is not a problem, as we are aborting fork(); this process will never run. A reproducer can trigger this usually at the first try: https://gitlab.com/davidhildenbrand/scratchspace/-/raw/main/reproducers/pat_fork.c WARNING: CPU: 26 PID: 11650 at arch/x86/mm/pat/memtype.c:983 get_pat_info+0xf6/0x110 Modules linked in: ... CPU: 26 UID: 0 PID: 11650 Comm: repro3 Not tainted 6.12.0-rc5+ #92 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:get_pat_info+0xf6/0x110 ... Call Trace: <TASK> ... untrack_pfn+0x52/0x110 unmap_single_vma+0xa6/0xe0 unmap_vmas+0x105/0x1f0 exit_mmap+0xf6/0x460 __mmput+0x4b/0x120 copy_process+0x1bf6/0x2aa0 kernel_clone+0xab/0x440 __do_sys_clone+0x66/0x90 do_syscall_64+0x95/0x180 Likely this case was missed in: d155df53f310 ("x86/mm/pat: clear VM_PAT if copy_p4d_range failed") ... and instead of undoing the reservation we simply cleared the VM_PAT flag. Keep the documentation of these functions in include/linux/pgtable.h, one place is more than sufficient -- we should clean that up for the other functions like track_pfn_remap/untrack_pfn separately.
CVE-2025-22103: In the Linux kernel, the following vulnerability has been resolved: net: fix NULL pointer dereference in l3mdev_l3_rcv When delete l3s ipvlan: ip link del link eth0 ipvlan1 type ipvlan mode l3s This may cause a null pointer dereference: Call trace: ip_rcv_finish+0x48/0xd0 ip_rcv+0x5c/0x100 __netif_receive_skb_one_core+0x64/0xb0 __netif_receive_skb+0x20/0x80 process_backlog+0xb4/0x204 napi_poll+0xe8/0x294 net_rx_action+0xd8/0x22c __do_softirq+0x12c/0x354 This is because l3mdev_l3_rcv() visit dev->l3mdev_ops after ipvlan_l3s_unregister() assign the dev->l3mdev_ops to NULL. The process like this: (CPU1) | (CPU2) l3mdev_l3_rcv() | check dev->priv_flags: | master = skb->dev; | | | ipvlan_l3s_unregister() | set dev->priv_flags | dev->l3mdev_ops = NULL; | visit master->l3mdev_ops | To avoid this by do not set dev->l3mdev_ops when unregister l3s ipvlan.
CVE-2025-22104: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Use kernel helpers for hex dumps Previously, when the driver was printing hex dumps, the buffer was cast to an 8 byte long and printed using string formatters. If the buffer size was not a multiple of 8 then a read buffer overflow was possible. Therefore, create a new ibmvnic function that loops over a buffer and calls hex_dump_to_buffer instead. This patch address KASAN reports like the one below: ibmvnic 30000003 env3: Login Buffer: ibmvnic 30000003 env3: 01000000af000000 <...> ibmvnic 30000003 env3: 2e6d62692e736261 ibmvnic 30000003 env3: 65050003006d6f63 ================================================================== BUG: KASAN: slab-out-of-bounds in ibmvnic_login+0xacc/0xffc [ibmvnic] Read of size 8 at addr c0000001331a9aa8 by task ip/17681 <...> Allocated by task 17681: <...> ibmvnic_login+0x2f0/0xffc [ibmvnic] ibmvnic_open+0x148/0x308 [ibmvnic] __dev_open+0x1ac/0x304 <...> The buggy address is located 168 bytes inside of allocated 175-byte region [c0000001331a9a00, c0000001331a9aaf) <...> ================================================================= ibmvnic 30000003 env3: 000000000033766e
CVE-2025-22107: In the Linux kernel, the following vulnerability has been resolved: net: dsa: sja1105: fix kasan out-of-bounds warning in sja1105_table_delete_entry() There are actually 2 problems: - deleting the last element doesn't require the memmove of elements [i + 1, end) over it. Actually, element i+1 is out of bounds. - The memmove itself should move size - i - 1 elements, because the last element is out of bounds. The out-of-bounds element still remains out of bounds after being accessed, so the problem is only that we touch it, not that it becomes in active use. But I suppose it can lead to issues if the out-of-bounds element is part of an unmapped page.
CVE-2025-22109: In the Linux kernel, the following vulnerability has been resolved: ax25: Remove broken autobind Binding AX25 socket by using the autobind feature leads to memory leaks in ax25_connect() and also refcount leaks in ax25_release(). Memory leak was detected with kmemleak: ================================================================ unreferenced object 0xffff8880253cd680 (size 96): backtrace: __kmalloc_node_track_caller_noprof (./include/linux/kmemleak.h:43) kmemdup_noprof (mm/util.c:136) ax25_rt_autobind (net/ax25/ax25_route.c:428) ax25_connect (net/ax25/af_ax25.c:1282) __sys_connect_file (net/socket.c:2045) __sys_connect (net/socket.c:2064) __x64_sys_connect (net/socket.c:2067) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) ================================================================ When socket is bound, refcounts must be incremented the way it is done in ax25_bind() and ax25_setsockopt() (SO_BINDTODEVICE). In case of autobind, the refcounts are not incremented. This bug leads to the following issue reported by Syzkaller: ================================================================ ax25_connect(): syz-executor318 uses autobind, please contact jreuter@yaina.de ------------[ cut here ]------------ refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 0 PID: 5317 at lib/refcount.c:31 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 Modules linked in: CPU: 0 UID: 0 PID: 5317 Comm: syz-executor318 Not tainted 6.14.0-rc4-syzkaller-00278-gece144f151ac #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 ... Call Trace: <TASK> __refcount_dec include/linux/refcount.h:336 [inline] refcount_dec include/linux/refcount.h:351 [inline] ref_tracker_free+0x6af/0x7e0 lib/ref_tracker.c:236 netdev_tracker_free include/linux/netdevice.h:4302 [inline] netdev_put include/linux/netdevice.h:4319 [inline] ax25_release+0x368/0x960 net/ax25/af_ax25.c:1080 __sock_release net/socket.c:647 [inline] sock_close+0xbc/0x240 net/socket.c:1398 __fput+0x3e9/0x9f0 fs/file_table.c:464 __do_sys_close fs/open.c:1580 [inline] __se_sys_close fs/open.c:1565 [inline] __x64_sys_close+0x7f/0x110 fs/open.c:1565 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f ... </TASK> ================================================================ Considering the issues above and the comments left in the code that say: "check if we can remove this feature. It is broken."; "autobinding in this may or may not work"; - it is better to completely remove this feature than to fix it because it is broken and leads to various kinds of memory bugs. Now calling connect() without first binding socket will result in an error (-EINVAL). Userspace software that relies on the autobind feature might get broken. However, this feature does not seem widely used with this specific driver as it was not reliable at any point of time, and it is already broken anyway. E.g. ax25-tools and ax25-apps packages for popular distributions do not use the autobind feature for AF_AX25. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2025-22125: In the Linux kernel, the following vulnerability has been resolved: md/raid1,raid10: don't ignore IO flags If blk-wbt is enabled by default, it's found that raid write performance is quite bad because all IO are throttled by wbt of underlying disks, due to flag REQ_IDLE is ignored. And turns out this behaviour exist since blk-wbt is introduced. Other than REQ_IDLE, other flags should not be ignored as well, for example REQ_META can be set for filesystems, clearing it can cause priority reverse problems; And REQ_NOWAIT should not be cleared as well, because io will wait instead of failing directly in underlying disks. Fix those problems by keep IO flags from master bio. Fises: f51d46d0e7cb ("md: add support for REQ_NOWAIT")
CVE-2025-22127: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix potential deadloop in prepare_compress_overwrite() Jan Prusakowski reported a kernel hang issue as below: When running xfstests on linux-next kernel (6.14.0-rc3, 6.12) I encountered a problem in generic/475 test where fsstress process gets blocked in __f2fs_write_data_pages() and the test hangs. The options I used are: MKFS_OPTIONS -- -O compression -O extra_attr -O project_quota -O quota /dev/vdc MOUNT_OPTIONS -- -o acl,user_xattr -o discard,compress_extension=* /dev/vdc /vdc INFO: task kworker/u8:0:11 blocked for more than 122 seconds. Not tainted 6.14.0-rc3-xfstests-lockdep #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u8:0 state:D stack:0 pid:11 tgid:11 ppid:2 task_flags:0x4208160 flags:0x00004000 Workqueue: writeback wb_workfn (flush-253:0) Call Trace: <TASK> __schedule+0x309/0x8e0 schedule+0x3a/0x100 schedule_preempt_disabled+0x15/0x30 __mutex_lock+0x59a/0xdb0 __f2fs_write_data_pages+0x3ac/0x400 do_writepages+0xe8/0x290 __writeback_single_inode+0x5c/0x360 writeback_sb_inodes+0x22f/0x570 wb_writeback+0xb0/0x410 wb_do_writeback+0x47/0x2f0 wb_workfn+0x5a/0x1c0 process_one_work+0x223/0x5b0 worker_thread+0x1d5/0x3c0 kthread+0xfd/0x230 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x1a/0x30 </TASK> The root cause is: once generic/475 starts toload error table to dm device, f2fs_prepare_compress_overwrite() will loop reading compressed cluster pages due to IO error, meanwhile it has held .writepages lock, it can block all other writeback tasks. Let's fix this issue w/ below changes: - add f2fs_handle_page_eio() in prepare_compress_overwrite() to detect IO error. - detect cp_error earler in f2fs_read_multi_pages().
CVE-2025-23130: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid panic once fallocation fails for pinfile syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2746! CPU: 0 UID: 0 PID: 5323 Comm: syz.0.0 Not tainted 6.13.0-rc2-syzkaller-00018-g7cb1b4663150 #0 RIP: 0010:get_new_segment fs/f2fs/segment.c:2746 [inline] RIP: 0010:new_curseg+0x1f52/0x1f70 fs/f2fs/segment.c:2876 Call Trace: <TASK> __allocate_new_segment+0x1ce/0x940 fs/f2fs/segment.c:3210 f2fs_allocate_new_section fs/f2fs/segment.c:3224 [inline] f2fs_allocate_pinning_section+0xfa/0x4e0 fs/f2fs/segment.c:3238 f2fs_expand_inode_data+0x696/0xca0 fs/f2fs/file.c:1830 f2fs_fallocate+0x537/0xa10 fs/f2fs/file.c:1940 vfs_fallocate+0x569/0x6e0 fs/open.c:327 do_vfs_ioctl+0x258c/0x2e40 fs/ioctl.c:885 __do_sys_ioctl fs/ioctl.c:904 [inline] __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Concurrent pinfile allocation may run out of free section, result in panic in get_new_segment(), let's expand pin_sem lock coverage to include f2fs_gc(), so that we can make sure to reclaim enough free space for following allocation. In addition, do below changes to enhance error path handling: - call f2fs_bug_on() only in non-pinfile allocation path in get_new_segment(). - call reset_curseg_fields() to reset all fields of curseg in new_curseg()
CVE-2025-23131: In the Linux kernel, the following vulnerability has been resolved: dlm: prevent NPD when writing a positive value to event_done do_uevent returns the value written to event_done. In case it is a positive value, new_lockspace would undo all the work, and lockspace would not be set. __dlm_new_lockspace, however, would treat that positive value as a success due to commit 8511a2728ab8 ("dlm: fix use count with multiple joins"). Down the line, device_create_lockspace would pass that NULL lockspace to dlm_find_lockspace_local, leading to a NULL pointer dereference. Treating such positive values as successes prevents the problem. Given this has been broken for so long, this is unlikely to break userspace expectations.
CVE-2025-23132: In the Linux kernel, the following vulnerability has been resolved: f2fs: quota: fix to avoid warning in dquot_writeback_dquots() F2FS-fs (dm-59): checkpoint=enable has some unwritten data. ------------[ cut here ]------------ WARNING: CPU: 6 PID: 8013 at fs/quota/dquot.c:691 dquot_writeback_dquots+0x2fc/0x308 pc : dquot_writeback_dquots+0x2fc/0x308 lr : f2fs_quota_sync+0xcc/0x1c4 Call trace: dquot_writeback_dquots+0x2fc/0x308 f2fs_quota_sync+0xcc/0x1c4 f2fs_write_checkpoint+0x3d4/0x9b0 f2fs_issue_checkpoint+0x1bc/0x2c0 f2fs_sync_fs+0x54/0x150 f2fs_do_sync_file+0x2f8/0x814 __f2fs_ioctl+0x1960/0x3244 f2fs_ioctl+0x54/0xe0 __arm64_sys_ioctl+0xa8/0xe4 invoke_syscall+0x58/0x114 checkpoint and f2fs_remount may race as below, resulting triggering warning in dquot_writeback_dquots(). atomic write remount - do_remount - down_write(&sb->s_umount); - f2fs_remount - ioctl - f2fs_do_sync_file - f2fs_sync_fs - f2fs_write_checkpoint - block_operations - locked = down_read_trylock(&sbi->sb->s_umount) : fail to lock due to the write lock was held by remount - up_write(&sb->s_umount); - f2fs_quota_sync - dquot_writeback_dquots - WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)) : trigger warning because s_umount lock was unlocked by remount If checkpoint comes from mount/umount/remount/freeze/quotactl, caller of checkpoint has already held s_umount lock, calling dquot_writeback_dquots() in the context should be safe. So let's record task to sbi->umount_lock_holder, so that checkpoint can know whether the lock has held in the context or not by checking current w/ it. In addition, in order to not misrepresent caller of checkpoint, we should not allow to trigger async checkpoint for those callers: mount/umount/remount/ freeze/quotactl.
CVE-2025-23161: In the Linux kernel, the following vulnerability has been resolved: PCI: vmd: Make vmd_dev::cfg_lock a raw_spinlock_t type The access to the PCI config space via pci_ops::read and pci_ops::write is a low-level hardware access. The functions can be accessed with disabled interrupts even on PREEMPT_RT. The pci_lock is a raw_spinlock_t for this purpose. A spinlock_t becomes a sleeping lock on PREEMPT_RT, so it cannot be acquired with disabled interrupts. The vmd_dev::cfg_lock is accessed in the same context as the pci_lock. Make vmd_dev::cfg_lock a raw_spinlock_t type so it can be used with interrupts disabled. This was reported as: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 Call Trace: rt_spin_lock+0x4e/0x130 vmd_pci_read+0x8d/0x100 [vmd] pci_user_read_config_byte+0x6f/0xe0 pci_read_config+0xfe/0x290 sysfs_kf_bin_read+0x68/0x90 [bigeasy: reword commit message] Tested-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com> [kwilczynski: commit log] [bhelgaas: add back report info from https://lore.kernel.org/lkml/20241218115951.83062-1-ryotkkr98@gmail.com/]
CVE-2025-27558: IEEE P802.11-REVme D1.1 through D7.0 allows FragAttacks against mesh networks. In mesh networks using Wi-Fi Protected Access (WPA, WPA2, or WPA3) or Wired Equivalent Privacy (WEP), an adversary can exploit this vulnerability to inject arbitrary frames towards devices that support receiving non-SSP A-MSDU frames. NOTE: this issue exists because of an incorrect fix for CVE-2020-24588. P802.11-REVme, as of early 2025, is a planned release of the 802.11 standard.
CVE-2025-37742: In the Linux kernel, the following vulnerability has been resolved: jfs: Fix uninit-value access of imap allocated in the diMount() function syzbot reports that hex_dump_to_buffer is using uninit-value: ===================================================== BUG: KMSAN: uninit-value in hex_dump_to_buffer+0x888/0x1100 lib/hexdump.c:171 hex_dump_to_buffer+0x888/0x1100 lib/hexdump.c:171 print_hex_dump+0x13d/0x3e0 lib/hexdump.c:276 diFree+0x5ba/0x4350 fs/jfs/jfs_imap.c:876 jfs_evict_inode+0x510/0x550 fs/jfs/inode.c:156 evict+0x723/0xd10 fs/inode.c:796 iput_final fs/inode.c:1946 [inline] iput+0x97b/0xdb0 fs/inode.c:1972 txUpdateMap+0xf3e/0x1150 fs/jfs/jfs_txnmgr.c:2367 txLazyCommit fs/jfs/jfs_txnmgr.c:2664 [inline] jfs_lazycommit+0x627/0x11d0 fs/jfs/jfs_txnmgr.c:2733 kthread+0x6b9/0xef0 kernel/kthread.c:464 ret_from_fork+0x6d/0x90 arch/x86/kernel/process.c:148 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Uninit was created at: slab_post_alloc_hook mm/slub.c:4121 [inline] slab_alloc_node mm/slub.c:4164 [inline] __kmalloc_cache_noprof+0x8e3/0xdf0 mm/slub.c:4320 kmalloc_noprof include/linux/slab.h:901 [inline] diMount+0x61/0x7f0 fs/jfs/jfs_imap.c:105 jfs_mount+0xa8e/0x11d0 fs/jfs/jfs_mount.c:176 jfs_fill_super+0xa47/0x17c0 fs/jfs/super.c:523 get_tree_bdev_flags+0x6ec/0x910 fs/super.c:1636 get_tree_bdev+0x37/0x50 fs/super.c:1659 jfs_get_tree+0x34/0x40 fs/jfs/super.c:635 vfs_get_tree+0xb1/0x5a0 fs/super.c:1814 do_new_mount+0x71f/0x15e0 fs/namespace.c:3560 path_mount+0x742/0x1f10 fs/namespace.c:3887 do_mount fs/namespace.c:3900 [inline] __do_sys_mount fs/namespace.c:4111 [inline] __se_sys_mount+0x71f/0x800 fs/namespace.c:4088 __x64_sys_mount+0xe4/0x150 fs/namespace.c:4088 x64_sys_call+0x39bf/0x3c30 arch/x86/include/generated/asm/syscalls_64.h:166 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f ===================================================== The reason is that imap is not properly initialized after memory allocation. It will cause the snprintf() function to write uninitialized data into linebuf within hex_dump_to_buffer(). Fix this by using kzalloc instead of kmalloc to clear its content at the beginning in diMount().
CVE-2025-37786: In the Linux kernel, the following vulnerability has been resolved: net: dsa: free routing table on probe failure If complete = true in dsa_tree_setup(), it means that we are the last switch of the tree which is successfully probing, and we should be setting up all switches from our probe path. After "complete" becomes true, dsa_tree_setup_cpu_ports() or any subsequent function may fail. If that happens, the entire tree setup is in limbo: the first N-1 switches have successfully finished probing (doing nothing but having allocated persistent memory in the tree's dst->ports, and maybe dst->rtable), and switch N failed to probe, ending the tree setup process before anything is tangible from the user's PoV. If switch N fails to probe, its memory (ports) will be freed and removed from dst->ports. However, the dst->rtable elements pointing to its ports, as created by dsa_link_touch(), will remain there, and will lead to use-after-free if dereferenced. If dsa_tree_setup_switches() returns -EPROBE_DEFER, which is entirely possible because that is where ds->ops->setup() is, we get a kasan report like this: ================================================================== BUG: KASAN: slab-use-after-free in mv88e6xxx_setup_upstream_port+0x240/0x568 Read of size 8 at addr ffff000004f56020 by task kworker/u8:3/42 Call trace: __asan_report_load8_noabort+0x20/0x30 mv88e6xxx_setup_upstream_port+0x240/0x568 mv88e6xxx_setup+0xebc/0x1eb0 dsa_register_switch+0x1af4/0x2ae0 mv88e6xxx_register_switch+0x1b8/0x2a8 mv88e6xxx_probe+0xc4c/0xf60 mdio_probe+0x78/0xb8 really_probe+0x2b8/0x5a8 __driver_probe_device+0x164/0x298 driver_probe_device+0x78/0x258 __device_attach_driver+0x274/0x350 Allocated by task 42: __kasan_kmalloc+0x84/0xa0 __kmalloc_cache_noprof+0x298/0x490 dsa_switch_touch_ports+0x174/0x3d8 dsa_register_switch+0x800/0x2ae0 mv88e6xxx_register_switch+0x1b8/0x2a8 mv88e6xxx_probe+0xc4c/0xf60 mdio_probe+0x78/0xb8 really_probe+0x2b8/0x5a8 __driver_probe_device+0x164/0x298 driver_probe_device+0x78/0x258 __device_attach_driver+0x274/0x350 Freed by task 42: __kasan_slab_free+0x48/0x68 kfree+0x138/0x418 dsa_register_switch+0x2694/0x2ae0 mv88e6xxx_register_switch+0x1b8/0x2a8 mv88e6xxx_probe+0xc4c/0xf60 mdio_probe+0x78/0xb8 really_probe+0x2b8/0x5a8 __driver_probe_device+0x164/0x298 driver_probe_device+0x78/0x258 __device_attach_driver+0x274/0x350 The simplest way to fix the bug is to delete the routing table in its entirety. dsa_tree_setup_routing_table() has no problem in regenerating it even if we deleted links between ports other than those of switch N, because dsa_link_touch() first checks whether the port pair already exists in dst->rtable, allocating if not. The deletion of the routing table in its entirety already exists in dsa_tree_teardown(), so refactor that into a function that can also be called from the tree setup error path. In my analysis of the commit to blame, it is the one which added dsa_link elements to dst->rtable. Prior to that, each switch had its own ds->rtable which is freed when the switch fails to probe. But the tree is potentially persistent memory.
CVE-2025-37800: In the Linux kernel, the following vulnerability has been resolved: driver core: fix potential NULL pointer dereference in dev_uevent() If userspace reads "uevent" device attribute at the same time as another threads unbinds the device from its driver, change to dev->driver from a valid pointer to NULL may result in crash. Fix this by using READ_ONCE() when fetching the pointer, and take bus' drivers klist lock to make sure driver instance will not disappear while we access it. Use WRITE_ONCE() when setting the driver pointer to ensure there is no tearing.
CVE-2025-37807: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix kmemleak warning for percpu hashmap Vlad Poenaru reported the following kmemleak issue: unreferenced object 0x606fd7c44ac8 (size 32): backtrace (crc 0): pcpu_alloc_noprof+0x730/0xeb0 bpf_map_alloc_percpu+0x69/0xc0 prealloc_init+0x9d/0x1b0 htab_map_alloc+0x363/0x510 map_create+0x215/0x3a0 __sys_bpf+0x16b/0x3e0 __x64_sys_bpf+0x18/0x20 do_syscall_64+0x7b/0x150 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Further investigation shows the reason is due to not 8-byte aligned store of percpu pointer in htab_elem_set_ptr(): *(void __percpu **)(l->key + key_size) = pptr; Note that the whole htab_elem alignment is 8 (for x86_64). If the key_size is 4, that means pptr is stored in a location which is 4 byte aligned but not 8 byte aligned. In mm/kmemleak.c, scan_block() scans the memory based on 8 byte stride, so it won't detect above pptr, hence reporting the memory leak. In htab_map_alloc(), we already have htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) htab->elem_size += sizeof(void *); else htab->elem_size += round_up(htab->map.value_size, 8); So storing pptr with 8-byte alignment won't cause any problem and can fix kmemleak too. The issue can be reproduced with bpf selftest as well: 1. Enable CONFIG_DEBUG_KMEMLEAK config 2. Add a getchar() before skel destroy in test_hash_map() in prog_tests/for_each.c. The purpose is to keep map available so kmemleak can be detected. 3. run './test_progs -t for_each/hash_map &' and a kmemleak should be reported.
CVE-2025-37820: In the Linux kernel, the following vulnerability has been resolved: xen-netfront: handle NULL returned by xdp_convert_buff_to_frame() The function xdp_convert_buff_to_frame() may return NULL if it fails to correctly convert the XDP buffer into an XDP frame due to memory constraints, internal errors, or invalid data. Failing to check for NULL may lead to a NULL pointer dereference if the result is used later in processing, potentially causing crashes, data corruption, or undefined behavior. On XDP redirect failure, the associated page must be released explicitly if it was previously retained via get_page(). Failing to do so may result in a memory leak, as the pages reference count is not decremented.
CVE-2025-37833: In the Linux kernel, the following vulnerability has been resolved: net/niu: Niu requires MSIX ENTRY_DATA fields touch before entry reads Fix niu_try_msix() to not cause a fatal trap on sparc systems. Set PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST on the struct pci_dev to work around a bug in the hardware or firmware. For each vector entry in the msix table, niu chips will cause a fatal trap if any registers in that entry are read before that entries' ENTRY_DATA register is written to. Testing indicates writes to other registers are not sufficient to prevent the fatal trap, however the value does not appear to matter. This only needs to happen once after power up, so simply rebooting into a kernel lacking this fix will NOT cause the trap. NON-RESUMABLE ERROR: Reporting on cpu 64 NON-RESUMABLE ERROR: TPC [0x00000000005f6900] <msix_prepare_msi_desc+0x90/0xa0> NON-RESUMABLE ERROR: RAW [4010000000000016:00000e37f93e32ff:0000000202000080:ffffffffffffffff NON-RESUMABLE ERROR: 0000000800000000:0000000000000000:0000000000000000:0000000000000000] NON-RESUMABLE ERROR: handle [0x4010000000000016] stick [0x00000e37f93e32ff] NON-RESUMABLE ERROR: type [precise nonresumable] NON-RESUMABLE ERROR: attrs [0x02000080] < ASI sp-faulted priv > NON-RESUMABLE ERROR: raddr [0xffffffffffffffff] NON-RESUMABLE ERROR: insn effective address [0x000000c50020000c] NON-RESUMABLE ERROR: size [0x8] NON-RESUMABLE ERROR: asi [0x00] CPU: 64 UID: 0 PID: 745 Comm: kworker/64:1 Not tainted 6.11.5 #63 Workqueue: events work_for_cpu_fn TSTATE: 0000000011001602 TPC: 00000000005f6900 TNPC: 00000000005f6904 Y: 00000000 Not tainted TPC: <msix_prepare_msi_desc+0x90/0xa0> g0: 00000000000002e9 g1: 000000000000000c g2: 000000c50020000c g3: 0000000000000100 g4: ffff8000470307c0 g5: ffff800fec5be000 g6: ffff800047a08000 g7: 0000000000000000 o0: ffff800014feb000 o1: ffff800047a0b620 o2: 0000000000000011 o3: ffff800047a0b620 o4: 0000000000000080 o5: 0000000000000011 sp: ffff800047a0ad51 ret_pc: 00000000005f7128 RPC: <__pci_enable_msix_range+0x3cc/0x460> l0: 000000000000000d l1: 000000000000c01f l2: ffff800014feb0a8 l3: 0000000000000020 l4: 000000000000c000 l5: 0000000000000001 l6: 0000000020000000 l7: ffff800047a0b734 i0: ffff800014feb000 i1: ffff800047a0b730 i2: 0000000000000001 i3: 000000000000000d i4: 0000000000000000 i5: 0000000000000000 i6: ffff800047a0ae81 i7: 00000000101888b0 I7: <niu_try_msix.constprop.0+0xc0/0x130 [niu]> Call Trace: [<00000000101888b0>] niu_try_msix.constprop.0+0xc0/0x130 [niu] [<000000001018f840>] niu_get_invariants+0x183c/0x207c [niu] [<00000000101902fc>] niu_pci_init_one+0x27c/0x2fc [niu] [<00000000005ef3e4>] local_pci_probe+0x28/0x74 [<0000000000469240>] work_for_cpu_fn+0x8/0x1c [<000000000046b008>] process_scheduled_works+0x144/0x210 [<000000000046b518>] worker_thread+0x13c/0x1c0 [<00000000004710e0>] kthread+0xb8/0xc8 [<00000000004060c8>] ret_from_fork+0x1c/0x2c [<0000000000000000>] 0x0 Kernel panic - not syncing: Non-resumable error.
CVE-2025-37834: In the Linux kernel, the following vulnerability has been resolved: mm/vmscan: don't try to reclaim hwpoison folio Syzkaller reports a bug as follows: Injecting memory failure for pfn 0x18b00e at process virtual address 0x20ffd000 Memory failure: 0x18b00e: dirty swapcache page still referenced by 2 users Memory failure: 0x18b00e: recovery action for dirty swapcache page: Failed page: refcount:2 mapcount:0 mapping:0000000000000000 index:0x20ffd pfn:0x18b00e memcg:ffff0000dd6d9000 anon flags: 0x5ffffe00482011(locked|dirty|arch_1|swapbacked|hwpoison|node=0|zone=2|lastcpupid=0xfffff) raw: 005ffffe00482011 dead000000000100 dead000000000122 ffff0000e232a7c9 raw: 0000000000020ffd 0000000000000000 00000002ffffffff ffff0000dd6d9000 page dumped because: VM_BUG_ON_FOLIO(!folio_test_uptodate(folio)) ------------[ cut here ]------------ kernel BUG at mm/swap_state.c:184! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP Modules linked in: CPU: 0 PID: 60 Comm: kswapd0 Not tainted 6.6.0-gcb097e7de84e #3 Hardware name: linux,dummy-virt (DT) pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : add_to_swap+0xbc/0x158 lr : add_to_swap+0xbc/0x158 sp : ffff800087f37340 x29: ffff800087f37340 x28: fffffc00052c0380 x27: ffff800087f37780 x26: ffff800087f37490 x25: ffff800087f37c78 x24: ffff800087f377a0 x23: ffff800087f37c50 x22: 0000000000000000 x21: fffffc00052c03b4 x20: 0000000000000000 x19: fffffc00052c0380 x18: 0000000000000000 x17: 296f696c6f662865 x16: 7461646f7470755f x15: 747365745f6f696c x14: 6f6621284f494c4f x13: 0000000000000001 x12: ffff600036d8b97b x11: 1fffe00036d8b97a x10: ffff600036d8b97a x9 : dfff800000000000 x8 : 00009fffc9274686 x7 : ffff0001b6c5cbd3 x6 : 0000000000000001 x5 : ffff0000c25896c0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : ffff0000c25896c0 x0 : 0000000000000000 Call trace: add_to_swap+0xbc/0x158 shrink_folio_list+0x12ac/0x2648 shrink_inactive_list+0x318/0x948 shrink_lruvec+0x450/0x720 shrink_node_memcgs+0x280/0x4a8 shrink_node+0x128/0x978 balance_pgdat+0x4f0/0xb20 kswapd+0x228/0x438 kthread+0x214/0x230 ret_from_fork+0x10/0x20 I can reproduce this issue with the following steps: 1) When a dirty swapcache page is isolated by reclaim process and the page isn't locked, inject memory failure for the page. me_swapcache_dirty() clears uptodate flag and tries to delete from lru, but fails. Reclaim process will put the hwpoisoned page back to lru. 2) The process that maps the hwpoisoned page exits, the page is deleted the page will never be freed and will be in the lru forever. 3) If we trigger a reclaim again and tries to reclaim the page, add_to_swap() will trigger VM_BUG_ON_FOLIO due to the uptodate flag is cleared. To fix it, skip the hwpoisoned page in shrink_folio_list(). Besides, the hwpoison folio may not be unmapped by hwpoison_user_mappings() yet, unmap it in shrink_folio_list(), otherwise the folio will fail to be unmaped by hwpoison_user_mappings() since the folio isn't in lru list.
CVE-2025-37842: In the Linux kernel, the following vulnerability has been resolved: spi: fsl-qspi: use devm function instead of driver remove Driver use devm APIs to manage clk/irq/resources and register the spi controller, but the legacy remove function will be called first during device detach and trigger kernel panic. Drop the remove function and use devm_add_action_or_reset() for driver cleanup to ensure the release sequence. Trigger kernel panic on i.MX8MQ by echo 30bb0000.spi >/sys/bus/platform/drivers/fsl-quadspi/unbind
CVE-2025-37849: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Tear down vGIC on failed vCPU creation If kvm_arch_vcpu_create() fails to share the vCPU page with the hypervisor, we propagate the error back to the ioctl but leave the vGIC vCPU data initialised. Note only does this leak the corresponding memory when the vCPU is destroyed but it can also lead to use-after-free if the redistributor device handling tries to walk into the vCPU. Add the missing cleanup to kvm_arch_vcpu_create(), ensuring that the vGIC vCPU structures are destroyed on error.
CVE-2025-37852: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: handle amdgpu_cgs_create_device() errors in amd_powerplay_create() Add error handling to propagate amdgpu_cgs_create_device() failures to the caller. When amdgpu_cgs_create_device() fails, release hwmgr and return -ENOMEM to prevent null pointer dereference. [v1]->[v2]: Change error code from -EINVAL to -ENOMEM. Free hwmgr.
CVE-2025-37853: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: debugfs hang_hws skip GPU with MES debugfs hang_hws is used by GPU reset test with HWS, for MES this crash the kernel with NULL pointer access because dqm->packet_mgr is not setup for MES path. Skip GPU with MES for now, MES hang_hws debugfs interface will be supported later.
CVE-2025-37879: In the Linux kernel, the following vulnerability has been resolved: 9p/net: fix improper handling of bogus negative read/write replies In p9_client_write() and p9_client_read_once(), if the server incorrectly replies with success but a negative write/read count then we would consider written (negative) <= rsize (positive) because both variables were signed. Make variables unsigned to avoid this problem. The reproducer linked below now fails with the following error instead of a null pointer deref: 9pnet: bogus RWRITE count (4294967295 > 3)
CVE-2025-37880: In the Linux kernel, the following vulnerability has been resolved: um: work around sched_yield not yielding in time-travel mode sched_yield by a userspace may not actually cause scheduling in time-travel mode as no time has passed. In the case seen it appears to be a badly implemented userspace spinlock in ASAN. Unfortunately, with time-travel it causes an extreme slowdown or even deadlock depending on the kernel configuration (CONFIG_UML_MAX_USERSPACE_ITERATIONS). Work around it by accounting time to the process whenever it executes a sched_yield syscall.
CVE-2025-37883: In the Linux kernel, the following vulnerability has been resolved: s390/sclp: Add check for get_zeroed_page() Add check for the return value of get_zeroed_page() in sclp_console_init() to prevent null pointer dereference. Furthermore, to solve the memory leak caused by the loop allocation, add a free helper to do the free job.
CVE-2025-37903: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix slab-use-after-free in hdcp The HDCP code in amdgpu_dm_hdcp.c copies pointers to amdgpu_dm_connector objects without incrementing the kref reference counts. When using a USB-C dock, and the dock is unplugged, the corresponding amdgpu_dm_connector objects are freed, creating dangling pointers in the HDCP code. When the dock is plugged back, the dangling pointers are dereferenced, resulting in a slab-use-after-free: [ 66.775837] BUG: KASAN: slab-use-after-free in event_property_validate+0x42f/0x6c0 [amdgpu] [ 66.776171] Read of size 4 at addr ffff888127804120 by task kworker/0:1/10 [ 66.776179] CPU: 0 UID: 0 PID: 10 Comm: kworker/0:1 Not tainted 6.14.0-rc7-00180-g54505f727a38-dirty #233 [ 66.776183] Hardware name: HP HP Pavilion Aero Laptop 13-be0xxx/8916, BIOS F.17 12/18/2024 [ 66.776186] Workqueue: events event_property_validate [amdgpu] [ 66.776494] Call Trace: [ 66.776496] <TASK> [ 66.776497] dump_stack_lvl+0x70/0xa0 [ 66.776504] print_report+0x175/0x555 [ 66.776507] ? __virt_addr_valid+0x243/0x450 [ 66.776510] ? kasan_complete_mode_report_info+0x66/0x1c0 [ 66.776515] kasan_report+0xeb/0x1c0 [ 66.776518] ? event_property_validate+0x42f/0x6c0 [amdgpu] [ 66.776819] ? event_property_validate+0x42f/0x6c0 [amdgpu] [ 66.777121] __asan_report_load4_noabort+0x14/0x20 [ 66.777124] event_property_validate+0x42f/0x6c0 [amdgpu] [ 66.777342] ? __lock_acquire+0x6b40/0x6b40 [ 66.777347] ? enable_assr+0x250/0x250 [amdgpu] [ 66.777571] process_one_work+0x86b/0x1510 [ 66.777575] ? pwq_dec_nr_in_flight+0xcf0/0xcf0 [ 66.777578] ? assign_work+0x16b/0x280 [ 66.777580] ? lock_is_held_type+0xa3/0x130 [ 66.777583] worker_thread+0x5c0/0xfa0 [ 66.777587] ? process_one_work+0x1510/0x1510 [ 66.777588] kthread+0x3a2/0x840 [ 66.777591] ? kthread_is_per_cpu+0xd0/0xd0 [ 66.777594] ? trace_hardirqs_on+0x4f/0x60 [ 66.777597] ? _raw_spin_unlock_irq+0x27/0x60 [ 66.777599] ? calculate_sigpending+0x77/0xa0 [ 66.777602] ? kthread_is_per_cpu+0xd0/0xd0 [ 66.777605] ret_from_fork+0x40/0x90 [ 66.777607] ? kthread_is_per_cpu+0xd0/0xd0 [ 66.777609] ret_from_fork_asm+0x11/0x20 [ 66.777614] </TASK> [ 66.777643] Allocated by task 10: [ 66.777646] kasan_save_stack+0x39/0x60 [ 66.777649] kasan_save_track+0x14/0x40 [ 66.777652] kasan_save_alloc_info+0x37/0x50 [ 66.777655] __kasan_kmalloc+0xbb/0xc0 [ 66.777658] __kmalloc_cache_noprof+0x1c8/0x4b0 [ 66.777661] dm_dp_add_mst_connector+0xdd/0x5c0 [amdgpu] [ 66.777880] drm_dp_mst_port_add_connector+0x47e/0x770 [drm_display_helper] [ 66.777892] drm_dp_send_link_address+0x1554/0x2bf0 [drm_display_helper] [ 66.777901] drm_dp_check_and_send_link_address+0x187/0x1f0 [drm_display_helper] [ 66.777909] drm_dp_mst_link_probe_work+0x2b8/0x410 [drm_display_helper] [ 66.777917] process_one_work+0x86b/0x1510 [ 66.777919] worker_thread+0x5c0/0xfa0 [ 66.777922] kthread+0x3a2/0x840 [ 66.777925] ret_from_fork+0x40/0x90 [ 66.777927] ret_from_fork_asm+0x11/0x20 [ 66.777932] Freed by task 1713: [ 66.777935] kasan_save_stack+0x39/0x60 [ 66.777938] kasan_save_track+0x14/0x40 [ 66.777940] kasan_save_free_info+0x3b/0x60 [ 66.777944] __kasan_slab_free+0x52/0x70 [ 66.777946] kfree+0x13f/0x4b0 [ 66.777949] dm_dp_mst_connector_destroy+0xfa/0x150 [amdgpu] [ 66.778179] drm_connector_free+0x7d/0xb0 [ 66.778184] drm_mode_object_put.part.0+0xee/0x160 [ 66.778188] drm_mode_object_put+0x37/0x50 [ 66.778191] drm_atomic_state_default_clear+0x220/0xd60 [ 66.778194] __drm_atomic_state_free+0x16e/0x2a0 [ 66.778197] drm_mode_atomic_ioctl+0x15ed/0x2ba0 [ 66.778200] drm_ioctl_kernel+0x17a/0x310 [ 66.778203] drm_ioctl+0x584/0xd10 [ 66.778206] amdgpu_drm_ioctl+0xd2/0x1c0 [amdgpu] [ 66.778375] __x64_sys_ioctl+0x139/0x1a0 [ 66.778378] x64_sys_call+0xee7/0xfb0 [ 66.778381] ---truncated---
CVE-2025-37911: In the Linux kernel, the following vulnerability has been resolved: bnxt_en: Fix out-of-bound memcpy() during ethtool -w When retrieving the FW coredump using ethtool, it can sometimes cause memory corruption: BUG: KFENCE: memory corruption in __bnxt_get_coredump+0x3ef/0x670 [bnxt_en] Corrupted memory at 0x000000008f0f30e8 [ ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ] (in kfence-#45): __bnxt_get_coredump+0x3ef/0x670 [bnxt_en] ethtool_get_dump_data+0xdc/0x1a0 __dev_ethtool+0xa1e/0x1af0 dev_ethtool+0xa8/0x170 dev_ioctl+0x1b5/0x580 sock_do_ioctl+0xab/0xf0 sock_ioctl+0x1ce/0x2e0 __x64_sys_ioctl+0x87/0xc0 do_syscall_64+0x5c/0xf0 entry_SYSCALL_64_after_hwframe+0x78/0x80 ... This happens when copying the coredump segment list in bnxt_hwrm_dbg_dma_data() with the HWRM_DBG_COREDUMP_LIST FW command. The info->dest_buf buffer is allocated based on the number of coredump segments returned by the FW. The segment list is then DMA'ed by the FW and the length of the DMA is returned by FW. The driver then copies this DMA'ed segment list to info->dest_buf. In some cases, this DMA length may exceed the info->dest_buf length and cause the above BUG condition. Fix it by capping the copy length to not exceed the length of info->dest_buf. The extra DMA data contains no useful information. This code path is shared for the HWRM_DBG_COREDUMP_LIST and the HWRM_DBG_COREDUMP_RETRIEVE FW commands. The buffering is different for these 2 FW commands. To simplify the logic, we need to move the line to adjust the buffer length for HWRM_DBG_COREDUMP_RETRIEVE up, so that the new check to cap the copy length will work for both commands.
CVE-2025-37920: In the Linux kernel, the following vulnerability has been resolved: xsk: Fix race condition in AF_XDP generic RX path Move rx_lock from xsk_socket to xsk_buff_pool. Fix synchronization for shared umem mode in generic RX path where multiple sockets share single xsk_buff_pool. RX queue is exclusive to xsk_socket, while FILL queue can be shared between multiple sockets. This could result in race condition where two CPU cores access RX path of two different sockets sharing the same umem. Protect both queues by acquiring spinlock in shared xsk_buff_pool. Lock contention may be minimized in the future by some per-thread FQ buffering. It's safe and necessary to move spin_lock_bh(rx_lock) after xsk_rcv_check(): * xs->pool and spinlock_init is synchronized by xsk_bind() -> xsk_is_bound() memory barriers. * xsk_rcv_check() may return true at the moment of xsk_release() or xsk_unbind_dev(), however this will not cause any data races or race conditions. xsk_unbind_dev() removes xdp socket from all maps and waits for completion of all outstanding rx operations. Packets in RX path will either complete safely or drop.
CVE-2025-37925: In the Linux kernel, the following vulnerability has been resolved: jfs: reject on-disk inodes of an unsupported type Syzbot has reported the following BUG: kernel BUG at fs/inode.c:668! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 3 UID: 0 PID: 139 Comm: jfsCommit Not tainted 6.12.0-rc4-syzkaller-00085-g4e46774408d9 #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-3.fc41 04/01/2014 RIP: 0010:clear_inode+0x168/0x190 Code: 4c 89 f7 e8 ba fe e5 ff e9 61 ff ff ff 44 89 f1 80 e1 07 80 c1 03 38 c1 7c c1 4c 89 f7 e8 90 ff e5 ff eb b7 0b e8 01 5d 7f ff 90 0f 0b e8 f9 5c 7f ff 90 0f 0b e8 f1 5c 7f RSP: 0018:ffffc900027dfae8 EFLAGS: 00010093 RAX: ffffffff82157a87 RBX: 0000000000000001 RCX: ffff888104d4b980 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffffc900027dfc90 R08: ffffffff82157977 R09: fffff520004fbf38 R10: dffffc0000000000 R11: fffff520004fbf38 R12: dffffc0000000000 R13: ffff88811315bc00 R14: ffff88811315bda8 R15: ffff88811315bb80 FS: 0000000000000000(0000) GS:ffff888135f00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005565222e0578 CR3: 0000000026ef0000 CR4: 00000000000006f0 Call Trace: <TASK> ? __die_body+0x5f/0xb0 ? die+0x9e/0xc0 ? do_trap+0x15a/0x3a0 ? clear_inode+0x168/0x190 ? do_error_trap+0x1dc/0x2c0 ? clear_inode+0x168/0x190 ? __pfx_do_error_trap+0x10/0x10 ? report_bug+0x3cd/0x500 ? handle_invalid_op+0x34/0x40 ? clear_inode+0x168/0x190 ? exc_invalid_op+0x38/0x50 ? asm_exc_invalid_op+0x1a/0x20 ? clear_inode+0x57/0x190 ? clear_inode+0x167/0x190 ? clear_inode+0x168/0x190 ? clear_inode+0x167/0x190 jfs_evict_inode+0xb5/0x440 ? __pfx_jfs_evict_inode+0x10/0x10 evict+0x4ea/0x9b0 ? __pfx_evict+0x10/0x10 ? iput+0x713/0xa50 txUpdateMap+0x931/0xb10 ? __pfx_txUpdateMap+0x10/0x10 jfs_lazycommit+0x49a/0xb80 ? _raw_spin_unlock_irqrestore+0x8f/0x140 ? lockdep_hardirqs_on+0x99/0x150 ? __pfx_jfs_lazycommit+0x10/0x10 ? __pfx_default_wake_function+0x10/0x10 ? __kthread_parkme+0x169/0x1d0 ? __pfx_jfs_lazycommit+0x10/0x10 kthread+0x2f2/0x390 ? __pfx_jfs_lazycommit+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x4d/0x80 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> This happens when 'clear_inode()' makes an attempt to finalize an underlying JFS inode of unknown type. According to JFS layout description from https://jfs.sourceforge.net/project/pub/jfslayout.pdf, inode types from 5 to 15 are reserved for future extensions and should not be encountered on a valid filesystem. So add an extra check for valid inode type in 'copy_from_dinode()'.
CVE-2025-37928: In the Linux kernel, the following vulnerability has been resolved: dm-bufio: don't schedule in atomic context A BUG was reported as below when CONFIG_DEBUG_ATOMIC_SLEEP and try_verify_in_tasklet are enabled. [ 129.444685][ T934] BUG: sleeping function called from invalid context at drivers/md/dm-bufio.c:2421 [ 129.444723][ T934] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 934, name: kworker/1:4 [ 129.444740][ T934] preempt_count: 201, expected: 0 [ 129.444756][ T934] RCU nest depth: 0, expected: 0 [ 129.444781][ T934] Preemption disabled at: [ 129.444789][ T934] [<ffffffd816231900>] shrink_work+0x21c/0x248 [ 129.445167][ T934] kernel BUG at kernel/sched/walt/walt_debug.c:16! [ 129.445183][ T934] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP [ 129.445204][ T934] Skip md ftrace buffer dump for: 0x1609e0 [ 129.447348][ T934] CPU: 1 PID: 934 Comm: kworker/1:4 Tainted: G W OE 6.6.56-android15-8-o-g6f82312b30b9-debug #1 1400000003000000474e5500b3187743670464e8 [ 129.447362][ T934] Hardware name: Qualcomm Technologies, Inc. Parrot QRD, Alpha-M (DT) [ 129.447373][ T934] Workqueue: dm_bufio_cache shrink_work [ 129.447394][ T934] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 129.447406][ T934] pc : android_rvh_schedule_bug+0x0/0x8 [sched_walt_debug] [ 129.447435][ T934] lr : __traceiter_android_rvh_schedule_bug+0x44/0x6c [ 129.447451][ T934] sp : ffffffc0843dbc90 [ 129.447459][ T934] x29: ffffffc0843dbc90 x28: ffffffffffffffff x27: 0000000000000c8b [ 129.447479][ T934] x26: 0000000000000040 x25: ffffff804b3d6260 x24: ffffffd816232b68 [ 129.447497][ T934] x23: ffffff805171c5b4 x22: 0000000000000000 x21: ffffffd816231900 [ 129.447517][ T934] x20: ffffff80306ba898 x19: 0000000000000000 x18: ffffffc084159030 [ 129.447535][ T934] x17: 00000000d2b5dd1f x16: 00000000d2b5dd1f x15: ffffffd816720358 [ 129.447554][ T934] x14: 0000000000000004 x13: ffffff89ef978000 x12: 0000000000000003 [ 129.447572][ T934] x11: ffffffd817a823c4 x10: 0000000000000202 x9 : 7e779c5735de9400 [ 129.447591][ T934] x8 : ffffffd81560d004 x7 : 205b5d3938373434 x6 : ffffffd8167397c8 [ 129.447610][ T934] x5 : 0000000000000000 x4 : 0000000000000001 x3 : ffffffc0843db9e0 [ 129.447629][ T934] x2 : 0000000000002f15 x1 : 0000000000000000 x0 : 0000000000000000 [ 129.447647][ T934] Call trace: [ 129.447655][ T934] android_rvh_schedule_bug+0x0/0x8 [sched_walt_debug 1400000003000000474e550080cce8a8a78606b6] [ 129.447681][ T934] __might_resched+0x190/0x1a8 [ 129.447694][ T934] shrink_work+0x180/0x248 [ 129.447706][ T934] process_one_work+0x260/0x624 [ 129.447718][ T934] worker_thread+0x28c/0x454 [ 129.447729][ T934] kthread+0x118/0x158 [ 129.447742][ T934] ret_from_fork+0x10/0x20 [ 129.447761][ T934] Code: ???????? ???????? ???????? d2b5dd1f (d4210000) [ 129.447772][ T934] ---[ end trace 0000000000000000 ]--- dm_bufio_lock will call spin_lock_bh when try_verify_in_tasklet is enabled, and __scan will be called in atomic context.
CVE-2025-37951: In the Linux kernel, the following vulnerability has been resolved: drm/v3d: Add job to pending list if the reset was skipped When a CL/CSD job times out, we check if the GPU has made any progress since the last timeout. If so, instead of resetting the hardware, we skip the reset and let the timer get rearmed. This gives long-running jobs a chance to complete. However, when `timedout_job()` is called, the job in question is removed from the pending list, which means it won't be automatically freed through `free_job()`. Consequently, when we skip the reset and keep the job running, the job won't be freed when it finally completes. This situation leads to a memory leak, as exposed in [1] and [2]. Similarly to commit 704d3d60fec4 ("drm/etnaviv: don't block scheduler when GPU is still active"), this patch ensures the job is put back on the pending list when extending the timeout.
CVE-2025-37959: In the Linux kernel, the following vulnerability has been resolved: bpf: Scrub packet on bpf_redirect_peer When bpf_redirect_peer is used to redirect packets to a device in another network namespace, the skb isn't scrubbed. That can lead skb information from one namespace to be "misused" in another namespace. As one example, this is causing Cilium to drop traffic when using bpf_redirect_peer to redirect packets that just went through IPsec decryption to a container namespace. The following pwru trace shows (1) the packet path from the host's XFRM layer to the container's XFRM layer where it's dropped and (2) the number of active skb extensions at each function. NETNS MARK IFACE TUPLE FUNC 4026533547 d00 eth0 10.244.3.124:35473->10.244.2.158:53 xfrm_rcv_cb .active_extensions = (__u8)2, 4026533547 d00 eth0 10.244.3.124:35473->10.244.2.158:53 xfrm4_rcv_cb .active_extensions = (__u8)2, 4026533547 d00 eth0 10.244.3.124:35473->10.244.2.158:53 gro_cells_receive .active_extensions = (__u8)2, [...] 4026533547 0 eth0 10.244.3.124:35473->10.244.2.158:53 skb_do_redirect .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 ip_rcv .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 ip_rcv_core .active_extensions = (__u8)2, [...] 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 udp_queue_rcv_one_skb .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 __xfrm_policy_check .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 __xfrm_decode_session .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 security_xfrm_decode_session .active_extensions = (__u8)2, 4026534999 0 eth0 10.244.3.124:35473->10.244.2.158:53 kfree_skb_reason(SKB_DROP_REASON_XFRM_POLICY) .active_extensions = (__u8)2, In this case, there are no XFRM policies in the container's network namespace so the drop is unexpected. When we decrypt the IPsec packet, the XFRM state used for decryption is set in the skb extensions. This information is preserved across the netns switch. When we reach the XFRM policy check in the container's netns, __xfrm_policy_check drops the packet with LINUX_MIB_XFRMINNOPOLS because a (container-side) XFRM policy can't be found that matches the (host-side) XFRM state used for decryption. This patch fixes this by scrubbing the packet when using bpf_redirect_peer, as is done on typical netns switches via veth devices except skb->mark and skb->tstamp are not zeroed.
CVE-2025-37961: In the Linux kernel, the following vulnerability has been resolved: ipvs: fix uninit-value for saddr in do_output_route4 syzbot reports for uninit-value for the saddr argument [1]. commit 4754957f04f5 ("ipvs: do not use random local source address for tunnels") already implies that the input value of saddr should be ignored but the code is still reading it which can prevent to connect the route. Fix it by changing the argument to ret_saddr. [1] BUG: KMSAN: uninit-value in do_output_route4+0x42c/0x4d0 net/netfilter/ipvs/ip_vs_xmit.c:147 do_output_route4+0x42c/0x4d0 net/netfilter/ipvs/ip_vs_xmit.c:147 __ip_vs_get_out_rt+0x403/0x21d0 net/netfilter/ipvs/ip_vs_xmit.c:330 ip_vs_tunnel_xmit+0x205/0x2380 net/netfilter/ipvs/ip_vs_xmit.c:1136 ip_vs_in_hook+0x1aa5/0x35b0 net/netfilter/ipvs/ip_vs_core.c:2063 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xf7/0x400 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] __ip_local_out+0x758/0x7e0 net/ipv4/ip_output.c:118 ip_local_out net/ipv4/ip_output.c:127 [inline] ip_send_skb+0x6a/0x3c0 net/ipv4/ip_output.c:1501 udp_send_skb+0xfda/0x1b70 net/ipv4/udp.c:1195 udp_sendmsg+0x2fe3/0x33c0 net/ipv4/udp.c:1483 inet_sendmsg+0x1fc/0x280 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:712 [inline] __sock_sendmsg+0x267/0x380 net/socket.c:727 ____sys_sendmsg+0x91b/0xda0 net/socket.c:2566 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2620 __sys_sendmmsg+0x41d/0x880 net/socket.c:2702 __compat_sys_sendmmsg net/compat.c:360 [inline] __do_compat_sys_sendmmsg net/compat.c:367 [inline] __se_compat_sys_sendmmsg net/compat.c:364 [inline] __ia32_compat_sys_sendmmsg+0xc8/0x140 net/compat.c:364 ia32_sys_call+0x3ffa/0x41f0 arch/x86/include/generated/asm/syscalls_32.h:346 do_syscall_32_irqs_on arch/x86/entry/syscall_32.c:83 [inline] __do_fast_syscall_32+0xb0/0x110 arch/x86/entry/syscall_32.c:306 do_fast_syscall_32+0x38/0x80 arch/x86/entry/syscall_32.c:331 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/syscall_32.c:369 entry_SYSENTER_compat_after_hwframe+0x84/0x8e Uninit was created at: slab_post_alloc_hook mm/slub.c:4167 [inline] slab_alloc_node mm/slub.c:4210 [inline] __kmalloc_cache_noprof+0x8fa/0xe00 mm/slub.c:4367 kmalloc_noprof include/linux/slab.h:905 [inline] ip_vs_dest_dst_alloc net/netfilter/ipvs/ip_vs_xmit.c:61 [inline] __ip_vs_get_out_rt+0x35d/0x21d0 net/netfilter/ipvs/ip_vs_xmit.c:323 ip_vs_tunnel_xmit+0x205/0x2380 net/netfilter/ipvs/ip_vs_xmit.c:1136 ip_vs_in_hook+0x1aa5/0x35b0 net/netfilter/ipvs/ip_vs_core.c:2063 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xf7/0x400 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] __ip_local_out+0x758/0x7e0 net/ipv4/ip_output.c:118 ip_local_out net/ipv4/ip_output.c:127 [inline] ip_send_skb+0x6a/0x3c0 net/ipv4/ip_output.c:1501 udp_send_skb+0xfda/0x1b70 net/ipv4/udp.c:1195 udp_sendmsg+0x2fe3/0x33c0 net/ipv4/udp.c:1483 inet_sendmsg+0x1fc/0x280 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:712 [inline] __sock_sendmsg+0x267/0x380 net/socket.c:727 ____sys_sendmsg+0x91b/0xda0 net/socket.c:2566 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2620 __sys_sendmmsg+0x41d/0x880 net/socket.c:2702 __compat_sys_sendmmsg net/compat.c:360 [inline] __do_compat_sys_sendmmsg net/compat.c:367 [inline] __se_compat_sys_sendmmsg net/compat.c:364 [inline] __ia32_compat_sys_sendmmsg+0xc8/0x140 net/compat.c:364 ia32_sys_call+0x3ffa/0x41f0 arch/x86/include/generated/asm/syscalls_32.h:346 do_syscall_32_irqs_on arch/x86/entry/syscall_32.c:83 [inline] __do_fast_syscall_32+0xb0/0x110 arch/x86/entry/syscall_32.c:306 do_fast_syscall_32+0x38/0x80 arch/x86/entry/syscall_32.c:331 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/syscall_32.c:369 entry_SYSENTER_compat_after_hwframe+0x84/0x8e CPU: 0 UID: 0 PID: 22408 Comm: syz.4.5165 Not tainted 6.15.0-rc3-syzkaller-00019-gbc3372351d0c #0 PREEMPT(undef) Hardware name: Google Google Compute Engi ---truncated---
CVE-2025-37967: In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: displayport: Fix deadlock This patch introduces the ucsi_con_mutex_lock / ucsi_con_mutex_unlock functions to the UCSI driver. ucsi_con_mutex_lock ensures the connector mutex is only locked if a connection is established and the partner pointer is valid. This resolves a deadlock scenario where ucsi_displayport_remove_partner holds con->mutex waiting for dp_altmode_work to complete while dp_altmode_work attempts to acquire it.
CVE-2025-37980: In the Linux kernel, the following vulnerability has been resolved: block: fix resource leak in blk_register_queue() error path When registering a queue fails after blk_mq_sysfs_register() is successful but the function later encounters an error, we need to clean up the blk_mq_sysfs resources. Add the missing blk_mq_sysfs_unregister() call in the error path to properly clean up these resources and prevent a memory leak.
CVE-2025-38014: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Refactor remove call with idxd_cleanup() helper The idxd_cleanup() helper cleans up perfmon, interrupts, internals and so on. Refactor remove call with the idxd_cleanup() helper to avoid code duplication. Note, this also fixes the missing put_device() for idxd groups, enginces and wqs.
CVE-2025-38029: In the Linux kernel, the following vulnerability has been resolved: kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range.
CVE-2025-38040: In the Linux kernel, the following vulnerability has been resolved: serial: mctrl_gpio: split disable_ms into sync and no_sync APIs The following splat has been observed on a SAMA5D27 platform using atmel_serial: BUG: sleeping function called from invalid context at kernel/irq/manage.c:738 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 27, name: kworker/u5:0 preempt_count: 1, expected: 0 INFO: lockdep is turned off. irq event stamp: 0 hardirqs last enabled at (0): [<00000000>] 0x0 hardirqs last disabled at (0): [<c01588f0>] copy_process+0x1c4c/0x7bec softirqs last enabled at (0): [<c0158944>] copy_process+0x1ca0/0x7bec softirqs last disabled at (0): [<00000000>] 0x0 CPU: 0 UID: 0 PID: 27 Comm: kworker/u5:0 Not tainted 6.13.0-rc7+ #74 Hardware name: Atmel SAMA5 Workqueue: hci0 hci_power_on [bluetooth] Call trace: unwind_backtrace from show_stack+0x18/0x1c show_stack from dump_stack_lvl+0x44/0x70 dump_stack_lvl from __might_resched+0x38c/0x598 __might_resched from disable_irq+0x1c/0x48 disable_irq from mctrl_gpio_disable_ms+0x74/0xc0 mctrl_gpio_disable_ms from atmel_disable_ms.part.0+0x80/0x1f4 atmel_disable_ms.part.0 from atmel_set_termios+0x764/0x11e8 atmel_set_termios from uart_change_line_settings+0x15c/0x994 uart_change_line_settings from uart_set_termios+0x2b0/0x668 uart_set_termios from tty_set_termios+0x600/0x8ec tty_set_termios from ttyport_set_flow_control+0x188/0x1e0 ttyport_set_flow_control from wilc_setup+0xd0/0x524 [hci_wilc] wilc_setup [hci_wilc] from hci_dev_open_sync+0x330/0x203c [bluetooth] hci_dev_open_sync [bluetooth] from hci_dev_do_open+0x40/0xb0 [bluetooth] hci_dev_do_open [bluetooth] from hci_power_on+0x12c/0x664 [bluetooth] hci_power_on [bluetooth] from process_one_work+0x998/0x1a38 process_one_work from worker_thread+0x6e0/0xfb4 worker_thread from kthread+0x3d4/0x484 kthread from ret_from_fork+0x14/0x28 This warning is emitted when trying to toggle, at the highest level, some flow control (with serdev_device_set_flow_control) in a device driver. At the lowest level, the atmel_serial driver is using serial_mctrl_gpio lib to enable/disable the corresponding IRQs accordingly. The warning emitted by CONFIG_DEBUG_ATOMIC_SLEEP is due to disable_irq (called in mctrl_gpio_disable_ms) being possibly called in some atomic context (some tty drivers perform modem lines configuration in regions protected by port lock). Split mctrl_gpio_disable_ms into two differents APIs, a non-blocking one and a blocking one. Replace mctrl_gpio_disable_ms calls with the relevant version depending on whether the call is protected by some port lock.
CVE-2025-38042: In the Linux kernel, the following vulnerability has been resolved: dmaengine: ti: k3-udma-glue: Drop skip_fdq argument from k3_udma_glue_reset_rx_chn The user of k3_udma_glue_reset_rx_chn() e.g. ti_am65_cpsw_nuss can run on multiple platforms having different DMA architectures. On some platforms there can be one FDQ for all flows in the RX channel while for others there is a separate FDQ for each flow in the RX channel. So far we have been relying on the skip_fdq argument of k3_udma_glue_reset_rx_chn(). Instead of relying on the user to provide this information, infer it based on DMA architecture during k3_udma_glue_request_rx_chn() and save it in an internal flag 'single_fdq'. Use that flag at k3_udma_glue_reset_rx_chn() to deicide if the FDQ needs to be cleared for every flow or just for flow 0. Fixes the below issue on ti_am65_cpsw_nuss driver on AM62-SK. > ip link set eth1 down > ip link set eth0 down > ethtool -L eth0 rx 8 > ip link set eth0 up > modprobe -r ti_am65_cpsw_nuss [ 103.045726] ------------[ cut here ]------------ [ 103.050505] k3_knav_desc_pool size 512000 != avail 64000 [ 103.050703] WARNING: CPU: 1 PID: 450 at drivers/net/ethernet/ti/k3-cppi-desc-pool.c:33 k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.068810] Modules linked in: ti_am65_cpsw_nuss(-) k3_cppi_desc_pool snd_soc_hdmi_codec crct10dif_ce snd_soc_simple_card snd_soc_simple_card_utils display_connector rtc_ti_k3 k3_j72xx_bandgap tidss drm_client_lib snd_soc_davinci_mcas p drm_dma_helper tps6598x phylink snd_soc_ti_udma rti_wdt drm_display_helper snd_soc_tlv320aic3x_i2c typec at24 phy_gmii_sel snd_soc_ti_edma snd_soc_tlv320aic3x sii902x snd_soc_ti_sdma sa2ul omap_mailbox drm_kms_helper authenc cfg80211 r fkill fuse drm drm_panel_orientation_quirks backlight ip_tables x_tables ipv6 [last unloaded: k3_cppi_desc_pool] [ 103.119950] CPU: 1 UID: 0 PID: 450 Comm: modprobe Not tainted 6.13.0-rc7-00001-g9c5e3435fa66 #1011 [ 103.119968] Hardware name: Texas Instruments AM625 SK (DT) [ 103.119974] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 103.119983] pc : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.148007] lr : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.154709] sp : ffff8000826ebbc0 [ 103.158015] x29: ffff8000826ebbc0 x28: ffff0000090b6300 x27: 0000000000000000 [ 103.165145] x26: 0000000000000000 x25: 0000000000000000 x24: ffff0000019df6b0 [ 103.172271] x23: ffff0000019df6b8 x22: ffff0000019df410 x21: ffff8000826ebc88 [ 103.179397] x20: 000000000007d000 x19: ffff00000a3b3000 x18: 0000000000000000 [ 103.186522] x17: 0000000000000000 x16: 0000000000000000 x15: 000001e8c35e1cde [ 103.193647] x14: 0000000000000396 x13: 000000000000035c x12: 0000000000000000 [ 103.200772] x11: 000000000000003a x10: 00000000000009c0 x9 : ffff8000826eba20 [ 103.207897] x8 : ffff0000090b6d20 x7 : ffff00007728c180 x6 : ffff00007728c100 [ 103.215022] x5 : 0000000000000001 x4 : ffff000000508a50 x3 : ffff7ffff6146000 [ 103.222147] x2 : 0000000000000000 x1 : e300b4173ee6b200 x0 : 0000000000000000 [ 103.229274] Call trace: [ 103.231714] k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] (P) [ 103.238408] am65_cpsw_nuss_free_rx_chns+0x28/0x4c [ti_am65_cpsw_nuss] [ 103.244942] devm_action_release+0x14/0x20 [ 103.249040] release_nodes+0x3c/0x68 [ 103.252610] devres_release_all+0x8c/0xdc [ 103.256614] device_unbind_cleanup+0x18/0x60 [ 103.260876] device_release_driver_internal+0xf8/0x178 [ 103.266004] driver_detach+0x50/0x9c [ 103.269571] bus_remove_driver+0x6c/0xbc [ 103.273485] driver_unregister+0x30/0x60 [ 103.277401] platform_driver_unregister+0x14/0x20 [ 103.282096] am65_cpsw_nuss_driver_exit+0x18/0xff4 [ti_am65_cpsw_nuss] [ 103.288620] __arm64_sys_delete_module+0x17c/0x25c [ 103.293404] invoke_syscall+0x44/0x100 [ 103.297149] el0_svc_common.constprop.0+0xc0/0xe0 [ 103.301845] do_el0_svc+0x1c/0x28 [ 103.305155] el0_svc+0x28/0x98 ---truncated---
CVE-2025-38057: In the Linux kernel, the following vulnerability has been resolved: espintcp: fix skb leaks A few error paths are missing a kfree_skb.
CVE-2025-38059: In the Linux kernel, the following vulnerability has been resolved: btrfs: avoid NULL pointer dereference if no valid csum tree [BUG] When trying read-only scrub on a btrfs with rescue=idatacsums mount option, it will crash with the following call trace: BUG: kernel NULL pointer dereference, address: 0000000000000208 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page CPU: 1 UID: 0 PID: 835 Comm: btrfs Tainted: G O 6.15.0-rc3-custom+ #236 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022 RIP: 0010:btrfs_lookup_csums_bitmap+0x49/0x480 [btrfs] Call Trace: <TASK> scrub_find_fill_first_stripe+0x35b/0x3d0 [btrfs] scrub_simple_mirror+0x175/0x290 [btrfs] scrub_stripe+0x5f7/0x6f0 [btrfs] scrub_chunk+0x9a/0x150 [btrfs] scrub_enumerate_chunks+0x333/0x660 [btrfs] btrfs_scrub_dev+0x23e/0x600 [btrfs] btrfs_ioctl+0x1dcf/0x2f80 [btrfs] __x64_sys_ioctl+0x97/0xc0 do_syscall_64+0x4f/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e [CAUSE] Mount option "rescue=idatacsums" will completely skip loading the csum tree, so that any data read will not find any data csum thus we will ignore data checksum verification. Normally call sites utilizing csum tree will check the fs state flag NO_DATA_CSUMS bit, but unfortunately scrub does not check that bit at all. This results in scrub to call btrfs_search_slot() on a NULL pointer and triggered above crash. [FIX] Check both extent and csum tree root before doing any tree search.
CVE-2025-38062: In the Linux kernel, the following vulnerability has been resolved: genirq/msi: Store the IOMMU IOVA directly in msi_desc instead of iommu_cookie The IOMMU translation for MSI message addresses has been a 2-step process, separated in time: 1) iommu_dma_prepare_msi(): A cookie pointer containing the IOVA address is stored in the MSI descriptor when an MSI interrupt is allocated. 2) iommu_dma_compose_msi_msg(): this cookie pointer is used to compute a translated message address. This has an inherent lifetime problem for the pointer stored in the cookie that must remain valid between the two steps. However, there is no locking at the irq layer that helps protect the lifetime. Today, this works under the assumption that the iommu domain is not changed while MSI interrupts being programmed. This is true for normal DMA API users within the kernel, as the iommu domain is attached before the driver is probed and cannot be changed while a driver is attached. Classic VFIO type1 also prevented changing the iommu domain while VFIO was running as it does not support changing the "container" after starting up. However, iommufd has improved this so that the iommu domain can be changed during VFIO operation. This potentially allows userspace to directly race VFIO_DEVICE_ATTACH_IOMMUFD_PT (which calls iommu_attach_group()) and VFIO_DEVICE_SET_IRQS (which calls into iommu_dma_compose_msi_msg()). This potentially causes both the cookie pointer and the unlocked call to iommu_get_domain_for_dev() on the MSI translation path to become UAFs. Fix the MSI cookie UAF by removing the cookie pointer. The translated IOVA address is already known during iommu_dma_prepare_msi() and cannot change. Thus, it can simply be stored as an integer in the MSI descriptor. The other UAF related to iommu_get_domain_for_dev() will be addressed in patch "iommu: Make iommu_dma_prepare_msi() into a generic operation" by using the IOMMU group mutex.
CVE-2025-38063: In the Linux kernel, the following vulnerability has been resolved: dm: fix unconditional IO throttle caused by REQ_PREFLUSH When a bio with REQ_PREFLUSH is submitted to dm, __send_empty_flush() generates a flush_bio with REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC, which causes the flush_bio to be throttled by wbt_wait(). An example from v5.4, similar problem also exists in upstream: crash> bt 2091206 PID: 2091206 TASK: ffff2050df92a300 CPU: 109 COMMAND: "kworker/u260:0" #0 [ffff800084a2f7f0] __switch_to at ffff80004008aeb8 #1 [ffff800084a2f820] __schedule at ffff800040bfa0c4 #2 [ffff800084a2f880] schedule at ffff800040bfa4b4 #3 [ffff800084a2f8a0] io_schedule at ffff800040bfa9c4 #4 [ffff800084a2f8c0] rq_qos_wait at ffff8000405925bc #5 [ffff800084a2f940] wbt_wait at ffff8000405bb3a0 #6 [ffff800084a2f9a0] __rq_qos_throttle at ffff800040592254 #7 [ffff800084a2f9c0] blk_mq_make_request at ffff80004057cf38 #8 [ffff800084a2fa60] generic_make_request at ffff800040570138 #9 [ffff800084a2fae0] submit_bio at ffff8000405703b4 #10 [ffff800084a2fb50] xlog_write_iclog at ffff800001280834 [xfs] #11 [ffff800084a2fbb0] xlog_sync at ffff800001280c3c [xfs] #12 [ffff800084a2fbf0] xlog_state_release_iclog at ffff800001280df4 [xfs] #13 [ffff800084a2fc10] xlog_write at ffff80000128203c [xfs] #14 [ffff800084a2fcd0] xlog_cil_push at ffff8000012846dc [xfs] #15 [ffff800084a2fda0] xlog_cil_push_work at ffff800001284a2c [xfs] #16 [ffff800084a2fdb0] process_one_work at ffff800040111d08 #17 [ffff800084a2fe00] worker_thread at ffff8000401121cc #18 [ffff800084a2fe70] kthread at ffff800040118de4 After commit 2def2845cc33 ("xfs: don't allow log IO to be throttled"), the metadata submitted by xlog_write_iclog() should not be throttled. But due to the existence of the dm layer, throttling flush_bio indirectly causes the metadata bio to be throttled. Fix this by conditionally adding REQ_IDLE to flush_bio.bi_opf, which makes wbt_should_throttle() return false to avoid wbt_wait().
CVE-2025-38064: In the Linux kernel, the following vulnerability has been resolved: virtio: break and reset virtio devices on device_shutdown() Hongyu reported a hang on kexec in a VM. QEMU reported invalid memory accesses during the hang. Invalid read at addr 0x102877002, size 2, region '(null)', reason: rejected Invalid write at addr 0x102877A44, size 2, region '(null)', reason: rejected ... It was traced down to virtio-console. Kexec works fine if virtio-console is not in use. The issue is that virtio-console continues to write to the MMIO even after underlying virtio-pci device is reset. Additionally, Eric noticed that IOMMUs are reset before devices, if devices are not reset on shutdown they continue to poke at guest memory and get errors from the IOMMU. Some devices get wedged then. The problem can be solved by breaking all virtio devices on virtio bus shutdown, then resetting them.
CVE-2025-38068: In the Linux kernel, the following vulnerability has been resolved: crypto: lzo - Fix compression buffer overrun Unlike the decompression code, the compression code in LZO never checked for output overruns. It instead assumes that the caller always provides enough buffer space, disregarding the buffer length provided by the caller. Add a safe compression interface that checks for the end of buffer before each write. Use the safe interface in crypto/lzo.
CVE-2025-38069: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-test: Fix double free that causes kernel to oops Fix a kernel oops found while testing the stm32_pcie Endpoint driver with handling of PERST# deassertion: During EP initialization, pci_epf_test_alloc_space() allocates all BARs, which are further freed if epc_set_bar() fails (for instance, due to no free inbound window). However, when pci_epc_set_bar() fails, the error path: pci_epc_set_bar() -> pci_epf_free_space() does not clear the previous assignment to epf_test->reg[bar]. Then, if the host reboots, the PERST# deassertion restarts the BAR allocation sequence with the same allocation failure (no free inbound window), creating a double free situation since epf_test->reg[bar] was deallocated and is still non-NULL. Thus, make sure that pci_epf_alloc_space() and pci_epf_free_space() invocations are symmetric, and as such, set epf_test->reg[bar] to NULL when memory is freed. [kwilczynski: commit log]
CVE-2025-38080: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Increase block_sequence array size [Why] It's possible to generate more than 50 steps in hwss_build_fast_sequence, for example with a 6-pipe asic where all pipes are in one MPC chain. This overflows the block_sequence buffer and corrupts block_sequence_steps, causing a crash. [How] Expand block_sequence to 100 items. A naive upper bound on the possible number of steps for a 6-pipe asic, ignoring the potential for steps to be mutually exclusive, is 91 with current code, therefore 100 is sufficient.
CVE-2025-38096: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: don't warn when if there is a FW error iwl_trans_reclaim is warning if it is called when the FW is not alive. But if it is called when there is a pending restart, i.e. after a FW error, there is no need to warn, instead - return silently.
CVE-2025-38097: In the Linux kernel, the following vulnerability has been resolved: espintcp: remove encap socket caching to avoid reference leak The current scheme for caching the encap socket can lead to reference leaks when we try to delete the netns. The reference chain is: xfrm_state -> enacp_sk -> netns Since the encap socket is a userspace socket, it holds a reference on the netns. If we delete the espintcp state (through flush or individual delete) before removing the netns, the reference on the socket is dropped and the netns is correctly deleted. Otherwise, the netns may not be reachable anymore (if all processes within the ns have terminated), so we cannot delete the xfrm state to drop its reference on the socket. This patch results in a small (~2% in my tests) performance regression. A GC-type mechanism could be added for the socket cache, to clear references if the state hasn't been used "recently", but it's a lot more complex than just not caching the socket.
CVE-2025-38105: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Kill timer properly at removal The USB-audio MIDI code initializes the timer, but in a rare case, the driver might be freed without the disconnect call. This leaves the timer in an active state while the assigned object is released via snd_usbmidi_free(), which ends up with a kernel warning when the debug configuration is enabled, as spotted by fuzzer. For avoiding the problem, put timer_shutdown_sync() at snd_usbmidi_free(), so that the timer can be killed properly. While we're at it, replace the existing timer_delete_sync() at the disconnect callback with timer_shutdown_sync(), too.
CVE-2025-38117: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Protect mgmt_pending list with its own lock This uses a mutex to protect from concurrent access of mgmt_pending list which can cause crashes like: ================================================================== BUG: KASAN: slab-use-after-free in hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91 Read of size 2 at addr ffff0000c48885b2 by task syz.4.334/7318 CPU: 0 UID: 0 PID: 7318 Comm: syz.4.334 Not tainted 6.15.0-rc7-syzkaller-g187899f4124a #0 PREEMPT Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025 Call trace: show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:466 (C) __dump_stack+0x30/0x40 lib/dump_stack.c:94 dump_stack_lvl+0xd8/0x12c lib/dump_stack.c:120 print_address_description+0xa8/0x254 mm/kasan/report.c:408 print_report+0x68/0x84 mm/kasan/report.c:521 kasan_report+0xb0/0x110 mm/kasan/report.c:634 __asan_report_load2_noabort+0x20/0x2c mm/kasan/report_generic.c:379 hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91 mgmt_pending_find+0x7c/0x140 net/bluetooth/mgmt_util.c:223 pending_find net/bluetooth/mgmt.c:947 [inline] remove_adv_monitor+0x44/0x1a4 net/bluetooth/mgmt.c:5445 hci_mgmt_cmd+0x780/0xc00 net/bluetooth/hci_sock.c:1712 hci_sock_sendmsg+0x544/0xbb0 net/bluetooth/hci_sock.c:1832 sock_sendmsg_nosec net/socket.c:712 [inline] __sock_sendmsg net/socket.c:727 [inline] sock_write_iter+0x25c/0x378 net/socket.c:1131 new_sync_write fs/read_write.c:591 [inline] vfs_write+0x62c/0x97c fs/read_write.c:684 ksys_write+0x120/0x210 fs/read_write.c:736 __do_sys_write fs/read_write.c:747 [inline] __se_sys_write fs/read_write.c:744 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:744 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600 Allocated by task 7037: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x44/0x54 mm/kasan/generic.c:562 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x9c/0xb4 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __do_kmalloc_node mm/slub.c:4327 [inline] __kmalloc_noprof+0x2fc/0x4c8 mm/slub.c:4339 kmalloc_noprof include/linux/slab.h:909 [inline] sk_prot_alloc+0xc4/0x1f0 net/core/sock.c:2198 sk_alloc+0x44/0x3ac net/core/sock.c:2254 bt_sock_alloc+0x4c/0x300 net/bluetooth/af_bluetooth.c:148 hci_sock_create+0xa8/0x194 net/bluetooth/hci_sock.c:2202 bt_sock_create+0x14c/0x24c net/bluetooth/af_bluetooth.c:132 __sock_create+0x43c/0x91c net/socket.c:1541 sock_create net/socket.c:1599 [inline] __sys_socket_create net/socket.c:1636 [inline] __sys_socket+0xd4/0x1c0 net/socket.c:1683 __do_sys_socket net/socket.c:1697 [inline] __se_sys_socket net/socket.c:1695 [inline] __arm64_sys_socket+0x7c/0x94 net/socket.c:1695 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600 Freed by task 6607: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:576 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x68/0x88 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline ---truncated---
CVE-2025-38125: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: make sure that ptp_rate is not 0 before configuring EST If the ptp_rate recorded earlier in the driver happens to be 0, this bogus value will propagate up to EST configuration, where it will trigger a division by 0. Prevent this division by 0 by adding the corresponding check and error code.
CVE-2025-38126: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: make sure that ptp_rate is not 0 before configuring timestamping The stmmac platform drivers that do not open-code the clk_ptp_rate value after having retrieved the default one from the device-tree can end up with 0 in clk_ptp_rate (as clk_get_rate can return 0). It will eventually propagate up to PTP initialization when bringing up the interface, leading to a divide by 0: Division by zero in kernel. CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.30-00001-g48313bd5768a #22 Hardware name: STM32 (Device Tree Support) Call trace: unwind_backtrace from show_stack+0x18/0x1c show_stack from dump_stack_lvl+0x6c/0x8c dump_stack_lvl from Ldiv0_64+0x8/0x18 Ldiv0_64 from stmmac_init_tstamp_counter+0x190/0x1a4 stmmac_init_tstamp_counter from stmmac_hw_setup+0xc1c/0x111c stmmac_hw_setup from __stmmac_open+0x18c/0x434 __stmmac_open from stmmac_open+0x3c/0xbc stmmac_open from __dev_open+0xf4/0x1ac __dev_open from __dev_change_flags+0x1cc/0x224 __dev_change_flags from dev_change_flags+0x24/0x60 dev_change_flags from ip_auto_config+0x2e8/0x11a0 ip_auto_config from do_one_initcall+0x84/0x33c do_one_initcall from kernel_init_freeable+0x1b8/0x214 kernel_init_freeable from kernel_init+0x24/0x140 kernel_init from ret_from_fork+0x14/0x28 Exception stack(0xe0815fb0 to 0xe0815ff8) Prevent this division by 0 by adding an explicit check and error log about the actual issue. While at it, remove the same check from stmmac_ptp_register, which then becomes duplicate
CVE-2025-38127: In the Linux kernel, the following vulnerability has been resolved: ice: fix Tx scheduler error handling in XDP callback When the XDP program is loaded, the XDP callback adds new Tx queues. This means that the callback must update the Tx scheduler with the new queue number. In the event of a Tx scheduler failure, the XDP callback should also fail and roll back any changes previously made for XDP preparation. The previous implementation had a bug that not all changes made by the XDP callback were rolled back. This caused the crash with the following call trace: [ +9.549584] ice 0000:ca:00.0: Failed VSI LAN queue config for XDP, error: -5 [ +0.382335] Oops: general protection fault, probably for non-canonical address 0x50a2250a90495525: 0000 [#1] SMP NOPTI [ +0.010710] CPU: 103 UID: 0 PID: 0 Comm: swapper/103 Not tainted 6.14.0-net-next-mar-31+ #14 PREEMPT(voluntary) [ +0.010175] Hardware name: Intel Corporation M50CYP2SBSTD/M50CYP2SBSTD, BIOS SE5C620.86B.01.01.0005.2202160810 02/16/2022 [ +0.010946] RIP: 0010:__ice_update_sample+0x39/0xe0 [ice] [...] [ +0.002715] Call Trace: [ +0.002452] <IRQ> [ +0.002021] ? __die_body.cold+0x19/0x29 [ +0.003922] ? die_addr+0x3c/0x60 [ +0.003319] ? exc_general_protection+0x17c/0x400 [ +0.004707] ? asm_exc_general_protection+0x26/0x30 [ +0.004879] ? __ice_update_sample+0x39/0xe0 [ice] [ +0.004835] ice_napi_poll+0x665/0x680 [ice] [ +0.004320] __napi_poll+0x28/0x190 [ +0.003500] net_rx_action+0x198/0x360 [ +0.003752] ? update_rq_clock+0x39/0x220 [ +0.004013] handle_softirqs+0xf1/0x340 [ +0.003840] ? sched_clock_cpu+0xf/0x1f0 [ +0.003925] __irq_exit_rcu+0xc2/0xe0 [ +0.003665] common_interrupt+0x85/0xa0 [ +0.003839] </IRQ> [ +0.002098] <TASK> [ +0.002106] asm_common_interrupt+0x26/0x40 [ +0.004184] RIP: 0010:cpuidle_enter_state+0xd3/0x690 Fix this by performing the missing unmapping of XDP queues from q_vectors and setting the XDP rings pointer back to NULL after all those queues are released. Also, add an immediate exit from the XDP callback in case of ring preparation failure.
CVE-2025-38129: In the Linux kernel, the following vulnerability has been resolved: page_pool: Fix use-after-free in page_pool_recycle_in_ring syzbot reported a uaf in page_pool_recycle_in_ring: BUG: KASAN: slab-use-after-free in lock_release+0x151/0xa30 kernel/locking/lockdep.c:5862 Read of size 8 at addr ffff8880286045a0 by task syz.0.284/6943 CPU: 0 UID: 0 PID: 6943 Comm: syz.0.284 Not tainted 6.13.0-rc3-syzkaller-gdfa94ce54f41 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x169/0x550 mm/kasan/report.c:489 kasan_report+0x143/0x180 mm/kasan/report.c:602 lock_release+0x151/0xa30 kernel/locking/lockdep.c:5862 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:165 [inline] _raw_spin_unlock_bh+0x1b/0x40 kernel/locking/spinlock.c:210 spin_unlock_bh include/linux/spinlock.h:396 [inline] ptr_ring_produce_bh include/linux/ptr_ring.h:164 [inline] page_pool_recycle_in_ring net/core/page_pool.c:707 [inline] page_pool_put_unrefed_netmem+0x748/0xb00 net/core/page_pool.c:826 page_pool_put_netmem include/net/page_pool/helpers.h:323 [inline] page_pool_put_full_netmem include/net/page_pool/helpers.h:353 [inline] napi_pp_put_page+0x149/0x2b0 net/core/skbuff.c:1036 skb_pp_recycle net/core/skbuff.c:1047 [inline] skb_free_head net/core/skbuff.c:1094 [inline] skb_release_data+0x6c4/0x8a0 net/core/skbuff.c:1125 skb_release_all net/core/skbuff.c:1190 [inline] __kfree_skb net/core/skbuff.c:1204 [inline] sk_skb_reason_drop+0x1c9/0x380 net/core/skbuff.c:1242 kfree_skb_reason include/linux/skbuff.h:1263 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3343 [inline] root cause is: page_pool_recycle_in_ring ptr_ring_produce spin_lock(&r->producer_lock); WRITE_ONCE(r->queue[r->producer++], ptr) //recycle last page to pool page_pool_release page_pool_scrub page_pool_empty_ring ptr_ring_consume page_pool_return_page //release all page __page_pool_destroy free_percpu(pool->recycle_stats); free(pool) //free spin_unlock(&r->producer_lock); //pool->ring uaf read recycle_stat_inc(pool, ring); page_pool can be free while page pool recycle the last page in ring. Add producer-lock barrier to page_pool_release to prevent the page pool from being free before all pages have been recycled. recycle_stat_inc() is empty when CONFIG_PAGE_POOL_STATS is not enabled, which will trigger Wempty-body build warning. Add definition for pool stat macro to fix warning.
CVE-2025-38148: In the Linux kernel, the following vulnerability has been resolved: net: phy: mscc: Fix memory leak when using one step timestamping Fix memory leak when running one-step timestamping. When running one-step sync timestamping, the HW is configured to insert the TX time into the frame, so there is no reason to keep the skb anymore. As in this case the HW will never generate an interrupt to say that the frame was timestamped, then the frame will never released. Fix this by freeing the frame in case of one-step timestamping.
CVE-2025-38159: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix the 'para' buffer size to avoid reading out of bounds Set the size to 6 instead of 2, since 'para' array is passed to 'rtw_fw_bt_wifi_control(rtwdev, para[0], &para[1])', which reads 5 bytes: void rtw_fw_bt_wifi_control(struct rtw_dev *rtwdev, u8 op_code, u8 *data) { ... SET_BT_WIFI_CONTROL_DATA1(h2c_pkt, *data); SET_BT_WIFI_CONTROL_DATA2(h2c_pkt, *(data + 1)); ... SET_BT_WIFI_CONTROL_DATA5(h2c_pkt, *(data + 4)); Detected using the static analysis tool - Svace.
CVE-2025-38162: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: prevent overflow in lookup table allocation When calculating the lookup table size, ensure the following multiplication does not overflow: - desc->field_len[] maximum value is U8_MAX multiplied by NFT_PIPAPO_GROUPS_PER_BYTE(f) that can be 2, worst case. - NFT_PIPAPO_BUCKETS(f->bb) is 2^8, worst case. - sizeof(unsigned long), from sizeof(*f->lt), lt in struct nft_pipapo_field. Then, use check_mul_overflow() to multiply by bucket size and then use check_add_overflow() to the alignment for avx2 (if needed). Finally, add lt_size_check_overflow() helper and use it to consolidate this. While at it, replace leftover allocation using the GFP_KERNEL to GFP_KERNEL_ACCOUNT for consistency, in pipapo_resize().
CVE-2025-38166: In the Linux kernel, the following vulnerability has been resolved: bpf: fix ktls panic with sockmap [ 2172.936997] ------------[ cut here ]------------ [ 2172.936999] kernel BUG at lib/iov_iter.c:629! ...... [ 2172.944996] PKRU: 55555554 [ 2172.945155] Call Trace: [ 2172.945299] <TASK> [ 2172.945428] ? die+0x36/0x90 [ 2172.945601] ? do_trap+0xdd/0x100 [ 2172.945795] ? iov_iter_revert+0x178/0x180 [ 2172.946031] ? iov_iter_revert+0x178/0x180 [ 2172.946267] ? do_error_trap+0x7d/0x110 [ 2172.946499] ? iov_iter_revert+0x178/0x180 [ 2172.946736] ? exc_invalid_op+0x50/0x70 [ 2172.946961] ? iov_iter_revert+0x178/0x180 [ 2172.947197] ? asm_exc_invalid_op+0x1a/0x20 [ 2172.947446] ? iov_iter_revert+0x178/0x180 [ 2172.947683] ? iov_iter_revert+0x5c/0x180 [ 2172.947913] tls_sw_sendmsg_locked.isra.0+0x794/0x840 [ 2172.948206] tls_sw_sendmsg+0x52/0x80 [ 2172.948420] ? inet_sendmsg+0x1f/0x70 [ 2172.948634] __sys_sendto+0x1cd/0x200 [ 2172.948848] ? find_held_lock+0x2b/0x80 [ 2172.949072] ? syscall_trace_enter+0x140/0x270 [ 2172.949330] ? __lock_release.isra.0+0x5e/0x170 [ 2172.949595] ? find_held_lock+0x2b/0x80 [ 2172.949817] ? syscall_trace_enter+0x140/0x270 [ 2172.950211] ? lockdep_hardirqs_on_prepare+0xda/0x190 [ 2172.950632] ? ktime_get_coarse_real_ts64+0xc2/0xd0 [ 2172.951036] __x64_sys_sendto+0x24/0x30 [ 2172.951382] do_syscall_64+0x90/0x170 ...... After calling bpf_exec_tx_verdict(), the size of msg_pl->sg may increase, e.g., when the BPF program executes bpf_msg_push_data(). If the BPF program sets cork_bytes and sg.size is smaller than cork_bytes, it will return -ENOSPC and attempt to roll back to the non-zero copy logic. However, during rollback, msg->msg_iter is reset, but since msg_pl->sg.size has been increased, subsequent executions will exceed the actual size of msg_iter. ''' iov_iter_revert(&msg->msg_iter, msg_pl->sg.size - orig_size); ''' The changes in this commit are based on the following considerations: 1. When cork_bytes is set, rolling back to non-zero copy logic is pointless and can directly go to zero-copy logic. 2. We can not calculate the correct number of bytes to revert msg_iter. Assume the original data is "abcdefgh" (8 bytes), and after 3 pushes by the BPF program, it becomes 11-byte data: "abc?de?fgh?". Then, we set cork_bytes to 6, which means the first 6 bytes have been processed, and the remaining 5 bytes "?fgh?" will be cached until the length meets the cork_bytes requirement. However, some data in "?fgh?" is not within 'sg->msg_iter' (but in msg_pl instead), especially the data "?" we pushed. So it doesn't seem as simple as just reverting through an offset of msg_iter. 3. For non-TLS sockets in tcp_bpf_sendmsg, when a "cork" situation occurs, the user-space send() doesn't return an error, and the returned length is the same as the input length parameter, even if some data is cached. Additionally, I saw that the current non-zero-copy logic for handling corking is written as: ''' line 1177 else if (ret != -EAGAIN) { if (ret == -ENOSPC) ret = 0; goto send_end; ''' So it's ok to just return 'copied' without error when a "cork" situation occurs.
CVE-2025-38192: In the Linux kernel, the following vulnerability has been resolved: net: clear the dst when changing skb protocol A not-so-careful NAT46 BPF program can crash the kernel if it indiscriminately flips ingress packets from v4 to v6: BUG: kernel NULL pointer dereference, address: 0000000000000000 ip6_rcv_core (net/ipv6/ip6_input.c:190:20) ipv6_rcv (net/ipv6/ip6_input.c:306:8) process_backlog (net/core/dev.c:6186:4) napi_poll (net/core/dev.c:6906:9) net_rx_action (net/core/dev.c:7028:13) do_softirq (kernel/softirq.c:462:3) netif_rx (net/core/dev.c:5326:3) dev_loopback_xmit (net/core/dev.c:4015:2) ip_mc_finish_output (net/ipv4/ip_output.c:363:8) NF_HOOK (./include/linux/netfilter.h:314:9) ip_mc_output (net/ipv4/ip_output.c:400:5) dst_output (./include/net/dst.h:459:9) ip_local_out (net/ipv4/ip_output.c:130:9) ip_send_skb (net/ipv4/ip_output.c:1496:8) udp_send_skb (net/ipv4/udp.c:1040:8) udp_sendmsg (net/ipv4/udp.c:1328:10) The output interface has a 4->6 program attached at ingress. We try to loop the multicast skb back to the sending socket. Ingress BPF runs as part of netif_rx(), pushes a valid v6 hdr and changes skb->protocol to v6. We enter ip6_rcv_core which tries to use skb_dst(). But the dst is still an IPv4 one left after IPv4 mcast output. Clear the dst in all BPF helpers which change the protocol. Try to preserve metadata dsts, those may carry non-routing metadata.
CVE-2025-38207: In the Linux kernel, the following vulnerability has been resolved: mm: fix uprobe pte be overwritten when expanding vma Patch series "Fix uprobe pte be overwritten when expanding vma". This patch (of 4): We encountered a BUG alert triggered by Syzkaller as follows: BUG: Bad rss-counter state mm:00000000b4a60fca type:MM_ANONPAGES val:1 And we can reproduce it with the following steps: 1. register uprobe on file at zero offset 2. mmap the file at zero offset: addr1 = mmap(NULL, 2 * 4096, PROT_NONE, MAP_PRIVATE, fd, 0); 3. mremap part of vma1 to new vma2: addr2 = mremap(addr1, 4096, 2 * 4096, MREMAP_MAYMOVE); 4. mremap back to orig addr1: mremap(addr2, 4096, 4096, MREMAP_MAYMOVE | MREMAP_FIXED, addr1); In step 3, the vma1 range [addr1, addr1 + 4096] will be remap to new vma2 with range [addr2, addr2 + 8192], and remap uprobe anon page from the vma1 to vma2, then unmap the vma1 range [addr1, addr1 + 4096]. In step 4, the vma2 range [addr2, addr2 + 4096] will be remap back to the addr range [addr1, addr1 + 4096]. Since the addr range [addr1 + 4096, addr1 + 8192] still maps the file, it will take vma_merge_new_range to expand the range, and then do uprobe_mmap in vma_complete. Since the merged vma pgoff is also zero offset, it will install uprobe anon page to the merged vma. However, the upcomming move_page_tables step, which use set_pte_at to remap the vma2 uprobe pte to the merged vma, will overwrite the newly uprobe pte in the merged vma, and lead that pte to be orphan. Since the uprobe pte will be remapped to the merged vma, we can remove the unnecessary uprobe_mmap upon merged vma. This problem was first found in linux-6.6.y and also exists in the community syzkaller: https://lore.kernel.org/all/000000000000ada39605a5e71711@google.com/T/
CVE-2025-38215: In the Linux kernel, the following vulnerability has been resolved: fbdev: Fix do_register_framebuffer to prevent null-ptr-deref in fb_videomode_to_var If fb_add_videomode() in do_register_framebuffer() fails to allocate memory for fb_videomode, it will later lead to a null-ptr dereference in fb_videomode_to_var(), as the fb_info is registered while not having the mode in modelist that is expected to be there, i.e. the one that is described in fb_info->var. ================================================================ general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 PID: 30371 Comm: syz-executor.1 Not tainted 5.10.226-syzkaller #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 RIP: 0010:fb_videomode_to_var+0x24/0x610 drivers/video/fbdev/core/modedb.c:901 Call Trace: display_to_var+0x3a/0x7c0 drivers/video/fbdev/core/fbcon.c:929 fbcon_resize+0x3e2/0x8f0 drivers/video/fbdev/core/fbcon.c:2071 resize_screen drivers/tty/vt/vt.c:1176 [inline] vc_do_resize+0x53a/0x1170 drivers/tty/vt/vt.c:1263 fbcon_modechanged+0x3ac/0x6e0 drivers/video/fbdev/core/fbcon.c:2720 fbcon_update_vcs+0x43/0x60 drivers/video/fbdev/core/fbcon.c:2776 do_fb_ioctl+0x6d2/0x740 drivers/video/fbdev/core/fbmem.c:1128 fb_ioctl+0xe7/0x150 drivers/video/fbdev/core/fbmem.c:1203 vfs_ioctl fs/ioctl.c:48 [inline] __do_sys_ioctl fs/ioctl.c:753 [inline] __se_sys_ioctl fs/ioctl.c:739 [inline] __x64_sys_ioctl+0x19a/0x210 fs/ioctl.c:739 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x67/0xd1 ================================================================ Even though fbcon_init() checks beforehand if fb_match_mode() in var_to_display() fails, it can not prevent the panic because fbcon_init() does not return error code. Considering this and the comment in the code about fb_match_mode() returning NULL - "This should not happen" - it is better to prevent registering the fb_info if its mode was not set successfully. Also move fb_add_videomode() closer to the beginning of do_register_framebuffer() to avoid having to do the cleanup on fail. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2025-38232: In the Linux kernel, the following vulnerability has been resolved: NFSD: fix race between nfsd registration and exports_proc As of now nfsd calls create_proc_exports_entry() at start of init_nfsd and cleanup by remove_proc_entry() at last of exit_nfsd. Which causes kernel OOPs if there is race between below 2 operations: (i) exportfs -r (ii) mount -t nfsd none /proc/fs/nfsd for 5.4 kernel ARM64: CPU 1: el1_irq+0xbc/0x180 arch_counter_get_cntvct+0x14/0x18 running_clock+0xc/0x18 preempt_count_add+0x88/0x110 prep_new_page+0xb0/0x220 get_page_from_freelist+0x2d8/0x1778 __alloc_pages_nodemask+0x15c/0xef0 __vmalloc_node_range+0x28c/0x478 __vmalloc_node_flags_caller+0x8c/0xb0 kvmalloc_node+0x88/0xe0 nfsd_init_net+0x6c/0x108 [nfsd] ops_init+0x44/0x170 register_pernet_operations+0x114/0x270 register_pernet_subsys+0x34/0x50 init_nfsd+0xa8/0x718 [nfsd] do_one_initcall+0x54/0x2e0 CPU 2 : Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 PC is at : exports_net_open+0x50/0x68 [nfsd] Call trace: exports_net_open+0x50/0x68 [nfsd] exports_proc_open+0x2c/0x38 [nfsd] proc_reg_open+0xb8/0x198 do_dentry_open+0x1c4/0x418 vfs_open+0x38/0x48 path_openat+0x28c/0xf18 do_filp_open+0x70/0xe8 do_sys_open+0x154/0x248 Sometimes it crashes at exports_net_open() and sometimes cache_seq_next_rcu(). and same is happening on latest 6.14 kernel as well: [ 0.000000] Linux version 6.14.0-rc5-next-20250304-dirty ... [ 285.455918] Unable to handle kernel paging request at virtual address 00001f4800001f48 ... [ 285.464902] pc : cache_seq_next_rcu+0x78/0xa4 ... [ 285.469695] Call trace: [ 285.470083] cache_seq_next_rcu+0x78/0xa4 (P) [ 285.470488] seq_read+0xe0/0x11c [ 285.470675] proc_reg_read+0x9c/0xf0 [ 285.470874] vfs_read+0xc4/0x2fc [ 285.471057] ksys_read+0x6c/0xf4 [ 285.471231] __arm64_sys_read+0x1c/0x28 [ 285.471428] invoke_syscall+0x44/0x100 [ 285.471633] el0_svc_common.constprop.0+0x40/0xe0 [ 285.471870] do_el0_svc_compat+0x1c/0x34 [ 285.472073] el0_svc_compat+0x2c/0x80 [ 285.472265] el0t_32_sync_handler+0x90/0x140 [ 285.472473] el0t_32_sync+0x19c/0x1a0 [ 285.472887] Code: f9400885 93407c23 937d7c27 11000421 (f86378a3) [ 285.473422] ---[ end trace 0000000000000000 ]--- It reproduced simply with below script: while [ 1 ] do /exportfs -r done & while [ 1 ] do insmod /nfsd.ko mount -t nfsd none /proc/fs/nfsd umount /proc/fs/nfsd rmmod nfsd done & So exporting interfaces to user space shall be done at last and cleanup at first place. With change there is no Kernel OOPs.
CVE-2025-38234: In the Linux kernel, the following vulnerability has been resolved: sched/rt: Fix race in push_rt_task Overview ======== When a CPU chooses to call push_rt_task and picks a task to push to another CPU's runqueue then it will call find_lock_lowest_rq method which would take a double lock on both CPUs' runqueues. If one of the locks aren't readily available, it may lead to dropping the current runqueue lock and reacquiring both the locks at once. During this window it is possible that the task is already migrated and is running on some other CPU. These cases are already handled. However, if the task is migrated and has already been executed and another CPU is now trying to wake it up (ttwu) such that it is queued again on the runqeue (on_rq is 1) and also if the task was run by the same CPU, then the current checks will pass even though the task was migrated out and is no longer in the pushable tasks list. Crashes ======= This bug resulted in quite a few flavors of crashes triggering kernel panics with various crash signatures such as assert failures, page faults, null pointer dereferences, and queue corruption errors all coming from scheduler itself. Some of the crashes: -> kernel BUG at kernel/sched/rt.c:1616! BUG_ON(idx >= MAX_RT_PRIO) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? pick_next_task_rt+0x6e/0x1d0 ? do_error_trap+0x64/0xa0 ? pick_next_task_rt+0x6e/0x1d0 ? exc_invalid_op+0x4c/0x60 ? pick_next_task_rt+0x6e/0x1d0 ? asm_exc_invalid_op+0x12/0x20 ? pick_next_task_rt+0x6e/0x1d0 __schedule+0x5cb/0x790 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: kernel NULL pointer dereference, address: 00000000000000c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? __warn+0x8a/0xe0 ? exc_page_fault+0x3d6/0x520 ? asm_exc_page_fault+0x1e/0x30 ? pick_next_task_rt+0xb5/0x1d0 ? pick_next_task_rt+0x8c/0x1d0 __schedule+0x583/0x7e0 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: unable to handle page fault for address: ffff9464daea5900 kernel BUG at kernel/sched/rt.c:1861! BUG_ON(rq->cpu != task_cpu(p)) -> kernel BUG at kernel/sched/rt.c:1055! BUG_ON(!rq->nr_running) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? dequeue_top_rt_rq+0xa2/0xb0 ? do_error_trap+0x64/0xa0 ? dequeue_top_rt_rq+0xa2/0xb0 ? exc_invalid_op+0x4c/0x60 ? dequeue_top_rt_rq+0xa2/0xb0 ? asm_exc_invalid_op+0x12/0x20 ? dequeue_top_rt_rq+0xa2/0xb0 dequeue_rt_entity+0x1f/0x70 dequeue_task_rt+0x2d/0x70 __schedule+0x1a8/0x7e0 ? blk_finish_plug+0x25/0x40 schedule+0x3c/0xb0 futex_wait_queue_me+0xb6/0x120 futex_wait+0xd9/0x240 do_futex+0x344/0xa90 ? get_mm_exe_file+0x30/0x60 ? audit_exe_compare+0x58/0x70 ? audit_filter_rules.constprop.26+0x65e/0x1220 __x64_sys_futex+0x148/0x1f0 do_syscall_64+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x62/0xc7 -> BUG: unable to handle page fault for address: ffff8cf3608bc2c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? spurious_kernel_fault+0x171/0x1c0 ? exc_page_fault+0x3b6/0x520 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? asm_exc_page_fault+0x1e/0x30 ? _cond_resched+0x15/0x30 ? futex_wait_queue_me+0xc8/0x120 ? futex_wait+0xd9/0x240 ? try_to_wake_up+0x1b8/0x490 ? futex_wake+0x78/0x160 ? do_futex+0xcd/0xa90 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? plist_del+0x6a/0xd0 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? dequeue_pushable_task+0x20/0x70 ? __schedule+0x382/0x7e0 ? asm_sysvec_reschedule_i ---truncated---
CVE-2025-38250: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: Fix use-after-free in vhci_flush() syzbot reported use-after-free in vhci_flush() without repro. [0] From the splat, a thread close()d a vhci file descriptor while its device was being used by iotcl() on another thread. Once the last fd refcnt is released, vhci_release() calls hci_unregister_dev(), hci_free_dev(), and kfree() for struct vhci_data, which is set to hci_dev->dev->driver_data. The problem is that there is no synchronisation after unlinking hdev from hci_dev_list in hci_unregister_dev(). There might be another thread still accessing the hdev which was fetched before the unlink operation. We can use SRCU for such synchronisation. Let's run hci_dev_reset() under SRCU and wait for its completion in hci_unregister_dev(). Another option would be to restore hci_dev->destruct(), which was removed in commit 587ae086f6e4 ("Bluetooth: Remove unused hci-destruct cb"). However, this would not be a good solution, as we should not run hci_unregister_dev() while there are in-flight ioctl() requests, which could lead to another data-race KCSAN splat. Note that other drivers seem to have the same problem, for exmaple, virtbt_remove(). [0]: BUG: KASAN: slab-use-after-free in skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline] BUG: KASAN: slab-use-after-free in skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937 Read of size 8 at addr ffff88807cb8d858 by task syz.1.219/6718 CPU: 1 UID: 0 PID: 6718 Comm: syz.1.219 Not tainted 6.16.0-rc1-syzkaller-00196-g08207f42d3ff #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:408 [inline] print_report+0xd2/0x2b0 mm/kasan/report.c:521 kasan_report+0x118/0x150 mm/kasan/report.c:634 skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline] skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937 skb_queue_purge include/linux/skbuff.h:3368 [inline] vhci_flush+0x44/0x50 drivers/bluetooth/hci_vhci.c:69 hci_dev_do_reset net/bluetooth/hci_core.c:552 [inline] hci_dev_reset+0x420/0x5c0 net/bluetooth/hci_core.c:592 sock_do_ioctl+0xd9/0x300 net/socket.c:1190 sock_ioctl+0x576/0x790 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fcf5b98e929 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fcf5c7b9038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fcf5bbb6160 RCX: 00007fcf5b98e929 RDX: 0000000000000000 RSI: 00000000400448cb RDI: 0000000000000009 RBP: 00007fcf5ba10b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007fcf5bbb6160 R15: 00007ffd6353d528 </TASK> Allocated by task 6535: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __kmalloc_cache_noprof+0x230/0x3d0 mm/slub.c:4359 kmalloc_noprof include/linux/slab.h:905 [inline] kzalloc_noprof include/linux/slab.h:1039 [inline] vhci_open+0x57/0x360 drivers/bluetooth/hci_vhci.c:635 misc_open+0x2bc/0x330 drivers/char/misc.c:161 chrdev_open+0x4c9/0x5e0 fs/char_dev.c:414 do_dentry_open+0xdf0/0x1970 fs/open.c:964 vfs_open+0x3b/0x340 fs/open.c:1094 do_open fs/namei.c:3887 [inline] path_openat+0x2ee5/0x3830 fs/name ---truncated---
CVE-2025-38257: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Prevent overflow in size calculation for memdup_user() Number of apqn target list entries contained in 'nr_apqns' variable is determined by userspace via an ioctl call so the result of the product in calculation of size passed to memdup_user() may overflow. In this case the actual size of the allocated area and the value describing it won't be in sync leading to various types of unpredictable behaviour later. Use a proper memdup_array_user() helper which returns an error if an overflow is detected. Note that it is different from when nr_apqns is initially zero - that case is considered valid and should be handled in subsequent pkey_handler implementations. Found by Linux Verification Center (linuxtesting.org).
CVE-2025-38259: In the Linux kernel, the following vulnerability has been resolved: ASoC: codecs: wcd9335: Fix missing free of regulator supplies Driver gets and enables all regulator supplies in probe path (wcd9335_parse_dt() and wcd9335_power_on_reset()), but does not cleanup in final error paths and in unbind (missing remove() callback). This leads to leaked memory and unbalanced regulator enable count during probe errors or unbind. Fix this by converting entire code into devm_regulator_bulk_get_enable() which also greatly simplifies the code.
CVE-2025-38261: In the Linux kernel, the following vulnerability has been resolved: riscv: save the SR_SUM status over switches When threads/tasks are switched we need to ensure the old execution's SR_SUM state is saved and the new thread has the old SR_SUM state restored. The issue was seen under heavy load especially with the syz-stress tool running, with crashes as follows in schedule_tail: Unable to handle kernel access to user memory without uaccess routines at virtual address 000000002749f0d0 Oops [#1] Modules linked in: CPU: 1 PID: 4875 Comm: syz-executor.0 Not tainted 5.12.0-rc2-syzkaller-00467-g0d7588ab9ef9 #0 Hardware name: riscv-virtio,qemu (DT) epc : schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 ra : task_pid_vnr include/linux/sched.h:1421 [inline] ra : schedule_tail+0x70/0xb2 kernel/sched/core.c:4264 epc : ffffffe00008c8b0 ra : ffffffe00008c8ae sp : ffffffe025d17ec0 gp : ffffffe005d25378 tp : ffffffe00f0d0000 t0 : 0000000000000000 t1 : 0000000000000001 t2 : 00000000000f4240 s0 : ffffffe025d17ee0 s1 : 000000002749f0d0 a0 : 000000000000002a a1 : 0000000000000003 a2 : 1ffffffc0cfac500 a3 : ffffffe0000c80cc a4 : 5ae9db91c19bbe00 a5 : 0000000000000000 a6 : 0000000000f00000 a7 : ffffffe000082eba s2 : 0000000000040000 s3 : ffffffe00eef96c0 s4 : ffffffe022c77fe0 s5 : 0000000000004000 s6 : ffffffe067d74e00 s7 : ffffffe067d74850 s8 : ffffffe067d73e18 s9 : ffffffe067d74e00 s10: ffffffe00eef96e8 s11: 000000ae6cdf8368 t3 : 5ae9db91c19bbe00 t4 : ffffffc4043cafb2 t5 : ffffffc4043cafba t6 : 0000000000040000 status: 0000000000000120 badaddr: 000000002749f0d0 cause: 000000000000000f Call Trace: [<ffffffe00008c8b0>] schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 [<ffffffe000005570>] ret_from_exception+0x0/0x14 Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace b5f8f9231dc87dda ]--- The issue comes from the put_user() in schedule_tail (kernel/sched/core.c) doing the following: asmlinkage __visible void schedule_tail(struct task_struct *prev) { ... if (current->set_child_tid) put_user(task_pid_vnr(current), current->set_child_tid); ... } the put_user() macro causes the code sequence to come out as follows: 1: __enable_user_access() 2: reg = task_pid_vnr(current); 3: *current->set_child_tid = reg; 4: __disable_user_access() The problem is that we may have a sleeping function as argument which could clear SR_SUM causing the panic above. This was fixed by evaluating the argument of the put_user() macro outside the user-enabled section in commit 285a76bb2cf5 ("riscv: evaluate put_user() arg before enabling user access")" In order for riscv to take advantage of unsafe_get/put_XXX() macros and to avoid the same issue we had with put_user() and sleeping functions we must ensure code flow can go through switch_to() from within a region of code with SR_SUM enabled and come back with SR_SUM still enabled. This patch addresses the problem allowing future work to enable full use of unsafe_get/put_XXX() macros without needing to take a CSR bit flip cost on every access. Make switch_to() save and restore SR_SUM.
CVE-2025-38262: In the Linux kernel, the following vulnerability has been resolved: tty: serial: uartlite: register uart driver in init When two instances of uart devices are probing, a concurrency race can occur. If one thread calls uart_register_driver function, which first allocates and assigns memory to 'uart_state' member of uart_driver structure, the other instance can bypass uart driver registration and call ulite_assign. This calls uart_add_one_port, which expects the uart driver to be fully initialized. This leads to a kernel panic due to a null pointer dereference: [ 8.143581] BUG: kernel NULL pointer dereference, address: 00000000000002b8 [ 8.156982] #PF: supervisor write access in kernel mode [ 8.156984] #PF: error_code(0x0002) - not-present page [ 8.156986] PGD 0 P4D 0 ... [ 8.180668] RIP: 0010:mutex_lock+0x19/0x30 [ 8.188624] Call Trace: [ 8.188629] ? __die_body.cold+0x1a/0x1f [ 8.195260] ? page_fault_oops+0x15c/0x290 [ 8.209183] ? __irq_resolve_mapping+0x47/0x80 [ 8.209187] ? exc_page_fault+0x64/0x140 [ 8.209190] ? asm_exc_page_fault+0x22/0x30 [ 8.209196] ? mutex_lock+0x19/0x30 [ 8.223116] uart_add_one_port+0x60/0x440 [ 8.223122] ? proc_tty_register_driver+0x43/0x50 [ 8.223126] ? tty_register_driver+0x1ca/0x1e0 [ 8.246250] ulite_probe+0x357/0x4b0 [uartlite] To prevent it, move uart driver registration in to init function. This will ensure that uart_driver is always registered when probe function is called.
CVE-2025-38264: In the Linux kernel, the following vulnerability has been resolved: nvme-tcp: sanitize request list handling Validate the request in nvme_tcp_handle_r2t() to ensure it's not part of any list, otherwise a malicious R2T PDU might inject a loop in request list processing.
CVE-2025-38272: In the Linux kernel, the following vulnerability has been resolved: net: dsa: b53: do not enable EEE on bcm63xx BCM63xx internal switches do not support EEE, but provide multiple RGMII ports where external PHYs may be connected. If one of these PHYs are EEE capable, we may try to enable EEE for the MACs, which then hangs the system on access of the (non-existent) EEE registers. Fix this by checking if the switch actually supports EEE before attempting to configure it.
CVE-2025-38280: In the Linux kernel, the following vulnerability has been resolved: bpf: Avoid __bpf_prog_ret0_warn when jit fails syzkaller reported an issue: WARNING: CPU: 3 PID: 217 at kernel/bpf/core.c:2357 __bpf_prog_ret0_warn+0xa/0x20 kernel/bpf/core.c:2357 Modules linked in: CPU: 3 UID: 0 PID: 217 Comm: kworker/u32:6 Not tainted 6.15.0-rc4-syzkaller-00040-g8bac8898fe39 RIP: 0010:__bpf_prog_ret0_warn+0xa/0x20 kernel/bpf/core.c:2357 Call Trace: <TASK> bpf_dispatcher_nop_func include/linux/bpf.h:1316 [inline] __bpf_prog_run include/linux/filter.h:718 [inline] bpf_prog_run include/linux/filter.h:725 [inline] cls_bpf_classify+0x74a/0x1110 net/sched/cls_bpf.c:105 ... When creating bpf program, 'fp->jit_requested' depends on bpf_jit_enable. This issue is triggered because of CONFIG_BPF_JIT_ALWAYS_ON is not set and bpf_jit_enable is set to 1, causing the arch to attempt JIT the prog, but jit failed due to FAULT_INJECTION. As a result, incorrectly treats the program as valid, when the program runs it calls `__bpf_prog_ret0_warn` and triggers the WARN_ON_ONCE(1).
CVE-2025-38300: In the Linux kernel, the following vulnerability has been resolved: crypto: sun8i-ce-cipher - fix error handling in sun8i_ce_cipher_prepare() Fix two DMA cleanup issues on the error path in sun8i_ce_cipher_prepare(): 1] If dma_map_sg() fails for areq->dst, the device driver would try to free DMA memory it has not allocated in the first place. To fix this, on the "theend_sgs" error path, call dma unmap only if the corresponding dma map was successful. 2] If the dma_map_single() call for the IV fails, the device driver would try to free an invalid DMA memory address on the "theend_iv" path: ------------[ cut here ]------------ DMA-API: sun8i-ce 1904000.crypto: device driver tries to free an invalid DMA memory address WARNING: CPU: 2 PID: 69 at kernel/dma/debug.c:968 check_unmap+0x123c/0x1b90 Modules linked in: skcipher_example(O+) CPU: 2 UID: 0 PID: 69 Comm: 1904000.crypto- Tainted: G O 6.15.0-rc3+ #24 PREEMPT Tainted: [O]=OOT_MODULE Hardware name: OrangePi Zero2 (DT) pc : check_unmap+0x123c/0x1b90 lr : check_unmap+0x123c/0x1b90 ... Call trace: check_unmap+0x123c/0x1b90 (P) debug_dma_unmap_page+0xac/0xc0 dma_unmap_page_attrs+0x1f4/0x5fc sun8i_ce_cipher_do_one+0x1bd4/0x1f40 crypto_pump_work+0x334/0x6e0 kthread_worker_fn+0x21c/0x438 kthread+0x374/0x664 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- To fix this, check for !dma_mapping_error() before calling dma_unmap_single() on the "theend_iv" path.
CVE-2025-38310: In the Linux kernel, the following vulnerability has been resolved: seg6: Fix validation of nexthop addresses The kernel currently validates that the length of the provided nexthop address does not exceed the specified length. This can lead to the kernel reading uninitialized memory if user space provided a shorter length than the specified one. Fix by validating that the provided length exactly matches the specified one.
CVE-2025-38319: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pp: Fix potential NULL pointer dereference in atomctrl_initialize_mc_reg_table The function atomctrl_initialize_mc_reg_table() and atomctrl_initialize_mc_reg_table_v2_2() does not check the return value of smu_atom_get_data_table(). If smu_atom_get_data_table() fails to retrieve vram_info, it returns NULL which is later dereferenced.
CVE-2025-38331: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: cortina: Use TOE/TSO on all TCP It is desireable to push the hardware accelerator to also process non-segmented TCP frames: we pass the skb->len to the "TOE/TSO" offloader and it will handle them. Without this quirk the driver becomes unstable and lock up and and crash. I do not know exactly why, but it is probably due to the TOE (TCP offload engine) feature that is coupled with the segmentation feature - it is not possible to turn one part off and not the other, either both TOE and TSO are active, or neither of them. Not having the TOE part active seems detrimental, as if that hardware feature is not really supposed to be turned off. The datasheet says: "Based on packet parsing and TCP connection/NAT table lookup results, the NetEngine puts the packets belonging to the same TCP connection to the same queue for the software to process. The NetEngine puts incoming packets to the buffer or series of buffers for a jumbo packet. With this hardware acceleration, IP/TCP header parsing, checksum validation and connection lookup are offloaded from the software processing." After numerous tests with the hardware locking up after something between minutes and hours depending on load using iperf3 I have concluded this is necessary to stabilize the hardware.
CVE-2025-38333: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to bail out in get_new_segment() ------------[ cut here ]------------ WARNING: CPU: 3 PID: 579 at fs/f2fs/segment.c:2832 new_curseg+0x5e8/0x6dc pc : new_curseg+0x5e8/0x6dc Call trace: new_curseg+0x5e8/0x6dc f2fs_allocate_data_block+0xa54/0xe28 do_write_page+0x6c/0x194 f2fs_do_write_node_page+0x38/0x78 __write_node_page+0x248/0x6d4 f2fs_sync_node_pages+0x524/0x72c f2fs_write_checkpoint+0x4bc/0x9b0 __checkpoint_and_complete_reqs+0x80/0x244 issue_checkpoint_thread+0x8c/0xec kthread+0x114/0x1bc ret_from_fork+0x10/0x20 get_new_segment() detects inconsistent status in between free_segmap and free_secmap, let's record such error into super block, and bail out get_new_segment() instead of continue using the segment.
CVE-2025-38359: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Fix in_atomic() handling in do_secure_storage_access() Kernel user spaces accesses to not exported pages in atomic context incorrectly try to resolve the page fault. With debug options enabled call traces like this can be seen: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1523 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 419074, name: qemu-system-s39 preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 INFO: lockdep is turned off. Preemption disabled at: [<00000383ea47cfa2>] copy_page_from_iter_atomic+0xa2/0x8a0 CPU: 12 UID: 0 PID: 419074 Comm: qemu-system-s39 Tainted: G W 6.16.0-20250531.rc0.git0.69b3a602feac.63.fc42.s390x+debug #1 PREEMPT Tainted: [W]=WARN Hardware name: IBM 3931 A01 703 (LPAR) Call Trace: [<00000383e990d282>] dump_stack_lvl+0xa2/0xe8 [<00000383e99bf152>] __might_resched+0x292/0x2d0 [<00000383eaa7c374>] down_read+0x34/0x2d0 [<00000383e99432f8>] do_secure_storage_access+0x108/0x360 [<00000383eaa724b0>] __do_pgm_check+0x130/0x220 [<00000383eaa842e4>] pgm_check_handler+0x114/0x160 [<00000383ea47d028>] copy_page_from_iter_atomic+0x128/0x8a0 ([<00000383ea47d016>] copy_page_from_iter_atomic+0x116/0x8a0) [<00000383e9c45eae>] generic_perform_write+0x16e/0x310 [<00000383e9eb87f4>] ext4_buffered_write_iter+0x84/0x160 [<00000383e9da0de4>] vfs_write+0x1c4/0x460 [<00000383e9da123c>] ksys_write+0x7c/0x100 [<00000383eaa7284e>] __do_syscall+0x15e/0x280 [<00000383eaa8417e>] system_call+0x6e/0x90 INFO: lockdep is turned off. It is not allowed to take the mmap_lock while in atomic context. Therefore handle such a secure storage access fault as if the accessed page is not mapped: the uaccess function will return -EFAULT, and the caller has to deal with this. Usually this means that the access is retried in process context, which allows to resolve the page fault (or in this case export the page).
CVE-2025-38361: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check dce_hwseq before dereferencing it [WHAT] hws was checked for null earlier in dce110_blank_stream, indicating hws can be null, and should be checked whenever it is used. (cherry picked from commit 79db43611ff61280b6de58ce1305e0b2ecf675ad)
CVE-2025-38362: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null pointer check for get_first_active_display() The function mod_hdcp_hdcp1_enable_encryption() calls the function get_first_active_display(), but does not check its return value. The return value is a null pointer if the display list is empty. This will lead to a null pointer dereference in mod_hdcp_hdcp2_enable_encryption(). Add a null pointer check for get_first_active_display() and return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND if the function return null.
CVE-2025-38369: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Check availability of workqueue allocated by idxd wq driver before using Running IDXD workloads in a container with the /dev directory mounted can trigger a call trace or even a kernel panic when the parent process of the container is terminated. This issue occurs because, under certain configurations, Docker does not properly propagate the mount replica back to the original mount point. In this case, when the user driver detaches, the WQ is destroyed but it still calls destroy_workqueue() attempting to completes all pending work. It's necessary to check wq->wq and skip the drain if it no longer exists.
CVE-2025-38408: In the Linux kernel, the following vulnerability has been resolved: genirq/irq_sim: Initialize work context pointers properly Initialize `ops` member's pointers properly by using kzalloc() instead of kmalloc() when allocating the simulation work context. Otherwise the pointers contain random content leading to invalid dereferencing.
CVE-2025-38409: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix another leak in the submit error path put_unused_fd() doesn't free the installed file, if we've already done fd_install(). So we need to also free the sync_file. Patchwork: https://patchwork.freedesktop.org/patch/653583/
CVE-2025-38410: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix a fence leak in submit error path In error paths, we could unref the submit without calling drm_sched_entity_push_job(), so msm_job_free() will never get called. Since drm_sched_job_cleanup() will NULL out the s_fence, we can use that to detect this case. Patchwork: https://patchwork.freedesktop.org/patch/653584/
CVE-2025-38422: In the Linux kernel, the following vulnerability has been resolved: net: lan743x: Modify the EEPROM and OTP size for PCI1xxxx devices Maximum OTP and EEPROM size for hearthstone PCI1xxxx devices are 8 Kb and 64 Kb respectively. Adjust max size definitions and return correct EEPROM length based on device. Also prevent out-of-bound read/write.
CVE-2025-38426: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add basic validation for RAS header If RAS header read from EEPROM is corrupted, it could result in trying to allocate huge memory for reading the records. Add some validation to header fields.
CVE-2025-38436: In the Linux kernel, the following vulnerability has been resolved: drm/scheduler: signal scheduled fence when kill job When an entity from application B is killed, drm_sched_entity_kill() removes all jobs belonging to that entity through drm_sched_entity_kill_jobs_work(). If application A's job depends on a scheduled fence from application B's job, and that fence is not properly signaled during the killing process, application A's dependency cannot be cleared. This leads to application A hanging indefinitely while waiting for a dependency that will never be resolved. Fix this issue by ensuring that scheduled fences are properly signaled when an entity is killed, allowing dependent applications to continue execution.
CVE-2025-38438: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda: Use devm_kstrdup() to avoid memleak. sof_pdata->tplg_filename can have address allocated by kstrdup() and can be overwritten. Memory leak was detected with kmemleak: unreferenced object 0xffff88812391ff60 (size 16): comm "kworker/4:1", pid 161, jiffies 4294802931 hex dump (first 16 bytes): 73 6f 66 2d 68 64 61 2d 67 65 6e 65 72 69 63 00 sof-hda-generic. backtrace (crc 4bf1675c): __kmalloc_node_track_caller_noprof+0x49c/0x6b0 kstrdup+0x46/0xc0 hda_machine_select.cold+0x1de/0x12cf [snd_sof_intel_hda_generic] sof_init_environment+0x16f/0xb50 [snd_sof] sof_probe_continue+0x45/0x7c0 [snd_sof] sof_probe_work+0x1e/0x40 [snd_sof] process_one_work+0x894/0x14b0 worker_thread+0x5e5/0xfb0 kthread+0x39d/0x760 ret_from_fork+0x31/0x70 ret_from_fork_asm+0x1a/0x30
CVE-2025-38449: In the Linux kernel, the following vulnerability has been resolved: drm/gem: Acquire references on GEM handles for framebuffers A GEM handle can be released while the GEM buffer object is attached to a DRM framebuffer. This leads to the release of the dma-buf backing the buffer object, if any. [1] Trying to use the framebuffer in further mode-setting operations leads to a segmentation fault. Most easily happens with driver that use shadow planes for vmap-ing the dma-buf during a page flip. An example is shown below. [ 156.791968] ------------[ cut here ]------------ [ 156.796830] WARNING: CPU: 2 PID: 2255 at drivers/dma-buf/dma-buf.c:1527 dma_buf_vmap+0x224/0x430 [...] [ 156.942028] RIP: 0010:dma_buf_vmap+0x224/0x430 [ 157.043420] Call Trace: [ 157.045898] <TASK> [ 157.048030] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.052436] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.056836] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.061253] ? drm_gem_shmem_vmap+0x74/0x710 [ 157.065567] ? dma_buf_vmap+0x224/0x430 [ 157.069446] ? __warn.cold+0x58/0xe4 [ 157.073061] ? dma_buf_vmap+0x224/0x430 [ 157.077111] ? report_bug+0x1dd/0x390 [ 157.080842] ? handle_bug+0x5e/0xa0 [ 157.084389] ? exc_invalid_op+0x14/0x50 [ 157.088291] ? asm_exc_invalid_op+0x16/0x20 [ 157.092548] ? dma_buf_vmap+0x224/0x430 [ 157.096663] ? dma_resv_get_singleton+0x6d/0x230 [ 157.101341] ? __pfx_dma_buf_vmap+0x10/0x10 [ 157.105588] ? __pfx_dma_resv_get_singleton+0x10/0x10 [ 157.110697] drm_gem_shmem_vmap+0x74/0x710 [ 157.114866] drm_gem_vmap+0xa9/0x1b0 [ 157.118763] drm_gem_vmap_unlocked+0x46/0xa0 [ 157.123086] drm_gem_fb_vmap+0xab/0x300 [ 157.126979] drm_atomic_helper_prepare_planes.part.0+0x487/0xb10 [ 157.133032] ? lockdep_init_map_type+0x19d/0x880 [ 157.137701] drm_atomic_helper_commit+0x13d/0x2e0 [ 157.142671] ? drm_atomic_nonblocking_commit+0xa0/0x180 [ 157.147988] drm_mode_atomic_ioctl+0x766/0xe40 [...] [ 157.346424] ---[ end trace 0000000000000000 ]--- Acquiring GEM handles for the framebuffer's GEM buffer objects prevents this from happening. The framebuffer's cleanup later puts the handle references. Commit 1a148af06000 ("drm/gem-shmem: Use dma_buf from GEM object instance") triggers the segmentation fault easily by using the dma-buf field more widely. The underlying issue with reference counting has been present before. v2: - acquire the handle instead of the BO (Christian) - fix comment style (Christian) - drop the Fixes tag (Christian) - rename err_ gotos - add missing Link tag
CVE-2025-38491: In the Linux kernel, the following vulnerability has been resolved: mptcp: make fallback action and fallback decision atomic Syzkaller reported the following splat: WARNING: CPU: 1 PID: 7704 at net/mptcp/protocol.h:1223 __mptcp_do_fallback net/mptcp/protocol.h:1223 [inline] WARNING: CPU: 1 PID: 7704 at net/mptcp/protocol.h:1223 mptcp_do_fallback net/mptcp/protocol.h:1244 [inline] WARNING: CPU: 1 PID: 7704 at net/mptcp/protocol.h:1223 check_fully_established net/mptcp/options.c:982 [inline] WARNING: CPU: 1 PID: 7704 at net/mptcp/protocol.h:1223 mptcp_incoming_options+0x21a8/0x2510 net/mptcp/options.c:1153 Modules linked in: CPU: 1 UID: 0 PID: 7704 Comm: syz.3.1419 Not tainted 6.16.0-rc3-gbd5ce2324dba #20 PREEMPT(voluntary) Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:__mptcp_do_fallback net/mptcp/protocol.h:1223 [inline] RIP: 0010:mptcp_do_fallback net/mptcp/protocol.h:1244 [inline] RIP: 0010:check_fully_established net/mptcp/options.c:982 [inline] RIP: 0010:mptcp_incoming_options+0x21a8/0x2510 net/mptcp/options.c:1153 Code: 24 18 e8 bb 2a 00 fd e9 1b df ff ff e8 b1 21 0f 00 e8 ec 5f c4 fc 44 0f b7 ac 24 b0 00 00 00 e9 54 f1 ff ff e8 d9 5f c4 fc 90 <0f> 0b 90 e9 b8 f4 ff ff e8 8b 2a 00 fd e9 8d e6 ff ff e8 81 2a 00 RSP: 0018:ffff8880a3f08448 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8880180a8000 RCX: ffffffff84afcf45 RDX: ffff888090223700 RSI: ffffffff84afdaa7 RDI: 0000000000000001 RBP: ffff888017955780 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffff8880180a8910 R14: ffff8880a3e9d058 R15: 0000000000000000 FS: 00005555791b8500(0000) GS:ffff88811c495000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000110c2800b7 CR3: 0000000058e44000 CR4: 0000000000350ef0 Call Trace: <IRQ> tcp_reset+0x26f/0x2b0 net/ipv4/tcp_input.c:4432 tcp_validate_incoming+0x1057/0x1b60 net/ipv4/tcp_input.c:5975 tcp_rcv_established+0x5b5/0x21f0 net/ipv4/tcp_input.c:6166 tcp_v4_do_rcv+0x5dc/0xa70 net/ipv4/tcp_ipv4.c:1925 tcp_v4_rcv+0x3473/0x44a0 net/ipv4/tcp_ipv4.c:2363 ip_protocol_deliver_rcu+0xba/0x480 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x2f1/0x500 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:317 [inline] NF_HOOK include/linux/netfilter.h:311 [inline] ip_local_deliver+0x1be/0x560 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:469 [inline] ip_rcv_finish net/ipv4/ip_input.c:447 [inline] NF_HOOK include/linux/netfilter.h:317 [inline] NF_HOOK include/linux/netfilter.h:311 [inline] ip_rcv+0x514/0x810 net/ipv4/ip_input.c:567 __netif_receive_skb_one_core+0x197/0x1e0 net/core/dev.c:5975 __netif_receive_skb+0x1f/0x120 net/core/dev.c:6088 process_backlog+0x301/0x1360 net/core/dev.c:6440 __napi_poll.constprop.0+0xba/0x550 net/core/dev.c:7453 napi_poll net/core/dev.c:7517 [inline] net_rx_action+0xb44/0x1010 net/core/dev.c:7644 handle_softirqs+0x1d0/0x770 kernel/softirq.c:579 do_softirq+0x3f/0x90 kernel/softirq.c:480 </IRQ> <TASK> __local_bh_enable_ip+0xed/0x110 kernel/softirq.c:407 local_bh_enable include/linux/bottom_half.h:33 [inline] inet_csk_listen_stop+0x2c5/0x1070 net/ipv4/inet_connection_sock.c:1524 mptcp_check_listen_stop.part.0+0x1cc/0x220 net/mptcp/protocol.c:2985 mptcp_check_listen_stop net/mptcp/mib.h:118 [inline] __mptcp_close+0x9b9/0xbd0 net/mptcp/protocol.c:3000 mptcp_close+0x2f/0x140 net/mptcp/protocol.c:3066 inet_release+0xed/0x200 net/ipv4/af_inet.c:435 inet6_release+0x4f/0x70 net/ipv6/af_inet6.c:487 __sock_release+0xb3/0x270 net/socket.c:649 sock_close+0x1c/0x30 net/socket.c:1439 __fput+0x402/0xb70 fs/file_table.c:465 task_work_run+0x150/0x240 kernel/task_work.c:227 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline] exit_to_user_mode_loop+0xd4 ---truncated---
CVE-2025-38499: In the Linux kernel, the following vulnerability has been resolved: clone_private_mnt(): make sure that caller has CAP_SYS_ADMIN in the right userns What we want is to verify there is that clone won't expose something hidden by a mount we wouldn't be able to undo. "Wouldn't be able to undo" may be a result of MNT_LOCKED on a child, but it may also come from lacking admin rights in the userns of the namespace mount belongs to. clone_private_mnt() checks the former, but not the latter. There's a number of rather confusing CAP_SYS_ADMIN checks in various userns during the mount, especially with the new mount API; they serve different purposes and in case of clone_private_mnt() they usually, but not always end up covering the missing check mentioned above.
CVE-2025-38502: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix oob access in cgroup local storage Lonial reported that an out-of-bounds access in cgroup local storage can be crafted via tail calls. Given two programs each utilizing a cgroup local storage with a different value size, and one program doing a tail call into the other. The verifier will validate each of the indivial programs just fine. However, in the runtime context the bpf_cg_run_ctx holds an bpf_prog_array_item which contains the BPF program as well as any cgroup local storage flavor the program uses. Helpers such as bpf_get_local_storage() pick this up from the runtime context: ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); storage = ctx->prog_item->cgroup_storage[stype]; if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; else ptr = this_cpu_ptr(storage->percpu_buf); For the second program which was called from the originally attached one, this means bpf_get_local_storage() will pick up the former program's map, not its own. With mismatching sizes, this can result in an unintended out-of-bounds access. To fix this issue, we need to extend bpf_map_owner with an array of storage_cookie[] to match on i) the exact maps from the original program if the second program was using bpf_get_local_storage(), or ii) allow the tail call combination if the second program was not using any of the cgroup local storage maps.
CVE-2025-38524: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix recv-recv race of completed call If a call receives an event (such as incoming data), the call gets placed on the socket's queue and a thread in recvmsg can be awakened to go and process it. Once the thread has picked up the call off of the queue, further events will cause it to be requeued, and once the socket lock is dropped (recvmsg uses call->user_mutex to allow the socket to be used in parallel), a second thread can come in and its recvmsg can pop the call off the socket queue again. In such a case, the first thread will be receiving stuff from the call and the second thread will be blocked on call->user_mutex. The first thread can, at this point, process both the event that it picked call for and the event that the second thread picked the call for and may see the call terminate - in which case the call will be "released", decoupling the call from the user call ID assigned to it (RXRPC_USER_CALL_ID in the control message). The first thread will return okay, but then the second thread will wake up holding the user_mutex and, if it sees that the call has been released by the first thread, it will BUG thusly: kernel BUG at net/rxrpc/recvmsg.c:474! Fix this by just dequeuing the call and ignoring it if it is seen to be already released. We can't tell userspace about it anyway as the user call ID has become stale.
CVE-2025-38527: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free in cifs_oplock_break A race condition can occur in cifs_oplock_break() leading to a use-after-free of the cinode structure when unmounting: cifs_oplock_break() _cifsFileInfo_put(cfile) cifsFileInfo_put_final() cifs_sb_deactive() [last ref, start releasing sb] kill_sb() kill_anon_super() generic_shutdown_super() evict_inodes() dispose_list() evict() destroy_inode() call_rcu(&inode->i_rcu, i_callback) spin_lock(&cinode->open_file_lock) <- OK [later] i_callback() cifs_free_inode() kmem_cache_free(cinode) spin_unlock(&cinode->open_file_lock) <- UAF cifs_done_oplock_break(cinode) <- UAF The issue occurs when umount has already released its reference to the superblock. When _cifsFileInfo_put() calls cifs_sb_deactive(), this releases the last reference, triggering the immediate cleanup of all inodes under RCU. However, cifs_oplock_break() continues to access the cinode after this point, resulting in use-after-free. Fix this by holding an extra reference to the superblock during the entire oplock break operation. This ensures that the superblock and its inodes remain valid until the oplock break completes.
CVE-2025-38544: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix bug due to prealloc collision When userspace is using AF_RXRPC to provide a server, it has to preallocate incoming calls and assign to them call IDs that will be used to thread related recvmsg() and sendmsg() together. The preallocated call IDs will automatically be attached to calls as they come in until the pool is empty. To the kernel, the call IDs are just arbitrary numbers, but userspace can use the call ID to hold a pointer to prepared structs. In any case, the user isn't permitted to create two calls with the same call ID (call IDs become available again when the call ends) and EBADSLT should result from sendmsg() if an attempt is made to preallocate a call with an in-use call ID. However, the cleanup in the error handling will trigger both assertions in rxrpc_cleanup_call() because the call isn't marked complete and isn't marked as having been released. Fix this by setting the call state in rxrpc_service_prealloc_one() and then marking it as being released before calling the cleanup function.
CVE-2025-38584: In the Linux kernel, the following vulnerability has been resolved: padata: Fix pd UAF once and for all There is a race condition/UAF in padata_reorder that goes back to the initial commit. A reference count is taken at the start of the process in padata_do_parallel, and released at the end in padata_serial_worker. This reference count is (and only is) required for padata_replace to function correctly. If padata_replace is never called then there is no issue. In the function padata_reorder which serves as the core of padata, as soon as padata is added to queue->serial.list, and the associated spin lock released, that padata may be processed and the reference count on pd would go away. Fix this by getting the next padata before the squeue->serial lock is released. In order to make this possible, simplify padata_reorder by only calling it once the next padata arrives.
CVE-2025-38590: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Remove skb secpath if xfrm state is not found Hardware returns a unique identifier for a decrypted packet's xfrm state, this state is looked up in an xarray. However, the state might have been freed by the time of this lookup. Currently, if the state is not found, only a counter is incremented. The secpath (sp) extension on the skb is not removed, resulting in sp->len becoming 0. Subsequently, functions like __xfrm_policy_check() attempt to access fields such as xfrm_input_state(skb)->xso.type (which dereferences sp->xvec[sp->len - 1]) without first validating sp->len. This leads to a crash when dereferencing an invalid state pointer. This patch prevents the crash by explicitly removing the secpath extension from the skb if the xfrm state is not found after hardware decryption. This ensures downstream functions do not operate on a zero-length secpath. BUG: unable to handle page fault for address: ffffffff000002c8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 282e067 P4D 282e067 PUD 0 Oops: Oops: 0000 [#1] SMP CPU: 12 UID: 0 PID: 0 Comm: swapper/12 Not tainted 6.15.0-rc7_for_upstream_min_debug_2025_05_27_22_44 #1 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:__xfrm_policy_check+0x61a/0xa30 Code: b6 77 7f 83 e6 02 74 14 4d 8b af d8 00 00 00 41 0f b6 45 05 c1 e0 03 48 98 49 01 c5 41 8b 45 00 83 e8 01 48 98 49 8b 44 c5 10 <0f> b6 80 c8 02 00 00 83 e0 0c 3c 04 0f 84 0c 02 00 00 31 ff 80 fa RSP: 0018:ffff88885fb04918 EFLAGS: 00010297 RAX: ffffffff00000000 RBX: 0000000000000002 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000002 RDI: 0000000000000000 RBP: ffffffff8311af80 R08: 0000000000000020 R09: 00000000c2eda353 R10: ffff88812be2bbc8 R11: 000000001faab533 R12: ffff88885fb049c8 R13: ffff88812be2bbc8 R14: 0000000000000000 R15: ffff88811896ae00 FS: 0000000000000000(0000) GS:ffff8888dca82000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff000002c8 CR3: 0000000243050002 CR4: 0000000000372eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> ? try_to_wake_up+0x108/0x4c0 ? udp4_lib_lookup2+0xbe/0x150 ? udp_lib_lport_inuse+0x100/0x100 ? __udp4_lib_lookup+0x2b0/0x410 __xfrm_policy_check2.constprop.0+0x11e/0x130 udp_queue_rcv_one_skb+0x1d/0x530 udp_unicast_rcv_skb+0x76/0x90 __udp4_lib_rcv+0xa64/0xe90 ip_protocol_deliver_rcu+0x20/0x130 ip_local_deliver_finish+0x75/0xa0 ip_local_deliver+0xc1/0xd0 ? ip_protocol_deliver_rcu+0x130/0x130 ip_sublist_rcv+0x1f9/0x240 ? ip_rcv_finish_core+0x430/0x430 ip_list_rcv+0xfc/0x130 __netif_receive_skb_list_core+0x181/0x1e0 netif_receive_skb_list_internal+0x200/0x360 ? mlx5e_build_rx_skb+0x1bc/0xda0 [mlx5_core] gro_receive_skb+0xfd/0x210 mlx5e_handle_rx_cqe_mpwrq+0x141/0x280 [mlx5_core] mlx5e_poll_rx_cq+0xcc/0x8e0 [mlx5_core] ? mlx5e_handle_rx_dim+0x91/0xd0 [mlx5_core] mlx5e_napi_poll+0x114/0xab0 [mlx5_core] __napi_poll+0x25/0x170 net_rx_action+0x32d/0x3a0 ? mlx5_eq_comp_int+0x8d/0x280 [mlx5_core] ? notifier_call_chain+0x33/0xa0 handle_softirqs+0xda/0x250 irq_exit_rcu+0x6d/0xc0 common_interrupt+0x81/0xa0 </IRQ>
CVE-2025-38595: In the Linux kernel, the following vulnerability has been resolved: xen: fix UAF in dmabuf_exp_from_pages() [dma_buf_fd() fixes; no preferences regarding the tree it goes through - up to xen folks] As soon as we'd inserted a file reference into descriptor table, another thread could close it. That's fine for the case when all we are doing is returning that descriptor to userland (it's a race, but it's a userland race and there's nothing the kernel can do about it). However, if we follow fd_install() with any kind of access to objects that would be destroyed on close (be it the struct file itself or anything destroyed by its ->release()), we have a UAF. dma_buf_fd() is a combination of reserving a descriptor and fd_install(). gntdev dmabuf_exp_from_pages() calls it and then proceeds to access the objects destroyed on close - starting with gntdev_dmabuf itself. Fix that by doing reserving descriptor before anything else and do fd_install() only when everything had been set up.
CVE-2025-38614: In the Linux kernel, the following vulnerability has been resolved: eventpoll: Fix semi-unbounded recursion Ensure that epoll instances can never form a graph deeper than EP_MAX_NESTS+1 links. Currently, ep_loop_check_proc() ensures that the graph is loop-free and does some recursion depth checks, but those recursion depth checks don't limit the depth of the resulting tree for two reasons: - They don't look upwards in the tree. - If there are multiple downwards paths of different lengths, only one of the paths is actually considered for the depth check since commit 28d82dc1c4ed ("epoll: limit paths"). Essentially, the current recursion depth check in ep_loop_check_proc() just serves to prevent it from recursing too deeply while checking for loops. A more thorough check is done in reverse_path_check() after the new graph edge has already been created; this checks, among other things, that no paths going upwards from any non-epoll file with a length of more than 5 edges exist. However, this check does not apply to non-epoll files. As a result, it is possible to recurse to a depth of at least roughly 500, tested on v6.15. (I am unsure if deeper recursion is possible; and this may have changed with commit 8c44dac8add7 ("eventpoll: Fix priority inversion problem").) To fix it: 1. In ep_loop_check_proc(), note the subtree depth of each visited node, and use subtree depths for the total depth calculation even when a subtree has already been visited. 2. Add ep_get_upwards_depth_proc() for similarly determining the maximum depth of an upwards walk. 3. In ep_loop_check(), use these values to limit the total path length between epoll nodes to EP_MAX_NESTS edges.
CVE-2025-38626: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to trigger foreground gc during f2fs_map_blocks() in lfs mode w/ "mode=lfs" mount option, generic/299 will cause system panic as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2835! Call Trace: <TASK> f2fs_allocate_data_block+0x6f4/0xc50 f2fs_map_blocks+0x970/0x1550 f2fs_iomap_begin+0xb2/0x1e0 iomap_iter+0x1d6/0x430 __iomap_dio_rw+0x208/0x9a0 f2fs_file_write_iter+0x6b3/0xfa0 aio_write+0x15d/0x2e0 io_submit_one+0x55e/0xab0 __x64_sys_io_submit+0xa5/0x230 do_syscall_64+0x84/0x2f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0010:new_curseg+0x70f/0x720 The root cause of we run out-of-space is: in f2fs_map_blocks(), f2fs may trigger foreground gc only if it allocates any physical block, it will be a little bit later when there is multiple threads writing data w/ aio/dio/bufio method in parallel, since we always use OPU in lfs mode, so f2fs_map_blocks() does block allocations aggressively. In order to fix this issue, let's give a chance to trigger foreground gc in prior to block allocation in f2fs_map_blocks().
CVE-2025-38643: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: Add missing lock in cfg80211_check_and_end_cac() Callers of wdev_chandef() must hold the wiphy mutex. But the worker cfg80211_propagate_cac_done_wk() never takes the lock. Which triggers the warning below with the mesh_peer_connected_dfs test from hostapd and not (yet) released mac80211 code changes: WARNING: CPU: 0 PID: 495 at net/wireless/chan.c:1552 wdev_chandef+0x60/0x165 Modules linked in: CPU: 0 UID: 0 PID: 495 Comm: kworker/u4:2 Not tainted 6.14.0-rc5-wt-g03960e6f9d47 #33 13c287eeabfe1efea01c0bcc863723ab082e17cf Workqueue: cfg80211 cfg80211_propagate_cac_done_wk Stack: 00000000 00000001 ffffff00 6093267c 00000000 6002ec30 6d577c50 60037608 00000000 67e8d108 6063717b 00000000 Call Trace: [<6002ec30>] ? _printk+0x0/0x98 [<6003c2b3>] show_stack+0x10e/0x11a [<6002ec30>] ? _printk+0x0/0x98 [<60037608>] dump_stack_lvl+0x71/0xb8 [<6063717b>] ? wdev_chandef+0x60/0x165 [<6003766d>] dump_stack+0x1e/0x20 [<6005d1b7>] __warn+0x101/0x20f [<6005d3a8>] warn_slowpath_fmt+0xe3/0x15d [<600b0c5c>] ? mark_lock.part.0+0x0/0x4ec [<60751191>] ? __this_cpu_preempt_check+0x0/0x16 [<600b11a2>] ? mark_held_locks+0x5a/0x6e [<6005d2c5>] ? warn_slowpath_fmt+0x0/0x15d [<60052e53>] ? unblock_signals+0x3a/0xe7 [<60052f2d>] ? um_set_signals+0x2d/0x43 [<60751191>] ? __this_cpu_preempt_check+0x0/0x16 [<607508b2>] ? lock_is_held_type+0x207/0x21f [<6063717b>] wdev_chandef+0x60/0x165 [<605f89b4>] regulatory_propagate_dfs_state+0x247/0x43f [<60052f00>] ? um_set_signals+0x0/0x43 [<605e6bfd>] cfg80211_propagate_cac_done_wk+0x3a/0x4a [<6007e460>] process_scheduled_works+0x3bc/0x60e [<6007d0ec>] ? move_linked_works+0x4d/0x81 [<6007d120>] ? assign_work+0x0/0xaa [<6007f81f>] worker_thread+0x220/0x2dc [<600786ef>] ? set_pf_worker+0x0/0x57 [<60087c96>] ? to_kthread+0x0/0x43 [<6008ab3c>] kthread+0x2d3/0x2e2 [<6007f5ff>] ? worker_thread+0x0/0x2dc [<6006c05b>] ? calculate_sigpending+0x0/0x56 [<6003b37d>] new_thread_handler+0x4a/0x64 irq event stamp: 614611 hardirqs last enabled at (614621): [<00000000600bc96b>] __up_console_sem+0x82/0xaf hardirqs last disabled at (614630): [<00000000600bc92c>] __up_console_sem+0x43/0xaf softirqs last enabled at (614268): [<00000000606c55c6>] __ieee80211_wake_queue+0x933/0x985 softirqs last disabled at (614266): [<00000000606c52d6>] __ieee80211_wake_queue+0x643/0x985
CVE-2025-38644: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: reject TDLS operations when station is not associated syzbot triggered a WARN in ieee80211_tdls_oper() by sending NL80211_TDLS_ENABLE_LINK immediately after NL80211_CMD_CONNECT, before association completed and without prior TDLS setup. This left internal state like sdata->u.mgd.tdls_peer uninitialized, leading to a WARN_ON() in code paths that assumed it was valid. Reject the operation early if not in station mode or not associated.
CVE-2025-38645: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Check device memory pointer before usage Add a NULL check before accessing device memory to prevent a crash if dev->dm allocation in mlx5_init_once() fails.
CVE-2025-38659: In the Linux kernel, the following vulnerability has been resolved: gfs2: No more self recovery When a node withdraws and it turns out that it is the only node that has the filesystem mounted, gfs2 currently tries to replay the local journal to bring the filesystem back into a consistent state. Not only is that a very bad idea, it has also never worked because gfs2_recover_func() will refuse to do anything during a withdraw. However, before even getting to this point, gfs2_recover_func() dereferences sdp->sd_jdesc->jd_inode. This was a use-after-free before commit 04133b607a78 ("gfs2: Prevent double iput for journal on error") and is a NULL pointer dereference since then. Simply get rid of self recovery to fix that.
CVE-2025-38665: In the Linux kernel, the following vulnerability has been resolved: can: netlink: can_changelink(): fix NULL pointer deref of struct can_priv::do_set_mode Andrei Lalaev reported a NULL pointer deref when a CAN device is restarted from Bus Off and the driver does not implement the struct can_priv::do_set_mode callback. There are 2 code path that call struct can_priv::do_set_mode: - directly by a manual restart from the user space, via can_changelink() - delayed automatic restart after bus off (deactivated by default) To prevent the NULL pointer deference, refuse a manual restart or configure the automatic restart delay in can_changelink() and report the error via extack to user space. As an additional safety measure let can_restart() return an error if can_priv::do_set_mode is not set instead of dereferencing it unchecked.
CVE-2025-38679: In the Linux kernel, the following vulnerability has been resolved: media: venus: Fix OOB read due to missing payload bound check Currently, The event_seq_changed() handler processes a variable number of properties sent by the firmware. The number of properties is indicated by the firmware and used to iterate over the payload. However, the payload size is not being validated against the actual message length. This can lead to out-of-bounds memory access if the firmware provides a property count that exceeds the data available in the payload. Such a condition can result in kernel crashes or potential information leaks if memory beyond the buffer is accessed. Fix this by properly validating the remaining size of the payload before each property access and updating bounds accordingly as properties are parsed. This ensures that property parsing is safely bounded within the received message buffer and protects against malformed or malicious firmware behavior.
CVE-2025-38685: In the Linux kernel, the following vulnerability has been resolved: fbdev: Fix vmalloc out-of-bounds write in fast_imageblit This issue triggers when a userspace program does an ioctl FBIOPUT_CON2FBMAP by passing console number and frame buffer number. Ideally this maps console to frame buffer and updates the screen if console is visible. As part of mapping it has to do resize of console according to frame buffer info. if this resize fails and returns from vc_do_resize() and continues further. At this point console and new frame buffer are mapped and sets display vars. Despite failure still it continue to proceed updating the screen at later stages where vc_data is related to previous frame buffer and frame buffer info and display vars are mapped to new frame buffer and eventully leading to out-of-bounds write in fast_imageblit(). This bheviour is excepted only when fg_console is equal to requested console which is a visible console and updates screen with invalid struct references in fbcon_putcs().
CVE-2025-38692: In the Linux kernel, the following vulnerability has been resolved: exfat: add cluster chain loop check for dir An infinite loop may occur if the following conditions occur due to file system corruption. (1) Condition for exfat_count_dir_entries() to loop infinitely. - The cluster chain includes a loop. - There is no UNUSED entry in the cluster chain. (2) Condition for exfat_create_upcase_table() to loop infinitely. - The cluster chain of the root directory includes a loop. - There are no UNUSED entry and up-case table entry in the cluster chain of the root directory. (3) Condition for exfat_load_bitmap() to loop infinitely. - The cluster chain of the root directory includes a loop. - There are no UNUSED entry and bitmap entry in the cluster chain of the root directory. (4) Condition for exfat_find_dir_entry() to loop infinitely. - The cluster chain includes a loop. - The unused directory entries were exhausted by some operation. (5) Condition for exfat_check_dir_empty() to loop infinitely. - The cluster chain includes a loop. - The unused directory entries were exhausted by some operation. - All files and sub-directories under the directory are deleted. This commit adds checks to break the above infinite loop.
CVE-2025-38693: In the Linux kernel, the following vulnerability has been resolved: media: dvb-frontends: w7090p: fix null-ptr-deref in w7090p_tuner_write_serpar and w7090p_tuner_read_serpar In w7090p_tuner_write_serpar, msg is controlled by user. When msg[0].buf is null and msg[0].len is zero, former checks on msg[0].buf would be passed. If accessing msg[0].buf[2] without sanity check, null pointer deref would happen. We add check on msg[0].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()")
CVE-2025-38702: In the Linux kernel, the following vulnerability has been resolved: fbdev: fix potential buffer overflow in do_register_framebuffer() The current implementation may lead to buffer overflow when: 1. Unregistration creates NULL gaps in registered_fb[] 2. All array slots become occupied despite num_registered_fb < FB_MAX 3. The registration loop exceeds array bounds Add boundary check to prevent registered_fb[FB_MAX] access.
CVE-2025-38705: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: fix null pointer access Writing a string without delimiters (' ', '\n', '\0') to the under gpu_od/fan_ctrl sysfs or pp_power_profile_mode for the CUSTOM profile will result in a null pointer dereference.
CVE-2025-38709: In the Linux kernel, the following vulnerability has been resolved: loop: Avoid updating block size under exclusive owner Syzbot came up with a reproducer where a loop device block size is changed underneath a mounted filesystem. This causes a mismatch between the block device block size and the block size stored in the superblock causing confusion in various places such as fs/buffer.c. The particular issue triggered by syzbot was a warning in __getblk_slow() due to requested buffer size not matching block device block size. Fix the problem by getting exclusive hold of the loop device to change its block size. This fails if somebody (such as filesystem) has already an exclusive ownership of the block device and thus prevents modifying the loop device under some exclusive owner which doesn't expect it.
CVE-2025-38710: In the Linux kernel, the following vulnerability has been resolved: gfs2: Validate i_depth for exhash directories A fuzzer test introduced corruption that ends up with a depth of 0 in dir_e_read(), causing an undefined shift by 32 at: index = hash >> (32 - dip->i_depth); As calculated in an open-coded way in dir_make_exhash(), the minimum depth for an exhash directory is ilog2(sdp->sd_hash_ptrs) and 0 is invalid as sdp->sd_hash_ptrs is fixed as sdp->bsize / 16 at mount time. So we can avoid the undefined behaviour by checking for depth values lower than the minimum in gfs2_dinode_in(). Values greater than the maximum are already being checked for there. Also switch the calculation in dir_make_exhash() to use ilog2() to clarify how the depth is calculated. Tested with the syzkaller repro.c and xfstests '-g quick'.
CVE-2025-38716: In the Linux kernel, the following vulnerability has been resolved: hfs: fix general protection fault in hfs_find_init() The hfs_find_init() method can trigger the crash if tree pointer is NULL: [ 45.746290][ T9787] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000008: 0000 [#1] SMP KAI [ 45.747287][ T9787] KASAN: null-ptr-deref in range [0x0000000000000040-0x0000000000000047] [ 45.748716][ T9787] CPU: 2 UID: 0 PID: 9787 Comm: repro Not tainted 6.16.0-rc3 #10 PREEMPT(full) [ 45.750250][ T9787] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 45.751983][ T9787] RIP: 0010:hfs_find_init+0x86/0x230 [ 45.752834][ T9787] Code: c1 ea 03 80 3c 02 00 0f 85 9a 01 00 00 4c 8d 6b 40 48 c7 45 18 00 00 00 00 48 b8 00 00 00 00 00 fc [ 45.755574][ T9787] RSP: 0018:ffffc90015157668 EFLAGS: 00010202 [ 45.756432][ T9787] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff819a4d09 [ 45.757457][ T9787] RDX: 0000000000000008 RSI: ffffffff819acd3a RDI: ffffc900151576e8 [ 45.758282][ T9787] RBP: ffffc900151576d0 R08: 0000000000000005 R09: 0000000000000000 [ 45.758943][ T9787] R10: 0000000080000000 R11: 0000000000000001 R12: 0000000000000004 [ 45.759619][ T9787] R13: 0000000000000040 R14: ffff88802c50814a R15: 0000000000000000 [ 45.760293][ T9787] FS: 00007ffb72734540(0000) GS:ffff8880cec64000(0000) knlGS:0000000000000000 [ 45.761050][ T9787] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 45.761606][ T9787] CR2: 00007f9bd8225000 CR3: 000000010979a000 CR4: 00000000000006f0 [ 45.762286][ T9787] Call Trace: [ 45.762570][ T9787] <TASK> [ 45.762824][ T9787] hfs_ext_read_extent+0x190/0x9d0 [ 45.763269][ T9787] ? submit_bio_noacct_nocheck+0x2dd/0xce0 [ 45.763766][ T9787] ? __pfx_hfs_ext_read_extent+0x10/0x10 [ 45.764250][ T9787] hfs_get_block+0x55f/0x830 [ 45.764646][ T9787] block_read_full_folio+0x36d/0x850 [ 45.765105][ T9787] ? __pfx_hfs_get_block+0x10/0x10 [ 45.765541][ T9787] ? const_folio_flags+0x5b/0x100 [ 45.765972][ T9787] ? __pfx_hfs_read_folio+0x10/0x10 [ 45.766415][ T9787] filemap_read_folio+0xbe/0x290 [ 45.766840][ T9787] ? __pfx_filemap_read_folio+0x10/0x10 [ 45.767325][ T9787] ? __filemap_get_folio+0x32b/0xbf0 [ 45.767780][ T9787] do_read_cache_folio+0x263/0x5c0 [ 45.768223][ T9787] ? __pfx_hfs_read_folio+0x10/0x10 [ 45.768666][ T9787] read_cache_page+0x5b/0x160 [ 45.769070][ T9787] hfs_btree_open+0x491/0x1740 [ 45.769481][ T9787] hfs_mdb_get+0x15e2/0x1fb0 [ 45.769877][ T9787] ? __pfx_hfs_mdb_get+0x10/0x10 [ 45.770316][ T9787] ? find_held_lock+0x2b/0x80 [ 45.770731][ T9787] ? lockdep_init_map_type+0x5c/0x280 [ 45.771200][ T9787] ? lockdep_init_map_type+0x5c/0x280 [ 45.771674][ T9787] hfs_fill_super+0x38e/0x720 [ 45.772092][ T9787] ? __pfx_hfs_fill_super+0x10/0x10 [ 45.772549][ T9787] ? snprintf+0xbe/0x100 [ 45.772931][ T9787] ? __pfx_snprintf+0x10/0x10 [ 45.773350][ T9787] ? do_raw_spin_lock+0x129/0x2b0 [ 45.773796][ T9787] ? find_held_lock+0x2b/0x80 [ 45.774215][ T9787] ? set_blocksize+0x40a/0x510 [ 45.774636][ T9787] ? sb_set_blocksize+0x176/0x1d0 [ 45.775087][ T9787] ? setup_bdev_super+0x369/0x730 [ 45.775533][ T9787] get_tree_bdev_flags+0x384/0x620 [ 45.775985][ T9787] ? __pfx_hfs_fill_super+0x10/0x10 [ 45.776453][ T9787] ? __pfx_get_tree_bdev_flags+0x10/0x10 [ 45.776950][ T9787] ? bpf_lsm_capable+0x9/0x10 [ 45.777365][ T9787] ? security_capable+0x80/0x260 [ 45.777803][ T9787] vfs_get_tree+0x8e/0x340 [ 45.778203][ T9787] path_mount+0x13de/0x2010 [ 45.778604][ T9787] ? kmem_cache_free+0x2b0/0x4c0 [ 45.779052][ T9787] ? __pfx_path_mount+0x10/0x10 [ 45.779480][ T9787] ? getname_flags.part.0+0x1c5/0x550 [ 45.779954][ T9787] ? putname+0x154/0x1a0 [ 45.780335][ T9787] __x64_sys_mount+0x27b/0x300 [ 45.780758][ T9787] ? __pfx___x64_sys_mount+0x10/0x10 [ 45.781232][ T9787] ---truncated---
CVE-2025-38717: In the Linux kernel, the following vulnerability has been resolved: net: kcm: Fix race condition in kcm_unattach() syzbot found a race condition when kcm_unattach(psock) and kcm_release(kcm) are executed at the same time. kcm_unattach() is missing a check of the flag kcm->tx_stopped before calling queue_work(). If the kcm has a reserved psock, kcm_unattach() might get executed between cancel_work_sync() and unreserve_psock() in kcm_release(), requeuing kcm->tx_work right before kcm gets freed in kcm_done(). Remove kcm->tx_stopped and replace it by the less error-prone disable_work_sync().
CVE-2025-38728: In the Linux kernel, the following vulnerability has been resolved: smb3: fix for slab out of bounds on mount to ksmbd With KASAN enabled, it is possible to get a slab out of bounds during mount to ksmbd due to missing check in parse_server_interfaces() (see below): BUG: KASAN: slab-out-of-bounds in parse_server_interfaces+0x14ee/0x1880 [cifs] Read of size 4 at addr ffff8881433dba98 by task mount/9827 CPU: 5 UID: 0 PID: 9827 Comm: mount Tainted: G OE 6.16.0-rc2-kasan #2 PREEMPT(voluntary) Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. Precision Tower 3620/0MWYPT, BIOS 2.13.1 06/14/2019 Call Trace: <TASK> dump_stack_lvl+0x9f/0xf0 print_report+0xd1/0x670 __virt_addr_valid+0x22c/0x430 ? parse_server_interfaces+0x14ee/0x1880 [cifs] ? kasan_complete_mode_report_info+0x2a/0x1f0 ? parse_server_interfaces+0x14ee/0x1880 [cifs] kasan_report+0xd6/0x110 parse_server_interfaces+0x14ee/0x1880 [cifs] __asan_report_load_n_noabort+0x13/0x20 parse_server_interfaces+0x14ee/0x1880 [cifs] ? __pfx_parse_server_interfaces+0x10/0x10 [cifs] ? trace_hardirqs_on+0x51/0x60 SMB3_request_interfaces+0x1ad/0x3f0 [cifs] ? __pfx_SMB3_request_interfaces+0x10/0x10 [cifs] ? SMB2_tcon+0x23c/0x15d0 [cifs] smb3_qfs_tcon+0x173/0x2b0 [cifs] ? __pfx_smb3_qfs_tcon+0x10/0x10 [cifs] ? cifs_get_tcon+0x105d/0x2120 [cifs] ? do_raw_spin_unlock+0x5d/0x200 ? cifs_get_tcon+0x105d/0x2120 [cifs] ? __pfx_smb3_qfs_tcon+0x10/0x10 [cifs] cifs_mount_get_tcon+0x369/0xb90 [cifs] ? dfs_cache_find+0xe7/0x150 [cifs] dfs_mount_share+0x985/0x2970 [cifs] ? check_path.constprop.0+0x28/0x50 ? save_trace+0x54/0x370 ? __pfx_dfs_mount_share+0x10/0x10 [cifs] ? __lock_acquire+0xb82/0x2ba0 ? __kasan_check_write+0x18/0x20 cifs_mount+0xbc/0x9e0 [cifs] ? __pfx_cifs_mount+0x10/0x10 [cifs] ? do_raw_spin_unlock+0x5d/0x200 ? cifs_setup_cifs_sb+0x29d/0x810 [cifs] cifs_smb3_do_mount+0x263/0x1990 [cifs]
CVE-2025-38734: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix UAF on smcsk after smc_listen_out() BPF CI testing report a UAF issue: [ 16.446633] BUG: kernel NULL pointer dereference, address: 000000000000003 0 [ 16.447134] #PF: supervisor read access in kernel mod e [ 16.447516] #PF: error_code(0x0000) - not-present pag e [ 16.447878] PGD 0 P4D 0 [ 16.448063] Oops: Oops: 0000 [#1] PREEMPT SMP NOPT I [ 16.448409] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:1 Tainted: G OE 6.13.0-rc3-g89e8a75fda73-dirty #4 2 [ 16.449124] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODUL E [ 16.449502] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/201 4 [ 16.450201] Workqueue: smc_hs_wq smc_listen_wor k [ 16.450531] RIP: 0010:smc_listen_work+0xc02/0x159 0 [ 16.452158] RSP: 0018:ffffb5ab40053d98 EFLAGS: 0001024 6 [ 16.452526] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 000000000000030 0 [ 16.452994] RDX: 0000000000000280 RSI: 00003513840053f0 RDI: 000000000000000 0 [ 16.453492] RBP: ffffa097808e3800 R08: ffffa09782dba1e0 R09: 000000000000000 5 [ 16.453987] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0978274640 0 [ 16.454497] R13: 0000000000000000 R14: 0000000000000000 R15: ffffa09782d4092 0 [ 16.454996] FS: 0000000000000000(0000) GS:ffffa097bbc00000(0000) knlGS:000000000000000 0 [ 16.455557] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003 3 [ 16.455961] CR2: 0000000000000030 CR3: 0000000102788004 CR4: 0000000000770ef 0 [ 16.456459] PKRU: 5555555 4 [ 16.456654] Call Trace : [ 16.456832] <TASK > [ 16.456989] ? __die+0x23/0x7 0 [ 16.457215] ? page_fault_oops+0x180/0x4c 0 [ 16.457508] ? __lock_acquire+0x3e6/0x249 0 [ 16.457801] ? exc_page_fault+0x68/0x20 0 [ 16.458080] ? asm_exc_page_fault+0x26/0x3 0 [ 16.458389] ? smc_listen_work+0xc02/0x159 0 [ 16.458689] ? smc_listen_work+0xc02/0x159 0 [ 16.458987] ? lock_is_held_type+0x8f/0x10 0 [ 16.459284] process_one_work+0x1ea/0x6d 0 [ 16.459570] worker_thread+0x1c3/0x38 0 [ 16.459839] ? __pfx_worker_thread+0x10/0x1 0 [ 16.460144] kthread+0xe0/0x11 0 [ 16.460372] ? __pfx_kthread+0x10/0x1 0 [ 16.460640] ret_from_fork+0x31/0x5 0 [ 16.460896] ? __pfx_kthread+0x10/0x1 0 [ 16.461166] ret_from_fork_asm+0x1a/0x3 0 [ 16.461453] </TASK > [ 16.461616] Modules linked in: bpf_testmod(OE) [last unloaded: bpf_testmod(OE) ] [ 16.462134] CR2: 000000000000003 0 [ 16.462380] ---[ end trace 0000000000000000 ]--- [ 16.462710] RIP: 0010:smc_listen_work+0xc02/0x1590 The direct cause of this issue is that after smc_listen_out_connected(), newclcsock->sk may be NULL since it will releases the smcsk. Therefore, if the application closes the socket immediately after accept, newclcsock->sk can be NULL. A possible execution order could be as follows: smc_listen_work | userspace ----------------------------------------------------------------- lock_sock(sk) | smc_listen_out_connected() | | \- smc_listen_out | | | \- release_sock | | |- sk->sk_data_ready() | | fd = accept(); | close(fd); | \- socket->sk = NULL; /* newclcsock->sk is NULL now */ SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk)) Since smc_listen_out_connected() will not fail, simply swapping the order of the code can easily fix this issue.
CVE-2025-39675: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null pointer check in mod_hdcp_hdcp1_create_session() The function mod_hdcp_hdcp1_create_session() calls the function get_first_active_display(), but does not check its return value. The return value is a null pointer if the display list is empty. This will lead to a null pointer dereference. Add a null pointer check for get_first_active_display() and return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND if the function return null. This is similar to the commit c3e9826a2202 ("drm/amd/display: Add null pointer check for get_first_active_display()"). (cherry picked from commit 5e43eb3cd731649c4f8b9134f857be62a416c893)
CVE-2025-39677: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix backlog accounting in qdisc_dequeue_internal This issue applies for the following qdiscs: hhf, fq, fq_codel, and fq_pie, and occurs in their change handlers when adjusting to the new limit. The problem is the following in the values passed to the subsequent qdisc_tree_reduce_backlog call given a tbf parent: When the tbf parent runs out of tokens, skbs of these qdiscs will be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued, which accounts for both qlen and backlog. However, in the case of qdisc_dequeue_internal, ONLY qlen is accounted for when pulling from gso_skb. This means that these qdiscs are missing a qdisc_qstats_backlog_dec when dropping packets to satisfy the new limit in their change handlers. One can observe this issue with the following (with tc patched to support a limit of 0): export TARGET=fq tc qdisc del dev lo root tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000 echo ''; echo 'add child'; tc -s -d qdisc show dev lo ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null echo ''; echo 'after ping'; tc -s -d qdisc show dev lo tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0 echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo tc qdisc replace dev lo handle 2: parent 1:1 sfq echo ''; echo 'post graft'; tc -s -d qdisc show dev lo The second to last show command shows 0 packets but a positive number (74) of backlog bytes. The problem becomes clearer in the last show command, where qdisc_purge_queue triggers qdisc_tree_reduce_backlog with the positive backlog and causes an underflow in the tbf parent's backlog (4096 Mb instead of 0). To fix this issue, the codepath for all clients of qdisc_dequeue_internal has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel. qdisc_dequeue_internal handles the backlog adjustments for all cases that do not directly use the dequeue handler. The old fq_codel_change limit adjustment loop accumulated the arguments to the subsequent qdisc_tree_reduce_backlog call through the cstats field. However, this is confusing and error prone as fq_codel_dequeue could also potentially mutate this field (which qdisc_dequeue_internal calls in the non gso_skb case), so we have unified the code here with other qdiscs.
CVE-2025-39684: In the Linux kernel, the following vulnerability has been resolved: comedi: Fix use of uninitialized memory in do_insn_ioctl() and do_insnlist_ioctl() syzbot reports a KMSAN kernel-infoleak in `do_insn_ioctl()`. A kernel buffer is allocated to hold `insn->n` samples (each of which is an `unsigned int`). For some instruction types, `insn->n` samples are copied back to user-space, unless an error code is being returned. The problem is that not all the instruction handlers that need to return data to userspace fill in the whole `insn->n` samples, so that there is an information leak. There is a similar syzbot report for `do_insnlist_ioctl()`, although it does not have a reproducer for it at the time of writing. One culprit is `insn_rw_emulate_bits()` which is used as the handler for `INSN_READ` or `INSN_WRITE` instructions for subdevices that do not have a specific handler for that instruction, but do have an `INSN_BITS` handler. For `INSN_READ` it only fills in at most 1 sample, so if `insn->n` is greater than 1, the remaining `insn->n - 1` samples copied to userspace will be uninitialized kernel data. Another culprit is `vm80xx_ai_insn_read()` in the "vm80xx" driver. It never returns an error, even if it fails to fill the buffer. Fix it in `do_insn_ioctl()` and `do_insnlist_ioctl()` by making sure that uninitialized parts of the allocated buffer are zeroed before handling each instruction. Thanks to Arnaud Lecomte for their fix to `do_insn_ioctl()`. That fix replaced the call to `kmalloc_array()` with `kcalloc()`, but it is not always necessary to clear the whole buffer.
CVE-2025-39685: In the Linux kernel, the following vulnerability has been resolved: comedi: pcl726: Prevent invalid irq number The reproducer passed in an irq number(0x80008000) that was too large, which triggered the oob. Added an interrupt number check to prevent users from passing in an irq number that was too large. If `it->options[1]` is 31, then `1 << it->options[1]` is still invalid because it shifts a 1-bit into the sign bit (which is UB in C). Possible solutions include reducing the upper bound on the `it->options[1]` value to 30 or lower, or using `1U << it->options[1]`. The old code would just not attempt to request the IRQ if the `options[1]` value were invalid. And it would still configure the device without interrupts even if the call to `request_irq` returned an error. So it would be better to combine this test with the test below.
CVE-2025-39686: In the Linux kernel, the following vulnerability has been resolved: comedi: Make insn_rw_emulate_bits() do insn->n samples The `insn_rw_emulate_bits()` function is used as a default handler for `INSN_READ` instructions for subdevices that have a handler for `INSN_BITS` but not for `INSN_READ`. Similarly, it is used as a default handler for `INSN_WRITE` instructions for subdevices that have a handler for `INSN_BITS` but not for `INSN_WRITE`. It works by emulating the `INSN_READ` or `INSN_WRITE` instruction handling with a constructed `INSN_BITS` instruction. However, `INSN_READ` and `INSN_WRITE` instructions are supposed to be able read or write multiple samples, indicated by the `insn->n` value, but `insn_rw_emulate_bits()` currently only handles a single sample. For `INSN_READ`, the comedi core will copy `insn->n` samples back to user-space. (That triggered KASAN kernel-infoleak errors when `insn->n` was greater than 1, but that is being fixed more generally elsewhere in the comedi core.) Make `insn_rw_emulate_bits()` either handle `insn->n` samples, or return an error, to conform to the general expectation for `INSN_READ` and `INSN_WRITE` handlers.
CVE-2025-39693: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Avoid a NULL pointer dereference [WHY] Although unlikely drm_atomic_get_new_connector_state() or drm_atomic_get_old_connector_state() can return NULL. [HOW] Check returns before dereference. (cherry picked from commit 1e5e8d672fec9f2ab352be121be971877bff2af9)
CVE-2025-39705: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix a Null pointer dereference vulnerability [Why] A null pointer dereference vulnerability exists in the AMD display driver's (DC module) cleanup function dc_destruct(). When display control context (dc->ctx) construction fails (due to memory allocation failure), this pointer remains NULL. During subsequent error handling when dc_destruct() is called, there's no NULL check before dereferencing the perf_trace member (dc->ctx->perf_trace), causing a kernel null pointer dereference crash. [How] Check if dc->ctx is non-NULL before dereferencing. (Updated commit text and removed unnecessary error message) (cherry picked from commit 9dd8e2ba268c636c240a918e0a31e6feaee19404)
CVE-2025-39706: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Destroy KFD debugfs after destroy KFD wq Since KFD proc content was moved to kernel debugfs, we can't destroy KFD debugfs before kfd_process_destroy_wq. Move kfd_process_destroy_wq prior to kfd_debugfs_fini to fix a kernel NULL pointer problem. It happens when /sys/kernel/debug/kfd was already destroyed in kfd_debugfs_fini but kfd_process_destroy_wq calls kfd_debugfs_remove_process. This line debugfs_remove_recursive(entry->proc_dentry); tries to remove /sys/kernel/debug/kfd/proc/<pid> while /sys/kernel/debug/kfd is already gone. It hangs the kernel by kernel NULL pointer. (cherry picked from commit 0333052d90683d88531558dcfdbf2525cc37c233)
CVE-2025-39707: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: check if hubbub is NULL in debugfs/amdgpu_dm_capabilities HUBBUB structure is not initialized on DCE hardware, so check if it is NULL to avoid null dereference while accessing amdgpu_dm_capabilities file in debugfs.
CVE-2025-39716: In the Linux kernel, the following vulnerability has been resolved: parisc: Revise __get_user() to probe user read access Because of the way read access support is implemented, read access interruptions are only triggered at privilege levels 2 and 3. The kernel executes at privilege level 0, so __get_user() never triggers a read access interruption (code 26). Thus, it is currently possible for user code to access a read protected address via a system call. Fix this by probing read access rights at privilege level 3 (PRIV_USER) and setting __gu_err to -EFAULT (-14) if access isn't allowed. Note the cmpiclr instruction does a 32-bit compare because COND macro doesn't work inside asm.
CVE-2025-39726: In the Linux kernel, the following vulnerability has been resolved: s390/ism: fix concurrency management in ism_cmd() The s390x ISM device data sheet clearly states that only one request-response sequence is allowable per ISM function at any point in time. Unfortunately as of today the s390/ism driver in Linux does not honor that requirement. This patch aims to rectify that. This problem was discovered based on Aliaksei's bug report which states that for certain workloads the ISM functions end up entering error state (with PEC 2 as seen from the logs) after a while and as a consequence connections handled by the respective function break, and for future connection requests the ISM device is not considered -- given it is in a dysfunctional state. During further debugging PEC 3A was observed as well. A kernel message like [ 1211.244319] zpci: 061a:00:00.0: Event 0x2 reports an error for PCI function 0x61a is a reliable indicator of the stated function entering error state with PEC 2. Let me also point out that a kernel message like [ 1211.244325] zpci: 061a:00:00.0: The ism driver bound to the device does not support error recovery is a reliable indicator that the ISM function won't be auto-recovered because the ISM driver currently lacks support for it. On a technical level, without this synchronization, commands (inputs to the FW) may be partially or fully overwritten (corrupted) by another CPU trying to issue commands on the same function. There is hard evidence that this can lead to DMB token values being used as DMB IOVAs, leading to PEC 2 PCI events indicating invalid DMA. But this is only one of the failure modes imaginable. In theory even completely losing one command and executing another one twice and then trying to interpret the outputs as if the command we intended to execute was actually executed and not the other one is also possible. Frankly, I don't feel confident about providing an exhaustive list of possible consequences.
CVE-2025-39732: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix sleeping-in-atomic in ath11k_mac_op_set_bitrate_mask() ath11k_mac_disable_peer_fixed_rate() is passed as the iterator to ieee80211_iterate_stations_atomic(). Note in this case the iterator is required to be atomic, however ath11k_mac_disable_peer_fixed_rate() does not follow it as it might sleep. Consequently below warning is seen: BUG: sleeping function called from invalid context at wmi.c:304 Call Trace: <TASK> dump_stack_lvl __might_resched.cold ath11k_wmi_cmd_send ath11k_wmi_set_peer_param ath11k_mac_disable_peer_fixed_rate ieee80211_iterate_stations_atomic ath11k_mac_op_set_bitrate_mask.cold Change to ieee80211_iterate_stations_mtx() to fix this issue. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
CVE-2025-39744: In the Linux kernel, the following vulnerability has been resolved: rcu: Fix rcu_read_unlock() deadloop due to IRQ work During rcu_read_unlock_special(), if this happens during irq_exit(), we can lockup if an IPI is issued. This is because the IPI itself triggers the irq_exit() path causing a recursive lock up. This is precisely what Xiongfeng found when invoking a BPF program on the trace_tick_stop() tracepoint As shown in the trace below. Fix by managing the irq_work state correctly. irq_exit() __irq_exit_rcu() /* in_hardirq() returns false after this */ preempt_count_sub(HARDIRQ_OFFSET) tick_irq_exit() tick_nohz_irq_exit() tick_nohz_stop_sched_tick() trace_tick_stop() /* a bpf prog is hooked on this trace point */ __bpf_trace_tick_stop() bpf_trace_run2() rcu_read_unlock_special() /* will send a IPI to itself */ irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); A simple reproducer can also be obtained by doing the following in tick_irq_exit(). It will hang on boot without the patch: static inline void tick_irq_exit(void) { + rcu_read_lock(); + WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true); + rcu_read_unlock(); + [neeraj: Apply Frederic's suggested fix for PREEMPT_RT]
CVE-2025-39746: In the Linux kernel, the following vulnerability has been resolved: wifi: ath10k: shutdown driver when hardware is unreliable In rare cases, ath10k may lose connection with the PCIe bus due to some unknown reasons, which could further lead to system crashes during resuming due to watchdog timeout: ath10k_pci 0000:01:00.0: wmi command 20486 timeout, restarting hardware ath10k_pci 0000:01:00.0: already restarting ath10k_pci 0000:01:00.0: failed to stop WMI vdev 0: -11 ath10k_pci 0000:01:00.0: failed to stop vdev 0: -11 ieee80211 phy0: PM: **** DPM device timeout **** Call Trace: panic+0x125/0x315 dpm_watchdog_set+0x54/0x54 dpm_watchdog_handler+0x57/0x57 call_timer_fn+0x31/0x13c At this point, all WMI commands will timeout and attempt to restart device. So set a threshold for consecutive restart failures. If the threshold is exceeded, consider the hardware is unreliable and all ath10k operations should be skipped to avoid system crash. fail_cont_count and pending_recovery are atomic variables, and do not involve complex conditional logic. Therefore, even if recovery check and reconfig complete are executed concurrently, the recovery mechanism will not be broken. Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00288-QCARMSWPZ-1
CVE-2025-39747: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Add error handling for krealloc in metadata setup Function msm_ioctl_gem_info_set_metadata() now checks for krealloc failure and returns -ENOMEM, avoiding potential NULL pointer dereference. Explicitly avoids __GFP_NOFAIL due to deadlock risks and allocation constraints. Patchwork: https://patchwork.freedesktop.org/patch/661235/
CVE-2025-39748: In the Linux kernel, the following vulnerability has been resolved: bpf: Forget ranges when refining tnum after JSET Syzbot reported a kernel warning due to a range invariant violation on the following BPF program. 0: call bpf_get_netns_cookie 1: if r0 == 0 goto <exit> 2: if r0 & Oxffffffff goto <exit> The issue is on the path where we fall through both jumps. That path is unreachable at runtime: after insn 1, we know r0 != 0, but with the sign extension on the jset, we would only fallthrough insn 2 if r0 == 0. Unfortunately, is_branch_taken() isn't currently able to figure this out, so the verifier walks all branches. The verifier then refines the register bounds using the second condition and we end up with inconsistent bounds on this unreachable path: 1: if r0 == 0 goto <exit> r0: u64=[0x1, 0xffffffffffffffff] var_off=(0, 0xffffffffffffffff) 2: if r0 & 0xffffffff goto <exit> r0 before reg_bounds_sync: u64=[0x1, 0xffffffffffffffff] var_off=(0, 0) r0 after reg_bounds_sync: u64=[0x1, 0] var_off=(0, 0) Improving the range refinement for JSET to cover all cases is tricky. We also don't expect many users to rely on JSET given LLVM doesn't generate those instructions. So instead of improving the range refinement for JSETs, Eduard suggested we forget the ranges whenever we're narrowing tnums after a JSET. This patch implements that approach.
CVE-2025-39754: In the Linux kernel, the following vulnerability has been resolved: mm/smaps: fix race between smaps_hugetlb_range and migration smaps_hugetlb_range() handles the pte without holdling ptl, and may be concurrenct with migration, leaing to BUG_ON in pfn_swap_entry_to_page(). The race is as follows. smaps_hugetlb_range migrate_pages huge_ptep_get remove_migration_ptes folio_unlock pfn_swap_entry_folio BUG_ON To fix it, hold ptl lock in smaps_hugetlb_range().
CVE-2025-39759: In the Linux kernel, the following vulnerability has been resolved: btrfs: qgroup: fix race between quota disable and quota rescan ioctl There's a race between a task disabling quotas and another running the rescan ioctl that can result in a use-after-free of qgroup records from the fs_info->qgroup_tree rbtree. This happens as follows: 1) Task A enters btrfs_ioctl_quota_rescan() -> btrfs_qgroup_rescan(); 2) Task B enters btrfs_quota_disable() and calls btrfs_qgroup_wait_for_completion(), which does nothing because at that point fs_info->qgroup_rescan_running is false (it wasn't set yet by task A); 3) Task B calls btrfs_free_qgroup_config() which starts freeing qgroups from fs_info->qgroup_tree without taking the lock fs_info->qgroup_lock; 4) Task A enters qgroup_rescan_zero_tracking() which starts iterating the fs_info->qgroup_tree tree while holding fs_info->qgroup_lock, but task B is freeing qgroup records from that tree without holding the lock, resulting in a use-after-free. Fix this by taking fs_info->qgroup_lock at btrfs_free_qgroup_config(). Also at btrfs_qgroup_rescan() don't start the rescan worker if quotas were already disabled.
CVE-2025-39762: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: add null check [WHY] Prevents null pointer dereferences to enhance function robustness [HOW] Adds early null check and return false if invalid.
CVE-2025-39763: In the Linux kernel, the following vulnerability has been resolved: ACPI: APEI: send SIGBUS to current task if synchronous memory error not recovered If a synchronous error is detected as a result of user-space process triggering a 2-bit uncorrected error, the CPU will take a synchronous error exception such as Synchronous External Abort (SEA) on Arm64. The kernel will queue a memory_failure() work which poisons the related page, unmaps the page, and then sends a SIGBUS to the process, so that a system wide panic can be avoided. However, no memory_failure() work will be queued when abnormal synchronous errors occur. These errors can include situations like invalid PA, unexpected severity, no memory failure config support, invalid GUID section, etc. In such a case, the user-space process will trigger SEA again. This loop can potentially exceed the platform firmware threshold or even trigger a kernel hard lockup, leading to a system reboot. Fix it by performing a force kill if no memory_failure() work is queued for synchronous errors. [ rjw: Changelog edits ]
CVE-2025-39764: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: remove refcounting in expectation dumpers Same pattern as previous patch: do not keep the expectation object alive via refcount, only store a cookie value and then use that as the skip hint for dump resumption. AFAICS this has the same issue as the one resolved in the conntrack dumper, when we do if (!refcount_inc_not_zero(&exp->use)) to increment the refcount, there is a chance that exp == last, which causes a double-increment of the refcount and subsequent memory leak.
CVE-2025-39770: In the Linux kernel, the following vulnerability has been resolved: net: gso: Forbid IPv6 TSO with extensions on devices with only IPV6_CSUM When performing Generic Segmentation Offload (GSO) on an IPv6 packet that contains extension headers, the kernel incorrectly requests checksum offload if the egress device only advertises NETIF_F_IPV6_CSUM feature, which has a strict contract: it supports checksum offload only for plain TCP or UDP over IPv6 and explicitly does not support packets with extension headers. The current GSO logic violates this contract by failing to disable the feature for packets with extension headers, such as those used in GREoIPv6 tunnels. This violation results in the device being asked to perform an operation it cannot support, leading to a `skb_warn_bad_offload` warning and a collapse of network throughput. While device TSO/USO is correctly bypassed in favor of software GSO for these packets, the GSO stack must be explicitly told not to request checksum offload. Mask NETIF_F_IPV6_CSUM, NETIF_F_TSO6 and NETIF_F_GSO_UDP_L4 in gso_features_check if the IPv6 header contains extension headers to compute checksum in software. The exception is a BIG TCP extension, which, as stated in commit 68e068cabd2c6c53 ("net: reenable NETIF_F_IPV6_CSUM offload for BIG TCP packets"): "The feature is only enabled on devices that support BIG TCP TSO. The header is only present for PF_PACKET taps like tcpdump, and not transmitted by physical devices." kernel log output (truncated): WARNING: CPU: 1 PID: 5273 at net/core/dev.c:3535 skb_warn_bad_offload+0x81/0x140 ... Call Trace: <TASK> skb_checksum_help+0x12a/0x1f0 validate_xmit_skb+0x1a3/0x2d0 validate_xmit_skb_list+0x4f/0x80 sch_direct_xmit+0x1a2/0x380 __dev_xmit_skb+0x242/0x670 __dev_queue_xmit+0x3fc/0x7f0 ip6_finish_output2+0x25e/0x5d0 ip6_finish_output+0x1fc/0x3f0 ip6_tnl_xmit+0x608/0xc00 [ip6_tunnel] ip6gre_tunnel_xmit+0x1c0/0x390 [ip6_gre] dev_hard_start_xmit+0x63/0x1c0 __dev_queue_xmit+0x6d0/0x7f0 ip6_finish_output2+0x214/0x5d0 ip6_finish_output+0x1fc/0x3f0 ip6_xmit+0x2ca/0x6f0 ip6_finish_output+0x1fc/0x3f0 ip6_xmit+0x2ca/0x6f0 inet6_csk_xmit+0xeb/0x150 __tcp_transmit_skb+0x555/0xa80 tcp_write_xmit+0x32a/0xe90 tcp_sendmsg_locked+0x437/0x1110 tcp_sendmsg+0x2f/0x50 ... skb linear: 00000000: e4 3d 1a 7d ec 30 e4 3d 1a 7e 5d 90 86 dd 60 0e skb linear: 00000010: 00 0a 1b 34 3c 40 20 11 00 00 00 00 00 00 00 00 skb linear: 00000020: 00 00 00 00 00 12 20 11 00 00 00 00 00 00 00 00 skb linear: 00000030: 00 00 00 00 00 11 2f 00 04 01 04 01 01 00 00 00 skb linear: 00000040: 86 dd 60 0e 00 0a 1b 00 06 40 20 23 00 00 00 00 skb linear: 00000050: 00 00 00 00 00 00 00 00 00 12 20 23 00 00 00 00 skb linear: 00000060: 00 00 00 00 00 00 00 00 00 11 bf 96 14 51 13 f9 skb linear: 00000070: ae 27 a0 a8 2b e3 80 18 00 40 5b 6f 00 00 01 01 skb linear: 00000080: 08 0a 42 d4 50 d5 4b 70 f8 1a
CVE-2025-39772: In the Linux kernel, the following vulnerability has been resolved: drm/hisilicon/hibmc: fix the hibmc loaded failed bug When hibmc loaded failed, the driver use hibmc_unload to free the resource, but the mutexes in mode.config are not init, which will access an NULL pointer. Just change goto statement to return, because hibnc_hw_init() doesn't need to free anything.
CVE-2025-39773: In the Linux kernel, the following vulnerability has been resolved: net: bridge: fix soft lockup in br_multicast_query_expired() When set multicast_query_interval to a large value, the local variable 'time' in br_multicast_send_query() may overflow. If the time is smaller than jiffies, the timer will expire immediately, and then call mod_timer() again, which creates a loop and may trigger the following soft lockup issue. watchdog: BUG: soft lockup - CPU#1 stuck for 221s! [rb_consumer:66] CPU: 1 UID: 0 PID: 66 Comm: rb_consumer Not tainted 6.16.0+ #259 PREEMPT(none) Call Trace: <IRQ> __netdev_alloc_skb+0x2e/0x3a0 br_ip6_multicast_alloc_query+0x212/0x1b70 __br_multicast_send_query+0x376/0xac0 br_multicast_send_query+0x299/0x510 br_multicast_query_expired.constprop.0+0x16d/0x1b0 call_timer_fn+0x3b/0x2a0 __run_timers+0x619/0x950 run_timer_softirq+0x11c/0x220 handle_softirqs+0x18e/0x560 __irq_exit_rcu+0x158/0x1a0 sysvec_apic_timer_interrupt+0x76/0x90 </IRQ> This issue can be reproduced with: ip link add br0 type bridge echo 1 > /sys/class/net/br0/bridge/multicast_querier echo 0xffffffffffffffff > /sys/class/net/br0/bridge/multicast_query_interval ip link set dev br0 up The multicast_startup_query_interval can also cause this issue. Similar to the commit 99b40610956a ("net: bridge: mcast: add and enforce query interval minimum"), add check for the query interval maximum to fix this issue.
CVE-2025-39789: In the Linux kernel, the following vulnerability has been resolved: crypto: x86/aegis - Add missing error checks The skcipher_walk functions can allocate memory and can fail, so checking for errors is necessary.
CVE-2025-39790: In the Linux kernel, the following vulnerability has been resolved: bus: mhi: host: Detect events pointing to unexpected TREs When a remote device sends a completion event to the host, it contains a pointer to the consumed TRE. The host uses this pointer to process all of the TREs between it and the host's local copy of the ring's read pointer. This works when processing completion for chained transactions, but can lead to nasty results if the device sends an event for a single-element transaction with a read pointer that is multiple elements ahead of the host's read pointer. For instance, if the host accesses an event ring while the device is updating it, the pointer inside of the event might still point to an old TRE. If the host uses the channel's xfer_cb() to directly free the buffer pointed to by the TRE, the buffer will be double-freed. This behavior was observed on an ep that used upstream EP stack without 'commit 6f18d174b73d ("bus: mhi: ep: Update read pointer only after buffer is written")'. Where the device updated the events ring pointer before updating the event contents, so it left a window where the host was able to access the stale data the event pointed to, before the device had the chance to update them. The usual pattern was that the host received an event pointing to a TRE that is not immediately after the last processed one, so it got treated as if it was a chained transaction, processing all of the TREs in between the two read pointers. This commit aims to harden the host by ensuring transactions where the event points to a TRE that isn't local_rp + 1 are chained. [mani: added stable tag and reworded commit message]
CVE-2025-39797: In the Linux kernel, the following vulnerability has been resolved: xfrm: Duplicate SPI Handling The issue originates when Strongswan initiates an XFRM_MSG_ALLOCSPI Netlink message, which triggers the kernel function xfrm_alloc_spi(). This function is expected to ensure uniqueness of the Security Parameter Index (SPI) for inbound Security Associations (SAs). However, it can return success even when the requested SPI is already in use, leading to duplicate SPIs assigned to multiple inbound SAs, differentiated only by their destination addresses. This behavior causes inconsistencies during SPI lookups for inbound packets. Since the lookup may return an arbitrary SA among those with the same SPI, packet processing can fail, resulting in packet drops. According to RFC 4301 section 4.4.2 , for inbound processing a unicast SA is uniquely identified by the SPI and optionally protocol. Reproducing the Issue Reliably: To consistently reproduce the problem, restrict the available SPI range in charon.conf : spi_min = 0x10000000 spi_max = 0x10000002 This limits the system to only 2 usable SPI values. Next, create more than 2 Child SA. each using unique pair of src/dst address. As soon as the 3rd Child SA is initiated, it will be assigned a duplicate SPI, since the SPI pool is already exhausted. With a narrow SPI range, the issue is consistently reproducible. With a broader/default range, it becomes rare and unpredictable. Current implementation: xfrm_spi_hash() lookup function computes hash using daddr, proto, and family. So if two SAs have the same SPI but different destination addresses, then they will: a. Hash into different buckets b. Be stored in different linked lists (byspi + h) c. Not be seen in the same hlist_for_each_entry_rcu() iteration. As a result, the lookup will result in NULL and kernel allows that Duplicate SPI Proposed Change: xfrm_state_lookup_spi_proto() does a truly global search - across all states, regardless of hash bucket and matches SPI and proto.
CVE-2025-39800: In the Linux kernel, the following vulnerability has been resolved: btrfs: abort transaction on unexpected eb generation at btrfs_copy_root() If we find an unexpected generation for the extent buffer we are cloning at btrfs_copy_root(), we just WARN_ON() and don't error out and abort the transaction, meaning we allow to persist metadata with an unexpected generation. Instead of warning only, abort the transaction and return -EUCLEAN.
CVE-2025-39801: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: Remove WARN_ON for device endpoint command timeouts This commit addresses a rarely observed endpoint command timeout which causes kernel panic due to warn when 'panic_on_warn' is enabled and unnecessary call trace prints when 'panic_on_warn' is disabled. It is seen during fast software-controlled connect/disconnect testcases. The following is one such endpoint command timeout that we observed: 1. Connect ======= ->dwc3_thread_interrupt ->dwc3_ep0_interrupt ->configfs_composite_setup ->composite_setup ->usb_ep_queue ->dwc3_gadget_ep0_queue ->__dwc3_gadget_ep0_queue ->__dwc3_ep0_do_control_data ->dwc3_send_gadget_ep_cmd 2. Disconnect ========== ->dwc3_thread_interrupt ->dwc3_gadget_disconnect_interrupt ->dwc3_ep0_reset_state ->dwc3_ep0_end_control_data ->dwc3_send_gadget_ep_cmd In the issue scenario, in Exynos platforms, we observed that control transfers for the previous connect have not yet been completed and end transfer command sent as a part of the disconnect sequence and processing of USB_ENDPOINT_HALT feature request from the host timeout. This maybe an expected scenario since the controller is processing EP commands sent as a part of the previous connect. It maybe better to remove WARN_ON in all places where device endpoint commands are sent to avoid unnecessary kernel panic due to warn.
CVE-2025-39810: In the Linux kernel, the following vulnerability has been resolved: bnxt_en: Fix memory corruption when FW resources change during ifdown bnxt_set_dflt_rings() assumes that it is always called before any TC has been created. So it doesn't take bp->num_tc into account and assumes that it is always 0 or 1. In the FW resource or capability change scenario, the FW will return flags in bnxt_hwrm_if_change() that will cause the driver to reinitialize and call bnxt_cancel_reservations(). This will lead to bnxt_init_dflt_ring_mode() calling bnxt_set_dflt_rings() and bp->num_tc may be greater than 1. This will cause bp->tx_ring[] to be sized too small and cause memory corruption in bnxt_alloc_cp_rings(). Fix it by properly scaling the TX rings by bp->num_tc in the code paths mentioned above. Add 2 helper functions to determine bp->tx_nr_rings and bp->tx_nr_rings_per_tc.
CVE-2025-39819: In the Linux kernel, the following vulnerability has been resolved: fs/smb: Fix inconsistent refcnt update A possible inconsistent update of refcount was identified in `smb2_compound_op`. Such inconsistent update could lead to possible resource leaks. Why it is a possible bug: 1. In the comment section of the function, it clearly states that the reference to `cfile` should be dropped after calling this function. 2. Every control flow path would check and drop the reference to `cfile`, except the patched one. 3. Existing callers would not handle refcount update of `cfile` if -ENOMEM is returned. To fix the bug, an extra goto label "out" is added, to make sure that the cleanup logic would always be respected. As the problem is caused by the allocation failure of `vars`, the cleanup logic between label "finished" and "out" can be safely ignored. According to the definition of function `is_replayable_error`, the error code of "-ENOMEM" is not recoverable. Therefore, the replay logic also gets ignored.
CVE-2025-39826: In the Linux kernel, the following vulnerability has been resolved: net: rose: convert 'use' field to refcount_t The 'use' field in struct rose_neigh is used as a reference counter but lacks atomicity. This can lead to race conditions where a rose_neigh structure is freed while still being referenced by other code paths. For example, when rose_neigh->use becomes zero during an ioctl operation via rose_rt_ioctl(), the structure may be removed while its timer is still active, potentially causing use-after-free issues. This patch changes the type of 'use' from unsigned short to refcount_t and updates all code paths to use rose_neigh_hold() and rose_neigh_put() which operate reference counts atomically.
CVE-2025-39827: In the Linux kernel, the following vulnerability has been resolved: net: rose: include node references in rose_neigh refcount Current implementation maintains two separate reference counting mechanisms: the 'count' field in struct rose_neigh tracks references from rose_node structures, while the 'use' field (now refcount_t) tracks references from rose_sock. This patch merges these two reference counting systems using 'use' field for proper reference management. Specifically, this patch adds incrementing and decrementing of rose_neigh->use when rose_neigh->count is incremented or decremented. This patch also modifies rose_rt_free(), rose_rt_device_down() and rose_clear_route() to properly release references to rose_neigh objects before freeing a rose_node through rose_remove_node(). These changes ensure rose_neigh structures are properly freed only when all references, including those from rose_node structures, are released. As a result, this resolves a slab-use-after-free issue reported by Syzbot.
CVE-2025-39829: In the Linux kernel, the following vulnerability has been resolved: trace/fgraph: Fix the warning caused by missing unregister notifier This warning was triggered during testing on v6.16: notifier callback ftrace_suspend_notifier_call already registered WARNING: CPU: 2 PID: 86 at kernel/notifier.c:23 notifier_chain_register+0x44/0xb0 ... Call Trace: <TASK> blocking_notifier_chain_register+0x34/0x60 register_ftrace_graph+0x330/0x410 ftrace_profile_write+0x1e9/0x340 vfs_write+0xf8/0x420 ? filp_flush+0x8a/0xa0 ? filp_close+0x1f/0x30 ? do_dup2+0xaf/0x160 ksys_write+0x65/0xe0 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x77/0x7f When writing to the function_profile_enabled interface, the notifier was not unregistered after start_graph_tracing failed, causing a warning the next time function_profile_enabled was written. Fixed by adding unregister_pm_notifier in the exception path.
CVE-2025-39833: In the Linux kernel, the following vulnerability has been resolved: mISDN: hfcpci: Fix warning when deleting uninitialized timer With CONFIG_DEBUG_OBJECTS_TIMERS unloading hfcpci module leads to the following splat: [ 250.215892] ODEBUG: assert_init not available (active state 0) object: ffffffffc01a3dc0 object type: timer_list hint: 0x0 [ 250.217520] WARNING: CPU: 0 PID: 233 at lib/debugobjects.c:612 debug_print_object+0x1b6/0x2c0 [ 250.218775] Modules linked in: hfcpci(-) mISDN_core [ 250.219537] CPU: 0 UID: 0 PID: 233 Comm: rmmod Not tainted 6.17.0-rc2-g6f713187ac98 #2 PREEMPT(voluntary) [ 250.220940] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 250.222377] RIP: 0010:debug_print_object+0x1b6/0x2c0 [ 250.223131] Code: fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 4f 41 56 48 8b 14 dd a0 4e 01 9f 48 89 ee 48 c7 c7 20 46 01 9f e8 cb 84d [ 250.225805] RSP: 0018:ffff888015ea7c08 EFLAGS: 00010286 [ 250.226608] RAX: 0000000000000000 RBX: 0000000000000005 RCX: ffffffff9be93a95 [ 250.227708] RDX: 1ffff1100d945138 RSI: 0000000000000008 RDI: ffff88806ca289c0 [ 250.228993] RBP: ffffffff9f014a00 R08: 0000000000000001 R09: ffffed1002bd4f39 [ 250.230043] R10: ffff888015ea79cf R11: 0000000000000001 R12: 0000000000000001 [ 250.231185] R13: ffffffff9eea0520 R14: 0000000000000000 R15: ffff888015ea7cc8 [ 250.232454] FS: 00007f3208f01540(0000) GS:ffff8880caf5a000(0000) knlGS:0000000000000000 [ 250.233851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 250.234856] CR2: 00007f32090a7421 CR3: 0000000004d63000 CR4: 00000000000006f0 [ 250.236117] Call Trace: [ 250.236599] <TASK> [ 250.236967] ? trace_irq_enable.constprop.0+0xd4/0x130 [ 250.237920] debug_object_assert_init+0x1f6/0x310 [ 250.238762] ? __pfx_debug_object_assert_init+0x10/0x10 [ 250.239658] ? __lock_acquire+0xdea/0x1c70 [ 250.240369] __try_to_del_timer_sync+0x69/0x140 [ 250.241172] ? __pfx___try_to_del_timer_sync+0x10/0x10 [ 250.242058] ? __timer_delete_sync+0xc6/0x120 [ 250.242842] ? lock_acquire+0x30/0x80 [ 250.243474] ? __timer_delete_sync+0xc6/0x120 [ 250.244262] __timer_delete_sync+0x98/0x120 [ 250.245015] HFC_cleanup+0x10/0x20 [hfcpci] [ 250.245704] __do_sys_delete_module+0x348/0x510 [ 250.246461] ? __pfx___do_sys_delete_module+0x10/0x10 [ 250.247338] do_syscall_64+0xc1/0x360 [ 250.247924] entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by initializing hfc_tl timer with DEFINE_TIMER macro. Also, use mod_timer instead of manual timeout update.
CVE-2025-39850: In the Linux kernel, the following vulnerability has been resolved: vxlan: Fix NPD in {arp,neigh}_reduce() when using nexthop objects When the "proxy" option is enabled on a VXLAN device, the device will suppress ARP requests and IPv6 Neighbor Solicitation messages if it is able to reply on behalf of the remote host. That is, if a matching and valid neighbor entry is configured on the VXLAN device whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The code currently assumes that the FDB entry for the neighbor's MAC address points to a valid remote destination, but this is incorrect if the entry is associated with an FDB nexthop group. This can result in a NPD [1][3] which can be reproduced using [2][4]. Fix by checking that the remote destination exists before dereferencing it. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 4 UID: 0 PID: 365 Comm: arping Not tainted 6.17.0-rc2-virtme-g2a89cb21162c #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014 RIP: 0010:vxlan_xmit+0xb58/0x15f0 [...] Call Trace: <TASK> dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 packet_sendmsg+0x113a/0x1850 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [2] #!/bin/bash ip address add 192.0.2.1/32 dev lo ip nexthop add id 1 via 192.0.2.2 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 4789 proxy ip neigh add 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm dev vx0 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10 arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3 [3] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 13 UID: 0 PID: 372 Comm: ndisc6 Not tainted 6.17.0-rc2-virtmne-g6ee90cb26014 #3 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1v996), BIOS 1.17.0-4.fc41 04/01/2x014 RIP: 0010:vxlan_xmit+0x803/0x1600 [...] Call Trace: <TASK> dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 ip6_finish_output2+0x210/0x6c0 ip6_finish_output+0x1af/0x2b0 ip6_mr_output+0x92/0x3e0 ip6_send_skb+0x30/0x90 rawv6_sendmsg+0xe6e/0x12e0 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7f383422ec77 [4] #!/bin/bash ip address add 2001:db8:1::1/128 dev lo ip nexthop add id 1 via 2001:db8:1::1 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 2001:db8:1::1 dstport 4789 proxy ip neigh add 2001:db8:1::3 lladdr 00:11:22:33:44:55 nud perm dev vx0 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10 ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0
CVE-2025-39851: In the Linux kernel, the following vulnerability has been resolved: vxlan: Fix NPD when refreshing an FDB entry with a nexthop object VXLAN FDB entries can point to either a remote destination or an FDB nexthop group. The latter is usually used in EVPN deployments where learning is disabled. However, when learning is enabled, an incoming packet might try to refresh an FDB entry that points to an FDB nexthop group and therefore does not have a remote. Such packets should be dropped, but they are only dropped after dereferencing the non-existent remote, resulting in a NPD [1] which can be reproduced using [2]. Fix by dropping such packets earlier. Remove the misleading comment from first_remote_rcu(). [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 13 UID: 0 PID: 361 Comm: mausezahn Not tainted 6.17.0-rc1-virtme-g9f6b606b6b37 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014 RIP: 0010:vxlan_snoop+0x98/0x1e0 [...] Call Trace: <TASK> vxlan_encap_bypass+0x209/0x240 encap_bypass_if_local+0xb1/0x100 vxlan_xmit_one+0x1375/0x17e0 vxlan_xmit+0x6b4/0x15f0 dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 packet_sendmsg+0x113a/0x1850 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [2] #!/bin/bash ip address add 192.0.2.1/32 dev lo ip address add 192.0.2.2/32 dev lo ip nexthop add id 1 via 192.0.2.3 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass ip link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning bridge fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020 bridge fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q
CVE-2025-39863: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmfmac: fix use-after-free when rescheduling brcmf_btcoex_info work The brcmf_btcoex_detach() only shuts down the btcoex timer, if the flag timer_on is false. However, the brcmf_btcoex_timerfunc(), which runs as timer handler, sets timer_on to false. This creates critical race conditions: 1.If brcmf_btcoex_detach() is called while brcmf_btcoex_timerfunc() is executing, it may observe timer_on as false and skip the call to timer_shutdown_sync(). 2.The brcmf_btcoex_timerfunc() may then reschedule the brcmf_btcoex_info worker after the cancel_work_sync() has been executed, resulting in use-after-free bugs. The use-after-free bugs occur in two distinct scenarios, depending on the timing of when the brcmf_btcoex_info struct is freed relative to the execution of its worker thread. Scenario 1: Freed before the worker is scheduled The brcmf_btcoex_info is deallocated before the worker is scheduled. A race condition can occur when schedule_work(&bt_local->work) is called after the target memory has been freed. The sequence of events is detailed below: CPU0 | CPU1 brcmf_btcoex_detach | brcmf_btcoex_timerfunc | bt_local->timer_on = false; if (cfg->btcoex->timer_on) | ... | cancel_work_sync(); | ... | kfree(cfg->btcoex); // FREE | | schedule_work(&bt_local->work); // USE Scenario 2: Freed after the worker is scheduled The brcmf_btcoex_info is freed after the worker has been scheduled but before or during its execution. In this case, statements within the brcmf_btcoex_handler() — such as the container_of macro and subsequent dereferences of the brcmf_btcoex_info object will cause a use-after-free access. The following timeline illustrates this scenario: CPU0 | CPU1 brcmf_btcoex_detach | brcmf_btcoex_timerfunc | bt_local->timer_on = false; if (cfg->btcoex->timer_on) | ... | cancel_work_sync(); | ... | schedule_work(); // Reschedule | kfree(cfg->btcoex); // FREE | brcmf_btcoex_handler() // Worker /* | btci = container_of(....); // USE The kfree() above could | ... also occur at any point | btci-> // USE during the worker's execution| */ | To resolve the race conditions, drop the conditional check and call timer_shutdown_sync() directly. It can deactivate the timer reliably, regardless of its current state. Once stopped, the timer_on state is then set to false.
CVE-2025-39873: In the Linux kernel, the following vulnerability has been resolved: can: xilinx_can: xcan_write_frame(): fix use-after-free of transmitted SKB can_put_echo_skb() takes ownership of the SKB and it may be freed during or after the call. However, xilinx_can xcan_write_frame() keeps using SKB after the call. Fix that by only calling can_put_echo_skb() after the code is done touching the SKB. The tx_lock is held for the entire xcan_write_frame() execution and also on the can_get_echo_skb() side so the order of operations does not matter. An earlier fix commit 3d3c817c3a40 ("can: xilinx_can: Fix usage of skb memory") did not move the can_put_echo_skb() call far enough. [mkl: add "commit" in front of sha1 in patch description] [mkl: fix indention]
CVE-2025-39901: In the Linux kernel, the following vulnerability has been resolved: i40e: remove read access to debugfs files The 'command' and 'netdev_ops' debugfs files are a legacy debugging interface supported by the i40e driver since its early days by commit 02e9c290814c ("i40e: debugfs interface"). Both of these debugfs files provide a read handler which is mostly useless, and which is implemented with questionable logic. They both use a static 256 byte buffer which is initialized to the empty string. In the case of the 'command' file this buffer is literally never used and simply wastes space. In the case of the 'netdev_ops' file, the last command written is saved here. On read, the files contents are presented as the name of the device followed by a colon and then the contents of their respective static buffer. For 'command' this will always be "<device>: ". For 'netdev_ops', this will be "<device>: <last command written>". But note the buffer is shared between all devices operated by this module. At best, it is mostly meaningless information, and at worse it could be accessed simultaneously as there doesn't appear to be any locking mechanism. We have also recently received multiple reports for both read functions about their use of snprintf and potential overflow that could result in reading arbitrary kernel memory. For the 'command' file, this is definitely impossible, since the static buffer is always zero and never written to. For the 'netdev_ops' file, it does appear to be possible, if the user carefully crafts the command input, it will be copied into the buffer, which could be large enough to cause snprintf to truncate, which then causes the copy_to_user to read beyond the length of the buffer allocated by kzalloc. A minimal fix would be to replace snprintf() with scnprintf() which would cap the return to the number of bytes written, preventing an overflow. A more involved fix would be to drop the mostly useless static buffers, saving 512 bytes and modifying the read functions to stop needing those as input. Instead, lets just completely drop the read access to these files. These are debug interfaces exposed as part of debugfs, and I don't believe that dropping read access will break any script, as the provided output is pretty useless. You can find the netdev name through other more standard interfaces, and the 'netdev_ops' interface can easily result in garbage if you issue simultaneous writes to multiple devices at once. In order to properly remove the i40e_dbg_netdev_ops_buf, we need to refactor its write function to avoid using the static buffer. Instead, use the same logic as the i40e_dbg_command_write, with an allocated buffer. Update the code to use this instead of the static buffer, and ensure we free the buffer on exit. This fixes simultaneous writes to 'netdev_ops' on multiple devices, and allows us to remove the now unused static buffer along with removing the read access.
CVE-2025-39925: In the Linux kernel, the following vulnerability has been resolved: can: j1939: implement NETDEV_UNREGISTER notification handler syzbot is reporting unregister_netdevice: waiting for vcan0 to become free. Usage count = 2 problem, for j1939 protocol did not have NETDEV_UNREGISTER notification handler for undoing changes made by j1939_sk_bind(). Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") expects that a call to j1939_priv_put() can be unconditionally delayed until j1939_sk_sock_destruct() is called. But we need to call j1939_priv_put() against an extra ref held by j1939_sk_bind() call (as a part of undoing changes made by j1939_sk_bind()) as soon as NETDEV_UNREGISTER notification fires (i.e. before j1939_sk_sock_destruct() is called via j1939_sk_release()). Otherwise, the extra ref on "struct j1939_priv" held by j1939_sk_bind() call prevents "struct net_device" from dropping the usage count to 1; making it impossible for unregister_netdevice() to continue. [mkl: remove space in front of label]
CVE-2025-39927: In the Linux kernel, the following vulnerability has been resolved: ceph: fix race condition validating r_parent before applying state Add validation to ensure the cached parent directory inode matches the directory info in MDS replies. This prevents client-side race conditions where concurrent operations (e.g. rename) cause r_parent to become stale between request initiation and reply processing, which could lead to applying state changes to incorrect directory inodes. [ idryomov: folded a kerneldoc fixup and a follow-up fix from Alex to move CEPH_CAP_PIN reference when r_parent is updated: When the parent directory lock is not held, req->r_parent can become stale and is updated to point to the correct inode. However, the associated CEPH_CAP_PIN reference was not being adjusted. The CEPH_CAP_PIN is a reference on an inode that is tracked for accounting purposes. Moving this pin is important to keep the accounting balanced. When the pin was not moved from the old parent to the new one, it created two problems: The reference on the old, stale parent was never released, causing a reference leak. A reference for the new parent was never acquired, creating the risk of a reference underflow later in ceph_mdsc_release_request(). This patch corrects the logic by releasing the pin from the old parent and acquiring it for the new parent when r_parent is switched. This ensures reference accounting stays balanced. ]
CVE-2025-39929: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix smbdirect_recv_io leak in smbd_negotiate() error path During tests of another unrelated patch I was able to trigger this error: Objects remaining on __kmem_cache_shutdown()
CVE-2025-39931: In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - Set merge to zero early in af_alg_sendmsg If an error causes af_alg_sendmsg to abort, ctx->merge may contain a garbage value from the previous loop. This may then trigger a crash on the next entry into af_alg_sendmsg when it attempts to do a merge that can't be done. Fix this by setting ctx->merge to zero near the start of the loop.
CVE-2025-39932: In the Linux kernel, the following vulnerability has been resolved: smb: client: let smbd_destroy() call disable_work_sync(&info->post_send_credits_work) In smbd_destroy() we may destroy the memory so we better wait until post_send_credits_work is no longer pending and will never be started again. I actually just hit the case using rxe: WARNING: CPU: 0 PID: 138 at drivers/infiniband/sw/rxe/rxe_verbs.c:1032 rxe_post_recv+0x1ee/0x480 [rdma_rxe] ... [ 5305.686979] [ T138] smbd_post_recv+0x445/0xc10 [cifs] [ 5305.687135] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687149] [ T138] ? __kasan_check_write+0x14/0x30 [ 5305.687185] [ T138] ? __pfx_smbd_post_recv+0x10/0x10 [cifs] [ 5305.687329] [ T138] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 5305.687356] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687368] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687378] [ T138] ? _raw_spin_unlock_irqrestore+0x11/0x60 [ 5305.687389] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687399] [ T138] ? get_receive_buffer+0x168/0x210 [cifs] [ 5305.687555] [ T138] smbd_post_send_credits+0x382/0x4b0 [cifs] [ 5305.687701] [ T138] ? __pfx_smbd_post_send_credits+0x10/0x10 [cifs] [ 5305.687855] [ T138] ? __pfx___schedule+0x10/0x10 [ 5305.687865] [ T138] ? __pfx__raw_spin_lock_irq+0x10/0x10 [ 5305.687875] [ T138] ? queue_delayed_work_on+0x8e/0xa0 [ 5305.687889] [ T138] process_one_work+0x629/0xf80 [ 5305.687908] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687917] [ T138] ? __kasan_check_write+0x14/0x30 [ 5305.687933] [ T138] worker_thread+0x87f/0x1570 ... It means rxe_post_recv was called after rdma_destroy_qp(). This happened because put_receive_buffer() was triggered by ib_drain_qp() and called: queue_work(info->workqueue, &info->post_send_credits_work);
CVE-2025-39933: In the Linux kernel, the following vulnerability has been resolved: smb: client: let recv_done verify data_offset, data_length and remaining_data_length This is inspired by the related server fixes.
CVE-2025-39940: In the Linux kernel, the following vulnerability has been resolved: dm-stripe: fix a possible integer overflow There's a possible integer overflow in stripe_io_hints if we have too large chunk size. Test if the overflow happened, and if it did, don't set limits->io_min and limits->io_opt;
CVE-2025-39952: In the Linux kernel, the following vulnerability has been resolved: wifi: wilc1000: avoid buffer overflow in WID string configuration Fix the following copy overflow warning identified by Smatch checker. drivers/net/wireless/microchip/wilc1000/wlan_cfg.c:184 wilc_wlan_parse_response_frame() error: '__memcpy()' 'cfg->s[i]->str' copy overflow (512 vs 65537) This patch introduces size check before accessing the memory buffer. The checks are base on the WID type of received data from the firmware. For WID string configuration, the size limit is determined by individual element size in 'struct wilc_cfg_str_vals' that is maintained in 'len' field of 'struct wilc_cfg_str'.
CVE-2025-39961: In the Linux kernel, the following vulnerability has been resolved: iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path.
CVE-2025-39990: In the Linux kernel, the following vulnerability has been resolved: bpf: Check the helper function is valid in get_helper_proto kernel test robot reported verifier bug [1] where the helper func pointer could be NULL due to disabled config option. As Alexei suggested we could check on that in get_helper_proto directly. Marking tail_call helper func with BPF_PTR_POISON, because it is unused by design. [1] https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com
CVE-2025-40003: In the Linux kernel, the following vulnerability has been resolved: net: mscc: ocelot: Fix use-after-free caused by cyclic delayed work The origin code calls cancel_delayed_work() in ocelot_stats_deinit() to cancel the cyclic delayed work item ocelot->stats_work. However, cancel_delayed_work() may fail to cancel the work item if it is already executing. While destroy_workqueue() does wait for all pending work items in the work queue to complete before destroying the work queue, it cannot prevent the delayed work item from being rescheduled within the ocelot_check_stats_work() function. This limitation exists because the delayed work item is only enqueued into the work queue after its timer expires. Before the timer expiration, destroy_workqueue() has no visibility of this pending work item. Once the work queue appears empty, destroy_workqueue() proceeds with destruction. When the timer eventually expires, the delayed work item gets queued again, leading to the following warning: workqueue: cannot queue ocelot_check_stats_work on wq ocelot-switch-stats WARNING: CPU: 2 PID: 0 at kernel/workqueue.c:2255 __queue_work+0x875/0xaf0 ... RIP: 0010:__queue_work+0x875/0xaf0 ... RSP: 0018:ffff88806d108b10 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 0000000000000101 RCX: 0000000000000027 RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffff88806d123e88 RBP: ffffffff813c3170 R08: 0000000000000000 R09: ffffed100da247d2 R10: ffffed100da247d1 R11: ffff88806d123e8b R12: ffff88800c00f000 R13: ffff88800d7285c0 R14: ffff88806d0a5580 R15: ffff88800d7285a0 FS: 0000000000000000(0000) GS:ffff8880e5725000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe18e45ea10 CR3: 0000000005e6c000 CR4: 00000000000006f0 Call Trace: <IRQ> ? kasan_report+0xc6/0xf0 ? __pfx_delayed_work_timer_fn+0x10/0x10 ? __pfx_delayed_work_timer_fn+0x10/0x10 call_timer_fn+0x25/0x1c0 __run_timer_base.part.0+0x3be/0x8c0 ? __pfx_delayed_work_timer_fn+0x10/0x10 ? rcu_sched_clock_irq+0xb06/0x27d0 ? __pfx___run_timer_base.part.0+0x10/0x10 ? try_to_wake_up+0xb15/0x1960 ? _raw_spin_lock_irq+0x80/0xe0 ? __pfx__raw_spin_lock_irq+0x10/0x10 tmigr_handle_remote_up+0x603/0x7e0 ? __pfx_tmigr_handle_remote_up+0x10/0x10 ? sched_balance_trigger+0x1c0/0x9f0 ? sched_tick+0x221/0x5a0 ? _raw_spin_lock_irq+0x80/0xe0 ? __pfx__raw_spin_lock_irq+0x10/0x10 ? tick_nohz_handler+0x339/0x440 ? __pfx_tmigr_handle_remote_up+0x10/0x10 __walk_groups.isra.0+0x42/0x150 tmigr_handle_remote+0x1f4/0x2e0 ? __pfx_tmigr_handle_remote+0x10/0x10 ? ktime_get+0x60/0x140 ? lapic_next_event+0x11/0x20 ? clockevents_program_event+0x1d4/0x2a0 ? hrtimer_interrupt+0x322/0x780 handle_softirqs+0x16a/0x550 irq_exit_rcu+0xaf/0xe0 sysvec_apic_timer_interrupt+0x70/0x80 </IRQ> ... The following diagram reveals the cause of the above warning: CPU 0 (remove) | CPU 1 (delayed work callback) mscc_ocelot_remove() | ocelot_deinit() | ocelot_check_stats_work() ocelot_stats_deinit() | cancel_delayed_work()| ... | queue_delayed_work() destroy_workqueue() | (wait a time) | __queue_work() //UAF The above scenario actually constitutes a UAF vulnerability. The ocelot_stats_deinit() is only invoked when initialization failure or resource destruction, so we must ensure that any delayed work items cannot be rescheduled. Replace cancel_delayed_work() with disable_delayed_work_sync() to guarantee proper cancellation of the delayed work item and ensure completion of any currently executing work before the workqueue is deallocated. A deadlock concern was considered: ocelot_stats_deinit() is called in a process context and is not holding any locks that the delayed work item might also need. Therefore, the use of the _sync() variant is safe here. This bug was identified through static analysis. To reproduce the issue and validate the fix, I simulated ocelot-swit ---truncated---
CVE-2025-40005: In the Linux kernel, the following vulnerability has been resolved: spi: cadence-quadspi: Implement refcount to handle unbind during busy driver support indirect read and indirect write operation with assumption no force device removal(unbind) operation. However force device removal(removal) is still available to root superuser. Unbinding driver during operation causes kernel crash. This changes ensure driver able to handle such operation for indirect read and indirect write by implementing refcount to track attached devices to the controller and gracefully wait and until attached devices remove operation completed before proceed with removal operation.
CVE-2025-40016: In the Linux kernel, the following vulnerability has been resolved: media: uvcvideo: Mark invalid entities with id UVC_INVALID_ENTITY_ID Per UVC 1.1+ specification 3.7.2, units and terminals must have a non-zero unique ID. ``` Each Unit and Terminal within the video function is assigned a unique identification number, the Unit ID (UID) or Terminal ID (TID), contained in the bUnitID or bTerminalID field of the descriptor. The value 0x00 is reserved for undefined ID, ``` If we add a new entity with id 0 or a duplicated ID, it will be marked as UVC_INVALID_ENTITY_ID. In a previous attempt commit 3dd075fe8ebb ("media: uvcvideo: Require entities to have a non-zero unique ID"), we ignored all the invalid units, this broke a lot of non-compatible cameras. Hopefully we are more lucky this time. This also prevents some syzkaller reproducers from triggering warnings due to a chain of entities referring to themselves. In one particular case, an Output Unit is connected to an Input Unit, both with the same ID of 1. But when looking up for the source ID of the Output Unit, that same entity is found instead of the input entity, which leads to such warnings. In another case, a backward chain was considered finished as the source ID was 0. Later on, that entity was found, but its pads were not valid. Here is a sample stack trace for one of those cases. [ 20.650953] usb 1-1: new high-speed USB device number 2 using dummy_hcd [ 20.830206] usb 1-1: Using ep0 maxpacket: 8 [ 20.833501] usb 1-1: config 0 descriptor?? [ 21.038518] usb 1-1: string descriptor 0 read error: -71 [ 21.038893] usb 1-1: Found UVC 0.00 device <unnamed> (2833:0201) [ 21.039299] uvcvideo 1-1:0.0: Entity type for entity Output 1 was not initialized! [ 21.041583] uvcvideo 1-1:0.0: Entity type for entity Input 1 was not initialized! [ 21.042218] ------------[ cut here ]------------ [ 21.042536] WARNING: CPU: 0 PID: 9 at drivers/media/mc/mc-entity.c:1147 media_create_pad_link+0x2c4/0x2e0 [ 21.043195] Modules linked in: [ 21.043535] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.11.0-rc7-00030-g3480e43aeccf #444 [ 21.044101] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 [ 21.044639] Workqueue: usb_hub_wq hub_event [ 21.045100] RIP: 0010:media_create_pad_link+0x2c4/0x2e0 [ 21.045508] Code: fe e8 20 01 00 00 b8 f4 ff ff ff 48 83 c4 30 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc 0f 0b eb e9 0f 0b eb 0a 0f 0b eb 06 <0f> 0b eb 02 0f 0b b8 ea ff ff ff eb d4 66 2e 0f 1f 84 00 00 00 00 [ 21.046801] RSP: 0018:ffffc9000004b318 EFLAGS: 00010246 [ 21.047227] RAX: ffff888004e5d458 RBX: 0000000000000000 RCX: ffffffff818fccf1 [ 21.047719] RDX: 000000000000007b RSI: 0000000000000000 RDI: ffff888004313290 [ 21.048241] RBP: ffff888004313290 R08: 0001ffffffffffff R09: 0000000000000000 [ 21.048701] R10: 0000000000000013 R11: 0001888004313290 R12: 0000000000000003 [ 21.049138] R13: ffff888004313080 R14: ffff888004313080 R15: 0000000000000000 [ 21.049648] FS: 0000000000000000(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 [ 21.050271] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 21.050688] CR2: 0000592cc27635b0 CR3: 000000000431c000 CR4: 0000000000750ef0 [ 21.051136] PKRU: 55555554 [ 21.051331] Call Trace: [ 21.051480] <TASK> [ 21.051611] ? __warn+0xc4/0x210 [ 21.051861] ? media_create_pad_link+0x2c4/0x2e0 [ 21.052252] ? report_bug+0x11b/0x1a0 [ 21.052540] ? trace_hardirqs_on+0x31/0x40 [ 21.052901] ? handle_bug+0x3d/0x70 [ 21.053197] ? exc_invalid_op+0x1a/0x50 [ 21.053511] ? asm_exc_invalid_op+0x1a/0x20 [ 21.053924] ? media_create_pad_link+0x91/0x2e0 [ 21.054364] ? media_create_pad_link+0x2c4/0x2e0 [ 21.054834] ? media_create_pad_link+0x91/0x2e0 [ 21.055131] ? _raw_spin_unlock+0x1e/0x40 [ 21.055441] ? __v4l2_device_register_subdev+0x202/0x210 [ 21.055837] uvc_mc_register_entities+0x358/0x400 [ 21.056144] uvc_register_chains+0x1 ---truncated---
CVE-2025-40025: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer for non inode dnode As syzbot reported below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/file.c:1243! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 5354 Comm: syz.0.0 Not tainted 6.17.0-rc1-syzkaller-00211-g90d970cade8e #0 PREEMPT(full) RIP: 0010:f2fs_truncate_hole+0x69e/0x6c0 fs/f2fs/file.c:1243 Call Trace: <TASK> f2fs_punch_hole+0x2db/0x330 fs/f2fs/file.c:1306 f2fs_fallocate+0x546/0x990 fs/f2fs/file.c:2018 vfs_fallocate+0x666/0x7e0 fs/open.c:342 ksys_fallocate fs/open.c:366 [inline] __do_sys_fallocate fs/open.c:371 [inline] __se_sys_fallocate fs/open.c:369 [inline] __x64_sys_fallocate+0xc0/0x110 fs/open.c:369 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f1e65f8ebe9 w/ a fuzzed image, f2fs may encounter panic due to it detects inconsistent truncation range in direct node in f2fs_truncate_hole(). The root cause is: a non-inode dnode may has the same footer.ino and footer.nid, so the dnode will be parsed as an inode, then ADDRS_PER_PAGE() may return wrong blkaddr count which may be 923 typically, by chance, dn.ofs_in_node is equal to 923, then count can be calculated to 0 in below statement, later it will trigger panic w/ f2fs_bug_on(, count == 0 || ...). count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); This patch introduces a new node_type NODE_TYPE_NON_INODE, then allowing passing the new_type to sanity_check_node_footer in f2fs_get_node_folio() to detect corruption that a non-inode dnode has the same footer.ino and footer.nid. Scripts to reproduce: mkfs.f2fs -f /dev/vdb mount /dev/vdb /mnt/f2fs touch /mnt/f2fs/foo touch /mnt/f2fs/bar dd if=/dev/zero of=/mnt/f2fs/foo bs=1M count=8 umount /mnt/f2fs inject.f2fs --node --mb i_nid --nid 4 --idx 0 --val 5 /dev/vdb mount /dev/vdb /mnt/f2fs xfs_io /mnt/f2fs/foo -c "fpunch 6984k 4k"
CVE-2025-40032: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-test: Add NULL check for DMA channels before release The fields dma_chan_tx and dma_chan_rx of the struct pci_epf_test can be NULL even after EPF initialization. Then it is prudent to check that they have non-NULL values before releasing the channels. Add the checks in pci_epf_test_clean_dma_chan(). Without the checks, NULL pointer dereferences happen and they can lead to a kernel panic in some cases: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000050 Call trace: dma_release_channel+0x2c/0x120 (P) pci_epf_test_epc_deinit+0x94/0xc0 [pci_epf_test] pci_epc_deinit_notify+0x74/0xc0 tegra_pcie_ep_pex_rst_irq+0x250/0x5d8 irq_thread_fn+0x34/0xb8 irq_thread+0x18c/0x2e8 kthread+0x14c/0x210 ret_from_fork+0x10/0x20 [mani: trimmed the stack trace]
CVE-2025-40036: In the Linux kernel, the following vulnerability has been resolved: misc: fastrpc: fix possible map leak in fastrpc_put_args copy_to_user() failure would cause an early return without cleaning up the fdlist, which has been updated by the DSP. This could lead to map leak. Fix this by redirecting to a cleanup path on failure, ensuring that all mapped buffers are properly released before returning.
CVE-2025-40043: In the Linux kernel, the following vulnerability has been resolved: net: nfc: nci: Add parameter validation for packet data Syzbot reported an uninitialized value bug in nci_init_req, which was introduced by commit 5aca7966d2a7 ("Merge tag 'perf-tools-fixes-for-v6.17-2025-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools"). This bug arises due to very limited and poor input validation that was done at nic_valid_size(). This validation only validates the skb->len (directly reflects size provided at the userspace interface) with the length provided in the buffer itself (interpreted as NCI_HEADER). This leads to the processing of memory content at the address assuming the correct layout per what opcode requires there. This leads to the accesses to buffer of `skb_buff->data` which is not assigned anything yet. Following the same silent drop of packets of invalid sizes at `nic_valid_size()`, add validation of the data in the respective handlers and return error values in case of failure. Release the skb if error values are returned from handlers in `nci_nft_packet` and effectively do a silent drop Possible TODO: because we silently drop the packets, the call to `nci_request` will be waiting for completion of request and will face timeouts. These timeouts can get excessively logged in the dmesg. A proper handling of them may require to export `nci_request_cancel` (or propagate error handling from the nft packets handlers).
CVE-2025-40054: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix UAF issue in f2fs_merge_page_bio() As JY reported in bugzilla [1], Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 pc : [0xffffffe51d249484] f2fs_is_cp_guaranteed+0x70/0x98 lr : [0xffffffe51d24adbc] f2fs_merge_page_bio+0x520/0x6d4 CPU: 3 UID: 0 PID: 6790 Comm: kworker/u16:3 Tainted: P B W OE 6.12.30-android16-5-maybe-dirty-4k #1 5f7701c9cbf727d1eebe77c89bbbeb3371e895e5 Tainted: [P]=PROPRIETARY_MODULE, [B]=BAD_PAGE, [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Workqueue: writeback wb_workfn (flush-254:49) Call trace: f2fs_is_cp_guaranteed+0x70/0x98 f2fs_inplace_write_data+0x174/0x2f4 f2fs_do_write_data_page+0x214/0x81c f2fs_write_single_data_page+0x28c/0x764 f2fs_write_data_pages+0x78c/0xce4 do_writepages+0xe8/0x2fc __writeback_single_inode+0x4c/0x4b4 writeback_sb_inodes+0x314/0x540 __writeback_inodes_wb+0xa4/0xf4 wb_writeback+0x160/0x448 wb_workfn+0x2f0/0x5dc process_scheduled_works+0x1c8/0x458 worker_thread+0x334/0x3f0 kthread+0x118/0x1ac ret_from_fork+0x10/0x20 [1] https://bugzilla.kernel.org/show_bug.cgi?id=220575 The panic was caused by UAF issue w/ below race condition: kworker - writepages - f2fs_write_cache_pages - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #1 into bio & cache bio in io->bio_list - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #2 into bio which is linked in io->bio_list write - f2fs_write_begin : write page #1 - f2fs_folio_wait_writeback - f2fs_submit_merged_ipu_write - f2fs_submit_write_bio : submit bio which inclues page #1 and #2 software IRQ - f2fs_write_end_io - fscrypt_free_bounce_page : freed bounced page which belongs to page #2 - inc_page_count( , WB_DATA_TYPE(data_folio), false) : data_folio points to fio->encrypted_page the bounced page can be freed before accessing it in f2fs_is_cp_guarantee() It can reproduce w/ below testcase: Run below script in shell #1: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" Run below script in shell #2: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" So, in f2fs_merge_page_bio(), let's avoid using fio->encrypted_page after commit page into internal ipu cache.
CVE-2025-40064: In the Linux kernel, the following vulnerability has been resolved: smc: Fix use-after-free in __pnet_find_base_ndev(). syzbot reported use-after-free of net_device in __pnet_find_base_ndev(), which was called during connect(). [0] smc_pnet_find_ism_resource() fetches sk_dst_get(sk)->dev and passes down to pnet_find_base_ndev(), where RTNL is held. Then, UAF happened at __pnet_find_base_ndev() when the dev is first used. This means dev had already been freed before acquiring RTNL in pnet_find_base_ndev(). While dev is going away, dst->dev could be swapped with blackhole_netdev, and the dev's refcnt by dst will be released. We must hold dev's refcnt before calling smc_pnet_find_ism_resource(). Also, smc_pnet_find_roce_resource() has the same problem. Let's use __sk_dst_get() and dst_dev_rcu() in the two functions. [0]: BUG: KASAN: use-after-free in __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 Read of size 1 at addr ffff888036bac33a by task syz.0.3632/18609 CPU: 1 UID: 0 PID: 18609 Comm: syz.0.3632 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 pnet_find_base_ndev net/smc/smc_pnet.c:946 [inline] smc_pnet_find_ism_by_pnetid net/smc/smc_pnet.c:1103 [inline] smc_pnet_find_ism_resource+0xef/0x390 net/smc/smc_pnet.c:1154 smc_find_ism_device net/smc/af_smc.c:1030 [inline] smc_find_proposal_devices net/smc/af_smc.c:1115 [inline] __smc_connect+0x372/0x1890 net/smc/af_smc.c:1545 smc_connect+0x877/0xd90 net/smc/af_smc.c:1715 __sys_connect_file net/socket.c:2086 [inline] __sys_connect+0x313/0x440 net/socket.c:2105 __do_sys_connect net/socket.c:2111 [inline] __se_sys_connect net/socket.c:2108 [inline] __x64_sys_connect+0x7a/0x90 net/socket.c:2108 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f47cbf8eba9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f47ccdb1038 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 00007f47cc1d5fa0 RCX: 00007f47cbf8eba9 RDX: 0000000000000010 RSI: 0000200000000280 RDI: 000000000000000b RBP: 00007f47cc011e19 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f47cc1d6038 R14: 00007f47cc1d5fa0 R15: 00007ffc512f8aa8 </TASK> The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888036bacd00 pfn:0x36bac flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000000 ffffea0001243d08 ffff8880b863fdc0 0000000000000000 raw: ffff888036bacd00 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as freed page last allocated via order 2, migratetype Unmovable, gfp_mask 0x446dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO|__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_COMP), pid 16741, tgid 16741 (syz-executor), ts 343313197788, free_ts 380670750466 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x240/0x2a0 mm/page_alloc.c:1851 prep_new_page mm/page_alloc.c:1859 [inline] get_page_from_freelist+0x21e4/0x22c0 mm/page_alloc.c:3858 __alloc_frozen_pages_noprof+0x181/0x370 mm/page_alloc.c:5148 alloc_pages_mpol+0x232/0x4a0 mm/mempolicy.c:2416 ___kmalloc_large_node+0x5f/0x1b0 mm/slub.c:4317 __kmalloc_large_node_noprof+0x18/0x90 mm/slub.c:4348 __do_kmalloc_node mm/slub.c:4364 [inline] __kvmalloc_node ---truncated---
CVE-2025-40074: In the Linux kernel, the following vulnerability has been resolved: ipv4: start using dst_dev_rcu() Change icmpv4_xrlim_allow(), ip_defrag() to prevent possible UAF. Change ipmr_prepare_xmit(), ipmr_queue_fwd_xmit(), ip_mr_output(), ipv4_neigh_lookup() to use lockdep enabled dst_dev_rcu().
CVE-2025-40075: In the Linux kernel, the following vulnerability has been resolved: tcp_metrics: use dst_dev_net_rcu() Replace three dst_dev() with a lockdep enabled helper.
CVE-2025-40077: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid overflow while left shift operation Should cast type of folio->index from pgoff_t to loff_t to avoid overflow while left shift operation.
CVE-2025-40080: In the Linux kernel, the following vulnerability has been resolved: nbd: restrict sockets to TCP and UDP Recently, syzbot started to abuse NBD with all kinds of sockets. Commit cf1b2326b734 ("nbd: verify socket is supported during setup") made sure the socket supported a shutdown() method. Explicitely accept TCP and UNIX stream sockets.
CVE-2025-40082: In the Linux kernel, the following vulnerability has been resolved: hfsplus: fix slab-out-of-bounds read in hfsplus_uni2asc() BUG: KASAN: slab-out-of-bounds in hfsplus_uni2asc+0xa71/0xb90 fs/hfsplus/unicode.c:186 Read of size 2 at addr ffff8880289ef218 by task syz.6.248/14290 CPU: 0 UID: 0 PID: 14290 Comm: syz.6.248 Not tainted 6.16.4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x116/0x1b0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x5f0 mm/kasan/report.c:482 kasan_report+0xca/0x100 mm/kasan/report.c:595 hfsplus_uni2asc+0xa71/0xb90 fs/hfsplus/unicode.c:186 hfsplus_listxattr+0x5b6/0xbd0 fs/hfsplus/xattr.c:738 vfs_listxattr+0xbe/0x140 fs/xattr.c:493 listxattr+0xee/0x190 fs/xattr.c:924 filename_listxattr fs/xattr.c:958 [inline] path_listxattrat+0x143/0x360 fs/xattr.c:988 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcb/0x4c0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fe0e9fae16d Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fe0eae67f98 EFLAGS: 00000246 ORIG_RAX: 00000000000000c3 RAX: ffffffffffffffda RBX: 00007fe0ea205fa0 RCX: 00007fe0e9fae16d RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000200000000000 RBP: 00007fe0ea0480f0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fe0ea206038 R14: 00007fe0ea205fa0 R15: 00007fe0eae48000 </TASK> Allocated by task 14290: kasan_save_stack+0x24/0x50 mm/kasan/common.c:47 kasan_save_track+0x14/0x30 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __do_kmalloc_node mm/slub.c:4333 [inline] __kmalloc_noprof+0x219/0x540 mm/slub.c:4345 kmalloc_noprof include/linux/slab.h:909 [inline] hfsplus_find_init+0x95/0x1f0 fs/hfsplus/bfind.c:21 hfsplus_listxattr+0x331/0xbd0 fs/hfsplus/xattr.c:697 vfs_listxattr+0xbe/0x140 fs/xattr.c:493 listxattr+0xee/0x190 fs/xattr.c:924 filename_listxattr fs/xattr.c:958 [inline] path_listxattrat+0x143/0x360 fs/xattr.c:988 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcb/0x4c0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f When hfsplus_uni2asc is called from hfsplus_listxattr, it actually passes in a struct hfsplus_attr_unistr*. The size of the corresponding structure is different from that of hfsplus_unistr, so the previous fix (94458781aee6) is insufficient. The pointer on the unicode buffer is still going beyond the allocated memory. This patch introduces two warpper functions hfsplus_uni2asc_xattr_str and hfsplus_uni2asc_str to process two unicode buffers, struct hfsplus_attr_unistr* and struct hfsplus_unistr* respectively. When ustrlen value is bigger than the allocated memory size, the ustrlen value is limited to an safe size.
CVE-2025-40092: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: Refactor bind path to use __free() After an bind/unbind cycle, the ncm->notify_req is left stale. If a subsequent bind fails, the unified error label attempts to free this stale request, leading to a NULL pointer dereference when accessing ep->ops->free_request. Refactor the error handling in the bind path to use the __free() automatic cleanup mechanism. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 Call trace: usb_ep_free_request+0x2c/0xec ncm_bind+0x39c/0x3dc usb_add_function+0xcc/0x1f0 configfs_composite_bind+0x468/0x588 gadget_bind_driver+0x104/0x270 really_probe+0x190/0x374 __driver_probe_device+0xa0/0x12c driver_probe_device+0x3c/0x218 __device_attach_driver+0x14c/0x188 bus_for_each_drv+0x10c/0x168 __device_attach+0xfc/0x198 device_initial_probe+0x14/0x24 bus_probe_device+0x94/0x11c device_add+0x268/0x48c usb_add_gadget+0x198/0x28c dwc3_gadget_init+0x700/0x858 __dwc3_set_mode+0x3cc/0x664 process_scheduled_works+0x1d8/0x488 worker_thread+0x244/0x334 kthread+0x114/0x1bc ret_from_fork+0x10/0x20
CVE-2025-40093: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ecm: Refactor bind path to use __free() After an bind/unbind cycle, the ecm->notify_req is left stale. If a subsequent bind fails, the unified error label attempts to free this stale request, leading to a NULL pointer dereference when accessing ep->ops->free_request. Refactor the error handling in the bind path to use the __free() automatic cleanup mechanism.
CVE-2025-40094: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_acm: Refactor bind path to use __free() After an bind/unbind cycle, the acm->notify_req is left stale. If a subsequent bind fails, the unified error label attempts to free this stale request, leading to a NULL pointer dereference when accessing ep->ops->free_request. Refactor the error handling in the bind path to use the __free() automatic cleanup mechanism. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 Call trace: usb_ep_free_request+0x2c/0xec gs_free_req+0x30/0x44 acm_bind+0x1b8/0x1f4 usb_add_function+0xcc/0x1f0 configfs_composite_bind+0x468/0x588 gadget_bind_driver+0x104/0x270 really_probe+0x190/0x374 __driver_probe_device+0xa0/0x12c driver_probe_device+0x3c/0x218 __device_attach_driver+0x14c/0x188 bus_for_each_drv+0x10c/0x168 __device_attach+0xfc/0x198 device_initial_probe+0x14/0x24 bus_probe_device+0x94/0x11c device_add+0x268/0x48c usb_add_gadget+0x198/0x28c dwc3_gadget_init+0x700/0x858 __dwc3_set_mode+0x3cc/0x664 process_scheduled_works+0x1d8/0x488 worker_thread+0x244/0x334 kthread+0x114/0x1bc ret_from_fork+0x10/0x20
CVE-2025-40095: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_rndis: Refactor bind path to use __free() After an bind/unbind cycle, the rndis->notify_req is left stale. If a subsequent bind fails, the unified error label attempts to free this stale request, leading to a NULL pointer dereference when accessing ep->ops->free_request. Refactor the error handling in the bind path to use the __free() automatic cleanup mechanism.
CVE-2025-40099: In the Linux kernel, the following vulnerability has been resolved: cifs: parse_dfs_referrals: prevent oob on malformed input Malicious SMB server can send invalid reply to FSCTL_DFS_GET_REFERRALS - reply smaller than sizeof(struct get_dfs_referral_rsp) - reply with number of referrals smaller than NumberOfReferrals in the header Processing of such replies will cause oob. Return -EINVAL error on such replies to prevent oob-s.
CVE-2025-40100: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not assert we found block group item when creating free space tree Currently, when building a free space tree at populate_free_space_tree(), if we are not using the block group tree feature, we always expect to find block group items (either extent items or a block group item with key type BTRFS_BLOCK_GROUP_ITEM_KEY) when we search the extent tree with btrfs_search_slot_for_read(), so we assert that we found an item. However this expectation is wrong since we can have a new block group created in the current transaction which is still empty and for which we still have not added the block group's item to the extent tree, in which case we do not have any items in the extent tree associated to the block group. The insertion of a new block group's block group item in the extent tree happens at btrfs_create_pending_block_groups() when it calls the helper insert_block_group_item(). This typically is done when a transaction handle is released, committed or when running delayed refs (either as part of a transaction commit or when serving tickets for space reservation if we are low on free space). So remove the assertion at populate_free_space_tree() even when the block group tree feature is not enabled and update the comment to mention this case. Syzbot reported this with the following stack trace: BTRFS info (device loop3 state M): rebuilding free space tree assertion failed: ret == 0 :: 0, in fs/btrfs/free-space-tree.c:1115 ------------[ cut here ]------------ kernel BUG at fs/btrfs/free-space-tree.c:1115! Oops: invalid opcode: 0000 [#1] SMP KASAN PTI CPU: 1 UID: 0 PID: 6352 Comm: syz.3.25 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025 RIP: 0010:populate_free_space_tree+0x700/0x710 fs/btrfs/free-space-tree.c:1115 Code: ff ff e8 d3 (...) RSP: 0018:ffffc9000430f780 EFLAGS: 00010246 RAX: 0000000000000043 RBX: ffff88805b709630 RCX: fea61d0e2e79d000 RDX: 0000000000000000 RSI: 0000000080000000 RDI: 0000000000000000 RBP: ffffc9000430f8b0 R08: ffffc9000430f4a7 R09: 1ffff92000861e94 R10: dffffc0000000000 R11: fffff52000861e95 R12: 0000000000000001 R13: 1ffff92000861f00 R14: dffffc0000000000 R15: 0000000000000000 FS: 00007f424d9fe6c0(0000) GS:ffff888125afc000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fd78ad212c0 CR3: 0000000076d68000 CR4: 00000000003526f0 Call Trace: <TASK> btrfs_rebuild_free_space_tree+0x1ba/0x6d0 fs/btrfs/free-space-tree.c:1364 btrfs_start_pre_rw_mount+0x128f/0x1bf0 fs/btrfs/disk-io.c:3062 btrfs_remount_rw fs/btrfs/super.c:1334 [inline] btrfs_reconfigure+0xaed/0x2160 fs/btrfs/super.c:1559 reconfigure_super+0x227/0x890 fs/super.c:1076 do_remount fs/namespace.c:3279 [inline] path_mount+0xd1a/0xfe0 fs/namespace.c:4027 do_mount fs/namespace.c:4048 [inline] __do_sys_mount fs/namespace.c:4236 [inline] __se_sys_mount+0x313/0x410 fs/namespace.c:4213 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f424e39066a Code: d8 64 89 02 (...) RSP: 002b:00007f424d9fde68 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f424d9fdef0 RCX: 00007f424e39066a RDX: 0000200000000180 RSI: 0000200000000380 RDI: 0000000000000000 RBP: 0000200000000180 R08: 00007f424d9fdef0 R09: 0000000000000020 R10: 0000000000000020 R11: 0000000000000246 R12: 0000200000000380 R13: 00007f424d9fdeb0 R14: 0000000000000000 R15: 00002000000002c0 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]---
CVE-2025-40102: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Prevent access to vCPU events before init Another day, another syzkaller bug. KVM erroneously allows userspace to pend vCPU events for a vCPU that hasn't been initialized yet, leading to KVM interpreting a bunch of uninitialized garbage for routing / injecting the exception. In one case the injection code and the hyp disagree on whether the vCPU has a 32bit EL1 and put the vCPU into an illegal mode for AArch64, tripping the BUG() in exception_target_el() during the next injection: kernel BUG at arch/arm64/kvm/inject_fault.c:40! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 3 UID: 0 PID: 318 Comm: repro Not tainted 6.17.0-rc4-00104-g10fd0285305d #6 PREEMPT Hardware name: linux,dummy-virt (DT) pstate: 21402009 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : exception_target_el+0x88/0x8c lr : pend_serror_exception+0x18/0x13c sp : ffff800082f03a10 x29: ffff800082f03a10 x28: ffff0000cb132280 x27: 0000000000000000 x26: 0000000000000000 x25: ffff0000c2a99c20 x24: 0000000000000000 x23: 0000000000008000 x22: 0000000000000002 x21: 0000000000000004 x20: 0000000000008000 x19: ffff0000c2a99c20 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000200000c0 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : ffff800082f03af8 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffff800080f621f0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 000000000040009b x1 : 0000000000000003 x0 : ffff0000c2a99c20 Call trace: exception_target_el+0x88/0x8c (P) kvm_inject_serror_esr+0x40/0x3b4 __kvm_arm_vcpu_set_events+0xf0/0x100 kvm_arch_vcpu_ioctl+0x180/0x9d4 kvm_vcpu_ioctl+0x60c/0x9f4 __arm64_sys_ioctl+0xac/0x104 invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x34/0xf0 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Code: f946bc01 b4fffe61 9101e020 17fffff2 (d4210000) Reject the ioctls outright as no sane VMM would call these before KVM_ARM_VCPU_INIT anyway. Even if it did the exception would've been thrown away by the eventual reset of the vCPU's state.
CVE-2025-40103: In the Linux kernel, the following vulnerability has been resolved: smb: client: Fix refcount leak for cifs_sb_tlink Fix three refcount inconsistency issues related to `cifs_sb_tlink`. Comments for `cifs_sb_tlink` state that `cifs_put_tlink()` needs to be called after successful calls to `cifs_sb_tlink()`. Three calls fail to update refcount accordingly, leading to possible resource leaks.
CVE-2025-40104: In the Linux kernel, the following vulnerability has been resolved: ixgbevf: fix mailbox API compatibility by negotiating supported features There was backward compatibility in the terms of mailbox API. Various drivers from various OSes supporting 10G adapters from Intel portfolio could easily negotiate mailbox API. This convention has been broken since introducing API 1.4. Commit 0062e7cc955e ("ixgbevf: add VF IPsec offload code") added support for IPSec which is specific only for the kernel ixgbe driver. None of the rest of the Intel 10G PF/VF drivers supports it. And actually lack of support was not included in the IPSec implementation - there were no such code paths. No possibility to negotiate support for the feature was introduced along with introduction of the feature itself. Commit 339f28964147 ("ixgbevf: Add support for new mailbox communication between PF and VF") increasing API version to 1.5 did the same - it introduced code supported specifically by the PF ESX driver. It altered API version for the VF driver in the same time not touching the version defined for the PF ixgbe driver. It led to additional discrepancies, as the code provided within API 1.6 cannot be supported for Linux ixgbe driver as it causes crashes. The issue was noticed some time ago and mitigated by Jake within the commit d0725312adf5 ("ixgbevf: stop attempting IPSEC offload on Mailbox API 1.5"). As a result we have regression for IPsec support and after increasing API to version 1.6 ixgbevf driver stopped to support ESX MBX. To fix this mess add new mailbox op asking PF driver about supported features. Basing on a response determine whether to set support for IPSec and ESX-specific enhanced mailbox. New mailbox op, for compatibility purposes, must be added within new API revision, as API version of OOT PF & VF drivers is already increased to 1.6 and doesn't incorporate features negotiate op. Features negotiation mechanism gives possibility to be extended with new features when needed in the future.
CVE-2025-40107: In the Linux kernel, the following vulnerability has been resolved: can: hi311x: fix null pointer dereference when resuming from sleep before interface was enabled This issue is similar to the vulnerability in the `mcp251x` driver, which was fixed in commit 03c427147b2d ("can: mcp251x: fix resume from sleep before interface was brought up"). In the `hi311x` driver, when the device resumes from sleep, the driver schedules `priv->restart_work`. However, if the network interface was not previously enabled, the `priv->wq` (workqueue) is not allocated and initialized, leading to a null pointer dereference. To fix this, we move the allocation and initialization of the workqueue from the `hi3110_open` function to the `hi3110_can_probe` function. This ensures that the workqueue is properly initialized before it is used during device resume. And added logic to destroy the workqueue in the error handling paths of `hi3110_can_probe` and in the `hi3110_can_remove` function to prevent resource leaks.
CVE-2025-40123: In the Linux kernel, the following vulnerability has been resolved: bpf: Enforce expected_attach_type for tailcall compatibility Yinhao et al. recently reported: Our fuzzer tool discovered an uninitialized pointer issue in the bpf_prog_test_run_xdp() function within the Linux kernel's BPF subsystem. This leads to a NULL pointer dereference when a BPF program attempts to deference the txq member of struct xdp_buff object. The test initializes two programs of BPF_PROG_TYPE_XDP: progA acts as the entry point for bpf_prog_test_run_xdp() and its expected_attach_type can neither be of be BPF_XDP_DEVMAP nor BPF_XDP_CPUMAP. progA calls into a slot of a tailcall map it owns. progB's expected_attach_type must be BPF_XDP_DEVMAP to pass xdp_is_valid_access() validation. The program returns struct xdp_md's egress_ifindex, and the latter is only allowed to be accessed under mentioned expected_attach_type. progB is then inserted into the tailcall which progA calls. The underlying issue goes beyond XDP though. Another example are programs of type BPF_PROG_TYPE_CGROUP_SOCK_ADDR. sock_addr_is_valid_access() as well as sock_addr_func_proto() have different logic depending on the programs' expected_attach_type. Similarly, a program attached to BPF_CGROUP_INET4_GETPEERNAME should not be allowed doing a tailcall into a program which calls bpf_bind() out of BPF which is only enabled for BPF_CGROUP_INET4_CONNECT. In short, specifying expected_attach_type allows to open up additional functionality or restrictions beyond what the basic bpf_prog_type enables. The use of tailcalls must not violate these constraints. Fix it by enforcing expected_attach_type in __bpf_prog_map_compatible(). Note that we only enforce this for tailcall maps, but not for BPF devmaps or cpumaps: There, the programs are invoked through dev_map_bpf_prog_run*() and cpu_map_bpf_prog_run*() which set up a new environment / context and therefore these situations are not prone to this issue.
CVE-2025-40135: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_xmit() Use RCU in ip6_xmit() in order to use dst_dev_rcu() to prevent possible UAF.
CVE-2025-40137: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to truncate first page in error path of f2fs_truncate() syzbot reports a bug as below: loop0: detected capacity change from 0 to 40427 F2FS-fs (loop0): Wrong SSA boundary, start(3584) end(4096) blocks(3072) F2FS-fs (loop0): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop0): invalid crc value F2FS-fs (loop0): f2fs_convert_inline_folio: corrupted inline inode ino=3, i_addr[0]:0x1601, run fsck to fix. ------------[ cut here ]------------ kernel BUG at fs/inode.c:753! RIP: 0010:clear_inode+0x169/0x190 fs/inode.c:753 Call Trace: <TASK> evict+0x504/0x9c0 fs/inode.c:810 f2fs_fill_super+0x5612/0x6fa0 fs/f2fs/super.c:5047 get_tree_bdev_flags+0x40e/0x4d0 fs/super.c:1692 vfs_get_tree+0x8f/0x2b0 fs/super.c:1815 do_new_mount+0x2a2/0x9e0 fs/namespace.c:3808 do_mount fs/namespace.c:4136 [inline] __do_sys_mount fs/namespace.c:4347 [inline] __se_sys_mount+0x317/0x410 fs/namespace.c:4324 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f During f2fs_evict_inode(), clear_inode() detects that we missed to truncate all page cache before destorying inode, that is because in below path, we will create page #0 in cache, but missed to drop it in error path, let's fix it. - evict - f2fs_evict_inode - f2fs_truncate - f2fs_convert_inline_inode - f2fs_grab_cache_folio : create page #0 in cache - f2fs_convert_inline_folio : sanity check failed, return -EFSCORRUPTED - clear_inode detects that inode->i_data.nrpages is not zero
CVE-2025-40139: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in in smc_clc_prfx_set(). smc_clc_prfx_set() is called during connect() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dev_dst_rcu() under rcu_read_lock() after kernel_getsockname(). Note that the returned value of smc_clc_prfx_set() is not used in the caller. While at it, we change the 1st arg of smc_clc_prfx_set[46]_rcu() not to touch dst there.
CVE-2025-40146: In the Linux kernel, the following vulnerability has been resolved: blk-mq: fix potential deadlock while nr_requests grown Allocate and free sched_tags while queue is freezed can deadlock[1], this is a long term problem, hence allocate memory before freezing queue and free memory after queue is unfreezed. [1] https://lore.kernel.org/all/0659ea8d-a463-47c8-9180-43c719e106eb@linux.ibm.com/
CVE-2025-40149: In the Linux kernel, the following vulnerability has been resolved: tls: Use __sk_dst_get() and dst_dev_rcu() in get_netdev_for_sock(). get_netdev_for_sock() is called during setsockopt(), so not under RCU. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dst_dev_rcu(). Note that the only ->ndo_sk_get_lower_dev() user is bond_sk_get_lower_dev(), which uses RCU.
CVE-2025-40158: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_output() Use RCU in ip6_output() in order to use dst_dev_rcu() to prevent possible UAF. We can remove rcu_read_lock()/rcu_read_unlock() pairs from ip6_finish_output2().
CVE-2025-40160: In the Linux kernel, the following vulnerability has been resolved: xen/events: Return -EEXIST for bound VIRQs Change find_virq() to return -EEXIST when a VIRQ is bound to a different CPU than the one passed in. With that, remove the BUG_ON() from bind_virq_to_irq() to propogate the error upwards. Some VIRQs are per-cpu, but others are per-domain or global. Those must be bound to CPU0 and can then migrate elsewhere. The lookup for per-domain and global will probably fail when migrated off CPU 0, especially when the current CPU is tracked. This now returns -EEXIST instead of BUG_ON(). A second call to bind a per-domain or global VIRQ is not expected, but make it non-fatal to avoid trying to look up the irq, since we don't know which per_cpu(virq_to_irq) it will be in.
CVE-2025-40164: In the Linux kernel, the following vulnerability has been resolved: usbnet: Fix using smp_processor_id() in preemptible code warnings Syzbot reported the following warning: BUG: using smp_processor_id() in preemptible [00000000] code: dhcpcd/2879 caller is usbnet_skb_return+0x74/0x490 drivers/net/usb/usbnet.c:331 CPU: 1 UID: 0 PID: 2879 Comm: dhcpcd Not tainted 6.15.0-rc4-syzkaller-00098-g615dca38c2ea #0 PREEMPT(voluntary) Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x16c/0x1f0 lib/dump_stack.c:120 check_preemption_disabled+0xd0/0xe0 lib/smp_processor_id.c:49 usbnet_skb_return+0x74/0x490 drivers/net/usb/usbnet.c:331 usbnet_resume_rx+0x4b/0x170 drivers/net/usb/usbnet.c:708 usbnet_change_mtu+0x1be/0x220 drivers/net/usb/usbnet.c:417 __dev_set_mtu net/core/dev.c:9443 [inline] netif_set_mtu_ext+0x369/0x5c0 net/core/dev.c:9496 netif_set_mtu+0xb0/0x160 net/core/dev.c:9520 dev_set_mtu+0xae/0x170 net/core/dev_api.c:247 dev_ifsioc+0xa31/0x18d0 net/core/dev_ioctl.c:572 dev_ioctl+0x223/0x10e0 net/core/dev_ioctl.c:821 sock_do_ioctl+0x19d/0x280 net/socket.c:1204 sock_ioctl+0x42f/0x6a0 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl fs/ioctl.c:892 [inline] __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcd/0x260 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f For historical and portability reasons, the netif_rx() is usually run in the softirq or interrupt context, this commit therefore add local_bh_disable/enable() protection in the usbnet_resume_rx().
CVE-2025-40168: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in smc_clc_prfx_match(). smc_clc_prfx_match() is called from smc_listen_work() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dst_dev_rcu(). Note that the returned value of smc_clc_prfx_match() is not used in the caller.
CVE-2025-40170: In the Linux kernel, the following vulnerability has been resolved: net: use dst_dev_rcu() in sk_setup_caps() Use RCU to protect accesses to dst->dev from sk_setup_caps() and sk_dst_gso_max_size(). Also use dst_dev_rcu() in ip6_dst_mtu_maybe_forward(), and ip_dst_mtu_maybe_forward(). ip4_dst_hoplimit() can use dst_dev_net_rcu().
CVE-2025-40180: In the Linux kernel, the following vulnerability has been resolved: mailbox: zynqmp-ipi: Fix out-of-bounds access in mailbox cleanup loop The cleanup loop was starting at the wrong array index, causing out-of-bounds access. Start the loop at the correct index for zero-indexed arrays to prevent accessing memory beyond the allocated array bounds.
CVE-2025-40193: In the Linux kernel, the following vulnerability has been resolved: xtensa: simdisk: add input size check in proc_write_simdisk A malicious user could pass an arbitrarily bad value to memdup_user_nul(), potentially causing kernel crash. This follows the same pattern as commit ee76746387f6 ("netdevsim: prevent bad user input in nsim_dev_health_break_write()")
CVE-2025-40196: In the Linux kernel, the following vulnerability has been resolved: fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ...
CVE-2025-40206: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_objref: validate objref and objrefmap expressions Referencing a synproxy stateful object from OUTPUT hook causes kernel crash due to infinite recursive calls: BUG: TASK stack guard page was hit at 000000008bda5b8c (stack is 000000003ab1c4a5..00000000494d8b12) [...] Call Trace: __find_rr_leaf+0x99/0x230 fib6_table_lookup+0x13b/0x2d0 ip6_pol_route+0xa4/0x400 fib6_rule_lookup+0x156/0x240 ip6_route_output_flags+0xc6/0x150 __nf_ip6_route+0x23/0x50 synproxy_send_tcp_ipv6+0x106/0x200 synproxy_send_client_synack_ipv6+0x1aa/0x1f0 nft_synproxy_do_eval+0x263/0x310 nft_do_chain+0x5a8/0x5f0 [nf_tables nft_do_chain_inet+0x98/0x110 nf_hook_slow+0x43/0xc0 __ip6_local_out+0xf0/0x170 ip6_local_out+0x17/0x70 synproxy_send_tcp_ipv6+0x1a2/0x200 synproxy_send_client_synack_ipv6+0x1aa/0x1f0 [...] Implement objref and objrefmap expression validate functions. Currently, only NFT_OBJECT_SYNPROXY object type requires validation. This will also handle a jump to a chain using a synproxy object from the OUTPUT hook. Now when trying to reference a synproxy object in the OUTPUT hook, nft will produce the following error: synproxy_crash.nft: Error: Could not process rule: Operation not supported synproxy name mysynproxy ^^^^^^^^^^^^^^^^^^^^^^^^
CVE-2025-40219: In the Linux kernel, the following vulnerability has been resolved: PCI/IOV: Fix race between SR-IOV enable/disable and hotplug Commit 05703271c3cd ("PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV") tried to fix a race between the VF removal inside sriov_del_vfs() and concurrent hot unplug by taking the PCI rescan/remove lock in sriov_del_vfs(). Similarly the PCI rescan/remove lock was also taken in sriov_add_vfs() to protect addition of VFs. This approach however causes deadlock on trying to remove PFs with SR-IOV enabled because PFs disable SR-IOV during removal and this removal happens under the PCI rescan/remove lock. So the original fix had to be reverted. Instead of taking the PCI rescan/remove lock in sriov_add_vfs() and sriov_del_vfs(), fix the race that occurs with SR-IOV enable and disable vs hotplug higher up in the callchain by taking the lock in sriov_numvfs_store() before calling into the driver's sriov_configure() callback.
CVE-2025-40242: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix unlikely race in gdlm_put_lock In gdlm_put_lock(), there is a small window of time in which the DFL_UNMOUNT flag has been set but the lockspace hasn't been released, yet. In that window, dlm may still call gdlm_ast() and gdlm_bast(). To prevent it from dereferencing freed glock objects, only free the glock if the lockspace has actually been released.
CVE-2025-40247: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix pgtable prealloc error path The following splat was reported: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000008d0fd8000 [0000000000000010] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] SMP CPU: 5 UID: 1000 PID: 149076 Comm: Xwayland Tainted: G S 6.16.0-rc2-00809-g0b6974bb4134-dirty #367 PREEMPT Tainted: [S]=CPU_OUT_OF_SPEC Hardware name: Qualcomm Technologies, Inc. SM8650 HDK (DT) pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : build_detached_freelist+0x28/0x224 lr : kmem_cache_free_bulk.part.0+0x38/0x244 sp : ffff000a508c7a20 x29: ffff000a508c7a20 x28: ffff000a508c7d50 x27: ffffc4e49d16f350 x26: 0000000000000058 x25: 00000000fffffffc x24: 0000000000000000 x23: ffff00098c4e1450 x22: 00000000fffffffc x21: 0000000000000000 x20: ffff000a508c7af8 x19: 0000000000000002 x18: 00000000000003e8 x17: ffff000809523850 x16: ffff000809523820 x15: 0000000000401640 x14: ffff000809371140 x13: 0000000000000130 x12: ffff0008b5711e30 x11: 00000000001058fa x10: 0000000000000a80 x9 : ffff000a508c7940 x8 : ffff000809371ba0 x7 : 781fffe033087fff x6 : 0000000000000000 x5 : ffff0008003cd000 x4 : 781fffe033083fff x3 : ffff000a508c7af8 x2 : fffffdffc0000000 x1 : 0001000000000000 x0 : ffff0008001a6a00 Call trace: build_detached_freelist+0x28/0x224 (P) kmem_cache_free_bulk.part.0+0x38/0x244 kmem_cache_free_bulk+0x10/0x1c msm_iommu_pagetable_prealloc_cleanup+0x3c/0xd0 msm_vma_job_free+0x30/0x240 msm_ioctl_vm_bind+0x1d0/0x9a0 drm_ioctl_kernel+0x84/0x104 drm_ioctl+0x358/0x4d4 __arm64_sys_ioctl+0x8c/0xe0 invoke_syscall+0x44/0x100 el0_svc_common.constprop.0+0x3c/0xe0 do_el0_svc+0x18/0x20 el0_svc+0x30/0x100 el0t_64_sync_handler+0x104/0x130 el0t_64_sync+0x170/0x174 Code: aa0203f5 b26287e2 f2dfbfe2 aa0303f4 (f8737ab6) ---[ end trace 0000000000000000 ]--- Since msm_vma_job_free() is called directly from the ioctl, this looks like an error path cleanup issue. Which I think results from prealloc_cleanup() called without a preceding successful prealloc_allocate() call. So handle that case better. Patchwork: https://patchwork.freedesktop.org/patch/678677/
CVE-2025-40252: In the Linux kernel, the following vulnerability has been resolved: net: qlogic/qede: fix potential out-of-bounds read in qede_tpa_cont() and qede_tpa_end() The loops in 'qede_tpa_cont()' and 'qede_tpa_end()', iterate over 'cqe->len_list[]' using only a zero-length terminator as the stopping condition. If the terminator was missing or malformed, the loop could run past the end of the fixed-size array. Add an explicit bound check using ARRAY_SIZE() in both loops to prevent a potential out-of-bounds access. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2025-40261: In the Linux kernel, the following vulnerability has been resolved: nvme: nvme-fc: Ensure ->ioerr_work is cancelled in nvme_fc_delete_ctrl() nvme_fc_delete_assocation() waits for pending I/O to complete before returning, and an error can cause ->ioerr_work to be queued after cancel_work_sync() had been called. Move the call to cancel_work_sync() to be after nvme_fc_delete_association() to ensure ->ioerr_work is not running when the nvme_fc_ctrl object is freed. Otherwise the following can occur: [ 1135.911754] list_del corruption, ff2d24c8093f31f8->next is NULL [ 1135.917705] ------------[ cut here ]------------ [ 1135.922336] kernel BUG at lib/list_debug.c:52! [ 1135.926784] Oops: invalid opcode: 0000 [#1] SMP NOPTI [ 1135.931851] CPU: 48 UID: 0 PID: 726 Comm: kworker/u449:23 Kdump: loaded Not tainted 6.12.0 #1 PREEMPT(voluntary) [ 1135.943490] Hardware name: Dell Inc. PowerEdge R660/0HGTK9, BIOS 2.5.4 01/16/2025 [ 1135.950969] Workqueue: 0x0 (nvme-wq) [ 1135.954673] RIP: 0010:__list_del_entry_valid_or_report.cold+0xf/0x6f [ 1135.961041] Code: c7 c7 98 68 72 94 e8 26 45 fe ff 0f 0b 48 c7 c7 70 68 72 94 e8 18 45 fe ff 0f 0b 48 89 fe 48 c7 c7 80 69 72 94 e8 07 45 fe ff <0f> 0b 48 89 d1 48 c7 c7 a0 6a 72 94 48 89 c2 e8 f3 44 fe ff 0f 0b [ 1135.979788] RSP: 0018:ff579b19482d3e50 EFLAGS: 00010046 [ 1135.985015] RAX: 0000000000000033 RBX: ff2d24c8093f31f0 RCX: 0000000000000000 [ 1135.992148] RDX: 0000000000000000 RSI: ff2d24d6bfa1d0c0 RDI: ff2d24d6bfa1d0c0 [ 1135.999278] RBP: ff2d24c8093f31f8 R08: 0000000000000000 R09: ffffffff951e2b08 [ 1136.006413] R10: ffffffff95122ac8 R11: 0000000000000003 R12: ff2d24c78697c100 [ 1136.013546] R13: fffffffffffffff8 R14: 0000000000000000 R15: ff2d24c78697c0c0 [ 1136.020677] FS: 0000000000000000(0000) GS:ff2d24d6bfa00000(0000) knlGS:0000000000000000 [ 1136.028765] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1136.034510] CR2: 00007fd207f90b80 CR3: 000000163ea22003 CR4: 0000000000f73ef0 [ 1136.041641] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1136.048776] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 1136.055910] PKRU: 55555554 [ 1136.058623] Call Trace: [ 1136.061074] <TASK> [ 1136.063179] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.067540] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.071898] ? move_linked_works+0x4a/0xa0 [ 1136.075998] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.081744] ? __die_body.cold+0x8/0x12 [ 1136.085584] ? die+0x2e/0x50 [ 1136.088469] ? do_trap+0xca/0x110 [ 1136.091789] ? do_error_trap+0x65/0x80 [ 1136.095543] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.101289] ? exc_invalid_op+0x50/0x70 [ 1136.105127] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.110874] ? asm_exc_invalid_op+0x1a/0x20 [ 1136.115059] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.120806] move_linked_works+0x4a/0xa0 [ 1136.124733] worker_thread+0x216/0x3a0 [ 1136.128485] ? __pfx_worker_thread+0x10/0x10 [ 1136.132758] kthread+0xfa/0x240 [ 1136.135904] ? __pfx_kthread+0x10/0x10 [ 1136.139657] ret_from_fork+0x31/0x50 [ 1136.143236] ? __pfx_kthread+0x10/0x10 [ 1136.146988] ret_from_fork_asm+0x1a/0x30 [ 1136.150915] </TASK>
CVE-2025-40266: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Check the untrusted offset in FF-A memory share Verify the offset to prevent OOB access in the hypervisor FF-A buffer in case an untrusted large enough value [U32_MAX - sizeof(struct ffa_composite_mem_region) + 1, U32_MAX] is set from the host kernel.
CVE-2025-40279: In the Linux kernel, the following vulnerability has been resolved: net: sched: act_connmark: initialize struct tc_ife to fix kernel leak In tcf_connmark_dump(), the variable 'opt' was partially initialized using a designatied initializer. While the padding bytes are reamined uninitialized. nla_put() copies the entire structure into a netlink message, these uninitialized bytes leaked to userspace. Initialize the structure with memset before assigning its fields to ensure all members and padding are cleared prior to beign copied.
CVE-2025-40288: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix NULL pointer dereference in VRAM logic for APU devices Previously, APU platforms (and other scenarios with uninitialized VRAM managers) triggered a NULL pointer dereference in `ttm_resource_manager_usage()`. The root cause is not that the `struct ttm_resource_manager *man` pointer itself is NULL, but that `man->bdev` (the backing device pointer within the manager) remains uninitialized (NULL) on APUs—since APUs lack dedicated VRAM and do not fully set up VRAM manager structures. When `ttm_resource_manager_usage()` attempts to acquire `man->bdev->lru_lock`, it dereferences the NULL `man->bdev`, leading to a kernel OOPS. 1. **amdgpu_cs.c**: Extend the existing bandwidth control check in `amdgpu_cs_get_threshold_for_moves()` to include a check for `ttm_resource_manager_used()`. If the manager is not used (uninitialized `bdev`), return 0 for migration thresholds immediately—skipping VRAM-specific logic that would trigger the NULL dereference. 2. **amdgpu_kms.c**: Update the `AMDGPU_INFO_VRAM_USAGE` ioctl and memory info reporting to use a conditional: if the manager is used, return the real VRAM usage; otherwise, return 0. This avoids accessing `man->bdev` when it is NULL. 3. **amdgpu_virt.c**: Modify the vf2pf (virtual function to physical function) data write path. Use `ttm_resource_manager_used()` to check validity: if the manager is usable, calculate `fb_usage` from VRAM usage; otherwise, set `fb_usage` to 0 (APUs have no discrete framebuffer to report). This approach is more robust than APU-specific checks because it: - Works for all scenarios where the VRAM manager is uninitialized (not just APUs), - Aligns with TTM's design by using its native helper function, - Preserves correct behavior for discrete GPUs (which have fully initialized `man->bdev` and pass the `ttm_resource_manager_used()` check). v4: use ttm_resource_manager_used(&adev->mman.vram_mgr.manager) instead of checking the adev->gmc.is_app_apu flag (Christian)
CVE-2025-40289: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: hide VRAM sysfs attributes on GPUs without VRAM Otherwise accessing them can cause a crash.
CVE-2025-40303: In the Linux kernel, the following vulnerability has been resolved: btrfs: ensure no dirty metadata is written back for an fs with errors [BUG] During development of a minor feature (make sure all btrfs_bio::end_io() is called in task context), I noticed a crash in generic/388, where metadata writes triggered new works after btrfs_stop_all_workers(). It turns out that it can even happen without any code modification, just using RAID5 for metadata and the same workload from generic/388 is going to trigger the use-after-free. [CAUSE] If btrfs hits an error, the fs is marked as error, no new transaction is allowed thus metadata is in a frozen state. But there are some metadata modifications before that error, and they are still in the btree inode page cache. Since there will be no real transaction commit, all those dirty folios are just kept as is in the page cache, and they can not be invalidated by invalidate_inode_pages2() call inside close_ctree(), because they are dirty. And finally after btrfs_stop_all_workers(), we call iput() on btree inode, which triggers writeback of those dirty metadata. And if the fs is using RAID56 metadata, this will trigger RMW and queue new works into rmw_workers, which is already stopped, causing warning from queue_work() and use-after-free. [FIX] Add a special handling for write_one_eb(), that if the fs is already in an error state, immediately mark the bbio as failure, instead of really submitting them. Then during close_ctree(), iput() will just discard all those dirty tree blocks without really writing them back, thus no more new jobs for already stopped-and-freed workqueues. The extra discard in write_one_eb() also acts as an extra safenet. E.g. the transaction abort is triggered by some extent/free space tree corruptions, and since extent/free space tree is already corrupted some tree blocks may be allocated where they shouldn't be (overwriting existing tree blocks). In that case writing them back will further corrupting the fs.
CVE-2025-40307: In the Linux kernel, the following vulnerability has been resolved: exfat: validate cluster allocation bits of the allocation bitmap syzbot created an exfat image with cluster bits not set for the allocation bitmap. exfat-fs reads and uses the allocation bitmap without checking this. The problem is that if the start cluster of the allocation bitmap is 6, cluster 6 can be allocated when creating a directory with mkdir. exfat zeros out this cluster in exfat_mkdir, which can delete existing entries. This can reallocate the allocated entries. In addition, the allocation bitmap is also zeroed out, so cluster 6 can be reallocated. This patch adds exfat_test_bitmap_range to validate that clusters used for the allocation bitmap are correctly marked as in-use.
CVE-2025-40311: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: support mapping cb with vmalloc-backed coherent memory When IOMMU is enabled, dma_alloc_coherent() with GFP_USER may return addresses from the vmalloc range. If such an address is mapped without VM_MIXEDMAP, vm_insert_page() will trigger a BUG_ON due to the VM_PFNMAP restriction. Fix this by checking for vmalloc addresses and setting VM_MIXEDMAP in the VMA before mapping. This ensures safe mapping and avoids kernel crashes. The memory is still driver-allocated and cannot be accessed directly by userspace.
CVE-2025-40314: In the Linux kernel, the following vulnerability has been resolved: usb: cdns3: gadget: Use-after-free during failed initialization and exit of cdnsp gadget In the __cdnsp_gadget_init() and cdnsp_gadget_exit() functions, the gadget structure (pdev->gadget) was freed before its endpoints. The endpoints are linked via the ep_list in the gadget structure. Freeing the gadget first leaves dangling pointers in the endpoint list. When the endpoints are subsequently freed, this results in a use-after-free. Fix: By separating the usb_del_gadget_udc() operation into distinct "del" and "put" steps, cdnsp_gadget_free_endpoints() can be executed prior to the final release of the gadget structure with usb_put_gadget(). A patch similar to bb9c74a5bd14("usb: dwc3: gadget: Free gadget structure only after freeing endpoints").
CVE-2025-40323: In the Linux kernel, the following vulnerability has been resolved: fbcon: Set fb_display[i]->mode to NULL when the mode is released Recently, we discovered the following issue through syzkaller: BUG: KASAN: slab-use-after-free in fb_mode_is_equal+0x285/0x2f0 Read of size 4 at addr ff11000001b3c69c by task syz.xxx ... Call Trace: <TASK> dump_stack_lvl+0xab/0xe0 print_address_description.constprop.0+0x2c/0x390 print_report+0xb9/0x280 kasan_report+0xb8/0xf0 fb_mode_is_equal+0x285/0x2f0 fbcon_mode_deleted+0x129/0x180 fb_set_var+0xe7f/0x11d0 do_fb_ioctl+0x6a0/0x750 fb_ioctl+0xe0/0x140 __x64_sys_ioctl+0x193/0x210 do_syscall_64+0x5f/0x9c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e Based on experimentation and analysis, during framebuffer unregistration, only the memory of fb_info->modelist is freed, without setting the corresponding fb_display[i]->mode to NULL for the freed modes. This leads to UAF issues during subsequent accesses. Here's an example of reproduction steps: 1. With /dev/fb0 already registered in the system, load a kernel module to register a new device /dev/fb1; 2. Set fb1's mode to the global fb_display[] array (via FBIOPUT_CON2FBMAP); 3. Switch console from fb to VGA (to allow normal rmmod of the ko); 4. Unload the kernel module, at this point fb1's modelist is freed, leaving a wild pointer in fb_display[]; 5. Trigger the bug via system calls through fb0 attempting to delete a mode from fb0. Add a check in do_unregister_framebuffer(): if the mode to be freed exists in fb_display[], set the corresponding mode pointer to NULL.
CVE-2025-40333: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix infinite loop in __insert_extent_tree() When we get wrong extent info data, and look up extent_node in rb tree, it will cause infinite loop (CONFIG_F2FS_CHECK_FS=n). Avoiding this by return NULL and print some kernel messages in that case.
CVE-2025-40337: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: Correctly handle Rx checksum offload errors The stmmac_rx function would previously set skb->ip_summed to CHECKSUM_UNNECESSARY if hardware checksum offload (CoE) was enabled and the packet was of a known IP ethertype. However, this logic failed to check if the hardware had actually reported a checksum error. The hardware status, indicating a header or payload checksum failure, was being ignored at this stage. This could cause corrupt packets to be passed up the network stack as valid. This patch corrects the logic by checking the `csum_none` status flag, which is set when the hardware reports a checksum error. If this flag is set, skb->ip_summed is now correctly set to CHECKSUM_NONE, ensuring the kernel's network stack will perform its own validation and properly handle the corrupt packet.
CVE-2025-40339: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix nullptr err of vm_handle_moved If a amdgpu_bo_va is fpriv->prt_va, the bo of this one is always NULL. So, such kind of amdgpu_bo_va should be updated separately before amdgpu_vm_handle_moved.
CVE-2025-40341: In the Linux kernel, the following vulnerability has been resolved: futex: Don't leak robust_list pointer on exec race sys_get_robust_list() and compat_get_robust_list() use ptrace_may_access() to check if the calling task is allowed to access another task's robust_list pointer. This check is racy against a concurrent exec() in the target process. During exec(), a task may transition from a non-privileged binary to a privileged one (e.g., setuid binary) and its credentials/memory mappings may change. If get_robust_list() performs ptrace_may_access() before this transition, it may erroneously allow access to sensitive information after the target becomes privileged. A racy access allows an attacker to exploit a window during which ptrace_may_access() passes before a target process transitions to a privileged state via exec(). For example, consider a non-privileged task T that is about to execute a setuid-root binary. An attacker task A calls get_robust_list(T) while T is still unprivileged. Since ptrace_may_access() checks permissions based on current credentials, it succeeds. However, if T begins exec immediately afterwards, it becomes privileged and may change its memory mappings. Because get_robust_list() proceeds to access T->robust_list without synchronizing with exec() it may read user-space pointers from a now-privileged process. This violates the intended post-exec access restrictions and could expose sensitive memory addresses or be used as a primitive in a larger exploit chain. Consequently, the race can lead to unauthorized disclosure of information across privilege boundaries and poses a potential security risk. Take a read lock on signal->exec_update_lock prior to invoking ptrace_may_access() and accessing the robust_list/compat_robust_list. This ensures that the target task's exec state remains stable during the check, allowing for consistent and synchronized validation of credentials.
CVE-2025-40343: In the Linux kernel, the following vulnerability has been resolved: nvmet-fc: avoid scheduling association deletion twice When forcefully shutting down a port via the configfs interface, nvmet_port_subsys_drop_link() first calls nvmet_port_del_ctrls() and then nvmet_disable_port(). Both functions will eventually schedule all remaining associations for deletion. The current implementation checks whether an association is about to be removed, but only after the work item has already been scheduled. As a result, it is possible for the first scheduled work item to free all resources, and then for the same work item to be scheduled again for deletion. Because the association list is an RCU list, it is not possible to take a lock and remove the list entry directly, so it cannot be looked up again. Instead, a flag (terminating) must be used to determine whether the association is already in the process of being deleted.
CVE-2025-40347: In the Linux kernel, the following vulnerability has been resolved: net: enetc: fix the deadlock of enetc_mdio_lock After applying the workaround for err050089, the LS1028A platform experiences RCU stalls on RT kernel. This issue is caused by the recursive acquisition of the read lock enetc_mdio_lock. Here list some of the call stacks identified under the enetc_poll path that may lead to a deadlock: enetc_poll -> enetc_lock_mdio -> enetc_clean_rx_ring OR napi_complete_done -> napi_gro_receive -> enetc_start_xmit -> enetc_lock_mdio -> enetc_map_tx_buffs -> enetc_unlock_mdio -> enetc_unlock_mdio After enetc_poll acquires the read lock, a higher-priority writer attempts to acquire the lock, causing preemption. The writer detects that a read lock is already held and is scheduled out. However, readers under enetc_poll cannot acquire the read lock again because a writer is already waiting, leading to a thread hang. Currently, the deadlock is avoided by adjusting enetc_lock_mdio to prevent recursive lock acquisition.
CVE-2025-40354: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: increase max link count and fix link->enc NULL pointer access [why] 1.) dc->links[MAX_LINKS] array size smaller than actual requested. max_connector + max_dpia + 4 virtual = 14. increase from 12 to 14. 2.) hw_init() access null LINK_ENC for dpia non display_endpoint. (cherry picked from commit d7f5a61e1b04ed87b008c8d327649d184dc5bb45)
CVE-2025-40355: In the Linux kernel, the following vulnerability has been resolved: sysfs: check visibility before changing group attribute ownership Since commit 0c17270f9b92 ("net: sysfs: Implement is_visible for phys_(port_id, port_name, switch_id)"), __dev_change_net_namespace() can hit WARN_ON() when trying to change owner of a file that isn't visible. See the trace below: WARNING: CPU: 6 PID: 2938 at net/core/dev.c:12410 __dev_change_net_namespace+0xb89/0xc30 CPU: 6 UID: 0 PID: 2938 Comm: incusd Not tainted 6.17.1-1-mainline #1 PREEMPT(full) 4b783b4a638669fb644857f484487d17cb45ed1f Hardware name: Framework Laptop 13 (AMD Ryzen 7040Series)/FRANMDCP07, BIOS 03.07 02/19/2025 RIP: 0010:__dev_change_net_namespace+0xb89/0xc30 [...] Call Trace: <TASK> ? if6_seq_show+0x30/0x50 do_setlink.isra.0+0xc7/0x1270 ? __nla_validate_parse+0x5c/0xcc0 ? security_capable+0x94/0x1a0 rtnl_newlink+0x858/0xc20 ? update_curr+0x8e/0x1c0 ? update_entity_lag+0x71/0x80 ? sched_balance_newidle+0x358/0x450 ? psi_task_switch+0x113/0x2a0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x346/0x3e0 ? sched_clock+0x10/0x30 ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x59/0x110 netlink_unicast+0x285/0x3c0 ? __alloc_skb+0xdb/0x1a0 netlink_sendmsg+0x20d/0x430 ____sys_sendmsg+0x39f/0x3d0 ? import_iovec+0x2f/0x40 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x81/0x970 ? __sys_bind+0xe3/0x110 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? sock_alloc_file+0x63/0xc0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? alloc_fd+0x12e/0x190 ? put_unused_fd+0x2a/0x70 ? do_sys_openat2+0xa2/0xe0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? exc_page_fault+0x7e/0x1a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e [...] </TASK> Fix this by checking is_visible() before trying to touch the attribute.
CVE-2025-40358: In the Linux kernel, the following vulnerability has been resolved: riscv: stacktrace: Disable KASAN checks for non-current tasks Unwinding the stack of a task other than current, KASAN would report "BUG: KASAN: out-of-bounds in walk_stackframe+0x41c/0x460" There is a same issue on x86 and has been resolved by the commit 84936118bdf3 ("x86/unwind: Disable KASAN checks for non-current tasks") The solution could be applied to RISC-V too. This patch also can solve the issue: https://seclists.org/oss-sec/2025/q4/23 [pjw@kernel.org: clean up checkpatch issues]
CVE-2025-54505:
CVE-2025-68173: In the Linux kernel, the following vulnerability has been resolved: ftrace: Fix softlockup in ftrace_module_enable A soft lockup was observed when loading amdgpu module. If a module has a lot of tracable functions, multiple calls to kallsyms_lookup can spend too much time in RCU critical section and with disabled preemption, causing kernel panic. This is the same issue that was fixed in commit d0b24b4e91fc ("ftrace: Prevent RCU stall on PREEMPT_VOLUNTARY kernels") and commit 42ea22e754ba ("ftrace: Add cond_resched() to ftrace_graph_set_hash()"). Fix it the same way by adding cond_resched() in ftrace_module_enable.
CVE-2025-68188: In the Linux kernel, the following vulnerability has been resolved: tcp: use dst_dev_rcu() in tcp_fastopen_active_disable_ofo_check() Use RCU to avoid a pair of atomic operations and a potential UAF on dst_dev()->flags.
CVE-2025-68190: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/atom: Check kcalloc() for WS buffer in amdgpu_atom_execute_table_locked() kcalloc() may fail. When WS is non-zero and allocation fails, ectx.ws remains NULL while ectx.ws_size is set, leading to a potential NULL pointer dereference in atom_get_src_int() when accessing WS entries. Return -ENOMEM on allocation failure to avoid the NULL dereference.
CVE-2025-68206: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: add seqadj extension for natted connections Sequence adjustment may be required for FTP traffic with PASV/EPSV modes. due to need to re-write packet payload (IP, port) on the ftp control connection. This can require changes to the TCP length and expected seq / ack_seq. The easiest way to reproduce this issue is with PASV mode. Example ruleset: table inet ftp_nat { ct helper ftp_helper { type "ftp" protocol tcp l3proto inet } chain prerouting { type filter hook prerouting priority 0; policy accept; tcp dport 21 ct state new ct helper set "ftp_helper" } } table ip nat { chain prerouting { type nat hook prerouting priority -100; policy accept; tcp dport 21 dnat ip prefix to ip daddr map { 192.168.100.1 : 192.168.13.2/32 } } chain postrouting { type nat hook postrouting priority 100 ; policy accept; tcp sport 21 snat ip prefix to ip saddr map { 192.168.13.2 : 192.168.100.1/32 } } } Note that the ftp helper gets assigned *after* the dnat setup. The inverse (nat after helper assign) is handled by an existing check in nf_nat_setup_info() and will not show the problem. Topoloy: +-------------------+ +----------------------------------+ | FTP: 192.168.13.2 | <-> | NAT: 192.168.13.3, 192.168.100.1 | +-------------------+ +----------------------------------+ | +-----------------------+ | Client: 192.168.100.2 | +-----------------------+ ftp nat changes do not work as expected in this case: Connected to 192.168.100.1. [..] ftp> epsv EPSV/EPRT on IPv4 off. ftp> ls 227 Entering passive mode (192,168,100,1,209,129). 421 Service not available, remote server has closed connection. Kernel logs: Missing nfct_seqadj_ext_add() setup call WARNING: CPU: 1 PID: 0 at net/netfilter/nf_conntrack_seqadj.c:41 [..] __nf_nat_mangle_tcp_packet+0x100/0x160 [nf_nat] nf_nat_ftp+0x142/0x280 [nf_nat_ftp] help+0x4d1/0x880 [nf_conntrack_ftp] nf_confirm+0x122/0x2e0 [nf_conntrack] nf_hook_slow+0x3c/0xb0 .. Fix this by adding the required extension when a conntrack helper is assigned to a connection that has a nat binding.
CVE-2025-68223: In the Linux kernel, the following vulnerability has been resolved: drm/radeon: delete radeon_fence_process in is_signaled, no deadlock Delete the attempt to progress the queue when checking if fence is signaled. This avoids deadlock. dma-fence_ops::signaled can be called with the fence lock in unknown state. For radeon, the fence lock is also the wait queue lock. This can cause a self deadlock when signaled() tries to make forward progress on the wait queue. But advancing the queue is unneeded because incorrectly returning false from signaled() is perfectly acceptable. (cherry picked from commit 527ba26e50ec2ca2be9c7c82f3ad42998a75d0db)
CVE-2025-68231: In the Linux kernel, the following vulnerability has been resolved: mm/mempool: fix poisoning order>0 pages with HIGHMEM The kernel test has reported: BUG: unable to handle page fault for address: fffba000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page *pde = 03171067 *pte = 00000000 Oops: Oops: 0002 [#1] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G T 6.18.0-rc2-00031-gec7f31b2a2d3 #1 NONE a1d066dfe789f54bc7645c7989957d2bdee593ca Tainted: [T]=RANDSTRUCT Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 EIP: memset (arch/x86/include/asm/string_32.h:168 arch/x86/lib/memcpy_32.c:17) Code: a5 8b 4d f4 83 e1 03 74 02 f3 a4 83 c4 04 5e 5f 5d 2e e9 73 41 01 00 90 90 90 3e 8d 74 26 00 55 89 e5 57 56 89 c6 89 d0 89 f7 <f3> aa 89 f0 5e 5f 5d 2e e9 53 41 01 00 cc cc cc 55 89 e5 53 57 56 EAX: 0000006b EBX: 00000015 ECX: 001fefff EDX: 0000006b ESI: fffb9000 EDI: fffba000 EBP: c611fbf0 ESP: c611fbe8 DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068 EFLAGS: 00010287 CR0: 80050033 CR2: fffba000 CR3: 0316e000 CR4: 00040690 Call Trace: poison_element (mm/mempool.c:83 mm/mempool.c:102) mempool_init_node (mm/mempool.c:142 mm/mempool.c:226) mempool_init_noprof (mm/mempool.c:250 (discriminator 1)) ? mempool_alloc_pages (mm/mempool.c:640) bio_integrity_initfn (block/bio-integrity.c:483 (discriminator 8)) ? mempool_alloc_pages (mm/mempool.c:640) do_one_initcall (init/main.c:1283) Christoph found out this is due to the poisoning code not dealing properly with CONFIG_HIGHMEM because only the first page is mapped but then the whole potentially high-order page is accessed. We could give up on HIGHMEM here, but it's straightforward to fix this with a loop that's mapping, poisoning or checking and unmapping individual pages.
CVE-2025-68236: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: ufs-qcom: Fix UFS OCP issue during UFS power down (PC=3) According to UFS specifications, the power-off sequence for a UFS device includes: - Sending an SSU command with Power_Condition=3 and await a response. - Asserting RST_N low. - Turning off REF_CLK. - Turning off VCC. - Turning off VCCQ/VCCQ2. As part of ufs shutdown, after the SSU command completion, asserting hardware reset (HWRST) triggers the device firmware to wake up and execute its reset routine. This routine initializes hardware blocks and takes a few milliseconds to complete. During this time, the ICCQ draws a large current. This large ICCQ current may cause issues for the regulator which is supplying power to UFS, because the turn off request from UFS driver to the regulator framework will be immediately followed by low power mode(LPM) request by regulator framework. This is done by framework because UFS which is the only client is requesting for disable. So if the rail is still in the process of shutting down while ICCQ exceeds LPM current thresholds, and LPM mode is activated in hardware during this state, it may trigger an overcurrent protection (OCP) fault in the regulator. To prevent this, a 10ms delay is added after asserting HWRST. This allows the reset operation to complete while power rails remain active and in high-power mode. Currently there is no way for Host to query whether the reset is completed or not and hence this the delay is based on experiments with Qualcomm UFS controllers across multiple UFS vendors.
CVE-2025-68239: In the Linux kernel, the following vulnerability has been resolved: binfmt_misc: restore write access before closing files opened by open_exec() bm_register_write() opens an executable file using open_exec(), which internally calls do_open_execat() and denies write access on the file to avoid modification while it is being executed. However, when an error occurs, bm_register_write() closes the file using filp_close() directly. This does not restore the write permission, which may cause subsequent write operations on the same file to fail. Fix this by calling exe_file_allow_write_access() before filp_close() to restore the write permission properly.
CVE-2025-68254: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: fix out-of-bounds read in OnBeacon ESR IE parsing The Extended Supported Rates (ESR) IE handling in OnBeacon accessed *(p + 1 + ielen) and *(p + 2 + ielen) without verifying that these offsets lie within the received frame buffer. A malformed beacon with an ESR IE positioned at the end of the buffer could cause an out-of-bounds read, potentially triggering a kernel panic. Add a boundary check to ensure that the ESR IE body and the subsequent bytes are within the limits of the frame before attempting to access them. This prevents OOB reads caused by malformed beacon frames.
CVE-2025-68256: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: fix out-of-bounds read in rtw_get_ie() parser The Information Element (IE) parser rtw_get_ie() trusted the length byte of each IE without validating that the IE body (len bytes after the 2-byte header) fits inside the remaining frame buffer. A malformed frame can advertise an IE length larger than the available data, causing the parser to increment its pointer beyond the buffer end. This results in out-of-bounds reads or, depending on the pattern, an infinite loop. Fix by validating that (offset + 2 + len) does not exceed the limit before accepting the IE or advancing to the next element. This prevents OOB reads and ensures the parser terminates safely on malformed frames.
CVE-2025-68283: In the Linux kernel, the following vulnerability has been resolved: libceph: replace BUG_ON with bounds check for map->max_osd OSD indexes come from untrusted network packets. Boundary checks are added to validate these against map->max_osd. [ idryomov: drop BUG_ON in ceph_get_primary_affinity(), minor cosmetic edits ]
CVE-2025-68296: In the Linux kernel, the following vulnerability has been resolved: drm, fbcon, vga_switcheroo: Avoid race condition in fbcon setup Protect vga_switcheroo_client_fb_set() with console lock. Avoids OOB access in fbcon_remap_all(). Without holding the console lock the call races with switching outputs. VGA switcheroo calls fbcon_remap_all() when switching clients. The fbcon function uses struct fb_info.node, which is set by register_framebuffer(). As the fb-helper code currently sets up VGA switcheroo before registering the framebuffer, the value of node is -1 and therefore not a legal value. For example, fbcon uses the value within set_con2fb_map() [1] as an index into an array. Moving vga_switcheroo_client_fb_set() after register_framebuffer() can result in VGA switching that does not switch fbcon correctly. Therefore move vga_switcheroo_client_fb_set() under fbcon_fb_registered(), which already holds the console lock. Fbdev calls fbcon_fb_registered() from within register_framebuffer(). Serializes the helper with VGA switcheroo's call to fbcon_remap_all(). Although vga_switcheroo_client_fb_set() takes an instance of struct fb_info as parameter, it really only needs the contained fbcon state. Moving the call to fbcon initialization is therefore cleaner than before. Only amdgpu, i915, nouveau and radeon support vga_switcheroo. For all other drivers, this change does nothing.
CVE-2025-68303: In the Linux kernel, the following vulnerability has been resolved: platform/x86: intel: punit_ipc: fix memory corruption This passes the address of the pointer "&punit_ipcdev" when the intent was to pass the pointer itself "punit_ipcdev" (without the ampersand). This means that the: complete(&ipcdev->cmd_complete); in intel_punit_ioc() will write to a wrong memory address corrupting it.
CVE-2025-68307: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: gs_usb_xmit_callback(): fix handling of failed transmitted URBs The driver lacks the cleanup of failed transfers of URBs. This reduces the number of available URBs per error by 1. This leads to reduced performance and ultimately to a complete stop of the transmission. If the sending of a bulk URB fails do proper cleanup: - increase netdev stats - mark the echo_sbk as free - free the driver's context and do accounting - wake the send queue
CVE-2025-68315: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to detect potential corrupted nid in free_nid_list As reported, on-disk footer.ino and footer.nid is the same and out-of-range, let's add sanity check on f2fs_alloc_nid() to detect any potential corruption in free_nid_list.
CVE-2025-68321: In the Linux kernel, the following vulnerability has been resolved: page_pool: always add GFP_NOWARN for ATOMIC allocations Driver authors often forget to add GFP_NOWARN for page allocation from the datapath. This is annoying to users as OOMs are a fact of life, and we pretty much expect network Rx to hit page allocation failures during OOM. Make page pool add GFP_NOWARN for ATOMIC allocations by default.
CVE-2025-68322: In the Linux kernel, the following vulnerability has been resolved: parisc: Avoid crash due to unaligned access in unwinder Guenter Roeck reported this kernel crash on his emulated B160L machine: Starting network: udhcpc: started, v1.36.1 Backtrace: [<104320d4>] unwind_once+0x1c/0x5c [<10434a00>] walk_stackframe.isra.0+0x74/0xb8 [<10434a6c>] arch_stack_walk+0x28/0x38 [<104e5efc>] stack_trace_save+0x48/0x5c [<105d1bdc>] set_track_prepare+0x44/0x6c [<105d9c80>] ___slab_alloc+0xfc4/0x1024 [<105d9d38>] __slab_alloc.isra.0+0x58/0x90 [<105dc80c>] kmem_cache_alloc_noprof+0x2ac/0x4a0 [<105b8e54>] __anon_vma_prepare+0x60/0x280 [<105a823c>] __vmf_anon_prepare+0x68/0x94 [<105a8b34>] do_wp_page+0x8cc/0xf10 [<105aad88>] handle_mm_fault+0x6c0/0xf08 [<10425568>] do_page_fault+0x110/0x440 [<10427938>] handle_interruption+0x184/0x748 [<11178398>] schedule+0x4c/0x190 BUG: spinlock recursion on CPU#0, ifconfig/2420 lock: terminate_lock.2+0x0/0x1c, .magic: dead4ead, .owner: ifconfig/2420, .owner_cpu: 0 While creating the stack trace, the unwinder uses the stack pointer to guess the previous frame to read the previous stack pointer from memory. The crash happens, because the unwinder tries to read from unaligned memory and as such triggers the unalignment trap handler which then leads to the spinlock recursion and finally to a deadlock. Fix it by checking the alignment before accessing the memory.
CVE-2025-68324: In the Linux kernel, the following vulnerability has been resolved: scsi: imm: Fix use-after-free bug caused by unfinished delayed work The delayed work item 'imm_tq' is initialized in imm_attach() and scheduled via imm_queuecommand() for processing SCSI commands. When the IMM parallel port SCSI host adapter is detached through imm_detach(), the imm_struct device instance is deallocated. However, the delayed work might still be pending or executing when imm_detach() is called, leading to use-after-free bugs when the work function imm_interrupt() accesses the already freed imm_struct memory. The race condition can occur as follows: CPU 0(detach thread) | CPU 1 | imm_queuecommand() | imm_queuecommand_lck() imm_detach() | schedule_delayed_work() kfree(dev) //FREE | imm_interrupt() | dev = container_of(...) //USE dev-> //USE Add disable_delayed_work_sync() in imm_detach() to guarantee proper cancellation of the delayed work item before imm_struct is deallocated.
CVE-2025-68330: In the Linux kernel, the following vulnerability has been resolved: iio: accel: bmc150: Fix irq assumption regression The code in bmc150-accel-core.c unconditionally calls bmc150_accel_set_interrupt() in the iio_buffer_setup_ops, such as on the runtime PM resume path giving a kernel splat like this if the device has no interrupts: Unable to handle kernel NULL pointer dereference at virtual address 00000001 when read PC is at bmc150_accel_set_interrupt+0x98/0x194 LR is at __pm_runtime_resume+0x5c/0x64 (...) Call trace: bmc150_accel_set_interrupt from bmc150_accel_buffer_postenable+0x40/0x108 bmc150_accel_buffer_postenable from __iio_update_buffers+0xbe0/0xcbc __iio_update_buffers from enable_store+0x84/0xc8 enable_store from kernfs_fop_write_iter+0x154/0x1b4 This bug seems to have been in the driver since the beginning, but it only manifests recently, I do not know why. Store the IRQ number in the state struct, as this is a common pattern in other drivers, then use this to determine if we have IRQ support or not.
CVE-2025-68335: In the Linux kernel, the following vulnerability has been resolved: comedi: pcl818: fix null-ptr-deref in pcl818_ai_cancel() Syzbot identified an issue [1] in pcl818_ai_cancel(), which stems from the fact that in case of early device detach via pcl818_detach(), subdevice dev->read_subdev may not have initialized its pointer to &struct comedi_async as intended. Thus, any such dereferencing of &s->async->cmd will lead to general protection fault and kernel crash. Mitigate this problem by removing a call to pcl818_ai_cancel() from pcl818_detach() altogether. This way, if the subdevice setups its support for async commands, everything async-related will be handled via subdevice's own ->cancel() function in comedi_device_detach_locked() even before pcl818_detach(). If no support for asynchronous commands is provided, there is no need to cancel anything either. [1] Syzbot crash: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] CPU: 1 UID: 0 PID: 6050 Comm: syz.0.18 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025 RIP: 0010:pcl818_ai_cancel+0x69/0x3f0 drivers/comedi/drivers/pcl818.c:762 ... Call Trace: <TASK> pcl818_detach+0x66/0xd0 drivers/comedi/drivers/pcl818.c:1115 comedi_device_detach_locked+0x178/0x750 drivers/comedi/drivers.c:207 do_devconfig_ioctl drivers/comedi/comedi_fops.c:848 [inline] comedi_unlocked_ioctl+0xcde/0x1020 drivers/comedi/comedi_fops.c:2178 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] ...
CVE-2025-68340: In the Linux kernel, the following vulnerability has been resolved: team: Move team device type change at the end of team_port_add Attempting to add a port device that is already up will expectedly fail, but not before modifying the team device header_ops. In the case of the syzbot reproducer the gre0 device is already in state UP when it attempts to add it as a port device of team0, this fails but before that header_ops->create of team0 is changed from eth_header to ipgre_header in the call to team_dev_type_check_change. Later when we end up in ipgre_header() struct ip_tunnel* points to nonsense as the private data of the device still holds a struct team. Example sequence of iproute2 commands to reproduce the hang/BUG(): ip link add dev team0 type team ip link add dev gre0 type gre ip link set dev gre0 up ip link set dev gre0 master team0 ip link set dev team0 up ping -I team0 1.1.1.1 Move team_dev_type_check_change down where all other checks have passed as it changes the dev type with no way to restore it in case one of the checks that follow it fail. Also make sure to preserve the origial mtu assignment: - If port_dev is not the same type as dev, dev takes mtu from port_dev - If port_dev is the same type as dev, port_dev takes mtu from dev This is done by adding a conditional before the call to dev_set_mtu to prevent it from assigning port_dev->mtu = dev->mtu and instead letting team_dev_type_check_change assign dev->mtu = port_dev->mtu. The conditional is needed because the patch moves the call to team_dev_type_check_change past dev_set_mtu. Testing: - team device driver in-tree selftests - Add/remove various devices as slaves of team device - syzbot
CVE-2025-68342: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing data The URB received in gs_usb_receive_bulk_callback() contains a struct gs_host_frame. The length of the data after the header depends on the gs_host_frame hf::flags and the active device features (e.g. time stamping). Introduce a new function gs_usb_get_minimum_length() and check that we have at least received the required amount of data before accessing it. Only copy the data to that skb that has actually been received. [mkl: rename gs_usb_get_minimum_length() -> +gs_usb_get_minimum_rx_length()]
CVE-2025-68343: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing header The driver expects to receive a struct gs_host_frame in gs_usb_receive_bulk_callback(). Use struct_group to describe the header of the struct gs_host_frame and check that we have at least received the header before accessing any members of it. To resubmit the URB, do not dereference the pointer chain "dev->parent->hf_size_rx" but use "parent->hf_size_rx" instead. Since "urb->context" contains "parent", it is always defined, while "dev" is not defined if the URB it too short.
CVE-2025-68358: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix racy bitfield write in btrfs_clear_space_info_full() From the memory-barriers.txt document regarding memory barrier ordering guarantees: (*) These guarantees do not apply to bitfields, because compilers often generate code to modify these using non-atomic read-modify-write sequences. Do not attempt to use bitfields to synchronize parallel algorithms. (*) Even in cases where bitfields are protected by locks, all fields in a given bitfield must be protected by one lock. If two fields in a given bitfield are protected by different locks, the compiler's non-atomic read-modify-write sequences can cause an update to one field to corrupt the value of an adjacent field. btrfs_space_info has a bitfield sharing an underlying word consisting of the fields full, chunk_alloc, and flush: struct btrfs_space_info { struct btrfs_fs_info * fs_info; /* 0 8 */ struct btrfs_space_info * parent; /* 8 8 */ ... int clamp; /* 172 4 */ unsigned int full:1; /* 176: 0 4 */ unsigned int chunk_alloc:1; /* 176: 1 4 */ unsigned int flush:1; /* 176: 2 4 */ ... Therefore, to be safe from parallel read-modify-writes losing a write to one of the bitfield members protected by a lock, all writes to all the bitfields must use the lock. They almost universally do, except for btrfs_clear_space_info_full() which iterates over the space_infos and writes out found->full = 0 without a lock. Imagine that we have one thread completing a transaction in which we finished deleting a block_group and are thus calling btrfs_clear_space_info_full() while simultaneously the data reclaim ticket infrastructure is running do_async_reclaim_data_space(): T1 T2 btrfs_commit_transaction btrfs_clear_space_info_full data_sinfo->full = 0 READ: full:0, chunk_alloc:0, flush:1 do_async_reclaim_data_space(data_sinfo) spin_lock(&space_info->lock); if(list_empty(tickets)) space_info->flush = 0; READ: full: 0, chunk_alloc:0, flush:1 MOD/WRITE: full: 0, chunk_alloc:0, flush:0 spin_unlock(&space_info->lock); return; MOD/WRITE: full:0, chunk_alloc:0, flush:1 and now data_sinfo->flush is 1 but the reclaim worker has exited. This breaks the invariant that flush is 0 iff there is no work queued or running. Once this invariant is violated, future allocations that go into __reserve_bytes() will add tickets to space_info->tickets but will see space_info->flush is set to 1 and not queue the work. After this, they will block forever on the resulting ticket, as it is now impossible to kick the worker again. I also confirmed by looking at the assembly of the affected kernel that it is doing RMW operations. For example, to set the flush (3rd) bit to 0, the assembly is: andb $0xfb,0x60(%rbx) and similarly for setting the full (1st) bit to 0: andb $0xfe,-0x20(%rax) So I think this is really a bug on practical systems. I have observed a number of systems in this exact state, but am currently unable to reproduce it. Rather than leaving this footgun lying around for the future, take advantage of the fact that there is room in the struct anyway, and that it is already quite large and simply change the three bitfield members to bools. This avoids writes to space_info->full having any effect on ---truncated---
CVE-2025-68378: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix stackmap overflow check in __bpf_get_stackid() Syzkaller reported a KASAN slab-out-of-bounds write in __bpf_get_stackid() when copying stack trace data. The issue occurs when the perf trace contains more stack entries than the stack map bucket can hold, leading to an out-of-bounds write in the bucket's data array.
CVE-2025-68379: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Fix null deref on srq->rq.queue after resize failure A NULL pointer dereference can occur in rxe_srq_chk_attr() when ibv_modify_srq() is invoked twice in succession under certain error conditions. The first call may fail in rxe_queue_resize(), which leads rxe_srq_from_attr() to set srq->rq.queue = NULL. The second call then triggers a crash (null deref) when accessing srq->rq.queue->buf->index_mask. Call Trace: <TASK> rxe_modify_srq+0x170/0x480 [rdma_rxe] ? __pfx_rxe_modify_srq+0x10/0x10 [rdma_rxe] ? uverbs_try_lock_object+0x4f/0xa0 [ib_uverbs] ? rdma_lookup_get_uobject+0x1f0/0x380 [ib_uverbs] ib_uverbs_modify_srq+0x204/0x290 [ib_uverbs] ? __pfx_ib_uverbs_modify_srq+0x10/0x10 [ib_uverbs] ? tryinc_node_nr_active+0xe6/0x150 ? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x2c0/0x470 [ib_uverbs] ? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs] ? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs] ib_uverbs_run_method+0x55a/0x6e0 [ib_uverbs] ? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs] ib_uverbs_cmd_verbs+0x54d/0x800 [ib_uverbs] ? __pfx_ib_uverbs_cmd_verbs+0x10/0x10 [ib_uverbs] ? __pfx___raw_spin_lock_irqsave+0x10/0x10 ? __pfx_do_vfs_ioctl+0x10/0x10 ? ioctl_has_perm.constprop.0.isra.0+0x2c7/0x4c0 ? __pfx_ioctl_has_perm.constprop.0.isra.0+0x10/0x10 ib_uverbs_ioctl+0x13e/0x220 [ib_uverbs] ? __pfx_ib_uverbs_ioctl+0x10/0x10 [ib_uverbs] __x64_sys_ioctl+0x138/0x1c0 do_syscall_64+0x82/0x250 ? fdget_pos+0x58/0x4c0 ? ksys_write+0xf3/0x1c0 ? __pfx_ksys_write+0x10/0x10 ? do_syscall_64+0xc8/0x250 ? __pfx_vm_mmap_pgoff+0x10/0x10 ? fget+0x173/0x230 ? fput+0x2a/0x80 ? ksys_mmap_pgoff+0x224/0x4c0 ? do_syscall_64+0xc8/0x250 ? do_user_addr_fault+0x37b/0xfe0 ? clear_bhb_loop+0x50/0xa0 ? clear_bhb_loop+0x50/0xa0 ? clear_bhb_loop+0x50/0xa0 entry_SYSCALL_64_after_hwframe+0x76/0x7e
CVE-2025-68742: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix invalid prog->stats access when update_effective_progs fails Syzkaller triggers an invalid memory access issue following fault injection in update_effective_progs. The issue can be described as follows: __cgroup_bpf_detach update_effective_progs compute_effective_progs bpf_prog_array_alloc <-- fault inject purge_effective_progs /* change to dummy_bpf_prog */ array->items[index] = &dummy_bpf_prog.prog ---softirq start--- __do_softirq ... __cgroup_bpf_run_filter_skb __bpf_prog_run_save_cb bpf_prog_run stats = this_cpu_ptr(prog->stats) /* invalid memory access */ flags = u64_stats_update_begin_irqsave(&stats->syncp) ---softirq end--- static_branch_dec(&cgroup_bpf_enabled_key[atype]) The reason is that fault injection caused update_effective_progs to fail and then changed the original prog into dummy_bpf_prog.prog in purge_effective_progs. Then a softirq came, and accessing the members of dummy_bpf_prog.prog in the softirq triggers invalid mem access. To fix it, skip updating stats when stats is NULL.
CVE-2025-68745: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Clear cmds after chip reset Commit aefed3e5548f ("scsi: qla2xxx: target: Fix offline port handling and host reset handling") caused two problems: 1. Commands sent to FW, after chip reset got stuck and never freed as FW is not going to respond to them anymore. 2. BUG_ON(cmd->sg_mapped) in qlt_free_cmd(). Commit 26f9ce53817a ("scsi: qla2xxx: Fix missed DMA unmap for aborted commands") attempted to fix this, but introduced another bug under different circumstances when two different CPUs were racing to call qlt_unmap_sg() at the same time: BUG_ON(!valid_dma_direction(dir)) in dma_unmap_sg_attrs(). So revert "scsi: qla2xxx: Fix missed DMA unmap for aborted commands" and partially revert "scsi: qla2xxx: target: Fix offline port handling and host reset handling" at __qla2x00_abort_all_cmds.
CVE-2025-68755: In the Linux kernel, the following vulnerability has been resolved: staging: most: remove broken i2c driver The MOST I2C driver has been completely broken for five years without anyone noticing so remove the driver from staging. Specifically, commit 723de0f9171e ("staging: most: remove device from interface structure") started requiring drivers to set the interface device pointer before registration, but the I2C driver was never updated which results in a NULL pointer dereference if anyone ever tries to probe it.
CVE-2025-68765: In the Linux kernel, the following vulnerability has been resolved: mt76: mt7615: Fix memory leak in mt7615_mcu_wtbl_sta_add() In mt7615_mcu_wtbl_sta_add(), an skb sskb is allocated. If the subsequent call to mt76_connac_mcu_alloc_wtbl_req() fails, the function returns an error without freeing sskb, leading to a memory leak. Fix this by calling dev_kfree_skb() on sskb in the error handling path to ensure it is properly released.
CVE-2025-68768: In the Linux kernel, the following vulnerability has been resolved: inet: frags: flush pending skbs in fqdir_pre_exit() We have been seeing occasional deadlocks on pernet_ops_rwsem since September in NIPA. The stuck task was usually modprobe (often loading a driver like ipvlan), trying to take the lock as a Writer. lockdep does not track readers for rwsems so the read wasn't obvious from the reports. On closer inspection the Reader holding the lock was conntrack looping forever in nf_conntrack_cleanup_net_list(). Based on past experience with occasional NIPA crashes I looked thru the tests which run before the crash and noticed that the crash follows ip_defrag.sh. An immediate red flag. Scouring thru (de)fragmentation queues reveals skbs sitting around, holding conntrack references. The problem is that since conntrack depends on nf_defrag_ipv6, nf_defrag_ipv6 will load first. Since nf_defrag_ipv6 loads first its netns exit hooks run _after_ conntrack's netns exit hook. Flush all fragment queue SKBs during fqdir_pre_exit() to release conntrack references before conntrack cleanup runs. Also flush the queues in timer expiry handlers when they discover fqdir->dead is set, in case packet sneaks in while we're running the pre_exit flush. The commit under Fixes is not exactly the culprit, but I think previously the timer firing would eventually unblock the spinning conntrack.
CVE-2025-68772: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid updating compression context during writeback Bai, Shuangpeng <sjb7183@psu.edu> reported a bug as below: Oops: divide error: 0000 [#1] SMP KASAN PTI CPU: 0 UID: 0 PID: 11441 Comm: syz.0.46 Not tainted 6.17.0 #1 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:f2fs_all_cluster_page_ready+0x106/0x550 fs/f2fs/compress.c:857 Call Trace: <TASK> f2fs_write_cache_pages fs/f2fs/data.c:3078 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3290 [inline] f2fs_write_data_pages+0x1c19/0x3600 fs/f2fs/data.c:3317 do_writepages+0x38e/0x640 mm/page-writeback.c:2634 filemap_fdatawrite_wbc mm/filemap.c:386 [inline] __filemap_fdatawrite_range mm/filemap.c:419 [inline] file_write_and_wait_range+0x2ba/0x3e0 mm/filemap.c:794 f2fs_do_sync_file+0x6e6/0x1b00 fs/f2fs/file.c:294 generic_write_sync include/linux/fs.h:3043 [inline] f2fs_file_write_iter+0x76e/0x2700 fs/f2fs/file.c:5259 new_sync_write fs/read_write.c:593 [inline] vfs_write+0x7e9/0xe00 fs/read_write.c:686 ksys_write+0x19d/0x2d0 fs/read_write.c:738 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf7/0x470 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The bug was triggered w/ below race condition: fsync setattr ioctl - f2fs_do_sync_file - file_write_and_wait_range - f2fs_write_cache_pages : inode is non-compressed : cc.cluster_size = F2FS_I(inode)->i_cluster_size = 0 - tag_pages_for_writeback - f2fs_setattr - truncate_setsize - f2fs_truncate - f2fs_fileattr_set - f2fs_setflags_common - set_compress_context : F2FS_I(inode)->i_cluster_size = 4 : set_inode_flag(inode, FI_COMPRESSED_FILE) - f2fs_compressed_file : return true - f2fs_all_cluster_page_ready : "pgidx % cc->cluster_size" trigger dividing 0 issue Let's change as below to fix this issue: - introduce a new atomic type variable .writeback in structure f2fs_inode_info to track the number of threads which calling f2fs_write_cache_pages(). - use .i_sem lock to protect .writeback update. - check .writeback before update compression context in f2fs_setflags_common() to avoid race w/ ->writepages.
CVE-2025-68778: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't log conflicting inode if it's a dir moved in the current transaction We can't log a conflicting inode if it's a directory and it was moved from one parent directory to another parent directory in the current transaction, as this can result an attempt to have a directory with two hard links during log replay, one for the old parent directory and another for the new parent directory. The following scenario triggers that issue: 1) We have directories "dir1" and "dir2" created in a past transaction. Directory "dir1" has inode A as its parent directory; 2) We move "dir1" to some other directory; 3) We create a file with the name "dir1" in directory inode A; 4) We fsync the new file. This results in logging the inode of the new file and the inode for the directory "dir1" that was previously moved in the current transaction. So the log tree has the INODE_REF item for the new location of "dir1"; 5) We move the new file to some other directory. This results in updating the log tree to included the new INODE_REF for the new location of the file and removes the INODE_REF for the old location. This happens during the rename when we call btrfs_log_new_name(); 6) We fsync the file, and that persists the log tree changes done in the previous step (btrfs_log_new_name() only updates the log tree in memory); 7) We have a power failure; 8) Next time the fs is mounted, log replay happens and when processing the inode for directory "dir1" we find a new INODE_REF and add that link, but we don't remove the old link of the inode since we have not logged the old parent directory of the directory inode "dir1". As a result after log replay finishes when we trigger writeback of the subvolume tree's extent buffers, the tree check will detect that we have a directory a hard link count of 2 and we get a mount failure. The errors and stack traces reported in dmesg/syslog are like this: [ 3845.729764] BTRFS info (device dm-0): start tree-log replay [ 3845.730304] page: refcount:3 mapcount:0 mapping:000000005c8a3027 index:0x1d00 pfn:0x11510c [ 3845.731236] memcg:ffff9264c02f4e00 [ 3845.731751] aops:btree_aops [btrfs] ino:1 [ 3845.732300] flags: 0x17fffc00000400a(uptodate|private|writeback|node=0|zone=2|lastcpupid=0x1ffff) [ 3845.733346] raw: 017fffc00000400a 0000000000000000 dead000000000122 ffff9264d978aea8 [ 3845.734265] raw: 0000000000001d00 ffff92650e6d4738 00000003ffffffff ffff9264c02f4e00 [ 3845.735305] page dumped because: eb page dump [ 3845.735981] BTRFS critical (device dm-0): corrupt leaf: root=5 block=30408704 slot=6 ino=257, invalid nlink: has 2 expect no more than 1 for dir [ 3845.737786] BTRFS info (device dm-0): leaf 30408704 gen 10 total ptrs 17 free space 14881 owner 5 [ 3845.737789] BTRFS info (device dm-0): refs 4 lock_owner 0 current 30701 [ 3845.737792] item 0 key (256 INODE_ITEM 0) itemoff 16123 itemsize 160 [ 3845.737794] inode generation 3 transid 9 size 16 nbytes 16384 [ 3845.737795] block group 0 mode 40755 links 1 uid 0 gid 0 [ 3845.737797] rdev 0 sequence 2 flags 0x0 [ 3845.737798] atime 1764259517.0 [ 3845.737800] ctime 1764259517.572889464 [ 3845.737801] mtime 1764259517.572889464 [ 3845.737802] otime 1764259517.0 [ 3845.737803] item 1 key (256 INODE_REF 256) itemoff 16111 itemsize 12 [ 3845.737805] index 0 name_len 2 [ 3845.737807] item 2 key (256 DIR_ITEM 2363071922) itemoff 16077 itemsize 34 [ 3845.737808] location key (257 1 0) type 2 [ 3845.737810] transid 9 data_len 0 name_len 4 [ 3845.737811] item 3 key (256 DIR_ITEM 2676584006) itemoff 16043 itemsize 34 [ 3845.737813] location key (258 1 0) type 2 [ 3845.737814] transid 9 data_len 0 name_len 4 [ 3845.737815] item 4 key (256 DIR_INDEX 2) itemoff 16009 itemsize 34 [ 3845.737816] location key (257 1 0) type 2 [ ---truncated---
CVE-2025-68780: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: only set free_cpus for online runqueues Commit 16b269436b72 ("sched/deadline: Modify cpudl::free_cpus to reflect rd->online") introduced the cpudl_set/clear_freecpu functions to allow the cpu_dl::free_cpus mask to be manipulated by the deadline scheduler class rq_on/offline callbacks so the mask would also reflect this state. Commit 9659e1eeee28 ("sched/deadline: Remove cpu_active_mask from cpudl_find()") removed the check of the cpu_active_mask to save some processing on the premise that the cpudl::free_cpus mask already reflected the runqueue online state. Unfortunately, there are cases where it is possible for the cpudl_clear function to set the free_cpus bit for a CPU when the deadline runqueue is offline. When this occurs while a CPU is connected to the default root domain the flag may retain the bad state after the CPU has been unplugged. Later, a different CPU that is transitioning through the default root domain may push a deadline task to the powered down CPU when cpudl_find sees its free_cpus bit is set. If this happens the task will not have the opportunity to run. One example is outlined here: https://lore.kernel.org/lkml/20250110233010.2339521-1-opendmb@gmail.com Another occurs when the last deadline task is migrated from a CPU that has an offlined runqueue. The dequeue_task member of the deadline scheduler class will eventually call cpudl_clear and set the free_cpus bit for the CPU. This commit modifies the cpudl_clear function to be aware of the online state of the deadline runqueue so that the free_cpus mask can be updated appropriately. It is no longer necessary to manage the mask outside of the cpudl_set/clear functions so the cpudl_set/clear_freecpu functions are removed. In addition, since the free_cpus mask is now only updated under the cpudl lock the code was changed to use the non-atomic __cpumask functions.
CVE-2025-68781: In the Linux kernel, the following vulnerability has been resolved: usb: phy: fsl-usb: Fix use-after-free in delayed work during device removal The delayed work item otg_event is initialized in fsl_otg_conf() and scheduled under two conditions: 1. When a host controller binds to the OTG controller. 2. When the USB ID pin state changes (cable insertion/removal). A race condition occurs when the device is removed via fsl_otg_remove(): the fsl_otg instance may be freed while the delayed work is still pending or executing. This leads to use-after-free when the work function fsl_otg_event() accesses the already freed memory. The problematic scenario: (detach thread) | (delayed work) fsl_otg_remove() | kfree(fsl_otg_dev) //FREE| fsl_otg_event() | og = container_of(...) //USE | og-> //USE Fix this by calling disable_delayed_work_sync() in fsl_otg_remove() before deallocating the fsl_otg structure. This ensures the delayed work is properly canceled and completes execution prior to memory deallocation. This bug was identified through static analysis.
CVE-2025-68794: In the Linux kernel, the following vulnerability has been resolved: iomap: adjust read range correctly for non-block-aligned positions iomap_adjust_read_range() assumes that the position and length passed in are block-aligned. This is not always the case however, as shown in the syzbot generated case for erofs. This causes too many bytes to be skipped for uptodate blocks, which results in returning the incorrect position and length to read in. If all the blocks are uptodate, this underflows length and returns a position beyond the folio. Fix the calculation to also take into account the block offset when calculating how many bytes can be skipped for uptodate blocks.
CVE-2025-68822: In the Linux kernel, the following vulnerability has been resolved: Input: alps - fix use-after-free bugs caused by dev3_register_work The dev3_register_work delayed work item is initialized within alps_reconnect() and scheduled upon receipt of the first bare PS/2 packet from an external PS/2 device connected to the ALPS touchpad. During device detachment, the original implementation calls flush_workqueue() in psmouse_disconnect() to ensure completion of dev3_register_work. However, the flush_workqueue() in psmouse_disconnect() only blocks and waits for work items that were already queued to the workqueue prior to its invocation. Any work items submitted after flush_workqueue() is called are not included in the set of tasks that the flush operation awaits. This means that after flush_workqueue() has finished executing, the dev3_register_work could still be scheduled. Although the psmouse state is set to PSMOUSE_CMD_MODE in psmouse_disconnect(), the scheduling of dev3_register_work remains unaffected. The race condition can occur as follows: CPU 0 (cleanup path) | CPU 1 (delayed work) psmouse_disconnect() | psmouse_set_state() | flush_workqueue() | alps_report_bare_ps2_packet() alps_disconnect() | psmouse_queue_work() kfree(priv); // FREE | alps_register_bare_ps2_mouse() | priv = container_of(work...); // USE | priv->dev3 // USE Add disable_delayed_work_sync() in alps_disconnect() to ensure that dev3_register_work is properly canceled and prevented from executing after the alps_data structure has been deallocated. This bug is identified by static analysis.
CVE-2025-71073: In the Linux kernel, the following vulnerability has been resolved: Input: lkkbd - disable pending work before freeing device lkkbd_interrupt() schedules lk->tq via schedule_work(), and the work handler lkkbd_reinit() dereferences the lkkbd structure and its serio/input_dev fields. lkkbd_disconnect() and error paths in lkkbd_connect() free the lkkbd structure without preventing the reinit work from being queued again until serio_close() returns. This can allow the work handler to run after the structure has been freed, leading to a potential use-after-free. Use disable_work_sync() instead of cancel_work_sync() to ensure the reinit work cannot be re-queued, and call it both in lkkbd_disconnect() and in lkkbd_connect() error paths after serio_open().
CVE-2025-71074: In the Linux kernel, the following vulnerability has been resolved: functionfs: fix the open/removal races ffs_epfile_open() can race with removal, ending up with file->private_data pointing to freed object. There is a total count of opened files on functionfs (both ep0 and dynamic ones) and when it hits zero, dynamic files get removed. Unfortunately, that removal can happen while another thread is in ffs_epfile_open(), but has not incremented the count yet. In that case open will succeed, leaving us with UAF on any subsequent read() or write(). The root cause is that ffs->opened is misused; atomic_dec_and_test() vs. atomic_add_return() is not a good idea, when object remains visible all along. To untangle that * serialize openers on ffs->mutex (both for ep0 and for dynamic files) * have dynamic ones use atomic_inc_not_zero() and fail if we had zero ->opened; in that case the file we are opening is doomed. * have the inodes of dynamic files marked on removal (from the callback of simple_recursive_removal()) - clear ->i_private there. * have open of dynamic ones verify they hadn't been already removed, along with checking that state is FFS_ACTIVE.
CVE-2025-71078: In the Linux kernel, the following vulnerability has been resolved: powerpc/64s/slb: Fix SLB multihit issue during SLB preload On systems using the hash MMU, there is a software SLB preload cache that mirrors the entries loaded into the hardware SLB buffer. This preload cache is subject to periodic eviction — typically after every 256 context switches — to remove old entry. To optimize performance, the kernel skips switch_mmu_context() in switch_mm_irqs_off() when the prev and next mm_struct are the same. However, on hash MMU systems, this can lead to inconsistencies between the hardware SLB and the software preload cache. If an SLB entry for a process is evicted from the software cache on one CPU, and the same process later runs on another CPU without executing switch_mmu_context(), the hardware SLB may retain stale entries. If the kernel then attempts to reload that entry, it can trigger an SLB multi-hit error. The following timeline shows how stale SLB entries are created and can cause a multi-hit error when a process moves between CPUs without a MMU context switch. CPU 0 CPU 1 ----- ----- Process P exec swapper/1 load_elf_binary begin_new_exc activate_mm switch_mm_irqs_off switch_mmu_context switch_slb /* * This invalidates all * the entries in the HW * and setup the new HW * SLB entries as per the * preload cache. */ context_switch sched_migrate_task migrates process P to cpu-1 Process swapper/0 context switch (to process P) (uses mm_struct of Process P) switch_mm_irqs_off() switch_slb load_slb++ /* * load_slb becomes 0 here * and we evict an entry from * the preload cache with * preload_age(). We still * keep HW SLB and preload * cache in sync, that is * because all HW SLB entries * anyways gets evicted in * switch_slb during SLBIA. * We then only add those * entries back in HW SLB, * which are currently * present in preload_cache * (after eviction). */ load_elf_binary continues... setup_new_exec() slb_setup_new_exec() sched_switch event sched_migrate_task migrates process P to cpu-0 context_switch from swapper/0 to Process P switch_mm_irqs_off() /* * Since both prev and next mm struct are same we don't call * switch_mmu_context(). This will cause the HW SLB and SW preload * cache to go out of sync in preload_new_slb_context. Because there * was an SLB entry which was evicted from both HW and preload cache * on cpu-1. Now later in preload_new_slb_context(), when we will try * to add the same preload entry again, we will add this to the SW * preload cache and then will add it to the HW SLB. Since on cpu-0 * this entry was never invalidated, hence adding this entry to the HW * SLB will cause a SLB multi-hit error. */ load_elf_binary cont ---truncated---
CVE-2025-71081: In the Linux kernel, the following vulnerability has been resolved: ASoC: stm32: sai: fix OF node leak on probe The reference taken to the sync provider OF node when probing the platform device is currently only dropped if the set_sync() callback fails during DAI probe. Make sure to drop the reference on platform probe failures (e.g. probe deferral) and on driver unbind. This also avoids a potential use-after-free in case the DAI is ever reprobed without first rebinding the platform driver.
CVE-2025-71082: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: revert use of devm_kzalloc in btusb This reverts commit 98921dbd00c4e ("Bluetooth: Use devm_kzalloc in btusb.c file"). In btusb_probe(), we use devm_kzalloc() to allocate the btusb data. This ties the lifetime of all the btusb data to the binding of a driver to one interface, INTF. In a driver that binds to other interfaces, ISOC and DIAG, this is an accident waiting to happen. The issue is revealed in btusb_disconnect(), where calling usb_driver_release_interface(&btusb_driver, data->intf) will have devm free the data that is also being used by the other interfaces of the driver that may not be released yet. To fix this, revert the use of devm and go back to freeing memory explicitly.
CVE-2025-71083: In the Linux kernel, the following vulnerability has been resolved: drm/ttm: Avoid NULL pointer deref for evicted BOs It is possible for a BO to exist that is not currently associated with a resource, e.g. because it has been evicted. When devcoredump tries to read the contents of all BOs for dumping, we need to expect this as well -- in this case, ENODATA is recorded instead of the buffer contents.
CVE-2025-71089: In the Linux kernel, the following vulnerability has been resolved: iommu: disable SVA when CONFIG_X86 is set Patch series "Fix stale IOTLB entries for kernel address space", v7. This proposes a fix for a security vulnerability related to IOMMU Shared Virtual Addressing (SVA). In an SVA context, an IOMMU can cache kernel page table entries. When a kernel page table page is freed and reallocated for another purpose, the IOMMU might still hold stale, incorrect entries. This can be exploited to cause a use-after-free or write-after-free condition, potentially leading to privilege escalation or data corruption. This solution introduces a deferred freeing mechanism for kernel page table pages, which provides a safe window to notify the IOMMU to invalidate its caches before the page is reused. This patch (of 8): In the IOMMU Shared Virtual Addressing (SVA) context, the IOMMU hardware shares and walks the CPU's page tables. The x86 architecture maps the kernel's virtual address space into the upper portion of every process's page table. Consequently, in an SVA context, the IOMMU hardware can walk and cache kernel page table entries. The Linux kernel currently lacks a notification mechanism for kernel page table changes, specifically when page table pages are freed and reused. The IOMMU driver is only notified of changes to user virtual address mappings. This can cause the IOMMU's internal caches to retain stale entries for kernel VA. Use-After-Free (UAF) and Write-After-Free (WAF) conditions arise when kernel page table pages are freed and later reallocated. The IOMMU could misinterpret the new data as valid page table entries. The IOMMU might then walk into attacker-controlled memory, leading to arbitrary physical memory DMA access or privilege escalation. This is also a Write-After-Free issue, as the IOMMU will potentially continue to write Accessed and Dirty bits to the freed memory while attempting to walk the stale page tables. Currently, SVA contexts are unprivileged and cannot access kernel mappings. However, the IOMMU will still walk kernel-only page tables all the way down to the leaf entries, where it realizes the mapping is for the kernel and errors out. This means the IOMMU still caches these intermediate page table entries, making the described vulnerability a real concern. Disable SVA on x86 architecture until the IOMMU can receive notification to flush the paging cache before freeing the CPU kernel page table pages.
CVE-2025-71109: In the Linux kernel, the following vulnerability has been resolved: MIPS: ftrace: Fix memory corruption when kernel is located beyond 32 bits Since commit e424054000878 ("MIPS: Tracing: Reduce the overhead of dynamic Function Tracer"), the macro UASM_i_LA_mostly has been used, and this macro can generate more than 2 instructions. At the same time, the code in ftrace assumes that no more than 2 instructions can be generated, which is why it stores them in an int[2] array. However, as previously noted, the macro UASM_i_LA_mostly (and now UASM_i_LA) causes a buffer overflow when _mcount is beyond 32 bits. This leads to corruption of the variables located in the __read_mostly section. This corruption was observed because the variable __cpu_primary_thread_mask was corrupted, causing a hang very early during boot. This fix prevents the corruption by avoiding the generation of instructions if they could exceed 2 instructions in length. Fortunately, insn_la_mcount is only used if the instrumented code is located outside the kernel code section, so dynamic ftrace can still be used, albeit in a more limited scope. This is still preferable to corrupting memory and/or crashing the kernel.
CVE-2025-71121: In the Linux kernel, the following vulnerability has been resolved: parisc: Do not reprogram affinitiy on ASP chip The ASP chip is a very old variant of the GSP chip and is used e.g. in HP 730 workstations. When trying to reprogram the affinity it will crash with a HPMC as the relevant registers don't seem to be at the usual location. Let's avoid the crash by checking the sversion. Also note, that reprogramming isn't necessary either, as the HP730 is a just a single-CPU machine.
CVE-2025-71152: In the Linux kernel, the following vulnerability has been resolved: net: dsa: properly keep track of conduit reference Problem description ------------------- DSA has a mumbo-jumbo of reference handling of the conduit net device and its kobject which, sadly, is just wrong and doesn't make sense. There are two distinct problems. 1. The OF path, which uses of_find_net_device_by_node(), never releases the elevated refcount on the conduit's kobject. Nominally, the OF and non-OF paths should result in objects having identical reference counts taken, and it is already suspicious that dsa_dev_to_net_device() has a put_device() call which is missing in dsa_port_parse_of(), but we can actually even verify that an issue exists. With CONFIG_DEBUG_KOBJECT_RELEASE=y, if we run this command "before" and "after" applying this patch: (unbind the conduit driver for net device eno2) echo 0000:00:00.2 > /sys/bus/pci/drivers/fsl_enetc/unbind we see these lines in the output diff which appear only with the patch applied: kobject: 'eno2' (ffff002009a3a6b8): kobject_release, parent 0000000000000000 (delayed 1000) kobject: '109' (ffff0020099d59a0): kobject_release, parent 0000000000000000 (delayed 1000) 2. After we find the conduit interface one way (OF) or another (non-OF), it can get unregistered at any time, and DSA remains with a long-lived, but in this case stale, cpu_dp->conduit pointer. Holding the net device's underlying kobject isn't actually of much help, it just prevents it from being freed (but we never need that kobject directly). What helps us to prevent the net device from being unregistered is the parallel netdev reference mechanism (dev_hold() and dev_put()). Actually we actually use that netdev tracker mechanism implicitly on user ports since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), via netdev_upper_dev_link(). But time still passes at DSA switch probe time between the initial of_find_net_device_by_node() code and the user port creation time, time during which the conduit could unregister itself and DSA wouldn't know about it. So we have to run of_find_net_device_by_node() under rtnl_lock() to prevent that from happening, and release the lock only with the netdev tracker having acquired the reference. Do we need to keep the reference until dsa_unregister_switch() / dsa_switch_shutdown()? 1: Maybe yes. A switch device will still be registered even if all user ports failed to probe, see commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal"), and the cpu_dp->conduit pointers remain valid. I haven't audited all call paths to see whether they will actually use the conduit in lack of any user port, but if they do, it seems safer to not rely on user ports for that reference. 2. Definitely yes. We support changing the conduit which a user port is associated to, and we can get into a situation where we've moved all user ports away from a conduit, thus no longer hold any reference to it via the net device tracker. But we shouldn't let it go nonetheless - see the next change in relation to dsa_tree_find_first_conduit() and LAG conduits which disappear. We have to be prepared to return to the physical conduit, so the CPU port must explicitly keep another reference to it. This is also to say: the user ports and their CPU ports may not always keep a reference to the same conduit net device, and both are needed. As for the conduit's kobject for the /sys/class/net/ entry, we don't care about it, we can release it as soon as we hold the net device object itself. History and blame attribution ----------------------------- The code has been refactored so many times, it is very difficult to follow and properly attribute a blame, but I'll try to make a short history which I hope to be correct. We have two distinct probing paths: - one for OF, introduced in 2016 i ---truncated---
CVE-2025-71160: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: avoid chain re-validation if possible Hamza Mahfooz reports cpu soft lock-ups in nft_chain_validate(): watchdog: BUG: soft lockup - CPU#1 stuck for 27s! [iptables-nft-re:37547] [..] RIP: 0010:nft_chain_validate+0xcb/0x110 [nf_tables] [..] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_table_validate+0x6b/0xb0 [nf_tables] nf_tables_validate+0x8b/0xa0 [nf_tables] nf_tables_commit+0x1df/0x1eb0 [nf_tables] [..] Currently nf_tables will traverse the entire table (chain graph), starting from the entry points (base chains), exploring all possible paths (chain jumps). But there are cases where we could avoid revalidation. Consider: 1 input -> j2 -> j3 2 input -> j2 -> j3 3 input -> j1 -> j2 -> j3 Then the second rule does not need to revalidate j2, and, by extension j3, because this was already checked during validation of the first rule. We need to validate it only for rule 3. This is needed because chain loop detection also ensures we do not exceed the jump stack: Just because we know that j2 is cycle free, its last jump might now exceed the allowed stack size. We also need to update all reachable chains with the new largest observed call depth. Care has to be taken to revalidate even if the chain depth won't be an issue: chain validation also ensures that expressions are not called from invalid base chains. For example, the masquerade expression can only be called from NAT postrouting base chains. Therefore we also need to keep record of the base chain context (type, hooknum) and revalidate if the chain becomes reachable from a different hook location.
CVE-2025-71161: In the Linux kernel, the following vulnerability has been resolved: dm-verity: disable recursive forward error correction There are two problems with the recursive correction: 1. It may cause denial-of-service. In fec_read_bufs, there is a loop that has 253 iterations. For each iteration, we may call verity_hash_for_block recursively. There is a limit of 4 nested recursions - that means that there may be at most 253^4 (4 billion) iterations. Red Hat QE team actually created an image that pushes dm-verity to this limit - and this image just makes the udev-worker process get stuck in the 'D' state. 2. It doesn't work. In fec_read_bufs we store data into the variable "fio->bufs", but fio bufs is shared between recursive invocations, if "verity_hash_for_block" invoked correction recursively, it would overwrite partially filled fio->bufs.
CVE-2025-71183: In the Linux kernel, the following vulnerability has been resolved: btrfs: always detect conflicting inodes when logging inode refs After rename exchanging (either with the rename exchange operation or regular renames in multiple non-atomic steps) two inodes and at least one of them is a directory, we can end up with a log tree that contains only of the inodes and after a power failure that can result in an attempt to delete the other inode when it should not because it was not deleted before the power failure. In some case that delete attempt fails when the target inode is a directory that contains a subvolume inside it, since the log replay code is not prepared to deal with directory entries that point to root items (only inode items). 1) We have directories "dir1" (inode A) and "dir2" (inode B) under the same parent directory; 2) We have a file (inode C) under directory "dir1" (inode A); 3) We have a subvolume inside directory "dir2" (inode B); 4) All these inodes were persisted in a past transaction and we are currently at transaction N; 5) We rename the file (inode C), so at btrfs_log_new_name() we update inode C's last_unlink_trans to N; 6) We get a rename exchange for "dir1" (inode A) and "dir2" (inode B), so after the exchange "dir1" is inode B and "dir2" is inode A. During the rename exchange we call btrfs_log_new_name() for inodes A and B, but because they are directories, we don't update their last_unlink_trans to N; 7) An fsync against the file (inode C) is done, and because its inode has a last_unlink_trans with a value of N we log its parent directory (inode A) (through btrfs_log_all_parents(), called from btrfs_log_inode_parent()). 8) So we end up with inode B not logged, which now has the old name of inode A. At copy_inode_items_to_log(), when logging inode A, we did not check if we had any conflicting inode to log because inode A has a generation lower than the current transaction (created in a past transaction); 9) After a power failure, when replaying the log tree, since we find that inode A has a new name that conflicts with the name of inode B in the fs tree, we attempt to delete inode B... this is wrong since that directory was never deleted before the power failure, and because there is a subvolume inside that directory, attempting to delete it will fail since replay_dir_deletes() and btrfs_unlink_inode() are not prepared to deal with dir items that point to roots instead of inodes. When that happens the mount fails and we get a stack trace like the following: [87.2314] BTRFS info (device dm-0): start tree-log replay [87.2318] BTRFS critical (device dm-0): failed to delete reference to subvol, root 5 inode 256 parent 259 [87.2332] ------------[ cut here ]------------ [87.2338] BTRFS: Transaction aborted (error -2) [87.2346] WARNING: CPU: 1 PID: 638968 at fs/btrfs/inode.c:4345 __btrfs_unlink_inode+0x416/0x440 [btrfs] [87.2368] Modules linked in: btrfs loop dm_thin_pool (...) [87.2470] CPU: 1 UID: 0 PID: 638968 Comm: mount Tainted: G W 6.18.0-rc7-btrfs-next-218+ #2 PREEMPT(full) [87.2489] Tainted: [W]=WARN [87.2494] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014 [87.2514] RIP: 0010:__btrfs_unlink_inode+0x416/0x440 [btrfs] [87.2538] Code: c0 89 04 24 (...) [87.2568] RSP: 0018:ffffc0e741f4b9b8 EFLAGS: 00010286 [87.2574] RAX: 0000000000000000 RBX: ffff9d3ec8a6cf60 RCX: 0000000000000000 [87.2582] RDX: 0000000000000002 RSI: ffffffff84ab45a1 RDI: 00000000ffffffff [87.2591] RBP: ffff9d3ec8a6ef20 R08: 0000000000000000 R09: ffffc0e741f4b840 [87.2599] R10: ffff9d45dc1fffa8 R11: 0000000000000003 R12: ffff9d3ee26d77e0 [87.2608] R13: ffffc0e741f4ba98 R14: ffff9d4458040800 R15: ffff9d44b6b7ca10 [87.2618] FS: 00007f7b9603a840(0000) GS:ffff9d4658982000(0000) knlGS:0000000000000000 [87. ---truncated---
CVE-2025-71184: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix NULL dereference on root when tracing inode eviction When evicting an inode the first thing we do is to setup tracing for it, which implies fetching the root's id. But in btrfs_evict_inode() the root might be NULL, as implied in the next check that we do in btrfs_evict_inode(). Hence, we either should set the ->root_objectid to 0 in case the root is NULL, or we move tracing setup after checking that the root is not NULL. Setting the rootid to 0 at least gives us the possibility to trace this call even in the case when the root is NULL, so that's the solution taken here.
CVE-2025-71192: In the Linux kernel, the following vulnerability has been resolved: ALSA: ac97: fix a double free in snd_ac97_controller_register() If ac97_add_adapter() fails, put_device() is the correct way to drop the device reference. kfree() is not required. Add kfree() if idr_alloc() fails and in ac97_adapter_release() to do the cleanup. Found by code review.
CVE-2025-71193: In the Linux kernel, the following vulnerability has been resolved: phy: qcom-qusb2: Fix NULL pointer dereference on early suspend Enabling runtime PM before attaching the QPHY instance as driver data can lead to a NULL pointer dereference in runtime PM callbacks that expect valid driver data. There is a small window where the suspend callback may run after PM runtime enabling and before runtime forbid. This causes a sporadic crash during boot: ``` Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a1 [...] CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.7+ #116 PREEMPT Workqueue: pm pm_runtime_work pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : qusb2_phy_runtime_suspend+0x14/0x1e0 [phy_qcom_qusb2] lr : pm_generic_runtime_suspend+0x2c/0x44 [...] ``` Attach the QPHY instance as driver data before enabling runtime PM to prevent NULL pointer dereference in runtime PM callbacks. Reorder pm_runtime_enable() and pm_runtime_forbid() to prevent a short window where an unnecessary runtime suspend can occur. Use the devres-managed version to ensure PM runtime is symmetrically disabled during driver removal for proper cleanup.
CVE-2025-71198: In the Linux kernel, the following vulnerability has been resolved: iio: imu: st_lsm6dsx: fix iio_chan_spec for sensors without event detection The st_lsm6dsx_acc_channels array of struct iio_chan_spec has a non-NULL event_spec field, indicating support for IIO events. However, event detection is not supported for all sensors, and if userspace tries to configure accelerometer wakeup events on a sensor device that does not support them (e.g. LSM6DS0), st_lsm6dsx_write_event() dereferences a NULL pointer when trying to write to the wakeup register. Define an additional struct iio_chan_spec array whose members have a NULL event_spec field, and use this array instead of st_lsm6dsx_acc_channels for sensors without event detection capability.
CVE-2025-71202: In the Linux kernel, the following vulnerability has been resolved: iommu/sva: invalidate stale IOTLB entries for kernel address space Introduce a new IOMMU interface to flush IOTLB paging cache entries for the CPU kernel address space. This interface is invoked from the x86 architecture code that manages combined user and kernel page tables, specifically before any kernel page table page is freed and reused. This addresses the main issue with vfree() which is a common occurrence and can be triggered by unprivileged users. While this resolves the primary problem, it doesn't address some extremely rare case related to memory unplug of memory that was present as reserved memory at boot, which cannot be triggered by unprivileged users. The discussion can be found at the link below. Enable SVA on x86 architecture since the IOMMU can now receive notification to flush the paging cache before freeing the CPU kernel page table pages.
CVE-2025-71221: In the Linux kernel, the following vulnerability has been resolved: dmaengine: mmp_pdma: Fix race condition in mmp_pdma_residue() Add proper locking in mmp_pdma_residue() to prevent use-after-free when accessing descriptor list and descriptor contents. The race occurs when multiple threads call tx_status() while the tasklet on another CPU is freeing completed descriptors: CPU 0 CPU 1 ----- ----- mmp_pdma_tx_status() mmp_pdma_residue() -> NO LOCK held list_for_each_entry(sw, ..) DMA interrupt dma_do_tasklet() -> spin_lock(&desc_lock) list_move(sw->node, ...) spin_unlock(&desc_lock) | dma_pool_free(sw) <- FREED! -> access sw->desc <- UAF! This issue can be reproduced when running dmatest on the same channel with multiple threads (threads_per_chan > 1). Fix by protecting the chain_running list iteration and descriptor access with the chan->desc_lock spinlock.
CVE-2025-71225: In the Linux kernel, the following vulnerability has been resolved: md: suspend array while updating raid_disks via sysfs In raid1_reshape(), freeze_array() is called before modifying the r1bio memory pool (conf->r1bio_pool) and conf->raid_disks, and unfreeze_array() is called after the update is completed. However, freeze_array() only waits until nr_sync_pending and (nr_pending - nr_queued) of all buckets reaches zero. When an I/O error occurs, nr_queued is increased and the corresponding r1bio is queued to either retry_list or bio_end_io_list. As a result, freeze_array() may unblock before these r1bios are released. This can lead to a situation where conf->raid_disks and the mempool have already been updated while queued r1bios, allocated with the old raid_disks value, are later released. Consequently, free_r1bio() may access memory out of bounds in put_all_bios() and release r1bios of the wrong size to the new mempool, potentially causing issues with the mempool as well. Since only normal I/O might increase nr_queued while an I/O error occurs, suspending the array avoids this issue. Note: Updating raid_disks via ioctl SET_ARRAY_INFO already suspends the array. Therefore, we suspend the array when updating raid_disks via sysfs to avoid this issue too.
CVE-2025-71227: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: don't WARN for connections on invalid channels It's not clear (to me) how exactly syzbot managed to hit this, but it seems conceivable that e.g. regulatory changed and has disabled a channel between scanning (channel is checked to be usable by cfg80211_get_ies_channel_number) and connecting on the channel later. With one scenario that isn't covered elsewhere described above, the warning isn't good, replace it with a (more informative) error message.
CVE-2025-71268: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix reservation leak in some error paths when inserting inline extent If we fail to allocate a path or join a transaction, we return from __cow_file_range_inline() without freeing the reserved qgroup data, resulting in a leak. Fix this by ensuring we call btrfs_qgroup_free_data() in such cases.
CVE-2025-71269: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not free data reservation in fallback from inline due to -ENOSPC If we fail to create an inline extent due to -ENOSPC, we will attempt to go through the normal COW path, reserve an extent, create an ordered extent, etc. However we were always freeing the reserved qgroup data, which is wrong since we will use data. Fix this by freeing the reserved qgroup data in __cow_file_range_inline() only if we are not doing the fallback (ret is <= 0).
CVE-2026-23004: In the Linux kernel, the following vulnerability has been resolved: dst: fix races in rt6_uncached_list_del() and rt_del_uncached_list() syzbot was able to crash the kernel in rt6_uncached_list_flush_dev() in an interesting way [1] Crash happens in list_del_init()/INIT_LIST_HEAD() while writing list->prev, while the prior write on list->next went well. static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); // This went well WRITE_ONCE(list->prev, list); // Crash, @list has been freed. } Issue here is that rt6_uncached_list_del() did not attempt to lock ul->lock, as list_empty(&rt->dst.rt_uncached) returned true because the WRITE_ONCE(list->next, list) happened on the other CPU. We might use list_del_init_careful() and list_empty_careful(), or make sure rt6_uncached_list_del() always grabs the spinlock whenever rt->dst.rt_uncached_list has been set. A similar fix is neeed for IPv4. [1] BUG: KASAN: slab-use-after-free in INIT_LIST_HEAD include/linux/list.h:46 [inline] BUG: KASAN: slab-use-after-free in list_del_init include/linux/list.h:296 [inline] BUG: KASAN: slab-use-after-free in rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] BUG: KASAN: slab-use-after-free in rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 Write of size 8 at addr ffff8880294cfa78 by task kworker/u8:14/3450 CPU: 0 UID: 0 PID: 3450 Comm: kworker/u8:14 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025 Workqueue: netns cleanup_net Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 INIT_LIST_HEAD include/linux/list.h:46 [inline] list_del_init include/linux/list.h:296 [inline] rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 addrconf_ifdown+0x143/0x18a0 net/ipv6/addrconf.c:3853 addrconf_notify+0x1bc/0x1050 net/ipv6/addrconf.c:-1 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85 call_netdevice_notifiers_extack net/core/dev.c:2268 [inline] call_netdevice_notifiers net/core/dev.c:2282 [inline] netif_close_many+0x29c/0x410 net/core/dev.c:1785 unregister_netdevice_many_notify+0xb50/0x2330 net/core/dev.c:12353 ops_exit_rtnl_list net/core/net_namespace.c:187 [inline] ops_undo_list+0x3dc/0x990 net/core/net_namespace.c:248 cleanup_net+0x4de/0x7b0 net/core/net_namespace.c:696 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 </TASK> Allocated by task 803: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 unpoison_slab_object mm/kasan/common.c:340 [inline] __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366 kasan_slab_alloc include/linux/kasan.h:253 [inline] slab_post_alloc_hook mm/slub.c:4953 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x18d/0x6c0 mm/slub.c:5270 dst_alloc+0x105/0x170 net/core/dst.c:89 ip6_dst_alloc net/ipv6/route.c:342 [inline] icmp6_dst_alloc+0x75/0x460 net/ipv6/route.c:3333 mld_sendpack+0x683/0xe60 net/ipv6/mcast.c:1844 mld_send_cr net/ipv6/mcast.c:2154 [inline] mld_ifc_work+0x83e/0xd60 net/ipv6/mcast.c:2693 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entr ---truncated---
CVE-2026-23019: In the Linux kernel, the following vulnerability has been resolved: net: marvell: prestera: fix NULL dereference on devlink_alloc() failure devlink_alloc() may return NULL on allocation failure, but prestera_devlink_alloc() unconditionally calls devlink_priv() on the returned pointer. This leads to a NULL pointer dereference if devlink allocation fails. Add a check for a NULL devlink pointer and return NULL early to avoid the crash.
CVE-2026-23031: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: gs_usb_receive_bulk_callback(): fix URB memory leak In gs_can_open(), the URBs for USB-in transfers are allocated, added to the parent->rx_submitted anchor and submitted. In the complete callback gs_usb_receive_bulk_callback(), the URB is processed and resubmitted. In gs_can_close() the URBs are freed by calling usb_kill_anchored_urbs(parent->rx_submitted). However, this does not take into account that the USB framework unanchors the URB before the complete function is called. This means that once an in-URB has been completed, it is no longer anchored and is ultimately not released in gs_can_close(). Fix the memory leak by anchoring the URB in the gs_usb_receive_bulk_callback() to the parent->rx_submitted anchor.
CVE-2026-23050: In the Linux kernel, the following vulnerability has been resolved: pNFS: Fix a deadlock when returning a delegation during open() Ben Coddington reports seeing a hang in the following stack trace: 0 [ffffd0b50e1774e0] __schedule at ffffffff9ca05415 1 [ffffd0b50e177548] schedule at ffffffff9ca05717 2 [ffffd0b50e177558] bit_wait at ffffffff9ca061e1 3 [ffffd0b50e177568] __wait_on_bit at ffffffff9ca05cfb 4 [ffffd0b50e1775c8] out_of_line_wait_on_bit at ffffffff9ca05ea5 5 [ffffd0b50e177618] pnfs_roc at ffffffffc154207b [nfsv4] 6 [ffffd0b50e1776b8] _nfs4_proc_delegreturn at ffffffffc1506586 [nfsv4] 7 [ffffd0b50e177788] nfs4_proc_delegreturn at ffffffffc1507480 [nfsv4] 8 [ffffd0b50e1777f8] nfs_do_return_delegation at ffffffffc1523e41 [nfsv4] 9 [ffffd0b50e177838] nfs_inode_set_delegation at ffffffffc1524a75 [nfsv4] 10 [ffffd0b50e177888] nfs4_process_delegation at ffffffffc14f41dd [nfsv4] 11 [ffffd0b50e1778a0] _nfs4_opendata_to_nfs4_state at ffffffffc1503edf [nfsv4] 12 [ffffd0b50e1778c0] _nfs4_open_and_get_state at ffffffffc1504e56 [nfsv4] 13 [ffffd0b50e177978] _nfs4_do_open at ffffffffc15051b8 [nfsv4] 14 [ffffd0b50e1779f8] nfs4_do_open at ffffffffc150559c [nfsv4] 15 [ffffd0b50e177a80] nfs4_atomic_open at ffffffffc15057fb [nfsv4] 16 [ffffd0b50e177ad0] nfs4_file_open at ffffffffc15219be [nfsv4] 17 [ffffd0b50e177b78] do_dentry_open at ffffffff9c09e6ea 18 [ffffd0b50e177ba8] vfs_open at ffffffff9c0a082e 19 [ffffd0b50e177bd0] dentry_open at ffffffff9c0a0935 The issue is that the delegreturn is being asked to wait for a layout return that cannot complete because a state recovery was initiated. The state recovery cannot complete until the open() finishes processing the delegations it was given. The solution is to propagate the existing flags that indicate a non-blocking call to the function pnfs_roc(), so that it knows not to wait in this situation.
CVE-2026-23054: In the Linux kernel, the following vulnerability has been resolved: net: hv_netvsc: reject RSS hash key programming without RX indirection table RSS configuration requires a valid RX indirection table. When the device reports a single receive queue, rndis_filter_device_add() does not allocate an indirection table, accepting RSS hash key updates in this state leads to a hang. Fix this by gating netvsc_set_rxfh() on ndc->rx_table_sz and return -EOPNOTSUPP when the table is absent. This aligns set_rxfh with the device capabilities and prevents incorrect behavior.
CVE-2026-23066: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix recvmsg() unconditional requeue If rxrpc_recvmsg() fails because MSG_DONTWAIT was specified but the call at the front of the recvmsg queue already has its mutex locked, it requeues the call - whether or not the call is already queued. The call may be on the queue because MSG_PEEK was also passed and so the call was not dequeued or because the I/O thread requeued it. The unconditional requeue may then corrupt the recvmsg queue, leading to things like UAFs or refcount underruns. Fix this by only requeuing the call if it isn't already on the queue - and moving it to the front if it is already queued. If we don't queue it, we have to put the ref we obtained by dequeuing it. Also, MSG_PEEK doesn't dequeue the call so shouldn't call rxrpc_notify_socket() for the call if we didn't use up all the data on the queue, so fix that also.
CVE-2026-23068: In the Linux kernel, the following vulnerability has been resolved: spi: spi-sprd-adi: Fix double free in probe error path The driver currently uses spi_alloc_host() to allocate the controller but registers it using devm_spi_register_controller(). If devm_register_restart_handler() fails, the code jumps to the put_ctlr label and calls spi_controller_put(). However, since the controller was registered via a devm function, the device core will automatically call spi_controller_put() again when the probe fails. This results in a double-free of the spi_controller structure. Fix this by switching to devm_spi_alloc_host() and removing the manual spi_controller_put() call.
CVE-2026-23069: In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: fix potential underflow in virtio_transport_get_credit() The credit calculation in virtio_transport_get_credit() uses unsigned arithmetic: ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); If the peer shrinks its advertised buffer (peer_buf_alloc) while bytes are in flight, the subtraction can underflow and produce a large positive value, potentially allowing more data to be queued than the peer can handle. Reuse virtio_transport_has_space() which already handles this case and add a comment to make it clear why we are doing that. [Stefano: use virtio_transport_has_space() instead of duplicating the code] [Stefano: tweak the commit message]
CVE-2026-23086: In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: cap TX credit to local buffer size The virtio transports derives its TX credit directly from peer_buf_alloc, which is set from the remote endpoint's SO_VM_SOCKETS_BUFFER_SIZE value. On the host side this means that the amount of data we are willing to queue for a connection is scaled by a guest-chosen buffer size, rather than the host's own vsock configuration. A malicious guest can advertise a large buffer and read slowly, causing the host to allocate a correspondingly large amount of sk_buff memory. The same thing would happen in the guest with a malicious host, since virtio transports share the same code base. Introduce a small helper, virtio_transport_tx_buf_size(), that returns min(peer_buf_alloc, buf_alloc), and use it wherever we consume peer_buf_alloc. This ensures the effective TX window is bounded by both the peer's advertised buffer and our own buf_alloc (already clamped to buffer_max_size via SO_VM_SOCKETS_BUFFER_MAX_SIZE), so a remote peer cannot force the other to queue more data than allowed by its own vsock settings. On an unpatched Ubuntu 22.04 host (~64 GiB RAM), running a PoC with 32 guest vsock connections advertising 2 GiB each and reading slowly drove Slab/SUnreclaim from ~0.5 GiB to ~57 GiB; the system only recovered after killing the QEMU process. That said, if QEMU memory is limited with cgroups, the maximum memory used will be limited. With this patch applied: Before: MemFree: ~61.6 GiB Slab: ~142 MiB SUnreclaim: ~117 MiB After 32 high-credit connections: MemFree: ~61.5 GiB Slab: ~178 MiB SUnreclaim: ~152 MiB Only ~35 MiB increase in Slab/SUnreclaim, no host OOM, and the guest remains responsive. Compatibility with non-virtio transports: - VMCI uses the AF_VSOCK buffer knobs to size its queue pairs per socket based on the local vsk->buffer_* values; the remote side cannot enlarge those queues beyond what the local endpoint configured. - Hyper-V's vsock transport uses fixed-size VMBus ring buffers and an MTU bound; there is no peer-controlled credit field comparable to peer_buf_alloc, and the remote endpoint cannot drive in-flight kernel memory above those ring sizes. - The loopback path reuses virtio_transport_common.c, so it naturally follows the same semantics as the virtio transport. This change is limited to virtio_transport_common.c and thus affects virtio-vsock, vhost-vsock, and loopback, bringing them in line with the "remote window intersected with local policy" behaviour that VMCI and Hyper-V already effectively have. [Stefano: small adjustments after changing the previous patch] [Stefano: tweak the commit message]
CVE-2026-23088: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix crash on synthetic stacktrace field usage When creating a synthetic event based on an existing synthetic event that had a stacktrace field and the new synthetic event used that field a kernel crash occurred: ~# cd /sys/kernel/tracing ~# echo 's:stack unsigned long stack[];' > dynamic_events ~# echo 'hist:keys=prev_pid:s0=common_stacktrace if prev_state & 3' >> events/sched/sched_switch/trigger ~# echo 'hist:keys=next_pid:s1=$s0:onmatch(sched.sched_switch).trace(stack,$s1)' >> events/sched/sched_switch/trigger The above creates a synthetic event that takes a stacktrace when a task schedules out in a non-running state and passes that stacktrace to the sched_switch event when that task schedules back in. It triggers the "stack" synthetic event that has a stacktrace as its field (called "stack"). ~# echo 's:syscall_stack s64 id; unsigned long stack[];' >> dynamic_events ~# echo 'hist:keys=common_pid:s2=stack' >> events/synthetic/stack/trigger ~# echo 'hist:keys=common_pid:s3=$s2,i0=id:onmatch(synthetic.stack).trace(syscall_stack,$i0,$s3)' >> events/raw_syscalls/sys_exit/trigger The above makes another synthetic event called "syscall_stack" that attaches the first synthetic event (stack) to the sys_exit trace event and records the stacktrace from the stack event with the id of the system call that is exiting. When enabling this event (or using it in a historgram): ~# echo 1 > events/synthetic/syscall_stack/enable Produces a kernel crash! BUG: unable to handle page fault for address: 0000000000400010 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP PTI CPU: 6 UID: 0 PID: 1257 Comm: bash Not tainted 6.16.3+deb14-amd64 #1 PREEMPT(lazy) Debian 6.16.3-1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 RIP: 0010:trace_event_raw_event_synth+0x90/0x380 Code: c5 00 00 00 00 85 d2 0f 84 e1 00 00 00 31 db eb 34 0f 1f 00 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 2e 0f 1f 84 00 00 00 00 00 <49> 8b 04 24 48 83 c3 01 8d 0c c5 08 00 00 00 01 cd 41 3b 5d 40 0f RSP: 0018:ffffd2670388f958 EFLAGS: 00010202 RAX: ffff8ba1065cc100 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: fffff266ffda7b90 RDI: ffffd2670388f9b0 RBP: 0000000000000010 R08: ffff8ba104e76000 R09: ffffd2670388fa50 R10: ffff8ba102dd42e0 R11: ffffffff9a908970 R12: 0000000000400010 R13: ffff8ba10a246400 R14: ffff8ba10a710220 R15: fffff266ffda7b90 FS: 00007fa3bc63f740(0000) GS:ffff8ba2e0f48000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000400010 CR3: 0000000107f9e003 CR4: 0000000000172ef0 Call Trace: <TASK> ? __tracing_map_insert+0x208/0x3a0 action_trace+0x67/0x70 event_hist_trigger+0x633/0x6d0 event_triggers_call+0x82/0x130 trace_event_buffer_commit+0x19d/0x250 trace_event_raw_event_sys_exit+0x62/0xb0 syscall_exit_work+0x9d/0x140 do_syscall_64+0x20a/0x2f0 ? trace_event_raw_event_sched_switch+0x12b/0x170 ? save_fpregs_to_fpstate+0x3e/0x90 ? _raw_spin_unlock+0xe/0x30 ? finish_task_switch.isra.0+0x97/0x2c0 ? __rseq_handle_notify_resume+0xad/0x4c0 ? __schedule+0x4b8/0xd00 ? restore_fpregs_from_fpstate+0x3c/0x90 ? switch_fpu_return+0x5b/0xe0 ? do_syscall_64+0x1ef/0x2f0 ? do_fault+0x2e9/0x540 ? __handle_mm_fault+0x7d1/0xf70 ? count_memcg_events+0x167/0x1d0 ? handle_mm_fault+0x1d7/0x2e0 ? do_user_addr_fault+0x2c3/0x7f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e The reason is that the stacktrace field is not labeled as such, and is treated as a normal field and not as a dynamic event that it is. In trace_event_raw_event_synth() the event is field is still treated as a dynamic array, but the retrieval of the data is considered a normal field, and the reference is just the meta data: // Meta data is retrieved instead of a dynamic array ---truncated---
CVE-2026-23099: In the Linux kernel, the following vulnerability has been resolved: bonding: limit BOND_MODE_8023AD to Ethernet devices BOND_MODE_8023AD makes sense for ARPHRD_ETHER only. syzbot reported: BUG: KASAN: global-out-of-bounds in __hw_addr_create net/core/dev_addr_lists.c:63 [inline] BUG: KASAN: global-out-of-bounds in __hw_addr_add_ex+0x25d/0x760 net/core/dev_addr_lists.c:118 Read of size 16 at addr ffffffff8bf94040 by task syz.1.3580/19497 CPU: 1 UID: 0 PID: 19497 Comm: syz.1.3580 Tainted: G L syzkaller #0 PREEMPT(full) Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025 Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 check_region_inline mm/kasan/generic.c:-1 [inline] kasan_check_range+0x2b0/0x2c0 mm/kasan/generic.c:200 __asan_memcpy+0x29/0x70 mm/kasan/shadow.c:105 __hw_addr_create net/core/dev_addr_lists.c:63 [inline] __hw_addr_add_ex+0x25d/0x760 net/core/dev_addr_lists.c:118 __dev_mc_add net/core/dev_addr_lists.c:868 [inline] dev_mc_add+0xa1/0x120 net/core/dev_addr_lists.c:886 bond_enslave+0x2b8b/0x3ac0 drivers/net/bonding/bond_main.c:2180 do_set_master+0x533/0x6d0 net/core/rtnetlink.c:2963 do_setlink+0xcf0/0x41c0 net/core/rtnetlink.c:3165 rtnl_changelink net/core/rtnetlink.c:3776 [inline] __rtnl_newlink net/core/rtnetlink.c:3935 [inline] rtnl_newlink+0x161c/0x1c90 net/core/rtnetlink.c:4072 rtnetlink_rcv_msg+0x7cf/0xb70 net/core/rtnetlink.c:6958 netlink_rcv_skb+0x208/0x470 net/netlink/af_netlink.c:2550 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x82f/0x9e0 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x805/0xb30 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg+0x21c/0x270 net/socket.c:742 ____sys_sendmsg+0x505/0x820 net/socket.c:2592 ___sys_sendmsg+0x21f/0x2a0 net/socket.c:2646 __sys_sendmsg+0x164/0x220 net/socket.c:2678 do_syscall_32_irqs_on arch/x86/entry/syscall_32.c:83 [inline] __do_fast_syscall_32+0x1dc/0x560 arch/x86/entry/syscall_32.c:307 do_fast_syscall_32+0x34/0x80 arch/x86/entry/syscall_32.c:332 entry_SYSENTER_compat_after_hwframe+0x84/0x8e </TASK> The buggy address belongs to the variable: lacpdu_mcast_addr+0x0/0x40
CVE-2026-23100: In the Linux kernel, the following vulnerability has been resolved: mm/hugetlb: fix hugetlb_pmd_shared() Patch series "mm/hugetlb: fixes for PMD table sharing (incl. using mmu_gather)", v3. One functional fix, one performance regression fix, and two related comment fixes. I cleaned up my prototype I recently shared [1] for the performance fix, deferring most of the cleanups I had in the prototype to a later point. While doing that I identified the other things. The goal of this patch set is to be backported to stable trees "fairly" easily. At least patch #1 and #4. Patch #1 fixes hugetlb_pmd_shared() not detecting any sharing Patch #2 + #3 are simple comment fixes that patch #4 interacts with. Patch #4 is a fix for the reported performance regression due to excessive IPI broadcasts during fork()+exit(). The last patch is all about TLB flushes, IPIs and mmu_gather. Read: complicated There are plenty of cleanups in the future to be had + one reasonable optimization on x86. But that's all out of scope for this series. Runtime tested, with a focus on fixing the performance regression using the original reproducer [2] on x86. This patch (of 4): We switched from (wrongly) using the page count to an independent shared count. Now, shared page tables have a refcount of 1 (excluding speculative references) and instead use ptdesc->pt_share_count to identify sharing. We didn't convert hugetlb_pmd_shared(), so right now, we would never detect a shared PMD table as such, because sharing/unsharing no longer touches the refcount of a PMD table. Page migration, like mbind() or migrate_pages() would allow for migrating folios mapped into such shared PMD tables, even though the folios are not exclusive. In smaps we would account them as "private" although they are "shared", and we would be wrongly setting the PM_MMAP_EXCLUSIVE in the pagemap interface. Fix it by properly using ptdesc_pmd_is_shared() in hugetlb_pmd_shared().
CVE-2026-23110: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Wake up the error handler when final completions race against each other The fragile ordering between marking commands completed or failed so that the error handler only wakes when the last running command completes or times out has race conditions. These race conditions can cause the SCSI layer to fail to wake the error handler, leaving I/O through the SCSI host stuck as the error state cannot advance. First, there is an memory ordering issue within scsi_dec_host_busy(). The write which clears SCMD_STATE_INFLIGHT may be reordered with reads counting in scsi_host_busy(). While the local CPU will see its own write, reordering can allow other CPUs in scsi_dec_host_busy() or scsi_eh_inc_host_failed() to see a raised busy count, causing no CPU to see a host busy equal to the host_failed count. This race condition can be prevented with a memory barrier on the error path to force the write to be visible before counting host busy commands. Second, there is a general ordering issue with scsi_eh_inc_host_failed(). By counting busy commands before incrementing host_failed, it can race with a final command in scsi_dec_host_busy(), such that scsi_dec_host_busy() does not see host_failed incremented but scsi_eh_inc_host_failed() counts busy commands before SCMD_STATE_INFLIGHT is cleared by scsi_dec_host_busy(), resulting in neither waking the error handler task. This needs the call to scsi_host_busy() to be moved after host_failed is incremented to close the race condition.
CVE-2026-23111: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix inverted genmask check in nft_map_catchall_activate() nft_map_catchall_activate() has an inverted element activity check compared to its non-catchall counterpart nft_mapelem_activate() and compared to what is logically required. nft_map_catchall_activate() is called from the abort path to re-activate catchall map elements that were deactivated during a failed transaction. It should skip elements that are already active (they don't need re-activation) and process elements that are inactive (they need to be restored). Instead, the current code does the opposite: it skips inactive elements and processes active ones. Compare the non-catchall activate callback, which is correct: nft_mapelem_activate(): if (nft_set_elem_active(ext, iter->genmask)) return 0; /* skip active, process inactive */ With the buggy catchall version: nft_map_catchall_activate(): if (!nft_set_elem_active(ext, genmask)) continue; /* skip inactive, process active */ The consequence is that when a DELSET operation is aborted, nft_setelem_data_activate() is never called for the catchall element. For NFT_GOTO verdict elements, this means nft_data_hold() is never called to restore the chain->use reference count. Each abort cycle permanently decrements chain->use. Once chain->use reaches zero, DELCHAIN succeeds and frees the chain while catchall verdict elements still reference it, resulting in a use-after-free. This is exploitable for local privilege escalation from an unprivileged user via user namespaces + nftables on distributions that enable CONFIG_USER_NS and CONFIG_NF_TABLES. Fix by removing the negation so the check matches nft_mapelem_activate(): skip active elements, process inactive ones.
CVE-2026-23118: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix data-race warning and potential load/store tearing Fix the following: BUG: KCSAN: data-race in rxrpc_peer_keepalive_worker / rxrpc_send_data_packet which is reporting an issue with the reads and writes to ->last_tx_at in: conn->peer->last_tx_at = ktime_get_seconds(); and: keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; The lockless accesses to these to values aren't actually a problem as the read only needs an approximate time of last transmission for the purposes of deciding whether or not the transmission of a keepalive packet is warranted yet. Also, as ->last_tx_at is a 64-bit value, tearing can occur on a 32-bit arch. Fix both of these by switching to an unsigned int for ->last_tx_at and only storing the LSW of the time64_t. It can then be reconstructed at need provided no more than 68 years has elapsed since the last transmission.
CVE-2026-23126: In the Linux kernel, the following vulnerability has been resolved: netdevsim: fix a race issue related to the operation on bpf_bound_progs list The netdevsim driver lacks a protection mechanism for operations on the bpf_bound_progs list. When the nsim_bpf_create_prog() performs list_add_tail, it is possible that nsim_bpf_destroy_prog() is simultaneously performs list_del. Concurrent operations on the list may lead to list corruption and trigger a kernel crash as follows: [ 417.290971] kernel BUG at lib/list_debug.c:62! [ 417.290983] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [ 417.290992] CPU: 10 PID: 168 Comm: kworker/10:1 Kdump: loaded Not tainted 6.19.0-rc5 #1 [ 417.291003] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 417.291007] Workqueue: events bpf_prog_free_deferred [ 417.291021] RIP: 0010:__list_del_entry_valid_or_report+0xa7/0xc0 [ 417.291034] Code: a8 ff 0f 0b 48 89 fe 48 89 ca 48 c7 c7 48 a1 eb ae e8 ed fb a8 ff 0f 0b 48 89 fe 48 89 c2 48 c7 c7 80 a1 eb ae e8 d9 fb a8 ff <0f> 0b 48 89 d1 48 c7 c7 d0 a1 eb ae 48 89 f2 48 89 c6 e8 c2 fb a8 [ 417.291040] RSP: 0018:ffffb16a40807df8 EFLAGS: 00010246 [ 417.291046] RAX: 000000000000006d RBX: ffff8e589866f500 RCX: 0000000000000000 [ 417.291051] RDX: 0000000000000000 RSI: ffff8e59f7b23180 RDI: ffff8e59f7b23180 [ 417.291055] RBP: ffffb16a412c9000 R08: 0000000000000000 R09: 0000000000000003 [ 417.291059] R10: ffffb16a40807c80 R11: ffffffffaf9edce8 R12: ffff8e594427ac20 [ 417.291063] R13: ffff8e59f7b44780 R14: ffff8e58800b7a05 R15: 0000000000000000 [ 417.291074] FS: 0000000000000000(0000) GS:ffff8e59f7b00000(0000) knlGS:0000000000000000 [ 417.291079] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 417.291083] CR2: 00007fc4083efe08 CR3: 00000001c3626006 CR4: 0000000000770ee0 [ 417.291088] PKRU: 55555554 [ 417.291091] Call Trace: [ 417.291096] <TASK> [ 417.291103] nsim_bpf_destroy_prog+0x31/0x80 [netdevsim] [ 417.291154] __bpf_prog_offload_destroy+0x2a/0x80 [ 417.291163] bpf_prog_dev_bound_destroy+0x6f/0xb0 [ 417.291171] bpf_prog_free_deferred+0x18e/0x1a0 [ 417.291178] process_one_work+0x18a/0x3a0 [ 417.291188] worker_thread+0x27b/0x3a0 [ 417.291197] ? __pfx_worker_thread+0x10/0x10 [ 417.291207] kthread+0xe5/0x120 [ 417.291214] ? __pfx_kthread+0x10/0x10 [ 417.291221] ret_from_fork+0x31/0x50 [ 417.291230] ? __pfx_kthread+0x10/0x10 [ 417.291236] ret_from_fork_asm+0x1a/0x30 [ 417.291246] </TASK> Add a mutex lock, to prevent simultaneous addition and deletion operations on the list.
CVE-2026-23137: In the Linux kernel, the following vulnerability has been resolved: of: unittest: Fix memory leak in unittest_data_add() In unittest_data_add(), if of_resolve_phandles() fails, the allocated unittest_data is not freed, leading to a memory leak. Fix this by using scope-based cleanup helper __free(kfree) for automatic resource cleanup. This ensures unittest_data is automatically freed when it goes out of scope in error paths. For the success path, use retain_and_null_ptr() to transfer ownership of the memory to the device tree and prevent double freeing.
CVE-2026-23138: In the Linux kernel, the following vulnerability has been resolved: tracing: Add recursion protection in kernel stack trace recording A bug was reported about an infinite recursion caused by tracing the rcu events with the kernel stack trace trigger enabled. The stack trace code called back into RCU which then called the stack trace again. Expand the ftrace recursion protection to add a set of bits to protect events from recursion. Each bit represents the context that the event is in (normal, softirq, interrupt and NMI). Have the stack trace code use the interrupt context to protect against recursion. Note, the bug showed an issue in both the RCU code as well as the tracing stacktrace code. This only handles the tracing stack trace side of the bug. The RCU fix will be handled separately.
CVE-2026-23141: In the Linux kernel, the following vulnerability has been resolved: btrfs: send: check for inline extents in range_is_hole_in_parent() Before accessing the disk_bytenr field of a file extent item we need to check if we are dealing with an inline extent. This is because for inline extents their data starts at the offset of the disk_bytenr field. So accessing the disk_bytenr means we are accessing inline data or in case the inline data is less than 8 bytes we can actually cause an invalid memory access if this inline extent item is the first item in the leaf or access metadata from other items.
CVE-2026-23154: In the Linux kernel, the following vulnerability has been resolved: net: fix segmentation of forwarding fraglist GRO This patch enhances GSO segment handling by properly checking the SKB_GSO_DODGY flag for frag_list GSO packets, addressing low throughput issues observed when a station accesses IPv4 servers via hotspots with an IPv6-only upstream interface. Specifically, it fixes a bug in GSO segmentation when forwarding GRO packets containing a frag_list. The function skb_segment_list cannot correctly process GRO skbs that have been converted by XLAT, since XLAT only translates the header of the head skb. Consequently, skbs in the frag_list may remain untranslated, resulting in protocol inconsistencies and reduced throughput. To address this, the patch explicitly sets the SKB_GSO_DODGY flag for GSO packets in XLAT's IPv4/IPv6 protocol translation helpers (bpf_skb_proto_4_to_6 and bpf_skb_proto_6_to_4). This marks GSO packets as potentially modified after protocol translation. As a result, GSO segmentation will avoid using skb_segment_list and instead falls back to skb_segment for packets with the SKB_GSO_DODGY flag. This ensures that only safe and fully translated frag_list packets are processed by skb_segment_list, resolving protocol inconsistencies and improving throughput when forwarding GRO packets converted by XLAT.
CVE-2026-23157: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not strictly require dirty metadata threshold for metadata writepages [BUG] There is an internal report that over 1000 processes are waiting at the io_schedule_timeout() of balance_dirty_pages(), causing a system hang and trigger a kernel coredump. The kernel is v6.4 kernel based, but the root problem still applies to any upstream kernel before v6.18. [CAUSE] From Jan Kara for his wisdom on the dirty page balance behavior first. This cgroup dirty limit was what was actually playing the role here because the cgroup had only a small amount of memory and so the dirty limit for it was something like 16MB. Dirty throttling is responsible for enforcing that nobody can dirty (significantly) more dirty memory than there's dirty limit. Thus when a task is dirtying pages it periodically enters into balance_dirty_pages() and we let it sleep there to slow down the dirtying. When the system is over dirty limit already (either globally or within a cgroup of the running task), we will not let the task exit from balance_dirty_pages() until the number of dirty pages drops below the limit. So in this particular case, as I already mentioned, there was a cgroup with relatively small amount of memory and as a result with dirty limit set at 16MB. A task from that cgroup has dirtied about 28MB worth of pages in btrfs btree inode and these were practically the only dirty pages in that cgroup. So that means the only way to reduce the dirty pages of that cgroup is to writeback the dirty pages of btrfs btree inode, and only after that those processes can exit balance_dirty_pages(). Now back to the btrfs part, btree_writepages() is responsible for writing back dirty btree inode pages. The problem here is, there is a btrfs internal threshold that if the btree inode's dirty bytes are below the 32M threshold, it will not do any writeback. This behavior is to batch as much metadata as possible so we won't write back those tree blocks and then later re-COW them again for another modification. This internal 32MiB is higher than the existing dirty page size (28MiB), meaning no writeback will happen, causing a deadlock between btrfs and cgroup: - Btrfs doesn't want to write back btree inode until more dirty pages - Cgroup/MM doesn't want more dirty pages for btrfs btree inode Thus any process touching that btree inode is put into sleep until the number of dirty pages is reduced. Thanks Jan Kara a lot for the analysis of the root cause. [ENHANCEMENT] Since kernel commit b55102826d7d ("btrfs: set AS_KERNEL_FILE on the btree_inode"), btrfs btree inode pages will only be charged to the root cgroup which should have a much larger limit than btrfs' 32MiB threshold. So it should not affect newer kernels. But for all current LTS kernels, they are all affected by this problem, and backporting the whole AS_KERNEL_FILE may not be a good idea. Even for newer kernels I still think it's a good idea to get rid of the internal threshold at btree_writepages(), since for most cases cgroup/MM has a better view of full system memory usage than btrfs' fixed threshold. For internal callers using btrfs_btree_balance_dirty() since that function is already doing internal threshold check, we don't need to bother them. But for external callers of btree_writepages(), just respect their requests and write back whatever they want, ignoring the internal btrfs threshold to avoid such deadlock on btree inode dirty page balancing.
CVE-2026-23191: In the Linux kernel, the following vulnerability has been resolved: ALSA: aloop: Fix racy access at PCM trigger The PCM trigger callback of aloop driver tries to check the PCM state and stop the stream of the tied substream in the corresponding cable. Since both check and stop operations are performed outside the cable lock, this may result in UAF when a program attempts to trigger frequently while opening/closing the tied stream, as spotted by fuzzers. For addressing the UAF, this patch changes two things: - It covers the most of code in loopback_check_format() with cable->lock spinlock, and add the proper NULL checks. This avoids already some racy accesses. - In addition, now we try to check the state of the capture PCM stream that may be stopped in this function, which was the major pain point leading to UAF.
CVE-2026-23204: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_u32: use skb_header_pointer_careful() skb_header_pointer() does not fully validate negative @offset values. Use skb_header_pointer_careful() instead. GangMin Kim provided a report and a repro fooling u32_classify(): BUG: KASAN: slab-out-of-bounds in u32_classify+0x1180/0x11b0 net/sched/cls_u32.c:221
CVE-2026-23208: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Prevent excessive number of frames In this case, the user constructed the parameters with maxpacksize 40 for rate 22050 / pps 1000, and packsize[0] 22 packsize[1] 23. The buffer size for each data URB is maxpacksize * packets, which in this example is 40 * 6 = 240; When the user performs a write operation to send audio data into the ALSA PCM playback stream, the calculated number of frames is packsize[0] * packets = 264, which exceeds the allocated URB buffer size, triggering the out-of-bounds (OOB) issue reported by syzbot [1]. Added a check for the number of single data URB frames when calculating the number of frames to prevent [1]. [1] BUG: KASAN: slab-out-of-bounds in copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 Write of size 264 at addr ffff88804337e800 by task syz.0.17/5506 Call Trace: copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 prepare_playback_urb+0x953/0x13d0 sound/usb/pcm.c:1611 prepare_outbound_urb+0x377/0xc50 sound/usb/endpoint.c:333
CVE-2026-23212: In the Linux kernel, the following vulnerability has been resolved: bonding: annotate data-races around slave->last_rx slave->last_rx and slave->target_last_arp_rx[...] can be read and written locklessly. Add READ_ONCE() and WRITE_ONCE() annotations. syzbot reported: BUG: KCSAN: data-race in bond_rcv_validate / bond_rcv_validate write to 0xffff888149f0d428 of 8 bytes by interrupt on cpu 1: bond_rcv_validate+0x202/0x7a0 drivers/net/bonding/bond_main.c:3335 bond_handle_frame+0xde/0x5e0 drivers/net/bonding/bond_main.c:1533 __netif_receive_skb_core+0x5b1/0x1950 net/core/dev.c:6039 __netif_receive_skb_one_core net/core/dev.c:6150 [inline] __netif_receive_skb+0x59/0x270 net/core/dev.c:6265 netif_receive_skb_internal net/core/dev.c:6351 [inline] netif_receive_skb+0x4b/0x2d0 net/core/dev.c:6410 ... write to 0xffff888149f0d428 of 8 bytes by interrupt on cpu 0: bond_rcv_validate+0x202/0x7a0 drivers/net/bonding/bond_main.c:3335 bond_handle_frame+0xde/0x5e0 drivers/net/bonding/bond_main.c:1533 __netif_receive_skb_core+0x5b1/0x1950 net/core/dev.c:6039 __netif_receive_skb_one_core net/core/dev.c:6150 [inline] __netif_receive_skb+0x59/0x270 net/core/dev.c:6265 netif_receive_skb_internal net/core/dev.c:6351 [inline] netif_receive_skb+0x4b/0x2d0 net/core/dev.c:6410 br_netif_receive_skb net/bridge/br_input.c:30 [inline] NF_HOOK include/linux/netfilter.h:318 [inline] ... value changed: 0x0000000100005365 -> 0x0000000100005366
CVE-2026-23213: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: Disable MMIO access during SMU Mode 1 reset During Mode 1 reset, the ASIC undergoes a reset cycle and becomes temporarily inaccessible via PCIe. Any attempt to access MMIO registers during this window (e.g., from interrupt handlers or other driver threads) can result in uncompleted PCIe transactions, leading to NMI panics or system hangs. To prevent this, set the `no_hw_access` flag to true immediately after triggering the reset. This signals other driver components to skip register accesses while the device is offline. A memory barrier `smp_mb()` is added to ensure the flag update is globally visible to all cores before the driver enters the sleep/wait state. (cherry picked from commit 7edb503fe4b6d67f47d8bb0dfafb8e699bb0f8a4)
CVE-2026-23221: In the Linux kernel, the following vulnerability has been resolved: bus: fsl-mc: fix use-after-free in driver_override_show() The driver_override_show() function reads the driver_override string without holding the device_lock. However, driver_override_store() uses driver_set_override(), which modifies and frees the string while holding the device_lock. This can result in a concurrent use-after-free if the string is freed by the store function while being read by the show function. Fix this by holding the device_lock around the read operation.
CVE-2026-23227: In the Linux kernel, the following vulnerability has been resolved: drm/exynos: vidi: use ctx->lock to protect struct vidi_context member variables related to memory alloc/free Exynos Virtual Display driver performs memory alloc/free operations without lock protection, which easily causes concurrency problem. For example, use-after-free can occur in race scenario like this: ``` CPU0 CPU1 CPU2 ---- ---- ---- vidi_connection_ioctl() if (vidi->connection) // true drm_edid = drm_edid_alloc(); // alloc drm_edid ... ctx->raw_edid = drm_edid; ... drm_mode_getconnector() drm_helper_probe_single_connector_modes() vidi_get_modes() if (ctx->raw_edid) // true drm_edid_dup(ctx->raw_edid); if (!drm_edid) // false ... vidi_connection_ioctl() if (vidi->connection) // false drm_edid_free(ctx->raw_edid); // free drm_edid ... drm_edid_alloc(drm_edid->edid) kmemdup(edid); // UAF!! ... ``` To prevent these vulns, at least in vidi_context, member variables related to memory alloc/free should be protected with ctx->lock.
CVE-2026-23231: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix use-after-free in nf_tables_addchain() nf_tables_addchain() publishes the chain to table->chains via list_add_tail_rcu() (in nft_chain_add()) before registering hooks. If nf_tables_register_hook() then fails, the error path calls nft_chain_del() (list_del_rcu()) followed by nf_tables_chain_destroy() with no RCU grace period in between. This creates two use-after-free conditions: 1) Control-plane: nf_tables_dump_chains() traverses table->chains under rcu_read_lock(). A concurrent dump can still be walking the chain when the error path frees it. 2) Packet path: for NFPROTO_INET, nf_register_net_hook() briefly installs the IPv4 hook before IPv6 registration fails. Packets entering nft_do_chain() via the transient IPv4 hook can still be dereferencing chain->blob_gen_X when the error path frees the chain. Add synchronize_rcu() between nft_chain_del() and the chain destroy so that all RCU readers -- both dump threads and in-flight packet evaluation -- have finished before the chain is freed.
CVE-2026-23239: In the Linux kernel, the following vulnerability has been resolved: espintcp: Fix race condition in espintcp_close() This issue was discovered during a code audit. After cancel_work_sync() is called from espintcp_close(), espintcp_tx_work() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the espintcp_tx_work() worker may dereference a freed espintcp ctx or sk. The following is a simple race scenario: cpu0 cpu1 espintcp_close() cancel_work_sync(&ctx->work); espintcp_write_space() schedule_work(&ctx->work); To prevent this race condition, cancel_work_sync() is replaced with disable_work_sync().
CVE-2026-23240: In the Linux kernel, the following vulnerability has been resolved: tls: Fix race condition in tls_sw_cancel_work_tx() This issue was discovered during a code audit. After cancel_delayed_work_sync() is called from tls_sk_proto_close(), tx_work_handler() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the tx_work_handler() worker may dereference a freed TLS object. The following is a simple race scenario: cpu0 cpu1 tls_sk_proto_close() tls_sw_cancel_work_tx() tls_write_space() tls_sw_write_space() if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); cancel_delayed_work_sync(&ctx->tx_work.work); schedule_delayed_work(&tx_ctx->tx_work.work, 0); To prevent this race condition, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().
CVE-2026-23242: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Fix potential NULL pointer dereference in header processing If siw_get_hdr() returns -EINVAL before set_rx_fpdu_context(), qp->rx_fpdu can be NULL. The error path in siw_tcp_rx_data() dereferences qp->rx_fpdu->more_ddp_segs without checking, which may lead to a NULL pointer deref. Only check more_ddp_segs when rx_fpdu is present. KASAN splat: [ 101.384271] KASAN: null-ptr-deref in range [0x00000000000000c0-0x00000000000000c7] [ 101.385869] RIP: 0010:siw_tcp_rx_data+0x13ad/0x1e50
CVE-2026-23243: In the Linux kernel, the following vulnerability has been resolved: RDMA/umad: Reject negative data_len in ib_umad_write ib_umad_write computes data_len from user-controlled count and the MAD header sizes. With a mismatched user MAD header size and RMPP header length, data_len can become negative and reach ib_create_send_mad(). This can make the padding calculation exceed the segment size and trigger an out-of-bounds memset in alloc_send_rmpp_list(). Add an explicit check to reject negative data_len before creating the send buffer. KASAN splat: [ 211.363464] BUG: KASAN: slab-out-of-bounds in ib_create_send_mad+0xa01/0x11b0 [ 211.364077] Write of size 220 at addr ffff88800c3fa1f8 by task spray_thread/102 [ 211.365867] ib_create_send_mad+0xa01/0x11b0 [ 211.365887] ib_umad_write+0x853/0x1c80
CVE-2026-23245: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_gate: snapshot parameters with RCU on replace The gate action can be replaced while the hrtimer callback or dump path is walking the schedule list. Convert the parameters to an RCU-protected snapshot and swap updates under tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits the entry list, preserve the existing schedule so the effective state is unchanged.
CVE-2026-23247: In the Linux kernel, the following vulnerability has been resolved: tcp: secure_seq: add back ports to TS offset This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets") tcp_tw_recycle went away in 2017. Zhouyan Deng reported off-path TCP source port leakage via SYN cookie side-channel that can be fixed in multiple ways. One of them is to bring back TCP ports in TS offset randomization. As a bonus, we perform a single siphash() computation to provide both an ISN and a TS offset.
CVE-2026-23253: In the Linux kernel, the following vulnerability has been resolved: media: dvb-core: fix wrong reinitialization of ringbuffer on reopen dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty. Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}. The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions. Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.
CVE-2026-23255: In the Linux kernel, the following vulnerability has been resolved: net: add proper RCU protection to /proc/net/ptype Yin Fengwei reported an RCU stall in ptype_seq_show() and provided a patch. Real issue is that ptype_seq_next() and ptype_seq_show() violate RCU rules. ptype_seq_show() runs under rcu_read_lock(), and reads pt->dev to get device name without any barrier. At the same time, concurrent writers can remove a packet_type structure (which is correctly freed after an RCU grace period) and clear pt->dev without an RCU grace period. Define ptype_iter_state to carry a dev pointer along seq_net_private: struct ptype_iter_state { struct seq_net_private p; struct net_device *dev; // added in this patch }; We need to record the device pointer in ptype_get_idx() and ptype_seq_next() so that ptype_seq_show() is safe against concurrent pt->dev changes. We also need to add full RCU protection in ptype_seq_next(). (Missing READ_ONCE() when reading list.next values) Many thanks to Dong Chenchen for providing a repro.
CVE-2026-23265: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer in {read,write}_end_io -----------[ cut here ]------------ kernel BUG at fs/f2fs/data.c:358! Call Trace: <IRQ> blk_update_request+0x5eb/0xe70 block/blk-mq.c:987 blk_mq_end_request+0x3e/0x70 block/blk-mq.c:1149 blk_complete_reqs block/blk-mq.c:1224 [inline] blk_done_softirq+0x107/0x160 block/blk-mq.c:1229 handle_softirqs+0x283/0x870 kernel/softirq.c:579 __do_softirq kernel/softirq.c:613 [inline] invoke_softirq kernel/softirq.c:453 [inline] __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1050 </IRQ> In f2fs_write_end_io(), it detects there is inconsistency in between node page index (nid) and footer.nid of node page. If footer of node page is corrupted in fuzzed image, then we load corrupted node page w/ async method, e.g. f2fs_ra_node_pages() or f2fs_ra_node_page(), in where we won't do sanity check on node footer, once node page becomes dirty, we will encounter this bug after node page writeback.
CVE-2026-23267: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix IS_CHECKPOINTED flag inconsistency issue caused by concurrent atomic commit and checkpoint writes During SPO tests, when mounting F2FS, an -EINVAL error was returned from f2fs_recover_inode_page. The issue occurred under the following scenario Thread A Thread B f2fs_ioc_commit_atomic_write - f2fs_do_sync_file // atomic = true - f2fs_fsync_node_pages : last_folio = inode folio : schedule before folio_lock(last_folio) f2fs_write_checkpoint - block_operations// writeback last_folio - schedule before f2fs_flush_nat_entries : set_fsync_mark(last_folio, 1) : set_dentry_mark(last_folio, 1) : folio_mark_dirty(last_folio) - __write_node_folio(last_folio) : f2fs_down_read(&sbi->node_write)//block - f2fs_flush_nat_entries : {struct nat_entry}->flag |= BIT(IS_CHECKPOINTED) - unblock_operations : f2fs_up_write(&sbi->node_write) f2fs_write_checkpoint//return : f2fs_do_write_node_page() f2fs_ioc_commit_atomic_write//return SPO Thread A calls f2fs_need_dentry_mark(sbi, ino), and the last_folio has already been written once. However, the {struct nat_entry}->flag did not have the IS_CHECKPOINTED set, causing set_dentry_mark(last_folio, 1) and write last_folio again after Thread B finishes f2fs_write_checkpoint. After SPO and reboot, it was detected that {struct node_info}->blk_addr was not NULL_ADDR because Thread B successfully write the checkpoint. This issue only occurs in atomic write scenarios. For regular file fsync operations, the folio must be dirty. If block_operations->f2fs_sync_node_pages successfully submit the folio write, this path will not be executed. Otherwise, the f2fs_write_checkpoint will need to wait for the folio write submission to complete, as sbi->nr_pages[F2FS_DIRTY_NODES] > 0. Therefore, the situation where f2fs_need_dentry_mark checks that the {struct nat_entry}->flag /wo the IS_CHECKPOINTED flag, but the folio write has already been submitted, will not occur. Therefore, for atomic file fsync, sbi->node_write should be acquired through __write_node_folio to ensure that the IS_CHECKPOINTED flag correctly indicates that the checkpoint write has been completed.
CVE-2026-23271: In the Linux kernel, the following vulnerability has been resolved: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race Make sure that __perf_event_overflow() runs with IRQs disabled for all possible callchains. Specifically the software events can end up running it with only preemption disabled. This opens up a race vs perf_event_exit_event() and friends that will go and free various things the overflow path expects to be present, like the BPF program.
CVE-2026-23272: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: unconditionally bump set->nelems before insertion In case that the set is full, a new element gets published then removed without waiting for the RCU grace period, while RCU reader can be walking over it already. To address this issue, add the element transaction even if set is full, but toggle the set_full flag to report -ENFILE so the abort path safely unwinds the set to its previous state. As for element updates, decrement set->nelems to restore it. A simpler fix is to call synchronize_rcu() in the error path. However, with a large batch adding elements to already maxed-out set, this could cause noticeable slowdown of such batches.
CVE-2026-23273: In the Linux kernel, the following vulnerability has been resolved: macvlan: observe an RCU grace period in macvlan_common_newlink() error path valis reported that a race condition still happens after my prior patch. macvlan_common_newlink() might have made @dev visible before detecting an error, and its caller will directly call free_netdev(dev). We must respect an RCU period, either in macvlan or the core networking stack. After adding a temporary mdelay(1000) in macvlan_forward_source_one() to open the race window, valis repro was: ip link add p1 type veth peer p2 ip link set address 00:00:00:00:00:20 dev p1 ip link set up dev p1 ip link set up dev p2 ip link add mv0 link p2 type macvlan mode source (ip link add invalid% link p2 type macvlan mode source macaddr add 00:00:00:00:00:20 &) ; sleep 0.5 ; ping -c1 -I p1 1.2.3.4 PING 1.2.3.4 (1.2.3.4): 56 data bytes RTNETLINK answers: Invalid argument BUG: KASAN: slab-use-after-free in macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) Read of size 8 at addr ffff888016bb89c0 by task e/175 CPU: 1 UID: 1000 PID: 175 Comm: e Not tainted 6.19.0-rc8+ #33 NONE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) kasan_report (mm/kasan/report.c:597) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) ? tasklet_init (kernel/softirq.c:983) macvlan_handle_frame (drivers/net/macvlan.c:501) Allocated by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) __kasan_kmalloc (mm/kasan/common.c:419) __kvmalloc_node_noprof (./include/linux/kasan.h:263 mm/slub.c:5657 mm/slub.c:7140) alloc_netdev_mqs (net/core/dev.c:12012) rtnl_create_link (net/core/rtnetlink.c:3648) rtnl_newlink (net/core/rtnetlink.c:3830 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131) Freed by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) kasan_save_free_info (mm/kasan/generic.c:587) __kasan_slab_free (mm/kasan/common.c:287) kfree (mm/slub.c:6674 mm/slub.c:6882) rtnl_newlink (net/core/rtnetlink.c:3845 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
CVE-2026-23274: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels IDLETIMER revision 0 rules reuse existing timers by label and always call mod_timer() on timer->timer. If the label was created first by revision 1 with XT_IDLETIMER_ALARM, the object uses alarm timer semantics and timer->timer is never initialized. Reusing that object from revision 0 causes mod_timer() on an uninitialized timer_list, triggering debugobjects warnings and possible panic when panic_on_warn=1. Fix this by rejecting revision 0 rule insertion when an existing timer with the same label is of ALARM type.
CVE-2026-23276: In the Linux kernel, the following vulnerability has been resolved: net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: <TASK> __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread </TASK>
CVE-2026-23277: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit through slave devices, but does not update skb->dev to the slave device beforehand. When a gretap tunnel is a TEQL slave, the transmit path reaches iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0 master) and later calls iptunnel_xmit_stats(dev, pkt_len). This function does: get_cpu_ptr(dev->tstats) Since teql_master_setup() does not set dev->pcpu_stat_type to NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes NULL + __per_cpu_offset[cpu], resulting in a page fault. BUG: unable to handle page fault for address: ffff8880e6659018 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 68bc067 P4D 68bc067 PUD 0 Oops: Oops: 0002 [#1] SMP KASAN PTI RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89) Call Trace: <TASK> ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) __gre_xmit (net/ipv4/ip_gre.c:478) gre_tap_xmit (net/ipv4/ip_gre.c:779) teql_master_xmit (net/sched/sch_teql.c:319) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) neigh_direct_output (net/core/neighbour.c:1660) ip_finish_output2 (net/ipv4/ip_output.c:237) __ip_finish_output.part.0 (net/ipv4/ip_output.c:315) ip_mc_output (net/ipv4/ip_output.c:369) ip_send_skb (net/ipv4/ip_output.c:1508) udp_send_skb (net/ipv4/udp.c:1195) udp_sendmsg (net/ipv4/udp.c:1485) inet_sendmsg (net/ipv4/af_inet.c:859) __sys_sendto (net/socket.c:2206) Fix this by setting skb->dev = slave before calling netdev_start_xmit(), so that tunnel xmit functions see the correct slave device with properly allocated tstats.
CVE-2026-23278: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: always walk all pending catchall elements During transaction processing we might have more than one catchall element: 1 live catchall element and 1 pending element that is coming as part of the new batch. If the map holding the catchall elements is also going away, its required to toggle all catchall elements and not just the first viable candidate. Otherwise, we get: WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables] [..] __nft_set_elem_destroy+0x106/0x380 [nf_tables] nf_tables_abort_release+0x348/0x8d0 [nf_tables] nf_tables_abort+0xcf2/0x3ac0 [nf_tables] nfnetlink_rcv_batch+0x9c9/0x20e0 [..]
CVE-2026-23279: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame() In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check: ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl; ... pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value); The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference. A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required. Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211] CR2: 0000000000000000 Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code. The bug has been present since v3.13 (released 2014-01-19).
CVE-2026-23281: In the Linux kernel, the following vulnerability has been resolved: wifi: libertas: fix use-after-free in lbs_free_adapter() The lbs_free_adapter() function uses timer_delete() (non-synchronous) for both command_timer and tx_lockup_timer before the structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete. If a timer callback is executing when lbs_free_adapter() is called, the callback will access freed memory since lbs_cfg_free() frees the containing structure immediately after lbs_free_adapter() returns. Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler) access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields, which would all be use-after-free violations. Use timer_delete_sync() instead to ensure any running timer callback has completed before returning. This bug was introduced in commit 8f641d93c38a ("libertas: detect TX lockups and reset hardware") where del_timer() was used instead of del_timer_sync() in the cleanup path. The command_timer has had the same issue since the driver was first written.
CVE-2026-23286: In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix null-ptr-deref in lec_arp_clear_vccs syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer. In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry. For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables: 1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL. 2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash. Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers. The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket. The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.
CVE-2026-23287: In the Linux kernel, the following vulnerability has been resolved: irqchip/sifive-plic: Fix frozen interrupt due to affinity setting PLIC ignores interrupt completion message for disabled interrupt, explained by the specification: The PLIC signals it has completed executing an interrupt handler by writing the interrupt ID it received from the claim to the claim/complete register. The PLIC does not check whether the completion ID is the same as the last claim ID for that target. If the completion ID does not match an interrupt source that is currently enabled for the target, the completion is silently ignored. This caused problems in the past, because an interrupt can be disabled while still being handled and plic_irq_eoi() had no effect. That was fixed by checking if the interrupt is disabled, and if so enable it, before sending the completion message. That check is done with irqd_irq_disabled(). However, that is not sufficient because the enable bit for the handling hart can be zero despite irqd_irq_disabled(d) being false. This can happen when affinity setting is changed while a hart is still handling the interrupt. This problem is easily reproducible by dumping a large file to uart (which generates lots of interrupts) and at the same time keep changing the uart interrupt's affinity setting. The uart port becomes frozen almost instantaneously. Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().
CVE-2026-23289: In the Linux kernel, the following vulnerability has been resolved: IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq() Fix a user triggerable leak on the system call failure path.
CVE-2026-23290: In the Linux kernel, the following vulnerability has been resolved: net: usb: pegasus: validate USB endpoints The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23291: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: properly drop the usb interface reference on disconnect When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.
CVE-2026-23292: In the Linux kernel, the following vulnerability has been resolved: scsi: target: Fix recursive locking in __configfs_open_file() In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace: down_read __configfs_open_file do_dentry_open vfs_open do_open path_openat do_filp_open file_open_name filp_open target_core_item_dbroot_store flush_write_buffer configfs_write_iter target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows: db_root: not a directory: /sys/kernel/config/target/dbroot indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking. Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.
CVE-2026-23293: In the Linux kernel, the following vulnerability has been resolved: net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If an IPv6 packet is injected into the interface, route_shortcircuit() is called and a NULL pointer dereference happens on neigh_lookup(). BUG: kernel NULL pointer dereference, address: 0000000000000380 Oops: Oops: 0000 [#1] SMP NOPTI [...] RIP: 0010:neigh_lookup+0x20/0x270 [...] Call Trace: <TASK> vxlan_xmit+0x638/0x1ef0 [vxlan] dev_hard_start_xmit+0x9e/0x2e0 __dev_queue_xmit+0xbee/0x14e0 packet_sendmsg+0x116f/0x1930 __sys_sendto+0x1f5/0x200 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x12f/0x1590 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fix this by adding an early check on route_shortcircuit() when protocol is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because VXLAN can be built-in even when IPv6 is built as a module.
CVE-2026-23296: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix refcount leak for tagset_refcnt This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace: [130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid" #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef
CVE-2026-23298: In the Linux kernel, the following vulnerability has been resolved: can: ucan: Fix infinite loop from zero-length messages If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one. This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.
CVE-2026-23300: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop When a standalone IPv6 nexthop object is created with a loopback device (e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies it as a reject route. This is because nexthop objects have no destination prefix (fc_dst=::), causing fib6_is_reject() to match any loopback nexthop. The reject path skips fib_nh_common_init(), leaving nhc_pcpu_rth_output unallocated. If an IPv4 route later references this nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and panics. Simplify the check in fib6_nh_init() to only match explicit reject routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback promotion heuristic in fib6_is_reject() is handled separately by ip6_route_info_create_nh(). After this change, the three cases behave as follows: 1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"): RTF_REJECT is set, enters reject path, skips fib_nh_common_init(). No behavior change. 2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. ip6_route_info_create_nh() still promotes it to reject afterward. nhc_pcpu_rth_output is allocated but unused, which is harmless. 3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. nhc_pcpu_rth_output is properly allocated, fixing the crash when IPv4 routes reference this nexthop.
CVE-2026-23302: In the Linux kernel, the following vulnerability has been resolved: net: annotate data-races around sk->sk_{data_ready,write_space} skmsg (and probably other layers) are changing these pointers while other cpus might read them concurrently. Add corresponding READ_ONCE()/WRITE_ONCE() annotations for UDP, TCP and AF_UNIX.
CVE-2026-23303: In the Linux kernel, the following vulnerability has been resolved: smb: client: Don't log plaintext credentials in cifs_set_cifscreds When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.
CVE-2026-23304: In the Linux kernel, the following vulnerability has been resolved: ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu() l3mdev_master_dev_rcu() can return NULL when the slave device is being un-slaved from a VRF. All other callers deal with this, but we lost the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu() with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address"). KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f] RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418) Call Trace: ip6_pol_route (net/ipv6/route.c:2318) fib6_rule_lookup (net/ipv6/fib6_rules.c:115) ip6_route_output_flags (net/ipv6/route.c:2607) vrf_process_v6_outbound (drivers/net/vrf.c:437) I was tempted to rework the un-slaving code to clear the flag first and insert synchronize_rcu() before we remove the upper. But looks like the explicit fallback to loopback_dev is an established pattern. And I guess avoiding the synchronize_rcu() is nice, too.
CVE-2026-23307: In the Linux kernel, the following vulnerability has been resolved: can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer. When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.
CVE-2026-23312: In the Linux kernel, the following vulnerability has been resolved: net: usb: kaweth: validate USB endpoints The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23315: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob access. [fix check to also cover mgmt->u.action.u.addba_req.capab, correct Fixes tag]
CVE-2026-23318: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Use correct version for UAC3 header validation The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields. The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.
CVE-2026-23330: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: complete pending data exchange on device close In nci_close_device(), complete any pending data exchange before closing. The data exchange callback (e.g. rawsock_data_exchange_complete) holds a socket reference. NIPA occasionally hits this leak: unreferenced object 0xff1100000f435000 (size 2048): comm "nci_dev", pid 3954, jiffies 4295441245 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00 '..@............ backtrace (crc ec2b3c5): __kmalloc_noprof+0x4db/0x730 sk_prot_alloc.isra.0+0xe4/0x1d0 sk_alloc+0x36/0x760 rawsock_create+0xd1/0x540 nfc_sock_create+0x11f/0x280 __sock_create+0x22d/0x630 __sys_socket+0x115/0x1d0 __x64_sys_socket+0x72/0xd0 do_syscall_64+0x117/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53
CVE-2026-23336: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel rfkill_block work in wiphy_unregister() There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller: BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220 Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326 CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: events cfg80211_rfkill_block_work Call Trace: <TASK> dump_stack_lvl+0x116/0x1f0 print_report+0xcd/0x630 kasan_report+0xe0/0x110 cfg80211_shutdown_all_interfaces+0x213/0x220 cfg80211_rfkill_block_work+0x1e/0x30 process_one_work+0x9cf/0x1b70 worker_thread+0x6c8/0xf10 kthread+0x3c5/0x780 ret_from_fork+0x56d/0x700 ret_from_fork_asm+0x1a/0x30 </TASK> The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2026-23339: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: free skb on nci_transceive early error paths nci_transceive() takes ownership of the skb passed by the caller, but the -EPROTO, -EINVAL, and -EBUSY error paths return without freeing it. Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes the nci/nci_dev selftest hits the error path occasionally in NIPA, and kmemleak detects leaks: unreferenced object 0xff11000015ce6a40 (size 640): comm "nci_dev", pid 3954, jiffies 4295441246 hex dump (first 32 bytes): 6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b kkkk.......kkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace (crc 7c40cc2a): kmem_cache_alloc_node_noprof+0x492/0x630 __alloc_skb+0x11e/0x5f0 alloc_skb_with_frags+0xc6/0x8f0 sock_alloc_send_pskb+0x326/0x3f0 nfc_alloc_send_skb+0x94/0x1d0 rawsock_sendmsg+0x162/0x4c0 do_syscall_64+0x117/0xfc0
CVE-2026-23340: In the Linux kernel, the following vulnerability has been resolved: net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs When shrinking the number of real tx queues, netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush qdiscs for queues which will no longer be used. qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with qdisc_lock(). However, for lockless qdiscs, the dequeue path is serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so qdisc_reset() can run concurrently with __qdisc_run() and free skbs while they are still being dequeued, leading to UAF. This can easily be reproduced on e.g. virtio-net by imposing heavy traffic while frequently changing the number of queue pairs: iperf3 -ub0 -c $peer -t 0 & while :; do ethtool -L eth0 combined 1 ethtool -L eth0 combined 2 done With KASAN enabled, this leads to reports like: BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760 ... Call Trace: <TASK> ... __qdisc_run+0x133f/0x1760 __dev_queue_xmit+0x248f/0x3550 ip_finish_output2+0xa42/0x2110 ip_output+0x1a7/0x410 ip_send_skb+0x2e6/0x480 udp_send_skb+0xb0a/0x1590 udp_sendmsg+0x13c9/0x1fc0 ... </TASK> Allocated by task 1270 on cpu 5 at 44.558414s: ... alloc_skb_with_frags+0x84/0x7c0 sock_alloc_send_pskb+0x69a/0x830 __ip_append_data+0x1b86/0x48c0 ip_make_skb+0x1e8/0x2b0 udp_sendmsg+0x13a6/0x1fc0 ... Freed by task 1306 on cpu 3 at 44.558445s: ... kmem_cache_free+0x117/0x5e0 pfifo_fast_reset+0x14d/0x580 qdisc_reset+0x9e/0x5f0 netif_set_real_num_tx_queues+0x303/0x840 virtnet_set_channels+0x1bf/0x260 [virtio_net] ethnl_set_channels+0x684/0xae0 ethnl_default_set_doit+0x31a/0x890 ... Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the serialization model already used by dev_reset_queue(). Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state reflects an empty queue, avoiding needless re-scheduling.
CVE-2026-23351: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: split gc into unlink and reclaim phase Yiming Qian reports Use-after-free in the pipapo set type: Under a large number of expired elements, commit-time GC can run for a very long time in a non-preemptible context, triggering soft lockup warnings and RCU stall reports (local denial of service). We must split GC in an unlink and a reclaim phase. We cannot queue elements for freeing until pointers have been swapped. Expired elements are still exposed to both the packet path and userspace dumpers via the live copy of the data structure. call_rcu() does not protect us: dump operations or element lookups starting after call_rcu has fired can still observe the free'd element, unless the commit phase has made enough progress to swap the clone and live pointers before any new reader has picked up the old version. This a similar approach as done recently for the rbtree backend in commit 35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").
CVE-2026-23352: In the Linux kernel, the following vulnerability has been resolved: x86/efi: defer freeing of boot services memory efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late(). There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area(). More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete. Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM. If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages. Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map. Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency. More robust approach is to only defer freeing of the EFI boot services memory. Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.
CVE-2026-23356: In the Linux kernel, the following vulnerability has been resolved: drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock() Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing. If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error. The rest of the code now assumed that this request has references for the relevant activity log extents. The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case. Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put(). Fix: Do not crash the kernel for a condition that is harmless during normal operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n". And do not try to be smart and "guess" whether something will work, then be surprised when it does not. Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock(). A latter call for the same request will then resume from where we left off.
CVE-2026-23357: In the Linux kernel, the following vulnerability has been resolved: can: mcp251x: fix deadlock in error path of mcp251x_open The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish. This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can: mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path. To solve this issue move the call to free_irq() after the lock is released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ handler will exit right away once it acquired the lock.
CVE-2026-23361: In the Linux kernel, the following vulnerability has been resolved: PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X interrupt to the host using a writel(), which generates a PCI posted write transaction. There's no completion for posted writes, so the writel() may return before the PCI write completes. dw_pcie_ep_raise_msix_irq() also unmaps the outbound ATU entry used for the PCI write, so the write races with the unmap. If the PCI write loses the race with the ATU unmap, the write may corrupt host memory or cause IOMMU errors, e.g., these when running fio with a larger queue depth against nvmet-pci-epf: arm-smmu-v3 fc900000.iommu: 0x0000010000000010 arm-smmu-v3 fc900000.iommu: 0x0000020000000000 arm-smmu-v3 fc900000.iommu: 0x000000090000f040 arm-smmu-v3 fc900000.iommu: 0x0000000000000000 arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0 arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0 Flush the write by performing a readl() of the same address to ensure that the write has reached the destination before the ATU entry is unmapped. The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there it was solved by dedicating an outbound iATU only for MSI. We can't do the same for MSI-X because each vector can have a different msg_addr and the msg_addr may be changed while the vector is masked. [bhelgaas: commit log]
CVE-2026-23362: In the Linux kernel, the following vulnerability has been resolved: can: bcm: fix locking for bcm_op runtime updates Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup(). Usually the RX_SETUP only handles and filters incoming traffic with one exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.
CVE-2026-23365: In the Linux kernel, the following vulnerability has been resolved: net: usb: kalmia: validate USB endpoints The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23367: In the Linux kernel, the following vulnerability has been resolved: wifi: radiotap: reject radiotap with unknown bits The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value. Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.
CVE-2026-23368: In the Linux kernel, the following vulnerability has been resolved: net: phy: register phy led_triggers during probe to avoid AB-BA deadlock There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and LED_TRIGGER_PHY are enabled: [ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock); [ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234 [ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c [ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c [ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0 [ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0 [ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c [ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78 [ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654 <-- Hold lock "rtnl_mutex" by calling rtnl_lock(); [ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0 [ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c [ 1362.104022] [<80014504>] syscall_common+0x34/0x58 Here LED_TRIGGER_PHY is registering LED triggers during phy_attach while holding RTNL and then taking triggers_list_lock. [ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168 <-- Trying to get lock "rtnl_mutex" via rtnl_lock(); [ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4 [ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock); [ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c [ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc [ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c [ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4 [ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c [ 1362.232164] [<80014504>] syscall_common+0x34/0x58 Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes triggers_list_lock and then RTNL. A classical AB-BA deadlock. phy_led_triggers_registers() does not require the RTNL, it does not make any calls into the network stack which require protection. There is also no requirement the PHY has been attached to a MAC, the triggers only make use of phydev state. This allows the call to phy_led_triggers_registers() to be placed elsewhere. PHY probe() and release() don't hold RTNL, so solving the AB-BA deadlock.
CVE-2026-23371: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting Running stress-ng --schedpolicy 0 on an RT kernel on a big machine might lead to the following WARNINGs (edited). sched: DL de-boosted task PID 22725: REPLENISH flag missing WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8 ... (running_bw underflow) Call trace: dequeue_task_dl+0x15c/0x1f8 (P) dequeue_task+0x80/0x168 deactivate_task+0x24/0x50 push_dl_task+0x264/0x2e0 dl_task_timer+0x1b0/0x228 __hrtimer_run_queues+0x188/0x378 hrtimer_interrupt+0xfc/0x260 ... The problem is that when a SCHED_DEADLINE task (lock holder) is changed to a lower priority class via sched_setscheduler(), it may fail to properly inherit the parameters of potential DEADLINE donors if it didn't already inherit them in the past (shorter deadline than donor's at that time). This might lead to bandwidth accounting corruption, as enqueue_task_dl() won't recognize the lock holder as boosted. The scenario occurs when: 1. A DEADLINE task (donor) blocks on a PI mutex held by another DEADLINE task (holder), but the holder doesn't inherit parameters (e.g., it already has a shorter deadline) 2. sched_setscheduler() changes the holder from DEADLINE to a lower class while still holding the mutex 3. The holder should now inherit DEADLINE parameters from the donor and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen Fix the issue by introducing __setscheduler_dl_pi(), which detects when a DEADLINE (proper or boosted) task gets setscheduled to a lower priority class. In case, the function makes the task inherit DEADLINE parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to ensure proper bandwidth accounting during the next enqueue operation.
CVE-2026-23372: In the Linux kernel, the following vulnerability has been resolved: nfc: rawsock: cancel tx_work before socket teardown In rawsock_release(), cancel any pending tx_work and purge the write queue before orphaning the socket. rawsock_tx_work runs on the system workqueue and calls nfc_data_exchange which dereferences the NCI device. Without synchronization, tx_work can race with socket and device teardown when a process is killed (e.g. by SIGKILL), leading to use-after-free or leaked references. Set SEND_SHUTDOWN first so that if tx_work is already running it will see the flag and skip transmitting, then use cancel_work_sync to wait for any in-progress execution to finish, and finally purge any remaining queued skbs.
CVE-2026-23374: In the Linux kernel, the following vulnerability has been resolved: blktrace: fix __this_cpu_read/write in preemptible context tracing_record_cmdline() internally uses __this_cpu_read() and __this_cpu_write() on the per-CPU variable trace_cmdline_save, and trace_save_cmdline() explicitly asserts preemption is disabled via lockdep_assert_preemption_disabled(). These operations are only safe when preemption is off, as they were designed to be called from the scheduler context (probe_wakeup_sched_switch() / probe_wakeup()). __blk_add_trace() was calling tracing_record_cmdline(current) early in the blk_tracer path, before ring buffer reservation, from process context where preemption is fully enabled. This triggers the following using blktests/blktrace/002: blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed] runtime 0.367s ... 0.437s something found in dmesg: [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 ... (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message) [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 [ 81.362895] check_preemption_disabled+0xce/0xe0 [ 81.362902] tracing_record_cmdline+0x10/0x40 [ 81.362923] __blk_add_trace+0x307/0x5d0 [ 81.362934] ? lock_acquire+0xe0/0x300 [ 81.362940] ? iov_iter_extract_pages+0x101/0xa30 [ 81.362959] blk_add_trace_bio+0x106/0x1e0 [ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0 [ 81.362979] ? lockdep_init_map_type+0x58/0x260 [ 81.362988] submit_bio_wait+0x56/0x90 [ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250 [ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10 [ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0 [ 81.363051] blkdev_read_iter+0xc1/0x140 [ 81.363059] vfs_read+0x20b/0x330 [ 81.363083] ksys_read+0x67/0xe0 [ 81.363090] do_syscall_64+0xbf/0xf00 [ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 81.363106] RIP: 0033:0x7f281906029d [ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec [ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d [ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000 [ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000 [ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000 [ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a [ 81.363142] </TASK> The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(), and blk_add_trace_rq() paths as well. The purpose of tracin ---truncated---
CVE-2026-23378: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ife: Fix metalist update behavior Whenever an ife action replace changes the metalist, instead of replacing the old data on the metalist, the current ife code is appending the new metadata. Aside from being innapropriate behavior, this may lead to an unbounded addition of metadata to the metalist which might cause an out of bounds error when running the encode op: [ 138.423369][ C1] ================================================================== [ 138.424317][ C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.424906][ C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255 [ 138.425778][ C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full) [ 138.425795][ C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 138.425800][ C1] Call Trace: [ 138.425804][ C1] <IRQ> [ 138.425808][ C1] dump_stack_lvl (lib/dump_stack.c:122) [ 138.425828][ C1] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 138.425839][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425844][ C1] ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1)) [ 138.425853][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425859][ C1] kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597) [ 138.425868][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425878][ C1] kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1)) [ 138.425884][ C1] __asan_memset (mm/kasan/shadow.c:84 (discriminator 2)) [ 138.425889][ C1] ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425893][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:171) [ 138.425898][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425903][ C1] ife_encode_meta_u16 (net/sched/act_ife.c:57) [ 138.425910][ C1] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114) [ 138.425916][ C1] ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3)) [ 138.425921][ C1] ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45) [ 138.425927][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425931][ C1] tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879) To solve this issue, fix the replace behavior by adding the metalist to the ife rcu data structure.
CVE-2026-23379: In the Linux kernel, the following vulnerability has been resolved: net/sched: ets: fix divide by zero in the offload path Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat: Oops: divide error: 0000 [#1] SMP PTI CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full) Tainted: [E]=UNSIGNED_MODULE Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Call Trace: <TASK> ets_qdisc_change+0x870/0xf40 [sch_ets] qdisc_create+0x12b/0x540 tc_modify_qdisc+0x6d7/0xbd0 rtnetlink_rcv_msg+0x168/0x6b0 netlink_rcv_skb+0x5c/0x110 netlink_unicast+0x1d6/0x2b0 netlink_sendmsg+0x22e/0x470 ____sys_sendmsg+0x38a/0x3c0 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x111/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f440b81c77e Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980 </TASK> Modules linked in: sch_ets(E) netdevsim(E) ---[ end trace 0000000000000000 ]--- RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- Fix this using 64-bit integers for 'q_sum' and 'q_psum'.
CVE-2026-23381: In the Linux kernel, the following vulnerability has been resolved: net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. Then, if neigh_suppress is enabled and an ICMPv6 Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will dereference ipv6_stub->nd_tbl which is NULL, passing it to neigh_lookup(). This causes a kernel NULL pointer dereference. BUG: kernel NULL pointer dereference, address: 0000000000000268 Oops: 0000 [#1] PREEMPT SMP NOPTI [...] RIP: 0010:neigh_lookup+0x16/0xe0 [...] Call Trace: <IRQ> ? neigh_lookup+0x16/0xe0 br_do_suppress_nd+0x160/0x290 [bridge] br_handle_frame_finish+0x500/0x620 [bridge] br_handle_frame+0x353/0x440 [bridge] __netif_receive_skb_core.constprop.0+0x298/0x1110 __netif_receive_skb_one_core+0x3d/0xa0 process_backlog+0xa0/0x140 __napi_poll+0x2c/0x170 net_rx_action+0x2c4/0x3a0 handle_softirqs+0xd0/0x270 do_softirq+0x3f/0x60 Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in the callers. This is in essence disabling NS/NA suppression when IPv6 is disabled.
CVE-2026-23382: In the Linux kernel, the following vulnerability has been resolved: HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system. Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.
CVE-2026-23388: In the Linux kernel, the following vulnerability has been resolved: Squashfs: check metadata block offset is within range Syzkaller reports a "general protection fault in squashfs_copy_data" This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset. This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access. The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.
CVE-2026-23389: In the Linux kernel, the following vulnerability has been resolved: ice: Fix memory leak in ice_set_ringparam() In ice_set_ringparam, tx_rings and xdp_rings are allocated before rx_rings. If the allocation of rx_rings fails, the code jumps to the done label leaking both tx_rings and xdp_rings. Furthermore, if the setup of an individual Rx ring fails during the loop, the code jumps to the free_tx label which releases tx_rings but leaks xdp_rings. Fix this by introducing a free_xdp label and updating the error paths to ensure both xdp_rings and tx_rings are properly freed if rx_rings allocation or setup fails. Compile tested only. Issue found using a prototype static analysis tool and code review.
CVE-2026-23391: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_CT: drop pending enqueued packets on template removal Templates refer to objects that can go away while packets are sitting in nfqueue refer to: - helper, this can be an issue on module removal. - timeout policy, nfnetlink_cttimeout might remove it. The use of templates with zone and event cache filter are safe, since this just copies values. Flush these enqueued packets in case the template rule gets removed.
CVE-2026-23392: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: release flowtable after rcu grace period on error Call synchronize_rcu() after unregistering the hooks from error path, since a hook that already refers to this flowtable can be already registered, exposing this flowtable to packet path and nfnetlink_hook control plane. This error path is rare, it should only happen by reaching the maximum number hooks or by failing to set up to hardware offload, just call synchronize_rcu(). There is a check for already used device hooks by different flowtable that could result in EEXIST at this late stage. The hook parser can be updated to perform this check earlier to this error path really becomes rarely exercised. Uncovered by KASAN reported as use-after-free from nfnetlink_hook path when dumping hooks.
CVE-2026-23395: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ Currently the code attempts to accept requests regardless of the command identifier which may cause multiple requests to be marked as pending (FLAG_DEFER_SETUP) which can cause more than L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer causing an overflow. The spec is quite clear that the same identifier shall not be used on subsequent requests: 'Within each signaling channel a different Identifier shall be used for each successive request or indication.' https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-adaptation-protocol-specification.html#UUID-32a25a06-4aa4-c6c7-77c5-dcfe3682355d So this attempts to check if there are any channels pending with the same identifier and rejects if any are found.
CVE-2026-23396: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL deref in mesh_matches_local() mesh_matches_local() unconditionally dereferences ie->mesh_config to compare mesh configuration parameters. When called from mesh_rx_csa_frame(), the parsed action-frame elements may not contain a Mesh Configuration IE, leaving ie->mesh_config NULL and triggering a kernel NULL pointer dereference. The other two callers are already safe: - ieee80211_mesh_rx_bcn_presp() checks !elems->mesh_config before calling mesh_matches_local() - mesh_plink_get_event() is only reached through mesh_process_plink_frame(), which checks !elems->mesh_config, too mesh_rx_csa_frame() is the only caller that passes raw parsed elements to mesh_matches_local() without guarding mesh_config. An adjacent attacker can exploit this by sending a crafted CSA action frame that includes a valid Mesh ID IE but omits the Mesh Configuration IE, crashing the kernel. The captured crash log: Oops: general protection fault, probably for non-canonical address ... KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Workqueue: events_unbound cfg80211_wiphy_work [...] Call Trace: <TASK> ? __pfx_mesh_matches_local (net/mac80211/mesh.c:65) ieee80211_mesh_rx_queued_mgmt (net/mac80211/mesh.c:1686) [...] ieee80211_iface_work (net/mac80211/iface.c:1754 net/mac80211/iface.c:1802) [...] cfg80211_wiphy_work (net/wireless/core.c:426) process_one_work (net/kernel/workqueue.c:3280) ? assign_work (net/kernel/workqueue.c:1219) worker_thread (net/kernel/workqueue.c:3352) ? __pfx_worker_thread (net/kernel/workqueue.c:3385) kthread (net/kernel/kthread.c:436) [...] ret_from_fork_asm (net/arch/x86/entry/entry_64.S:255) </TASK> This patch adds a NULL check for ie->mesh_config at the top of mesh_matches_local() to return false early when the Mesh Configuration IE is absent.
CVE-2026-23397: In the Linux kernel, the following vulnerability has been resolved: nfnetlink_osf: validate individual option lengths in fingerprints nfnl_osf_add_callback() validates opt_num bounds and string NUL-termination but does not check individual option length fields. A zero-length option causes nf_osf_match_one() to enter the option matching loop even when foptsize sums to zero, which matches packets with no TCP options where ctx->optp is NULL: Oops: general protection fault KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:227) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:293) nf_hook_slow (net/netfilter/core.c:623) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) Additionally, an MSS option (kind=2) with length < 4 causes out-of-bounds reads when nf_osf_match_one() unconditionally accesses optp[2] and optp[3] for MSS value extraction. While RFC 9293 section 3.2 specifies that the MSS option is always exactly 4 bytes (Kind=2, Length=4), the check uses "< 4" rather than "!= 4" because lengths greater than 4 do not cause memory safety issues -- the buffer is guaranteed to be at least foptsize bytes by the ctx->optsize == foptsize check. Reject fingerprints where any option has zero length, or where an MSS option has length less than 4, at add time rather than trusting these values in the packet matching hot path.
CVE-2026-23398: In the Linux kernel, the following vulnerability has been resolved: icmp: fix NULL pointer dereference in icmp_tag_validation() icmp_tag_validation() unconditionally dereferences the result of rcu_dereference(inet_protos[proto]) without checking for NULL. The inet_protos[] array is sparse -- only about 15 of 256 protocol numbers have registered handlers. When ip_no_pmtu_disc is set to 3 (hardened PMTU mode) and the kernel receives an ICMP Fragmentation Needed error with a quoted inner IP header containing an unregistered protocol number, the NULL dereference causes a kernel panic in softirq context. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:icmp_unreach (net/ipv4/icmp.c:1085 net/ipv4/icmp.c:1143) Call Trace: <IRQ> icmp_rcv (net/ipv4/icmp.c:1527) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207) ip_local_deliver_finish (net/ipv4/ip_input.c:242) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) __netif_receive_skb_one_core (net/core/dev.c:6164) process_backlog (net/core/dev.c:6628) handle_softirqs (kernel/softirq.c:561) </IRQ> Add a NULL check before accessing icmp_strict_tag_validation. If the protocol has no registered handler, return false since it cannot perform strict tag validation.
CVE-2026-23420: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Fix a locking bug Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.
CVE-2026-23434: In the Linux kernel, the following vulnerability has been resolved: mtd: rawnand: serialize lock/unlock against other NAND operations nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area without holding the NAND device lock. On controllers that implement SET_FEATURES via multiple low-level PIO commands, these can race with concurrent UBI/UBIFS background erase/write operations that hold the device lock, resulting in cmd_pending conflicts on the NAND controller. Add nand_get_device()/nand_release_device() around the lock/unlock operations to serialize them against all other NAND controller access.
CVE-2026-23439: In the Linux kernel, the following vulnerability has been resolved: udp_tunnel: fix NULL deref caused by udp_sock_create6 when CONFIG_IPV6=n When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0 (success) without actually creating a socket. Callers such as fou_create() then proceed to dereference the uninitialized socket pointer, resulting in a NULL pointer dereference. The captured NULL deref crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764) [...] Call Trace: <TASK> genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209) [...] netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sock_sendmsg (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1)) __sys_sendto (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:2183 (discriminator 1)) __x64_sys_sendto (net/socket.c:2213 (discriminator 1) net/socket.c:2209 (discriminator 1) net/socket.c:2209 (discriminator 1)) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (net/arch/x86/entry/entry_64.S:130) This patch makes udp_sock_create6 return -EPFNOSUPPORT instead, so callers correctly take their error paths. There is only one caller of the vulnerable function and only privileged users can trigger it.
CVE-2026-23442: In the Linux kernel, the following vulnerability has been resolved: ipv6: add NULL checks for idev in SRv6 paths __in6_dev_get() can return NULL when the device has no IPv6 configuration (e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER). Add NULL checks for idev returned by __in6_dev_get() in both seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL pointer dereferences.
CVE-2026-23444: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure ieee80211_tx_prepare_skb() has three error paths, but only two of them free the skb. The first error path (ieee80211_tx_prepare() returning TX_DROP) does not free it, while invoke_tx_handlers() failure and the fragmentation check both do. Add kfree_skb() to the first error path so all three are consistent, and remove the now-redundant frees in callers (ath9k, mt76, mac80211_hwsim) to avoid double-free. Document the skb ownership guarantee in the function's kdoc.
CVE-2026-23446: In the Linux kernel, the following vulnerability has been resolved: net: usb: aqc111: Do not perform PM inside suspend callback syzbot reports "task hung in rpm_resume" This is caused by aqc111_suspend calling the PM variant of its write_cmd routine. The simplified call trace looks like this: rpm_suspend() usb_suspend_both() - here udev->dev.power.runtime_status == RPM_SUSPENDING aqc111_suspend() - called for the usb device interface aqc111_write32_cmd() usb_autopm_get_interface() pm_runtime_resume_and_get() rpm_resume() - here we call rpm_resume() on our parent rpm_resume() - Here we wait for a status change that will never happen. At this point we block another task which holds rtnl_lock and locks up the whole networking stack. Fix this by replacing the write_cmd calls with their _nopm variants
CVE-2026-23447: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check The same bounds-check bug fixed for NDP16 in the previous patch also exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated against the total skb length without accounting for ndpoffset, allowing out-of-bounds reads when the NDP32 is placed near the end of the NTB. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly. Compile-tested only.
CVE-2026-23448: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE entries fit within the skb. The first check correctly accounts for ndpoffset: if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len) but the second check omits it: if ((sizeof(struct usb_cdc_ncm_ndp16) + ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len) This validates the DPE array size against the total skb length as if the NDP were at offset 0, rather than at ndpoffset. When the NDP is placed near the end of the NTB (large wNdpIndex), the DPE entries can extend past the skb data buffer even though the check passes. cdc_ncm_rx_fixup() then reads out-of-bounds memory when iterating the DPE array. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly.
CVE-2026-23449: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: Fix double-free in teql_master_xmit Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should be called using the seq_lock to avoid racing with the datapath. Failure to do so may cause crashes like the following: [ 238.028993][ T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139) [ 238.029328][ T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318 [ 238.029749][ T318] [ 238.029900][ T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full) [ 238.029906][ T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 238.029910][ T318] Call Trace: [ 238.029913][ T318] <TASK> [ 238.029916][ T318] dump_stack_lvl (lib/dump_stack.c:122) [ 238.029928][ T318] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 238.029940][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029944][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.029957][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029969][ T318] kasan_report_invalid_free (mm/kasan/report.c:221 mm/kasan/report.c:563) [ 238.029979][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029989][ T318] check_slab_allocation (mm/kasan/common.c:231) [ 238.029995][ T318] kmem_cache_free (mm/slub.c:2637 (discriminator 1) mm/slub.c:6168 (discriminator 1) mm/slub.c:6298 (discriminator 1)) [ 238.030004][ T318] skb_release_data (net/core/skbuff.c:1139) ... [ 238.030025][ T318] sk_skb_reason_drop (net/core/skbuff.c:1256) [ 238.030032][ T318] pfifo_fast_reset (./include/linux/ptr_ring.h:171 ./include/linux/ptr_ring.h:309 ./include/linux/skb_array.h:98 net/sched/sch_generic.c:827) [ 238.030039][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.030054][ T318] qdisc_reset (net/sched/sch_generic.c:1034) [ 238.030062][ T318] teql_destroy (./include/linux/spinlock.h:395 net/sched/sch_teql.c:157) [ 238.030071][ T318] __qdisc_destroy (./include/net/pkt_sched.h:328 net/sched/sch_generic.c:1077) [ 238.030077][ T318] qdisc_graft (net/sched/sch_api.c:1062 net/sched/sch_api.c:1053 net/sched/sch_api.c:1159) [ 238.030089][ T318] ? __pfx_qdisc_graft (net/sched/sch_api.c:1091) [ 238.030095][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030102][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030106][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030114][ T318] tc_get_qdisc (net/sched/sch_api.c:1529 net/sched/sch_api.c:1556) ... [ 238.072958][ T318] Allocated by task 303 on cpu 5 at 238.026275s: [ 238.073392][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.073884][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.074230][ T318] __kasan_slab_alloc (mm/kasan/common.c:369) [ 238.074578][ T318] kmem_cache_alloc_node_noprof (./include/linux/kasan.h:253 mm/slub.c:4542 mm/slub.c:4869 mm/slub.c:4921) [ 238.076091][ T318] kmalloc_reserve (net/core/skbuff.c:616 (discriminator 107)) [ 238.076450][ T318] __alloc_skb (net/core/skbuff.c:713) [ 238.076834][ T318] alloc_skb_with_frags (./include/linux/skbuff.h:1383 net/core/skbuff.c:6763) [ 238.077178][ T318] sock_alloc_send_pskb (net/core/sock.c:2997) [ 238.077520][ T318] packet_sendmsg (net/packet/af_packet.c:2926 net/packet/af_packet.c:3019 net/packet/af_packet.c:3108) [ 238.081469][ T318] [ 238.081870][ T318] Freed by task 299 on cpu 1 at 238.028496s: [ 238.082761][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.083481][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.085348][ T318] kasan_save_free_info (mm/kasan/generic.c:587 (discriminator 1)) [ 238.085900][ T318] __kasan_slab_free (mm/ ---truncated---
CVE-2026-23452: In the Linux kernel, the following vulnerability has been resolved: PM: runtime: Fix a race condition related to device removal The following code in pm_runtime_work() may dereference the dev->parent pointer after the parent device has been freed: /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } Fix this by inserting a flush_work() call in pm_runtime_remove(). Without this patch blktest block/001 triggers the following complaint sporadically: BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160 Read of size 1 at addr ffff88812bef7198 by task kworker/u553:1/3081 Workqueue: pm pm_runtime_work Call Trace: <TASK> dump_stack_lvl+0x61/0x80 print_address_description.constprop.0+0x8b/0x310 print_report+0xfd/0x1d7 kasan_report+0xd8/0x1d0 __kasan_check_byte+0x42/0x60 lock_acquire.part.0+0x38/0x230 lock_acquire+0x70/0x160 _raw_spin_lock+0x36/0x50 rpm_suspend+0xc6a/0xfe0 rpm_idle+0x578/0x770 pm_runtime_work+0xee/0x120 process_one_work+0xde3/0x1410 worker_thread+0x5eb/0xfe0 kthread+0x37b/0x480 ret_from_fork+0x6cb/0x920 ret_from_fork_asm+0x11/0x20 </TASK> Allocated by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_alloc_info+0x3d/0x50 __kasan_kmalloc+0xa0/0xb0 __kmalloc_noprof+0x311/0x990 scsi_alloc_target+0x122/0xb60 [scsi_mod] __scsi_scan_target+0x101/0x460 [scsi_mod] scsi_scan_channel+0x179/0x1c0 [scsi_mod] scsi_scan_host_selected+0x259/0x2d0 [scsi_mod] store_scan+0x2d2/0x390 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810 do_syscall_64+0xee/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Freed by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_free_info+0x3f/0x50 __kasan_slab_free+0x67/0x80 kfree+0x225/0x6c0 scsi_target_dev_release+0x3d/0x60 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_dev_release+0xacf/0x12c0 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_put+0x7f/0xc0 [scsi_mod] sdev_store_delete+0xa5/0x120 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810
CVE-2026-23455: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement.
CVE-2026-23456: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint().
CVE-2026-23457: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length.
CVE-2026-23458: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0
CVE-2026-23460: In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516
CVE-2026-23462: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated---
CVE-2026-23463: In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between fq_table[fq->idx] state and freeing/allocating from the pool and WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered. Indeed, we can have: Thread A Thread B qman_destroy_fq() qman_create_fq() qman_release_fqid() qman_shutdown_fq() gen_pool_free() -- At this point, the fqid is available again -- qman_alloc_fqid() -- so, we can get the just-freed fqid in thread B -- fq->fqid = fqid; fq->idx = fqid * 2; WARN_ON(fq_table[fq->idx]); fq_table[fq->idx] = fq; fq_table[fq->idx] = NULL; And adding some logs between qman_release_fqid() and fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more. To prevent that, ensure that fq_table[fq->idx] is set to NULL before gen_pool_free() is called by using smp_wmb().
CVE-2026-23465: In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . <power failure> # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon.
CVE-2026-23468: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion Userspace can pass an arbitrary number of BO list entries via the bo_number field. Although the previous multiplication overflow check prevents out-of-bounds allocation, a large number of entries could still cause excessive memory allocation (up to potentially gigabytes) and unnecessarily long list processing times. Introduce a hard limit of 128k entries per BO list, which is more than sufficient for any realistic use case (e.g., a single list containing all buffers in a large scene). This prevents memory exhaustion attacks and ensures predictable performance. Return -EINVAL if the requested entry count exceeds the limit (cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332)
CVE-2026-23472: In the Linux kernel, the following vulnerability has been resolved: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN uart_write_room() and uart_write() behave inconsistently when xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were never properly initialized): - uart_write_room() returns kfifo_avail() which can be > 0 - uart_write() checks xmit_buf and returns 0 if NULL This inconsistency causes an infinite loop in drivers that rely on tty_write_room() to determine if they can write: while (tty_write_room(tty) > 0) { written = tty->ops->write(...); // written is always 0, loop never exits } For example, caif_serial's handle_tx() enters an infinite loop when used with PORT_UNKNOWN serial ports, causing system hangs. Fix by making uart_write_room() also check xmit_buf and return 0 if it's NULL, consistent with uart_write(). Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13
CVE-2026-23474: In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds.
CVE-2026-31391: In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tfm_count to avoid blocking future reads.
CVE-2026-31392: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5 mounts were failing against a single server as the client was trying to mount the shares with wrong credentials. It turned out the client was reusing SMB session from first mount to try mounting the other shares, even though a different username= option had been specified to the other mounts. By using username mount option along with sec=krb5 to search for principals from keytab is supported by cifs.upcall(8) since cifs-utils-4.8. So fix this by matching username mount option in match_session() even with Kerberos. For example, the second mount below should fail with -ENOKEY as there is no 'foobar' principal in keytab (/etc/krb5.keytab). The client ends up reusing SMB session from first mount to perform the second one, which is wrong. ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ---------------------------------------------------------------- 1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96) $ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser $ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar $ mount -t cifs | grep -Po 'username=\K\w+' testuser testuser ```
CVE-2026-31393: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled.
CVE-2026-31396: In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every opening of the interface and destroyed on every closing. However it may be accessed via get_ts_info ethtool call which is possible while the interface is just present in the kernel. BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 Read of size 4 at addr ffff8880194345cc by task syz.0.6/948 CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106 print_address_description mm/kasan/report.c:316 [inline] print_report+0x17f/0x496 mm/kasan/report.c:420 kasan_report+0xd9/0x180 mm/kasan/report.c:524 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558 ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline] __dev_ethtool net/ethtool/ioctl.c:3017 [inline] dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215 sock_ioctl+0x577/0x6d0 net/socket.c:1320 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 </TASK> Allocated by task 457: kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:699 [inline] ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920 __dev_open+0x2ce/0x500 net/core/dev.c:1501 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651 dev_change_flags+0x92/0x170 net/core/dev.c:8722 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x14b/0x180 net/socket.c:730 __sys_sendto+0x320/0x3b0 net/socket.c:2152 __do_sys_sendto net/socket.c:2164 [inline] __se_sys_sendto net/socket.c:2160 [inline] __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 938: kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1729 [inline] slab_free_freelist_hook mm/slub.c:1755 [inline] slab_free mm/slub.c:3687 [inline] __kmem_cache_free+0xbc/0x320 mm/slub.c:3700 device_release+0xa0/0x240 drivers/base/core.c:2507 kobject_cleanup lib/kobject.c:681 [inline] kobject_release lib/kobject.c:712 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1cd/0x350 lib/kobject.c:729 put_device+0x1b/0x30 drivers/base/core.c:3805 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585 __dev_close net/core/dev.c:1597 [inline] __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649 dev_change_fl ---truncated---
CVE-2026-31399: In the Linux kernel, the following vulnerability has been resolved: nvdimm/bus: Fix potential use after free in asynchronous initialization Dingisoul with KASAN reports a use after free if device_add() fails in nd_async_device_register(). Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while scheduling async init") correctly added a reference on the parent device to be held until asynchronous initialization was complete. However, if device_add() results in an allocation failure the ref count of the device drops to 0 prior to the parent pointer being accessed. Thus resulting in use after free. The bug bot AI correctly identified the fix. Save a reference to the parent pointer to be used to drop the parent reference regardless of the outcome of device_add().
CVE-2026-31400: In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed while in the middle of reading a cache_request (rp->offset != 0), cache_release() decrements the request's readers count but never checks whether it should free the request. In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the cache_request is removed from the queue and freed along with its buffer and cache_head reference. cache_release() lacks this cleanup. The only other path that frees requests with readers == 0 is cache_dequeue(), but it runs only when CACHE_PENDING transitions from set to clear. If that transition already happened while readers was still non-zero, cache_dequeue() will have skipped the request, and no subsequent call will clean it up. Add the same cleanup logic from cache_read() to cache_release(): after decrementing readers, check if it reached 0 with CACHE_PENDING clear, and if so, dequeue and free the cache_request.
CVE-2026-31402: In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request.
CVE-2026-31403: In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/exports proc entry is created at module init and persists for the module's lifetime. exports_proc_open() captures the caller's current network namespace and stores its svc_export_cache in seq->private, but takes no reference on the namespace. If the namespace is subsequently torn down (e.g. container destruction after the opener does setns() to a different namespace), nfsd_net_exit() calls nfsd_export_shutdown() which frees the cache. Subsequent reads on the still-open fd dereference the freed cache_detail, walking a freed hash table. Hold a reference on the struct net for the lifetime of the open file descriptor. This prevents nfsd_net_exit() from running -- and thus prevents nfsd_export_shutdown() from freeing the cache -- while any exports fd is open. cache_detail already stores its net pointer (cd->net, set by cache_create_net()), so exports_release() can retrieve it without additional per-file storage.
CVE-2026-31405: In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded.
CVE-2026-31407: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.
CVE-2026-31408: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.
CVE-2026-31411: In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock as its first member, they share the same lifetime. Therefore using sock_hold/sock_put is sufficient to keep the vcc alive while it is being used. Note that there may be a race with sigd_close() which could mark the vcc with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns. However, sock_hold() guarantees the memory remains valid, so this race only affects the logical state, not memory safety. [1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3
CVE-2026-31412: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows.
CVE-2026-31414: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /proc to dump the helper name. Using nfct_help() without holding a reference to the master conntrack is unsafe. Use exp->master->helper in ctnetlink path if userspace does not provide an explicit helper when creating an expectation to retain the existing behaviour. The ctnetlink expectation path holds the reference on the master conntrack and nf_conntrack_expect lock and the nfnetlink glue path refers to the master ct that is attached to the skb.
CVE-2026-31415: In the Linux kernel, the following vulnerability has been resolved: ipv6: avoid overflows in ip6_datagram_send_ctl() Yiming Qian reported : <quote> I believe I found a locally triggerable kernel bug in the IPv6 sendmsg ancillary-data path that can panic the kernel via `skb_under_panic()` (local DoS). The core issue is a mismatch between: - a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type `__u16`) and - a pointer to the *last* provided destination-options header (`opt->dst1opt`) when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided. - `include/net/ipv6.h`: - `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible). (lines 291-307, especially 298) - `net/ipv6/datagram.c:ip6_datagram_send_ctl()`: - Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen` without rejecting duplicates. (lines 909-933) - `net/ipv6/ip6_output.c:__ip6_append_data()`: - Uses `opt->opt_flen + opt->opt_nflen` to compute header sizes/headroom decisions. (lines 1448-1466, especially 1463-1465) - `net/ipv6/ip6_output.c:__ip6_make_skb()`: - Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero. (lines 1930-1934) - `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`: - Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the pointed-to header). (lines 1179-1185 and 1206-1211) 1. `opt_flen` is a 16-bit accumulator: - `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr */`. 2. `ip6_datagram_send_ctl()` accepts *repeated* `IPV6_DSTOPTS` cmsgs and increments `opt_flen` each time: - In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`: - It computes `len = ((hdr->hdrlen + 1) << 3);` - It checks `CAP_NET_RAW` using `ns_capable(net->user_ns, CAP_NET_RAW)`. (line 922) - Then it does: - `opt->opt_flen += len;` (line 927) - `opt->dst1opt = hdr;` (line 928) There is no duplicate rejection here (unlike the legacy `IPV6_2292DSTOPTS` path which rejects duplicates at `net/ipv6/datagram.c:901-904`). If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps while `dst1opt` still points to a large (2048-byte) destination-options header. In the attached PoC (`poc.c`): - 32 cmsgs with `hdrlen=255` => `len = (255+1)*8 = 2048` - 1 cmsg with `hdrlen=0` => `len = 8` - Total increment: `32*2048 + 8 = 65544`, so `(__u16)opt_flen == 8` - The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header. 3. The transmit path sizes headers using the wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1463-1465`: - `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + ...;` With wrapped `opt_flen`, `headersize`/headroom decisions underestimate what will be pushed later. 4. When building the final skb, the actual push length comes from `dst1opt` and is not limited by wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1930-1934`: - `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);` - In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes `dst1opt` via `ipv6_push_exthdr()`. - In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does: - `skb_push(skb, ipv6_optlen(opt));` - `memcpy(h, opt, ipv6_optlen(opt));` With insufficient headroom, `skb_push()` underflows and triggers `skb_under_panic()` -> `BUG()`: - `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`) - `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`) - The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`). - Root (or any task with `CAP_NET_RAW`) can trigger this without user namespaces. - An unprivileged `uid=1000` user can trigger this if unprivileged user namespaces are enabled and it can create a userns+netns to obtain namespaced `CAP_NET_RAW` (the attached PoC does this). - Local denial of service: kernel BUG/panic (system crash). - ---truncated---
CVE-2026-31416: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: account for netlink header size This is a followup to an old bug fix: NLMSG_DONE needs to account for the netlink header size, not just the attribute size. This can result in a WARN splat + drop of the netlink message, but other than this there are no ill effects.
CVE-2026-31417: In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`.
CVE-2026-31418: In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: drop logically empty buckets in mtype_del mtype_del() counts empty slots below n->pos in k, but it only drops the bucket when both n->pos and k are zero. This misses buckets whose live entries have all been removed while n->pos still points past deleted slots. Treat a bucket as empty when all positions below n->pos are unused and release it directly instead of shrinking it further.
CVE-2026-31419: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================
CVE-2026-31420: In the Linux kernel, the following vulnerability has been resolved: bridge: mrp: reject zero test interval to avoid OOM panic br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied interval value from netlink without validation. When interval is 0, usecs_to_jiffies(0) yields 0, causing the delayed work (br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule itself with zero delay. This creates a tight loop on system_percpu_wq that allocates and transmits MRP test frames at maximum rate, exhausting all system memory and causing a kernel panic via OOM deadlock. The same zero-interval issue applies to br_mrp_start_in_test_parse() for interconnect test frames. Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both IFLA_BRIDGE_MRP_START_TEST_INTERVAL and IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the netlink attribute parsing layer before the value ever reaches the workqueue scheduling code. This is consistent with how other bridge subsystems (br_fdb, br_mst) enforce range constraints on netlink attributes.
CVE-2026-31421: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_fw: fix NULL pointer dereference on shared blocks The old-method path in fw_classify() calls tcf_block_q() and dereferences q->handle. Shared blocks leave block->q NULL, causing a NULL deref when an empty cls_fw filter is attached to a shared block and a packet with a nonzero major skb mark is classified. Reject the configuration in fw_change() when the old method (no TCA_OPTIONS) is used on a shared block, since fw_classify()'s old-method path needs block->q which is NULL for shared blocks. The fixed null-ptr-deref calling stack: KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:fw_classify (net/sched/cls_fw.c:81) Call Trace: tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860) tc_run (net/core/dev.c:4401) __dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790)
CVE-2026-31422: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_flow: fix NULL pointer dereference on shared blocks flow_change() calls tcf_block_q() and dereferences q->handle to derive a default baseclass. Shared blocks leave block->q NULL, causing a NULL deref when a flow filter without a fully qualified baseclass is created on a shared block. Check tcf_block_shared() before accessing block->q and return -EINVAL for shared blocks. This avoids the null-deref shown below: ======================================================================= KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:flow_change (net/sched/cls_flow.c:508) Call Trace: tc_new_tfilter (net/sched/cls_api.c:2432) rtnetlink_rcv_msg (net/core/rtnetlink.c:6980) [...] =======================================================================
CVE-2026-31423: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_hfsc: fix divide-by-zero in rtsc_min() m2sm() converts a u32 slope to a u64 scaled value. For large inputs (e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores the difference of two such u64 values in a u32 variable `dsm` and uses it as a divisor. When the difference is exactly 2^32 the truncation yields zero, causing a divide-by-zero oops in the concave-curve intersection path: Oops: divide error: 0000 RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601) Call Trace: init_ed (net/sched/sch_hfsc.c:629) hfsc_enqueue (net/sched/sch_hfsc.c:1569) [...] Widen `dsm` to u64 and replace do_div() with div64_u64() so the full difference is preserved.
CVE-2026-31424: In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: restrict xt_check_match/xt_check_target extensions for NFPROTO_ARP Weiming Shi says: xt_match and xt_target structs registered with NFPROTO_UNSPEC can be loaded by any protocol family through nft_compat. When such a match/target sets .hooks to restrict which hooks it may run on, the bitmask uses NF_INET_* constants. This is only correct for families whose hook layout matches NF_INET_*: IPv4, IPv6, INET, and bridge all share the same five hooks (PRE_ROUTING ... POST_ROUTING). ARP only has three hooks (IN=0, OUT=1, FORWARD=2) with different semantics. Because NF_ARP_OUT == 1 == NF_INET_LOCAL_IN, the .hooks validation silently passes for the wrong reasons, allowing matches to run on ARP chains where the hook assumptions (e.g. state->in being set on input hooks) do not hold. This leads to NULL pointer dereferences; xt_devgroup is one concrete example: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000044: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000220-0x0000000000000227] RIP: 0010:devgroup_mt+0xff/0x350 Call Trace: <TASK> nft_match_eval (net/netfilter/nft_compat.c:407) nft_do_chain (net/netfilter/nf_tables_core.c:285) nft_do_chain_arp (net/netfilter/nft_chain_filter.c:61) nf_hook_slow (net/netfilter/core.c:623) arp_xmit (net/ipv4/arp.c:666) </TASK> Kernel panic - not syncing: Fatal exception in interrupt Fix it by restricting arptables to NFPROTO_ARP extensions only. Note that arptables-legacy only supports: - arpt_CLASSIFY - arpt_mangle - arpt_MARK that provide explicit NFPROTO_ARP match/target declarations.
CVE-2026-31425: In the Linux kernel, the following vulnerability has been resolved: rds: ib: reject FRMR registration before IB connection is established rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with i_cm_id = NULL because the connection worker has not yet called rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses the control message before any connection establishment, allowing rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the kernel. The existing guard in rds_ib_reg_frmr() only checks for !ic (added in commit 9e630bcb7701), which does not catch this case since ic is allocated early and is always non-NULL once the connection object exists. KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920 Call Trace: rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167) rds_ib_map_frmr (net/rds/ib_frmr.c:252) rds_ib_reg_frmr (net/rds/ib_frmr.c:430) rds_ib_get_mr (net/rds/ib_rdma.c:615) __rds_rdma_map (net/rds/rdma.c:295) rds_cmsg_rdma_map (net/rds/rdma.c:860) rds_sendmsg (net/rds/send.c:1363) ____sys_sendmsg do_syscall_64 Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all non-NULL before proceeding with FRMR registration, mirroring the guard already present in rds_ib_post_inv(). Return -ENODEV when the connection is not ready, which the existing error handling in rds_cmsg_send() converts to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to start the connection worker.
CVE-2026-31426: In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: <TASK> mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) </TASK> Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC
CVE-2026-31427: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp process_sdp() declares union nf_inet_addr rtp_addr on the stack and passes it to the nf_nat_sip sdp_session hook after walking the SDP media descriptions. However rtp_addr is only initialized inside the media loop when a recognized media type with a non-zero port is found. If the SDP body contains no m= lines, only inactive media sections (m=audio 0 ...) or only unrecognized media types, rtp_addr is never assigned. Despite that, the function still calls hooks->sdp_session() with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack value as an IP address and rewrite the SDP session owner and connection lines with it. With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this results in the session-level o= and c= addresses being rewritten to 0.0.0.0 for inactive SDP sessions. Without stack auto-init the rewritten address is whatever happened to be on the stack. Fix this by pre-initializing rtp_addr from the session-level connection address (caddr) when available, and tracking via a have_rtp_addr flag whether any valid address was established. Skip the sdp_session hook entirely when no valid address exists.
CVE-2026-31428: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD __build_packet_message() manually constructs the NFULA_PAYLOAD netlink attribute using skb_put() and skb_copy_bits(), bypassing the standard nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes are allocated (including NLA alignment padding), only data_len bytes of actual packet data are copied. The trailing nla_padlen(data_len) bytes (1-3 when data_len is not 4-byte aligned) are never initialized, leaking stale heap contents to userspace via the NFLOG netlink socket. Replace the manual attribute construction with nla_reserve(), which handles the tailroom check, header setup, and padding zeroing via __nla_reserve(). The subsequent skb_copy_bits() fills in the payload data on top of the properly initialized attribute.
CVE-2026-31431: In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.
CVE-2026-31441: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix memory leak when a wq is reset idxd_wq_disable_cleanup() which is called from the reset path for a workqueue, sets the wq type to NONE, which for other parts of the driver mean that the wq is empty (all its resources were released). Only set the wq type to NONE after its resources are released.
CVE-2026-31446: In the Linux kernel, the following vulnerability has been resolved: ext4: fix use-after-free in update_super_work when racing with umount Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups reads during unmount. However, this introduced a use-after-free because update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which accesses the kobject's kernfs_node after it has been freed by kobject_del() in ext4_unregister_sysfs(): update_super_work ext4_put_super ----------------- -------------- ext4_unregister_sysfs(sb) kobject_del(&sbi->s_kobj) __kobject_del() sysfs_remove_dir() kobj->sd = NULL sysfs_put(sd) kernfs_put() // RCU free ext4_notify_error_sysfs(sbi) sysfs_notify(&sbi->s_kobj) kn = kobj->sd // stale pointer kernfs_get(kn) // UAF on freed kernfs_node ext4_journal_destroy() flush_work(&sbi->s_sb_upd_work) Instead of reordering the teardown sequence, fix this by making ext4_notify_error_sysfs() detect that sysfs has already been torn down by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call in that case. A dedicated mutex (s_error_notify_mutex) serializes ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs() to prevent TOCTOU races where the kobject could be deleted between the state_in_sysfs check and the sysfs_notify() call.
CVE-2026-31447: In the Linux kernel, the following vulnerability has been resolved: ext4: reject mount if bigalloc with s_first_data_block != 0 bigalloc with s_first_data_block != 0 is not supported, reject mounting it.
CVE-2026-31448: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid infinite loops caused by residual data On the mkdir/mknod path, when mapping logical blocks to physical blocks, if inserting a new extent into the extent tree fails (in this example, because the file system disabled the huge file feature when marking the inode as dirty), ext4_ext_map_blocks() only calls ext4_free_blocks() to reclaim the physical block without deleting the corresponding data in the extent tree. This causes subsequent mkdir operations to reference the previously reclaimed physical block number again, even though this physical block is already being used by the xattr block. Therefore, a situation arises where both the directory and xattr are using the same buffer head block in memory simultaneously. The above causes ext4_xattr_block_set() to enter an infinite loop about "inserted" and cannot release the inode lock, ultimately leading to the 143s blocking problem mentioned in [1]. If the metadata is corrupted, then trying to remove some extent space can do even more harm. Also in case EXT4_GET_BLOCKS_DELALLOC_RESERVE was passed, remove space wrongly update quota information. Jan Kara suggests distinguishing between two cases: 1) The error is ENOSPC or EDQUOT - in this case the filesystem is fully consistent and we must maintain its consistency including all the accounting. However these errors can happen only early before we've inserted the extent into the extent tree. So current code works correctly for this case. 2) Some other error - this means metadata is corrupted. We should strive to do as few modifications as possible to limit damage. So I'd just skip freeing of allocated blocks. [1] INFO: task syz.0.17:5995 blocked for more than 143 seconds. Call Trace: inode_lock_nested include/linux/fs.h:1073 [inline] __start_dirop fs/namei.c:2923 [inline] start_dirop fs/namei.c:2934 [inline]
CVE-2026-31449: In the Linux kernel, the following vulnerability has been resolved: ext4: validate p_idx bounds in ext4_ext_correct_indexes ext4_ext_correct_indexes() walks up the extent tree correcting index entries when the first extent in a leaf is modified. Before accessing path[k].p_idx->ei_block, there is no validation that p_idx falls within the valid range of index entries for that level. If the on-disk extent header contains a corrupted or crafted eh_entries value, p_idx can point past the end of the allocated buffer, causing a slab-out-of-bounds read. Fix this by validating path[k].p_idx against EXT_LAST_INDEX() at both access sites: before the while loop and inside it. Return -EFSCORRUPTED if the index pointer is out of range, consistent with how other bounds violations are handled in the ext4 extent tree code.
CVE-2026-31450: In the Linux kernel, the following vulnerability has been resolved: ext4: publish jinode after initialization ext4_inode_attach_jinode() publishes ei->jinode to concurrent users. It used to set ei->jinode before jbd2_journal_init_jbd_inode(), allowing a reader to observe a non-NULL jinode with i_vfs_inode still unset. The fast commit flush path can then pass this jinode to jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and may crash. Below is the crash I observe: ``` BUG: unable to handle page fault for address: 000000010beb47f4 PGD 110e51067 P4D 110e51067 PUD 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014 RIP: 0010:xas_find_marked+0x3d/0x2e0 Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02 RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246 RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003 RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10 RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000 R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88 FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> filemap_get_folios_tag+0x87/0x2a0 __filemap_fdatawait_range+0x5f/0xd0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __schedule+0x3e7/0x10c0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? cap_safe_nice+0x37/0x70 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 filemap_fdatawait_range_keep_errors+0x12/0x40 ext4_fc_commit+0x697/0x8b0 ? ext4_file_write_iter+0x64b/0x950 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? vfs_write+0x356/0x480 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ext4_sync_file+0xf7/0x370 do_fsync+0x3b/0x80 ? syscall_trace_enter+0x108/0x1d0 __x64_sys_fdatasync+0x16/0x20 do_syscall_64+0x62/0x2c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... ``` Fix this by initializing the jbd2_inode first. Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after initialization. Readers use READ_ONCE() to fetch the pointer.
CVE-2026-31451: In the Linux kernel, the following vulnerability has been resolved: ext4: replace BUG_ON with proper error handling in ext4_read_inline_folio Replace BUG_ON() with proper error handling when inline data size exceeds PAGE_SIZE. This prevents kernel panic and allows the system to continue running while properly reporting the filesystem corruption. The error is logged via ext4_error_inode(), the buffer head is released to prevent memory leak, and -EFSCORRUPTED is returned to indicate filesystem corruption.
CVE-2026-31452: In the Linux kernel, the following vulnerability has been resolved: ext4: convert inline data to extents when truncate exceeds inline size Add a check in ext4_setattr() to convert files from inline data storage to extent-based storage when truncate() grows the file size beyond the inline capacity. This prevents the filesystem from entering an inconsistent state where the inline data flag is set but the file size exceeds what can be stored inline. Without this fix, the following sequence causes a kernel BUG_ON(): 1. Mount filesystem with inode that has inline flag set and small size 2. truncate(file, 50MB) - grows size but inline flag remains set 3. sendfile() attempts to write data 4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity) The crash occurs because ext4_write_inline_data() expects inline storage to accommodate the write, but the actual inline capacity (~60 bytes for i_block + ~96 bytes for xattrs) is far smaller than the file size and write request. The fix checks if the new size from setattr exceeds the inode's actual inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to extent-based storage before proceeding with the size change. This addresses the root cause by ensuring the inline data flag and file size remain consistent during truncate operations.
CVE-2026-31453: In the Linux kernel, the following vulnerability has been resolved: xfs: avoid dereferencing log items after push callbacks After xfsaild_push_item() calls iop_push(), the log item may have been freed if the AIL lock was dropped during the push. Background inode reclaim or the dquot shrinker can free the log item while the AIL lock is not held, and the tracepoints in the switch statement dereference the log item after iop_push() returns. Fix this by capturing the log item type, flags, and LSN before calling xfsaild_push_item(), and introducing a new xfs_ail_push_class trace event class that takes these pre-captured values and the ailp pointer instead of the log item pointer.
CVE-2026-31454: In the Linux kernel, the following vulnerability has been resolved: xfs: save ailp before dropping the AIL lock in push callbacks In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock is dropped to perform buffer IO. Once the cluster buffer no longer protects the log item from reclaim, the log item may be freed by background reclaim or the dquot shrinker. The subsequent spin_lock() call dereferences lip->li_ailp, which is a use-after-free. Fix this by saving the ailp pointer in a local variable while the AIL lock is held and the log item is guaranteed to be valid.
CVE-2026-31455: In the Linux kernel, the following vulnerability has been resolved: xfs: stop reclaim before pushing AIL during unmount The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while background reclaim and inodegc are still running. This is broken independently of any use-after-free issues - background reclaim and inodegc should not be running while the AIL is being pushed during unmount, as inodegc can dirty and insert inodes into the AIL during the flush, and background reclaim can race to abort and free dirty inodes. Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background reclaim before pushing the AIL. Stop inodegc before cancelling m_reclaim_work because the inodegc worker can re-queue m_reclaim_work via xfs_inodegc_set_reclaimable.
CVE-2026-31462: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: prevent immediate PASID reuse case PASID resue could cause interrupt issue when process immediately runs into hw state left by previous process exited with the same PASID, it's possible that page faults are still pending in the IH ring buffer when the process exits and frees up its PASID. To prevent the case, it uses idr cyclic allocator same as kernel pid's. (cherry picked from commit 8f1de51f49be692de137c8525106e0fce2d1912d)
CVE-2026-31464: In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Fix OOB access in ibmvfc_discover_targets_done() A malicious or compromised VIO server can return a num_written value in the discover targets MAD response that exceeds max_targets. This value is stored directly in vhost->num_targets without validation, and is then used as the loop bound in ibmvfc_alloc_targets() to index into disc_buf[], which is only allocated for max_targets entries. Indices at or beyond max_targets access kernel memory outside the DMA-coherent allocation. The out-of-bounds data is subsequently embedded in Implicit Logout and PLOGI MADs that are sent back to the VIO server, leaking kernel memory. Fix by clamping num_written to max_targets before storing it.
CVE-2026-31466: In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix folio isn't locked in softleaf_to_folio() On arm64 server, we found folio that get from migration entry isn't locked in softleaf_to_folio(). This issue triggers when mTHP splitting and zap_nonpresent_ptes() races, and the root cause is lack of memory barrier in softleaf_to_folio(). The race is as follows: CPU0 CPU1 deferred_split_scan() zap_nonpresent_ptes() lock folio split_folio() unmap_folio() change ptes to migration entries __split_folio_to_order() softleaf_to_folio() set flags(including PG_locked) for tail pages folio = pfn_folio(softleaf_to_pfn(entry)) smp_wmb() VM_WARN_ON_ONCE(!folio_test_locked(folio)) prep_compound_page() for tail pages In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages are visible before the tail page becomes non-compound. smp_wmb() should be paired with smp_rmb() in softleaf_to_folio(), which is missed. As a result, if zap_nonpresent_ptes() accesses migration entry that stores tail pfn, softleaf_to_folio() may see the updated compound_head of tail page before page->flags. This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio() because of the race between folio split and zap_nonpresent_ptes() leading to a folio incorrectly undergoing modification without a folio lock being held. This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further swapops predicates"), which in merged in v6.19-rc1. To fix it, add missing smp_rmb() if the softleaf entry is migration entry in softleaf_to_folio() and softleaf_to_page(). [tujinjiang@huawei.com: update function name and comments]
CVE-2026-31469: In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared and napi_tx is false A UAF issue occurs when the virtio_net driver is configured with napi_tx=N and the device's IFF_XMIT_DST_RELEASE flag is cleared (e.g., during the configuration of tc route filter rules). When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack expects the driver to hold the reference to skb->dst until the packet is fully transmitted and freed. In virtio_net with napi_tx=N, skbs may remain in the virtio transmit ring for an extended period. If the network namespace is destroyed while these skbs are still pending, the corresponding dst_ops structure has freed. When a subsequent packet is transmitted, free_old_xmit() is triggered to clean up old skbs. It then calls dst_release() on the skb associated with the stale dst_entry. Since the dst_ops (referenced by the dst_entry) has already been freed, a UAF kernel paging request occurs. fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release the dst reference before the skb is queued in virtio_net. Call Trace: Unable to handle kernel paging request at virtual address ffff80007e150000 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT ... percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P) dst_release+0xe0/0x110 net/core/dst.c:177 skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177 sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255 dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469 napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527 __free_old_xmit+0x164/0x230 drivers/net/virtio_net.c:611 [virtio_net] free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net] start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net] ... Reproduction Steps: NETDEV="enp3s0" config_qdisc_route_filter() { tc qdisc del dev $NETDEV root tc qdisc add dev $NETDEV root handle 1: prio tc filter add dev $NETDEV parent 1:0 \ protocol ip prio 100 route to 100 flowid 1:1 ip route add 192.168.1.100/32 dev $NETDEV realm 100 } test_ns() { ip netns add testns ip link set $NETDEV netns testns ip netns exec testns ifconfig $NETDEV 10.0.32.46/24 ip netns exec testns ping -c 1 10.0.32.1 ip netns del testns } config_qdisc_route_filter test_ns sleep 2 test_ns
CVE-2026-31473: In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.
CVE-2026-31485: In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().
CVE-2026-31486: In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/core) Protect regulator operations with mutex The regulator operations pmbus_regulator_get_voltage(), pmbus_regulator_set_voltage(), and pmbus_regulator_list_voltage() access PMBus registers and shared data but were not protected by the update_lock mutex. This could lead to race conditions. However, adding mutex protection directly to these functions causes a deadlock because pmbus_regulator_notify() (which calls regulator_notifier_call_chain()) is often called with the mutex already held (e.g., from pmbus_fault_handler()). If a regulator callback then calls one of the now-protected voltage functions, it will attempt to acquire the same mutex. Rework pmbus_regulator_notify() to utilize a worker function to send notifications outside of the mutex protection. Events are stored as atomics in a per-page bitmask and processed by the worker. Initialize the worker and its associated data during regulator registration, and ensure it is cancelled on device removal using devm_add_action_or_reset(). While at it, remove the unnecessary include of linux/of.h.
CVE-2026-31487: In the Linux kernel, the following vulnerability has been resolved: spi: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Also note that we do not enable the driver_override feature of struct bus_type, as SPI - in contrast to most other buses - passes "" to sysfs_emit() when the driver_override pointer is NULL. Thus, printing "\n" instead of "(null)\n".
CVE-2026-31489: In the Linux kernel, the following vulnerability has been resolved: spi: meson-spicc: Fix double-put in remove path meson_spicc_probe() registers the controller with devm_spi_register_controller(), so teardown already drops the controller reference via devm cleanup. Calling spi_controller_put() again in meson_spicc_remove() causes a double-put.
CVE-2026-31494: In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.
CVE-2026-31495: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: use netlink policy range checks Replace manual range and mask validations with netlink policy annotations in ctnetlink code paths, so that the netlink core rejects invalid values early and can generate extack errors. - CTA_PROTOINFO_TCP_STATE: reject values > TCP_CONNTRACK_SYN_SENT2 at policy level, removing the manual >= TCP_CONNTRACK_MAX check. - CTA_PROTOINFO_TCP_WSCALE_ORIGINAL/REPLY: reject values > TCP_MAX_WSCALE (14). The normal TCP option parsing path already clamps to this value, but the ctnetlink path accepted 0-255, causing undefined behavior when used as a u32 shift count. - CTA_FILTER_ORIG_FLAGS/REPLY_FLAGS: use NLA_POLICY_MASK with CTA_FILTER_F_ALL, removing the manual mask checks. - CTA_EXPECT_FLAGS: use NLA_POLICY_MASK with NF_CT_EXPECT_MASK, adding a new mask define grouping all valid expect flags. Extracted from a broader nf-next patch by Florian Westphal, scoped to ctnetlink for the fixes tree.
CVE-2026-31496: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: skip expectations in other netns via proc Skip expectations that do not reside in this netns. Similar to e77e6ff502ea ("netfilter: conntrack: do not dump other netns's conntrack entries via proc").
CVE-2026-31497: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: clamp SCO altsetting table indices btusb_work() maps the number of active SCO links to USB alternate settings through a three-entry lookup table when CVSD traffic uses transparent voice settings. The lookup currently indexes alts[] with data->sco_num - 1 without first constraining sco_num to the number of available table entries. While the table only defines alternate settings for up to three SCO links, data->sco_num comes from hci_conn_num() and is used directly. Cap the lookup to the last table entry before indexing it so the driver keeps selecting the highest supported alternate setting without reading past alts[].
CVE-2026-31498: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop l2cap_config_req() processes CONFIG_REQ for channels in BT_CONNECTED state to support L2CAP reconfiguration (e.g. MTU changes). However, since both CONF_INPUT_DONE and CONF_OUTPUT_DONE are already set from the initial configuration, the reconfiguration path falls through to l2cap_ertm_init(), which re-initializes tx_q, srej_q, srej_list, and retrans_list without freeing the previous allocations and sets chan->sdu to NULL without freeing the existing skb. This leaks all previously allocated ERTM resources. Additionally, l2cap_parse_conf_req() does not validate the minimum value of remote_mps derived from the RFC max_pdu_size option. A zero value propagates to l2cap_segment_sdu() where pdu_len becomes zero, causing the while loop to never terminate since len is never decremented, exhausting all available memory. Fix the double-init by skipping l2cap_ertm_init() and l2cap_chan_ready() when the channel is already in BT_CONNECTED state, while still allowing the reconfiguration parameters to be updated through l2cap_parse_conf_req(). Also add a pdu_len zero check in l2cap_segment_sdu() as a safeguard.
CVE-2026-31500: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock btintel_hw_error() issues two __hci_cmd_sync() calls (HCI_OP_RESET and Intel exception-info retrieval) without holding hci_req_sync_lock(). This lets it race against hci_dev_do_close() -> btintel_shutdown_combined(), which also runs __hci_cmd_sync() under the same lock. When both paths manipulate hdev->req_status/req_rsp concurrently, the close path may free the response skb first, and the still-running hw_error path hits a slab-use-after-free in kfree_skb(). Wrap the whole recovery sequence in hci_req_sync_lock/unlock so it is serialized with every other synchronous HCI command issuer. Below is the data race report and the kasan report: BUG: data-race in __hci_cmd_sync_sk / btintel_shutdown_combined read of hdev->req_rsp at net/bluetooth/hci_sync.c:199 by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x114/0x670 drivers/bluetooth/btintel.c:254 hci_error_reset+0x348/0xa30 net/bluetooth/hci_core.c:1030 write/free by task ioctl/22580: btintel_shutdown_combined+0xd0/0x360 drivers/bluetooth/btintel.c:3648 hci_dev_close_sync+0x9ae/0x2c10 net/bluetooth/hci_sync.c:5246 hci_dev_do_close+0x232/0x460 net/bluetooth/hci_core.c:526 BUG: KASAN: slab-use-after-free in sk_skb_reason_drop+0x43/0x380 net/core/skbuff.c:1202 Read of size 4 at addr ffff888144a738dc by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x186/0x670 drivers/bluetooth/btintel.c:260
CVE-2026-31502: In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.
CVE-2026-31503: In the Linux kernel, the following vulnerability has been resolved: udp: Fix wildcard bind conflict check when using hash2 When binding a udp_sock to a local address and port, UDP uses two hashes (udptable->hash and udptable->hash2) for collision detection. The current code switches to "hash2" when hslot->count > 10. "hash2" is keyed by local address and local port. "hash" is keyed by local port only. The issue can be shown in the following bind sequence (pseudo code): bind(fd1, "[fd00::1]:8888") bind(fd2, "[fd00::2]:8888") bind(fd3, "[fd00::3]:8888") bind(fd4, "[fd00::4]:8888") bind(fd5, "[fd00::5]:8888") bind(fd6, "[fd00::6]:8888") bind(fd7, "[fd00::7]:8888") bind(fd8, "[fd00::8]:8888") bind(fd9, "[fd00::9]:8888") bind(fd10, "[fd00::10]:8888") /* Correctly return -EADDRINUSE because "hash" is used * instead of "hash2". udp_lib_lport_inuse() detects the * conflict. */ bind(fail_fd, "[::]:8888") /* After one more socket is bound to "[fd00::11]:8888", * hslot->count exceeds 10 and "hash2" is used instead. */ bind(fd11, "[fd00::11]:8888") bind(fail_fd, "[::]:8888") /* succeeds unexpectedly */ The same issue applies to the IPv4 wildcard address "0.0.0.0" and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For example, if there are existing sockets bound to "192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or "[::ffff:0.0.0.0]:8888" can also miss the conflict when hslot->count > 10. TCP inet_csk_get_port() already has the correct check in inet_use_bhash2_on_bind(). Rename it to inet_use_hash2_on_bind() and move it to inet_hashtables.h so udp.c can reuse it in this fix.
CVE-2026-31504: In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.
CVE-2026-31507: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: <TASK> smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.
CVE-2026-31508: In the Linux kernel, the following vulnerability has been resolved: net: openvswitch: Avoid releasing netdev before teardown completes The patch cited in the Fixes tag below changed the teardown code for OVS ports to no longer unconditionally take the RTNL. After this change, the netdev_destroy() callback can proceed immediately to the call_rcu() invocation if the IFF_OVS_DATAPATH flag is already cleared on the netdev. The ovs_netdev_detach_dev() function clears the flag before completing the unregistration, and if it gets preempted after clearing the flag (as can happen on an -rt kernel), netdev_destroy() can complete and the device can be freed before the unregistration completes. This leads to a splat like: [ 998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI [ 998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT [ 998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025 [ 998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0 [ 998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90 [ 998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246 [ 998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000 [ 998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05 [ 998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000 [ 998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006 [ 998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000 [ 998.393931] FS: 00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000 [ 998.393936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0 [ 998.393944] PKRU: 55555554 [ 998.393946] Call Trace: [ 998.393949] <TASK> [ 998.393952] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393961] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393975] ? dp_device_event+0x41/0x80 [openvswitch] [ 998.394009] ? __die_body.cold+0x8/0x12 [ 998.394016] ? die_addr+0x3c/0x60 [ 998.394027] ? exc_general_protection+0x16d/0x390 [ 998.394042] ? asm_exc_general_protection+0x26/0x30 [ 998.394058] ? dev_set_promiscuity+0x8d/0xa0 [ 998.394066] ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch] [ 998.394092] dp_device_event+0x41/0x80 [openvswitch] [ 998.394102] notifier_call_chain+0x5a/0xd0 [ 998.394106] unregister_netdevice_many_notify+0x51b/0xa60 [ 998.394110] rtnl_dellink+0x169/0x3e0 [ 998.394121] ? rt_mutex_slowlock.constprop.0+0x95/0xd0 [ 998.394125] rtnetlink_rcv_msg+0x142/0x3f0 [ 998.394128] ? avc_has_perm_noaudit+0x69/0xf0 [ 998.394130] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 998.394132] netlink_rcv_skb+0x50/0x100 [ 998.394138] netlink_unicast+0x292/0x3f0 [ 998.394141] netlink_sendmsg+0x21b/0x470 [ 998.394145] ____sys_sendmsg+0x39d/0x3d0 [ 998.394149] ___sys_sendmsg+0x9a/0xe0 [ 998.394156] __sys_sendmsg+0x7a/0xd0 [ 998.394160] do_syscall_64+0x7f/0x170 [ 998.394162] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 998.394165] RIP: 0033:0x7fad61bf4724 [ 998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 [ 998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724 [ 998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003 [ 998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f [ 998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2 ---truncated---
CVE-2026-31509: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: fix circular locking dependency in nci_close_device nci_close_device() flushes rx_wq and tx_wq while holding req_lock. This causes a circular locking dependency because nci_rx_work() running on rx_wq can end up taking req_lock too: nci_rx_work -> nci_rx_data_packet -> nci_data_exchange_complete -> __sk_destruct -> rawsock_destruct -> nfc_deactivate_target -> nci_deactivate_target -> nci_request -> mutex_lock(&ndev->req_lock) Move the flush of rx_wq after req_lock has been released. This should safe (I think) because NCI_UP has already been cleared and the transport is closed, so the work will see it and return -ENETDOWN. NIPA has been hitting this running the nci selftest with a debug kernel on roughly 4% of the runs.
CVE-2026-31510: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref on l2cap_sock_ready_cb Before using sk pointer, check if it is null. Fix the following: KASAN: null-ptr-deref in range [0x0000000000000260-0x0000000000000267] CPU: 0 UID: 0 PID: 5985 Comm: kworker/0:5 Not tainted 7.0.0-rc4-00029-ga989fde763f4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-9.fc43 06/10/2025 Workqueue: events l2cap_info_timeout RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce veth0_macvtap: entered promiscuous mode RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005582615a5008 CR3: 000000007007e000 CR4: 0000000000752ef0 PKRU: 55555554 Call Trace: <TASK> __kasan_check_byte+0x12/0x40 lock_acquire+0x79/0x2e0 lock_sock_nested+0x48/0x100 ? l2cap_sock_ready_cb+0x46/0x160 l2cap_sock_ready_cb+0x46/0x160 l2cap_conn_start+0x779/0xff0 ? __pfx_l2cap_conn_start+0x10/0x10 ? l2cap_info_timeout+0x60/0xa0 ? __pfx___mutex_lock+0x10/0x10 l2cap_info_timeout+0x68/0xa0 ? process_scheduled_works+0xa8d/0x18c0 process_scheduled_works+0xb6e/0x18c0 ? __pfx_process_scheduled_works+0x10/0x10 ? assign_work+0x3d5/0x5e0 worker_thread+0xa53/0xfc0 kthread+0x388/0x470 ? __pfx_worker_thread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x51e/0xb90 ? __pfx_ret_from_fork+0x10/0x10 veth1_macvtap: entered promiscuous mode ? __switch_to+0xc7d/0x1450 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- batman_adv: batadv0: Interface activated: batadv_slave_0 batman_adv: batadv0: Interface activated: batadv_slave_1 netdevsim netdevsim7 netdevsim0: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim1: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim2: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0 RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce ieee80211 phy39: Selected rate control algorithm 'minstrel_ht' RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7e16139e9c CR3: 000000000e74e000 CR4: 0000000000752ef0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception
CVE-2026-31512: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate PDU length before reading SDU length in l2cap_ecred_data_rcv() l2cap_ecred_data_rcv() reads the SDU length field from skb->data using get_unaligned_le16() without first verifying that skb contains at least L2CAP_SDULEN_SIZE (2) bytes. When skb->len is less than 2, this reads past the valid data in the skb. The ERTM reassembly path correctly calls pskb_may_pull() before reading the SDU length (l2cap_reassemble_sdu, L2CAP_SAR_START case). Apply the same validation to the Enhanced Credit Based Flow Control data path.
CVE-2026-31515: In the Linux kernel, the following vulnerability has been resolved: af_key: validate families in pfkey_send_migrate() syzbot was able to trigger a crash in skb_put() [1] Issue is that pfkey_send_migrate() does not check old/new families, and that set_ipsecrequest() @family argument was truncated, thus possibly overfilling the skb. Validate families early, do not wait set_ipsecrequest(). [1] skbuff: skb_over_panic: text:ffffffff8a752120 len:392 put:16 head:ffff88802a4ad040 data:ffff88802a4ad040 tail:0x188 end:0x180 dev:<NULL> kernel BUG at net/core/skbuff.c:214 ! Call Trace: <TASK> skb_over_panic net/core/skbuff.c:219 [inline] skb_put+0x159/0x210 net/core/skbuff.c:2655 skb_put_zero include/linux/skbuff.h:2788 [inline] set_ipsecrequest net/key/af_key.c:3532 [inline] pfkey_send_migrate+0x1270/0x2e50 net/key/af_key.c:3636 km_migrate+0x155/0x260 net/xfrm/xfrm_state.c:2848 xfrm_migrate+0x2140/0x2450 net/xfrm/xfrm_policy.c:4705 xfrm_do_migrate+0x8ff/0xaa0 net/xfrm/xfrm_user.c:3150
CVE-2026-31516: In the Linux kernel, the following vulnerability has been resolved: xfrm: prevent policy_hthresh.work from racing with netns teardown A XFRM_MSG_NEWSPDINFO request can queue the per-net work item policy_hthresh.work onto the system workqueue. The queued callback, xfrm_hash_rebuild(), retrieves the enclosing struct net via container_of(). If the net namespace is torn down before that work runs, the associated struct net may already have been freed, and xfrm_hash_rebuild() may then dereference stale memory. xfrm_policy_fini() already flushes policy_hash_work during teardown, but it does not synchronize policy_hthresh.work. Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the queued work cannot outlive the net namespace teardown and access a freed struct net.
CVE-2026-31518: In the Linux kernel, the following vulnerability has been resolved: esp: fix skb leak with espintcp and async crypto When the TX queue for espintcp is full, esp_output_tail_tcp will return an error and not free the skb, because with synchronous crypto, the common xfrm output code will drop the packet for us. With async crypto (esp_output_done), we need to drop the skb when esp_output_tail_tcp returns an error.
CVE-2026-31519: In the Linux kernel, the following vulnerability has been resolved: btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create We have recently observed a number of subvolumes with broken dentries. ls-ing the parent dir looks like: drwxrwxrwt 1 root root 16 Jan 23 16:49 . drwxr-xr-x 1 root root 24 Jan 23 16:48 .. d????????? ? ? ? ? ? broken_subvol and similarly stat-ing the file fails. In this state, deleting the subvol fails with ENOENT, but attempting to create a new file or subvol over it errors out with EEXIST and even aborts the fs. Which leaves us a bit stuck. dmesg contains a single notable error message reading: "could not do orphan cleanup -2" 2 is ENOENT and the error comes from the failure handling path of btrfs_orphan_cleanup(), with the stack leading back up to btrfs_lookup(). btrfs_lookup btrfs_lookup_dentry btrfs_orphan_cleanup // prints that message and returns -ENOENT After some detailed inspection of the internal state, it became clear that: - there are no orphan items for the subvol - the subvol is otherwise healthy looking, it is not half-deleted or anything, there is no drop progress, etc. - the subvol was created a while ago and does the meaningful first btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much later. - after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT, which results in a negative dentry for the subvolume via d_splice_alias(NULL, dentry), leading to the observed behavior. The bug can be mitigated by dropping the dentry cache, at which point we can successfully delete the subvolume if we want. i.e., btrfs_lookup() btrfs_lookup_dentry() if (!sb_rdonly(inode->vfs_inode)->vfs_inode) btrfs_orphan_cleanup(sub_root) test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) btrfs_search_slot() // finds orphan item for inode N ... prints "could not do orphan cleanup -2" if (inode == ERR_PTR(-ENOENT)) inode = NULL; return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) on the root when it runs, so it cannot run more than once on a given root, so something else must run concurrently. However, the obvious routes to deleting an orphan when nlinks goes to 0 should not be able to run without first doing a lookup into the subvolume, which should run btrfs_orphan_cleanup() and set the bit. The final important observation is that create_subvol() calls d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if the dentry cache gets dropped, the next lookup into the subvolume will make a real call into btrfs_orphan_cleanup() for the first time. This opens up the possibility of concurrently deleting the inode/orphan items but most typical evict() paths will be holding a reference on the parent dentry (child dentry holds parent->d_lockref.count via dget in d_alloc(), released in __dentry_kill()) and prevent the parent from being removed from the dentry cache. The one exception is delayed iputs. Ordered extent creation calls igrab() on the inode. If the file is unlinked and closed while those refs are held, iput() in __dentry_kill() decrements i_count but does not trigger eviction (i_count > 0). The child dentry is freed and the subvol dentry's d_lockref.count drops to 0, making it evictable while the inode is still alive. Since there are two races (the race between writeback and unlink and the race between lookup and delayed iputs), and there are too many moving parts, the following three diagrams show the complete picture. (Only the second and third are races) Phase 1: Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set btrfs_mksubvol() lookup_one_len() __lookup_slow() d_alloc_parallel() __d_alloc() // d_lockref.count = 1 create_subvol(dentry) // doesn't touch the bit.. d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.c ---truncated---
CVE-2026-31521: In the Linux kernel, the following vulnerability has been resolved: module: Fix kernel panic when a symbol st_shndx is out of bounds The module loader doesn't check for bounds of the ELF section index in simplify_symbols(): for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char *name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: [...] default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else /** HERE --> **/ secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } A symbol with an out-of-bounds st_shndx value, for example 0xffff (known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic: BUG: unable to handle page fault for address: ... RIP: 0010:simplify_symbols+0x2b2/0x480 ... Kernel panic - not syncing: Fatal exception This can happen when module ELF is legitimately using SHN_XINDEX or when it is corrupted. Add a bounds check in simplify_symbols() to validate that st_shndx is within the valid range before using it. This issue was discovered due to a bug in llvm-objcopy, see relevant discussion for details [1]. [1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/
CVE-2026-31523: In the Linux kernel, the following vulnerability has been resolved: nvme-pci: ensure we're polling a polled queue A user can change the polled queue count at run time. There's a brief window during a reset where a hipri task may try to poll that queue before the block layer has updated the queue maps, which would race with the now interrupt driven queue and may cause double completions.
CVE-2026-31524: In the Linux kernel, the following vulnerability has been resolved: HID: asus: avoid memory leak in asus_report_fixup() The asus_report_fixup() function was returning a newly allocated kmemdup()-allocated buffer, but never freeing it. Switch to devm_kzalloc() to ensure the memory is managed and freed automatically when the device is removed. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a pointer whose lifetime is at least that of the input buffer. Also fix a harmless out-of-bounds read by copying only the original descriptor size.
CVE-2026-31527: In the Linux kernel, the following vulnerability has been resolved: driver core: platform: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1]
CVE-2026-31531: In the Linux kernel, the following vulnerability has been resolved: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop() When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for single nexthops and small Equal-Cost Multi-Path groups, this fixed allocation fails for large nexthop groups like 512 nexthops. This results in the following warning splat: WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608 [...] RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395) [...] Call Trace: <TASK> rtnetlink_rcv_msg (net/core/rtnetlink.c:6989) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585) ___sys_sendmsg (net/socket.c:2641) __sys_sendmsg (net/socket.c:2671) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Fix this by allocating the size dynamically using nh_nlmsg_size() and using nlmsg_new(), this is consistent with nexthop_notify() behavior. In addition, adjust nh_nlmsg_size_grp() so it calculates the size needed based on flags passed. While at it, also add the size of NHA_FDB for nexthop group size calculation as it was missing too. This cannot be reproduced via iproute2 as the group size is currently limited and the command fails as follows: addattr_l ERROR: message exceeded bound of 1048
CVE-2026-31532: In the Linux kernel, the following vulnerability has been resolved: can: raw: fix ro->uniq use-after-free in raw_rcv() raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage. Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained. [mkl: applied manually]
CVE-2026-31540: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: Check set_default_submission() before deferencing When the i915 driver firmware binaries are not present, the set_default_submission pointer is not set. This pointer is dereferenced during suspend anyways. Add a check to make sure it is set before dereferencing. [ 23.289926] PM: suspend entry (deep) [ 23.293558] Filesystems sync: 0.000 seconds [ 23.298010] Freezing user space processes [ 23.302771] Freezing user space processes completed (elapsed 0.000 seconds) [ 23.309766] OOM killer disabled. [ 23.313027] Freezing remaining freezable tasks [ 23.318540] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 23.342038] serial 00:05: disabled [ 23.345719] serial 00:02: disabled [ 23.349342] serial 00:01: disabled [ 23.353782] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 23.358993] sd 1:0:0:0: [sdb] Synchronizing SCSI cache [ 23.361635] ata1.00: Entering standby power mode [ 23.368863] ata2.00: Entering standby power mode [ 23.445187] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 23.452194] #PF: supervisor instruction fetch in kernel mode [ 23.457896] #PF: error_code(0x0010) - not-present page [ 23.463065] PGD 0 P4D 0 [ 23.465640] Oops: Oops: 0010 [#1] SMP NOPTI [ 23.469869] CPU: 8 UID: 0 PID: 211 Comm: kworker/u48:18 Tainted: G S W 6.19.0-rc4-00020-gf0b9d8eb98df #10 PREEMPT(voluntary) [ 23.482512] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 23.496511] Workqueue: async async_run_entry_fn [ 23.501087] RIP: 0010:0x0 [ 23.503755] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 23.510324] RSP: 0018:ffffb4a60065fca8 EFLAGS: 00010246 [ 23.515592] RAX: 0000000000000000 RBX: ffff9f428290e000 RCX: 000000000000000f [ 23.522765] RDX: 0000000000000000 RSI: 0000000000000282 RDI: ffff9f428290e000 [ 23.529937] RBP: ffff9f4282907070 R08: ffff9f4281130428 R09: 00000000ffffffff [ 23.537111] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f42829070f8 [ 23.544284] R13: ffff9f4282906028 R14: ffff9f4282900000 R15: ffff9f4282906b68 [ 23.551457] FS: 0000000000000000(0000) GS:ffff9f466b2cf000(0000) knlGS:0000000000000000 [ 23.559588] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 23.565365] CR2: ffffffffffffffd6 CR3: 000000031c230001 CR4: 0000000000f70ef0 [ 23.572539] PKRU: 55555554 [ 23.575281] Call Trace: [ 23.577770] <TASK> [ 23.579905] intel_engines_reset_default_submission+0x42/0x60 [ 23.585695] __intel_gt_unset_wedged+0x191/0x200 [ 23.590360] intel_gt_unset_wedged+0x20/0x40 [ 23.594675] gt_sanitize+0x15e/0x170 [ 23.598290] i915_gem_suspend_late+0x6b/0x180 [ 23.602692] i915_drm_suspend_late+0x35/0xf0 [ 23.607008] ? __pfx_pci_pm_suspend_late+0x10/0x10 [ 23.611843] dpm_run_callback+0x78/0x1c0 [ 23.615817] device_suspend_late+0xde/0x2e0 [ 23.620037] async_suspend_late+0x18/0x30 [ 23.624082] async_run_entry_fn+0x25/0xa0 [ 23.628129] process_one_work+0x15b/0x380 [ 23.632182] worker_thread+0x2a5/0x3c0 [ 23.635973] ? __pfx_worker_thread+0x10/0x10 [ 23.640279] kthread+0xf6/0x1f0 [ 23.643464] ? __pfx_kthread+0x10/0x10 [ 23.647263] ? __pfx_kthread+0x10/0x10 [ 23.651045] ret_from_fork+0x131/0x190 [ 23.654837] ? __pfx_kthread+0x10/0x10 [ 23.658634] ret_from_fork_asm+0x1a/0x30 [ 23.662597] </TASK> [ 23.664826] Modules linked in: [ 23.667914] CR2: 0000000000000000 [ 23.671271] ------------[ cut here ]------------ (cherry picked from commit daa199abc3d3d1740c9e3a2c3e9216ae5b447cad)
CVE-2026-31545: In the Linux kernel, the following vulnerability has been resolved: NFC: nxp-nci: allow GPIOs to sleep Allow the firmware and enable GPIOs to sleep. This fixes a `WARN_ON' and allows the driver to operate GPIOs which are connected to I2C GPIO expanders. -- >8 -- kernel: WARNING: CPU: 3 PID: 2636 at drivers/gpio/gpiolib.c:3880 gpiod_set_value+0x88/0x98 -- >8 --
CVE-2026-31546: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix NULL deref in bond_debug_rlb_hash_show rlb_clear_slave intentionally keeps RLB hash-table entries on the rx_hashtbl_used_head list with slave set to NULL when no replacement slave is available. However, bond_debug_rlb_hash_show visites client_info->slave without checking if it's NULL. Other used-list iterators in bond_alb.c already handle this NULL-slave state safely: - rlb_update_client returns early on !client_info->slave - rlb_req_update_slave_clients, rlb_clear_slave, and rlb_rebalance compare slave values before visiting - lb_req_update_subnet_clients continues if slave is NULL The following NULL deref crash can be trigger in bond_debug_rlb_hash_show: [ 1.289791] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 1.292058] RIP: 0010:bond_debug_rlb_hash_show (drivers/net/bonding/bond_debugfs.c:41) [ 1.293101] RSP: 0018:ffffc900004a7d00 EFLAGS: 00010286 [ 1.293333] RAX: 0000000000000000 RBX: ffff888102b48200 RCX: ffff888102b48204 [ 1.293631] RDX: ffff888102b48200 RSI: ffffffff839daad5 RDI: ffff888102815078 [ 1.293924] RBP: ffff888102815078 R08: ffff888102b4820e R09: 0000000000000000 [ 1.294267] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100f929c0 [ 1.294564] R13: ffff888100f92a00 R14: 0000000000000001 R15: ffffc900004a7ed8 [ 1.294864] FS: 0000000001395380(0000) GS:ffff888196e75000(0000) knlGS:0000000000000000 [ 1.295239] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.295480] CR2: 0000000000000000 CR3: 0000000102adc004 CR4: 0000000000772ef0 [ 1.295897] Call Trace: [ 1.296134] seq_read_iter (fs/seq_file.c:231) [ 1.296341] seq_read (fs/seq_file.c:164) [ 1.296493] full_proxy_read (fs/debugfs/file.c:378 (discriminator 1)) [ 1.296658] vfs_read (fs/read_write.c:572) [ 1.296981] ksys_read (fs/read_write.c:717) [ 1.297132] do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) [ 1.297325] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Add a NULL check and print "(none)" for entries with no assigned slave.
CVE-2026-31548: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel pmsr_free_wk in cfg80211_pmsr_wdev_down When the nl80211 socket that originated a PMSR request is closed, cfg80211_release_pmsr() sets the request's nl_portid to zero and schedules pmsr_free_wk to process the abort asynchronously. If the interface is concurrently torn down before that work runs, cfg80211_pmsr_wdev_down() calls cfg80211_pmsr_process_abort() directly. However, the already- scheduled pmsr_free_wk work item remains pending and may run after the interface has been removed from the driver. This could cause the driver's abort_pmsr callback to operate on a torn-down interface, leading to undefined behavior and potential crashes. Cancel pmsr_free_wk synchronously in cfg80211_pmsr_wdev_down() before calling cfg80211_pmsr_process_abort(). This ensures any pending or in-progress work is drained before interface teardown proceeds, preventing the work from invoking the driver abort callback after the interface is gone.
CVE-2026-31550: In the Linux kernel, the following vulnerability has been resolved: pmdomain: bcm: bcm2835-power: Increase ASB control timeout The bcm2835_asb_control() function uses a tight polling loop to wait for the ASB bridge to acknowledge a request. During intensive workloads, this handshake intermittently fails for V3D's master ASB on BCM2711, resulting in "Failed to disable ASB master for v3d" errors during runtime PM suspend. As a consequence, the failed power-off leaves V3D in a broken state, leading to bus faults or system hangs on later accesses. As the timeout is insufficient in some scenarios, increase the polling timeout from 1us to 5us, which is still negligible in the context of a power domain transition. Also, replace the open-coded ktime_get_ns()/ cpu_relax() polling loop with readl_poll_timeout_atomic().
CVE-2026-31552: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Return -ENOMEM instead of -EAGAIN if there is not enough headroom Since upstream commit e75665dd0968 ("wifi: wlcore: ensure skb headroom before skb_push"), wl1271_tx_allocate() and with it wl1271_prepare_tx_frame() returns -EAGAIN if pskb_expand_head() fails. However, in wlcore_tx_work_locked(), a return value of -EAGAIN from wl1271_prepare_tx_frame() is interpreted as the aggregation buffer being full. This causes the code to flush the buffer, put the skb back at the head of the queue, and immediately retry the same skb in a tight while loop. Because wlcore_tx_work_locked() holds wl->mutex, and the retry happens immediately with GFP_ATOMIC, this will result in an infinite loop and a CPU soft lockup. Return -ENOMEM instead so the packet is dropped and the loop terminates. The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y.
CVE-2026-31555: In the Linux kernel, the following vulnerability has been resolved: futex: Clear stale exiting pointer in futex_lock_pi() retry path Fuzzying/stressing futexes triggered: WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524 When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY and stores a refcounted task pointer in 'exiting'. After wait_for_owner_exiting() consumes that reference, the local pointer is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a different error, the bogus pointer is passed to wait_for_owner_exiting(). CPU0 CPU1 CPU2 futex_lock_pi(uaddr) // acquires the PI futex exit() futex_cleanup_begin() futex_state = EXITING; futex_lock_pi(uaddr) futex_lock_pi_atomic() attach_to_pi_owner() // observes EXITING *exiting = owner; // takes ref return -EBUSY wait_for_owner_exiting(-EBUSY, owner) put_task_struct(); // drops ref // exiting still points to owner goto retry; futex_lock_pi_atomic() lock_pi_update_atomic() cmpxchg(uaddr) *uaddr ^= WAITERS // whatever // value changed return -EAGAIN; wait_for_owner_exiting(-EAGAIN, exiting) // stale WARN_ON_ONCE(exiting) Fix this by resetting upon retry, essentially aligning it with requeue_pi.
CVE-2026-31560: In the Linux kernel, the following vulnerability has been resolved: spi: spi-dw-dma: fix print error log when wait finish transaction If an error occurs, the device may not have a current message. In this case, the system will crash. In this case, it's better to use dev from the struct ctlr (struct spi_controller*).
CVE-2026-31568: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Add missing secure storage access fixups for donated memory There are special cases where secure storage access exceptions happen in a kernel context for pages that don't have the PG_arch_1 bit set. That bit is set for non-exported guest secure storage (memory) but is absent on storage donated to the Ultravisor since the kernel isn't allowed to export donated pages. Prior to this patch we would try to export the page by calling arch_make_folio_accessible() which would instantly return since the arch bit is absent signifying that the page was already exported and no further action is necessary. This leads to secure storage access exception loops which can never be resolved. With this patch we unconditionally try to export and if that fails we fixup.
CVE-2026-31570: In the Linux kernel, the following vulnerability has been resolved: can: gw: fix OOB heap access in cgw_csum_crc8_rel() cgw_csum_crc8_rel() correctly computes bounds-safe indices via calc_idx(): int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); if (from < 0 || to < 0 || res < 0) return; However, the loop and the result write then use the raw s8 fields directly instead of the computed variables: for (i = crc8->from_idx; ...) /* BUG: raw negative index */ cf->data[crc8->result_idx] = ...; /* BUG: raw negative index */ With from_idx = to_idx = result_idx = -64 on a 64-byte CAN FD frame, calc_idx(-64, 64) = 0 so the guard passes, but the loop iterates with i = -64, reading cf->data[-64], and the write goes to cf->data[-64]. This write might end up to 56 (7.0-rc) or 40 (<= 6.19) bytes before the start of the canfd_frame on the heap. The companion function cgw_csum_xor_rel() uses `from`/`to`/`res` correctly throughout; fix cgw_csum_crc8_rel() to match. Confirmed with KASAN on linux-7.0-rc2: BUG: KASAN: slab-out-of-bounds in cgw_csum_crc8_rel+0x515/0x5b0 Read of size 1 at addr ffff8880076619c8 by task poc_cgw_oob/62 To configure the can-gw crc8 checksums CAP_NET_ADMIN is needed.
CVE-2026-31574: In the Linux kernel, the following vulnerability has been resolved: clockevents: Add missing resets of the next_event_forced flag The prevention mechanism against timer interrupt starvation missed to reset the next_event_forced flag in a couple of places: - When the clock event state changes. That can cause the flag to be stale over a shutdown/startup sequence - When a non-forced event is armed, which then prevents rearming before that event. If that event is far out in the future this will cause missed timer interrupts. - In the suspend wakeup handler. That led to stalls which have been reported by several people. Add the missing resets, which fixes the problems for the reporters.
CVE-2026-31575: In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: fix hugetlb fault mutex hash calculation In mfill_atomic_hugetlb(), linear_page_index() is used to calculate the page index for hugetlb_fault_mutex_hash(). However, linear_page_index() returns the index in PAGE_SIZE units, while hugetlb_fault_mutex_hash() expects the index in huge page units. This mismatch means that different addresses within the same huge page can produce different hash values, leading to the use of different mutexes for the same huge page. This can cause races between faulting threads, which can corrupt the reservation map and trigger the BUG_ON in resv_map_release(). Fix this by introducing hugetlb_linear_page_index(), which returns the page index in huge page granularity, and using it in place of linear_page_index().
CVE-2026-31576: In the Linux kernel, the following vulnerability has been resolved: media: hackrf: fix to not free memory after the device is registered in hackrf_probe() In hackrf driver, the following race condition occurs: ``` CPU0 CPU1 hackrf_probe() kzalloc(); // alloc hackrf_dev .... v4l2_device_register(); .... fd = sys_open("/path/to/dev"); // open hackrf fd .... v4l2_device_unregister(); .... kfree(); // free hackrf_dev .... sys_ioctl(fd, ...); v4l2_ioctl(); video_is_registered() // UAF!! .... sys_close(fd); v4l2_release() // UAF!! hackrf_video_release() kfree(); // DFB!! ``` When a V4L2 or video device is unregistered, the device node is removed so new open() calls are blocked. However, file descriptors that are already open-and any in-flight I/O-do not terminate immediately; they remain valid until the last reference is dropped and the driver's release() is invoked. Therefore, freeing device memory on the error path after hackrf_probe() has registered dev it will lead to a race to use-after-free vuln, since those already-open handles haven't been released yet. And since release() free memory too, race to use-after-free and double-free vuln occur. To prevent this, if device is registered from probe(), it should be modified to free memory only through release() rather than calling kfree() directly.
CVE-2026-31577: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map The DAT inode's btree node cache (i_assoc_inode) is initialized lazily during btree operations. However, nilfs_mdt_save_to_shadow_map() assumes i_assoc_inode is already initialized when copying dirty pages to the shadow map during GC. If NILFS_IOCTL_CLEAN_SEGMENTS is called immediately after mount before any btree operation has occurred on the DAT inode, i_assoc_inode is NULL leading to a general protection fault. Fix this by calling nilfs_attach_btree_node_cache() on the DAT inode in nilfs_dat_read() at mount time, ensuring i_assoc_inode is always initialized before any GC operation can use it.
CVE-2026-31578: In the Linux kernel, the following vulnerability has been resolved: media: as102: fix to not free memory after the device is registered in as102_usb_probe() In as102_usb driver, the following race condition occurs: ``` CPU0 CPU1 as102_usb_probe() kzalloc(); // alloc as102_dev_t .... usb_register_dev(); fd = sys_open("/path/to/dev"); // open as102 fd .... usb_deregister_dev(); .... kfree(); // free as102_dev_t .... sys_close(fd); as102_release() // UAF!! as102_usb_release() kfree(); // DFB!! ``` When a USB character device registered with usb_register_dev() is later unregistered (via usb_deregister_dev() or disconnect), the device node is removed so new open() calls fail. However, file descriptors that are already open do not go away immediately: they remain valid until the last reference is dropped and the driver's .release() is invoked. In as102, as102_usb_probe() calls usb_register_dev() and then, on an error path, does usb_deregister_dev() and frees as102_dev_t right away. If userspace raced a successful open() before the deregistration, that open FD will later hit as102_release() --> as102_usb_release() and access or free as102_dev_t again, occur a race to use-after-free and double-free vuln. The fix is to never kfree(as102_dev_t) directly once usb_register_dev() has succeeded. After deregistration, defer freeing memory to .release(). In other words, let release() perform the last kfree when the final open FD is closed.
CVE-2026-31579: In the Linux kernel, the following vulnerability has been resolved: wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wg_netns_pre_exit() manually acquires rtnl_lock() inside the pernet .pre_exit callback. This causes a hung task when another thread holds rtnl_mutex - the cleanup_net workqueue (or the setup_net failure rollback path) blocks indefinitely in wg_netns_pre_exit() waiting to acquire the lock. Convert to .exit_rtnl, introduced in commit 7a60d91c690b ("net: Add ->exit_rtnl() hook to struct pernet_operations."), where the framework already holds RTNL and batches all callbacks under a single rtnl_lock()/rtnl_unlock() pair, eliminating the contention window. The rcu_assign_pointer(wg->creating_net, NULL) is safe to move from .pre_exit to .exit_rtnl (which runs after synchronize_rcu()) because all RCU readers of creating_net either use maybe_get_net() - which returns NULL for a dying namespace with zero refcount - or access net->user_ns which remains valid throughout the entire ops_undo_list sequence. [ Jason: added __net_exit and __read_mostly annotations that were missing. ]
CVE-2026-31580: In the Linux kernel, the following vulnerability has been resolved: bcache: fix cached_dev.sb_bio use-after-free and crash In our production environment, we have received multiple crash reports regarding libceph, which have caught our attention: ``` [6888366.280350] Call Trace: [6888366.280452] blk_update_request+0x14e/0x370 [6888366.280561] blk_mq_end_request+0x1a/0x130 [6888366.280671] rbd_img_handle_request+0x1a0/0x1b0 [rbd] [6888366.280792] rbd_obj_handle_request+0x32/0x40 [rbd] [6888366.280903] __complete_request+0x22/0x70 [libceph] [6888366.281032] osd_dispatch+0x15e/0xb40 [libceph] [6888366.281164] ? inet_recvmsg+0x5b/0xd0 [6888366.281272] ? ceph_tcp_recvmsg+0x6f/0xa0 [libceph] [6888366.281405] ceph_con_process_message+0x79/0x140 [libceph] [6888366.281534] ceph_con_v1_try_read+0x5d7/0xf30 [libceph] [6888366.281661] ceph_con_workfn+0x329/0x680 [libceph] ``` After analyzing the coredump file, we found that the address of dc->sb_bio has been freed. We know that cached_dev is only freed when it is stopped. Since sb_bio is a part of struct cached_dev, rather than an alloc every time. If the device is stopped while writing to the superblock, the released address will be accessed at endio. This patch hopes to wait for sb_write to complete in cached_dev_free. It should be noted that we analyzed the cause of the problem, then tell all details to the QWEN and adopted the modifications it made.
CVE-2026-31581: In the Linux kernel, the following vulnerability has been resolved: ALSA: 6fire: fix use-after-free on disconnect In usb6fire_chip_abort(), the chip struct is allocated as the card's private data (via snd_card_new with sizeof(struct sfire_chip)). When snd_card_free_when_closed() is called and no file handles are open, the card and embedded chip are freed synchronously. The subsequent chip->card = NULL write then hits freed slab memory. Call trace: usb6fire_chip_abort sound/usb/6fire/chip.c:59 [inline] usb6fire_chip_disconnect+0x348/0x358 sound/usb/6fire/chip.c:182 usb_unbind_interface+0x1a8/0x88c drivers/usb/core/driver.c:458 ... hub_event+0x1a04/0x4518 drivers/usb/core/hub.c:5953 Fix by moving the card lifecycle out of usb6fire_chip_abort() and into usb6fire_chip_disconnect(). The card pointer is saved in a local before any teardown, snd_card_disconnect() is called first to prevent new opens, URBs are aborted while chip is still valid, and snd_card_free_when_closed() is called last so chip is never accessed after the card may be freed.
CVE-2026-31582: In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix use-after-free on USB disconnect After powerz_disconnect() frees the URB and releases the mutex, a subsequent powerz_read() call can acquire the mutex and call powerz_read_data(), which dereferences the freed URB pointer. Fix by: - Setting priv->urb to NULL in powerz_disconnect() so that powerz_read_data() can detect the disconnected state. - Adding a !priv->urb check at the start of powerz_read_data() to return -ENODEV on a disconnected device. - Moving usb_set_intfdata() before hwmon registration so the disconnect handler can always find the priv pointer.
CVE-2026-31583: In the Linux kernel, the following vulnerability has been resolved: media: em28xx: fix use-after-free in em28xx_v4l2_open() em28xx_v4l2_open() reads dev->v4l2 without holding dev->lock, creating a race with em28xx_v4l2_init()'s error path and em28xx_v4l2_fini(), both of which free the em28xx_v4l2 struct and set dev->v4l2 to NULL under dev->lock. This race leads to two issues: - use-after-free in v4l2_fh_init() when accessing vdev->ctrl_handler, since the video_device is embedded in the freed em28xx_v4l2 struct. - NULL pointer dereference in em28xx_resolution_set() when accessing v4l2->norm, since dev->v4l2 has been set to NULL. Fix this by moving the mutex_lock() before the dev->v4l2 read and adding a NULL check for dev->v4l2 under the lock.
CVE-2026-31584: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: fix use-after-free in encoder release path The fops_vcodec_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->encode_work. This creates a race window where the workqueue handler (mtk_venc_worker) may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release path) CPU 1 (workqueue) --------------------- ------------------ fops_vcodec_release() v4l2_m2m_ctx_release() v4l2_m2m_cancel_job() // waits for m2m job "done" mtk_venc_worker() v4l2_m2m_job_finish() // m2m job "done" // BUT worker still running! // post-job_finish access: other ctx dereferences // UAF if ctx already freed // returns (job "done") kfree(ctx) // ctx freed Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle. After v4l2_m2m_job_finish() is called, the m2m framework considers the job complete and v4l2_m2m_ctx_release() returns, but the worker function continues executing and may still access ctx. The work is queued during encode operations via: queue_work(ctx->dev->encode_workqueue, &ctx->encode_work) The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx fields even after calling v4l2_m2m_job_finish(). This vulnerability was confirmed with KASAN by running an instrumented test module that widens the post-job_finish race window. KASAN detected: BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180 Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12 Workqueue: mtk_vcodec_enc_wq mtk_venc_worker Allocated by task 47: __kasan_kmalloc+0x7f/0x90 fops_vcodec_open+0x85/0x1a0 Freed by task 47: __kasan_slab_free+0x43/0x70 kfree+0xee/0x3a0 fops_vcodec_release+0xb7/0x190 Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx). This ensures the workqueue handler is both cancelled (if pending) and synchronized (waits for any running handler to complete) before the context is freed. Placement rationale: The fix is placed after v4l2_ctrl_handler_free() and before list_del_init(&ctx->list). At this point, all m2m operations are done (v4l2_m2m_ctx_release() has returned), and we need to ensure the workqueue is synchronized before removing ctx from the list and freeing it. Note: The open error path does NOT need cancel_work_sync() because INIT_WORK() only initializes the work structure - it does not schedule it. Work is only scheduled later during device_run() operations.
CVE-2026-31585: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix nfeeds state corruption on start_streaming failure syzbot reported a memory leak in vidtv_psi_service_desc_init [1]. When vidtv_start_streaming() fails inside vidtv_start_feed(), the nfeeds counter is left incremented even though no feed was actually started. This corrupts the driver state: subsequent start_feed calls see nfeeds > 1 and skip starting the mux, while stop_feed calls eventually try to stop a non-existent stream. This state corruption can also lead to memory leaks, since the mux and channel resources may be partially allocated during a failed start_streaming but never cleaned up, as the stop path finds dvb->streaming == false and returns early. Fix by decrementing nfeeds back when start_streaming fails, keeping the counter in sync with the actual number of active feeds. [1] BUG: memory leak unreferenced object 0xffff888145b50820 (size 32): comm "syz.0.17", pid 6068, jiffies 4294944486 backtrace (crc 90a0c7d4): vidtv_psi_service_desc_init+0x74/0x1b0 drivers/media/test-drivers/vidtv/vidtv_psi.c:288 vidtv_channel_s302m_init+0xb1/0x2a0 drivers/media/test-drivers/vidtv/vidtv_channel.c:83 vidtv_channels_init+0x1b/0x40 drivers/media/test-drivers/vidtv/vidtv_channel.c:524 vidtv_mux_init+0x516/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:518 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31586: In the Linux kernel, the following vulnerability has been resolved: mm: blk-cgroup: fix use-after-free in cgwb_release_workfn() cgwb_release_workfn() calls css_put(wb->blkcg_css) and then later accesses wb->blkcg_css again via blkcg_unpin_online(). If css_put() drops the last reference, the blkcg can be freed asynchronously (css_free_rwork_fn -> blkcg_css_free -> kfree) before blkcg_unpin_online() dereferences the pointer to access blkcg->online_pin, resulting in a use-after-free: BUG: KASAN: slab-use-after-free in blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) Write of size 4 at addr ff11000117aa6160 by task kworker/71:1/531 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) cgwb_release_workfn (mm/backing-dev.c:629) process_scheduled_works (kernel/workqueue.c:3278 kernel/workqueue.c:3385) Freed by task 1016: kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6246 mm/slub.c:6561) css_free_rwork_fn (kernel/cgroup/cgroup.c:5542) process_scheduled_works (kernel/workqueue.c:3302 kernel/workqueue.c:3385) ** Stack based on commit 66672af7a095 ("Add linux-next specific files for 20260410") I am seeing this crash sporadically in Meta fleet across multiple kernel versions. A full reproducer is available at: https://github.com/leitao/debug/blob/main/reproducers/repro_blkcg_uaf.sh (The race window is narrow. To make it easily reproducible, inject a msleep(100) between css_put() and blkcg_unpin_online() in cgwb_release_workfn(). With that delay and a KASAN-enabled kernel, the reproducer triggers the splat reliably in less than a second.) Fix this by moving blkcg_unpin_online() before css_put(), so the cgwb's CSS reference keeps the blkcg alive while blkcg_unpin_online() accesses it.
CVE-2026-31587: In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm: move component registration to unmanaged version q6apm component registers dais dynamically from ASoC toplology, which are allocated using device managed version apis. Allocating both component and dynamic dais using managed version could lead to incorrect free ordering, dai will be freed while component still holding references to it. Fix this issue by moving component to unmanged version so that the dai pointers are only freeded after the component is removed. ================================================================== BUG: KASAN: slab-use-after-free in snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] Read of size 8 at addr ffff00084493a6e8 by task kworker/u48:0/3426 Tainted: [W]=WARN Hardware name: LENOVO 21N2ZC5PUS/21N2ZC5PUS, BIOS N42ET57W (1.31 ) 08/08/2024 Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] Call trace: show_stack+0x28/0x7c (C) dump_stack_lvl+0x60/0x80 print_report+0x160/0x4b4 kasan_report+0xac/0xfc __asan_report_load8_noabort+0x20/0x34 snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] snd_soc_unregister_component_by_driver+0x50/0x88 [snd_soc_core] devm_component_release+0x30/0x5c [snd_soc_core] devres_release_all+0x13c/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Allocated by task 77: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 kasan_save_alloc_info+0x44/0x58 __kasan_kmalloc+0xbc/0xdc __kmalloc_node_track_caller_noprof+0x1f4/0x620 devm_kmalloc+0x7c/0x1c8 snd_soc_register_dai+0x50/0x4f0 [snd_soc_core] soc_tplg_pcm_elems_load+0x55c/0x1eb8 [snd_soc_core] snd_soc_tplg_component_load+0x4f8/0xb60 [snd_soc_core] audioreach_tplg_init+0x124/0x1fc [snd_q6apm] q6apm_audio_probe+0x10/0x1c [snd_q6apm] snd_soc_component_probe+0x5c/0x118 [snd_soc_core] soc_probe_component+0x44c/0xaf0 [snd_soc_core] snd_soc_bind_card+0xad0/0x2370 [snd_soc_core] snd_soc_register_card+0x3b0/0x4c0 [snd_soc_core] devm_snd_soc_register_card+0x50/0xc8 [snd_soc_core] x1e80100_platform_probe+0x208/0x368 [snd_soc_x1e80100] platform_probe+0xc0/0x188 really_probe+0x188/0x804 __driver_probe_device+0x158/0x358 driver_probe_device+0x60/0x190 __device_attach_driver+0x16c/0x2a8 bus_for_each_drv+0x100/0x194 __device_attach+0x174/0x380 device_initial_probe+0x14/0x20 bus_probe_device+0x124/0x154 deferred_probe_work_func+0x140/0x220 process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Freed by task 3426: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 __kasan_save_free_info+0x4c/0x80 __kasan_slab_free+0x78/0xa0 kfree+0x100/0x4a4 devres_release_all+0x144/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20
CVE-2026-31588: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use scratch field in MMIO fragment to hold small write values When exiting to userspace to service an emulated MMIO write, copy the to-be-written value to a scratch field in the MMIO fragment if the size of the data payload is 8 bytes or less, i.e. can fit in a single chunk, instead of pointing the fragment directly at the source value. This fixes a class of use-after-free bugs that occur when the emulator initiates a write using an on-stack, local variable as the source, the write splits a page boundary, *and* both pages are MMIO pages. Because KVM's ABI only allows for physically contiguous MMIO requests, accesses that split MMIO pages are separated into two fragments, and are sent to userspace one at a time. When KVM attempts to complete userspace MMIO in response to KVM_RUN after the first fragment, KVM will detect the second fragment and generate a second userspace exit, and reference the on-stack variable. The issue is most visible if the second KVM_RUN is performed by a separate task, in which case the stack of the initiating task can show up as truly freed data. ================================================================== BUG: KASAN: use-after-free in complete_emulated_mmio+0x305/0x420 Read of size 1 at addr ffff888009c378d1 by task syz-executor417/984 CPU: 1 PID: 984 Comm: syz-executor417 Not tainted 5.10.0-182.0.0.95.h2627.eulerosv2r13.x86_64 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xbe/0xfd print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 check_memory_region+0xfd/0x1f0 memcpy+0x20/0x60 complete_emulated_mmio+0x305/0x420 kvm_arch_vcpu_ioctl_run+0x63f/0x6d0 kvm_vcpu_ioctl+0x413/0xb20 __se_sys_ioctl+0x111/0x160 do_syscall_64+0x30/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 RIP: 0033:0x42477d Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007faa8e6890e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000004d7338 RCX: 000000000042477d RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005 RBP: 00000000004d7330 R08: 00007fff28d546df R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d733c R13: 0000000000000000 R14: 000000000040a200 R15: 00007fff28d54720 The buggy address belongs to the page: page:0000000029f6a428 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9c37 flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea0000270dc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888009c37780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888009c37880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888009c37900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== The bug can also be reproduced with a targeted KVM-Unit-Test by hacking KVM to fill a large on-stack variable in complete_emulated_mmio(), i.e. by overwrite the data value with garbage. Limit the use of the scratch fields to 8-byte or smaller accesses, and to just writes, as larger accesses and reads are not affected thanks to implementation details in the emulator, but add a sanity check to ensure those details don't change in the future. Specifically, KVM never uses on-stack variables for accesses larger that 8 bytes, e.g. uses an operand in the emulator context, and *al ---truncated---
CVE-2026-31589: In the Linux kernel, the following vulnerability has been resolved: mm: call ->free_folio() directly in folio_unmap_invalidate() We can only call filemap_free_folio() if we have a reference to (or hold a lock on) the mapping. Otherwise, we've already removed the folio from the mapping so it no longer pins the mapping and the mapping can be removed, causing a use-after-free when accessing mapping->a_ops. Follow the same pattern as __remove_mapping() and load the free_folio function pointer before dropping the lock on the mapping. That lets us make filemap_free_folio() static as this was the only caller outside filemap.c.
CVE-2026-31590: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing: struct kvm_enc_region range = { .addr = 0, .size = -1ul, }; __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future. if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.
CVE-2026-31591: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel. Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).
CVE-2026-31592: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Protect *all* of sev_mem_enc_register_region() with kvm->lock Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G U W O 6.16.0-smp-DEV #1 NONE Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024 RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83 Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00 RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256 RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000 RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000 R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000 R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000 FS: 00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0 Call Trace: <TASK> kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371 kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363 __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f34e9f7e9a9 Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9 RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007 RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8 </TASK> with a syzlang reproducer that looks like: syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async) r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0) r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0) r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0) r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0) ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async) ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async) r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0) openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async) ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2) close(r0) (async) openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async) ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0) Opportunistically use guard() to avoid having to define a new error label and goto usage.
CVE-2026-31593: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host. BUG: unable to handle page fault for address: ff1276cbfdf36000 #PF: supervisor write access in kernel mode #PF: error_code(0x80000003) - RMP violation PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163 SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f] Oops: Oops: 0003 [#1] SMP NOPTI CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G OE Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023 RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd] Call Trace: <TASK> snp_launch_update_vmsa+0x19d/0x290 [kvm_amd] snp_launch_finish+0xb6/0x380 [kvm_amd] sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd] kvm_arch_vm_ioctl+0x837/0xcf0 [kvm] kvm_vm_ioctl+0x3fd/0xcc0 [kvm] __x64_sys_ioctl+0xa3/0x100 x64_sys_call+0xfe0/0x2350 do_syscall_64+0x81/0x10f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7ffff673287d </TASK> Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().
CVE-2026-31594: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case: Unable to handle kernel paging request at virtual address dead000000000108 [...] [dead000000000108] address between user and kernel address ranges Internal error: Oops: 0000000096000044 [#1] SMP [...] Call trace: pci_epc_remove_epf+0x78/0xe0 (P) pci_primary_epc_epf_link+0x88/0xa8 configfs_symlink+0x1f4/0x5a0 vfs_symlink+0x134/0x1d8 do_symlinkat+0x88/0x138 __arm64_sys_symlinkat+0x74/0xe0 [...] Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.
CVE-2026-31595: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down. Unable to handle kernel paging request at virtual address ffff800083f46004 [...] Internal error: Oops: 0000000096000007 [#1] SMP [...] Call trace: epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P) process_one_work+0x154/0x3b0 worker_thread+0x2c8/0x400 kthread+0x148/0x210 ret_from_fork+0x10/0x20
CVE-2026-31596: In the Linux kernel, the following vulnerability has been resolved: ocfs2: handle invalid dinode in ocfs2_group_extend [BUG] kernel BUG at fs/ocfs2/resize.c:308! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308 Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe Call Trace: ... ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... [CAUSE] ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl. [FIX] Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.
CVE-2026-31597: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.
CVE-2026-31598: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix possible deadlock between unlink and dio_end_io_write ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key. Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem): ocfs2_unlink ocfs2_prepare_orphan_dir ocfs2_lookup_lock_orphan_dir inode_lock(orphan_dir_inode) <- lock A __ocfs2_prepare_orphan_dir ocfs2_prepare_dir_for_insert ocfs2_extend_dir ocfs2_expand_inline_dir down_write(&oi->ip_alloc_sem) <- Lock B Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock): ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan() inode_lock(orphan_dir_inode) <- Lock A Deadlock Scenario: CPU0 (unlink) CPU1 (dio_end_io_write) ------ ------ inode_lock(orphan_dir_inode) down_write(ip_alloc_sem) down_write(ip_alloc_sem) inode_lock(orphan_dir_inode) Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.
CVE-2026-31599: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections syzbot reported a general protection fault in vidtv_psi_desc_assign [1]. vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault. Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629 Call Trace: <TASK> vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline] vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31600: In the Linux kernel, the following vulnerability has been resolved: arm64: mm: Handle invalid large leaf mappings correctly It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way. It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result: [ 15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers [ 15.476896] Unable to handle kernel paging request at virtual address ffff000019600000 [ 15.513762] Mem abort info: [ 15.527245] ESR = 0x0000000096000046 [ 15.548553] EC = 0x25: DABT (current EL), IL = 32 bits [ 15.572146] SET = 0, FnV = 0 [ 15.592141] EA = 0, S1PTW = 0 [ 15.612694] FSC = 0x06: level 2 translation fault [ 15.640644] Data abort info: [ 15.661983] ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000 [ 15.694875] CM = 0, WnR = 1, TnD = 0, TagAccess = 0 [ 15.723740] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000 [ 15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704 [ 15.855046] Internal error: Oops: 0000000096000046 [#1] SMP [ 15.886394] Modules linked in: [ 15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT [ 15.935258] Hardware name: linux,dummy-virt (DT) [ 15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 15.986009] pc : __pi_memcpy_generic+0x128/0x22c [ 16.006163] lr : swiotlb_bounce+0xf4/0x158 [ 16.024145] sp : ffff80008000b8f0 [ 16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000 [ 16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000 [ 16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0 [ 16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc [ 16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974 [ 16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018 [ 16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000 [ 16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000 [ 16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000 [ 16.349071] Call trace: [ 16.360143] __pi_memcpy_generic+0x128/0x22c (P) [ 16.380310] swiotlb_tbl_map_single+0x154/0x2b4 [ 16.400282] swiotlb_map+0x5c/0x228 [ 16.415984] dma_map_phys+0x244/0x2b8 [ 16.432199] dma_map_page_attrs+0x44/0x58 [ 16.449782] virtqueue_map_page_attrs+0x38/0x44 [ 16.469596] virtqueue_map_single_attrs+0xc0/0x130 [ 16.490509] virtnet_rq_alloc.isra.0+0xa4/0x1fc [ 16.510355] try_fill_recv+0x2a4/0x584 [ 16.526989] virtnet_open+0xd4/0x238 [ 16.542775] __dev_open+0x110/0x24c [ 16.558280] __dev_change_flags+0x194/0x20c [ 16.576879] netif_change_flags+0x24/0x6c [ 16.594489] dev_change_flags+0x48/0x7c [ 16.611462] ip_auto_config+0x258/0x1114 [ 16.628727] do_one_initcall+0x80/0x1c8 [ 16.645590] kernel_init_freeable+0x208/0x2f0 [ 16.664917] kernel_init+0x24/0x1e0 [ 16.680295] ret_from_fork+0x10/0x20 [ 16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c) [ 16.723106] ---[ end trace 0000000000000000 ]--- [ 16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 16.792556] Kernel Offset: 0x3396ea200000 from 0xffff8000800000 ---truncated---
CVE-2026-31601: In the Linux kernel, the following vulnerability has been resolved: vfio/xe: Reorganize the init to decouple migration from reset Attempting to issue reset on VF devices that don't support migration leads to the following: BUG: unable to handle page fault for address: 00000000000011f8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 7443 Comm: xe_sriov_flr Tainted: G S U 7.0.0-rc1-lgci-xe-xe-4588-cec43d5c2696af219-nodebug+ #1 PREEMPT(lazy) Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR4 RVP, BIOS RPLPFWI1.R00.4035.A00.2301200723 01/20/2023 RIP: 0010:xe_sriov_vfio_wait_flr_done+0xc/0x80 [xe] Code: ff c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 54 53 <83> bf f8 11 00 00 02 75 61 41 89 f4 85 f6 74 52 48 8b 47 08 48 89 RSP: 0018:ffffc9000f7c39b8 EFLAGS: 00010202 RAX: ffffffffa04d8660 RBX: ffff88813e3e4000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc9000f7c39c8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888101a48800 R13: ffff88813e3e4150 R14: ffff888130d0d008 R15: ffff88813e3e40d0 FS: 00007877d3d0d940(0000) GS:ffff88890b6d3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000011f8 CR3: 000000015a762000 CR4: 0000000000f52ef0 PKRU: 55555554 Call Trace: <TASK> xe_vfio_pci_reset_done+0x49/0x120 [xe_vfio_pci] pci_dev_restore+0x3b/0x80 pci_reset_function+0x109/0x140 reset_store+0x5c/0xb0 dev_attr_store+0x17/0x40 sysfs_kf_write+0x72/0x90 kernfs_fop_write_iter+0x161/0x1f0 vfs_write+0x261/0x440 ksys_write+0x69/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x259/0x26e0 do_syscall_64+0xcb/0x1500 ? __fput+0x1a2/0x2d0 ? fput_close_sync+0x3d/0xa0 ? __x64_sys_close+0x3e/0x90 ? x64_sys_call+0x1b7c/0x26e0 ? do_syscall_64+0x109/0x1500 ? __task_pid_nr_ns+0x68/0x100 ? __do_sys_getpid+0x1d/0x30 ? x64_sys_call+0x10b5/0x26e0 ? do_syscall_64+0x109/0x1500 ? putname+0x41/0x90 ? do_faccessat+0x1e8/0x300 ? __x64_sys_access+0x1c/0x30 ? x64_sys_call+0x1822/0x26e0 ? do_syscall_64+0x109/0x1500 ? tick_program_event+0x43/0xa0 ? hrtimer_interrupt+0x126/0x260 ? irqentry_exit+0xb2/0x710 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7877d5f1c5a4 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fff48e5f908 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007877d5f1c5a4 RDX: 0000000000000001 RSI: 00007877d621b0c9 RDI: 0000000000000009 RBP: 0000000000000001 R08: 00005fb49113b010 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000202 R12: 00007877d621b0c9 R13: 0000000000000009 R14: 00007fff48e5fac0 R15: 00007fff48e5fac0 </TASK> This is caused by the fact that some of the xe_vfio_pci_core_device members needed for handling reset are only initialized as part of migration init. Fix the problem by reorganizing the code to decouple VF init from migration init.
CVE-2026-31602: In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Limit PTP to a single page Commit 391e69143d0a increased CT_PTP_NUM from 1 to 4 to support 256 playback streams, but the additional pages are not used by the card correctly. The CT20K2 hardware already has multiple VMEM_PTPAL registers, but using them separately would require refactoring the entire virtual memory allocation logic. ct_vm_map() always uses PTEs in vm->ptp[0].area regardless of CT_PTP_NUM. On AMD64 systems, a single PTP covers 512 PTEs (2M). When aggregate memory allocations exceed this limit, ct_vm_map() tries to access beyond the allocated space and causes a page fault: BUG: unable to handle page fault for address: ffffd4ae8a10a000 Oops: Oops: 0002 [#1] SMP PTI RIP: 0010:ct_vm_map+0x17c/0x280 [snd_ctxfi] Call Trace: atc_pcm_playback_prepare+0x225/0x3b0 ct_pcm_playback_prepare+0x38/0x60 snd_pcm_do_prepare+0x2f/0x50 snd_pcm_action_single+0x36/0x90 snd_pcm_action_nonatomic+0xbf/0xd0 snd_pcm_ioctl+0x28/0x40 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x81/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Revert CT_PTP_NUM to 1. The 256 SRC_RESOURCE_NUM and playback_count remain unchanged.
CVE-2026-31603: In the Linux kernel, the following vulnerability has been resolved: staging: sm750fb: fix division by zero in ps_to_hz() ps_to_hz() is called from hw_sm750_crtc_set_mode() without validating that pixclock is non-zero. A zero pixclock passed via FBIOPUT_VSCREENINFO causes a division by zero. Fix by rejecting zero pixclock in lynxfb_ops_check_var(), consistent with other framebuffer drivers.
CVE-2026-31604: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on all probe errors (e.g. when descriptor parsing fails). Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks.
CVE-2026-31605: In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31606: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: don't call cdev_init while cdev in use When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes. This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.
CVE-2026-31607: In the Linux kernel, the following vulnerability has been resolved: usbip: validate number_of_packets in usbip_pack_ret_submit() When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the *original* number_of_packets from the CMD_SUBMIT. A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region. KASAN confirmed this with kernel 7.0.0-rc5: BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640 Write of size 4 at addr ffff888106351d40 by task vhci_rx/69 The buggy address is located 0 bytes to the right of allocated 320-byte region [ffff888106351c00, ffff888106351d40) The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter bound: the response must not exceed the original number_of_packets. This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size. Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit. Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.
CVE-2026-31608: In the Linux kernel, the following vulnerability has been resolved: smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list() smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg() moved it to the batch list.
CVE-2026-31609: In the Linux kernel, the following vulnerability has been resolved: smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush() smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.
CVE-2026-31615: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: renesas_usb3: validate endpoint index in standard request handlers The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math. This is just like what was done in commit ee0d382feb44 ("usb: gadget: aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.
CVE-2026-31616: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete() A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers. pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap. Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path").
CVE-2026-31617: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb() The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of: ndp_index > (block_len - opts->ndp_size) will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely. The same underflow occurs in the datagram index checks against block_len - opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb. Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined. Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.
CVE-2026-31618: In the Linux kernel, the following vulnerability has been resolved: fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31619: In the Linux kernel, the following vulnerability has been resolved: ALSA: fireworks: bound device-supplied status before string array lookup The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value. Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings. Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.
CVE-2026-31620: In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0 A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly. Fix this up by checking the return value properly.
CVE-2026-31621: In the Linux kernel, the following vulnerability has been resolved: bnge: return after auxiliary_device_uninit() in error path When auxiliary_device_add() fails, the error block calls auxiliary_device_uninit() but does not return. The uninit drops the last reference and synchronously runs bnge_aux_dev_release(), which sets bd->auxr_dev = NULL and frees the underlying object. The subsequent bd->auxr_dev->net = bd->netdev then dereferences NULL, which is not a good thing to have happen when trying to clean up from an error. Add the missing return, as the auxiliary bus documentation states is a requirement (seems that LLM tools read documentation better than humans do...)
CVE-2026-31622: In the Linux kernel, the following vulnerability has been resolved: NFC: digital: Bounds check NFC-A cascade depth in SDD response handler The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows). ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round. Fix this by rejecting the response when the accumulated UID would exceed the buffer. Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.
CVE-2026-31623: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers. Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.
CVE-2026-31624: In the Linux kernel, the following vulnerability has been resolved: HID: core: clamp report_size in s32ton() to avoid undefined shift s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field(). Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way. Fix this up by just clamping the max value of n, just like snto32() does.
CVE-2026-31625: In the Linux kernel, the following vulnerability has been resolved: HID: alps: fix NULL pointer dereference in alps_raw_event() Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), but the alps driver was missed. Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.
CVE-2026-31626: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify() Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data. Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized: drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify() warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes) Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.
CVE-2026-31627: In the Linux kernel, the following vulnerability has been resolved: i2c: s3c24xx: check the size of the SMBUS message before using it The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it. This is the same logic that was added in commit a6e04f05ce0b ("i2c: tegra: check msg length in SMBUS block read") to the i2c tegra driver.
CVE-2026-31628: In the Linux kernel, the following vulnerability has been resolved: x86/CPU: Fix FPDSS on Zen1 Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread. Fix that with a chicken bit.
CVE-2026-31629: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: add missing return after LLCP_CLOSED checks In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free. Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.
CVE-2026-31630: In the Linux kernel, the following vulnerability has been resolved: rxrpc: proc: size address buffers for %pISpc output The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example
CVE-2026-31634: In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix reference count leak in rxrpc_server_keyring() This patch fixes a reference count leak in rxrpc_server_keyring() by checking if rx->securities is already set.
CVE-2026-31637: In the Linux kernel, the following vulnerability has been resolved: rxrpc: reject undecryptable rxkad response tickets rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then parses the buffer as plaintext without checking whether crypto_skcipher_decrypt() succeeded. A malformed RESPONSE can therefore use a non-block-aligned ticket length, make the decrypt operation fail, and still drive the ticket parser with attacker-controlled bytes. Check the decrypt result and abort the connection with RXKADBADTICKET when ticket decryption fails.
CVE-2026-31642: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix call removal to use RCU safe deletion Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu() rather than list_del_init() to prevent stuffing up reading /proc/net/rxrpc/calls from potentially getting into an infinite loop. This, however, means that list_empty() no longer works on an entry that's been deleted from the list, making it harder to detect prior deletion. Fix this by: Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that are unexpectedly still on the list. Limiting the number of steps means there's no need to call cond_resched() or to remove calls from the list here, thereby eliminating the need for rxrpc_put_call() to check for that. rxrpc_put_call() can then be fixed to unconditionally delete the call from the list as it is the only place that the deletion occurs.
CVE-2026-31649: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix integer underflow in chain mode The jumbo_frm() chain-mode implementation unconditionally computes len = nopaged_len - bmax; where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is BUF_SIZE_8KiB or BUF_SIZE_2KiB. However, the caller stmmac_xmit() decides to invoke jumbo_frm() based on skb->len (total length including page fragments): is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); When a packet has a small linear portion (nopaged_len <= bmax) but a large total length due to page fragments (skb->len > bmax), the subtraction wraps as an unsigned integer, producing a huge len value (~0xFFFFxxxx). This causes the while (len != 0) loop to execute hundreds of thousands of iterations, passing skb->data + bmax * i pointers far beyond the skb buffer to dma_map_single(). On IOMMU-less SoCs (the typical deployment for stmmac), this maps arbitrary kernel memory to the DMA engine, constituting a kernel memory disclosure and potential memory corruption from hardware. Fix this by introducing a buf_len local variable clamped to min(nopaged_len, bmax). Computing len = nopaged_len - buf_len is then always safe: it is zero when the linear portion fits within a single descriptor, causing the while (len != 0) loop to be skipped naturally, and the fragment loop in stmmac_xmit() handles page fragments afterward.
CVE-2026-31651: In the Linux kernel, the following vulnerability has been resolved: mmc: vub300: fix NULL-deref on disconnect Make sure to deregister the controller before dropping the reference to the driver data on disconnect to avoid NULL-pointer dereferences or use-after-free.
CVE-2026-31656: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <TASK> <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] </TASK> ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)
CVE-2026-31657: In the Linux kernel, the following vulnerability has been resolved: batman-adv: hold claim backbone gateways by reference batadv_bla_add_claim() can replace claim->backbone_gw and drop the old gateway's last reference while readers still follow the pointer. The netlink claim dump path dereferences claim->backbone_gw->orig and takes claim->backbone_gw->crc_lock without pinning the underlying backbone gateway. batadv_bla_check_claim() still has the same naked pointer access pattern. Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate on a stable gateway reference until the read-side work is complete. This keeps the dump and claim-check paths aligned with the lifetime rules introduced for the other BLA claim readers.
CVE-2026-31658: In the Linux kernel, the following vulnerability has been resolved: net: altera-tse: fix skb leak on DMA mapping error in tse_start_xmit() When dma_map_single() fails in tse_start_xmit(), the function returns NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the stack the packet was consumed, the skb is never freed, leaking memory on every DMA mapping failure. Add dev_kfree_skb_any() before returning to properly free the skb.
CVE-2026-31659: In the Linux kernel, the following vulnerability has been resolved: batman-adv: reject oversized global TT response buffers batadv_tt_prepare_tvlv_global_data() builds the allocation length for a global TT response in 16-bit temporaries. When a remote originator advertises a large enough global TT, the TT payload length plus the VLAN header offset can exceed 65535 and wrap before kmalloc(). The full-table response path still uses the original TT payload length when it fills tt_change, so the wrapped allocation is too small and batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object before the later packet-size check runs. Fix this by rejecting TT responses whose TVLV value length cannot fit in the 16-bit TVLV payload length field.
CVE-2026-31660: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: allocate rx skb before consuming bytes pn532_receive_buf() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already hand a complete frame to pn533_recv_frame() before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted.
CVE-2026-31661: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmsmac: Fix dma_free_coherent() size dma_alloc_consistent() may change the size to align it. The new size is saved in alloced. Change the free size to match the allocation size.
CVE-2026-31662: In the Linux kernel, the following vulnerability has been resolved: tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements bc_ackers on every inbound group ACK, even when the same member has already acknowledged the current broadcast round. Because bc_ackers is a u16, a duplicate ACK received after the last legitimate ACK wraps the counter to 65535. Once wrapped, tipc_group_bc_cong() keeps reporting congestion and later group broadcasts on the affected socket stay blocked until the group is recreated. Fix this by ignoring duplicate or stale ACKs before touching bc_acked or bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and prevents the underflow path.
CVE-2026-31663: In the Linux kernel, the following vulnerability has been resolved: xfrm: hold dev ref until after transport_finish NF_HOOK After async crypto completes, xfrm_input_resume() calls dev_put() immediately on re-entry before the skb reaches transport_finish. The skb->dev pointer is then used inside NF_HOOK and its okfn, which can race with device teardown. Remove the dev_put from the async resumption entry and instead drop the reference after the NF_HOOK call in transport_finish, using a saved device pointer since NF_HOOK may consume the skb. This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip the okfn. For non-transport exits (decaps, gro, drop) and secondary async return points, release the reference inline when async is set.
CVE-2026-31664: In the Linux kernel, the following vulnerability has been resolved: xfrm: clear trailing padding in build_polexpire() build_expire() clears the trailing padding bytes of struct xfrm_user_expire after setting the hard field via memset_after(), but the analogous function build_polexpire() does not do this for struct xfrm_user_polexpire. The padding bytes after the __u8 hard field are left uninitialized from the heap allocation, and are then sent to userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners, leaking kernel heap memory contents. Add the missing memset_after() call, matching build_expire().
CVE-2026-31665: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: fix use-after-free in timeout object destroy nft_ct_timeout_obj_destroy() frees the timeout object with kfree() immediately after nf_ct_untimeout(), without waiting for an RCU grace period. Concurrent packet processing on other CPUs may still hold RCU-protected references to the timeout object obtained via rcu_dereference() in nf_ct_timeout_data(). Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer freeing until after an RCU grace period, matching the approach already used in nfnetlink_cttimeout.c. KASAN report: BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0 Read of size 4 at addr ffff8881035fe19c by task exploit/80 Call Trace: nf_conntrack_tcp_packet+0x1381/0x29d0 nf_conntrack_in+0x612/0x8b0 nf_hook_slow+0x70/0x100 __ip_local_out+0x1b2/0x210 tcp_sendmsg_locked+0x722/0x1580 __sys_sendto+0x2d8/0x320 Allocated by task 75: nft_ct_timeout_obj_init+0xf6/0x290 nft_obj_init+0x107/0x1b0 nf_tables_newobj+0x680/0x9c0 nfnetlink_rcv_batch+0xc29/0xe00 Freed by task 26: nft_obj_destroy+0x3f/0xa0 nf_tables_trans_destroy_work+0x51c/0x5c0 process_one_work+0x2c4/0x5a0
CVE-2026-31667: In the Linux kernel, the following vulnerability has been resolved: Input: uinput - fix circular locking dependency with ff-core A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)
CVE-2026-31668: In the Linux kernel, the following vulnerability has been resolved: seg6: separate dst_cache for input and output paths in seg6 lwtunnel The seg6 lwtunnel uses a single dst_cache per encap route, shared between seg6_input_core() and seg6_output_core(). These two paths can perform the post-encap SID lookup in different routing contexts (e.g., ip rules matching on the ingress interface, or VRF table separation). Whichever path runs first populates the cache, and the other reuses it blindly, bypassing its own lookup. Fix this by splitting the cache into cache_input and cache_output, so each path maintains its own cached dst independently.
CVE-2026-31670: In the Linux kernel, the following vulnerability has been resolved: net: rfkill: prevent unlimited numbers of rfkill events from being created Userspace can create an unlimited number of rfkill events if the system is so configured, while not consuming them from the rfkill file descriptor, causing a potential out of memory situation. Prevent this from bounding the number of pending rfkill events at a "large" number (i.e. 1000) to prevent abuses like this.
CVE-2026-31671: In the Linux kernel, the following vulnerability has been resolved: xfrm_user: fix info leak in build_report() struct xfrm_user_report is a __u8 proto field followed by a struct xfrm_selector which means there is three "empty" bytes of padding, but the padding is never zeroed before copying to userspace. Fix that up by zeroing the structure before setting individual member variables.
CVE-2026-31672: In the Linux kernel, the following vulnerability has been resolved: wifi: rt2x00usb: fix devres lifetime USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the USB anchor lifetime so that it is released on driver unbind.
CVE-2026-31673: In the Linux kernel, the following vulnerability has been resolved: af_unix: read UNIX_DIAG_VFS data under unix_state_lock Exact UNIX diag lookups hold a reference to the socket, but not to u->path. Meanwhile, unix_release_sock() clears u->path under unix_state_lock() and drops the path reference after unlocking. Read the inode and device numbers for UNIX_DIAG_VFS while holding unix_state_lock(), then emit the netlink attribute after dropping the lock. This keeps the VFS data stable while the reply is being built.
CVE-2026-31674: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check() Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS. rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[]. Validate addrnr during rule installation so malformed rules are rejected before the match logic can use an out-of-range value.
CVE-2026-31675: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_netem: fix out-of-bounds access in packet corruption In netem_enqueue(), the packet corruption logic uses get_random_u32_below(skb_headlen(skb)) to select an index for modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0. Passing 0 to get_random_u32_below() takes the variable-ceil slow path which returns an unconstrained 32-bit random integer. Using this unconstrained value as an offset into skb->data results in an out-of-bounds memory access. Fix this by verifying skb_headlen(skb) is non-zero before attempting to corrupt the linear data area. Fully non-linear packets will silently bypass the corruption logic.
CVE-2026-31676: In the Linux kernel, the following vulnerability has been resolved: rxrpc: only handle RESPONSE during service challenge Only process RESPONSE packets while the service connection is still in RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before running response verification and security initialization, then use a local secured flag to decide whether to queue the secured-connection work after the state transition. This keeps duplicate or late RESPONSE packets from re-running the setup path and removes the unlocked post-transition state test.
CVE-2026-31677: In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - limit RX SG extraction by receive buffer budget Make af_alg_get_rsgl() limit each RX scatterlist extraction to the remaining receive buffer budget. af_alg_get_rsgl() currently uses af_alg_readable() only as a gate before extracting data into the RX scatterlist. Limit each extraction to the remaining af_alg_rcvbuf(sk) budget so that receive-side accounting matches the amount of data attached to the request. If skcipher cannot obtain enough RX space for at least one chunk while more data remains to be processed, reject the recvmsg call instead of rounding the request length down to zero.
CVE-2026-31678: In the Linux kernel, the following vulnerability has been resolved: openvswitch: defer tunnel netdev_put to RCU release ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already detached the device. Dropping the netdev reference in destroy can race with concurrent readers that still observe vport->dev. Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let vport_netdev_free() drop the reference from the RCU callback, matching the non-tunnel destroy path and avoiding additional synchronization under RTNL.
CVE-2026-31679: In the Linux kernel, the following vulnerability has been resolved: openvswitch: validate MPLS set/set_masked payload length validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for SET/SET_MASKED actions. In action handling, OVS expects fixed-size MPLS key data (struct ovs_key_mpls). Use the already normalized key_len (masked case included) and reject non-matching MPLS action key sizes. Reject invalid MPLS action payload lengths early.
CVE-2026-31680: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: flowlabel: defer exclusive option free until RCU teardown `ip6fl_seq_show()` walks the global flowlabel hash under the seq-file RCU read-side lock and prints `fl->opt->opt_nflen` when an option block is present. Exclusive flowlabels currently free `fl->opt` as soon as `fl->users` drops to zero in `fl_release()`. However, the surrounding `struct ip6_flowlabel` remains visible in the global hash table until later garbage collection removes it and `fl_free_rcu()` finally tears it down. A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that early `kfree()` and dereference freed option state, triggering a crash in `ip6fl_seq_show()`. Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches the lifetime already required for the enclosing flowlabel while readers can still reach it under RCU.
CVE-2026-31681: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_multiport: validate range encoding in checkentry ports_match_v1() treats any non-zero pflags entry as the start of a port range and unconditionally consumes the next ports[] element as the range end. The checkentry path currently validates protocol, flags and count, but it does not validate the range encoding itself. As a result, malformed rules can mark the last slot as a range start or place two range starts back to back, leaving ports_match_v1() to step past the last valid ports[] element while interpreting the rule. Reject malformed multiport v1 rules in checkentry by validating that each range start has a following element and that the following element is not itself marked as another range start.
CVE-2026-31682: In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: linearize skb before parsing ND options br_nd_send() parses neighbour discovery options from ns->opt[] and assumes that these options are in the linear part of request. Its callers only guarantee that the ICMPv6 header and target address are available, so the option area can still be non-linear. Parsing ns->opt[] in that case can access data past the linear buffer. Linearize request before option parsing and derive ns from the linear network header.
CVE-2026-31683: In the Linux kernel, the following vulnerability has been resolved: batman-adv: avoid OGM aggregation when skb tailroom is insufficient When OGM aggregation state is toggled at runtime, an existing forwarded packet may have been allocated with only packet_len bytes, while a later packet can still be selected for aggregation. Appending in this case can hit skb_put overflow conditions. Reject aggregation when the target skb tailroom cannot accommodate the new packet. The caller then falls back to creating a new forward packet instead of appending.
CVE-2026-31684: In the Linux kernel, the following vulnerability has been resolved: net: sched: act_csum: validate nested VLAN headers tcf_csum_act() walks nested VLAN headers directly from skb->data when an skb still carries in-payload VLAN tags. The current code reads vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without first ensuring that the full VLAN header is present in the linear area. If only part of an inner VLAN header is linearized, accessing h_vlan_encapsulated_proto reads past the linear area, and the following skb_pull(VLAN_HLEN) may violate skb invariants. Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and pulling each nested VLAN header. If the header still is not fully available, drop the packet through the existing error path.
CVE-2026-31685: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_eui64: reject invalid MAC header for all packets `eui64_mt6()` derives a modified EUI-64 from the Ethernet source address and compares it with the low 64 bits of the IPv6 source address. The existing guard only rejects an invalid MAC header when `par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()` can still reach `eth_hdr(skb)` even when the MAC header is not valid. Fix this by removing the `par->fragoff != 0` condition so that packets with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.
CVE-2026-31788: In the Linux kernel, the following vulnerability has been resolved: xen/privcmd: restrict usage in unprivileged domU The Xen privcmd driver allows to issue arbitrary hypercalls from user space processes. This is normally no problem, as access is usually limited to root and the hypervisor will deny any hypercalls affecting other domains. In case the guest is booted using secure boot, however, the privcmd driver would be enabling a root user process to modify e.g. kernel memory contents, thus breaking the secure boot feature. The only known case where an unprivileged domU is really needing to use the privcmd driver is the case when it is acting as the device model for another guest. In this case all hypercalls issued via the privcmd driver will target that other guest. Fortunately the privcmd driver can already be locked down to allow only hypercalls targeting a specific domain, but this mode can be activated from user land only today. The target domain can be obtained from Xenstore, so when not running in dom0 restrict the privcmd driver to that target domain from the beginning, resolving the potential problem of breaking secure boot. This is XSA-482 --- V2: - defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich) - wait in open() if target domain isn't known yet - issue message in case no target domain found (Jan Beulich)

5 issues postponed or untriaged:

CVE-2019-15213: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-16089: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: (postponed; to be fixed through a stable update) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: (needs triaging) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.

44 ignored issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2022-0480: A flaw was found in the filelock_init in fs/locks.c function in the Linux kernel. This issue can lead to host memory exhaustion due to memcg not limiting the number of Portable Operating System Interface (POSIX) file locks.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2020-12362: Integer overflow in the firmware for some Intel(R) Graphics Drivers for Windows * before version 26.20.100.7212 and before Linux kernel version 5.5 may allow a privileged user to potentially enable an escalation of privilege via local access.
CVE-2020-12363: Improper input validation in some Intel(R) Graphics Drivers for Windows* before version 26.20.100.7212 and before Linux kernel version 5.5 may allow a privileged user to potentially enable a denial of service via local access.
CVE-2020-12364: Null pointer reference in some Intel(R) Graphics Drivers for Windows* before version 26.20.100.7212 and before version Linux kernel version 5.5 may allow a privileged user to potentially enable a denial of service via local access.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2020-24504: Uncontrolled resource consumption in some Intel(R) Ethernet E810 Adapter drivers for Linux before version 1.0.4 may allow an authenticated user to potentially enable denial of service via local access.
CVE-2022-49034: In the Linux kernel, the following vulnerability has been resolved: sh: cpuinfo: Fix a warning for CONFIG_CPUMASK_OFFSTACK When CONFIG_CPUMASK_OFFSTACK and CONFIG_DEBUG_PER_CPU_MAPS are selected, cpu_max_bits_warn() generates a runtime warning similar as below when showing /proc/cpuinfo. Fix this by using nr_cpu_ids (the runtime limit) instead of NR_CPUS to iterate CPUs. [ 3.052463] ------------[ cut here ]------------ [ 3.059679] WARNING: CPU: 3 PID: 1 at include/linux/cpumask.h:108 show_cpuinfo+0x5e8/0x5f0 [ 3.070072] Modules linked in: efivarfs autofs4 [ 3.076257] CPU: 0 PID: 1 Comm: systemd Not tainted 5.19-rc5+ #1052 [ 3.099465] Stack : 9000000100157b08 9000000000f18530 9000000000cf846c 9000000100154000 [ 3.109127] 9000000100157a50 0000000000000000 9000000100157a58 9000000000ef7430 [ 3.118774] 90000001001578e8 0000000000000040 0000000000000020 ffffffffffffffff [ 3.128412] 0000000000aaaaaa 1ab25f00eec96a37 900000010021de80 900000000101c890 [ 3.138056] 0000000000000000 0000000000000000 0000000000000000 0000000000aaaaaa [ 3.147711] ffff8000339dc220 0000000000000001 0000000006ab4000 0000000000000000 [ 3.157364] 900000000101c998 0000000000000004 9000000000ef7430 0000000000000000 [ 3.167012] 0000000000000009 000000000000006c 0000000000000000 0000000000000000 [ 3.176641] 9000000000d3de08 9000000001639390 90000000002086d8 00007ffff0080286 [ 3.186260] 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c [ 3.195868] ... [ 3.199917] Call Trace: [ 3.203941] [<90000000002086d8>] show_stack+0x38/0x14c [ 3.210666] [<9000000000cf846c>] dump_stack_lvl+0x60/0x88 [ 3.217625] [<900000000023d268>] __warn+0xd0/0x100 [ 3.223958] [<9000000000cf3c90>] warn_slowpath_fmt+0x7c/0xcc [ 3.231150] [<9000000000210220>] show_cpuinfo+0x5e8/0x5f0 [ 3.238080] [<90000000004f578c>] seq_read_iter+0x354/0x4b4 [ 3.245098] [<90000000004c2e90>] new_sync_read+0x17c/0x1c4 [ 3.252114] [<90000000004c5174>] vfs_read+0x138/0x1d0 [ 3.258694] [<90000000004c55f8>] ksys_read+0x70/0x100 [ 3.265265] [<9000000000cfde9c>] do_syscall+0x7c/0x94 [ 3.271820] [<9000000000202fe4>] handle_syscall+0xc4/0x160 [ 3.281824] ---[ end trace 8b484262b4b8c24c ]---
CVE-2024-25742: In the Linux kernel before 6.9, an untrusted hypervisor can inject virtual interrupt 29 (#VC) at any point in time and can trigger its handler. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-25743: In the Linux kernel through 6.9, an untrusted hypervisor can inject virtual interrupts 0 and 14 at any point in time and can trigger the SIGFPE signal handler in userspace applications. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-26706: In the Linux kernel, the following vulnerability has been resolved: parisc: Fix random data corruption from exception handler The current exception handler implementation, which assists when accessing user space memory, may exhibit random data corruption if the compiler decides to use a different register than the specified register %r29 (defined in ASM_EXCEPTIONTABLE_REG) for the error code. If the compiler choose another register, the fault handler will nevertheless store -EFAULT into %r29 and thus trash whatever this register is used for. Looking at the assembly I found that this happens sometimes in emulate_ldd(). To solve the issue, the easiest solution would be if it somehow is possible to tell the fault handler which register is used to hold the error code. Using %0 or %1 in the inline assembly is not posssible as it will show up as e.g. %r29 (with the "%r" prefix), which the GNU assembler can not convert to an integer. This patch takes another, better and more flexible approach: We extend the __ex_table (which is out of the execution path) by one 32-word. In this word we tell the compiler to insert the assembler instruction "or %r0,%r0,%reg", where %reg references the register which the compiler choosed for the error return code. In case of an access failure, the fault handler finds the __ex_table entry and can examine the opcode. The used register is encoded in the lowest 5 bits, and the fault handler can then store -EFAULT into this register. Since we extend the __ex_table to 3 words we can't use the BUILDTIME_TABLE_SORT config option any longer.
CVE-2024-27054: In the Linux kernel, the following vulnerability has been resolved: s390/dasd: fix double module refcount decrement Once the discipline is associated with the device, deleting the device takes care of decrementing the module's refcount. Doing it manually on this error path causes refcount to artificially decrease on each error while it should just stay the same.
CVE-2024-42267: In the Linux kernel, the following vulnerability has been resolved: riscv/mm: Add handling for VM_FAULT_SIGSEGV in mm_fault_error() Handle VM_FAULT_SIGSEGV in the page fault path so that we correctly kill the process and we don't BUG() the kernel.
CVE-2024-42271: In the Linux kernel, the following vulnerability has been resolved: net/iucv: fix use after free in iucv_sock_close() iucv_sever_path() is called from process context and from bh context. iucv->path is used as indicator whether somebody else is taking care of severing the path (or it is already removed / never existed). This needs to be done with atomic compare and swap, otherwise there is a small window where iucv_sock_close() will try to work with a path that has already been severed and freed by iucv_callback_connrej() called by iucv_tasklet_fn(). Example: [452744.123844] Call Trace: [452744.123845] ([<0000001e87f03880>] 0x1e87f03880) [452744.123966] [<00000000d593001e>] iucv_path_sever+0x96/0x138 [452744.124330] [<000003ff801ddbca>] iucv_sever_path+0xc2/0xd0 [af_iucv] [452744.124336] [<000003ff801e01b6>] iucv_sock_close+0xa6/0x310 [af_iucv] [452744.124341] [<000003ff801e08cc>] iucv_sock_release+0x3c/0xd0 [af_iucv] [452744.124345] [<00000000d574794e>] __sock_release+0x5e/0xe8 [452744.124815] [<00000000d5747a0c>] sock_close+0x34/0x48 [452744.124820] [<00000000d5421642>] __fput+0xba/0x268 [452744.124826] [<00000000d51b382c>] task_work_run+0xbc/0xf0 [452744.124832] [<00000000d5145710>] do_notify_resume+0x88/0x90 [452744.124841] [<00000000d5978096>] system_call+0xe2/0x2c8 [452744.125319] Last Breaking-Event-Address: [452744.125321] [<00000000d5930018>] iucv_path_sever+0x90/0x138 [452744.125324] [452744.125325] Kernel panic - not syncing: Fatal exception in interrupt Note that bh_lock_sock() is not serializing the tasklet context against process context, because the check for sock_owned_by_user() and corresponding handling is missing. Ideas for a future clean-up patch: A) Correct usage of bh_lock_sock() in tasklet context, as described in Re-enqueue, if needed. This may require adding return values to the tasklet functions and thus changes to all users of iucv. B) Change iucv tasklet into worker and use only lock_sock() in af_iucv.
CVE-2024-44949: In the Linux kernel, the following vulnerability has been resolved: parisc: fix a possible DMA corruption ARCH_DMA_MINALIGN was defined as 16 - this is too small - it may be possible that two unrelated 16-byte allocations share a cache line. If one of these allocations is written using DMA and the other is written using cached write, the value that was written with DMA may be corrupted. This commit changes ARCH_DMA_MINALIGN to be 128 on PA20 and 32 on PA1.1 - that's the largest possible cache line size. As different parisc microarchitectures have different cache line size, we define arch_slab_minalign(), cache_line_size() and dma_get_cache_alignment() so that the kernel may tune slab cache parameters dynamically, based on the detected cache line size.
CVE-2024-46761: In the Linux kernel, the following vulnerability has been resolved: pci/hotplug/pnv_php: Fix hotplug driver crash on Powernv The hotplug driver for powerpc (pci/hotplug/pnv_php.c) causes a kernel crash when we try to hot-unplug/disable the PCIe switch/bridge from the PHB. The crash occurs because although the MSI data structure has been released during disable/hot-unplug path and it has been assigned with NULL, still during unregistration the code was again trying to explicitly disable the MSI which causes the NULL pointer dereference and kernel crash. The patch fixes the check during unregistration path to prevent invoking pci_disable_msi/msix() since its data structure is already freed.
CVE-2024-46774: In the Linux kernel, the following vulnerability has been resolved: powerpc/rtas: Prevent Spectre v1 gadget construction in sys_rtas() Smatch warns: arch/powerpc/kernel/rtas.c:1932 __do_sys_rtas() warn: potential spectre issue 'args.args' [r] (local cap) The 'nargs' and 'nret' locals come directly from a user-supplied buffer and are used as indexes into a small stack-based array and as inputs to copy_to_user() after they are subject to bounds checks. Use array_index_nospec() after the bounds checks to clamp these values for speculative execution.
CVE-2024-46832: In the Linux kernel, the following vulnerability has been resolved: MIPS: cevt-r4k: Don't call get_c0_compare_int if timer irq is installed This avoids warning: [ 0.118053] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 Caused by get_c0_compare_int on secondary CPU. We also skipped saving IRQ number to struct clock_event_device *cd as it's never used by clockevent core, as per comments it's only meant for "non CPU local devices".
CVE-2024-47747: In the Linux kernel, the following vulnerability has been resolved: net: seeq: Fix use after free vulnerability in ether3 Driver Due to Race Condition In the ether3_probe function, a timer is initialized with a callback function ether3_ledoff, bound to &prev(dev)->timer. Once the timer is started, there is a risk of a race condition if the module or device is removed, triggering the ether3_remove function to perform cleanup. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | ether3_ledoff ether3_remove | free_netdev(dev); | put_devic | kfree(dev); | | ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2); | // use dev Fix it by ensuring that the timer is canceled before proceeding with the cleanup in ether3_remove.
CVE-2024-49924: In the Linux kernel, the following vulnerability has been resolved: fbdev: pxafb: Fix possible use after free in pxafb_task() In the pxafb_probe function, it calls the pxafb_init_fbinfo function, after which &fbi->task is associated with pxafb_task. Moreover, within this pxafb_init_fbinfo function, the pxafb_blank function within the &pxafb_ops struct is capable of scheduling work. If we remove the module which will call pxafb_remove to make cleanup, it will call unregister_framebuffer function which can call do_unregister_framebuffer to free fbi->fb through put_fb_info(fb_info), while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | pxafb_task pxafb_remove | unregister_framebuffer(info) | do_unregister_framebuffer(fb_info) | put_fb_info(fb_info) | // free fbi->fb | set_ctrlr_state(fbi, state) | __pxafb_lcd_power(fbi, 0) | fbi->lcd_power(on, &fbi->fb.var) | //use fbi->fb Fix it by ensuring that the work is canceled before proceeding with the cleanup in pxafb_remove. Note that only root user can remove the driver at runtime.
CVE-2024-49997: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: lantiq_etop: fix memory disclosure When applying padding, the buffer is not zeroed, which results in memory disclosure. The mentioned data is observed on the wire. This patch uses skb_put_padto() to pad Ethernet frames properly. The mentioned function zeroes the expanded buffer. In case the packet cannot be padded it is silently dropped. Statistics are also not incremented. This driver does not support statistics in the old 32-bit format or the new 64-bit format. These will be added in the future. In its current form, the patch should be easily backported to stable versions. Ethernet MACs on Amazon-SE and Danube cannot do padding of the packets in hardware, so software padding must be applied.
CVE-2024-50051: In the Linux kernel, the following vulnerability has been resolved: spi: mpc52xx: Add cancel_work_sync before module remove If we remove the module which will call mpc52xx_spi_remove it will free 'ms' through spi_unregister_controller. while the work ms->work will be used. The sequence of operations that may lead to a UAF bug. Fix it by ensuring that the work is canceled before proceeding with the cleanup in mpc52xx_spi_remove.
CVE-2024-50168: In the Linux kernel, the following vulnerability has been resolved: net/sun3_82586: fix potential memory leak in sun3_82586_send_packet() The sun3_82586_send_packet() returns NETDEV_TX_OK without freeing skb in case of skb->len being too long, add dev_kfree_skb() to fix it.
CVE-2024-53165: In the Linux kernel, the following vulnerability has been resolved: sh: intc: Fix use-after-free bug in register_intc_controller() In the error handling for this function, d is freed without ever removing it from intc_list which would lead to a use after free. To fix this, let's only add it to the list after everything has succeeded.
CVE-2024-56746: In the Linux kernel, the following vulnerability has been resolved: fbdev: sh7760fb: Fix a possible memory leak in sh7760fb_alloc_mem() When information such as info->screen_base is not ready, calling sh7760fb_free_mem() does not release memory correctly. Call dma_free_coherent() instead.
CVE-2024-56785: In the Linux kernel, the following vulnerability has been resolved: MIPS: Loongson64: DTS: Really fix PCIe port nodes for ls7a Fix the dtc warnings: arch/mips/boot/dts/loongson/ls7a-pch.dtsi:68.16-416.5: Warning (interrupt_provider): /bus@10000000/pci@1a000000: '#interrupt-cells' found, but node is not an interrupt provider arch/mips/boot/dts/loongson/ls7a-pch.dtsi:68.16-416.5: Warning (interrupt_provider): /bus@10000000/pci@1a000000: '#interrupt-cells' found, but node is not an interrupt provider arch/mips/boot/dts/loongson/loongson64g_4core_ls7a.dtb: Warning (interrupt_map): Failed prerequisite 'interrupt_provider' And a runtime warning introduced in commit 045b14ca5c36 ("of: WARN on deprecated #address-cells/#size-cells handling"): WARNING: CPU: 0 PID: 1 at drivers/of/base.c:106 of_bus_n_addr_cells+0x9c/0xe0 Missing '#address-cells' in /bus@10000000/pci@1a000000/pci_bridge@9,0 The fix is similar to commit d89a415ff8d5 ("MIPS: Loongson64: DTS: Fix PCIe port nodes for ls7a"), which has fixed the issue for ls2k (despite its subject mentions ls7a).
CVE-2024-57849: In the Linux kernel, the following vulnerability has been resolved: s390/cpum_sf: Handle CPU hotplug remove during sampling CPU hotplug remove handling triggers the following function call sequence: CPUHP_AP_PERF_S390_SF_ONLINE --> s390_pmu_sf_offline_cpu() ... CPUHP_AP_PERF_ONLINE --> perf_event_exit_cpu() The s390 CPUMF sampling CPU hotplug handler invokes: s390_pmu_sf_offline_cpu() +--> cpusf_pmu_setup() +--> setup_pmc_cpu() +--> deallocate_buffers() This function de-allocates all sampling data buffers (SDBs) allocated for that CPU at event initialization. It also clears the PMU_F_RESERVED bit. The CPU is gone and can not be sampled. With the event still being active on the removed CPU, the CPU event hotplug support in kernel performance subsystem triggers the following function calls on the removed CPU: perf_event_exit_cpu() +--> perf_event_exit_cpu_context() +--> __perf_event_exit_context() +--> __perf_remove_from_context() +--> event_sched_out() +--> cpumsf_pmu_del() +--> cpumsf_pmu_stop() +--> hw_perf_event_update() to stop and remove the event. During removal of the event, the sampling device driver tries to read out the remaining samples from the sample data buffers (SDBs). But they have already been freed (and may have been re-assigned). This may lead to a use after free situation in which case the samples are most likely invalid. In the best case the memory has not been reassigned and still contains valid data. Remedy this situation and check if the CPU is still in reserved state (bit PMU_F_RESERVED set). In this case the SDBs have not been released an contain valid data. This is always the case when the event is removed (and no CPU hotplug off occured). If the PMU_F_RESERVED bit is not set, the SDB buffers are gone.
CVE-2024-57939: In the Linux kernel, the following vulnerability has been resolved: riscv: Fix sleeping in invalid context in die() die() can be called in exception handler, and therefore cannot sleep. However, die() takes spinlock_t which can sleep with PREEMPT_RT enabled. That causes the following warning: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 285, name: mutex preempt_count: 110001, expected: 0 RCU nest depth: 0, expected: 0 CPU: 0 UID: 0 PID: 285 Comm: mutex Not tainted 6.12.0-rc7-00022-ge19049cf7d56-dirty #234 Hardware name: riscv-virtio,qemu (DT) Call Trace: dump_backtrace+0x1c/0x24 show_stack+0x2c/0x38 dump_stack_lvl+0x5a/0x72 dump_stack+0x14/0x1c __might_resched+0x130/0x13a rt_spin_lock+0x2a/0x5c die+0x24/0x112 do_trap_insn_illegal+0xa0/0xea _new_vmalloc_restore_context_a0+0xcc/0xd8 Oops - illegal instruction [#1] Switch to use raw_spinlock_t, which does not sleep even with PREEMPT_RT enabled.
CVE-2025-21866: In the Linux kernel, the following vulnerability has been resolved: powerpc/code-patching: Fix KASAN hit by not flagging text patching area as VM_ALLOC Erhard reported the following KASAN hit while booting his PowerMac G4 with a KASAN-enabled kernel 6.13-rc6: BUG: KASAN: vmalloc-out-of-bounds in copy_to_kernel_nofault+0xd8/0x1c8 Write of size 8 at addr f1000000 by task chronyd/1293 CPU: 0 UID: 123 PID: 1293 Comm: chronyd Tainted: G W 6.13.0-rc6-PMacG4 #2 Tainted: [W]=WARN Hardware name: PowerMac3,6 7455 0x80010303 PowerMac Call Trace: [c2437590] [c1631a84] dump_stack_lvl+0x70/0x8c (unreliable) [c24375b0] [c0504998] print_report+0xdc/0x504 [c2437610] [c050475c] kasan_report+0xf8/0x108 [c2437690] [c0505a3c] kasan_check_range+0x24/0x18c [c24376a0] [c03fb5e4] copy_to_kernel_nofault+0xd8/0x1c8 [c24376c0] [c004c014] patch_instructions+0x15c/0x16c [c2437710] [c00731a8] bpf_arch_text_copy+0x60/0x7c [c2437730] [c0281168] bpf_jit_binary_pack_finalize+0x50/0xac [c2437750] [c0073cf4] bpf_int_jit_compile+0xb30/0xdec [c2437880] [c0280394] bpf_prog_select_runtime+0x15c/0x478 [c24378d0] [c1263428] bpf_prepare_filter+0xbf8/0xc14 [c2437990] [c12677ec] bpf_prog_create_from_user+0x258/0x2b4 [c24379d0] [c027111c] do_seccomp+0x3dc/0x1890 [c2437ac0] [c001d8e0] system_call_exception+0x2dc/0x420 [c2437f30] [c00281ac] ret_from_syscall+0x0/0x2c --- interrupt: c00 at 0x5a1274 NIP: 005a1274 LR: 006a3b3c CTR: 005296c8 REGS: c2437f40 TRAP: 0c00 Tainted: G W (6.13.0-rc6-PMacG4) MSR: 0200f932 <VEC,EE,PR,FP,ME,IR,DR,RI> CR: 24004422 XER: 00000000 GPR00: 00000166 af8f3fa0 a7ee3540 00000001 00000000 013b6500 005a5858 0200f932 GPR08: 00000000 00001fe9 013d5fc8 005296c8 2822244c 00b2fcd8 00000000 af8f4b57 GPR16: 00000000 00000001 00000000 00000000 00000000 00000001 00000000 00000002 GPR24: 00afdbb0 00000000 00000000 00000000 006e0004 013ce060 006e7c1c 00000001 NIP [005a1274] 0x5a1274 LR [006a3b3c] 0x6a3b3c --- interrupt: c00 The buggy address belongs to the virtual mapping at [f1000000, f1002000) created by: text_area_cpu_up+0x20/0x190 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:00000000 index:0x0 pfn:0x76e30 flags: 0x80000000(zone=2) raw: 80000000 00000000 00000122 00000000 00000000 00000000 ffffffff 00000001 raw: 00000000 page dumped because: kasan: bad access detected Memory state around the buggy address: f0ffff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f0ffff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >f1000000: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ f1000080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f1000100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== f8 corresponds to KASAN_VMALLOC_INVALID which means the area is not initialised hence not supposed to be used yet. Powerpc text patching infrastructure allocates a virtual memory area using get_vm_area() and flags it as VM_ALLOC. But that flag is meant to be used for vmalloc() and vmalloc() allocated memory is not supposed to be used before a call to __vmalloc_node_range() which is never called for that area. That went undetected until commit e4137f08816b ("mm, kasan, kmsan: instrument copy_from/to_kernel_nofault") The area allocated by text_area_cpu_up() is not vmalloc memory, it is mapped directly on demand when needed by map_kernel_page(). There is no VM flag corresponding to such usage, so just pass no flag. That way the area will be unpoisonned and usable immediately.
CVE-2025-22071: In the Linux kernel, the following vulnerability has been resolved: spufs: fix a leak in spufs_create_context() Leak fixes back in 2008 missed one case - if we are trying to set affinity and spufs_mkdir() fails, we need to drop the reference to neighbor.
CVE-2025-22073: In the Linux kernel, the following vulnerability has been resolved: spufs: fix a leak on spufs_new_file() failure It's called from spufs_fill_dir(), and caller of that will do spufs_rmdir() in case of failure. That does remove everything we'd managed to create, but... the problem dentry is still negative. IOW, it needs to be explicitly dropped.
CVE-2025-37758: In the Linux kernel, the following vulnerability has been resolved: ata: pata_pxa: Fix potential NULL pointer dereference in pxa_ata_probe() devm_ioremap() returns NULL on error. Currently, pxa_ata_probe() does not check for this case, which can result in a NULL pointer dereference. Add NULL check after devm_ioremap() to prevent this issue.
CVE-2025-37991: In the Linux kernel, the following vulnerability has been resolved: parisc: Fix double SIGFPE crash Camm noticed that on parisc a SIGFPE exception will crash an application with a second SIGFPE in the signal handler. Dave analyzed it, and it happens because glibc uses a double-word floating-point store to atomically update function descriptors. As a result of lazy binding, we hit a floating-point store in fpe_func almost immediately. When the T bit is set, an assist exception trap occurs when when the co-processor encounters *any* floating-point instruction except for a double store of register %fr0. The latter cancels all pending traps. Let's fix this by clearing the Trap (T) bit in the FP status register before returning to the signal handler in userspace. The issue can be reproduced with this test program: root@parisc:~# cat fpe.c static void fpe_func(int sig, siginfo_t *i, void *v) { sigset_t set; sigemptyset(&set); sigaddset(&set, SIGFPE); sigprocmask(SIG_UNBLOCK, &set, NULL); printf("GOT signal %d with si_code %ld\n", sig, i->si_code); } int main() { struct sigaction action = { .sa_sigaction = fpe_func, .sa_flags = SA_RESTART|SA_SIGINFO }; sigaction(SIGFPE, &action, 0); feenableexcept(FE_OVERFLOW); return printf("%lf\n",1.7976931348623158E308*1.7976931348623158E308); } root@parisc:~# gcc fpe.c -lm root@parisc:~# ./a.out Floating point exception root@parisc:~# strace -f ./a.out execve("./a.out", ["./a.out"], 0xf9ac7034 /* 20 vars */) = 0 getrlimit(RLIMIT_STACK, {rlim_cur=8192*1024, rlim_max=RLIM_INFINITY}) = 0 ... rt_sigaction(SIGFPE, {sa_handler=0x1110a, sa_mask=[], sa_flags=SA_RESTART|SA_SIGINFO}, NULL, 8) = 0 --- SIGFPE {si_signo=SIGFPE, si_code=FPE_FLTOVF, si_addr=0x1078f} --- --- SIGFPE {si_signo=SIGFPE, si_code=FPE_FLTOVF, si_addr=0xf8f21237} --- +++ killed by SIGFPE +++ Floating point exception
CVE-2025-38576: In the Linux kernel, the following vulnerability has been resolved: powerpc/eeh: Make EEH driver device hotplug safe Multiple race conditions existed between the PCIe hotplug driver and the EEH driver, leading to a variety of kernel oopses of the same general nature: <pcie device unplug> <eeh driver trigger> <hotplug removal trigger> <pcie tree reconfiguration> <eeh recovery next step> <oops in EEH driver bus iteration loop> A second class of oops is also seen when the underlying bus disappears during device recovery. Refactor the EEH module to be PCI rescan and remove safe. Also clean up a few minor formatting / readability issues.
CVE-2025-38623: In the Linux kernel, the following vulnerability has been resolved: PCI: pnv_php: Fix surprise plug detection and recovery The existing PowerNV hotplug code did not handle surprise plug events correctly, leading to a complete failure of the hotplug system after device removal and a required reboot to detect new devices. This comes down to two issues: 1) When a device is surprise removed, often the bridge upstream port will cause a PE freeze on the PHB. If this freeze is not cleared, the MSI interrupts from the bridge hotplug notification logic will not be received by the kernel, stalling all plug events on all slots associated with the PE. 2) When a device is removed from a slot, regardless of surprise or programmatic removal, the associated PHB/PE ls left frozen. If this freeze is not cleared via a fundamental reset, skiboot is unable to clear the freeze and cannot retrain / rescan the slot. This also requires a reboot to clear the freeze and redetect the device in the slot. Issue the appropriate unfreeze and rescan commands on hotplug events, and don't oops on hotplug if pci_bus_to_OF_node() returns NULL. [bhelgaas: tidy comments]
CVE-2025-38624: In the Linux kernel, the following vulnerability has been resolved: PCI: pnv_php: Clean up allocated IRQs on unplug When the root of a nested PCIe bridge configuration is unplugged, the pnv_php driver leaked the allocated IRQ resources for the child bridges' hotplug event notifications, resulting in a panic. Fix this by walking all child buses and deallocating all its IRQ resources before calling pci_hp_remove_devices(). Also modify the lifetime of the workqueue at struct pnv_php_slot::wq so that it is only destroyed in pnv_php_free_slot(), instead of pnv_php_disable_irq(). This is required since pnv_php_disable_irq() will now be called by workers triggered by hot unplug interrupts, so the workqueue needs to stay allocated. The abridged kernel panic that occurs without this patch is as follows: WARNING: CPU: 0 PID: 687 at kernel/irq/msi.c:292 msi_device_data_release+0x6c/0x9c CPU: 0 UID: 0 PID: 687 Comm: bash Not tainted 6.14.0-rc5+ #2 Call Trace: msi_device_data_release+0x34/0x9c (unreliable) release_nodes+0x64/0x13c devres_release_all+0xc0/0x140 device_del+0x2d4/0x46c pci_destroy_dev+0x5c/0x194 pci_hp_remove_devices+0x90/0x128 pci_hp_remove_devices+0x44/0x128 pnv_php_disable_slot+0x54/0xd4 power_write_file+0xf8/0x18c pci_slot_attr_store+0x40/0x5c sysfs_kf_write+0x64/0x78 kernfs_fop_write_iter+0x1b0/0x290 vfs_write+0x3bc/0x50c ksys_write+0x84/0x140 system_call_exception+0x124/0x230 system_call_vectored_common+0x15c/0x2ec [bhelgaas: tidy comments]
CVE-2025-38630: In the Linux kernel, the following vulnerability has been resolved: fbdev: imxfb: Check fb_add_videomode to prevent null-ptr-deref fb_add_videomode() can fail with -ENOMEM when its internal kmalloc() cannot allocate a struct fb_modelist. If that happens, the modelist stays empty but the driver continues to register. Add a check for its return value to prevent poteintial null-ptr-deref, which is similar to the commit 17186f1f90d3 ("fbdev: Fix do_register_framebuffer to prevent null-ptr-deref in fb_videomode_to_var").
CVE-2025-38696: In the Linux kernel, the following vulnerability has been resolved: MIPS: Don't crash in stack_top() for tasks without ABI or vDSO Not all tasks have an ABI associated or vDSO mapped, for example kthreads never do. If such a task ever ends up calling stack_top(), it will derefence the NULL ABI pointer and crash. This can for example happen when using kunit: mips_stack_top+0x28/0xc0 arch_pick_mmap_layout+0x190/0x220 kunit_vm_mmap_init+0xf8/0x138 __kunit_add_resource+0x40/0xa8 kunit_vm_mmap+0x88/0xd8 usercopy_test_init+0xb8/0x240 kunit_try_run_case+0x5c/0x1a8 kunit_generic_run_threadfn_adapter+0x28/0x50 kthread+0x118/0x240 ret_from_kernel_thread+0x14/0x1c Only dereference the ABI point if it is set. The GIC page is also included as it is specific to the vDSO. Also move the randomization adjustment into the same conditional.
CVE-2025-40112: In the Linux kernel, the following vulnerability has been resolved: sparc: fix accurate exception reporting in copy_{from_to}_user for Niagara The referenced commit introduced exception handlers on user-space memory references in copy_from_user and copy_to_user. These handlers return from the respective function and calculate the remaining bytes left to copy using the current register contents. This commit fixes a couple of bad calculations and a broken epilogue in the exception handlers. This will prevent crashes and ensure correct return values of copy_from_user and copy_to_user in the faulting case. The behaviour of memcpy stays unchanged.
CVE-2025-40124: In the Linux kernel, the following vulnerability has been resolved: sparc: fix accurate exception reporting in copy_{from_to}_user for UltraSPARC III Anthony Yznaga tracked down that a BUG_ON in ext4 code with large folios enabled resulted from copy_from_user() returning impossibly large values greater than the size to be copied. This lead to __copy_from_iter() returning impossible values instead of the actual number of bytes it was able to copy. The BUG_ON has been reported in https://lore.kernel.org/r/b14f55642207e63e907965e209f6323a0df6dcee.camel@physik.fu-berlin.de The referenced commit introduced exception handlers on user-space memory references in copy_from_user and copy_to_user. These handlers return from the respective function and calculate the remaining bytes left to copy using the current register contents. The exception handlers expect that %o2 has already been masked during the bulk copy loop, but the masking was performed after that loop. This will fix the return value of copy_from_user and copy_to_user in the faulting case. The behaviour of memcpy stays unchanged.
CVE-2025-40126: In the Linux kernel, the following vulnerability has been resolved: sparc: fix accurate exception reporting in copy_{from_to}_user for UltraSPARC The referenced commit introduced exception handlers on user-space memory references in copy_from_user and copy_to_user. These handlers return from the respective function and calculate the remaining bytes left to copy using the current register contents. This commit fixes a couple of bad calculations. This will fix the return value of copy_from_user and copy_to_user in the faulting case. The behaviour of memcpy stays unchanged.
CVE-2025-40253: In the Linux kernel, the following vulnerability has been resolved: s390/ctcm: Fix double-kfree The function 'mpc_rcvd_sweep_req(mpcginfo)' is called conditionally from function 'ctcmpc_unpack_skb'. It frees passed mpcginfo. After that a call to function 'kfree' in function 'ctcmpc_unpack_skb' frees it again. Remove 'kfree' call in function 'mpc_rcvd_sweep_req(mpcginfo)'. Bug detected by the clang static analyzer.
CVE-2025-71188: In the Linux kernel, the following vulnerability has been resolved: dmaengine: lpc18xx-dmamux: fix device leak on route allocation Make sure to drop the reference taken when looking up the DMA mux platform device during route allocation. Note that holding a reference to a device does not prevent its driver data from going away so there is no point in keeping the reference.

Created: 2022-07-04 Last update: 2026-04-26 05:02

966 security issues in bookworm high

There are 966 open security issues in bookworm.

957 important issues:

CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2023-0597: A flaw possibility of memory leak in the Linux kernel cpu_entry_area mapping of X86 CPU data to memory was found in the way user can guess location of exception stack(s) or other important data. A local user could use this flaw to get access to some important data with expected location in memory.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-4133: A use-after-free vulnerability was found in the cxgb4 driver in the Linux kernel. The bug occurs when the cxgb4 device is detaching due to a possible rearming of the flower_stats_timer from the work queue. This flaw allows a local user to crash the system, causing a denial of service condition.
CVE-2023-6039: A use-after-free flaw was found in lan78xx_disconnect in drivers/net/usb/lan78xx.c in the network sub-component, net/usb/lan78xx in the Linux Kernel. This flaw allows a local attacker to crash the system when the LAN78XX USB device detaches.
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2023-21264: In multiple functions of mem_protect.c, there is a possible way to access hypervisor memory due to a memory access check in the wrong place. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.
CVE-2023-23005: In the Linux kernel before 6.2, mm/memory-tiers.c misinterprets the alloc_memory_type return value (expects it to be NULL in the error case, whereas it is actually an error pointer). NOTE: this is disputed by third parties because there are no realistic cases in which a user can cause the alloc_memory_type error case to be reached.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2023-52452: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix accesses to uninit stack slots Privileged programs are supposed to be able to read uninitialized stack memory (ever since 6715df8d5) but, before this patch, these accesses were permitted inconsistently. In particular, accesses were permitted above state->allocated_stack, but not below it. In other words, if the stack was already "large enough", the access was permitted, but otherwise the access was rejected instead of being allowed to "grow the stack". This undesired rejection was happening in two places: - in check_stack_slot_within_bounds() - in check_stack_range_initialized() This patch arranges for these accesses to be permitted. A bunch of tests that were relying on the old rejection had to change; all of them were changed to add also run unprivileged, in which case the old behavior persists. One tests couldn't be updated - global_func16 - because it can't run unprivileged for other reasons. This patch also fixes the tracking of the stack size for variable-offset reads. This second fix is bundled in the same commit as the first one because they're inter-related. Before this patch, writes to the stack using registers containing a variable offset (as opposed to registers with fixed, known values) were not properly contributing to the function's needed stack size. As a result, it was possible for a program to verify, but then to attempt to read out-of-bounds data at runtime because a too small stack had been allocated for it. Each function tracks the size of the stack it needs in bpf_subprog_info.stack_depth, which is maintained by update_stack_depth(). For regular memory accesses, check_mem_access() was calling update_state_depth() but it was passing in only the fixed part of the offset register, ignoring the variable offset. This was incorrect; the minimum possible value of that register should be used instead. This tracking is now fixed by centralizing the tracking of stack size in grow_stack_state(), and by lifting the calls to grow_stack_state() to check_stack_access_within_bounds() as suggested by Andrii. The code is now simpler and more convincingly tracks the correct maximum stack size. check_stack_range_initialized() can now rely on enough stack having been allocated for the access; this helps with the fix for the first issue. A few tests were changed to also check the stack depth computation. The one that fails without this patch is verifier_var_off:stack_write_priv_vs_unpriv.
CVE-2023-52485: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before sending a command [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] For functions that execute within a DC context or DC lock we can wrap the direct calls to dm_execute_dmub_cmd/list with code that exits idle power optimizations and reallows once we're done with the command submission on success. For DM direct submissions the DM will need to manage the enter/exit sequencing manually. We cannot invoke a DMCUB command directly within the DM execution helper or we can deadlock.
CVE-2023-52586: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: Add mutex lock in control vblank irq Add a mutex lock to control vblank irq to synchronize vblank enable/disable operations happening from different threads to prevent race conditions while registering/unregistering the vblank irq callback. v4: -Removed vblank_ctl_lock from dpu_encoder_virt, so it is only a parameter of dpu_encoder_phys. -Switch from atomic refcnt to a simple int counter as mutex has now been added v3: Mistakenly did not change wording in last version. It is done now. v2: Slightly changed wording of commit message Patchwork: https://patchwork.freedesktop.org/patch/571854/
CVE-2023-52590: In the Linux kernel, the following vulnerability has been resolved: ocfs2: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change ocfs2 rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52591: In the Linux kernel, the following vulnerability has been resolved: reiserfs: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change reiserfs rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52624: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before executing GPINT commands [Why] DMCUB can be in idle when we attempt to interface with the HW through the GPINT mailbox resulting in a system hang. [How] Add dc_wake_and_execute_gpint() to wrap the wake, execute, sleep sequence. If the GPINT executes successfully then DMCUB will be put back into sleep after the optional response is returned. It functions similar to the inbox command interface.
CVE-2023-52625: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Refactor DMCUB enter/exit idle interface [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] We need to exit out of the idle state prior to sending a command, but the process that performs the exit also invokes a command itself. Fixing this issue involves the following: 1. Using a software state to track whether or not we need to start the process to exit idle or notify idle. It's possible for the hardware to have exited an idle state without driver knowledge, but entering one is always restricted to a driver allow - which makes the SW state vs HW state mismatch issue purely one of optimization, which should seldomly be hit, if at all. 2. Refactor any instances of exit/notify idle to use a single wrapper that maintains this SW state. This works simialr to dc_allow_idle_optimizations, but works at the DMCUB level and makes sure the state is marked prior to any notify/exit idle so we don't enter an infinite loop. 3. Make sure we exit out of idle prior to sending any commands or waiting for DMCUB idle. This patch takes care of 1/2. A future patch will take care of wrapping DMCUB command submission with calls to this new interface.
CVE-2023-52629: In the Linux kernel, the following vulnerability has been resolved: sh: push-switch: Reorder cleanup operations to avoid use-after-free bug The original code puts flush_work() before timer_shutdown_sync() in switch_drv_remove(). Although we use flush_work() to stop the worker, it could be rescheduled in switch_timer(). As a result, a use-after-free bug can occur. The details are shown below: (cpu 0) | (cpu 1) switch_drv_remove() | flush_work() | ... | switch_timer // timer | schedule_work(&psw->work) timer_shutdown_sync() | ... | switch_work_handler // worker kfree(psw) // free | | psw->state = 0 // use This patch puts timer_shutdown_sync() before flush_work() to mitigate the bugs. As a result, the worker and timer will be stopped safely before the deallocate operations.
CVE-2023-52648: In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Unmap the surface before resetting it on a plane state Switch to a new plane state requires unreferencing of all held surfaces. In the work required for mob cursors the mapped surfaces started being cached but the variable indicating whether the surface is currently mapped was not being reset. This leads to crashes as the duplicated state, incorrectly, indicates the that surface is mapped even when no surface is present. That's because after unreferencing the surface it's perfectly possible for the plane to be backed by a bo instead of a surface. Reset the surface mapped flag when unreferencing the plane state surface to fix null derefs in cleanup. Fixes crashes in KDE KWin 6.0 on Wayland: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 4 PID: 2533 Comm: kwin_wayland Not tainted 6.7.0-rc3-vmwgfx #2 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 RIP: 0010:vmw_du_cursor_plane_cleanup_fb+0x124/0x140 [vmwgfx] Code: 00 00 00 75 3a 48 83 c4 10 5b 5d c3 cc cc cc cc 48 8b b3 a8 00 00 00 48 c7 c7 99 90 43 c0 e8 93 c5 db ca 48 8b 83 a8 00 00 00 <48> 8b 78 28 e8 e3 f> RSP: 0018:ffffb6b98216fa80 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff969d84cdcb00 RCX: 0000000000000027 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff969e75f21600 RBP: ffff969d4143dc50 R08: 0000000000000000 R09: ffffb6b98216f920 R10: 0000000000000003 R11: ffff969e7feb3b10 R12: 0000000000000000 R13: 0000000000000000 R14: 000000000000027b R15: ffff969d49c9fc00 FS: 00007f1e8f1b4180(0000) GS:ffff969e75f00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000028 CR3: 0000000104006004 CR4: 00000000003706f0 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? exc_page_fault+0x7f/0x180 ? asm_exc_page_fault+0x26/0x30 ? vmw_du_cursor_plane_cleanup_fb+0x124/0x140 [vmwgfx] drm_atomic_helper_cleanup_planes+0x9b/0xc0 commit_tail+0xd1/0x130 drm_atomic_helper_commit+0x11a/0x140 drm_atomic_commit+0x97/0xd0 ? __pfx___drm_printfn_info+0x10/0x10 drm_atomic_helper_update_plane+0xf5/0x160 drm_mode_cursor_universal+0x10e/0x270 drm_mode_cursor_common+0x102/0x230 ? __pfx_drm_mode_cursor2_ioctl+0x10/0x10 drm_ioctl_kernel+0xb2/0x110 drm_ioctl+0x26d/0x4b0 ? __pfx_drm_mode_cursor2_ioctl+0x10/0x10 ? __pfx_drm_ioctl+0x10/0x10 vmw_generic_ioctl+0xa4/0x110 [vmwgfx] __x64_sys_ioctl+0x94/0xd0 do_syscall_64+0x61/0xe0 ? __x64_sys_ioctl+0xaf/0xd0 ? syscall_exit_to_user_mode+0x2b/0x40 ? do_syscall_64+0x70/0xe0 ? __x64_sys_ioctl+0xaf/0xd0 ? syscall_exit_to_user_mode+0x2b/0x40 ? do_syscall_64+0x70/0xe0 ? exc_page_fault+0x7f/0x180 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7f1e93f279ed Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff f> RSP: 002b:00007ffca0faf600 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 000055db876ed2c0 RCX: 00007f1e93f279ed RDX: 00007ffca0faf6c0 RSI: 00000000c02464bb RDI: 0000000000000015 RBP: 00007ffca0faf650 R08: 000055db87184010 R09: 0000000000000007 R10: 000055db886471a0 R11: 0000000000000246 R12: 00007ffca0faf6c0 R13: 00000000c02464bb R14: 0000000000000015 R15: 00007ffca0faf790 </TASK> Modules linked in: snd_seq_dummy snd_hrtimer nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_ine> CR2: 0000000000000028 ---[ end trace 0000000000000000 ]--- RIP: 0010:vmw_du_cursor_plane_cleanup_fb+0x124/0x140 [vmwgfx] Code: 00 00 00 75 3a 48 83 c4 10 5b 5d c3 cc cc cc cc 48 8b b3 a8 00 00 00 48 c7 c7 99 90 43 c0 e8 93 c5 db ca 48 8b 83 a8 00 00 00 <48> 8b 78 28 e8 e3 f> RSP: 0018:ffffb6b98216fa80 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff969d84cdcb00 RCX: 0000000000000027 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff969e75f21600 RBP: ffff969d4143 ---truncated---
CVE-2023-52653: In the Linux kernel, the following vulnerability has been resolved: SUNRPC: fix a memleak in gss_import_v2_context The ctx->mech_used.data allocated by kmemdup is not freed in neither gss_import_v2_context nor it only caller gss_krb5_import_sec_context, which frees ctx on error. Thus, this patch reform the last call of gss_import_v2_context to the gss_krb5_import_ctx_v2, preventing the memleak while keepping the return formation.
CVE-2023-52671: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix hang/underflow when transitioning to ODM4:1 [Why] Under some circumstances, disabling an OPTC and attempting to reclaim its OPP(s) for a different OPTC could cause a hang/underflow due to OPPs not being properly disconnected from the disabled OPTC. [How] Ensure that all OPPs are unassigned from an OPTC when it gets disabled.
CVE-2023-52676: In the Linux kernel, the following vulnerability has been resolved: bpf: Guard stack limits against 32bit overflow This patch promotes the arithmetic around checking stack bounds to be done in the 64-bit domain, instead of the current 32bit. The arithmetic implies adding together a 64-bit register with a int offset. The register was checked to be below 1<<29 when it was variable, but not when it was fixed. The offset either comes from an instruction (in which case it is 16 bit), from another register (in which case the caller checked it to be below 1<<29 [1]), or from the size of an argument to a kfunc (in which case it can be a u32 [2]). Between the register being inconsistently checked to be below 1<<29, and the offset being up to an u32, it appears that we were open to overflowing the `int`s which were currently used for arithmetic. [1] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L7494-L7498 [2] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L11904
CVE-2023-52751: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free in smb2_query_info_compound() The following UAF was triggered when running fstests generic/072 with KASAN enabled against Windows Server 2022 and mount options 'multichannel,max_channels=2,vers=3.1.1,mfsymlinks,noperm' BUG: KASAN: slab-use-after-free in smb2_query_info_compound+0x423/0x6d0 [cifs] Read of size 8 at addr ffff888014941048 by task xfs_io/27534 CPU: 0 PID: 27534 Comm: xfs_io Not tainted 6.6.0-rc7 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 Call Trace: dump_stack_lvl+0x4a/0x80 print_report+0xcf/0x650 ? srso_alias_return_thunk+0x5/0x7f ? srso_alias_return_thunk+0x5/0x7f ? __phys_addr+0x46/0x90 kasan_report+0xda/0x110 ? smb2_query_info_compound+0x423/0x6d0 [cifs] ? smb2_query_info_compound+0x423/0x6d0 [cifs] smb2_query_info_compound+0x423/0x6d0 [cifs] ? __pfx_smb2_query_info_compound+0x10/0x10 [cifs] ? srso_alias_return_thunk+0x5/0x7f ? __stack_depot_save+0x39/0x480 ? kasan_save_stack+0x33/0x60 ? kasan_set_track+0x25/0x30 ? ____kasan_slab_free+0x126/0x170 smb2_queryfs+0xc2/0x2c0 [cifs] ? __pfx_smb2_queryfs+0x10/0x10 [cifs] ? __pfx___lock_acquire+0x10/0x10 smb311_queryfs+0x210/0x220 [cifs] ? __pfx_smb311_queryfs+0x10/0x10 [cifs] ? srso_alias_return_thunk+0x5/0x7f ? __lock_acquire+0x480/0x26c0 ? lock_release+0x1ed/0x640 ? srso_alias_return_thunk+0x5/0x7f ? do_raw_spin_unlock+0x9b/0x100 cifs_statfs+0x18c/0x4b0 [cifs] statfs_by_dentry+0x9b/0xf0 fd_statfs+0x4e/0xb0 __do_sys_fstatfs+0x7f/0xe0 ? __pfx___do_sys_fstatfs+0x10/0x10 ? srso_alias_return_thunk+0x5/0x7f ? lockdep_hardirqs_on_prepare+0x136/0x200 ? srso_alias_return_thunk+0x5/0x7f do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 27534: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 __kasan_kmalloc+0x8f/0xa0 open_cached_dir+0x71b/0x1240 [cifs] smb2_query_info_compound+0x5c3/0x6d0 [cifs] smb2_queryfs+0xc2/0x2c0 [cifs] smb311_queryfs+0x210/0x220 [cifs] cifs_statfs+0x18c/0x4b0 [cifs] statfs_by_dentry+0x9b/0xf0 fd_statfs+0x4e/0xb0 __do_sys_fstatfs+0x7f/0xe0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 27534: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2b/0x50 ____kasan_slab_free+0x126/0x170 slab_free_freelist_hook+0xd0/0x1e0 __kmem_cache_free+0x9d/0x1b0 open_cached_dir+0xff5/0x1240 [cifs] smb2_query_info_compound+0x5c3/0x6d0 [cifs] smb2_queryfs+0xc2/0x2c0 [cifs] This is a race between open_cached_dir() and cached_dir_lease_break() where the cache entry for the open directory handle receives a lease break while creating it. And before returning from open_cached_dir(), we put the last reference of the new @cfid because of !@cfid->has_lease. Besides the UAF, while running xfstests a lot of missed lease breaks have been noticed in tests that run several concurrent statfs(2) calls on those cached fids CIFS: VFS: \\w22-root1.gandalf.test No task to wake, unknown frame... CIFS: VFS: \\w22-root1.gandalf.test Cmd: 18 Err: 0x0 Flags: 0x1... CIFS: VFS: \\w22-root1.gandalf.test smb buf 00000000715bfe83 len 108 CIFS: VFS: Dump pending requests: CIFS: VFS: \\w22-root1.gandalf.test No task to wake, unknown frame... CIFS: VFS: \\w22-root1.gandalf.test Cmd: 18 Err: 0x0 Flags: 0x1... CIFS: VFS: \\w22-root1.gandalf.test smb buf 000000005aa7316e len 108 ... To fix both, in open_cached_dir() ensure that @cfid->has_lease is set right before sending out compounded request so that any potential lease break will be get processed by demultiplex thread while we're still caching @cfid. And, if open failed for some reason, re-check @cfid->has_lease to decide whether or not put lease reference.
CVE-2023-52761: In the Linux kernel, the following vulnerability has been resolved: riscv: VMAP_STACK overflow detection thread-safe commit 31da94c25aea ("riscv: add VMAP_STACK overflow detection") added support for CONFIG_VMAP_STACK. If overflow is detected, CPU switches to `shadow_stack` temporarily before switching finally to per-cpu `overflow_stack`. If two CPUs/harts are racing and end up in over flowing kernel stack, one or both will end up corrupting each other state because `shadow_stack` is not per-cpu. This patch optimizes per-cpu overflow stack switch by directly picking per-cpu `overflow_stack` and gets rid of `shadow_stack`. Following are the changes in this patch - Defines an asm macro to obtain per-cpu symbols in destination register. - In entry.S, when overflow is detected, per-cpu overflow stack is located using per-cpu asm macro. Computing per-cpu symbol requires a temporary register. x31 is saved away into CSR_SCRATCH (CSR_SCRATCH is anyways zero since we're in kernel). Please see Links for additional relevant disccussion and alternative solution. Tested by `echo EXHAUST_STACK > /sys/kernel/debug/provoke-crash/DIRECT` Kernel crash log below Insufficient stack space to handle exception!/debug/provoke-crash/DIRECT Task stack: [0xff20000010a98000..0xff20000010a9c000] Overflow stack: [0xff600001f7d98370..0xff600001f7d99370] CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) epc : __memset+0x60/0xfc ra : recursive_loop+0x48/0xc6 [lkdtm] epc : ffffffff808de0e4 ra : ffffffff0163a752 sp : ff20000010a97e80 gp : ffffffff815c0330 tp : ff600000820ea280 t0 : ff20000010a97e88 t1 : 000000000000002e t2 : 3233206874706564 s0 : ff20000010a982b0 s1 : 0000000000000012 a0 : ff20000010a97e88 a1 : 0000000000000000 a2 : 0000000000000400 a3 : ff20000010a98288 a4 : 0000000000000000 a5 : 0000000000000000 a6 : fffffffffffe43f0 a7 : 00007fffffffffff s2 : ff20000010a97e88 s3 : ffffffff01644680 s4 : ff20000010a9be90 s5 : ff600000842ba6c0 s6 : 00aaaaaac29e42b0 s7 : 00fffffff0aa3684 s8 : 00aaaaaac2978040 s9 : 0000000000000065 s10: 00ffffff8a7cad10 s11: 00ffffff8a76a4e0 t3 : ffffffff815dbaf4 t4 : ffffffff815dbaf4 t5 : ffffffff815dbab8 t6 : ff20000010a9bb48 status: 0000000200000120 badaddr: ff20000010a97e88 cause: 000000000000000f Kernel panic - not syncing: Kernel stack overflow CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006754>] dump_backtrace+0x30/0x38 [<ffffffff808de798>] show_stack+0x40/0x4c [<ffffffff808ea2a8>] dump_stack_lvl+0x44/0x5c [<ffffffff808ea2d8>] dump_stack+0x18/0x20 [<ffffffff808dec06>] panic+0x126/0x2fe [<ffffffff800065ea>] walk_stackframe+0x0/0xf0 [<ffffffff0163a752>] recursive_loop+0x48/0xc6 [lkdtm] SMP: stopping secondary CPUs ---[ end Kernel panic - not syncing: Kernel stack overflow ]---
CVE-2023-52770: In the Linux kernel, the following vulnerability has been resolved: f2fs: split initial and dynamic conditions for extent_cache Let's allocate the extent_cache tree without dynamic conditions to avoid a missing condition causing a panic as below. # create a file w/ a compressed flag # disable the compression # panic while updating extent_cache F2FS-fs (dm-64): Swapfile: last extent is not aligned to section F2FS-fs (dm-64): Swapfile (3) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(2097152 * N) Adding 124996k swap on ./swap-file. Priority:0 extents:2 across:17179494468k ================================================================== BUG: KASAN: null-ptr-deref in instrument_atomic_read_write out/common/include/linux/instrumented.h:101 [inline] BUG: KASAN: null-ptr-deref in atomic_try_cmpxchg_acquire out/common/include/asm-generic/atomic-instrumented.h:705 [inline] BUG: KASAN: null-ptr-deref in queued_write_lock out/common/include/asm-generic/qrwlock.h:92 [inline] BUG: KASAN: null-ptr-deref in __raw_write_lock out/common/include/linux/rwlock_api_smp.h:211 [inline] BUG: KASAN: null-ptr-deref in _raw_write_lock+0x5a/0x110 out/common/kernel/locking/spinlock.c:295 Write of size 4 at addr 0000000000000030 by task syz-executor154/3327 CPU: 0 PID: 3327 Comm: syz-executor154 Tainted: G O 5.10.185 #1 Hardware name: emulation qemu-x86/qemu-x86, BIOS 2023.01-21885-gb3cc1cd24d 01/01/2023 Call Trace: __dump_stack out/common/lib/dump_stack.c:77 [inline] dump_stack_lvl+0x17e/0x1c4 out/common/lib/dump_stack.c:118 __kasan_report+0x16c/0x260 out/common/mm/kasan/report.c:415 kasan_report+0x51/0x70 out/common/mm/kasan/report.c:428 kasan_check_range+0x2f3/0x340 out/common/mm/kasan/generic.c:186 __kasan_check_write+0x14/0x20 out/common/mm/kasan/shadow.c:37 instrument_atomic_read_write out/common/include/linux/instrumented.h:101 [inline] atomic_try_cmpxchg_acquire out/common/include/asm-generic/atomic-instrumented.h:705 [inline] queued_write_lock out/common/include/asm-generic/qrwlock.h:92 [inline] __raw_write_lock out/common/include/linux/rwlock_api_smp.h:211 [inline] _raw_write_lock+0x5a/0x110 out/common/kernel/locking/spinlock.c:295 __drop_extent_tree+0xdf/0x2f0 out/common/fs/f2fs/extent_cache.c:1155 f2fs_drop_extent_tree+0x17/0x30 out/common/fs/f2fs/extent_cache.c:1172 f2fs_insert_range out/common/fs/f2fs/file.c:1600 [inline] f2fs_fallocate+0x19fd/0x1f40 out/common/fs/f2fs/file.c:1764 vfs_fallocate+0x514/0x9b0 out/common/fs/open.c:310 ksys_fallocate out/common/fs/open.c:333 [inline] __do_sys_fallocate out/common/fs/open.c:341 [inline] __se_sys_fallocate out/common/fs/open.c:339 [inline] __x64_sys_fallocate+0xb8/0x100 out/common/fs/open.c:339 do_syscall_64+0x35/0x50 out/common/arch/x86/entry/common.c:46
CVE-2023-52771: In the Linux kernel, the following vulnerability has been resolved: cxl/port: Fix delete_endpoint() vs parent unregistration race The CXL subsystem, at cxl_mem ->probe() time, establishes a lineage of ports (struct cxl_port objects) between an endpoint and the root of a CXL topology. Each port including the endpoint port is attached to the cxl_port driver. Given that setup, it follows that when either any port in that lineage goes through a cxl_port ->remove() event, or the memdev goes through a cxl_mem ->remove() event. The hierarchy below the removed port, or the entire hierarchy if the memdev is removed needs to come down. The delete_endpoint() callback is careful to check whether it is being called to tear down the hierarchy, or if it is only being called to teardown the memdev because an ancestor port is going through ->remove(). That care needs to take the device_lock() of the endpoint's parent. Which requires 2 bugs to be fixed: 1/ A reference on the parent is needed to prevent use-after-free scenarios like this signature: BUG: spinlock bad magic on CPU#0, kworker/u56:0/11 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20230524-3.fc38 05/24/2023 Workqueue: cxl_port detach_memdev [cxl_core] RIP: 0010:spin_bug+0x65/0xa0 Call Trace: do_raw_spin_lock+0x69/0xa0 __mutex_lock+0x695/0xb80 delete_endpoint+0xad/0x150 [cxl_core] devres_release_all+0xb8/0x110 device_unbind_cleanup+0xe/0x70 device_release_driver_internal+0x1d2/0x210 detach_memdev+0x15/0x20 [cxl_core] process_one_work+0x1e3/0x4c0 worker_thread+0x1dd/0x3d0 2/ In the case of RCH topologies, the parent device that needs to be locked is not always @port->dev as returned by cxl_mem_find_port(), use endpoint->dev.parent instead.
CVE-2023-52797: In the Linux kernel, the following vulnerability has been resolved: drivers: perf: Check find_first_bit() return value We must check the return value of find_first_bit() before using the return value as an index array since it happens to overflow the array and then panic: [ 107.318430] Kernel BUG [#1] [ 107.319434] CPU: 3 PID: 1238 Comm: kill Tainted: G E 6.6.0-rc6ubuntu-defconfig #2 [ 107.319465] Hardware name: riscv-virtio,qemu (DT) [ 107.319551] epc : pmu_sbi_ovf_handler+0x3a4/0x3ae [ 107.319840] ra : pmu_sbi_ovf_handler+0x52/0x3ae [ 107.319868] epc : ffffffff80a0a77c ra : ffffffff80a0a42a sp : ffffaf83fecda350 [ 107.319884] gp : ffffffff823961a8 tp : ffffaf8083db1dc0 t0 : ffffaf83fecda480 [ 107.319899] t1 : ffffffff80cafe62 t2 : 000000000000ff00 s0 : ffffaf83fecda520 [ 107.319921] s1 : ffffaf83fecda380 a0 : 00000018fca29df0 a1 : ffffffffffffffff [ 107.319936] a2 : 0000000001073734 a3 : 0000000000000004 a4 : 0000000000000000 [ 107.319951] a5 : 0000000000000040 a6 : 000000001d1c8774 a7 : 0000000000504d55 [ 107.319965] s2 : ffffffff82451f10 s3 : ffffffff82724e70 s4 : 000000000000003f [ 107.319980] s5 : 0000000000000011 s6 : ffffaf8083db27c0 s7 : 0000000000000000 [ 107.319995] s8 : 0000000000000001 s9 : 00007fffb45d6558 s10: 00007fffb45d81a0 [ 107.320009] s11: ffffaf7ffff60000 t3 : 0000000000000004 t4 : 0000000000000000 [ 107.320023] t5 : ffffaf7f80000000 t6 : ffffaf8000000000 [ 107.320037] status: 0000000200000100 badaddr: 0000000000000000 cause: 0000000000000003 [ 107.320081] [<ffffffff80a0a77c>] pmu_sbi_ovf_handler+0x3a4/0x3ae [ 107.320112] [<ffffffff800b42d0>] handle_percpu_devid_irq+0x9e/0x1a0 [ 107.320131] [<ffffffff800ad92c>] generic_handle_domain_irq+0x28/0x36 [ 107.320148] [<ffffffff8065f9f8>] riscv_intc_irq+0x36/0x4e [ 107.320166] [<ffffffff80caf4a0>] handle_riscv_irq+0x54/0x86 [ 107.320189] [<ffffffff80cb0036>] do_irq+0x64/0x96 [ 107.320271] Code: 85a6 855e b097 ff7f 80e7 9220 b709 9002 4501 bbd9 (9002) 6097 [ 107.320585] ---[ end trace 0000000000000000 ]--- [ 107.320704] Kernel panic - not syncing: Fatal exception in interrupt [ 107.320775] SMP: stopping secondary CPUs [ 107.321219] Kernel Offset: 0x0 from 0xffffffff80000000 [ 107.333051] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---
CVE-2023-52888: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: Only free buffer VA that is not NULL In the MediaTek vcodec driver, while mtk_vcodec_mem_free() is mostly called only when the buffer to free exists, there are some instances that didn't do the check and triggered warnings in practice. We believe those checks were forgotten unintentionally. Add the checks back to fix the warnings.
CVE-2023-52920: In the Linux kernel, the following vulnerability has been resolved: bpf: support non-r10 register spill/fill to/from stack in precision tracking Use instruction (jump) history to record instructions that performed register spill/fill to/from stack, regardless if this was done through read-only r10 register, or any other register after copying r10 into it *and* potentially adjusting offset. To make this work reliably, we push extra per-instruction flags into instruction history, encoding stack slot index (spi) and stack frame number in extra 10 bit flags we take away from prev_idx in instruction history. We don't touch idx field for maximum performance, as it's checked most frequently during backtracking. This change removes basically the last remaining practical limitation of precision backtracking logic in BPF verifier. It fixes known deficiencies, but also opens up new opportunities to reduce number of verified states, explored in the subsequent patches. There are only three differences in selftests' BPF object files according to veristat, all in the positive direction (less states). File Program Insns (A) Insns (B) Insns (DIFF) States (A) States (B) States (DIFF) -------------------------------------- ------------- --------- --------- ------------- ---------- ---------- ------------- test_cls_redirect_dynptr.bpf.linked3.o cls_redirect 2987 2864 -123 (-4.12%) 240 231 -9 (-3.75%) xdp_synproxy_kern.bpf.linked3.o syncookie_tc 82848 82661 -187 (-0.23%) 5107 5073 -34 (-0.67%) xdp_synproxy_kern.bpf.linked3.o syncookie_xdp 85116 84964 -152 (-0.18%) 5162 5130 -32 (-0.62%) Note, I avoided renaming jmp_history to more generic insn_hist to minimize number of lines changed and potential merge conflicts between bpf and bpf-next trees. Notice also cur_hist_entry pointer reset to NULL at the beginning of instruction verification loop. This pointer avoids the problem of relying on last jump history entry's insn_idx to determine whether we already have entry for current instruction or not. It can happen that we added jump history entry because current instruction is_jmp_point(), but also we need to add instruction flags for stack access. In this case, we don't want to entries, so we need to reuse last added entry, if it is present. Relying on insn_idx comparison has the same ambiguity problem as the one that was fixed recently in [0], so we avoid that. [0] https://patchwork.kernel.org/project/netdevbpf/patch/20231110002638.4168352-3-andrii@kernel.org/
CVE-2023-53149: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid deadlock in fs reclaim with page writeback Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock.
CVE-2023-53218: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Make it so that a waiting process can be aborted When sendmsg() creates an rxrpc call, it queues it to wait for a connection and channel to be assigned and then waits before it can start shovelling data as the encrypted DATA packet content includes a summary of the connection parameters. However, sendmsg() may get interrupted before a connection gets assigned and further sendmsg() calls will fail with EBUSY until an assignment is made. Fix this so that the call can at least be aborted without failing on EBUSY. We have to be careful here as sendmsg() mustn't be allowed to start the call timer if the call doesn't yet have a connection assigned as an oops may follow shortly thereafter.
CVE-2023-53231: In the Linux kernel, the following vulnerability has been resolved: erofs: Fix detection of atomic context Current check for atomic context is not sufficient as z_erofs_decompressqueue_endio can be called under rcu lock from blk_mq_flush_plug_list(). See the stacktrace [1] In such case we should hand off the decompression work for async processing rather than trying to do sync decompression in current context. Patch fixes the detection by checking for rcu_read_lock_any_held() and while at it use more appropriate !in_task() check than in_atomic(). Background: Historically erofs would always schedule a kworker for decompression which would incur the scheduling cost regardless of the context. But z_erofs_decompressqueue_endio() may not always be in atomic context and we could actually benefit from doing the decompression in z_erofs_decompressqueue_endio() if we are in thread context, for example when running with dm-verity. This optimization was later added in patch [2] which has shown improvement in performance benchmarks. ============================================== [1] Problem stacktrace [name:core&]BUG: sleeping function called from invalid context at kernel/locking/mutex.c:291 [name:core&]in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1615, name: CpuMonitorServi [name:core&]preempt_count: 0, expected: 0 [name:core&]RCU nest depth: 1, expected: 0 CPU: 7 PID: 1615 Comm: CpuMonitorServi Tainted: G S W OE 6.1.25-android14-5-maybe-dirty-mainline #1 Hardware name: MT6897 (DT) Call trace: dump_backtrace+0x108/0x15c show_stack+0x20/0x30 dump_stack_lvl+0x6c/0x8c dump_stack+0x20/0x48 __might_resched+0x1fc/0x308 __might_sleep+0x50/0x88 mutex_lock+0x2c/0x110 z_erofs_decompress_queue+0x11c/0xc10 z_erofs_decompress_kickoff+0x110/0x1a4 z_erofs_decompressqueue_endio+0x154/0x180 bio_endio+0x1b0/0x1d8 __dm_io_complete+0x22c/0x280 clone_endio+0xe4/0x280 bio_endio+0x1b0/0x1d8 blk_update_request+0x138/0x3a4 blk_mq_plug_issue_direct+0xd4/0x19c blk_mq_flush_plug_list+0x2b0/0x354 __blk_flush_plug+0x110/0x160 blk_finish_plug+0x30/0x4c read_pages+0x2fc/0x370 page_cache_ra_unbounded+0xa4/0x23c page_cache_ra_order+0x290/0x320 do_sync_mmap_readahead+0x108/0x2c0 filemap_fault+0x19c/0x52c __do_fault+0xc4/0x114 handle_mm_fault+0x5b4/0x1168 do_page_fault+0x338/0x4b4 do_translation_fault+0x40/0x60 do_mem_abort+0x60/0xc8 el0_da+0x4c/0xe0 el0t_64_sync_handler+0xd4/0xfc el0t_64_sync+0x1a0/0x1a4 [2] Link: https://lore.kernel.org/all/20210317035448.13921-1-huangjianan@oppo.com/
CVE-2023-53261: In the Linux kernel, the following vulnerability has been resolved: coresight: Fix memory leak in acpi_buffer->pointer There are memory leaks reported by kmemleak: ... unreferenced object 0xffff00213c141000 (size 1024): comm "systemd-udevd", pid 2123, jiffies 4294909467 (age 6062.160s) hex dump (first 32 bytes): 04 00 00 00 02 00 00 00 18 10 14 3c 21 00 ff ff ...........<!... 00 00 00 00 00 00 00 00 03 00 00 00 10 00 00 00 ................ backtrace: [<000000004b7c9001>] __kmem_cache_alloc_node+0x2f8/0x348 [<00000000b0fc7ceb>] __kmalloc+0x58/0x108 [<0000000064ff4695>] acpi_os_allocate+0x2c/0x68 [<000000007d57d116>] acpi_ut_initialize_buffer+0x54/0xe0 [<0000000024583908>] acpi_evaluate_object+0x388/0x438 [<0000000017b2e72b>] acpi_evaluate_object_typed+0xe8/0x240 [<000000005df0eac2>] coresight_get_platform_data+0x1b4/0x988 [coresight] ... The ACPI buffer memory (buf.pointer) should be freed. But the buffer is also used after returning from acpi_get_dsd_graph(). Move the temporary variables buf to acpi_coresight_parse_graph(), and free it before the function return to prevent memory leak.
CVE-2023-53292: In the Linux kernel, the following vulnerability has been resolved: blk-mq: fix NULL dereference on q->elevator in blk_mq_elv_switch_none After grabbing q->sysfs_lock, q->elevator may become NULL because of elevator switch. Fix the NULL dereference on q->elevator by checking it with lock.
CVE-2023-53336: In the Linux kernel, the following vulnerability has been resolved: media: ipu-bridge: Fix null pointer deref on SSDB/PLD parsing warnings When ipu_bridge_parse_rotation() and ipu_bridge_parse_orientation() run sensor->adev is not set yet. So if either of the dev_warn() calls about unknown values are hit this will lead to a NULL pointer deref. Set sensor->adev earlier, with a borrowed ref to avoid making unrolling on errors harder, to fix this.
CVE-2023-53353: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: postpone mem_mgr IDR destruction to hpriv_release() The memory manager IDR is currently destroyed when user releases the file descriptor. However, at this point the user context might be still held, and memory buffers might be still in use. Later on, calls to release those buffers will fail due to not finding their handles in the IDR, leading to a memory leak. To avoid this leak, split the IDR destruction from the memory manager fini, and postpone it to hpriv_release() when there is no user context and no buffers are used.
CVE-2023-53367: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: fix mem leak in capture user mappings This commit fixes a memory leak caused when clearing the user_mappings info when a new context is opened immediately after user_mapping is captured and a hard reset is performed.
CVE-2023-53394: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: xsk: Fix crash on regular rq reactivation When the regular rq is reactivated after the XSK socket is closed it could be reading stale cqes which eventually corrupts the rq. This leads to no more traffic being received on the regular rq and a crash on the next close or deactivation of the rq. Kal Cuttler Conely reported this issue as a crash on the release path when the xdpsock sample program is stopped (killed) and restarted in sequence while traffic is running. This patch flushes all cqes when during the rq flush. The cqe flushing is done in the reset state of the rq. mlx5e_rq_to_ready code is moved into the flush function to allow for this.
CVE-2023-53429: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't check PageError in __extent_writepage __extent_writepage currenly sets PageError whenever any error happens, and the also checks for PageError to decide if to call error handling. This leads to very unclear responsibility for cleaning up on errors. In the VM and generic writeback helpers the basic idea is that once I/O is fired off all error handling responsibility is delegated to the end I/O handler. But if that end I/O handler sets the PageError bit, and the submitter checks it, the bit could in some cases leak into the submission context for fast enough I/O. Fix this by simply not checking PageError and just using the local ret variable to check for submission errors. This also fundamentally solves the long problem documented in a comment in __extent_writepage by never leaking the error bit into the submission context.
CVE-2023-53447: In the Linux kernel, the following vulnerability has been resolved: f2fs: don't reset unchangable mount option in f2fs_remount() syzbot reports a bug as below: general protection fault, probably for non-canonical address 0xdffffc0000000009: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:__lock_acquire+0x69/0x2000 kernel/locking/lockdep.c:4942 Call Trace: lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5691 __raw_write_lock include/linux/rwlock_api_smp.h:209 [inline] _raw_write_lock+0x2e/0x40 kernel/locking/spinlock.c:300 __drop_extent_tree+0x3ac/0x660 fs/f2fs/extent_cache.c:1100 f2fs_drop_extent_tree+0x17/0x30 fs/f2fs/extent_cache.c:1116 f2fs_insert_range+0x2d5/0x3c0 fs/f2fs/file.c:1664 f2fs_fallocate+0x4e4/0x6d0 fs/f2fs/file.c:1838 vfs_fallocate+0x54b/0x6b0 fs/open.c:324 ksys_fallocate fs/open.c:347 [inline] __do_sys_fallocate fs/open.c:355 [inline] __se_sys_fallocate fs/open.c:353 [inline] __x64_sys_fallocate+0xbd/0x100 fs/open.c:353 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is race condition as below: - since it tries to remount rw filesystem, so that do_remount won't call sb_prepare_remount_readonly to block fallocate, there may be race condition in between remount and fallocate. - in f2fs_remount(), default_options() will reset mount option to default one, and then update it based on result of parse_options(), so there is a hole which race condition can happen. Thread A Thread B - f2fs_fill_super - parse_options - clear_opt(READ_EXTENT_CACHE) - f2fs_remount - default_options - set_opt(READ_EXTENT_CACHE) - f2fs_fallocate - f2fs_insert_range - f2fs_drop_extent_tree - __drop_extent_tree - __may_extent_tree - test_opt(READ_EXTENT_CACHE) return true - write_lock(&et->lock) access NULL pointer - parse_options - clear_opt(READ_EXTENT_CACHE)
CVE-2023-53460: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix memory leak in rtw_usb_probe() drivers/net/wireless/realtek/rtw88/usb.c:876 rtw_usb_probe() warn: 'hw' from ieee80211_alloc_hw() not released on lines: 811 Fix this by modifying return to a goto statement.
CVE-2023-53491: In the Linux kernel, the following vulnerability has been resolved: start_kernel: Add __no_stack_protector function attribute Back during the discussion of commit a9a3ed1eff36 ("x86: Fix early boot crash on gcc-10, third try") we discussed the need for a function attribute to control the omission of stack protectors on a per-function basis; at the time Clang had support for no_stack_protector but GCC did not. This was fixed in gcc-11. Now that the function attribute is available, let's start using it. Callers of boot_init_stack_canary need to use this function attribute unless they're compiled with -fno-stack-protector, otherwise the canary stored in the stack slot of the caller will differ upon the call to boot_init_stack_canary. This will lead to a call to __stack_chk_fail() then panic.
CVE-2023-53510: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix handling of lrbp->cmd ufshcd_queuecommand() may be called two times in a row for a SCSI command before it is completed. Hence make the following changes: - In the functions that submit a command, do not check the old value of lrbp->cmd nor clear lrbp->cmd in error paths. - In ufshcd_release_scsi_cmd(), do not clear lrbp->cmd. See also scsi_send_eh_cmnd(). This commit prevents that the following appears if a command times out: WARNING: at drivers/ufs/core/ufshcd.c:2965 ufshcd_queuecommand+0x6f8/0x9a8 Call trace: ufshcd_queuecommand+0x6f8/0x9a8 scsi_send_eh_cmnd+0x2c0/0x960 scsi_eh_test_devices+0x100/0x314 scsi_eh_ready_devs+0xd90/0x114c scsi_error_handler+0x2b4/0xb70 kthread+0x16c/0x1e0
CVE-2023-53523: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: fix time stamp counter initialization If the gs_usb device driver is unloaded (or unbound) before the interface is shut down, the USB stack first calls the struct usb_driver::disconnect and then the struct net_device_ops::ndo_stop callback. In gs_usb_disconnect() all pending bulk URBs are killed, i.e. no more RX'ed CAN frames are send from the USB device to the host. Later in gs_can_close() a reset control message is send to each CAN channel to remove the controller from the CAN bus. In this race window the USB device can still receive CAN frames from the bus and internally queue them to be send to the host. At least in the current version of the candlelight firmware, the queue of received CAN frames is not emptied during the reset command. After loading (or binding) the gs_usb driver, new URBs are submitted during the struct net_device_ops::ndo_open callback and the candlelight firmware starts sending its already queued CAN frames to the host. However, this scenario was not considered when implementing the hardware timestamp function. The cycle counter/time counter infrastructure is set up (gs_usb_timestamp_init()) after the USBs are submitted, resulting in a NULL pointer dereference if timecounter_cyc2time() (via the call chain: gs_usb_receive_bulk_callback() -> gs_usb_set_timestamp() -> gs_usb_skb_set_timestamp()) is called too early. Move the gs_usb_timestamp_init() function before the URBs are submitted to fix this problem. For a comprehensive solution, we need to consider gs_usb devices with more than 1 channel. The cycle counter/time counter infrastructure is setup per channel, but the RX URBs are per device. Once gs_can_open() of _a_ channel has been called, and URBs have been submitted, the gs_usb_receive_bulk_callback() can be called for _all_ available channels, even for channels that are not running, yet. As cycle counter/time counter has not set up, this will again lead to a NULL pointer dereference. Convert the cycle counter/time counter from a "per channel" to a "per device" functionality. Also set it up, before submitting any URBs to the device. Further in gs_usb_receive_bulk_callback(), don't process any URBs for not started CAN channels, only resubmit the URB.
CVE-2023-53529: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: Fix memory leak in rtw88_usb Kmemleak shows the following leak arising from routine in the usb probe routine: unreferenced object 0xffff895cb29bba00 (size 512): comm "(udev-worker)", pid 534, jiffies 4294903932 (age 102751.088s) hex dump (first 32 bytes): 77 30 30 30 00 00 00 00 02 2f 2d 2b 30 00 00 00 w000...../-+0... 02 00 2a 28 00 00 00 00 ff 55 ff ff ff 00 00 00 ..*(.....U...... backtrace: [<ffffffff9265fa36>] kmalloc_trace+0x26/0x90 [<ffffffffc17eec41>] rtw_usb_probe+0x2f1/0x680 [rtw_usb] [<ffffffffc03e19fd>] usb_probe_interface+0xdd/0x2e0 [usbcore] [<ffffffff92b4f2fe>] really_probe+0x18e/0x3d0 [<ffffffff92b4f5b8>] __driver_probe_device+0x78/0x160 [<ffffffff92b4f6bf>] driver_probe_device+0x1f/0x90 [<ffffffff92b4f8df>] __driver_attach+0xbf/0x1b0 [<ffffffff92b4d350>] bus_for_each_dev+0x70/0xc0 [<ffffffff92b4e51e>] bus_add_driver+0x10e/0x210 [<ffffffff92b50935>] driver_register+0x55/0xf0 [<ffffffffc03e0708>] usb_register_driver+0x88/0x140 [usbcore] [<ffffffff92401153>] do_one_initcall+0x43/0x210 [<ffffffff9254f42a>] do_init_module+0x4a/0x200 [<ffffffff92551d1c>] __do_sys_finit_module+0xac/0x120 [<ffffffff92ee6626>] do_syscall_64+0x56/0x80 [<ffffffff9300006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0 The leak was verified to be real by unloading the driver, which resulted in a dangling pointer to the allocation. The allocated memory is freed in rtw_usb_intf_deinit().
CVE-2023-53538: In the Linux kernel, the following vulnerability has been resolved: btrfs: insert tree mod log move in push_node_left There is a fairly unlikely race condition in tree mod log rewind that can result in a kernel panic which has the following trace: [530.569] BTRFS critical (device sda3): unable to find logical 0 length 4096 [530.585] BTRFS critical (device sda3): unable to find logical 0 length 4096 [530.602] BUG: kernel NULL pointer dereference, address: 0000000000000002 [530.618] #PF: supervisor read access in kernel mode [530.629] #PF: error_code(0x0000) - not-present page [530.641] PGD 0 P4D 0 [530.647] Oops: 0000 [#1] SMP [530.654] CPU: 30 PID: 398973 Comm: below Kdump: loaded Tainted: G S O K 5.12.0-0_fbk13_clang_7455_gb24de3bdb045 #1 [530.680] Hardware name: Quanta Mono Lake-M.2 SATA 1HY9U9Z001G/Mono Lake-M.2 SATA, BIOS F20_3A15 08/16/2017 [530.703] RIP: 0010:__btrfs_map_block+0xaa/0xd00 [530.755] RSP: 0018:ffffc9002c2f7600 EFLAGS: 00010246 [530.767] RAX: ffffffffffffffea RBX: ffff888292e41000 RCX: f2702d8b8be15100 [530.784] RDX: ffff88885fda6fb8 RSI: ffff88885fd973c8 RDI: ffff88885fd973c8 [530.800] RBP: ffff888292e410d0 R08: ffffffff82fd7fd0 R09: 00000000fffeffff [530.816] R10: ffffffff82e57fd0 R11: ffffffff82e57d70 R12: 0000000000000000 [530.832] R13: 0000000000001000 R14: 0000000000001000 R15: ffffc9002c2f76f0 [530.848] FS: 00007f38d64af000(0000) GS:ffff88885fd80000(0000) knlGS:0000000000000000 [530.866] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [530.880] CR2: 0000000000000002 CR3: 00000002b6770004 CR4: 00000000003706e0 [530.896] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [530.912] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [530.928] Call Trace: [530.934] ? btrfs_printk+0x13b/0x18c [530.943] ? btrfs_bio_counter_inc_blocked+0x3d/0x130 [530.955] btrfs_map_bio+0x75/0x330 [530.963] ? kmem_cache_alloc+0x12a/0x2d0 [530.973] ? btrfs_submit_metadata_bio+0x63/0x100 [530.984] btrfs_submit_metadata_bio+0xa4/0x100 [530.995] submit_extent_page+0x30f/0x360 [531.004] read_extent_buffer_pages+0x49e/0x6d0 [531.015] ? submit_extent_page+0x360/0x360 [531.025] btree_read_extent_buffer_pages+0x5f/0x150 [531.037] read_tree_block+0x37/0x60 [531.046] read_block_for_search+0x18b/0x410 [531.056] btrfs_search_old_slot+0x198/0x2f0 [531.066] resolve_indirect_ref+0xfe/0x6f0 [531.076] ? ulist_alloc+0x31/0x60 [531.084] ? kmem_cache_alloc_trace+0x12e/0x2b0 [531.095] find_parent_nodes+0x720/0x1830 [531.105] ? ulist_alloc+0x10/0x60 [531.113] iterate_extent_inodes+0xea/0x370 [531.123] ? btrfs_previous_extent_item+0x8f/0x110 [531.134] ? btrfs_search_path_in_tree+0x240/0x240 [531.146] iterate_inodes_from_logical+0x98/0xd0 [531.157] ? btrfs_search_path_in_tree+0x240/0x240 [531.168] btrfs_ioctl_logical_to_ino+0xd9/0x180 [531.179] btrfs_ioctl+0xe2/0x2eb0 This occurs when logical inode resolution takes a tree mod log sequence number, and then while backref walking hits a rewind on a busy node which has the following sequence of tree mod log operations (numbers filled in from a specific example, but they are somewhat arbitrary) REMOVE_WHILE_FREEING slot 532 REMOVE_WHILE_FREEING slot 531 REMOVE_WHILE_FREEING slot 530 ... REMOVE_WHILE_FREEING slot 0 REMOVE slot 455 REMOVE slot 454 REMOVE slot 453 ... REMOVE slot 0 ADD slot 455 ADD slot 454 ADD slot 453 ... ADD slot 0 MOVE src slot 0 -> dst slot 456 nritems 533 REMOVE slot 455 REMOVE slot 454 REMOVE slot 453 ... REMOVE slot 0 When this sequence gets applied via btrfs_tree_mod_log_rewind, it allocates a fresh rewind eb, and first inserts the correct key info for the 533 elements, then overwrites the first 456 of them, then decrements the count by 456 via the add ops, then rewinds the move by doing a memmove from 456:988->0:532. We have never written anything past 532, ---truncated---
CVE-2023-53545: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: unmap and remove csa_va properly Root PD BO should be reserved before unmap and remove a bo_va from VM otherwise lockdep will complain. v2: check fpriv->csa_va is not NULL instead of amdgpu_mcbp (christian) [14616.936827] WARNING: CPU: 6 PID: 1711 at drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c:1762 amdgpu_vm_bo_del+0x399/0x3f0 [amdgpu] [14616.937096] Call Trace: [14616.937097] <TASK> [14616.937102] amdgpu_driver_postclose_kms+0x249/0x2f0 [amdgpu] [14616.937187] drm_file_free+0x1d6/0x300 [drm] [14616.937207] drm_close_helper.isra.0+0x62/0x70 [drm] [14616.937220] drm_release+0x5e/0x100 [drm] [14616.937234] __fput+0x9f/0x280 [14616.937239] ____fput+0xe/0x20 [14616.937241] task_work_run+0x61/0x90 [14616.937246] exit_to_user_mode_prepare+0x215/0x220 [14616.937251] syscall_exit_to_user_mode+0x2a/0x60 [14616.937254] do_syscall_64+0x48/0x90 [14616.937257] entry_SYSCALL_64_after_hwframe+0x63/0xcd
CVE-2023-53574: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: delete timer and free skb queue when unloading Fix possible crash and memory leak on driver unload by deleting TX purge timer and freeing C2H queue in 'rtw_core_deinit()', shrink critical section in the latter by freeing COEX queue out of TX report lock scope.
CVE-2023-53627: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Grab sas_dev lock when traversing the members of sas_dev.list When freeing slots in function slot_complete_v3_hw(), it is possible that sas_dev.list is being traversed elsewhere, and it may trigger a NULL pointer exception, such as follows: ==>cq thread ==>scsi_eh_6 ==>scsi_error_handler() ==>sas_eh_handle_sas_errors() ==>sas_scsi_find_task() ==>lldd_abort_task() ==>slot_complete_v3_hw() ==>hisi_sas_abort_task() ==>hisi_sas_slot_task_free() ==>dereg_device_v3_hw() ==>list_del_init() ==>list_for_each_entry_safe() [ 7165.434918] sas: Enter sas_scsi_recover_host busy: 32 failed: 32 [ 7165.434926] sas: trying to find task 0x00000000769b5ba5 [ 7165.434927] sas: sas_scsi_find_task: aborting task 0x00000000769b5ba5 [ 7165.434940] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000769b5ba5) aborted [ 7165.434964] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000c9f7aa07) ignored [ 7165.434965] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000e2a1cf01) ignored [ 7165.434968] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 7165.434972] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000022d52d93) ignored [ 7165.434975] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000066a7516c) ignored [ 7165.434976] Mem abort info: [ 7165.434982] ESR = 0x96000004 [ 7165.434991] Exception class = DABT (current EL), IL = 32 bits [ 7165.434992] SET = 0, FnV = 0 [ 7165.434993] EA = 0, S1PTW = 0 [ 7165.434994] Data abort info: [ 7165.434994] ISV = 0, ISS = 0x00000004 [ 7165.434995] CM = 0, WnR = 0 [ 7165.434997] user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000f29543f2 [ 7165.434998] [0000000000000000] pgd=0000000000000000 [ 7165.435003] Internal error: Oops: 96000004 [#1] SMP [ 7165.439863] Process scsi_eh_6 (pid: 4109, stack limit = 0x00000000c43818d5) [ 7165.468862] pstate: 00c00009 (nzcv daif +PAN +UAO) [ 7165.473637] pc : dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.479443] lr : dereg_device_v3_hw+0x2c/0xa8 [hisi_sas_v3_hw] [ 7165.485247] sp : ffff00001d623bc0 [ 7165.488546] x29: ffff00001d623bc0 x28: ffffa027d03b9508 [ 7165.493835] x27: ffff80278ed50af0 x26: ffffa027dd31e0a8 [ 7165.499123] x25: ffffa027d9b27f88 x24: ffffa027d9b209f8 [ 7165.504411] x23: ffffa027c45b0d60 x22: ffff80278ec07c00 [ 7165.509700] x21: 0000000000000008 x20: ffffa027d9b209f8 [ 7165.514988] x19: ffffa027d9b27f88 x18: ffffffffffffffff [ 7165.520276] x17: 0000000000000000 x16: 0000000000000000 [ 7165.525564] x15: ffff0000091d9708 x14: ffff0000093b7dc8 [ 7165.530852] x13: ffff0000093b7a23 x12: 6e7265746e692067 [ 7165.536140] x11: 0000000000000000 x10: 0000000000000bb0 [ 7165.541429] x9 : ffff00001d6238f0 x8 : ffffa027d877af00 [ 7165.546718] x7 : ffffa027d6329600 x6 : ffff7e809f58ca00 [ 7165.552006] x5 : 0000000000001f8a x4 : 000000000000088e [ 7165.557295] x3 : ffffa027d9b27fa8 x2 : 0000000000000000 [ 7165.562583] x1 : 0000000000000000 x0 : 000000003000188e [ 7165.567872] Call trace: [ 7165.570309] dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.575775] hisi_sas_abort_task+0x248/0x358 [hisi_sas_main] [ 7165.581415] sas_eh_handle_sas_errors+0x258/0x8e0 [libsas] [ 7165.586876] sas_scsi_recover_host+0x134/0x458 [libsas] [ 7165.592082] scsi_error_handler+0xb4/0x488 [ 7165.596163] kthread+0x134/0x138 [ 7165.599380] ret_from_fork+0x10/0x18 [ 7165.602940] Code: d5033e9f b9000040 aa0103e2 eb03003f (f9400021) [ 7165.609004] kernel fault(0x1) notification starting on CPU 75 [ 7165.700728] ---[ end trace fc042cbbea224efc ]--- [ 7165.705326] Kernel panic - not syncing: Fatal exception To fix the issue, grab sas_dev lock when traversing the members of sas_dev.list in dereg_device_v3_hw() and hisi_sas_release_tasks() to avoid concurrency of adding and deleting member. When ---truncated---
CVE-2023-53706: In the Linux kernel, the following vulnerability has been resolved: mm/vmemmap/devdax: fix kernel crash when probing devdax devices commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") added support for using optimized vmmemap for devdax devices. But how vmemmap mappings are created are architecture specific. For example, powerpc with hash translation doesn't have vmemmap mappings in init_mm page table instead they are bolted table entries in the hardware page table vmemmap_populate_compound_pages() used by vmemmap optimization code is not aware of these architecture-specific mapping. Hence allow architecture to opt for this feature. I selected architectures supporting HUGETLB_PAGE_OPTIMIZE_VMEMMAP option as also supporting this feature. This patch fixes the below crash on ppc64. BUG: Unable to handle kernel data access on write at 0xc00c000100400038 Faulting instruction address: 0xc000000001269d90 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries NIP: c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000 REGS: c000000003632c30 TRAP: 0300 Not tainted (6.3.0-rc5-150500.34-default+) MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24842228 XER: 00000000 CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0 .... NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0 Call Trace: [c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable) [c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250 [c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0 [c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0 [c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0 [c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140 [c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520 [c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120 [c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0 [c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130 [c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250 [c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110 [c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10 [c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530 [c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270 [c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70 [c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0 [c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520 [c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120 [c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240 [c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130 [c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50 [c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300 [c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0 [c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100 [c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48 [c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320 [c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400 [c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0 [c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64
CVE-2023-53762: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_sync: Fix UAF in hci_disconnect_all_sync Use-after-free can occur in hci_disconnect_all_sync if a connection is deleted by concurrent processing of a controller event. To prevent this the code now tries to iterate over the list backwards to ensure the links are cleanup before its parents, also it no longer relies on a cursor, instead it always uses the last element since hci_abort_conn_sync is guaranteed to call hci_conn_del. UAF crash log: ================================================================== BUG: KASAN: slab-use-after-free in hci_set_powered_sync (net/bluetooth/hci_sync.c:5424) [bluetooth] Read of size 8 at addr ffff888009d9c000 by task kworker/u9:0/124 CPU: 0 PID: 124 Comm: kworker/u9:0 Tainted: G W 6.5.0-rc1+ #10 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-1.fc38 04/01/2014 Workqueue: hci0 hci_cmd_sync_work [bluetooth] Call Trace: <TASK> dump_stack_lvl+0x5b/0x90 print_report+0xcf/0x670 ? __virt_addr_valid+0xdd/0x160 ? hci_set_powered_sync+0x2c9/0x4a0 [bluetooth] kasan_report+0xa6/0xe0 ? hci_set_powered_sync+0x2c9/0x4a0 [bluetooth] ? __pfx_set_powered_sync+0x10/0x10 [bluetooth] hci_set_powered_sync+0x2c9/0x4a0 [bluetooth] ? __pfx_hci_set_powered_sync+0x10/0x10 [bluetooth] ? __pfx_lock_release+0x10/0x10 ? __pfx_set_powered_sync+0x10/0x10 [bluetooth] hci_cmd_sync_work+0x137/0x220 [bluetooth] process_one_work+0x526/0x9d0 ? __pfx_process_one_work+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? mark_held_locks+0x1a/0x90 worker_thread+0x92/0x630 ? __pfx_worker_thread+0x10/0x10 kthread+0x196/0x1e0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 </TASK> Allocated by task 1782: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 __kasan_kmalloc+0x8f/0xa0 hci_conn_add+0xa5/0xa80 [bluetooth] hci_bind_cis+0x881/0x9b0 [bluetooth] iso_connect_cis+0x121/0x520 [bluetooth] iso_sock_connect+0x3f6/0x790 [bluetooth] __sys_connect+0x109/0x130 __x64_sys_connect+0x40/0x50 do_syscall_64+0x60/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 695: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2b/0x50 __kasan_slab_free+0x10a/0x180 __kmem_cache_free+0x14d/0x2e0 device_release+0x5d/0xf0 kobject_put+0xdf/0x270 hci_disconn_complete_evt+0x274/0x3a0 [bluetooth] hci_event_packet+0x579/0x7e0 [bluetooth] hci_rx_work+0x287/0xaa0 [bluetooth] process_one_work+0x526/0x9d0 worker_thread+0x92/0x630 kthread+0x196/0x1e0 ret_from_fork+0x2c/0x50 ==================================================================
CVE-2023-53781: In the Linux kernel, the following vulnerability has been resolved: smc: Fix use-after-free in tcp_write_timer_handler(). With Eric's ref tracker, syzbot finally found a repro for use-after-free in tcp_write_timer_handler() by kernel TCP sockets. [0] If SMC creates a kernel socket in __smc_create(), the kernel socket is supposed to be freed in smc_clcsock_release() by calling sock_release() when we close() the parent SMC socket. However, at the end of smc_clcsock_release(), the kernel socket's sk_state might not be TCP_CLOSE. This means that we have not called inet_csk_destroy_sock() in __tcp_close() and have not stopped the TCP timers. The kernel socket's TCP timers can be fired later, so we need to hold a refcnt for net as we do for MPTCP subflows in mptcp_subflow_create_socket(). [0]: leaked reference. sk_alloc (./include/net/net_namespace.h:335 net/core/sock.c:2108) inet_create (net/ipv4/af_inet.c:319 net/ipv4/af_inet.c:244) __sock_create (net/socket.c:1546) smc_create (net/smc/af_smc.c:3269 net/smc/af_smc.c:3284) __sock_create (net/socket.c:1546) __sys_socket (net/socket.c:1634 net/socket.c:1618 net/socket.c:1661) __x64_sys_socket (net/socket.c:1672) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) ================================================================== BUG: KASAN: slab-use-after-free in tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) Read of size 1 at addr ffff888052b65e0d by task syzrepro/18091 CPU: 0 PID: 18091 Comm: syzrepro Tainted: G W 6.3.0-rc4-01174-gb5d54eb5899a #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107) print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) kasan_report (mm/kasan/report.c:538) tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594) tcp_write_timer (./include/linux/spinlock.h:390 net/ipv4/tcp_timer.c:643) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2022) run_timer_softirq (kernel/time/timer.c:2037) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) __irq_exit_rcu (kernel/softirq.c:445 kernel/softirq.c:650) irq_exit_rcu (kernel/softirq.c:664) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1107 (discriminator 14)) </IRQ>
CVE-2023-53823: In the Linux kernel, the following vulnerability has been resolved: block/rq_qos: protect rq_qos apis with a new lock commit 50e34d78815e ("block: disable the elevator int del_gendisk") move rq_qos_exit() from disk_release() to del_gendisk(), this will introduce some problems: 1) If rq_qos_add() is triggered by enabling iocost/iolatency through cgroupfs, then it can concurrent with del_gendisk(), it's not safe to write 'q->rq_qos' concurrently. 2) Activate cgroup policy that is relied on rq_qos will call rq_qos_add() and blkcg_activate_policy(), and if rq_qos_exit() is called in the middle, null-ptr-dereference will be triggered in blkcg_activate_policy(). 3) blkg_conf_open_bdev() can call blkdev_get_no_open() first to find the disk, then if rq_qos_exit() from del_gendisk() is done before rq_qos_add(), then memory will be leaked. This patch add a new disk level mutex 'rq_qos_mutex': 1) The lock will protect rq_qos_exit() directly. 2) For wbt that doesn't relied on blk-cgroup, rq_qos_add() can only be called from disk initialization for now because wbt can't be destructed until rq_qos_exit(), so it's safe not to protect wbt for now. Hoever, in case that rq_qos dynamically destruction is supported in the furture, this patch also protect rq_qos_add() from wbt_init() directly, this is enough because blk-sysfs already synchronize writers with disk removal. 3) For iocost and iolatency, in order to synchronize disk removal and cgroup configuration, the lock is held after blkdev_get_no_open() from blkg_conf_open_bdev(), and is released in blkg_conf_exit(). In order to fix the above memory leak, disk_live() is checked after holding the new lock.
CVE-2023-53846: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on direct node in truncate_dnode() syzbot reports below bug: BUG: KASAN: slab-use-after-free in f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 Read of size 4 at addr ffff88802a25c000 by task syz-executor148/5000 CPU: 1 PID: 5000 Comm: syz-executor148 Not tainted 6.4.0-rc7-syzkaller-00041-ge660abd551f1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351 print_report mm/kasan/report.c:462 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:572 f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 truncate_dnode+0x229/0x2e0 fs/f2fs/node.c:944 f2fs_truncate_inode_blocks+0x64b/0xde0 fs/f2fs/node.c:1154 f2fs_do_truncate_blocks+0x4ac/0xf30 fs/f2fs/file.c:721 f2fs_truncate_blocks+0x7b/0x300 fs/f2fs/file.c:749 f2fs_truncate.part.0+0x4a5/0x630 fs/f2fs/file.c:799 f2fs_truncate include/linux/fs.h:825 [inline] f2fs_setattr+0x1738/0x2090 fs/f2fs/file.c:1006 notify_change+0xb2c/0x1180 fs/attr.c:483 do_truncate+0x143/0x200 fs/open.c:66 handle_truncate fs/namei.c:3295 [inline] do_open fs/namei.c:3640 [inline] path_openat+0x2083/0x2750 fs/namei.c:3791 do_filp_open+0x1ba/0x410 fs/namei.c:3818 do_sys_openat2+0x16d/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_creat fs/open.c:1448 [inline] __se_sys_creat fs/open.c:1442 [inline] __x64_sys_creat+0xcd/0x120 fs/open.c:1442 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is, inodeA references inodeB via inodeB's ino, once inodeA is truncated, it calls truncate_dnode() to truncate data blocks in inodeB's node page, it traverse mapping data from node->i.i_addr[0] to node->i.i_addr[ADDRS_PER_BLOCK() - 1], result in out-of-boundary access. This patch fixes to add sanity check on dnode page in truncate_dnode(), so that, it can help to avoid triggering such issue, and once it encounters such issue, it will record newly introduced ERROR_INVALID_NODE_REFERENCE error into superblock, later fsck can detect such issue and try repairing. Also, it removes f2fs_truncate_data_blocks() for cleanup due to the function has only one caller, and uses f2fs_truncate_data_blocks_range() instead.
CVE-2023-53851: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dp: Drop aux devices together with DP controller Using devres to depopulate the aux bus made sure that upon a probe deferral the EDP panel device would be destroyed and recreated upon next attempt. But the struct device which the devres is tied to is the DPUs (drm_dev->dev), which may be happen after the DP controller is torn down. Indications of this can be seen in the commonly seen EDID-hexdump full of zeros in the log, or the occasional/rare KASAN fault where the panel's attempt to read the EDID information causes a use after free on DP resources. It's tempting to move the devres to the DP controller's struct device, but the resources used by the device(s) on the aux bus are explicitly torn down in the error path. The KASAN-reported use-after-free also remains, as the DP aux "module" explicitly frees its devres-allocated memory in this code path. As such, explicitly depopulate the aux bus in the error path, and in the component unbind path, to avoid these issues. Patchwork: https://patchwork.freedesktop.org/patch/542163/
CVE-2023-53857: In the Linux kernel, the following vulnerability has been resolved: bpf: bpf_sk_storage: Fix invalid wait context lockdep report './test_progs -t test_local_storage' reported a splat: [ 27.137569] ============================= [ 27.138122] [ BUG: Invalid wait context ] [ 27.138650] 6.5.0-03980-gd11ae1b16b0a #247 Tainted: G O [ 27.139542] ----------------------------- [ 27.140106] test_progs/1729 is trying to lock: [ 27.140713] ffff8883ef047b88 (stock_lock){-.-.}-{3:3}, at: local_lock_acquire+0x9/0x130 [ 27.141834] other info that might help us debug this: [ 27.142437] context-{5:5} [ 27.142856] 2 locks held by test_progs/1729: [ 27.143352] #0: ffffffff84bcd9c0 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x4/0x40 [ 27.144492] #1: ffff888107deb2c0 (&storage->lock){..-.}-{2:2}, at: bpf_local_storage_update+0x39e/0x8e0 [ 27.145855] stack backtrace: [ 27.146274] CPU: 0 PID: 1729 Comm: test_progs Tainted: G O 6.5.0-03980-gd11ae1b16b0a #247 [ 27.147550] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 27.149127] Call Trace: [ 27.149490] <TASK> [ 27.149867] dump_stack_lvl+0x130/0x1d0 [ 27.152609] dump_stack+0x14/0x20 [ 27.153131] __lock_acquire+0x1657/0x2220 [ 27.153677] lock_acquire+0x1b8/0x510 [ 27.157908] local_lock_acquire+0x29/0x130 [ 27.159048] obj_cgroup_charge+0xf4/0x3c0 [ 27.160794] slab_pre_alloc_hook+0x28e/0x2b0 [ 27.161931] __kmem_cache_alloc_node+0x51/0x210 [ 27.163557] __kmalloc+0xaa/0x210 [ 27.164593] bpf_map_kzalloc+0xbc/0x170 [ 27.165147] bpf_selem_alloc+0x130/0x510 [ 27.166295] bpf_local_storage_update+0x5aa/0x8e0 [ 27.167042] bpf_fd_sk_storage_update_elem+0xdb/0x1a0 [ 27.169199] bpf_map_update_value+0x415/0x4f0 [ 27.169871] map_update_elem+0x413/0x550 [ 27.170330] __sys_bpf+0x5e9/0x640 [ 27.174065] __x64_sys_bpf+0x80/0x90 [ 27.174568] do_syscall_64+0x48/0xa0 [ 27.175201] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 27.175932] RIP: 0033:0x7effb40e41ad [ 27.176357] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d8 [ 27.179028] RSP: 002b:00007ffe64c21fc8 EFLAGS: 00000202 ORIG_RAX: 0000000000000141 [ 27.180088] RAX: ffffffffffffffda RBX: 00007ffe64c22768 RCX: 00007effb40e41ad [ 27.181082] RDX: 0000000000000020 RSI: 00007ffe64c22008 RDI: 0000000000000002 [ 27.182030] RBP: 00007ffe64c21ff0 R08: 0000000000000000 R09: 00007ffe64c22788 [ 27.183038] R10: 0000000000000064 R11: 0000000000000202 R12: 0000000000000000 [ 27.184006] R13: 00007ffe64c22788 R14: 00007effb42a1000 R15: 0000000000000000 [ 27.184958] </TASK> It complains about acquiring a local_lock while holding a raw_spin_lock. It means it should not allocate memory while holding a raw_spin_lock since it is not safe for RT. raw_spin_lock is needed because bpf_local_storage supports tracing context. In particular for task local storage, it is easy to get a "current" task PTR_TO_BTF_ID in tracing bpf prog. However, task (and cgroup) local storage has already been moved to bpf mem allocator which can be used after raw_spin_lock. The splat is for the sk storage. For sk (and inode) storage, it has not been moved to bpf mem allocator. Using raw_spin_lock or not, kzalloc(GFP_ATOMIC) could theoretically be unsafe in tracing context. However, the local storage helper requires a verifier accepted sk pointer (PTR_TO_BTF_ID), it is hypothetical if that (mean running a bpf prog in a kzalloc unsafe context and also able to hold a verifier accepted sk pointer) could happen. This patch avoids kzalloc after raw_spin_lock to silent the splat. There is an existing kzalloc before the raw_spin_lock. At that point, a kzalloc is very likely required because a lookup has just been done before. Thus, this patch always does the kzalloc before acq ---truncated---
CVE-2023-53989: In the Linux kernel, the following vulnerability has been resolved: arm64: mm: fix VA-range sanity check Both create_mapping_noalloc() and update_mapping_prot() sanity-check their 'virt' parameter, but the check itself doesn't make much sense. The condition used today appears to be a historical accident. The sanity-check condition: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } ... can only be true for the KASAN shadow region or the module region, and there's no reason to exclude these specifically for creating and updateing mappings. When arm64 support was first upstreamed in commit: c1cc1552616d0f35 ("arm64: MMU initialisation") ... the condition was: if (virt < VMALLOC_START) { [ ... warning here ... ] return; } At the time, VMALLOC_START was the lowest kernel address, and this was checking whether 'virt' would be translated via TTBR1. Subsequently in commit: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space") ... the condition was changed to: if ((virt >= VA_START) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } This appear to have been a thinko. The commit moved the linear map to the bottom of the kernel address space, with VMALLOC_START being at the halfway point. The old condition would warn for changes to the linear map below this, and at the time VA_START was the end of the linear map. Subsequently we cleaned up the naming of VA_START in commit: 77ad4ce69321abbe ("arm64: memory: rename VA_START to PAGE_END") ... keeping the erroneous condition as: if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { [ ... warning here ... ] return; } Correct the condition to check against the start of the TTBR1 address space, which is currently PAGE_OFFSET. This simplifies the logic, and more clearly matches the "outside kernel range" message in the warning.
CVE-2023-53999: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: TC, Fix internal port memory leak The flow rule can be splited, and the extra post_act rules are added to post_act table. It's possible to trigger memleak when the rule forwards packets from internal port and over tunnel, in the case that, for example, CT 'new' state offload is allowed. As int_port object is assigned to the flow attribute of post_act rule, and its refcnt is incremented by mlx5e_tc_int_port_get(), but mlx5e_tc_int_port_put() is not called, the refcnt is never decremented, then int_port is never freed. The kmemleak reports the following error: unreferenced object 0xffff888128204b80 (size 64): comm "handler20", pid 50121, jiffies 4296973009 (age 642.932s) hex dump (first 32 bytes): 01 00 00 00 19 00 00 00 03 f0 00 00 04 00 00 00 ................ 98 77 67 41 81 88 ff ff 98 77 67 41 81 88 ff ff .wgA.....wgA.... backtrace: [<00000000e992680d>] kmalloc_trace+0x27/0x120 [<000000009e945a98>] mlx5e_tc_int_port_get+0x3f3/0xe20 [mlx5_core] [<0000000035a537f0>] mlx5e_tc_add_fdb_flow+0x473/0xcf0 [mlx5_core] [<0000000070c2cec6>] __mlx5e_add_fdb_flow+0x7cf/0xe90 [mlx5_core] [<000000005cc84048>] mlx5e_configure_flower+0xd40/0x4c40 [mlx5_core] [<000000004f8a2031>] mlx5e_rep_indr_offload.isra.0+0x10e/0x1c0 [mlx5_core] [<000000007df797dc>] mlx5e_rep_indr_setup_tc_cb+0x90/0x130 [mlx5_core] [<0000000016c15cc3>] tc_setup_cb_add+0x1cf/0x410 [<00000000a63305b4>] fl_hw_replace_filter+0x38f/0x670 [cls_flower] [<000000008bc9e77c>] fl_change+0x1fd5/0x4430 [cls_flower] [<00000000e7f766e4>] tc_new_tfilter+0x867/0x2010 [<00000000e101c0ef>] rtnetlink_rcv_msg+0x6fc/0x9f0 [<00000000e1111d44>] netlink_rcv_skb+0x12c/0x360 [<0000000082dd6c8b>] netlink_unicast+0x438/0x710 [<00000000fc568f70>] netlink_sendmsg+0x794/0xc50 [<0000000016e92590>] sock_sendmsg+0xc5/0x190 So fix this by moving int_port cleanup code to the flow attribute free helper, which is used by all the attribute free cases.
CVE-2023-54013: In the Linux kernel, the following vulnerability has been resolved: interconnect: Fix locking for runpm vs reclaim For cases where icc_bw_set() can be called in callbaths that could deadlock against shrinker/reclaim, such as runpm resume, we need to decouple the icc locking. Introduce a new icc_bw_lock for cases where we need to serialize bw aggregation and update to decouple that from paths that require memory allocation such as node/link creation/ destruction. Fixes this lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc8-debug+ #554 Not tainted ------------------------------------------------------ ring0/132 is trying to acquire lock: ffffff80871916d0 (&gmu->lock){+.+.}-{3:3}, at: a6xx_pm_resume+0xf0/0x234 but task is already holding lock: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 (dma_fence_map){++++}-{0:0}: __dma_fence_might_wait+0x74/0xc0 dma_resv_lockdep+0x1f4/0x2f4 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}: fs_reclaim_acquire+0x80/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 topology_parse_cpu_capacity+0x8c/0x178 get_cpu_for_node+0x88/0xc4 parse_cluster+0x1b0/0x28c parse_cluster+0x8c/0x28c init_cpu_topology+0x168/0x188 smp_prepare_cpus+0x24/0xf8 kernel_init_freeable+0x18c/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #2 (fs_reclaim){+.+.}-{0:0}: __fs_reclaim_acquire+0x3c/0x48 fs_reclaim_acquire+0x54/0xa8 slab_pre_alloc_hook.constprop.0+0x40/0x25c __kmem_cache_alloc_node+0x60/0x1cc __kmalloc+0xd8/0x100 kzalloc.constprop.0+0x14/0x20 icc_node_create_nolock+0x4c/0xc4 icc_node_create+0x38/0x58 qcom_icc_rpmh_probe+0x1b8/0x248 platform_probe+0x70/0xc4 really_probe+0x158/0x290 __driver_probe_device+0xc8/0xe0 driver_probe_device+0x44/0x100 __driver_attach+0xf8/0x108 bus_for_each_dev+0x78/0xc4 driver_attach+0x2c/0x38 bus_add_driver+0xd0/0x1d8 driver_register+0xbc/0xf8 __platform_driver_register+0x30/0x3c qnoc_driver_init+0x24/0x30 do_one_initcall+0x104/0x2bc kernel_init_freeable+0x344/0x34c kernel_init+0x30/0x134 ret_from_fork+0x10/0x20 -> #1 (icc_lock){+.+.}-{3:3}: __mutex_lock+0xcc/0x3c8 mutex_lock_nested+0x30/0x44 icc_set_bw+0x88/0x2b4 _set_opp_bw+0x8c/0xd8 _set_opp+0x19c/0x300 dev_pm_opp_set_opp+0x84/0x94 a6xx_gmu_resume+0x18c/0x804 a6xx_pm_resume+0xf8/0x234 adreno_runtime_resume+0x2c/0x38 pm_generic_runtime_resume+0x30/0x44 __rpm_callback+0x15c/0x174 rpm_callback+0x78/0x7c rpm_resume+0x318/0x524 __pm_runtime_resume+0x78/0xbc adreno_load_gpu+0xc4/0x17c msm_open+0x50/0x120 drm_file_alloc+0x17c/0x228 drm_open_helper+0x74/0x118 drm_open+0xa0/0x144 drm_stub_open+0xd4/0xe4 chrdev_open+0x1b8/0x1e4 do_dentry_open+0x2f8/0x38c vfs_open+0x34/0x40 path_openat+0x64c/0x7b4 do_filp_open+0x54/0xc4 do_sys_openat2+0x9c/0x100 do_sys_open+0x50/0x7c __arm64_sys_openat+0x28/0x34 invoke_syscall+0x8c/0x128 el0_svc_common.constprop.0+0xa0/0x11c do_el0_ ---truncated---
CVE-2023-54030: In the Linux kernel, the following vulnerability has been resolved: io_uring/net: don't overflow multishot recv Don't allow overflowing multishot recv CQEs, it might get out of hand, hurt performance, and in the worst case scenario OOM the task.
CVE-2023-54088: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: hold queue_lock when removing blkg->q_node When blkg is removed from q->blkg_list from blkg_free_workfn(), queue_lock has to be held, otherwise, all kinds of bugs(list corruption, hard lockup, ..) can be triggered from blkg_destroy_all().
CVE-2023-54107: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: dropping parent refcount after pd_free_fn() is done Some cgroup policies will access parent pd through child pd even after pd_offline_fn() is done. If pd_free_fn() for parent is called before child, then UAF can be triggered. Hence it's better to guarantee the order of pd_free_fn(). Currently refcount of parent blkg is dropped in __blkg_release(), which is before pd_free_fn() is called in blkg_free_work_fn() while blkg_free_work_fn() is called asynchronously. This patch make sure pd_free_fn() called from removing cgroup is ordered by delaying dropping parent refcount after calling pd_free_fn() for child. BTW, pd_free_fn() will also be called from blkcg_deactivate_policy() from deleting device, and following patches will guarantee the order.
CVE-2023-54125: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Return error for inconsistent extended attributes ntfs_read_ea is called when we want to read extended attributes. There are some sanity checks for the validity of the EAs. However, it fails to return a proper error code for the inconsistent attributes, which might lead to unpredicted memory accesses after return. [ 138.916927] BUG: KASAN: use-after-free in ntfs_set_ea+0x453/0xbf0 [ 138.923876] Write of size 4 at addr ffff88800205cfac by task poc/199 [ 138.931132] [ 138.933016] CPU: 0 PID: 199 Comm: poc Not tainted 6.2.0-rc1+ #4 [ 138.938070] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 [ 138.947327] Call Trace: [ 138.949557] <TASK> [ 138.951539] dump_stack_lvl+0x4d/0x67 [ 138.956834] print_report+0x16f/0x4a6 [ 138.960798] ? ntfs_set_ea+0x453/0xbf0 [ 138.964437] ? kasan_complete_mode_report_info+0x7d/0x200 [ 138.969793] ? ntfs_set_ea+0x453/0xbf0 [ 138.973523] kasan_report+0xb8/0x140 [ 138.976740] ? ntfs_set_ea+0x453/0xbf0 [ 138.980578] __asan_store4+0x76/0xa0 [ 138.984669] ntfs_set_ea+0x453/0xbf0 [ 138.988115] ? __pfx_ntfs_set_ea+0x10/0x10 [ 138.993390] ? kernel_text_address+0xd3/0xe0 [ 138.998270] ? __kernel_text_address+0x16/0x50 [ 139.002121] ? unwind_get_return_address+0x3e/0x60 [ 139.005659] ? __pfx_stack_trace_consume_entry+0x10/0x10 [ 139.010177] ? arch_stack_walk+0xa2/0x100 [ 139.013657] ? filter_irq_stacks+0x27/0x80 [ 139.017018] ntfs_setxattr+0x405/0x440 [ 139.022151] ? __pfx_ntfs_setxattr+0x10/0x10 [ 139.026569] ? kvmalloc_node+0x2d/0x120 [ 139.030329] ? kasan_save_stack+0x41/0x60 [ 139.033883] ? kasan_save_stack+0x2a/0x60 [ 139.037338] ? kasan_set_track+0x29/0x40 [ 139.040163] ? kasan_save_alloc_info+0x1f/0x30 [ 139.043588] ? __kasan_kmalloc+0x8b/0xa0 [ 139.047255] ? __kmalloc_node+0x68/0x150 [ 139.051264] ? kvmalloc_node+0x2d/0x120 [ 139.055301] ? vmemdup_user+0x2b/0xa0 [ 139.058584] __vfs_setxattr+0x121/0x170 [ 139.062617] ? __pfx___vfs_setxattr+0x10/0x10 [ 139.066282] __vfs_setxattr_noperm+0x97/0x300 [ 139.070061] __vfs_setxattr_locked+0x145/0x170 [ 139.073580] vfs_setxattr+0x137/0x2a0 [ 139.076641] ? __pfx_vfs_setxattr+0x10/0x10 [ 139.080223] ? __kasan_check_write+0x18/0x20 [ 139.084234] do_setxattr+0xce/0x150 [ 139.087768] setxattr+0x126/0x140 [ 139.091250] ? __pfx_setxattr+0x10/0x10 [ 139.094948] ? __virt_addr_valid+0xcb/0x140 [ 139.097838] ? __call_rcu_common.constprop.0+0x1c7/0x330 [ 139.102688] ? debug_smp_processor_id+0x1b/0x30 [ 139.105985] ? kasan_quarantine_put+0x5b/0x190 [ 139.109980] ? putname+0x84/0xa0 [ 139.113886] ? __kasan_slab_free+0x11e/0x1b0 [ 139.117961] ? putname+0x84/0xa0 [ 139.121316] ? preempt_count_sub+0x1c/0xd0 [ 139.124427] ? __mnt_want_write+0xae/0x100 [ 139.127836] ? mnt_want_write+0x8f/0x150 [ 139.130954] path_setxattr+0x164/0x180 [ 139.133998] ? __pfx_path_setxattr+0x10/0x10 [ 139.137853] ? __pfx_ksys_pwrite64+0x10/0x10 [ 139.141299] ? debug_smp_processor_id+0x1b/0x30 [ 139.145714] ? fpregs_assert_state_consistent+0x6b/0x80 [ 139.150796] __x64_sys_setxattr+0x71/0x90 [ 139.155407] do_syscall_64+0x3f/0x90 [ 139.159035] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 139.163843] RIP: 0033:0x7f108cae4469 [ 139.166481] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 088 [ 139.183764] RSP: 002b:00007fff87588388 EFLAGS: 00000286 ORIG_RAX: 00000000000000bc [ 139.190657] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f108cae4469 [ 139.196586] RDX: 00007fff875883b0 RSI: 00007fff875883d1 RDI: 00007fff875883b6 [ 139.201716] RBP: 00007fff8758c530 R08: 0000000000000001 R09: 00007fff8758c618 [ 139.207940] R10: 0000000000000006 R11: 0000000000000286 R12: 00000000004004c0 [ 139.214007] R13: 00007fff8758c610 R14: 0000000000000000 R15 ---truncated---
CVE-2023-54227: In the Linux kernel, the following vulnerability has been resolved: blk-mq: fix tags leak when shrink nr_hw_queues Although we don't need to realloc set->tags[] when shrink nr_hw_queues, we need to free them. Or these tags will be leaked. How to reproduce: 1. mount -t configfs configfs /mnt 2. modprobe null_blk nr_devices=0 submit_queues=8 3. mkdir /mnt/nullb/nullb0 4. echo 1 > /mnt/nullb/nullb0/power 5. echo 4 > /mnt/nullb/nullb0/submit_queues 6. rmdir /mnt/nullb/nullb0 In step 4, will alloc 9 tags (8 submit queues and 1 poll queue), then in step 5, new_nr_hw_queues = 5 (4 submit queues and 1 poll queue). At last in step 6, only these 5 tags are freed, the other 4 tags leaked.
CVE-2023-54233: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: avoid a NULL dereference with unsupported widgets If an IPC4 topology contains an unsupported widget, its .module_info field won't be set, then sof_ipc4_route_setup() will cause a kernel Oops trying to dereference it. Add a check for such cases.
CVE-2023-54263: In the Linux kernel, the following vulnerability has been resolved: drm/nouveau/kms/nv50-: init hpd_irq_lock for PIOR DP Fixes OOPS on boards with ANX9805 DP encoders.
CVE-2023-54271: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init blk-iocost sometimes causes the following crash: BUG: kernel NULL pointer dereference, address: 00000000000000e0 ... RIP: 0010:_raw_spin_lock+0x17/0x30 Code: be 01 02 00 00 e8 79 38 39 ff 31 d2 89 d0 5d c3 0f 1f 00 0f 1f 44 00 00 55 48 89 e5 65 ff 05 48 d0 34 7e b9 01 00 00 00 31 c0 <f0> 0f b1 0f 75 02 5d c3 89 c6 e8 ea 04 00 00 5d c3 0f 1f 84 00 00 RSP: 0018:ffffc900023b3d40 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 00000000000000e0 RCX: 0000000000000001 RDX: ffffc900023b3d20 RSI: ffffc900023b3cf0 RDI: 00000000000000e0 RBP: ffffc900023b3d40 R08: ffffc900023b3c10 R09: 0000000000000003 R10: 0000000000000064 R11: 000000000000000a R12: ffff888102337000 R13: fffffffffffffff2 R14: ffff88810af408c8 R15: ffff8881070c3600 FS: 00007faaaf364fc0(0000) GS:ffff88842fdc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e0 CR3: 00000001097b1000 CR4: 0000000000350ea0 Call Trace: <TASK> ioc_weight_write+0x13d/0x410 cgroup_file_write+0x7a/0x130 kernfs_fop_write_iter+0xf5/0x170 vfs_write+0x298/0x370 ksys_write+0x5f/0xb0 __x64_sys_write+0x1b/0x20 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 This happens because iocg->ioc is NULL. The field is initialized by ioc_pd_init() and never cleared. The NULL deref is caused by blkcg_activate_policy() installing blkg_policy_data before initializing it. blkcg_activate_policy() was doing the following: 1. Allocate pd's for all existing blkg's and install them in blkg->pd[]. 2. Initialize all pd's. 3. Online all pd's. blkcg_activate_policy() only grabs the queue_lock and may release and re-acquire the lock as allocation may need to sleep. ioc_weight_write() grabs blkcg->lock and iterates all its blkg's. The two can race and if ioc_weight_write() runs during #1 or between #1 and #2, it can encounter a pd which is not initialized yet, leading to crash. The crash can be reproduced with the following script: #!/bin/bash echo +io > /sys/fs/cgroup/cgroup.subtree_control systemd-run --unit touch-sda --scope dd if=/dev/sda of=/dev/null bs=1M count=1 iflag=direct echo 100 > /sys/fs/cgroup/system.slice/io.weight bash -c "echo '8:0 enable=1' > /sys/fs/cgroup/io.cost.qos" & sleep .2 echo 100 > /sys/fs/cgroup/system.slice/io.weight with the following patch applied: > diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c > index fc49be622e05..38d671d5e10c 100644 > --- a/block/blk-cgroup.c > +++ b/block/blk-cgroup.c > @@ -1553,6 +1553,12 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) > pd->online = false; > } > > + if (system_state == SYSTEM_RUNNING) { > + spin_unlock_irq(&q->queue_lock); > + ssleep(1); > + spin_lock_irq(&q->queue_lock); > + } > + > /* all allocated, init in the same order */ > if (pol->pd_init_fn) > list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) I don't see a reason why all pd's should be allocated, initialized and onlined together. The only ordering requirement is that parent blkgs to be initialized and onlined before children, which is guaranteed from the walking order. Let's fix the bug by allocating, initializing and onlining pd for each blkg and holding blkcg->lock over initialization and onlining. This ensures that an installed blkg is always fully initialized and onlined removing the the race window.
CVE-2023-54280: In the Linux kernel, the following vulnerability has been resolved: cifs: fix potential race when tree connecting ipc Protect access of TCP_Server_Info::hostname when building the ipc tree name as it might get freed in cifsd thread and thus causing an use-after-free bug in __tree_connect_dfs_target(). Also, while at it, update status of IPC tcon on success and then avoid any extra tree connects.
CVE-2023-54322: In the Linux kernel, the following vulnerability has been resolved: arm64: set __exception_irq_entry with __irq_entry as a default filter_irq_stacks() is supposed to cut entries which are related irq entries from its call stack. And in_irqentry_text() which is called by filter_irq_stacks() uses __irqentry_text_start/end symbol to find irq entries in callstack. But it doesn't work correctly as without "CONFIG_FUNCTION_GRAPH_TRACER", arm64 kernel doesn't include gic_handle_irq which is entry point of arm64 irq between __irqentry_text_start and __irqentry_text_end as we discussed in below link. https://lore.kernel.org/all/CACT4Y+aReMGLYua2rCLHgFpS9io5cZC04Q8GLs-uNmrn1ezxYQ@mail.gmail.com/#t This problem can makes unintentional deep call stack entries especially in KASAN enabled situation as below. [ 2479.383395]I[0:launcher-loader: 1719] Stack depot reached limit capacity [ 2479.383538]I[0:launcher-loader: 1719] WARNING: CPU: 0 PID: 1719 at lib/stackdepot.c:129 __stack_depot_save+0x464/0x46c [ 2479.385693]I[0:launcher-loader: 1719] pstate: 624000c5 (nZCv daIF +PAN -UAO +TCO -DIT -SSBS BTYPE=--) [ 2479.385724]I[0:launcher-loader: 1719] pc : __stack_depot_save+0x464/0x46c [ 2479.385751]I[0:launcher-loader: 1719] lr : __stack_depot_save+0x460/0x46c [ 2479.385774]I[0:launcher-loader: 1719] sp : ffffffc0080073c0 [ 2479.385793]I[0:launcher-loader: 1719] x29: ffffffc0080073e0 x28: ffffffd00b78a000 x27: 0000000000000000 [ 2479.385839]I[0:launcher-loader: 1719] x26: 000000000004d1dd x25: ffffff891474f000 x24: 00000000ca64d1dd [ 2479.385882]I[0:launcher-loader: 1719] x23: 0000000000000200 x22: 0000000000000220 x21: 0000000000000040 [ 2479.385925]I[0:launcher-loader: 1719] x20: ffffffc008007440 x19: 0000000000000000 x18: 0000000000000000 [ 2479.385969]I[0:launcher-loader: 1719] x17: 2065726568207475 x16: 000000000000005e x15: 2d2d2d2d2d2d2d20 [ 2479.386013]I[0:launcher-loader: 1719] x14: 5d39313731203a72 x13: 00000000002f6b30 x12: 00000000002f6af8 [ 2479.386057]I[0:launcher-loader: 1719] x11: 00000000ffffffff x10: ffffffb90aacf000 x9 : e8a74a6c16008800 [ 2479.386101]I[0:launcher-loader: 1719] x8 : e8a74a6c16008800 x7 : 00000000002f6b30 x6 : 00000000002f6af8 [ 2479.386145]I[0:launcher-loader: 1719] x5 : ffffffc0080070c8 x4 : ffffffd00b192380 x3 : ffffffd0092b313c [ 2479.386189]I[0:launcher-loader: 1719] x2 : 0000000000000001 x1 : 0000000000000004 x0 : 0000000000000022 [ 2479.386231]I[0:launcher-loader: 1719] Call trace: [ 2479.386248]I[0:launcher-loader: 1719] __stack_depot_save+0x464/0x46c [ 2479.386273]I[0:launcher-loader: 1719] kasan_save_stack+0x58/0x70 [ 2479.386303]I[0:launcher-loader: 1719] save_stack_info+0x34/0x138 [ 2479.386331]I[0:launcher-loader: 1719] kasan_save_free_info+0x18/0x24 [ 2479.386358]I[0:launcher-loader: 1719] ____kasan_slab_free+0x16c/0x170 [ 2479.386385]I[0:launcher-loader: 1719] __kasan_slab_free+0x10/0x20 [ 2479.386410]I[0:launcher-loader: 1719] kmem_cache_free+0x238/0x53c [ 2479.386435]I[0:launcher-loader: 1719] mempool_free_slab+0x1c/0x28 [ 2479.386460]I[0:launcher-loader: 1719] mempool_free+0x7c/0x1a0 [ 2479.386484]I[0:launcher-loader: 1719] bvec_free+0x34/0x80 [ 2479.386514]I[0:launcher-loader: 1719] bio_free+0x60/0x98 [ 2479.386540]I[0:launcher-loader: 1719] bio_put+0x50/0x21c [ 2479.386567]I[0:launcher-loader: 1719] f2fs_write_end_io+0x4ac/0x4d0 [ 2479.386594]I[0:launcher-loader: 1719] bio_endio+0x2dc/0x300 [ 2479.386622]I[0:launcher-loader: 1719] __dm_io_complete+0x324/0x37c [ 2479.386650]I[0:launcher-loader: 1719] dm_io_dec_pending+0x60/0xa4 [ 2479.386676]I[0:launcher-loader: 1719] clone_endio+0xf8/0x2f0 [ 2479.386700]I[0:launcher-loader: 1719] bio_endio+0x2dc/0x300 [ 2479.386727]I[0:launcher-loader: 1719] blk_update_request+0x258/0x63c [ 2479.386754]I[0:launcher-loader: 1719] scsi_end_request+0x50/0x304 [ 2479.386782]I[0:launcher-loader: 1719] scsi_io_completion+0x88/0x160 [ 2479.386808]I[0:launcher-loader: 1719] scsi_finish_command+0x17c/0x194 [ 2479.386833]I ---truncated---
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-25740: A memory leak flaw was found in the UBI driver in drivers/mtd/ubi/attach.c in the Linux kernel through 6.7.4 for UBI_IOCATT, because kobj->name is not released.
CVE-2024-25742: In the Linux kernel before 6.9, an untrusted hypervisor can inject virtual interrupt 29 (#VC) at any point in time and can trigger its handler. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-25743: In the Linux kernel through 6.9, an untrusted hypervisor can inject virtual interrupts 0 and 14 at any point in time and can trigger the SIGFPE signal handler in userspace applications. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-26661: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL test for 'timing generator' in 'dcn21_set_pipe()' In "u32 otg_inst = pipe_ctx->stream_res.tg->inst;" pipe_ctx->stream_res.tg could be NULL, it is relying on the caller to ensure the tg is not NULL.
CVE-2024-26662: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix 'panel_cntl' could be null in 'dcn21_set_backlight_level()' 'panel_cntl' structure used to control the display panel could be null, dereferencing it could lead to a null pointer access. Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn21/dcn21_hwseq.c:269 dcn21_set_backlight_level() error: we previously assumed 'panel_cntl' could be null (see line 250)
CVE-2024-26669: In the Linux kernel, the following vulnerability has been resolved: net/sched: flower: Fix chain template offload When a qdisc is deleted from a net device the stack instructs the underlying driver to remove its flow offload callback from the associated filter block using the 'FLOW_BLOCK_UNBIND' command. The stack then continues to replay the removal of the filters in the block for this driver by iterating over the chains in the block and invoking the 'reoffload' operation of the classifier being used. In turn, the classifier in its 'reoffload' operation prepares and emits a 'FLOW_CLS_DESTROY' command for each filter. However, the stack does not do the same for chain templates and the underlying driver never receives a 'FLOW_CLS_TMPLT_DESTROY' command when a qdisc is deleted. This results in a memory leak [1] which can be reproduced using [2]. Fix by introducing a 'tmplt_reoffload' operation and have the stack invoke it with the appropriate arguments as part of the replay. Implement the operation in the sole classifier that supports chain templates (flower) by emitting the 'FLOW_CLS_TMPLT_{CREATE,DESTROY}' command based on whether a flow offload callback is being bound to a filter block or being unbound from one. As far as I can tell, the issue happens since cited commit which reordered tcf_block_offload_unbind() before tcf_block_flush_all_chains() in __tcf_block_put(). The order cannot be reversed as the filter block is expected to be freed after flushing all the chains. [1] unreferenced object 0xffff888107e28800 (size 2048): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): b1 a6 7c 11 81 88 ff ff e0 5b b3 10 81 88 ff ff ..|......[...... 01 00 00 00 00 00 00 00 e0 aa b0 84 ff ff ff ff ................ backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab374e>] __kmalloc+0x4e/0x90 [<ffffffff832aec6d>] mlxsw_sp_acl_ruleset_get+0x34d/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80 [<ffffffff8379d29a>] ___sys_sendmsg+0x13a/0x1e0 [<ffffffff8379d50c>] __sys_sendmsg+0x11c/0x1f0 [<ffffffff843b9ce0>] do_syscall_64+0x40/0xe0 unreferenced object 0xffff88816d2c0400 (size 1024): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): 40 00 00 00 00 00 00 00 57 f6 38 be 00 00 00 00 @.......W.8..... 10 04 2c 6d 81 88 ff ff 10 04 2c 6d 81 88 ff ff ..,m......,m.... backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab36c1>] __kmalloc_node+0x51/0x90 [<ffffffff81a8ed96>] kvmalloc_node+0xa6/0x1f0 [<ffffffff82827d03>] bucket_table_alloc.isra.0+0x83/0x460 [<ffffffff82828d2b>] rhashtable_init+0x43b/0x7c0 [<ffffffff832aed48>] mlxsw_sp_acl_ruleset_get+0x428/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80 [2] # tc qdisc add dev swp1 clsact # tc chain add dev swp1 ingress proto ip chain 1 flower dst_ip 0.0.0.0/32 # tc qdisc del dev ---truncated---
CVE-2024-26670: In the Linux kernel, the following vulnerability has been resolved: arm64: entry: fix ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD Currently the ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround isn't quite right, as it is supposed to be applied after the last explicit memory access, but is immediately followed by an LDR. The ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD workaround is used to handle Cortex-A520 erratum 2966298 and Cortex-A510 erratum 3117295, which are described in: * https://developer.arm.com/documentation/SDEN2444153/0600/?lang=en * https://developer.arm.com/documentation/SDEN1873361/1600/?lang=en In both cases the workaround is described as: | If pagetable isolation is disabled, the context switch logic in the | kernel can be updated to execute the following sequence on affected | cores before exiting to EL0, and after all explicit memory accesses: | | 1. A non-shareable TLBI to any context and/or address, including | unused contexts or addresses, such as a `TLBI VALE1 Xzr`. | | 2. A DSB NSH to guarantee completion of the TLBI. The important part being that the TLBI+DSB must be placed "after all explicit memory accesses". Unfortunately, as-implemented, the TLBI+DSB is immediately followed by an LDR, as we have: | alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD | tlbi vale1, xzr | dsb nsh | alternative_else_nop_endif | alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 | ldr lr, [sp, #S_LR] | add sp, sp, #PT_REGS_SIZE // restore sp | eret | alternative_else_nop_endif | | [ ... KPTI exception return path ... ] This patch fixes this by reworking the logic to place the TLBI+DSB immediately before the ERET, after all explicit memory accesses. The ERET is currently in a separate alternative block, and alternatives cannot be nested. To account for this, the alternative block for ARM64_UNMAP_KERNEL_AT_EL0 is replaced with a single alternative branch to skip the KPTI logic, with the new shape of the logic being: | alternative_insn "b .L_skip_tramp_exit_\@", nop, ARM64_UNMAP_KERNEL_AT_EL0 | [ ... KPTI exception return path ... ] | .L_skip_tramp_exit_\@: | | ldr lr, [sp, #S_LR] | add sp, sp, #PT_REGS_SIZE // restore sp | | alternative_if ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD | tlbi vale1, xzr | dsb nsh | alternative_else_nop_endif | eret The new structure means that the workaround is only applied when KPTI is not in use; this is fine as noted in the documented implications of the erratum: | Pagetable isolation between EL0 and higher level ELs prevents the | issue from occurring. ... and as per the workaround description quoted above, the workaround is only necessary "If pagetable isolation is disabled".
CVE-2024-26672: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix variable 'mca_funcs' dereferenced before NULL check in 'amdgpu_mca_smu_get_mca_entry()' Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c:377 amdgpu_mca_smu_get_mca_entry() warn: variable dereferenced before check 'mca_funcs' (see line 368) 357 int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, 358 int idx, struct mca_bank_entry *entry) 359 { 360 const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; 361 int count; 362 363 switch (type) { 364 case AMDGPU_MCA_ERROR_TYPE_UE: 365 count = mca_funcs->max_ue_count; mca_funcs is dereferenced here. 366 break; 367 case AMDGPU_MCA_ERROR_TYPE_CE: 368 count = mca_funcs->max_ce_count; mca_funcs is dereferenced here. 369 break; 370 default: 371 return -EINVAL; 372 } 373 374 if (idx >= count) 375 return -EINVAL; 376 377 if (mca_funcs && mca_funcs->mca_get_mca_entry) ^^^^^^^^^ Checked too late!
CVE-2024-26677: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix delayed ACKs to not set the reference serial number Fix the construction of delayed ACKs to not set the reference serial number as they can't be used as an RTT reference.
CVE-2024-26691: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Fix circular locking dependency The rule inside kvm enforces that the vcpu->mutex is taken *inside* kvm->lock. The rule is violated by the pkvm_create_hyp_vm() which acquires the kvm->lock while already holding the vcpu->mutex lock from kvm_vcpu_ioctl(). Avoid the circular locking dependency altogether by protecting the hyp vm handle with the config_lock, much like we already do for other forms of VM-scoped data.
CVE-2024-26740: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_mirred: use the backlog for mirred ingress The test Davide added in commit ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") hangs our testing VMs every 10 or so runs, with the familiar tcp_v4_rcv -> tcp_v4_rcv deadlock reported by lockdep. The problem as previously described by Davide (see Link) is that if we reverse flow of traffic with the redirect (egress -> ingress) we may reach the same socket which generated the packet. And we may still be holding its socket lock. The common solution to such deadlocks is to put the packet in the Rx backlog, rather than run the Rx path inline. Do that for all egress -> ingress reversals, not just once we started to nest mirred calls. In the past there was a concern that the backlog indirection will lead to loss of error reporting / less accurate stats. But the current workaround does not seem to address the issue.
CVE-2024-26756: In the Linux kernel, the following vulnerability has been resolved: md: Don't register sync_thread for reshape directly Currently, if reshape is interrupted, then reassemble the array will register sync_thread directly from pers->run(), in this case 'MD_RECOVERY_RUNNING' is set directly, however, there is no guarantee that md_do_sync() will be executed, hence stop_sync_thread() will hang because 'MD_RECOVERY_RUNNING' can't be cleared. Last patch make sure that md_do_sync() will set MD_RECOVERY_DONE, however, following hang can still be triggered by dm-raid test shell/lvconvert-raid-reshape.sh occasionally: [root@fedora ~]# cat /proc/1982/stack [<0>] stop_sync_thread+0x1ab/0x270 [md_mod] [<0>] md_frozen_sync_thread+0x5c/0xa0 [md_mod] [<0>] raid_presuspend+0x1e/0x70 [dm_raid] [<0>] dm_table_presuspend_targets+0x40/0xb0 [dm_mod] [<0>] __dm_destroy+0x2a5/0x310 [dm_mod] [<0>] dm_destroy+0x16/0x30 [dm_mod] [<0>] dev_remove+0x165/0x290 [dm_mod] [<0>] ctl_ioctl+0x4bb/0x7b0 [dm_mod] [<0>] dm_ctl_ioctl+0x11/0x20 [dm_mod] [<0>] vfs_ioctl+0x21/0x60 [<0>] __x64_sys_ioctl+0xb9/0xe0 [<0>] do_syscall_64+0xc6/0x230 [<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74 Meanwhile mddev->recovery is: MD_RECOVERY_RUNNING | MD_RECOVERY_INTR | MD_RECOVERY_RESHAPE | MD_RECOVERY_FROZEN Fix this problem by remove the code to register sync_thread directly from raid10 and raid5. And let md_check_recovery() to register sync_thread.
CVE-2024-26757: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore read-only array in md_check_recovery() Usually if the array is not read-write, md_check_recovery() won't register new sync_thread in the first place. And if the array is read-write and sync_thread is registered, md_set_readonly() will unregister sync_thread before setting the array read-only. md/raid follow this behavior hence there is no problem. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) array is read-only. dm-raid update super block: rs_update_sbs ro = mddev->ro mddev->ro = 0 -> set array read-write md_update_sb 2) register new sync thread concurrently. 3) dm-raid set array back to read-only: rs_update_sbs mddev->ro = ro 4) stop the array: raid_dtr md_stop stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 5) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 6) daemon thread can't unregister sync thread: md_check_recovery if (!md_is_rdwr(mddev) && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return; -> -> MD_RECOVERY_RUNNING can't be cleared, hence step 4 hang; The root cause is that dm-raid manipulate 'mddev->ro' by itself, however, dm-raid really should stop sync thread before setting the array read-only. Unfortunately, I need to read more code before I can refacter the handler of 'mddev->ro' in dm-raid, hence let's fix the problem the easy way for now to prevent dm-raid regression.
CVE-2024-26758: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore suspended array in md_check_recovery() mddev_suspend() never stop sync_thread, hence it doesn't make sense to ignore suspended array in md_check_recovery(), which might cause sync_thread can't be unregistered. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) suspend the array: raid_postsuspend mddev_suspend 2) stop the array: raid_dtr md_stop __md_stop_writes stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 3) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 4) daemon thread can't unregister sync thread: md_check_recovery if (mddev->suspended) return; -> return directly md_read_sync_thread clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); -> MD_RECOVERY_RUNNING can't be cleared, hence step 2 hang; This problem is not just related to dm-raid, fix it by ignoring suspended array in md_check_recovery(). And follow up patches will improve dm-raid better to frozen sync thread during suspend.
CVE-2024-26768: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Change acpi_core_pic[NR_CPUS] to acpi_core_pic[MAX_CORE_PIC] With default config, the value of NR_CPUS is 64. When HW platform has more then 64 cpus, system will crash on these platforms. MAX_CORE_PIC is the maximum cpu number in MADT table (max physical number) which can exceed the supported maximum cpu number (NR_CPUS, max logical number), but kernel should not crash. Kernel should boot cpus with NR_CPUS, let the remainder cpus stay in BIOS. The potential crash reason is that the array acpi_core_pic[NR_CPUS] can be overflowed when parsing MADT table, and it is obvious that CORE_PIC should be corresponding to physical core rather than logical core, so it is better to define the array as acpi_core_pic[MAX_CORE_PIC]. With the patch, system can boot up 64 vcpus with qemu parameter -smp 128, otherwise system will crash with the following message. [ 0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000420000004259, era == 90000000037a5f0c, ra == 90000000037a46ec [ 0.000000] Oops[#1]: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.8.0-rc2+ #192 [ 0.000000] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022 [ 0.000000] pc 90000000037a5f0c ra 90000000037a46ec tp 9000000003c90000 sp 9000000003c93d60 [ 0.000000] a0 0000000000000019 a1 9000000003d93bc0 a2 0000000000000000 a3 9000000003c93bd8 [ 0.000000] a4 9000000003c93a74 a5 9000000083c93a67 a6 9000000003c938f0 a7 0000000000000005 [ 0.000000] t0 0000420000004201 t1 0000000000000000 t2 0000000000000001 t3 0000000000000001 [ 0.000000] t4 0000000000000003 t5 0000000000000000 t6 0000000000000030 t7 0000000000000063 [ 0.000000] t8 0000000000000014 u0 ffffffffffffffff s9 0000000000000000 s0 9000000003caee98 [ 0.000000] s1 90000000041b0480 s2 9000000003c93da0 s3 9000000003c93d98 s4 9000000003c93d90 [ 0.000000] s5 9000000003caa000 s6 000000000a7fd000 s7 000000000f556b60 s8 000000000e0a4330 [ 0.000000] ra: 90000000037a46ec platform_init+0x214/0x250 [ 0.000000] ERA: 90000000037a5f0c efi_runtime_init+0x30/0x94 [ 0.000000] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 0.000000] PRMD: 00000000 (PPLV0 -PIE -PWE) [ 0.000000] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 0.000000] ECFG: 00070800 (LIE=11 VS=7) [ 0.000000] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) [ 0.000000] BADV: 0000420000004259 [ 0.000000] PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) [ 0.000000] Modules linked in: [ 0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____)) [ 0.000000] Stack : 9000000003c93a14 9000000003800898 90000000041844f8 90000000037a46ec [ 0.000000] 000000000a7fd000 0000000008290000 0000000000000000 0000000000000000 [ 0.000000] 0000000000000000 0000000000000000 00000000019d8000 000000000f556b60 [ 0.000000] 000000000a7fd000 000000000f556b08 9000000003ca7700 9000000003800000 [ 0.000000] 9000000003c93e50 9000000003800898 9000000003800108 90000000037a484c [ 0.000000] 000000000e0a4330 000000000f556b60 000000000a7fd000 000000000f556b08 [ 0.000000] 9000000003ca7700 9000000004184000 0000000000200000 000000000e02b018 [ 0.000000] 000000000a7fd000 90000000037a0790 9000000003800108 0000000000000000 [ 0.000000] 0000000000000000 000000000e0a4330 000000000f556b60 000000000a7fd000 [ 0.000000] 000000000f556b08 000000000eaae298 000000000eaa5040 0000000000200000 [ 0.000000] ... [ 0.000000] Call Trace: [ 0.000000] [<90000000037a5f0c>] efi_runtime_init+0x30/0x94 [ 0.000000] [<90000000037a46ec>] platform_init+0x214/0x250 [ 0.000000] [<90000000037a484c>] setup_arch+0x124/0x45c [ 0.000000] [<90000000037a0790>] start_kernel+0x90/0x670 [ 0.000000] [<900000000378b0d8>] kernel_entry+0xd8/0xdc
CVE-2024-26799: In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: Fix uninitialized pointer dmactl In the case where __lpass_get_dmactl_handle is called and the driver id dai_id is invalid the pointer dmactl is not being assigned a value, and dmactl contains a garbage value since it has not been initialized and so the null check may not work. Fix this to initialize dmactl to NULL. One could argue that modern compilers will set this to zero, but it is useful to keep this initialized as per the same way in functions __lpass_platform_codec_intf_init and lpass_cdc_dma_daiops_hw_params. Cleans up clang scan build warning: sound/soc/qcom/lpass-cdc-dma.c:275:7: warning: Branch condition evaluates to a garbage value [core.uninitialized.Branch]
CVE-2024-26836: In the Linux kernel, the following vulnerability has been resolved: platform/x86: think-lmi: Fix password opcode ordering for workstations The Lenovo workstations require the password opcode to be run before the attribute value is changed (if Admin password is enabled). Tested on some Thinkpads to confirm they are OK with this order too.
CVE-2024-26841: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Update cpu_sibling_map when disabling nonboot CPUs Update cpu_sibling_map when disabling nonboot CPUs by defining & calling clear_cpu_sibling_map(), otherwise we get such errors on SMT systems: jump label: negative count! WARNING: CPU: 6 PID: 45 at kernel/jump_label.c:263 __static_key_slow_dec_cpuslocked+0xec/0x100 CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 pc 90000000004c302c ra 90000000004c302c tp 90000001005bc000 sp 90000001005bfd20 a0 000000000000001b a1 900000000224c278 a2 90000001005bfb58 a3 900000000224c280 a4 900000000224c278 a5 90000001005bfb50 a6 0000000000000001 a7 0000000000000001 t0 ce87a4763eb5234a t1 ce87a4763eb5234a t2 0000000000000000 t3 0000000000000000 t4 0000000000000006 t5 0000000000000000 t6 0000000000000064 t7 0000000000001964 t8 000000000009ebf6 u0 9000000001f2a068 s9 0000000000000000 s0 900000000246a2d8 s1 ffffffffffffffff s2 ffffffffffffffff s3 90000000021518c0 s4 0000000000000040 s5 9000000002151058 s6 9000000009828e40 s7 00000000000000b4 s8 0000000000000006 ra: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 ERA: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000000 (-FPE -SXE -ASXE -BTE) ECFG: 00071c1c (LIE=2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014d000 (Loongson-64bit, Loongson-3A6000-HV) CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 Stack : 0000000000000000 900000000203f258 900000000179afc8 90000001005bc000 90000001005bf980 0000000000000000 90000001005bf988 9000000001fe0be0 900000000224c280 900000000224c278 90000001005bf8c0 0000000000000001 0000000000000001 ce87a4763eb5234a 0000000007f38000 90000001003f8cc0 0000000000000000 0000000000000006 0000000000000000 4c206e6f73676e6f 6f4c203a656d616e 000000000009ec99 0000000007f38000 0000000000000000 900000000214b000 9000000001fe0be0 0000000000000004 0000000000000000 0000000000000107 0000000000000009 ffffffffffafdabe 00000000000000b4 0000000000000006 90000000004c302c 9000000000224528 00005555939a0c7c 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c ... Call Trace: [<9000000000224528>] show_stack+0x48/0x1a0 [<900000000179afc8>] dump_stack_lvl+0x78/0xa0 [<9000000000263ed0>] __warn+0x90/0x1a0 [<90000000017419b8>] report_bug+0x1b8/0x280 [<900000000179c564>] do_bp+0x264/0x420 [<90000000004c302c>] __static_key_slow_dec_cpuslocked+0xec/0x100 [<90000000002b4d7c>] sched_cpu_deactivate+0x2fc/0x300 [<9000000000266498>] cpuhp_invoke_callback+0x178/0x8a0 [<9000000000267f70>] cpuhp_thread_fun+0xf0/0x240 [<90000000002a117c>] smpboot_thread_fn+0x1dc/0x2e0 [<900000000029a720>] kthread+0x140/0x160 [<9000000000222288>] ret_from_kernel_thread+0xc/0xa4
CVE-2024-26866: In the Linux kernel, the following vulnerability has been resolved: spi: lpspi: Avoid potential use-after-free in probe() fsl_lpspi_probe() is allocating/disposing memory manually with spi_alloc_host()/spi_alloc_target(), but uses devm_spi_register_controller(). In case of error after the latter call the memory will be explicitly freed in the probe function by spi_controller_put() call, but used afterwards by "devm" management outside probe() (spi_unregister_controller() <- devm_spi_unregister() below). Unable to handle kernel NULL pointer dereference at virtual address 0000000000000070 ... Call trace: kernfs_find_ns kernfs_find_and_get_ns sysfs_remove_group sysfs_remove_groups device_remove_attrs device_del spi_unregister_controller devm_spi_unregister release_nodes devres_release_all really_probe driver_probe_device __device_attach_driver bus_for_each_drv __device_attach device_initial_probe bus_probe_device deferred_probe_work_func process_one_work worker_thread kthread ret_from_fork
CVE-2024-26869: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to truncate meta inode pages forcely Below race case can cause data corruption: Thread A GC thread - gc_data_segment - ra_data_block - locked meta_inode page - f2fs_inplace_write_data - invalidate_mapping_pages : fail to invalidate meta_inode page due to lock failure or dirty|writeback status - f2fs_submit_page_bio : write last dirty data to old blkaddr - move_data_block - load old data from meta_inode page - f2fs_submit_page_write : write old data to new blkaddr Because invalidate_mapping_pages() will skip invalidating page which has unclear status including locked, dirty, writeback and so on, so we need to use truncate_inode_pages_range() instead of invalidate_mapping_pages() to make sure meta_inode page will be dropped.
CVE-2024-26876: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: adv7511: fix crash on irq during probe Moved IRQ registration down to end of adv7511_probe(). If an IRQ already is pending during adv7511_probe (before adv7511_cec_init) then cec_received_msg_ts could crash using uninitialized data: Unable to handle kernel read from unreadable memory at virtual address 00000000000003d5 Internal error: Oops: 96000004 [#1] PREEMPT_RT SMP Call trace: cec_received_msg_ts+0x48/0x990 [cec] adv7511_cec_irq_process+0x1cc/0x308 [adv7511] adv7511_irq_process+0xd8/0x120 [adv7511] adv7511_irq_handler+0x1c/0x30 [adv7511] irq_thread_fn+0x30/0xa0 irq_thread+0x14c/0x238 kthread+0x190/0x1a8
CVE-2024-26902: In the Linux kernel, the following vulnerability has been resolved: perf: RISCV: Fix panic on pmu overflow handler (1 << idx) of int is not desired when setting bits in unsigned long overflowed_ctrs, use BIT() instead. This panic happens when running 'perf record -e branches' on sophgo sg2042. [ 273.311852] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000098 [ 273.320851] Oops [#1] [ 273.323179] Modules linked in: [ 273.326303] CPU: 0 PID: 1475 Comm: perf Not tainted 6.6.0-rc3+ #9 [ 273.332521] Hardware name: Sophgo Mango (DT) [ 273.336878] epc : riscv_pmu_ctr_get_width_mask+0x8/0x62 [ 273.342291] ra : pmu_sbi_ovf_handler+0x2e0/0x34e [ 273.347091] epc : ffffffff80aecd98 ra : ffffffff80aee056 sp : fffffff6e36928b0 [ 273.354454] gp : ffffffff821f82d0 tp : ffffffd90c353200 t0 : 0000002ade4f9978 [ 273.361815] t1 : 0000000000504d55 t2 : ffffffff8016cd8c s0 : fffffff6e3692a70 [ 273.369180] s1 : 0000000000000020 a0 : 0000000000000000 a1 : 00001a8e81800000 [ 273.376540] a2 : 0000003c00070198 a3 : 0000003c00db75a4 a4 : 0000000000000015 [ 273.383901] a5 : ffffffd7ff8804b0 a6 : 0000000000000015 a7 : 000000000000002a [ 273.391327] s2 : 000000000000ffff s3 : 0000000000000000 s4 : ffffffd7ff8803b0 [ 273.398773] s5 : 0000000000504d55 s6 : ffffffd905069800 s7 : ffffffff821fe210 [ 273.406139] s8 : 000000007fffffff s9 : ffffffd7ff8803b0 s10: ffffffd903f29098 [ 273.413660] s11: 0000000080000000 t3 : 0000000000000003 t4 : ffffffff8017a0ca [ 273.421022] t5 : ffffffff8023cfc2 t6 : ffffffd9040780e8 [ 273.426437] status: 0000000200000100 badaddr: 0000000000000098 cause: 000000000000000d [ 273.434512] [<ffffffff80aecd98>] riscv_pmu_ctr_get_width_mask+0x8/0x62 [ 273.441169] [<ffffffff80076bd8>] handle_percpu_devid_irq+0x98/0x1ee [ 273.447562] [<ffffffff80071158>] generic_handle_domain_irq+0x28/0x36 [ 273.454151] [<ffffffff8047a99a>] riscv_intc_irq+0x36/0x4e [ 273.459659] [<ffffffff80c944de>] handle_riscv_irq+0x4a/0x74 [ 273.465442] [<ffffffff80c94c48>] do_irq+0x62/0x92 [ 273.470360] Code: 0420 60a2 6402 5529 0141 8082 0013 0000 0013 0000 (6d5c) b783 [ 273.477921] ---[ end trace 0000000000000000 ]--- [ 273.482630] Kernel panic - not syncing: Fatal exception in interrupt
CVE-2024-26913: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix dcn35 8k30 Underflow/Corruption Issue [why] odm calculation is missing for pipe split policy determination and cause Underflow/Corruption issue. [how] Add the odm calculation.
CVE-2024-26914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix incorrect mpc_combine array size [why] MAX_SURFACES is per stream, while MAX_PLANES is per asic. The mpc_combine is an array that records all the planes per asic. Therefore MAX_PLANES should be used as the array size. Using MAX_SURFACES causes array overflow when there are more than 3 planes. [how] Use the MAX_PLANES for the mpc_combine array size.
CVE-2024-26944: In the Linux kernel, the following vulnerability has been resolved: btrfs: zoned: fix use-after-free in do_zone_finish() Shinichiro reported the following use-after-free triggered by the device replace operation in fstests btrfs/070. BTRFS info (device nullb1): scrub: finished on devid 1 with status: 0 ================================================================== BUG: KASAN: slab-use-after-free in do_zone_finish+0x91a/0xb90 [btrfs] Read of size 8 at addr ffff8881543c8060 by task btrfs-cleaner/3494007 CPU: 0 PID: 3494007 Comm: btrfs-cleaner Tainted: G W 6.8.0-rc5-kts #1 Hardware name: Supermicro Super Server/X11SPi-TF, BIOS 3.3 02/21/2020 Call Trace: <TASK> dump_stack_lvl+0x5b/0x90 print_report+0xcf/0x670 ? __virt_addr_valid+0x200/0x3e0 kasan_report+0xd8/0x110 ? do_zone_finish+0x91a/0xb90 [btrfs] ? do_zone_finish+0x91a/0xb90 [btrfs] do_zone_finish+0x91a/0xb90 [btrfs] btrfs_delete_unused_bgs+0x5e1/0x1750 [btrfs] ? __pfx_btrfs_delete_unused_bgs+0x10/0x10 [btrfs] ? btrfs_put_root+0x2d/0x220 [btrfs] ? btrfs_clean_one_deleted_snapshot+0x299/0x430 [btrfs] cleaner_kthread+0x21e/0x380 [btrfs] ? __pfx_cleaner_kthread+0x10/0x10 [btrfs] kthread+0x2e3/0x3c0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Allocated by task 3493983: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 btrfs_alloc_device+0xb3/0x4e0 [btrfs] device_list_add.constprop.0+0x993/0x1630 [btrfs] btrfs_scan_one_device+0x219/0x3d0 [btrfs] btrfs_control_ioctl+0x26e/0x310 [btrfs] __x64_sys_ioctl+0x134/0x1b0 do_syscall_64+0x99/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 Freed by task 3494056: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3f/0x60 poison_slab_object+0x102/0x170 __kasan_slab_free+0x32/0x70 kfree+0x11b/0x320 btrfs_rm_dev_replace_free_srcdev+0xca/0x280 [btrfs] btrfs_dev_replace_finishing+0xd7e/0x14f0 [btrfs] btrfs_dev_replace_by_ioctl+0x1286/0x25a0 [btrfs] btrfs_ioctl+0xb27/0x57d0 [btrfs] __x64_sys_ioctl+0x134/0x1b0 do_syscall_64+0x99/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 The buggy address belongs to the object at ffff8881543c8000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 96 bytes inside of freed 1024-byte region [ffff8881543c8000, ffff8881543c8400) The buggy address belongs to the physical page: page:00000000fe2c1285 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1543c8 head:00000000fe2c1285 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x17ffffc0000840(slab|head|node=0|zone=2|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 0017ffffc0000840 ffff888100042dc0 ffffea0019e8f200 dead000000000002 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881543c7f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8881543c7f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff8881543c8000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8881543c8080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881543c8100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb This UAF happens because we're accessing stale zone information of a already removed btrfs_device in do_zone_finish(). The sequence of events is as follows: btrfs_dev_replace_start btrfs_scrub_dev btrfs_dev_replace_finishing btrfs_dev_replace_update_device_in_mapping_tree <-- devices replaced btrfs_rm_dev_replace_free_srcdev btrfs_free_device <-- device freed cleaner_kthread btrfs_delete_unused_bgs btrfs_zone_finish do_zone_finish <-- refers the freed device The reason for this is that we're using a ---truncated---
CVE-2024-26947: In the Linux kernel, the following vulnerability has been resolved: ARM: 9359/1: flush: check if the folio is reserved for no-mapping addresses Since commit a4d5613c4dc6 ("arm: extend pfn_valid to take into account freed memory map alignment") changes the semantics of pfn_valid() to check presence of the memory map for a PFN. A valid page for an address which is reserved but not mapped by the kernel[1], the system crashed during some uio test with the following memory layout: node 0: [mem 0x00000000c0a00000-0x00000000cc8fffff] node 0: [mem 0x00000000d0000000-0x00000000da1fffff] the uio layout is：0xc0900000, 0x100000 the crash backtrace like: Unable to handle kernel paging request at virtual address bff00000 [...] CPU: 1 PID: 465 Comm: startapp.bin Tainted: G O 5.10.0 #1 Hardware name: Generic DT based system PC is at b15_flush_kern_dcache_area+0x24/0x3c LR is at __sync_icache_dcache+0x6c/0x98 [...] (b15_flush_kern_dcache_area) from (__sync_icache_dcache+0x6c/0x98) (__sync_icache_dcache) from (set_pte_at+0x28/0x54) (set_pte_at) from (remap_pfn_range+0x1a0/0x274) (remap_pfn_range) from (uio_mmap+0x184/0x1b8 [uio]) (uio_mmap [uio]) from (__mmap_region+0x264/0x5f4) (__mmap_region) from (__do_mmap_mm+0x3ec/0x440) (__do_mmap_mm) from (do_mmap+0x50/0x58) (do_mmap) from (vm_mmap_pgoff+0xfc/0x188) (vm_mmap_pgoff) from (ksys_mmap_pgoff+0xac/0xc4) (ksys_mmap_pgoff) from (ret_fast_syscall+0x0/0x5c) Code: e0801001 e2423001 e1c00003 f57ff04f (ee070f3e) ---[ end trace 09cf0734c3805d52 ]--- Kernel panic - not syncing: Fatal exception So check if PG_reserved was set to solve this issue. [1]: https://lore.kernel.org/lkml/Zbtdue57RO0QScJM@linux.ibm.com/
CVE-2024-26948: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add a dc_state NULL check in dc_state_release [How] Check wheather state is NULL before releasing it.
CVE-2024-26953: In the Linux kernel, the following vulnerability has been resolved: net: esp: fix bad handling of pages from page_pool When the skb is reorganized during esp_output (!esp->inline), the pages coming from the original skb fragments are supposed to be released back to the system through put_page. But if the skb fragment pages are originating from a page_pool, calling put_page on them will trigger a page_pool leak which will eventually result in a crash. This leak can be easily observed when using CONFIG_DEBUG_VM and doing ipsec + gre (non offloaded) forwarding: BUG: Bad page state in process ksoftirqd/16 pfn:1451b6 page:00000000de2b8d32 refcount:0 mapcount:0 mapping:0000000000000000 index:0x1451b6000 pfn:0x1451b6 flags: 0x200000000000000(node=0|zone=2) page_type: 0xffffffff() raw: 0200000000000000 dead000000000040 ffff88810d23c000 0000000000000000 raw: 00000001451b6000 0000000000000001 00000000ffffffff 0000000000000000 page dumped because: page_pool leak Modules linked in: ip_gre gre mlx5_ib mlx5_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay zram zsmalloc fuse [last unloaded: mlx5_core] CPU: 16 PID: 96 Comm: ksoftirqd/16 Not tainted 6.8.0-rc4+ #22 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x36/0x50 bad_page+0x70/0xf0 free_unref_page_prepare+0x27a/0x460 free_unref_page+0x38/0x120 esp_ssg_unref.isra.0+0x15f/0x200 esp_output_tail+0x66d/0x780 esp_xmit+0x2c5/0x360 validate_xmit_xfrm+0x313/0x370 ? validate_xmit_skb+0x1d/0x330 validate_xmit_skb_list+0x4c/0x70 sch_direct_xmit+0x23e/0x350 __dev_queue_xmit+0x337/0xba0 ? nf_hook_slow+0x3f/0xd0 ip_finish_output2+0x25e/0x580 iptunnel_xmit+0x19b/0x240 ip_tunnel_xmit+0x5fb/0xb60 ipgre_xmit+0x14d/0x280 [ip_gre] dev_hard_start_xmit+0xc3/0x1c0 __dev_queue_xmit+0x208/0xba0 ? nf_hook_slow+0x3f/0xd0 ip_finish_output2+0x1ca/0x580 ip_sublist_rcv_finish+0x32/0x40 ip_sublist_rcv+0x1b2/0x1f0 ? ip_rcv_finish_core.constprop.0+0x460/0x460 ip_list_rcv+0x103/0x130 __netif_receive_skb_list_core+0x181/0x1e0 netif_receive_skb_list_internal+0x1b3/0x2c0 napi_gro_receive+0xc8/0x200 gro_cell_poll+0x52/0x90 __napi_poll+0x25/0x1a0 net_rx_action+0x28e/0x300 __do_softirq+0xc3/0x276 ? sort_range+0x20/0x20 run_ksoftirqd+0x1e/0x30 smpboot_thread_fn+0xa6/0x130 kthread+0xcd/0x100 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x31/0x50 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork_asm+0x11/0x20 </TASK> The suggested fix is to introduce a new wrapper (skb_page_unref) that covers page refcounting for page_pool pages as well.
CVE-2024-26962: In the Linux kernel, the following vulnerability has been resolved: dm-raid456, md/raid456: fix a deadlock for dm-raid456 while io concurrent with reshape For raid456, if reshape is still in progress, then IO across reshape position will wait for reshape to make progress. However, for dm-raid, in following cases reshape will never make progress hence IO will hang: 1) the array is read-only; 2) MD_RECOVERY_WAIT is set; 3) MD_RECOVERY_FROZEN is set; After commit c467e97f079f ("md/raid6: use valid sector values to determine if an I/O should wait on the reshape") fix the problem that IO across reshape position doesn't wait for reshape, the dm-raid test shell/lvconvert-raid-reshape.sh start to hang: [root@fedora ~]# cat /proc/979/stack [<0>] wait_woken+0x7d/0x90 [<0>] raid5_make_request+0x929/0x1d70 [raid456] [<0>] md_handle_request+0xc2/0x3b0 [md_mod] [<0>] raid_map+0x2c/0x50 [dm_raid] [<0>] __map_bio+0x251/0x380 [dm_mod] [<0>] dm_submit_bio+0x1f0/0x760 [dm_mod] [<0>] __submit_bio+0xc2/0x1c0 [<0>] submit_bio_noacct_nocheck+0x17f/0x450 [<0>] submit_bio_noacct+0x2bc/0x780 [<0>] submit_bio+0x70/0xc0 [<0>] mpage_readahead+0x169/0x1f0 [<0>] blkdev_readahead+0x18/0x30 [<0>] read_pages+0x7c/0x3b0 [<0>] page_cache_ra_unbounded+0x1ab/0x280 [<0>] force_page_cache_ra+0x9e/0x130 [<0>] page_cache_sync_ra+0x3b/0x110 [<0>] filemap_get_pages+0x143/0xa30 [<0>] filemap_read+0xdc/0x4b0 [<0>] blkdev_read_iter+0x75/0x200 [<0>] vfs_read+0x272/0x460 [<0>] ksys_read+0x7a/0x170 [<0>] __x64_sys_read+0x1c/0x30 [<0>] do_syscall_64+0xc6/0x230 [<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74 This is because reshape can't make progress. For md/raid, the problem doesn't exist because register new sync_thread doesn't rely on the IO to be done any more: 1) If array is read-only, it can switch to read-write by ioctl/sysfs; 2) md/raid never set MD_RECOVERY_WAIT; 3) If MD_RECOVERY_FROZEN is set, mddev_suspend() doesn't hold 'reconfig_mutex', hence it can be cleared and reshape can continue by sysfs api 'sync_action'. However, I'm not sure yet how to avoid the problem in dm-raid yet. This patch on the one hand make sure raid_message() can't change sync_thread() through raid_message() after presuspend(), on the other hand detect the above 3 cases before wait for IO do be done in dm_suspend(), and let dm-raid requeue those IO.
CVE-2024-27010: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix mirred deadlock on device recursion When the mirred action is used on a classful egress qdisc and a packet is mirrored or redirected to self we hit a qdisc lock deadlock. See trace below. [..... other info removed for brevity....] [ 82.890906] [ 82.890906] ============================================ [ 82.890906] WARNING: possible recursive locking detected [ 82.890906] 6.8.0-05205-g77fadd89fe2d-dirty #213 Tainted: G W [ 82.890906] -------------------------------------------- [ 82.890906] ping/418 is trying to acquire lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] but task is already holding lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] other info that might help us debug this: [ 82.890906] Possible unsafe locking scenario: [ 82.890906] [ 82.890906] CPU0 [ 82.890906] ---- [ 82.890906] lock(&sch->q.lock); [ 82.890906] lock(&sch->q.lock); [ 82.890906] [ 82.890906] *** DEADLOCK *** [ 82.890906] [..... other info removed for brevity....] Example setup (eth0->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 Another example(eth0->eth1->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth1 tc qdisc add dev eth1 root handle 1: htb default 30 tc filter add dev eth1 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 We fix this by adding an owner field (CPU id) to struct Qdisc set after root qdisc is entered. When the softirq enters it a second time, if the qdisc owner is the same CPU, the packet is dropped to break the loop.
CVE-2024-27011: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix memleak in map from abort path The delete set command does not rely on the transaction object for element removal, therefore, a combination of delete element + delete set from the abort path could result in restoring twice the refcount of the mapping. Check for inactive element in the next generation for the delete element command in the abort path, skip restoring state if next generation bit has been already cleared. This is similar to the activate logic using the set walk iterator. [ 6170.286929] ------------[ cut here ]------------ [ 6170.286939] WARNING: CPU: 6 PID: 790302 at net/netfilter/nf_tables_api.c:2086 nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287071] Modules linked in: [...] [ 6170.287633] CPU: 6 PID: 790302 Comm: kworker/6:2 Not tainted 6.9.0-rc3+ #365 [ 6170.287768] RIP: 0010:nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287886] Code: df 48 8d 7d 58 e8 69 2e 3b df 48 8b 7d 58 e8 80 1b 37 df 48 8d 7d 68 e8 57 2e 3b df 48 8b 7d 68 e8 6e 1b 37 df 48 89 ef eb c4 <0f> 0b 48 83 c4 08 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 0f [ 6170.287895] RSP: 0018:ffff888134b8fd08 EFLAGS: 00010202 [ 6170.287904] RAX: 0000000000000001 RBX: ffff888125bffb28 RCX: dffffc0000000000 [ 6170.287912] RDX: 0000000000000003 RSI: ffffffffa20298ab RDI: ffff88811ebe4750 [ 6170.287919] RBP: ffff88811ebe4700 R08: ffff88838e812650 R09: fffffbfff0623a55 [ 6170.287926] R10: ffffffff8311d2af R11: 0000000000000001 R12: ffff888125bffb10 [ 6170.287933] R13: ffff888125bffb10 R14: dead000000000122 R15: dead000000000100 [ 6170.287940] FS: 0000000000000000(0000) GS:ffff888390b00000(0000) knlGS:0000000000000000 [ 6170.287948] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6170.287955] CR2: 00007fd31fc00710 CR3: 0000000133f60004 CR4: 00000000001706f0 [ 6170.287962] Call Trace: [ 6170.287967] <TASK> [ 6170.287973] ? __warn+0x9f/0x1a0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.288104] ? handle_bug+0x3c/0x70 [ 6170.288112] ? exc_invalid_op+0x17/0x40 [ 6170.288120] ? asm_exc_invalid_op+0x1a/0x20 [ 6170.288132] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288243] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288366] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288483] nf_tables_trans_destroy_work+0x588/0x590 [nf_tables]
CVE-2024-27012: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: restore set elements when delete set fails From abort path, nft_mapelem_activate() needs to restore refcounters to the original state. Currently, it uses the set->ops->walk() to iterate over these set elements. The existing set iterator skips inactive elements in the next generation, this does not work from the abort path to restore the original state since it has to skip active elements instead (not inactive ones). This patch moves the check for inactive elements to the set iterator callback, then it reverses the logic for the .activate case which needs to skip active elements. Toggle next generation bit for elements when delete set command is invoked and call nft_clear() from .activate (abort) path to restore the next generation bit. The splat below shows an object in mappings memleak: [43929.457523] ------------[ cut here ]------------ [43929.457532] WARNING: CPU: 0 PID: 1139 at include/net/netfilter/nf_tables.h:1237 nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [...] [43929.458014] RIP: 0010:nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458076] Code: 83 f8 01 77 ab 49 8d 7c 24 08 e8 37 5e d0 de 49 8b 6c 24 08 48 8d 7d 50 e8 e9 5c d0 de 8b 45 50 8d 50 ff 89 55 50 85 c0 75 86 <0f> 0b eb 82 0f 0b eb b3 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 [43929.458081] RSP: 0018:ffff888140f9f4b0 EFLAGS: 00010246 [43929.458086] RAX: 0000000000000000 RBX: ffff8881434f5288 RCX: dffffc0000000000 [43929.458090] RDX: 00000000ffffffff RSI: ffffffffa26d28a7 RDI: ffff88810ecc9550 [43929.458093] RBP: ffff88810ecc9500 R08: 0000000000000001 R09: ffffed10281f3e8f [43929.458096] R10: 0000000000000003 R11: ffff0000ffff0000 R12: ffff8881434f52a0 [43929.458100] R13: ffff888140f9f5f4 R14: ffff888151c7a800 R15: 0000000000000002 [43929.458103] FS: 00007f0c687c4740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000 [43929.458107] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [43929.458111] CR2: 00007f58dbe5b008 CR3: 0000000123602005 CR4: 00000000001706f0 [43929.458114] Call Trace: [43929.458118] <TASK> [43929.458121] ? __warn+0x9f/0x1a0 [43929.458127] ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458188] ? report_bug+0x1b1/0x1e0 [43929.458196] ? handle_bug+0x3c/0x70 [43929.458200] ? exc_invalid_op+0x17/0x40 [43929.458211] ? nft_setelem_data_deactivate+0xd7/0xf0 [nf_tables] [43929.458271] ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables] [43929.458332] nft_mapelem_deactivate+0x24/0x30 [nf_tables] [43929.458392] nft_rhash_walk+0xdd/0x180 [nf_tables] [43929.458453] ? __pfx_nft_rhash_walk+0x10/0x10 [nf_tables] [43929.458512] ? rb_insert_color+0x2e/0x280 [43929.458520] nft_map_deactivate+0xdc/0x1e0 [nf_tables] [43929.458582] ? __pfx_nft_map_deactivate+0x10/0x10 [nf_tables] [43929.458642] ? __pfx_nft_mapelem_deactivate+0x10/0x10 [nf_tables] [43929.458701] ? __rcu_read_unlock+0x46/0x70 [43929.458709] nft_delset+0xff/0x110 [nf_tables] [43929.458769] nft_flush_table+0x16f/0x460 [nf_tables] [43929.458830] nf_tables_deltable+0x501/0x580 [nf_tables]
CVE-2024-27041: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix NULL checks for adev->dm.dc in amdgpu_dm_fini() Since 'adev->dm.dc' in amdgpu_dm_fini() might turn out to be NULL before the call to dc_enable_dmub_notifications(), check beforehand to ensure there will not be a possible NULL-ptr-deref there. Also, since commit 1e88eb1b2c25 ("drm/amd/display: Drop CONFIG_DRM_AMD_DC_HDCP") there are two separate checks for NULL in 'adev->dm.dc' before dc_deinit_callbacks() and dc_dmub_srv_destroy(). Clean up by combining them all under one 'if'. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE.
CVE-2024-27057: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: ipc4-pcm: Workaround for crashed firmware on system suspend When the system is suspended while audio is active, the sof_ipc4_pcm_hw_free() is invoked to reset the pipelines since during suspend the DSP is turned off, streams will be re-started after resume. If the firmware crashes during while audio is running (or when we reset the stream before suspend) then the sof_ipc4_set_multi_pipeline_state() will fail with IPC error and the state change is interrupted. This will cause misalignment between the kernel and firmware state on next DSP boot resulting errors returned by firmware for IPC messages, eventually failing the audio resume. On stream close the errors are ignored so the kernel state will be corrected on the next DSP boot, so the second boot after the DSP panic. If sof_ipc4_trigger_pipelines() is called from sof_ipc4_pcm_hw_free() then state parameter is SOF_IPC4_PIPE_RESET and only in this case. Treat a forced pipeline reset similarly to how we treat a pcm_free by ignoring error on state sending to allow the kernel's state to be consistent with the state the firmware will have after the next boot.
CVE-2024-27062: In the Linux kernel, the following vulnerability has been resolved: nouveau: lock the client object tree. It appears the client object tree has no locking unless I've missed something else. Fix races around adding/removing client objects, mostly vram bar mappings. 4562.099306] general protection fault, probably for non-canonical address 0x6677ed422bceb80c: 0000 [#1] PREEMPT SMP PTI [ 4562.099314] CPU: 2 PID: 23171 Comm: deqp-vk Not tainted 6.8.0-rc6+ #27 [ 4562.099324] Hardware name: Gigabyte Technology Co., Ltd. Z390 I AORUS PRO WIFI/Z390 I AORUS PRO WIFI-CF, BIOS F8 11/05/2021 [ 4562.099330] RIP: 0010:nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099503] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 48 89 f8 48 85 f6 74 39 48 8b 87 a0 00 00 00 48 85 c0 74 12 <48> 8b 48 f8 48 39 ce 73 15 48 8b 40 10 48 85 c0 75 ee 48 c7 c0 fe [ 4562.099506] RSP: 0000:ffffa94cc420bbf8 EFLAGS: 00010206 [ 4562.099512] RAX: 6677ed422bceb814 RBX: ffff98108791f400 RCX: ffff9810f26b8f58 [ 4562.099517] RDX: 0000000000000000 RSI: ffff9810f26b9158 RDI: ffff98108791f400 [ 4562.099519] RBP: ffff9810f26b9158 R08: 0000000000000000 R09: 0000000000000000 [ 4562.099521] R10: ffffa94cc420bc48 R11: 0000000000000001 R12: ffff9810f02a7cc0 [ 4562.099526] R13: 0000000000000000 R14: 00000000000000ff R15: 0000000000000007 [ 4562.099528] FS: 00007f629c5017c0(0000) GS:ffff98142c700000(0000) knlGS:0000000000000000 [ 4562.099534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4562.099536] CR2: 00007f629a882000 CR3: 000000017019e004 CR4: 00000000003706f0 [ 4562.099541] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4562.099542] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4562.099544] Call Trace: [ 4562.099555] <TASK> [ 4562.099573] ? die_addr+0x36/0x90 [ 4562.099583] ? exc_general_protection+0x246/0x4a0 [ 4562.099593] ? asm_exc_general_protection+0x26/0x30 [ 4562.099600] ? nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099730] nvkm_ioctl+0xa1/0x250 [nouveau] [ 4562.099861] nvif_object_map_handle+0xc8/0x180 [nouveau] [ 4562.099986] nouveau_ttm_io_mem_reserve+0x122/0x270 [nouveau] [ 4562.100156] ? dma_resv_test_signaled+0x26/0xb0 [ 4562.100163] ttm_bo_vm_fault_reserved+0x97/0x3c0 [ttm] [ 4562.100182] ? __mutex_unlock_slowpath+0x2a/0x270 [ 4562.100189] nouveau_ttm_fault+0x69/0xb0 [nouveau] [ 4562.100356] __do_fault+0x32/0x150 [ 4562.100362] do_fault+0x7c/0x560 [ 4562.100369] __handle_mm_fault+0x800/0xc10 [ 4562.100382] handle_mm_fault+0x17c/0x3e0 [ 4562.100388] do_user_addr_fault+0x208/0x860 [ 4562.100395] exc_page_fault+0x7f/0x200 [ 4562.100402] asm_exc_page_fault+0x26/0x30 [ 4562.100412] RIP: 0033:0x9b9870 [ 4562.100419] Code: 85 a8 f7 ff ff 8b 8d 80 f7 ff ff 89 08 e9 18 f2 ff ff 0f 1f 84 00 00 00 00 00 44 89 32 e9 90 fa ff ff 0f 1f 84 00 00 00 00 00 <44> 89 32 e9 f8 f1 ff ff 0f 1f 84 00 00 00 00 00 66 44 89 32 e9 e7 [ 4562.100422] RSP: 002b:00007fff9ba2dc70 EFLAGS: 00010246 [ 4562.100426] RAX: 0000000000000004 RBX: 000000000dd65e10 RCX: 000000fff0000000 [ 4562.100428] RDX: 00007f629a882000 RSI: 00007f629a882000 RDI: 0000000000000066 [ 4562.100432] RBP: 00007fff9ba2e570 R08: 0000000000000000 R09: 0000000123ddf000 [ 4562.100434] R10: 0000000000000001 R11: 0000000000000246 R12: 000000007fffffff [ 4562.100436] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 4562.100446] </TASK> [ 4562.100448] Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink cmac bnep sunrpc iwlmvm intel_rapl_msr intel_rapl_common snd_sof_pci_intel_cnl x86_pkg_temp_thermal intel_powerclamp snd_sof_intel_hda_common mac80211 coretemp snd_soc_acpi_intel_match kvm_intel snd_soc_acpi snd_soc_hdac_hda snd_sof_pci snd_sof_xtensa_dsp snd_sof_intel_hda_mlink ---truncated---
CVE-2024-27079: In the Linux kernel, the following vulnerability has been resolved: iommu/vt-d: Fix NULL domain on device release In the kdump kernel, the IOMMU operates in deferred_attach mode. In this mode, info->domain may not yet be assigned by the time the release_device function is called. It leads to the following crash in the crash kernel: BUG: kernel NULL pointer dereference, address: 000000000000003c ... RIP: 0010:do_raw_spin_lock+0xa/0xa0 ... _raw_spin_lock_irqsave+0x1b/0x30 intel_iommu_release_device+0x96/0x170 iommu_deinit_device+0x39/0xf0 __iommu_group_remove_device+0xa0/0xd0 iommu_bus_notifier+0x55/0xb0 notifier_call_chain+0x5a/0xd0 blocking_notifier_call_chain+0x41/0x60 bus_notify+0x34/0x50 device_del+0x269/0x3d0 pci_remove_bus_device+0x77/0x100 p2sb_bar+0xae/0x1d0 ... i801_probe+0x423/0x740 Use the release_domain mechanism to fix it. The scalable mode context entry which is not part of release domain should be cleared in release_device().
CVE-2024-27408: In the Linux kernel, the following vulnerability has been resolved: dmaengine: dw-edma: eDMA: Add sync read before starting the DMA transfer in remote setup The Linked list element and pointer are not stored in the same memory as the eDMA controller register. If the doorbell register is toggled before the full write of the linked list a race condition error will occur. In remote setup we can only use a readl to the memory to assure the full write has occurred.
CVE-2024-35784: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix deadlock with fiemap and extent locking While working on the patchset to remove extent locking I got a lockdep splat with fiemap and pagefaulting with my new extent lock replacement lock. This deadlock exists with our normal code, we just don't have lockdep annotations with the extent locking so we've never noticed it. Since we're copying the fiemap extent to user space on every iteration we have the chance of pagefaulting. Because we hold the extent lock for the entire range we could mkwrite into a range in the file that we have mmap'ed. This would deadlock with the following stack trace [<0>] lock_extent+0x28d/0x2f0 [<0>] btrfs_page_mkwrite+0x273/0x8a0 [<0>] do_page_mkwrite+0x50/0xb0 [<0>] do_fault+0xc1/0x7b0 [<0>] __handle_mm_fault+0x2fa/0x460 [<0>] handle_mm_fault+0xa4/0x330 [<0>] do_user_addr_fault+0x1f4/0x800 [<0>] exc_page_fault+0x7c/0x1e0 [<0>] asm_exc_page_fault+0x26/0x30 [<0>] rep_movs_alternative+0x33/0x70 [<0>] _copy_to_user+0x49/0x70 [<0>] fiemap_fill_next_extent+0xc8/0x120 [<0>] emit_fiemap_extent+0x4d/0xa0 [<0>] extent_fiemap+0x7f8/0xad0 [<0>] btrfs_fiemap+0x49/0x80 [<0>] __x64_sys_ioctl+0x3e1/0xb50 [<0>] do_syscall_64+0x94/0x1a0 [<0>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 I wrote an fstest to reproduce this deadlock without my replacement lock and verified that the deadlock exists with our existing locking. To fix this simply don't take the extent lock for the entire duration of the fiemap. This is safe in general because we keep track of where we are when we're searching the tree, so if an ordered extent updates in the middle of our fiemap call we'll still emit the correct extents because we know what offset we were on before. The only place we maintain the lock is searching delalloc. Since the delalloc stuff can change during writeback we want to lock the extent range so we have a consistent view of delalloc at the time we're checking to see if we need to set the delalloc flag. With this patch applied we no longer deadlock with my testcase.
CVE-2024-35794: In the Linux kernel, the following vulnerability has been resolved: dm-raid: really frozen sync_thread during suspend 1) commit f52f5c71f3d4 ("md: fix stopping sync thread") remove MD_RECOVERY_FROZEN from __md_stop_writes() and doesn't realize that dm-raid relies on __md_stop_writes() to frozen sync_thread indirectly. Fix this problem by adding MD_RECOVERY_FROZEN in md_stop_writes(), and since stop_sync_thread() is only used for dm-raid in this case, also move stop_sync_thread() to md_stop_writes(). 2) The flag MD_RECOVERY_FROZEN doesn't mean that sync thread is frozen, it only prevent new sync_thread to start, and it can't stop the running sync thread; In order to frozen sync_thread, after seting the flag, stop_sync_thread() should be used. 3) The flag MD_RECOVERY_FROZEN doesn't mean that writes are stopped, use it as condition for md_stop_writes() in raid_postsuspend() doesn't look correct. Consider that reentrant stop_sync_thread() do nothing, always call md_stop_writes() in raid_postsuspend(). 4) raid_message can set/clear the flag MD_RECOVERY_FROZEN at anytime, and if MD_RECOVERY_FROZEN is cleared while the array is suspended, new sync_thread can start unexpected. Fix this by disallow raid_message() to change sync_thread status during suspend. Note that after commit f52f5c71f3d4 ("md: fix stopping sync thread"), the test shell/lvconvert-raid-reshape.sh start to hang in stop_sync_thread(), and with previous fixes, the test won't hang there anymore, however, the test will still fail and complain that ext4 is corrupted. And with this patch, the test won't hang due to stop_sync_thread() or fail due to ext4 is corrupted anymore. However, there is still a deadlock related to dm-raid456 that will be fixed in following patches.
CVE-2024-35799: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Prevent crash when disable stream [Why] Disabling stream encoder invokes a function that no longer exists. [How] Check if the function declaration is NULL in disable stream encoder.
CVE-2024-35808: In the Linux kernel, the following vulnerability has been resolved: md/dm-raid: don't call md_reap_sync_thread() directly Currently md_reap_sync_thread() is called from raid_message() directly without holding 'reconfig_mutex', this is definitely unsafe because md_reap_sync_thread() can change many fields that is protected by 'reconfig_mutex'. However, hold 'reconfig_mutex' here is still problematic because this will cause deadlock, for example, commit 130443d60b1b ("md: refactor idle/frozen_sync_thread() to fix deadlock"). Fix this problem by using stop_sync_thread() to unregister sync_thread, like md/raid did.
CVE-2024-35843: In the Linux kernel, the following vulnerability has been resolved: iommu/vt-d: Use device rbtree in iopf reporting path The existing I/O page fault handler currently locates the PCI device by calling pci_get_domain_bus_and_slot(). This function searches the list of all PCI devices until the desired device is found. To improve lookup efficiency, replace it with device_rbtree_find() to search the device within the probed device rbtree. The I/O page fault is initiated by the device, which does not have any synchronization mechanism with the software to ensure that the device stays in the probed device tree. Theoretically, a device could be released by the IOMMU subsystem after device_rbtree_find() and before iopf_get_dev_fault_param(), which would cause a use-after-free problem. Add a mutex to synchronize the I/O page fault reporting path and the IOMMU release device path. This lock doesn't introduce any performance overhead, as the conflict between I/O page fault reporting and device releasing is very rare.
CVE-2024-35860: In the Linux kernel, the following vulnerability has been resolved: bpf: support deferring bpf_link dealloc to after RCU grace period BPF link for some program types is passed as a "context" which can be used by those BPF programs to look up additional information. E.g., for multi-kprobes and multi-uprobes, link is used to fetch BPF cookie values. Because of this runtime dependency, when bpf_link refcnt drops to zero there could still be active BPF programs running accessing link data. This patch adds generic support to defer bpf_link dealloc callback to after RCU GP, if requested. This is done by exposing two different deallocation callbacks, one synchronous and one deferred. If deferred one is provided, bpf_link_free() will schedule dealloc_deferred() callback to happen after RCU GP. BPF is using two flavors of RCU: "classic" non-sleepable one and RCU tasks trace one. The latter is used when sleepable BPF programs are used. bpf_link_free() accommodates that by checking underlying BPF program's sleepable flag, and goes either through normal RCU GP only for non-sleepable, or through RCU tasks trace GP *and* then normal RCU GP (taking into account rcu_trace_implies_rcu_gp() optimization), if BPF program is sleepable. We use this for multi-kprobe and multi-uprobe links, which dereference link during program run. We also preventively switch raw_tp link to use deferred dealloc callback, as upcoming changes in bpf-next tree expose raw_tp link data (specifically, cookie value) to BPF program at runtime as well.
CVE-2024-35887: In the Linux kernel, the following vulnerability has been resolved: ax25: fix use-after-free bugs caused by ax25_ds_del_timer When the ax25 device is detaching, the ax25_dev_device_down() calls ax25_ds_del_timer() to cleanup the slave_timer. When the timer handler is running, the ax25_ds_del_timer() that calls del_timer() in it will return directly. As a result, the use-after-free bugs could happen, one of the scenarios is shown below: (Thread 1) | (Thread 2) | ax25_ds_timeout() ax25_dev_device_down() | ax25_ds_del_timer() | del_timer() | ax25_dev_put() //FREE | | ax25_dev-> //USE In order to mitigate bugs, when the device is detaching, use timer_shutdown_sync() to stop the timer.
CVE-2024-35904: In the Linux kernel, the following vulnerability has been resolved: selinux: avoid dereference of garbage after mount failure In case kern_mount() fails and returns an error pointer return in the error branch instead of continuing and dereferencing the error pointer. While on it drop the never read static variable selinuxfs_mount.
CVE-2024-35924: In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: Limit read size on v1.2 Between UCSI 1.2 and UCSI 2.0, the size of the MESSAGE_IN region was increased from 16 to 256. In order to avoid overflowing reads for older systems, add a mechanism to use the read UCSI version to truncate read sizes on UCSI v1.2.
CVE-2024-35931: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Skip do PCI error slot reset during RAS recovery Why: The PCI error slot reset maybe triggered after inject ue to UMC multi times, this caused system hang. [ 557.371857] amdgpu 0000:af:00.0: amdgpu: GPU reset succeeded, trying to resume [ 557.373718] [drm] PCIE GART of 512M enabled. [ 557.373722] [drm] PTB located at 0x0000031FED700000 [ 557.373788] [drm] VRAM is lost due to GPU reset! [ 557.373789] [drm] PSP is resuming... [ 557.547012] mlx5_core 0000:55:00.0: mlx5_pci_err_detected Device state = 1 pci_status: 0. Exit, result = 3, need reset [ 557.547067] [drm] PCI error: detected callback, state(1)!! [ 557.547069] [drm] No support for XGMI hive yet... [ 557.548125] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 0. Enter [ 557.607763] mlx5_core 0000:55:00.0: wait vital counter value 0x16b5b after 1 iterations [ 557.607777] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 1. Exit, err = 0, result = 5, recovered [ 557.610492] [drm] PCI error: slot reset callback!! ... [ 560.689382] amdgpu 0000:3f:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689546] amdgpu 0000:5a:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689562] general protection fault, probably for non-canonical address 0x5f080b54534f611f: 0000 [#1] SMP NOPTI [ 560.701008] CPU: 16 PID: 2361 Comm: kworker/u448:9 Tainted: G OE 5.15.0-91-generic #101-Ubuntu [ 560.712057] Hardware name: Microsoft C278A/C278A, BIOS C2789.5.BS.1C11.AG.1 11/08/2023 [ 560.720959] Workqueue: amdgpu-reset-hive amdgpu_ras_do_recovery [amdgpu] [ 560.728887] RIP: 0010:amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.736891] Code: ff 41 89 c6 e9 1b ff ff ff 44 0f b6 45 b0 e9 4f ff ff ff be 01 00 00 00 4c 89 e7 e8 76 c9 8b ff 44 0f b6 45 b0 e9 3c fd ff ff <48> 83 ba 18 02 00 00 00 0f 84 6a f8 ff ff 48 8d 7a 78 be 01 00 00 [ 560.757967] RSP: 0018:ffa0000032e53d80 EFLAGS: 00010202 [ 560.763848] RAX: ffa00000001dfd10 RBX: ffa0000000197090 RCX: ffa0000032e53db0 [ 560.771856] RDX: 5f080b54534f5f07 RSI: 0000000000000000 RDI: ff11000128100010 [ 560.779867] RBP: ffa0000032e53df0 R08: 0000000000000000 R09: ffffffffffe77f08 [ 560.787879] R10: 0000000000ffff0a R11: 0000000000000001 R12: 0000000000000000 [ 560.795889] R13: ffa0000032e53e00 R14: 0000000000000000 R15: 0000000000000000 [ 560.803889] FS: 0000000000000000(0000) GS:ff11007e7e800000(0000) knlGS:0000000000000000 [ 560.812973] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 560.819422] CR2: 000055a04c118e68 CR3: 0000000007410005 CR4: 0000000000771ee0 [ 560.827433] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 560.835433] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 560.843444] PKRU: 55555554 [ 560.846480] Call Trace: [ 560.849225] <TASK> [ 560.851580] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.856488] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.861379] ? amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.867778] ? show_regs.part.0+0x23/0x29 [ 560.872293] ? __die_body.cold+0x8/0xd [ 560.876502] ? die_addr+0x3e/0x60 [ 560.880238] ? exc_general_protection+0x1c5/0x410 [ 560.885532] ? asm_exc_general_protection+0x27/0x30 [ 560.891025] ? amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.898323] amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.904520] process_one_work+0x228/0x3d0 How: In RAS recovery, mode-1 reset is issued from RAS fatal error handling and expected all the nodes in a hive to be reset. no need to issue another mode-1 during this procedure.
CVE-2024-35942: In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx8mp-blk-ctrl: imx8mp_blk: Add fdcc clock to hdmimix domain According to i.MX8MP RM and HDMI ADD, the fdcc clock is part of hdmi rx verification IP that should not enable for HDMI TX. But actually if the clock is disabled before HDMI/LCDIF probe, LCDIF will not get pixel clock from HDMI PHY and print the error logs: [CRTC:39:crtc-2] vblank wait timed out WARNING: CPU: 2 PID: 9 at drivers/gpu/drm/drm_atomic_helper.c:1634 drm_atomic_helper_wait_for_vblanks.part.0+0x23c/0x260 Add fdcc clock to LCDIF and HDMI TX power domains to fix the issue.
CVE-2024-35945: In the Linux kernel, the following vulnerability has been resolved: net: phy: phy_device: Prevent nullptr exceptions on ISR If phydev->irq is set unconditionally, check for valid interrupt handler or fall back to polling mode to prevent nullptr exceptions in interrupt service routine.
CVE-2024-35946: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw89: fix null pointer access when abort scan During cancel scan we might use vif that weren't scanning. Fix this by using the actual scanning vif.
CVE-2024-35951: In the Linux kernel, the following vulnerability has been resolved: drm/panfrost: Fix the error path in panfrost_mmu_map_fault_addr() Subject: [PATCH] drm/panfrost: Fix the error path in panfrost_mmu_map_fault_addr() If some the pages or sgt allocation failed, we shouldn't release the pages ref we got earlier, otherwise we will end up with unbalanced get/put_pages() calls. We should instead leave everything in place and let the BO release function deal with extra cleanup when the object is destroyed, or let the fault handler try again next time it's called.
CVE-2024-35961: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Register devlink first under devlink lock In case device is having a non fatal FW error during probe, the driver will report the error to user via devlink. This will trigger a WARN_ON, since mlx5 is calling devlink_register() last. In order to avoid the WARN_ON[1], change mlx5 to invoke devl_register() first under devlink lock. [1] WARNING: CPU: 5 PID: 227 at net/devlink/health.c:483 devlink_recover_notify.constprop.0+0xb8/0xc0 CPU: 5 PID: 227 Comm: kworker/u16:3 Not tainted 6.4.0-rc5_for_upstream_min_debug_2023_06_12_12_38 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: mlx5_health0000:08:00.0 mlx5_fw_reporter_err_work [mlx5_core] RIP: 0010:devlink_recover_notify.constprop.0+0xb8/0xc0 Call Trace: <TASK> ? __warn+0x79/0x120 ? devlink_recover_notify.constprop.0+0xb8/0xc0 ? report_bug+0x17c/0x190 ? handle_bug+0x3c/0x60 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? devlink_recover_notify.constprop.0+0xb8/0xc0 devlink_health_report+0x4a/0x1c0 mlx5_fw_reporter_err_work+0xa4/0xd0 [mlx5_core] process_one_work+0x1bb/0x3c0 ? process_one_work+0x3c0/0x3c0 worker_thread+0x4d/0x3c0 ? process_one_work+0x3c0/0x3c0 kthread+0xc6/0xf0 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 </TASK>
CVE-2024-36013: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix slab-use-after-free in l2cap_connect() Extend a critical section to prevent chan from early freeing. Also make the l2cap_connect() return type void. Nothing is using the returned value but it is ugly to return a potentially freed pointer. Making it void will help with backports because earlier kernels did use the return value. Now the compile will break for kernels where this patch is not a complete fix. Call stack summary: [use] l2cap_bredr_sig_cmd l2cap_connect ┌ mutex_lock(&conn->chan_lock); │ chan = pchan->ops->new_connection(pchan); <- alloc chan │ __l2cap_chan_add(conn, chan); │ l2cap_chan_hold(chan); │ list_add(&chan->list, &conn->chan_l); ... (1) └ mutex_unlock(&conn->chan_lock); chan->conf_state ... (4) <- use after free [free] l2cap_conn_del ┌ mutex_lock(&conn->chan_lock); │ foreach chan in conn->chan_l: ... (2) │ l2cap_chan_put(chan); │ l2cap_chan_destroy │ kfree(chan) ... (3) <- chan freed └ mutex_unlock(&conn->chan_lock); ================================================================== BUG: KASAN: slab-use-after-free in instrument_atomic_read include/linux/instrumented.h:68 [inline] BUG: KASAN: slab-use-after-free in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline] BUG: KASAN: slab-use-after-free in l2cap_connect+0xa67/0x11a0 net/bluetooth/l2cap_core.c:4260 Read of size 8 at addr ffff88810bf040a0 by task kworker/u3:1/311
CVE-2024-36024: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Disable idle reallow as part of command/gpint execution [Why] Workaroud for a race condition where DMCUB is in the process of committing to IPS1 during the handshake causing us to miss the transition into IPS2 and touch the INBOX1 RPTR causing a HW hang. [How] Disable the reallow to ensure that we have enough of a gap between entry and exit and we're not seeing back-to-back wake_and_executes.
CVE-2024-36881: In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: reset ptes when close() for wr-protected ones Userfaultfd unregister includes a step to remove wr-protect bits from all the relevant pgtable entries, but that only covered an explicit UFFDIO_UNREGISTER ioctl, not a close() on the userfaultfd itself. Cover that too. This fixes a WARN trace. The only user visible side effect is the user can observe leftover wr-protect bits even if the user close()ed on an userfaultfd when releasing the last reference of it. However hopefully that should be harmless, and nothing bad should happen even if so. This change is now more important after the recent page-table-check patch we merged in mm-unstable (446dd9ad37d0 ("mm/page_table_check: support userfault wr-protect entries")), as we'll do sanity check on uffd-wp bits without vma context. So it's better if we can 100% guarantee no uffd-wp bit leftovers, to make sure each report will be valid.
CVE-2024-36911: In the Linux kernel, the following vulnerability has been resolved: hv_netvsc: Don't free decrypted memory In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. The netvsc driver could free decrypted/shared pages if set_memory_decrypted() fails. Check the decrypted field in the gpadl to decide whether to free the memory.
CVE-2024-36922: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: read txq->read_ptr under lock If we read txq->read_ptr without lock, we can read the same value twice, then obtain the lock, and reclaim from there to two different places, but crucially reclaim the same entry twice, resulting in the WARN_ONCE() a little later. Fix that by reading txq->read_ptr under lock.
CVE-2024-36949: In the Linux kernel, the following vulnerability has been resolved: amd/amdkfd: sync all devices to wait all processes being evicted If there are more than one device doing reset in parallel, the first device will call kfd_suspend_all_processes() to evict all processes on all devices, this call takes time to finish. other device will start reset and recover without waiting. if the process has not been evicted before doing recover, it will be restored, then caused page fault.
CVE-2024-36951: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: range check cp bad op exception interrupts Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well.
CVE-2024-36968: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() l2cap_le_flowctl_init() can cause both div-by-zero and an integer overflow since hdev->le_mtu may not fall in the valid range. Move MTU from hci_dev to hci_conn to validate MTU and stop the connection process earlier if MTU is invalid. Also, add a missing validation in read_buffer_size() and make it return an error value if the validation fails. Now hci_conn_add() returns ERR_PTR() as it can fail due to the both a kzalloc failure and invalid MTU value. divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 67 Comm: kworker/u5:0 Tainted: G W 6.9.0-rc5+ #20 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: hci0 hci_rx_work RIP: 0010:l2cap_le_flowctl_init+0x19e/0x3f0 net/bluetooth/l2cap_core.c:547 Code: e8 17 17 0c 00 66 41 89 9f 84 00 00 00 bf 01 00 00 00 41 b8 02 00 00 00 4c 89 fe 4c 89 e2 89 d9 e8 27 17 0c 00 44 89 f0 31 d2 <66> f7 f3 89 c3 ff c3 4d 8d b7 88 00 00 00 4c 89 f0 48 c1 e8 03 42 RSP: 0018:ffff88810bc0f858 EFLAGS: 00010246 RAX: 00000000000002a0 RBX: 0000000000000000 RCX: dffffc0000000000 RDX: 0000000000000000 RSI: ffff88810bc0f7c0 RDI: ffffc90002dcb66f RBP: ffff88810bc0f880 R08: aa69db2dda70ff01 R09: 0000ffaaaaaaaaaa R10: 0084000000ffaaaa R11: 0000000000000000 R12: ffff88810d65a084 R13: dffffc0000000000 R14: 00000000000002a0 R15: ffff88810d65a000 FS: 0000000000000000(0000) GS:ffff88811ac00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000100 CR3: 0000000103268003 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: <TASK> l2cap_le_connect_req net/bluetooth/l2cap_core.c:4902 [inline] l2cap_le_sig_cmd net/bluetooth/l2cap_core.c:5420 [inline] l2cap_le_sig_channel net/bluetooth/l2cap_core.c:5486 [inline] l2cap_recv_frame+0xe59d/0x11710 net/bluetooth/l2cap_core.c:6809 l2cap_recv_acldata+0x544/0x10a0 net/bluetooth/l2cap_core.c:7506 hci_acldata_packet net/bluetooth/hci_core.c:3939 [inline] hci_rx_work+0x5e5/0xb20 net/bluetooth/hci_core.c:4176 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0x90f/0x1530 kernel/workqueue.c:3335 worker_thread+0x926/0xe70 kernel/workqueue.c:3416 kthread+0x2e3/0x380 kernel/kthread.c:388 ret_from_fork+0x5c/0x90 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]---
CVE-2024-38557: In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Reload only IB representors upon lag disable/enable On lag disable, the bond IB device along with all of its representors are destroyed, and then the slaves' representors get reloaded. In case the slave IB representor load fails, the eswitch error flow unloads all representors, including ethernet representors, where the netdevs get detached and removed from lag bond. Such flow is inaccurate as the lag driver is not responsible for loading/unloading ethernet representors. Furthermore, the flow described above begins by holding lag lock to prevent bond changes during disable flow. However, when reaching the ethernet representors detachment from lag, the lag lock is required again, triggering the following deadlock: Call trace: __switch_to+0xf4/0x148 __schedule+0x2c8/0x7d0 schedule+0x50/0xe0 schedule_preempt_disabled+0x18/0x28 __mutex_lock.isra.13+0x2b8/0x570 __mutex_lock_slowpath+0x1c/0x28 mutex_lock+0x4c/0x68 mlx5_lag_remove_netdev+0x3c/0x1a0 [mlx5_core] mlx5e_uplink_rep_disable+0x70/0xa0 [mlx5_core] mlx5e_detach_netdev+0x6c/0xb0 [mlx5_core] mlx5e_netdev_change_profile+0x44/0x138 [mlx5_core] mlx5e_netdev_attach_nic_profile+0x28/0x38 [mlx5_core] mlx5e_vport_rep_unload+0x184/0x1b8 [mlx5_core] mlx5_esw_offloads_rep_load+0xd8/0xe0 [mlx5_core] mlx5_eswitch_reload_reps+0x74/0xd0 [mlx5_core] mlx5_disable_lag+0x130/0x138 [mlx5_core] mlx5_lag_disable_change+0x6c/0x70 [mlx5_core] // hold ldev->lock mlx5_devlink_eswitch_mode_set+0xc0/0x410 [mlx5_core] devlink_nl_cmd_eswitch_set_doit+0xdc/0x180 genl_family_rcv_msg_doit.isra.17+0xe8/0x138 genl_rcv_msg+0xe4/0x220 netlink_rcv_skb+0x44/0x108 genl_rcv+0x40/0x58 netlink_unicast+0x198/0x268 netlink_sendmsg+0x1d4/0x418 sock_sendmsg+0x54/0x60 __sys_sendto+0xf4/0x120 __arm64_sys_sendto+0x30/0x40 el0_svc_common+0x8c/0x120 do_el0_svc+0x30/0xa0 el0_svc+0x20/0x30 el0_sync_handler+0x90/0xb8 el0_sync+0x160/0x180 Thus, upon lag enable/disable, load and unload only the IB representors of the slaves preventing the deadlock mentioned above. While at it, refactor the mlx5_esw_offloads_rep_load() function to have a static helper method for its internal logic, in symmetry with the representor unload design.
CVE-2024-38564: In the Linux kernel, the following vulnerability has been resolved: bpf: Add BPF_PROG_TYPE_CGROUP_SKB attach type enforcement in BPF_LINK_CREATE bpf_prog_attach uses attach_type_to_prog_type to enforce proper attach type for BPF_PROG_TYPE_CGROUP_SKB. link_create uses bpf_prog_get and relies on bpf_prog_attach_check_attach_type to properly verify prog_type <> attach_type association. Add missing attach_type enforcement for the link_create case. Otherwise, it's currently possible to attach cgroup_skb prog types to other cgroup hooks.
CVE-2024-38570: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix potential glock use-after-free on unmount When a DLM lockspace is released and there ares still locks in that lockspace, DLM will unlock those locks automatically. Commit fb6791d100d1b started exploiting this behavior to speed up filesystem unmount: gfs2 would simply free glocks it didn't want to unlock and then release the lockspace. This didn't take the bast callbacks for asynchronous lock contention notifications into account, which remain active until until a lock is unlocked or its lockspace is released. To prevent those callbacks from accessing deallocated objects, put the glocks that should not be unlocked on the sd_dead_glocks list, release the lockspace, and only then free those glocks. As an additional measure, ignore unexpected ast and bast callbacks if the receiving glock is dead.
CVE-2024-38594: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: move the EST lock to struct stmmac_priv Reinitialize the whole EST structure would also reset the mutex lock which is embedded in the EST structure, and then trigger the following warning. To address this, move the lock to struct stmmac_priv. We also need to reacquire the mutex lock when doing this initialization. DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 505 at kernel/locking/mutex.c:587 __mutex_lock+0xd84/0x1068 Modules linked in: CPU: 3 PID: 505 Comm: tc Not tainted 6.9.0-rc6-00053-g0106679839f7-dirty #29 Hardware name: NXP i.MX8MPlus EVK board (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __mutex_lock+0xd84/0x1068 lr : __mutex_lock+0xd84/0x1068 sp : ffffffc0864e3570 x29: ffffffc0864e3570 x28: ffffffc0817bdc78 x27: 0000000000000003 x26: ffffff80c54f1808 x25: ffffff80c9164080 x24: ffffffc080d723ac x23: 0000000000000000 x22: 0000000000000002 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffc083bc3000 x18: ffffffffffffffff x17: ffffffc08117b080 x16: 0000000000000002 x15: ffffff80d2d40000 x14: 00000000000002da x13: ffffff80d2d404b8 x12: ffffffc082b5a5c8 x11: ffffffc082bca680 x10: ffffffc082bb2640 x9 : ffffffc082bb2698 x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001 x5 : ffffff8178fe0d48 x4 : 0000000000000000 x3 : 0000000000000027 x2 : ffffff8178fe0d50 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: __mutex_lock+0xd84/0x1068 mutex_lock_nested+0x28/0x34 tc_setup_taprio+0x118/0x68c stmmac_setup_tc+0x50/0xf0 taprio_change+0x868/0xc9c
CVE-2024-38608: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix netif state handling mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]---
CVE-2024-38620: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HCI: Remove HCI_AMP support Since BT_HS has been remove HCI_AMP controllers no longer has any use so remove it along with the capability of creating AMP controllers. Since we no longer need to differentiate between AMP and Primary controllers, as only HCI_PRIMARY is left, this also remove hdev->dev_type altogether.
CVE-2024-38622: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: Add callback function pointer check before its call In dpu_core_irq_callback_handler() callback function pointer is compared to NULL, but then callback function is unconditionally called by this pointer. Fix this bug by adding conditional return. Found by Linux Verification Center (linuxtesting.org) with SVACE. Patchwork: https://patchwork.freedesktop.org/patch/588237/
CVE-2024-38625: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Check 'folio' pointer for NULL It can be NULL if bmap is called.
CVE-2024-38630: In the Linux kernel, the following vulnerability has been resolved: watchdog: cpu5wdt.c: Fix use-after-free bug caused by cpu5wdt_trigger When the cpu5wdt module is removing, the origin code uses del_timer() to de-activate the timer. If the timer handler is running, del_timer() could not stop it and will return directly. If the port region is released by release_region() and then the timer handler cpu5wdt_trigger() calls outb() to write into the region that is released, the use-after-free bug will happen. Change del_timer() to timer_shutdown_sync() in order that the timer handler could be finished before the port region is released.
CVE-2024-39508: In the Linux kernel, the following vulnerability has been resolved: io_uring/io-wq: Use set_bit() and test_bit() at worker->flags Utilize set_bit() and test_bit() on worker->flags within io_uring/io-wq to address potential data races. The structure io_worker->flags may be accessed through various data paths, leading to concurrency issues. When KCSAN is enabled, it reveals data races occurring in io_worker_handle_work and io_wq_activate_free_worker functions. BUG: KCSAN: data-race in io_worker_handle_work / io_wq_activate_free_worker write to 0xffff8885c4246404 of 4 bytes by task 49071 on cpu 28: io_worker_handle_work (io_uring/io-wq.c:434 io_uring/io-wq.c:569) io_wq_worker (io_uring/io-wq.c:?) <snip> read to 0xffff8885c4246404 of 4 bytes by task 49024 on cpu 5: io_wq_activate_free_worker (io_uring/io-wq.c:? io_uring/io-wq.c:285) io_wq_enqueue (io_uring/io-wq.c:947) io_queue_iowq (io_uring/io_uring.c:524) io_req_task_submit (io_uring/io_uring.c:1511) io_handle_tw_list (io_uring/io_uring.c:1198) <snip> Line numbers against commit 18daea77cca6 ("Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm"). These races involve writes and reads to the same memory location by different tasks running on different CPUs. To mitigate this, refactor the code to use atomic operations such as set_bit(), test_bit(), and clear_bit() instead of basic "and" and "or" operations. This ensures thread-safe manipulation of worker flags. Also, move `create_index` to avoid holes in the structure.
CVE-2024-40965: In the Linux kernel, the following vulnerability has been resolved: i2c: lpi2c: Avoid calling clk_get_rate during transfer Instead of repeatedly calling clk_get_rate for each transfer, lock the clock rate and cache the value. A deadlock has been observed while adding tlv320aic32x4 audio codec to the system. When this clock provider adds its clock, the clk mutex is locked already, it needs to access i2c, which in return needs the mutex for clk_get_rate as well.
CVE-2024-40969: In the Linux kernel, the following vulnerability has been resolved: f2fs: don't set RO when shutting down f2fs Shutdown does not check the error of thaw_super due to readonly, which causes a deadlock like below. f2fs_ioc_shutdown(F2FS_GOING_DOWN_FULLSYNC) issue_discard_thread - bdev_freeze - freeze_super - f2fs_stop_checkpoint() - f2fs_handle_critical_error - sb_start_write - set RO - waiting - bdev_thaw - thaw_super_locked - return -EINVAL, if sb_rdonly() - f2fs_stop_discard_thread -> wait for kthread_stop(discard_thread);
CVE-2024-40975: In the Linux kernel, the following vulnerability has been resolved: platform/x86: x86-android-tablets: Unregister devices in reverse order Not all subsystems support a device getting removed while there are still consumers of the device with a reference to the device. One example of this is the regulator subsystem. If a regulator gets unregistered while there are still drivers holding a reference a WARN() at drivers/regulator/core.c:5829 triggers, e.g.: WARNING: CPU: 1 PID: 1587 at drivers/regulator/core.c:5829 regulator_unregister Hardware name: Intel Corp. VALLEYVIEW C0 PLATFORM/BYT-T FFD8, BIOS BLADE_21.X64.0005.R00.1504101516 FFD8_X64_R_2015_04_10_1516 04/10/2015 RIP: 0010:regulator_unregister Call Trace: <TASK> regulator_unregister devres_release_group i2c_device_remove device_release_driver_internal bus_remove_device device_del device_unregister x86_android_tablet_remove On the Lenovo Yoga Tablet 2 series the bq24190 charger chip also provides a 5V boost converter output for powering USB devices connected to the micro USB port, the bq24190-charger driver exports this as a Vbus regulator. On the 830 (8") and 1050 ("10") models this regulator is controlled by a platform_device and x86_android_tablet_remove() removes platform_device-s before i2c_clients so the consumer gets removed first. But on the 1380 (13") model there is a lc824206xa micro-USB switch connected over I2C and the extcon driver for that controls the regulator. The bq24190 i2c-client *must* be registered first, because that creates the regulator with the lc824206xa listed as its consumer. If the regulator has not been registered yet the lc824206xa driver will end up getting a dummy regulator. Since in this case both the regulator provider and consumer are I2C devices, the only way to ensure that the consumer is unregistered first is to unregister the I2C devices in reverse order of in which they were created. For consistency and to avoid similar problems in the future change x86_android_tablet_remove() to unregister all device types in reverse order.
CVE-2024-40998: In the Linux kernel, the following vulnerability has been resolved: ext4: fix uninitialized ratelimit_state->lock access in __ext4_fill_super() In the following concurrency we will access the uninitialized rs->lock: ext4_fill_super ext4_register_sysfs // sysfs registered msg_ratelimit_interval_ms // Other processes modify rs->interval to // non-zero via msg_ratelimit_interval_ms ext4_orphan_cleanup ext4_msg(sb, KERN_INFO, "Errors on filesystem, " __ext4_msg ___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state) if (!rs->interval) // do nothing if interval is 0 return 1; raw_spin_trylock_irqsave(&rs->lock, flags) raw_spin_trylock(lock) _raw_spin_trylock __raw_spin_trylock spin_acquire(&lock->dep_map, 0, 1, _RET_IP_) lock_acquire __lock_acquire register_lock_class assign_lock_key dump_stack(); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); raw_spin_lock_init(&rs->lock); // init rs->lock here and get the following dump_stack: ========================================================= INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 12 PID: 753 Comm: mount Tainted: G E 6.7.0-rc6-next-20231222 #504 [...] Call Trace: dump_stack_lvl+0xc5/0x170 dump_stack+0x18/0x30 register_lock_class+0x740/0x7c0 __lock_acquire+0x69/0x13a0 lock_acquire+0x120/0x450 _raw_spin_trylock+0x98/0xd0 ___ratelimit+0xf6/0x220 __ext4_msg+0x7f/0x160 [ext4] ext4_orphan_cleanup+0x665/0x740 [ext4] __ext4_fill_super+0x21ea/0x2b10 [ext4] ext4_fill_super+0x14d/0x360 [ext4] [...] ========================================================= Normally interval is 0 until s_msg_ratelimit_state is initialized, so ___ratelimit() does nothing. But registering sysfs precedes initializing rs->lock, so it is possible to change rs->interval to a non-zero value via the msg_ratelimit_interval_ms interface of sysfs while rs->lock is uninitialized, and then a call to ext4_msg triggers the problem by accessing an uninitialized rs->lock. Therefore register sysfs after all initializations are complete to avoid such problems.
CVE-2024-40999: In the Linux kernel, the following vulnerability has been resolved: net: ena: Add validation for completion descriptors consistency Validate that `first` flag is set only for the first descriptor in multi-buffer packets. In case of an invalid descriptor, a reset will occur. A new reset reason for RX data corruption has been added.
CVE-2024-41008: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: change vm->task_info handling This patch changes the handling and lifecycle of vm->task_info object. The major changes are: - vm->task_info is a dynamically allocated ptr now, and its uasge is reference counted. - introducing two new helper funcs for task_info lifecycle management - amdgpu_vm_get_task_info: reference counts up task_info before returning this info - amdgpu_vm_put_task_info: reference counts down task_info - last put to task_info() frees task_info from the vm. This patch also does logistical changes required for existing usage of vm->task_info. V2: Do not block all the prints when task_info not found (Felix) V3: Fixed review comments from Felix - Fix wrong indentation - No debug message for -ENOMEM - Add NULL check for task_info - Do not duplicate the debug messages (ti vs no ti) - Get first reference of task_info in vm_init(), put last in vm_fini() V4: Fixed review comments from Felix - fix double reference increment in create_task_info - change amdgpu_vm_get_task_info_pasid - additional changes in amdgpu_gem.c while porting
CVE-2024-41023: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix task_struct reference leak During the execution of the following stress test with linux-rt: stress-ng --cyclic 30 --timeout 30 --minimize --quiet kmemleak frequently reported a memory leak concerning the task_struct: unreferenced object 0xffff8881305b8000 (size 16136): comm "stress-ng", pid 614, jiffies 4294883961 (age 286.412s) object hex dump (first 32 bytes): 02 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 .@.............. 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ debug hex dump (first 16 bytes): 53 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 S............... backtrace: [<00000000046b6790>] dup_task_struct+0x30/0x540 [<00000000c5ca0f0b>] copy_process+0x3d9/0x50e0 [<00000000ced59777>] kernel_clone+0xb0/0x770 [<00000000a50befdc>] __do_sys_clone+0xb6/0xf0 [<000000001dbf2008>] do_syscall_64+0x5d/0xf0 [<00000000552900ff>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 The issue occurs in start_dl_timer(), which increments the task_struct reference count and sets a timer. The timer callback, dl_task_timer, is supposed to decrement the reference count upon expiration. However, if enqueue_task_dl() is called before the timer expires and cancels it, the reference count is not decremented, leading to the leak. This patch fixes the reference leak by ensuring the task_struct reference count is properly decremented when the timer is canceled.
CVE-2024-41031: In the Linux kernel, the following vulnerability has been resolved: mm/filemap: skip to create PMD-sized page cache if needed On ARM64, HPAGE_PMD_ORDER is 13 when the base page size is 64KB. The PMD-sized page cache can't be supported by xarray as the following error messages indicate. ------------[ cut here ]------------ WARNING: CPU: 35 PID: 7484 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm \ fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 \ sha1_ce virtio_net net_failover virtio_console virtio_blk failover \ dimlib virtio_mmio CPU: 35 PID: 7484 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x720 sp : ffff800087a4f6c0 x29: ffff800087a4f6c0 x28: ffff800087a4f720 x27: 000000001fffffff x26: 0000000000000c40 x25: 000000000000000d x24: ffff00010625b858 x23: ffff800087a4f720 x22: ffffffdfc0780000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0780000 x18: 000000001ff40000 x17: 00000000ffffffff x16: 0000018000000000 x15: 51ec004000000000 x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020 x11: 51ec000000000000 x10: 51ece1c0ffff8000 x9 : ffffbeb961a44d28 x8 : 0000000000000003 x7 : ffffffdfc0456420 x6 : ffff0000e1aa6eb8 x5 : 20bf08b4fe778fca x4 : ffffffdfc0456420 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x720 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2e8 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by skipping to allocate PMD-sized page cache when its size is larger than MAX_PAGECACHE_ORDER. For this specific case, we will fall to regular path where the readahead window is determined by BDI's sysfs file (read_ahead_kb).
CVE-2024-41045: In the Linux kernel, the following vulnerability has been resolved: bpf: Defer work in bpf_timer_cancel_and_free Currently, the same case as previous patch (two timer callbacks trying to cancel each other) can be invoked through bpf_map_update_elem as well, or more precisely, freeing map elements containing timers. Since this relies on hrtimer_cancel as well, it is prone to the same deadlock situation as the previous patch. It would be sufficient to use hrtimer_try_to_cancel to fix this problem, as the timer cannot be enqueued after async_cancel_and_free. Once async_cancel_and_free has been done, the timer must be reinitialized before it can be armed again. The callback running in parallel trying to arm the timer will fail, and freeing bpf_hrtimer without waiting is sufficient (given kfree_rcu), and bpf_timer_cb will return HRTIMER_NORESTART, preventing the timer from being rearmed again. However, there exists a UAF scenario where the callback arms the timer before entering this function, such that if cancellation fails (due to timer callback invoking this routine, or the target timer callback running concurrently). In such a case, if the timer expiration is significantly far in the future, the RCU grace period expiration happening before it will free the bpf_hrtimer state and along with it the struct hrtimer, that is enqueued. Hence, it is clear cancellation needs to occur after async_cancel_and_free, and yet it cannot be done inline due to deadlock issues. We thus modify bpf_timer_cancel_and_free to defer work to the global workqueue, adding a work_struct alongside rcu_head (both used at _different_ points of time, so can share space). Update existing code comments to reflect the new state of affairs.
CVE-2024-41082: In the Linux kernel, the following vulnerability has been resolved: nvme-fabrics: use reserved tag for reg read/write command In some scenarios, if too many commands are issued by nvme command in the same time by user tasks, this may exhaust all tags of admin_q. If a reset (nvme reset or IO timeout) occurs before these commands finish, reconnect routine may fail to update nvme regs due to insufficient tags, which will cause kernel hang forever. In order to workaround this issue, maybe we can let reg_read32()/reg_read64()/reg_write32() use reserved tags. This maybe safe for nvmf: 1. For the disable ctrl path, we will not issue connect command 2. For the enable ctrl / fw activate path, since connect and reg_xx() are called serially. So the reserved tags may still be enough while reg_xx() use reserved tags.
CVE-2024-41935: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to shrink read extent node in batches We use rwlock to protect core structure data of extent tree during its shrink, however, if there is a huge number of extent nodes in extent tree, during shrink of extent tree, it may hold rwlock for a very long time, which may trigger kernel hang issue. This patch fixes to shrink read extent node in batches, so that, critical region of the rwlock can be shrunk to avoid its extreme long time hold.
CVE-2024-42107: In the Linux kernel, the following vulnerability has been resolved: ice: Don't process extts if PTP is disabled The ice_ptp_extts_event() function can race with ice_ptp_release() and result in a NULL pointer dereference which leads to a kernel panic. Panic occurs because the ice_ptp_extts_event() function calls ptp_clock_event() with a NULL pointer. The ice driver has already released the PTP clock by the time the interrupt for the next external timestamp event occurs. To fix this, modify the ice_ptp_extts_event() function to check the PTP state and bail early if PTP is not ready.
CVE-2024-42118: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not return negative stream id for array [WHY] resource_stream_to_stream_idx returns an array index and it return -1 when not found; however, -1 is not a valid array index number. [HOW] When this happens, call ASSERT(), and return a zero instead. This fixes an OVERRUN and an NEGATIVE_RETURNS issues reported by Coverity.
CVE-2024-42123: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix double free err_addr pointer warnings In amdgpu_umc_bad_page_polling_timeout, the amdgpu_umc_handle_bad_pages will be run many times so that double free err_addr in some special case. So set the err_addr to NULL to avoid the warnings.
CVE-2024-42128: In the Linux kernel, the following vulnerability has been resolved: leds: an30259a: Use devm_mutex_init() for mutex initialization In this driver LEDs are registered using devm_led_classdev_register() so they are automatically unregistered after module's remove() is done. led_classdev_unregister() calls module's led_set_brightness() to turn off the LEDs and that callback uses mutex which was destroyed already in module's remove() so use devm API instead.
CVE-2024-42139: In the Linux kernel, the following vulnerability has been resolved: ice: Fix improper extts handling Extts events are disabled and enabled by the application ts2phc. However, in case where the driver is removed when the application is running, a specific extts event remains enabled and can cause a kernel crash. As a side effect, when the driver is reloaded and application is started again, remaining extts event for the channel from a previous run will keep firing and the message "extts on unexpected channel" might be printed to the user. To avoid that, extts events shall be disabled when PTP is released.
CVE-2024-42155: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Wipe copies of protected- and secure-keys Although the clear-key of neither protected- nor secure-keys is accessible, this key material should only be visible to the calling process. So wipe all copies of protected- or secure-keys from stack, even in case of an error.
CVE-2024-42156: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Wipe copies of clear-key structures on failure Wipe all sensitive data from stack for all IOCTLs, which convert a clear-key into a protected- or secure-key.
CVE-2024-42158: In the Linux kernel, the following vulnerability has been resolved: s390/pkey: Use kfree_sensitive() to fix Coccinelle warnings Replace memzero_explicit() and kfree() with kfree_sensitive() to fix warnings reported by Coccinelle: WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1506) WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1643) WARNING opportunity for kfree_sensitive/kvfree_sensitive (line 1770)
CVE-2024-42162: In the Linux kernel, the following vulnerability has been resolved: gve: Account for stopped queues when reading NIC stats We now account for the fact that the NIC might send us stats for a subset of queues. Without this change, gve_get_ethtool_stats might make an invalid access on the priv->stats_report->stats array.
CVE-2024-42239: In the Linux kernel, the following vulnerability has been resolved: bpf: Fail bpf_timer_cancel when callback is being cancelled Given a schedule: timer1 cb timer2 cb bpf_timer_cancel(timer2); bpf_timer_cancel(timer1); Both bpf_timer_cancel calls would wait for the other callback to finish executing, introducing a lockup. Add an atomic_t count named 'cancelling' in bpf_hrtimer. This keeps track of all in-flight cancellation requests for a given BPF timer. Whenever cancelling a BPF timer, we must check if we have outstanding cancellation requests, and if so, we must fail the operation with an error (-EDEADLK) since cancellation is synchronous and waits for the callback to finish executing. This implies that we can enter a deadlock situation involving two or more timer callbacks executing in parallel and attempting to cancel one another. Note that we avoid incrementing the cancelling counter for the target timer (the one being cancelled) if bpf_timer_cancel is not invoked from a callback, to avoid spurious errors. The whole point of detecting cur->cancelling and returning -EDEADLK is to not enter a busy wait loop (which may or may not lead to a lockup). This does not apply in case the caller is in a non-callback context, the other side can continue to cancel as it sees fit without running into errors. Background on prior attempts: Earlier versions of this patch used a bool 'cancelling' bit and used the following pattern under timer->lock to publish cancellation status. lock(t->lock); t->cancelling = true; mb(); if (cur->cancelling) return -EDEADLK; unlock(t->lock); hrtimer_cancel(t->timer); t->cancelling = false; The store outside the critical section could overwrite a parallel requests t->cancelling assignment to true, to ensure the parallely executing callback observes its cancellation status. It would be necessary to clear this cancelling bit once hrtimer_cancel is done, but lack of serialization introduced races. Another option was explored where bpf_timer_start would clear the bit when (re)starting the timer under timer->lock. This would ensure serialized access to the cancelling bit, but may allow it to be cleared before in-flight hrtimer_cancel has finished executing, such that lockups can occur again. Thus, we choose an atomic counter to keep track of all outstanding cancellation requests and use it to prevent lockups in case callbacks attempt to cancel each other while executing in parallel.
CVE-2024-42241: In the Linux kernel, the following vulnerability has been resolved: mm/shmem: disable PMD-sized page cache if needed For shmem files, it's possible that PMD-sized page cache can't be supported by xarray. For example, 512MB page cache on ARM64 when the base page size is 64KB can't be supported by xarray. It leads to errors as the following messages indicate when this sort of xarray entry is split. WARNING: CPU: 34 PID: 7578 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: binfmt_misc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 \ nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject \ nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse xfs \ libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 sha1_ce virtio_net \ net_failover virtio_console virtio_blk failover dimlib virtio_mmio CPU: 34 PID: 7578 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x720 sp : ffff8000882af5f0 x29: ffff8000882af5f0 x28: ffff8000882af650 x27: ffff8000882af768 x26: 0000000000000cc0 x25: 000000000000000d x24: ffff00010625b858 x23: ffff8000882af650 x22: ffffffdfc0900000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0900000 x18: 0000000000000000 x17: 0000000000000000 x16: 0000018000000000 x15: 52f8004000000000 x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020 x11: 52f8000000000000 x10: 52f8e1c0ffff6000 x9 : ffffbeb9619a681c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff00010b02ddb0 x5 : ffffbeb96395e378 x4 : 0000000000000000 x3 : 0000000000000cc0 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x720 truncate_inode_partial_folio+0xdc/0x160 shmem_undo_range+0x2bc/0x6a8 shmem_fallocate+0x134/0x430 vfs_fallocate+0x124/0x2e8 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by disabling PMD-sized page cache when HPAGE_PMD_ORDER is larger than MAX_PAGECACHE_ORDER. As Matthew Wilcox pointed, the page cache in a shmem file isn't represented by a multi-index entry and doesn't have this limitation when the xarry entry is split until commit 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache").
CVE-2024-42243: In the Linux kernel, the following vulnerability has been resolved: mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray Patch series "mm/filemap: Limit page cache size to that supported by xarray", v2. Currently, xarray can't support arbitrary page cache size. More details can be found from the WARN_ON() statement in xas_split_alloc(). In our test whose code is attached below, we hit the WARN_ON() on ARM64 system where the base page size is 64KB and huge page size is 512MB. The issue was reported long time ago and some discussions on it can be found here [1]. [1] https://www.spinics.net/lists/linux-xfs/msg75404.html In order to fix the issue, we need to adjust MAX_PAGECACHE_ORDER to one supported by xarray and avoid PMD-sized page cache if needed. The code changes are suggested by David Hildenbrand. PATCH[1] adjusts MAX_PAGECACHE_ORDER to that supported by xarray PATCH[2-3] avoids PMD-sized page cache in the synchronous readahead path PATCH[4] avoids PMD-sized page cache for shmem files if needed Test program ============ # cat test.c #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <fcntl.h> #include <errno.h> #include <sys/syscall.h> #include <sys/mman.h> #define TEST_XFS_FILENAME "/tmp/data" #define TEST_SHMEM_FILENAME "/dev/shm/data" #define TEST_MEM_SIZE 0x20000000 int main(int argc, char **argv) { const char *filename; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret; if (pgsize != 0x10000) { fprintf(stderr, "64KB base page size is required\n"); return -EPERM; } system("echo force > /sys/kernel/mm/transparent_hugepage/shmem_enabled"); system("rm -fr /tmp/data"); system("rm -fr /dev/shm/data"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open xfs or shmem file */ filename = TEST_XFS_FILENAME; if (argc > 1 && !strcmp(argv[1], "shmem")) filename = TEST_SHMEM_FILENAME; fd = open(filename, O_CREAT | O_RDWR | O_TRUNC); if (fd < 0) { fprintf(stderr, "Unable to open <%s>\n", filename); return -EIO; } /* Extend file size */ ret = ftruncate(fd, TEST_MEM_SIZE); if (ret) { fprintf(stderr, "Error %d to ftruncate()\n", ret); goto cleanup; } /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); if (buf == (void *)-1) { fprintf(stderr, "Unable to mmap <%s>\n", filename); goto cleanup; } fprintf(stdout, "mapped buffer at 0x%p\n", buf); ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); if (ret) { fprintf(stderr, "Unable to madvise(MADV_HUGEPAGE)\n"); goto cleanup; } /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_WRITE); if (ret) { fprintf(stderr, "Error %d to madvise(MADV_POPULATE_WRITE)\n", ret); goto cleanup; } /* Punch the file to enforce xarray split */ ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); if (ret) fprintf(stderr, "Error %d to fallocate()\n", ret); cleanup: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return 0; } # gcc test.c -o test # cat /proc/1/smaps | grep KernelPageSize | head -n 1 KernelPageSize: 64 kB # ./test shmem : ------------[ cut here ]------------ WARNING: CPU: 17 PID: 5253 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set nf_tables rfkill nfnetlink vfat fat virtio_balloon \ drm fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 \ virtio_net sha1_ce net_failover failover virtio_console virtio_blk \ dimlib virtio_mmio CPU: 17 PID: 5253 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #12 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TC ---truncated---
CVE-2024-42279: In the Linux kernel, the following vulnerability has been resolved: spi: microchip-core: ensure TX and RX FIFOs are empty at start of a transfer While transmitting with rx_len == 0, the RX FIFO is not going to be emptied in the interrupt handler. A subsequent transfer could then read crap from the previous transfer out of the RX FIFO into the start RX buffer. The core provides a register that will empty the RX and TX FIFOs, so do that before each transfer.
CVE-2024-42317: In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: avoid PMD-size page cache if needed xarray can't support arbitrary page cache size. the largest and supported page cache size is defined as MAX_PAGECACHE_ORDER by commit 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray"). However, it's possible to have 512MB page cache in the huge memory's collapsing path on ARM64 system whose base page size is 64KB. 512MB page cache is breaking the limitation and a warning is raised when the xarray entry is split as shown in the following example. [root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize KernelPageSize: 64 kB [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c : int main(int argc, char **argv) { const char *filename = TEST_XFS_FILENAME; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret = 0; if (pgsize != 0x10000) { fprintf(stdout, "System with 64KB base page size is required!\n"); return -EPERM; } system("echo 0 > /sys/devices/virtual/bdi/253:0/read_ahead_kb"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open the xfs file */ fd = open(filename, O_RDONLY); assert(fd > 0); /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ, MAP_SHARED, fd, 0); assert(buf != (void *)-1); fprintf(stdout, "mapped buffer at 0x%p\n", buf); /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_NOHUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_READ); assert(ret == 0); /* Collapse VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_COLLAPSE); if (ret) { fprintf(stdout, "Error %d to madvise(MADV_COLLAPSE)\n", errno); goto out; } /* Split xarray entry. Write permission is needed */ munmap(buf, TEST_MEM_SIZE); buf = (void *)-1; close(fd); fd = open(filename, O_RDWR); assert(fd > 0); fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); out: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return ret; } [root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test [root@dhcp-10-26-1-207 ~]# /tmp/test ------------[ cut here ]------------ WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse \ xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 virtio_net \ sha1_ce net_failover virtio_blk virtio_console failover dimlib virtio_mmio CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x780 sp : ffff8000ac32f660 x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0 x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000 x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8 x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x780 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa ---truncated---
CVE-2024-43819: In the Linux kernel, the following vulnerability has been resolved: kvm: s390: Reject memory region operations for ucontrol VMs This change rejects the KVM_SET_USER_MEMORY_REGION and KVM_SET_USER_MEMORY_REGION2 ioctls when called on a ucontrol VM. This is necessary since ucontrol VMs have kvm->arch.gmap set to 0 and would thus result in a null pointer dereference further in. Memory management needs to be performed in userspace and using the ioctls KVM_S390_UCAS_MAP and KVM_S390_UCAS_UNMAP. Also improve s390 specific documentation for KVM_SET_USER_MEMORY_REGION and KVM_SET_USER_MEMORY_REGION2. [frankja@linux.ibm.com: commit message spelling fix, subject prefix fix]
CVE-2024-43824: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-test: Make use of cached 'epc_features' in pci_epf_test_core_init() Instead of getting the epc_features from pci_epc_get_features() API, use the cached pci_epf_test::epc_features value to avoid the NULL check. Since the NULL check is already performed in pci_epf_test_bind(), having one more check in pci_epf_test_core_init() is redundant and it is not possible to hit the NULL pointer dereference. Also with commit a01e7214bef9 ("PCI: endpoint: Remove "core_init_notifier" flag"), 'epc_features' got dereferenced without the NULL check, leading to the following false positive Smatch warning: drivers/pci/endpoint/functions/pci-epf-test.c:784 pci_epf_test_core_init() error: we previously assumed 'epc_features' could be null (see line 747) Thus, remove the redundant NULL check and also use the epc_features:: {msix_capable/msi_capable} flags directly to avoid local variables. [kwilczynski: commit log]
CVE-2024-43850: In the Linux kernel, the following vulnerability has been resolved: soc: qcom: icc-bwmon: Fix refcount imbalance seen during bwmon_remove The following warning is seen during bwmon_remove due to refcount imbalance, fix this by releasing the OPPs after use. Logs: WARNING: at drivers/opp/core.c:1640 _opp_table_kref_release+0x150/0x158 Hardware name: Qualcomm Technologies, Inc. X1E80100 CRD (DT) ... Call trace: _opp_table_kref_release+0x150/0x158 dev_pm_opp_remove_table+0x100/0x1b4 devm_pm_opp_of_table_release+0x10/0x1c devm_action_release+0x14/0x20 devres_release_all+0xa4/0x104 device_unbind_cleanup+0x18/0x60 device_release_driver_internal+0x1ec/0x228 driver_detach+0x50/0x98 bus_remove_driver+0x6c/0xbc driver_unregister+0x30/0x60 platform_driver_unregister+0x14/0x20 bwmon_driver_exit+0x18/0x524 [icc_bwmon] __arm64_sys_delete_module+0x184/0x264 invoke_syscall+0x48/0x118 el0_svc_common.constprop.0+0xc8/0xe8 do_el0_svc+0x20/0x2c el0_svc+0x34/0xdc el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 --[ end trace 0000000000000000 ]---
CVE-2024-43872: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix soft lockup under heavy CEQE load CEQEs are handled in interrupt handler currently. This may cause the CPU core staying in interrupt context too long and lead to soft lockup under heavy load. Handle CEQEs in BH workqueue and set an upper limit for the number of CEQE handled by a single call of work handler.
CVE-2024-43899: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix null pointer deref in dcn20_resource.c Fixes a hang thats triggered when MPV is run on a DCN401 dGPU: mpv --hwdec=vaapi --vo=gpu --hwdec-codecs=all and then enabling fullscreen playback (double click on the video) The following calltrace will be seen: [ 181.843989] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 181.843997] #PF: supervisor instruction fetch in kernel mode [ 181.844003] #PF: error_code(0x0010) - not-present page [ 181.844009] PGD 0 P4D 0 [ 181.844020] Oops: 0010 [#1] PREEMPT SMP NOPTI [ 181.844028] CPU: 6 PID: 1892 Comm: gnome-shell Tainted: G W OE 6.5.0-41-generic #41~22.04.2-Ubuntu [ 181.844038] Hardware name: System manufacturer System Product Name/CROSSHAIR VI HERO, BIOS 6302 10/23/2018 [ 181.844044] RIP: 0010:0x0 [ 181.844079] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 181.844084] RSP: 0018:ffffb593c2b8f7b0 EFLAGS: 00010246 [ 181.844093] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000004 [ 181.844099] RDX: ffffb593c2b8f804 RSI: ffffb593c2b8f7e0 RDI: ffff9e3c8e758400 [ 181.844105] RBP: ffffb593c2b8f7b8 R08: ffffb593c2b8f9c8 R09: ffffb593c2b8f96c [ 181.844110] R10: 0000000000000000 R11: 0000000000000000 R12: ffffb593c2b8f9c8 [ 181.844115] R13: 0000000000000001 R14: ffff9e3c88000000 R15: 0000000000000005 [ 181.844121] FS: 00007c6e323bb5c0(0000) GS:ffff9e3f85f80000(0000) knlGS:0000000000000000 [ 181.844128] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 181.844134] CR2: ffffffffffffffd6 CR3: 0000000140fbe000 CR4: 00000000003506e0 [ 181.844141] Call Trace: [ 181.844146] <TASK> [ 181.844153] ? show_regs+0x6d/0x80 [ 181.844167] ? __die+0x24/0x80 [ 181.844179] ? page_fault_oops+0x99/0x1b0 [ 181.844192] ? do_user_addr_fault+0x31d/0x6b0 [ 181.844204] ? exc_page_fault+0x83/0x1b0 [ 181.844216] ? asm_exc_page_fault+0x27/0x30 [ 181.844237] dcn20_get_dcc_compression_cap+0x23/0x30 [amdgpu] [ 181.845115] amdgpu_dm_plane_validate_dcc.constprop.0+0xe5/0x180 [amdgpu] [ 181.845985] amdgpu_dm_plane_fill_plane_buffer_attributes+0x300/0x580 [amdgpu] [ 181.846848] fill_dc_plane_info_and_addr+0x258/0x350 [amdgpu] [ 181.847734] fill_dc_plane_attributes+0x162/0x350 [amdgpu] [ 181.848748] dm_update_plane_state.constprop.0+0x4e3/0x6b0 [amdgpu] [ 181.849791] ? dm_update_plane_state.constprop.0+0x4e3/0x6b0 [amdgpu] [ 181.850840] amdgpu_dm_atomic_check+0xdfe/0x1760 [amdgpu]
CVE-2024-43901: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix NULL pointer dereference for DTN log in DCN401 When users run the command: cat /sys/kernel/debug/dri/0/amdgpu_dm_dtn_log The following NULL pointer dereference happens: [ +0.000003] BUG: kernel NULL pointer dereference, address: NULL [ +0.000005] #PF: supervisor instruction fetch in kernel mode [ +0.000002] #PF: error_code(0x0010) - not-present page [ +0.000002] PGD 0 P4D 0 [ +0.000004] Oops: 0010 [#1] PREEMPT SMP NOPTI [ +0.000003] RIP: 0010:0x0 [ +0.000008] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [...] [ +0.000002] PKRU: 55555554 [ +0.000002] Call Trace: [ +0.000002] <TASK> [ +0.000003] ? show_regs+0x65/0x70 [ +0.000006] ? __die+0x24/0x70 [ +0.000004] ? page_fault_oops+0x160/0x470 [ +0.000006] ? do_user_addr_fault+0x2b5/0x690 [ +0.000003] ? prb_read_valid+0x1c/0x30 [ +0.000005] ? exc_page_fault+0x8c/0x1a0 [ +0.000005] ? asm_exc_page_fault+0x27/0x30 [ +0.000012] dcn10_log_color_state+0xf9/0x510 [amdgpu] [ +0.000306] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000003] ? vsnprintf+0x2fb/0x600 [ +0.000009] dcn10_log_hw_state+0xfd0/0xfe0 [amdgpu] [ +0.000218] ? __mod_memcg_lruvec_state+0xe8/0x170 [ +0.000008] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? debug_smp_processor_id+0x17/0x20 [ +0.000003] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? set_ptes.isra.0+0x2b/0x90 [ +0.000004] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? _raw_spin_unlock+0x19/0x40 [ +0.000004] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000002] ? do_anonymous_page+0x337/0x700 [ +0.000004] dtn_log_read+0x82/0x120 [amdgpu] [ +0.000207] full_proxy_read+0x66/0x90 [ +0.000007] vfs_read+0xb0/0x340 [ +0.000005] ? __count_memcg_events+0x79/0xe0 [ +0.000002] ? srso_alias_return_thunk+0x5/0xfbef5 [ +0.000003] ? count_memcg_events.constprop.0+0x1e/0x40 [ +0.000003] ? handle_mm_fault+0xb2/0x370 [ +0.000003] ksys_read+0x6b/0xf0 [ +0.000004] __x64_sys_read+0x19/0x20 [ +0.000003] do_syscall_64+0x60/0x130 [ +0.000004] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ +0.000003] RIP: 0033:0x7fdf32f147e2 [...] This error happens when the color log tries to read the gamut remap information from DCN401 which is not initialized in the dcn401_dpp_funcs which leads to a null pointer dereference. This commit addresses this issue by adding a proper guard to access the gamut_remap callback in case the specific ASIC did not implement this function.
CVE-2024-43913: In the Linux kernel, the following vulnerability has been resolved: nvme: apple: fix device reference counting Drivers must call nvme_uninit_ctrl after a successful nvme_init_ctrl. Split the allocation side out to make the error handling boundary easier to navigate. The apple driver had been doing this wrong, leaking the controller device memory on a tagset failure.
CVE-2024-44941: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to cover read extent cache access with lock syzbot reports a f2fs bug as below: BUG: KASAN: slab-use-after-free in sanity_check_extent_cache+0x370/0x410 fs/f2fs/extent_cache.c:46 Read of size 4 at addr ffff8880739ab220 by task syz-executor200/5097 CPU: 0 PID: 5097 Comm: syz-executor200 Not tainted 6.9.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 sanity_check_extent_cache+0x370/0x410 fs/f2fs/extent_cache.c:46 do_read_inode fs/f2fs/inode.c:509 [inline] f2fs_iget+0x33e1/0x46e0 fs/f2fs/inode.c:560 f2fs_nfs_get_inode+0x74/0x100 fs/f2fs/super.c:3237 generic_fh_to_dentry+0x9f/0xf0 fs/libfs.c:1413 exportfs_decode_fh_raw+0x152/0x5f0 fs/exportfs/expfs.c:444 exportfs_decode_fh+0x3c/0x80 fs/exportfs/expfs.c:584 do_handle_to_path fs/fhandle.c:155 [inline] handle_to_path fs/fhandle.c:210 [inline] do_handle_open+0x495/0x650 fs/fhandle.c:226 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f We missed to cover sanity_check_extent_cache() w/ extent cache lock, so, below race case may happen, result in use after free issue. - f2fs_iget - do_read_inode - f2fs_init_read_extent_tree : add largest extent entry in to cache - shrink - f2fs_shrink_read_extent_tree - __shrink_extent_tree - __detach_extent_node : drop largest extent entry - sanity_check_extent_cache : access et->largest w/o lock let's refactor sanity_check_extent_cache() to avoid extent cache access and call it before f2fs_init_read_extent_tree() to fix this issue.
CVE-2024-44942: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing.
CVE-2024-44951: In the Linux kernel, the following vulnerability has been resolved: serial: sc16is7xx: fix TX fifo corruption Sometimes, when a packet is received on channel A at almost the same time as a packet is about to be transmitted on channel B, we observe with a logic analyzer that the received packet on channel A is transmitted on channel B. In other words, the Tx buffer data on channel B is corrupted with data from channel A. The problem appeared since commit 4409df5866b7 ("serial: sc16is7xx: change EFR lock to operate on each channels"), which changed the EFR locking to operate on each channel instead of chip-wise. This commit has introduced a regression, because the EFR lock is used not only to protect the EFR registers access, but also, in a very obscure and undocumented way, to protect access to the data buffer, which is shared by the Tx and Rx handlers, but also by each channel of the IC. Fix this regression first by switching to kfifo_out_linear_ptr() in sc16is7xx_handle_tx() to eliminate the need for a shared Rx/Tx buffer. Secondly, replace the chip-wise Rx buffer with a separate Rx buffer for each channel.
CVE-2024-44963: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not BUG_ON() when freeing tree block after error When freeing a tree block, at btrfs_free_tree_block(), if we fail to create a delayed reference we don't deal with the error and just do a BUG_ON(). The error most likely to happen is -ENOMEM, and we have a comment mentioning that only -ENOMEM can happen, but that is not true, because in case qgroups are enabled any error returned from btrfs_qgroup_trace_extent_post() (can be -EUCLEAN or anything returned from btrfs_search_slot() for example) can be propagated back to btrfs_free_tree_block(). So stop doing a BUG_ON() and return the error to the callers and make them abort the transaction to prevent leaking space. Syzbot was triggering this, likely due to memory allocation failure injection.
CVE-2024-45015: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: move dpu_encoder's connector assignment to atomic_enable() For cases where the crtc's connectors_changed was set without enable/active getting toggled , there is an atomic_enable() call followed by an atomic_disable() but without an atomic_mode_set(). This results in a NULL ptr access for the dpu_encoder_get_drm_fmt() call in the atomic_enable() as the dpu_encoder's connector was cleared in the atomic_disable() but not re-assigned as there was no atomic_mode_set() call. Fix the NULL ptr access by moving the assignment for atomic_enable() and also use drm_atomic_get_new_connector_for_encoder() to get the connector from the atomic_state. Patchwork: https://patchwork.freedesktop.org/patch/606729/
CVE-2024-46678: In the Linux kernel, the following vulnerability has been resolved: bonding: change ipsec_lock from spin lock to mutex In the cited commit, bond->ipsec_lock is added to protect ipsec_list, hence xdo_dev_state_add and xdo_dev_state_delete are called inside this lock. As ipsec_lock is a spin lock and such xfrmdev ops may sleep, "scheduling while atomic" will be triggered when changing bond's active slave. [ 101.055189] BUG: scheduling while atomic: bash/902/0x00000200 [ 101.055726] Modules linked in: [ 101.058211] CPU: 3 PID: 902 Comm: bash Not tainted 6.9.0-rc4+ #1 [ 101.058760] Hardware name: [ 101.059434] Call Trace: [ 101.059436] <TASK> [ 101.060873] dump_stack_lvl+0x51/0x60 [ 101.061275] __schedule_bug+0x4e/0x60 [ 101.061682] __schedule+0x612/0x7c0 [ 101.062078] ? __mod_timer+0x25c/0x370 [ 101.062486] schedule+0x25/0xd0 [ 101.062845] schedule_timeout+0x77/0xf0 [ 101.063265] ? asm_common_interrupt+0x22/0x40 [ 101.063724] ? __bpf_trace_itimer_state+0x10/0x10 [ 101.064215] __wait_for_common+0x87/0x190 [ 101.064648] ? usleep_range_state+0x90/0x90 [ 101.065091] cmd_exec+0x437/0xb20 [mlx5_core] [ 101.065569] mlx5_cmd_do+0x1e/0x40 [mlx5_core] [ 101.066051] mlx5_cmd_exec+0x18/0x30 [mlx5_core] [ 101.066552] mlx5_crypto_create_dek_key+0xea/0x120 [mlx5_core] [ 101.067163] ? bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.067738] ? kmalloc_trace+0x4d/0x350 [ 101.068156] mlx5_ipsec_create_sa_ctx+0x33/0x100 [mlx5_core] [ 101.068747] mlx5e_xfrm_add_state+0x47b/0xaa0 [mlx5_core] [ 101.069312] bond_change_active_slave+0x392/0x900 [bonding] [ 101.069868] bond_option_active_slave_set+0x1c2/0x240 [bonding] [ 101.070454] __bond_opt_set+0xa6/0x430 [bonding] [ 101.070935] __bond_opt_set_notify+0x2f/0x90 [bonding] [ 101.071453] bond_opt_tryset_rtnl+0x72/0xb0 [bonding] [ 101.071965] bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.072567] kernfs_fop_write_iter+0x10c/0x1a0 [ 101.073033] vfs_write+0x2d8/0x400 [ 101.073416] ? alloc_fd+0x48/0x180 [ 101.073798] ksys_write+0x5f/0xe0 [ 101.074175] do_syscall_64+0x52/0x110 [ 101.074576] entry_SYSCALL_64_after_hwframe+0x4b/0x53 As bond_ipsec_add_sa_all and bond_ipsec_del_sa_all are only called from bond_change_active_slave, which requires holding the RTNL lock. And bond_ipsec_add_sa and bond_ipsec_del_sa are xfrm state xdo_dev_state_add and xdo_dev_state_delete APIs, which are in user context. So ipsec_lock doesn't have to be spin lock, change it to mutex, and thus the above issue can be resolved.
CVE-2024-46681: In the Linux kernel, the following vulnerability has been resolved: pktgen: use cpus_read_lock() in pg_net_init() I have seen the WARN_ON(smp_processor_id() != cpu) firing in pktgen_thread_worker() during tests. We must use cpus_read_lock()/cpus_read_unlock() around the for_each_online_cpu(cpu) loop. While we are at it use WARN_ON_ONCE() to avoid a possible syslog flood.
CVE-2024-46698: In the Linux kernel, the following vulnerability has been resolved: video/aperture: optionally match the device in sysfb_disable() In aperture_remove_conflicting_pci_devices(), we currently only call sysfb_disable() on vga class devices. This leads to the following problem when the pimary device is not VGA compatible: 1. A PCI device with a non-VGA class is the boot display 2. That device is probed first and it is not a VGA device so sysfb_disable() is not called, but the device resources are freed by aperture_detach_platform_device() 3. Non-primary GPU has a VGA class and it ends up calling sysfb_disable() 4. NULL pointer dereference via sysfb_disable() since the resources have already been freed by aperture_detach_platform_device() when it was called by the other device. Fix this by passing a device pointer to sysfb_disable() and checking the device to determine if we should execute it or not. v2: Fix build when CONFIG_SCREEN_INFO is not set v3: Move device check into the mutex Drop primary variable in aperture_remove_conflicting_pci_devices() Drop __init on pci sysfb_pci_dev_is_enabled()
CVE-2024-46727: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add otg_master NULL check within resource_log_pipe_topology_update [Why] Coverity reports NULL_RETURN warning. [How] Add otg_master NULL check.
CVE-2024-46728: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check index for aux_rd_interval before using aux_rd_interval has size of 7 and should be checked. This fixes 3 OVERRUN and 1 INTEGER_OVERFLOW issues reported by Coverity.
CVE-2024-46729: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix incorrect size calculation for loop [WHY] fe_clk_en has size of 5 but sizeof(fe_clk_en) has byte size 20 which is lager than the array size. [HOW] Divide byte size 20 by its element size. This fixes 2 OVERRUN issues reported by Coverity.
CVE-2024-46730: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Ensure array index tg_inst won't be -1 [WHY & HOW] tg_inst will be a negative if timing_generator_count equals 0, which should be checked before used. This fixes 2 OVERRUN issues reported by Coverity.
CVE-2024-46754: In the Linux kernel, the following vulnerability has been resolved: bpf: Remove tst_run from lwt_seg6local_prog_ops. The syzbot reported that the lwt_seg6 related BPF ops can be invoked via bpf_test_run() without without entering input_action_end_bpf() first. Martin KaFai Lau said that self test for BPF_PROG_TYPE_LWT_SEG6LOCAL probably didn't work since it was introduced in commit 04d4b274e2a ("ipv6: sr: Add seg6local action End.BPF"). The reason is that the per-CPU variable seg6_bpf_srh_states::srh is never assigned in the self test case but each BPF function expects it. Remove test_run for BPF_PROG_TYPE_LWT_SEG6LOCAL.
CVE-2024-46760: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: usb: schedule rx work after everything is set up Right now it's possible to hit NULL pointer dereference in rtw_rx_fill_rx_status on hw object and/or its fields because initialization routine can start getting USB replies before rtw_dev is fully setup. The stack trace looks like this: rtw_rx_fill_rx_status rtw8821c_query_rx_desc rtw_usb_rx_handler ... queue_work rtw_usb_read_port_complete ... usb_submit_urb rtw_usb_rx_resubmit rtw_usb_init_rx rtw_usb_probe So while we do the async stuff rtw_usb_probe continues and calls rtw_register_hw, which does all kinds of initialization (e.g. via ieee80211_register_hw) that rtw_rx_fill_rx_status relies on. Fix this by moving the first usb_submit_urb after everything is set up. For me, this bug manifested as: [ 8.893177] rtw_8821cu 1-1:1.2: band wrong, packet dropped [ 8.910904] rtw_8821cu 1-1:1.2: hw->conf.chandef.chan NULL in rtw_rx_fill_rx_status because I'm using Larry's backport of rtw88 driver with the NULL checks in rtw_rx_fill_rx_status.
CVE-2024-46765: In the Linux kernel, the following vulnerability has been resolved: ice: protect XDP configuration with a mutex The main threat to data consistency in ice_xdp() is a possible asynchronous PF reset. It can be triggered by a user or by TX timeout handler. XDP setup and PF reset code access the same resources in the following sections: * ice_vsi_close() in ice_prepare_for_reset() - already rtnl-locked * ice_vsi_rebuild() for the PF VSI - not protected * ice_vsi_open() - already rtnl-locked With an unfortunate timing, such accesses can result in a crash such as the one below: [ +1.999878] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 14 [ +2.002992] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 18 [Mar15 18:17] ice 0000:b1:00.0 ens801f0np0: NETDEV WATCHDOG: CPU: 38: transmit queue 14 timed out 80692736 ms [ +0.000093] ice 0000:b1:00.0 ens801f0np0: tx_timeout: VSI_num: 6, Q 14, NTC: 0x0, HW_HEAD: 0x0, NTU: 0x0, INT: 0x4000001 [ +0.000012] ice 0000:b1:00.0 ens801f0np0: tx_timeout recovery level 1, txqueue 14 [ +0.394718] ice 0000:b1:00.0: PTP reset successful [ +0.006184] BUG: kernel NULL pointer dereference, address: 0000000000000098 [ +0.000045] #PF: supervisor read access in kernel mode [ +0.000023] #PF: error_code(0x0000) - not-present page [ +0.000023] PGD 0 P4D 0 [ +0.000018] Oops: 0000 [#1] PREEMPT SMP NOPTI [ +0.000023] CPU: 38 PID: 7540 Comm: kworker/38:1 Not tainted 6.8.0-rc7 #1 [ +0.000031] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021 [ +0.000036] Workqueue: ice ice_service_task [ice] [ +0.000183] RIP: 0010:ice_clean_tx_ring+0xa/0xd0 [ice] [...] [ +0.000013] Call Trace: [ +0.000016] <TASK> [ +0.000014] ? __die+0x1f/0x70 [ +0.000029] ? page_fault_oops+0x171/0x4f0 [ +0.000029] ? schedule+0x3b/0xd0 [ +0.000027] ? exc_page_fault+0x7b/0x180 [ +0.000022] ? asm_exc_page_fault+0x22/0x30 [ +0.000031] ? ice_clean_tx_ring+0xa/0xd0 [ice] [ +0.000194] ice_free_tx_ring+0xe/0x60 [ice] [ +0.000186] ice_destroy_xdp_rings+0x157/0x310 [ice] [ +0.000151] ice_vsi_decfg+0x53/0xe0 [ice] [ +0.000180] ice_vsi_rebuild+0x239/0x540 [ice] [ +0.000186] ice_vsi_rebuild_by_type+0x76/0x180 [ice] [ +0.000145] ice_rebuild+0x18c/0x840 [ice] [ +0.000145] ? delay_tsc+0x4a/0xc0 [ +0.000022] ? delay_tsc+0x92/0xc0 [ +0.000020] ice_do_reset+0x140/0x180 [ice] [ +0.000886] ice_service_task+0x404/0x1030 [ice] [ +0.000824] process_one_work+0x171/0x340 [ +0.000685] worker_thread+0x277/0x3a0 [ +0.000675] ? preempt_count_add+0x6a/0xa0 [ +0.000677] ? _raw_spin_lock_irqsave+0x23/0x50 [ +0.000679] ? __pfx_worker_thread+0x10/0x10 [ +0.000653] kthread+0xf0/0x120 [ +0.000635] ? __pfx_kthread+0x10/0x10 [ +0.000616] ret_from_fork+0x2d/0x50 [ +0.000612] ? __pfx_kthread+0x10/0x10 [ +0.000604] ret_from_fork_asm+0x1b/0x30 [ +0.000604] </TASK> The previous way of handling this through returning -EBUSY is not viable, particularly when destroying AF_XDP socket, because the kernel proceeds with removal anyway. There is plenty of code between those calls and there is no need to create a large critical section that covers all of them, same as there is no need to protect ice_vsi_rebuild() with rtnl_lock(). Add xdp_state_lock mutex to protect ice_vsi_rebuild() and ice_xdp(). Leaving unprotected sections in between would result in two states that have to be considered: 1. when the VSI is closed, but not yet rebuild 2. when VSI is already rebuild, but not yet open The latter case is actually already handled through !netif_running() case, we just need to adjust flag checking a little. The former one is not as trivial, because between ice_vsi_close() and ice_vsi_rebuild(), a lot of hardware interaction happens, this can make adding/deleting rings exit with an error. Luckily, VSI rebuild is pending and can apply new configuration for us in a managed fashion. Therefore, add an additional VSI state flag ICE_VSI_REBUILD_PENDING to indicate that ice_x ---truncated---
CVE-2024-46775: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Validate function returns [WHAT & HOW] Function return values must be checked before data can be used in subsequent functions. This fixes 4 CHECKED_RETURN issues reported by Coverity.
CVE-2024-46776: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Run DC_LOG_DC after checking link->link_enc [WHAT] The DC_LOG_DC should be run after link->link_enc is checked, not before. This fixes 1 REVERSE_INULL issue reported by Coverity.
CVE-2024-46787: In the Linux kernel, the following vulnerability has been resolved: userfaultfd: fix checks for huge PMDs Patch series "userfaultfd: fix races around pmd_trans_huge() check", v2. The pmd_trans_huge() code in mfill_atomic() is wrong in three different ways depending on kernel version: 1. The pmd_trans_huge() check is racy and can lead to a BUG_ON() (if you hit the right two race windows) - I've tested this in a kernel build with some extra mdelay() calls. See the commit message for a description of the race scenario. On older kernels (before 6.5), I think the same bug can even theoretically lead to accessing transhuge page contents as a page table if you hit the right 5 narrow race windows (I haven't tested this case). 2. As pointed out by Qi Zheng, pmd_trans_huge() is not sufficient for detecting PMDs that don't point to page tables. On older kernels (before 6.5), you'd just have to win a single fairly wide race to hit this. I've tested this on 6.1 stable by racing migration (with a mdelay() patched into try_to_migrate()) against UFFDIO_ZEROPAGE - on my x86 VM, that causes a kernel oops in ptlock_ptr(). 3. On newer kernels (>=6.5), for shmem mappings, khugepaged is allowed to yank page tables out from under us (though I haven't tested that), so I think the BUG_ON() checks in mfill_atomic() are just wrong. I decided to write two separate fixes for these (one fix for bugs 1+2, one fix for bug 3), so that the first fix can be backported to kernels affected by bugs 1+2. This patch (of 2): This fixes two issues. I discovered that the following race can occur: mfill_atomic other thread ============ ============ <zap PMD> pmdp_get_lockless() [reads none pmd] <bail if trans_huge> <if none:> <pagefault creates transhuge zeropage> __pte_alloc [no-op] <zap PMD> <bail if pmd_trans_huge(*dst_pmd)> BUG_ON(pmd_none(*dst_pmd)) I have experimentally verified this in a kernel with extra mdelay() calls; the BUG_ON(pmd_none(*dst_pmd)) triggers. On kernels newer than commit 0d940a9b270b ("mm/pgtable: allow pte_offset_map[_lock]() to fail"), this can't lead to anything worse than a BUG_ON(), since the page table access helpers are actually designed to deal with page tables concurrently disappearing; but on older kernels (<=6.4), I think we could probably theoretically race past the two BUG_ON() checks and end up treating a hugepage as a page table. The second issue is that, as Qi Zheng pointed out, there are other types of huge PMDs that pmd_trans_huge() can't catch: devmap PMDs and swap PMDs (in particular, migration PMDs). On <=6.4, this is worse than the first issue: If mfill_atomic() runs on a PMD that contains a migration entry (which just requires winning a single, fairly wide race), it will pass the PMD to pte_offset_map_lock(), which assumes that the PMD points to a page table. Breakage follows: First, the kernel tries to take the PTE lock (which will crash or maybe worse if there is no "struct page" for the address bits in the migration entry PMD - I think at least on X86 there usually is no corresponding "struct page" thanks to the PTE inversion mitigation, amd64 looks different). If that didn't crash, the kernel would next try to write a PTE into what it wrongly thinks is a page table. As part of fixing these issues, get rid of the check for pmd_trans_huge() before __pte_alloc() - that's redundant, we're going to have to check for that after the __pte_alloc() anyway. Backport note: pmdp_get_lockless() is pmd_read_atomic() in older kernels.
CVE-2024-46806: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix the warning division or modulo by zero Checks the partition mode and returns an error for an invalid mode.
CVE-2024-46808: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add missing NULL pointer check within dpcd_extend_address_range [Why & How] ASSERT if return NULL from kcalloc.
CVE-2024-46811: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix index may exceed array range within fpu_update_bw_bounding_box [Why] Coverity reports OVERRUN warning. soc.num_states could be 40. But array range of bw_params->clk_table.entries is 8. [How] Assert if soc.num_states greater than 8.
CVE-2024-46813: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check link_index before accessing dc->links[] [WHY & HOW] dc->links[] has max size of MAX_LINKS and NULL is return when trying to access with out-of-bound index. This fixes 3 OVERRUN and 1 RESOURCE_LEAK issues reported by Coverity.
CVE-2024-46834: In the Linux kernel, the following vulnerability has been resolved: ethtool: fail closed if we can't get max channel used in indirection tables Commit 0d1b7d6c9274 ("bnxt: fix crashes when reducing ring count with active RSS contexts") proves that allowing indirection table to contain channels with out of bounds IDs may lead to crashes. Currently the max channel check in the core gets skipped if driver can't fetch the indirection table or when we can't allocate memory. Both of those conditions should be extremely rare but if they do happen we should try to be safe and fail the channel change.
CVE-2024-46860: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: mt7921: fix NULL pointer access in mt7921_ipv6_addr_change When disabling wifi mt7921_ipv6_addr_change() is called as a notifier. At this point mvif->phy is already NULL so we cannot use it here.
CVE-2024-46870: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Disable DMCUB timeout for DCN35 [Why] DMCUB can intermittently take longer than expected to process commands. Old ASIC policy was to continue while logging a diagnostic error - which works fine for ASIC without IPS, but with IPS this could lead to a race condition where we attempt to access DCN state while it's inaccessible, leading to a system hang when the NIU port is not disabled or register accesses that timeout and the display configuration in an undefined state. [How] We need to investigate why these accesses take longer than expected, but for now we should disable the timeout on DCN35 to avoid this race condition. Since the waits happen only at lower interrupt levels the risk of taking too long at higher IRQ and causing a system watchdog timeout are minimal.
CVE-2024-47141: In the Linux kernel, the following vulnerability has been resolved: pinmux: Use sequential access to access desc->pinmux data When two client of the same gpio call pinctrl_select_state() for the same functionality, we are seeing NULL pointer issue while accessing desc->mux_owner. Let's say two processes A, B executing in pin_request() for the same pin and process A updates the desc->mux_usecount but not yet updated the desc->mux_owner while process B see the desc->mux_usecount which got updated by A path and further executes strcmp and while accessing desc->mux_owner it crashes with NULL pointer. Serialize the access to mux related setting with a mutex lock. cpu0 (process A) cpu1(process B) pinctrl_select_state() { pinctrl_select_state() { pin_request() { pin_request() { ... .... } else { desc->mux_usecount++; desc->mux_usecount && strcmp(desc->mux_owner, owner)) { if (desc->mux_usecount > 1) return 0; desc->mux_owner = owner; } }
CVE-2024-47658: In the Linux kernel, the following vulnerability has been resolved: crypto: stm32/cryp - call finalize with bh disabled The finalize operation in interrupt mode produce a produces a spinlock recursion warning. The reason is the fact that BH must be disabled during this process.
CVE-2024-47661: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Avoid overflow from uint32_t to uint8_t [WHAT & HOW] dmub_rb_cmd's ramping_boundary has size of uint8_t and it is assigned 0xFFFF. Fix it by changing it to uint8_t with value of 0xFF. This fixes 2 INTEGER_OVERFLOW issues reported by Coverity.
CVE-2024-47662: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Remove register from DCN35 DMCUB diagnostic collection [Why] These registers should not be read from driver and triggering the security violation when DMCUB work times out and diagnostics are collected blocks Z8 entry. [How] Remove the register read from DCN35.
CVE-2024-47664: In the Linux kernel, the following vulnerability has been resolved: spi: hisi-kunpeng: Add verification for the max_frequency provided by the firmware If the value of max_speed_hz is 0, it may cause a division by zero error in hisi_calc_effective_speed(). The value of max_speed_hz is provided by firmware. Firmware is generally considered as a trusted domain. However, as division by zero errors can cause system failure, for defense measure, the value of max_speed is validated here. So 0 is regarded as invalid and an error code is returned.
CVE-2024-47691: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid use-after-free in f2fs_stop_gc_thread() syzbot reports a f2fs bug as below: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_report+0xe8/0x550 mm/kasan/report.c:491 kasan_report+0x143/0x180 mm/kasan/report.c:601 kasan_check_range+0x282/0x290 mm/kasan/generic.c:189 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_fetch_add_relaxed include/linux/atomic/atomic-instrumented.h:252 [inline] __refcount_add include/linux/refcount.h:184 [inline] __refcount_inc include/linux/refcount.h:241 [inline] refcount_inc include/linux/refcount.h:258 [inline] get_task_struct include/linux/sched/task.h:118 [inline] kthread_stop+0xca/0x630 kernel/kthread.c:704 f2fs_stop_gc_thread+0x65/0xb0 fs/f2fs/gc.c:210 f2fs_do_shutdown+0x192/0x540 fs/f2fs/file.c:2283 f2fs_ioc_shutdown fs/f2fs/file.c:2325 [inline] __f2fs_ioctl+0x443a/0xbe60 fs/f2fs/file.c:4325 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is below race condition, it may cause use-after-free issue in sbi->gc_th pointer. - remount - f2fs_remount - f2fs_stop_gc_thread - kfree(gc_th) - f2fs_ioc_shutdown - f2fs_do_shutdown - f2fs_stop_gc_thread - kthread_stop(gc_th->f2fs_gc_task) : sbi->gc_thread = NULL; We will call f2fs_do_shutdown() in two paths: - for f2fs_ioc_shutdown() path, we should grab sb->s_umount semaphore for fixing. - for f2fs_shutdown() path, it's safe since caller has already grabbed sb->s_umount semaphore.
CVE-2024-47703: In the Linux kernel, the following vulnerability has been resolved: bpf, lsm: Add check for BPF LSM return value A bpf prog returning a positive number attached to file_alloc_security hook makes kernel panic. This happens because file system can not filter out the positive number returned by the LSM prog using IS_ERR, and misinterprets this positive number as a file pointer. Given that hook file_alloc_security never returned positive number before the introduction of BPF LSM, and other BPF LSM hooks may encounter similar issues, this patch adds LSM return value check in verifier, to ensure no unexpected value is returned.
CVE-2024-47736: In the Linux kernel, the following vulnerability has been resolved: erofs: handle overlapped pclusters out of crafted images properly syzbot reported a task hang issue due to a deadlock case where it is waiting for the folio lock of a cached folio that will be used for cache I/Os. After looking into the crafted fuzzed image, I found it's formed with several overlapped big pclusters as below: Ext: logical offset | length : physical offset | length 0: 0.. 16384 | 16384 : 151552.. 167936 | 16384 1: 16384.. 32768 | 16384 : 155648.. 172032 | 16384 2: 32768.. 49152 | 16384 : 537223168.. 537239552 | 16384 ... Here, extent 0/1 are physically overlapped although it's entirely _impossible_ for normal filesystem images generated by mkfs. First, managed folios containing compressed data will be marked as up-to-date and then unlocked immediately (unlike in-place folios) when compressed I/Os are complete. If physical blocks are not submitted in the incremental order, there should be separate BIOs to avoid dependency issues. However, the current code mis-arranges z_erofs_fill_bio_vec() and BIO submission which causes unexpected BIO waits. Second, managed folios will be connected to their own pclusters for efficient inter-queries. However, this is somewhat hard to implement easily if overlapped big pclusters exist. Again, these only appear in fuzzed images so let's simply fall back to temporary short-lived pages for correctness. Additionally, it justifies that referenced managed folios cannot be truncated for now and reverts part of commit 2080ca1ed3e4 ("erofs: tidy up `struct z_erofs_bvec`") for simplicity although it shouldn't be any difference.
CVE-2024-47752: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: Fix H264 stateless decoder smatch warning Fix a smatch static checker warning on vdec_h264_req_if.c. Which leads to a kernel crash when fb is NULL.
CVE-2024-47794: In the Linux kernel, the following vulnerability has been resolved: bpf: Prevent tailcall infinite loop caused by freplace There is a potential infinite loop issue that can occur when using a combination of tail calls and freplace. In an upcoming selftest, the attach target for entry_freplace of tailcall_freplace.c is subprog_tc of tc_bpf2bpf.c, while the tail call in entry_freplace leads to entry_tc. This results in an infinite loop: entry_tc -> subprog_tc -> entry_freplace --tailcall-> entry_tc. The problem arises because the tail_call_cnt in entry_freplace resets to zero each time entry_freplace is executed, causing the tail call mechanism to never terminate, eventually leading to a kernel panic. To fix this issue, the solution is twofold: 1. Prevent updating a program extended by an freplace program to a prog_array map. 2. Prevent extending a program that is already part of a prog_array map with an freplace program. This ensures that: * If a program or its subprogram has been extended by an freplace program, it can no longer be updated to a prog_array map. * If a program has been added to a prog_array map, neither it nor its subprograms can be extended by an freplace program. Moreover, an extension program should not be tailcalled. As such, return -EINVAL if the program has a type of BPF_PROG_TYPE_EXT when adding it to a prog_array map. Additionally, fix a minor code style issue by replacing eight spaces with a tab for proper formatting.
CVE-2024-47809: In the Linux kernel, the following vulnerability has been resolved: dlm: fix possible lkb_resource null dereference This patch fixes a possible null pointer dereference when this function is called from request_lock() as lkb->lkb_resource is not assigned yet, only after validate_lock_args() by calling attach_lkb(). Another issue is that a resource name could be a non printable bytearray and we cannot assume to be ASCII coded. The log functionality is probably never being hit when DLM is used in normal way and no debug logging is enabled. The null pointer dereference can only occur on a new created lkb that does not have the resource assigned yet, it probably never hits the null pointer dereference but we should be sure that other changes might not change this behaviour and we actually can hit the mentioned null pointer dereference. In this patch we just drop the printout of the resource name, the lkb id is enough to make a possible connection to a resource name if this exists.
CVE-2024-49568: In the Linux kernel, the following vulnerability has been resolved: net/smc: check v2_ext_offset/eid_cnt/ism_gid_cnt when receiving proposal msg When receiving proposal msg in server, the fields v2_ext_offset/ eid_cnt/ism_gid_cnt in proposal msg are from the remote client and can not be fully trusted. Especially the field v2_ext_offset, once exceed the max value, there has the chance to access wrong address, and crash may happen. This patch checks the fields v2_ext_offset/eid_cnt/ism_gid_cnt before using them.
CVE-2024-49569: In the Linux kernel, the following vulnerability has been resolved: nvme-rdma: unquiesce admin_q before destroy it Kernel will hang on destroy admin_q while we create ctrl failed, such as following calltrace: PID: 23644 TASK: ff2d52b40f439fc0 CPU: 2 COMMAND: "nvme" #0 [ff61d23de260fb78] __schedule at ffffffff8323bc15 #1 [ff61d23de260fc08] schedule at ffffffff8323c014 #2 [ff61d23de260fc28] blk_mq_freeze_queue_wait at ffffffff82a3dba1 #3 [ff61d23de260fc78] blk_freeze_queue at ffffffff82a4113a #4 [ff61d23de260fc90] blk_cleanup_queue at ffffffff82a33006 #5 [ff61d23de260fcb0] nvme_rdma_destroy_admin_queue at ffffffffc12686ce #6 [ff61d23de260fcc8] nvme_rdma_setup_ctrl at ffffffffc1268ced #7 [ff61d23de260fd28] nvme_rdma_create_ctrl at ffffffffc126919b #8 [ff61d23de260fd68] nvmf_dev_write at ffffffffc024f362 #9 [ff61d23de260fe38] vfs_write at ffffffff827d5f25 RIP: 00007fda7891d574 RSP: 00007ffe2ef06958 RFLAGS: 00000202 RAX: ffffffffffffffda RBX: 000055e8122a4d90 RCX: 00007fda7891d574 RDX: 000000000000012b RSI: 000055e8122a4d90 RDI: 0000000000000004 RBP: 00007ffe2ef079c0 R8: 000000000000012b R9: 000055e8122a4d90 R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000004 R13: 000055e8122923c0 R14: 000000000000012b R15: 00007fda78a54500 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b This due to we have quiesced admi_q before cancel requests, but forgot to unquiesce before destroy it, as a result we fail to drain the pending requests, and hang on blk_mq_freeze_queue_wait() forever. Here try to reuse nvme_rdma_teardown_admin_queue() to fix this issue and simplify the code.
CVE-2024-49893: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check stream_status before it is used [WHAT & HOW] dc_state_get_stream_status can return null, and therefore null must be checked before stream_status is used. This fixes 1 NULL_RETURNS issue reported by Coverity.
CVE-2024-49901: In the Linux kernel, the following vulnerability has been resolved: drm/msm/adreno: Assign msm_gpu->pdev earlier to avoid nullptrs There are some cases, such as the one uncovered by Commit 46d4efcccc68 ("drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails") where msm_gpu_cleanup() : platform_set_drvdata(gpu->pdev, NULL); is called on gpu->pdev == NULL, as the GPU device has not been fully initialized yet. Turns out that there's more than just the aforementioned path that causes this to happen (e.g. the case when there's speedbin data in the catalog, but opp-supported-hw is missing in DT). Assigning msm_gpu->pdev earlier seems like the least painful solution to this, therefore do so. Patchwork: https://patchwork.freedesktop.org/patch/602742/
CVE-2024-49906: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointer before try to access it [why & how] Change the order of the pipe_ctx->plane_state check to ensure that plane_state is not null before accessing it.
CVE-2024-49908: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for 'afb' in amdgpu_dm_update_cursor (v2) This commit adds a null check for the 'afb' variable in the amdgpu_dm_update_cursor function. Previously, 'afb' was assumed to be null at line 8388, but was used later in the code without a null check. This could potentially lead to a null pointer dereference. Changes since v1: - Moved the null check for 'afb' to the line where 'afb' is used. (Alex) Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:8433 amdgpu_dm_update_cursor() error: we previously assumed 'afb' could be null (see line 8388)
CVE-2024-49910: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for function pointer in dcn401_set_output_transfer_func This commit adds a null check for the set_output_gamma function pointer in the dcn401_set_output_transfer_func function. Previously, set_output_gamma was being checked for null, but then it was being dereferenced without any null check. This could lead to a null pointer dereference if set_output_gamma is null. To fix this, we now ensure that set_output_gamma is not null before dereferencing it. We do this by adding a null check for set_output_gamma before the call to set_output_gamma.
CVE-2024-49914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe This commit addresses a null pointer dereference issue in the `dcn20_program_pipe` function. The issue could occur when `pipe_ctx->plane_state` is null. The fix adds a check to ensure `pipe_ctx->plane_state` is not null before accessing. This prevents a null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn20/dcn20_hwseq.c:1925 dcn20_program_pipe() error: we previously assumed 'pipe_ctx->plane_state' could be null (see line 1877)
CVE-2024-49916: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add NULL check for clk_mgr and clk_mgr->funcs in dcn401_init_hw This commit addresses a potential null pointer dereference issue in the `dcn401_init_hw` function. The issue could occur when `dc->clk_mgr` or `dc->clk_mgr->funcs` is null. The fix adds a check to ensure `dc->clk_mgr` and `dc->clk_mgr->funcs` is not null before accessing its functions. This prevents a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn401/dcn401_hwseq.c:416 dcn401_init_hw() error: we previously assumed 'dc->clk_mgr' could be null (see line 225)
CVE-2024-49918: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for head_pipe in dcn32_acquire_idle_pipe_for_head_pipe_in_layer This commit addresses a potential null pointer dereference issue in the `dcn32_acquire_idle_pipe_for_head_pipe_in_layer` function. The issue could occur when `head_pipe` is null. The fix adds a check to ensure `head_pipe` is not null before asserting it. If `head_pipe` is null, the function returns NULL to prevent a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn32/dcn32_resource.c:2690 dcn32_acquire_idle_pipe_for_head_pipe_in_layer() error: we previously assumed 'head_pipe' could be null (see line 2681)
CVE-2024-49919: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add null check for head_pipe in dcn201_acquire_free_pipe_for_layer This commit addresses a potential null pointer dereference issue in the `dcn201_acquire_free_pipe_for_layer` function. The issue could occur when `head_pipe` is null. The fix adds a check to ensure `head_pipe` is not null before asserting it. If `head_pipe` is null, the function returns NULL to prevent a potential null pointer dereference. Reported by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn201/dcn201_resource.c:1016 dcn201_acquire_free_pipe_for_layer() error: we previously assumed 'head_pipe' could be null (see line 1010)
CVE-2024-49920: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before multiple uses [WHAT & HOW] Poniters, such as stream_enc and dc->bw_vbios, are null checked previously in the same function, so Coverity warns "implies that stream_enc and dc->bw_vbios might be null". They are used multiple times in the subsequent code and need to be checked. This fixes 10 FORWARD_NULL issues reported by Coverity.
CVE-2024-49921: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before used [WHAT & HOW] Poniters, such as dc->clk_mgr, are null checked previously in the same function, so Coverity warns "implies that "dc->clk_mgr" might be null". As a result, these pointers need to be checked when used again. This fixes 10 FORWARD_NULL issues reported by Coverity.
CVE-2024-49922: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Check null pointers before using them [WHAT & HOW] These pointers are null checked previously in the same function, indicating they might be null as reported by Coverity. As a result, they need to be checked when used again. This fixes 3 FORWARD_NULL issue reported by Coverity.
CVE-2024-49923: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Pass non-null to dcn20_validate_apply_pipe_split_flags [WHAT & HOW] "dcn20_validate_apply_pipe_split_flags" dereferences merge, and thus it cannot be a null pointer. Let's pass a valid pointer to avoid null dereference. This fixes 2 FORWARD_NULL issues reported by Coverity.
CVE-2024-49926: In the Linux kernel, the following vulnerability has been resolved: rcu-tasks: Fix access non-existent percpu rtpcp variable in rcu_tasks_need_gpcb() For kernels built with CONFIG_FORCE_NR_CPUS=y, the nr_cpu_ids is defined as NR_CPUS instead of the number of possible cpus, this will cause the following system panic: smpboot: Allowing 4 CPUs, 0 hotplug CPUs ... setup_percpu: NR_CPUS:512 nr_cpumask_bits:512 nr_cpu_ids:512 nr_node_ids:1 ... BUG: unable to handle page fault for address: ffffffff9911c8c8 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 15 Comm: rcu_tasks_trace Tainted: G W 6.6.21 #1 5dc7acf91a5e8e9ac9dcfc35bee0245691283ea6 RIP: 0010:rcu_tasks_need_gpcb+0x25d/0x2c0 RSP: 0018:ffffa371c00a3e60 EFLAGS: 00010082 CR2: ffffffff9911c8c8 CR3: 000000040fa20005 CR4: 00000000001706f0 Call Trace: <TASK> ? __die+0x23/0x80 ? page_fault_oops+0xa4/0x180 ? exc_page_fault+0x152/0x180 ? asm_exc_page_fault+0x26/0x40 ? rcu_tasks_need_gpcb+0x25d/0x2c0 ? __pfx_rcu_tasks_kthread+0x40/0x40 rcu_tasks_one_gp+0x69/0x180 rcu_tasks_kthread+0x94/0xc0 kthread+0xe8/0x140 ? __pfx_kthread+0x40/0x40 ret_from_fork+0x34/0x80 ? __pfx_kthread+0x40/0x40 ret_from_fork_asm+0x1b/0x80 </TASK> Considering that there may be holes in the CPU numbers, use the maximum possible cpu number, instead of nr_cpu_ids, for configuring enqueue and dequeue limits. [ neeraj.upadhyay: Fix htmldocs build error reported by Stephen Rothwell ]
CVE-2024-49940: In the Linux kernel, the following vulnerability has been resolved: l2tp: prevent possible tunnel refcount underflow When a session is created, it sets a backpointer to its tunnel. When the session refcount drops to 0, l2tp_session_free drops the tunnel refcount if session->tunnel is non-NULL. However, session->tunnel is set in l2tp_session_create, before the tunnel refcount is incremented by l2tp_session_register, which leaves a small window where session->tunnel is non-NULL when the tunnel refcount hasn't been bumped. Moving the assignment to l2tp_session_register is trivial but l2tp_session_create calls l2tp_session_set_header_len which uses session->tunnel to get the tunnel's encap. Add an encap arg to l2tp_session_set_header_len to avoid using session->tunnel. If l2tpv3 sessions have colliding IDs, it is possible for l2tp_v3_session_get to race with l2tp_session_register and fetch a session which doesn't yet have session->tunnel set. Add a check for this case.
CVE-2024-49945: In the Linux kernel, the following vulnerability has been resolved: net/ncsi: Disable the ncsi work before freeing the associated structure The work function can run after the ncsi device is freed, resulting in use-after-free bugs or kernel panic.
CVE-2024-49970: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Implement bounds check for stream encoder creation in DCN401 'stream_enc_regs' array is an array of dcn10_stream_enc_registers structures. The array is initialized with four elements, corresponding to the four calls to stream_enc_regs() in the array initializer. This means that valid indices for this array are 0, 1, 2, and 3. The error message 'stream_enc_regs' 4 <= 5 below, is indicating that there is an attempt to access this array with an index of 5, which is out of bounds. This could lead to undefined behavior Here, eng_id is used as an index to access the stream_enc_regs array. If eng_id is 5, this would result in an out-of-bounds access on the stream_enc_regs array. Thus fixing Buffer overflow error in dcn401_stream_encoder_create Found by smatch: drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn401/dcn401_resource.c:1209 dcn401_stream_encoder_create() error: buffer overflow 'stream_enc_regs' 4 <= 5
CVE-2024-49988: In the Linux kernel, the following vulnerability has been resolved: ksmbd: add refcnt to ksmbd_conn struct When sending an oplock break request, opinfo->conn is used, But freed ->conn can be used on multichannel. This patch add a reference count to the ksmbd_conn struct so that it can be freed when it is no longer used.
CVE-2024-49998: In the Linux kernel, the following vulnerability has been resolved: net: dsa: improve shutdown sequence Alexander Sverdlin presents 2 problems during shutdown with the lan9303 driver. One is specific to lan9303 and the other just happens to reproduce there. The first problem is that lan9303 is unique among DSA drivers in that it calls dev_get_drvdata() at "arbitrary runtime" (not probe, not shutdown, not remove): phy_state_machine() -> ... -> dsa_user_phy_read() -> ds->ops->phy_read() -> lan9303_phy_read() -> chip->ops->phy_read() -> lan9303_mdio_phy_read() -> dev_get_drvdata() But we never stop the phy_state_machine(), so it may continue to run after dsa_switch_shutdown(). Our common pattern in all DSA drivers is to set drvdata to NULL to suppress the remove() method that may come afterwards. But in this case it will result in an NPD. The second problem is that the way in which we set dp->conduit->dsa_ptr = NULL; is concurrent with receive packet processing. dsa_switch_rcv() checks once whether dev->dsa_ptr is NULL, but afterwards, rather than continuing to use that non-NULL value, dev->dsa_ptr is dereferenced again and again without NULL checks: dsa_conduit_find_user() and many other places. In between dereferences, there is no locking to ensure that what was valid once continues to be valid. Both problems have the common aspect that closing the conduit interface solves them. In the first case, dev_close(conduit) triggers the NETDEV_GOING_DOWN event in dsa_user_netdevice_event() which closes user ports as well. dsa_port_disable_rt() calls phylink_stop(), which synchronously stops the phylink state machine, and ds->ops->phy_read() will thus no longer call into the driver after this point. In the second case, dev_close(conduit) should do this, as per Documentation/networking/driver.rst: | Quiescence | ---------- | | After the ndo_stop routine has been called, the hardware must | not receive or transmit any data. All in flight packets must | be aborted. If necessary, poll or wait for completion of | any reset commands. So it should be sufficient to ensure that later, when we zeroize conduit->dsa_ptr, there will be no concurrent dsa_switch_rcv() call on this conduit. The addition of the netif_device_detach() function is to ensure that ioctls, rtnetlinks and ethtool requests on the user ports no longer propagate down to the driver - we're no longer prepared to handle them. The race condition actually did not exist when commit 0650bf52b31f ("net: dsa: be compatible with masters which unregister on shutdown") first introduced dsa_switch_shutdown(). It was created later, when we stopped unregistering the user interfaces from a bad spot, and we just replaced that sequence with a racy zeroization of conduit->dsa_ptr (one which doesn't ensure that the interfaces aren't up).
CVE-2024-50009: In the Linux kernel, the following vulnerability has been resolved: cpufreq: amd-pstate: add check for cpufreq_cpu_get's return value cpufreq_cpu_get may return NULL. To avoid NULL-dereference check it and return in case of error. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2024-50017: In the Linux kernel, the following vulnerability has been resolved: x86/mm/ident_map: Use gbpages only where full GB page should be mapped. When ident_pud_init() uses only GB pages to create identity maps, large ranges of addresses not actually requested can be included in the resulting table; a 4K request will map a full GB. This can include a lot of extra address space past that requested, including areas marked reserved by the BIOS. That allows processor speculation into reserved regions, that on UV systems can cause system halts. Only use GB pages when map creation requests include the full GB page of space. Fall back to using smaller 2M pages when only portions of a GB page are included in the request. No attempt is made to coalesce mapping requests. If a request requires a map entry at the 2M (pmd) level, subsequent mapping requests within the same 1G region will also be at the pmd level, even if adjacent or overlapping such requests could have been combined to map a full GB page. Existing usage starts with larger regions and then adds smaller regions, so this should not have any great consequence.
CVE-2024-50028: In the Linux kernel, the following vulnerability has been resolved: thermal: core: Reference count the zone in thermal_zone_get_by_id() There are places in the thermal netlink code where nothing prevents the thermal zone object from going away while being accessed after it has been returned by thermal_zone_get_by_id(). To address this, make thermal_zone_get_by_id() get a reference on the thermal zone device object to be returned with the help of get_device(), under thermal_list_lock, and adjust all of its callers to this change with the help of the cleanup.h infrastructure.
CVE-2024-50029: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: Fix UAF in hci_enhanced_setup_sync This checks if the ACL connection remains valid as it could be destroyed while hci_enhanced_setup_sync is pending on cmd_sync leading to the following trace: BUG: KASAN: slab-use-after-free in hci_enhanced_setup_sync+0x91b/0xa60 Read of size 1 at addr ffff888002328ffd by task kworker/u5:2/37 CPU: 0 UID: 0 PID: 37 Comm: kworker/u5:2 Not tainted 6.11.0-rc6-01300-g810be445d8d6 #7099 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 Workqueue: hci0 hci_cmd_sync_work Call Trace: <TASK> dump_stack_lvl+0x5d/0x80 ? hci_enhanced_setup_sync+0x91b/0xa60 print_report+0x152/0x4c0 ? hci_enhanced_setup_sync+0x91b/0xa60 ? __virt_addr_valid+0x1fa/0x420 ? hci_enhanced_setup_sync+0x91b/0xa60 kasan_report+0xda/0x1b0 ? hci_enhanced_setup_sync+0x91b/0xa60 hci_enhanced_setup_sync+0x91b/0xa60 ? __pfx_hci_enhanced_setup_sync+0x10/0x10 ? __pfx___mutex_lock+0x10/0x10 hci_cmd_sync_work+0x1c2/0x330 process_one_work+0x7d9/0x1360 ? __pfx_lock_acquire+0x10/0x10 ? __pfx_process_one_work+0x10/0x10 ? assign_work+0x167/0x240 worker_thread+0x5b7/0xf60 ? __kthread_parkme+0xac/0x1c0 ? __pfx_worker_thread+0x10/0x10 ? __pfx_worker_thread+0x10/0x10 kthread+0x293/0x360 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Allocated by task 34: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 __hci_conn_add+0x187/0x17d0 hci_connect_sco+0x2e1/0xb90 sco_sock_connect+0x2a2/0xb80 __sys_connect+0x227/0x2a0 __x64_sys_connect+0x6d/0xb0 do_syscall_64+0x71/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 37: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x101/0x160 kfree+0xd0/0x250 device_release+0x9a/0x210 kobject_put+0x151/0x280 hci_conn_del+0x448/0xbf0 hci_abort_conn_sync+0x46f/0x980 hci_cmd_sync_work+0x1c2/0x330 process_one_work+0x7d9/0x1360 worker_thread+0x5b7/0xf60 kthread+0x293/0x360 ret_from_fork+0x2f/0x70 ret_from_fork_asm+0x1a/0x30
CVE-2024-50057: In the Linux kernel, the following vulnerability has been resolved: usb: typec: tipd: Free IRQ only if it was requested before In polling mode, if no IRQ was requested there is no need to free it. Call devm_free_irq() only if client->irq is set. This fixes the warning caused by the tps6598x module removal: WARNING: CPU: 2 PID: 333 at kernel/irq/devres.c:144 devm_free_irq+0x80/0x8c ... ... Call trace: devm_free_irq+0x80/0x8c tps6598x_remove+0x28/0x88 [tps6598x] i2c_device_remove+0x2c/0x9c device_remove+0x4c/0x80 device_release_driver_internal+0x1cc/0x228 driver_detach+0x50/0x98 bus_remove_driver+0x6c/0xbc driver_unregister+0x30/0x60 i2c_del_driver+0x54/0x64 tps6598x_i2c_driver_exit+0x18/0xc3c [tps6598x] __arm64_sys_delete_module+0x184/0x264 invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0xc8/0xe8 do_el0_svc+0x20/0x2c el0_svc+0x28/0x98 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194
CVE-2024-50111: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Enable IRQ if do_ale() triggered in irq-enabled context Unaligned access exception can be triggered in irq-enabled context such as user mode, in this case do_ale() may call get_user() which may cause sleep. Then we will get: BUG: sleeping function called from invalid context at arch/loongarch/kernel/access-helper.h:7 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 129, name: modprobe preempt_count: 0, expected: 0 RCU nest depth: 0, expected: 0 CPU: 0 UID: 0 PID: 129 Comm: modprobe Tainted: G W 6.12.0-rc1+ #1723 Tainted: [W]=WARN Stack : 9000000105e0bd48 0000000000000000 9000000003803944 9000000105e08000 9000000105e0bc70 9000000105e0bc78 0000000000000000 0000000000000000 9000000105e0bc78 0000000000000001 9000000185e0ba07 9000000105e0b890 ffffffffffffffff 9000000105e0bc78 73924b81763be05b 9000000100194500 000000000000020c 000000000000000a 0000000000000000 0000000000000003 00000000000023f0 00000000000e1401 00000000072f8000 0000007ffbb0e260 0000000000000000 0000000000000000 9000000005437650 90000000055d5000 0000000000000000 0000000000000003 0000007ffbb0e1f0 0000000000000000 0000005567b00490 0000000000000000 9000000003803964 0000007ffbb0dfec 00000000000000b0 0000000000000007 0000000000000003 0000000000071c1d ... Call Trace: [<9000000003803964>] show_stack+0x64/0x1a0 [<9000000004c57464>] dump_stack_lvl+0x74/0xb0 [<9000000003861ab4>] __might_resched+0x154/0x1a0 [<900000000380c96c>] emulate_load_store_insn+0x6c/0xf60 [<9000000004c58118>] do_ale+0x78/0x180 [<9000000003801bc8>] handle_ale+0x128/0x1e0 So enable IRQ if unaligned access exception is triggered in irq-enabled context to fix it.
CVE-2024-50135: In the Linux kernel, the following vulnerability has been resolved: nvme-pci: fix race condition between reset and nvme_dev_disable() nvme_dev_disable() modifies the dev->online_queues field, therefore nvme_pci_update_nr_queues() should avoid racing against it, otherwise we could end up passing invalid values to blk_mq_update_nr_hw_queues(). WARNING: CPU: 39 PID: 61303 at drivers/pci/msi/api.c:347 pci_irq_get_affinity+0x187/0x210 Workqueue: nvme-reset-wq nvme_reset_work [nvme] RIP: 0010:pci_irq_get_affinity+0x187/0x210 Call Trace: <TASK> ? blk_mq_pci_map_queues+0x87/0x3c0 ? pci_irq_get_affinity+0x187/0x210 blk_mq_pci_map_queues+0x87/0x3c0 nvme_pci_map_queues+0x189/0x460 [nvme] blk_mq_update_nr_hw_queues+0x2a/0x40 nvme_reset_work+0x1be/0x2a0 [nvme] Fix the bug by locking the shutdown_lock mutex before using dev->online_queues. Give up if nvme_dev_disable() is running or if it has been executed already.
CVE-2024-50166: In the Linux kernel, the following vulnerability has been resolved: fsl/fman: Fix refcount handling of fman-related devices In mac_probe() there are multiple calls to of_find_device_by_node(), fman_bind() and fman_port_bind() which takes references to of_dev->dev. Not all references taken by these calls are released later on error path in mac_probe() and in mac_remove() which lead to reference leaks. Add references release.
CVE-2024-50211: In the Linux kernel, the following vulnerability has been resolved: udf: refactor inode_bmap() to handle error Refactor inode_bmap() to handle error since udf_next_aext() can return error now. On situations like ftruncate, udf_extend_file() can now detect errors and bail out early without resorting to checking for particular offsets and assuming internal behavior of these functions.
CVE-2024-50217: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix use-after-free of block device file in __btrfs_free_extra_devids() Mounting btrfs from two images (which have the same one fsid and two different dev_uuids) in certain executing order may trigger an UAF for variable 'device->bdev_file' in __btrfs_free_extra_devids(). And following are the details: 1. Attach image_1 to loop0, attach image_2 to loop1, and scan btrfs devices by ioctl(BTRFS_IOC_SCAN_DEV): / btrfs_device_1 → loop0 fs_device \ btrfs_device_2 → loop1 2. mount /dev/loop0 /mnt btrfs_open_devices btrfs_device_1->bdev_file = btrfs_get_bdev_and_sb(loop0) btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1) btrfs_fill_super open_ctree fail: btrfs_close_devices // -ENOMEM btrfs_close_bdev(btrfs_device_1) fput(btrfs_device_1->bdev_file) // btrfs_device_1->bdev_file is freed btrfs_close_bdev(btrfs_device_2) fput(btrfs_device_2->bdev_file) 3. mount /dev/loop1 /mnt btrfs_open_devices btrfs_get_bdev_and_sb(&bdev_file) // EIO, btrfs_device_1->bdev_file is not assigned, // which points to a freed memory area btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1) btrfs_fill_super open_ctree btrfs_free_extra_devids if (btrfs_device_1->bdev_file) fput(btrfs_device_1->bdev_file) // UAF ! Fix it by setting 'device->bdev_file' as 'NULL' after closing the btrfs_device in btrfs_close_one_device().
CVE-2024-50226: In the Linux kernel, the following vulnerability has been resolved: cxl/port: Fix use-after-free, permit out-of-order decoder shutdown In support of investigating an initialization failure report [1], cxl_test was updated to register mock memory-devices after the mock root-port/bus device had been registered. That led to cxl_test crashing with a use-after-free bug with the following signature: cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem0:decoder7.0 @ 0 next: cxl_switch_uport.0 nr_eps: 1 nr_targets: 1 cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem4:decoder14.0 @ 1 next: cxl_switch_uport.0 nr_eps: 2 nr_targets: 1 cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[0] = cxl_switch_dport.0 for mem0:decoder7.0 @ 0 1) cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[1] = cxl_switch_dport.4 for mem4:decoder14.0 @ 1 [..] cxld_unregister: cxl decoder14.0: cxl_region_decode_reset: cxl_region region3: mock_decoder_reset: cxl_port port3: decoder3.0 reset 2) mock_decoder_reset: cxl_port port3: decoder3.0: out of order reset, expected decoder3.1 cxl_endpoint_decoder_release: cxl decoder14.0: [..] cxld_unregister: cxl decoder7.0: 3) cxl_region_decode_reset: cxl_region region3: Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6bc3: 0000 [#1] PREEMPT SMP PTI [..] RIP: 0010:to_cxl_port+0x8/0x60 [cxl_core] [..] Call Trace: <TASK> cxl_region_decode_reset+0x69/0x190 [cxl_core] cxl_region_detach+0xe8/0x210 [cxl_core] cxl_decoder_kill_region+0x27/0x40 [cxl_core] cxld_unregister+0x5d/0x60 [cxl_core] At 1) a region has been established with 2 endpoint decoders (7.0 and 14.0). Those endpoints share a common switch-decoder in the topology (3.0). At teardown, 2), decoder14.0 is the first to be removed and hits the "out of order reset case" in the switch decoder. The effect though is that region3 cleanup is aborted leaving it in-tact and referencing decoder14.0. At 3) the second attempt to teardown region3 trips over the stale decoder14.0 object which has long since been deleted. The fix here is to recognize that the CXL specification places no mandate on in-order shutdown of switch-decoders, the driver enforces in-order allocation, and hardware enforces in-order commit. So, rather than fail and leave objects dangling, always remove them. In support of making cxl_region_decode_reset() always succeed, cxl_region_invalidate_memregion() failures are turned into warnings. Crashing the kernel is ok there since system integrity is at risk if caches cannot be managed around physical address mutation events like CXL region destruction. A new device_for_each_child_reverse_from() is added to cleanup port->commit_end after all dependent decoders have been disabled. In other words if decoders are allocated 0->1->2 and disabled 1->2->0 then port->commit_end only decrements from 2 after 2 has been disabled, and it decrements all the way to zero since 1 was disabled previously.
CVE-2024-50282: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: add missing size check in amdgpu_debugfs_gprwave_read() Avoid a possible buffer overflow if size is larger than 4K. (cherry picked from commit f5d873f5825b40d886d03bd2aede91d4cf002434)
CVE-2024-50285: In the Linux kernel, the following vulnerability has been resolved: ksmbd: check outstanding simultaneous SMB operations If Client send simultaneous SMB operations to ksmbd, It exhausts too much memory through the "ksmbd_work_cache”. It will cause OOM issue. ksmbd has a credit mechanism but it can't handle this problem. This patch add the check if it exceeds max credits to prevent this problem by assuming that one smb request consumes at least one credit.
CVE-2024-50289: In the Linux kernel, the following vulnerability has been resolved: media: av7110: fix a spectre vulnerability As warned by smatch: drivers/staging/media/av7110/av7110_ca.c:270 dvb_ca_ioctl() warn: potential spectre issue 'av7110->ci_slot' [w] (local cap) There is a spectre-related vulnerability at the code. Fix it.
CVE-2024-50298: In the Linux kernel, the following vulnerability has been resolved: net: enetc: allocate vf_state during PF probes In the previous implementation, vf_state is allocated memory only when VF is enabled. However, net_device_ops::ndo_set_vf_mac() may be called before VF is enabled to configure the MAC address of VF. If this is the case, enetc_pf_set_vf_mac() will access vf_state, resulting in access to a null pointer. The simplified error log is as follows. root@ls1028ardb:~# ip link set eno0 vf 1 mac 00:0c:e7:66:77:89 [ 173.543315] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004 [ 173.637254] pc : enetc_pf_set_vf_mac+0x3c/0x80 Message from sy [ 173.641973] lr : do_setlink+0x4a8/0xec8 [ 173.732292] Call trace: [ 173.734740] enetc_pf_set_vf_mac+0x3c/0x80 [ 173.738847] __rtnl_newlink+0x530/0x89c [ 173.742692] rtnl_newlink+0x50/0x7c [ 173.746189] rtnetlink_rcv_msg+0x128/0x390 [ 173.750298] netlink_rcv_skb+0x60/0x130 [ 173.754145] rtnetlink_rcv+0x18/0x24 [ 173.757731] netlink_unicast+0x318/0x380 [ 173.761665] netlink_sendmsg+0x17c/0x3c8
CVE-2024-52559: In the Linux kernel, the following vulnerability has been resolved: drm/msm/gem: prevent integer overflow in msm_ioctl_gem_submit() The "submit->cmd[i].size" and "submit->cmd[i].offset" variables are u32 values that come from the user via the submit_lookup_cmds() function. This addition could lead to an integer wrapping bug so use size_add() to prevent that. Patchwork: https://patchwork.freedesktop.org/patch/624696/
CVE-2024-52560: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Mark inode as bad as soon as error detected in mi_enum_attr() Extended the `mi_enum_attr()` function interface with an additional parameter, `struct ntfs_inode *ni`, to allow marking the inode as bad as soon as an error is detected.
CVE-2024-53051: In the Linux kernel, the following vulnerability has been resolved: drm/i915/hdcp: Add encoder check in intel_hdcp_get_capability Sometimes during hotplug scenario or suspend/resume scenario encoder is not always initialized when intel_hdcp_get_capability add a check to avoid kernel null pointer dereference.
CVE-2024-53056: In the Linux kernel, the following vulnerability has been resolved: drm/mediatek: Fix potential NULL dereference in mtk_crtc_destroy() In mtk_crtc_create(), if the call to mbox_request_channel() fails then we set the "mtk_crtc->cmdq_client.chan" pointer to NULL. In that situation, we do not call cmdq_pkt_create(). During the cleanup, we need to check if the "mtk_crtc->cmdq_client.chan" is NULL first before calling cmdq_pkt_destroy(). Calling cmdq_pkt_destroy() is unnecessary if we didn't call cmdq_pkt_create() and it will result in a NULL pointer dereference.
CVE-2024-53068: In the Linux kernel, the following vulnerability has been resolved: firmware: arm_scmi: Fix slab-use-after-free in scmi_bus_notifier() The scmi_dev->name is released prematurely in __scmi_device_destroy(), which causes slab-use-after-free when accessing scmi_dev->name in scmi_bus_notifier(). So move the release of scmi_dev->name to scmi_device_release() to avoid slab-use-after-free. | BUG: KASAN: slab-use-after-free in strncmp+0xe4/0xec | Read of size 1 at addr ffffff80a482bcc0 by task swapper/0/1 | | CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.6.38-debug #1 | Hardware name: Qualcomm Technologies, Inc. SA8775P Ride (DT) | Call trace: | dump_backtrace+0x94/0x114 | show_stack+0x18/0x24 | dump_stack_lvl+0x48/0x60 | print_report+0xf4/0x5b0 | kasan_report+0xa4/0xec | __asan_report_load1_noabort+0x20/0x2c | strncmp+0xe4/0xec | scmi_bus_notifier+0x5c/0x54c | notifier_call_chain+0xb4/0x31c | blocking_notifier_call_chain+0x68/0x9c | bus_notify+0x54/0x78 | device_del+0x1bc/0x840 | device_unregister+0x20/0xb4 | __scmi_device_destroy+0xac/0x280 | scmi_device_destroy+0x94/0xd0 | scmi_chan_setup+0x524/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20 | | Allocated by task 1: | kasan_save_stack+0x2c/0x54 | kasan_set_track+0x2c/0x40 | kasan_save_alloc_info+0x24/0x34 | __kasan_kmalloc+0xa0/0xb8 | __kmalloc_node_track_caller+0x6c/0x104 | kstrdup+0x48/0x84 | kstrdup_const+0x34/0x40 | __scmi_device_create.part.0+0x8c/0x408 | scmi_device_create+0x104/0x370 | scmi_chan_setup+0x2a0/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20 | | Freed by task 1: | kasan_save_stack+0x2c/0x54 | kasan_set_track+0x2c/0x40 | kasan_save_free_info+0x38/0x5c | __kasan_slab_free+0xe8/0x164 | __kmem_cache_free+0x11c/0x230 | kfree+0x70/0x130 | kfree_const+0x20/0x40 | __scmi_device_destroy+0x70/0x280 | scmi_device_destroy+0x94/0xd0 | scmi_chan_setup+0x524/0x750 | scmi_probe+0x7fc/0x1508 | platform_probe+0xc4/0x19c | really_probe+0x32c/0x99c | __driver_probe_device+0x15c/0x3c4 | driver_probe_device+0x5c/0x170 | __driver_attach+0x1c8/0x440 | bus_for_each_dev+0xf4/0x178 | driver_attach+0x3c/0x58 | bus_add_driver+0x234/0x4d4 | driver_register+0xf4/0x3c0 | __platform_driver_register+0x60/0x88 | scmi_driver_init+0xb0/0x104 | do_one_initcall+0xb4/0x664 | kernel_init_freeable+0x3c8/0x894 | kernel_init+0x24/0x1e8 | ret_from_fork+0x10/0x20
CVE-2024-53079: In the Linux kernel, the following vulnerability has been resolved: mm/thp: fix deferred split unqueue naming and locking Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. Before fixing locking: rename misleading folio_undo_large_rmappable(), which does not undo large_rmappable, to folio_unqueue_deferred_split(), which is what it does. But that and its out-of-line __callee are mm internals of very limited usability: add comment and WARN_ON_ONCEs to check usage; and return a bool to say if a deferred split was unqueued, which can then be used in WARN_ON_ONCEs around safety checks (sparing callers the arcane conditionals in __folio_unqueue_deferred_split()). Just omit the folio_unqueue_deferred_split() from free_unref_folios(), all of whose callers now call it beforehand (and if any forget then bad_page() will tell) - except for its caller put_pages_list(), which itself no longer has any callers (and will be deleted separately). Swapout: mem_cgroup_swapout() has been resetting folio->memcg_data 0 without checking and unqueueing a THP folio from deferred split list; which is unfortunate, since the split_queue_lock depends on the memcg (when memcg is enabled); so swapout has been unqueueing such THPs later, when freeing the folio, using the pgdat's lock instead: potentially corrupting the memcg's list. __remove_mapping() has frozen refcount to 0 here, so no problem with calling folio_unqueue_deferred_split() before resetting memcg_data. That goes back to 5.4 commit 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware"): which included a check on swapcache before adding to deferred queue, but no check on deferred queue before adding THP to swapcache. That worked fine with the usual sequence of events in reclaim (though there were a couple of rare ways in which a THP on deferred queue could have been swapped out), but 6.12 commit dafff3f4c850 ("mm: split underused THPs") avoids splitting underused THPs in reclaim, which makes swapcache THPs on deferred queue commonplace. Keep the check on swapcache before adding to deferred queue? Yes: it is no longer essential, but preserves the existing behaviour, and is likely to be a worthwhile optimization (vmstat showed much more traffic on the queue under swapping load if the check was removed); update its comment. Memcg-v1 move (deprecated): mem_cgroup_move_account() has been changing folio->memcg_data without checking and unqueueing a THP folio from the deferred list, sometimes corrupting "from" memcg's list, like swapout. Refcount is non-zero here, so folio_unqueue_deferred_split() can only be used in a WARN_ON_ONCE to validate the fix, which must be done earlier: mem_cgroup_move_charge_pte_range() first try to split the THP (splitting of course unqueues), or skip it if that fails. Not ideal, but moving charge has been requested, and khugepaged should repair the THP later: nobody wants new custom unqueueing code just for this deprecated case. The 87eaceb3faa5 commit did have the code to move from one deferred list to another (but was not conscious of its unsafety while refcount non-0); but that was removed by 5.6 commit fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path"), which argued that the existence of a PMD mapping guarantees that the THP cannot be on a deferred list. As above, false in rare cases, and now commonly false. Backport to 6.11 should be straightforward. Earlier backports must take care that other _deferred_list fixes and dependencies are included. There is not a strong case for backports, but they can fix cornercases.
CVE-2024-53085: In the Linux kernel, the following vulnerability has been resolved: tpm: Lock TPM chip in tpm_pm_suspend() first Setting TPM_CHIP_FLAG_SUSPENDED in the end of tpm_pm_suspend() can be racy according, as this leaves window for tpm_hwrng_read() to be called while the operation is in progress. The recent bug report gives also evidence of this behaviour. Aadress this by locking the TPM chip before checking any chip->flags both in tpm_pm_suspend() and tpm_hwrng_read(). Move TPM_CHIP_FLAG_SUSPENDED check inside tpm_get_random() so that it will be always checked only when the lock is reserved.
CVE-2024-53089: In the Linux kernel, the following vulnerability has been resolved: LoongArch: KVM: Mark hrtimer to expire in hard interrupt context Like commit 2c0d278f3293f ("KVM: LAPIC: Mark hrtimer to expire in hard interrupt context") and commit 9090825fa9974 ("KVM: arm/arm64: Let the timer expire in hardirq context on RT"), On PREEMPT_RT enabled kernels unmarked hrtimers are moved into soft interrupt expiry mode by default. Then the timers are canceled from an preempt-notifier which is invoked with disabled preemption which is not allowed on PREEMPT_RT. The timer callback is short so in could be invoked in hard-IRQ context. So let the timer expire on hard-IRQ context even on -RT. This fix a "scheduling while atomic" bug for PREEMPT_RT enabled kernels: BUG: scheduling while atomic: qemu-system-loo/1011/0x00000002 Modules linked in: amdgpu rfkill nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat ns CPU: 1 UID: 0 PID: 1011 Comm: qemu-system-loo Tainted: G W 6.12.0-rc2+ #1774 Tainted: [W]=WARN Hardware name: Loongson Loongson-3A5000-7A1000-1w-CRB/Loongson-LS3A5000-7A1000-1w-CRB, BIOS vUDK2018-LoongArch-V2.0.0-prebeta9 10/21/2022 Stack : ffffffffffffffff 0000000000000000 9000000004e3ea38 9000000116744000 90000001167475a0 0000000000000000 90000001167475a8 9000000005644830 90000000058dc000 90000000058dbff8 9000000116747420 0000000000000001 0000000000000001 6a613fc938313980 000000000790c000 90000001001c1140 00000000000003fe 0000000000000001 000000000000000d 0000000000000003 0000000000000030 00000000000003f3 000000000790c000 9000000116747830 90000000057ef000 0000000000000000 9000000005644830 0000000000000004 0000000000000000 90000000057f4b58 0000000000000001 9000000116747868 900000000451b600 9000000005644830 9000000003a13998 0000000010000020 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1d ... Call Trace: [<9000000003a13998>] show_stack+0x38/0x180 [<9000000004e3ea34>] dump_stack_lvl+0x84/0xc0 [<9000000003a71708>] __schedule_bug+0x48/0x60 [<9000000004e45734>] __schedule+0x1114/0x1660 [<9000000004e46040>] schedule_rtlock+0x20/0x60 [<9000000004e4e330>] rtlock_slowlock_locked+0x3f0/0x10a0 [<9000000004e4f038>] rt_spin_lock+0x58/0x80 [<9000000003b02d68>] hrtimer_cancel_wait_running+0x68/0xc0 [<9000000003b02e30>] hrtimer_cancel+0x70/0x80 [<ffff80000235eb70>] kvm_restore_timer+0x50/0x1a0 [kvm] [<ffff8000023616c8>] kvm_arch_vcpu_load+0x68/0x2a0 [kvm] [<ffff80000234c2d4>] kvm_sched_in+0x34/0x60 [kvm] [<9000000003a749a0>] finish_task_switch.isra.0+0x140/0x2e0 [<9000000004e44a70>] __schedule+0x450/0x1660 [<9000000004e45cb0>] schedule+0x30/0x180 [<ffff800002354c70>] kvm_vcpu_block+0x70/0x120 [kvm] [<ffff800002354d80>] kvm_vcpu_halt+0x60/0x3e0 [kvm] [<ffff80000235b194>] kvm_handle_gspr+0x3f4/0x4e0 [kvm] [<ffff80000235f548>] kvm_handle_exit+0x1c8/0x260 [kvm]
CVE-2024-53090: In the Linux kernel, the following vulnerability has been resolved: afs: Fix lock recursion afs_wake_up_async_call() can incur lock recursion. The problem is that it is called from AF_RXRPC whilst holding the ->notify_lock, but it tries to take a ref on the afs_call struct in order to pass it to a work queue - but if the afs_call is already queued, we then have an extraneous ref that must be put... calling afs_put_call() may call back down into AF_RXRPC through rxrpc_kernel_shutdown_call(), however, which might try taking the ->notify_lock again. This case isn't very common, however, so defer it to a workqueue. The oops looks something like: BUG: spinlock recursion on CPU#0, krxrpcio/7001/1646 lock: 0xffff888141399b30, .magic: dead4ead, .owner: krxrpcio/7001/1646, .owner_cpu: 0 CPU: 0 UID: 0 PID: 1646 Comm: krxrpcio/7001 Not tainted 6.12.0-rc2-build3+ #4351 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Call Trace: <TASK> dump_stack_lvl+0x47/0x70 do_raw_spin_lock+0x3c/0x90 rxrpc_kernel_shutdown_call+0x83/0xb0 afs_put_call+0xd7/0x180 rxrpc_notify_socket+0xa0/0x190 rxrpc_input_split_jumbo+0x198/0x1d0 rxrpc_input_data+0x14b/0x1e0 ? rxrpc_input_call_packet+0xc2/0x1f0 rxrpc_input_call_event+0xad/0x6b0 rxrpc_input_packet_on_conn+0x1e1/0x210 rxrpc_input_packet+0x3f2/0x4d0 rxrpc_io_thread+0x243/0x410 ? __pfx_rxrpc_io_thread+0x10/0x10 kthread+0xcf/0xe0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x24/0x40 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2024-53091: In the Linux kernel, the following vulnerability has been resolved: bpf: Add sk_is_inet and IS_ICSK check in tls_sw_has_ctx_tx/rx As the introduction of the support for vsock and unix sockets in sockmap, tls_sw_has_ctx_tx/rx cannot presume the socket passed in must be IS_ICSK. vsock and af_unix sockets have vsock_sock and unix_sock instead of inet_connection_sock. For these sockets, tls_get_ctx may return an invalid pointer and cause page fault in function tls_sw_ctx_rx. BUG: unable to handle page fault for address: 0000000000040030 Workqueue: vsock-loopback vsock_loopback_work RIP: 0010:sk_psock_strp_data_ready+0x23/0x60 Call Trace: ? __die+0x81/0xc3 ? no_context+0x194/0x350 ? do_page_fault+0x30/0x110 ? async_page_fault+0x3e/0x50 ? sk_psock_strp_data_ready+0x23/0x60 virtio_transport_recv_pkt+0x750/0x800 ? update_load_avg+0x7e/0x620 vsock_loopback_work+0xd0/0x100 process_one_work+0x1a7/0x360 worker_thread+0x30/0x390 ? create_worker+0x1a0/0x1a0 kthread+0x112/0x130 ? __kthread_cancel_work+0x40/0x40 ret_from_fork+0x1f/0x40 v2: - Add IS_ICSK check v3: - Update the commits in Fixes
CVE-2024-53094: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Add sendpage_ok() check to disable MSG_SPLICE_PAGES While running ISER over SIW, the initiator machine encounters a warning from skb_splice_from_iter() indicating that a slab page is being used in send_page. To address this, it is better to add a sendpage_ok() check within the driver itself, and if it returns 0, then MSG_SPLICE_PAGES flag should be disabled before entering the network stack. A similar issue has been discussed for NVMe in this thread: https://lore.kernel.org/all/20240530142417.146696-1-ofir.gal@volumez.com/ WARNING: CPU: 0 PID: 5342 at net/core/skbuff.c:7140 skb_splice_from_iter+0x173/0x320 Call Trace: tcp_sendmsg_locked+0x368/0xe40 siw_tx_hdt+0x695/0xa40 [siw] siw_qp_sq_process+0x102/0xb00 [siw] siw_sq_resume+0x39/0x110 [siw] siw_run_sq+0x74/0x160 [siw] kthread+0xd2/0x100 ret_from_fork+0x34/0x40 ret_from_fork_asm+0x1a/0x30
CVE-2024-53095: In the Linux kernel, the following vulnerability has been resolved: smb: client: Fix use-after-free of network namespace. Recently, we got a customer report that CIFS triggers oops while reconnecting to a server. [0] The workload runs on Kubernetes, and some pods mount CIFS servers in non-root network namespaces. The problem rarely happened, but it was always while the pod was dying. The root cause is wrong reference counting for network namespace. CIFS uses kernel sockets, which do not hold refcnt of the netns that the socket belongs to. That means CIFS must ensure the socket is always freed before its netns; otherwise, use-after-free happens. The repro steps are roughly: 1. mount CIFS in a non-root netns 2. drop packets from the netns 3. destroy the netns 4. unmount CIFS We can reproduce the issue quickly with the script [1] below and see the splat [2] if CONFIG_NET_NS_REFCNT_TRACKER is enabled. When the socket is TCP, it is hard to guarantee the netns lifetime without holding refcnt due to async timers. Let's hold netns refcnt for each socket as done for SMC in commit 9744d2bf1976 ("smc: Fix use-after-free in tcp_write_timer_handler()."). Note that we need to move put_net() from cifs_put_tcp_session() to clean_demultiplex_info(); otherwise, __sock_create() still could touch a freed netns while cifsd tries to reconnect from cifs_demultiplex_thread(). Also, maybe_get_net() cannot be put just before __sock_create() because the code is not under RCU and there is a small chance that the same address happened to be reallocated to another netns. [0]: CIFS: VFS: \\XXXXXXXXXXX has not responded in 15 seconds. Reconnecting... CIFS: Serverclose failed 4 times, giving up Unable to handle kernel paging request at virtual address 14de99e461f84a07 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [14de99e461f84a07] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] SMP Modules linked in: cls_bpf sch_ingress nls_utf8 cifs cifs_arc4 cifs_md4 dns_resolver tcp_diag inet_diag veth xt_state xt_connmark nf_conntrack_netlink xt_nat xt_statistic xt_MASQUERADE xt_mark xt_addrtype ipt_REJECT nf_reject_ipv4 nft_chain_nat nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_comment nft_compat nf_tables nfnetlink overlay nls_ascii nls_cp437 sunrpc vfat fat aes_ce_blk aes_ce_cipher ghash_ce sm4_ce_cipher sm4 sm3_ce sm3 sha3_ce sha512_ce sha512_arm64 sha1_ce ena button sch_fq_codel loop fuse configfs dmi_sysfs sha2_ce sha256_arm64 dm_mirror dm_region_hash dm_log dm_mod dax efivarfs CPU: 5 PID: 2690970 Comm: cifsd Not tainted 6.1.103-109.184.amzn2023.aarch64 #1 Hardware name: Amazon EC2 r7g.4xlarge/, BIOS 1.0 11/1/2018 pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : fib_rules_lookup+0x44/0x238 lr : __fib_lookup+0x64/0xbc sp : ffff8000265db790 x29: ffff8000265db790 x28: 0000000000000000 x27: 000000000000bd01 x26: 0000000000000000 x25: ffff000b4baf8000 x24: ffff00047b5e4580 x23: ffff8000265db7e0 x22: 0000000000000000 x21: ffff00047b5e4500 x20: ffff0010e3f694f8 x19: 14de99e461f849f7 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 3f92800abd010002 x11: 0000000000000001 x10: ffff0010e3f69420 x9 : ffff800008a6f294 x8 : 0000000000000000 x7 : 0000000000000006 x6 : 0000000000000000 x5 : 0000000000000001 x4 : ffff001924354280 x3 : ffff8000265db7e0 x2 : 0000000000000000 x1 : ffff0010e3f694f8 x0 : ffff00047b5e4500 Call trace: fib_rules_lookup+0x44/0x238 __fib_lookup+0x64/0xbc ip_route_output_key_hash_rcu+0x2c4/0x398 ip_route_output_key_hash+0x60/0x8c tcp_v4_connect+0x290/0x488 __inet_stream_connect+0x108/0x3d0 inet_stream_connect+0x50/0x78 kernel_connect+0x6c/0xac generic_ip_conne ---truncated---
CVE-2024-53114: In the Linux kernel, the following vulnerability has been resolved: x86/CPU/AMD: Clear virtualized VMLOAD/VMSAVE on Zen4 client A number of Zen4 client SoCs advertise the ability to use virtualized VMLOAD/VMSAVE, but using these instructions is reported to be a cause of a random host reboot. These instructions aren't intended to be advertised on Zen4 client so clear the capability.
CVE-2024-53134: In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx93-blk-ctrl: correct remove path The check condition should be 'i < bc->onecell_data.num_domains', not 'bc->onecell_data.num_domains' which will make the look never finish and cause kernel panic. Also disable runtime to address "imx93-blk-ctrl 4ac10000.system-controller: Unbalanced pm_runtime_enable!"
CVE-2024-53147: In the Linux kernel, the following vulnerability has been resolved: exfat: fix out-of-bounds access of directory entries In the case of the directory size is greater than or equal to the cluster size, if start_clu becomes an EOF cluster(an invalid cluster) due to file system corruption, then the directory entry where ei->hint_femp.eidx hint is outside the directory, resulting in an out-of-bounds access, which may cause further file system corruption. This commit adds a check for start_clu, if it is an invalid cluster, the file or directory will be treated as empty.
CVE-2024-53168: In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix one UAF issue caused by sunrpc kernel tcp socket BUG: KASAN: slab-use-after-free in tcp_write_timer_handler+0x156/0x3e0 Read of size 1 at addr ffff888111f322cd by task swapper/0/0 CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc4-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 Call Trace: <IRQ> dump_stack_lvl+0x68/0xa0 print_address_description.constprop.0+0x2c/0x3d0 print_report+0xb4/0x270 kasan_report+0xbd/0xf0 tcp_write_timer_handler+0x156/0x3e0 tcp_write_timer+0x66/0x170 call_timer_fn+0xfb/0x1d0 __run_timers+0x3f8/0x480 run_timer_softirq+0x9b/0x100 handle_softirqs+0x153/0x390 __irq_exit_rcu+0x103/0x120 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x76/0x90 </IRQ> <TASK> asm_sysvec_apic_timer_interrupt+0x1a/0x20 RIP: 0010:default_idle+0xf/0x20 Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 66 90 0f 00 2d 33 f8 25 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 RSP: 0018:ffffffffa2007e28 EFLAGS: 00000242 RAX: 00000000000f3b31 RBX: 1ffffffff4400fc7 RCX: ffffffffa09c3196 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff9f00590f RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed102360835d R10: ffff88811b041aeb R11: 0000000000000001 R12: 0000000000000000 R13: ffffffffa202d7c0 R14: 0000000000000000 R15: 00000000000147d0 default_idle_call+0x6b/0xa0 cpuidle_idle_call+0x1af/0x1f0 do_idle+0xbc/0x130 cpu_startup_entry+0x33/0x40 rest_init+0x11f/0x210 start_kernel+0x39a/0x420 x86_64_start_reservations+0x18/0x30 x86_64_start_kernel+0x97/0xa0 common_startup_64+0x13e/0x141 </TASK> Allocated by task 595: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 __kasan_slab_alloc+0x87/0x90 kmem_cache_alloc_noprof+0x12b/0x3f0 copy_net_ns+0x94/0x380 create_new_namespaces+0x24c/0x500 unshare_nsproxy_namespaces+0x75/0xf0 ksys_unshare+0x24e/0x4f0 __x64_sys_unshare+0x1f/0x30 do_syscall_64+0x70/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 100: kasan_save_stack+0x24/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x54/0x70 kmem_cache_free+0x156/0x5d0 cleanup_net+0x5d3/0x670 process_one_work+0x776/0xa90 worker_thread+0x2e2/0x560 kthread+0x1a8/0x1f0 ret_from_fork+0x34/0x60 ret_from_fork_asm+0x1a/0x30 Reproduction script: mkdir -p /mnt/nfsshare mkdir -p /mnt/nfs/netns_1 mkfs.ext4 /dev/sdb mount /dev/sdb /mnt/nfsshare systemctl restart nfs-server chmod 777 /mnt/nfsshare exportfs -i -o rw,no_root_squash *:/mnt/nfsshare ip netns add netns_1 ip link add name veth_1_peer type veth peer veth_1 ifconfig veth_1_peer 11.11.0.254 up ip link set veth_1 netns netns_1 ip netns exec netns_1 ifconfig veth_1 11.11.0.1 ip netns exec netns_1 /root/iptables -A OUTPUT -d 11.11.0.254 -p tcp \ --tcp-flags FIN FIN -j DROP (note: In my environment, a DESTROY_CLIENTID operation is always sent immediately, breaking the nfs tcp connection.) ip netns exec netns_1 timeout -s 9 300 mount -t nfs -o proto=tcp,vers=4.1 \ 11.11.0.254:/mnt/nfsshare /mnt/nfs/netns_1 ip netns del netns_1 The reason here is that the tcp socket in netns_1 (nfs side) has been shutdown and closed (done in xs_destroy), but the FIN message (with ack) is discarded, and the nfsd side keeps sending retransmission messages. As a result, when the tcp sock in netns_1 processes the received message, it sends the message (FIN message) in the sending queue, and the tcp timer is re-established. When the network namespace is deleted, the net structure accessed by tcp's timer handler function causes problems. To fix this problem, let's hold netns refcnt for the tcp kernel socket as done in other modules. This is an ugly hack which can easily be backported to earlier kernels. A proper fix which cleans up the interfaces will follow, but may not be so easy to backport.
CVE-2024-53176: In the Linux kernel, the following vulnerability has been resolved: smb: During unmount, ensure all cached dir instances drop their dentry The unmount process (cifs_kill_sb() calling close_all_cached_dirs()) can race with various cached directory operations, which ultimately results in dentries not being dropped and these kernel BUGs: BUG: Dentry ffff88814f37e358{i=1000000000080,n=/} still in use (2) [unmount of cifs cifs] VFS: Busy inodes after unmount of cifs (cifs) ------------[ cut here ]------------ kernel BUG at fs/super.c:661! This happens when a cfid is in the process of being cleaned up when, and has been removed from the cfids->entries list, including: - Receiving a lease break from the server - Server reconnection triggers invalidate_all_cached_dirs(), which removes all the cfids from the list - The laundromat thread decides to expire an old cfid. To solve these problems, dropping the dentry is done in queued work done in a newly-added cfid_put_wq workqueue, and close_all_cached_dirs() flushes that workqueue after it drops all the dentries of which it's aware. This is a global workqueue (rather than scoped to a mount), but the queued work is minimal. The final cleanup work for cleaning up a cfid is performed via work queued in the serverclose_wq workqueue; this is done separate from dropping the dentries so that close_all_cached_dirs() doesn't block on any server operations. Both of these queued works expect to invoked with a cfid reference and a tcon reference to avoid those objects from being freed while the work is ongoing. While we're here, add proper locking to close_all_cached_dirs(), and locking around the freeing of cfid->dentry.
CVE-2024-53178: In the Linux kernel, the following vulnerability has been resolved: smb: Don't leak cfid when reconnect races with open_cached_dir open_cached_dir() may either race with the tcon reconnection even before compound_send_recv() or directly trigger a reconnection via SMB2_open_init() or SMB_query_info_init(). The reconnection process invokes invalidate_all_cached_dirs() via cifs_mark_open_files_invalid(), which removes all cfids from the cfids->entries list but doesn't drop a ref if has_lease isn't true. This results in the currently-being-constructed cfid not being on the list, but still having a refcount of 2. It leaks if returned from open_cached_dir(). Fix this by setting cfid->has_lease when the ref is actually taken; the cfid will not be used by other threads until it has a valid time. Addresses these kmemleaks: unreferenced object 0xffff8881090c4000 (size 1024): comm "bash", pid 1860, jiffies 4295126592 hex dump (first 32 bytes): 00 01 00 00 00 00 ad de 22 01 00 00 00 00 ad de ........"....... 00 ca 45 22 81 88 ff ff f8 dc 4f 04 81 88 ff ff ..E"......O..... backtrace (crc 6f58c20f): [<ffffffff8b895a1e>] __kmalloc_cache_noprof+0x2be/0x350 [<ffffffff8bda06e3>] open_cached_dir+0x993/0x1fb0 [<ffffffff8bdaa750>] cifs_readdir+0x15a0/0x1d50 [<ffffffff8b9a853f>] iterate_dir+0x28f/0x4b0 [<ffffffff8b9a9aed>] __x64_sys_getdents64+0xfd/0x200 [<ffffffff8cf6da05>] do_syscall_64+0x95/0x1a0 [<ffffffff8d00012f>] entry_SYSCALL_64_after_hwframe+0x76/0x7e unreferenced object 0xffff8881044fdcf8 (size 8): comm "bash", pid 1860, jiffies 4295126592 hex dump (first 8 bytes): 00 cc cc cc cc cc cc cc ........ backtrace (crc 10c106a9): [<ffffffff8b89a3d3>] __kmalloc_node_track_caller_noprof+0x363/0x480 [<ffffffff8b7d7256>] kstrdup+0x36/0x60 [<ffffffff8bda0700>] open_cached_dir+0x9b0/0x1fb0 [<ffffffff8bdaa750>] cifs_readdir+0x15a0/0x1d50 [<ffffffff8b9a853f>] iterate_dir+0x28f/0x4b0 [<ffffffff8b9a9aed>] __x64_sys_getdents64+0xfd/0x200 [<ffffffff8cf6da05>] do_syscall_64+0x95/0x1a0 [<ffffffff8d00012f>] entry_SYSCALL_64_after_hwframe+0x76/0x7e And addresses these BUG splats when unmounting the SMB filesystem: BUG: Dentry ffff888140590ba0{i=1000000000080,n=/} still in use (2) [unmount of cifs cifs] WARNING: CPU: 3 PID: 3433 at fs/dcache.c:1536 umount_check+0xd0/0x100 Modules linked in: CPU: 3 UID: 0 PID: 3433 Comm: bash Not tainted 6.12.0-rc4-g850925a8133c-dirty #49 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 RIP: 0010:umount_check+0xd0/0x100 Code: 8d 7c 24 40 e8 31 5a f4 ff 49 8b 54 24 40 41 56 49 89 e9 45 89 e8 48 89 d9 41 57 48 89 de 48 c7 c7 80 e7 db ac e8 f0 72 9a ff <0f> 0b 58 31 c0 5a 5b 5d 41 5c 41 5d 41 5e 41 5f e9 2b e5 5d 01 41 RSP: 0018:ffff88811cc27978 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff888140590ba0 RCX: ffffffffaaf20bae RDX: dffffc0000000000 RSI: 0000000000000008 RDI: ffff8881f6fb6f40 RBP: ffff8881462ec000 R08: 0000000000000001 R09: ffffed1023984ee3 R10: ffff88811cc2771f R11: 00000000016cfcc0 R12: ffff888134383e08 R13: 0000000000000002 R14: ffff8881462ec668 R15: ffffffffaceab4c0 FS: 00007f23bfa98740(0000) GS:ffff8881f6f80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556de4a6f808 CR3: 0000000123c80000 CR4: 0000000000350ef0 Call Trace: <TASK> d_walk+0x6a/0x530 shrink_dcache_for_umount+0x6a/0x200 generic_shutdown_super+0x52/0x2a0 kill_anon_super+0x22/0x40 cifs_kill_sb+0x159/0x1e0 deactivate_locked_super+0x66/0xe0 cleanup_mnt+0x140/0x210 task_work_run+0xfb/0x170 syscall_exit_to_user_mode+0x29f/0x2b0 do_syscall_64+0xa1/0x1a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f23bfb93ae7 Code: ff ff ff ff c3 66 0f 1f 44 00 00 48 8b 0d 11 93 0d 00 f7 d8 64 89 01 b8 ff ff ff ff eb bf 0f 1f 44 00 00 b8 50 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d e9 92 0d 00 f7 d8 64 89 ---truncated---
CVE-2024-53179: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free of signing key Customers have reported use-after-free in @ses->auth_key.response with SMB2.1 + sign mounts which occurs due to following race: task A task B cifs_mount() dfs_mount_share() get_session() cifs_mount_get_session() cifs_send_recv() cifs_get_smb_ses() compound_send_recv() cifs_setup_session() smb2_setup_request() kfree_sensitive() smb2_calc_signature() crypto_shash_setkey() *UAF* Fix this by ensuring that we have a valid @ses->auth_key.response by checking whether @ses->ses_status is SES_GOOD or SES_EXITING with @ses->ses_lock held. After commit 24a9799aa8ef ("smb: client: fix UAF in smb2_reconnect_server()"), we made sure to call ->logoff() only when @ses was known to be good (e.g. valid ->auth_key.response), so it's safe to access signing key when @ses->ses_status == SES_EXITING.
CVE-2024-53187: In the Linux kernel, the following vulnerability has been resolved: io_uring: check for overflows in io_pin_pages WARNING: CPU: 0 PID: 5834 at io_uring/memmap.c:144 io_pin_pages+0x149/0x180 io_uring/memmap.c:144 CPU: 0 UID: 0 PID: 5834 Comm: syz-executor825 Not tainted 6.12.0-next-20241118-syzkaller #0 Call Trace: <TASK> __io_uaddr_map+0xfb/0x2d0 io_uring/memmap.c:183 io_rings_map io_uring/io_uring.c:2611 [inline] io_allocate_scq_urings+0x1c0/0x650 io_uring/io_uring.c:3470 io_uring_create+0x5b5/0xc00 io_uring/io_uring.c:3692 io_uring_setup io_uring/io_uring.c:3781 [inline] ... </TASK> io_pin_pages()'s uaddr parameter came directly from the user and can be garbage. Don't just add size to it as it can overflow.
CVE-2024-53195: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Get rid of userspace_irqchip_in_use Improper use of userspace_irqchip_in_use led to syzbot hitting the following WARN_ON() in kvm_timer_update_irq(): WARNING: CPU: 0 PID: 3281 at arch/arm64/kvm/arch_timer.c:459 kvm_timer_update_irq+0x21c/0x394 Call trace: kvm_timer_update_irq+0x21c/0x394 arch/arm64/kvm/arch_timer.c:459 kvm_timer_vcpu_reset+0x158/0x684 arch/arm64/kvm/arch_timer.c:968 kvm_reset_vcpu+0x3b4/0x560 arch/arm64/kvm/reset.c:264 kvm_vcpu_set_target arch/arm64/kvm/arm.c:1553 [inline] kvm_arch_vcpu_ioctl_vcpu_init arch/arm64/kvm/arm.c:1573 [inline] kvm_arch_vcpu_ioctl+0x112c/0x1b3c arch/arm64/kvm/arm.c:1695 kvm_vcpu_ioctl+0x4ec/0xf74 virt/kvm/kvm_main.c:4658 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x108/0x184 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x78/0x1b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0xe8/0x1b0 arch/arm64/kernel/syscall.c:132 do_el0_svc+0x40/0x50 arch/arm64/kernel/syscall.c:151 el0_svc+0x54/0x14c arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The following sequence led to the scenario: - Userspace creates a VM and a vCPU. - The vCPU is initialized with KVM_ARM_VCPU_PMU_V3 during KVM_ARM_VCPU_INIT. - Without any other setup, such as vGIC or vPMU, userspace issues KVM_RUN on the vCPU. Since the vPMU is requested, but not setup, kvm_arm_pmu_v3_enable() fails in kvm_arch_vcpu_run_pid_change(). As a result, KVM_RUN returns after enabling the timer, but before incrementing 'userspace_irqchip_in_use': kvm_arch_vcpu_run_pid_change() ret = kvm_arm_pmu_v3_enable() if (!vcpu->arch.pmu.created) return -EINVAL; if (ret) return ret; [...] if (!irqchip_in_kernel(kvm)) static_branch_inc(&userspace_irqchip_in_use); - Userspace ignores the error and issues KVM_ARM_VCPU_INIT again. Since the timer is already enabled, control moves through the following flow, ultimately hitting the WARN_ON(): kvm_timer_vcpu_reset() if (timer->enabled) kvm_timer_update_irq() if (!userspace_irqchip()) ret = kvm_vgic_inject_irq() ret = vgic_lazy_init() if (unlikely(!vgic_initialized(kvm))) if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; WARN_ON(ret); Theoretically, since userspace_irqchip_in_use's functionality can be simply replaced by '!irqchip_in_kernel()', get rid of the static key to avoid the mismanagement, which also helps with the syzbot issue.
CVE-2024-53216: In the Linux kernel, the following vulnerability has been resolved: nfsd: release svc_expkey/svc_export with rcu_work The last reference for `cache_head` can be reduced to zero in `c_show` and `e_show`(using `rcu_read_lock` and `rcu_read_unlock`). Consequently, `svc_export_put` and `expkey_put` will be invoked, leading to two issues: 1. The `svc_export_put` will directly free ex_uuid. However, `e_show`/`c_show` will access `ex_uuid` after `cache_put`, which can trigger a use-after-free issue, shown below. ================================================================== BUG: KASAN: slab-use-after-free in svc_export_show+0x362/0x430 [nfsd] Read of size 1 at addr ff11000010fdc120 by task cat/870 CPU: 1 UID: 0 PID: 870 Comm: cat Not tainted 6.12.0-rc3+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x2c/0x3a0 print_report+0xb9/0x280 kasan_report+0xae/0xe0 svc_export_show+0x362/0x430 [nfsd] c_show+0x161/0x390 [sunrpc] seq_read_iter+0x589/0x770 seq_read+0x1e5/0x270 proc_reg_read+0xe1/0x140 vfs_read+0x125/0x530 ksys_read+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 830: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 __kmalloc_node_track_caller_noprof+0x1bc/0x400 kmemdup_noprof+0x22/0x50 svc_export_parse+0x8a9/0xb80 [nfsd] cache_do_downcall+0x71/0xa0 [sunrpc] cache_write_procfs+0x8e/0xd0 [sunrpc] proc_reg_write+0xe1/0x140 vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 868: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x37/0x50 kfree+0xf3/0x3e0 svc_export_put+0x87/0xb0 [nfsd] cache_purge+0x17f/0x1f0 [sunrpc] nfsd_destroy_serv+0x226/0x2d0 [nfsd] nfsd_svc+0x125/0x1e0 [nfsd] write_threads+0x16a/0x2a0 [nfsd] nfsctl_transaction_write+0x74/0xa0 [nfsd] vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e 2. We cannot sleep while using `rcu_read_lock`/`rcu_read_unlock`. However, `svc_export_put`/`expkey_put` will call path_put, which subsequently triggers a sleeping operation due to the following `dput`. ============================= WARNING: suspicious RCU usage 5.10.0-dirty #141 Not tainted ----------------------------- ... Call Trace: dump_stack+0x9a/0xd0 ___might_sleep+0x231/0x240 dput+0x39/0x600 path_put+0x1b/0x30 svc_export_put+0x17/0x80 e_show+0x1c9/0x200 seq_read_iter+0x63f/0x7c0 seq_read+0x226/0x2d0 vfs_read+0x113/0x2c0 ksys_read+0xc9/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 Fix these issues by using `rcu_work` to help release `svc_expkey`/`svc_export`. This approach allows for an asynchronous context to invoke `path_put` and also facilitates the freeing of `uuid/exp/key` after an RCU grace period.
CVE-2024-53218: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix race in concurrent f2fs_stop_gc_thread In my test case, concurrent calls to f2fs shutdown report the following stack trace: Oops: general protection fault, probably for non-canonical address 0xc6cfff63bb5513fc: 0000 [#1] PREEMPT SMP PTI CPU: 0 UID: 0 PID: 678 Comm: f2fs_rep_shutdo Not tainted 6.12.0-rc5-next-20241029-g6fb2fa9805c5-dirty #85 Call Trace: <TASK> ? show_regs+0x8b/0xa0 ? __die_body+0x26/0xa0 ? die_addr+0x54/0x90 ? exc_general_protection+0x24b/0x5c0 ? asm_exc_general_protection+0x26/0x30 ? kthread_stop+0x46/0x390 f2fs_stop_gc_thread+0x6c/0x110 f2fs_do_shutdown+0x309/0x3a0 f2fs_ioc_shutdown+0x150/0x1c0 __f2fs_ioctl+0xffd/0x2ac0 f2fs_ioctl+0x76/0xe0 vfs_ioctl+0x23/0x60 __x64_sys_ioctl+0xce/0xf0 x64_sys_call+0x2b1b/0x4540 do_syscall_64+0xa7/0x240 entry_SYSCALL_64_after_hwframe+0x76/0x7e The root cause is a race condition in f2fs_stop_gc_thread() called from different f2fs shutdown paths: [CPU0] [CPU1] ---------------------- ----------------------- f2fs_stop_gc_thread f2fs_stop_gc_thread gc_th = sbi->gc_thread gc_th = sbi->gc_thread kfree(gc_th) sbi->gc_thread = NULL < gc_th != NULL > kthread_stop(gc_th->f2fs_gc_task) //UAF The commit c7f114d864ac ("f2fs: fix to avoid use-after-free in f2fs_stop_gc_thread()") attempted to fix this issue by using a read semaphore to prevent races between shutdown and remount threads, but it fails to prevent all race conditions. Fix it by converting to write lock of s_umount in f2fs_do_shutdown().
CVE-2024-53219: In the Linux kernel, the following vulnerability has been resolved: virtiofs: use pages instead of pointer for kernel direct IO When trying to insert a 10MB kernel module kept in a virtio-fs with cache disabled, the following warning was reported: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 404 at mm/page_alloc.c:4551 ...... Modules linked in: CPU: 1 PID: 404 Comm: insmod Not tainted 6.9.0-rc5+ #123 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ...... RIP: 0010:__alloc_pages+0x2bf/0x380 ...... Call Trace: <TASK> ? __warn+0x8e/0x150 ? __alloc_pages+0x2bf/0x380 __kmalloc_large_node+0x86/0x160 __kmalloc+0x33c/0x480 virtio_fs_enqueue_req+0x240/0x6d0 virtio_fs_wake_pending_and_unlock+0x7f/0x190 queue_request_and_unlock+0x55/0x60 fuse_simple_request+0x152/0x2b0 fuse_direct_io+0x5d2/0x8c0 fuse_file_read_iter+0x121/0x160 __kernel_read+0x151/0x2d0 kernel_read+0x45/0x50 kernel_read_file+0x1a9/0x2a0 init_module_from_file+0x6a/0xe0 idempotent_init_module+0x175/0x230 __x64_sys_finit_module+0x5d/0xb0 x64_sys_call+0x1c3/0x9e0 do_syscall_64+0x3d/0xc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ...... </TASK> ---[ end trace 0000000000000000 ]--- The warning is triggered as follows: 1) syscall finit_module() handles the module insertion and it invokes kernel_read_file() to read the content of the module first. 2) kernel_read_file() allocates a 10MB buffer by using vmalloc() and passes it to kernel_read(). kernel_read() constructs a kvec iter by using iov_iter_kvec() and passes it to fuse_file_read_iter(). 3) virtio-fs disables the cache, so fuse_file_read_iter() invokes fuse_direct_io(). As for now, the maximal read size for kvec iter is only limited by fc->max_read. For virtio-fs, max_read is UINT_MAX, so fuse_direct_io() doesn't split the 10MB buffer. It saves the address and the size of the 10MB-sized buffer in out_args[0] of a fuse request and passes the fuse request to virtio_fs_wake_pending_and_unlock(). 4) virtio_fs_wake_pending_and_unlock() uses virtio_fs_enqueue_req() to queue the request. Because virtiofs need DMA-able address, so virtio_fs_enqueue_req() uses kmalloc() to allocate a bounce buffer for all fuse args, copies these args into the bounce buffer and passed the physical address of the bounce buffer to virtiofsd. The total length of these fuse args for the passed fuse request is about 10MB, so copy_args_to_argbuf() invokes kmalloc() with a 10MB size parameter and it triggers the warning in __alloc_pages(): if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)) return NULL; 5) virtio_fs_enqueue_req() will retry the memory allocation in a kworker, but it won't help, because kmalloc() will always return NULL due to the abnormal size and finit_module() will hang forever. A feasible solution is to limit the value of max_read for virtio-fs, so the length passed to kmalloc() will be limited. However it will affect the maximal read size for normal read. And for virtio-fs write initiated from kernel, it has the similar problem but now there is no way to limit fc->max_write in kernel. So instead of limiting both the values of max_read and max_write in kernel, introducing use_pages_for_kvec_io in fuse_conn and setting it as true in virtiofs. When use_pages_for_kvec_io is enabled, fuse will use pages instead of pointer to pass the KVEC_IO data. After switching to pages for KVEC_IO data, these pages will be used for DMA through virtio-fs. If these pages are backed by vmalloc(), {flush|invalidate}_kernel_vmap_range() are necessary to flush or invalidate the cache before the DMA operation. So add two new fields in fuse_args_pages to record the base address of vmalloc area and the condition indicating whether invalidation is needed. Perform the flush in fuse_get_user_pages() for write operations and the invalidation in fuse_release_user_pages() for read operations. It may seem necessary to introduce another fie ---truncated---
CVE-2024-53221: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix null-ptr-deref in f2fs_submit_page_bio() There's issue as follows when concurrently installing the f2fs.ko module and mounting the f2fs file system: KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] RIP: 0010:__bio_alloc+0x2fb/0x6c0 [f2fs] Call Trace: <TASK> f2fs_submit_page_bio+0x126/0x8b0 [f2fs] __get_meta_page+0x1d4/0x920 [f2fs] get_checkpoint_version.constprop.0+0x2b/0x3c0 [f2fs] validate_checkpoint+0xac/0x290 [f2fs] f2fs_get_valid_checkpoint+0x207/0x950 [f2fs] f2fs_fill_super+0x1007/0x39b0 [f2fs] mount_bdev+0x183/0x250 legacy_get_tree+0xf4/0x1e0 vfs_get_tree+0x88/0x340 do_new_mount+0x283/0x5e0 path_mount+0x2b2/0x15b0 __x64_sys_mount+0x1fe/0x270 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Above issue happens as the biset of the f2fs file system is not initialized before register "f2fs_fs_type". To address above issue just register "f2fs_fs_type" at the last in init_f2fs_fs(). Ensure that all f2fs file system resources are initialized.
CVE-2024-53224: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Move events notifier registration to be after device registration Move pkey change work initialization and cleanup from device resources stage to notifier stage, since this is the stage which handles this work events. Fix a race between the device deregistration and pkey change work by moving MLX5_IB_STAGE_DEVICE_NOTIFIER to be after MLX5_IB_STAGE_IB_REG in order to ensure that the notifier is deregistered before the device during cleanup. Which ensures there are no works that are being executed after the device has already unregistered which can cause the panic below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 630071 Comm: kworker/1:2 Kdump: loaded Tainted: G W OE --------- --- 5.14.0-162.6.1.el9_1.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 02/27/2023 Workqueue: events pkey_change_handler [mlx5_ib] RIP: 0010:setup_qp+0x38/0x1f0 [mlx5_ib] Code: ee 41 54 45 31 e4 55 89 f5 53 48 89 fb 48 83 ec 20 8b 77 08 65 48 8b 04 25 28 00 00 00 48 89 44 24 18 48 8b 07 48 8d 4c 24 16 <4c> 8b 38 49 8b 87 80 0b 00 00 4c 89 ff 48 8b 80 08 05 00 00 8b 40 RSP: 0018:ffffbcc54068be20 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff954054494128 RCX: ffffbcc54068be36 RDX: ffff954004934000 RSI: 0000000000000001 RDI: ffff954054494128 RBP: 0000000000000023 R08: ffff954001be2c20 R09: 0000000000000001 R10: ffff954001be2c20 R11: ffff9540260133c0 R12: 0000000000000000 R13: 0000000000000023 R14: 0000000000000000 R15: ffff9540ffcb0905 FS: 0000000000000000(0000) GS:ffff9540ffc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000010625c001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_ib_gsi_pkey_change+0x20/0x40 [mlx5_ib] process_one_work+0x1e8/0x3c0 worker_thread+0x50/0x3b0 ? rescuer_thread+0x380/0x380 kthread+0x149/0x170 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Modules linked in: rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) mlx5_fwctl(OE) fwctl(OE) ib_uverbs(OE) mlx5_core(OE) mlxdevm(OE) ib_core(OE) mlx_compat(OE) psample mlxfw(OE) tls knem(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache netfs qrtr rfkill sunrpc intel_rapl_msr intel_rapl_common rapl hv_balloon hv_utils i2c_piix4 pcspkr joydev fuse ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ata_generic pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper drm_kms_helper hv_storvsc syscopyarea hv_netvsc sysfillrect sysimgblt hid_hyperv fb_sys_fops scsi_transport_fc hyperv_keyboard drm ata_piix crct10dif_pclmul crc32_pclmul crc32c_intel libata ghash_clmulni_intel hv_vmbus serio_raw [last unloaded: ib_core] CR2: 0000000000000000 ---[ end trace f6f8be4eae12f7bc ]---
CVE-2024-53687: In the Linux kernel, the following vulnerability has been resolved: riscv: Fix IPIs usage in kfence_protect_page() flush_tlb_kernel_range() may use IPIs to flush the TLBs of all the cores, which triggers the following warning when the irqs are disabled: [ 3.455330] WARNING: CPU: 1 PID: 0 at kernel/smp.c:815 smp_call_function_many_cond+0x452/0x520 [ 3.456647] Modules linked in: [ 3.457218] CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Not tainted 6.12.0-rc7-00010-g91d3de7240b8 #1 [ 3.457416] Hardware name: QEMU QEMU Virtual Machine, BIOS [ 3.457633] epc : smp_call_function_many_cond+0x452/0x520 [ 3.457736] ra : on_each_cpu_cond_mask+0x1e/0x30 [ 3.457786] epc : ffffffff800b669a ra : ffffffff800b67c2 sp : ff2000000000bb50 [ 3.457824] gp : ffffffff815212b8 tp : ff6000008014f080 t0 : 000000000000003f [ 3.457859] t1 : ffffffff815221e0 t2 : 000000000000000f s0 : ff2000000000bc10 [ 3.457920] s1 : 0000000000000040 a0 : ffffffff815221e0 a1 : 0000000000000001 [ 3.457953] a2 : 0000000000010000 a3 : 0000000000000003 a4 : 0000000000000000 [ 3.458006] a5 : 0000000000000000 a6 : ffffffffffffffff a7 : 0000000000000000 [ 3.458042] s2 : ffffffff815223be s3 : 00fffffffffff000 s4 : ff600001ffe38fc0 [ 3.458076] s5 : ff600001ff950d00 s6 : 0000000200000120 s7 : 0000000000000001 [ 3.458109] s8 : 0000000000000001 s9 : ff60000080841ef0 s10: 0000000000000001 [ 3.458141] s11: ffffffff81524812 t3 : 0000000000000001 t4 : ff60000080092bc0 [ 3.458172] t5 : 0000000000000000 t6 : ff200000000236d0 [ 3.458203] status: 0000000200000100 badaddr: ffffffff800b669a cause: 0000000000000003 [ 3.458373] [<ffffffff800b669a>] smp_call_function_many_cond+0x452/0x520 [ 3.458593] [<ffffffff800b67c2>] on_each_cpu_cond_mask+0x1e/0x30 [ 3.458625] [<ffffffff8000e4ca>] __flush_tlb_range+0x118/0x1ca [ 3.458656] [<ffffffff8000e6b2>] flush_tlb_kernel_range+0x1e/0x26 [ 3.458683] [<ffffffff801ea56a>] kfence_protect+0xc0/0xce [ 3.458717] [<ffffffff801e9456>] kfence_guarded_free+0xc6/0x1c0 [ 3.458742] [<ffffffff801e9d6c>] __kfence_free+0x62/0xc6 [ 3.458764] [<ffffffff801c57d8>] kfree+0x106/0x32c [ 3.458786] [<ffffffff80588cf2>] detach_buf_split+0x188/0x1a8 [ 3.458816] [<ffffffff8058708c>] virtqueue_get_buf_ctx+0xb6/0x1f6 [ 3.458839] [<ffffffff805871da>] virtqueue_get_buf+0xe/0x16 [ 3.458880] [<ffffffff80613d6a>] virtblk_done+0x5c/0xe2 [ 3.458908] [<ffffffff8058766e>] vring_interrupt+0x6a/0x74 [ 3.458930] [<ffffffff800747d8>] __handle_irq_event_percpu+0x7c/0xe2 [ 3.458956] [<ffffffff800748f0>] handle_irq_event+0x3c/0x86 [ 3.458978] [<ffffffff800786cc>] handle_simple_irq+0x9e/0xbe [ 3.459004] [<ffffffff80073934>] generic_handle_domain_irq+0x1c/0x2a [ 3.459027] [<ffffffff804bf87c>] imsic_handle_irq+0xba/0x120 [ 3.459056] [<ffffffff80073934>] generic_handle_domain_irq+0x1c/0x2a [ 3.459080] [<ffffffff804bdb76>] riscv_intc_aia_irq+0x24/0x34 [ 3.459103] [<ffffffff809d0452>] handle_riscv_irq+0x2e/0x4c [ 3.459133] [<ffffffff809d923e>] call_on_irq_stack+0x32/0x40 So only flush the local TLB and let the lazy kfence page fault handling deal with the faults which could happen when a core has an old protected pte version cached in its TLB. That leads to potential inaccuracies which can be tolerated when using kfence.
CVE-2024-54683: In the Linux kernel, the following vulnerability has been resolved: netfilter: IDLETIMER: Fix for possible ABBA deadlock Deletion of the last rule referencing a given idletimer may happen at the same time as a read of its file in sysfs: | ====================================================== | WARNING: possible circular locking dependency detected | 6.12.0-rc7-01692-g5e9a28f41134-dirty #594 Not tainted | ------------------------------------------------------ | iptables/3303 is trying to acquire lock: | ffff8881057e04b8 (kn->active#48){++++}-{0:0}, at: __kernfs_remove+0x20 | | but task is already holding lock: | ffffffffa0249068 (list_mutex){+.+.}-{3:3}, at: idletimer_tg_destroy_v] | | which lock already depends on the new lock. A simple reproducer is: | #!/bin/bash | | while true; do | iptables -A INPUT -i foo -j IDLETIMER --timeout 10 --label "testme" | iptables -D INPUT -i foo -j IDLETIMER --timeout 10 --label "testme" | done & | while true; do | cat /sys/class/xt_idletimer/timers/testme >/dev/null | done Avoid this by freeing list_mutex right after deleting the element from the list, then continuing with the teardown.
CVE-2024-56538: In the Linux kernel, the following vulnerability has been resolved: drm: zynqmp_kms: Unplug DRM device before removal Prevent userspace accesses to the DRM device from causing use-after-frees by unplugging the device before we remove it. This causes any further userspace accesses to result in an error without further calls into this driver's internals.
CVE-2024-56544: In the Linux kernel, the following vulnerability has been resolved: udmabuf: change folios array from kmalloc to kvmalloc When PAGE_SIZE 4096, MAX_PAGE_ORDER 10, 64bit machine, page_alloc only support 4MB. If above this, trigger this warn and return NULL. udmabuf can change size limit, if change it to 3072(3GB), and then alloc 3GB udmabuf, will fail create. [ 4080.876581] ------------[ cut here ]------------ [ 4080.876843] WARNING: CPU: 3 PID: 2015 at mm/page_alloc.c:4556 __alloc_pages+0x2c8/0x350 [ 4080.878839] RIP: 0010:__alloc_pages+0x2c8/0x350 [ 4080.879470] Call Trace: [ 4080.879473] <TASK> [ 4080.879473] ? __alloc_pages+0x2c8/0x350 [ 4080.879475] ? __warn.cold+0x8e/0xe8 [ 4080.880647] ? __alloc_pages+0x2c8/0x350 [ 4080.880909] ? report_bug+0xff/0x140 [ 4080.881175] ? handle_bug+0x3c/0x80 [ 4080.881556] ? exc_invalid_op+0x17/0x70 [ 4080.881559] ? asm_exc_invalid_op+0x1a/0x20 [ 4080.882077] ? udmabuf_create+0x131/0x400 Because MAX_PAGE_ORDER, kmalloc can max alloc 4096 * (1 << 10), 4MB memory, each array entry is pointer(8byte), so can save 524288 pages(2GB). Further more, costly order(order 3) may not be guaranteed that it can be applied for, due to fragmentation. This patch change udmabuf array use kvmalloc_array, this can fallback alloc into vmalloc, which can guarantee allocation for any size and does not affect the performance of kmalloc allocations.
CVE-2024-56565: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to drop all discards after creating snapshot on lvm device Piergiorgio reported a bug in bugzilla as below: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 969 at fs/f2fs/segment.c:1330 RIP: 0010:__submit_discard_cmd+0x27d/0x400 [f2fs] Call Trace: __issue_discard_cmd+0x1ca/0x350 [f2fs] issue_discard_thread+0x191/0x480 [f2fs] kthread+0xcf/0x100 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x1a/0x30 w/ below testcase, it can reproduce this bug quickly: - pvcreate /dev/vdb - vgcreate myvg1 /dev/vdb - lvcreate -L 1024m -n mylv1 myvg1 - mount /dev/myvg1/mylv1 /mnt/f2fs - dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=20 - sync - rm /mnt/f2fs/file - sync - lvcreate -L 1024m -s -n mylv1-snapshot /dev/myvg1/mylv1 - umount /mnt/f2fs The root cause is: it will update discard_max_bytes of mounted lvm device to zero after creating snapshot on this lvm device, then, __submit_discard_cmd() will pass parameter @nr_sects w/ zero value to __blkdev_issue_discard(), it returns a NULL bio pointer, result in panic. This patch changes as below for fixing: 1. Let's drop all remained discards in f2fs_unfreeze() if snapshot of lvm device is created. 2. Checking discard_max_bytes before submitting discard during __submit_discard_cmd().
CVE-2024-56566: In the Linux kernel, the following vulnerability has been resolved: mm/slub: Avoid list corruption when removing a slab from the full list Boot with slub_debug=UFPZ. If allocated object failed in alloc_consistency_checks, all objects of the slab will be marked as used, and then the slab will be removed from the partial list. When an object belonging to the slab got freed later, the remove_full() function is called. Because the slab is neither on the partial list nor on the full list, it eventually lead to a list corruption (actually a list poison being detected). So we need to mark and isolate the slab page with metadata corruption, do not put it back in circulation. Because the debug caches avoid all the fastpaths, reusing the frozen bit to mark slab page with metadata corruption seems to be fine. [ 4277.385669] list_del corruption, ffffea00044b3e50->next is LIST_POISON1 (dead000000000100) [ 4277.387023] ------------[ cut here ]------------ [ 4277.387880] kernel BUG at lib/list_debug.c:56! [ 4277.388680] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 4277.389562] CPU: 5 PID: 90 Comm: kworker/5:1 Kdump: loaded Tainted: G OE 6.6.1-1 #1 [ 4277.392113] Workqueue: xfs-inodegc/vda1 xfs_inodegc_worker [xfs] [ 4277.393551] RIP: 0010:__list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.394518] Code: 48 91 82 e8 37 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 28 49 91 82 e8 26 f9 9a ff 0f 0b 48 89 fe 48 c7 c7 58 49 91 [ 4277.397292] RSP: 0018:ffffc90000333b38 EFLAGS: 00010082 [ 4277.398202] RAX: 000000000000004e RBX: ffffea00044b3e50 RCX: 0000000000000000 [ 4277.399340] RDX: 0000000000000002 RSI: ffffffff828f8715 RDI: 00000000ffffffff [ 4277.400545] RBP: ffffea00044b3e40 R08: 0000000000000000 R09: ffffc900003339f0 [ 4277.401710] R10: 0000000000000003 R11: ffffffff82d44088 R12: ffff888112cf9910 [ 4277.402887] R13: 0000000000000001 R14: 0000000000000001 R15: ffff8881000424c0 [ 4277.404049] FS: 0000000000000000(0000) GS:ffff88842fd40000(0000) knlGS:0000000000000000 [ 4277.405357] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4277.406389] CR2: 00007f2ad0b24000 CR3: 0000000102a3a006 CR4: 00000000007706e0 [ 4277.407589] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4277.408780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4277.410000] PKRU: 55555554 [ 4277.410645] Call Trace: [ 4277.411234] <TASK> [ 4277.411777] ? die+0x32/0x80 [ 4277.412439] ? do_trap+0xd6/0x100 [ 4277.413150] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.414158] ? do_error_trap+0x6a/0x90 [ 4277.414948] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.415915] ? exc_invalid_op+0x4c/0x60 [ 4277.416710] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.417675] ? asm_exc_invalid_op+0x16/0x20 [ 4277.418482] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.419466] ? __list_del_entry_valid_or_report+0x7b/0xc0 [ 4277.420410] free_to_partial_list+0x515/0x5e0 [ 4277.421242] ? xfs_iext_remove+0x41a/0xa10 [xfs] [ 4277.422298] xfs_iext_remove+0x41a/0xa10 [xfs] [ 4277.423316] ? xfs_inodegc_worker+0xb4/0x1a0 [xfs] [ 4277.424383] xfs_bmap_del_extent_delay+0x4fe/0x7d0 [xfs] [ 4277.425490] __xfs_bunmapi+0x50d/0x840 [xfs] [ 4277.426445] xfs_itruncate_extents_flags+0x13a/0x490 [xfs] [ 4277.427553] xfs_inactive_truncate+0xa3/0x120 [xfs] [ 4277.428567] xfs_inactive+0x22d/0x290 [xfs] [ 4277.429500] xfs_inodegc_worker+0xb4/0x1a0 [xfs] [ 4277.430479] process_one_work+0x171/0x340 [ 4277.431227] worker_thread+0x277/0x390 [ 4277.431962] ? __pfx_worker_thread+0x10/0x10 [ 4277.432752] kthread+0xf0/0x120 [ 4277.433382] ? __pfx_kthread+0x10/0x10 [ 4277.434134] ret_from_fork+0x2d/0x50 [ 4277.434837] ? __pfx_kthread+0x10/0x10 [ 4277.435566] ret_from_fork_asm+0x1b/0x30 [ 4277.436280] </TASK>
CVE-2024-56583: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix warning in migrate_enable for boosted tasks When running the following command: while true; do stress-ng --cyclic 30 --timeout 30s --minimize --quiet done a warning is eventually triggered: WARNING: CPU: 43 PID: 2848 at kernel/sched/deadline.c:794 setup_new_dl_entity+0x13e/0x180 ... Call Trace: <TASK> ? show_trace_log_lvl+0x1c4/0x2df ? enqueue_dl_entity+0x631/0x6e0 ? setup_new_dl_entity+0x13e/0x180 ? __warn+0x7e/0xd0 ? report_bug+0x11a/0x1a0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 enqueue_dl_entity+0x631/0x6e0 enqueue_task_dl+0x7d/0x120 __do_set_cpus_allowed+0xe3/0x280 __set_cpus_allowed_ptr_locked+0x140/0x1d0 __set_cpus_allowed_ptr+0x54/0xa0 migrate_enable+0x7e/0x150 rt_spin_unlock+0x1c/0x90 group_send_sig_info+0xf7/0x1a0 ? kill_pid_info+0x1f/0x1d0 kill_pid_info+0x78/0x1d0 kill_proc_info+0x5b/0x110 __x64_sys_kill+0x93/0xc0 do_syscall_64+0x5c/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7f0dab31f92b This warning occurs because set_cpus_allowed dequeues and enqueues tasks with the ENQUEUE_RESTORE flag set. If the task is boosted, the warning is triggered. A boosted task already had its parameters set by rt_mutex_setprio, and a new call to setup_new_dl_entity is unnecessary, hence the WARN_ON call. Check if we are requeueing a boosted task and avoid calling setup_new_dl_entity if that's the case.
CVE-2024-56588: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Create all dump files during debugfs initialization For the current debugfs of hisi_sas, after user triggers dump, the driver allocate memory space to save the register information and create debugfs files to display the saved information. In this process, the debugfs files created after each dump. Therefore, when the dump is triggered while the driver is unbind, the following hang occurs: [67840.853907] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0 [67840.862947] Mem abort info: [67840.865855] ESR = 0x0000000096000004 [67840.869713] EC = 0x25: DABT (current EL), IL = 32 bits [67840.875125] SET = 0, FnV = 0 [67840.878291] EA = 0, S1PTW = 0 [67840.881545] FSC = 0x04: level 0 translation fault [67840.886528] Data abort info: [67840.889524] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [67840.895117] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [67840.900284] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [67840.905709] user pgtable: 4k pages, 48-bit VAs, pgdp=0000002803a1f000 [67840.912263] [00000000000000a0] pgd=0000000000000000, p4d=0000000000000000 [67840.919177] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP [67840.996435] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [67841.003628] pc : down_write+0x30/0x98 [67841.007546] lr : start_creating.part.0+0x60/0x198 [67841.012495] sp : ffff8000b979ba20 [67841.016046] x29: ffff8000b979ba20 x28: 0000000000000010 x27: 0000000000024b40 [67841.023412] x26: 0000000000000012 x25: ffff20202b355ae8 x24: ffff20202b35a8c8 [67841.030779] x23: ffffa36877928208 x22: ffffa368b4972240 x21: ffff8000b979bb18 [67841.038147] x20: ffff00281dc1e3c0 x19: fffffffffffffffe x18: 0000000000000020 [67841.045515] x17: 0000000000000000 x16: ffffa368b128a530 x15: ffffffffffffffff [67841.052888] x14: ffff8000b979bc18 x13: ffffffffffffffff x12: ffff8000b979bb18 [67841.060263] x11: 0000000000000000 x10: 0000000000000000 x9 : ffffa368b1289b18 [67841.067640] x8 : 0000000000000012 x7 : 0000000000000000 x6 : 00000000000003a9 [67841.075014] x5 : 0000000000000000 x4 : ffff002818c5cb00 x3 : 0000000000000001 [67841.082388] x2 : 0000000000000000 x1 : ffff002818c5cb00 x0 : 00000000000000a0 [67841.089759] Call trace: [67841.092456] down_write+0x30/0x98 [67841.096017] start_creating.part.0+0x60/0x198 [67841.100613] debugfs_create_dir+0x48/0x1f8 [67841.104950] debugfs_create_files_v3_hw+0x88/0x348 [hisi_sas_v3_hw] [67841.111447] debugfs_snapshot_regs_v3_hw+0x708/0x798 [hisi_sas_v3_hw] [67841.118111] debugfs_trigger_dump_v3_hw_write+0x9c/0x120 [hisi_sas_v3_hw] [67841.125115] full_proxy_write+0x68/0xc8 [67841.129175] vfs_write+0xd8/0x3f0 [67841.132708] ksys_write+0x70/0x108 [67841.136317] __arm64_sys_write+0x24/0x38 [67841.140440] invoke_syscall+0x50/0x128 [67841.144385] el0_svc_common.constprop.0+0xc8/0xf0 [67841.149273] do_el0_svc+0x24/0x38 [67841.152773] el0_svc+0x38/0xd8 [67841.156009] el0t_64_sync_handler+0xc0/0xc8 [67841.160361] el0t_64_sync+0x1a4/0x1a8 [67841.164189] Code: b9000882 d2800002 d2800023 f9800011 (c85ffc05) [67841.170443] ---[ end trace 0000000000000000 ]--- To fix this issue, create all directories and files during debugfs initialization. In this way, the driver only needs to allocate memory space to save information each time the user triggers dumping.
CVE-2024-56591: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_conn: Use disable_delayed_work_sync This makes use of disable_delayed_work_sync instead cancel_delayed_work_sync as it not only cancel the ongoing work but also disables new submit which is disarable since the object holding the work is about to be freed.
CVE-2024-56592: In the Linux kernel, the following vulnerability has been resolved: bpf: Call free_htab_elem() after htab_unlock_bucket() For htab of maps, when the map is removed from the htab, it may hold the last reference of the map. bpf_map_fd_put_ptr() will invoke bpf_map_free_id() to free the id of the removed map element. However, bpf_map_fd_put_ptr() is invoked while holding a bucket lock (raw_spin_lock_t), and bpf_map_free_id() attempts to acquire map_idr_lock (spinlock_t), triggering the following lockdep warning: ============================= [ BUG: Invalid wait context ] 6.11.0-rc4+ #49 Not tainted ----------------------------- test_maps/4881 is trying to lock: ffffffff84884578 (map_idr_lock){+...}-{3:3}, at: bpf_map_free_id.part.0+0x21/0x70 other info that might help us debug this: context-{5:5} 2 locks held by test_maps/4881: #0: ffffffff846caf60 (rcu_read_lock){....}-{1:3}, at: bpf_fd_htab_map_update_elem+0xf9/0x270 #1: ffff888149ced148 (&htab->lockdep_key#2){....}-{2:2}, at: htab_map_update_elem+0x178/0xa80 stack backtrace: CPU: 0 UID: 0 PID: 4881 Comm: test_maps Not tainted 6.11.0-rc4+ #49 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ... Call Trace: <TASK> dump_stack_lvl+0x6e/0xb0 dump_stack+0x10/0x20 __lock_acquire+0x73e/0x36c0 lock_acquire+0x182/0x450 _raw_spin_lock_irqsave+0x43/0x70 bpf_map_free_id.part.0+0x21/0x70 bpf_map_put+0xcf/0x110 bpf_map_fd_put_ptr+0x9a/0xb0 free_htab_elem+0x69/0xe0 htab_map_update_elem+0x50f/0xa80 bpf_fd_htab_map_update_elem+0x131/0x270 htab_map_update_elem+0x50f/0xa80 bpf_fd_htab_map_update_elem+0x131/0x270 bpf_map_update_value+0x266/0x380 __sys_bpf+0x21bb/0x36b0 __x64_sys_bpf+0x45/0x60 x64_sys_call+0x1b2a/0x20d0 do_syscall_64+0x5d/0x100 entry_SYSCALL_64_after_hwframe+0x76/0x7e One way to fix the lockdep warning is using raw_spinlock_t for map_idr_lock as well. However, bpf_map_alloc_id() invokes idr_alloc_cyclic() after acquiring map_idr_lock, it will trigger a similar lockdep warning because the slab's lock (s->cpu_slab->lock) is still a spinlock. Instead of changing map_idr_lock's type, fix the issue by invoking htab_put_fd_value() after htab_unlock_bucket(). However, only deferring the invocation of htab_put_fd_value() is not enough, because the old map pointers in htab of maps can not be saved during batched deletion. Therefore, also defer the invocation of free_htab_elem(), so these to-be-freed elements could be linked together similar to lru map. There are four callers for ->map_fd_put_ptr: (1) alloc_htab_elem() (through htab_put_fd_value()) It invokes ->map_fd_put_ptr() under a raw_spinlock_t. The invocation of htab_put_fd_value() can not simply move after htab_unlock_bucket(), because the old element has already been stashed in htab->extra_elems. It may be reused immediately after htab_unlock_bucket() and the invocation of htab_put_fd_value() after htab_unlock_bucket() may release the newly-added element incorrectly. Therefore, saving the map pointer of the old element for htab of maps before unlocking the bucket and releasing the map_ptr after unlock. Beside the map pointer in the old element, should do the same thing for the special fields in the old element as well. (2) free_htab_elem() (through htab_put_fd_value()) Its caller includes __htab_map_lookup_and_delete_elem(), htab_map_delete_elem() and __htab_map_lookup_and_delete_batch(). For htab_map_delete_elem(), simply invoke free_htab_elem() after htab_unlock_bucket(). For __htab_map_lookup_and_delete_batch(), just like lru map, linking the to-be-freed element into node_to_free list and invoking free_htab_elem() for these element after unlock. It is safe to reuse batch_flink as the link for node_to_free, because these elements have been removed from the hash llist. Because htab of maps doesn't support lookup_and_delete operation, __htab_map_lookup_and_delete_elem() doesn't have the problem, so kept it as ---truncated---
CVE-2024-56611: In the Linux kernel, the following vulnerability has been resolved: mm/mempolicy: fix migrate_to_node() assuming there is at least one VMA in a MM We currently assume that there is at least one VMA in a MM, which isn't true. So we might end up having find_vma() return NULL, to then de-reference NULL. So properly handle find_vma() returning NULL. This fixes the report: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 1 UID: 0 PID: 6021 Comm: syz-executor284 Not tainted 6.12.0-rc7-syzkaller-00187-gf868cd251776 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/30/2024 RIP: 0010:migrate_to_node mm/mempolicy.c:1090 [inline] RIP: 0010:do_migrate_pages+0x403/0x6f0 mm/mempolicy.c:1194 Code: ... RSP: 0018:ffffc9000375fd08 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffc9000375fd78 RCX: 0000000000000000 RDX: ffff88807e171300 RSI: dffffc0000000000 RDI: ffff88803390c044 RBP: ffff88807e171428 R08: 0000000000000014 R09: fffffbfff2039ef1 R10: ffffffff901cf78f R11: 0000000000000000 R12: 0000000000000003 R13: ffffc9000375fe90 R14: ffffc9000375fe98 R15: ffffc9000375fdf8 FS: 00005555919e1380(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005555919e1ca8 CR3: 000000007f12a000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> kernel_migrate_pages+0x5b2/0x750 mm/mempolicy.c:1709 __do_sys_migrate_pages mm/mempolicy.c:1727 [inline] __se_sys_migrate_pages mm/mempolicy.c:1723 [inline] __x64_sys_migrate_pages+0x96/0x100 mm/mempolicy.c:1723 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f [akpm@linux-foundation.org: add unlikely()]
CVE-2024-56641: In the Linux kernel, the following vulnerability has been resolved: net/smc: initialize close_work early to avoid warning We encountered a warning that close_work was canceled before initialization. WARNING: CPU: 7 PID: 111103 at kernel/workqueue.c:3047 __flush_work+0x19e/0x1b0 Workqueue: events smc_lgr_terminate_work [smc] RIP: 0010:__flush_work+0x19e/0x1b0 Call Trace: ? __wake_up_common+0x7a/0x190 ? work_busy+0x80/0x80 __cancel_work_timer+0xe3/0x160 smc_close_cancel_work+0x1a/0x70 [smc] smc_close_active_abort+0x207/0x360 [smc] __smc_lgr_terminate.part.38+0xc8/0x180 [smc] process_one_work+0x19e/0x340 worker_thread+0x30/0x370 ? process_one_work+0x340/0x340 kthread+0x117/0x130 ? __kthread_cancel_work+0x50/0x50 ret_from_fork+0x22/0x30 This is because when smc_close_cancel_work is triggered, e.g. the RDMA driver is rmmod and the LGR is terminated, the conn->close_work is flushed before initialization, resulting in WARN_ON(!work->func). __smc_lgr_terminate | smc_connect_{rdma|ism} ------------------------------------------------------------- | smc_conn_create | \- smc_lgr_register_conn for conn in lgr->conns_all | \- smc_conn_kill | \- smc_close_active_abort | \- smc_close_cancel_work | \- cancel_work_sync | \- __flush_work | (close_work) | | smc_close_init | \- INIT_WORK(&close_work) So fix this by initializing close_work before establishing the connection.
CVE-2024-56647: In the Linux kernel, the following vulnerability has been resolved: net: Fix icmp host relookup triggering ip_rt_bug arp link failure may trigger ip_rt_bug while xfrm enabled, call trace is: WARNING: CPU: 0 PID: 0 at net/ipv4/route.c:1241 ip_rt_bug+0x14/0x20 Modules linked in: CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.0-rc6-00077-g2e1b3cc9d7f7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:ip_rt_bug+0x14/0x20 Call Trace: <IRQ> ip_send_skb+0x14/0x40 __icmp_send+0x42d/0x6a0 ipv4_link_failure+0xe2/0x1d0 arp_error_report+0x3c/0x50 neigh_invalidate+0x8d/0x100 neigh_timer_handler+0x2e1/0x330 call_timer_fn+0x21/0x120 __run_timer_base.part.0+0x1c9/0x270 run_timer_softirq+0x4c/0x80 handle_softirqs+0xac/0x280 irq_exit_rcu+0x62/0x80 sysvec_apic_timer_interrupt+0x77/0x90 The script below reproduces this scenario: ip xfrm policy add src 0.0.0.0/0 dst 0.0.0.0/0 \ dir out priority 0 ptype main flag localok icmp ip l a veth1 type veth ip a a 192.168.141.111/24 dev veth0 ip l s veth0 up ping 192.168.141.155 -c 1 icmp_route_lookup() create input routes for locally generated packets while xfrm relookup ICMP traffic.Then it will set input route (dst->out = ip_rt_bug) to skb for DESTUNREACH. For ICMP err triggered by locally generated packets, dst->dev of output route is loopback. Generally, xfrm relookup verification is not required on loopback interfaces (net.ipv4.conf.lo.disable_xfrm = 1). Skip icmp relookup for locally generated packets to fix it.
CVE-2024-56657: In the Linux kernel, the following vulnerability has been resolved: ALSA: control: Avoid WARN() for symlink errors Using WARN() for showing the error of symlink creations don't give more information than telling that something goes wrong, since the usual code path is a lregister callback from each control element creation. More badly, the use of WARN() rather confuses fuzzer as if it were serious issues. This patch downgrades the warning messages to use the normal dev_err() instead of WARN(). For making it clearer, add the function name to the prefix, too.
CVE-2024-56692: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node blkaddr in truncate_node() syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2534! RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 Call Trace: truncate_node+0x1ae/0x8c0 fs/f2fs/node.c:909 f2fs_remove_inode_page+0x5c2/0x870 fs/f2fs/node.c:1288 f2fs_evict_inode+0x879/0x15c0 fs/f2fs/inode.c:856 evict+0x4e8/0x9b0 fs/inode.c:723 f2fs_handle_failed_inode+0x271/0x2e0 fs/f2fs/inode.c:986 f2fs_create+0x357/0x530 fs/f2fs/namei.c:394 lookup_open fs/namei.c:3595 [inline] open_last_lookups fs/namei.c:3694 [inline] path_openat+0x1c03/0x3590 fs/namei.c:3930 do_filp_open+0x235/0x490 fs/namei.c:3960 do_sys_openat2+0x13e/0x1d0 fs/open.c:1415 do_sys_open fs/open.c:1430 [inline] __do_sys_openat fs/open.c:1446 [inline] __se_sys_openat fs/open.c:1441 [inline] __x64_sys_openat+0x247/0x2a0 fs/open.c:1441 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 The root cause is: on a fuzzed image, blkaddr in nat entry may be corrupted, then it will cause system panic when using it in f2fs_invalidate_blocks(), to avoid this, let's add sanity check on nat blkaddr in truncate_node().
CVE-2024-56712: In the Linux kernel, the following vulnerability has been resolved: udmabuf: fix memory leak on last export_udmabuf() error path In export_udmabuf(), if dma_buf_fd() fails because the FD table is full, a dma_buf owning the udmabuf has already been created; but the error handling in udmabuf_create() will tear down the udmabuf without doing anything about the containing dma_buf. This leaves a dma_buf in memory that contains a dangling pointer; though that doesn't seem to lead to anything bad except a memory leak. Fix it by moving the dma_buf_fd() call out of export_udmabuf() so that we can give it different error handling. Note that the shape of this code changed a lot in commit 5e72b2b41a21 ("udmabuf: convert udmabuf driver to use folios"); but the memory leak seems to have existed since the introduction of udmabuf.
CVE-2024-56719: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix TSO DMA API usage causing oops Commit 66600fac7a98 ("net: stmmac: TSO: Fix unbalanced DMA map/unmap for non-paged SKB data") moved the assignment of tx_skbuff_dma[]'s members to be later in stmmac_tso_xmit(). The buf (dma cookie) and len stored in this structure are passed to dma_unmap_single() by stmmac_tx_clean(). The DMA API requires that the dma cookie passed to dma_unmap_single() is the same as the value returned from dma_map_single(). However, by moving the assignment later, this is not the case when priv->dma_cap.addr64 > 32 as "des" is offset by proto_hdr_len. This causes problems such as: dwc-eth-dwmac 2490000.ethernet eth0: Tx DMA map failed and with DMA_API_DEBUG enabled: DMA-API: dwc-eth-dwmac 2490000.ethernet: device driver tries to +free DMA memory it has not allocated [device address=0x000000ffffcf65c0] [size=66 bytes] Fix this by maintaining "des" as the original DMA cookie, and use tso_des to pass the offset DMA cookie to stmmac_tso_allocator(). Full details of the crashes can be found at: https://lore.kernel.org/all/d8112193-0386-4e14-b516-37c2d838171a@nvidia.com/ https://lore.kernel.org/all/klkzp5yn5kq5efgtrow6wbvnc46bcqfxs65nz3qy77ujr5turc@bwwhelz2l4dw/
CVE-2024-56729: In the Linux kernel, the following vulnerability has been resolved: smb: Initialize cfid->tcon before performing network ops Avoid leaking a tcon ref when a lease break races with opening the cached directory. Processing the leak break might take a reference to the tcon in cached_dir_lease_break() and then fail to release the ref in cached_dir_offload_close, since cfid->tcon is still NULL.
CVE-2024-56742: In the Linux kernel, the following vulnerability has been resolved: vfio/mlx5: Fix an unwind issue in mlx5vf_add_migration_pages() Fix an unwind issue in mlx5vf_add_migration_pages(). If a set of pages is allocated but fails to be added to the SG table, they need to be freed to prevent a memory leak. Any pages successfully added to the SG table will be freed as part of mlx5vf_free_data_buffer().
CVE-2024-56775: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix handling of plane refcount [Why] The mechanism to backup and restore plane states doesn't maintain refcount, which can cause issues if the refcount of the plane changes in between backup and restore operations, such as memory leaks if the refcount was supposed to go down, or double frees / invalid memory accesses if the refcount was supposed to go up. [How] Cache and re-apply current refcount when restoring plane states.
CVE-2024-57795: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Remove the direct link to net_device The similar patch in siw is in the link: https://git.kernel.org/rdma/rdma/c/16b87037b48889 This problem also occurred in RXE. The following analyze this problem. In the following Call Traces: " BUG: KASAN: slab-use-after-free in dev_get_flags+0x188/0x1d0 net/core/dev.c:8782 Read of size 4 at addr ffff8880554640b0 by task kworker/1:4/5295 CPU: 1 UID: 0 PID: 5295 Comm: kworker/1:4 Not tainted 6.12.0-rc3-syzkaller-00399-g9197b73fd7bb #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: infiniband ib_cache_event_task Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 dev_get_flags+0x188/0x1d0 net/core/dev.c:8782 rxe_query_port+0x12d/0x260 drivers/infiniband/sw/rxe/rxe_verbs.c:60 __ib_query_port drivers/infiniband/core/device.c:2111 [inline] ib_query_port+0x168/0x7d0 drivers/infiniband/core/device.c:2143 ib_cache_update+0x1a9/0xb80 drivers/infiniband/core/cache.c:1494 ib_cache_event_task+0xf3/0x1e0 drivers/infiniband/core/cache.c:1568 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa65/0x1850 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f2/0x390 kernel/kthread.c:389 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> " 1). In the link [1], " infiniband syz2: set down " This means that on 839.350575, the event ib_cache_event_task was sent andi queued in ib_wq. 2). In the link [1], " team0 (unregistering): Port device team_slave_0 removed " It indicates that before 843.251853, the net device should be freed. 3). In the link [1], " BUG: KASAN: slab-use-after-free in dev_get_flags+0x188/0x1d0 " This means that on 850.559070, this slab-use-after-free problem occurred. In all, on 839.350575, the event ib_cache_event_task was sent and queued in ib_wq, before 843.251853, the net device veth was freed. on 850.559070, this event was executed, and the mentioned freed net device was called. Thus, the above call trace occurred. [1] https://syzkaller.appspot.com/x/log.txt?x=12e7025f980000
CVE-2024-57804: In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Fix corrupt config pages PHY state is switched in sysfs The driver, through the SAS transport, exposes a sysfs interface to enable/disable PHYs in a controller/expander setup. When multiple PHYs are disabled and enabled in rapid succession, the persistent and current config pages related to SAS IO unit/SAS Expander pages could get corrupted. Use separate memory for each config request.
CVE-2024-57809: In the Linux kernel, the following vulnerability has been resolved: PCI: imx6: Fix suspend/resume support on i.MX6QDL The suspend/resume functionality is currently broken on the i.MX6QDL platform, as documented in the NXP errata (ERR005723): https://www.nxp.com/docs/en/errata/IMX6DQCE.pdf This patch addresses the issue by sharing most of the suspend/resume sequences used by other i.MX devices, while avoiding modifications to critical registers that disrupt the PCIe functionality. It targets the same problem as the following downstream commit: https://github.com/nxp-imx/linux-imx/commit/4e92355e1f79d225ea842511fcfd42b343b32995 Unlike the downstream commit, this patch also resets the connected PCIe device if possible. Without this reset, certain drivers, such as ath10k or iwlwifi, will crash on resume. The device reset is also done by the driver on other i.MX platforms, making this patch consistent with existing practices. Upon resuming, the kernel will hang and display an error. Here's an example of the error encountered with the ath10k driver: ath10k_pci 0000:01:00.0: Unable to change power state from D3hot to D0, device inaccessible Unhandled fault: imprecise external abort (0x1406) at 0x0106f944 Without this patch, suspend/resume will fail on i.MX6QDL devices if a PCIe device is connected. [kwilczynski: commit log, added tag for stable releases]
CVE-2024-57857: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Remove direct link to net_device Do not manage a per device direct link to net_device. Rely on associated ib_devices net_device management, not doubling the effort locally. A badly managed local link to net_device was causing a 'KASAN: slab-use-after-free' exception during siw_query_port() call.
CVE-2024-57872: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: pltfrm: Dellocate HBA during ufshcd_pltfrm_remove() This will ensure that the scsi host is cleaned up properly using scsi_host_dev_release(). Otherwise, it may lead to memory leaks.
CVE-2024-57888: In the Linux kernel, the following vulnerability has been resolved: workqueue: Do not warn when cancelling WQ_MEM_RECLAIM work from !WQ_MEM_RECLAIM worker After commit 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM") amdgpu started seeing the following warning: [ ] workqueue: WQ_MEM_RECLAIM sdma0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_device_delay_enable_gfx_off [amdgpu] ... [ ] Workqueue: sdma0 drm_sched_run_job_work [gpu_sched] ... [ ] Call Trace: [ ] <TASK> ... [ ] ? check_flush_dependency+0xf5/0x110 ... [ ] cancel_delayed_work_sync+0x6e/0x80 [ ] amdgpu_gfx_off_ctrl+0xab/0x140 [amdgpu] [ ] amdgpu_ring_alloc+0x40/0x50 [amdgpu] [ ] amdgpu_ib_schedule+0xf4/0x810 [amdgpu] [ ] ? drm_sched_run_job_work+0x22c/0x430 [gpu_sched] [ ] amdgpu_job_run+0xaa/0x1f0 [amdgpu] [ ] drm_sched_run_job_work+0x257/0x430 [gpu_sched] [ ] process_one_work+0x217/0x720 ... [ ] </TASK> The intent of the verifcation done in check_flush_depedency is to ensure forward progress during memory reclaim, by flagging cases when either a memory reclaim process, or a memory reclaim work item is flushed from a context not marked as memory reclaim safe. This is correct when flushing, but when called from the cancel(_delayed)_work_sync() paths it is a false positive because work is either already running, or will not be running at all. Therefore cancelling it is safe and we can relax the warning criteria by letting the helper know of the calling context. References: 746ae46c1113 ("drm/sched: Mark scheduler work queues with WQ_MEM_RECLAIM")
CVE-2024-57900: In the Linux kernel, the following vulnerability has been resolved: ila: serialize calls to nf_register_net_hooks() syzbot found a race in ila_add_mapping() [1] commit 031ae72825ce ("ila: call nf_unregister_net_hooks() sooner") attempted to fix a similar issue. Looking at the syzbot repro, we have concurrent ILA_CMD_ADD commands. Add a mutex to make sure at most one thread is calling nf_register_net_hooks(). [1] BUG: KASAN: slab-use-after-free in rht_key_hashfn include/linux/rhashtable.h:159 [inline] BUG: KASAN: slab-use-after-free in __rhashtable_lookup.constprop.0+0x426/0x550 include/linux/rhashtable.h:604 Read of size 4 at addr ffff888028f40008 by task dhcpcd/5501 CPU: 1 UID: 0 PID: 5501 Comm: dhcpcd Not tainted 6.13.0-rc4-syzkaller-00054-gd6ef8b40d075 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xc3/0x620 mm/kasan/report.c:489 kasan_report+0xd9/0x110 mm/kasan/report.c:602 rht_key_hashfn include/linux/rhashtable.h:159 [inline] __rhashtable_lookup.constprop.0+0x426/0x550 include/linux/rhashtable.h:604 rhashtable_lookup include/linux/rhashtable.h:646 [inline] rhashtable_lookup_fast include/linux/rhashtable.h:672 [inline] ila_lookup_wildcards net/ipv6/ila/ila_xlat.c:127 [inline] ila_xlat_addr net/ipv6/ila/ila_xlat.c:652 [inline] ila_nf_input+0x1ee/0x620 net/ipv6/ila/ila_xlat.c:185 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xbb/0x200 net/netfilter/core.c:626 nf_hook.constprop.0+0x42e/0x750 include/linux/netfilter.h:269 NF_HOOK include/linux/netfilter.h:312 [inline] ipv6_rcv+0xa4/0x680 net/ipv6/ip6_input.c:309 __netif_receive_skb_one_core+0x12e/0x1e0 net/core/dev.c:5672 __netif_receive_skb+0x1d/0x160 net/core/dev.c:5785 process_backlog+0x443/0x15f0 net/core/dev.c:6117 __napi_poll.constprop.0+0xb7/0x550 net/core/dev.c:6883 napi_poll net/core/dev.c:6952 [inline] net_rx_action+0xa94/0x1010 net/core/dev.c:7074 handle_softirqs+0x213/0x8f0 kernel/softirq.c:561 __do_softirq kernel/softirq.c:595 [inline] invoke_softirq kernel/softirq.c:435 [inline] __irq_exit_rcu+0x109/0x170 kernel/softirq.c:662 irq_exit_rcu+0x9/0x30 kernel/softirq.c:678 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1049 [inline] sysvec_apic_timer_interrupt+0xa4/0xc0 arch/x86/kernel/apic/apic.c:1049
CVE-2024-57974: In the Linux kernel, the following vulnerability has been resolved: udp: Deal with race between UDP socket address change and rehash If a UDP socket changes its local address while it's receiving datagrams, as a result of connect(), there is a period during which a lookup operation might fail to find it, after the address is changed but before the secondary hash (port and address) and the four-tuple hash (local and remote ports and addresses) are updated. Secondary hash chains were introduced by commit 30fff9231fad ("udp: bind() optimisation") and, as a result, a rehash operation became needed to make a bound socket reachable again after a connect(). This operation was introduced by commit 719f835853a9 ("udp: add rehash on connect()") which isn't however a complete fix: the socket will be found once the rehashing completes, but not while it's pending. This is noticeable with a socat(1) server in UDP4-LISTEN mode, and a client sending datagrams to it. After the server receives the first datagram (cf. _xioopen_ipdgram_listen()), it issues a connect() to the address of the sender, in order to set up a directed flow. Now, if the client, running on a different CPU thread, happens to send a (subsequent) datagram while the server's socket changes its address, but is not rehashed yet, this will result in a failed lookup and a port unreachable error delivered to the client, as apparent from the following reproducer: LEN=$(($(cat /proc/sys/net/core/wmem_default) / 4)) dd if=/dev/urandom bs=1 count=${LEN} of=tmp.in while :; do taskset -c 1 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,trunc & sleep 0.1 || sleep 1 taskset -c 2 socat OPEN:tmp.in UDP4:localhost:1337,shut-null wait done where the client will eventually get ECONNREFUSED on a write() (typically the second or third one of a given iteration): 2024/11/13 21:28:23 socat[46901] E write(6, 0x556db2e3c000, 8192): Connection refused This issue was first observed as a seldom failure in Podman's tests checking UDP functionality while using pasta(1) to connect the container's network namespace, which leads us to a reproducer with the lookup error resulting in an ICMP packet on a tap device: LOCAL_ADDR="$(ip -j -4 addr show|jq -rM '.[] | .addr_info[0] | select(.scope == "global").local')" while :; do ./pasta --config-net -p pasta.pcap -u 1337 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,trunc & sleep 0.2 || sleep 1 socat OPEN:tmp.in UDP4:${LOCAL_ADDR}:1337,shut-null wait cmp tmp.in tmp.out done Once this fails: tmp.in tmp.out differ: char 8193, line 29 we can finally have a look at what's going on: $ tshark -r pasta.pcap 1 0.000000 :: ? ff02::16 ICMPv6 110 Multicast Listener Report Message v2 2 0.168690 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 3 0.168767 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 4 0.168806 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 5 0.168827 c6:47:05:8d:dc:04 ? Broadcast ARP 42 Who has 88.198.0.161? Tell 88.198.0.164 6 0.168851 9a:55:9a:55:9a:55 ? c6:47:05:8d:dc:04 ARP 42 88.198.0.161 is at 9a:55:9a:55:9a:55 7 0.168875 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 8 0.168896 88.198.0.164 ? 88.198.0.161 ICMP 590 Destination unreachable (Port unreachable) 9 0.168926 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 10 0.168959 88.198.0.161 ? 88.198.0.164 UDP 8234 60260 ? 1337 Len=8192 11 0.168989 88.198.0.161 ? 88.198.0.164 UDP 4138 60260 ? 1337 Len=4096 12 0.169010 88.198.0.161 ? 88.198.0.164 UDP 42 60260 ? 1337 Len=0 On the third datagram received, the network namespace of the container initiates an ARP lookup to deliver the ICMP message. In another variant of this reproducer, starting the client with: strace -f pasta --config-net -u 1337 socat UDP4-LISTEN:1337,null-eof OPEN:tmp.out,create,tru ---truncated---
CVE-2024-57975: In the Linux kernel, the following vulnerability has been resolved: btrfs: do proper folio cleanup when run_delalloc_nocow() failed [BUG] With CONFIG_DEBUG_VM set, test case generic/476 has some chance to crash with the following VM_BUG_ON_FOLIO(): BTRFS error (device dm-3): cow_file_range failed, start 1146880 end 1253375 len 106496 ret -28 BTRFS error (device dm-3): run_delalloc_nocow failed, start 1146880 end 1253375 len 106496 ret -28 page: refcount:4 mapcount:0 mapping:00000000592787cc index:0x12 pfn:0x10664 aops:btrfs_aops [btrfs] ino:101 dentry name(?):"f1774" flags: 0x2fffff80004028(uptodate|lru|private|node=0|zone=2|lastcpupid=0xfffff) page dumped because: VM_BUG_ON_FOLIO(!folio_test_locked(folio)) ------------[ cut here ]------------ kernel BUG at mm/page-writeback.c:2992! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 2 UID: 0 PID: 3943513 Comm: kworker/u24:15 Tainted: G OE 6.12.0-rc7-custom+ #87 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : folio_clear_dirty_for_io+0x128/0x258 lr : folio_clear_dirty_for_io+0x128/0x258 Call trace: folio_clear_dirty_for_io+0x128/0x258 btrfs_folio_clamp_clear_dirty+0x80/0xd0 [btrfs] __process_folios_contig+0x154/0x268 [btrfs] extent_clear_unlock_delalloc+0x5c/0x80 [btrfs] run_delalloc_nocow+0x5f8/0x760 [btrfs] btrfs_run_delalloc_range+0xa8/0x220 [btrfs] writepage_delalloc+0x230/0x4c8 [btrfs] extent_writepage+0xb8/0x358 [btrfs] extent_write_cache_pages+0x21c/0x4e8 [btrfs] btrfs_writepages+0x94/0x150 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x88/0xc8 start_delalloc_inodes+0x178/0x3a8 [btrfs] btrfs_start_delalloc_roots+0x174/0x280 [btrfs] shrink_delalloc+0x114/0x280 [btrfs] flush_space+0x250/0x2f8 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x164/0x408 worker_thread+0x25c/0x388 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: 910a8021 a90363f7 a9046bf9 94012379 (d4210000) ---[ end trace 0000000000000000 ]--- [CAUSE] The first two lines of extra debug messages show the problem is caused by the error handling of run_delalloc_nocow(). E.g. we have the following dirtied range (4K blocksize 4K page size): 0 16K 32K |//////////////////////////////////////| | Pre-allocated | And the range [0, 16K) has a preallocated extent. - Enter run_delalloc_nocow() for range [0, 16K) Which found range [0, 16K) is preallocated, can do the proper NOCOW write. - Enter fallback_to_fow() for range [16K, 32K) Since the range [16K, 32K) is not backed by preallocated extent, we have to go COW. - cow_file_range() failed for range [16K, 32K) So cow_file_range() will do the clean up by clearing folio dirty, unlock the folios. Now the folios in range [16K, 32K) is unlocked. - Enter extent_clear_unlock_delalloc() from run_delalloc_nocow() Which is called with PAGE_START_WRITEBACK to start page writeback. But folios can only be marked writeback when it's properly locked, thus this triggered the VM_BUG_ON_FOLIO(). Furthermore there is another hidden but common bug that run_delalloc_nocow() is not clearing the folio dirty flags in its error handling path. This is the common bug shared between run_delalloc_nocow() and cow_file_range(). [FIX] - Clear folio dirty for range [@start, @cur_offset) Introduce a helper, cleanup_dirty_folios(), which will find and lock the folio in the range, clear the dirty flag and start/end the writeback, with the extra handling for the @locked_folio. - Introduce a helper to clear folio dirty, start and end writeback - Introduce a helper to record the last failed COW range end This is to trace which range we should skip, to avoid double unlocking. - Skip the failed COW range for the e ---truncated---
CVE-2024-57976: In the Linux kernel, the following vulnerability has been resolved: btrfs: do proper folio cleanup when cow_file_range() failed [BUG] When testing with COW fixup marked as BUG_ON() (this is involved with the new pin_user_pages*() change, which should not result new out-of-band dirty pages), I hit a crash triggered by the BUG_ON() from hitting COW fixup path. This BUG_ON() happens just after a failed btrfs_run_delalloc_range(): BTRFS error (device dm-2): failed to run delalloc range, root 348 ino 405 folio 65536 submit_bitmap 6-15 start 90112 len 106496: -28 ------------[ cut here ]------------ kernel BUG at fs/btrfs/extent_io.c:1444! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 0 UID: 0 PID: 434621 Comm: kworker/u24:8 Tainted: G OE 6.12.0-rc7-custom+ #86 Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : extent_writepage_io+0x2d4/0x308 [btrfs] lr : extent_writepage_io+0x2d4/0x308 [btrfs] Call trace: extent_writepage_io+0x2d4/0x308 [btrfs] extent_writepage+0x218/0x330 [btrfs] extent_write_cache_pages+0x1d4/0x4b0 [btrfs] btrfs_writepages+0x94/0x150 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x88/0xc8 start_delalloc_inodes+0x180/0x3b0 [btrfs] btrfs_start_delalloc_roots+0x174/0x280 [btrfs] shrink_delalloc+0x114/0x280 [btrfs] flush_space+0x250/0x2f8 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x164/0x408 worker_thread+0x25c/0x388 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: aa1403e1 9402f3ef aa1403e0 9402f36f (d4210000) ---[ end trace 0000000000000000 ]--- [CAUSE] That failure is mostly from cow_file_range(), where we can hit -ENOSPC. Although the -ENOSPC is already a bug related to our space reservation code, let's just focus on the error handling. For example, we have the following dirty range [0, 64K) of an inode, with 4K sector size and 4K page size: 0 16K 32K 48K 64K |///////////////////////////////////////| |#######################################| Where |///| means page are still dirty, and |###| means the extent io tree has EXTENT_DELALLOC flag. - Enter extent_writepage() for page 0 - Enter btrfs_run_delalloc_range() for range [0, 64K) - Enter cow_file_range() for range [0, 64K) - Function btrfs_reserve_extent() only reserved one 16K extent So we created extent map and ordered extent for range [0, 16K) 0 16K 32K 48K 64K |////////|//////////////////////////////| |<- OE ->|##############################| And range [0, 16K) has its delalloc flag cleared. But since we haven't yet submit any bio, involved 4 pages are still dirty. - Function btrfs_reserve_extent() returns with -ENOSPC Now we have to run error cleanup, which will clear all EXTENT_DELALLOC* flags and clear the dirty flags for the remaining ranges: 0 16K 32K 48K 64K |////////| | | | | Note that range [0, 16K) still has its pages dirty. - Some time later, writeback is triggered again for the range [0, 16K) since the page range still has dirty flags. - btrfs_run_delalloc_range() will do nothing because there is no EXTENT_DELALLOC flag. - extent_writepage_io() finds page 0 has no ordered flag Which falls into the COW fixup path, triggering the BUG_ON(). Unfortunately this error handling bug dates back to the introduction of btrfs. Thankfully with the abuse of COW fixup, at least it won't crash the kernel. [FIX] Instead of immediately unlocking the extent and folios, we keep the extent and folios locked until either erroring out or the whole delalloc range finished. When the whole delalloc range finished without error, we just unlock the whole range with PAGE_SET_ORDERED (and PAGE_UNLOCK for !keep_locked cases) ---truncated---
CVE-2024-57982: In the Linux kernel, the following vulnerability has been resolved: xfrm: state: fix out-of-bounds read during lookup lookup and resize can run in parallel. The xfrm_state_hash_generation seqlock ensures a retry, but the hash functions can observe a hmask value that is too large for the new hlist array. rehash does: rcu_assign_pointer(net->xfrm.state_bydst, ndst) [..] net->xfrm.state_hmask = nhashmask; While state lookup does: h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { This is only safe in case the update to state_bydst is larger than net->xfrm.xfrm_state_hmask (or if the lookup function gets serialized via state spinlock again). Fix this by prefetching state_hmask and the associated pointers. The xfrm_state_hash_generation seqlock retry will ensure that the pointer and the hmask will be consistent. The existing helpers, like xfrm_dst_hash(), are now unsafe for RCU side, add lockdep assertions to document that they are only safe for insert side. xfrm_state_lookup_byaddr() uses the spinlock rather than RCU. AFAICS this is an oversight from back when state lookup was converted to RCU, this lock should be replaced with RCU in a future patch.
CVE-2024-57984: In the Linux kernel, the following vulnerability has been resolved: i3c: dw: Fix use-after-free in dw_i3c_master driver due to race condition In dw_i3c_common_probe, &master->hj_work is bound with dw_i3c_hj_work. And dw_i3c_master_irq_handler can call dw_i3c_master_irq_handle_ibis function to start the work. If we remove the module which will call dw_i3c_common_remove to make cleanup, it will free master->base through i3c_master_unregister while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | dw_i3c_hj_work dw_i3c_common_remove | i3c_master_unregister(&master->base) | device_unregister(&master->dev) | device_release | //free master->base | | i3c_master_do_daa(&master->base) | //use master->base Fix it by ensuring that the work is canceled before proceeding with the cleanup in dw_i3c_common_remove.
CVE-2024-57999: In the Linux kernel, the following vulnerability has been resolved: powerpc/pseries/iommu: IOMMU incorrectly marks MMIO range in DDW Power Hypervisor can possibily allocate MMIO window intersecting with Dynamic DMA Window (DDW) range, which is over 32-bit addressing. These MMIO pages needs to be marked as reserved so that IOMMU doesn't map DMA buffers in this range. The current code is not marking these pages correctly which is resulting in LPAR to OOPS while booting. The stack is at below BUG: Unable to handle kernel data access on read at 0xc00800005cd40000 Faulting instruction address: 0xc00000000005cdac Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: af_packet rfkill ibmveth(X) lpfc(+) nvmet_fc nvmet nvme_keyring crct10dif_vpmsum nvme_fc nvme_fabrics nvme_core be2net(+) nvme_auth rtc_generic nfsd auth_rpcgss nfs_acl lockd grace sunrpc fuse configfs ip_tables x_tables xfs libcrc32c dm_service_time ibmvfc(X) scsi_transport_fc vmx_crypto gf128mul crc32c_vpmsum dm_mirror dm_region_hash dm_log dm_multipath dm_mod sd_mod scsi_dh_emc scsi_dh_rdac scsi_dh_alua t10_pi crc64_rocksoft_generic crc64_rocksoft sg crc64 scsi_mod Supported: Yes, External CPU: 8 PID: 241 Comm: kworker/8:1 Kdump: loaded Not tainted 6.4.0-150600.23.14-default #1 SLE15-SP6 b44ee71c81261b9e4bab5e0cde1f2ed891d5359b Hardware name: IBM,9080-M9S POWER9 (raw) 0x4e2103 0xf000005 of:IBM,FW950.B0 (VH950_149) hv:phyp pSeries Workqueue: events work_for_cpu_fn NIP: c00000000005cdac LR: c00000000005e830 CTR: 0000000000000000 REGS: c00001400c9ff770 TRAP: 0300 Not tainted (6.4.0-150600.23.14-default) MSR: 800000000280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 24228448 XER: 00000001 CFAR: c00000000005cdd4 DAR: c00800005cd40000 DSISR: 40000000 IRQMASK: 0 GPR00: c00000000005e830 c00001400c9ffa10 c000000001987d00 c00001400c4fe800 GPR04: 0000080000000000 0000000000000001 0000000004000000 0000000000800000 GPR08: 0000000004000000 0000000000000001 c00800005cd40000 ffffffffffffffff GPR12: 0000000084228882 c00000000a4c4f00 0000000000000010 0000080000000000 GPR16: c00001400c4fe800 0000000004000000 0800000000000000 c00000006088b800 GPR20: c00001401a7be980 c00001400eff3800 c000000002a2da68 000000000000002b GPR24: c0000000026793a8 c000000002679368 000000000000002a c0000000026793c8 GPR28: 000008007effffff 0000080000000000 0000000000800000 c00001400c4fe800 NIP [c00000000005cdac] iommu_table_reserve_pages+0xac/0x100 LR [c00000000005e830] iommu_init_table+0x80/0x1e0 Call Trace: [c00001400c9ffa10] [c00000000005e810] iommu_init_table+0x60/0x1e0 (unreliable) [c00001400c9ffa90] [c00000000010356c] iommu_bypass_supported_pSeriesLP+0x9cc/0xe40 [c00001400c9ffc30] [c00000000005c300] dma_iommu_dma_supported+0xf0/0x230 [c00001400c9ffcb0] [c00000000024b0c4] dma_supported+0x44/0x90 [c00001400c9ffcd0] [c00000000024b14c] dma_set_mask+0x3c/0x80 [c00001400c9ffd00] [c0080000555b715c] be_probe+0xc4/0xb90 [be2net] [c00001400c9ffdc0] [c000000000986f3c] local_pci_probe+0x6c/0x110 [c00001400c9ffe40] [c000000000188f28] work_for_cpu_fn+0x38/0x60 [c00001400c9ffe70] [c00000000018e454] process_one_work+0x314/0x620 [c00001400c9fff10] [c00000000018f280] worker_thread+0x2b0/0x620 [c00001400c9fff90] [c00000000019bb18] kthread+0x148/0x150 [c00001400c9fffe0] [c00000000000ded8] start_kernel_thread+0x14/0x18 There are 2 issues in the code 1. The index is "int" while the address is "unsigned long". This results in negative value when setting the bitmap. 2. The DMA offset is page shifted but the MMIO range is used as-is (64-bit address). MMIO address needs to be page shifted as well.
CVE-2024-58006: In the Linux kernel, the following vulnerability has been resolved: PCI: dwc: ep: Prevent changing BAR size/flags in pci_epc_set_bar() In commit 4284c88fff0e ("PCI: designware-ep: Allow pci_epc_set_bar() update inbound map address") set_bar() was modified to support dynamically changing the backing physical address of a BAR that was already configured. This means that set_bar() can be called twice, without ever calling clear_bar() (as calling clear_bar() would clear the BAR's PCI address assigned by the host). This can only be done if the new BAR size/flags does not differ from the existing BAR configuration. Add these missing checks. If we allow set_bar() to set e.g. a new BAR size that differs from the existing BAR size, the new address translation range will be smaller than the BAR size already determined by the host, which would mean that a read past the new BAR size would pass the iATU untranslated, which could allow the host to read memory not belonging to the new struct pci_epf_bar. While at it, add comments which clarifies the support for dynamically changing the physical address of a BAR. (Which was also missing.)
CVE-2024-58012: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda-dai: Ensure DAI widget is valid during params Each cpu DAI should associate with a widget. However, the topology might not create the right number of DAI widgets for aggregated amps. And it will cause NULL pointer deference. Check that the DAI widget associated with the CPU DAI is valid to prevent NULL pointer deference due to missing DAI widgets in topologies with aggregated amps.
CVE-2024-58053: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix handling of received connection abort Fix the handling of a connection abort that we've received. Though the abort is at the connection level, it needs propagating to the calls on that connection. Whilst the propagation bit is performed, the calls aren't then woken up to go and process their termination, and as no further input is forthcoming, they just hang. Also add some tracing for the logging of connection aborts.
CVE-2024-58089: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix double accounting race when btrfs_run_delalloc_range() failed [BUG] When running btrfs with block size (4K) smaller than page size (64K, aarch64), there is a very high chance to crash the kernel at generic/750, with the following messages: (before the call traces, there are 3 extra debug messages added) BTRFS warning (device dm-3): read-write for sector size 4096 with page size 65536 is experimental BTRFS info (device dm-3): checking UUID tree hrtimer: interrupt took 5451385 ns BTRFS error (device dm-3): cow_file_range failed, root=4957 inode=257 start=1605632 len=69632: -28 BTRFS error (device dm-3): run_delalloc_nocow failed, root=4957 inode=257 start=1605632 len=69632: -28 BTRFS error (device dm-3): failed to run delalloc range, root=4957 ino=257 folio=1572864 submit_bitmap=8-15 start=1605632 len=69632: -28 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 3020984 at ordered-data.c:360 can_finish_ordered_extent+0x370/0x3b8 [btrfs] CPU: 2 UID: 0 PID: 3020984 Comm: kworker/u24:1 Tainted: G OE 6.13.0-rc1-custom+ #89 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: events_unbound btrfs_async_reclaim_data_space [btrfs] pc : can_finish_ordered_extent+0x370/0x3b8 [btrfs] lr : can_finish_ordered_extent+0x1ec/0x3b8 [btrfs] Call trace: can_finish_ordered_extent+0x370/0x3b8 [btrfs] (P) can_finish_ordered_extent+0x1ec/0x3b8 [btrfs] (L) btrfs_mark_ordered_io_finished+0x130/0x2b8 [btrfs] extent_writepage+0x10c/0x3b8 [btrfs] extent_write_cache_pages+0x21c/0x4e8 [btrfs] btrfs_writepages+0x94/0x160 [btrfs] do_writepages+0x74/0x190 filemap_fdatawrite_wbc+0x74/0xa0 start_delalloc_inodes+0x17c/0x3b0 [btrfs] btrfs_start_delalloc_roots+0x17c/0x288 [btrfs] shrink_delalloc+0x11c/0x280 [btrfs] flush_space+0x288/0x328 [btrfs] btrfs_async_reclaim_data_space+0x180/0x228 [btrfs] process_one_work+0x228/0x680 worker_thread+0x1bc/0x360 kthread+0x100/0x118 ret_from_fork+0x10/0x20 ---[ end trace 0000000000000000 ]--- BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1605632 OE len=16384 to_dec=16384 left=0 BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1622016 OE len=12288 to_dec=12288 left=0 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 BTRFS critical (device dm-3): bad ordered extent accounting, root=4957 ino=257 OE offset=1634304 OE len=8192 to_dec=4096 left=0 CPU: 1 UID: 0 PID: 3286940 Comm: kworker/u24:3 Tainted: G W OE 6.13.0-rc1-custom+ #89 Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 Workqueue: btrfs_work_helper [btrfs] (btrfs-endio-write) pstate: 404000c5 (nZcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : process_one_work+0x110/0x680 lr : worker_thread+0x1bc/0x360 Call trace: process_one_work+0x110/0x680 (P) worker_thread+0x1bc/0x360 (L) worker_thread+0x1bc/0x360 kthread+0x100/0x118 ret_from_fork+0x10/0x20 Code: f84086a1 f9000fe1 53041c21 b9003361 (f9400661) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs SMP: failed to stop secondary CPUs 2-3 Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: 0x275bb9540000 from 0xffff800080000000 PHYS_OFFSET: 0xffff8fbba0000000 CPU features: 0x100,00000070,00801250,8201720b [CAUSE] The above warning is triggered immediately after the delalloc range failure, this happens in the following sequence: - Range [1568K, 1636K) is dirty 1536K 1568K 1600K 1636K 1664K | |/////////|////////| | Where 1536K, 1600K and 1664K are page boundaries (64K page size) - Enter extent_writepage() for page 1536K - Enter run_delalloc_nocow() with locke ---truncated---
CVE-2024-58093: In the Linux kernel, the following vulnerability has been resolved: PCI/ASPM: Fix link state exit during switch upstream function removal Before 456d8aa37d0f ("PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free"), we would free the ASPM link only after the last function on the bus pertaining to the given link was removed. That was too late. If function 0 is removed before sibling function, link->downstream would point to free'd memory after. After above change, we freed the ASPM parent link state upon any function removal on the bus pertaining to a given link. That is too early. If the link is to a PCIe switch with MFD on the upstream port, then removing functions other than 0 first would free a link which still remains parent_link to the remaining downstream ports. The resulting GPFs are especially frequent during hot-unplug, because pciehp removes devices on the link bus in reverse order. On that switch, function 0 is the virtual P2P bridge to the internal bus. Free exactly when function 0 is removed -- before the parent link is obsolete, but after all subordinate links are gone. [kwilczynski: commit log]
CVE-2024-58094: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before truncation in jfs_truncate_nolock() Added a check for "read-only" mode in the `jfs_truncate_nolock` function to avoid errors related to writing to a read-only filesystem. Call stack: block_write_begin() { jfs_write_failed() { jfs_truncate() { jfs_truncate_nolock() { txEnd() { ... log = JFS_SBI(tblk->sb)->log; // (log == NULL) If the `isReadOnly(ip)` condition is triggered in `jfs_truncate_nolock`, the function execution will stop, and no further data modification will occur. Instead, the `xtTruncate` function will be called with the "COMMIT_WMAP" flag, preventing modifications in "read-only" mode.
CVE-2024-58095: In the Linux kernel, the following vulnerability has been resolved: jfs: add check read-only before txBeginAnon() call Added a read-only check before calling `txBeginAnon` in `extAlloc` and `extRecord`. This prevents modification attempts on a read-only mounted filesystem, avoiding potential errors or crashes. Call trace: txBeginAnon+0xac/0x154 extAlloc+0xe8/0xdec fs/jfs/jfs_extent.c:78 jfs_get_block+0x340/0xb98 fs/jfs/inode.c:248 __block_write_begin_int+0x580/0x166c fs/buffer.c:2128 __block_write_begin fs/buffer.c:2177 [inline] block_write_begin+0x98/0x11c fs/buffer.c:2236 jfs_write_begin+0x44/0x88 fs/jfs/inode.c:299
CVE-2024-58096: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: add srng->lock for ath11k_hal_srng_* in monitor mode ath11k_hal_srng_* should be used with srng->lock to protect srng data. For ath11k_dp_rx_mon_dest_process() and ath11k_dp_full_mon_process_rx(), they use ath11k_hal_srng_* for many times but never call srng->lock. So when running (full) monitor mode, warning will occur: RIP: 0010:ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k] Call Trace: ? ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k] ath11k_dp_rx_process_mon_status+0xc45/0x1190 [ath11k] ? idr_alloc_u32+0x97/0xd0 ath11k_dp_rx_process_mon_rings+0x32a/0x550 [ath11k] ath11k_dp_service_srng+0x289/0x5a0 [ath11k] ath11k_pcic_ext_grp_napi_poll+0x30/0xd0 [ath11k] __napi_poll+0x30/0x1f0 net_rx_action+0x198/0x320 __do_softirq+0xdd/0x319 So add srng->lock for them to avoid such warnings. Inorder to fetch the srng->lock, should change srng's definition from 'void' to 'struct hal_srng'. And initialize them elsewhere to prevent one line of code from being too long. This is consistent with other ring process functions, such as ath11k_dp_process_rx(). Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2024-58097: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix RCU stall while reaping monitor destination ring While processing the monitor destination ring, MSDUs are reaped from the link descriptor based on the corresponding buf_id. However, sometimes the driver cannot obtain a valid buffer corresponding to the buf_id received from the hardware. This causes an infinite loop in the destination processing, resulting in a kernel crash. kernel log: ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309 ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309 ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed Fix this by skipping the problematic buf_id and reaping the next entry, replacing the break with the next MSDU processing. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30 Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
CVE-2024-58098: In the Linux kernel, the following vulnerability has been resolved: bpf: track changes_pkt_data property for global functions When processing calls to certain helpers, verifier invalidates all packet pointers in a current state. For example, consider the following program: __attribute__((__noinline__)) long skb_pull_data(struct __sk_buff *sk, __u32 len) { return bpf_skb_pull_data(sk, len); } SEC("tc") int test_invalidate_checks(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP; skb_pull_data(sk, 0); *p = 42; return TCX_PASS; } After a call to bpf_skb_pull_data() the pointer 'p' can't be used safely. See function filter.c:bpf_helper_changes_pkt_data() for a list of such helpers. At the moment verifier invalidates packet pointers when processing helper function calls, and does not traverse global sub-programs when processing calls to global sub-programs. This means that calls to helpers done from global sub-programs do not invalidate pointers in the caller state. E.g. the program above is unsafe, but is not rejected by verifier. This commit fixes the omission by computing field bpf_subprog_info->changes_pkt_data for each sub-program before main verification pass. changes_pkt_data should be set if: - subprogram calls helper for which bpf_helper_changes_pkt_data returns true; - subprogram calls a global function, for which bpf_subprog_info->changes_pkt_data should be set. The verifier.c:check_cfg() pass is modified to compute this information. The commit relies on depth first instruction traversal done by check_cfg() and absence of recursive function calls: - check_cfg() would eventually visit every call to subprogram S in a state when S is fully explored; - when S is fully explored: - every direct helper call within S is explored (and thus changes_pkt_data is set if needed); - every call to subprogram S1 called by S was visited with S1 fully explored (and thus S inherits changes_pkt_data from S1). The downside of such approach is that dead code elimination is not taken into account: if a helper call inside global function is dead because of current configuration, verifier would conservatively assume that the call occurs for the purpose of the changes_pkt_data computation.
CVE-2024-58100: In the Linux kernel, the following vulnerability has been resolved: bpf: check changes_pkt_data property for extension programs When processing calls to global sub-programs, verifier decides whether to invalidate all packet pointers in current state depending on the changes_pkt_data property of the global sub-program. Because of this, an extension program replacing a global sub-program must be compatible with changes_pkt_data property of the sub-program being replaced. This commit: - adds changes_pkt_data flag to struct bpf_prog_aux: - this flag is set in check_cfg() for main sub-program; - in jit_subprogs() for other sub-programs; - modifies bpf_check_attach_btf_id() to check changes_pkt_data flag; - moves call to check_attach_btf_id() after the call to check_cfg(), because it needs changes_pkt_data flag to be set: bpf_check: ... ... - check_attach_btf_id resolve_pseudo_ldimm64 resolve_pseudo_ldimm64 --> bpf_prog_is_offloaded bpf_prog_is_offloaded check_cfg check_cfg + check_attach_btf_id ... ... The following fields are set by check_attach_btf_id(): - env->ops - prog->aux->attach_btf_trace - prog->aux->attach_func_name - prog->aux->attach_func_proto - prog->aux->dst_trampoline - prog->aux->mod - prog->aux->saved_dst_attach_type - prog->aux->saved_dst_prog_type - prog->expected_attach_type Neither of these fields are used by resolve_pseudo_ldimm64() or bpf_prog_offload_verifier_prep() (for netronome and netdevsim drivers), so the reordering is safe.
CVE-2024-58237: In the Linux kernel, the following vulnerability has been resolved: bpf: consider that tail calls invalidate packet pointers Tail-called programs could execute any of the helpers that invalidate packet pointers. Hence, conservatively assume that each tail call invalidates packet pointers. Making the change in bpf_helper_changes_pkt_data() automatically makes use of check_cfg() logic that computes 'changes_pkt_data' effect for global sub-programs, such that the following program could be rejected: int tail_call(struct __sk_buff *sk) { bpf_tail_call_static(sk, &jmp_table, 0); return 0; } SEC("tc") int not_safe(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; ... make p valid ... tail_call(sk); *p = 42; /* this is unsafe */ ... } The tc_bpf2bpf.c:subprog_tc() needs change: mark it as a function that can invalidate packet pointers. Otherwise, it can't be freplaced with tailcall_freplace.c:entry_freplace() that does a tail call.
CVE-2024-58241: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: Disable works on hci_unregister_dev This make use of disable_work_* on hci_unregister_dev since the hci_dev is about to be freed new submissions are not disarable.
CVE-2025-21634: In the Linux kernel, the following vulnerability has been resolved: cgroup/cpuset: remove kernfs active break A warning was found: WARNING: CPU: 10 PID: 3486953 at fs/kernfs/file.c:828 CPU: 10 PID: 3486953 Comm: rmdir Kdump: loaded Tainted: G RIP: 0010:kernfs_should_drain_open_files+0x1a1/0x1b0 RSP: 0018:ffff8881107ef9e0 EFLAGS: 00010202 RAX: 0000000080000002 RBX: ffff888154738c00 RCX: dffffc0000000000 RDX: 0000000000000007 RSI: 0000000000000004 RDI: ffff888154738c04 RBP: ffff888154738c04 R08: ffffffffaf27fa15 R09: ffffed102a8e7180 R10: ffff888154738c07 R11: 0000000000000000 R12: ffff888154738c08 R13: ffff888750f8c000 R14: ffff888750f8c0e8 R15: ffff888154738ca0 FS: 00007f84cd0be740(0000) GS:ffff8887ddc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555f9fbe00c8 CR3: 0000000153eec001 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: kernfs_drain+0x15e/0x2f0 __kernfs_remove+0x165/0x300 kernfs_remove_by_name_ns+0x7b/0xc0 cgroup_rm_file+0x154/0x1c0 cgroup_addrm_files+0x1c2/0x1f0 css_clear_dir+0x77/0x110 kill_css+0x4c/0x1b0 cgroup_destroy_locked+0x194/0x380 cgroup_rmdir+0x2a/0x140 It can be explained by: rmdir echo 1 > cpuset.cpus kernfs_fop_write_iter // active=0 cgroup_rm_file kernfs_remove_by_name_ns kernfs_get_active // active=1 __kernfs_remove // active=0x80000002 kernfs_drain cpuset_write_resmask wait_event //waiting (active == 0x80000001) kernfs_break_active_protection // active = 0x80000001 // continue kernfs_unbreak_active_protection // active = 0x80000002 ... kernfs_should_drain_open_files // warning occurs kernfs_put_active This warning is caused by 'kernfs_break_active_protection' when it is writing to cpuset.cpus, and the cgroup is removed concurrently. The commit 3a5a6d0c2b03 ("cpuset: don't nest cgroup_mutex inside get_online_cpus()") made cpuset_hotplug_workfn asynchronous, This change involves calling flush_work(), which can create a multiple processes circular locking dependency that involve cgroup_mutex, potentially leading to a deadlock. To avoid deadlock. the commit 76bb5ab8f6e3 ("cpuset: break kernfs active protection in cpuset_write_resmask()") added 'kernfs_break_active_protection' in the cpuset_write_resmask. This could lead to this warning. After the commit 2125c0034c5d ("cgroup/cpuset: Make cpuset hotplug processing synchronous"), the cpuset_write_resmask no longer needs to wait the hotplug to finish, which means that concurrent hotplug and cpuset operations are no longer possible. Therefore, the deadlock doesn't exist anymore and it does not have to 'break active protection' now. To fix this warning, just remove kernfs_break_active_protection operation in the 'cpuset_write_resmask'.
CVE-2025-21635: In the Linux kernel, the following vulnerability has been resolved: rds: sysctl: rds_tcp_{rcv,snd}buf: avoid using current->nsproxy As mentioned in a previous commit of this series, using the 'net' structure via 'current' is not recommended for different reasons: - Inconsistency: getting info from the reader's/writer's netns vs only from the opener's netns. - current->nsproxy can be NULL in some cases, resulting in an 'Oops' (null-ptr-deref), e.g. when the current task is exiting, as spotted by syzbot [1] using acct(2). The per-netns structure can be obtained from the table->data using container_of(), then the 'net' one can be retrieved from the listen socket (if available).
CVE-2025-21649: In the Linux kernel, the following vulnerability has been resolved: net: hns3: fix kernel crash when 1588 is sent on HIP08 devices Currently, HIP08 devices does not register the ptp devices, so the hdev->ptp is NULL. But the tx process would still try to set hardware time stamp info with SKBTX_HW_TSTAMP flag and cause a kernel crash. [ 128.087798] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000018 ... [ 128.280251] pc : hclge_ptp_set_tx_info+0x2c/0x140 [hclge] [ 128.286600] lr : hclge_ptp_set_tx_info+0x20/0x140 [hclge] [ 128.292938] sp : ffff800059b93140 [ 128.297200] x29: ffff800059b93140 x28: 0000000000003280 [ 128.303455] x27: ffff800020d48280 x26: ffff0cb9dc814080 [ 128.309715] x25: ffff0cb9cde93fa0 x24: 0000000000000001 [ 128.315969] x23: 0000000000000000 x22: 0000000000000194 [ 128.322219] x21: ffff0cd94f986000 x20: 0000000000000000 [ 128.328462] x19: ffff0cb9d2a166c0 x18: 0000000000000000 [ 128.334698] x17: 0000000000000000 x16: ffffcf1fc523ed24 [ 128.340934] x15: 0000ffffd530a518 x14: 0000000000000000 [ 128.347162] x13: ffff0cd6bdb31310 x12: 0000000000000368 [ 128.353388] x11: ffff0cb9cfbc7070 x10: ffff2cf55dd11e02 [ 128.359606] x9 : ffffcf1f85a212b4 x8 : ffff0cd7cf27dab0 [ 128.365831] x7 : 0000000000000a20 x6 : ffff0cd7cf27d000 [ 128.372040] x5 : 0000000000000000 x4 : 000000000000ffff [ 128.378243] x3 : 0000000000000400 x2 : ffffcf1f85a21294 [ 128.384437] x1 : ffff0cb9db520080 x0 : ffff0cb9db500080 [ 128.390626] Call trace: [ 128.393964] hclge_ptp_set_tx_info+0x2c/0x140 [hclge] [ 128.399893] hns3_nic_net_xmit+0x39c/0x4c4 [hns3] [ 128.405468] xmit_one.constprop.0+0xc4/0x200 [ 128.410600] dev_hard_start_xmit+0x54/0xf0 [ 128.415556] sch_direct_xmit+0xe8/0x634 [ 128.420246] __dev_queue_xmit+0x224/0xc70 [ 128.425101] dev_queue_xmit+0x1c/0x40 [ 128.429608] ovs_vport_send+0xac/0x1a0 [openvswitch] [ 128.435409] do_output+0x60/0x17c [openvswitch] [ 128.440770] do_execute_actions+0x898/0x8c4 [openvswitch] [ 128.446993] ovs_execute_actions+0x64/0xf0 [openvswitch] [ 128.453129] ovs_dp_process_packet+0xa0/0x224 [openvswitch] [ 128.459530] ovs_vport_receive+0x7c/0xfc [openvswitch] [ 128.465497] internal_dev_xmit+0x34/0xb0 [openvswitch] [ 128.471460] xmit_one.constprop.0+0xc4/0x200 [ 128.476561] dev_hard_start_xmit+0x54/0xf0 [ 128.481489] __dev_queue_xmit+0x968/0xc70 [ 128.486330] dev_queue_xmit+0x1c/0x40 [ 128.490856] ip_finish_output2+0x250/0x570 [ 128.495810] __ip_finish_output+0x170/0x1e0 [ 128.500832] ip_finish_output+0x3c/0xf0 [ 128.505504] ip_output+0xbc/0x160 [ 128.509654] ip_send_skb+0x58/0xd4 [ 128.513892] udp_send_skb+0x12c/0x354 [ 128.518387] udp_sendmsg+0x7a8/0x9c0 [ 128.522793] inet_sendmsg+0x4c/0x8c [ 128.527116] __sock_sendmsg+0x48/0x80 [ 128.531609] __sys_sendto+0x124/0x164 [ 128.536099] __arm64_sys_sendto+0x30/0x5c [ 128.540935] invoke_syscall+0x50/0x130 [ 128.545508] el0_svc_common.constprop.0+0x10c/0x124 [ 128.551205] do_el0_svc+0x34/0xdc [ 128.555347] el0_svc+0x20/0x30 [ 128.559227] el0_sync_handler+0xb8/0xc0 [ 128.563883] el0_sync+0x160/0x180
CVE-2025-21651: In the Linux kernel, the following vulnerability has been resolved: net: hns3: don't auto enable misc vector Currently, there is a time window between misc irq enabled and service task inited. If an interrupte is reported at this time, it will cause warning like below: [ 16.324639] Call trace: [ 16.324641] __queue_delayed_work+0xb8/0xe0 [ 16.324643] mod_delayed_work_on+0x78/0xd0 [ 16.324655] hclge_errhand_task_schedule+0x58/0x90 [hclge] [ 16.324662] hclge_misc_irq_handle+0x168/0x240 [hclge] [ 16.324666] __handle_irq_event_percpu+0x64/0x1e0 [ 16.324667] handle_irq_event+0x80/0x170 [ 16.324670] handle_fasteoi_edge_irq+0x110/0x2bc [ 16.324671] __handle_domain_irq+0x84/0xfc [ 16.324673] gic_handle_irq+0x88/0x2c0 [ 16.324674] el1_irq+0xb8/0x140 [ 16.324677] arch_cpu_idle+0x18/0x40 [ 16.324679] default_idle_call+0x5c/0x1bc [ 16.324682] cpuidle_idle_call+0x18c/0x1c4 [ 16.324684] do_idle+0x174/0x17c [ 16.324685] cpu_startup_entry+0x30/0x6c [ 16.324687] secondary_start_kernel+0x1a4/0x280 [ 16.324688] ---[ end trace 6aa0bff672a964aa ]--- So don't auto enable misc vector when request irq..
CVE-2025-21656: In the Linux kernel, the following vulnerability has been resolved: hwmon: (drivetemp) Fix driver producing garbage data when SCSI errors occur scsi_execute_cmd() function can return both negative (linux codes) and positive (scsi_cmnd result field) error codes. Currently the driver just passes error codes of scsi_execute_cmd() to hwmon core, which is incorrect because hwmon only checks for negative error codes. This leads to hwmon reporting uninitialized data to userspace in case of SCSI errors (for example if the disk drive was disconnected). This patch checks scsi_execute_cmd() output and returns -EIO if it's error code is positive. [groeck: Avoid inline variable declaration for portability]
CVE-2025-21658: In the Linux kernel, the following vulnerability has been resolved: btrfs: avoid NULL pointer dereference if no valid extent tree [BUG] Syzbot reported a crash with the following call trace: BTRFS info (device loop0): scrub: started on devid 1 BUG: kernel NULL pointer dereference, address: 0000000000000208 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 106e70067 P4D 106e70067 PUD 107143067 PMD 0 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 UID: 0 PID: 689 Comm: repro Kdump: loaded Tainted: G O 6.13.0-rc4-custom+ #206 Tainted: [O]=OOT_MODULE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022 RIP: 0010:find_first_extent_item+0x26/0x1f0 [btrfs] Call Trace: <TASK> scrub_find_fill_first_stripe+0x13d/0x3b0 [btrfs] scrub_simple_mirror+0x175/0x260 [btrfs] scrub_stripe+0x5d4/0x6c0 [btrfs] scrub_chunk+0xbb/0x170 [btrfs] scrub_enumerate_chunks+0x2f4/0x5f0 [btrfs] btrfs_scrub_dev+0x240/0x600 [btrfs] btrfs_ioctl+0x1dc8/0x2fa0 [btrfs] ? do_sys_openat2+0xa5/0xf0 __x64_sys_ioctl+0x97/0xc0 do_syscall_64+0x4f/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e </TASK> [CAUSE] The reproducer is using a corrupted image where extent tree root is corrupted, thus forcing to use "rescue=all,ro" mount option to mount the image. Then it triggered a scrub, but since scrub relies on extent tree to find where the data/metadata extents are, scrub_find_fill_first_stripe() relies on an non-empty extent root. But unfortunately scrub_find_fill_first_stripe() doesn't really expect an NULL pointer for extent root, it use extent_root to grab fs_info and triggered a NULL pointer dereference. [FIX] Add an extra check for a valid extent root at the beginning of scrub_find_fill_first_stripe(). The new error path is introduced by 42437a6386ff ("btrfs: introduce mount option rescue=ignorebadroots"), but that's pretty old, and later commit b979547513ff ("btrfs: scrub: introduce helper to find and fill sector info for a scrub_stripe") changed how we do scrub. So for kernels older than 6.6, the fix will need manual backport.
CVE-2025-21673: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix double free of TCP_Server_Info::hostname When shutting down the server in cifs_put_tcp_session(), cifsd thread might be reconnecting to multiple DFS targets before it realizes it should exit the loop, so @server->hostname can't be freed as long as cifsd thread isn't done. Otherwise the following can happen: RIP: 0010:__slab_free+0x223/0x3c0 Code: 5e 41 5f c3 cc cc cc cc 4c 89 de 4c 89 cf 44 89 44 24 08 4c 89 1c 24 e8 fb cf 8e 00 44 8b 44 24 08 4c 8b 1c 24 e9 5f fe ff ff <0f> 0b 41 f7 45 08 00 0d 21 00 0f 85 2d ff ff ff e9 1f ff ff ff 80 RSP: 0018:ffffb26180dbfd08 EFLAGS: 00010246 RAX: ffff8ea34728e510 RBX: ffff8ea34728e500 RCX: 0000000000800068 RDX: 0000000000800068 RSI: 0000000000000000 RDI: ffff8ea340042400 RBP: ffffe112041ca380 R08: 0000000000000001 R09: 0000000000000000 R10: 6170732e31303000 R11: 70726f632e786563 R12: ffff8ea34728e500 R13: ffff8ea340042400 R14: ffff8ea34728e500 R15: 0000000000800068 FS: 0000000000000000(0000) GS:ffff8ea66fd80000(0000) 000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffc25376080 CR3: 000000012a2ba001 CR4: PKRU: 55555554 Call Trace: <TASK> ? show_trace_log_lvl+0x1c4/0x2df ? show_trace_log_lvl+0x1c4/0x2df ? __reconnect_target_unlocked+0x3e/0x160 [cifs] ? __die_body.cold+0x8/0xd ? die+0x2b/0x50 ? do_trap+0xce/0x120 ? __slab_free+0x223/0x3c0 ? do_error_trap+0x65/0x80 ? __slab_free+0x223/0x3c0 ? exc_invalid_op+0x4e/0x70 ? __slab_free+0x223/0x3c0 ? asm_exc_invalid_op+0x16/0x20 ? __slab_free+0x223/0x3c0 ? extract_hostname+0x5c/0xa0 [cifs] ? extract_hostname+0x5c/0xa0 [cifs] ? __kmalloc+0x4b/0x140 __reconnect_target_unlocked+0x3e/0x160 [cifs] reconnect_dfs_server+0x145/0x430 [cifs] cifs_handle_standard+0x1ad/0x1d0 [cifs] cifs_demultiplex_thread+0x592/0x730 [cifs] ? __pfx_cifs_demultiplex_thread+0x10/0x10 [cifs] kthread+0xdd/0x100 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x29/0x50 </TASK>
CVE-2025-21676: In the Linux kernel, the following vulnerability has been resolved: net: fec: handle page_pool_dev_alloc_pages error The fec_enet_update_cbd function calls page_pool_dev_alloc_pages but did not handle the case when it returned NULL. There was a WARN_ON(!new_page) but it would still proceed to use the NULL pointer and then crash. This case does seem somewhat rare but when the system is under memory pressure it can happen. One case where I can duplicate this with some frequency is when writing over a smbd share to a SATA HDD attached to an imx6q. Setting /proc/sys/vm/min_free_kbytes to higher values also seems to solve the problem for my test case. But it still seems wrong that the fec driver ignores the memory allocation error and can crash. This commit handles the allocation error by dropping the current packet.
CVE-2025-21682: In the Linux kernel, the following vulnerability has been resolved: eth: bnxt: always recalculate features after XDP clearing, fix null-deref Recalculate features when XDP is detached. Before: # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp # ip li set dev eth0 xdp off # ethtool -k eth0 | grep gro rx-gro-hw: off [requested on] After: # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp # ip li set dev eth0 xdp off # ethtool -k eth0 | grep gro rx-gro-hw: on The fact that HW-GRO doesn't get re-enabled automatically is just a minor annoyance. The real issue is that the features will randomly come back during another reconfiguration which just happens to invoke netdev_update_features(). The driver doesn't handle reconfiguring two things at a time very robustly. Starting with commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in __bnxt_reserve_rings()") we only reconfigure the RSS hash table if the "effective" number of Rx rings has changed. If HW-GRO is enabled "effective" number of rings is 2x what user sees. So if we are in the bad state, with HW-GRO re-enablement "pending" after XDP off, and we lower the rings by / 2 - the HW-GRO rings doing 2x and the ethtool -L doing / 2 may cancel each other out, and the: if (old_rx_rings != bp->hw_resc.resv_rx_rings && condition in __bnxt_reserve_rings() will be false. The RSS map won't get updated, and we'll crash with: BUG: kernel NULL pointer dereference, address: 0000000000000168 RIP: 0010:__bnxt_hwrm_vnic_set_rss+0x13a/0x1a0 bnxt_hwrm_vnic_rss_cfg_p5+0x47/0x180 __bnxt_setup_vnic_p5+0x58/0x110 bnxt_init_nic+0xb72/0xf50 __bnxt_open_nic+0x40d/0xab0 bnxt_open_nic+0x2b/0x60 ethtool_set_channels+0x18c/0x1d0 As we try to access a freed ring. The issue is present since XDP support was added, really, but prior to commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in __bnxt_reserve_rings()") it wasn't causing major issues.
CVE-2025-21693: In the Linux kernel, the following vulnerability has been resolved: mm: zswap: properly synchronize freeing resources during CPU hotunplug In zswap_compress() and zswap_decompress(), the per-CPU acomp_ctx of the current CPU at the beginning of the operation is retrieved and used throughout. However, since neither preemption nor migration are disabled, it is possible that the operation continues on a different CPU. If the original CPU is hotunplugged while the acomp_ctx is still in use, we run into a UAF bug as some of the resources attached to the acomp_ctx are freed during hotunplug in zswap_cpu_comp_dead() (i.e. acomp_ctx.buffer, acomp_ctx.req, or acomp_ctx.acomp). The problem was introduced in commit 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration") when the switch to the crypto_acomp API was made. Prior to that, the per-CPU crypto_comp was retrieved using get_cpu_ptr() which disables preemption and makes sure the CPU cannot go away from under us. Preemption cannot be disabled with the crypto_acomp API as a sleepable context is needed. Use the acomp_ctx.mutex to synchronize CPU hotplug callbacks allocating and freeing resources with compression/decompression paths. Make sure that acomp_ctx.req is NULL when the resources are freed. In the compression/decompression paths, check if acomp_ctx.req is NULL after acquiring the mutex (meaning the CPU was offlined) and retry on the new CPU. The initialization of acomp_ctx.mutex is moved from the CPU hotplug callback to the pool initialization where it belongs (where the mutex is allocated). In addition to adding clarity, this makes sure that CPU hotplug cannot reinitialize a mutex that is already locked by compression/decompression. Previously a fix was attempted by holding cpus_read_lock() [1]. This would have caused a potential deadlock as it is possible for code already holding the lock to fall into reclaim and enter zswap (causing a deadlock). A fix was also attempted using SRCU for synchronization, but Johannes pointed out that synchronize_srcu() cannot be used in CPU hotplug notifiers [2]. Alternative fixes that were considered/attempted and could have worked: - Refcounting the per-CPU acomp_ctx. This involves complexity in handling the race between the refcount dropping to zero in zswap_[de]compress() and the refcount being re-initialized when the CPU is onlined. - Disabling migration before getting the per-CPU acomp_ctx [3], but that's discouraged and is a much bigger hammer than needed, and could result in subtle performance issues. [1]https://lkml.kernel.org/20241219212437.2714151-1-yosryahmed@google.com/ [2]https://lkml.kernel.org/20250107074724.1756696-2-yosryahmed@google.com/ [3]https://lkml.kernel.org/20250107222236.2715883-2-yosryahmed@google.com/ [yosryahmed@google.com: remove comment]
CVE-2025-21696: In the Linux kernel, the following vulnerability has been resolved: mm: clear uffd-wp PTE/PMD state on mremap() When mremap()ing a memory region previously registered with userfaultfd as write-protected but without UFFD_FEATURE_EVENT_REMAP, an inconsistency in flag clearing leads to a mismatch between the vma flags (which have uffd-wp cleared) and the pte/pmd flags (which do not have uffd-wp cleared). This mismatch causes a subsequent mprotect(PROT_WRITE) to trigger a warning in page_table_check_pte_flags() due to setting the pte to writable while uffd-wp is still set. Fix this by always explicitly clearing the uffd-wp pte/pmd flags on any such mremap() so that the values are consistent with the existing clearing of VM_UFFD_WP. Be careful to clear the logical flag regardless of its physical form; a PTE bit, a swap PTE bit, or a PTE marker. Cover PTE, huge PMD and hugetlb paths.
CVE-2025-21714: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix implicit ODP use after free Prevent double queueing of implicit ODP mr destroy work by using __xa_cmpxchg() to make sure this is the only time we are destroying this specific mr. Without this change, we could try to invalidate this mr twice, which in turn could result in queuing a MR work destroy twice, and eventually the second work could execute after the MR was freed due to the first work, causing a user after free and trace below. refcount_t: underflow; use-after-free. WARNING: CPU: 2 PID: 12178 at lib/refcount.c:28 refcount_warn_saturate+0x12b/0x130 Modules linked in: bonding ib_ipoib vfio_pci ip_gre geneve nf_tables ip6_gre gre ip6_tunnel tunnel6 ipip tunnel4 ib_umad rdma_ucm mlx5_vfio_pci vfio_pci_core vfio_iommu_type1 mlx5_ib vfio ib_uverbs mlx5_core iptable_raw openvswitch nsh rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay zram zsmalloc fuse [last unloaded: ib_uverbs] CPU: 2 PID: 12178 Comm: kworker/u20:5 Not tainted 6.5.0-rc1_net_next_mlx5_58c644e #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: events_unbound free_implicit_child_mr_work [mlx5_ib] RIP: 0010:refcount_warn_saturate+0x12b/0x130 Code: 48 c7 c7 38 95 2a 82 c6 05 bc c6 fe 00 01 e8 0c 66 aa ff 0f 0b 5b c3 48 c7 c7 e0 94 2a 82 c6 05 a7 c6 fe 00 01 e8 f5 65 aa ff <0f> 0b 5b c3 90 8b 07 3d 00 00 00 c0 74 12 83 f8 01 74 13 8d 50 ff RSP: 0018:ffff8881008e3e40 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000027 RDX: ffff88852c91b5c8 RSI: 0000000000000001 RDI: ffff88852c91b5c0 RBP: ffff8881dacd4e00 R08: 00000000ffffffff R09: 0000000000000019 R10: 000000000000072e R11: 0000000063666572 R12: ffff88812bfd9e00 R13: ffff8881c792d200 R14: ffff88810011c005 R15: ffff8881002099c0 FS: 0000000000000000(0000) GS:ffff88852c900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f5694b5e000 CR3: 00000001153f6003 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? refcount_warn_saturate+0x12b/0x130 free_implicit_child_mr_work+0x180/0x1b0 [mlx5_ib] process_one_work+0x1cc/0x3c0 worker_thread+0x218/0x3c0 kthread+0xc6/0xf0 ret_from_fork+0x1f/0x30 </TASK>
CVE-2025-21723: In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Fix possible crash when setting up bsg fails If bsg_setup_queue() fails, the bsg_queue is assigned a non-NULL value. Consequently, in mpi3mr_bsg_exit(), the condition "if(!mrioc->bsg_queue)" will not be satisfied, preventing execution from entering bsg_remove_queue(), which could lead to the following crash: BUG: kernel NULL pointer dereference, address: 000000000000041c Call Trace: <TASK> mpi3mr_bsg_exit+0x1f/0x50 [mpi3mr] mpi3mr_remove+0x6f/0x340 [mpi3mr] pci_device_remove+0x3f/0xb0 device_release_driver_internal+0x19d/0x220 unbind_store+0xa4/0xb0 kernfs_fop_write_iter+0x11f/0x200 vfs_write+0x1fc/0x3e0 ksys_write+0x67/0xe0 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x78/0xe2
CVE-2025-21729: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw89: fix race between cancel_hw_scan and hw_scan completion The rtwdev->scanning flag isn't protected by mutex originally, so cancel_hw_scan can pass the condition, but suddenly hw_scan completion unset the flag and calls ieee80211_scan_completed() that will free local->hw_scan_req. Then, cancel_hw_scan raises null-ptr-deref and use-after-free. Fix it by moving the check condition to where protected by mutex. KASAN: null-ptr-deref in range [0x0000000000000088-0x000000000000008f] CPU: 2 PID: 6922 Comm: kworker/2:2 Tainted: G OE Hardware name: LENOVO 2356AD1/2356AD1, BIOS G7ETB6WW (2.76 ) 09/10/2019 Workqueue: events cfg80211_conn_work [cfg80211] RIP: 0010:rtw89_fw_h2c_scan_offload_be+0xc33/0x13c3 [rtw89_core] Code: 00 45 89 6c 24 1c 0f 85 23 01 00 00 48 8b 85 20 ff ff ff 48 8d RSP: 0018:ffff88811fd9f068 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: ffff88811fd9f258 RCX: 0000000000000001 RDX: 0000000000000011 RSI: 0000000000000001 RDI: 0000000000000089 RBP: ffff88811fd9f170 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88811fd9f108 R11: 0000000000000000 R12: ffff88810e47f960 R13: 0000000000000000 R14: 000000000000ffff R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8881d6f00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007531dfca55b0 CR3: 00000001be296004 CR4: 00000000001706e0 Call Trace: <TASK> ? show_regs+0x61/0x73 ? __die_body+0x20/0x73 ? die_addr+0x4f/0x7b ? exc_general_protection+0x191/0x1db ? asm_exc_general_protection+0x27/0x30 ? rtw89_fw_h2c_scan_offload_be+0xc33/0x13c3 [rtw89_core] ? rtw89_fw_h2c_scan_offload_be+0x458/0x13c3 [rtw89_core] ? __pfx_rtw89_fw_h2c_scan_offload_be+0x10/0x10 [rtw89_core] ? do_raw_spin_lock+0x75/0xdb ? __pfx_do_raw_spin_lock+0x10/0x10 rtw89_hw_scan_offload+0xb5e/0xbf7 [rtw89_core] ? _raw_spin_unlock+0xe/0x24 ? __mutex_lock.constprop.0+0x40c/0x471 ? __pfx_rtw89_hw_scan_offload+0x10/0x10 [rtw89_core] ? __mutex_lock_slowpath+0x13/0x1f ? mutex_lock+0xa2/0xdc ? __pfx_mutex_lock+0x10/0x10 rtw89_hw_scan_abort+0x58/0xb7 [rtw89_core] rtw89_ops_cancel_hw_scan+0x120/0x13b [rtw89_core] ieee80211_scan_cancel+0x468/0x4d0 [mac80211] ieee80211_prep_connection+0x858/0x899 [mac80211] ieee80211_mgd_auth+0xbea/0xdde [mac80211] ? __pfx_ieee80211_mgd_auth+0x10/0x10 [mac80211] ? cfg80211_find_elem+0x15/0x29 [cfg80211] ? is_bss+0x1b7/0x1d7 [cfg80211] ieee80211_auth+0x18/0x27 [mac80211] cfg80211_mlme_auth+0x3bb/0x3e7 [cfg80211] cfg80211_conn_do_work+0x410/0xb81 [cfg80211] ? __pfx_cfg80211_conn_do_work+0x10/0x10 [cfg80211] ? __kasan_check_read+0x11/0x1f ? psi_group_change+0x8bc/0x944 ? __kasan_check_write+0x14/0x22 ? mutex_lock+0x8e/0xdc ? __pfx_mutex_lock+0x10/0x10 ? __pfx___radix_tree_lookup+0x10/0x10 cfg80211_conn_work+0x245/0x34d [cfg80211] ? __pfx_cfg80211_conn_work+0x10/0x10 [cfg80211] ? update_cfs_rq_load_avg+0x3bc/0x3d7 ? sched_clock_noinstr+0x9/0x1a ? sched_clock+0x10/0x24 ? sched_clock_cpu+0x7e/0x42e ? newidle_balance+0x796/0x937 ? __pfx_sched_clock_cpu+0x10/0x10 ? __pfx_newidle_balance+0x10/0x10 ? __kasan_check_read+0x11/0x1f ? psi_group_change+0x8bc/0x944 ? _raw_spin_unlock+0xe/0x24 ? raw_spin_rq_unlock+0x47/0x54 ? raw_spin_rq_unlock_irq+0x9/0x1f ? finish_task_switch.isra.0+0x347/0x586 ? __schedule+0x27bf/0x2892 ? mutex_unlock+0x80/0xd0 ? do_raw_spin_lock+0x75/0xdb ? __pfx___schedule+0x10/0x10 process_scheduled_works+0x58c/0x821 worker_thread+0x4c7/0x586 ? __kasan_check_read+0x11/0x1f kthread+0x285/0x294 ? __pfx_worker_thread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x29/0x6f ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK>
CVE-2025-21732: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix a race for an ODP MR which leads to CQE with error This patch addresses a race condition for an ODP MR that can result in a CQE with an error on the UMR QP. During the __mlx5_ib_dereg_mr() flow, the following sequence of calls occurs: mlx5_revoke_mr() mlx5r_umr_revoke_mr() mlx5r_umr_post_send_wait() At this point, the lkey is freed from the hardware's perspective. However, concurrently, mlx5_ib_invalidate_range() might be triggered by another task attempting to invalidate a range for the same freed lkey. This task will: - Acquire the umem_odp->umem_mutex lock. - Call mlx5r_umr_update_xlt() on the UMR QP. - Since the lkey has already been freed, this can lead to a CQE error, causing the UMR QP to enter an error state [1]. To resolve this race condition, the umem_odp->umem_mutex lock is now also acquired as part of the mlx5_revoke_mr() scope. Upon successful revoke, we set umem_odp->private which points to that MR to NULL, preventing any further invalidation attempts on its lkey. [1] From dmesg: infiniband rocep8s0f0: dump_cqe:277:(pid 0): WC error: 6, Message: memory bind operation error cqe_dump: 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 cqe_dump: 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 cqe_dump: 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 cqe_dump: 00000030: 00 00 00 00 08 00 78 06 25 00 11 b9 00 0e dd d2 WARNING: CPU: 15 PID: 1506 at drivers/infiniband/hw/mlx5/umr.c:394 mlx5r_umr_post_send_wait+0x15a/0x2b0 [mlx5_ib] Modules linked in: ip6table_mangle ip6table_natip6table_filter ip6_tables iptable_mangle xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_umad ib_ipoib ib_cm mlx5_ib ib_uverbs ib_core fuse mlx5_core CPU: 15 UID: 0 PID: 1506 Comm: ibv_rc_pingpong Not tainted 6.12.0-rc7+ #1626 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:mlx5r_umr_post_send_wait+0x15a/0x2b0 [mlx5_ib] [..] Call Trace: <TASK> mlx5r_umr_update_xlt+0x23c/0x3e0 [mlx5_ib] mlx5_ib_invalidate_range+0x2e1/0x330 [mlx5_ib] __mmu_notifier_invalidate_range_start+0x1e1/0x240 zap_page_range_single+0xf1/0x1a0 madvise_vma_behavior+0x677/0x6e0 do_madvise+0x1a2/0x4b0 __x64_sys_madvise+0x25/0x30 do_syscall_64+0x6b/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e
CVE-2025-21739: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix use-after free in init error and remove paths devm_blk_crypto_profile_init() registers a cleanup handler to run when the associated (platform-) device is being released. For UFS, the crypto private data and pointers are stored as part of the ufs_hba's data structure 'struct ufs_hba::crypto_profile'. This structure is allocated as part of the underlying ufshcd and therefore Scsi_host allocation. During driver release or during error handling in ufshcd_pltfrm_init(), this structure is released as part of ufshcd_dealloc_host() before the (platform-) device associated with the crypto call above is released. Once this device is released, the crypto cleanup code will run, using the just-released 'struct ufs_hba::crypto_profile'. This causes a use-after-free situation: Call trace: kfree+0x60/0x2d8 (P) kvfree+0x44/0x60 blk_crypto_profile_destroy_callback+0x28/0x70 devm_action_release+0x1c/0x30 release_nodes+0x6c/0x108 devres_release_all+0x98/0x100 device_unbind_cleanup+0x20/0x70 really_probe+0x218/0x2d0 In other words, the initialisation code flow is: platform-device probe ufshcd_pltfrm_init() ufshcd_alloc_host() scsi_host_alloc() allocation of struct ufs_hba creation of scsi-host devices devm_blk_crypto_profile_init() devm registration of cleanup handler using platform-device and during error handling of ufshcd_pltfrm_init() or during driver removal: ufshcd_dealloc_host() scsi_host_put() put_device(scsi-host) release of struct ufs_hba put_device(platform-device) crypto cleanup handler To fix this use-after free, change ufshcd_alloc_host() to register a devres action to automatically cleanup the underlying SCSI device on ufshcd destruction, without requiring explicit calls to ufshcd_dealloc_host(). This way: * the crypto profile and all other ufs_hba-owned resources are destroyed before SCSI (as they've been registered after) * a memleak is plugged in tc-dwc-g210-pci.c remove() as a side-effect * EXPORT_SYMBOL_GPL(ufshcd_dealloc_host) can be removed fully as it's not needed anymore * no future drivers using ufshcd_alloc_host() could ever forget adding the cleanup
CVE-2025-21759: In the Linux kernel, the following vulnerability has been resolved: ipv6: mcast: extend RCU protection in igmp6_send() igmp6_send() can be called without RTNL or RCU being held. Extend RCU protection so that we can safely fetch the net pointer and avoid a potential UAF. Note that we no longer can use sock_alloc_send_skb() because ipv6.igmp_sk uses GFP_KERNEL allocations which can sleep. Instead use alloc_skb() and charge the net->ipv6.igmp_sk socket under RCU protection.
CVE-2025-21768: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix dst ref loops in rpl, seg6 and ioam6 lwtunnels Some lwtunnels have a dst cache for post-transformation dst. If the packet destination did not change we may end up recording a reference to the lwtunnel in its own cache, and the lwtunnel state will never be freed. Discovered by the ioam6.sh test, kmemleak was recently fixed to catch per-cpu memory leaks. I'm not sure if rpl and seg6 can actually hit this, but in principle I don't see why not.
CVE-2025-21801: In the Linux kernel, the following vulnerability has been resolved: net: ravb: Fix missing rtnl lock in suspend/resume path Fix the suspend/resume path by ensuring the rtnl lock is held where required. Calls to ravb_open, ravb_close and wol operations must be performed under the rtnl lock to prevent conflicts with ongoing ndo operations. Without this fix, the following warning is triggered: [ 39.032969] ============================= [ 39.032983] WARNING: suspicious RCU usage [ 39.033019] ----------------------------- [ 39.033033] drivers/net/phy/phy_device.c:2004 suspicious rcu_dereference_protected() usage! ... [ 39.033597] stack backtrace: [ 39.033613] CPU: 0 UID: 0 PID: 174 Comm: python3 Not tainted 6.13.0-rc7-next-20250116-arm64-renesas-00002-g35245dfdc62c #7 [ 39.033623] Hardware name: Renesas SMARC EVK version 2 based on r9a08g045s33 (DT) [ 39.033628] Call trace: [ 39.033633] show_stack+0x14/0x1c (C) [ 39.033652] dump_stack_lvl+0xb4/0xc4 [ 39.033664] dump_stack+0x14/0x1c [ 39.033671] lockdep_rcu_suspicious+0x16c/0x22c [ 39.033682] phy_detach+0x160/0x190 [ 39.033694] phy_disconnect+0x40/0x54 [ 39.033703] ravb_close+0x6c/0x1cc [ 39.033714] ravb_suspend+0x48/0x120 [ 39.033721] dpm_run_callback+0x4c/0x14c [ 39.033731] device_suspend+0x11c/0x4dc [ 39.033740] dpm_suspend+0xdc/0x214 [ 39.033748] dpm_suspend_start+0x48/0x60 [ 39.033758] suspend_devices_and_enter+0x124/0x574 [ 39.033769] pm_suspend+0x1ac/0x274 [ 39.033778] state_store+0x88/0x124 [ 39.033788] kobj_attr_store+0x14/0x24 [ 39.033798] sysfs_kf_write+0x48/0x6c [ 39.033808] kernfs_fop_write_iter+0x118/0x1a8 [ 39.033817] vfs_write+0x27c/0x378 [ 39.033825] ksys_write+0x64/0xf4 [ 39.033833] __arm64_sys_write+0x18/0x20 [ 39.033841] invoke_syscall+0x44/0x104 [ 39.033852] el0_svc_common.constprop.0+0xb4/0xd4 [ 39.033862] do_el0_svc+0x18/0x20 [ 39.033870] el0_svc+0x3c/0xf0 [ 39.033880] el0t_64_sync_handler+0xc0/0xc4 [ 39.033888] el0t_64_sync+0x154/0x158 [ 39.041274] ravb 11c30000.ethernet eth0: Link is Down
CVE-2025-21825: In the Linux kernel, the following vulnerability has been resolved: bpf: Cancel the running bpf_timer through kworker for PREEMPT_RT During the update procedure, when overwrite element in a pre-allocated htab, the freeing of old_element is protected by the bucket lock. The reason why the bucket lock is necessary is that the old_element has already been stashed in htab->extra_elems after alloc_htab_elem() returns. If freeing the old_element after the bucket lock is unlocked, the stashed element may be reused by concurrent update procedure and the freeing of old_element will run concurrently with the reuse of the old_element. However, the invocation of check_and_free_fields() may acquire a spin-lock which violates the lockdep rule because its caller has already held a raw-spin-lock (bucket lock). The following warning will be reported when such race happens: BUG: scheduling while atomic: test_progs/676/0x00000003 3 locks held by test_progs/676: #0: ffffffff864b0240 (rcu_read_lock_trace){....}-{0:0}, at: bpf_prog_test_run_syscall+0x2c0/0x830 #1: ffff88810e961188 (&htab->lockdep_key){....}-{2:2}, at: htab_map_update_elem+0x306/0x1500 #2: ffff8881f4eac1b8 (&base->softirq_expiry_lock){....}-{2:2}, at: hrtimer_cancel_wait_running+0xe9/0x1b0 Modules linked in: bpf_testmod(O) Preemption disabled at: [<ffffffff817837a3>] htab_map_update_elem+0x293/0x1500 CPU: 0 UID: 0 PID: 676 Comm: test_progs Tainted: G ... 6.12.0+ #11 Tainted: [W]=WARN, [O]=OOT_MODULE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)... Call Trace: <TASK> dump_stack_lvl+0x57/0x70 dump_stack+0x10/0x20 __schedule_bug+0x120/0x170 __schedule+0x300c/0x4800 schedule_rtlock+0x37/0x60 rtlock_slowlock_locked+0x6d9/0x54c0 rt_spin_lock+0x168/0x230 hrtimer_cancel_wait_running+0xe9/0x1b0 hrtimer_cancel+0x24/0x30 bpf_timer_delete_work+0x1d/0x40 bpf_timer_cancel_and_free+0x5e/0x80 bpf_obj_free_fields+0x262/0x4a0 check_and_free_fields+0x1d0/0x280 htab_map_update_elem+0x7fc/0x1500 bpf_prog_9f90bc20768e0cb9_overwrite_cb+0x3f/0x43 bpf_prog_ea601c4649694dbd_overwrite_timer+0x5d/0x7e bpf_prog_test_run_syscall+0x322/0x830 __sys_bpf+0x135d/0x3ca0 __x64_sys_bpf+0x75/0xb0 x64_sys_call+0x1b5/0xa10 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ... </TASK> It seems feasible to break the reuse and refill of per-cpu extra_elems into two independent parts: reuse the per-cpu extra_elems with bucket lock being held and refill the old_element as per-cpu extra_elems after the bucket lock is unlocked. However, it will make the concurrent overwrite procedures on the same CPU return unexpected -E2BIG error when the map is full. Therefore, the patch fixes the lock problem by breaking the cancelling of bpf_timer into two steps for PREEMPT_RT: 1) use hrtimer_try_to_cancel() and check its return value 2) if the timer is running, use hrtimer_cancel() through a kworker to cancel it again Considering that the current implementation of hrtimer_cancel() will try to acquire a being held softirq_expiry_lock when the current timer is running, these steps above are reasonable. However, it also has downside. When the timer is running, the cancelling of the timer is delayed when releasing the last map uref. The delay is also fixable (e.g., break the cancelling of bpf timer into two parts: one part in locked scope, another one in unlocked scope), it can be revised later if necessary. It is a bit hard to decide the right fix tag. One reason is that the problem depends on PREEMPT_RT which is enabled in v6.12. Considering the softirq_expiry_lock lock exists since v5.4 and bpf_timer is introduced in v5.15, the bpf_timer commit is used in the fixes tag and an extra depends-on tag is added to state the dependency on PREEMPT_RT. Depends-on: v6.12+ with PREEMPT_RT enabled
CVE-2025-21831: In the Linux kernel, the following vulnerability has been resolved: PCI: Avoid putting some root ports into D3 on TUXEDO Sirius Gen1 commit 9d26d3a8f1b0 ("PCI: Put PCIe ports into D3 during suspend") sets the policy that all PCIe ports are allowed to use D3. When the system is suspended if the port is not power manageable by the platform and won't be used for wakeup via a PME this sets up the policy for these ports to go into D3hot. This policy generally makes sense from an OSPM perspective but it leads to problems with wakeup from suspend on the TUXEDO Sirius 16 Gen 1 with a specific old BIOS. This manifests as a system hang. On the affected Device + BIOS combination, add a quirk for the root port of the problematic controller to ensure that these root ports are not put into D3hot at suspend. This patch is based on https://lore.kernel.org/linux-pci/20230708214457.1229-2-mario.limonciello@amd.com but with the added condition both in the documentation and in the code to apply only to the TUXEDO Sirius 16 Gen 1 with a specific old BIOS and only the affected root ports.
CVE-2025-21836: In the Linux kernel, the following vulnerability has been resolved: io_uring/kbuf: reallocate buf lists on upgrade IORING_REGISTER_PBUF_RING can reuse an old struct io_buffer_list if it was created for legacy selected buffer and has been emptied. It violates the requirement that most of the field should stay stable after publish. Always reallocate it instead.
CVE-2025-21863: In the Linux kernel, the following vulnerability has been resolved: io_uring: prevent opcode speculation sqe->opcode is used for different tables, make sure we santitise it against speculations.
CVE-2025-21870: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: ipc4-topology: Harden loops for looking up ALH copiers Other, non DAI copier widgets could have the same stream name (sname) as the ALH copier and in that case the copier->data is NULL, no alh_data is attached, which could lead to NULL pointer dereference. We could check for this NULL pointer in sof_ipc4_prepare_copier_module() and avoid the crash, but a similar loop in sof_ipc4_widget_setup_comp_dai() will miscalculate the ALH device count, causing broken audio. The correct fix is to harden the matching logic by making sure that the 1. widget is a DAI widget - so dai = w->private is valid 2. the dai (and thus the copier) is ALH copier
CVE-2025-21872: In the Linux kernel, the following vulnerability has been resolved: efi: Don't map the entire mokvar table to determine its size Currently, when validating the mokvar table, we (re)map the entire table on each iteration of the loop, adding space as we discover new entries. If the table grows over a certain size, this fails due to limitations of early_memmap(), and we get a failure and traceback: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at mm/early_ioremap.c:139 __early_ioremap+0xef/0x220 ... Call Trace: <TASK> ? __early_ioremap+0xef/0x220 ? __warn.cold+0x93/0xfa ? __early_ioremap+0xef/0x220 ? report_bug+0xff/0x140 ? early_fixup_exception+0x5d/0xb0 ? early_idt_handler_common+0x2f/0x3a ? __early_ioremap+0xef/0x220 ? efi_mokvar_table_init+0xce/0x1d0 ? setup_arch+0x864/0xc10 ? start_kernel+0x6b/0xa10 ? x86_64_start_reservations+0x24/0x30 ? x86_64_start_kernel+0xed/0xf0 ? common_startup_64+0x13e/0x141 </TASK> ---[ end trace 0000000000000000 ]--- mokvar: Failed to map EFI MOKvar config table pa=0x7c4c3000, size=265187. Mapping the entire structure isn't actually necessary, as we don't ever need more than one entry header mapped at once. Changes efi_mokvar_table_init() to only map each entry header, not the entire table, when determining the table size. Since we're not mapping any data past the variable name, it also changes the code to enforce that each variable name is NUL terminated, rather than attempting to verify it in place.
CVE-2025-21885: In the Linux kernel, the following vulnerability has been resolved: RDMA/bnxt_re: Fix the page details for the srq created by kernel consumers While using nvme target with use_srq on, below kernel panic is noticed. [ 549.698111] bnxt_en 0000:41:00.0 enp65s0np0: FEC autoneg off encoding: Clause 91 RS(544,514) [ 566.393619] Oops: divide error: 0000 [#1] PREEMPT SMP NOPTI .. [ 566.393799] <TASK> [ 566.393807] ? __die_body+0x1a/0x60 [ 566.393823] ? die+0x38/0x60 [ 566.393835] ? do_trap+0xe4/0x110 [ 566.393847] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393867] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393881] ? do_error_trap+0x7c/0x120 [ 566.393890] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393911] ? exc_divide_error+0x34/0x50 [ 566.393923] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393939] ? asm_exc_divide_error+0x16/0x20 [ 566.393966] ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re] [ 566.393997] bnxt_qplib_create_srq+0xc9/0x340 [bnxt_re] [ 566.394040] bnxt_re_create_srq+0x335/0x3b0 [bnxt_re] [ 566.394057] ? srso_return_thunk+0x5/0x5f [ 566.394068] ? __init_swait_queue_head+0x4a/0x60 [ 566.394090] ib_create_srq_user+0xa7/0x150 [ib_core] [ 566.394147] nvmet_rdma_queue_connect+0x7d0/0xbe0 [nvmet_rdma] [ 566.394174] ? lock_release+0x22c/0x3f0 [ 566.394187] ? srso_return_thunk+0x5/0x5f Page size and shift info is set only for the user space SRQs. Set page size and page shift for kernel space SRQs also.
CVE-2025-21888: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix a WARN during dereg_mr for DM type Memory regions (MR) of type DM (device memory) do not have an associated umem. In the __mlx5_ib_dereg_mr() -> mlx5_free_priv_descs() flow, the code incorrectly takes the wrong branch, attempting to call dma_unmap_single() on a DMA address that is not mapped. This results in a WARN [1], as shown below. The issue is resolved by properly accounting for the DM type and ensuring the correct branch is selected in mlx5_free_priv_descs(). [1] WARNING: CPU: 12 PID: 1346 at drivers/iommu/dma-iommu.c:1230 iommu_dma_unmap_page+0x79/0x90 Modules linked in: ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry ovelay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core fuse mlx5_core CPU: 12 UID: 0 PID: 1346 Comm: ibv_rc_pingpong Not tainted 6.12.0-rc7+ #1631 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:iommu_dma_unmap_page+0x79/0x90 Code: 2b 49 3b 29 72 26 49 3b 69 08 73 20 4d 89 f0 44 89 e9 4c 89 e2 48 89 ee 48 89 df 5b 5d 41 5c 41 5d 41 5e 41 5f e9 07 b8 88 ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 66 0f 1f 44 00 RSP: 0018:ffffc90001913a10 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88810194b0a8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88810194b0a8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f537abdd740(0000) GS:ffff88885fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f537aeb8000 CR3: 000000010c248001 CR4: 0000000000372eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __warn+0x84/0x190 ? iommu_dma_unmap_page+0x79/0x90 ? report_bug+0xf8/0x1c0 ? handle_bug+0x55/0x90 ? exc_invalid_op+0x13/0x60 ? asm_exc_invalid_op+0x16/0x20 ? iommu_dma_unmap_page+0x79/0x90 dma_unmap_page_attrs+0xe6/0x290 mlx5_free_priv_descs+0xb0/0xe0 [mlx5_ib] __mlx5_ib_dereg_mr+0x37e/0x520 [mlx5_ib] ? _raw_spin_unlock_irq+0x24/0x40 ? wait_for_completion+0xfe/0x130 ? rdma_restrack_put+0x63/0xe0 [ib_core] ib_dereg_mr_user+0x5f/0x120 [ib_core] ? lock_release+0xc6/0x280 destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs] uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs] uobj_destroy+0x3f/0x70 [ib_uverbs] ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs] ? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs] ? lock_acquire+0xc1/0x2f0 ? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs] ? ib_uverbs_ioctl+0x116/0x170 [ib_uverbs] ? lock_release+0xc6/0x280 ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs] ? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs] __x64_sys_ioctl+0x1b0/0xa70 do_syscall_64+0x6b/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f537adaf17b Code: 0f 1e fa 48 8b 05 1d ad 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ed ac 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffff218f0b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffff218f1d8 RCX: 00007f537adaf17b RDX: 00007ffff218f1c0 RSI: 00000000c0181b01 RDI: 0000000000000003 RBP: 00007ffff218f1a0 R08: 00007f537aa8d010 R09: 0000561ee2e4f270 R10: 00007f537aace3a8 R11: 0000000000000246 R12: 00007ffff218f190 R13: 000000000000001c R14: 0000561ee2e4d7c0 R15: 00007ffff218f450 </TASK>
CVE-2025-21892: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix the recovery flow of the UMR QP This patch addresses an issue in the recovery flow of the UMR QP, ensuring tasks do not get stuck, as highlighted by the call trace [1]. During recovery, before transitioning the QP to the RESET state, the software must wait for all outstanding WRs to complete. Failing to do so can cause the firmware to skip sending some flushed CQEs with errors and simply discard them upon the RESET, as per the IB specification. This race condition can result in lost CQEs and tasks becoming stuck. To resolve this, the patch sends a final WR which serves only as a barrier before moving the QP state to RESET. Once a CQE is received for that final WR, it guarantees that no outstanding WRs remain, making it safe to transition the QP to RESET and subsequently back to RTS, restoring proper functionality. Note: For the barrier WR, we simply reuse the failed and ready WR. Since the QP is in an error state, it will only receive IB_WC_WR_FLUSH_ERR. However, as it serves only as a barrier we don't care about its status. [1] INFO: task rdma_resource_l:1922 blocked for more than 120 seconds. Tainted: G W 6.12.0-rc7+ #1626 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:rdma_resource_l state:D stack:0 pid:1922 tgid:1922 ppid:1369 flags:0x00004004 Call Trace: <TASK> __schedule+0x420/0xd30 schedule+0x47/0x130 schedule_timeout+0x280/0x300 ? mark_held_locks+0x48/0x80 ? lockdep_hardirqs_on_prepare+0xe5/0x1a0 wait_for_completion+0x75/0x130 mlx5r_umr_post_send_wait+0x3c2/0x5b0 [mlx5_ib] ? __pfx_mlx5r_umr_done+0x10/0x10 [mlx5_ib] mlx5r_umr_revoke_mr+0x93/0xc0 [mlx5_ib] __mlx5_ib_dereg_mr+0x299/0x520 [mlx5_ib] ? _raw_spin_unlock_irq+0x24/0x40 ? wait_for_completion+0xfe/0x130 ? rdma_restrack_put+0x63/0xe0 [ib_core] ib_dereg_mr_user+0x5f/0x120 [ib_core] ? lock_release+0xc6/0x280 destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs] uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs] uobj_destroy+0x3f/0x70 [ib_uverbs] ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs] ? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs] ? __lock_acquire+0x64e/0x2080 ? mark_held_locks+0x48/0x80 ? find_held_lock+0x2d/0xa0 ? lock_acquire+0xc1/0x2f0 ? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs] ? __fget_files+0xc3/0x1b0 ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs] ? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs] __x64_sys_ioctl+0x1b0/0xa70 do_syscall_64+0x6b/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f99c918b17b RSP: 002b:00007ffc766d0468 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffc766d0578 RCX: 00007f99c918b17b RDX: 00007ffc766d0560 RSI: 00000000c0181b01 RDI: 0000000000000003 RBP: 00007ffc766d0540 R08: 00007f99c8f99010 R09: 000000000000bd7e R10: 00007f99c94c1c70 R11: 0000000000000246 R12: 00007ffc766d0530 R13: 000000000000001c R14: 0000000040246a80 R15: 0000000000000000 </TASK>
CVE-2025-21894: In the Linux kernel, the following vulnerability has been resolved: net: enetc: VFs do not support HWTSTAMP_TX_ONESTEP_SYNC Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash if VFs are used to test one-step timestamp, the crash log as follows. [ 129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0 [ 129.287769] Call trace: [ 129.290219] enetc_port_mac_wr+0x30/0xec (P) [ 129.294504] enetc_start_xmit+0xda4/0xe74 [ 129.298525] enetc_xmit+0x70/0xec [ 129.301848] dev_hard_start_xmit+0x98/0x118
CVE-2025-21907: In the Linux kernel, the following vulnerability has been resolved: mm: memory-failure: update ttu flag inside unmap_poisoned_folio Patch series "mm: memory_failure: unmap poisoned folio during migrate properly", v3. Fix two bugs during folio migration if the folio is poisoned. This patch (of 3): Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON in order to stop send SIGBUS signal when accessing an error page after a memory error on a clean folio. However during page migration, anon folio must be set with TTU_HWPOISON during unmap_*(). For pagecache we need some policy just like the one in hwpoison_user_mappings to set this flag. So move this policy from hwpoison_user_mappings to unmap_poisoned_folio to handle this warning properly. Warning will be produced during unamp poison folio with the following log: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c Modules linked in: CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G W 6.13.0-rc1-00018-gacdb4bbda7ab #42 Tainted: [W]=WARN Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : try_to_unmap_one+0x8fc/0xd3c lr : try_to_unmap_one+0x3dc/0xd3c Call trace: try_to_unmap_one+0x8fc/0xd3c (P) try_to_unmap_one+0x3dc/0xd3c (L) rmap_walk_anon+0xdc/0x1f8 rmap_walk+0x3c/0x58 try_to_unmap+0x88/0x90 unmap_poisoned_folio+0x30/0xa8 do_migrate_range+0x4a0/0x568 offline_pages+0x5a4/0x670 memory_block_action+0x17c/0x374 memory_subsys_offline+0x3c/0x78 device_offline+0xa4/0xd0 state_store+0x8c/0xf0 dev_attr_store+0x18/0x2c sysfs_kf_write+0x44/0x54 kernfs_fop_write_iter+0x118/0x1a8 vfs_write+0x3a8/0x4bc ksys_write+0x6c/0xf8 __arm64_sys_write+0x1c/0x28 invoke_syscall+0x44/0x100 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x30/0xd0 el0t_64_sync_handler+0xc8/0xcc el0t_64_sync+0x198/0x19c ---[ end trace 0000000000000000 ]--- [mawupeng1@huawei.com: unmap_poisoned_folio(): remove shadowed local `mapping', per Miaohe]
CVE-2025-21927: In the Linux kernel, the following vulnerability has been resolved: nvme-tcp: fix potential memory corruption in nvme_tcp_recv_pdu() nvme_tcp_recv_pdu() doesn't check the validity of the header length. When header digests are enabled, a target might send a packet with an invalid header length (e.g. 255), causing nvme_tcp_verify_hdgst() to access memory outside the allocated area and cause memory corruptions by overwriting it with the calculated digest. Fix this by rejecting packets with an unexpected header length.
CVE-2025-21949: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Set hugetlb mmap base address aligned with pmd size With ltp test case "testcases/bin/hugefork02", there is a dmesg error report message such as: kernel BUG at mm/hugetlb.c:5550! Oops - BUG[#1]: CPU: 0 UID: 0 PID: 1517 Comm: hugefork02 Not tainted 6.14.0-rc2+ #241 Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022 pc 90000000004eaf1c ra 9000000000485538 tp 900000010edbc000 sp 900000010edbf940 a0 900000010edbfb00 a1 9000000108d20280 a2 00007fffe9474000 a3 00007ffff3474000 a4 0000000000000000 a5 0000000000000003 a6 00000000003cadd3 a7 0000000000000000 t0 0000000001ffffff t1 0000000001474000 t2 900000010ecd7900 t3 00007fffe9474000 t4 00007fffe9474000 t5 0000000000000040 t6 900000010edbfb00 t7 0000000000000001 t8 0000000000000005 u0 90000000004849d0 s9 900000010edbfa00 s0 9000000108d20280 s1 00007fffe9474000 s2 0000000002000000 s3 9000000108d20280 s4 9000000002b38b10 s5 900000010edbfb00 s6 00007ffff3474000 s7 0000000000000406 s8 900000010edbfa08 ra: 9000000000485538 unmap_vmas+0x130/0x218 ERA: 90000000004eaf1c __unmap_hugepage_range+0x6f4/0x7d0 PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000007 (+FPE +SXE +ASXE -BTE) ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) Process hugefork02 (pid: 1517, threadinfo=00000000a670eaf4, task=000000007a95fc64) Call Trace: [<90000000004eaf1c>] __unmap_hugepage_range+0x6f4/0x7d0 [<9000000000485534>] unmap_vmas+0x12c/0x218 [<9000000000494068>] exit_mmap+0xe0/0x308 [<900000000025fdc4>] mmput+0x74/0x180 [<900000000026a284>] do_exit+0x294/0x898 [<900000000026aa30>] do_group_exit+0x30/0x98 [<900000000027bed4>] get_signal+0x83c/0x868 [<90000000002457b4>] arch_do_signal_or_restart+0x54/0xfa0 [<90000000015795e8>] irqentry_exit_to_user_mode+0xb8/0x138 [<90000000002572d0>] tlb_do_page_fault_1+0x114/0x1b4 The problem is that base address allocated from hugetlbfs is not aligned with pmd size. Here add a checking for hugetlbfs and align base address with pmd size. After this patch the test case "testcases/bin/hugefork02" passes to run. This is similar to the commit 7f24cbc9c4d42db8a3c8484d1 ("mm/mmap: teach generic_get_unmapped_area{_topdown} to handle hugetlb mappings").
CVE-2025-21955: In the Linux kernel, the following vulnerability has been resolved: ksmbd: prevent connection release during oplock break notification ksmbd_work could be freed when after connection release. Increment r_count of ksmbd_conn to indicate that requests are not finished yet and to not release the connection.
CVE-2025-21961: In the Linux kernel, the following vulnerability has been resolved: eth: bnxt: fix truesize for mb-xdp-pass case When mb-xdp is set and return is XDP_PASS, packet is converted from xdp_buff to sk_buff with xdp_update_skb_shared_info() in bnxt_xdp_build_skb(). bnxt_xdp_build_skb() passes incorrect truesize argument to xdp_update_skb_shared_info(). The truesize is calculated as BNXT_RX_PAGE_SIZE * sinfo->nr_frags but the skb_shared_info was wiped by napi_build_skb() before. So it stores sinfo->nr_frags before bnxt_xdp_build_skb() and use it instead of getting skb_shared_info from xdp_get_shared_info_from_buff(). Splat looks like: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 0 at net/core/skbuff.c:6072 skb_try_coalesce+0x504/0x590 Modules linked in: xt_nat xt_tcpudp veth af_packet xt_conntrack nft_chain_nat xt_MASQUERADE nf_conntrack_netlink xfrm_user xt_addrtype nft_coms CPU: 2 UID: 0 PID: 0 Comm: swapper/2 Not tainted 6.14.0-rc2+ #3 RIP: 0010:skb_try_coalesce+0x504/0x590 Code: 4b fd ff ff 49 8b 34 24 40 80 e6 40 0f 84 3d fd ff ff 49 8b 74 24 48 40 f6 c6 01 0f 84 2e fd ff ff 48 8d 4e ff e9 25 fd ff ff <0f> 0b e99 RSP: 0018:ffffb62c4120caa8 EFLAGS: 00010287 RAX: 0000000000000003 RBX: ffffb62c4120cb14 RCX: 0000000000000ec0 RDX: 0000000000001000 RSI: ffffa06e5d7dc000 RDI: 0000000000000003 RBP: ffffa06e5d7ddec0 R08: ffffa06e6120a800 R09: ffffa06e7a119900 R10: 0000000000002310 R11: ffffa06e5d7dcec0 R12: ffffe4360575f740 R13: ffffe43600000000 R14: 0000000000000002 R15: 0000000000000002 FS: 0000000000000000(0000) GS:ffffa0755f700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f147b76b0f8 CR3: 00000001615d4000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: <IRQ> ? __warn+0x84/0x130 ? skb_try_coalesce+0x504/0x590 ? report_bug+0x18a/0x1a0 ? handle_bug+0x53/0x90 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? skb_try_coalesce+0x504/0x590 inet_frag_reasm_finish+0x11f/0x2e0 ip_defrag+0x37a/0x900 ip_local_deliver+0x51/0x120 ip_sublist_rcv_finish+0x64/0x70 ip_sublist_rcv+0x179/0x210 ip_list_rcv+0xf9/0x130 How to reproduce: <Node A> ip link set $interface1 xdp obj xdp_pass.o ip link set $interface1 mtu 9000 up ip a a 10.0.0.1/24 dev $interface1 <Node B> ip link set $interfac2 mtu 9000 up ip a a 10.0.0.2/24 dev $interface2 ping 10.0.0.1 -s 65000 Following ping.py patch adds xdp-mb-pass case. so ping.py is going to be able to reproduce this issue.
CVE-2025-21967: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in ksmbd_free_work_struct ->interim_entry of ksmbd_work could be deleted after oplock is freed. We don't need to manage it with linked list. The interim request could be immediately sent whenever a oplock break wait is needed.
CVE-2025-21969: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix slab-use-after-free Read in l2cap_send_cmd After the hci sync command releases l2cap_conn, the hci receive data work queue references the released l2cap_conn when sending to the upper layer. Add hci dev lock to the hci receive data work queue to synchronize the two. [1] BUG: KASAN: slab-use-after-free in l2cap_send_cmd+0x187/0x8d0 net/bluetooth/l2cap_core.c:954 Read of size 8 at addr ffff8880271a4000 by task kworker/u9:2/5837 CPU: 0 UID: 0 PID: 5837 Comm: kworker/u9:2 Not tainted 6.13.0-rc5-syzkaller-00163-gab75170520d4 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 Workqueue: hci1 hci_rx_work Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x169/0x550 mm/kasan/report.c:489 kasan_report+0x143/0x180 mm/kasan/report.c:602 l2cap_build_cmd net/bluetooth/l2cap_core.c:2964 [inline] l2cap_send_cmd+0x187/0x8d0 net/bluetooth/l2cap_core.c:954 l2cap_sig_send_rej net/bluetooth/l2cap_core.c:5502 [inline] l2cap_sig_channel net/bluetooth/l2cap_core.c:5538 [inline] l2cap_recv_frame+0x221f/0x10db0 net/bluetooth/l2cap_core.c:6817 hci_acldata_packet net/bluetooth/hci_core.c:3797 [inline] hci_rx_work+0x508/0xdb0 net/bluetooth/hci_core.c:4040 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa66/0x1840 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Allocated by task 5837: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __kmalloc_cache_noprof+0x243/0x390 mm/slub.c:4329 kmalloc_noprof include/linux/slab.h:901 [inline] kzalloc_noprof include/linux/slab.h:1037 [inline] l2cap_conn_add+0xa9/0x8e0 net/bluetooth/l2cap_core.c:6860 l2cap_connect_cfm+0x115/0x1090 net/bluetooth/l2cap_core.c:7239 hci_connect_cfm include/net/bluetooth/hci_core.h:2057 [inline] hci_remote_features_evt+0x68e/0xac0 net/bluetooth/hci_event.c:3726 hci_event_func net/bluetooth/hci_event.c:7473 [inline] hci_event_packet+0xac2/0x1540 net/bluetooth/hci_event.c:7525 hci_rx_work+0x3f3/0xdb0 net/bluetooth/hci_core.c:4035 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa66/0x1840 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Freed by task 54: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:582 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline] slab_free_hook mm/slub.c:2353 [inline] slab_free mm/slub.c:4613 [inline] kfree+0x196/0x430 mm/slub.c:4761 l2cap_connect_cfm+0xcc/0x1090 net/bluetooth/l2cap_core.c:7235 hci_connect_cfm include/net/bluetooth/hci_core.h:2057 [inline] hci_conn_failed+0x287/0x400 net/bluetooth/hci_conn.c:1266 hci_abort_conn_sync+0x56c/0x11f0 net/bluetooth/hci_sync.c:5603 hci_cmd_sync_work+0x22b/0x400 net/bluetooth/hci_sync.c:332 process_one_work kernel/workqueue.c:3229 [inline] process_scheduled_works+0xa66/0x1840 kernel/workqueue.c:3310 worker_thread+0x870/0xd30 kernel/workqueue.c:3391 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entr ---truncated---
CVE-2025-21972: In the Linux kernel, the following vulnerability has been resolved: net: mctp: unshare packets when reassembling Ensure that the frag_list used for reassembly isn't shared with other packets. This avoids incorrect reassembly when packets are cloned, and prevents a memory leak due to circular references between fragments and their skb_shared_info. The upcoming MCTP-over-USB driver uses skb_clone which can trigger the problem - other MCTP drivers don't share SKBs. A kunit test is added to reproduce the issue.
CVE-2025-21976: In the Linux kernel, the following vulnerability has been resolved: fbdev: hyperv_fb: Allow graceful removal of framebuffer When a Hyper-V framebuffer device is unbind, hyperv_fb driver tries to release the framebuffer forcefully. If this framebuffer is in use it produce the following WARN and hence this framebuffer is never released. [ 44.111220] WARNING: CPU: 35 PID: 1882 at drivers/video/fbdev/core/fb_info.c:70 framebuffer_release+0x2c/0x40 < snip > [ 44.111289] Call Trace: [ 44.111290] <TASK> [ 44.111291] ? show_regs+0x6c/0x80 [ 44.111295] ? __warn+0x8d/0x150 [ 44.111298] ? framebuffer_release+0x2c/0x40 [ 44.111300] ? report_bug+0x182/0x1b0 [ 44.111303] ? handle_bug+0x6e/0xb0 [ 44.111306] ? exc_invalid_op+0x18/0x80 [ 44.111308] ? asm_exc_invalid_op+0x1b/0x20 [ 44.111311] ? framebuffer_release+0x2c/0x40 [ 44.111313] ? hvfb_remove+0x86/0xa0 [hyperv_fb] [ 44.111315] vmbus_remove+0x24/0x40 [hv_vmbus] [ 44.111323] device_remove+0x40/0x80 [ 44.111325] device_release_driver_internal+0x20b/0x270 [ 44.111327] ? bus_find_device+0xb3/0xf0 Fix this by moving the release of framebuffer and assosiated memory to fb_ops.fb_destroy function, so that framebuffer framework handles it gracefully. While we fix this, also replace manual registrations/unregistration of framebuffer with devm_register_framebuffer.
CVE-2025-21985: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix out-of-bound accesses [WHAT & HOW] hpo_stream_to_link_encoder_mapping has size MAX_HPO_DP2_ENCODERS(=4), but location can have size up to 6. As a result, it is necessary to check location against MAX_HPO_DP2_ENCODERS. Similiarly, disp_cfg_stream_location can be used as an array index which should be 0..5, so the ASSERT's conditions should be less without equal.
CVE-2025-22028: In the Linux kernel, the following vulnerability has been resolved: media: vimc: skip .s_stream() for stopped entities Syzbot reported [1] a warning prompted by a check in call_s_stream() that checks whether .s_stream() operation is warranted for unstarted or stopped subdevs. Add a simple fix in vimc_streamer_pipeline_terminate() ensuring that entities skip a call to .s_stream() unless they have been previously properly started. [1] Syzbot report: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 5933 at drivers/media/v4l2-core/v4l2-subdev.c:460 call_s_stream+0x2df/0x350 drivers/media/v4l2-core/v4l2-subdev.c:460 Modules linked in: CPU: 0 UID: 0 PID: 5933 Comm: syz-executor330 Not tainted 6.13.0-rc2-syzkaller-00362-g2d8308bf5b67 #0 ... Call Trace: <TASK> vimc_streamer_pipeline_terminate+0x218/0x320 drivers/media/test-drivers/vimc/vimc-streamer.c:62 vimc_streamer_pipeline_init drivers/media/test-drivers/vimc/vimc-streamer.c:101 [inline] vimc_streamer_s_stream+0x650/0x9a0 drivers/media/test-drivers/vimc/vimc-streamer.c:203 vimc_capture_start_streaming+0xa1/0x130 drivers/media/test-drivers/vimc/vimc-capture.c:256 vb2_start_streaming+0x15f/0x5a0 drivers/media/common/videobuf2/videobuf2-core.c:1789 vb2_core_streamon+0x2a7/0x450 drivers/media/common/videobuf2/videobuf2-core.c:2348 vb2_streamon drivers/media/common/videobuf2/videobuf2-v4l2.c:875 [inline] vb2_ioctl_streamon+0xf4/0x170 drivers/media/common/videobuf2/videobuf2-v4l2.c:1118 __video_do_ioctl+0xaf0/0xf00 drivers/media/v4l2-core/v4l2-ioctl.c:3122 video_usercopy+0x4d2/0x1620 drivers/media/v4l2-core/v4l2-ioctl.c:3463 v4l2_ioctl+0x1ba/0x250 drivers/media/v4l2-core/v4l2-dev.c:366 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl fs/ioctl.c:892 [inline] __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f2b85c01b19 ...
CVE-2025-22037: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix null pointer dereference in alloc_preauth_hash() The Client send malformed smb2 negotiate request. ksmbd return error response. Subsequently, the client can send smb2 session setup even thought conn->preauth_info is not allocated. This patch add KSMBD_SESS_NEED_SETUP status of connection to ignore session setup request if smb2 negotiate phase is not complete.
CVE-2025-22039: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix overflow in dacloffset bounds check The dacloffset field was originally typed as int and used in an unchecked addition, which could overflow and bypass the existing bounds check in both smb_check_perm_dacl() and smb_inherit_dacl(). This could result in out-of-bounds memory access and a kernel crash when dereferencing the DACL pointer. This patch converts dacloffset to unsigned int and uses check_add_overflow() to validate access to the DACL.
CVE-2025-22043: In the Linux kernel, the following vulnerability has been resolved: ksmbd: add bounds check for durable handle context Add missing bounds check for durable handle context.
CVE-2025-22048: In the Linux kernel, the following vulnerability has been resolved: LoongArch: BPF: Don't override subprog's return value The verifier test `calls: div by 0 in subprog` triggers a panic at the ld.bu instruction. The ld.bu insn is trying to load byte from memory address returned by the subprog. The subprog actually set the correct address at the a5 register (dedicated register for BPF return values). But at commit 73c359d1d356 ("LoongArch: BPF: Sign-extend return values") we also sign extended a5 to the a0 register (return value in LoongArch). For function call insn, we later propagate the a0 register back to a5 register. This is right for native calls but wrong for bpf2bpf calls which expect zero-extended return value in a5 register. So only move a0 to a5 for native calls (i.e. non-BPF_PSEUDO_CALL).
CVE-2025-22053: In the Linux kernel, the following vulnerability has been resolved: net: ibmveth: make veth_pool_store stop hanging v2: - Created a single error handling unlock and exit in veth_pool_store - Greatly expanded commit message with previous explanatory-only text Summary: Use rtnl_mutex to synchronize veth_pool_store with itself, ibmveth_close and ibmveth_open, preventing multiple calls in a row to napi_disable. Background: Two (or more) threads could call veth_pool_store through writing to /sys/devices/vio/30000002/pool*/*. You can do this easily with a little shell script. This causes a hang. I configured LOCKDEP, compiled ibmveth.c with DEBUG, and built a new kernel. I ran this test again and saw: Setting pool0/active to 0 Setting pool1/active to 1 [ 73.911067][ T4365] ibmveth 30000002 eth0: close starting Setting pool1/active to 1 Setting pool1/active to 0 [ 73.911367][ T4366] ibmveth 30000002 eth0: close starting [ 73.916056][ T4365] ibmveth 30000002 eth0: close complete [ 73.916064][ T4365] ibmveth 30000002 eth0: open starting [ 110.808564][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 230.808495][ T712] systemd-journald[712]: Sent WATCHDOG=1 notification. [ 243.683786][ T123] INFO: task stress.sh:4365 blocked for more than 122 seconds. [ 243.683827][ T123] Not tainted 6.14.0-01103-g2df0c02dab82-dirty #8 [ 243.683833][ T123] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 243.683838][ T123] task:stress.sh state:D stack:28096 pid:4365 tgid:4365 ppid:4364 task_flags:0x400040 flags:0x00042000 [ 243.683852][ T123] Call Trace: [ 243.683857][ T123] [c00000000c38f690] [0000000000000001] 0x1 (unreliable) [ 243.683868][ T123] [c00000000c38f840] [c00000000001f908] __switch_to+0x318/0x4e0 [ 243.683878][ T123] [c00000000c38f8a0] [c000000001549a70] __schedule+0x500/0x12a0 [ 243.683888][ T123] [c00000000c38f9a0] [c00000000154a878] schedule+0x68/0x210 [ 243.683896][ T123] [c00000000c38f9d0] [c00000000154ac80] schedule_preempt_disabled+0x30/0x50 [ 243.683904][ T123] [c00000000c38fa00] [c00000000154dbb0] __mutex_lock+0x730/0x10f0 [ 243.683913][ T123] [c00000000c38fb10] [c000000001154d40] napi_enable+0x30/0x60 [ 243.683921][ T123] [c00000000c38fb40] [c000000000f4ae94] ibmveth_open+0x68/0x5dc [ 243.683928][ T123] [c00000000c38fbe0] [c000000000f4aa20] veth_pool_store+0x220/0x270 [ 243.683936][ T123] [c00000000c38fc70] [c000000000826278] sysfs_kf_write+0x68/0xb0 [ 243.683944][ T123] [c00000000c38fcb0] [c0000000008240b8] kernfs_fop_write_iter+0x198/0x2d0 [ 243.683951][ T123] [c00000000c38fd00] [c00000000071b9ac] vfs_write+0x34c/0x650 [ 243.683958][ T123] [c00000000c38fdc0] [c00000000071bea8] ksys_write+0x88/0x150 [ 243.683966][ T123] [c00000000c38fe10] [c0000000000317f4] system_call_exception+0x124/0x340 [ 243.683973][ T123] [c00000000c38fe50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec ... [ 243.684087][ T123] Showing all locks held in the system: [ 243.684095][ T123] 1 lock held by khungtaskd/123: [ 243.684099][ T123] #0: c00000000278e370 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x50/0x248 [ 243.684114][ T123] 4 locks held by stress.sh/4365: [ 243.684119][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243.684132][ T123] #1: c000000041aea888 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0 [ 243.684143][ T123] #2: c0000000366fb9a8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0 [ 243.684155][ T123] #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_enable+0x30/0x60 [ 243.684166][ T123] 5 locks held by stress.sh/4366: [ 243.684170][ T123] #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150 [ 243. ---truncated---
CVE-2025-22057: In the Linux kernel, the following vulnerability has been resolved: net: decrease cached dst counters in dst_release Upstream fix ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") moved decrementing the dst count from dst_destroy to dst_release to avoid accessing already freed data in case of netns dismantle. However in case CONFIG_DST_CACHE is enabled and OvS+tunnels are used, this fix is incomplete as the same issue will be seen for cached dsts: Unable to handle kernel paging request at virtual address ffff5aabf6b5c000 Call trace: percpu_counter_add_batch+0x3c/0x160 (P) dst_release+0xec/0x108 dst_cache_destroy+0x68/0xd8 dst_destroy+0x13c/0x168 dst_destroy_rcu+0x1c/0xb0 rcu_do_batch+0x18c/0x7d0 rcu_core+0x174/0x378 rcu_core_si+0x18/0x30 Fix this by invalidating the cache, and thus decrementing cached dst counters, in dst_release too.
CVE-2025-22070: In the Linux kernel, the following vulnerability has been resolved: fs/9p: fix NULL pointer dereference on mkdir When a 9p tree was mounted with option 'posixacl', parent directory had a default ACL set for its subdirectories, e.g.: setfacl -m default:group:simpsons:rwx parentdir then creating a subdirectory crashed 9p client, as v9fs_fid_add() call in function v9fs_vfs_mkdir_dotl() sets the passed 'fid' pointer to NULL (since dafbe689736) even though the subsequent v9fs_set_create_acl() call expects a valid non-NULL 'fid' pointer: [ 37.273191] BUG: kernel NULL pointer dereference, address: 0000000000000000 ... [ 37.322338] Call Trace: [ 37.323043] <TASK> [ 37.323621] ? __die (arch/x86/kernel/dumpstack.c:421 arch/x86/kernel/dumpstack.c:434) [ 37.324448] ? page_fault_oops (arch/x86/mm/fault.c:714) [ 37.325532] ? search_module_extables (kernel/module/main.c:3733) [ 37.326742] ? p9_client_walk (net/9p/client.c:1165) 9pnet [ 37.328006] ? search_bpf_extables (kernel/bpf/core.c:804) [ 37.329142] ? exc_page_fault (./arch/x86/include/asm/paravirt.h:686 arch/x86/mm/fault.c:1488 arch/x86/mm/fault.c:1538) [ 37.330196] ? asm_exc_page_fault (./arch/x86/include/asm/idtentry.h:574) [ 37.331330] ? p9_client_walk (net/9p/client.c:1165) 9pnet [ 37.332562] ? v9fs_fid_xattr_get (fs/9p/xattr.c:30) 9p [ 37.333824] v9fs_fid_xattr_set (fs/9p/fid.h:23 fs/9p/xattr.c:121) 9p [ 37.335077] v9fs_set_acl (fs/9p/acl.c:276) 9p [ 37.336112] v9fs_set_create_acl (fs/9p/acl.c:307) 9p [ 37.337326] v9fs_vfs_mkdir_dotl (fs/9p/vfs_inode_dotl.c:411) 9p [ 37.338590] vfs_mkdir (fs/namei.c:4313) [ 37.339535] do_mkdirat (fs/namei.c:4336) [ 37.340465] __x64_sys_mkdir (fs/namei.c:4354) [ 37.341455] do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) [ 37.342447] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fix this by simply swapping the sequence of these two calls in v9fs_vfs_mkdir_dotl(), i.e. calling v9fs_set_create_acl() before v9fs_fid_add().
CVE-2025-22103: In the Linux kernel, the following vulnerability has been resolved: net: fix NULL pointer dereference in l3mdev_l3_rcv When delete l3s ipvlan: ip link del link eth0 ipvlan1 type ipvlan mode l3s This may cause a null pointer dereference: Call trace: ip_rcv_finish+0x48/0xd0 ip_rcv+0x5c/0x100 __netif_receive_skb_one_core+0x64/0xb0 __netif_receive_skb+0x20/0x80 process_backlog+0xb4/0x204 napi_poll+0xe8/0x294 net_rx_action+0xd8/0x22c __do_softirq+0x12c/0x354 This is because l3mdev_l3_rcv() visit dev->l3mdev_ops after ipvlan_l3s_unregister() assign the dev->l3mdev_ops to NULL. The process like this: (CPU1) | (CPU2) l3mdev_l3_rcv() | check dev->priv_flags: | master = skb->dev; | | | ipvlan_l3s_unregister() | set dev->priv_flags | dev->l3mdev_ops = NULL; | visit master->l3mdev_ops | To avoid this by do not set dev->l3mdev_ops when unregister l3s ipvlan.
CVE-2025-22104: In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Use kernel helpers for hex dumps Previously, when the driver was printing hex dumps, the buffer was cast to an 8 byte long and printed using string formatters. If the buffer size was not a multiple of 8 then a read buffer overflow was possible. Therefore, create a new ibmvnic function that loops over a buffer and calls hex_dump_to_buffer instead. This patch address KASAN reports like the one below: ibmvnic 30000003 env3: Login Buffer: ibmvnic 30000003 env3: 01000000af000000 <...> ibmvnic 30000003 env3: 2e6d62692e736261 ibmvnic 30000003 env3: 65050003006d6f63 ================================================================== BUG: KASAN: slab-out-of-bounds in ibmvnic_login+0xacc/0xffc [ibmvnic] Read of size 8 at addr c0000001331a9aa8 by task ip/17681 <...> Allocated by task 17681: <...> ibmvnic_login+0x2f0/0xffc [ibmvnic] ibmvnic_open+0x148/0x308 [ibmvnic] __dev_open+0x1ac/0x304 <...> The buggy address is located 168 bytes inside of allocated 175-byte region [c0000001331a9a00, c0000001331a9aaf) <...> ================================================================= ibmvnic 30000003 env3: 000000000033766e
CVE-2025-22105: In the Linux kernel, the following vulnerability has been resolved: bonding: check xdp prog when set bond mode Following operations can trigger a warning[1]: ip netns add ns1 ip netns exec ns1 ip link add bond0 type bond mode balance-rr ip netns exec ns1 ip link set dev bond0 xdp obj af_xdp_kern.o sec xdp ip netns exec ns1 ip link set bond0 type bond mode broadcast ip netns del ns1 When delete the namespace, dev_xdp_uninstall() is called to remove xdp program on bond dev, and bond_xdp_set() will check the bond mode. If bond mode is changed after attaching xdp program, the warning may occur. Some bond modes (broadcast, etc.) do not support native xdp. Set bond mode with xdp program attached is not good. Add check for xdp program when set bond mode. [1] ------------[ cut here ]------------ WARNING: CPU: 0 PID: 11 at net/core/dev.c:9912 unregister_netdevice_many_notify+0x8d9/0x930 Modules linked in: CPU: 0 UID: 0 PID: 11 Comm: kworker/u4:0 Not tainted 6.14.0-rc4 #107 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Workqueue: netns cleanup_net RIP: 0010:unregister_netdevice_many_notify+0x8d9/0x930 Code: 00 00 48 c7 c6 6f e3 a2 82 48 c7 c7 d0 b3 96 82 e8 9c 10 3e ... RSP: 0018:ffffc90000063d80 EFLAGS: 00000282 RAX: 00000000ffffffa1 RBX: ffff888004959000 RCX: 00000000ffffdfff RDX: 0000000000000000 RSI: 00000000ffffffea RDI: ffffc90000063b48 RBP: ffffc90000063e28 R08: ffffffff82d39b28 R09: 0000000000009ffb R10: 0000000000000175 R11: ffffffff82d09b40 R12: ffff8880049598e8 R13: 0000000000000001 R14: dead000000000100 R15: ffffc90000045000 FS: 0000000000000000(0000) GS:ffff888007a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000d406b60 CR3: 000000000483e000 CR4: 00000000000006f0 Call Trace: <TASK> ? __warn+0x83/0x130 ? unregister_netdevice_many_notify+0x8d9/0x930 ? report_bug+0x18e/0x1a0 ? handle_bug+0x54/0x90 ? exc_invalid_op+0x18/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? unregister_netdevice_many_notify+0x8d9/0x930 ? bond_net_exit_batch_rtnl+0x5c/0x90 cleanup_net+0x237/0x3d0 process_one_work+0x163/0x390 worker_thread+0x293/0x3b0 ? __pfx_worker_thread+0x10/0x10 kthread+0xec/0x1e0 ? __pfx_kthread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> ---[ end trace 0000000000000000 ]---
CVE-2025-22109: In the Linux kernel, the following vulnerability has been resolved: ax25: Remove broken autobind Binding AX25 socket by using the autobind feature leads to memory leaks in ax25_connect() and also refcount leaks in ax25_release(). Memory leak was detected with kmemleak: ================================================================ unreferenced object 0xffff8880253cd680 (size 96): backtrace: __kmalloc_node_track_caller_noprof (./include/linux/kmemleak.h:43) kmemdup_noprof (mm/util.c:136) ax25_rt_autobind (net/ax25/ax25_route.c:428) ax25_connect (net/ax25/af_ax25.c:1282) __sys_connect_file (net/socket.c:2045) __sys_connect (net/socket.c:2064) __x64_sys_connect (net/socket.c:2067) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) ================================================================ When socket is bound, refcounts must be incremented the way it is done in ax25_bind() and ax25_setsockopt() (SO_BINDTODEVICE). In case of autobind, the refcounts are not incremented. This bug leads to the following issue reported by Syzkaller: ================================================================ ax25_connect(): syz-executor318 uses autobind, please contact jreuter@yaina.de ------------[ cut here ]------------ refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 0 PID: 5317 at lib/refcount.c:31 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 Modules linked in: CPU: 0 UID: 0 PID: 5317 Comm: syz-executor318 Not tainted 6.14.0-rc4-syzkaller-00278-gece144f151ac #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 RIP: 0010:refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31 ... Call Trace: <TASK> __refcount_dec include/linux/refcount.h:336 [inline] refcount_dec include/linux/refcount.h:351 [inline] ref_tracker_free+0x6af/0x7e0 lib/ref_tracker.c:236 netdev_tracker_free include/linux/netdevice.h:4302 [inline] netdev_put include/linux/netdevice.h:4319 [inline] ax25_release+0x368/0x960 net/ax25/af_ax25.c:1080 __sock_release net/socket.c:647 [inline] sock_close+0xbc/0x240 net/socket.c:1398 __fput+0x3e9/0x9f0 fs/file_table.c:464 __do_sys_close fs/open.c:1580 [inline] __se_sys_close fs/open.c:1565 [inline] __x64_sys_close+0x7f/0x110 fs/open.c:1565 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f ... </TASK> ================================================================ Considering the issues above and the comments left in the code that say: "check if we can remove this feature. It is broken."; "autobinding in this may or may not work"; - it is better to completely remove this feature than to fix it because it is broken and leads to various kinds of memory bugs. Now calling connect() without first binding socket will result in an error (-EINVAL). Userspace software that relies on the autobind feature might get broken. However, this feature does not seem widely used with this specific driver as it was not reliable at any point of time, and it is already broken anyway. E.g. ax25-tools and ax25-apps packages for popular distributions do not use the autobind feature for AF_AX25. Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2025-22113: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid journaling sb update on error if journal is destroying Presently we always BUG_ON if trying to start a transaction on a journal marked with JBD2_UNMOUNT, since this should never happen. However, while ltp running stress tests, it was observed that in case of some error handling paths, it is possible for update_super_work to start a transaction after the journal is destroyed eg: (umount) ext4_kill_sb kill_block_super generic_shutdown_super sync_filesystem /* commits all txns */ evict_inodes /* might start a new txn */ ext4_put_super flush_work(&sbi->s_sb_upd_work) /* flush the workqueue */ jbd2_journal_destroy journal_kill_thread journal->j_flags |= JBD2_UNMOUNT; jbd2_journal_commit_transaction jbd2_journal_get_descriptor_buffer jbd2_journal_bmap ext4_journal_bmap ext4_map_blocks ... ext4_inode_error ext4_handle_error schedule_work(&sbi->s_sb_upd_work) /* work queue kicks in */ update_super_work jbd2_journal_start start_this_handle BUG_ON(journal->j_flags & JBD2_UNMOUNT) Hence, introduce a new mount flag to indicate journal is destroying and only do a journaled (and deferred) update of sb if this flag is not set. Otherwise, just fallback to an un-journaled commit. Further, in the journal destroy path, we have the following sequence: 1. Set mount flag indicating journal is destroying 2. force a commit and wait for it 3. flush pending sb updates This sequence is important as it ensures that, after this point, there is no sb update that might be journaled so it is safe to update the sb outside the journal. (To avoid race discussed in 2d01ddc86606) Also, we don't need a similar check in ext4_grp_locked_error since it is only called from mballoc and AFAICT it would be always valid to schedule work here.
CVE-2025-22115: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix block group refcount race in btrfs_create_pending_block_groups() Block group creation is done in two phases, which results in a slightly unintuitive property: a block group can be allocated/deallocated from after btrfs_make_block_group() adds it to the space_info with btrfs_add_bg_to_space_info(), but before creation is completely completed in btrfs_create_pending_block_groups(). As a result, it is possible for a block group to go unused and have 'btrfs_mark_bg_unused' called on it concurrently with 'btrfs_create_pending_block_groups'. This causes a number of issues, which were fixed with the block group flag 'BLOCK_GROUP_FLAG_NEW'. However, this fix is not quite complete. Since it does not use the unused_bg_lock, it is possible for the following race to occur: btrfs_create_pending_block_groups btrfs_mark_bg_unused if list_empty // false list_del_init clear_bit else if (test_bit) // true list_move_tail And we get into the exact same broken ref count and invalid new_bgs state for transaction cleanup that BLOCK_GROUP_FLAG_NEW was designed to prevent. The broken refcount aspect will result in a warning like: [1272.943527] refcount_t: underflow; use-after-free. [1272.943967] WARNING: CPU: 1 PID: 61 at lib/refcount.c:28 refcount_warn_saturate+0xba/0x110 [1272.944731] Modules linked in: btrfs virtio_net xor zstd_compress raid6_pq null_blk [last unloaded: btrfs] [1272.945550] CPU: 1 UID: 0 PID: 61 Comm: kworker/u32:1 Kdump: loaded Tainted: G W 6.14.0-rc5+ #108 [1272.946368] Tainted: [W]=WARN [1272.946585] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014 [1272.947273] Workqueue: btrfs_discard btrfs_discard_workfn [btrfs] [1272.947788] RIP: 0010:refcount_warn_saturate+0xba/0x110 [1272.949532] RSP: 0018:ffffbf1200247df0 EFLAGS: 00010282 [1272.949901] RAX: 0000000000000000 RBX: ffffa14b00e3f800 RCX: 0000000000000000 [1272.950437] RDX: 0000000000000000 RSI: ffffbf1200247c78 RDI: 00000000ffffdfff [1272.950986] RBP: ffffa14b00dc2860 R08: 00000000ffffdfff R09: ffffffff90526268 [1272.951512] R10: ffffffff904762c0 R11: 0000000063666572 R12: ffffa14b00dc28c0 [1272.952024] R13: 0000000000000000 R14: ffffa14b00dc2868 R15: 000001285dcd12c0 [1272.952850] FS: 0000000000000000(0000) GS:ffffa14d33c40000(0000) knlGS:0000000000000000 [1272.953458] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [1272.953931] CR2: 00007f838cbda000 CR3: 000000010104e000 CR4: 00000000000006f0 [1272.954474] Call Trace: [1272.954655] <TASK> [1272.954812] ? refcount_warn_saturate+0xba/0x110 [1272.955173] ? __warn.cold+0x93/0xd7 [1272.955487] ? refcount_warn_saturate+0xba/0x110 [1272.955816] ? report_bug+0xe7/0x120 [1272.956103] ? handle_bug+0x53/0x90 [1272.956424] ? exc_invalid_op+0x13/0x60 [1272.956700] ? asm_exc_invalid_op+0x16/0x20 [1272.957011] ? refcount_warn_saturate+0xba/0x110 [1272.957399] btrfs_discard_cancel_work.cold+0x26/0x2b [btrfs] [1272.957853] btrfs_put_block_group.cold+0x5d/0x8e [btrfs] [1272.958289] btrfs_discard_workfn+0x194/0x380 [btrfs] [1272.958729] process_one_work+0x130/0x290 [1272.959026] worker_thread+0x2ea/0x420 [1272.959335] ? __pfx_worker_thread+0x10/0x10 [1272.959644] kthread+0xd7/0x1c0 [1272.959872] ? __pfx_kthread+0x10/0x10 [1272.960172] ret_from_fork+0x30/0x50 [1272.960474] ? __pfx_kthread+0x10/0x10 [1272.960745] ret_from_fork_asm+0x1a/0x30 [1272.961035] </TASK> [1272.961238] ---[ end trace 0000000000000000 ]--- Though we have seen them in the async discard workfn as well. It is most likely to happen after a relocation finishes which cancels discard, tears down the block group, etc. Fix this fully by taking the lock arou ---truncated---
CVE-2025-22125: In the Linux kernel, the following vulnerability has been resolved: md/raid1,raid10: don't ignore IO flags If blk-wbt is enabled by default, it's found that raid write performance is quite bad because all IO are throttled by wbt of underlying disks, due to flag REQ_IDLE is ignored. And turns out this behaviour exist since blk-wbt is introduced. Other than REQ_IDLE, other flags should not be ignored as well, for example REQ_META can be set for filesystems, clearing it can cause priority reverse problems; And REQ_NOWAIT should not be cleared as well, because io will wait instead of failing directly in underlying disks. Fix those problems by keep IO flags from master bio. Fises: f51d46d0e7cb ("md: add support for REQ_NOWAIT")
CVE-2025-22127: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix potential deadloop in prepare_compress_overwrite() Jan Prusakowski reported a kernel hang issue as below: When running xfstests on linux-next kernel (6.14.0-rc3, 6.12) I encountered a problem in generic/475 test where fsstress process gets blocked in __f2fs_write_data_pages() and the test hangs. The options I used are: MKFS_OPTIONS -- -O compression -O extra_attr -O project_quota -O quota /dev/vdc MOUNT_OPTIONS -- -o acl,user_xattr -o discard,compress_extension=* /dev/vdc /vdc INFO: task kworker/u8:0:11 blocked for more than 122 seconds. Not tainted 6.14.0-rc3-xfstests-lockdep #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u8:0 state:D stack:0 pid:11 tgid:11 ppid:2 task_flags:0x4208160 flags:0x00004000 Workqueue: writeback wb_workfn (flush-253:0) Call Trace: <TASK> __schedule+0x309/0x8e0 schedule+0x3a/0x100 schedule_preempt_disabled+0x15/0x30 __mutex_lock+0x59a/0xdb0 __f2fs_write_data_pages+0x3ac/0x400 do_writepages+0xe8/0x290 __writeback_single_inode+0x5c/0x360 writeback_sb_inodes+0x22f/0x570 wb_writeback+0xb0/0x410 wb_do_writeback+0x47/0x2f0 wb_workfn+0x5a/0x1c0 process_one_work+0x223/0x5b0 worker_thread+0x1d5/0x3c0 kthread+0xfd/0x230 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x1a/0x30 </TASK> The root cause is: once generic/475 starts toload error table to dm device, f2fs_prepare_compress_overwrite() will loop reading compressed cluster pages due to IO error, meanwhile it has held .writepages lock, it can block all other writeback tasks. Let's fix this issue w/ below changes: - add f2fs_handle_page_eio() in prepare_compress_overwrite() to detect IO error. - detect cp_error earler in f2fs_read_multi_pages().
CVE-2025-23129: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: Clear affinity hint before calling ath11k_pcic_free_irq() in error path If a shared IRQ is used by the driver due to platform limitation, then the IRQ affinity hint is set right after the allocation of IRQ vectors in ath11k_pci_alloc_msi(). This does no harm unless one of the functions requesting the IRQ fails and attempt to free the IRQ. This results in the below warning: WARNING: CPU: 7 PID: 349 at kernel/irq/manage.c:1929 free_irq+0x278/0x29c Call trace: free_irq+0x278/0x29c ath11k_pcic_free_irq+0x70/0x10c [ath11k] ath11k_pci_probe+0x800/0x820 [ath11k_pci] local_pci_probe+0x40/0xbc The warning is due to not clearing the affinity hint before freeing the IRQs. So to fix this issue, clear the IRQ affinity hint before calling ath11k_pcic_free_irq() in the error path. The affinity will be cleared once again further down the error path due to code organization, but that does no harm. Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-05266-QCAHSTSWPLZ_V2_TO_X86-1
CVE-2025-23130: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid panic once fallocation fails for pinfile syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2746! CPU: 0 UID: 0 PID: 5323 Comm: syz.0.0 Not tainted 6.13.0-rc2-syzkaller-00018-g7cb1b4663150 #0 RIP: 0010:get_new_segment fs/f2fs/segment.c:2746 [inline] RIP: 0010:new_curseg+0x1f52/0x1f70 fs/f2fs/segment.c:2876 Call Trace: <TASK> __allocate_new_segment+0x1ce/0x940 fs/f2fs/segment.c:3210 f2fs_allocate_new_section fs/f2fs/segment.c:3224 [inline] f2fs_allocate_pinning_section+0xfa/0x4e0 fs/f2fs/segment.c:3238 f2fs_expand_inode_data+0x696/0xca0 fs/f2fs/file.c:1830 f2fs_fallocate+0x537/0xa10 fs/f2fs/file.c:1940 vfs_fallocate+0x569/0x6e0 fs/open.c:327 do_vfs_ioctl+0x258c/0x2e40 fs/ioctl.c:885 __do_sys_ioctl fs/ioctl.c:904 [inline] __se_sys_ioctl+0x80/0x170 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Concurrent pinfile allocation may run out of free section, result in panic in get_new_segment(), let's expand pin_sem lock coverage to include f2fs_gc(), so that we can make sure to reclaim enough free space for following allocation. In addition, do below changes to enhance error path handling: - call f2fs_bug_on() only in non-pinfile allocation path in get_new_segment(). - call reset_curseg_fields() to reset all fields of curseg in new_curseg()
CVE-2025-23131: In the Linux kernel, the following vulnerability has been resolved: dlm: prevent NPD when writing a positive value to event_done do_uevent returns the value written to event_done. In case it is a positive value, new_lockspace would undo all the work, and lockspace would not be set. __dlm_new_lockspace, however, would treat that positive value as a success due to commit 8511a2728ab8 ("dlm: fix use count with multiple joins"). Down the line, device_create_lockspace would pass that NULL lockspace to dlm_find_lockspace_local, leading to a NULL pointer dereference. Treating such positive values as successes prevents the problem. Given this has been broken for so long, this is unlikely to break userspace expectations.
CVE-2025-23132: In the Linux kernel, the following vulnerability has been resolved: f2fs: quota: fix to avoid warning in dquot_writeback_dquots() F2FS-fs (dm-59): checkpoint=enable has some unwritten data. ------------[ cut here ]------------ WARNING: CPU: 6 PID: 8013 at fs/quota/dquot.c:691 dquot_writeback_dquots+0x2fc/0x308 pc : dquot_writeback_dquots+0x2fc/0x308 lr : f2fs_quota_sync+0xcc/0x1c4 Call trace: dquot_writeback_dquots+0x2fc/0x308 f2fs_quota_sync+0xcc/0x1c4 f2fs_write_checkpoint+0x3d4/0x9b0 f2fs_issue_checkpoint+0x1bc/0x2c0 f2fs_sync_fs+0x54/0x150 f2fs_do_sync_file+0x2f8/0x814 __f2fs_ioctl+0x1960/0x3244 f2fs_ioctl+0x54/0xe0 __arm64_sys_ioctl+0xa8/0xe4 invoke_syscall+0x58/0x114 checkpoint and f2fs_remount may race as below, resulting triggering warning in dquot_writeback_dquots(). atomic write remount - do_remount - down_write(&sb->s_umount); - f2fs_remount - ioctl - f2fs_do_sync_file - f2fs_sync_fs - f2fs_write_checkpoint - block_operations - locked = down_read_trylock(&sbi->sb->s_umount) : fail to lock due to the write lock was held by remount - up_write(&sb->s_umount); - f2fs_quota_sync - dquot_writeback_dquots - WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)) : trigger warning because s_umount lock was unlocked by remount If checkpoint comes from mount/umount/remount/freeze/quotactl, caller of checkpoint has already held s_umount lock, calling dquot_writeback_dquots() in the context should be safe. So let's record task to sbi->umount_lock_holder, so that checkpoint can know whether the lock has held in the context or not by checking current w/ it. In addition, in order to not misrepresent caller of checkpoint, we should not allow to trigger async checkpoint for those callers: mount/umount/remount/ freeze/quotactl.
CVE-2025-23133: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: update channel list in reg notifier instead reg worker Currently when ath11k gets a new channel list, it will be processed according to the following steps: 1. update new channel list to cfg80211 and queue reg_work. 2. cfg80211 handles new channel list during reg_work. 3. update cfg80211's handled channel list to firmware by ath11k_reg_update_chan_list(). But ath11k will immediately execute step 3 after reg_work is just queued. Since step 2 is asynchronous, cfg80211 may not have completed handling the new channel list, which may leading to an out-of-bounds write error: BUG: KASAN: slab-out-of-bounds in ath11k_reg_update_chan_list Call Trace: ath11k_reg_update_chan_list+0xbfe/0xfe0 [ath11k] kfree+0x109/0x3a0 ath11k_regd_update+0x1cf/0x350 [ath11k] ath11k_regd_update_work+0x14/0x20 [ath11k] process_one_work+0xe35/0x14c0 Should ensure step 2 is completely done before executing step 3. Thus Wen raised patch[1]. When flag NL80211_REGDOM_SET_BY_DRIVER is set, cfg80211 will notify ath11k after step 2 is done. So enable the flag NL80211_REGDOM_SET_BY_DRIVER then cfg80211 will notify ath11k after step 2 is done. At this time, there will be no KASAN bug during the execution of the step 3. [1] https://patchwork.kernel.org/project/linux-wireless/patch/20230201065313.27203-1-quic_wgong@quicinc.com/ Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3
CVE-2025-37747: In the Linux kernel, the following vulnerability has been resolved: perf: Fix hang while freeing sigtrap event Perf can hang while freeing a sigtrap event if a related deferred signal hadn't managed to be sent before the file got closed: perf_event_overflow() task_work_add(perf_pending_task) fput() task_work_add(____fput()) task_work_run() ____fput() perf_release() perf_event_release_kernel() _free_event() perf_pending_task_sync() task_work_cancel() -> FAILED rcuwait_wait_event() Once task_work_run() is running, the list of pending callbacks is removed from the task_struct and from this point on task_work_cancel() can't remove any pending and not yet started work items, hence the task_work_cancel() failure and the hang on rcuwait_wait_event(). Task work could be changed to remove one work at a time, so a work running on the current task can always cancel a pending one, however the wait / wake design is still subject to inverted dependencies when remote targets are involved, as pictured by Oleg: T1 T2 fd = perf_event_open(pid => T2->pid); fd = perf_event_open(pid => T1->pid); close(fd) close(fd) <IRQ> <IRQ> perf_event_overflow() perf_event_overflow() task_work_add(perf_pending_task) task_work_add(perf_pending_task) </IRQ> </IRQ> fput() fput() task_work_add(____fput()) task_work_add(____fput()) task_work_run() task_work_run() ____fput() ____fput() perf_release() perf_release() perf_event_release_kernel() perf_event_release_kernel() _free_event() _free_event() perf_pending_task_sync() perf_pending_task_sync() rcuwait_wait_event() rcuwait_wait_event() Therefore the only option left is to acquire the event reference count upon queueing the perf task work and release it from the task work, just like it was done before 3a5465418f5f ("perf: Fix event leak upon exec and file release") but without the leaks it fixed. Some adjustments are necessary to make it work: * A child event might dereference its parent upon freeing. Care must be taken to release the parent last. * Some places assuming the event doesn't have any reference held and therefore can be freed right away must instead put the reference and let the reference counting to its job.
CVE-2025-37750: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix UAF in decryption with multichannel After commit f7025d861694 ("smb: client: allocate crypto only for primary server") and commit b0abcd65ec54 ("smb: client: fix UAF in async decryption"), the channels started reusing AEAD TFM from primary channel to perform synchronous decryption, but that can't done as there could be multiple cifsd threads (one per channel) simultaneously accessing it to perform decryption. This fixes the following KASAN splat when running fstest generic/249 with 'vers=3.1.1,multichannel,max_channels=4,seal' against Windows Server 2022: BUG: KASAN: slab-use-after-free in gf128mul_4k_lle+0xba/0x110 Read of size 8 at addr ffff8881046c18a0 by task cifsd/986 CPU: 3 UID: 0 PID: 986 Comm: cifsd Not tainted 6.15.0-rc1 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-3.fc41 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x5d/0x80 print_report+0x156/0x528 ? gf128mul_4k_lle+0xba/0x110 ? __virt_addr_valid+0x145/0x300 ? __phys_addr+0x46/0x90 ? gf128mul_4k_lle+0xba/0x110 kasan_report+0xdf/0x1a0 ? gf128mul_4k_lle+0xba/0x110 gf128mul_4k_lle+0xba/0x110 ghash_update+0x189/0x210 shash_ahash_update+0x295/0x370 ? __pfx_shash_ahash_update+0x10/0x10 ? __pfx_shash_ahash_update+0x10/0x10 ? __pfx_extract_iter_to_sg+0x10/0x10 ? ___kmalloc_large_node+0x10e/0x180 ? __asan_memset+0x23/0x50 crypto_ahash_update+0x3c/0xc0 gcm_hash_assoc_remain_continue+0x93/0xc0 crypt_message+0xe09/0xec0 [cifs] ? __pfx_crypt_message+0x10/0x10 [cifs] ? _raw_spin_unlock+0x23/0x40 ? __pfx_cifs_readv_from_socket+0x10/0x10 [cifs] decrypt_raw_data+0x229/0x380 [cifs] ? __pfx_decrypt_raw_data+0x10/0x10 [cifs] ? __pfx_cifs_read_iter_from_socket+0x10/0x10 [cifs] smb3_receive_transform+0x837/0xc80 [cifs] ? __pfx_smb3_receive_transform+0x10/0x10 [cifs] ? __pfx___might_resched+0x10/0x10 ? __pfx_smb3_is_transform_hdr+0x10/0x10 [cifs] cifs_demultiplex_thread+0x692/0x1570 [cifs] ? __pfx_cifs_demultiplex_thread+0x10/0x10 [cifs] ? rcu_is_watching+0x20/0x50 ? rcu_lockdep_current_cpu_online+0x62/0xb0 ? find_held_lock+0x32/0x90 ? kvm_sched_clock_read+0x11/0x20 ? local_clock_noinstr+0xd/0xd0 ? trace_irq_enable.constprop.0+0xa8/0xe0 ? __pfx_cifs_demultiplex_thread+0x10/0x10 [cifs] kthread+0x1fe/0x380 ? kthread+0x10f/0x380 ? __pfx_kthread+0x10/0x10 ? local_clock_noinstr+0xd/0xd0 ? ret_from_fork+0x1b/0x60 ? local_clock+0x15/0x30 ? lock_release+0x29b/0x390 ? rcu_is_watching+0x20/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x60 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2025-37776: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in smb_break_all_levII_oplock() There is a room in smb_break_all_levII_oplock that can cause racy issues when unlocking in the middle of the loop. This patch use read lock to protect whole loop.
CVE-2025-37777: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free in __smb2_lease_break_noti() Move tcp_transport free to ksmbd_conn_free. If ksmbd connection is referenced when ksmbd server thread terminates, It will not be freed, but conn->tcp_transport is freed. __smb2_lease_break_noti can be performed asynchronously when the connection is disconnected. __smb2_lease_break_noti calls ksmbd_conn_write, which can cause use-after-free when conn->ksmbd_transport is already freed.
CVE-2025-37800: In the Linux kernel, the following vulnerability has been resolved: driver core: fix potential NULL pointer dereference in dev_uevent() If userspace reads "uevent" device attribute at the same time as another threads unbinds the device from its driver, change to dev->driver from a valid pointer to NULL may result in crash. Fix this by using READ_ONCE() when fetching the pointer, and take bus' drivers klist lock to make sure driver instance will not disappear while we access it. Use WRITE_ONCE() when setting the driver pointer to ensure there is no tearing.
CVE-2025-37802: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix WARNING "do not call blocking ops when !TASK_RUNNING" wait_event_timeout() will set the state of the current task to TASK_UNINTERRUPTIBLE, before doing the condition check. This means that ksmbd_durable_scavenger_alive() will try to acquire the mutex while already in a sleeping state. The scheduler warns us by giving the following warning: do not call blocking ops when !TASK_RUNNING; state=2 set at [<0000000061515a6f>] prepare_to_wait_event+0x9f/0x6c0 WARNING: CPU: 2 PID: 4147 at kernel/sched/core.c:10099 __might_sleep+0x12f/0x160 mutex lock is not needed in ksmbd_durable_scavenger_alive().
CVE-2025-37806: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Keep write operations atomic syzbot reported a NULL pointer dereference in __generic_file_write_iter. [1] Before the write operation is completed, the user executes ioctl[2] to clear the compress flag of the file, which causes the is_compressed() judgment to return 0, further causing the program to enter the wrong process and call the wrong ops ntfs_aops_cmpr, which triggers the null pointer dereference of write_begin. Use inode lock to synchronize ioctl and write to avoid this case. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x0000000086000006 EC = 0x21: IABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault user pgtable: 4k pages, 48-bit VAs, pgdp=000000011896d000 [0000000000000000] pgd=0800000118b44403, p4d=0800000118b44403, pud=0800000117517403, pmd=0000000000000000 Internal error: Oops: 0000000086000006 [#1] PREEMPT SMP Modules linked in: CPU: 0 UID: 0 PID: 6427 Comm: syz-executor347 Not tainted 6.13.0-rc3-syzkaller-g573067a5a685 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : 0x0 lr : generic_perform_write+0x29c/0x868 mm/filemap.c:4055 sp : ffff80009d4978a0 x29: ffff80009d4979c0 x28: dfff800000000000 x27: ffff80009d497bc8 x26: 0000000000000000 x25: ffff80009d497960 x24: ffff80008ba71c68 x23: 0000000000000000 x22: ffff0000c655dac0 x21: 0000000000001000 x20: 000000000000000c x19: 1ffff00013a92f2c x18: ffff0000e183aa1c x17: 0004060000000014 x16: ffff800083275834 x15: 0000000000000001 x14: 0000000000000000 x13: 0000000000000001 x12: ffff0000c655dac0 x11: 0000000000ff0100 x10: 0000000000ff0100 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffff80009d497980 x4 : ffff80009d497960 x3 : 0000000000001000 x2 : 0000000000000000 x1 : ffff0000e183a928 x0 : ffff0000d60b0fc0 Call trace: 0x0 (P) __generic_file_write_iter+0xfc/0x204 mm/filemap.c:4156 ntfs_file_write_iter+0x54c/0x630 fs/ntfs3/file.c:1267 new_sync_write fs/read_write.c:586 [inline] vfs_write+0x920/0xcf4 fs/read_write.c:679 ksys_write+0x15c/0x26c fs/read_write.c:731 __do_sys_write fs/read_write.c:742 [inline] __se_sys_write fs/read_write.c:739 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:739 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:744 el0t_64_sync_handler+0x84/0x108 arch/arm64/kernel/entry-common.c:762 [2] ioctl$FS_IOC_SETFLAGS(r0, 0x40086602, &(0x7f00000000c0)=0x20)
CVE-2025-37807: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix kmemleak warning for percpu hashmap Vlad Poenaru reported the following kmemleak issue: unreferenced object 0x606fd7c44ac8 (size 32): backtrace (crc 0): pcpu_alloc_noprof+0x730/0xeb0 bpf_map_alloc_percpu+0x69/0xc0 prealloc_init+0x9d/0x1b0 htab_map_alloc+0x363/0x510 map_create+0x215/0x3a0 __sys_bpf+0x16b/0x3e0 __x64_sys_bpf+0x18/0x20 do_syscall_64+0x7b/0x150 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Further investigation shows the reason is due to not 8-byte aligned store of percpu pointer in htab_elem_set_ptr(): *(void __percpu **)(l->key + key_size) = pptr; Note that the whole htab_elem alignment is 8 (for x86_64). If the key_size is 4, that means pptr is stored in a location which is 4 byte aligned but not 8 byte aligned. In mm/kmemleak.c, scan_block() scans the memory based on 8 byte stride, so it won't detect above pptr, hence reporting the memory leak. In htab_map_alloc(), we already have htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) htab->elem_size += sizeof(void *); else htab->elem_size += round_up(htab->map.value_size, 8); So storing pptr with 8-byte alignment won't cause any problem and can fix kmemleak too. The issue can be reproduced with bpf selftest as well: 1. Enable CONFIG_DEBUG_KMEMLEAK config 2. Add a getchar() before skel destroy in test_hash_map() in prog_tests/for_each.c. The purpose is to keep map available so kmemleak can be detected. 3. run './test_progs -t for_each/hash_map &' and a kmemleak should be reported.
CVE-2025-37833: In the Linux kernel, the following vulnerability has been resolved: net/niu: Niu requires MSIX ENTRY_DATA fields touch before entry reads Fix niu_try_msix() to not cause a fatal trap on sparc systems. Set PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST on the struct pci_dev to work around a bug in the hardware or firmware. For each vector entry in the msix table, niu chips will cause a fatal trap if any registers in that entry are read before that entries' ENTRY_DATA register is written to. Testing indicates writes to other registers are not sufficient to prevent the fatal trap, however the value does not appear to matter. This only needs to happen once after power up, so simply rebooting into a kernel lacking this fix will NOT cause the trap. NON-RESUMABLE ERROR: Reporting on cpu 64 NON-RESUMABLE ERROR: TPC [0x00000000005f6900] <msix_prepare_msi_desc+0x90/0xa0> NON-RESUMABLE ERROR: RAW [4010000000000016:00000e37f93e32ff:0000000202000080:ffffffffffffffff NON-RESUMABLE ERROR: 0000000800000000:0000000000000000:0000000000000000:0000000000000000] NON-RESUMABLE ERROR: handle [0x4010000000000016] stick [0x00000e37f93e32ff] NON-RESUMABLE ERROR: type [precise nonresumable] NON-RESUMABLE ERROR: attrs [0x02000080] < ASI sp-faulted priv > NON-RESUMABLE ERROR: raddr [0xffffffffffffffff] NON-RESUMABLE ERROR: insn effective address [0x000000c50020000c] NON-RESUMABLE ERROR: size [0x8] NON-RESUMABLE ERROR: asi [0x00] CPU: 64 UID: 0 PID: 745 Comm: kworker/64:1 Not tainted 6.11.5 #63 Workqueue: events work_for_cpu_fn TSTATE: 0000000011001602 TPC: 00000000005f6900 TNPC: 00000000005f6904 Y: 00000000 Not tainted TPC: <msix_prepare_msi_desc+0x90/0xa0> g0: 00000000000002e9 g1: 000000000000000c g2: 000000c50020000c g3: 0000000000000100 g4: ffff8000470307c0 g5: ffff800fec5be000 g6: ffff800047a08000 g7: 0000000000000000 o0: ffff800014feb000 o1: ffff800047a0b620 o2: 0000000000000011 o3: ffff800047a0b620 o4: 0000000000000080 o5: 0000000000000011 sp: ffff800047a0ad51 ret_pc: 00000000005f7128 RPC: <__pci_enable_msix_range+0x3cc/0x460> l0: 000000000000000d l1: 000000000000c01f l2: ffff800014feb0a8 l3: 0000000000000020 l4: 000000000000c000 l5: 0000000000000001 l6: 0000000020000000 l7: ffff800047a0b734 i0: ffff800014feb000 i1: ffff800047a0b730 i2: 0000000000000001 i3: 000000000000000d i4: 0000000000000000 i5: 0000000000000000 i6: ffff800047a0ae81 i7: 00000000101888b0 I7: <niu_try_msix.constprop.0+0xc0/0x130 [niu]> Call Trace: [<00000000101888b0>] niu_try_msix.constprop.0+0xc0/0x130 [niu] [<000000001018f840>] niu_get_invariants+0x183c/0x207c [niu] [<00000000101902fc>] niu_pci_init_one+0x27c/0x2fc [niu] [<00000000005ef3e4>] local_pci_probe+0x28/0x74 [<0000000000469240>] work_for_cpu_fn+0x8/0x1c [<000000000046b008>] process_scheduled_works+0x144/0x210 [<000000000046b518>] worker_thread+0x13c/0x1c0 [<00000000004710e0>] kthread+0xb8/0xc8 [<00000000004060c8>] ret_from_fork+0x1c/0x2c [<0000000000000000>] 0x0 Kernel panic - not syncing: Non-resumable error.
CVE-2025-37834: In the Linux kernel, the following vulnerability has been resolved: mm/vmscan: don't try to reclaim hwpoison folio Syzkaller reports a bug as follows: Injecting memory failure for pfn 0x18b00e at process virtual address 0x20ffd000 Memory failure: 0x18b00e: dirty swapcache page still referenced by 2 users Memory failure: 0x18b00e: recovery action for dirty swapcache page: Failed page: refcount:2 mapcount:0 mapping:0000000000000000 index:0x20ffd pfn:0x18b00e memcg:ffff0000dd6d9000 anon flags: 0x5ffffe00482011(locked|dirty|arch_1|swapbacked|hwpoison|node=0|zone=2|lastcpupid=0xfffff) raw: 005ffffe00482011 dead000000000100 dead000000000122 ffff0000e232a7c9 raw: 0000000000020ffd 0000000000000000 00000002ffffffff ffff0000dd6d9000 page dumped because: VM_BUG_ON_FOLIO(!folio_test_uptodate(folio)) ------------[ cut here ]------------ kernel BUG at mm/swap_state.c:184! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP Modules linked in: CPU: 0 PID: 60 Comm: kswapd0 Not tainted 6.6.0-gcb097e7de84e #3 Hardware name: linux,dummy-virt (DT) pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : add_to_swap+0xbc/0x158 lr : add_to_swap+0xbc/0x158 sp : ffff800087f37340 x29: ffff800087f37340 x28: fffffc00052c0380 x27: ffff800087f37780 x26: ffff800087f37490 x25: ffff800087f37c78 x24: ffff800087f377a0 x23: ffff800087f37c50 x22: 0000000000000000 x21: fffffc00052c03b4 x20: 0000000000000000 x19: fffffc00052c0380 x18: 0000000000000000 x17: 296f696c6f662865 x16: 7461646f7470755f x15: 747365745f6f696c x14: 6f6621284f494c4f x13: 0000000000000001 x12: ffff600036d8b97b x11: 1fffe00036d8b97a x10: ffff600036d8b97a x9 : dfff800000000000 x8 : 00009fffc9274686 x7 : ffff0001b6c5cbd3 x6 : 0000000000000001 x5 : ffff0000c25896c0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : ffff0000c25896c0 x0 : 0000000000000000 Call trace: add_to_swap+0xbc/0x158 shrink_folio_list+0x12ac/0x2648 shrink_inactive_list+0x318/0x948 shrink_lruvec+0x450/0x720 shrink_node_memcgs+0x280/0x4a8 shrink_node+0x128/0x978 balance_pgdat+0x4f0/0xb20 kswapd+0x228/0x438 kthread+0x214/0x230 ret_from_fork+0x10/0x20 I can reproduce this issue with the following steps: 1) When a dirty swapcache page is isolated by reclaim process and the page isn't locked, inject memory failure for the page. me_swapcache_dirty() clears uptodate flag and tries to delete from lru, but fails. Reclaim process will put the hwpoisoned page back to lru. 2) The process that maps the hwpoisoned page exits, the page is deleted the page will never be freed and will be in the lru forever. 3) If we trigger a reclaim again and tries to reclaim the page, add_to_swap() will trigger VM_BUG_ON_FOLIO due to the uptodate flag is cleared. To fix it, skip the hwpoisoned page in shrink_folio_list(). Besides, the hwpoison folio may not be unmapped by hwpoison_user_mappings() yet, unmap it in shrink_folio_list(), otherwise the folio will fail to be unmaped by hwpoison_user_mappings() since the folio isn't in lru list.
CVE-2025-37842: In the Linux kernel, the following vulnerability has been resolved: spi: fsl-qspi: use devm function instead of driver remove Driver use devm APIs to manage clk/irq/resources and register the spi controller, but the legacy remove function will be called first during device detach and trigger kernel panic. Drop the remove function and use devm_add_action_or_reset() for driver cleanup to ensure the release sequence. Trigger kernel panic on i.MX8MQ by echo 30bb0000.spi >/sys/bus/platform/drivers/fsl-quadspi/unbind
CVE-2025-37853: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: debugfs hang_hws skip GPU with MES debugfs hang_hws is used by GPU reset test with HWS, for MES this crash the kernel with NULL pointer access because dqm->packet_mgr is not setup for MES path. Skip GPU with MES for now, MES hang_hws debugfs interface will be supported later.
CVE-2025-37856: In the Linux kernel, the following vulnerability has been resolved: btrfs: harden block_group::bg_list against list_del() races As far as I can tell, these calls of list_del_init() on bg_list cannot run concurrently with btrfs_mark_bg_unused() or btrfs_mark_bg_to_reclaim(), as they are in transaction error paths and situations where the block group is readonly. However, if there is any chance at all of racing with mark_bg_unused(), or a different future user of bg_list, better to be safe than sorry. Otherwise we risk the following interleaving (bg_list refcount in parens) T1 (some random op) T2 (btrfs_mark_bg_unused) !list_empty(&bg->bg_list); (1) list_del_init(&bg->bg_list); (1) list_move_tail (1) btrfs_put_block_group (0) btrfs_delete_unused_bgs bg = list_first_entry list_del_init(&bg->bg_list); btrfs_put_block_group(bg); (-1) Ultimately, this results in a broken ref count that hits zero one deref early and the real final deref underflows the refcount, resulting in a WARNING.
CVE-2025-37860: In the Linux kernel, the following vulnerability has been resolved: sfc: fix NULL dereferences in ef100_process_design_param() Since cited commit, ef100_probe_main() and hence also ef100_check_design_params() run before efx->net_dev is created; consequently, we cannot netif_set_tso_max_size() or _segs() at this point. Move those netif calls to ef100_probe_netdev(), and also replace netif_err within the design params code with pci_err.
CVE-2025-37861: In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Synchronous access b/w reset and tm thread for reply queue When the task management thread processes reply queues while the reset thread resets them, the task management thread accesses an invalid queue ID (0xFFFF), set by the reset thread, which points to unallocated memory, causing a crash. Add flag 'io_admin_reset_sync' to synchronize access between the reset, I/O, and admin threads. Before a reset, the reset handler sets this flag to block I/O and admin processing threads. If any thread bypasses the initial check, the reset thread waits up to 10 seconds for processing to finish. If the wait exceeds 10 seconds, the controller is marked as unrecoverable.
CVE-2025-37864: In the Linux kernel, the following vulnerability has been resolved: net: dsa: clean up FDB, MDB, VLAN entries on unbind As explained in many places such as commit b117e1e8a86d ("net: dsa: delete dsa_legacy_fdb_add and dsa_legacy_fdb_del"), DSA is written given the assumption that higher layers have balanced additions/deletions. As such, it only makes sense to be extremely vocal when those assumptions are violated and the driver unbinds with entries still present. But Ido Schimmel points out a very simple situation where that is wrong: https://lore.kernel.org/netdev/ZDazSM5UsPPjQuKr@shredder/ (also briefly discussed by me in the aforementioned commit). Basically, while the bridge bypass operations are not something that DSA explicitly documents, and for the majority of DSA drivers this API simply causes them to go to promiscuous mode, that isn't the case for all drivers. Some have the necessary requirements for bridge bypass operations to do something useful - see dsa_switch_supports_uc_filtering(). Although in tools/testing/selftests/net/forwarding/local_termination.sh, we made an effort to popularize better mechanisms to manage address filters on DSA interfaces from user space - namely macvlan for unicast, and setsockopt(IP_ADD_MEMBERSHIP) - through mtools - for multicast, the fact is that 'bridge fdb add ... self static local' also exists as kernel UAPI, and might be useful to someone, even if only for a quick hack. It seems counter-productive to block that path by implementing shim .ndo_fdb_add and .ndo_fdb_del operations which just return -EOPNOTSUPP in order to prevent the ndo_dflt_fdb_add() and ndo_dflt_fdb_del() from running, although we could do that. Accepting that cleanup is necessary seems to be the only option. Especially since we appear to be coming back at this from a different angle as well. Russell King is noticing that the WARN_ON() triggers even for VLANs: https://lore.kernel.org/netdev/Z_li8Bj8bD4-BYKQ@shell.armlinux.org.uk/ What happens in the bug report above is that dsa_port_do_vlan_del() fails, then the VLAN entry lingers on, and then we warn on unbind and leak it. This is not a straight revert of the blamed commit, but we now add an informational print to the kernel log (to still have a way to see that bugs exist), and some extra comments gathered from past years' experience, to justify the logic.
CVE-2025-37880: In the Linux kernel, the following vulnerability has been resolved: um: work around sched_yield not yielding in time-travel mode sched_yield by a userspace may not actually cause scheduling in time-travel mode as no time has passed. In the case seen it appears to be a badly implemented userspace spinlock in ASAN. Unfortunately, with time-travel it causes an extreme slowdown or even deadlock depending on the kernel configuration (CONFIG_UML_MAX_USERSPACE_ITERATIONS). Work around it by accounting time to the process whenever it executes a sched_yield syscall.
CVE-2025-37893: In the Linux kernel, the following vulnerability has been resolved: LoongArch: BPF: Fix off-by-one error in build_prologue() Vincent reported that running BPF progs with tailcalls on LoongArch causes kernel hard lockup. Debugging the issues shows that the JITed image missing a jirl instruction at the end of the epilogue. There are two passes in JIT compiling, the first pass set the flags and the second pass generates JIT code based on those flags. With BPF progs mixing bpf2bpf and tailcalls, build_prologue() generates N insns in the first pass and then generates N+1 insns in the second pass. This makes epilogue_offset off by one and we will jump to some unexpected insn and cause lockup. Fix this by inserting a nop insn.
CVE-2025-37945: In the Linux kernel, the following vulnerability has been resolved: net: phy: allow MDIO bus PM ops to start/stop state machine for phylink-controlled PHY DSA has 2 kinds of drivers: 1. Those who call dsa_switch_suspend() and dsa_switch_resume() from their device PM ops: qca8k-8xxx, bcm_sf2, microchip ksz 2. Those who don't: all others. The above methods should be optional. For type 1, dsa_switch_suspend() calls dsa_user_suspend() -> phylink_stop(), and dsa_switch_resume() calls dsa_user_resume() -> phylink_start(). These seem good candidates for setting mac_managed_pm = true because that is essentially its definition [1], but that does not seem to be the biggest problem for now, and is not what this change focuses on. Talking strictly about the 2nd category of DSA drivers here (which do not have MAC managed PM, meaning that for their attached PHYs, mdio_bus_phy_suspend() and mdio_bus_phy_resume() should run in full), I have noticed that the following warning from mdio_bus_phy_resume() is triggered: WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY && phydev->state != PHY_UP); because the PHY state machine is running. It's running as a result of a previous dsa_user_open() -> ... -> phylink_start() -> phy_start() having been initiated by the user. The previous mdio_bus_phy_suspend() was supposed to have called phy_stop_machine(), but it didn't. So this is why the PHY is in state PHY_NOLINK by the time mdio_bus_phy_resume() runs. mdio_bus_phy_suspend() did not call phy_stop_machine() because for phylink, the phydev->adjust_link function pointer is NULL. This seems a technicality introduced by commit fddd91016d16 ("phylib: fix PAL state machine restart on resume"). That commit was written before phylink existed, and was intended to avoid crashing with consumer drivers which don't use the PHY state machine - phylink always does, when using a PHY. But phylink itself has historically not been developed with suspend/resume in mind, and apparently not tested too much in that scenario, allowing this bug to exist unnoticed for so long. Plus, prior to the WARN_ON(), it would have likely been invisible. This issue is not in fact restricted to type 2 DSA drivers (according to the above ad-hoc classification), but can be extrapolated to any MAC driver with phylink and MDIO-bus-managed PHY PM ops. DSA is just where the issue was reported. Assuming mac_managed_pm is set correctly, a quick search indicates the following other drivers might be affected: $ grep -Zlr PHYLINK_NETDEV drivers/ | xargs -0 grep -L mac_managed_pm drivers/net/ethernet/atheros/ag71xx.c drivers/net/ethernet/microchip/sparx5/sparx5_main.c drivers/net/ethernet/microchip/lan966x/lan966x_main.c drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c drivers/net/ethernet/freescale/dpaa/dpaa_eth.c drivers/net/ethernet/freescale/ucc_geth.c drivers/net/ethernet/freescale/enetc/enetc_pf_common.c drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c drivers/net/ethernet/marvell/mvneta.c drivers/net/ethernet/marvell/prestera/prestera_main.c drivers/net/ethernet/mediatek/mtk_eth_soc.c drivers/net/ethernet/altera/altera_tse_main.c drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c drivers/net/ethernet/meta/fbnic/fbnic_phylink.c drivers/net/ethernet/tehuti/tn40_phy.c drivers/net/ethernet/mscc/ocelot_net.c Make the existing conditions dependent on the PHY device having a phydev->phy_link_change() implementation equal to the default phy_link_change() provided by phylib. Otherwise, we implicitly know that the phydev has the phylink-provided phylink_phy_change() callback, and when phylink is used, the PHY state machine always needs to be stopped/ started on the suspend/resume path. The code is structured as such that if phydev->phy_link_change() is absent, it is a matter of time until the kernel will crash - no need to further complicate the test. Thus, for the situation where the PM is not managed b ---truncated---
CVE-2025-37952: In the Linux kernel, the following vulnerability has been resolved: ksmbd: Fix UAF in __close_file_table_ids A use-after-free is possible if one thread destroys the file via __ksmbd_close_fd while another thread holds a reference to it. The existing checks on fp->refcount are not sufficient to prevent this. The fix takes ft->lock around the section which removes the file from the file table. This prevents two threads acquiring the same file pointer via __close_file_table_ids, as well as the other functions which retrieve a file from the IDR and which already use this same lock.
CVE-2025-37956: In the Linux kernel, the following vulnerability has been resolved: ksmbd: prevent rename with empty string Client can send empty newname string to ksmbd server. It will cause a kernel oops from d_alloc. This patch return the error when attempting to rename a file or directory with an empty new name string.
CVE-2025-37957: In the Linux kernel, the following vulnerability has been resolved: KVM: SVM: Forcibly leave SMM mode on SHUTDOWN interception Previously, commit ed129ec9057f ("KVM: x86: forcibly leave nested mode on vCPU reset") addressed an issue where a triple fault occurring in nested mode could lead to use-after-free scenarios. However, the commit did not handle the analogous situation for System Management Mode (SMM). This omission results in triggering a WARN when KVM forces a vCPU INIT after SHUTDOWN interception while the vCPU is in SMM. This situation was reprodused using Syzkaller by: 1) Creating a KVM VM and vCPU 2) Sending a KVM_SMI ioctl to explicitly enter SMM 3) Executing invalid instructions causing consecutive exceptions and eventually a triple fault The issue manifests as follows: WARNING: CPU: 0 PID: 25506 at arch/x86/kvm/x86.c:12112 kvm_vcpu_reset+0x1d2/0x1530 arch/x86/kvm/x86.c:12112 Modules linked in: CPU: 0 PID: 25506 Comm: syz-executor.0 Not tainted 6.1.130-syzkaller-00157-g164fe5dde9b6 #0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 RIP: 0010:kvm_vcpu_reset+0x1d2/0x1530 arch/x86/kvm/x86.c:12112 Call Trace: <TASK> shutdown_interception+0x66/0xb0 arch/x86/kvm/svm/svm.c:2136 svm_invoke_exit_handler+0x110/0x530 arch/x86/kvm/svm/svm.c:3395 svm_handle_exit+0x424/0x920 arch/x86/kvm/svm/svm.c:3457 vcpu_enter_guest arch/x86/kvm/x86.c:10959 [inline] vcpu_run+0x2c43/0x5a90 arch/x86/kvm/x86.c:11062 kvm_arch_vcpu_ioctl_run+0x50f/0x1cf0 arch/x86/kvm/x86.c:11283 kvm_vcpu_ioctl+0x570/0xf00 arch/x86/kvm/../../../virt/kvm/kvm_main.c:4122 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x19a/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Architecturally, INIT is blocked when the CPU is in SMM, hence KVM's WARN() in kvm_vcpu_reset() to guard against KVM bugs, e.g. to detect improper emulation of INIT. SHUTDOWN on SVM is a weird edge case where KVM needs to do _something_ sane with the VMCB, since it's technically undefined, and INIT is the least awful choice given KVM's ABI. So, double down on stuffing INIT on SHUTDOWN, and force the vCPU out of SMM to avoid any weirdness (and the WARN). Found by Linux Verification Center (linuxtesting.org) with Syzkaller. [sean: massage changelog, make it clear this isn't architectural behavior]
CVE-2025-37977: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: exynos: Disable iocc if dma-coherent property isn't set If dma-coherent property isn't set then descriptors are non-cacheable and the iocc shareability bits should be disabled. Without this UFS can end up in an incompatible configuration and suffer from random cache related stability issues.
CVE-2025-37980: In the Linux kernel, the following vulnerability has been resolved: block: fix resource leak in blk_register_queue() error path When registering a queue fails after blk_mq_sysfs_register() is successful but the function later encounters an error, we need to clean up the blk_mq_sysfs resources. Add the missing blk_mq_sysfs_unregister() call in the error path to properly clean up these resources and prevent a memory leak.
CVE-2025-38006: In the Linux kernel, the following vulnerability has been resolved: net: mctp: Don't access ifa_index when missing In mctp_dump_addrinfo, ifa_index can be used to filter interfaces, but only when the struct ifaddrmsg is provided. Otherwise it will be comparing to uninitialised memory - reproducible in the syzkaller case from dhcpd, or busybox "ip addr show". The kernel MCTP implementation has always filtered by ifa_index, so existing userspace programs expecting to dump MCTP addresses must already be passing a valid ifa_index value (either 0 or a real index). BUG: KMSAN: uninit-value in mctp_dump_addrinfo+0x208/0xac0 net/mctp/device.c:128 mctp_dump_addrinfo+0x208/0xac0 net/mctp/device.c:128 rtnl_dump_all+0x3ec/0x5b0 net/core/rtnetlink.c:4380 rtnl_dumpit+0xd5/0x2f0 net/core/rtnetlink.c:6824 netlink_dump+0x97b/0x1690 net/netlink/af_netlink.c:2309
CVE-2025-38014: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Refactor remove call with idxd_cleanup() helper The idxd_cleanup() helper cleans up perfmon, interrupts, internals and so on. Refactor remove call with the idxd_cleanup() helper to avoid code duplication. Note, this also fixes the missing put_device() for idxd groups, enginces and wqs.
CVE-2025-38029: In the Linux kernel, the following vulnerability has been resolved: kasan: avoid sleepable page allocation from atomic context apply_to_pte_range() enters the lazy MMU mode and then invokes kasan_populate_vmalloc_pte() callback on each page table walk iteration. However, the callback can go into sleep when trying to allocate a single page, e.g. if an architecutre disables preemption on lazy MMU mode enter. On s390 if make arch_enter_lazy_mmu_mode() -> preempt_enable() and arch_leave_lazy_mmu_mode() -> preempt_disable(), such crash occurs: [ 0.663336] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:321 [ 0.663348] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2, name: kthreadd [ 0.663358] preempt_count: 1, expected: 0 [ 0.663366] RCU nest depth: 0, expected: 0 [ 0.663375] no locks held by kthreadd/2. [ 0.663383] Preemption disabled at: [ 0.663386] [<0002f3284cbb4eda>] apply_to_pte_range+0xfa/0x4a0 [ 0.663405] CPU: 0 UID: 0 PID: 2 Comm: kthreadd Not tainted 6.15.0-rc5-gcc-kasan-00043-gd76bb1ebb558-dirty #162 PREEMPT [ 0.663408] Hardware name: IBM 3931 A01 701 (KVM/Linux) [ 0.663409] Call Trace: [ 0.663410] [<0002f3284c385f58>] dump_stack_lvl+0xe8/0x140 [ 0.663413] [<0002f3284c507b9e>] __might_resched+0x66e/0x700 [ 0.663415] [<0002f3284cc4f6c0>] __alloc_frozen_pages_noprof+0x370/0x4b0 [ 0.663419] [<0002f3284ccc73c0>] alloc_pages_mpol+0x1a0/0x4a0 [ 0.663421] [<0002f3284ccc8518>] alloc_frozen_pages_noprof+0x88/0xc0 [ 0.663424] [<0002f3284ccc8572>] alloc_pages_noprof+0x22/0x120 [ 0.663427] [<0002f3284cc341ac>] get_free_pages_noprof+0x2c/0xc0 [ 0.663429] [<0002f3284cceba70>] kasan_populate_vmalloc_pte+0x50/0x120 [ 0.663433] [<0002f3284cbb4ef8>] apply_to_pte_range+0x118/0x4a0 [ 0.663435] [<0002f3284cbc7c14>] apply_to_pmd_range+0x194/0x3e0 [ 0.663437] [<0002f3284cbc99be>] __apply_to_page_range+0x2fe/0x7a0 [ 0.663440] [<0002f3284cbc9e88>] apply_to_page_range+0x28/0x40 [ 0.663442] [<0002f3284ccebf12>] kasan_populate_vmalloc+0x82/0xa0 [ 0.663445] [<0002f3284cc1578c>] alloc_vmap_area+0x34c/0xc10 [ 0.663448] [<0002f3284cc1c2a6>] __get_vm_area_node+0x186/0x2a0 [ 0.663451] [<0002f3284cc1e696>] __vmalloc_node_range_noprof+0x116/0x310 [ 0.663454] [<0002f3284cc1d950>] __vmalloc_node_noprof+0xd0/0x110 [ 0.663457] [<0002f3284c454b88>] alloc_thread_stack_node+0xf8/0x330 [ 0.663460] [<0002f3284c458d56>] dup_task_struct+0x66/0x4d0 [ 0.663463] [<0002f3284c45be90>] copy_process+0x280/0x4b90 [ 0.663465] [<0002f3284c460940>] kernel_clone+0xd0/0x4b0 [ 0.663467] [<0002f3284c46115e>] kernel_thread+0xbe/0xe0 [ 0.663469] [<0002f3284c4e440e>] kthreadd+0x50e/0x7f0 [ 0.663472] [<0002f3284c38c04a>] __ret_from_fork+0x8a/0xf0 [ 0.663475] [<0002f3284ed57ff2>] ret_from_fork+0xa/0x38 Instead of allocating single pages per-PTE, bulk-allocate the shadow memory prior to applying kasan_populate_vmalloc_pte() callback on a page range.
CVE-2025-38038: In the Linux kernel, the following vulnerability has been resolved: cpufreq: amd-pstate: Remove unnecessary driver_lock in set_boost set_boost is a per-policy function call, hence a driver wide lock is unnecessary. Also this mutex_acquire can collide with the mutex_acquire from the mode-switch path in status_store(), which can lead to a deadlock. So, remove it.
CVE-2025-38039: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Avoid WARN_ON when configuring MQPRIO with HTB offload enabled When attempting to enable MQPRIO while HTB offload is already configured, the driver currently returns `-EINVAL` and triggers a `WARN_ON`, leading to an unnecessary call trace. Update the code to handle this case more gracefully by returning `-EOPNOTSUPP` instead, while also providing a helpful user message.
CVE-2025-38041: In the Linux kernel, the following vulnerability has been resolved: clk: sunxi-ng: h616: Reparent GPU clock during frequency changes The H616 manual does not state that the GPU PLL supports dynamic frequency configuration, so we must take extra care when changing the frequency. Currently any attempt to do device DVFS on the GPU lead to panfrost various ooops, and GPU hangs. The manual describes the algorithm for changing the PLL frequency, which the CPU PLL notifier code already support, so we reuse that to reparent the GPU clock to GPU1 clock during frequency changes.
CVE-2025-38042: In the Linux kernel, the following vulnerability has been resolved: dmaengine: ti: k3-udma-glue: Drop skip_fdq argument from k3_udma_glue_reset_rx_chn The user of k3_udma_glue_reset_rx_chn() e.g. ti_am65_cpsw_nuss can run on multiple platforms having different DMA architectures. On some platforms there can be one FDQ for all flows in the RX channel while for others there is a separate FDQ for each flow in the RX channel. So far we have been relying on the skip_fdq argument of k3_udma_glue_reset_rx_chn(). Instead of relying on the user to provide this information, infer it based on DMA architecture during k3_udma_glue_request_rx_chn() and save it in an internal flag 'single_fdq'. Use that flag at k3_udma_glue_reset_rx_chn() to deicide if the FDQ needs to be cleared for every flow or just for flow 0. Fixes the below issue on ti_am65_cpsw_nuss driver on AM62-SK. > ip link set eth1 down > ip link set eth0 down > ethtool -L eth0 rx 8 > ip link set eth0 up > modprobe -r ti_am65_cpsw_nuss [ 103.045726] ------------[ cut here ]------------ [ 103.050505] k3_knav_desc_pool size 512000 != avail 64000 [ 103.050703] WARNING: CPU: 1 PID: 450 at drivers/net/ethernet/ti/k3-cppi-desc-pool.c:33 k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.068810] Modules linked in: ti_am65_cpsw_nuss(-) k3_cppi_desc_pool snd_soc_hdmi_codec crct10dif_ce snd_soc_simple_card snd_soc_simple_card_utils display_connector rtc_ti_k3 k3_j72xx_bandgap tidss drm_client_lib snd_soc_davinci_mcas p drm_dma_helper tps6598x phylink snd_soc_ti_udma rti_wdt drm_display_helper snd_soc_tlv320aic3x_i2c typec at24 phy_gmii_sel snd_soc_ti_edma snd_soc_tlv320aic3x sii902x snd_soc_ti_sdma sa2ul omap_mailbox drm_kms_helper authenc cfg80211 r fkill fuse drm drm_panel_orientation_quirks backlight ip_tables x_tables ipv6 [last unloaded: k3_cppi_desc_pool] [ 103.119950] CPU: 1 UID: 0 PID: 450 Comm: modprobe Not tainted 6.13.0-rc7-00001-g9c5e3435fa66 #1011 [ 103.119968] Hardware name: Texas Instruments AM625 SK (DT) [ 103.119974] pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 103.119983] pc : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.148007] lr : k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] [ 103.154709] sp : ffff8000826ebbc0 [ 103.158015] x29: ffff8000826ebbc0 x28: ffff0000090b6300 x27: 0000000000000000 [ 103.165145] x26: 0000000000000000 x25: 0000000000000000 x24: ffff0000019df6b0 [ 103.172271] x23: ffff0000019df6b8 x22: ffff0000019df410 x21: ffff8000826ebc88 [ 103.179397] x20: 000000000007d000 x19: ffff00000a3b3000 x18: 0000000000000000 [ 103.186522] x17: 0000000000000000 x16: 0000000000000000 x15: 000001e8c35e1cde [ 103.193647] x14: 0000000000000396 x13: 000000000000035c x12: 0000000000000000 [ 103.200772] x11: 000000000000003a x10: 00000000000009c0 x9 : ffff8000826eba20 [ 103.207897] x8 : ffff0000090b6d20 x7 : ffff00007728c180 x6 : ffff00007728c100 [ 103.215022] x5 : 0000000000000001 x4 : ffff000000508a50 x3 : ffff7ffff6146000 [ 103.222147] x2 : 0000000000000000 x1 : e300b4173ee6b200 x0 : 0000000000000000 [ 103.229274] Call trace: [ 103.231714] k3_cppi_desc_pool_destroy+0xa0/0xa8 [k3_cppi_desc_pool] (P) [ 103.238408] am65_cpsw_nuss_free_rx_chns+0x28/0x4c [ti_am65_cpsw_nuss] [ 103.244942] devm_action_release+0x14/0x20 [ 103.249040] release_nodes+0x3c/0x68 [ 103.252610] devres_release_all+0x8c/0xdc [ 103.256614] device_unbind_cleanup+0x18/0x60 [ 103.260876] device_release_driver_internal+0xf8/0x178 [ 103.266004] driver_detach+0x50/0x9c [ 103.269571] bus_remove_driver+0x6c/0xbc [ 103.273485] driver_unregister+0x30/0x60 [ 103.277401] platform_driver_unregister+0x14/0x20 [ 103.282096] am65_cpsw_nuss_driver_exit+0x18/0xff4 [ti_am65_cpsw_nuss] [ 103.288620] __arm64_sys_delete_module+0x17c/0x25c [ 103.293404] invoke_syscall+0x44/0x100 [ 103.297149] el0_svc_common.constprop.0+0xc0/0xe0 [ 103.301845] do_el0_svc+0x1c/0x28 [ 103.305155] el0_svc+0x28/0x98 ---truncated---
CVE-2025-38045: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: fix debug actions order The order of actions taken for debug was implemented incorrectly. Now we implemented the dump split and do the FW reset only in the middle of the dump (rather than the FW killing itself on error.) As a result, some of the actions taken when applying the config will now crash the device, so we need to fix the order.
CVE-2025-38059: In the Linux kernel, the following vulnerability has been resolved: btrfs: avoid NULL pointer dereference if no valid csum tree [BUG] When trying read-only scrub on a btrfs with rescue=idatacsums mount option, it will crash with the following call trace: BUG: kernel NULL pointer dereference, address: 0000000000000208 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page CPU: 1 UID: 0 PID: 835 Comm: btrfs Tainted: G O 6.15.0-rc3-custom+ #236 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022 RIP: 0010:btrfs_lookup_csums_bitmap+0x49/0x480 [btrfs] Call Trace: <TASK> scrub_find_fill_first_stripe+0x35b/0x3d0 [btrfs] scrub_simple_mirror+0x175/0x290 [btrfs] scrub_stripe+0x5f7/0x6f0 [btrfs] scrub_chunk+0x9a/0x150 [btrfs] scrub_enumerate_chunks+0x333/0x660 [btrfs] btrfs_scrub_dev+0x23e/0x600 [btrfs] btrfs_ioctl+0x1dcf/0x2f80 [btrfs] __x64_sys_ioctl+0x97/0xc0 do_syscall_64+0x4f/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e [CAUSE] Mount option "rescue=idatacsums" will completely skip loading the csum tree, so that any data read will not find any data csum thus we will ignore data checksum verification. Normally call sites utilizing csum tree will check the fs state flag NO_DATA_CSUMS bit, but unfortunately scrub does not check that bit at all. This results in scrub to call btrfs_search_slot() on a NULL pointer and triggered above crash. [FIX] Check both extent and csum tree root before doing any tree search.
CVE-2025-38064: In the Linux kernel, the following vulnerability has been resolved: virtio: break and reset virtio devices on device_shutdown() Hongyu reported a hang on kexec in a VM. QEMU reported invalid memory accesses during the hang. Invalid read at addr 0x102877002, size 2, region '(null)', reason: rejected Invalid write at addr 0x102877A44, size 2, region '(null)', reason: rejected ... It was traced down to virtio-console. Kexec works fine if virtio-console is not in use. The issue is that virtio-console continues to write to the MMIO even after underlying virtio-pci device is reset. Additionally, Eric noticed that IOMMUs are reset before devices, if devices are not reset on shutdown they continue to poke at guest memory and get errors from the IOMMU. Some devices get wedged then. The problem can be solved by breaking all virtio devices on virtio bus shutdown, then resetting them.
CVE-2025-38069: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-test: Fix double free that causes kernel to oops Fix a kernel oops found while testing the stm32_pcie Endpoint driver with handling of PERST# deassertion: During EP initialization, pci_epf_test_alloc_space() allocates all BARs, which are further freed if epc_set_bar() fails (for instance, due to no free inbound window). However, when pci_epc_set_bar() fails, the error path: pci_epc_set_bar() -> pci_epf_free_space() does not clear the previous assignment to epf_test->reg[bar]. Then, if the host reboots, the PERST# deassertion restarts the BAR allocation sequence with the same allocation failure (no free inbound window), creating a double free situation since epf_test->reg[bar] was deallocated and is still non-NULL. Thus, make sure that pci_epf_alloc_space() and pci_epf_free_space() invocations are symmetric, and as such, set epf_test->reg[bar] to NULL when memory is freed. [kwilczynski: commit log]
CVE-2025-38080: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Increase block_sequence array size [Why] It's possible to generate more than 50 steps in hwss_build_fast_sequence, for example with a 6-pipe asic where all pipes are in one MPC chain. This overflows the block_sequence buffer and corrupts block_sequence_steps, causing a crash. [How] Expand block_sequence to 100 items. A naive upper bound on the possible number of steps for a 6-pipe asic, ignoring the potential for steps to be mutually exclusive, is 91 with current code, therefore 100 is sufficient.
CVE-2025-38081: In the Linux kernel, the following vulnerability has been resolved: spi-rockchip: Fix register out of bounds access Do not write native chip select stuff for GPIO chip selects. GPIOs can be numbered much higher than native CS. Also, it makes no sense.
CVE-2025-38096: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: don't warn when if there is a FW error iwl_trans_reclaim is warning if it is called when the FW is not alive. But if it is called when there is a pending restart, i.e. after a FW error, there is no need to warn, instead - return silently.
CVE-2025-38105: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Kill timer properly at removal The USB-audio MIDI code initializes the timer, but in a rare case, the driver might be freed without the disconnect call. This leaves the timer in an active state while the assigned object is released via snd_usbmidi_free(), which ends up with a kernel warning when the debug configuration is enabled, as spotted by fuzzer. For avoiding the problem, put timer_shutdown_sync() at snd_usbmidi_free(), so that the timer can be killed properly. While we're at it, replace the existing timer_delete_sync() at the disconnect callback with timer_shutdown_sync(), too.
CVE-2025-38117: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Protect mgmt_pending list with its own lock This uses a mutex to protect from concurrent access of mgmt_pending list which can cause crashes like: ================================================================== BUG: KASAN: slab-use-after-free in hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91 Read of size 2 at addr ffff0000c48885b2 by task syz.4.334/7318 CPU: 0 UID: 0 PID: 7318 Comm: syz.4.334 Not tainted 6.15.0-rc7-syzkaller-g187899f4124a #0 PREEMPT Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025 Call trace: show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:466 (C) __dump_stack+0x30/0x40 lib/dump_stack.c:94 dump_stack_lvl+0xd8/0x12c lib/dump_stack.c:120 print_address_description+0xa8/0x254 mm/kasan/report.c:408 print_report+0x68/0x84 mm/kasan/report.c:521 kasan_report+0xb0/0x110 mm/kasan/report.c:634 __asan_report_load2_noabort+0x20/0x2c mm/kasan/report_generic.c:379 hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91 mgmt_pending_find+0x7c/0x140 net/bluetooth/mgmt_util.c:223 pending_find net/bluetooth/mgmt.c:947 [inline] remove_adv_monitor+0x44/0x1a4 net/bluetooth/mgmt.c:5445 hci_mgmt_cmd+0x780/0xc00 net/bluetooth/hci_sock.c:1712 hci_sock_sendmsg+0x544/0xbb0 net/bluetooth/hci_sock.c:1832 sock_sendmsg_nosec net/socket.c:712 [inline] __sock_sendmsg net/socket.c:727 [inline] sock_write_iter+0x25c/0x378 net/socket.c:1131 new_sync_write fs/read_write.c:591 [inline] vfs_write+0x62c/0x97c fs/read_write.c:684 ksys_write+0x120/0x210 fs/read_write.c:736 __do_sys_write fs/read_write.c:747 [inline] __se_sys_write fs/read_write.c:744 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:744 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600 Allocated by task 7037: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x44/0x54 mm/kasan/generic.c:562 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x9c/0xb4 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __do_kmalloc_node mm/slub.c:4327 [inline] __kmalloc_noprof+0x2fc/0x4c8 mm/slub.c:4339 kmalloc_noprof include/linux/slab.h:909 [inline] sk_prot_alloc+0xc4/0x1f0 net/core/sock.c:2198 sk_alloc+0x44/0x3ac net/core/sock.c:2254 bt_sock_alloc+0x4c/0x300 net/bluetooth/af_bluetooth.c:148 hci_sock_create+0xa8/0x194 net/bluetooth/hci_sock.c:2202 bt_sock_create+0x14c/0x24c net/bluetooth/af_bluetooth.c:132 __sock_create+0x43c/0x91c net/socket.c:1541 sock_create net/socket.c:1599 [inline] __sys_socket_create net/socket.c:1636 [inline] __sys_socket+0xd4/0x1c0 net/socket.c:1683 __do_sys_socket net/socket.c:1697 [inline] __se_sys_socket net/socket.c:1695 [inline] __arm64_sys_socket+0x7c/0x94 net/socket.c:1695 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600 Freed by task 6607: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:576 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x68/0x88 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline ---truncated---
CVE-2025-38127: In the Linux kernel, the following vulnerability has been resolved: ice: fix Tx scheduler error handling in XDP callback When the XDP program is loaded, the XDP callback adds new Tx queues. This means that the callback must update the Tx scheduler with the new queue number. In the event of a Tx scheduler failure, the XDP callback should also fail and roll back any changes previously made for XDP preparation. The previous implementation had a bug that not all changes made by the XDP callback were rolled back. This caused the crash with the following call trace: [ +9.549584] ice 0000:ca:00.0: Failed VSI LAN queue config for XDP, error: -5 [ +0.382335] Oops: general protection fault, probably for non-canonical address 0x50a2250a90495525: 0000 [#1] SMP NOPTI [ +0.010710] CPU: 103 UID: 0 PID: 0 Comm: swapper/103 Not tainted 6.14.0-net-next-mar-31+ #14 PREEMPT(voluntary) [ +0.010175] Hardware name: Intel Corporation M50CYP2SBSTD/M50CYP2SBSTD, BIOS SE5C620.86B.01.01.0005.2202160810 02/16/2022 [ +0.010946] RIP: 0010:__ice_update_sample+0x39/0xe0 [ice] [...] [ +0.002715] Call Trace: [ +0.002452] <IRQ> [ +0.002021] ? __die_body.cold+0x19/0x29 [ +0.003922] ? die_addr+0x3c/0x60 [ +0.003319] ? exc_general_protection+0x17c/0x400 [ +0.004707] ? asm_exc_general_protection+0x26/0x30 [ +0.004879] ? __ice_update_sample+0x39/0xe0 [ice] [ +0.004835] ice_napi_poll+0x665/0x680 [ice] [ +0.004320] __napi_poll+0x28/0x190 [ +0.003500] net_rx_action+0x198/0x360 [ +0.003752] ? update_rq_clock+0x39/0x220 [ +0.004013] handle_softirqs+0xf1/0x340 [ +0.003840] ? sched_clock_cpu+0xf/0x1f0 [ +0.003925] __irq_exit_rcu+0xc2/0xe0 [ +0.003665] common_interrupt+0x85/0xa0 [ +0.003839] </IRQ> [ +0.002098] <TASK> [ +0.002106] asm_common_interrupt+0x26/0x40 [ +0.004184] RIP: 0010:cpuidle_enter_state+0xd3/0x690 Fix this by performing the missing unmapping of XDP queues from q_vectors and setting the XDP rings pointer back to NULL after all those queues are released. Also, add an immediate exit from the XDP callback in case of ring preparation failure.
CVE-2025-38132: In the Linux kernel, the following vulnerability has been resolved: coresight: holding cscfg_csdev_lock while removing cscfg from csdev There'll be possible race scenario for coresight config: CPU0 CPU1 (perf enable) load module cscfg_load_config_sets() activate config. // sysfs (sys_active_cnt == 1) ... cscfg_csdev_enable_active_config() lock(csdev->cscfg_csdev_lock) deactivate config // sysfs (sys_activec_cnt == 0) cscfg_unload_config_sets() <iterating config_csdev_list> cscfg_remove_owned_csdev_configs() // here load config activate by CPU1 unlock(csdev->cscfg_csdev_lock) iterating config_csdev_list could be raced with config_csdev_list's entry delete. To resolve this race , hold csdev->cscfg_csdev_lock() while cscfg_remove_owned_csdev_configs()
CVE-2025-38140: In the Linux kernel, the following vulnerability has been resolved: dm: limit swapping tables for devices with zone write plugs dm_revalidate_zones() only allowed new or previously unzoned devices to call blk_revalidate_disk_zones(). If the device was already zoned, disk->nr_zones would always equal md->nr_zones, so dm_revalidate_zones() returned without doing any work. This would make the zoned settings for the device not match the new table. If the device had zone write plug resources, it could run into errors like bdev_zone_is_seq() reading invalid memory because disk->conv_zones_bitmap was the wrong size. If the device doesn't have any zone write plug resources, calling blk_revalidate_disk_zones() will always correctly update device. If blk_revalidate_disk_zones() fails, it can still overwrite or clear the current disk->nr_zones value. In this case, DM must restore the previous value of disk->nr_zones, so that the zoned settings will continue to match the previous value that it fell back to. If the device already has zone write plug resources, blk_revalidate_disk_zones() will not correctly update them, if it is called for arbitrary zoned device changes. Since there is not much need for this ability, the easiest solution is to disallow any table reloads that change the zoned settings, for devices that already have zone plug resources. Specifically, if a device already has zone plug resources allocated, it can only switch to another zoned table that also emulates zone append. Also, it cannot change the device size or the zone size. A device can switch to an error target.
CVE-2025-38162: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: prevent overflow in lookup table allocation When calculating the lookup table size, ensure the following multiplication does not overflow: - desc->field_len[] maximum value is U8_MAX multiplied by NFT_PIPAPO_GROUPS_PER_BYTE(f) that can be 2, worst case. - NFT_PIPAPO_BUCKETS(f->bb) is 2^8, worst case. - sizeof(unsigned long), from sizeof(*f->lt), lt in struct nft_pipapo_field. Then, use check_mul_overflow() to multiply by bucket size and then use check_add_overflow() to the alignment for avx2 (if needed). Finally, add lt_size_check_overflow() helper and use it to consolidate this. While at it, replace leftover allocation using the GFP_KERNEL to GFP_KERNEL_ACCOUNT for consistency, in pipapo_resize().
CVE-2025-38182: In the Linux kernel, the following vulnerability has been resolved: ublk: santizize the arguments from userspace when adding a device Sanity check the values for queue depth and number of queues we get from userspace when adding a device.
CVE-2025-38192: In the Linux kernel, the following vulnerability has been resolved: net: clear the dst when changing skb protocol A not-so-careful NAT46 BPF program can crash the kernel if it indiscriminately flips ingress packets from v4 to v6: BUG: kernel NULL pointer dereference, address: 0000000000000000 ip6_rcv_core (net/ipv6/ip6_input.c:190:20) ipv6_rcv (net/ipv6/ip6_input.c:306:8) process_backlog (net/core/dev.c:6186:4) napi_poll (net/core/dev.c:6906:9) net_rx_action (net/core/dev.c:7028:13) do_softirq (kernel/softirq.c:462:3) netif_rx (net/core/dev.c:5326:3) dev_loopback_xmit (net/core/dev.c:4015:2) ip_mc_finish_output (net/ipv4/ip_output.c:363:8) NF_HOOK (./include/linux/netfilter.h:314:9) ip_mc_output (net/ipv4/ip_output.c:400:5) dst_output (./include/net/dst.h:459:9) ip_local_out (net/ipv4/ip_output.c:130:9) ip_send_skb (net/ipv4/ip_output.c:1496:8) udp_send_skb (net/ipv4/udp.c:1040:8) udp_sendmsg (net/ipv4/udp.c:1328:10) The output interface has a 4->6 program attached at ingress. We try to loop the multicast skb back to the sending socket. Ingress BPF runs as part of netif_rx(), pushes a valid v6 hdr and changes skb->protocol to v6. We enter ip6_rcv_core which tries to use skb_dst(). But the dst is still an IPv4 one left after IPv4 mcast output. Clear the dst in all BPF helpers which change the protocol. Try to preserve metadata dsts, those may carry non-routing metadata.
CVE-2025-38195: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Fix panic caused by NULL-PMD in huge_pte_offset() ERROR INFO: CPU 25 Unable to handle kernel paging request at virtual address 0x0 ... Call Trace: [<900000000023c30c>] huge_pte_offset+0x3c/0x58 [<900000000057fd4c>] hugetlb_follow_page_mask+0x74/0x438 [<900000000051fee8>] __get_user_pages+0xe0/0x4c8 [<9000000000522414>] faultin_page_range+0x84/0x380 [<9000000000564e8c>] madvise_vma_behavior+0x534/0xa48 [<900000000056689c>] do_madvise+0x1bc/0x3e8 [<9000000000566df4>] sys_madvise+0x24/0x38 [<90000000015b9e88>] do_syscall+0x78/0x98 [<9000000000221f18>] handle_syscall+0xb8/0x158 In some cases, pmd may be NULL and rely on NULL as the return value for processing, so it is necessary to determine this situation here.
CVE-2025-38203: In the Linux kernel, the following vulnerability has been resolved: jfs: Fix null-ptr-deref in jfs_ioc_trim [ Syzkaller Report ] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000087: 0000 [#1 KASAN: null-ptr-deref in range [0x0000000000000438-0x000000000000043f] CPU: 2 UID: 0 PID: 10614 Comm: syz-executor.0 Not tainted 6.13.0-rc6-gfbfd64d25c7a-dirty #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Sched_ext: serialise (enabled+all), task: runnable_at=-30ms RIP: 0010:jfs_ioc_trim+0x34b/0x8f0 Code: e7 e8 59 a4 87 fe 4d 8b 24 24 4d 8d bc 24 38 04 00 00 48 8d 93 90 82 fe ff 4c 89 ff 31 f6 RSP: 0018:ffffc900055f7cd0 EFLAGS: 00010206 RAX: 0000000000000087 RBX: 00005866a9e67ff8 RCX: 000000000000000a RDX: 0000000000000001 RSI: 0000000000000004 RDI: 0000000000000001 RBP: dffffc0000000000 R08: ffff88807c180003 R09: 1ffff1100f830000 R10: dffffc0000000000 R11: ffffed100f830001 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000438 FS: 00007fe520225640(0000) GS:ffff8880b7e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005593c91b2c88 CR3: 000000014927c000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __die_body+0x61/0xb0 ? die_addr+0xb1/0xe0 ? exc_general_protection+0x333/0x510 ? asm_exc_general_protection+0x26/0x30 ? jfs_ioc_trim+0x34b/0x8f0 jfs_ioctl+0x3c8/0x4f0 ? __pfx_jfs_ioctl+0x10/0x10 ? __pfx_jfs_ioctl+0x10/0x10 __se_sys_ioctl+0x269/0x350 ? __pfx___se_sys_ioctl+0x10/0x10 ? do_syscall_64+0xfb/0x210 do_syscall_64+0xee/0x210 ? syscall_exit_to_user_mode+0x1e0/0x330 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fe51f4903ad Code: c3 e8 a7 2b 00 00 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d RSP: 002b:00007fe5202250c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fe51f5cbf80 RCX: 00007fe51f4903ad RDX: 0000000020000680 RSI: 00000000c0185879 RDI: 0000000000000005 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe520225640 R13: 000000000000000e R14: 00007fe51f44fca0 R15: 00007fe52021d000 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:jfs_ioc_trim+0x34b/0x8f0 Code: e7 e8 59 a4 87 fe 4d 8b 24 24 4d 8d bc 24 38 04 00 00 48 8d 93 90 82 fe ff 4c 89 ff 31 f6 RSP: 0018:ffffc900055f7cd0 EFLAGS: 00010206 RAX: 0000000000000087 RBX: 00005866a9e67ff8 RCX: 000000000000000a RDX: 0000000000000001 RSI: 0000000000000004 RDI: 0000000000000001 RBP: dffffc0000000000 R08: ffff88807c180003 R09: 1ffff1100f830000 R10: dffffc0000000000 R11: ffffed100f830001 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000438 FS: 00007fe520225640(0000) GS:ffff8880b7e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005593c91b2c88 CR3: 000000014927c000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Kernel panic - not syncing: Fatal exception [ Analysis ] We believe that we have found a concurrency bug in the `fs/jfs` module that results in a null pointer dereference. There is a closely related issue which has been fixed: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=d6c1b3599b2feb5c7291f5ac3a36e5fa7cedb234 ... but, unfortunately, the accepted patch appears to still be susceptible to a null pointer dereference under some interleavings. To trigger the bug, we think that `JFS_SBI(ipbmap->i_sb)->bmap` is set to NULL in `dbFreeBits` and then dereferenced in `jfs_ioc_trim`. This bug manifests quite rarely under normal circumstances, but is triggereable from a syz-program.
CVE-2025-38204: In the Linux kernel, the following vulnerability has been resolved: jfs: fix array-index-out-of-bounds read in add_missing_indices stbl is s8 but it must contain offsets into slot which can go from 0 to 127. Added a bound check for that error and return -EIO if the check fails. Also make jfs_readdir return with error if add_missing_indices returns with an error.
CVE-2025-38206: In the Linux kernel, the following vulnerability has been resolved: exfat: fix double free in delayed_free The double free could happen in the following path. exfat_create_upcase_table() exfat_create_upcase_table() : return error exfat_free_upcase_table() : free ->vol_utbl exfat_load_default_upcase_table : return error exfat_kill_sb() delayed_free() exfat_free_upcase_table() <--------- double free This patch set ->vol_util as NULL after freeing it.
CVE-2025-38207: In the Linux kernel, the following vulnerability has been resolved: mm: fix uprobe pte be overwritten when expanding vma Patch series "Fix uprobe pte be overwritten when expanding vma". This patch (of 4): We encountered a BUG alert triggered by Syzkaller as follows: BUG: Bad rss-counter state mm:00000000b4a60fca type:MM_ANONPAGES val:1 And we can reproduce it with the following steps: 1. register uprobe on file at zero offset 2. mmap the file at zero offset: addr1 = mmap(NULL, 2 * 4096, PROT_NONE, MAP_PRIVATE, fd, 0); 3. mremap part of vma1 to new vma2: addr2 = mremap(addr1, 4096, 2 * 4096, MREMAP_MAYMOVE); 4. mremap back to orig addr1: mremap(addr2, 4096, 4096, MREMAP_MAYMOVE | MREMAP_FIXED, addr1); In step 3, the vma1 range [addr1, addr1 + 4096] will be remap to new vma2 with range [addr2, addr2 + 8192], and remap uprobe anon page from the vma1 to vma2, then unmap the vma1 range [addr1, addr1 + 4096]. In step 4, the vma2 range [addr2, addr2 + 4096] will be remap back to the addr range [addr1, addr1 + 4096]. Since the addr range [addr1 + 4096, addr1 + 8192] still maps the file, it will take vma_merge_new_range to expand the range, and then do uprobe_mmap in vma_complete. Since the merged vma pgoff is also zero offset, it will install uprobe anon page to the merged vma. However, the upcomming move_page_tables step, which use set_pte_at to remap the vma2 uprobe pte to the merged vma, will overwrite the newly uprobe pte in the merged vma, and lead that pte to be orphan. Since the uprobe pte will be remapped to the merged vma, we can remove the unnecessary uprobe_mmap upon merged vma. This problem was first found in linux-6.6.y and also exists in the community syzkaller: https://lore.kernel.org/all/000000000000ada39605a5e71711@google.com/T/
CVE-2025-38234: In the Linux kernel, the following vulnerability has been resolved: sched/rt: Fix race in push_rt_task Overview ======== When a CPU chooses to call push_rt_task and picks a task to push to another CPU's runqueue then it will call find_lock_lowest_rq method which would take a double lock on both CPUs' runqueues. If one of the locks aren't readily available, it may lead to dropping the current runqueue lock and reacquiring both the locks at once. During this window it is possible that the task is already migrated and is running on some other CPU. These cases are already handled. However, if the task is migrated and has already been executed and another CPU is now trying to wake it up (ttwu) such that it is queued again on the runqeue (on_rq is 1) and also if the task was run by the same CPU, then the current checks will pass even though the task was migrated out and is no longer in the pushable tasks list. Crashes ======= This bug resulted in quite a few flavors of crashes triggering kernel panics with various crash signatures such as assert failures, page faults, null pointer dereferences, and queue corruption errors all coming from scheduler itself. Some of the crashes: -> kernel BUG at kernel/sched/rt.c:1616! BUG_ON(idx >= MAX_RT_PRIO) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? pick_next_task_rt+0x6e/0x1d0 ? do_error_trap+0x64/0xa0 ? pick_next_task_rt+0x6e/0x1d0 ? exc_invalid_op+0x4c/0x60 ? pick_next_task_rt+0x6e/0x1d0 ? asm_exc_invalid_op+0x12/0x20 ? pick_next_task_rt+0x6e/0x1d0 __schedule+0x5cb/0x790 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: kernel NULL pointer dereference, address: 00000000000000c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? __warn+0x8a/0xe0 ? exc_page_fault+0x3d6/0x520 ? asm_exc_page_fault+0x1e/0x30 ? pick_next_task_rt+0xb5/0x1d0 ? pick_next_task_rt+0x8c/0x1d0 __schedule+0x583/0x7e0 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: unable to handle page fault for address: ffff9464daea5900 kernel BUG at kernel/sched/rt.c:1861! BUG_ON(rq->cpu != task_cpu(p)) -> kernel BUG at kernel/sched/rt.c:1055! BUG_ON(!rq->nr_running) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? dequeue_top_rt_rq+0xa2/0xb0 ? do_error_trap+0x64/0xa0 ? dequeue_top_rt_rq+0xa2/0xb0 ? exc_invalid_op+0x4c/0x60 ? dequeue_top_rt_rq+0xa2/0xb0 ? asm_exc_invalid_op+0x12/0x20 ? dequeue_top_rt_rq+0xa2/0xb0 dequeue_rt_entity+0x1f/0x70 dequeue_task_rt+0x2d/0x70 __schedule+0x1a8/0x7e0 ? blk_finish_plug+0x25/0x40 schedule+0x3c/0xb0 futex_wait_queue_me+0xb6/0x120 futex_wait+0xd9/0x240 do_futex+0x344/0xa90 ? get_mm_exe_file+0x30/0x60 ? audit_exe_compare+0x58/0x70 ? audit_filter_rules.constprop.26+0x65e/0x1220 __x64_sys_futex+0x148/0x1f0 do_syscall_64+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x62/0xc7 -> BUG: unable to handle page fault for address: ffff8cf3608bc2c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? spurious_kernel_fault+0x171/0x1c0 ? exc_page_fault+0x3b6/0x520 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? asm_exc_page_fault+0x1e/0x30 ? _cond_resched+0x15/0x30 ? futex_wait_queue_me+0xc8/0x120 ? futex_wait+0xd9/0x240 ? try_to_wake_up+0x1b8/0x490 ? futex_wake+0x78/0x160 ? do_futex+0xcd/0xa90 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? plist_del+0x6a/0xd0 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? dequeue_pushable_task+0x20/0x70 ? __schedule+0x382/0x7e0 ? asm_sysvec_reschedule_i ---truncated---
CVE-2025-38237: In the Linux kernel, the following vulnerability has been resolved: media: platform: exynos4-is: Add hardware sync wait to fimc_is_hw_change_mode() In fimc_is_hw_change_mode(), the function changes camera modes without waiting for hardware completion, risking corrupted data or system hangs if subsequent operations proceed before the hardware is ready. Add fimc_is_hw_wait_intmsr0_intmsd0() after mode configuration, ensuring hardware state synchronization and stable interrupt handling.
CVE-2025-38244: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential deadlock when reconnecting channels Fix cifs_signal_cifsd_for_reconnect() to take the correct lock order and prevent the following deadlock from happening ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc3-build2+ #1301 Tainted: G S W ------------------------------------------------------ cifsd/6055 is trying to acquire lock: ffff88810ad56038 (&tcp_ses->srv_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x134/0x200 but task is already holding lock: ffff888119c64330 (&ret_buf->chan_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0xcf/0x200 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&ret_buf->chan_lock){+.+.}-{3:3}: validate_chain+0x1cf/0x270 __lock_acquire+0x60e/0x780 lock_acquire.part.0+0xb4/0x1f0 _raw_spin_lock+0x2f/0x40 cifs_setup_session+0x81/0x4b0 cifs_get_smb_ses+0x771/0x900 cifs_mount_get_session+0x7e/0x170 cifs_mount+0x92/0x2d0 cifs_smb3_do_mount+0x161/0x460 smb3_get_tree+0x55/0x90 vfs_get_tree+0x46/0x180 do_new_mount+0x1b0/0x2e0 path_mount+0x6ee/0x740 do_mount+0x98/0xe0 __do_sys_mount+0x148/0x180 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (&ret_buf->ses_lock){+.+.}-{3:3}: validate_chain+0x1cf/0x270 __lock_acquire+0x60e/0x780 lock_acquire.part.0+0xb4/0x1f0 _raw_spin_lock+0x2f/0x40 cifs_match_super+0x101/0x320 sget+0xab/0x270 cifs_smb3_do_mount+0x1e0/0x460 smb3_get_tree+0x55/0x90 vfs_get_tree+0x46/0x180 do_new_mount+0x1b0/0x2e0 path_mount+0x6ee/0x740 do_mount+0x98/0xe0 __do_sys_mount+0x148/0x180 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #0 (&tcp_ses->srv_lock){+.+.}-{3:3}: check_noncircular+0x95/0xc0 check_prev_add+0x115/0x2f0 validate_chain+0x1cf/0x270 __lock_acquire+0x60e/0x780 lock_acquire.part.0+0xb4/0x1f0 _raw_spin_lock+0x2f/0x40 cifs_signal_cifsd_for_reconnect+0x134/0x200 __cifs_reconnect+0x8f/0x500 cifs_handle_standard+0x112/0x280 cifs_demultiplex_thread+0x64d/0xbc0 kthread+0x2f7/0x310 ret_from_fork+0x2a/0x230 ret_from_fork_asm+0x1a/0x30 other info that might help us debug this: Chain exists of: &tcp_ses->srv_lock --> &ret_buf->ses_lock --> &ret_buf->chan_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&ret_buf->chan_lock); lock(&ret_buf->ses_lock); lock(&ret_buf->chan_lock); lock(&tcp_ses->srv_lock); *** DEADLOCK *** 3 locks held by cifsd/6055: #0: ffffffff857de398 (&cifs_tcp_ses_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x7b/0x200 #1: ffff888119c64060 (&ret_buf->ses_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x9c/0x200 #2: ffff888119c64330 (&ret_buf->chan_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0xcf/0x200
CVE-2025-38246: In the Linux kernel, the following vulnerability has been resolved: bnxt: properly flush XDP redirect lists We encountered following crash when testing a XDP_REDIRECT feature in production: [56251.579676] list_add corruption. next->prev should be prev (ffff93120dd40f30), but was ffffb301ef3a6740. (next=ffff93120dd 40f30). [56251.601413] ------------[ cut here ]------------ [56251.611357] kernel BUG at lib/list_debug.c:29! [56251.621082] Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [56251.632073] CPU: 111 UID: 0 PID: 0 Comm: swapper/111 Kdump: loaded Tainted: P O 6.12.33-cloudflare-2025.6. 3 #1 [56251.653155] Tainted: [P]=PROPRIETARY_MODULE, [O]=OOT_MODULE [56251.663877] Hardware name: MiTAC GC68B-B8032-G11P6-GPU/S8032GM-HE-CFR, BIOS V7.020.B10-sig 01/22/2025 [56251.682626] RIP: 0010:__list_add_valid_or_report+0x4b/0xa0 [56251.693203] Code: 0e 48 c7 c7 68 e7 d9 97 e8 42 16 fe ff 0f 0b 48 8b 52 08 48 39 c2 74 14 48 89 f1 48 c7 c7 90 e7 d9 97 48 89 c6 e8 25 16 fe ff <0f> 0b 4c 8b 02 49 39 f0 74 14 48 89 d1 48 c7 c7 e8 e7 d9 97 4c 89 [56251.725811] RSP: 0018:ffff93120dd40b80 EFLAGS: 00010246 [56251.736094] RAX: 0000000000000075 RBX: ffffb301e6bba9d8 RCX: 0000000000000000 [56251.748260] RDX: 0000000000000000 RSI: ffff9149afda0b80 RDI: ffff9149afda0b80 [56251.760349] RBP: ffff9131e49c8000 R08: 0000000000000000 R09: ffff93120dd40a18 [56251.772382] R10: ffff9159cf2ce1a8 R11: 0000000000000003 R12: ffff911a80850000 [56251.784364] R13: ffff93120fbc7000 R14: 0000000000000010 R15: ffff9139e7510e40 [56251.796278] FS: 0000000000000000(0000) GS:ffff9149afd80000(0000) knlGS:0000000000000000 [56251.809133] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [56251.819561] CR2: 00007f5e85e6f300 CR3: 00000038b85e2006 CR4: 0000000000770ef0 [56251.831365] PKRU: 55555554 [56251.838653] Call Trace: [56251.845560] <IRQ> [56251.851943] cpu_map_enqueue.cold+0x5/0xa [56251.860243] xdp_do_redirect+0x2d9/0x480 [56251.868388] bnxt_rx_xdp+0x1d8/0x4c0 [bnxt_en] [56251.877028] bnxt_rx_pkt+0x5f7/0x19b0 [bnxt_en] [56251.885665] ? cpu_max_write+0x1e/0x100 [56251.893510] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.902276] __bnxt_poll_work+0x190/0x340 [bnxt_en] [56251.911058] bnxt_poll+0xab/0x1b0 [bnxt_en] [56251.919041] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.927568] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.935958] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.944250] __napi_poll+0x2b/0x160 [56251.951155] bpf_trampoline_6442548651+0x79/0x123 [56251.959262] __napi_poll+0x5/0x160 [56251.966037] net_rx_action+0x3d2/0x880 [56251.973133] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.981265] ? srso_alias_return_thunk+0x5/0xfbef5 [56251.989262] ? __hrtimer_run_queues+0x162/0x2a0 [56251.996967] ? srso_alias_return_thunk+0x5/0xfbef5 [56252.004875] ? srso_alias_return_thunk+0x5/0xfbef5 [56252.012673] ? bnxt_msix+0x62/0x70 [bnxt_en] [56252.019903] handle_softirqs+0xcf/0x270 [56252.026650] irq_exit_rcu+0x67/0x90 [56252.032933] common_interrupt+0x85/0xa0 [56252.039498] </IRQ> [56252.044246] <TASK> [56252.048935] asm_common_interrupt+0x26/0x40 [56252.055727] RIP: 0010:cpuidle_enter_state+0xb8/0x420 [56252.063305] Code: dc 01 00 00 e8 f9 79 3b ff e8 64 f7 ff ff 49 89 c5 0f 1f 44 00 00 31 ff e8 a5 32 3a ff 45 84 ff 0f 85 ae 01 00 00 fb 45 85 f6 <0f> 88 88 01 00 00 48 8b 04 24 49 63 ce 4c 89 ea 48 6b f1 68 48 29 [56252.088911] RSP: 0018:ffff93120c97fe98 EFLAGS: 00000202 [56252.096912] RAX: ffff9149afd80000 RBX: ffff9141d3a72800 RCX: 0000000000000000 [56252.106844] RDX: 00003329176c6b98 RSI: ffffffe36db3fdc7 RDI: 0000000000000000 [56252.116733] RBP: 0000000000000002 R08: 0000000000000002 R09: 000000000000004e [56252.126652] R10: ffff9149afdb30c4 R11: 071c71c71c71c71c R12: ffffffff985ff860 [56252.136637] R13: 00003329176c6b98 R14: 0000000000000002 R15: 0000000000000000 [56252.146667] ? cpuidle_enter_state+0xab/0x420 [56252.153909] cpuidle_enter+0x2d/0x40 [56252.160360] do_idle+0x176/0x1c0 [56252.166456 ---truncated---
CVE-2025-38248: In the Linux kernel, the following vulnerability has been resolved: bridge: mcast: Fix use-after-free during router port configuration The bridge maintains a global list of ports behind which a multicast router resides. The list is consulted during forwarding to ensure multicast packets are forwarded to these ports even if the ports are not member in the matching MDB entry. When per-VLAN multicast snooping is enabled, the per-port multicast context is disabled on each port and the port is removed from the global router port list: # ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 1 # ip link add name dummy1 up master br1 type dummy # ip link set dev dummy1 type bridge_slave mcast_router 2 $ bridge -d mdb show | grep router router ports on br1: dummy1 # ip link set dev br1 type bridge mcast_vlan_snooping 1 $ bridge -d mdb show | grep router However, the port can be re-added to the global list even when per-VLAN multicast snooping is enabled: # ip link set dev dummy1 type bridge_slave mcast_router 0 # ip link set dev dummy1 type bridge_slave mcast_router 2 $ bridge -d mdb show | grep router router ports on br1: dummy1 Since commit 4b30ae9adb04 ("net: bridge: mcast: re-implement br_multicast_{enable, disable}_port functions"), when per-VLAN multicast snooping is enabled, multicast disablement on a port will disable the per-{port, VLAN} multicast contexts and not the per-port one. As a result, a port will remain in the global router port list even after it is deleted. This will lead to a use-after-free [1] when the list is traversed (when adding a new port to the list, for example): # ip link del dev dummy1 # ip link add name dummy2 up master br1 type dummy # ip link set dev dummy2 type bridge_slave mcast_router 2 Similarly, stale entries can also be found in the per-VLAN router port list. When per-VLAN multicast snooping is disabled, the per-{port, VLAN} contexts are disabled on each port and the port is removed from the per-VLAN router port list: # ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 1 mcast_vlan_snooping 1 # ip link add name dummy1 up master br1 type dummy # bridge vlan add vid 2 dev dummy1 # bridge vlan global set vid 2 dev br1 mcast_snooping 1 # bridge vlan set vid 2 dev dummy1 mcast_router 2 $ bridge vlan global show dev br1 vid 2 | grep router router ports: dummy1 # ip link set dev br1 type bridge mcast_vlan_snooping 0 $ bridge vlan global show dev br1 vid 2 | grep router However, the port can be re-added to the per-VLAN list even when per-VLAN multicast snooping is disabled: # bridge vlan set vid 2 dev dummy1 mcast_router 0 # bridge vlan set vid 2 dev dummy1 mcast_router 2 $ bridge vlan global show dev br1 vid 2 | grep router router ports: dummy1 When the VLAN is deleted from the port, the per-{port, VLAN} multicast context will not be disabled since multicast snooping is not enabled on the VLAN. As a result, the port will remain in the per-VLAN router port list even after it is no longer member in the VLAN. This will lead to a use-after-free [2] when the list is traversed (when adding a new port to the list, for example): # ip link add name dummy2 up master br1 type dummy # bridge vlan add vid 2 dev dummy2 # bridge vlan del vid 2 dev dummy1 # bridge vlan set vid 2 dev dummy2 mcast_router 2 Fix these issues by removing the port from the relevant (global or per-VLAN) router port list in br_multicast_port_ctx_deinit(). The function is invoked during port deletion with the per-port multicast context and during VLAN deletion with the per-{port, VLAN} multicast context. Note that deleting the multicast router timer is not enough as it only takes care of the temporary multicast router states (1 or 3) and not the permanent one (2). [1] BUG: KASAN: slab-out-of-bounds in br_multicast_add_router.part.0+0x3f1/0x560 Write of size 8 at addr ffff888004a67328 by task ip/384 [...] Call Trace: <TASK> dump_stack ---truncated---
CVE-2025-38250: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: Fix use-after-free in vhci_flush() syzbot reported use-after-free in vhci_flush() without repro. [0] From the splat, a thread close()d a vhci file descriptor while its device was being used by iotcl() on another thread. Once the last fd refcnt is released, vhci_release() calls hci_unregister_dev(), hci_free_dev(), and kfree() for struct vhci_data, which is set to hci_dev->dev->driver_data. The problem is that there is no synchronisation after unlinking hdev from hci_dev_list in hci_unregister_dev(). There might be another thread still accessing the hdev which was fetched before the unlink operation. We can use SRCU for such synchronisation. Let's run hci_dev_reset() under SRCU and wait for its completion in hci_unregister_dev(). Another option would be to restore hci_dev->destruct(), which was removed in commit 587ae086f6e4 ("Bluetooth: Remove unused hci-destruct cb"). However, this would not be a good solution, as we should not run hci_unregister_dev() while there are in-flight ioctl() requests, which could lead to another data-race KCSAN splat. Note that other drivers seem to have the same problem, for exmaple, virtbt_remove(). [0]: BUG: KASAN: slab-use-after-free in skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline] BUG: KASAN: slab-use-after-free in skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937 Read of size 8 at addr ffff88807cb8d858 by task syz.1.219/6718 CPU: 1 UID: 0 PID: 6718 Comm: syz.1.219 Not tainted 6.16.0-rc1-syzkaller-00196-g08207f42d3ff #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:408 [inline] print_report+0xd2/0x2b0 mm/kasan/report.c:521 kasan_report+0x118/0x150 mm/kasan/report.c:634 skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline] skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937 skb_queue_purge include/linux/skbuff.h:3368 [inline] vhci_flush+0x44/0x50 drivers/bluetooth/hci_vhci.c:69 hci_dev_do_reset net/bluetooth/hci_core.c:552 [inline] hci_dev_reset+0x420/0x5c0 net/bluetooth/hci_core.c:592 sock_do_ioctl+0xd9/0x300 net/socket.c:1190 sock_ioctl+0x576/0x790 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fcf5b98e929 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fcf5c7b9038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fcf5bbb6160 RCX: 00007fcf5b98e929 RDX: 0000000000000000 RSI: 00000000400448cb RDI: 0000000000000009 RBP: 00007fcf5ba10b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007fcf5bbb6160 R15: 00007ffd6353d528 </TASK> Allocated by task 6535: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __kmalloc_cache_noprof+0x230/0x3d0 mm/slub.c:4359 kmalloc_noprof include/linux/slab.h:905 [inline] kzalloc_noprof include/linux/slab.h:1039 [inline] vhci_open+0x57/0x360 drivers/bluetooth/hci_vhci.c:635 misc_open+0x2bc/0x330 drivers/char/misc.c:161 chrdev_open+0x4c9/0x5e0 fs/char_dev.c:414 do_dentry_open+0xdf0/0x1970 fs/open.c:964 vfs_open+0x3b/0x340 fs/open.c:1094 do_open fs/namei.c:3887 [inline] path_openat+0x2ee5/0x3830 fs/name ---truncated---
CVE-2025-38261: In the Linux kernel, the following vulnerability has been resolved: riscv: save the SR_SUM status over switches When threads/tasks are switched we need to ensure the old execution's SR_SUM state is saved and the new thread has the old SR_SUM state restored. The issue was seen under heavy load especially with the syz-stress tool running, with crashes as follows in schedule_tail: Unable to handle kernel access to user memory without uaccess routines at virtual address 000000002749f0d0 Oops [#1] Modules linked in: CPU: 1 PID: 4875 Comm: syz-executor.0 Not tainted 5.12.0-rc2-syzkaller-00467-g0d7588ab9ef9 #0 Hardware name: riscv-virtio,qemu (DT) epc : schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 ra : task_pid_vnr include/linux/sched.h:1421 [inline] ra : schedule_tail+0x70/0xb2 kernel/sched/core.c:4264 epc : ffffffe00008c8b0 ra : ffffffe00008c8ae sp : ffffffe025d17ec0 gp : ffffffe005d25378 tp : ffffffe00f0d0000 t0 : 0000000000000000 t1 : 0000000000000001 t2 : 00000000000f4240 s0 : ffffffe025d17ee0 s1 : 000000002749f0d0 a0 : 000000000000002a a1 : 0000000000000003 a2 : 1ffffffc0cfac500 a3 : ffffffe0000c80cc a4 : 5ae9db91c19bbe00 a5 : 0000000000000000 a6 : 0000000000f00000 a7 : ffffffe000082eba s2 : 0000000000040000 s3 : ffffffe00eef96c0 s4 : ffffffe022c77fe0 s5 : 0000000000004000 s6 : ffffffe067d74e00 s7 : ffffffe067d74850 s8 : ffffffe067d73e18 s9 : ffffffe067d74e00 s10: ffffffe00eef96e8 s11: 000000ae6cdf8368 t3 : 5ae9db91c19bbe00 t4 : ffffffc4043cafb2 t5 : ffffffc4043cafba t6 : 0000000000040000 status: 0000000000000120 badaddr: 000000002749f0d0 cause: 000000000000000f Call Trace: [<ffffffe00008c8b0>] schedule_tail+0x72/0xb2 kernel/sched/core.c:4264 [<ffffffe000005570>] ret_from_exception+0x0/0x14 Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace b5f8f9231dc87dda ]--- The issue comes from the put_user() in schedule_tail (kernel/sched/core.c) doing the following: asmlinkage __visible void schedule_tail(struct task_struct *prev) { ... if (current->set_child_tid) put_user(task_pid_vnr(current), current->set_child_tid); ... } the put_user() macro causes the code sequence to come out as follows: 1: __enable_user_access() 2: reg = task_pid_vnr(current); 3: *current->set_child_tid = reg; 4: __disable_user_access() The problem is that we may have a sleeping function as argument which could clear SR_SUM causing the panic above. This was fixed by evaluating the argument of the put_user() macro outside the user-enabled section in commit 285a76bb2cf5 ("riscv: evaluate put_user() arg before enabling user access")" In order for riscv to take advantage of unsafe_get/put_XXX() macros and to avoid the same issue we had with put_user() and sleeping functions we must ensure code flow can go through switch_to() from within a region of code with SR_SUM enabled and come back with SR_SUM still enabled. This patch addresses the problem allowing future work to enable full use of unsafe_get/put_XXX() macros without needing to take a CSR bit flip cost on every access. Make switch_to() save and restore SR_SUM.
CVE-2025-38264: In the Linux kernel, the following vulnerability has been resolved: nvme-tcp: sanitize request list handling Validate the request in nvme_tcp_handle_r2t() to ensure it's not part of any list, otherwise a malicious R2T PDU might inject a loop in request list processing.
CVE-2025-38272: In the Linux kernel, the following vulnerability has been resolved: net: dsa: b53: do not enable EEE on bcm63xx BCM63xx internal switches do not support EEE, but provide multiple RGMII ports where external PHYs may be connected. If one of these PHYs are EEE capable, we may try to enable EEE for the MACs, which then hangs the system on access of the (non-existent) EEE registers. Fix this by checking if the switch actually supports EEE before attempting to configure it.
CVE-2025-38283: In the Linux kernel, the following vulnerability has been resolved: hisi_acc_vfio_pci: bugfix live migration function without VF device driver If the VF device driver is not loaded in the Guest OS and we attempt to perform device data migration, the address of the migrated data will be NULL. The live migration recovery operation on the destination side will access a null address value, which will cause access errors. Therefore, live migration of VMs without added VF device drivers does not require device data migration. In addition, when the queue address data obtained by the destination is empty, device queue recovery processing will not be performed.
CVE-2025-38303: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: eir: Fix possible crashes on eir_create_adv_data eir_create_adv_data may attempt to add EIR_FLAGS and EIR_TX_POWER without checking if that would fit.
CVE-2025-38311: In the Linux kernel, the following vulnerability has been resolved: iavf: get rid of the crit lock Get rid of the crit lock. That frees us from the error prone logic of try_locks. Thanks to netdev_lock() by Jakub it is now easy, and in most cases we were protected by it already - replace crit lock by netdev lock when it was not the case. Lockdep reports that we should cancel the work under crit_lock [splat1], and that was the scheme we have mostly followed since [1] by Slawomir. But when that is done we still got into deadlocks [splat2]. So instead we should look at the bigger problem, namely "weird locking/scheduling" of the iavf. The first step to fix that is to remove the crit lock. I will followup with a -next series that simplifies scheduling/tasks. Cancel the work without netdev lock (weird unlock+lock scheme), to fix the [splat2] (which would be totally ugly if we would kept the crit lock). Extend protected part of iavf_watchdog_task() to include scheduling more work. Note that the removed comment in iavf_reset_task() was misplaced, it belonged to inside of the removed if condition, so it's gone now. [splat1] - w/o this patch - The deadlock during VF removal: WARNING: possible circular locking dependency detected sh/3825 is trying to acquire lock: ((work_completion)(&(&adapter->watchdog_task)->work)){+.+.}-{0:0}, at: start_flush_work+0x1a1/0x470 but task is already holding lock: (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_remove+0xd1/0x690 [iavf] which lock already depends on the new lock. [splat2] - when cancelling work under crit lock, w/o this series, see [2] for the band aid attempt WARNING: possible circular locking dependency detected sh/3550 is trying to acquire lock: ((wq_completion)iavf){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: (&dev->lock){+.+.}-{4:4}, at: iavf_remove+0xa6/0x6e0 [iavf] which lock already depends on the new lock. [1] fc2e6b3b132a ("iavf: Rework mutexes for better synchronisation") [2] https://github.com/pkitszel/linux/commit/52dddbfc2bb60294083f5711a158a
CVE-2025-38333: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to bail out in get_new_segment() ------------[ cut here ]------------ WARNING: CPU: 3 PID: 579 at fs/f2fs/segment.c:2832 new_curseg+0x5e8/0x6dc pc : new_curseg+0x5e8/0x6dc Call trace: new_curseg+0x5e8/0x6dc f2fs_allocate_data_block+0xa54/0xe28 do_write_page+0x6c/0x194 f2fs_do_write_node_page+0x38/0x78 __write_node_page+0x248/0x6d4 f2fs_sync_node_pages+0x524/0x72c f2fs_write_checkpoint+0x4bc/0x9b0 __checkpoint_and_complete_reqs+0x80/0x244 issue_checkpoint_thread+0x8c/0xec kthread+0x114/0x1bc ret_from_fork+0x10/0x20 get_new_segment() detects inconsistent status in between free_segmap and free_secmap, let's record such error into super block, and bail out get_new_segment() instead of continue using the segment.
CVE-2025-38359: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Fix in_atomic() handling in do_secure_storage_access() Kernel user spaces accesses to not exported pages in atomic context incorrectly try to resolve the page fault. With debug options enabled call traces like this can be seen: BUG: sleeping function called from invalid context at kernel/locking/rwsem.c:1523 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 419074, name: qemu-system-s39 preempt_count: 1, expected: 0 RCU nest depth: 0, expected: 0 INFO: lockdep is turned off. Preemption disabled at: [<00000383ea47cfa2>] copy_page_from_iter_atomic+0xa2/0x8a0 CPU: 12 UID: 0 PID: 419074 Comm: qemu-system-s39 Tainted: G W 6.16.0-20250531.rc0.git0.69b3a602feac.63.fc42.s390x+debug #1 PREEMPT Tainted: [W]=WARN Hardware name: IBM 3931 A01 703 (LPAR) Call Trace: [<00000383e990d282>] dump_stack_lvl+0xa2/0xe8 [<00000383e99bf152>] __might_resched+0x292/0x2d0 [<00000383eaa7c374>] down_read+0x34/0x2d0 [<00000383e99432f8>] do_secure_storage_access+0x108/0x360 [<00000383eaa724b0>] __do_pgm_check+0x130/0x220 [<00000383eaa842e4>] pgm_check_handler+0x114/0x160 [<00000383ea47d028>] copy_page_from_iter_atomic+0x128/0x8a0 ([<00000383ea47d016>] copy_page_from_iter_atomic+0x116/0x8a0) [<00000383e9c45eae>] generic_perform_write+0x16e/0x310 [<00000383e9eb87f4>] ext4_buffered_write_iter+0x84/0x160 [<00000383e9da0de4>] vfs_write+0x1c4/0x460 [<00000383e9da123c>] ksys_write+0x7c/0x100 [<00000383eaa7284e>] __do_syscall+0x15e/0x280 [<00000383eaa8417e>] system_call+0x6e/0x90 INFO: lockdep is turned off. It is not allowed to take the mmap_lock while in atomic context. Therefore handle such a secure storage access fault as if the accessed page is not mapped: the uaccess function will return -EFAULT, and the caller has to deal with this. Usually this means that the access is retried in process context, which allows to resolve the page fault (or in this case export the page).
CVE-2025-38369: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Check availability of workqueue allocated by idxd wq driver before using Running IDXD workloads in a container with the /dev directory mounted can trigger a call trace or even a kernel panic when the parent process of the container is terminated. This issue occurs because, under certain configurations, Docker does not properly propagate the mount replica back to the original mount point. In this case, when the user driver detaches, the WQ is destroyed but it still calls destroy_workqueue() attempting to completes all pending work. It's necessary to check wq->wq and skip the drain if it no longer exists.
CVE-2025-38426: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add basic validation for RAS header If RAS header read from EEPROM is corrupted, it could result in trying to allocate huge memory for reading the records. Add some validation to header fields.
CVE-2025-38429: In the Linux kernel, the following vulnerability has been resolved: bus: mhi: ep: Update read pointer only after buffer is written Inside mhi_ep_ring_add_element, the read pointer (rd_offset) is updated before the buffer is written, potentially causing race conditions where the host sees an updated read pointer before the buffer is actually written. Updating rd_offset prematurely can lead to the host accessing an uninitialized or incomplete element, resulting in data corruption. Invoke the buffer write before updating rd_offset to ensure the element is fully written before signaling its availability.
CVE-2025-38436: In the Linux kernel, the following vulnerability has been resolved: drm/scheduler: signal scheduled fence when kill job When an entity from application B is killed, drm_sched_entity_kill() removes all jobs belonging to that entity through drm_sched_entity_kill_jobs_work(). If application A's job depends on a scheduled fence from application B's job, and that fence is not properly signaled during the killing process, application A's dependency cannot be cleared. This leads to application A hanging indefinitely while waiting for a dependency that will never be resolved. Fix this issue by ensuring that scheduled fences are properly signaled when an entity is killed, allowing dependent applications to continue execution.
CVE-2025-38438: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: Intel: hda: Use devm_kstrdup() to avoid memleak. sof_pdata->tplg_filename can have address allocated by kstrdup() and can be overwritten. Memory leak was detected with kmemleak: unreferenced object 0xffff88812391ff60 (size 16): comm "kworker/4:1", pid 161, jiffies 4294802931 hex dump (first 16 bytes): 73 6f 66 2d 68 64 61 2d 67 65 6e 65 72 69 63 00 sof-hda-generic. backtrace (crc 4bf1675c): __kmalloc_node_track_caller_noprof+0x49c/0x6b0 kstrdup+0x46/0xc0 hda_machine_select.cold+0x1de/0x12cf [snd_sof_intel_hda_generic] sof_init_environment+0x16f/0xb50 [snd_sof] sof_probe_continue+0x45/0x7c0 [snd_sof] sof_probe_work+0x1e/0x40 [snd_sof] process_one_work+0x894/0x14b0 worker_thread+0x5e5/0xfb0 kthread+0x39d/0x760 ret_from_fork+0x31/0x70 ret_from_fork_asm+0x1a/0x30
CVE-2025-38449: In the Linux kernel, the following vulnerability has been resolved: drm/gem: Acquire references on GEM handles for framebuffers A GEM handle can be released while the GEM buffer object is attached to a DRM framebuffer. This leads to the release of the dma-buf backing the buffer object, if any. [1] Trying to use the framebuffer in further mode-setting operations leads to a segmentation fault. Most easily happens with driver that use shadow planes for vmap-ing the dma-buf during a page flip. An example is shown below. [ 156.791968] ------------[ cut here ]------------ [ 156.796830] WARNING: CPU: 2 PID: 2255 at drivers/dma-buf/dma-buf.c:1527 dma_buf_vmap+0x224/0x430 [...] [ 156.942028] RIP: 0010:dma_buf_vmap+0x224/0x430 [ 157.043420] Call Trace: [ 157.045898] <TASK> [ 157.048030] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.052436] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.056836] ? show_trace_log_lvl+0x1af/0x2c0 [ 157.061253] ? drm_gem_shmem_vmap+0x74/0x710 [ 157.065567] ? dma_buf_vmap+0x224/0x430 [ 157.069446] ? __warn.cold+0x58/0xe4 [ 157.073061] ? dma_buf_vmap+0x224/0x430 [ 157.077111] ? report_bug+0x1dd/0x390 [ 157.080842] ? handle_bug+0x5e/0xa0 [ 157.084389] ? exc_invalid_op+0x14/0x50 [ 157.088291] ? asm_exc_invalid_op+0x16/0x20 [ 157.092548] ? dma_buf_vmap+0x224/0x430 [ 157.096663] ? dma_resv_get_singleton+0x6d/0x230 [ 157.101341] ? __pfx_dma_buf_vmap+0x10/0x10 [ 157.105588] ? __pfx_dma_resv_get_singleton+0x10/0x10 [ 157.110697] drm_gem_shmem_vmap+0x74/0x710 [ 157.114866] drm_gem_vmap+0xa9/0x1b0 [ 157.118763] drm_gem_vmap_unlocked+0x46/0xa0 [ 157.123086] drm_gem_fb_vmap+0xab/0x300 [ 157.126979] drm_atomic_helper_prepare_planes.part.0+0x487/0xb10 [ 157.133032] ? lockdep_init_map_type+0x19d/0x880 [ 157.137701] drm_atomic_helper_commit+0x13d/0x2e0 [ 157.142671] ? drm_atomic_nonblocking_commit+0xa0/0x180 [ 157.147988] drm_mode_atomic_ioctl+0x766/0xe40 [...] [ 157.346424] ---[ end trace 0000000000000000 ]--- Acquiring GEM handles for the framebuffer's GEM buffer objects prevents this from happening. The framebuffer's cleanup later puts the handle references. Commit 1a148af06000 ("drm/gem-shmem: Use dma_buf from GEM object instance") triggers the segmentation fault easily by using the dma-buf field more widely. The underlying issue with reference counting has been present before. v2: - acquire the handle instead of the BO (Christian) - fix comment style (Christian) - drop the Fixes tag (Christian) - rename err_ gotos - add missing Link tag
CVE-2025-38507: In the Linux kernel, the following vulnerability has been resolved: HID: nintendo: avoid bluetooth suspend/resume stalls Ensure we don't stall or panic the kernel when using bluetooth-connected controllers. This was reported as an issue on android devices using kernel 6.6 due to the resume hook which had been added for usb joycons. First, set a new state value to JOYCON_CTLR_STATE_SUSPENDED in a newly-added nintendo_hid_suspend. This makes sure we will not stall out the kernel waiting for input reports during led classdev suspend. The stalls could happen if connectivity is unreliable or lost to the controller prior to suspend. Second, since we lose connectivity during suspend, do not try joycon_init() for bluetooth controllers in the nintendo_hid_resume path. Tested via multiple suspend/resume flows when using the controller both in USB and bluetooth modes.
CVE-2025-38524: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix recv-recv race of completed call If a call receives an event (such as incoming data), the call gets placed on the socket's queue and a thread in recvmsg can be awakened to go and process it. Once the thread has picked up the call off of the queue, further events will cause it to be requeued, and once the socket lock is dropped (recvmsg uses call->user_mutex to allow the socket to be used in parallel), a second thread can come in and its recvmsg can pop the call off the socket queue again. In such a case, the first thread will be receiving stuff from the call and the second thread will be blocked on call->user_mutex. The first thread can, at this point, process both the event that it picked call for and the event that the second thread picked the call for and may see the call terminate - in which case the call will be "released", decoupling the call from the user call ID assigned to it (RXRPC_USER_CALL_ID in the control message). The first thread will return okay, but then the second thread will wake up holding the user_mutex and, if it sees that the call has been released by the first thread, it will BUG thusly: kernel BUG at net/rxrpc/recvmsg.c:474! Fix this by just dequeuing the call and ignoring it if it is seen to be already released. We can't tell userspace about it anyway as the user call ID has become stale.
CVE-2025-38531: In the Linux kernel, the following vulnerability has been resolved: iio: common: st_sensors: Fix use of uninitialize device structs Throughout the various probe functions &indio_dev->dev is used before it is initialized. This caused a kernel panic in st_sensors_power_enable() when the call to devm_regulator_bulk_get_enable() fails and then calls dev_err_probe() with the uninitialized device. This seems to only cause a panic with dev_err_probe(), dev_err(), dev_warn() and dev_info() don't seem to cause a panic, but are fixed as well. The issue is reported and traced here: [1]
CVE-2025-38544: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix bug due to prealloc collision When userspace is using AF_RXRPC to provide a server, it has to preallocate incoming calls and assign to them call IDs that will be used to thread related recvmsg() and sendmsg() together. The preallocated call IDs will automatically be attached to calls as they come in until the pool is empty. To the kernel, the call IDs are just arbitrary numbers, but userspace can use the call ID to hold a pointer to prepared structs. In any case, the user isn't permitted to create two calls with the same call ID (call IDs become available again when the call ends) and EBADSLT should result from sendmsg() if an attempt is made to preallocate a call with an in-use call ID. However, the cleanup in the error handling will trigger both assertions in rxrpc_cleanup_call() because the call isn't marked complete and isn't marked as having been released. Fix this by setting the call state in rxrpc_service_prealloc_one() and then marking it as being released before calling the cleanup function.
CVE-2025-38582: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix double destruction of rsv_qp rsv_qp may be double destroyed in error flow, first in free_mr_init(), and then in hns_roce_exit(). Fix it by moving the free_mr_init() call into hns_roce_v2_init(). list_del corruption, ffff589732eb9b50->next is LIST_POISON1 (dead000000000100) WARNING: CPU: 8 PID: 1047115 at lib/list_debug.c:53 __list_del_entry_valid+0x148/0x240 ... Call trace: __list_del_entry_valid+0x148/0x240 hns_roce_qp_remove+0x4c/0x3f0 [hns_roce_hw_v2] hns_roce_v2_destroy_qp_common+0x1dc/0x5f4 [hns_roce_hw_v2] hns_roce_v2_destroy_qp+0x22c/0x46c [hns_roce_hw_v2] free_mr_exit+0x6c/0x120 [hns_roce_hw_v2] hns_roce_v2_exit+0x170/0x200 [hns_roce_hw_v2] hns_roce_exit+0x118/0x350 [hns_roce_hw_v2] __hns_roce_hw_v2_init_instance+0x1c8/0x304 [hns_roce_hw_v2] hns_roce_hw_v2_reset_notify_init+0x170/0x21c [hns_roce_hw_v2] hns_roce_hw_v2_reset_notify+0x6c/0x190 [hns_roce_hw_v2] hclge_notify_roce_client+0x6c/0x160 [hclge] hclge_reset_rebuild+0x150/0x5c0 [hclge] hclge_reset+0x10c/0x140 [hclge] hclge_reset_subtask+0x80/0x104 [hclge] hclge_reset_service_task+0x168/0x3ac [hclge] hclge_service_task+0x50/0x100 [hclge] process_one_work+0x250/0x9a0 worker_thread+0x324/0x990 kthread+0x190/0x210 ret_from_fork+0x10/0x18
CVE-2025-38584: In the Linux kernel, the following vulnerability has been resolved: padata: Fix pd UAF once and for all There is a race condition/UAF in padata_reorder that goes back to the initial commit. A reference count is taken at the start of the process in padata_do_parallel, and released at the end in padata_serial_worker. This reference count is (and only is) required for padata_replace to function correctly. If padata_replace is never called then there is no issue. In the function padata_reorder which serves as the core of padata, as soon as padata is added to queue->serial.list, and the associated spin lock released, that padata may be processed and the reference count on pd would go away. Fix this by getting the next padata before the squeue->serial lock is released. In order to make this possible, simplify padata_reorder by only calling it once the next padata arrives.
CVE-2025-38585: In the Linux kernel, the following vulnerability has been resolved: staging: media: atomisp: Fix stack buffer overflow in gmin_get_var_int() When gmin_get_config_var() calls efi.get_variable() and the EFI variable is larger than the expected buffer size, two behaviors combine to create a stack buffer overflow: 1. gmin_get_config_var() does not return the proper error code when efi.get_variable() fails. It returns the stale 'ret' value from earlier operations instead of indicating the EFI failure. 2. When efi.get_variable() returns EFI_BUFFER_TOO_SMALL, it updates *out_len to the required buffer size but writes no data to the output buffer. However, due to bug #1, gmin_get_var_int() believes the call succeeded. The caller gmin_get_var_int() then performs: - Allocates val[CFG_VAR_NAME_MAX + 1] (65 bytes) on stack - Calls gmin_get_config_var(dev, is_gmin, var, val, &len) with len=64 - If EFI variable is >64 bytes, efi.get_variable() sets len=required_size - Due to bug #1, thinks call succeeded with len=required_size - Executes val[len] = 0, writing past end of 65-byte stack buffer This creates a stack buffer overflow when EFI variables are larger than 64 bytes. Since EFI variables can be controlled by firmware or system configuration, this could potentially be exploited for code execution. Fix the bug by returning proper error codes from gmin_get_config_var() based on EFI status instead of stale 'ret' value. The gmin_get_var_int() function is called during device initialization for camera sensor configuration on Intel Bay Trail and Cherry Trail platforms using the atomisp camera stack.
CVE-2025-38590: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Remove skb secpath if xfrm state is not found Hardware returns a unique identifier for a decrypted packet's xfrm state, this state is looked up in an xarray. However, the state might have been freed by the time of this lookup. Currently, if the state is not found, only a counter is incremented. The secpath (sp) extension on the skb is not removed, resulting in sp->len becoming 0. Subsequently, functions like __xfrm_policy_check() attempt to access fields such as xfrm_input_state(skb)->xso.type (which dereferences sp->xvec[sp->len - 1]) without first validating sp->len. This leads to a crash when dereferencing an invalid state pointer. This patch prevents the crash by explicitly removing the secpath extension from the skb if the xfrm state is not found after hardware decryption. This ensures downstream functions do not operate on a zero-length secpath. BUG: unable to handle page fault for address: ffffffff000002c8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 282e067 P4D 282e067 PUD 0 Oops: Oops: 0000 [#1] SMP CPU: 12 UID: 0 PID: 0 Comm: swapper/12 Not tainted 6.15.0-rc7_for_upstream_min_debug_2025_05_27_22_44 #1 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:__xfrm_policy_check+0x61a/0xa30 Code: b6 77 7f 83 e6 02 74 14 4d 8b af d8 00 00 00 41 0f b6 45 05 c1 e0 03 48 98 49 01 c5 41 8b 45 00 83 e8 01 48 98 49 8b 44 c5 10 <0f> b6 80 c8 02 00 00 83 e0 0c 3c 04 0f 84 0c 02 00 00 31 ff 80 fa RSP: 0018:ffff88885fb04918 EFLAGS: 00010297 RAX: ffffffff00000000 RBX: 0000000000000002 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000002 RDI: 0000000000000000 RBP: ffffffff8311af80 R08: 0000000000000020 R09: 00000000c2eda353 R10: ffff88812be2bbc8 R11: 000000001faab533 R12: ffff88885fb049c8 R13: ffff88812be2bbc8 R14: 0000000000000000 R15: ffff88811896ae00 FS: 0000000000000000(0000) GS:ffff8888dca82000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff000002c8 CR3: 0000000243050002 CR4: 0000000000372eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> ? try_to_wake_up+0x108/0x4c0 ? udp4_lib_lookup2+0xbe/0x150 ? udp_lib_lport_inuse+0x100/0x100 ? __udp4_lib_lookup+0x2b0/0x410 __xfrm_policy_check2.constprop.0+0x11e/0x130 udp_queue_rcv_one_skb+0x1d/0x530 udp_unicast_rcv_skb+0x76/0x90 __udp4_lib_rcv+0xa64/0xe90 ip_protocol_deliver_rcu+0x20/0x130 ip_local_deliver_finish+0x75/0xa0 ip_local_deliver+0xc1/0xd0 ? ip_protocol_deliver_rcu+0x130/0x130 ip_sublist_rcv+0x1f9/0x240 ? ip_rcv_finish_core+0x430/0x430 ip_list_rcv+0xfc/0x130 __netif_receive_skb_list_core+0x181/0x1e0 netif_receive_skb_list_internal+0x200/0x360 ? mlx5e_build_rx_skb+0x1bc/0xda0 [mlx5_core] gro_receive_skb+0xfd/0x210 mlx5e_handle_rx_cqe_mpwrq+0x141/0x280 [mlx5_core] mlx5e_poll_rx_cq+0xcc/0x8e0 [mlx5_core] ? mlx5e_handle_rx_dim+0x91/0xd0 [mlx5_core] mlx5e_napi_poll+0x114/0xab0 [mlx5_core] __napi_poll+0x25/0x170 net_rx_action+0x32d/0x3a0 ? mlx5_eq_comp_int+0x8d/0x280 [mlx5_core] ? notifier_call_chain+0x33/0xa0 handle_softirqs+0xda/0x250 irq_exit_rcu+0x6d/0xc0 common_interrupt+0x81/0xa0 </IRQ>
CVE-2025-38595: In the Linux kernel, the following vulnerability has been resolved: xen: fix UAF in dmabuf_exp_from_pages() [dma_buf_fd() fixes; no preferences regarding the tree it goes through - up to xen folks] As soon as we'd inserted a file reference into descriptor table, another thread could close it. That's fine for the case when all we are doing is returning that descriptor to userland (it's a race, but it's a userland race and there's nothing the kernel can do about it). However, if we follow fd_install() with any kind of access to objects that would be destroyed on close (be it the struct file itself or anything destroyed by its ->release()), we have a UAF. dma_buf_fd() is a combination of reserving a descriptor and fd_install(). gntdev dmabuf_exp_from_pages() calls it and then proceeds to access the objects destroyed on close - starting with gntdev_dmabuf itself. Fix that by doing reserving descriptor before anything else and do fd_install() only when everything had been set up.
CVE-2025-38597: In the Linux kernel, the following vulnerability has been resolved: drm/rockchip: vop2: fail cleanly if missing a primary plane for a video-port Each window of a vop2 is usable by a specific set of video ports, so while binding the vop2, we look through the list of available windows trying to find one designated as primary-plane and usable by that specific port. The code later wants to use drm_crtc_init_with_planes with that found primary plane, but nothing has checked so far if a primary plane was actually found. For whatever reason, the rk3576 vp2 does not have a usable primary window (if vp0 is also in use) which brought the issue to light and ended in a null-pointer dereference further down. As we expect a primary-plane to exist for a video-port, add a check at the end of the window-iteration and fail probing if none was found.
CVE-2025-38615: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: cancle set bad inode after removing name fails The reproducer uses a file0 on a ntfs3 file system with a corrupted i_link. When renaming, the file0's inode is marked as a bad inode because the file name cannot be deleted. The underlying bug is that make_bad_inode() is called on a live inode. In some cases it's "icache lookup finds a normal inode, d_splice_alias() is called to attach it to dentry, while another thread decides to call make_bad_inode() on it - that would evict it from icache, but we'd already found it there earlier". In some it's outright "we have an inode attached to dentry - that's how we got it in the first place; let's call make_bad_inode() on it just for shits and giggles".
CVE-2025-38616: In the Linux kernel, the following vulnerability has been resolved: tls: handle data disappearing from under the TLS ULP TLS expects that it owns the receive queue of the TCP socket. This cannot be guaranteed in case the reader of the TCP socket entered before the TLS ULP was installed, or uses some non-standard read API (eg. zerocopy ones). Replace the WARN_ON() and a buggy early exit (which leaves anchor pointing to a freed skb) with real error handling. Wipe the parsing state and tell the reader to retry. We already reload the anchor every time we (re)acquire the socket lock, so the only condition we need to avoid is an out of bounds read (not having enough bytes in the socket for previously parsed record len). If some data was read from under TLS but there's enough in the queue we'll reload and decrypt what is most likely not a valid TLS record. Leading to some undefined behavior from TLS perspective (corrupting a stream? missing an alert? missing an attack?) but no kernel crash should take place.
CVE-2025-38626: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to trigger foreground gc during f2fs_map_blocks() in lfs mode w/ "mode=lfs" mount option, generic/299 will cause system panic as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2835! Call Trace: <TASK> f2fs_allocate_data_block+0x6f4/0xc50 f2fs_map_blocks+0x970/0x1550 f2fs_iomap_begin+0xb2/0x1e0 iomap_iter+0x1d6/0x430 __iomap_dio_rw+0x208/0x9a0 f2fs_file_write_iter+0x6b3/0xfa0 aio_write+0x15d/0x2e0 io_submit_one+0x55e/0xab0 __x64_sys_io_submit+0xa5/0x230 do_syscall_64+0x84/0x2f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0010:new_curseg+0x70f/0x720 The root cause of we run out-of-space is: in f2fs_map_blocks(), f2fs may trigger foreground gc only if it allocates any physical block, it will be a little bit later when there is multiple threads writing data w/ aio/dio/bufio method in parallel, since we always use OPU in lfs mode, so f2fs_map_blocks() does block allocations aggressively. In order to fix this issue, let's give a chance to trigger foreground gc in prior to block allocation in f2fs_map_blocks().
CVE-2025-38627: In the Linux kernel, the following vulnerability has been resolved: f2fs: compress: fix UAF of f2fs_inode_info in f2fs_free_dic The decompress_io_ctx may be released asynchronously after I/O completion. If this file is deleted immediately after read, and the kworker of processing post_read_wq has not been executed yet due to high workloads, It is possible that the inode(f2fs_inode_info) is evicted and freed before it is used f2fs_free_dic. The UAF case as below: Thread A Thread B - f2fs_decompress_end_io - f2fs_put_dic - queue_work add free_dic work to post_read_wq - do_unlink - iput - evict - call_rcu This file is deleted after read. Thread C kworker to process post_read_wq - rcu_do_batch - f2fs_free_inode - kmem_cache_free inode is freed by rcu - process_scheduled_works - f2fs_late_free_dic - f2fs_free_dic - f2fs_release_decomp_mem read (dic->inode)->i_compress_algorithm This patch store compress_algorithm and sbi in dic to avoid inode UAF. In addition, the previous solution is deprecated in [1] may cause system hang. [1] https://lore.kernel.org/all/c36ab955-c8db-4a8b-a9d0-f07b5f426c3f@kernel.org
CVE-2025-38636: In the Linux kernel, the following vulnerability has been resolved: rv: Use strings in da monitors tracepoints Using DA monitors tracepoints with KASAN enabled triggers the following warning: BUG: KASAN: global-out-of-bounds in do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 Read of size 32 at addr ffffffffaada8980 by task ... Call Trace: <TASK> [...] do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 ? __pfx_do_trace_event_raw_event_event_da_monitor+0x10/0x10 ? trace_event_sncid+0x83/0x200 trace_event_sncid+0x163/0x200 [...] The buggy address belongs to the variable: automaton_snep+0x4e0/0x5e0 This is caused by the tracepoints reading 32 bytes __array instead of __string from the automata definition. Such strings are literals and reading 32 bytes ends up in out of bound memory accesses (e.g. the next automaton's data in this case). The error is harmless as, while printing the string, we stop at the null terminator, but it should still be fixed. Use the __string facilities while defining the tracepoints to avoid reading out of bound memory.
CVE-2025-38659: In the Linux kernel, the following vulnerability has been resolved: gfs2: No more self recovery When a node withdraws and it turns out that it is the only node that has the filesystem mounted, gfs2 currently tries to replay the local journal to bring the filesystem back into a consistent state. Not only is that a very bad idea, it has also never worked because gfs2_recover_func() will refuse to do anything during a withdraw. However, before even getting to this point, gfs2_recover_func() dereferences sdp->sd_jdesc->jd_inode. This was a use-after-free before commit 04133b607a78 ("gfs2: Prevent double iput for journal on error") and is a NULL pointer dereference since then. Simply get rid of self recovery to fix that.
CVE-2025-38692: In the Linux kernel, the following vulnerability has been resolved: exfat: add cluster chain loop check for dir An infinite loop may occur if the following conditions occur due to file system corruption. (1) Condition for exfat_count_dir_entries() to loop infinitely. - The cluster chain includes a loop. - There is no UNUSED entry in the cluster chain. (2) Condition for exfat_create_upcase_table() to loop infinitely. - The cluster chain of the root directory includes a loop. - There are no UNUSED entry and up-case table entry in the cluster chain of the root directory. (3) Condition for exfat_load_bitmap() to loop infinitely. - The cluster chain of the root directory includes a loop. - There are no UNUSED entry and bitmap entry in the cluster chain of the root directory. (4) Condition for exfat_find_dir_entry() to loop infinitely. - The cluster chain includes a loop. - The unused directory entries were exhausted by some operation. (5) Condition for exfat_check_dir_empty() to loop infinitely. - The cluster chain includes a loop. - The unused directory entries were exhausted by some operation. - All files and sub-directories under the directory are deleted. This commit adds checks to break the above infinite loop.
CVE-2025-38704: In the Linux kernel, the following vulnerability has been resolved: rcu/nocb: Fix possible invalid rdp's->nocb_cb_kthread pointer access In the preparation stage of CPU online, if the corresponding the rdp's->nocb_cb_kthread does not exist, will be created, there is a situation where the rdp's rcuop kthreads creation fails, and then de-offload this CPU's rdp, does not assign this CPU's rdp->nocb_cb_kthread pointer, but this rdp's->nocb_gp_rdp and rdp's->rdp_gp->nocb_gp_kthread is still valid. This will cause the subsequent re-offload operation of this offline CPU, which will pass the conditional check and the kthread_unpark() will access invalid rdp's->nocb_cb_kthread pointer. This commit therefore use rdp's->nocb_gp_kthread instead of rdp_gp's->nocb_gp_kthread for safety check.
CVE-2025-38705: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: fix null pointer access Writing a string without delimiters (' ', '\n', '\0') to the under gpu_od/fan_ctrl sysfs or pp_power_profile_mode for the CUSTOM profile will result in a null pointer dereference.
CVE-2025-38709: In the Linux kernel, the following vulnerability has been resolved: loop: Avoid updating block size under exclusive owner Syzbot came up with a reproducer where a loop device block size is changed underneath a mounted filesystem. This causes a mismatch between the block device block size and the block size stored in the superblock causing confusion in various places such as fs/buffer.c. The particular issue triggered by syzbot was a warning in __getblk_slow() due to requested buffer size not matching block device block size. Fix the problem by getting exclusive hold of the loop device to change its block size. This fails if somebody (such as filesystem) has already an exclusive ownership of the block device and thus prevents modifying the loop device under some exclusive owner which doesn't expect it.
CVE-2025-38710: In the Linux kernel, the following vulnerability has been resolved: gfs2: Validate i_depth for exhash directories A fuzzer test introduced corruption that ends up with a depth of 0 in dir_e_read(), causing an undefined shift by 32 at: index = hash >> (32 - dip->i_depth); As calculated in an open-coded way in dir_make_exhash(), the minimum depth for an exhash directory is ilog2(sdp->sd_hash_ptrs) and 0 is invalid as sdp->sd_hash_ptrs is fixed as sdp->bsize / 16 at mount time. So we can avoid the undefined behaviour by checking for depth values lower than the minimum in gfs2_dinode_in(). Values greater than the maximum are already being checked for there. Also switch the calculation in dir_make_exhash() to use ilog2() to clarify how the depth is calculated. Tested with the syzkaller repro.c and xfstests '-g quick'.
CVE-2025-38716: In the Linux kernel, the following vulnerability has been resolved: hfs: fix general protection fault in hfs_find_init() The hfs_find_init() method can trigger the crash if tree pointer is NULL: [ 45.746290][ T9787] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000008: 0000 [#1] SMP KAI [ 45.747287][ T9787] KASAN: null-ptr-deref in range [0x0000000000000040-0x0000000000000047] [ 45.748716][ T9787] CPU: 2 UID: 0 PID: 9787 Comm: repro Not tainted 6.16.0-rc3 #10 PREEMPT(full) [ 45.750250][ T9787] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 45.751983][ T9787] RIP: 0010:hfs_find_init+0x86/0x230 [ 45.752834][ T9787] Code: c1 ea 03 80 3c 02 00 0f 85 9a 01 00 00 4c 8d 6b 40 48 c7 45 18 00 00 00 00 48 b8 00 00 00 00 00 fc [ 45.755574][ T9787] RSP: 0018:ffffc90015157668 EFLAGS: 00010202 [ 45.756432][ T9787] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff819a4d09 [ 45.757457][ T9787] RDX: 0000000000000008 RSI: ffffffff819acd3a RDI: ffffc900151576e8 [ 45.758282][ T9787] RBP: ffffc900151576d0 R08: 0000000000000005 R09: 0000000000000000 [ 45.758943][ T9787] R10: 0000000080000000 R11: 0000000000000001 R12: 0000000000000004 [ 45.759619][ T9787] R13: 0000000000000040 R14: ffff88802c50814a R15: 0000000000000000 [ 45.760293][ T9787] FS: 00007ffb72734540(0000) GS:ffff8880cec64000(0000) knlGS:0000000000000000 [ 45.761050][ T9787] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 45.761606][ T9787] CR2: 00007f9bd8225000 CR3: 000000010979a000 CR4: 00000000000006f0 [ 45.762286][ T9787] Call Trace: [ 45.762570][ T9787] <TASK> [ 45.762824][ T9787] hfs_ext_read_extent+0x190/0x9d0 [ 45.763269][ T9787] ? submit_bio_noacct_nocheck+0x2dd/0xce0 [ 45.763766][ T9787] ? __pfx_hfs_ext_read_extent+0x10/0x10 [ 45.764250][ T9787] hfs_get_block+0x55f/0x830 [ 45.764646][ T9787] block_read_full_folio+0x36d/0x850 [ 45.765105][ T9787] ? __pfx_hfs_get_block+0x10/0x10 [ 45.765541][ T9787] ? const_folio_flags+0x5b/0x100 [ 45.765972][ T9787] ? __pfx_hfs_read_folio+0x10/0x10 [ 45.766415][ T9787] filemap_read_folio+0xbe/0x290 [ 45.766840][ T9787] ? __pfx_filemap_read_folio+0x10/0x10 [ 45.767325][ T9787] ? __filemap_get_folio+0x32b/0xbf0 [ 45.767780][ T9787] do_read_cache_folio+0x263/0x5c0 [ 45.768223][ T9787] ? __pfx_hfs_read_folio+0x10/0x10 [ 45.768666][ T9787] read_cache_page+0x5b/0x160 [ 45.769070][ T9787] hfs_btree_open+0x491/0x1740 [ 45.769481][ T9787] hfs_mdb_get+0x15e2/0x1fb0 [ 45.769877][ T9787] ? __pfx_hfs_mdb_get+0x10/0x10 [ 45.770316][ T9787] ? find_held_lock+0x2b/0x80 [ 45.770731][ T9787] ? lockdep_init_map_type+0x5c/0x280 [ 45.771200][ T9787] ? lockdep_init_map_type+0x5c/0x280 [ 45.771674][ T9787] hfs_fill_super+0x38e/0x720 [ 45.772092][ T9787] ? __pfx_hfs_fill_super+0x10/0x10 [ 45.772549][ T9787] ? snprintf+0xbe/0x100 [ 45.772931][ T9787] ? __pfx_snprintf+0x10/0x10 [ 45.773350][ T9787] ? do_raw_spin_lock+0x129/0x2b0 [ 45.773796][ T9787] ? find_held_lock+0x2b/0x80 [ 45.774215][ T9787] ? set_blocksize+0x40a/0x510 [ 45.774636][ T9787] ? sb_set_blocksize+0x176/0x1d0 [ 45.775087][ T9787] ? setup_bdev_super+0x369/0x730 [ 45.775533][ T9787] get_tree_bdev_flags+0x384/0x620 [ 45.775985][ T9787] ? __pfx_hfs_fill_super+0x10/0x10 [ 45.776453][ T9787] ? __pfx_get_tree_bdev_flags+0x10/0x10 [ 45.776950][ T9787] ? bpf_lsm_capable+0x9/0x10 [ 45.777365][ T9787] ? security_capable+0x80/0x260 [ 45.777803][ T9787] vfs_get_tree+0x8e/0x340 [ 45.778203][ T9787] path_mount+0x13de/0x2010 [ 45.778604][ T9787] ? kmem_cache_free+0x2b0/0x4c0 [ 45.779052][ T9787] ? __pfx_path_mount+0x10/0x10 [ 45.779480][ T9787] ? getname_flags.part.0+0x1c5/0x550 [ 45.779954][ T9787] ? putname+0x154/0x1a0 [ 45.780335][ T9787] __x64_sys_mount+0x27b/0x300 [ 45.780758][ T9787] ? __pfx___x64_sys_mount+0x10/0x10 [ 45.781232][ T9787] ---truncated---
CVE-2025-38717: In the Linux kernel, the following vulnerability has been resolved: net: kcm: Fix race condition in kcm_unattach() syzbot found a race condition when kcm_unattach(psock) and kcm_release(kcm) are executed at the same time. kcm_unattach() is missing a check of the flag kcm->tx_stopped before calling queue_work(). If the kcm has a reserved psock, kcm_unattach() might get executed between cancel_work_sync() and unreserve_psock() in kcm_release(), requeuing kcm->tx_work right before kcm gets freed in kcm_done(). Remove kcm->tx_stopped and replace it by the less error-prone disable_work_sync().
CVE-2025-38722: In the Linux kernel, the following vulnerability has been resolved: habanalabs: fix UAF in export_dmabuf() As soon as we'd inserted a file reference into descriptor table, another thread could close it. That's fine for the case when all we are doing is returning that descriptor to userland (it's a race, but it's a userland race and there's nothing the kernel can do about it). However, if we follow fd_install() with any kind of access to objects that would be destroyed on close (be it the struct file itself or anything destroyed by its ->release()), we have a UAF. dma_buf_fd() is a combination of reserving a descriptor and fd_install(). habanalabs export_dmabuf() calls it and then proceeds to access the objects destroyed on close. In particular, it grabs an extra reference to another struct file that will be dropped as part of ->release() for ours; that "will be" is actually "might have already been". Fix that by reserving descriptor before anything else and do fd_install() only when everything had been set up. As a side benefit, we no longer have the failure exit with file already created, but reference to underlying file (as well as ->dmabuf_export_cnt, etc.) not grabbed yet; unlike dma_buf_fd(), fd_install() can't fail.
CVE-2025-38734: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix UAF on smcsk after smc_listen_out() BPF CI testing report a UAF issue: [ 16.446633] BUG: kernel NULL pointer dereference, address: 000000000000003 0 [ 16.447134] #PF: supervisor read access in kernel mod e [ 16.447516] #PF: error_code(0x0000) - not-present pag e [ 16.447878] PGD 0 P4D 0 [ 16.448063] Oops: Oops: 0000 [#1] PREEMPT SMP NOPT I [ 16.448409] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:1 Tainted: G OE 6.13.0-rc3-g89e8a75fda73-dirty #4 2 [ 16.449124] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODUL E [ 16.449502] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/201 4 [ 16.450201] Workqueue: smc_hs_wq smc_listen_wor k [ 16.450531] RIP: 0010:smc_listen_work+0xc02/0x159 0 [ 16.452158] RSP: 0018:ffffb5ab40053d98 EFLAGS: 0001024 6 [ 16.452526] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 000000000000030 0 [ 16.452994] RDX: 0000000000000280 RSI: 00003513840053f0 RDI: 000000000000000 0 [ 16.453492] RBP: ffffa097808e3800 R08: ffffa09782dba1e0 R09: 000000000000000 5 [ 16.453987] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0978274640 0 [ 16.454497] R13: 0000000000000000 R14: 0000000000000000 R15: ffffa09782d4092 0 [ 16.454996] FS: 0000000000000000(0000) GS:ffffa097bbc00000(0000) knlGS:000000000000000 0 [ 16.455557] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003 3 [ 16.455961] CR2: 0000000000000030 CR3: 0000000102788004 CR4: 0000000000770ef 0 [ 16.456459] PKRU: 5555555 4 [ 16.456654] Call Trace : [ 16.456832] <TASK > [ 16.456989] ? __die+0x23/0x7 0 [ 16.457215] ? page_fault_oops+0x180/0x4c 0 [ 16.457508] ? __lock_acquire+0x3e6/0x249 0 [ 16.457801] ? exc_page_fault+0x68/0x20 0 [ 16.458080] ? asm_exc_page_fault+0x26/0x3 0 [ 16.458389] ? smc_listen_work+0xc02/0x159 0 [ 16.458689] ? smc_listen_work+0xc02/0x159 0 [ 16.458987] ? lock_is_held_type+0x8f/0x10 0 [ 16.459284] process_one_work+0x1ea/0x6d 0 [ 16.459570] worker_thread+0x1c3/0x38 0 [ 16.459839] ? __pfx_worker_thread+0x10/0x1 0 [ 16.460144] kthread+0xe0/0x11 0 [ 16.460372] ? __pfx_kthread+0x10/0x1 0 [ 16.460640] ret_from_fork+0x31/0x5 0 [ 16.460896] ? __pfx_kthread+0x10/0x1 0 [ 16.461166] ret_from_fork_asm+0x1a/0x3 0 [ 16.461453] </TASK > [ 16.461616] Modules linked in: bpf_testmod(OE) [last unloaded: bpf_testmod(OE) ] [ 16.462134] CR2: 000000000000003 0 [ 16.462380] ---[ end trace 0000000000000000 ]--- [ 16.462710] RIP: 0010:smc_listen_work+0xc02/0x1590 The direct cause of this issue is that after smc_listen_out_connected(), newclcsock->sk may be NULL since it will releases the smcsk. Therefore, if the application closes the socket immediately after accept, newclcsock->sk can be NULL. A possible execution order could be as follows: smc_listen_work | userspace ----------------------------------------------------------------- lock_sock(sk) | smc_listen_out_connected() | | \- smc_listen_out | | | \- release_sock | | |- sk->sk_data_ready() | | fd = accept(); | close(fd); | \- socket->sk = NULL; /* newclcsock->sk is NULL now */ SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk)) Since smc_listen_out_connected() will not fail, simply swapping the order of the code can easily fix this issue.
CVE-2025-39677: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix backlog accounting in qdisc_dequeue_internal This issue applies for the following qdiscs: hhf, fq, fq_codel, and fq_pie, and occurs in their change handlers when adjusting to the new limit. The problem is the following in the values passed to the subsequent qdisc_tree_reduce_backlog call given a tbf parent: When the tbf parent runs out of tokens, skbs of these qdiscs will be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued, which accounts for both qlen and backlog. However, in the case of qdisc_dequeue_internal, ONLY qlen is accounted for when pulling from gso_skb. This means that these qdiscs are missing a qdisc_qstats_backlog_dec when dropping packets to satisfy the new limit in their change handlers. One can observe this issue with the following (with tc patched to support a limit of 0): export TARGET=fq tc qdisc del dev lo root tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000 echo ''; echo 'add child'; tc -s -d qdisc show dev lo ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null echo ''; echo 'after ping'; tc -s -d qdisc show dev lo tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0 echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo tc qdisc replace dev lo handle 2: parent 1:1 sfq echo ''; echo 'post graft'; tc -s -d qdisc show dev lo The second to last show command shows 0 packets but a positive number (74) of backlog bytes. The problem becomes clearer in the last show command, where qdisc_purge_queue triggers qdisc_tree_reduce_backlog with the positive backlog and causes an underflow in the tbf parent's backlog (4096 Mb instead of 0). To fix this issue, the codepath for all clients of qdisc_dequeue_internal has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel. qdisc_dequeue_internal handles the backlog adjustments for all cases that do not directly use the dequeue handler. The old fq_codel_change limit adjustment loop accumulated the arguments to the subsequent qdisc_tree_reduce_backlog call through the cstats field. However, this is confusing and error prone as fq_codel_dequeue could also potentially mutate this field (which qdisc_dequeue_internal calls in the non gso_skb case), so we have unified the code here with other qdiscs.
CVE-2025-39705: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix a Null pointer dereference vulnerability [Why] A null pointer dereference vulnerability exists in the AMD display driver's (DC module) cleanup function dc_destruct(). When display control context (dc->ctx) construction fails (due to memory allocation failure), this pointer remains NULL. During subsequent error handling when dc_destruct() is called, there's no NULL check before dereferencing the perf_trace member (dc->ctx->perf_trace), causing a kernel null pointer dereference crash. [How] Check if dc->ctx is non-NULL before dereferencing. (Updated commit text and removed unnecessary error message) (cherry picked from commit 9dd8e2ba268c636c240a918e0a31e6feaee19404)
CVE-2025-39707: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: check if hubbub is NULL in debugfs/amdgpu_dm_capabilities HUBBUB structure is not initialized on DCE hardware, so check if it is NULL to avoid null dereference while accessing amdgpu_dm_capabilities file in debugfs.
CVE-2025-39720: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix refcount leak causing resource not released When ksmbd_conn_releasing(opinfo->conn) returns true,the refcount was not decremented properly, causing a refcount leak that prevents the count from reaching zero and the memory from being released.
CVE-2025-39726: In the Linux kernel, the following vulnerability has been resolved: s390/ism: fix concurrency management in ism_cmd() The s390x ISM device data sheet clearly states that only one request-response sequence is allowable per ISM function at any point in time. Unfortunately as of today the s390/ism driver in Linux does not honor that requirement. This patch aims to rectify that. This problem was discovered based on Aliaksei's bug report which states that for certain workloads the ISM functions end up entering error state (with PEC 2 as seen from the logs) after a while and as a consequence connections handled by the respective function break, and for future connection requests the ISM device is not considered -- given it is in a dysfunctional state. During further debugging PEC 3A was observed as well. A kernel message like [ 1211.244319] zpci: 061a:00:00.0: Event 0x2 reports an error for PCI function 0x61a is a reliable indicator of the stated function entering error state with PEC 2. Let me also point out that a kernel message like [ 1211.244325] zpci: 061a:00:00.0: The ism driver bound to the device does not support error recovery is a reliable indicator that the ISM function won't be auto-recovered because the ISM driver currently lacks support for it. On a technical level, without this synchronization, commands (inputs to the FW) may be partially or fully overwritten (corrupted) by another CPU trying to issue commands on the same function. There is hard evidence that this can lead to DMB token values being used as DMB IOVAs, leading to PEC 2 PCI events indicating invalid DMA. But this is only one of the failure modes imaginable. In theory even completely losing one command and executing another one twice and then trying to interpret the outputs as if the command we intended to execute was actually executed and not the other one is also possible. Frankly, I don't feel confident about providing an exhaustive list of possible consequences.
CVE-2025-39732: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: fix sleeping-in-atomic in ath11k_mac_op_set_bitrate_mask() ath11k_mac_disable_peer_fixed_rate() is passed as the iterator to ieee80211_iterate_stations_atomic(). Note in this case the iterator is required to be atomic, however ath11k_mac_disable_peer_fixed_rate() does not follow it as it might sleep. Consequently below warning is seen: BUG: sleeping function called from invalid context at wmi.c:304 Call Trace: <TASK> dump_stack_lvl __might_resched.cold ath11k_wmi_cmd_send ath11k_wmi_set_peer_param ath11k_mac_disable_peer_fixed_rate ieee80211_iterate_stations_atomic ath11k_mac_op_set_bitrate_mask.cold Change to ieee80211_iterate_stations_mtx() to fix this issue. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
CVE-2025-39744: In the Linux kernel, the following vulnerability has been resolved: rcu: Fix rcu_read_unlock() deadloop due to IRQ work During rcu_read_unlock_special(), if this happens during irq_exit(), we can lockup if an IPI is issued. This is because the IPI itself triggers the irq_exit() path causing a recursive lock up. This is precisely what Xiongfeng found when invoking a BPF program on the trace_tick_stop() tracepoint As shown in the trace below. Fix by managing the irq_work state correctly. irq_exit() __irq_exit_rcu() /* in_hardirq() returns false after this */ preempt_count_sub(HARDIRQ_OFFSET) tick_irq_exit() tick_nohz_irq_exit() tick_nohz_stop_sched_tick() trace_tick_stop() /* a bpf prog is hooked on this trace point */ __bpf_trace_tick_stop() bpf_trace_run2() rcu_read_unlock_special() /* will send a IPI to itself */ irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); A simple reproducer can also be obtained by doing the following in tick_irq_exit(). It will hang on boot without the patch: static inline void tick_irq_exit(void) { + rcu_read_lock(); + WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true); + rcu_read_unlock(); + [neeraj: Apply Frederic's suggested fix for PREEMPT_RT]
CVE-2025-39746: In the Linux kernel, the following vulnerability has been resolved: wifi: ath10k: shutdown driver when hardware is unreliable In rare cases, ath10k may lose connection with the PCIe bus due to some unknown reasons, which could further lead to system crashes during resuming due to watchdog timeout: ath10k_pci 0000:01:00.0: wmi command 20486 timeout, restarting hardware ath10k_pci 0000:01:00.0: already restarting ath10k_pci 0000:01:00.0: failed to stop WMI vdev 0: -11 ath10k_pci 0000:01:00.0: failed to stop vdev 0: -11 ieee80211 phy0: PM: **** DPM device timeout **** Call Trace: panic+0x125/0x315 dpm_watchdog_set+0x54/0x54 dpm_watchdog_handler+0x57/0x57 call_timer_fn+0x31/0x13c At this point, all WMI commands will timeout and attempt to restart device. So set a threshold for consecutive restart failures. If the threshold is exceeded, consider the hardware is unreliable and all ath10k operations should be skipped to avoid system crash. fail_cont_count and pending_recovery are atomic variables, and do not involve complex conditional logic. Therefore, even if recovery check and reconfig complete are executed concurrently, the recovery mechanism will not be broken. Tested-on: QCA6174 hw3.2 PCI WLAN.RM.4.4.1-00288-QCARMSWPZ-1
CVE-2025-39747: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Add error handling for krealloc in metadata setup Function msm_ioctl_gem_info_set_metadata() now checks for krealloc failure and returns -ENOMEM, avoiding potential NULL pointer dereference. Explicitly avoids __GFP_NOFAIL due to deadlock risks and allocation constraints. Patchwork: https://patchwork.freedesktop.org/patch/661235/
CVE-2025-39748: In the Linux kernel, the following vulnerability has been resolved: bpf: Forget ranges when refining tnum after JSET Syzbot reported a kernel warning due to a range invariant violation on the following BPF program. 0: call bpf_get_netns_cookie 1: if r0 == 0 goto <exit> 2: if r0 & Oxffffffff goto <exit> The issue is on the path where we fall through both jumps. That path is unreachable at runtime: after insn 1, we know r0 != 0, but with the sign extension on the jset, we would only fallthrough insn 2 if r0 == 0. Unfortunately, is_branch_taken() isn't currently able to figure this out, so the verifier walks all branches. The verifier then refines the register bounds using the second condition and we end up with inconsistent bounds on this unreachable path: 1: if r0 == 0 goto <exit> r0: u64=[0x1, 0xffffffffffffffff] var_off=(0, 0xffffffffffffffff) 2: if r0 & 0xffffffff goto <exit> r0 before reg_bounds_sync: u64=[0x1, 0xffffffffffffffff] var_off=(0, 0) r0 after reg_bounds_sync: u64=[0x1, 0] var_off=(0, 0) Improving the range refinement for JSET to cover all cases is tricky. We also don't expect many users to rely on JSET given LLVM doesn't generate those instructions. So instead of improving the range refinement for JSETs, Eduard suggested we forget the ranges whenever we're narrowing tnums after a JSET. This patch implements that approach.
CVE-2025-39754: In the Linux kernel, the following vulnerability has been resolved: mm/smaps: fix race between smaps_hugetlb_range and migration smaps_hugetlb_range() handles the pte without holdling ptl, and may be concurrenct with migration, leaing to BUG_ON in pfn_swap_entry_to_page(). The race is as follows. smaps_hugetlb_range migrate_pages huge_ptep_get remove_migration_ptes folio_unlock pfn_swap_entry_folio BUG_ON To fix it, hold ptl lock in smaps_hugetlb_range().
CVE-2025-39762: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: add null check [WHY] Prevents null pointer dereferences to enhance function robustness [HOW] Adds early null check and return false if invalid.
CVE-2025-39764: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: remove refcounting in expectation dumpers Same pattern as previous patch: do not keep the expectation object alive via refcount, only store a cookie value and then use that as the skip hint for dump resumption. AFAICS this has the same issue as the one resolved in the conntrack dumper, when we do if (!refcount_inc_not_zero(&exp->use)) to increment the refcount, there is a chance that exp == last, which causes a double-increment of the refcount and subsequent memory leak.
CVE-2025-39767: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Optimize module load time by optimizing PLT/GOT counting When enabling CONFIG_KASAN, CONFIG_PREEMPT_VOLUNTARY_BUILD and CONFIG_PREEMPT_VOLUNTARY at the same time, there will be soft deadlock, the relevant logs are as follows: rcu: INFO: rcu_sched self-detected stall on CPU ... Call Trace: [<900000000024f9e4>] show_stack+0x5c/0x180 [<90000000002482f4>] dump_stack_lvl+0x94/0xbc [<9000000000224544>] rcu_dump_cpu_stacks+0x1fc/0x280 [<900000000037ac80>] rcu_sched_clock_irq+0x720/0xf88 [<9000000000396c34>] update_process_times+0xb4/0x150 [<90000000003b2474>] tick_nohz_handler+0xf4/0x250 [<9000000000397e28>] __hrtimer_run_queues+0x1d0/0x428 [<9000000000399b2c>] hrtimer_interrupt+0x214/0x538 [<9000000000253634>] constant_timer_interrupt+0x64/0x80 [<9000000000349938>] __handle_irq_event_percpu+0x78/0x1a0 [<9000000000349a78>] handle_irq_event_percpu+0x18/0x88 [<9000000000354c00>] handle_percpu_irq+0x90/0xf0 [<9000000000348c74>] handle_irq_desc+0x94/0xb8 [<9000000001012b28>] handle_cpu_irq+0x68/0xa0 [<9000000001def8c0>] handle_loongarch_irq+0x30/0x48 [<9000000001def958>] do_vint+0x80/0xd0 [<9000000000268a0c>] kasan_mem_to_shadow.part.0+0x2c/0x2a0 [<90000000006344f4>] __asan_load8+0x4c/0x120 [<900000000025c0d0>] module_frob_arch_sections+0x5c8/0x6b8 [<90000000003895f0>] load_module+0x9e0/0x2958 [<900000000038b770>] __do_sys_init_module+0x208/0x2d0 [<9000000001df0c34>] do_syscall+0x94/0x190 [<900000000024d6fc>] handle_syscall+0xbc/0x158 After analysis, this is because the slow speed of loading the amdgpu module leads to the long time occupation of the cpu and then the soft deadlock. When loading a module, module_frob_arch_sections() tries to figure out the number of PLTs/GOTs that will be needed to handle all the RELAs. It will call the count_max_entries() to find in an out-of-order date which counting algorithm has O(n^2) complexity. To make it faster, we sort the relocation list by info and addend. That way, to check for a duplicate relocation, it just needs to compare with the previous entry. This reduces the complexity of the algorithm to O(n log n), as done in commit d4e0340919fb ("arm64/module: Optimize module load time by optimizing PLT counting"). This gives sinificant reduction in module load time for modules with large number of relocations. After applying this patch, the soft deadlock problem has been solved, and the kernel starts normally without "Call Trace". Using the default configuration to test some modules, the results are as follows: Module Size ip_tables 36K fat 143K radeon 2.5MB amdgpu 16MB Without this patch: Module Module load time (ms) Count(PLTs/GOTs) ip_tables 18 59/6 fat 0 162/14 radeon 54 1221/84 amdgpu 1411 4525/1098 With this patch: Module Module load time (ms) Count(PLTs/GOTs) ip_tables 18 59/6 fat 0 162/14 radeon 22 1221/84 amdgpu 45 4525/1098
CVE-2025-39779: In the Linux kernel, the following vulnerability has been resolved: btrfs: subpage: keep TOWRITE tag until folio is cleaned btrfs_subpage_set_writeback() calls folio_start_writeback() the first time a folio is written back, and it also clears the PAGECACHE_TAG_TOWRITE tag even if there are still dirty blocks in the folio. This can break ordering guarantees, such as those required by btrfs_wait_ordered_extents(). That ordering breakage leads to a real failure. For example, running generic/464 on a zoned setup will hit the following ASSERT. This happens because the broken ordering fails to flush existing dirty pages before the file size is truncated. assertion failed: !list_empty(&ordered->list) :: 0, in fs/btrfs/zoned.c:1899 ------------[ cut here ]------------ kernel BUG at fs/btrfs/zoned.c:1899! Oops: invalid opcode: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 1906169 Comm: kworker/u130:2 Kdump: loaded Not tainted 6.16.0-rc6-BTRFS-ZNS+ #554 PREEMPT(voluntary) Hardware name: Supermicro Super Server/H12SSL-NT, BIOS 2.0 02/22/2021 Workqueue: btrfs-endio-write btrfs_work_helper [btrfs] RIP: 0010:btrfs_finish_ordered_zoned.cold+0x50/0x52 [btrfs] RSP: 0018:ffffc9002efdbd60 EFLAGS: 00010246 RAX: 000000000000004c RBX: ffff88811923c4e0 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff827e38b1 RDI: 00000000ffffffff RBP: ffff88810005d000 R08: 00000000ffffdfff R09: ffffffff831051c8 R10: ffffffff83055220 R11: 0000000000000000 R12: ffff8881c2458c00 R13: ffff88811923c540 R14: ffff88811923c5e8 R15: ffff8881c1bd9680 FS: 0000000000000000(0000) GS:ffff88a04acd0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f907c7a918c CR3: 0000000004024000 CR4: 0000000000350ef0 Call Trace: <TASK> ? srso_return_thunk+0x5/0x5f btrfs_finish_ordered_io+0x4a/0x60 [btrfs] btrfs_work_helper+0xf9/0x490 [btrfs] process_one_work+0x204/0x590 ? srso_return_thunk+0x5/0x5f worker_thread+0x1d6/0x3d0 ? __pfx_worker_thread+0x10/0x10 kthread+0x118/0x230 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x205/0x260 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Consider process A calling writepages() with WB_SYNC_NONE. In zoned mode or for compressed writes, it locks several folios for delalloc and starts writing them out. Let's call the last locked folio folio X. Suppose the write range only partially covers folio X, leaving some pages dirty. Process A calls btrfs_subpage_set_writeback() when building a bio. This function call clears the TOWRITE tag of folio X, whose size = 8K and the block size = 4K. It is following state. 0 4K 8K |/////|/////| (flag: DIRTY, tag: DIRTY) <-----> Process A will write this range. Now suppose process B concurrently calls writepages() with WB_SYNC_ALL. It calls tag_pages_for_writeback() to tag dirty folios with PAGECACHE_TAG_TOWRITE. Since folio X is still dirty, it gets tagged. Then, B collects tagged folios using filemap_get_folios_tag() and must wait for folio X to be written before returning from writepages(). 0 4K 8K |/////|/////| (flag: DIRTY, tag: DIRTY|TOWRITE) However, between tagging and collecting, process A may call btrfs_subpage_set_writeback() and clear folio X's TOWRITE tag. 0 4K 8K | |/////| (flag: DIRTY|WRITEBACK, tag: DIRTY) As a result, process B won't see folio X in its batch, and returns without waiting for it. This breaks the WB_SYNC_ALL ordering requirement. Fix this by using btrfs_subpage_set_writeback_keepwrite(), which retains the TOWRITE tag. We now manually clear the tag only after the folio becomes clean, via the xas operation.
CVE-2025-39789: In the Linux kernel, the following vulnerability has been resolved: crypto: x86/aegis - Add missing error checks The skcipher_walk functions can allocate memory and can fail, so checking for errors is necessary.
CVE-2025-39797: In the Linux kernel, the following vulnerability has been resolved: xfrm: Duplicate SPI Handling The issue originates when Strongswan initiates an XFRM_MSG_ALLOCSPI Netlink message, which triggers the kernel function xfrm_alloc_spi(). This function is expected to ensure uniqueness of the Security Parameter Index (SPI) for inbound Security Associations (SAs). However, it can return success even when the requested SPI is already in use, leading to duplicate SPIs assigned to multiple inbound SAs, differentiated only by their destination addresses. This behavior causes inconsistencies during SPI lookups for inbound packets. Since the lookup may return an arbitrary SA among those with the same SPI, packet processing can fail, resulting in packet drops. According to RFC 4301 section 4.4.2 , for inbound processing a unicast SA is uniquely identified by the SPI and optionally protocol. Reproducing the Issue Reliably: To consistently reproduce the problem, restrict the available SPI range in charon.conf : spi_min = 0x10000000 spi_max = 0x10000002 This limits the system to only 2 usable SPI values. Next, create more than 2 Child SA. each using unique pair of src/dst address. As soon as the 3rd Child SA is initiated, it will be assigned a duplicate SPI, since the SPI pool is already exhausted. With a narrow SPI range, the issue is consistently reproducible. With a broader/default range, it becomes rare and unpredictable. Current implementation: xfrm_spi_hash() lookup function computes hash using daddr, proto, and family. So if two SAs have the same SPI but different destination addresses, then they will: a. Hash into different buckets b. Be stored in different linked lists (byspi + h) c. Not be seen in the same hlist_for_each_entry_rcu() iteration. As a result, the lookup will result in NULL and kernel allows that Duplicate SPI Proposed Change: xfrm_state_lookup_spi_proto() does a truly global search - across all states, regardless of hash bucket and matches SPI and proto.
CVE-2025-39810: In the Linux kernel, the following vulnerability has been resolved: bnxt_en: Fix memory corruption when FW resources change during ifdown bnxt_set_dflt_rings() assumes that it is always called before any TC has been created. So it doesn't take bp->num_tc into account and assumes that it is always 0 or 1. In the FW resource or capability change scenario, the FW will return flags in bnxt_hwrm_if_change() that will cause the driver to reinitialize and call bnxt_cancel_reservations(). This will lead to bnxt_init_dflt_ring_mode() calling bnxt_set_dflt_rings() and bp->num_tc may be greater than 1. This will cause bp->tx_ring[] to be sized too small and cause memory corruption in bnxt_alloc_cp_rings(). Fix it by properly scaling the TX rings by bp->num_tc in the code paths mentioned above. Add 2 helper functions to determine bp->tx_nr_rings and bp->tx_nr_rings_per_tc.
CVE-2025-39829: In the Linux kernel, the following vulnerability has been resolved: trace/fgraph: Fix the warning caused by missing unregister notifier This warning was triggered during testing on v6.16: notifier callback ftrace_suspend_notifier_call already registered WARNING: CPU: 2 PID: 86 at kernel/notifier.c:23 notifier_chain_register+0x44/0xb0 ... Call Trace: <TASK> blocking_notifier_chain_register+0x34/0x60 register_ftrace_graph+0x330/0x410 ftrace_profile_write+0x1e9/0x340 vfs_write+0xf8/0x420 ? filp_flush+0x8a/0xa0 ? filp_close+0x1f/0x30 ? do_dup2+0xaf/0x160 ksys_write+0x65/0xe0 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x77/0x7f When writing to the function_profile_enabled interface, the notifier was not unregistered after start_graph_tracing failed, causing a warning the next time function_profile_enabled was written. Fixed by adding unregister_pm_notifier in the exception path.
CVE-2025-39833: In the Linux kernel, the following vulnerability has been resolved: mISDN: hfcpci: Fix warning when deleting uninitialized timer With CONFIG_DEBUG_OBJECTS_TIMERS unloading hfcpci module leads to the following splat: [ 250.215892] ODEBUG: assert_init not available (active state 0) object: ffffffffc01a3dc0 object type: timer_list hint: 0x0 [ 250.217520] WARNING: CPU: 0 PID: 233 at lib/debugobjects.c:612 debug_print_object+0x1b6/0x2c0 [ 250.218775] Modules linked in: hfcpci(-) mISDN_core [ 250.219537] CPU: 0 UID: 0 PID: 233 Comm: rmmod Not tainted 6.17.0-rc2-g6f713187ac98 #2 PREEMPT(voluntary) [ 250.220940] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 250.222377] RIP: 0010:debug_print_object+0x1b6/0x2c0 [ 250.223131] Code: fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 4f 41 56 48 8b 14 dd a0 4e 01 9f 48 89 ee 48 c7 c7 20 46 01 9f e8 cb 84d [ 250.225805] RSP: 0018:ffff888015ea7c08 EFLAGS: 00010286 [ 250.226608] RAX: 0000000000000000 RBX: 0000000000000005 RCX: ffffffff9be93a95 [ 250.227708] RDX: 1ffff1100d945138 RSI: 0000000000000008 RDI: ffff88806ca289c0 [ 250.228993] RBP: ffffffff9f014a00 R08: 0000000000000001 R09: ffffed1002bd4f39 [ 250.230043] R10: ffff888015ea79cf R11: 0000000000000001 R12: 0000000000000001 [ 250.231185] R13: ffffffff9eea0520 R14: 0000000000000000 R15: ffff888015ea7cc8 [ 250.232454] FS: 00007f3208f01540(0000) GS:ffff8880caf5a000(0000) knlGS:0000000000000000 [ 250.233851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 250.234856] CR2: 00007f32090a7421 CR3: 0000000004d63000 CR4: 00000000000006f0 [ 250.236117] Call Trace: [ 250.236599] <TASK> [ 250.236967] ? trace_irq_enable.constprop.0+0xd4/0x130 [ 250.237920] debug_object_assert_init+0x1f6/0x310 [ 250.238762] ? __pfx_debug_object_assert_init+0x10/0x10 [ 250.239658] ? __lock_acquire+0xdea/0x1c70 [ 250.240369] __try_to_del_timer_sync+0x69/0x140 [ 250.241172] ? __pfx___try_to_del_timer_sync+0x10/0x10 [ 250.242058] ? __timer_delete_sync+0xc6/0x120 [ 250.242842] ? lock_acquire+0x30/0x80 [ 250.243474] ? __timer_delete_sync+0xc6/0x120 [ 250.244262] __timer_delete_sync+0x98/0x120 [ 250.245015] HFC_cleanup+0x10/0x20 [hfcpci] [ 250.245704] __do_sys_delete_module+0x348/0x510 [ 250.246461] ? __pfx___do_sys_delete_module+0x10/0x10 [ 250.247338] do_syscall_64+0xc1/0x360 [ 250.247924] entry_SYSCALL_64_after_hwframe+0x77/0x7f Fix this by initializing hfc_tl timer with DEFINE_TIMER macro. Also, use mod_timer instead of manual timeout update.
CVE-2025-39850: In the Linux kernel, the following vulnerability has been resolved: vxlan: Fix NPD in {arp,neigh}_reduce() when using nexthop objects When the "proxy" option is enabled on a VXLAN device, the device will suppress ARP requests and IPv6 Neighbor Solicitation messages if it is able to reply on behalf of the remote host. That is, if a matching and valid neighbor entry is configured on the VXLAN device whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The code currently assumes that the FDB entry for the neighbor's MAC address points to a valid remote destination, but this is incorrect if the entry is associated with an FDB nexthop group. This can result in a NPD [1][3] which can be reproduced using [2][4]. Fix by checking that the remote destination exists before dereferencing it. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 4 UID: 0 PID: 365 Comm: arping Not tainted 6.17.0-rc2-virtme-g2a89cb21162c #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014 RIP: 0010:vxlan_xmit+0xb58/0x15f0 [...] Call Trace: <TASK> dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 packet_sendmsg+0x113a/0x1850 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [2] #!/bin/bash ip address add 192.0.2.1/32 dev lo ip nexthop add id 1 via 192.0.2.2 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 4789 proxy ip neigh add 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm dev vx0 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10 arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3 [3] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 13 UID: 0 PID: 372 Comm: ndisc6 Not tainted 6.17.0-rc2-virtmne-g6ee90cb26014 #3 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1v996), BIOS 1.17.0-4.fc41 04/01/2x014 RIP: 0010:vxlan_xmit+0x803/0x1600 [...] Call Trace: <TASK> dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 ip6_finish_output2+0x210/0x6c0 ip6_finish_output+0x1af/0x2b0 ip6_mr_output+0x92/0x3e0 ip6_send_skb+0x30/0x90 rawv6_sendmsg+0xe6e/0x12e0 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7f383422ec77 [4] #!/bin/bash ip address add 2001:db8:1::1/128 dev lo ip nexthop add id 1 via 2001:db8:1::1 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 2001:db8:1::1 dstport 4789 proxy ip neigh add 2001:db8:1::3 lladdr 00:11:22:33:44:55 nud perm dev vx0 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10 ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0
CVE-2025-39851: In the Linux kernel, the following vulnerability has been resolved: vxlan: Fix NPD when refreshing an FDB entry with a nexthop object VXLAN FDB entries can point to either a remote destination or an FDB nexthop group. The latter is usually used in EVPN deployments where learning is disabled. However, when learning is enabled, an incoming packet might try to refresh an FDB entry that points to an FDB nexthop group and therefore does not have a remote. Such packets should be dropped, but they are only dropped after dereferencing the non-existent remote, resulting in a NPD [1] which can be reproduced using [2]. Fix by dropping such packets earlier. Remove the misleading comment from first_remote_rcu(). [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 13 UID: 0 PID: 361 Comm: mausezahn Not tainted 6.17.0-rc1-virtme-g9f6b606b6b37 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014 RIP: 0010:vxlan_snoop+0x98/0x1e0 [...] Call Trace: <TASK> vxlan_encap_bypass+0x209/0x240 encap_bypass_if_local+0xb1/0x100 vxlan_xmit_one+0x1375/0x17e0 vxlan_xmit+0x6b4/0x15f0 dev_hard_start_xmit+0x5d/0x1c0 __dev_queue_xmit+0x246/0xfd0 packet_sendmsg+0x113a/0x1850 __sock_sendmsg+0x38/0x70 __sys_sendto+0x126/0x180 __x64_sys_sendto+0x24/0x30 do_syscall_64+0xa4/0x260 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [2] #!/bin/bash ip address add 192.0.2.1/32 dev lo ip address add 192.0.2.2/32 dev lo ip nexthop add id 1 via 192.0.2.3 fdb ip nexthop add id 10 group 1 fdb ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass ip link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning bridge fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020 bridge fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q
CVE-2025-39859: In the Linux kernel, the following vulnerability has been resolved: ptp: ocp: fix use-after-free bugs causing by ptp_ocp_watchdog The ptp_ocp_detach() only shuts down the watchdog timer if it is pending. However, if the timer handler is already running, the timer_delete_sync() is not called. This leads to race conditions where the devlink that contains the ptp_ocp is deallocated while the timer handler is still accessing it, resulting in use-after-free bugs. The following details one of the race scenarios. (thread 1) | (thread 2) ptp_ocp_remove() | ptp_ocp_detach() | ptp_ocp_watchdog() if (timer_pending(&bp->watchdog))| bp = timer_container_of() timer_delete_sync() | | devlink_free(devlink) //free | | bp-> //use Resolve this by unconditionally calling timer_delete_sync() to ensure the timer is reliably deactivated, preventing any access after free.
CVE-2025-39863: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmfmac: fix use-after-free when rescheduling brcmf_btcoex_info work The brcmf_btcoex_detach() only shuts down the btcoex timer, if the flag timer_on is false. However, the brcmf_btcoex_timerfunc(), which runs as timer handler, sets timer_on to false. This creates critical race conditions: 1.If brcmf_btcoex_detach() is called while brcmf_btcoex_timerfunc() is executing, it may observe timer_on as false and skip the call to timer_shutdown_sync(). 2.The brcmf_btcoex_timerfunc() may then reschedule the brcmf_btcoex_info worker after the cancel_work_sync() has been executed, resulting in use-after-free bugs. The use-after-free bugs occur in two distinct scenarios, depending on the timing of when the brcmf_btcoex_info struct is freed relative to the execution of its worker thread. Scenario 1: Freed before the worker is scheduled The brcmf_btcoex_info is deallocated before the worker is scheduled. A race condition can occur when schedule_work(&bt_local->work) is called after the target memory has been freed. The sequence of events is detailed below: CPU0 | CPU1 brcmf_btcoex_detach | brcmf_btcoex_timerfunc | bt_local->timer_on = false; if (cfg->btcoex->timer_on) | ... | cancel_work_sync(); | ... | kfree(cfg->btcoex); // FREE | | schedule_work(&bt_local->work); // USE Scenario 2: Freed after the worker is scheduled The brcmf_btcoex_info is freed after the worker has been scheduled but before or during its execution. In this case, statements within the brcmf_btcoex_handler() — such as the container_of macro and subsequent dereferences of the brcmf_btcoex_info object will cause a use-after-free access. The following timeline illustrates this scenario: CPU0 | CPU1 brcmf_btcoex_detach | brcmf_btcoex_timerfunc | bt_local->timer_on = false; if (cfg->btcoex->timer_on) | ... | cancel_work_sync(); | ... | schedule_work(); // Reschedule | kfree(cfg->btcoex); // FREE | brcmf_btcoex_handler() // Worker /* | btci = container_of(....); // USE The kfree() above could | ... also occur at any point | btci-> // USE during the worker's execution| */ | To resolve the race conditions, drop the conditional check and call timer_shutdown_sync() directly. It can deactivate the timer reliably, regardless of its current state. Once stopped, the timer_on state is then set to false.
CVE-2025-39886: In the Linux kernel, the following vulnerability has been resolved: bpf: Tell memcg to use allow_spinning=false path in bpf_timer_init() Currently, calling bpf_map_kmalloc_node() from __bpf_async_init() can cause various locking issues; see the following stack trace (edited for style) as one example: ... [10.011566] do_raw_spin_lock.cold [10.011570] try_to_wake_up (5) double-acquiring the same [10.011575] kick_pool rq_lock, causing a hardlockup [10.011579] __queue_work [10.011582] queue_work_on [10.011585] kernfs_notify [10.011589] cgroup_file_notify [10.011593] try_charge_memcg (4) memcg accounting raises an [10.011597] obj_cgroup_charge_pages MEMCG_MAX event [10.011599] obj_cgroup_charge_account [10.011600] __memcg_slab_post_alloc_hook [10.011603] __kmalloc_node_noprof ... [10.011611] bpf_map_kmalloc_node [10.011612] __bpf_async_init [10.011615] bpf_timer_init (3) BPF calls bpf_timer_init() [10.011617] bpf_prog_xxxxxxxxxxxxxxxx_fcg_runnable [10.011619] bpf__sched_ext_ops_runnable [10.011620] enqueue_task_scx (2) BPF runs with rq_lock held [10.011622] enqueue_task [10.011626] ttwu_do_activate [10.011629] sched_ttwu_pending (1) grabs rq_lock ... The above was reproduced on bpf-next (b338cf849ec8) by modifying ./tools/sched_ext/scx_flatcg.bpf.c to call bpf_timer_init() during ops.runnable(), and hacking the memcg accounting code a bit to make a bpf_timer_init() call more likely to raise an MEMCG_MAX event. We have also run into other similar variants (both internally and on bpf-next), including double-acquiring cgroup_file_kn_lock, the same worker_pool::lock, etc. As suggested by Shakeel, fix this by using __GFP_HIGH instead of GFP_ATOMIC in __bpf_async_init(), so that e.g. if try_charge_memcg() raises an MEMCG_MAX event, we call __memcg_memory_event() with @allow_spinning=false and avoid calling cgroup_file_notify() there. Depends on mm patch "memcg: skip cgroup_file_notify if spinning is not allowed": https://lore.kernel.org/bpf/20250905201606.66198-1-shakeel.butt@linux.dev/ v0 approach s/bpf_map_kmalloc_node/bpf_mem_alloc/ https://lore.kernel.org/bpf/20250905061919.439648-1-yepeilin@google.com/ v1 approach: https://lore.kernel.org/bpf/20250905234547.862249-1-yepeilin@google.com/
CVE-2025-39901: In the Linux kernel, the following vulnerability has been resolved: i40e: remove read access to debugfs files The 'command' and 'netdev_ops' debugfs files are a legacy debugging interface supported by the i40e driver since its early days by commit 02e9c290814c ("i40e: debugfs interface"). Both of these debugfs files provide a read handler which is mostly useless, and which is implemented with questionable logic. They both use a static 256 byte buffer which is initialized to the empty string. In the case of the 'command' file this buffer is literally never used and simply wastes space. In the case of the 'netdev_ops' file, the last command written is saved here. On read, the files contents are presented as the name of the device followed by a colon and then the contents of their respective static buffer. For 'command' this will always be "<device>: ". For 'netdev_ops', this will be "<device>: <last command written>". But note the buffer is shared between all devices operated by this module. At best, it is mostly meaningless information, and at worse it could be accessed simultaneously as there doesn't appear to be any locking mechanism. We have also recently received multiple reports for both read functions about their use of snprintf and potential overflow that could result in reading arbitrary kernel memory. For the 'command' file, this is definitely impossible, since the static buffer is always zero and never written to. For the 'netdev_ops' file, it does appear to be possible, if the user carefully crafts the command input, it will be copied into the buffer, which could be large enough to cause snprintf to truncate, which then causes the copy_to_user to read beyond the length of the buffer allocated by kzalloc. A minimal fix would be to replace snprintf() with scnprintf() which would cap the return to the number of bytes written, preventing an overflow. A more involved fix would be to drop the mostly useless static buffers, saving 512 bytes and modifying the read functions to stop needing those as input. Instead, lets just completely drop the read access to these files. These are debug interfaces exposed as part of debugfs, and I don't believe that dropping read access will break any script, as the provided output is pretty useless. You can find the netdev name through other more standard interfaces, and the 'netdev_ops' interface can easily result in garbage if you issue simultaneous writes to multiple devices at once. In order to properly remove the i40e_dbg_netdev_ops_buf, we need to refactor its write function to avoid using the static buffer. Instead, use the same logic as the i40e_dbg_command_write, with an allocated buffer. Update the code to use this instead of the static buffer, and ensure we free the buffer on exit. This fixes simultaneous writes to 'netdev_ops' on multiple devices, and allows us to remove the now unused static buffer along with removing the read access.
CVE-2025-39910: In the Linux kernel, the following vulnerability has been resolved: mm/vmalloc, mm/kasan: respect gfp mask in kasan_populate_vmalloc() kasan_populate_vmalloc() and its helpers ignore the caller's gfp_mask and always allocate memory using the hardcoded GFP_KERNEL flag. This makes them inconsistent with vmalloc(), which was recently extended to support GFP_NOFS and GFP_NOIO allocations. Page table allocations performed during shadow population also ignore the external gfp_mask. To preserve the intended semantics of GFP_NOFS and GFP_NOIO, wrap the apply_to_page_range() calls into the appropriate memalloc scope. xfs calls vmalloc with GFP_NOFS, so this bug could lead to deadlock. There was a report here https://lkml.kernel.org/r/686ea951.050a0220.385921.0016.GAE@google.com This patch: - Extends kasan_populate_vmalloc() and helpers to take gfp_mask; - Passes gfp_mask down to alloc_pages_bulk() and __get_free_page(); - Enforces GFP_NOFS/NOIO semantics with memalloc_*_save()/restore() around apply_to_page_range(); - Updates vmalloc.c and percpu allocator call sites accordingly.
CVE-2025-39925: In the Linux kernel, the following vulnerability has been resolved: can: j1939: implement NETDEV_UNREGISTER notification handler syzbot is reporting unregister_netdevice: waiting for vcan0 to become free. Usage count = 2 problem, for j1939 protocol did not have NETDEV_UNREGISTER notification handler for undoing changes made by j1939_sk_bind(). Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") expects that a call to j1939_priv_put() can be unconditionally delayed until j1939_sk_sock_destruct() is called. But we need to call j1939_priv_put() against an extra ref held by j1939_sk_bind() call (as a part of undoing changes made by j1939_sk_bind()) as soon as NETDEV_UNREGISTER notification fires (i.e. before j1939_sk_sock_destruct() is called via j1939_sk_release()). Otherwise, the extra ref on "struct j1939_priv" held by j1939_sk_bind() call prevents "struct net_device" from dropping the usage count to 1; making it impossible for unregister_netdevice() to continue. [mkl: remove space in front of label]
CVE-2025-39927: In the Linux kernel, the following vulnerability has been resolved: ceph: fix race condition validating r_parent before applying state Add validation to ensure the cached parent directory inode matches the directory info in MDS replies. This prevents client-side race conditions where concurrent operations (e.g. rename) cause r_parent to become stale between request initiation and reply processing, which could lead to applying state changes to incorrect directory inodes. [ idryomov: folded a kerneldoc fixup and a follow-up fix from Alex to move CEPH_CAP_PIN reference when r_parent is updated: When the parent directory lock is not held, req->r_parent can become stale and is updated to point to the correct inode. However, the associated CEPH_CAP_PIN reference was not being adjusted. The CEPH_CAP_PIN is a reference on an inode that is tracked for accounting purposes. Moving this pin is important to keep the accounting balanced. When the pin was not moved from the old parent to the new one, it created two problems: The reference on the old, stale parent was never released, causing a reference leak. A reference for the new parent was never acquired, creating the risk of a reference underflow later in ceph_mdsc_release_request(). This patch corrects the logic by releasing the pin from the old parent and acquiring it for the new parent when r_parent is switched. This ensures reference accounting stays balanced. ]
CVE-2025-39932: In the Linux kernel, the following vulnerability has been resolved: smb: client: let smbd_destroy() call disable_work_sync(&info->post_send_credits_work) In smbd_destroy() we may destroy the memory so we better wait until post_send_credits_work is no longer pending and will never be started again. I actually just hit the case using rxe: WARNING: CPU: 0 PID: 138 at drivers/infiniband/sw/rxe/rxe_verbs.c:1032 rxe_post_recv+0x1ee/0x480 [rdma_rxe] ... [ 5305.686979] [ T138] smbd_post_recv+0x445/0xc10 [cifs] [ 5305.687135] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687149] [ T138] ? __kasan_check_write+0x14/0x30 [ 5305.687185] [ T138] ? __pfx_smbd_post_recv+0x10/0x10 [cifs] [ 5305.687329] [ T138] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 5305.687356] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687368] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687378] [ T138] ? _raw_spin_unlock_irqrestore+0x11/0x60 [ 5305.687389] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687399] [ T138] ? get_receive_buffer+0x168/0x210 [cifs] [ 5305.687555] [ T138] smbd_post_send_credits+0x382/0x4b0 [cifs] [ 5305.687701] [ T138] ? __pfx_smbd_post_send_credits+0x10/0x10 [cifs] [ 5305.687855] [ T138] ? __pfx___schedule+0x10/0x10 [ 5305.687865] [ T138] ? __pfx__raw_spin_lock_irq+0x10/0x10 [ 5305.687875] [ T138] ? queue_delayed_work_on+0x8e/0xa0 [ 5305.687889] [ T138] process_one_work+0x629/0xf80 [ 5305.687908] [ T138] ? srso_alias_return_thunk+0x5/0xfbef5 [ 5305.687917] [ T138] ? __kasan_check_write+0x14/0x30 [ 5305.687933] [ T138] worker_thread+0x87f/0x1570 ... It means rxe_post_recv was called after rdma_destroy_qp(). This happened because put_receive_buffer() was triggered by ib_drain_qp() and called: queue_work(info->workqueue, &info->post_send_credits_work);
CVE-2025-39933: In the Linux kernel, the following vulnerability has been resolved: smb: client: let recv_done verify data_offset, data_length and remaining_data_length This is inspired by the related server fixes.
CVE-2025-39940: In the Linux kernel, the following vulnerability has been resolved: dm-stripe: fix a possible integer overflow There's a possible integer overflow in stripe_io_hints if we have too large chunk size. Test if the overflow happened, and if it did, don't set limits->io_min and limits->io_opt;
CVE-2025-39947: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Harden uplink netdev access against device unbind The function mlx5_uplink_netdev_get() gets the uplink netdevice pointer from mdev->mlx5e_res.uplink_netdev. However, the netdevice can be removed and its pointer cleared when unbound from the mlx5_core.eth driver. This results in a NULL pointer, causing a kernel panic. BUG: unable to handle page fault for address: 0000000000001300 at RIP: 0010:mlx5e_vport_rep_load+0x22a/0x270 [mlx5_core] Call Trace: <TASK> mlx5_esw_offloads_rep_load+0x68/0xe0 [mlx5_core] esw_offloads_enable+0x593/0x910 [mlx5_core] mlx5_eswitch_enable_locked+0x341/0x420 [mlx5_core] mlx5_devlink_eswitch_mode_set+0x17e/0x3a0 [mlx5_core] devlink_nl_eswitch_set_doit+0x60/0xd0 genl_family_rcv_msg_doit+0xe0/0x130 genl_rcv_msg+0x183/0x290 netlink_rcv_skb+0x4b/0xf0 genl_rcv+0x24/0x40 netlink_unicast+0x255/0x380 netlink_sendmsg+0x1f3/0x420 __sock_sendmsg+0x38/0x60 __sys_sendto+0x119/0x180 do_syscall_64+0x53/0x1d0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Ensure the pointer is valid before use by checking it for NULL. If it is valid, immediately call netdev_hold() to take a reference, and preventing the netdevice from being freed while it is in use.
CVE-2025-39952: In the Linux kernel, the following vulnerability has been resolved: wifi: wilc1000: avoid buffer overflow in WID string configuration Fix the following copy overflow warning identified by Smatch checker. drivers/net/wireless/microchip/wilc1000/wlan_cfg.c:184 wilc_wlan_parse_response_frame() error: '__memcpy()' 'cfg->s[i]->str' copy overflow (512 vs 65537) This patch introduces size check before accessing the memory buffer. The checks are base on the WID type of received data from the firmware. For WID string configuration, the size limit is determined by individual element size in 'struct wilc_cfg_str_vals' that is maintained in 'len' field of 'struct wilc_cfg_str'.
CVE-2025-39961: In the Linux kernel, the following vulnerability has been resolved: iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path.
CVE-2025-39981: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: MGMT: Fix possible UAFs This attemps to fix possible UAFs caused by struct mgmt_pending being freed while still being processed like in the following trace, in order to fix mgmt_pending_valid is introduce and use to check if the mgmt_pending hasn't been removed from the pending list, on the complete callbacks it is used to check and in addtion remove the cmd from the list while holding mgmt_pending_lock to avoid TOCTOU problems since if the cmd is left on the list it can still be accessed and freed. BUG: KASAN: slab-use-after-free in mgmt_add_adv_patterns_monitor_sync+0x35/0x50 net/bluetooth/mgmt.c:5223 Read of size 8 at addr ffff8880709d4dc0 by task kworker/u11:0/55 CPU: 0 UID: 0 PID: 55 Comm: kworker/u11:0 Not tainted 6.16.4 #2 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Workqueue: hci0 hci_cmd_sync_work Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 mgmt_add_adv_patterns_monitor_sync+0x35/0x50 net/bluetooth/mgmt.c:5223 hci_cmd_sync_work+0x210/0x3a0 net/bluetooth/hci_sync.c:332 process_one_work kernel/workqueue.c:3238 [inline] process_scheduled_works+0xade/0x17b0 kernel/workqueue.c:3321 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3402 kthread+0x711/0x8a0 kernel/kthread.c:464 ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148 ret_from_fork_asm+0x1a/0x30 home/kwqcheii/source/fuzzing/kernel/kasan/linux-6.16.4/arch/x86/entry/entry_64.S:245 </TASK> Allocated by task 12210: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:377 [inline] __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:394 kasan_kmalloc include/linux/kasan.h:260 [inline] __kmalloc_cache_noprof+0x230/0x3d0 mm/slub.c:4364 kmalloc_noprof include/linux/slab.h:905 [inline] kzalloc_noprof include/linux/slab.h:1039 [inline] mgmt_pending_new+0x65/0x1e0 net/bluetooth/mgmt_util.c:269 mgmt_pending_add+0x35/0x140 net/bluetooth/mgmt_util.c:296 __add_adv_patterns_monitor+0x130/0x200 net/bluetooth/mgmt.c:5247 add_adv_patterns_monitor+0x214/0x360 net/bluetooth/mgmt.c:5364 hci_mgmt_cmd+0x9c9/0xef0 net/bluetooth/hci_sock.c:1719 hci_sock_sendmsg+0x6ca/0xef0 net/bluetooth/hci_sock.c:1839 sock_sendmsg_nosec net/socket.c:714 [inline] __sock_sendmsg+0x219/0x270 net/socket.c:729 sock_write_iter+0x258/0x330 net/socket.c:1133 new_sync_write fs/read_write.c:593 [inline] vfs_write+0x5c9/0xb30 fs/read_write.c:686 ksys_write+0x145/0x250 fs/read_write.c:738 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 12221: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:576 poison_slab_object mm/kasan/common.c:247 [inline] __kasan_slab_free+0x62/0x70 mm/kasan/common.c:264 kasan_slab_free include/linux/kasan.h:233 [inline] slab_free_hook mm/slub.c:2381 [inline] slab_free mm/slub.c:4648 [inline] kfree+0x18e/0x440 mm/slub.c:4847 mgmt_pending_free net/bluetooth/mgmt_util.c:311 [inline] mgmt_pending_foreach+0x30d/0x380 net/bluetooth/mgmt_util.c:257 __mgmt_power_off+0x169/0x350 net/bluetooth/mgmt.c:9444 hci_dev_close_sync+0x754/0x1330 net/bluetooth/hci_sync.c:5290 hci_dev_do_close net/bluetooth/hci_core.c:501 [inline] hci_dev_close+0x108/0x200 net/bluetooth/hci_core.c:526 sock_do_ioctl+0xd9/0x300 net/socket.c:1192 sock_ioctl+0x576/0x790 net/socket.c:1313 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:907 [inline] __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf ---truncated---
CVE-2025-39989: In the Linux kernel, the following vulnerability has been resolved: x86/mce: use is_copy_from_user() to determine copy-from-user context Patch series "mm/hwpoison: Fix regressions in memory failure handling", v4. ## 1. What am I trying to do: This patchset resolves two critical regressions related to memory failure handling that have appeared in the upstream kernel since version 5.17, as compared to 5.10 LTS. - copyin case: poison found in user page while kernel copying from user space - instr case: poison found while instruction fetching in user space ## 2. What is the expected outcome and why - For copyin case: Kernel can recover from poison found where kernel is doing get_user() or copy_from_user() if those places get an error return and the kernel return -EFAULT to the process instead of crashing. More specifily, MCE handler checks the fixup handler type to decide whether an in kernel #MC can be recovered. When EX_TYPE_UACCESS is found, the PC jumps to recovery code specified in _ASM_EXTABLE_FAULT() and return a -EFAULT to user space. - For instr case: If a poison found while instruction fetching in user space, full recovery is possible. User process takes #PF, Linux allocates a new page and fills by reading from storage. ## 3. What actually happens and why - For copyin case: kernel panic since v5.17 Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and later patches updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. It breaks previous EX_TYPE_UACCESS handling when posion found in get_user() or copy_from_user(). - For instr case: user process is killed by a SIGBUS signal due to #CMCI and #MCE race When an uncorrected memory error is consumed there is a race between the CMCI from the memory controller reporting an uncorrected error with a UCNA signature, and the core reporting and SRAR signature machine check when the data is about to be consumed. ### Background: why *UN*corrected errors tied to *C*MCI in Intel platform [1] Prior to Icelake memory controllers reported patrol scrub events that detected a previously unseen uncorrected error in memory by signaling a broadcast machine check with an SRAO (Software Recoverable Action Optional) signature in the machine check bank. This was overkill because it's not an urgent problem that no core is on the verge of consuming that bad data. It's also found that multi SRAO UCE may cause nested MCE interrupts and finally become an IERR. Hence, Intel downgrades the machine check bank signature of patrol scrub from SRAO to UCNA (Uncorrected, No Action required), and signal changed to #CMCI. Just to add to the confusion, Linux does take an action (in uc_decode_notifier()) to try to offline the page despite the UC*NA* signature name. ### Background: why #CMCI and #MCE race when poison is consuming in Intel platform [1] Having decided that CMCI/UCNA is the best action for patrol scrub errors, the memory controller uses it for reads too. But the memory controller is executing asynchronously from the core, and can't tell the difference between a "real" read and a speculative read. So it will do CMCI/UCNA if an error is found in any read. Thus: 1) Core is clever and thinks address A is needed soon, issues a speculative read. 2) Core finds it is going to use address A soon after sending the read request 3) The CMCI from the memory controller is in a race with MCE from the core that will soon try to retire the load from address A. Quite often (because speculation has got better) the CMCI from the memory controller is delivered before the core is committed to the instruction reading address A, so the interrupt is taken, and Linux offlines the page (marking it as poison). ## Why user process is killed for instr case Commit 046545a661af ("mm/hwpoison: fix error page recovered but reported "not ---truncated---
CVE-2025-39990: In the Linux kernel, the following vulnerability has been resolved: bpf: Check the helper function is valid in get_helper_proto kernel test robot reported verifier bug [1] where the helper func pointer could be NULL due to disabled config option. As Alexei suggested we could check on that in get_helper_proto directly. Marking tail_call helper func with BPF_PTR_POISON, because it is unused by design. [1] https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com
CVE-2025-40003: In the Linux kernel, the following vulnerability has been resolved: net: mscc: ocelot: Fix use-after-free caused by cyclic delayed work The origin code calls cancel_delayed_work() in ocelot_stats_deinit() to cancel the cyclic delayed work item ocelot->stats_work. However, cancel_delayed_work() may fail to cancel the work item if it is already executing. While destroy_workqueue() does wait for all pending work items in the work queue to complete before destroying the work queue, it cannot prevent the delayed work item from being rescheduled within the ocelot_check_stats_work() function. This limitation exists because the delayed work item is only enqueued into the work queue after its timer expires. Before the timer expiration, destroy_workqueue() has no visibility of this pending work item. Once the work queue appears empty, destroy_workqueue() proceeds with destruction. When the timer eventually expires, the delayed work item gets queued again, leading to the following warning: workqueue: cannot queue ocelot_check_stats_work on wq ocelot-switch-stats WARNING: CPU: 2 PID: 0 at kernel/workqueue.c:2255 __queue_work+0x875/0xaf0 ... RIP: 0010:__queue_work+0x875/0xaf0 ... RSP: 0018:ffff88806d108b10 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 0000000000000101 RCX: 0000000000000027 RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffff88806d123e88 RBP: ffffffff813c3170 R08: 0000000000000000 R09: ffffed100da247d2 R10: ffffed100da247d1 R11: ffff88806d123e8b R12: ffff88800c00f000 R13: ffff88800d7285c0 R14: ffff88806d0a5580 R15: ffff88800d7285a0 FS: 0000000000000000(0000) GS:ffff8880e5725000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe18e45ea10 CR3: 0000000005e6c000 CR4: 00000000000006f0 Call Trace: <IRQ> ? kasan_report+0xc6/0xf0 ? __pfx_delayed_work_timer_fn+0x10/0x10 ? __pfx_delayed_work_timer_fn+0x10/0x10 call_timer_fn+0x25/0x1c0 __run_timer_base.part.0+0x3be/0x8c0 ? __pfx_delayed_work_timer_fn+0x10/0x10 ? rcu_sched_clock_irq+0xb06/0x27d0 ? __pfx___run_timer_base.part.0+0x10/0x10 ? try_to_wake_up+0xb15/0x1960 ? _raw_spin_lock_irq+0x80/0xe0 ? __pfx__raw_spin_lock_irq+0x10/0x10 tmigr_handle_remote_up+0x603/0x7e0 ? __pfx_tmigr_handle_remote_up+0x10/0x10 ? sched_balance_trigger+0x1c0/0x9f0 ? sched_tick+0x221/0x5a0 ? _raw_spin_lock_irq+0x80/0xe0 ? __pfx__raw_spin_lock_irq+0x10/0x10 ? tick_nohz_handler+0x339/0x440 ? __pfx_tmigr_handle_remote_up+0x10/0x10 __walk_groups.isra.0+0x42/0x150 tmigr_handle_remote+0x1f4/0x2e0 ? __pfx_tmigr_handle_remote+0x10/0x10 ? ktime_get+0x60/0x140 ? lapic_next_event+0x11/0x20 ? clockevents_program_event+0x1d4/0x2a0 ? hrtimer_interrupt+0x322/0x780 handle_softirqs+0x16a/0x550 irq_exit_rcu+0xaf/0xe0 sysvec_apic_timer_interrupt+0x70/0x80 </IRQ> ... The following diagram reveals the cause of the above warning: CPU 0 (remove) | CPU 1 (delayed work callback) mscc_ocelot_remove() | ocelot_deinit() | ocelot_check_stats_work() ocelot_stats_deinit() | cancel_delayed_work()| ... | queue_delayed_work() destroy_workqueue() | (wait a time) | __queue_work() //UAF The above scenario actually constitutes a UAF vulnerability. The ocelot_stats_deinit() is only invoked when initialization failure or resource destruction, so we must ensure that any delayed work items cannot be rescheduled. Replace cancel_delayed_work() with disable_delayed_work_sync() to guarantee proper cancellation of the delayed work item and ensure completion of any currently executing work before the workqueue is deallocated. A deadlock concern was considered: ocelot_stats_deinit() is called in a process context and is not holding any locks that the delayed work item might also need. Therefore, the use of the _sync() variant is safe here. This bug was identified through static analysis. To reproduce the issue and validate the fix, I simulated ocelot-swit ---truncated---
CVE-2025-40005: In the Linux kernel, the following vulnerability has been resolved: spi: cadence-quadspi: Implement refcount to handle unbind during busy driver support indirect read and indirect write operation with assumption no force device removal(unbind) operation. However force device removal(removal) is still available to root superuser. Unbinding driver during operation causes kernel crash. This changes ensure driver able to handle such operation for indirect read and indirect write by implementing refcount to track attached devices to the controller and gracefully wait and until attached devices remove operation completed before proceed with removal operation.
CVE-2025-40016: In the Linux kernel, the following vulnerability has been resolved: media: uvcvideo: Mark invalid entities with id UVC_INVALID_ENTITY_ID Per UVC 1.1+ specification 3.7.2, units and terminals must have a non-zero unique ID. ``` Each Unit and Terminal within the video function is assigned a unique identification number, the Unit ID (UID) or Terminal ID (TID), contained in the bUnitID or bTerminalID field of the descriptor. The value 0x00 is reserved for undefined ID, ``` If we add a new entity with id 0 or a duplicated ID, it will be marked as UVC_INVALID_ENTITY_ID. In a previous attempt commit 3dd075fe8ebb ("media: uvcvideo: Require entities to have a non-zero unique ID"), we ignored all the invalid units, this broke a lot of non-compatible cameras. Hopefully we are more lucky this time. This also prevents some syzkaller reproducers from triggering warnings due to a chain of entities referring to themselves. In one particular case, an Output Unit is connected to an Input Unit, both with the same ID of 1. But when looking up for the source ID of the Output Unit, that same entity is found instead of the input entity, which leads to such warnings. In another case, a backward chain was considered finished as the source ID was 0. Later on, that entity was found, but its pads were not valid. Here is a sample stack trace for one of those cases. [ 20.650953] usb 1-1: new high-speed USB device number 2 using dummy_hcd [ 20.830206] usb 1-1: Using ep0 maxpacket: 8 [ 20.833501] usb 1-1: config 0 descriptor?? [ 21.038518] usb 1-1: string descriptor 0 read error: -71 [ 21.038893] usb 1-1: Found UVC 0.00 device <unnamed> (2833:0201) [ 21.039299] uvcvideo 1-1:0.0: Entity type for entity Output 1 was not initialized! [ 21.041583] uvcvideo 1-1:0.0: Entity type for entity Input 1 was not initialized! [ 21.042218] ------------[ cut here ]------------ [ 21.042536] WARNING: CPU: 0 PID: 9 at drivers/media/mc/mc-entity.c:1147 media_create_pad_link+0x2c4/0x2e0 [ 21.043195] Modules linked in: [ 21.043535] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.11.0-rc7-00030-g3480e43aeccf #444 [ 21.044101] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 [ 21.044639] Workqueue: usb_hub_wq hub_event [ 21.045100] RIP: 0010:media_create_pad_link+0x2c4/0x2e0 [ 21.045508] Code: fe e8 20 01 00 00 b8 f4 ff ff ff 48 83 c4 30 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc 0f 0b eb e9 0f 0b eb 0a 0f 0b eb 06 <0f> 0b eb 02 0f 0b b8 ea ff ff ff eb d4 66 2e 0f 1f 84 00 00 00 00 [ 21.046801] RSP: 0018:ffffc9000004b318 EFLAGS: 00010246 [ 21.047227] RAX: ffff888004e5d458 RBX: 0000000000000000 RCX: ffffffff818fccf1 [ 21.047719] RDX: 000000000000007b RSI: 0000000000000000 RDI: ffff888004313290 [ 21.048241] RBP: ffff888004313290 R08: 0001ffffffffffff R09: 0000000000000000 [ 21.048701] R10: 0000000000000013 R11: 0001888004313290 R12: 0000000000000003 [ 21.049138] R13: ffff888004313080 R14: ffff888004313080 R15: 0000000000000000 [ 21.049648] FS: 0000000000000000(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000 [ 21.050271] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 21.050688] CR2: 0000592cc27635b0 CR3: 000000000431c000 CR4: 0000000000750ef0 [ 21.051136] PKRU: 55555554 [ 21.051331] Call Trace: [ 21.051480] <TASK> [ 21.051611] ? __warn+0xc4/0x210 [ 21.051861] ? media_create_pad_link+0x2c4/0x2e0 [ 21.052252] ? report_bug+0x11b/0x1a0 [ 21.052540] ? trace_hardirqs_on+0x31/0x40 [ 21.052901] ? handle_bug+0x3d/0x70 [ 21.053197] ? exc_invalid_op+0x1a/0x50 [ 21.053511] ? asm_exc_invalid_op+0x1a/0x20 [ 21.053924] ? media_create_pad_link+0x91/0x2e0 [ 21.054364] ? media_create_pad_link+0x2c4/0x2e0 [ 21.054834] ? media_create_pad_link+0x91/0x2e0 [ 21.055131] ? _raw_spin_unlock+0x1e/0x40 [ 21.055441] ? __v4l2_device_register_subdev+0x202/0x210 [ 21.055837] uvc_mc_register_entities+0x358/0x400 [ 21.056144] uvc_register_chains+0x1 ---truncated---
CVE-2025-40025: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer for non inode dnode As syzbot reported below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/file.c:1243! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI CPU: 0 UID: 0 PID: 5354 Comm: syz.0.0 Not tainted 6.17.0-rc1-syzkaller-00211-g90d970cade8e #0 PREEMPT(full) RIP: 0010:f2fs_truncate_hole+0x69e/0x6c0 fs/f2fs/file.c:1243 Call Trace: <TASK> f2fs_punch_hole+0x2db/0x330 fs/f2fs/file.c:1306 f2fs_fallocate+0x546/0x990 fs/f2fs/file.c:2018 vfs_fallocate+0x666/0x7e0 fs/open.c:342 ksys_fallocate fs/open.c:366 [inline] __do_sys_fallocate fs/open.c:371 [inline] __se_sys_fallocate fs/open.c:369 [inline] __x64_sys_fallocate+0xc0/0x110 fs/open.c:369 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f1e65f8ebe9 w/ a fuzzed image, f2fs may encounter panic due to it detects inconsistent truncation range in direct node in f2fs_truncate_hole(). The root cause is: a non-inode dnode may has the same footer.ino and footer.nid, so the dnode will be parsed as an inode, then ADDRS_PER_PAGE() may return wrong blkaddr count which may be 923 typically, by chance, dn.ofs_in_node is equal to 923, then count can be calculated to 0 in below statement, later it will trigger panic w/ f2fs_bug_on(, count == 0 || ...). count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); This patch introduces a new node_type NODE_TYPE_NON_INODE, then allowing passing the new_type to sanity_check_node_footer in f2fs_get_node_folio() to detect corruption that a non-inode dnode has the same footer.ino and footer.nid. Scripts to reproduce: mkfs.f2fs -f /dev/vdb mount /dev/vdb /mnt/f2fs touch /mnt/f2fs/foo touch /mnt/f2fs/bar dd if=/dev/zero of=/mnt/f2fs/foo bs=1M count=8 umount /mnt/f2fs inject.f2fs --node --mb i_nid --nid 4 --idx 0 --val 5 /dev/vdb mount /dev/vdb /mnt/f2fs xfs_io /mnt/f2fs/foo -c "fpunch 6984k 4k"
CVE-2025-40054: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix UAF issue in f2fs_merge_page_bio() As JY reported in bugzilla [1], Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 pc : [0xffffffe51d249484] f2fs_is_cp_guaranteed+0x70/0x98 lr : [0xffffffe51d24adbc] f2fs_merge_page_bio+0x520/0x6d4 CPU: 3 UID: 0 PID: 6790 Comm: kworker/u16:3 Tainted: P B W OE 6.12.30-android16-5-maybe-dirty-4k #1 5f7701c9cbf727d1eebe77c89bbbeb3371e895e5 Tainted: [P]=PROPRIETARY_MODULE, [B]=BAD_PAGE, [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Workqueue: writeback wb_workfn (flush-254:49) Call trace: f2fs_is_cp_guaranteed+0x70/0x98 f2fs_inplace_write_data+0x174/0x2f4 f2fs_do_write_data_page+0x214/0x81c f2fs_write_single_data_page+0x28c/0x764 f2fs_write_data_pages+0x78c/0xce4 do_writepages+0xe8/0x2fc __writeback_single_inode+0x4c/0x4b4 writeback_sb_inodes+0x314/0x540 __writeback_inodes_wb+0xa4/0xf4 wb_writeback+0x160/0x448 wb_workfn+0x2f0/0x5dc process_scheduled_works+0x1c8/0x458 worker_thread+0x334/0x3f0 kthread+0x118/0x1ac ret_from_fork+0x10/0x20 [1] https://bugzilla.kernel.org/show_bug.cgi?id=220575 The panic was caused by UAF issue w/ below race condition: kworker - writepages - f2fs_write_cache_pages - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #1 into bio & cache bio in io->bio_list - f2fs_write_single_data_page - f2fs_do_write_data_page - f2fs_inplace_write_data - f2fs_merge_page_bio - add_inu_page : cache page #2 into bio which is linked in io->bio_list write - f2fs_write_begin : write page #1 - f2fs_folio_wait_writeback - f2fs_submit_merged_ipu_write - f2fs_submit_write_bio : submit bio which inclues page #1 and #2 software IRQ - f2fs_write_end_io - fscrypt_free_bounce_page : freed bounced page which belongs to page #2 - inc_page_count( , WB_DATA_TYPE(data_folio), false) : data_folio points to fio->encrypted_page the bounced page can be freed before accessing it in f2fs_is_cp_guarantee() It can reproduce w/ below testcase: Run below script in shell #1: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" Run below script in shell #2: for ((i=1;i>0;i++)) do xfs_io -f /mnt/f2fs/enc/file \ -c "pwrite 0 32k" -c "fdatasync" So, in f2fs_merge_page_bio(), let's avoid using fio->encrypted_page after commit page into internal ipu cache.
CVE-2025-40057: In the Linux kernel, the following vulnerability has been resolved: ptp: Add a upper bound on max_vclocks syzbot reported WARNING in max_vclocks_store. This occurs when the argument max is too large for kcalloc to handle. Extend the guard to guard against values that are too large for kcalloc
CVE-2025-40064: In the Linux kernel, the following vulnerability has been resolved: smc: Fix use-after-free in __pnet_find_base_ndev(). syzbot reported use-after-free of net_device in __pnet_find_base_ndev(), which was called during connect(). [0] smc_pnet_find_ism_resource() fetches sk_dst_get(sk)->dev and passes down to pnet_find_base_ndev(), where RTNL is held. Then, UAF happened at __pnet_find_base_ndev() when the dev is first used. This means dev had already been freed before acquiring RTNL in pnet_find_base_ndev(). While dev is going away, dst->dev could be swapped with blackhole_netdev, and the dev's refcnt by dst will be released. We must hold dev's refcnt before calling smc_pnet_find_ism_resource(). Also, smc_pnet_find_roce_resource() has the same problem. Let's use __sk_dst_get() and dst_dev_rcu() in the two functions. [0]: BUG: KASAN: use-after-free in __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 Read of size 1 at addr ffff888036bac33a by task syz.0.3632/18609 CPU: 1 UID: 0 PID: 18609 Comm: syz.0.3632 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/18/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 __pnet_find_base_ndev+0x1b1/0x1c0 net/smc/smc_pnet.c:926 pnet_find_base_ndev net/smc/smc_pnet.c:946 [inline] smc_pnet_find_ism_by_pnetid net/smc/smc_pnet.c:1103 [inline] smc_pnet_find_ism_resource+0xef/0x390 net/smc/smc_pnet.c:1154 smc_find_ism_device net/smc/af_smc.c:1030 [inline] smc_find_proposal_devices net/smc/af_smc.c:1115 [inline] __smc_connect+0x372/0x1890 net/smc/af_smc.c:1545 smc_connect+0x877/0xd90 net/smc/af_smc.c:1715 __sys_connect_file net/socket.c:2086 [inline] __sys_connect+0x313/0x440 net/socket.c:2105 __do_sys_connect net/socket.c:2111 [inline] __se_sys_connect net/socket.c:2108 [inline] __x64_sys_connect+0x7a/0x90 net/socket.c:2108 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f47cbf8eba9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f47ccdb1038 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 00007f47cc1d5fa0 RCX: 00007f47cbf8eba9 RDX: 0000000000000010 RSI: 0000200000000280 RDI: 000000000000000b RBP: 00007f47cc011e19 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f47cc1d6038 R14: 00007f47cc1d5fa0 R15: 00007ffc512f8aa8 </TASK> The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888036bacd00 pfn:0x36bac flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000000 ffffea0001243d08 ffff8880b863fdc0 0000000000000000 raw: ffff888036bacd00 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as freed page last allocated via order 2, migratetype Unmovable, gfp_mask 0x446dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO|__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_COMP), pid 16741, tgid 16741 (syz-executor), ts 343313197788, free_ts 380670750466 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0x240/0x2a0 mm/page_alloc.c:1851 prep_new_page mm/page_alloc.c:1859 [inline] get_page_from_freelist+0x21e4/0x22c0 mm/page_alloc.c:3858 __alloc_frozen_pages_noprof+0x181/0x370 mm/page_alloc.c:5148 alloc_pages_mpol+0x232/0x4a0 mm/mempolicy.c:2416 ___kmalloc_large_node+0x5f/0x1b0 mm/slub.c:4317 __kmalloc_large_node_noprof+0x18/0x90 mm/slub.c:4348 __do_kmalloc_node mm/slub.c:4364 [inline] __kvmalloc_node ---truncated---
CVE-2025-40065: In the Linux kernel, the following vulnerability has been resolved: RISC-V: KVM: Write hgatp register with valid mode bits According to the RISC-V Privileged Architecture Spec, when MODE=Bare is selected,software must write zero to the remaining fields of hgatp. We have detected the valid mode supported by the HW before, So using a valid mode to detect how many vmid bits are supported.
CVE-2025-40071: In the Linux kernel, the following vulnerability has been resolved: tty: n_gsm: Don't block input queue by waiting MSC Currently gsm_queue() processes incoming frames and when opening a DLC channel it calls gsm_dlci_open() which calls gsm_modem_update(). If basic mode is used it calls gsm_modem_upd_via_msc() and it cannot block the input queue by waiting the response to come into the same input queue. Instead allow sending Modem Status Command without waiting for remote end to respond. Define a new function gsm_modem_send_initial_msc() for this purpose. As MSC is only valid for basic encoding, it does not do anything for advanced or when convergence layer type 2 is used.
CVE-2025-40074: In the Linux kernel, the following vulnerability has been resolved: ipv4: start using dst_dev_rcu() Change icmpv4_xrlim_allow(), ip_defrag() to prevent possible UAF. Change ipmr_prepare_xmit(), ipmr_queue_fwd_xmit(), ip_mr_output(), ipv4_neigh_lookup() to use lockdep enabled dst_dev_rcu().
CVE-2025-40075: In the Linux kernel, the following vulnerability has been resolved: tcp_metrics: use dst_dev_net_rcu() Replace three dst_dev() with a lockdep enabled helper.
CVE-2025-40077: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid overflow while left shift operation Should cast type of folio->index from pgoff_t to loff_t to avoid overflow while left shift operation.
CVE-2025-40097: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: Fix missing pointer check in hda_component_manager_init function The __component_match_add function may assign the 'matchptr' pointer the value ERR_PTR(-ENOMEM), which will subsequently be dereferenced. The call stack leading to the error looks like this: hda_component_manager_init |-> component_match_add |-> component_match_add_release |-> __component_match_add ( ... ,**matchptr, ... ) |-> *matchptr = ERR_PTR(-ENOMEM); // assign |-> component_master_add_with_match( ... match) |-> component_match_realloc(match, match->num); // dereference Add IS_ERR() check to prevent the crash. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2025-40102: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Prevent access to vCPU events before init Another day, another syzkaller bug. KVM erroneously allows userspace to pend vCPU events for a vCPU that hasn't been initialized yet, leading to KVM interpreting a bunch of uninitialized garbage for routing / injecting the exception. In one case the injection code and the hyp disagree on whether the vCPU has a 32bit EL1 and put the vCPU into an illegal mode for AArch64, tripping the BUG() in exception_target_el() during the next injection: kernel BUG at arch/arm64/kvm/inject_fault.c:40! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 3 UID: 0 PID: 318 Comm: repro Not tainted 6.17.0-rc4-00104-g10fd0285305d #6 PREEMPT Hardware name: linux,dummy-virt (DT) pstate: 21402009 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) pc : exception_target_el+0x88/0x8c lr : pend_serror_exception+0x18/0x13c sp : ffff800082f03a10 x29: ffff800082f03a10 x28: ffff0000cb132280 x27: 0000000000000000 x26: 0000000000000000 x25: ffff0000c2a99c20 x24: 0000000000000000 x23: 0000000000008000 x22: 0000000000000002 x21: 0000000000000004 x20: 0000000000008000 x19: ffff0000c2a99c20 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000200000c0 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : ffff800082f03af8 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffff800080f621f0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 000000000040009b x1 : 0000000000000003 x0 : ffff0000c2a99c20 Call trace: exception_target_el+0x88/0x8c (P) kvm_inject_serror_esr+0x40/0x3b4 __kvm_arm_vcpu_set_events+0xf0/0x100 kvm_arch_vcpu_ioctl+0x180/0x9d4 kvm_vcpu_ioctl+0x60c/0x9f4 __arm64_sys_ioctl+0xac/0x104 invoke_syscall+0x48/0x110 el0_svc_common.constprop.0+0x40/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x34/0xf0 el0t_64_sync_handler+0xa0/0xe4 el0t_64_sync+0x198/0x19c Code: f946bc01 b4fffe61 9101e020 17fffff2 (d4210000) Reject the ioctls outright as no sane VMM would call these before KVM_ARM_VCPU_INIT anyway. Even if it did the exception would've been thrown away by the eventual reset of the vCPU's state.
CVE-2025-40135: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_xmit() Use RCU in ip6_xmit() in order to use dst_dev_rcu() to prevent possible UAF.
CVE-2025-40136: In the Linux kernel, the following vulnerability has been resolved: crypto: hisilicon/qm - request reserved interrupt for virtual function The device interrupt vector 3 is an error interrupt for physical function and a reserved interrupt for virtual function. However, the driver has not registered the reserved interrupt for virtual function. When allocating interrupts, the number of interrupts is allocated based on powers of two, which includes this interrupt. When the system enables GICv4 and the virtual function passthrough to the virtual machine, releasing the interrupt in the driver triggers a warning. The WARNING report is: WARNING: CPU: 62 PID: 14889 at arch/arm64/kvm/vgic/vgic-its.c:852 its_free_ite+0x94/0xb4 Therefore, register a reserved interrupt for VF and set the IRQF_NO_AUTOEN flag to avoid that warning.
CVE-2025-40137: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to truncate first page in error path of f2fs_truncate() syzbot reports a bug as below: loop0: detected capacity change from 0 to 40427 F2FS-fs (loop0): Wrong SSA boundary, start(3584) end(4096) blocks(3072) F2FS-fs (loop0): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop0): invalid crc value F2FS-fs (loop0): f2fs_convert_inline_folio: corrupted inline inode ino=3, i_addr[0]:0x1601, run fsck to fix. ------------[ cut here ]------------ kernel BUG at fs/inode.c:753! RIP: 0010:clear_inode+0x169/0x190 fs/inode.c:753 Call Trace: <TASK> evict+0x504/0x9c0 fs/inode.c:810 f2fs_fill_super+0x5612/0x6fa0 fs/f2fs/super.c:5047 get_tree_bdev_flags+0x40e/0x4d0 fs/super.c:1692 vfs_get_tree+0x8f/0x2b0 fs/super.c:1815 do_new_mount+0x2a2/0x9e0 fs/namespace.c:3808 do_mount fs/namespace.c:4136 [inline] __do_sys_mount fs/namespace.c:4347 [inline] __se_sys_mount+0x317/0x410 fs/namespace.c:4324 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f During f2fs_evict_inode(), clear_inode() detects that we missed to truncate all page cache before destorying inode, that is because in below path, we will create page #0 in cache, but missed to drop it in error path, let's fix it. - evict - f2fs_evict_inode - f2fs_truncate - f2fs_convert_inline_inode - f2fs_grab_cache_folio : create page #0 in cache - f2fs_convert_inline_folio : sanity check failed, return -EFSCORRUPTED - clear_inode detects that inode->i_data.nrpages is not zero
CVE-2025-40139: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in in smc_clc_prfx_set(). smc_clc_prfx_set() is called during connect() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dev_dst_rcu() under rcu_read_lock() after kernel_getsockname(). Note that the returned value of smc_clc_prfx_set() is not used in the caller. While at it, we change the 1st arg of smc_clc_prfx_set[46]_rcu() not to touch dst there.
CVE-2025-40146: In the Linux kernel, the following vulnerability has been resolved: blk-mq: fix potential deadlock while nr_requests grown Allocate and free sched_tags while queue is freezed can deadlock[1], this is a long term problem, hence allocate memory before freezing queue and free memory after queue is unfreezed. [1] https://lore.kernel.org/all/0659ea8d-a463-47c8-9180-43c719e106eb@linux.ibm.com/
CVE-2025-40158: In the Linux kernel, the following vulnerability has been resolved: ipv6: use RCU in ip6_output() Use RCU in ip6_output() in order to use dst_dev_rcu() to prevent possible UAF. We can remove rcu_read_lock()/rcu_read_unlock() pairs from ip6_finish_output2().
CVE-2025-40160: In the Linux kernel, the following vulnerability has been resolved: xen/events: Return -EEXIST for bound VIRQs Change find_virq() to return -EEXIST when a VIRQ is bound to a different CPU than the one passed in. With that, remove the BUG_ON() from bind_virq_to_irq() to propogate the error upwards. Some VIRQs are per-cpu, but others are per-domain or global. Those must be bound to CPU0 and can then migrate elsewhere. The lookup for per-domain and global will probably fail when migrated off CPU 0, especially when the current CPU is tracked. This now returns -EEXIST instead of BUG_ON(). A second call to bind a per-domain or global VIRQ is not expected, but make it non-fatal to avoid trying to look up the irq, since we don't know which per_cpu(virq_to_irq) it will be in.
CVE-2025-40168: In the Linux kernel, the following vulnerability has been resolved: smc: Use __sk_dst_get() and dst_dev_rcu() in smc_clc_prfx_match(). smc_clc_prfx_match() is called from smc_listen_work() and not under RCU nor RTNL. Using sk_dst_get(sk)->dev could trigger UAF. Let's use __sk_dst_get() and dst_dev_rcu(). Note that the returned value of smc_clc_prfx_match() is not used in the caller.
CVE-2025-40170: In the Linux kernel, the following vulnerability has been resolved: net: use dst_dev_rcu() in sk_setup_caps() Use RCU to protect accesses to dst->dev from sk_setup_caps() and sk_dst_gso_max_size(). Also use dst_dev_rcu() in ip6_dst_mtu_maybe_forward(), and ip_dst_mtu_maybe_forward(). ip4_dst_hoplimit() can use dst_dev_net_rcu().
CVE-2025-40180: In the Linux kernel, the following vulnerability has been resolved: mailbox: zynqmp-ipi: Fix out-of-bounds access in mailbox cleanup loop The cleanup loop was starting at the wrong array index, causing out-of-bounds access. Start the loop at the correct index for zero-indexed arrays to prevent accessing memory beyond the allocated array bounds.
CVE-2025-40196: In the Linux kernel, the following vulnerability has been resolved: fs: quota: create dedicated workqueue for quota_release_work There is a kernel panic due to WARN_ONCE when panic_on_warn is set. This issue occurs when writeback is triggered due to sync call for an opened file(ie, writeback reason is WB_REASON_SYNC). When f2fs balance is needed at sync path, flush for quota_release_work is triggered. By default quota_release_work is queued to "events_unbound" queue which does not have WQ_MEM_RECLAIM flag. During f2fs balance "writeback" workqueue tries to flush quota_release_work causing kernel panic due to MEM_RECLAIM flag mismatch errors. This patch creates dedicated workqueue with WQ_MEM_RECLAIM flag for work quota_release_work. ------------[ cut here ]------------ WARNING: CPU: 4 PID: 14867 at kernel/workqueue.c:3721 check_flush_dependency+0x13c/0x148 Call trace: check_flush_dependency+0x13c/0x148 __flush_work+0xd0/0x398 flush_delayed_work+0x44/0x5c dquot_writeback_dquots+0x54/0x318 f2fs_do_quota_sync+0xb8/0x1a8 f2fs_write_checkpoint+0x3cc/0x99c f2fs_gc+0x190/0x750 f2fs_balance_fs+0x110/0x168 f2fs_write_single_data_page+0x474/0x7dc f2fs_write_data_pages+0x7d0/0xd0c do_writepages+0xe0/0x2f4 __writeback_single_inode+0x44/0x4ac writeback_sb_inodes+0x30c/0x538 wb_writeback+0xf4/0x440 wb_workfn+0x128/0x5d4 process_scheduled_works+0x1c4/0x45c worker_thread+0x32c/0x3e8 kthread+0x11c/0x1b0 ret_from_fork+0x10/0x20 Kernel panic - not syncing: kernel: panic_on_warn set ...
CVE-2025-40206: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_objref: validate objref and objrefmap expressions Referencing a synproxy stateful object from OUTPUT hook causes kernel crash due to infinite recursive calls: BUG: TASK stack guard page was hit at 000000008bda5b8c (stack is 000000003ab1c4a5..00000000494d8b12) [...] Call Trace: __find_rr_leaf+0x99/0x230 fib6_table_lookup+0x13b/0x2d0 ip6_pol_route+0xa4/0x400 fib6_rule_lookup+0x156/0x240 ip6_route_output_flags+0xc6/0x150 __nf_ip6_route+0x23/0x50 synproxy_send_tcp_ipv6+0x106/0x200 synproxy_send_client_synack_ipv6+0x1aa/0x1f0 nft_synproxy_do_eval+0x263/0x310 nft_do_chain+0x5a8/0x5f0 [nf_tables nft_do_chain_inet+0x98/0x110 nf_hook_slow+0x43/0xc0 __ip6_local_out+0xf0/0x170 ip6_local_out+0x17/0x70 synproxy_send_tcp_ipv6+0x1a2/0x200 synproxy_send_client_synack_ipv6+0x1aa/0x1f0 [...] Implement objref and objrefmap expression validate functions. Currently, only NFT_OBJECT_SYNPROXY object type requires validation. This will also handle a jump to a chain using a synproxy object from the OUTPUT hook. Now when trying to reference a synproxy object in the OUTPUT hook, nft will produce the following error: synproxy_crash.nft: Error: Could not process rule: Operation not supported synproxy name mysynproxy ^^^^^^^^^^^^^^^^^^^^^^^^
CVE-2025-40219: In the Linux kernel, the following vulnerability has been resolved: PCI/IOV: Fix race between SR-IOV enable/disable and hotplug Commit 05703271c3cd ("PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV") tried to fix a race between the VF removal inside sriov_del_vfs() and concurrent hot unplug by taking the PCI rescan/remove lock in sriov_del_vfs(). Similarly the PCI rescan/remove lock was also taken in sriov_add_vfs() to protect addition of VFs. This approach however causes deadlock on trying to remove PFs with SR-IOV enabled because PFs disable SR-IOV during removal and this removal happens under the PCI rescan/remove lock. So the original fix had to be reverted. Instead of taking the PCI rescan/remove lock in sriov_add_vfs() and sriov_del_vfs(), fix the race that occurs with SR-IOV enable and disable vs hotplug higher up in the callchain by taking the lock in sriov_numvfs_store() before calling into the driver's sriov_configure() callback.
CVE-2025-40242: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix unlikely race in gdlm_put_lock In gdlm_put_lock(), there is a small window of time in which the DFL_UNMOUNT flag has been set but the lockspace hasn't been released, yet. In that window, dlm may still call gdlm_ast() and gdlm_bast(). To prevent it from dereferencing freed glock objects, only free the glock if the lockspace has actually been released.
CVE-2025-40247: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix pgtable prealloc error path The following splat was reported: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000010 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00000008d0fd8000 [0000000000000010] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] SMP CPU: 5 UID: 1000 PID: 149076 Comm: Xwayland Tainted: G S 6.16.0-rc2-00809-g0b6974bb4134-dirty #367 PREEMPT Tainted: [S]=CPU_OUT_OF_SPEC Hardware name: Qualcomm Technologies, Inc. SM8650 HDK (DT) pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : build_detached_freelist+0x28/0x224 lr : kmem_cache_free_bulk.part.0+0x38/0x244 sp : ffff000a508c7a20 x29: ffff000a508c7a20 x28: ffff000a508c7d50 x27: ffffc4e49d16f350 x26: 0000000000000058 x25: 00000000fffffffc x24: 0000000000000000 x23: ffff00098c4e1450 x22: 00000000fffffffc x21: 0000000000000000 x20: ffff000a508c7af8 x19: 0000000000000002 x18: 00000000000003e8 x17: ffff000809523850 x16: ffff000809523820 x15: 0000000000401640 x14: ffff000809371140 x13: 0000000000000130 x12: ffff0008b5711e30 x11: 00000000001058fa x10: 0000000000000a80 x9 : ffff000a508c7940 x8 : ffff000809371ba0 x7 : 781fffe033087fff x6 : 0000000000000000 x5 : ffff0008003cd000 x4 : 781fffe033083fff x3 : ffff000a508c7af8 x2 : fffffdffc0000000 x1 : 0001000000000000 x0 : ffff0008001a6a00 Call trace: build_detached_freelist+0x28/0x224 (P) kmem_cache_free_bulk.part.0+0x38/0x244 kmem_cache_free_bulk+0x10/0x1c msm_iommu_pagetable_prealloc_cleanup+0x3c/0xd0 msm_vma_job_free+0x30/0x240 msm_ioctl_vm_bind+0x1d0/0x9a0 drm_ioctl_kernel+0x84/0x104 drm_ioctl+0x358/0x4d4 __arm64_sys_ioctl+0x8c/0xe0 invoke_syscall+0x44/0x100 el0_svc_common.constprop.0+0x3c/0xe0 do_el0_svc+0x18/0x20 el0_svc+0x30/0x100 el0t_64_sync_handler+0x104/0x130 el0t_64_sync+0x170/0x174 Code: aa0203f5 b26287e2 f2dfbfe2 aa0303f4 (f8737ab6) ---[ end trace 0000000000000000 ]--- Since msm_vma_job_free() is called directly from the ioctl, this looks like an error path cleanup issue. Which I think results from prealloc_cleanup() called without a preceding successful prealloc_allocate() call. So handle that case better. Patchwork: https://patchwork.freedesktop.org/patch/678677/
CVE-2025-40261: In the Linux kernel, the following vulnerability has been resolved: nvme: nvme-fc: Ensure ->ioerr_work is cancelled in nvme_fc_delete_ctrl() nvme_fc_delete_assocation() waits for pending I/O to complete before returning, and an error can cause ->ioerr_work to be queued after cancel_work_sync() had been called. Move the call to cancel_work_sync() to be after nvme_fc_delete_association() to ensure ->ioerr_work is not running when the nvme_fc_ctrl object is freed. Otherwise the following can occur: [ 1135.911754] list_del corruption, ff2d24c8093f31f8->next is NULL [ 1135.917705] ------------[ cut here ]------------ [ 1135.922336] kernel BUG at lib/list_debug.c:52! [ 1135.926784] Oops: invalid opcode: 0000 [#1] SMP NOPTI [ 1135.931851] CPU: 48 UID: 0 PID: 726 Comm: kworker/u449:23 Kdump: loaded Not tainted 6.12.0 #1 PREEMPT(voluntary) [ 1135.943490] Hardware name: Dell Inc. PowerEdge R660/0HGTK9, BIOS 2.5.4 01/16/2025 [ 1135.950969] Workqueue: 0x0 (nvme-wq) [ 1135.954673] RIP: 0010:__list_del_entry_valid_or_report.cold+0xf/0x6f [ 1135.961041] Code: c7 c7 98 68 72 94 e8 26 45 fe ff 0f 0b 48 c7 c7 70 68 72 94 e8 18 45 fe ff 0f 0b 48 89 fe 48 c7 c7 80 69 72 94 e8 07 45 fe ff <0f> 0b 48 89 d1 48 c7 c7 a0 6a 72 94 48 89 c2 e8 f3 44 fe ff 0f 0b [ 1135.979788] RSP: 0018:ff579b19482d3e50 EFLAGS: 00010046 [ 1135.985015] RAX: 0000000000000033 RBX: ff2d24c8093f31f0 RCX: 0000000000000000 [ 1135.992148] RDX: 0000000000000000 RSI: ff2d24d6bfa1d0c0 RDI: ff2d24d6bfa1d0c0 [ 1135.999278] RBP: ff2d24c8093f31f8 R08: 0000000000000000 R09: ffffffff951e2b08 [ 1136.006413] R10: ffffffff95122ac8 R11: 0000000000000003 R12: ff2d24c78697c100 [ 1136.013546] R13: fffffffffffffff8 R14: 0000000000000000 R15: ff2d24c78697c0c0 [ 1136.020677] FS: 0000000000000000(0000) GS:ff2d24d6bfa00000(0000) knlGS:0000000000000000 [ 1136.028765] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1136.034510] CR2: 00007fd207f90b80 CR3: 000000163ea22003 CR4: 0000000000f73ef0 [ 1136.041641] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1136.048776] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 1136.055910] PKRU: 55555554 [ 1136.058623] Call Trace: [ 1136.061074] <TASK> [ 1136.063179] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.067540] ? show_trace_log_lvl+0x1b0/0x2f0 [ 1136.071898] ? move_linked_works+0x4a/0xa0 [ 1136.075998] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.081744] ? __die_body.cold+0x8/0x12 [ 1136.085584] ? die+0x2e/0x50 [ 1136.088469] ? do_trap+0xca/0x110 [ 1136.091789] ? do_error_trap+0x65/0x80 [ 1136.095543] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.101289] ? exc_invalid_op+0x50/0x70 [ 1136.105127] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.110874] ? asm_exc_invalid_op+0x1a/0x20 [ 1136.115059] ? __list_del_entry_valid_or_report.cold+0xf/0x6f [ 1136.120806] move_linked_works+0x4a/0xa0 [ 1136.124733] worker_thread+0x216/0x3a0 [ 1136.128485] ? __pfx_worker_thread+0x10/0x10 [ 1136.132758] kthread+0xfa/0x240 [ 1136.135904] ? __pfx_kthread+0x10/0x10 [ 1136.139657] ret_from_fork+0x31/0x50 [ 1136.143236] ? __pfx_kthread+0x10/0x10 [ 1136.146988] ret_from_fork_asm+0x1a/0x30 [ 1136.150915] </TASK>
CVE-2025-40266: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Check the untrusted offset in FF-A memory share Verify the offset to prevent OOB access in the hypervisor FF-A buffer in case an untrusted large enough value [U32_MAX - sizeof(struct ffa_composite_mem_region) + 1, U32_MAX] is set from the host kernel.
CVE-2025-40268: In the Linux kernel, the following vulnerability has been resolved: cifs: client: fix memory leak in smb3_fs_context_parse_param The user calls fsconfig twice, but when the program exits, free() only frees ctx->source for the second fsconfig, not the first. Regarding fc->source, there is no code in the fs context related to its memory reclamation. To fix this memory leak, release the source memory corresponding to ctx or fc before each parsing. syzbot reported: BUG: memory leak unreferenced object 0xffff888128afa360 (size 96): backtrace (crc 79c9c7ba): kstrdup+0x3c/0x80 mm/util.c:84 smb3_fs_context_parse_param+0x229b/0x36c0 fs/smb/client/fs_context.c:1444 BUG: memory leak unreferenced object 0xffff888112c7d900 (size 96): backtrace (crc 79c9c7ba): smb3_fs_context_fullpath+0x70/0x1b0 fs/smb/client/fs_context.c:629 smb3_fs_context_parse_param+0x2266/0x36c0 fs/smb/client/fs_context.c:1438
CVE-2025-40289: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: hide VRAM sysfs attributes on GPUs without VRAM Otherwise accessing them can cause a crash.
CVE-2025-40303: In the Linux kernel, the following vulnerability has been resolved: btrfs: ensure no dirty metadata is written back for an fs with errors [BUG] During development of a minor feature (make sure all btrfs_bio::end_io() is called in task context), I noticed a crash in generic/388, where metadata writes triggered new works after btrfs_stop_all_workers(). It turns out that it can even happen without any code modification, just using RAID5 for metadata and the same workload from generic/388 is going to trigger the use-after-free. [CAUSE] If btrfs hits an error, the fs is marked as error, no new transaction is allowed thus metadata is in a frozen state. But there are some metadata modifications before that error, and they are still in the btree inode page cache. Since there will be no real transaction commit, all those dirty folios are just kept as is in the page cache, and they can not be invalidated by invalidate_inode_pages2() call inside close_ctree(), because they are dirty. And finally after btrfs_stop_all_workers(), we call iput() on btree inode, which triggers writeback of those dirty metadata. And if the fs is using RAID56 metadata, this will trigger RMW and queue new works into rmw_workers, which is already stopped, causing warning from queue_work() and use-after-free. [FIX] Add a special handling for write_one_eb(), that if the fs is already in an error state, immediately mark the bbio as failure, instead of really submitting them. Then during close_ctree(), iput() will just discard all those dirty tree blocks without really writing them back, thus no more new jobs for already stopped-and-freed workqueues. The extra discard in write_one_eb() also acts as an extra safenet. E.g. the transaction abort is triggered by some extent/free space tree corruptions, and since extent/free space tree is already corrupted some tree blocks may be allocated where they shouldn't be (overwriting existing tree blocks). In that case writing them back will further corrupting the fs.
CVE-2025-40307: In the Linux kernel, the following vulnerability has been resolved: exfat: validate cluster allocation bits of the allocation bitmap syzbot created an exfat image with cluster bits not set for the allocation bitmap. exfat-fs reads and uses the allocation bitmap without checking this. The problem is that if the start cluster of the allocation bitmap is 6, cluster 6 can be allocated when creating a directory with mkdir. exfat zeros out this cluster in exfat_mkdir, which can delete existing entries. This can reallocate the allocated entries. In addition, the allocation bitmap is also zeroed out, so cluster 6 can be reallocated. This patch adds exfat_test_bitmap_range to validate that clusters used for the allocation bitmap are correctly marked as in-use.
CVE-2025-40311: In the Linux kernel, the following vulnerability has been resolved: accel/habanalabs: support mapping cb with vmalloc-backed coherent memory When IOMMU is enabled, dma_alloc_coherent() with GFP_USER may return addresses from the vmalloc range. If such an address is mapped without VM_MIXEDMAP, vm_insert_page() will trigger a BUG_ON due to the VM_PFNMAP restriction. Fix this by checking for vmalloc addresses and setting VM_MIXEDMAP in the VMA before mapping. This ensures safe mapping and avoids kernel crashes. The memory is still driver-allocated and cannot be accessed directly by userspace.
CVE-2025-40325: In the Linux kernel, the following vulnerability has been resolved: md/raid10: wait barrier before returning discard request with REQ_NOWAIT raid10_handle_discard should wait barrier before returning a discard bio which has REQ_NOWAIT. And there is no need to print warning calltrace if a discard bio has REQ_NOWAIT flag. Quality engineer usually checks dmesg and reports error if dmesg has warning/error calltrace.
CVE-2025-40328: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_close_cached_fid() find_or_create_cached_dir() could grab a new reference after kref_put() had seen the refcount drop to zero but before cfid_list_lock is acquired in smb2_close_cached_fid(), leading to use-after-free. Switch to kref_put_lock() so cfid_release() is called with cfid_list_lock held, closing that gap.
CVE-2025-40333: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix infinite loop in __insert_extent_tree() When we get wrong extent info data, and look up extent_node in rb tree, it will cause infinite loop (CONFIG_F2FS_CHECK_FS=n). Avoiding this by return NULL and print some kernel messages in that case.
CVE-2025-40337: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: Correctly handle Rx checksum offload errors The stmmac_rx function would previously set skb->ip_summed to CHECKSUM_UNNECESSARY if hardware checksum offload (CoE) was enabled and the packet was of a known IP ethertype. However, this logic failed to check if the hardware had actually reported a checksum error. The hardware status, indicating a header or payload checksum failure, was being ignored at this stage. This could cause corrupt packets to be passed up the network stack as valid. This patch corrects the logic by checking the `csum_none` status flag, which is set when the hardware reports a checksum error. If this flag is set, skb->ip_summed is now correctly set to CHECKSUM_NONE, ensuring the kernel's network stack will perform its own validation and properly handle the corrupt packet.
CVE-2025-40338: In the Linux kernel, the following vulnerability has been resolved: ASoC: Intel: avs: Do not share the name pointer between components By sharing 'name' directly, tearing down components may lead to use-after-free errors. Duplicate the name to avoid that. At the same time, update the order of operations - since commit cee28113db17 ("ASoC: dmaengine_pcm: Allow passing component name via config") the framework does not override component->name if set before invoking the initializer.
CVE-2025-40339: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix nullptr err of vm_handle_moved If a amdgpu_bo_va is fpriv->prt_va, the bo of this one is always NULL. So, such kind of amdgpu_bo_va should be updated separately before amdgpu_vm_handle_moved.
CVE-2025-40347: In the Linux kernel, the following vulnerability has been resolved: net: enetc: fix the deadlock of enetc_mdio_lock After applying the workaround for err050089, the LS1028A platform experiences RCU stalls on RT kernel. This issue is caused by the recursive acquisition of the read lock enetc_mdio_lock. Here list some of the call stacks identified under the enetc_poll path that may lead to a deadlock: enetc_poll -> enetc_lock_mdio -> enetc_clean_rx_ring OR napi_complete_done -> napi_gro_receive -> enetc_start_xmit -> enetc_lock_mdio -> enetc_map_tx_buffs -> enetc_unlock_mdio -> enetc_unlock_mdio After enetc_poll acquires the read lock, a higher-priority writer attempts to acquire the lock, causing preemption. The writer detects that a read lock is already held and is scheduled out. However, readers under enetc_poll cannot acquire the read lock again because a writer is already waiting, leading to a thread hang. Currently, the deadlock is avoided by adjusting enetc_lock_mdio to prevent recursive lock acquisition.
CVE-2025-40354: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: increase max link count and fix link->enc NULL pointer access [why] 1.) dc->links[MAX_LINKS] array size smaller than actual requested. max_connector + max_dpia + 4 virtual = 14. increase from 12 to 14. 2.) hw_init() access null LINK_ENC for dpia non display_endpoint. (cherry picked from commit d7f5a61e1b04ed87b008c8d327649d184dc5bb45)
CVE-2025-40355: In the Linux kernel, the following vulnerability has been resolved: sysfs: check visibility before changing group attribute ownership Since commit 0c17270f9b92 ("net: sysfs: Implement is_visible for phys_(port_id, port_name, switch_id)"), __dev_change_net_namespace() can hit WARN_ON() when trying to change owner of a file that isn't visible. See the trace below: WARNING: CPU: 6 PID: 2938 at net/core/dev.c:12410 __dev_change_net_namespace+0xb89/0xc30 CPU: 6 UID: 0 PID: 2938 Comm: incusd Not tainted 6.17.1-1-mainline #1 PREEMPT(full) 4b783b4a638669fb644857f484487d17cb45ed1f Hardware name: Framework Laptop 13 (AMD Ryzen 7040Series)/FRANMDCP07, BIOS 03.07 02/19/2025 RIP: 0010:__dev_change_net_namespace+0xb89/0xc30 [...] Call Trace: <TASK> ? if6_seq_show+0x30/0x50 do_setlink.isra.0+0xc7/0x1270 ? __nla_validate_parse+0x5c/0xcc0 ? security_capable+0x94/0x1a0 rtnl_newlink+0x858/0xc20 ? update_curr+0x8e/0x1c0 ? update_entity_lag+0x71/0x80 ? sched_balance_newidle+0x358/0x450 ? psi_task_switch+0x113/0x2a0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x346/0x3e0 ? sched_clock+0x10/0x30 ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x59/0x110 netlink_unicast+0x285/0x3c0 ? __alloc_skb+0xdb/0x1a0 netlink_sendmsg+0x20d/0x430 ____sys_sendmsg+0x39f/0x3d0 ? import_iovec+0x2f/0x40 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x81/0x970 ? __sys_bind+0xe3/0x110 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? sock_alloc_file+0x63/0xc0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? alloc_fd+0x12e/0x190 ? put_unused_fd+0x2a/0x70 ? do_sys_openat2+0xa2/0xe0 ? syscall_exit_work+0x143/0x1b0 ? do_syscall_64+0x244/0x970 ? exc_page_fault+0x7e/0x1a0 entry_SYSCALL_64_after_hwframe+0x76/0x7e [...] </TASK> Fix this by checking is_visible() before trying to touch the attribute.
CVE-2025-40358: In the Linux kernel, the following vulnerability has been resolved: riscv: stacktrace: Disable KASAN checks for non-current tasks Unwinding the stack of a task other than current, KASAN would report "BUG: KASAN: out-of-bounds in walk_stackframe+0x41c/0x460" There is a same issue on x86 and has been resolved by the commit 84936118bdf3 ("x86/unwind: Disable KASAN checks for non-current tasks") The solution could be applied to RISC-V too. This patch also can solve the issue: https://seclists.org/oss-sec/2025/q4/23 [pjw@kernel.org: clean up checkpatch issues]
CVE-2025-54505:
CVE-2025-68183: In the Linux kernel, the following vulnerability has been resolved: ima: don't clear IMA_DIGSIG flag when setting or removing non-IMA xattr Currently when both IMA and EVM are in fix mode, the IMA signature will be reset to IMA hash if a program first stores IMA signature in security.ima and then writes/removes some other security xattr for the file. For example, on Fedora, after booting the kernel with "ima_appraise=fix evm=fix ima_policy=appraise_tcb" and installing rpm-plugin-ima, installing/reinstalling a package will not make good reference IMA signature generated. Instead IMA hash is generated, # getfattr -m - -d -e hex /usr/bin/bash # file: usr/bin/bash security.ima=0x0404... This happens because when setting security.selinux, the IMA_DIGSIG flag that had been set early was cleared. As a result, IMA hash is generated when the file is closed. Similarly, IMA signature can be cleared on file close after removing security xattr like security.evm or setting/removing ACL. Prevent replacing the IMA file signature with a file hash, by preventing the IMA_DIGSIG flag from being reset. Here's a minimal C reproducer which sets security.selinux as the last step which can also replaced by removing security.evm or setting ACL, #include <stdio.h> #include <sys/xattr.h> #include <fcntl.h> #include <unistd.h> #include <string.h> #include <stdlib.h> int main() { const char* file_path = "/usr/sbin/test_binary"; const char* hex_string = "030204d33204490066306402304"; int length = strlen(hex_string); char* ima_attr_value; int fd; fd = open(file_path, O_WRONLY|O_CREAT|O_EXCL, 0644); if (fd == -1) { perror("Error opening file"); return 1; } ima_attr_value = (char*)malloc(length / 2 ); for (int i = 0, j = 0; i < length; i += 2, j++) { sscanf(hex_string + i, "%2hhx", &ima_attr_value[j]); } if (fsetxattr(fd, "security.ima", ima_attr_value, length/2, 0) == -1) { perror("Error setting extended attribute"); close(fd); return 1; } const char* selinux_value= "system_u:object_r:bin_t:s0"; if (fsetxattr(fd, "security.selinux", selinux_value, strlen(selinux_value), 0) == -1) { perror("Error setting extended attribute"); close(fd); return 1; } close(fd); return 0; }
CVE-2025-68188: In the Linux kernel, the following vulnerability has been resolved: tcp: use dst_dev_rcu() in tcp_fastopen_active_disable_ofo_check() Use RCU to avoid a pair of atomic operations and a potential UAF on dst_dev()->flags.
CVE-2025-68190: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/atom: Check kcalloc() for WS buffer in amdgpu_atom_execute_table_locked() kcalloc() may fail. When WS is non-zero and allocation fails, ectx.ws remains NULL while ectx.ws_size is set, leading to a potential NULL pointer dereference in atom_get_src_int() when accessing WS entries. Return -ENOMEM on allocation failure to avoid the NULL dereference.
CVE-2025-68201: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: remove two invalid BUG_ON()s Those can be triggered trivially by userspace.
CVE-2025-68206: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: add seqadj extension for natted connections Sequence adjustment may be required for FTP traffic with PASV/EPSV modes. due to need to re-write packet payload (IP, port) on the ftp control connection. This can require changes to the TCP length and expected seq / ack_seq. The easiest way to reproduce this issue is with PASV mode. Example ruleset: table inet ftp_nat { ct helper ftp_helper { type "ftp" protocol tcp l3proto inet } chain prerouting { type filter hook prerouting priority 0; policy accept; tcp dport 21 ct state new ct helper set "ftp_helper" } } table ip nat { chain prerouting { type nat hook prerouting priority -100; policy accept; tcp dport 21 dnat ip prefix to ip daddr map { 192.168.100.1 : 192.168.13.2/32 } } chain postrouting { type nat hook postrouting priority 100 ; policy accept; tcp sport 21 snat ip prefix to ip saddr map { 192.168.13.2 : 192.168.100.1/32 } } } Note that the ftp helper gets assigned *after* the dnat setup. The inverse (nat after helper assign) is handled by an existing check in nf_nat_setup_info() and will not show the problem. Topoloy: +-------------------+ +----------------------------------+ | FTP: 192.168.13.2 | <-> | NAT: 192.168.13.3, 192.168.100.1 | +-------------------+ +----------------------------------+ | +-----------------------+ | Client: 192.168.100.2 | +-----------------------+ ftp nat changes do not work as expected in this case: Connected to 192.168.100.1. [..] ftp> epsv EPSV/EPRT on IPv4 off. ftp> ls 227 Entering passive mode (192,168,100,1,209,129). 421 Service not available, remote server has closed connection. Kernel logs: Missing nfct_seqadj_ext_add() setup call WARNING: CPU: 1 PID: 0 at net/netfilter/nf_conntrack_seqadj.c:41 [..] __nf_nat_mangle_tcp_packet+0x100/0x160 [nf_nat] nf_nat_ftp+0x142/0x280 [nf_nat_ftp] help+0x4d1/0x880 [nf_conntrack_ftp] nf_confirm+0x122/0x2e0 [nf_conntrack] nf_hook_slow+0x3c/0xb0 .. Fix this by adding the required extension when a conntrack helper is assigned to a connection that has a nat binding.
CVE-2025-68209: In the Linux kernel, the following vulnerability has been resolved: mlx5: Fix default values in create CQ Currently, CQs without a completion function are assigned the mlx5_add_cq_to_tasklet function by default. This is problematic since only user CQs created through the mlx5_ib driver are intended to use this function. Additionally, all CQs that will use doorbells instead of polling for completions must call mlx5_cq_arm. However, the default CQ creation flow leaves a valid value in the CQ's arm_db field, allowing FW to send interrupts to polling-only CQs in certain corner cases. These two factors would allow a polling-only kernel CQ to be triggered by an EQ interrupt and call a completion function intended only for user CQs, causing a null pointer exception. Some areas in the driver have prevented this issue with one-off fixes but did not address the root cause. This patch fixes the described issue by adding defaults to the create CQ flow. It adds a default dummy completion function to protect against null pointer exceptions, and it sets an invalid command sequence number by default in kernel CQs to prevent the FW from sending an interrupt to the CQ until it is armed. User CQs are responsible for their own initialization values. Callers of mlx5_core_create_cq are responsible for changing the completion function and arming the CQ per their needs.
CVE-2025-68219: In the Linux kernel, the following vulnerability has been resolved: cifs: fix memory leak in smb3_fs_context_parse_param error path Add proper cleanup of ctx->source and fc->source to the cifs_parse_mount_err error handler. This ensures that memory allocated for the source strings is correctly freed on all error paths, matching the cleanup already performed in the success path by smb3_cleanup_fs_context_contents(). Pointers are also set to NULL after freeing to prevent potential double-free issues. This change fixes a memory leak originally detected by syzbot. The leak occurred when processing Opt_source mount options if an error happened after ctx->source and fc->source were successfully allocated but before the function completed. The specific leak sequence was: 1. ctx->source = smb3_fs_context_fullpath(ctx, '/') allocates memory 2. fc->source = kstrdup(ctx->source, GFP_KERNEL) allocates more memory 3. A subsequent error jumps to cifs_parse_mount_err 4. The old error handler freed passwords but not the source strings, causing the memory to leak. This issue was not addressed by commit e8c73eb7db0a ("cifs: client: fix memory leak in smb3_fs_context_parse_param"), which only fixed leaks from repeated fsconfig() calls but not this error path. Patch updated with minor change suggested by kernel test robot
CVE-2025-68236: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: ufs-qcom: Fix UFS OCP issue during UFS power down (PC=3) According to UFS specifications, the power-off sequence for a UFS device includes: - Sending an SSU command with Power_Condition=3 and await a response. - Asserting RST_N low. - Turning off REF_CLK. - Turning off VCC. - Turning off VCCQ/VCCQ2. As part of ufs shutdown, after the SSU command completion, asserting hardware reset (HWRST) triggers the device firmware to wake up and execute its reset routine. This routine initializes hardware blocks and takes a few milliseconds to complete. During this time, the ICCQ draws a large current. This large ICCQ current may cause issues for the regulator which is supplying power to UFS, because the turn off request from UFS driver to the regulator framework will be immediately followed by low power mode(LPM) request by regulator framework. This is done by framework because UFS which is the only client is requesting for disable. So if the rail is still in the process of shutting down while ICCQ exceeds LPM current thresholds, and LPM mode is activated in hardware during this state, it may trigger an overcurrent protection (OCP) fault in the regulator. To prevent this, a 10ms delay is added after asserting HWRST. This allows the reset operation to complete while power rails remain active and in high-power mode. Currently there is no way for Host to query whether the reset is completed or not and hence this the delay is based on experiments with Qualcomm UFS controllers across multiple UFS vendors.
CVE-2025-68239: In the Linux kernel, the following vulnerability has been resolved: binfmt_misc: restore write access before closing files opened by open_exec() bm_register_write() opens an executable file using open_exec(), which internally calls do_open_execat() and denies write access on the file to avoid modification while it is being executed. However, when an error occurs, bm_register_write() closes the file using filp_close() directly. This does not restore the write permission, which may cause subsequent write operations on the same file to fail. Fix this by calling exe_file_allow_write_access() before filp_close() to restore the write permission properly.
CVE-2025-68265: In the Linux kernel, the following vulnerability has been resolved: nvme: fix admin request_queue lifetime The namespaces can access the controller's admin request_queue, and stale references on the namespaces may exist after tearing down the controller. Ensure the admin request_queue is active by moving the controller's 'put' to after all controller references have been released to ensure no one is can access the request_queue. This fixes a reported use-after-free bug: BUG: KASAN: slab-use-after-free in blk_queue_enter+0x41c/0x4a0 Read of size 8 at addr ffff88c0a53819f8 by task nvme/3287 CPU: 67 UID: 0 PID: 3287 Comm: nvme Tainted: G E 6.13.2-ga1582f1a031e #15 Tainted: [E]=UNSIGNED_MODULE Hardware name: Jabil /EGS 2S MB1, BIOS 1.00 06/18/2025 Call Trace: <TASK> dump_stack_lvl+0x4f/0x60 print_report+0xc4/0x620 ? _raw_spin_lock_irqsave+0x70/0xb0 ? _raw_read_unlock_irqrestore+0x30/0x30 ? blk_queue_enter+0x41c/0x4a0 kasan_report+0xab/0xe0 ? blk_queue_enter+0x41c/0x4a0 blk_queue_enter+0x41c/0x4a0 ? __irq_work_queue_local+0x75/0x1d0 ? blk_queue_start_drain+0x70/0x70 ? irq_work_queue+0x18/0x20 ? vprintk_emit.part.0+0x1cc/0x350 ? wake_up_klogd_work_func+0x60/0x60 blk_mq_alloc_request+0x2b7/0x6b0 ? __blk_mq_alloc_requests+0x1060/0x1060 ? __switch_to+0x5b7/0x1060 nvme_submit_user_cmd+0xa9/0x330 nvme_user_cmd.isra.0+0x240/0x3f0 ? force_sigsegv+0xe0/0xe0 ? nvme_user_cmd64+0x400/0x400 ? vfs_fileattr_set+0x9b0/0x9b0 ? cgroup_update_frozen_flag+0x24/0x1c0 ? cgroup_leave_frozen+0x204/0x330 ? nvme_ioctl+0x7c/0x2c0 blkdev_ioctl+0x1a8/0x4d0 ? blkdev_common_ioctl+0x1930/0x1930 ? fdget+0x54/0x380 __x64_sys_ioctl+0x129/0x190 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7f765f703b0b Code: ff ff ff 85 c0 79 9b 49 c7 c4 ff ff ff ff 5b 5d 4c 89 e0 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d dd 52 0f 00 f7 d8 64 89 01 48 RSP: 002b:00007ffe2cefe808 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffe2cefe860 RCX: 00007f765f703b0b RDX: 00007ffe2cefe860 RSI: 00000000c0484e41 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000003 R09: 0000000000000000 R10: 00007f765f611d50 R11: 0000000000000202 R12: 0000000000000003 R13: 00000000c0484e41 R14: 0000000000000001 R15: 00007ffe2cefea60 </TASK>
CVE-2025-68296: In the Linux kernel, the following vulnerability has been resolved: drm, fbcon, vga_switcheroo: Avoid race condition in fbcon setup Protect vga_switcheroo_client_fb_set() with console lock. Avoids OOB access in fbcon_remap_all(). Without holding the console lock the call races with switching outputs. VGA switcheroo calls fbcon_remap_all() when switching clients. The fbcon function uses struct fb_info.node, which is set by register_framebuffer(). As the fb-helper code currently sets up VGA switcheroo before registering the framebuffer, the value of node is -1 and therefore not a legal value. For example, fbcon uses the value within set_con2fb_map() [1] as an index into an array. Moving vga_switcheroo_client_fb_set() after register_framebuffer() can result in VGA switching that does not switch fbcon correctly. Therefore move vga_switcheroo_client_fb_set() under fbcon_fb_registered(), which already holds the console lock. Fbdev calls fbcon_fb_registered() from within register_framebuffer(). Serializes the helper with VGA switcheroo's call to fbcon_remap_all(). Although vga_switcheroo_client_fb_set() takes an instance of struct fb_info as parameter, it really only needs the contained fbcon state. Moving the call to fbcon initialization is therefore cleaner than before. Only amdgpu, i915, nouveau and radeon support vga_switcheroo. For all other drivers, this change does nothing.
CVE-2025-68304: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: hci_core: lookup hci_conn on RX path on protocol side The hdev lock/lookup/unlock/use pattern in the packet RX path doesn't ensure hci_conn* is not concurrently modified/deleted. This locking appears to be leftover from before conn_hash started using RCU commit bf4c63252490b ("Bluetooth: convert conn hash to RCU") and not clear if it had purpose since then. Currently, there are code paths that delete hci_conn* from elsewhere than the ordered hdev->workqueue where the RX work runs in. E.g. commit 5af1f84ed13a ("Bluetooth: hci_sync: Fix UAF on hci_abort_conn_sync") introduced some of these, and there probably were a few others before it. It's better to do the locking so that even if these run concurrently no UAF is possible. Move the lookup of hci_conn and associated socket-specific conn to protocol recv handlers, and do them within a single critical section to cover hci_conn* usage and lookup. syzkaller has reported a crash that appears to be this issue: [Task hdev->workqueue] [Task 2] hci_disconnect_all_sync l2cap_recv_acldata(hcon) hci_conn_get(hcon) hci_abort_conn_sync(hcon) hci_dev_lock hci_dev_lock hci_conn_del(hcon) v-------------------------------- hci_dev_unlock hci_conn_put(hcon) conn = hcon->l2cap_data (UAF)
CVE-2025-68315: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to detect potential corrupted nid in free_nid_list As reported, on-disk footer.ino and footer.nid is the same and out-of-range, let's add sanity check on f2fs_alloc_nid() to detect any potential corruption in free_nid_list.
CVE-2025-68320: In the Linux kernel, the following vulnerability has been resolved: lan966x: Fix sleeping in atomic context The following warning was seen when we try to connect using ssh to the device. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:575 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 104, name: dropbear preempt_count: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 UID: 0 PID: 104 Comm: dropbear Tainted: G W 6.18.0-rc2-00399-g6f1ab1b109b9-dirty #530 NONE Tainted: [W]=WARN Hardware name: Generic DT based system Call trace: unwind_backtrace from show_stack+0x10/0x14 show_stack from dump_stack_lvl+0x7c/0xac dump_stack_lvl from __might_resched+0x16c/0x2b0 __might_resched from __mutex_lock+0x64/0xd34 __mutex_lock from mutex_lock_nested+0x1c/0x24 mutex_lock_nested from lan966x_stats_get+0x5c/0x558 lan966x_stats_get from dev_get_stats+0x40/0x43c dev_get_stats from dev_seq_printf_stats+0x3c/0x184 dev_seq_printf_stats from dev_seq_show+0x10/0x30 dev_seq_show from seq_read_iter+0x350/0x4ec seq_read_iter from seq_read+0xfc/0x194 seq_read from proc_reg_read+0xac/0x100 proc_reg_read from vfs_read+0xb0/0x2b0 vfs_read from ksys_read+0x6c/0xec ksys_read from ret_fast_syscall+0x0/0x1c Exception stack(0xf0b11fa8 to 0xf0b11ff0) 1fa0: 00000001 00001000 00000008 be9048d8 00001000 00000001 1fc0: 00000001 00001000 00000008 00000003 be905920 0000001e 00000000 00000001 1fe0: 0005404c be9048c0 00018684 b6ec2cd8 It seems that we are using a mutex in a atomic context which is wrong. Change the mutex with a spinlock.
CVE-2025-68322: In the Linux kernel, the following vulnerability has been resolved: parisc: Avoid crash due to unaligned access in unwinder Guenter Roeck reported this kernel crash on his emulated B160L machine: Starting network: udhcpc: started, v1.36.1 Backtrace: [<104320d4>] unwind_once+0x1c/0x5c [<10434a00>] walk_stackframe.isra.0+0x74/0xb8 [<10434a6c>] arch_stack_walk+0x28/0x38 [<104e5efc>] stack_trace_save+0x48/0x5c [<105d1bdc>] set_track_prepare+0x44/0x6c [<105d9c80>] ___slab_alloc+0xfc4/0x1024 [<105d9d38>] __slab_alloc.isra.0+0x58/0x90 [<105dc80c>] kmem_cache_alloc_noprof+0x2ac/0x4a0 [<105b8e54>] __anon_vma_prepare+0x60/0x280 [<105a823c>] __vmf_anon_prepare+0x68/0x94 [<105a8b34>] do_wp_page+0x8cc/0xf10 [<105aad88>] handle_mm_fault+0x6c0/0xf08 [<10425568>] do_page_fault+0x110/0x440 [<10427938>] handle_interruption+0x184/0x748 [<11178398>] schedule+0x4c/0x190 BUG: spinlock recursion on CPU#0, ifconfig/2420 lock: terminate_lock.2+0x0/0x1c, .magic: dead4ead, .owner: ifconfig/2420, .owner_cpu: 0 While creating the stack trace, the unwinder uses the stack pointer to guess the previous frame to read the previous stack pointer from memory. The crash happens, because the unwinder tries to read from unaligned memory and as such triggers the unalignment trap handler which then leads to the spinlock recursion and finally to a deadlock. Fix it by checking the alignment before accessing the memory.
CVE-2025-68324: In the Linux kernel, the following vulnerability has been resolved: scsi: imm: Fix use-after-free bug caused by unfinished delayed work The delayed work item 'imm_tq' is initialized in imm_attach() and scheduled via imm_queuecommand() for processing SCSI commands. When the IMM parallel port SCSI host adapter is detached through imm_detach(), the imm_struct device instance is deallocated. However, the delayed work might still be pending or executing when imm_detach() is called, leading to use-after-free bugs when the work function imm_interrupt() accesses the already freed imm_struct memory. The race condition can occur as follows: CPU 0(detach thread) | CPU 1 | imm_queuecommand() | imm_queuecommand_lck() imm_detach() | schedule_delayed_work() kfree(dev) //FREE | imm_interrupt() | dev = container_of(...) //USE dev-> //USE Add disable_delayed_work_sync() in imm_detach() to guarantee proper cancellation of the delayed work item before imm_struct is deallocated.
CVE-2025-68334: In the Linux kernel, the following vulnerability has been resolved: platform/x86/amd/pmc: Add support for Van Gogh SoC The ROG Xbox Ally (non-X) SoC features a similar architecture to the Steam Deck. While the Steam Deck supports S3 (s2idle causes a crash), this support was dropped by the Xbox Ally which only S0ix suspend. Since the handler is missing here, this causes the device to not suspend and the AMD GPU driver to crash while trying to resume afterwards due to a power hang.
CVE-2025-68342: In the Linux kernel, the following vulnerability has been resolved: can: gs_usb: gs_usb_receive_bulk_callback(): check actual_length before accessing data The URB received in gs_usb_receive_bulk_callback() contains a struct gs_host_frame. The length of the data after the header depends on the gs_host_frame hf::flags and the active device features (e.g. time stamping). Introduce a new function gs_usb_get_minimum_length() and check that we have at least received the required amount of data before accessing it. Only copy the data to that skb that has actually been received. [mkl: rename gs_usb_get_minimum_length() -> +gs_usb_get_minimum_rx_length()]
CVE-2025-68378: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix stackmap overflow check in __bpf_get_stackid() Syzkaller reported a KASAN slab-out-of-bounds write in __bpf_get_stackid() when copying stack trace data. The issue occurs when the perf trace contains more stack entries than the stack map bucket can hold, leading to an out-of-bounds write in the bucket's data array.
CVE-2025-68379: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Fix null deref on srq->rq.queue after resize failure A NULL pointer dereference can occur in rxe_srq_chk_attr() when ibv_modify_srq() is invoked twice in succession under certain error conditions. The first call may fail in rxe_queue_resize(), which leads rxe_srq_from_attr() to set srq->rq.queue = NULL. The second call then triggers a crash (null deref) when accessing srq->rq.queue->buf->index_mask. Call Trace: <TASK> rxe_modify_srq+0x170/0x480 [rdma_rxe] ? __pfx_rxe_modify_srq+0x10/0x10 [rdma_rxe] ? uverbs_try_lock_object+0x4f/0xa0 [ib_uverbs] ? rdma_lookup_get_uobject+0x1f0/0x380 [ib_uverbs] ib_uverbs_modify_srq+0x204/0x290 [ib_uverbs] ? __pfx_ib_uverbs_modify_srq+0x10/0x10 [ib_uverbs] ? tryinc_node_nr_active+0xe6/0x150 ? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x2c0/0x470 [ib_uverbs] ? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs] ? uverbs_fill_udata+0xed/0x4f0 [ib_uverbs] ib_uverbs_run_method+0x55a/0x6e0 [ib_uverbs] ? __pfx_ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0x10/0x10 [ib_uverbs] ib_uverbs_cmd_verbs+0x54d/0x800 [ib_uverbs] ? __pfx_ib_uverbs_cmd_verbs+0x10/0x10 [ib_uverbs] ? __pfx___raw_spin_lock_irqsave+0x10/0x10 ? __pfx_do_vfs_ioctl+0x10/0x10 ? ioctl_has_perm.constprop.0.isra.0+0x2c7/0x4c0 ? __pfx_ioctl_has_perm.constprop.0.isra.0+0x10/0x10 ib_uverbs_ioctl+0x13e/0x220 [ib_uverbs] ? __pfx_ib_uverbs_ioctl+0x10/0x10 [ib_uverbs] __x64_sys_ioctl+0x138/0x1c0 do_syscall_64+0x82/0x250 ? fdget_pos+0x58/0x4c0 ? ksys_write+0xf3/0x1c0 ? __pfx_ksys_write+0x10/0x10 ? do_syscall_64+0xc8/0x250 ? __pfx_vm_mmap_pgoff+0x10/0x10 ? fget+0x173/0x230 ? fput+0x2a/0x80 ? ksys_mmap_pgoff+0x224/0x4c0 ? do_syscall_64+0xc8/0x250 ? do_user_addr_fault+0x37b/0xfe0 ? clear_bhb_loop+0x50/0xa0 ? clear_bhb_loop+0x50/0xa0 ? clear_bhb_loop+0x50/0xa0 entry_SYSCALL_64_after_hwframe+0x76/0x7e
CVE-2025-68736: In the Linux kernel, the following vulnerability has been resolved: landlock: Fix handling of disconnected directories Disconnected files or directories can appear when they are visible and opened from a bind mount, but have been renamed or moved from the source of the bind mount in a way that makes them inaccessible from the mount point (i.e. out of scope). Previously, access rights tied to files or directories opened through a disconnected directory were collected by walking the related hierarchy down to the root of the filesystem, without taking into account the mount point because it couldn't be found. This could lead to inconsistent access results, potential access right widening, and hard-to-debug renames, especially since such paths cannot be printed. For a sandboxed task to create a disconnected directory, it needs to have write access (i.e. FS_MAKE_REG, FS_REMOVE_FILE, and FS_REFER) to the underlying source of the bind mount, and read access to the related mount point. Because a sandboxed task cannot acquire more access rights than those defined by its Landlock domain, this could lead to inconsistent access rights due to missing permissions that should be inherited from the mount point hierarchy, while inheriting permissions from the filesystem hierarchy hidden by this mount point instead. Landlock now handles files and directories opened from disconnected directories by taking into account the filesystem hierarchy when the mount point is not found in the hierarchy walk, and also always taking into account the mount point from which these disconnected directories were opened. This ensures that a rename is not allowed if it would widen access rights [1]. The rationale is that, even if disconnected hierarchies might not be visible or accessible to a sandboxed task, relying on the collected access rights from them improves the guarantee that access rights will not be widened during a rename because of the access right comparison between the source and the destination (see LANDLOCK_ACCESS_FS_REFER). It may look like this would grant more access on disconnected files and directories, but the security policies are always enforced for all the evaluated hierarchies. This new behavior should be less surprising to users and safer from an access control perspective. Remove a wrong WARN_ON_ONCE() canary in collect_domain_accesses() and fix the related comment. Because opened files have their access rights stored in the related file security properties, there is no impact for disconnected or unlinked files.
CVE-2025-68745: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Clear cmds after chip reset Commit aefed3e5548f ("scsi: qla2xxx: target: Fix offline port handling and host reset handling") caused two problems: 1. Commands sent to FW, after chip reset got stuck and never freed as FW is not going to respond to them anymore. 2. BUG_ON(cmd->sg_mapped) in qlt_free_cmd(). Commit 26f9ce53817a ("scsi: qla2xxx: Fix missed DMA unmap for aborted commands") attempted to fix this, but introduced another bug under different circumstances when two different CPUs were racing to call qlt_unmap_sg() at the same time: BUG_ON(!valid_dma_direction(dir)) in dma_unmap_sg_attrs(). So revert "scsi: qla2xxx: Fix missed DMA unmap for aborted commands" and partially revert "scsi: qla2xxx: target: Fix offline port handling and host reset handling" at __qla2x00_abort_all_cmds.
CVE-2025-68755: In the Linux kernel, the following vulnerability has been resolved: staging: most: remove broken i2c driver The MOST I2C driver has been completely broken for five years without anyone noticing so remove the driver from staging. Specifically, commit 723de0f9171e ("staging: most: remove device from interface structure") started requiring drivers to set the interface device pointer before registration, but the I2C driver was never updated which results in a NULL pointer dereference if anyone ever tries to probe it.
CVE-2025-68768: In the Linux kernel, the following vulnerability has been resolved: inet: frags: flush pending skbs in fqdir_pre_exit() We have been seeing occasional deadlocks on pernet_ops_rwsem since September in NIPA. The stuck task was usually modprobe (often loading a driver like ipvlan), trying to take the lock as a Writer. lockdep does not track readers for rwsems so the read wasn't obvious from the reports. On closer inspection the Reader holding the lock was conntrack looping forever in nf_conntrack_cleanup_net_list(). Based on past experience with occasional NIPA crashes I looked thru the tests which run before the crash and noticed that the crash follows ip_defrag.sh. An immediate red flag. Scouring thru (de)fragmentation queues reveals skbs sitting around, holding conntrack references. The problem is that since conntrack depends on nf_defrag_ipv6, nf_defrag_ipv6 will load first. Since nf_defrag_ipv6 loads first its netns exit hooks run _after_ conntrack's netns exit hook. Flush all fragment queue SKBs during fqdir_pre_exit() to release conntrack references before conntrack cleanup runs. Also flush the queues in timer expiry handlers when they discover fqdir->dead is set, in case packet sneaks in while we're running the pre_exit flush. The commit under Fixes is not exactly the culprit, but I think previously the timer firing would eventually unblock the spinning conntrack.
CVE-2025-68794: In the Linux kernel, the following vulnerability has been resolved: iomap: adjust read range correctly for non-block-aligned positions iomap_adjust_read_range() assumes that the position and length passed in are block-aligned. This is not always the case however, as shown in the syzbot generated case for erofs. This causes too many bytes to be skipped for uptodate blocks, which results in returning the incorrect position and length to read in. If all the blocks are uptodate, this underflows length and returns a position beyond the folio. Fix the calculation to also take into account the block offset when calculating how many bytes can be skipped for uptodate blocks.
CVE-2025-68809: In the Linux kernel, the following vulnerability has been resolved: ksmbd: vfs: fix race on m_flags in vfs_cache ksmbd maintains delete-on-close and pending-delete state in ksmbd_inode->m_flags. In vfs_cache.c this field is accessed under inconsistent locking: some paths read and modify m_flags under ci->m_lock while others do so without taking the lock at all. Examples: - ksmbd_query_inode_status() and __ksmbd_inode_close() use ci->m_lock when checking or updating m_flags. - ksmbd_inode_pending_delete(), ksmbd_set_inode_pending_delete(), ksmbd_clear_inode_pending_delete() and ksmbd_fd_set_delete_on_close() used to read and modify m_flags without ci->m_lock. This creates a potential data race on m_flags when multiple threads open, close and delete the same file concurrently. In the worst case delete-on-close and pending-delete bits can be lost or observed in an inconsistent state, leading to confusing delete semantics (files that stay on disk after delete-on-close, or files that disappear while still in use). Fix it by: - Making ksmbd_query_inode_status() look at m_flags under ci->m_lock after dropping inode_hash_lock. - Adding ci->m_lock protection to all helpers that read or modify m_flags (ksmbd_inode_pending_delete(), ksmbd_set_inode_pending_delete(), ksmbd_clear_inode_pending_delete(), ksmbd_fd_set_delete_on_close()). - Keeping the existing ci->m_lock protection in __ksmbd_inode_close(), and moving the actual unlink/xattr removal outside the lock. This unifies the locking around m_flags and removes the data race while preserving the existing delete-on-close behaviour.
CVE-2025-68822: In the Linux kernel, the following vulnerability has been resolved: Input: alps - fix use-after-free bugs caused by dev3_register_work The dev3_register_work delayed work item is initialized within alps_reconnect() and scheduled upon receipt of the first bare PS/2 packet from an external PS/2 device connected to the ALPS touchpad. During device detachment, the original implementation calls flush_workqueue() in psmouse_disconnect() to ensure completion of dev3_register_work. However, the flush_workqueue() in psmouse_disconnect() only blocks and waits for work items that were already queued to the workqueue prior to its invocation. Any work items submitted after flush_workqueue() is called are not included in the set of tasks that the flush operation awaits. This means that after flush_workqueue() has finished executing, the dev3_register_work could still be scheduled. Although the psmouse state is set to PSMOUSE_CMD_MODE in psmouse_disconnect(), the scheduling of dev3_register_work remains unaffected. The race condition can occur as follows: CPU 0 (cleanup path) | CPU 1 (delayed work) psmouse_disconnect() | psmouse_set_state() | flush_workqueue() | alps_report_bare_ps2_packet() alps_disconnect() | psmouse_queue_work() kfree(priv); // FREE | alps_register_bare_ps2_mouse() | priv = container_of(work...); // USE | priv->dev3 // USE Add disable_delayed_work_sync() in alps_disconnect() to ensure that dev3_register_work is properly canceled and prevented from executing after the alps_data structure has been deallocated. This bug is identified by static analysis.
CVE-2025-68823: In the Linux kernel, the following vulnerability has been resolved: ublk: fix deadlock when reading partition table When one process(such as udev) opens ublk block device (e.g., to read the partition table via bdev_open()), a deadlock[1] can occur: 1. bdev_open() grabs disk->open_mutex 2. The process issues read I/O to ublk backend to read partition table 3. In __ublk_complete_rq(), blk_update_request() or blk_mq_end_request() runs bio->bi_end_io() callbacks 4. If this triggers fput() on file descriptor of ublk block device, the work may be deferred to current task's task work (see fput() implementation) 5. This eventually calls blkdev_release() from the same context 6. blkdev_release() tries to grab disk->open_mutex again 7. Deadlock: same task waiting for a mutex it already holds The fix is to run blk_update_request() and blk_mq_end_request() with bottom halves disabled. This forces blkdev_release() to run in kernel work-queue context instead of current task work context, and allows ublk server to make forward progress, and avoids the deadlock. [axboe: rewrite comment in ublk]
CVE-2025-71065: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid potential deadlock As Jiaming Zhang and syzbot reported, there is potential deadlock in f2fs as below: Chain exists of: &sbi->cp_rwsem --> fs_reclaim --> sb_internal#2 Possible unsafe locking scenario: CPU0 CPU1 ---- ---- rlock(sb_internal#2); lock(fs_reclaim); lock(sb_internal#2); rlock(&sbi->cp_rwsem); *** DEADLOCK *** 3 locks held by kswapd0/73: #0: ffffffff8e247a40 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat mm/vmscan.c:7015 [inline] #0: ffffffff8e247a40 (fs_reclaim){+.+.}-{0:0}, at: kswapd+0x951/0x2800 mm/vmscan.c:7389 #1: ffff8880118400e0 (&type->s_umount_key#50){.+.+}-{4:4}, at: super_trylock_shared fs/super.c:562 [inline] #1: ffff8880118400e0 (&type->s_umount_key#50){.+.+}-{4:4}, at: super_cache_scan+0x91/0x4b0 fs/super.c:197 #2: ffff888011840610 (sb_internal#2){.+.+}-{0:0}, at: f2fs_evict_inode+0x8d9/0x1b60 fs/f2fs/inode.c:890 stack backtrace: CPU: 0 UID: 0 PID: 73 Comm: kswapd0 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_circular_bug+0x2ee/0x310 kernel/locking/lockdep.c:2043 check_noncircular+0x134/0x160 kernel/locking/lockdep.c:2175 check_prev_add kernel/locking/lockdep.c:3165 [inline] check_prevs_add kernel/locking/lockdep.c:3284 [inline] validate_chain+0xb9b/0x2140 kernel/locking/lockdep.c:3908 __lock_acquire+0xab9/0xd20 kernel/locking/lockdep.c:5237 lock_acquire+0x120/0x360 kernel/locking/lockdep.c:5868 down_read+0x46/0x2e0 kernel/locking/rwsem.c:1537 f2fs_down_read fs/f2fs/f2fs.h:2278 [inline] f2fs_lock_op fs/f2fs/f2fs.h:2357 [inline] f2fs_do_truncate_blocks+0x21c/0x10c0 fs/f2fs/file.c:791 f2fs_truncate_blocks+0x10a/0x300 fs/f2fs/file.c:867 f2fs_truncate+0x489/0x7c0 fs/f2fs/file.c:925 f2fs_evict_inode+0x9f2/0x1b60 fs/f2fs/inode.c:897 evict+0x504/0x9c0 fs/inode.c:810 f2fs_evict_inode+0x1dc/0x1b60 fs/f2fs/inode.c:853 evict+0x504/0x9c0 fs/inode.c:810 dispose_list fs/inode.c:852 [inline] prune_icache_sb+0x21b/0x2c0 fs/inode.c:1000 super_cache_scan+0x39b/0x4b0 fs/super.c:224 do_shrink_slab+0x6ef/0x1110 mm/shrinker.c:437 shrink_slab_memcg mm/shrinker.c:550 [inline] shrink_slab+0x7ef/0x10d0 mm/shrinker.c:628 shrink_one+0x28a/0x7c0 mm/vmscan.c:4955 shrink_many mm/vmscan.c:5016 [inline] lru_gen_shrink_node mm/vmscan.c:5094 [inline] shrink_node+0x315d/0x3780 mm/vmscan.c:6081 kswapd_shrink_node mm/vmscan.c:6941 [inline] balance_pgdat mm/vmscan.c:7124 [inline] kswapd+0x147c/0x2800 mm/vmscan.c:7389 kthread+0x70e/0x8a0 kernel/kthread.c:463 ret_from_fork+0x4bc/0x870 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245 </TASK> The root cause is deadlock among four locks as below: kswapd - fs_reclaim --- Lock A - shrink_one - evict - f2fs_evict_inode - sb_start_intwrite --- Lock B - iput - evict - f2fs_evict_inode - sb_start_intwrite --- Lock B - f2fs_truncate - f2fs_truncate_blocks - f2fs_do_truncate_blocks - f2fs_lock_op --- Lock C ioctl - f2fs_ioc_commit_atomic_write - f2fs_lock_op --- Lock C - __f2fs_commit_atomic_write - __replace_atomic_write_block - f2fs_get_dnode_of_data - __get_node_folio - f2fs_check_nid_range - f2fs_handle_error - f2fs_record_errors - f2fs_down_write --- Lock D open - do_open - do_truncate - security_inode_need_killpriv - f2fs_getxattr - lookup_all_xattrs - f2fs_handle_error - f2fs_record_errors - f2fs_down_write --- Lock D - f2fs_commit_super - read_mapping_folio - filemap_alloc_folio_noprof - prepare_alloc_pages - fs_reclaim_acquire --- Lock A In order to a ---truncated---
CVE-2025-71067: In the Linux kernel, the following vulnerability has been resolved: ntfs: set dummy blocksize to read boot_block when mounting When mounting, sb->s_blocksize is used to read the boot_block without being defined or validated. Set a dummy blocksize before attempting to read the boot_block. The issue can be triggered with the following syz reproducer: mkdirat(0xffffffffffffff9c, &(0x7f0000000080)='./file1\x00', 0x0) r4 = openat$nullb(0xffffffffffffff9c, &(0x7f0000000040), 0x121403, 0x0) ioctl$FS_IOC_SETFLAGS(r4, 0x40081271, &(0x7f0000000980)=0x4000) mount(&(0x7f0000000140)=@nullb, &(0x7f0000000040)='./cgroup\x00', &(0x7f0000000000)='ntfs3\x00', 0x2208004, 0x0) syz_clone(0x88200200, 0x0, 0x0, 0x0, 0x0, 0x0) Here, the ioctl sets the bdev block size to 16384. During mount, get_tree_bdev_flags() calls sb_set_blocksize(sb, block_size(bdev)), but since block_size(bdev) > PAGE_SIZE, sb_set_blocksize() leaves sb->s_blocksize at zero. Later, ntfs_init_from_boot() attempts to read the boot_block while sb->s_blocksize is still zero, which triggers the bug. [almaz.alexandrovich@paragon-software.com: changed comment style, added return value handling]
CVE-2025-71068: In the Linux kernel, the following vulnerability has been resolved: svcrdma: bound check rq_pages index in inline path svc_rdma_copy_inline_range indexed rqstp->rq_pages[rc_curpage] without verifying rc_curpage stays within the allocated page array. Add guards before the first use and after advancing to a new page.
CVE-2025-71073: In the Linux kernel, the following vulnerability has been resolved: Input: lkkbd - disable pending work before freeing device lkkbd_interrupt() schedules lk->tq via schedule_work(), and the work handler lkkbd_reinit() dereferences the lkkbd structure and its serio/input_dev fields. lkkbd_disconnect() and error paths in lkkbd_connect() free the lkkbd structure without preventing the reinit work from being queued again until serio_close() returns. This can allow the work handler to run after the structure has been freed, leading to a potential use-after-free. Use disable_work_sync() instead of cancel_work_sync() to ensure the reinit work cannot be re-queued, and call it both in lkkbd_disconnect() and in lkkbd_connect() error paths after serio_open().
CVE-2025-71074: In the Linux kernel, the following vulnerability has been resolved: functionfs: fix the open/removal races ffs_epfile_open() can race with removal, ending up with file->private_data pointing to freed object. There is a total count of opened files on functionfs (both ep0 and dynamic ones) and when it hits zero, dynamic files get removed. Unfortunately, that removal can happen while another thread is in ffs_epfile_open(), but has not incremented the count yet. In that case open will succeed, leaving us with UAF on any subsequent read() or write(). The root cause is that ffs->opened is misused; atomic_dec_and_test() vs. atomic_add_return() is not a good idea, when object remains visible all along. To untangle that * serialize openers on ffs->mutex (both for ep0 and for dynamic files) * have dynamic ones use atomic_inc_not_zero() and fail if we had zero ->opened; in that case the file we are opening is doomed. * have the inodes of dynamic files marked on removal (from the callback of simple_recursive_removal()) - clear ->i_private there. * have open of dynamic ones verify they hadn't been already removed, along with checking that state is FFS_ACTIVE.
CVE-2025-71109: In the Linux kernel, the following vulnerability has been resolved: MIPS: ftrace: Fix memory corruption when kernel is located beyond 32 bits Since commit e424054000878 ("MIPS: Tracing: Reduce the overhead of dynamic Function Tracer"), the macro UASM_i_LA_mostly has been used, and this macro can generate more than 2 instructions. At the same time, the code in ftrace assumes that no more than 2 instructions can be generated, which is why it stores them in an int[2] array. However, as previously noted, the macro UASM_i_LA_mostly (and now UASM_i_LA) causes a buffer overflow when _mcount is beyond 32 bits. This leads to corruption of the variables located in the __read_mostly section. This corruption was observed because the variable __cpu_primary_thread_mask was corrupted, causing a hang very early during boot. This fix prevents the corruption by avoiding the generation of instructions if they could exceed 2 instructions in length. Fortunately, insn_la_mcount is only used if the instrumented code is located outside the kernel code section, so dynamic ftrace can still be used, albeit in a more limited scope. This is still preferable to corrupting memory and/or crashing the kernel.
CVE-2025-71129: In the Linux kernel, the following vulnerability has been resolved: LoongArch: BPF: Sign extend kfunc call arguments The kfunc calls are native calls so they should follow LoongArch calling conventions. Sign extend its arguments properly to avoid kernel panic. This is done by adding a new emit_abi_ext() helper. The emit_abi_ext() helper performs extension in place meaning a value already store in the target register (Note: this is different from the existing sign_extend() helper and thus we can't reuse it).
CVE-2025-71138: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: Add missing NULL pointer check for pingpong interface It is checked almost always in dpu_encoder_phys_wb_setup_ctl(), but in a single place the check is missing. Also use convenient locals instead of phys_enc->* where available. Patchwork: https://patchwork.freedesktop.org/patch/693860/
CVE-2025-71152: In the Linux kernel, the following vulnerability has been resolved: net: dsa: properly keep track of conduit reference Problem description ------------------- DSA has a mumbo-jumbo of reference handling of the conduit net device and its kobject which, sadly, is just wrong and doesn't make sense. There are two distinct problems. 1. The OF path, which uses of_find_net_device_by_node(), never releases the elevated refcount on the conduit's kobject. Nominally, the OF and non-OF paths should result in objects having identical reference counts taken, and it is already suspicious that dsa_dev_to_net_device() has a put_device() call which is missing in dsa_port_parse_of(), but we can actually even verify that an issue exists. With CONFIG_DEBUG_KOBJECT_RELEASE=y, if we run this command "before" and "after" applying this patch: (unbind the conduit driver for net device eno2) echo 0000:00:00.2 > /sys/bus/pci/drivers/fsl_enetc/unbind we see these lines in the output diff which appear only with the patch applied: kobject: 'eno2' (ffff002009a3a6b8): kobject_release, parent 0000000000000000 (delayed 1000) kobject: '109' (ffff0020099d59a0): kobject_release, parent 0000000000000000 (delayed 1000) 2. After we find the conduit interface one way (OF) or another (non-OF), it can get unregistered at any time, and DSA remains with a long-lived, but in this case stale, cpu_dp->conduit pointer. Holding the net device's underlying kobject isn't actually of much help, it just prevents it from being freed (but we never need that kobject directly). What helps us to prevent the net device from being unregistered is the parallel netdev reference mechanism (dev_hold() and dev_put()). Actually we actually use that netdev tracker mechanism implicitly on user ports since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), via netdev_upper_dev_link(). But time still passes at DSA switch probe time between the initial of_find_net_device_by_node() code and the user port creation time, time during which the conduit could unregister itself and DSA wouldn't know about it. So we have to run of_find_net_device_by_node() under rtnl_lock() to prevent that from happening, and release the lock only with the netdev tracker having acquired the reference. Do we need to keep the reference until dsa_unregister_switch() / dsa_switch_shutdown()? 1: Maybe yes. A switch device will still be registered even if all user ports failed to probe, see commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal"), and the cpu_dp->conduit pointers remain valid. I haven't audited all call paths to see whether they will actually use the conduit in lack of any user port, but if they do, it seems safer to not rely on user ports for that reference. 2. Definitely yes. We support changing the conduit which a user port is associated to, and we can get into a situation where we've moved all user ports away from a conduit, thus no longer hold any reference to it via the net device tracker. But we shouldn't let it go nonetheless - see the next change in relation to dsa_tree_find_first_conduit() and LAG conduits which disappear. We have to be prepared to return to the physical conduit, so the CPU port must explicitly keep another reference to it. This is also to say: the user ports and their CPU ports may not always keep a reference to the same conduit net device, and both are needed. As for the conduit's kobject for the /sys/class/net/ entry, we don't care about it, we can release it as soon as we hold the net device object itself. History and blame attribution ----------------------------- The code has been refactored so many times, it is very difficult to follow and properly attribute a blame, but I'll try to make a short history which I hope to be correct. We have two distinct probing paths: - one for OF, introduced in 2016 i ---truncated---
CVE-2025-71160: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: avoid chain re-validation if possible Hamza Mahfooz reports cpu soft lock-ups in nft_chain_validate(): watchdog: BUG: soft lockup - CPU#1 stuck for 27s! [iptables-nft-re:37547] [..] RIP: 0010:nft_chain_validate+0xcb/0x110 [nf_tables] [..] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_immediate_validate+0x36/0x50 [nf_tables] nft_chain_validate+0xc9/0x110 [nf_tables] nft_table_validate+0x6b/0xb0 [nf_tables] nf_tables_validate+0x8b/0xa0 [nf_tables] nf_tables_commit+0x1df/0x1eb0 [nf_tables] [..] Currently nf_tables will traverse the entire table (chain graph), starting from the entry points (base chains), exploring all possible paths (chain jumps). But there are cases where we could avoid revalidation. Consider: 1 input -> j2 -> j3 2 input -> j2 -> j3 3 input -> j1 -> j2 -> j3 Then the second rule does not need to revalidate j2, and, by extension j3, because this was already checked during validation of the first rule. We need to validate it only for rule 3. This is needed because chain loop detection also ensures we do not exceed the jump stack: Just because we know that j2 is cycle free, its last jump might now exceed the allowed stack size. We also need to update all reachable chains with the new largest observed call depth. Care has to be taken to revalidate even if the chain depth won't be an issue: chain validation also ensures that expressions are not called from invalid base chains. For example, the masquerade expression can only be called from NAT postrouting base chains. Therefore we also need to keep record of the base chain context (type, hooknum) and revalidate if the chain becomes reachable from a different hook location.
CVE-2025-71161: In the Linux kernel, the following vulnerability has been resolved: dm-verity: disable recursive forward error correction There are two problems with the recursive correction: 1. It may cause denial-of-service. In fec_read_bufs, there is a loop that has 253 iterations. For each iteration, we may call verity_hash_for_block recursively. There is a limit of 4 nested recursions - that means that there may be at most 253^4 (4 billion) iterations. Red Hat QE team actually created an image that pushes dm-verity to this limit - and this image just makes the udev-worker process get stuck in the 'D' state. 2. It doesn't work. In fec_read_bufs we store data into the variable "fio->bufs", but fio bufs is shared between recursive invocations, if "verity_hash_for_block" invoked correction recursively, it would overwrite partially filled fio->bufs.
CVE-2025-71184: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix NULL dereference on root when tracing inode eviction When evicting an inode the first thing we do is to setup tracing for it, which implies fetching the root's id. But in btrfs_evict_inode() the root might be NULL, as implied in the next check that we do in btrfs_evict_inode(). Hence, we either should set the ->root_objectid to 0 in case the root is NULL, or we move tracing setup after checking that the root is not NULL. Setting the rootid to 0 at least gives us the possibility to trace this call even in the case when the root is NULL, so that's the solution taken here.
CVE-2025-71193: In the Linux kernel, the following vulnerability has been resolved: phy: qcom-qusb2: Fix NULL pointer dereference on early suspend Enabling runtime PM before attaching the QPHY instance as driver data can lead to a NULL pointer dereference in runtime PM callbacks that expect valid driver data. There is a small window where the suspend callback may run after PM runtime enabling and before runtime forbid. This causes a sporadic crash during boot: ``` Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a1 [...] CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.7+ #116 PREEMPT Workqueue: pm pm_runtime_work pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : qusb2_phy_runtime_suspend+0x14/0x1e0 [phy_qcom_qusb2] lr : pm_generic_runtime_suspend+0x2c/0x44 [...] ``` Attach the QPHY instance as driver data before enabling runtime PM to prevent NULL pointer dereference in runtime PM callbacks. Reorder pm_runtime_enable() and pm_runtime_forbid() to prevent a short window where an unnecessary runtime suspend can occur. Use the devres-managed version to ensure PM runtime is symmetrically disabled during driver removal for proper cleanup.
CVE-2025-71198: In the Linux kernel, the following vulnerability has been resolved: iio: imu: st_lsm6dsx: fix iio_chan_spec for sensors without event detection The st_lsm6dsx_acc_channels array of struct iio_chan_spec has a non-NULL event_spec field, indicating support for IIO events. However, event detection is not supported for all sensors, and if userspace tries to configure accelerometer wakeup events on a sensor device that does not support them (e.g. LSM6DS0), st_lsm6dsx_write_event() dereferences a NULL pointer when trying to write to the wakeup register. Define an additional struct iio_chan_spec array whose members have a NULL event_spec field, and use this array instead of st_lsm6dsx_acc_channels for sensors without event detection capability.
CVE-2025-71202: In the Linux kernel, the following vulnerability has been resolved: iommu/sva: invalidate stale IOTLB entries for kernel address space Introduce a new IOMMU interface to flush IOTLB paging cache entries for the CPU kernel address space. This interface is invoked from the x86 architecture code that manages combined user and kernel page tables, specifically before any kernel page table page is freed and reused. This addresses the main issue with vfree() which is a common occurrence and can be triggered by unprivileged users. While this resolves the primary problem, it doesn't address some extremely rare case related to memory unplug of memory that was present as reserved memory at boot, which cannot be triggered by unprivileged users. The discussion can be found at the link below. Enable SVA on x86 architecture since the IOMMU can now receive notification to flush the paging cache before freeing the CPU kernel page table pages.
CVE-2025-71221: In the Linux kernel, the following vulnerability has been resolved: dmaengine: mmp_pdma: Fix race condition in mmp_pdma_residue() Add proper locking in mmp_pdma_residue() to prevent use-after-free when accessing descriptor list and descriptor contents. The race occurs when multiple threads call tx_status() while the tasklet on another CPU is freeing completed descriptors: CPU 0 CPU 1 ----- ----- mmp_pdma_tx_status() mmp_pdma_residue() -> NO LOCK held list_for_each_entry(sw, ..) DMA interrupt dma_do_tasklet() -> spin_lock(&desc_lock) list_move(sw->node, ...) spin_unlock(&desc_lock) | dma_pool_free(sw) <- FREED! -> access sw->desc <- UAF! This issue can be reproduced when running dmatest on the same channel with multiple threads (threads_per_chan > 1). Fix by protecting the chain_running list iteration and descriptor access with the chan->desc_lock spinlock.
CVE-2025-71225: In the Linux kernel, the following vulnerability has been resolved: md: suspend array while updating raid_disks via sysfs In raid1_reshape(), freeze_array() is called before modifying the r1bio memory pool (conf->r1bio_pool) and conf->raid_disks, and unfreeze_array() is called after the update is completed. However, freeze_array() only waits until nr_sync_pending and (nr_pending - nr_queued) of all buckets reaches zero. When an I/O error occurs, nr_queued is increased and the corresponding r1bio is queued to either retry_list or bio_end_io_list. As a result, freeze_array() may unblock before these r1bios are released. This can lead to a situation where conf->raid_disks and the mempool have already been updated while queued r1bios, allocated with the old raid_disks value, are later released. Consequently, free_r1bio() may access memory out of bounds in put_all_bios() and release r1bios of the wrong size to the new mempool, potentially causing issues with the mempool as well. Since only normal I/O might increase nr_queued while an I/O error occurs, suspending the array avoids this issue. Note: Updating raid_disks via ioctl SET_ARRAY_INFO already suspends the array. Therefore, we suspend the array when updating raid_disks via sysfs to avoid this issue too.
CVE-2025-71227: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: don't WARN for connections on invalid channels It's not clear (to me) how exactly syzbot managed to hit this, but it seems conceivable that e.g. regulatory changed and has disabled a channel between scanning (channel is checked to be usable by cfg80211_get_ies_channel_number) and connecting on the channel later. With one scenario that isn't covered elsewhere described above, the warning isn't good, replace it with a (more informative) error message.
CVE-2025-71265: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop in attr_load_runs_range on inconsistent metadata We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an attribute header indicates an empty run list, while directory entries reference it as containing actual data. In NTFS, setting evcn=-1 with svcn=0 is a valid way to represent an empty run list, and run_unpack() correctly handles this by checking if evcn + 1 equals svcn and returning early without parsing any run data. However, this creates a problem when there is metadata inconsistency, where the attribute header claims to be empty (evcn=-1) but the caller expects to read actual data. When run_unpack() immediately returns success upon seeing this condition, it leaves the runs_tree uninitialized with run->runs as a NULL. The calling function attr_load_runs_range() assumes that a successful return means that the runs were loaded and sets clen to 0, expecting the next run_lookup_entry() call to succeed. Because runs_tree remains uninitialized, run_lookup_entry() continues to fail, and the loop increments vcn by zero (vcn += 0), leading to an infinite loop. This patch adds a retry counter to detect when run_lookup_entry() fails consecutively after attr_load_runs_vcn(). If the run is still not found on the second attempt, it indicates corrupted metadata and returns -EINVAL, preventing the Denial-of-Service (DoS) vulnerability.
CVE-2025-71266: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: check return value of indx_find to avoid infinite loop We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed dentry in the ntfs3 filesystem can cause the kernel to hang during the lookup operations. By setting the HAS_SUB_NODE flag in an INDEX_ENTRY within a directory's INDEX_ALLOCATION block and manipulating the VCN pointer, an attacker can cause the indx_find() function to repeatedly read the same block, allocating 4 KB of memory each time. The kernel lacks VCN loop detection and depth limits, causing memory exhaustion and an OOM crash. This patch adds a return value check for fnd_push() to prevent a memory exhaustion vulnerability caused by infinite loops. When the index exceeds the size of the fnd->nodes array, fnd_push() returns -EINVAL. The indx_find() function checks this return value and stops processing, preventing further memory allocation.
CVE-2025-71267: In the Linux kernel, the following vulnerability has been resolved: fs: ntfs3: fix infinite loop triggered by zero-sized ATTR_LIST We found an infinite loop bug in the ntfs3 file system that can lead to a Denial-of-Service (DoS) condition. A malformed NTFS image can cause an infinite loop when an ATTR_LIST attribute indicates a zero data size while the driver allocates memory for it. When ntfs_load_attr_list() processes a resident ATTR_LIST with data_size set to zero, it still allocates memory because of al_aligned(0). This creates an inconsistent state where ni->attr_list.size is zero, but ni->attr_list.le is non-null. This causes ni_enum_attr_ex to incorrectly assume that no attribute list exists and enumerates only the primary MFT record. When it finds ATTR_LIST, the code reloads it and restarts the enumeration, repeating indefinitely. The mount operation never completes, hanging the kernel thread. This patch adds validation to ensure that data_size is non-zero before memory allocation. When a zero-sized ATTR_LIST is detected, the function returns -EINVAL, preventing a DoS vulnerability.
CVE-2025-71269: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not free data reservation in fallback from inline due to -ENOSPC If we fail to create an inline extent due to -ENOSPC, we will attempt to go through the normal COW path, reserve an extent, create an ordered extent, etc. However we were always freeing the reserved qgroup data, which is wrong since we will use data. Fix this by freeing the reserved qgroup data in __cow_file_range_inline() only if we are not doing the fallback (ret is <= 0).
CVE-2026-22996: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Don't store mlx5e_priv in mlx5e_dev devlink priv mlx5e_priv is an unstable structure that can be memset(0) if profile attaching fails, mlx5e_priv in mlx5e_dev devlink private is used to reference the netdev and mdev associated with that struct. Instead, store netdev directly into mlx5e_dev and get mdev from the containing mlx5_adev aux device structure. This fixes a kernel oops in mlx5e_remove when switchdev mode fails due to change profile failure. $ devlink dev eswitch set pci/0000:00:03.0 mode switchdev Error: mlx5_core: Failed setting eswitch to offloads. dmesg: workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 $ devlink dev reload pci/0000:00:03.0 ==> oops BUG: kernel NULL pointer dereference, address: 0000000000000520 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 3 UID: 0 PID: 521 Comm: devlink Not tainted 6.18.0-rc5+ #117 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_remove+0x68/0x130 RSP: 0018:ffffc900034838f0 EFLAGS: 00010246 RAX: ffff88810283c380 RBX: ffff888101874400 RCX: ffffffff826ffc45 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff888102d789c0 R08: ffff8881007137f0 R09: ffff888100264e10 R10: ffffc90003483898 R11: ffffc900034838a0 R12: ffff888100d261a0 R13: ffff888100d261a0 R14: ffff8881018749a0 R15: ffff888101874400 FS: 00007f8565fea740(0000) GS:ffff88856a759000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000520 CR3: 000000010b11a004 CR4: 0000000000370ef0 Call Trace: <TASK> device_release_driver_internal+0x19c/0x200 bus_remove_device+0xc6/0x130 device_del+0x160/0x3d0 ? devl_param_driverinit_value_get+0x2d/0x90 mlx5_detach_device+0x89/0xe0 mlx5_unload_one_devl_locked+0x3a/0x70 mlx5_devlink_reload_down+0xc8/0x220 devlink_reload+0x7d/0x260 devlink_nl_reload_doit+0x45b/0x5a0 genl_family_rcv_msg_doit+0xe8/0x140
CVE-2026-23000: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix crash on profile change rollback failure mlx5e_netdev_change_profile can fail to attach a new profile and can fail to rollback to old profile, in such case, we could end up with a dangling netdev with a fully reset netdev_priv. A retry to change profile, e.g. another attempt to call mlx5e_netdev_change_profile via switchdev mode change, will crash trying to access the now NULL priv->mdev. This fix allows mlx5e_netdev_change_profile() to handle previous failures and an empty priv, by not assuming priv is valid. Pass netdev and mdev to all flows requiring mlx5e_netdev_change_profile() and avoid passing priv. In mlx5e_netdev_change_profile() check if current priv is valid, and if not, just attach the new profile without trying to access the old one. This fixes the following oops, when enabling switchdev mode for the 2nd time after first time failure: ## Enabling switchdev mode first time: mlx5_core 0012:03:00.1: E-Switch: Supported tc chains and prios offload workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 ^^^^^^^^ mlx5_core 0000:00:03.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) ## retry: Enabling switchdev mode 2nd time: mlx5_core 0000:00:03.0: E-Switch: Supported tc chains and prios offload BUG: kernel NULL pointer dereference, address: 0000000000000038 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 13 UID: 0 PID: 520 Comm: devlink Not tainted 6.18.0-rc4+ #91 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_detach_netdev+0x3c/0x90 Code: 50 00 00 f0 80 4f 78 02 48 8b bf e8 07 00 00 48 85 ff 74 16 48 8b 73 78 48 d1 ee 83 e6 01 83 f6 01 40 0f b6 f6 e8 c4 42 00 00 <48> 8b 45 38 48 85 c0 74 08 48 89 df e8 cc 47 40 1e 48 8b bb f0 07 RSP: 0018:ffffc90000673890 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8881036a89c0 RCX: 0000000000000000 RDX: ffff888113f63800 RSI: ffffffff822fe720 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000002dcd R09: 0000000000000000 R10: ffffc900006738e8 R11: 00000000ffffffff R12: 0000000000000000 R13: 0000000000000000 R14: ffff8881036a89c0 R15: 0000000000000000 FS: 00007fdfb8384740(0000) GS:ffff88856a9d6000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 0000000112ae0005 CR4: 0000000000370ef0 Call Trace: <TASK> mlx5e_netdev_change_profile+0x45/0xb0 mlx5e_vport_rep_load+0x27b/0x2d0 mlx5_esw_offloads_rep_load+0x72/0xf0 esw_offloads_enable+0x5d0/0x970 mlx5_eswitch_enable_locked+0x349/0x430 ? is_mp_supported+0x57/0xb0 mlx5_devlink_eswitch_mode_set+0x26b/0x430 devlink_nl_eswitch_set_doit+0x6f/0xf0 genl_family_rcv_msg_doit+0xe8/0x140 genl_rcv_msg+0x18b/0x290 ? __pfx_devlink_nl_pre_doit+0x10/0x10 ? __pfx_devlink_nl_eswitch_set_doit+0x10/0x10 ? __pfx_devlink_nl_post_doit+0x10/0x10 ? __pfx_genl_rcv_msg+0x10/0x10 netlink_rcv_skb+0x52/0x100 genl_rcv+0x28/0x40 netlink_unicast+0x282/0x3e0 ? __alloc_skb+0xd6/0x190 netlink_sendmsg+0x1f7/0x430 __sys_sendto+0x213/0x220 ? __sys_recvmsg+0x6a/0xd0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x50/0x1f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fdfb8495047
CVE-2026-23004: In the Linux kernel, the following vulnerability has been resolved: dst: fix races in rt6_uncached_list_del() and rt_del_uncached_list() syzbot was able to crash the kernel in rt6_uncached_list_flush_dev() in an interesting way [1] Crash happens in list_del_init()/INIT_LIST_HEAD() while writing list->prev, while the prior write on list->next went well. static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); // This went well WRITE_ONCE(list->prev, list); // Crash, @list has been freed. } Issue here is that rt6_uncached_list_del() did not attempt to lock ul->lock, as list_empty(&rt->dst.rt_uncached) returned true because the WRITE_ONCE(list->next, list) happened on the other CPU. We might use list_del_init_careful() and list_empty_careful(), or make sure rt6_uncached_list_del() always grabs the spinlock whenever rt->dst.rt_uncached_list has been set. A similar fix is neeed for IPv4. [1] BUG: KASAN: slab-use-after-free in INIT_LIST_HEAD include/linux/list.h:46 [inline] BUG: KASAN: slab-use-after-free in list_del_init include/linux/list.h:296 [inline] BUG: KASAN: slab-use-after-free in rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] BUG: KASAN: slab-use-after-free in rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 Write of size 8 at addr ffff8880294cfa78 by task kworker/u8:14/3450 CPU: 0 UID: 0 PID: 3450 Comm: kworker/u8:14 Tainted: G L syzkaller #0 PREEMPT_{RT,(full)} Tainted: [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025 Workqueue: netns cleanup_net Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 INIT_LIST_HEAD include/linux/list.h:46 [inline] list_del_init include/linux/list.h:296 [inline] rt6_uncached_list_flush_dev net/ipv6/route.c:191 [inline] rt6_disable_ip+0x633/0x730 net/ipv6/route.c:5020 addrconf_ifdown+0x143/0x18a0 net/ipv6/addrconf.c:3853 addrconf_notify+0x1bc/0x1050 net/ipv6/addrconf.c:-1 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85 call_netdevice_notifiers_extack net/core/dev.c:2268 [inline] call_netdevice_notifiers net/core/dev.c:2282 [inline] netif_close_many+0x29c/0x410 net/core/dev.c:1785 unregister_netdevice_many_notify+0xb50/0x2330 net/core/dev.c:12353 ops_exit_rtnl_list net/core/net_namespace.c:187 [inline] ops_undo_list+0x3dc/0x990 net/core/net_namespace.c:248 cleanup_net+0x4de/0x7b0 net/core/net_namespace.c:696 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246 </TASK> Allocated by task 803: kasan_save_stack mm/kasan/common.c:57 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:78 unpoison_slab_object mm/kasan/common.c:340 [inline] __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366 kasan_slab_alloc include/linux/kasan.h:253 [inline] slab_post_alloc_hook mm/slub.c:4953 [inline] slab_alloc_node mm/slub.c:5263 [inline] kmem_cache_alloc_noprof+0x18d/0x6c0 mm/slub.c:5270 dst_alloc+0x105/0x170 net/core/dst.c:89 ip6_dst_alloc net/ipv6/route.c:342 [inline] icmp6_dst_alloc+0x75/0x460 net/ipv6/route.c:3333 mld_sendpack+0x683/0xe60 net/ipv6/mcast.c:1844 mld_send_cr net/ipv6/mcast.c:2154 [inline] mld_ifc_work+0x83e/0xd60 net/ipv6/mcast.c:2693 process_one_work kernel/workqueue.c:3257 [inline] process_scheduled_works+0xad1/0x1770 kernel/workqueue.c:3340 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3421 kthread+0x711/0x8a0 kernel/kthread.c:463 ret_from_fork+0x510/0xa50 arch/x86/kernel/process.c:158 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entr ---truncated---
CVE-2026-23035: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Pass netdev to mlx5e_destroy_netdev instead of priv mlx5e_priv is an unstable structure that can be memset(0) if profile attaching fails. Pass netdev to mlx5e_destroy_netdev() to guarantee it will work on a valid netdev. On mlx5e_remove: Check validity of priv->profile, before attempting to cleanup any resources that might be not there. This fixes a kernel oops in mlx5e_remove when switchdev mode fails due to change profile failure. $ devlink dev eswitch set pci/0000:00:03.0 mode switchdev Error: mlx5_core: Failed setting eswitch to offloads. dmesg: workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 $ devlink dev reload pci/0000:00:03.0 ==> oops BUG: kernel NULL pointer dereference, address: 0000000000000370 PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 15 UID: 0 PID: 520 Comm: devlink Not tainted 6.18.0-rc5+ #115 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_dcbnl_dscp_app+0x23/0x100 RSP: 0018:ffffc9000083f8b8 EFLAGS: 00010286 RAX: ffff8881126fc380 RBX: ffff8881015ac400 RCX: ffffffff826ffc45 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8881035109c0 RBP: ffff8881035109c0 R08: ffff888101e3e838 R09: ffff888100264e10 R10: ffffc9000083f898 R11: ffffc9000083f8a0 R12: ffff888101b921a0 R13: ffff888101b921a0 R14: ffff8881015ac9a0 R15: ffff8881015ac400 FS: 00007f789a3c8740(0000) GS:ffff88856aa59000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000370 CR3: 000000010b6c0001 CR4: 0000000000370ef0 Call Trace: <TASK> mlx5e_remove+0x57/0x110 device_release_driver_internal+0x19c/0x200 bus_remove_device+0xc6/0x130 device_del+0x160/0x3d0 ? devl_param_driverinit_value_get+0x2d/0x90 mlx5_detach_device+0x89/0xe0 mlx5_unload_one_devl_locked+0x3a/0x70 mlx5_devlink_reload_down+0xc8/0x220 devlink_reload+0x7d/0x260 devlink_nl_reload_doit+0x45b/0x5a0 genl_family_rcv_msg_doit+0xe8/0x140
CVE-2026-23050: In the Linux kernel, the following vulnerability has been resolved: pNFS: Fix a deadlock when returning a delegation during open() Ben Coddington reports seeing a hang in the following stack trace: 0 [ffffd0b50e1774e0] __schedule at ffffffff9ca05415 1 [ffffd0b50e177548] schedule at ffffffff9ca05717 2 [ffffd0b50e177558] bit_wait at ffffffff9ca061e1 3 [ffffd0b50e177568] __wait_on_bit at ffffffff9ca05cfb 4 [ffffd0b50e1775c8] out_of_line_wait_on_bit at ffffffff9ca05ea5 5 [ffffd0b50e177618] pnfs_roc at ffffffffc154207b [nfsv4] 6 [ffffd0b50e1776b8] _nfs4_proc_delegreturn at ffffffffc1506586 [nfsv4] 7 [ffffd0b50e177788] nfs4_proc_delegreturn at ffffffffc1507480 [nfsv4] 8 [ffffd0b50e1777f8] nfs_do_return_delegation at ffffffffc1523e41 [nfsv4] 9 [ffffd0b50e177838] nfs_inode_set_delegation at ffffffffc1524a75 [nfsv4] 10 [ffffd0b50e177888] nfs4_process_delegation at ffffffffc14f41dd [nfsv4] 11 [ffffd0b50e1778a0] _nfs4_opendata_to_nfs4_state at ffffffffc1503edf [nfsv4] 12 [ffffd0b50e1778c0] _nfs4_open_and_get_state at ffffffffc1504e56 [nfsv4] 13 [ffffd0b50e177978] _nfs4_do_open at ffffffffc15051b8 [nfsv4] 14 [ffffd0b50e1779f8] nfs4_do_open at ffffffffc150559c [nfsv4] 15 [ffffd0b50e177a80] nfs4_atomic_open at ffffffffc15057fb [nfsv4] 16 [ffffd0b50e177ad0] nfs4_file_open at ffffffffc15219be [nfsv4] 17 [ffffd0b50e177b78] do_dentry_open at ffffffff9c09e6ea 18 [ffffd0b50e177ba8] vfs_open at ffffffff9c0a082e 19 [ffffd0b50e177bd0] dentry_open at ffffffff9c0a0935 The issue is that the delegreturn is being asked to wait for a layout return that cannot complete because a state recovery was initiated. The state recovery cannot complete until the open() finishes processing the delegations it was given. The solution is to propagate the existing flags that indicate a non-blocking call to the function pnfs_roc(), so that it knows not to wait in this situation.
CVE-2026-23066: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix recvmsg() unconditional requeue If rxrpc_recvmsg() fails because MSG_DONTWAIT was specified but the call at the front of the recvmsg queue already has its mutex locked, it requeues the call - whether or not the call is already queued. The call may be on the queue because MSG_PEEK was also passed and so the call was not dequeued or because the I/O thread requeued it. The unconditional requeue may then corrupt the recvmsg queue, leading to things like UAFs or refcount underruns. Fix this by only requeuing the call if it isn't already on the queue - and moving it to the front if it is already queued. If we don't queue it, we have to put the ref we obtained by dequeuing it. Also, MSG_PEEK doesn't dequeue the call so shouldn't call rxrpc_notify_socket() for the call if we didn't use up all the data on the queue, so fix that also.
CVE-2026-23088: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix crash on synthetic stacktrace field usage When creating a synthetic event based on an existing synthetic event that had a stacktrace field and the new synthetic event used that field a kernel crash occurred: ~# cd /sys/kernel/tracing ~# echo 's:stack unsigned long stack[];' > dynamic_events ~# echo 'hist:keys=prev_pid:s0=common_stacktrace if prev_state & 3' >> events/sched/sched_switch/trigger ~# echo 'hist:keys=next_pid:s1=$s0:onmatch(sched.sched_switch).trace(stack,$s1)' >> events/sched/sched_switch/trigger The above creates a synthetic event that takes a stacktrace when a task schedules out in a non-running state and passes that stacktrace to the sched_switch event when that task schedules back in. It triggers the "stack" synthetic event that has a stacktrace as its field (called "stack"). ~# echo 's:syscall_stack s64 id; unsigned long stack[];' >> dynamic_events ~# echo 'hist:keys=common_pid:s2=stack' >> events/synthetic/stack/trigger ~# echo 'hist:keys=common_pid:s3=$s2,i0=id:onmatch(synthetic.stack).trace(syscall_stack,$i0,$s3)' >> events/raw_syscalls/sys_exit/trigger The above makes another synthetic event called "syscall_stack" that attaches the first synthetic event (stack) to the sys_exit trace event and records the stacktrace from the stack event with the id of the system call that is exiting. When enabling this event (or using it in a historgram): ~# echo 1 > events/synthetic/syscall_stack/enable Produces a kernel crash! BUG: unable to handle page fault for address: 0000000000400010 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP PTI CPU: 6 UID: 0 PID: 1257 Comm: bash Not tainted 6.16.3+deb14-amd64 #1 PREEMPT(lazy) Debian 6.16.3-1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 RIP: 0010:trace_event_raw_event_synth+0x90/0x380 Code: c5 00 00 00 00 85 d2 0f 84 e1 00 00 00 31 db eb 34 0f 1f 00 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 2e 0f 1f 84 00 00 00 00 00 <49> 8b 04 24 48 83 c3 01 8d 0c c5 08 00 00 00 01 cd 41 3b 5d 40 0f RSP: 0018:ffffd2670388f958 EFLAGS: 00010202 RAX: ffff8ba1065cc100 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: fffff266ffda7b90 RDI: ffffd2670388f9b0 RBP: 0000000000000010 R08: ffff8ba104e76000 R09: ffffd2670388fa50 R10: ffff8ba102dd42e0 R11: ffffffff9a908970 R12: 0000000000400010 R13: ffff8ba10a246400 R14: ffff8ba10a710220 R15: fffff266ffda7b90 FS: 00007fa3bc63f740(0000) GS:ffff8ba2e0f48000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000400010 CR3: 0000000107f9e003 CR4: 0000000000172ef0 Call Trace: <TASK> ? __tracing_map_insert+0x208/0x3a0 action_trace+0x67/0x70 event_hist_trigger+0x633/0x6d0 event_triggers_call+0x82/0x130 trace_event_buffer_commit+0x19d/0x250 trace_event_raw_event_sys_exit+0x62/0xb0 syscall_exit_work+0x9d/0x140 do_syscall_64+0x20a/0x2f0 ? trace_event_raw_event_sched_switch+0x12b/0x170 ? save_fpregs_to_fpstate+0x3e/0x90 ? _raw_spin_unlock+0xe/0x30 ? finish_task_switch.isra.0+0x97/0x2c0 ? __rseq_handle_notify_resume+0xad/0x4c0 ? __schedule+0x4b8/0xd00 ? restore_fpregs_from_fpstate+0x3c/0x90 ? switch_fpu_return+0x5b/0xe0 ? do_syscall_64+0x1ef/0x2f0 ? do_fault+0x2e9/0x540 ? __handle_mm_fault+0x7d1/0xf70 ? count_memcg_events+0x167/0x1d0 ? handle_mm_fault+0x1d7/0x2e0 ? do_user_addr_fault+0x2c3/0x7f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e The reason is that the stacktrace field is not labeled as such, and is treated as a normal field and not as a dynamic event that it is. In trace_event_raw_event_synth() the event is field is still treated as a dynamic array, but the retrieval of the data is considered a normal field, and the reference is just the meta data: // Meta data is retrieved instead of a dynamic array ---truncated---
CVE-2026-23100: In the Linux kernel, the following vulnerability has been resolved: mm/hugetlb: fix hugetlb_pmd_shared() Patch series "mm/hugetlb: fixes for PMD table sharing (incl. using mmu_gather)", v3. One functional fix, one performance regression fix, and two related comment fixes. I cleaned up my prototype I recently shared [1] for the performance fix, deferring most of the cleanups I had in the prototype to a later point. While doing that I identified the other things. The goal of this patch set is to be backported to stable trees "fairly" easily. At least patch #1 and #4. Patch #1 fixes hugetlb_pmd_shared() not detecting any sharing Patch #2 + #3 are simple comment fixes that patch #4 interacts with. Patch #4 is a fix for the reported performance regression due to excessive IPI broadcasts during fork()+exit(). The last patch is all about TLB flushes, IPIs and mmu_gather. Read: complicated There are plenty of cleanups in the future to be had + one reasonable optimization on x86. But that's all out of scope for this series. Runtime tested, with a focus on fixing the performance regression using the original reproducer [2] on x86. This patch (of 4): We switched from (wrongly) using the page count to an independent shared count. Now, shared page tables have a refcount of 1 (excluding speculative references) and instead use ptdesc->pt_share_count to identify sharing. We didn't convert hugetlb_pmd_shared(), so right now, we would never detect a shared PMD table as such, because sharing/unsharing no longer touches the refcount of a PMD table. Page migration, like mbind() or migrate_pages() would allow for migrating folios mapped into such shared PMD tables, even though the folios are not exclusive. In smaps we would account them as "private" although they are "shared", and we would be wrongly setting the PM_MMAP_EXCLUSIVE in the pagemap interface. Fix it by properly using ptdesc_pmd_is_shared() in hugetlb_pmd_shared().
CVE-2026-23113: In the Linux kernel, the following vulnerability has been resolved: io_uring/io-wq: check IO_WQ_BIT_EXIT inside work run loop Currently this is checked before running the pending work. Normally this is quite fine, as work items either end up blocking (which will create a new worker for other items), or they complete fairly quickly. But syzbot reports an issue where io-wq takes seemingly forever to exit, and with a bit of debugging, this turns out to be because it queues a bunch of big (2GB - 4096b) reads with a /dev/msr* file. Since this file type doesn't support ->read_iter(), loop_rw_iter() ends up handling them. Each read returns 16MB of data read, which takes 20 (!!) seconds. With a bunch of these pending, processing the whole chain can take a long time. Easily longer than the syzbot uninterruptible sleep timeout of 140 seconds. This then triggers a complaint off the io-wq exit path: INFO: task syz.4.135:6326 blocked for more than 143 seconds. Not tainted syzkaller #0 Blocked by coredump. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz.4.135 state:D stack:26824 pid:6326 tgid:6324 ppid:5957 task_flags:0x400548 flags:0x00080000 Call Trace: <TASK> context_switch kernel/sched/core.c:5256 [inline] __schedule+0x1139/0x6150 kernel/sched/core.c:6863 __schedule_loop kernel/sched/core.c:6945 [inline] schedule+0xe7/0x3a0 kernel/sched/core.c:6960 schedule_timeout+0x257/0x290 kernel/time/sleep_timeout.c:75 do_wait_for_common kernel/sched/completion.c:100 [inline] __wait_for_common+0x2fc/0x4e0 kernel/sched/completion.c:121 io_wq_exit_workers io_uring/io-wq.c:1328 [inline] io_wq_put_and_exit+0x271/0x8a0 io_uring/io-wq.c:1356 io_uring_clean_tctx+0x10d/0x190 io_uring/tctx.c:203 io_uring_cancel_generic+0x69c/0x9a0 io_uring/cancel.c:651 io_uring_files_cancel include/linux/io_uring.h:19 [inline] do_exit+0x2ce/0x2bd0 kernel/exit.c:911 do_group_exit+0xd3/0x2a0 kernel/exit.c:1112 get_signal+0x2671/0x26d0 kernel/signal.c:3034 arch_do_signal_or_restart+0x8f/0x7e0 arch/x86/kernel/signal.c:337 __exit_to_user_mode_loop kernel/entry/common.c:41 [inline] exit_to_user_mode_loop+0x8c/0x540 kernel/entry/common.c:75 __exit_to_user_mode_prepare include/linux/irq-entry-common.h:226 [inline] syscall_exit_to_user_mode_prepare include/linux/irq-entry-common.h:256 [inline] syscall_exit_to_user_mode_work include/linux/entry-common.h:159 [inline] syscall_exit_to_user_mode include/linux/entry-common.h:194 [inline] do_syscall_64+0x4ee/0xf80 arch/x86/entry/syscall_64.c:100 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fa02738f749 RSP: 002b:00007fa0281ae0e8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: fffffffffffffe00 RBX: 00007fa0275e6098 RCX: 00007fa02738f749 RDX: 0000000000000000 RSI: 0000000000000080 RDI: 00007fa0275e6098 RBP: 00007fa0275e6090 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fa0275e6128 R14: 00007fff14e4fcb0 R15: 00007fff14e4fd98 There's really nothing wrong here, outside of processing these reads will take a LONG time. However, we can speed up the exit by checking the IO_WQ_BIT_EXIT inside the io_worker_handle_work() loop, as syzbot will exit the ring after queueing up all of these reads. Then once the first item is processed, io-wq will simply cancel the rest. That should avoid syzbot running into this complaint again.
CVE-2026-23118: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix data-race warning and potential load/store tearing Fix the following: BUG: KCSAN: data-race in rxrpc_peer_keepalive_worker / rxrpc_send_data_packet which is reporting an issue with the reads and writes to ->last_tx_at in: conn->peer->last_tx_at = ktime_get_seconds(); and: keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; The lockless accesses to these to values aren't actually a problem as the read only needs an approximate time of last transmission for the purposes of deciding whether or not the transmission of a keepalive packet is warranted yet. Also, as ->last_tx_at is a 64-bit value, tearing can occur on a 32-bit arch. Fix both of these by switching to an unsigned int for ->last_tx_at and only storing the LSW of the time64_t. It can then be reconstructed at need provided no more than 68 years has elapsed since the last transmission.
CVE-2026-23137: In the Linux kernel, the following vulnerability has been resolved: of: unittest: Fix memory leak in unittest_data_add() In unittest_data_add(), if of_resolve_phandles() fails, the allocated unittest_data is not freed, leading to a memory leak. Fix this by using scope-based cleanup helper __free(kfree) for automatic resource cleanup. This ensures unittest_data is automatically freed when it goes out of scope in error paths. For the success path, use retain_and_null_ptr() to transfer ownership of the memory to the device tree and prevent double freeing.
CVE-2026-23138: In the Linux kernel, the following vulnerability has been resolved: tracing: Add recursion protection in kernel stack trace recording A bug was reported about an infinite recursion caused by tracing the rcu events with the kernel stack trace trigger enabled. The stack trace code called back into RCU which then called the stack trace again. Expand the ftrace recursion protection to add a set of bits to protect events from recursion. Each bit represents the context that the event is in (normal, softirq, interrupt and NMI). Have the stack trace code use the interrupt context to protect against recursion. Note, the bug showed an issue in both the RCU code as well as the tracing stacktrace code. This only handles the tracing stack trace side of the bug. The RCU fix will be handled separately.
CVE-2026-23141: In the Linux kernel, the following vulnerability has been resolved: btrfs: send: check for inline extents in range_is_hole_in_parent() Before accessing the disk_bytenr field of a file extent item we need to check if we are dealing with an inline extent. This is because for inline extents their data starts at the offset of the disk_bytenr field. So accessing the disk_bytenr means we are accessing inline data or in case the inline data is less than 8 bytes we can actually cause an invalid memory access if this inline extent item is the first item in the leaf or access metadata from other items.
CVE-2026-23154: In the Linux kernel, the following vulnerability has been resolved: net: fix segmentation of forwarding fraglist GRO This patch enhances GSO segment handling by properly checking the SKB_GSO_DODGY flag for frag_list GSO packets, addressing low throughput issues observed when a station accesses IPv4 servers via hotspots with an IPv6-only upstream interface. Specifically, it fixes a bug in GSO segmentation when forwarding GRO packets containing a frag_list. The function skb_segment_list cannot correctly process GRO skbs that have been converted by XLAT, since XLAT only translates the header of the head skb. Consequently, skbs in the frag_list may remain untranslated, resulting in protocol inconsistencies and reduced throughput. To address this, the patch explicitly sets the SKB_GSO_DODGY flag for GSO packets in XLAT's IPv4/IPv6 protocol translation helpers (bpf_skb_proto_4_to_6 and bpf_skb_proto_6_to_4). This marks GSO packets as potentially modified after protocol translation. As a result, GSO segmentation will avoid using skb_segment_list and instead falls back to skb_segment for packets with the SKB_GSO_DODGY flag. This ensures that only safe and fully translated frag_list packets are processed by skb_segment_list, resolving protocol inconsistencies and improving throughput when forwarding GRO packets converted by XLAT.
CVE-2026-23157: In the Linux kernel, the following vulnerability has been resolved: btrfs: do not strictly require dirty metadata threshold for metadata writepages [BUG] There is an internal report that over 1000 processes are waiting at the io_schedule_timeout() of balance_dirty_pages(), causing a system hang and trigger a kernel coredump. The kernel is v6.4 kernel based, but the root problem still applies to any upstream kernel before v6.18. [CAUSE] From Jan Kara for his wisdom on the dirty page balance behavior first. This cgroup dirty limit was what was actually playing the role here because the cgroup had only a small amount of memory and so the dirty limit for it was something like 16MB. Dirty throttling is responsible for enforcing that nobody can dirty (significantly) more dirty memory than there's dirty limit. Thus when a task is dirtying pages it periodically enters into balance_dirty_pages() and we let it sleep there to slow down the dirtying. When the system is over dirty limit already (either globally or within a cgroup of the running task), we will not let the task exit from balance_dirty_pages() until the number of dirty pages drops below the limit. So in this particular case, as I already mentioned, there was a cgroup with relatively small amount of memory and as a result with dirty limit set at 16MB. A task from that cgroup has dirtied about 28MB worth of pages in btrfs btree inode and these were practically the only dirty pages in that cgroup. So that means the only way to reduce the dirty pages of that cgroup is to writeback the dirty pages of btrfs btree inode, and only after that those processes can exit balance_dirty_pages(). Now back to the btrfs part, btree_writepages() is responsible for writing back dirty btree inode pages. The problem here is, there is a btrfs internal threshold that if the btree inode's dirty bytes are below the 32M threshold, it will not do any writeback. This behavior is to batch as much metadata as possible so we won't write back those tree blocks and then later re-COW them again for another modification. This internal 32MiB is higher than the existing dirty page size (28MiB), meaning no writeback will happen, causing a deadlock between btrfs and cgroup: - Btrfs doesn't want to write back btree inode until more dirty pages - Cgroup/MM doesn't want more dirty pages for btrfs btree inode Thus any process touching that btree inode is put into sleep until the number of dirty pages is reduced. Thanks Jan Kara a lot for the analysis of the root cause. [ENHANCEMENT] Since kernel commit b55102826d7d ("btrfs: set AS_KERNEL_FILE on the btree_inode"), btrfs btree inode pages will only be charged to the root cgroup which should have a much larger limit than btrfs' 32MiB threshold. So it should not affect newer kernels. But for all current LTS kernels, they are all affected by this problem, and backporting the whole AS_KERNEL_FILE may not be a good idea. Even for newer kernels I still think it's a good idea to get rid of the internal threshold at btree_writepages(), since for most cases cgroup/MM has a better view of full system memory usage than btrfs' fixed threshold. For internal callers using btrfs_btree_balance_dirty() since that function is already doing internal threshold check, we don't need to bother them. But for external callers of btree_writepages(), just respect their requests and write back whatever they want, ignoring the internal btrfs threshold to avoid such deadlock on btree inode dirty page balancing.
CVE-2026-23171: In the Linux kernel, the following vulnerability has been resolved: bonding: fix use-after-free due to enslave fail after slave array update Fix a use-after-free which happens due to enslave failure after the new slave has been added to the array. Since the new slave can be used for Tx immediately, we can use it after it has been freed by the enslave error cleanup path which frees the allocated slave memory. Slave update array is supposed to be called last when further enslave failures are not expected. Move it after xdp setup to avoid any problems. It is very easy to reproduce the problem with a simple xdp_pass prog: ip l add bond1 type bond mode balance-xor ip l set bond1 up ip l set dev bond1 xdp object xdp_pass.o sec xdp_pass ip l add dumdum type dummy Then run in parallel: while :; do ip l set dumdum master bond1 1>/dev/null 2>&1; done; mausezahn bond1 -a own -b rand -A rand -B 1.1.1.1 -c 0 -t tcp "dp=1-1023, flags=syn" The crash happens almost immediately: [ 605.602850] Oops: general protection fault, probably for non-canonical address 0xe0e6fc2460000137: 0000 [#1] SMP KASAN NOPTI [ 605.602916] KASAN: maybe wild-memory-access in range [0x07380123000009b8-0x07380123000009bf] [ 605.602946] CPU: 0 UID: 0 PID: 2445 Comm: mausezahn Kdump: loaded Tainted: G B 6.19.0-rc6+ #21 PREEMPT(voluntary) [ 605.602979] Tainted: [B]=BAD_PAGE [ 605.602998] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 605.603032] RIP: 0010:netdev_core_pick_tx+0xcd/0x210 [ 605.603063] Code: 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 3e 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 6b 08 49 8d 7d 30 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 25 01 00 00 49 8b 45 30 4c 89 e2 48 89 ee 48 89 [ 605.603111] RSP: 0018:ffff88817b9af348 EFLAGS: 00010213 [ 605.603145] RAX: dffffc0000000000 RBX: ffff88817d28b420 RCX: 0000000000000000 [ 605.603172] RDX: 00e7002460000137 RSI: 0000000000000008 RDI: 07380123000009be [ 605.603199] RBP: ffff88817b541a00 R08: 0000000000000001 R09: fffffbfff3ed8c0c [ 605.603226] R10: ffffffff9f6c6067 R11: 0000000000000001 R12: 0000000000000000 [ 605.603253] R13: 073801230000098e R14: ffff88817d28b448 R15: ffff88817b541a84 [ 605.603286] FS: 00007f6570ef67c0(0000) GS:ffff888221dfa000(0000) knlGS:0000000000000000 [ 605.603319] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 605.603343] CR2: 00007f65712fae40 CR3: 000000011371b000 CR4: 0000000000350ef0 [ 605.603373] Call Trace: [ 605.603392] <TASK> [ 605.603410] __dev_queue_xmit+0x448/0x32a0 [ 605.603434] ? __pfx_vprintk_emit+0x10/0x10 [ 605.603461] ? __pfx_vprintk_emit+0x10/0x10 [ 605.603484] ? __pfx___dev_queue_xmit+0x10/0x10 [ 605.603507] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603546] ? _printk+0xcb/0x100 [ 605.603566] ? __pfx__printk+0x10/0x10 [ 605.603589] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603627] ? add_taint+0x5e/0x70 [ 605.603648] ? add_taint+0x2a/0x70 [ 605.603670] ? end_report.cold+0x51/0x75 [ 605.603693] ? bond_start_xmit+0xbfb/0xc20 [bonding] [ 605.603731] bond_start_xmit+0x623/0xc20 [bonding]
CVE-2026-23191: In the Linux kernel, the following vulnerability has been resolved: ALSA: aloop: Fix racy access at PCM trigger The PCM trigger callback of aloop driver tries to check the PCM state and stop the stream of the tied substream in the corresponding cable. Since both check and stop operations are performed outside the cable lock, this may result in UAF when a program attempts to trigger frequently while opening/closing the tied stream, as spotted by fuzzers. For addressing the UAF, this patch changes two things: - It covers the most of code in loopback_check_format() with cable->lock spinlock, and add the proper NULL checks. This avoids already some racy accesses. - In addition, now we try to check the state of the capture PCM stream that may be stopped in this function, which was the major pain point leading to UAF.
CVE-2026-23204: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_u32: use skb_header_pointer_careful() skb_header_pointer() does not fully validate negative @offset values. Use skb_header_pointer_careful() instead. GangMin Kim provided a report and a repro fooling u32_classify(): BUG: KASAN: slab-out-of-bounds in u32_classify+0x1180/0x11b0 net/sched/cls_u32.c:221
CVE-2026-23207: In the Linux kernel, the following vulnerability has been resolved: spi: tegra210-quad: Protect curr_xfer check in IRQ handler Now that all other accesses to curr_xfer are done under the lock, protect the curr_xfer NULL check in tegra_qspi_isr_thread() with the spinlock. Without this protection, the following race can occur: CPU0 (ISR thread) CPU1 (timeout path) ---------------- ------------------- if (!tqspi->curr_xfer) // sees non-NULL spin_lock() tqspi->curr_xfer = NULL spin_unlock() handle_*_xfer() spin_lock() t = tqspi->curr_xfer // NULL! ... t->len ... // NULL dereference! With this patch, all curr_xfer accesses are now properly synchronized. Although all accesses to curr_xfer are done under the lock, in tegra_qspi_isr_thread() it checks for NULL, releases the lock and reacquires it later in handle_cpu_based_xfer()/handle_dma_based_xfer(). There is a potential for an update in between, which could cause a NULL pointer dereference. To handle this, add a NULL check inside the handlers after acquiring the lock. This ensures that if the timeout path has already cleared curr_xfer, the handler will safely return without dereferencing the NULL pointer.
CVE-2026-23208: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Prevent excessive number of frames In this case, the user constructed the parameters with maxpacksize 40 for rate 22050 / pps 1000, and packsize[0] 22 packsize[1] 23. The buffer size for each data URB is maxpacksize * packets, which in this example is 40 * 6 = 240; When the user performs a write operation to send audio data into the ALSA PCM playback stream, the calculated number of frames is packsize[0] * packets = 264, which exceeds the allocated URB buffer size, triggering the out-of-bounds (OOB) issue reported by syzbot [1]. Added a check for the number of single data URB frames when calculating the number of frames to prevent [1]. [1] BUG: KASAN: slab-out-of-bounds in copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 Write of size 264 at addr ffff88804337e800 by task syz.0.17/5506 Call Trace: copy_to_urb+0x261/0x460 sound/usb/pcm.c:1487 prepare_playback_urb+0x953/0x13d0 sound/usb/pcm.c:1611 prepare_outbound_urb+0x377/0xc50 sound/usb/endpoint.c:333
CVE-2026-23213: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: Disable MMIO access during SMU Mode 1 reset During Mode 1 reset, the ASIC undergoes a reset cycle and becomes temporarily inaccessible via PCIe. Any attempt to access MMIO registers during this window (e.g., from interrupt handlers or other driver threads) can result in uncompleted PCIe transactions, leading to NMI panics or system hangs. To prevent this, set the `no_hw_access` flag to true immediately after triggering the reset. This signals other driver components to skip register accesses while the device is offline. A memory barrier `smp_mb()` is added to ensure the flag update is globally visible to all cores before the driver enters the sleep/wait state. (cherry picked from commit 7edb503fe4b6d67f47d8bb0dfafb8e699bb0f8a4)
CVE-2026-23214: In the Linux kernel, the following vulnerability has been resolved: btrfs: reject new transactions if the fs is fully read-only [BUG] There is a bug report where a heavily fuzzed fs is mounted with all rescue mount options, which leads to the following warnings during unmount: BTRFS: Transaction aborted (error -22) Modules linked in: CPU: 0 UID: 0 PID: 9758 Comm: repro.out Not tainted 6.19.0-rc5-00002-gb71e635feefc #7 PREEMPT(full) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:find_free_extent_update_loop fs/btrfs/extent-tree.c:4208 [inline] RIP: 0010:find_free_extent+0x52f0/0x5d20 fs/btrfs/extent-tree.c:4611 Call Trace: <TASK> btrfs_reserve_extent+0x2cd/0x790 fs/btrfs/extent-tree.c:4705 btrfs_alloc_tree_block+0x1e1/0x10e0 fs/btrfs/extent-tree.c:5157 btrfs_force_cow_block+0x578/0x2410 fs/btrfs/ctree.c:517 btrfs_cow_block+0x3c4/0xa80 fs/btrfs/ctree.c:708 btrfs_search_slot+0xcad/0x2b50 fs/btrfs/ctree.c:2130 btrfs_truncate_inode_items+0x45d/0x2350 fs/btrfs/inode-item.c:499 btrfs_evict_inode+0x923/0xe70 fs/btrfs/inode.c:5628 evict+0x5f4/0xae0 fs/inode.c:837 __dentry_kill+0x209/0x660 fs/dcache.c:670 finish_dput+0xc9/0x480 fs/dcache.c:879 shrink_dcache_for_umount+0xa0/0x170 fs/dcache.c:1661 generic_shutdown_super+0x67/0x2c0 fs/super.c:621 kill_anon_super+0x3b/0x70 fs/super.c:1289 btrfs_kill_super+0x41/0x50 fs/btrfs/super.c:2127 deactivate_locked_super+0xbc/0x130 fs/super.c:474 cleanup_mnt+0x425/0x4c0 fs/namespace.c:1318 task_work_run+0x1d4/0x260 kernel/task_work.c:233 exit_task_work include/linux/task_work.h:40 [inline] do_exit+0x694/0x22f0 kernel/exit.c:971 do_group_exit+0x21c/0x2d0 kernel/exit.c:1112 __do_sys_exit_group kernel/exit.c:1123 [inline] __se_sys_exit_group kernel/exit.c:1121 [inline] __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1121 x64_sys_call+0x2210/0x2210 arch/x86/include/generated/asm/syscalls_64.h:232 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xe8/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x44f639 Code: Unable to access opcode bytes at 0x44f60f. RSP: 002b:00007ffc15c4e088 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 RAX: ffffffffffffffda RBX: 00000000004c32f0 RCX: 000000000044f639 RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000001 RBP: 0000000000000001 R08: ffffffffffffffc0 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004c32f0 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001 </TASK> Since rescue mount options will mark the full fs read-only, there should be no new transaction triggered. But during unmount we will evict all inodes, which can trigger a new transaction, and triggers warnings on a heavily corrupted fs. [CAUSE] Btrfs allows new transaction even on a read-only fs, this is to allow log replay happen even on read-only mounts, just like what ext4/xfs do. However with rescue mount options, the fs is fully read-only and cannot be remounted read-write, thus in that case we should also reject any new transactions. [FIX] If we find the fs has rescue mount options, we should treat the fs as error, so that no new transaction can be started.
CVE-2026-23226: In the Linux kernel, the following vulnerability has been resolved: ksmbd: add chann_lock to protect ksmbd_chann_list xarray ksmbd_chann_list xarray lacks synchronization, allowing use-after-free in multi-channel sessions (between lookup_chann_list() and ksmbd_chann_del). Adds rw_semaphore chann_lock to struct ksmbd_session and protects all xa_load/xa_store/xa_erase accesses.
CVE-2026-23227: In the Linux kernel, the following vulnerability has been resolved: drm/exynos: vidi: use ctx->lock to protect struct vidi_context member variables related to memory alloc/free Exynos Virtual Display driver performs memory alloc/free operations without lock protection, which easily causes concurrency problem. For example, use-after-free can occur in race scenario like this: ``` CPU0 CPU1 CPU2 ---- ---- ---- vidi_connection_ioctl() if (vidi->connection) // true drm_edid = drm_edid_alloc(); // alloc drm_edid ... ctx->raw_edid = drm_edid; ... drm_mode_getconnector() drm_helper_probe_single_connector_modes() vidi_get_modes() if (ctx->raw_edid) // true drm_edid_dup(ctx->raw_edid); if (!drm_edid) // false ... vidi_connection_ioctl() if (vidi->connection) // false drm_edid_free(ctx->raw_edid); // free drm_edid ... drm_edid_alloc(drm_edid->edid) kmemdup(edid); // UAF!! ... ``` To prevent these vulns, at least in vidi_context, member variables related to memory alloc/free should be protected with ctx->lock.
CVE-2026-23231: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix use-after-free in nf_tables_addchain() nf_tables_addchain() publishes the chain to table->chains via list_add_tail_rcu() (in nft_chain_add()) before registering hooks. If nf_tables_register_hook() then fails, the error path calls nft_chain_del() (list_del_rcu()) followed by nf_tables_chain_destroy() with no RCU grace period in between. This creates two use-after-free conditions: 1) Control-plane: nf_tables_dump_chains() traverses table->chains under rcu_read_lock(). A concurrent dump can still be walking the chain when the error path frees it. 2) Packet path: for NFPROTO_INET, nf_register_net_hook() briefly installs the IPv4 hook before IPv6 registration fails. Packets entering nft_do_chain() via the transient IPv4 hook can still be dereferencing chain->blob_gen_X when the error path frees the chain. Add synchronize_rcu() between nft_chain_del() and the chain destroy so that all RCU readers -- both dump threads and in-flight packet evaluation -- have finished before the chain is freed.
CVE-2026-23239: In the Linux kernel, the following vulnerability has been resolved: espintcp: Fix race condition in espintcp_close() This issue was discovered during a code audit. After cancel_work_sync() is called from espintcp_close(), espintcp_tx_work() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the espintcp_tx_work() worker may dereference a freed espintcp ctx or sk. The following is a simple race scenario: cpu0 cpu1 espintcp_close() cancel_work_sync(&ctx->work); espintcp_write_space() schedule_work(&ctx->work); To prevent this race condition, cancel_work_sync() is replaced with disable_work_sync().
CVE-2026-23240: In the Linux kernel, the following vulnerability has been resolved: tls: Fix race condition in tls_sw_cancel_work_tx() This issue was discovered during a code audit. After cancel_delayed_work_sync() is called from tls_sk_proto_close(), tx_work_handler() can still be scheduled from paths such as the Delayed ACK handler or ksoftirqd. As a result, the tx_work_handler() worker may dereference a freed TLS object. The following is a simple race scenario: cpu0 cpu1 tls_sk_proto_close() tls_sw_cancel_work_tx() tls_write_space() tls_sw_write_space() if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); cancel_delayed_work_sync(&ctx->tx_work.work); schedule_delayed_work(&tx_ctx->tx_work.work, 0); To prevent this race condition, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync().
CVE-2026-23242: In the Linux kernel, the following vulnerability has been resolved: RDMA/siw: Fix potential NULL pointer dereference in header processing If siw_get_hdr() returns -EINVAL before set_rx_fpdu_context(), qp->rx_fpdu can be NULL. The error path in siw_tcp_rx_data() dereferences qp->rx_fpdu->more_ddp_segs without checking, which may lead to a NULL pointer deref. Only check more_ddp_segs when rx_fpdu is present. KASAN splat: [ 101.384271] KASAN: null-ptr-deref in range [0x00000000000000c0-0x00000000000000c7] [ 101.385869] RIP: 0010:siw_tcp_rx_data+0x13ad/0x1e50
CVE-2026-23243: In the Linux kernel, the following vulnerability has been resolved: RDMA/umad: Reject negative data_len in ib_umad_write ib_umad_write computes data_len from user-controlled count and the MAD header sizes. With a mismatched user MAD header size and RMPP header length, data_len can become negative and reach ib_create_send_mad(). This can make the padding calculation exceed the segment size and trigger an out-of-bounds memset in alloc_send_rmpp_list(). Add an explicit check to reject negative data_len before creating the send buffer. KASAN splat: [ 211.363464] BUG: KASAN: slab-out-of-bounds in ib_create_send_mad+0xa01/0x11b0 [ 211.364077] Write of size 220 at addr ffff88800c3fa1f8 by task spray_thread/102 [ 211.365867] ib_create_send_mad+0xa01/0x11b0 [ 211.365887] ib_umad_write+0x853/0x1c80
CVE-2026-23245: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_gate: snapshot parameters with RCU on replace The gate action can be replaced while the hrtimer callback or dump path is walking the schedule list. Convert the parameters to an RCU-protected snapshot and swap updates under tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits the entry list, preserve the existing schedule so the effective state is unchanged.
CVE-2026-23247: In the Linux kernel, the following vulnerability has been resolved: tcp: secure_seq: add back ports to TS offset This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets") tcp_tw_recycle went away in 2017. Zhouyan Deng reported off-path TCP source port leakage via SYN cookie side-channel that can be fixed in multiple ways. One of them is to bring back TCP ports in TS offset randomization. As a bonus, we perform a single siphash() computation to provide both an ISN and a TS offset.
CVE-2026-23253: In the Linux kernel, the following vulnerability has been resolved: media: dvb-core: fix wrong reinitialization of ringbuffer on reopen dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty. Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}. The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions. Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.
CVE-2026-23255: In the Linux kernel, the following vulnerability has been resolved: net: add proper RCU protection to /proc/net/ptype Yin Fengwei reported an RCU stall in ptype_seq_show() and provided a patch. Real issue is that ptype_seq_next() and ptype_seq_show() violate RCU rules. ptype_seq_show() runs under rcu_read_lock(), and reads pt->dev to get device name without any barrier. At the same time, concurrent writers can remove a packet_type structure (which is correctly freed after an RCU grace period) and clear pt->dev without an RCU grace period. Define ptype_iter_state to carry a dev pointer along seq_net_private: struct ptype_iter_state { struct seq_net_private p; struct net_device *dev; // added in this patch }; We need to record the device pointer in ptype_get_idx() and ptype_seq_next() so that ptype_seq_show() is safe against concurrent pt->dev changes. We also need to add full RCU protection in ptype_seq_next(). (Missing READ_ONCE() when reading list.next values) Many thanks to Dong Chenchen for providing a repro.
CVE-2026-23265: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on node footer in {read,write}_end_io -----------[ cut here ]------------ kernel BUG at fs/f2fs/data.c:358! Call Trace: <IRQ> blk_update_request+0x5eb/0xe70 block/blk-mq.c:987 blk_mq_end_request+0x3e/0x70 block/blk-mq.c:1149 blk_complete_reqs block/blk-mq.c:1224 [inline] blk_done_softirq+0x107/0x160 block/blk-mq.c:1229 handle_softirqs+0x283/0x870 kernel/softirq.c:579 __do_softirq kernel/softirq.c:613 [inline] invoke_softirq kernel/softirq.c:453 [inline] __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1050 </IRQ> In f2fs_write_end_io(), it detects there is inconsistency in between node page index (nid) and footer.nid of node page. If footer of node page is corrupted in fuzzed image, then we load corrupted node page w/ async method, e.g. f2fs_ra_node_pages() or f2fs_ra_node_page(), in where we won't do sanity check on node footer, once node page becomes dirty, we will encounter this bug after node page writeback.
CVE-2026-23270: In the Linux kernel, the following vulnerability has been resolved: net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and shared blocks As Paolo said earlier [1]: "Since the blamed commit below, classify can return TC_ACT_CONSUMED while the current skb being held by the defragmentation engine. As reported by GangMin Kim, if such packet is that may cause a UaF when the defrag engine later on tries to tuch again such packet." act_ct was never meant to be used in the egress path, however some users are attaching it to egress today [2]. Attempting to reach a middle ground, we noticed that, while most qdiscs are not handling TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we address the issue by only allowing act_ct to bind to clsact/ingress qdiscs and shared blocks. That way it's still possible to attach act_ct to egress (albeit only with clsact). [1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/ [2] https://lore.kernel.org/netdev/cc6bfb4a-4a2b-42d8-b9ce-7ef6644fb22b@ovn.org/
CVE-2026-23271: In the Linux kernel, the following vulnerability has been resolved: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race Make sure that __perf_event_overflow() runs with IRQs disabled for all possible callchains. Specifically the software events can end up running it with only preemption disabled. This opens up a race vs perf_event_exit_event() and friends that will go and free various things the overflow path expects to be present, like the BPF program.
CVE-2026-23272: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: unconditionally bump set->nelems before insertion In case that the set is full, a new element gets published then removed without waiting for the RCU grace period, while RCU reader can be walking over it already. To address this issue, add the element transaction even if set is full, but toggle the set_full flag to report -ENFILE so the abort path safely unwinds the set to its previous state. As for element updates, decrement set->nelems to restore it. A simpler fix is to call synchronize_rcu() in the error path. However, with a large batch adding elements to already maxed-out set, this could cause noticeable slowdown of such batches.
CVE-2026-23273: In the Linux kernel, the following vulnerability has been resolved: macvlan: observe an RCU grace period in macvlan_common_newlink() error path valis reported that a race condition still happens after my prior patch. macvlan_common_newlink() might have made @dev visible before detecting an error, and its caller will directly call free_netdev(dev). We must respect an RCU period, either in macvlan or the core networking stack. After adding a temporary mdelay(1000) in macvlan_forward_source_one() to open the race window, valis repro was: ip link add p1 type veth peer p2 ip link set address 00:00:00:00:00:20 dev p1 ip link set up dev p1 ip link set up dev p2 ip link add mv0 link p2 type macvlan mode source (ip link add invalid% link p2 type macvlan mode source macaddr add 00:00:00:00:00:20 &) ; sleep 0.5 ; ping -c1 -I p1 1.2.3.4 PING 1.2.3.4 (1.2.3.4): 56 data bytes RTNETLINK answers: Invalid argument BUG: KASAN: slab-use-after-free in macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) Read of size 8 at addr ffff888016bb89c0 by task e/175 CPU: 1 UID: 1000 PID: 175 Comm: e Not tainted 6.19.0-rc8+ #33 NONE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) kasan_report (mm/kasan/report.c:597) ? macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) macvlan_forward_source (drivers/net/macvlan.c:408 drivers/net/macvlan.c:444) ? tasklet_init (kernel/softirq.c:983) macvlan_handle_frame (drivers/net/macvlan.c:501) Allocated by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) __kasan_kmalloc (mm/kasan/common.c:419) __kvmalloc_node_noprof (./include/linux/kasan.h:263 mm/slub.c:5657 mm/slub.c:7140) alloc_netdev_mqs (net/core/dev.c:12012) rtnl_create_link (net/core/rtnetlink.c:3648) rtnl_newlink (net/core/rtnetlink.c:3830 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131) Freed by task 169: kasan_save_stack (mm/kasan/common.c:58) kasan_save_track (./arch/x86/include/asm/current.h:25 mm/kasan/common.c:70 mm/kasan/common.c:79) kasan_save_free_info (mm/kasan/generic.c:587) __kasan_slab_free (mm/kasan/common.c:287) kfree (mm/slub.c:6674 mm/slub.c:6882) rtnl_newlink (net/core/rtnetlink.c:3845 net/core/rtnetlink.c:3957 net/core/rtnetlink.c:4072) rtnetlink_rcv_msg (net/core/rtnetlink.c:6958) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sys_sendto (net/socket.c:727 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
CVE-2026-23274: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels IDLETIMER revision 0 rules reuse existing timers by label and always call mod_timer() on timer->timer. If the label was created first by revision 1 with XT_IDLETIMER_ALARM, the object uses alarm timer semantics and timer->timer is never initialized. Reusing that object from revision 0 causes mod_timer() on an uninitialized timer_list, triggering debugobjects warnings and possible panic when panic_on_warn=1. Fix this by rejecting revision 0 rule insertion when an existing timer with the same label is of ALARM type.
CVE-2026-23276: In the Linux kernel, the following vulnerability has been resolved: net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: <TASK> __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread </TASK>
CVE-2026-23277: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit through slave devices, but does not update skb->dev to the slave device beforehand. When a gretap tunnel is a TEQL slave, the transmit path reaches iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0 master) and later calls iptunnel_xmit_stats(dev, pkt_len). This function does: get_cpu_ptr(dev->tstats) Since teql_master_setup() does not set dev->pcpu_stat_type to NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes NULL + __per_cpu_offset[cpu], resulting in a page fault. BUG: unable to handle page fault for address: ffff8880e6659018 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 68bc067 P4D 68bc067 PUD 0 Oops: Oops: 0002 [#1] SMP KASAN PTI RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89) Call Trace: <TASK> ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) __gre_xmit (net/ipv4/ip_gre.c:478) gre_tap_xmit (net/ipv4/ip_gre.c:779) teql_master_xmit (net/sched/sch_teql.c:319) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) neigh_direct_output (net/core/neighbour.c:1660) ip_finish_output2 (net/ipv4/ip_output.c:237) __ip_finish_output.part.0 (net/ipv4/ip_output.c:315) ip_mc_output (net/ipv4/ip_output.c:369) ip_send_skb (net/ipv4/ip_output.c:1508) udp_send_skb (net/ipv4/udp.c:1195) udp_sendmsg (net/ipv4/udp.c:1485) inet_sendmsg (net/ipv4/af_inet.c:859) __sys_sendto (net/socket.c:2206) Fix this by setting skb->dev = slave before calling netdev_start_xmit(), so that tunnel xmit functions see the correct slave device with properly allocated tstats.
CVE-2026-23278: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: always walk all pending catchall elements During transaction processing we might have more than one catchall element: 1 live catchall element and 1 pending element that is coming as part of the new batch. If the map holding the catchall elements is also going away, its required to toggle all catchall elements and not just the first viable candidate. Otherwise, we get: WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables] [..] __nft_set_elem_destroy+0x106/0x380 [nf_tables] nf_tables_abort_release+0x348/0x8d0 [nf_tables] nf_tables_abort+0xcf2/0x3ac0 [nf_tables] nfnetlink_rcv_batch+0x9c9/0x20e0 [..]
CVE-2026-23279: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame() In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check: ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl; ... pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value); The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference. A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required. Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211] CR2: 0000000000000000 Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code. The bug has been present since v3.13 (released 2014-01-19).
CVE-2026-23281: In the Linux kernel, the following vulnerability has been resolved: wifi: libertas: fix use-after-free in lbs_free_adapter() The lbs_free_adapter() function uses timer_delete() (non-synchronous) for both command_timer and tx_lockup_timer before the structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete. If a timer callback is executing when lbs_free_adapter() is called, the callback will access freed memory since lbs_cfg_free() frees the containing structure immediately after lbs_free_adapter() returns. Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler) access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields, which would all be use-after-free violations. Use timer_delete_sync() instead to ensure any running timer callback has completed before returning. This bug was introduced in commit 8f641d93c38a ("libertas: detect TX lockups and reset hardware") where del_timer() was used instead of del_timer_sync() in the cleanup path. The command_timer has had the same issue since the driver was first written.
CVE-2026-23284: In the Linux kernel, the following vulnerability has been resolved: net: ethernet: mtk_eth_soc: Reset prog ptr to old_prog in case of error in mtk_xdp_setup() Reset eBPF program pointer to old_prog and do not decrease its ref-count if mtk_open routine in mtk_xdp_setup() fails.
CVE-2026-23286: In the Linux kernel, the following vulnerability has been resolved: atm: lec: fix null-ptr-deref in lec_arp_clear_vccs syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer. In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry. For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables: 1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL. 2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash. Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers. The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket. The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.
CVE-2026-23287: In the Linux kernel, the following vulnerability has been resolved: irqchip/sifive-plic: Fix frozen interrupt due to affinity setting PLIC ignores interrupt completion message for disabled interrupt, explained by the specification: The PLIC signals it has completed executing an interrupt handler by writing the interrupt ID it received from the claim to the claim/complete register. The PLIC does not check whether the completion ID is the same as the last claim ID for that target. If the completion ID does not match an interrupt source that is currently enabled for the target, the completion is silently ignored. This caused problems in the past, because an interrupt can be disabled while still being handled and plic_irq_eoi() had no effect. That was fixed by checking if the interrupt is disabled, and if so enable it, before sending the completion message. That check is done with irqd_irq_disabled(). However, that is not sufficient because the enable bit for the handling hart can be zero despite irqd_irq_disabled(d) being false. This can happen when affinity setting is changed while a hart is still handling the interrupt. This problem is easily reproducible by dumping a large file to uart (which generates lots of interrupts) and at the same time keep changing the uart interrupt's affinity setting. The uart port becomes frozen almost instantaneously. Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().
CVE-2026-23289: In the Linux kernel, the following vulnerability has been resolved: IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq() Fix a user triggerable leak on the system call failure path.
CVE-2026-23290: In the Linux kernel, the following vulnerability has been resolved: net: usb: pegasus: validate USB endpoints The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23291: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: properly drop the usb interface reference on disconnect When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.
CVE-2026-23292: In the Linux kernel, the following vulnerability has been resolved: scsi: target: Fix recursive locking in __configfs_open_file() In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace: down_read __configfs_open_file do_dentry_open vfs_open do_open path_openat do_filp_open file_open_name filp_open target_core_item_dbroot_store flush_write_buffer configfs_write_iter target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows: db_root: not a directory: /sys/kernel/config/target/dbroot indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking. Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.
CVE-2026-23293: In the Linux kernel, the following vulnerability has been resolved: net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If an IPv6 packet is injected into the interface, route_shortcircuit() is called and a NULL pointer dereference happens on neigh_lookup(). BUG: kernel NULL pointer dereference, address: 0000000000000380 Oops: Oops: 0000 [#1] SMP NOPTI [...] RIP: 0010:neigh_lookup+0x20/0x270 [...] Call Trace: <TASK> vxlan_xmit+0x638/0x1ef0 [vxlan] dev_hard_start_xmit+0x9e/0x2e0 __dev_queue_xmit+0xbee/0x14e0 packet_sendmsg+0x116f/0x1930 __sys_sendto+0x1f5/0x200 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x12f/0x1590 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fix this by adding an early check on route_shortcircuit() when protocol is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because VXLAN can be built-in even when IPv6 is built as a module.
CVE-2026-23296: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix refcount leak for tagset_refcnt This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace: [130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid" #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef
CVE-2026-23298: In the Linux kernel, the following vulnerability has been resolved: can: ucan: Fix infinite loop from zero-length messages If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one. This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.
CVE-2026-23300: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop When a standalone IPv6 nexthop object is created with a loopback device (e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies it as a reject route. This is because nexthop objects have no destination prefix (fc_dst=::), causing fib6_is_reject() to match any loopback nexthop. The reject path skips fib_nh_common_init(), leaving nhc_pcpu_rth_output unallocated. If an IPv4 route later references this nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and panics. Simplify the check in fib6_nh_init() to only match explicit reject routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback promotion heuristic in fib6_is_reject() is handled separately by ip6_route_info_create_nh(). After this change, the three cases behave as follows: 1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"): RTF_REJECT is set, enters reject path, skips fib_nh_common_init(). No behavior change. 2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. ip6_route_info_create_nh() still promotes it to reject afterward. nhc_pcpu_rth_output is allocated but unused, which is harmless. 3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"): RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. nhc_pcpu_rth_output is properly allocated, fixing the crash when IPv4 routes reference this nexthop.
CVE-2026-23302: In the Linux kernel, the following vulnerability has been resolved: net: annotate data-races around sk->sk_{data_ready,write_space} skmsg (and probably other layers) are changing these pointers while other cpus might read them concurrently. Add corresponding READ_ONCE()/WRITE_ONCE() annotations for UDP, TCP and AF_UNIX.
CVE-2026-23303: In the Linux kernel, the following vulnerability has been resolved: smb: client: Don't log plaintext credentials in cifs_set_cifscreds When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.
CVE-2026-23304: In the Linux kernel, the following vulnerability has been resolved: ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu() l3mdev_master_dev_rcu() can return NULL when the slave device is being un-slaved from a VRF. All other callers deal with this, but we lost the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu() with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address"). KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f] RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418) Call Trace: ip6_pol_route (net/ipv6/route.c:2318) fib6_rule_lookup (net/ipv6/fib6_rules.c:115) ip6_route_output_flags (net/ipv6/route.c:2607) vrf_process_v6_outbound (drivers/net/vrf.c:437) I was tempted to rework the un-slaving code to clear the flag first and insert synchronize_rcu() before we remove the upper. But looks like the explicit fallback to loopback_dev is an established pattern. And I guess avoiding the synchronize_rcu() is nice, too.
CVE-2026-23306: In the Linux kernel, the following vulnerability has been resolved: scsi: pm8001: Fix use-after-free in pm8001_queue_command() Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors pm8001_queue_command(), however it introduces a potential cause of a double free scenario when it changes the function to return -ENODEV in case of phy down/device gone state. In this path, pm8001_queue_command() updates task status and calls task_done to indicate to upper layer that the task has been handled. However, this also frees the underlying SAS task. A -ENODEV is then returned to the caller. When libsas sas_ata_qc_issue() receives this error value, it assumes the task wasn't handled/queued by LLDD and proceeds to clean up and free the task again, resulting in a double free. Since pm8001_queue_command() handles the SAS task in this case, it should return 0 to the caller indicating that the task has been handled.
CVE-2026-23307: In the Linux kernel, the following vulnerability has been resolved: can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer. When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.
CVE-2026-23310: In the Linux kernel, the following vulnerability has been resolved: bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard. For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can: 1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3). 2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded. This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering: WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)) Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode. commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set(). Note: commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.
CVE-2026-23312: In the Linux kernel, the following vulnerability has been resolved: net: usb: kaweth: validate USB endpoints The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23315: In the Linux kernel, the following vulnerability has been resolved: wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211() Check frame length before accessing the mgmt fields in mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob access. [fix check to also cover mgmt->u.action.u.addba_req.capab, correct Fixes tag]
CVE-2026-23317: In the Linux kernel, the following vulnerability has been resolved: drm/vmwgfx: Return the correct value in vmw_translate_ptr functions Before the referenced fixes these functions used a lookup function that returned a pointer. This was changed to another lookup function that returned an error code with the pointer becoming an out parameter. The error path when the lookup failed was not changed to reflect this change and the code continued to return the PTR_ERR of the now uninitialized pointer. This could cause the vmw_translate_ptr functions to return success when they actually failed causing further uninitialized and OOB accesses.
CVE-2026-23318: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: Use correct version for UAC3 header validation The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields. The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.
CVE-2026-23319: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim The root cause of this bug is that when 'bpf_link_put' reduces the refcount of 'shim_link->link.link' to zero, the resource is considered released but may still be referenced via 'tr->progs_hlist' in 'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in 'bpf_shim_tramp_link_release' is deferred. During this window, another process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'. Based on Martin KaFai Lau's suggestions, I have created a simple patch. To fix this: Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'. Only increment the refcount if it is not already zero. Testing: I verified the fix by adding a delay in 'bpf_shim_tramp_link_release' to make the bug easier to trigger: static void bpf_shim_tramp_link_release(struct bpf_link *link) { /* ... */ if (!shim_link->trampoline) return; + msleep(100); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } Before the patch, running a PoC easily reproduced the crash(almost 100%) with a call trace similar to KaiyanM's report. After the patch, the bug no longer occurs even after millions of iterations.
CVE-2026-23321: In the Linux kernel, the following vulnerability has been resolved: mptcp: pm: in-kernel: always mark signal+subflow endp as used Syzkaller managed to find a combination of actions that was generating this warning: msk->pm.local_addr_used == 0 WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961 WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961 Modules linked in: CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full) Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014 RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline] RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline] RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210 Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a RSP: 0018:ffffc90001663880 EFLAGS: 00010293 RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640 R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650 FS: 00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0 Call Trace: <TASK> genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115 genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:727 [inline] __sock_sendmsg+0xc9/0xf0 net/socket.c:742 ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592 ___sys_sendmsg+0x2de/0x320 net/socket.c:2646 __sys_sendmsg net/socket.c:2678 [inline] __do_sys_sendmsg net/socket.c:2683 [inline] __se_sys_sendmsg net/socket.c:2681 [inline] __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f66346f826d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8 R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770 </TASK> The actions that caused that seem to be: - Set the MPTCP subflows limit to 0 - Create an MPTCP endpoint with both the 'signal' and 'subflow' flags - Create a new MPTCP connection from a different address: an ADD_ADDR linked to the MPTCP endpoint will be sent ('signal' flag), but no subflows is initiated ('subflow' flag) - Remove the MPTCP endpoint ---truncated---
CVE-2026-23324: In the Linux kernel, the following vulnerability has been resolved: can: usb: etas_es58x: correctly anchor the urb in the read bulk callback When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.
CVE-2026-23327: In the Linux kernel, the following vulnerability has been resolved: cxl/mbox: validate payload size before accessing contents in cxl_payload_from_user_allowed() cxl_payload_from_user_allowed() casts and dereferences the input payload without first verifying its size. When a raw mailbox command is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG, which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer, triggering a KASAN splat: BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683 Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258 CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0xab/0xe0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xce/0x650 mm/kasan/report.c:482 kasan_report+0xce/0x100 mm/kasan/report.c:595 memcmp+0x176/0x1d0 lib/string.c:683 uuid_equal include/linux/uuid.h:73 [inline] cxl_payload_from_user_allowed drivers/cxl/core/mbox.c:345 [inline] cxl_mbox_cmd_ctor drivers/cxl/core/mbox.c:368 [inline] cxl_validate_cmd_from_user drivers/cxl/core/mbox.c:522 [inline] cxl_send_cmd+0x9c0/0xb50 drivers/cxl/core/mbox.c:643 __cxl_memdev_ioctl drivers/cxl/core/memdev.c:698 [inline] cxl_memdev_ioctl+0x14f/0x190 drivers/cxl/core/memdev.c:713 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xa8/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fdaf331ba79 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fdaf1d77038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007fdaf3585fa0 RCX: 00007fdaf331ba79 RDX: 00002000000001c0 RSI: 00000000c030ce02 RDI: 0000000000000003 RBP: 00007fdaf33749df R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fdaf3586038 R14: 00007fdaf3585fa0 R15: 00007ffced2af768 </TASK> Add 'in_size' parameter to cxl_payload_from_user_allowed() and validate the payload is large enough.
CVE-2026-23330: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: complete pending data exchange on device close In nci_close_device(), complete any pending data exchange before closing. The data exchange callback (e.g. rawsock_data_exchange_complete) holds a socket reference. NIPA occasionally hits this leak: unreferenced object 0xff1100000f435000 (size 2048): comm "nci_dev", pid 3954, jiffies 4295441245 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00 '..@............ backtrace (crc ec2b3c5): __kmalloc_noprof+0x4db/0x730 sk_prot_alloc.isra.0+0xe4/0x1d0 sk_alloc+0x36/0x760 rawsock_create+0xd1/0x540 nfc_sock_create+0x11f/0x280 __sock_create+0x22d/0x630 __sys_socket+0x115/0x1d0 __x64_sys_socket+0x72/0xd0 do_syscall_64+0x117/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53
CVE-2026-23335: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah() struct irdma_create_ah_resp { // 8 bytes, no padding __u32 ah_id; // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx) __u8 rsvd[4]; // offset 4 - NEVER SET <- LEAK }; rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata(). The reserved members of the structure were not zeroed.
CVE-2026-23336: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel rfkill_block work in wiphy_unregister() There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller: BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220 Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326 CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: events cfg80211_rfkill_block_work Call Trace: <TASK> dump_stack_lvl+0x116/0x1f0 print_report+0xcd/0x630 kasan_report+0xe0/0x110 cfg80211_shutdown_all_interfaces+0x213/0x220 cfg80211_rfkill_block_work+0x1e/0x30 process_one_work+0x9cf/0x1b70 worker_thread+0x6c8/0xf10 kthread+0x3c5/0x780 ret_from_fork+0x56d/0x700 ret_from_fork_asm+0x1a/0x30 </TASK> The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister(). Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
CVE-2026-23339: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: free skb on nci_transceive early error paths nci_transceive() takes ownership of the skb passed by the caller, but the -EPROTO, -EINVAL, and -EBUSY error paths return without freeing it. Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes the nci/nci_dev selftest hits the error path occasionally in NIPA, and kmemleak detects leaks: unreferenced object 0xff11000015ce6a40 (size 640): comm "nci_dev", pid 3954, jiffies 4295441246 hex dump (first 32 bytes): 6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b kkkk.......kkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk backtrace (crc 7c40cc2a): kmem_cache_alloc_node_noprof+0x492/0x630 __alloc_skb+0x11e/0x5f0 alloc_skb_with_frags+0xc6/0x8f0 sock_alloc_send_pskb+0x326/0x3f0 nfc_alloc_send_skb+0x94/0x1d0 rawsock_sendmsg+0x162/0x4c0 do_syscall_64+0x117/0xfc0
CVE-2026-23340: In the Linux kernel, the following vulnerability has been resolved: net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs When shrinking the number of real tx queues, netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush qdiscs for queues which will no longer be used. qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with qdisc_lock(). However, for lockless qdiscs, the dequeue path is serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so qdisc_reset() can run concurrently with __qdisc_run() and free skbs while they are still being dequeued, leading to UAF. This can easily be reproduced on e.g. virtio-net by imposing heavy traffic while frequently changing the number of queue pairs: iperf3 -ub0 -c $peer -t 0 & while :; do ethtool -L eth0 combined 1 ethtool -L eth0 combined 2 done With KASAN enabled, this leads to reports like: BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760 ... Call Trace: <TASK> ... __qdisc_run+0x133f/0x1760 __dev_queue_xmit+0x248f/0x3550 ip_finish_output2+0xa42/0x2110 ip_output+0x1a7/0x410 ip_send_skb+0x2e6/0x480 udp_send_skb+0xb0a/0x1590 udp_sendmsg+0x13c9/0x1fc0 ... </TASK> Allocated by task 1270 on cpu 5 at 44.558414s: ... alloc_skb_with_frags+0x84/0x7c0 sock_alloc_send_pskb+0x69a/0x830 __ip_append_data+0x1b86/0x48c0 ip_make_skb+0x1e8/0x2b0 udp_sendmsg+0x13a6/0x1fc0 ... Freed by task 1306 on cpu 3 at 44.558445s: ... kmem_cache_free+0x117/0x5e0 pfifo_fast_reset+0x14d/0x580 qdisc_reset+0x9e/0x5f0 netif_set_real_num_tx_queues+0x303/0x840 virtnet_set_channels+0x1bf/0x260 [virtio_net] ethnl_set_channels+0x684/0xae0 ethnl_default_set_doit+0x31a/0x890 ... Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the serialization model already used by dev_reset_queue(). Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state reflects an empty queue, avoiding needless re-scheduling.
CVE-2026-23343: In the Linux kernel, the following vulnerability has been resolved: xdp: produce a warning when calculated tailroom is negative Many ethernet drivers report xdp Rx queue frag size as being the same as DMA write size. However, the only user of this field, namely bpf_xdp_frags_increase_tail(), clearly expects a truesize. Such difference leads to unspecific memory corruption issues under certain circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses all DMA-writable space in 2 buffers. This would be fine, if only rxq->frag_size was properly set to 4K, but value of 3K results in a negative tailroom, because there is a non-zero page offset. We are supposed to return -EINVAL and be done with it in such case, but due to tailroom being stored as an unsigned int, it is reported to be somewhere near UINT_MAX, resulting in a tail being grown, even if the requested offset is too much (it is around 2K in the abovementioned test). This later leads to all kinds of unspecific calltraces. [ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6 [ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4 [ 7340.338179] in libc.so.6[61c9d,7f4161aaf000+160000] [ 7340.339230] in xskxceiver[42b5,400000+69000] [ 7340.340300] likely on CPU 6 (core 0, socket 6) [ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe [ 7340.340888] likely on CPU 3 (core 0, socket 3) [ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7 [ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI [ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy) [ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014 [ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80 [ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89 [ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202 [ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010 [ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff [ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0 [ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0 [ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500 [ 7340.418229] FS: 0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000 [ 7340.419489] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0 [ 7340.421237] PKRU: 55555554 [ 7340.421623] Call Trace: [ 7340.421987] <TASK> [ 7340.422309] ? softleaf_from_pte+0x77/0xa0 [ 7340.422855] swap_pte_batch+0xa7/0x290 [ 7340.423363] zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270 [ 7340.424102] zap_pte_range+0x281/0x580 [ 7340.424607] zap_pmd_range.isra.0+0xc9/0x240 [ 7340.425177] unmap_page_range+0x24d/0x420 [ 7340.425714] unmap_vmas+0xa1/0x180 [ 7340.426185] exit_mmap+0xe1/0x3b0 [ 7340.426644] __mmput+0x41/0x150 [ 7340.427098] exit_mm+0xb1/0x110 [ 7340.427539] do_exit+0x1b2/0x460 [ 7340.427992] do_group_exit+0x2d/0xc0 [ 7340.428477] get_signal+0x79d/0x7e0 [ 7340.428957] arch_do_signal_or_restart+0x34/0x100 [ 7340.429571] exit_to_user_mode_loop+0x8e/0x4c0 [ 7340.430159] do_syscall_64+0x188/ ---truncated---
CVE-2026-23346: In the Linux kernel, the following vulnerability has been resolved: arm64: io: Extract user memory type in ioremap_prot() The only caller of ioremap_prot() outside of the generic ioremap() implementation is generic_access_phys(), which passes a 'pgprot_t' value determined from the user mapping of the target 'pfn' being accessed by the kernel. On arm64, the 'pgprot_t' contains all of the non-address bits from the pte, including the permission controls, and so we end up returning a new user mapping from ioremap_prot() which faults when accessed from the kernel on systems with PAN: | Unable to handle kernel read from unreadable memory at virtual address ffff80008ea89000 | ... | Call trace: | __memcpy_fromio+0x80/0xf8 | generic_access_phys+0x20c/0x2b8 | __access_remote_vm+0x46c/0x5b8 | access_remote_vm+0x18/0x30 | environ_read+0x238/0x3e8 | vfs_read+0xe4/0x2b0 | ksys_read+0xcc/0x178 | __arm64_sys_read+0x4c/0x68 Extract only the memory type from the user 'pgprot_t' in ioremap_prot() and assert that we're being passed a user mapping, to protect us against any changes in future that may require additional handling. To avoid falsely flagging users of ioremap(), provide our own ioremap() macro which simply wraps __ioremap_prot().
CVE-2026-23348: In the Linux kernel, the following vulnerability has been resolved: cxl: Fix race of nvdimm_bus object when creating nvdimm objects Found issue during running of cxl-translate.sh unit test. Adding a 3s sleep right before the test seems to make the issue reproduce fairly consistently. The cxl_translate module has dependency on cxl_acpi and causes orphaned nvdimm objects to reprobe after cxl_acpi is removed. The nvdimm_bus object is registered by the cxl_nvb object when cxl_acpi_probe() is called. With the nvdimm_bus object missing, __nd_device_register() will trigger NULL pointer dereference when accessing the dev->parent that points to &nvdimm_bus->dev. [ 192.884510] BUG: kernel NULL pointer dereference, address: 000000000000006c [ 192.895383] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20250812-19.fc42 08/12/2025 [ 192.897721] Workqueue: cxl_port cxl_bus_rescan_queue [cxl_core] [ 192.899459] RIP: 0010:kobject_get+0xc/0x90 [ 192.924871] Call Trace: [ 192.925959] <TASK> [ 192.926976] ? pm_runtime_init+0xb9/0xe0 [ 192.929712] __nd_device_register.part.0+0x4d/0xc0 [libnvdimm] [ 192.933314] __nvdimm_create+0x206/0x290 [libnvdimm] [ 192.936662] cxl_nvdimm_probe+0x119/0x1d0 [cxl_pmem] [ 192.940245] cxl_bus_probe+0x1a/0x60 [cxl_core] [ 192.943349] really_probe+0xde/0x380 This patch also relies on the previous change where devm_cxl_add_nvdimm_bridge() is called from drivers/cxl/pmem.c instead of drivers/cxl/core.c to ensure the dependency of cxl_acpi on cxl_pmem. 1. Set probe_type of cxl_nvb to PROBE_FORCE_SYNCHRONOUS to ensure the driver is probed synchronously when add_device() is called. 2. Add a check in __devm_cxl_add_nvdimm_bridge() to ensure that the cxl_nvb driver is attached during cxl_acpi_probe(). 3. Take the cxl_root uport_dev lock and the cxl_nvb->dev lock in devm_cxl_add_nvdimm() before checking nvdimm_bus is valid. 4. Set cxl_nvdimm flag to CXL_NVD_F_INVALIDATED so cxl_nvdimm_probe() will exit with -EBUSY. The removal of cxl_nvdimm devices should prevent any orphaned devices from probing once the nvdimm_bus is gone. [ dj: Fixed 0-day reported kdoc issue. ] [ dj: Fix cxl_nvb reference leak on error. Gregory (kreview-0811365) ]
CVE-2026-23351: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_set_pipapo: split gc into unlink and reclaim phase Yiming Qian reports Use-after-free in the pipapo set type: Under a large number of expired elements, commit-time GC can run for a very long time in a non-preemptible context, triggering soft lockup warnings and RCU stall reports (local denial of service). We must split GC in an unlink and a reclaim phase. We cannot queue elements for freeing until pointers have been swapped. Expired elements are still exposed to both the packet path and userspace dumpers via the live copy of the data structure. call_rcu() does not protect us: dump operations or element lookups starting after call_rcu has fired can still observe the free'd element, unless the commit phase has made enough progress to swap the clone and live pointers before any new reader has picked up the old version. This a similar approach as done recently for the rbtree backend in commit 35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").
CVE-2026-23352: In the Linux kernel, the following vulnerability has been resolved: x86/efi: defer freeing of boot services memory efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late(). There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area(). More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete. Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM. If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages. Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map. Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency. More robust approach is to only defer freeing of the EFI boot services memory. Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.
CVE-2026-23356: In the Linux kernel, the following vulnerability has been resolved: drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock() Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing. If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error. The rest of the code now assumed that this request has references for the relevant activity log extents. The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case. Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put(). Fix: Do not crash the kernel for a condition that is harmless during normal operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n". And do not try to be smart and "guess" whether something will work, then be surprised when it does not. Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock(). A latter call for the same request will then resume from where we left off.
CVE-2026-23357: In the Linux kernel, the following vulnerability has been resolved: can: mcp251x: fix deadlock in error path of mcp251x_open The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish. This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can: mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path. To solve this issue move the call to free_irq() after the lock is released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ handler will exit right away once it acquired the lock.
CVE-2026-23359: In the Linux kernel, the following vulnerability has been resolved: bpf: Fix stack-out-of-bounds write in devmap get_upper_ifindexes() iterates over all upper devices and writes their indices into an array without checking bounds. Also the callers assume that the max number of upper devices is MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack, but that assumption is not correct and the number of upper devices could be larger than MAX_NEST_DEV (e.g., many macvlans), causing a stack-out-of-bounds write. Add a max parameter to get_upper_ifindexes() to avoid the issue. When there are too many upper devices, return -EOVERFLOW and abort the redirect. To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS. Then send a packet to the device to trigger the XDP redirect path.
CVE-2026-23361: In the Linux kernel, the following vulnerability has been resolved: PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X interrupt to the host using a writel(), which generates a PCI posted write transaction. There's no completion for posted writes, so the writel() may return before the PCI write completes. dw_pcie_ep_raise_msix_irq() also unmaps the outbound ATU entry used for the PCI write, so the write races with the unmap. If the PCI write loses the race with the ATU unmap, the write may corrupt host memory or cause IOMMU errors, e.g., these when running fio with a larger queue depth against nvmet-pci-epf: arm-smmu-v3 fc900000.iommu: 0x0000010000000010 arm-smmu-v3 fc900000.iommu: 0x0000020000000000 arm-smmu-v3 fc900000.iommu: 0x000000090000f040 arm-smmu-v3 fc900000.iommu: 0x0000000000000000 arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0 arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0 Flush the write by performing a readl() of the same address to ensure that the write has reached the destination before the ATU entry is unmapped. The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there it was solved by dedicating an outbound iATU only for MSI. We can't do the same for MSI-X because each vector can have a different msg_addr and the msg_addr may be changed while the vector is masked. [bhelgaas: commit log]
CVE-2026-23362: In the Linux kernel, the following vulnerability has been resolved: can: bcm: fix locking for bcm_op runtime updates Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup(). Usually the RX_SETUP only handles and filters incoming traffic with one exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.
CVE-2026-23364: In the Linux kernel, the following vulnerability has been resolved: ksmbd: Compare MACs in constant time To prevent timing attacks, MAC comparisons need to be constant-time. Replace the memcmp() with the correct function, crypto_memneq().
CVE-2026-23365: In the Linux kernel, the following vulnerability has been resolved: net: usb: kalmia: validate USB endpoints The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
CVE-2026-23367: In the Linux kernel, the following vulnerability has been resolved: wifi: radiotap: reject radiotap with unknown bits The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value. Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.
CVE-2026-23368: In the Linux kernel, the following vulnerability has been resolved: net: phy: register phy led_triggers during probe to avoid AB-BA deadlock There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and LED_TRIGGER_PHY are enabled: [ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock); [ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234 [ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c [ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c [ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0 [ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0 [ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c [ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78 [ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654 <-- Hold lock "rtnl_mutex" by calling rtnl_lock(); [ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0 [ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c [ 1362.104022] [<80014504>] syscall_common+0x34/0x58 Here LED_TRIGGER_PHY is registering LED triggers during phy_attach while holding RTNL and then taking triggers_list_lock. [ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168 <-- Trying to get lock "rtnl_mutex" via rtnl_lock(); [ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4 [ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock); [ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c [ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc [ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c [ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4 [ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c [ 1362.232164] [<80014504>] syscall_common+0x34/0x58 Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes triggers_list_lock and then RTNL. A classical AB-BA deadlock. phy_led_triggers_registers() does not require the RTNL, it does not make any calls into the network stack which require protection. There is also no requirement the PHY has been attached to a MAC, the triggers only make use of phydev state. This allows the call to phy_led_triggers_registers() to be placed elsewhere. PHY probe() and release() don't hold RTNL, so solving the AB-BA deadlock.
CVE-2026-23370: In the Linux kernel, the following vulnerability has been resolved: platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data set_new_password() hex dumps the entire buffer, which contains plaintext password data, including current and new passwords. Remove the hex dump to avoid leaking credentials.
CVE-2026-23371: In the Linux kernel, the following vulnerability has been resolved: sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting Running stress-ng --schedpolicy 0 on an RT kernel on a big machine might lead to the following WARNINGs (edited). sched: DL de-boosted task PID 22725: REPLENISH flag missing WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8 ... (running_bw underflow) Call trace: dequeue_task_dl+0x15c/0x1f8 (P) dequeue_task+0x80/0x168 deactivate_task+0x24/0x50 push_dl_task+0x264/0x2e0 dl_task_timer+0x1b0/0x228 __hrtimer_run_queues+0x188/0x378 hrtimer_interrupt+0xfc/0x260 ... The problem is that when a SCHED_DEADLINE task (lock holder) is changed to a lower priority class via sched_setscheduler(), it may fail to properly inherit the parameters of potential DEADLINE donors if it didn't already inherit them in the past (shorter deadline than donor's at that time). This might lead to bandwidth accounting corruption, as enqueue_task_dl() won't recognize the lock holder as boosted. The scenario occurs when: 1. A DEADLINE task (donor) blocks on a PI mutex held by another DEADLINE task (holder), but the holder doesn't inherit parameters (e.g., it already has a shorter deadline) 2. sched_setscheduler() changes the holder from DEADLINE to a lower class while still holding the mutex 3. The holder should now inherit DEADLINE parameters from the donor and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen Fix the issue by introducing __setscheduler_dl_pi(), which detects when a DEADLINE (proper or boosted) task gets setscheduled to a lower priority class. In case, the function makes the task inherit DEADLINE parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to ensure proper bandwidth accounting during the next enqueue operation.
CVE-2026-23372: In the Linux kernel, the following vulnerability has been resolved: nfc: rawsock: cancel tx_work before socket teardown In rawsock_release(), cancel any pending tx_work and purge the write queue before orphaning the socket. rawsock_tx_work runs on the system workqueue and calls nfc_data_exchange which dereferences the NCI device. Without synchronization, tx_work can race with socket and device teardown when a process is killed (e.g. by SIGKILL), leading to use-after-free or leaked references. Set SEND_SHUTDOWN first so that if tx_work is already running it will see the flag and skip transmitting, then use cancel_work_sync to wait for any in-progress execution to finish, and finally purge any remaining queued skbs.
CVE-2026-23374: In the Linux kernel, the following vulnerability has been resolved: blktrace: fix __this_cpu_read/write in preemptible context tracing_record_cmdline() internally uses __this_cpu_read() and __this_cpu_write() on the per-CPU variable trace_cmdline_save, and trace_save_cmdline() explicitly asserts preemption is disabled via lockdep_assert_preemption_disabled(). These operations are only safe when preemption is off, as they were designed to be called from the scheduler context (probe_wakeup_sched_switch() / probe_wakeup()). __blk_add_trace() was calling tracing_record_cmdline(current) early in the blk_tracer path, before ring buffer reservation, from process context where preemption is fully enabled. This triggers the following using blktests/blktrace/002: blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed] runtime 0.367s ... 0.437s something found in dmesg: [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 ... (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message) [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] <TASK> [ 81.362886] dump_stack_lvl+0x8d/0xb0 [ 81.362895] check_preemption_disabled+0xce/0xe0 [ 81.362902] tracing_record_cmdline+0x10/0x40 [ 81.362923] __blk_add_trace+0x307/0x5d0 [ 81.362934] ? lock_acquire+0xe0/0x300 [ 81.362940] ? iov_iter_extract_pages+0x101/0xa30 [ 81.362959] blk_add_trace_bio+0x106/0x1e0 [ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0 [ 81.362979] ? lockdep_init_map_type+0x58/0x260 [ 81.362988] submit_bio_wait+0x56/0x90 [ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250 [ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10 [ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0 [ 81.363051] blkdev_read_iter+0xc1/0x140 [ 81.363059] vfs_read+0x20b/0x330 [ 81.363083] ksys_read+0x67/0xe0 [ 81.363090] do_syscall_64+0xbf/0xf00 [ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 81.363106] RIP: 0033:0x7f281906029d [ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec [ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d [ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000 [ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000 [ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000 [ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a [ 81.363142] </TASK> The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(), and blk_add_trace_rq() paths as well. The purpose of tracin ---truncated---
CVE-2026-23378: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_ife: Fix metalist update behavior Whenever an ife action replace changes the metalist, instead of replacing the old data on the metalist, the current ife code is appending the new metadata. Aside from being innapropriate behavior, this may lead to an unbounded addition of metadata to the metalist which might cause an out of bounds error when running the encode op: [ 138.423369][ C1] ================================================================== [ 138.424317][ C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.424906][ C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255 [ 138.425778][ C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full) [ 138.425795][ C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 138.425800][ C1] Call Trace: [ 138.425804][ C1] <IRQ> [ 138.425808][ C1] dump_stack_lvl (lib/dump_stack.c:122) [ 138.425828][ C1] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 138.425839][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425844][ C1] ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1)) [ 138.425853][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425859][ C1] kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597) [ 138.425868][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425878][ C1] kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1)) [ 138.425884][ C1] __asan_memset (mm/kasan/shadow.c:84 (discriminator 2)) [ 138.425889][ C1] ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425893][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:171) [ 138.425898][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425903][ C1] ife_encode_meta_u16 (net/sched/act_ife.c:57) [ 138.425910][ C1] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114) [ 138.425916][ C1] ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3)) [ 138.425921][ C1] ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45) [ 138.425927][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425931][ C1] tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879) To solve this issue, fix the replace behavior by adding the metalist to the ife rcu data structure.
CVE-2026-23379: In the Linux kernel, the following vulnerability has been resolved: net/sched: ets: fix divide by zero in the offload path Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat: Oops: divide error: 0000 [#1] SMP PTI CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full) Tainted: [E]=UNSIGNED_MODULE Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Call Trace: <TASK> ets_qdisc_change+0x870/0xf40 [sch_ets] qdisc_create+0x12b/0x540 tc_modify_qdisc+0x6d7/0xbd0 rtnetlink_rcv_msg+0x168/0x6b0 netlink_rcv_skb+0x5c/0x110 netlink_unicast+0x1d6/0x2b0 netlink_sendmsg+0x22e/0x470 ____sys_sendmsg+0x38a/0x3c0 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x111/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f440b81c77e Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980 </TASK> Modules linked in: sch_ets(E) netdevsim(E) ---[ end trace 0000000000000000 ]--- RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- Fix this using 64-bit integers for 'q_sum' and 'q_psum'.
CVE-2026-23381: In the Linux kernel, the following vulnerability has been resolved: net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. Then, if neigh_suppress is enabled and an ICMPv6 Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will dereference ipv6_stub->nd_tbl which is NULL, passing it to neigh_lookup(). This causes a kernel NULL pointer dereference. BUG: kernel NULL pointer dereference, address: 0000000000000268 Oops: 0000 [#1] PREEMPT SMP NOPTI [...] RIP: 0010:neigh_lookup+0x16/0xe0 [...] Call Trace: <IRQ> ? neigh_lookup+0x16/0xe0 br_do_suppress_nd+0x160/0x290 [bridge] br_handle_frame_finish+0x500/0x620 [bridge] br_handle_frame+0x353/0x440 [bridge] __netif_receive_skb_core.constprop.0+0x298/0x1110 __netif_receive_skb_one_core+0x3d/0xa0 process_backlog+0xa0/0x140 __napi_poll+0x2c/0x170 net_rx_action+0x2c4/0x3a0 handle_softirqs+0xd0/0x270 do_softirq+0x3f/0x60 Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in the callers. This is in essence disabling NS/NA suppression when IPv6 is disabled.
CVE-2026-23382: In the Linux kernel, the following vulnerability has been resolved: HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system. Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.
CVE-2026-23383: In the Linux kernel, the following vulnerability has been resolved: bpf, arm64: Force 8-byte alignment for JIT buffer to prevent atomic tearing struct bpf_plt contains a u64 target field. Currently, the BPF JIT allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT buffer. Because the base address of the JIT buffer can be 4-byte aligned (e.g., ending in 0x4 or 0xc), the relative padding logic in build_plt() fails to ensure that target lands on an 8-byte boundary. This leads to two issues: 1. UBSAN reports misaligned-access warnings when dereferencing the structure. 2. More critically, target is updated concurrently via WRITE_ONCE() in bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64, 64-bit loads/stores are only guaranteed to be single-copy atomic if they are 64-bit aligned. A misaligned target risks a torn read, causing the JIT to jump to a corrupted address. Fix this by increasing the allocation alignment requirement to 8 bytes (sizeof(u64)) in bpf_jit_binary_pack_alloc(). This anchors the base of the JIT buffer to an 8-byte boundary, allowing the relative padding math in build_plt() to correctly align the target field.
CVE-2026-23388: In the Linux kernel, the following vulnerability has been resolved: Squashfs: check metadata block offset is within range Syzkaller reports a "general protection fault in squashfs_copy_data" This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset. This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access. The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.
CVE-2026-23389: In the Linux kernel, the following vulnerability has been resolved: ice: Fix memory leak in ice_set_ringparam() In ice_set_ringparam, tx_rings and xdp_rings are allocated before rx_rings. If the allocation of rx_rings fails, the code jumps to the done label leaking both tx_rings and xdp_rings. Furthermore, if the setup of an individual Rx ring fails during the loop, the code jumps to the free_tx label which releases tx_rings but leaks xdp_rings. Fix this by introducing a free_xdp label and updating the error paths to ensure both xdp_rings and tx_rings are properly freed if rx_rings allocation or setup fails. Compile tested only. Issue found using a prototype static analysis tool and code review.
CVE-2026-23391: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_CT: drop pending enqueued packets on template removal Templates refer to objects that can go away while packets are sitting in nfqueue refer to: - helper, this can be an issue on module removal. - timeout policy, nfnetlink_cttimeout might remove it. The use of templates with zone and event cache filter are safe, since this just copies values. Flush these enqueued packets in case the template rule gets removed.
CVE-2026-23392: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: release flowtable after rcu grace period on error Call synchronize_rcu() after unregistering the hooks from error path, since a hook that already refers to this flowtable can be already registered, exposing this flowtable to packet path and nfnetlink_hook control plane. This error path is rare, it should only happen by reaching the maximum number hooks or by failing to set up to hardware offload, just call synchronize_rcu(). There is a check for already used device hooks by different flowtable that could result in EEXIST at this late stage. The hook parser can be updated to perform this check earlier to this error path really becomes rarely exercised. Uncovered by KASAN reported as use-after-free from nfnetlink_hook path when dumping hooks.
CVE-2026-23393: In the Linux kernel, the following vulnerability has been resolved: bridge: cfm: Fix race condition in peer_mep deletion When a peer MEP is being deleted, cancel_delayed_work_sync() is called on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in softirq context under rcu_read_lock (without RTNL) and can re-schedule ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync() returning and kfree_rcu() being called. The following is a simple race scenario: cpu0 cpu1 mep_delete_implementation() cancel_delayed_work_sync(ccm_rx_dwork); br_cfm_frame_rx() // peer_mep still in hlist if (peer_mep->ccm_defect) ccm_rx_timer_start() queue_delayed_work(ccm_rx_dwork) hlist_del_rcu(&peer_mep->head); kfree_rcu(peer_mep, rcu); ccm_rx_work_expired() // on freed peer_mep To prevent this, cancel_delayed_work_sync() is replaced with disable_delayed_work_sync() in both peer MEP deletion paths, so that subsequent queue_delayed_work() calls from br_cfm_frame_rx() are silently rejected. The cc_peer_disable() helper retains cancel_delayed_work_sync() because it is also used for the CC enable/disable toggle path where the work must remain re-schedulable.
CVE-2026-23394: In the Linux kernel, the following vulnerability has been resolved: af_unix: Give up GC if MSG_PEEK intervened. Igor Ushakov reported that GC purged the receive queue of an alive socket due to a race with MSG_PEEK with a nice repro. This is the exact same issue previously fixed by commit cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK"). After GC was replaced with the current algorithm, the cited commit removed the locking dance in unix_peek_fds() and reintroduced the same issue. The problem is that MSG_PEEK bumps a file refcount without interacting with GC. Consider an SCC containing sk-A and sk-B, where sk-A is close()d but can be recv()ed via sk-B. The bad thing happens if sk-A is recv()ed with MSG_PEEK from sk-B and sk-B is close()d while GC is checking unix_vertex_dead() for sk-A and sk-B. GC thread User thread --------- ----------- unix_vertex_dead(sk-A) -> true <------. \ `------ recv(sk-B, MSG_PEEK) invalidate !! -> sk-A's file refcount : 1 -> 2 close(sk-B) -> sk-B's file refcount : 2 -> 1 unix_vertex_dead(sk-B) -> true Initially, sk-A's file refcount is 1 by the inflight fd in sk-B recvq. GC thinks sk-A is dead because the file refcount is the same as the number of its inflight fds. However, sk-A's file refcount is bumped silently by MSG_PEEK, which invalidates the previous evaluation. At this moment, sk-B's file refcount is 2; one by the open fd, and one by the inflight fd in sk-A. The subsequent close() releases one refcount by the former. Finally, GC incorrectly concludes that both sk-A and sk-B are dead. One option is to restore the locking dance in unix_peek_fds(), but we can resolve this more elegantly thanks to the new algorithm. The point is that the issue does not occur without the subsequent close() and we actually do not need to synchronise MSG_PEEK with the dead SCC detection. When the issue occurs, close() and GC touch the same file refcount. If GC sees the refcount being decremented by close(), it can just give up garbage-collecting the SCC. Therefore, we only need to signal the race during MSG_PEEK with a proper memory barrier to make it visible to the GC. Let's use seqcount_t to notify GC when MSG_PEEK occurs and let it defer the SCC to the next run. This way no locking is needed on the MSG_PEEK side, and we can avoid imposing a penalty on every MSG_PEEK unnecessarily. Note that we can retry within unix_scc_dead() if MSG_PEEK is detected, but we do not do so to avoid hung task splat from abusive MSG_PEEK calls.
CVE-2026-23395: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ Currently the code attempts to accept requests regardless of the command identifier which may cause multiple requests to be marked as pending (FLAG_DEFER_SETUP) which can cause more than L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer causing an overflow. The spec is quite clear that the same identifier shall not be used on subsequent requests: 'Within each signaling channel a different Identifier shall be used for each successive request or indication.' https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-adaptation-protocol-specification.html#UUID-32a25a06-4aa4-c6c7-77c5-dcfe3682355d So this attempts to check if there are any channels pending with the same identifier and rejects if any are found.
CVE-2026-23396: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix NULL deref in mesh_matches_local() mesh_matches_local() unconditionally dereferences ie->mesh_config to compare mesh configuration parameters. When called from mesh_rx_csa_frame(), the parsed action-frame elements may not contain a Mesh Configuration IE, leaving ie->mesh_config NULL and triggering a kernel NULL pointer dereference. The other two callers are already safe: - ieee80211_mesh_rx_bcn_presp() checks !elems->mesh_config before calling mesh_matches_local() - mesh_plink_get_event() is only reached through mesh_process_plink_frame(), which checks !elems->mesh_config, too mesh_rx_csa_frame() is the only caller that passes raw parsed elements to mesh_matches_local() without guarding mesh_config. An adjacent attacker can exploit this by sending a crafted CSA action frame that includes a valid Mesh ID IE but omits the Mesh Configuration IE, crashing the kernel. The captured crash log: Oops: general protection fault, probably for non-canonical address ... KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Workqueue: events_unbound cfg80211_wiphy_work [...] Call Trace: <TASK> ? __pfx_mesh_matches_local (net/mac80211/mesh.c:65) ieee80211_mesh_rx_queued_mgmt (net/mac80211/mesh.c:1686) [...] ieee80211_iface_work (net/mac80211/iface.c:1754 net/mac80211/iface.c:1802) [...] cfg80211_wiphy_work (net/wireless/core.c:426) process_one_work (net/kernel/workqueue.c:3280) ? assign_work (net/kernel/workqueue.c:1219) worker_thread (net/kernel/workqueue.c:3352) ? __pfx_worker_thread (net/kernel/workqueue.c:3385) kthread (net/kernel/kthread.c:436) [...] ret_from_fork_asm (net/arch/x86/entry/entry_64.S:255) </TASK> This patch adds a NULL check for ie->mesh_config at the top of mesh_matches_local() to return false early when the Mesh Configuration IE is absent.
CVE-2026-23397: In the Linux kernel, the following vulnerability has been resolved: nfnetlink_osf: validate individual option lengths in fingerprints nfnl_osf_add_callback() validates opt_num bounds and string NUL-termination but does not check individual option length fields. A zero-length option causes nf_osf_match_one() to enter the option matching loop even when foptsize sums to zero, which matches packets with no TCP options where ctx->optp is NULL: Oops: general protection fault KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98) Call Trace: nf_osf_match (net/netfilter/nfnetlink_osf.c:227) xt_osf_match_packet (net/netfilter/xt_osf.c:32) ipt_do_table (net/ipv4/netfilter/ip_tables.c:293) nf_hook_slow (net/netfilter/core.c:623) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) Additionally, an MSS option (kind=2) with length < 4 causes out-of-bounds reads when nf_osf_match_one() unconditionally accesses optp[2] and optp[3] for MSS value extraction. While RFC 9293 section 3.2 specifies that the MSS option is always exactly 4 bytes (Kind=2, Length=4), the check uses "< 4" rather than "!= 4" because lengths greater than 4 do not cause memory safety issues -- the buffer is guaranteed to be at least foptsize bytes by the ctx->optsize == foptsize check. Reject fingerprints where any option has zero length, or where an MSS option has length less than 4, at add time rather than trusting these values in the packet matching hot path.
CVE-2026-23398: In the Linux kernel, the following vulnerability has been resolved: icmp: fix NULL pointer dereference in icmp_tag_validation() icmp_tag_validation() unconditionally dereferences the result of rcu_dereference(inet_protos[proto]) without checking for NULL. The inet_protos[] array is sparse -- only about 15 of 256 protocol numbers have registered handlers. When ip_no_pmtu_disc is set to 3 (hardened PMTU mode) and the kernel receives an ICMP Fragmentation Needed error with a quoted inner IP header containing an unregistered protocol number, the NULL dereference causes a kernel panic in softirq context. Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:icmp_unreach (net/ipv4/icmp.c:1085 net/ipv4/icmp.c:1143) Call Trace: <IRQ> icmp_rcv (net/ipv4/icmp.c:1527) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207) ip_local_deliver_finish (net/ipv4/ip_input.c:242) ip_local_deliver (net/ipv4/ip_input.c:262) ip_rcv (net/ipv4/ip_input.c:573) __netif_receive_skb_one_core (net/core/dev.c:6164) process_backlog (net/core/dev.c:6628) handle_softirqs (kernel/softirq.c:561) </IRQ> Add a NULL check before accessing icmp_strict_tag_validation. If the protocol has no registered handler, return false since it cannot perform strict tag validation.
CVE-2026-23399: In the Linux kernel, the following vulnerability has been resolved: nf_tables: nft_dynset: fix possible stateful expression memleak in error path If cloning the second stateful expression in the element via GFP_ATOMIC fails, then the first stateful expression remains in place without being released. unreferenced object (percpu) 0x607b97e9cab8 (size 16): comm "softirq", pid 0, jiffies 4294931867 hex dump (first 16 bytes on cpu 3): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 backtrace (crc 0): pcpu_alloc_noprof+0x453/0xd80 nft_counter_clone+0x9c/0x190 [nf_tables] nft_expr_clone+0x8f/0x1b0 [nf_tables] nft_dynset_new+0x2cb/0x5f0 [nf_tables] nft_rhash_update+0x236/0x11c0 [nf_tables] nft_dynset_eval+0x11f/0x670 [nf_tables] nft_do_chain+0x253/0x1700 [nf_tables] nft_do_chain_ipv4+0x18d/0x270 [nf_tables] nf_hook_slow+0xaa/0x1e0 ip_local_deliver+0x209/0x330
CVE-2026-23401: In the Linux kernel, the following vulnerability has been resolved: KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE When installing an emulated MMIO SPTE, do so *after* dropping/zapping the existing SPTE (if it's shadow-present). While commit a54aa15c6bda3 was right about it being impossible to convert a shadow-present SPTE to an MMIO SPTE due to a _guest_ write, it failed to account for writes to guest memory that are outside the scope of KVM. E.g. if host userspace modifies a shadowed gPTE to switch from a memslot to emulted MMIO and then the guest hits a relevant page fault, KVM will install the MMIO SPTE without first zapping the shadow-present SPTE. ------------[ cut here ]------------ is_shadow_present_pte(*sptep) WARNING: arch/x86/kvm/mmu/mmu.c:484 at mark_mmio_spte+0xb2/0xc0 [kvm], CPU#0: vmx_ept_stale_r/4292 Modules linked in: kvm_intel kvm irqbypass CPU: 0 UID: 1000 PID: 4292 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:mark_mmio_spte+0xb2/0xc0 [kvm] Call Trace: <TASK> mmu_set_spte+0x237/0x440 [kvm] ept_page_fault+0x535/0x7f0 [kvm] kvm_mmu_do_page_fault+0xee/0x1f0 [kvm] kvm_mmu_page_fault+0x8d/0x620 [kvm] vmx_handle_exit+0x18c/0x5a0 [kvm_intel] kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm] kvm_vcpu_ioctl+0x2d5/0x980 [kvm] __x64_sys_ioctl+0x8a/0xd0 do_syscall_64+0xb5/0x730 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x47fa3f </TASK> ---[ end trace 0000000000000000 ]---
CVE-2026-23414: In the Linux kernel, the following vulnerability has been resolved: tls: Purge async_hold in tls_decrypt_async_wait() The async_hold queue pins encrypted input skbs while the AEAD engine references their scatterlist data. Once tls_decrypt_async_wait() returns, every AEAD operation has completed and the engine no longer references those skbs, so they can be freed unconditionally. A subsequent patch adds batch async decryption to tls_sw_read_sock(), introducing a new call site that must drain pending AEAD operations and release held skbs. Move __skb_queue_purge(&ctx->async_hold) into tls_decrypt_async_wait() so the purge is centralized and every caller -- recvmsg's drain path, the -EBUSY fallback in tls_do_decryption(), and the new read_sock batch path -- releases held skbs on synchronization without each site managing the purge independently. This fixes a leak when tls_strp_msg_hold() fails part-way through, after having added some cloned skbs to the async_hold queue. tls_decrypt_sg() will then call tls_decrypt_async_wait() to process all pending decrypts, and drop back to synchronous mode, but tls_sw_recvmsg() only flushes the async_hold queue when one record has been processed in "fully-async" mode, which may not be the case here. [pabeni@redhat.com: added leak comment]
CVE-2026-23419: In the Linux kernel, the following vulnerability has been resolved: net/rds: Fix circular locking dependency in rds_tcp_tune syzbot reported a circular locking dependency in rds_tcp_tune() where sk_net_refcnt_upgrade() is called while holding the socket lock: ====================================================== WARNING: possible circular locking dependency detected ====================================================== kworker/u10:8/15040 is trying to acquire lock: ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0}, at: __kmalloc_cache_noprof+0x4b/0x6f0 but task is already holding lock: ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: rds_tcp_tune+0xd7/0x930 The issue occurs because sk_net_refcnt_upgrade() performs memory allocation (via get_net_track() -> ref_tracker_alloc()) while the socket lock is held, creating a circular dependency with fs_reclaim. Fix this by moving sk_net_refcnt_upgrade() outside the socket lock critical section. This is safe because the fields modified by the sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not accessed by any concurrent code path at this point. v2: - Corrected fixes tag - check patch line wrap nits - ai commentary nits
CVE-2026-23420: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Fix a locking bug Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.
CVE-2026-23422: In the Linux kernel, the following vulnerability has been resolved: dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ handler Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler") introduces a range check for if_id to avoid an out-of-bounds access. If an out-of-bounds if_id is detected, the interrupt status is not cleared. This may result in an interrupt storm. Clear the interrupt status after detecting an out-of-bounds if_id to avoid the problem. Found by an experimental AI code review agent at Google.
CVE-2026-23426: In the Linux kernel, the following vulnerability has been resolved: drm/logicvc: Fix device node reference leak in logicvc_drm_config_parse() The logicvc_drm_config_parse() function calls of_get_child_by_name() to find the "layers" node but fails to release the reference, leading to a device node reference leak. Fix this by using the __free(device_node) cleanup attribute to automatic release the reference when the variable goes out of scope.
CVE-2026-23428: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix use-after-free of share_conf in compound request smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state == TREE_CONNECTED on the initial lookup path, but the compound reuse path bypasses this check entirely. If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(), subsequent commands dereference the freed share_conf through work->tcon->share_conf. KASAN report: [ 4.144653] ================================================================== [ 4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70 [ 4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44 [ 4.145772] [ 4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY [ 4.145871] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 4.145875] Workqueue: ksmbd-io handle_ksmbd_work [ 4.145888] Call Trace: [ 4.145892] <TASK> [ 4.145894] dump_stack_lvl+0x64/0x80 [ 4.145910] print_report+0xce/0x660 [ 4.145919] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ 4.145928] ? smb2_write+0xc74/0xe70 [ 4.145931] kasan_report+0xce/0x100 [ 4.145934] ? smb2_write+0xc74/0xe70 [ 4.145937] smb2_write+0xc74/0xe70 [ 4.145939] ? __pfx_smb2_write+0x10/0x10 [ 4.145942] ? _raw_spin_unlock+0xe/0x30 [ 4.145945] ? ksmbd_smb2_check_message+0xeb2/0x24c0 [ 4.145948] ? smb2_tree_disconnect+0x31c/0x480 [ 4.145951] handle_ksmbd_work+0x40f/0x1080 [ 4.145953] process_one_work+0x5fa/0xef0 [ 4.145962] ? assign_work+0x122/0x3e0 [ 4.145964] worker_thread+0x54b/0xf70 [ 4.145967] ? __pfx_worker_thread+0x10/0x10 [ 4.145970] kthread+0x346/0x470 [ 4.145976] ? recalc_sigpending+0x19b/0x230 [ 4.145980] ? __pfx_kthread+0x10/0x10 [ 4.145984] ret_from_fork+0x4fb/0x6c0 [ 4.145992] ? __pfx_ret_from_fork+0x10/0x10 [ 4.145995] ? __switch_to+0x36c/0xbe0 [ 4.145999] ? __pfx_kthread+0x10/0x10 [ 4.146003] ret_from_fork_asm+0x1a/0x30 [ 4.146013] </TASK> [ 4.146014] [ 4.149858] Allocated by task 44: [ 4.149953] kasan_save_stack+0x33/0x60 [ 4.150061] kasan_save_track+0x14/0x30 [ 4.150169] __kasan_kmalloc+0x8f/0xa0 [ 4.150274] ksmbd_share_config_get+0x1dd/0xdd0 [ 4.150401] ksmbd_tree_conn_connect+0x7e/0x600 [ 4.150529] smb2_tree_connect+0x2e6/0x1000 [ 4.150645] handle_ksmbd_work+0x40f/0x1080 [ 4.150761] process_one_work+0x5fa/0xef0 [ 4.150873] worker_thread+0x54b/0xf70 [ 4.150978] kthread+0x346/0x470 [ 4.151071] ret_from_fork+0x4fb/0x6c0 [ 4.151176] ret_from_fork_asm+0x1a/0x30 [ 4.151286] [ 4.151332] Freed by task 44: [ 4.151418] kasan_save_stack+0x33/0x60 [ 4.151526] kasan_save_track+0x14/0x30 [ 4.151634] kasan_save_free_info+0x3b/0x60 [ 4.151751] __kasan_slab_free+0x43/0x70 [ 4.151861] kfree+0x1ca/0x430 [ 4.151952] __ksmbd_tree_conn_disconnect+0xc8/0x190 [ 4.152088] smb2_tree_disconnect+0x1cd/0x480 [ 4.152211] handle_ksmbd_work+0x40f/0x1080 [ 4.152326] process_one_work+0x5fa/0xef0 [ 4.152438] worker_thread+0x54b/0xf70 [ 4.152545] kthread+0x346/0x470 [ 4.152638] ret_from_fork+0x4fb/0x6c0 [ 4.152743] ret_from_fork_asm+0x1a/0x30 [ 4.152853] [ 4.152900] The buggy address belongs to the object at ffff88810430c180 [ 4.152900] which belongs to the cache kmalloc-96 of size 96 [ 4.153226] The buggy address is located 20 bytes inside of [ 4.153226] freed 96-byte region [ffff88810430c180, ffff88810430c1e0) [ 4.153549] [ 4.153596] The buggy address belongs to the physical page: [ 4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c [ 4.154000] flags: 0x ---truncated---
CVE-2026-23434: In the Linux kernel, the following vulnerability has been resolved: mtd: rawnand: serialize lock/unlock against other NAND operations nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area without holding the NAND device lock. On controllers that implement SET_FEATURES via multiple low-level PIO commands, these can race with concurrent UBI/UBIFS background erase/write operations that hold the device lock, resulting in cmd_pending conflicts on the NAND controller. Add nand_get_device()/nand_release_device() around the lock/unlock operations to serialize them against all other NAND controller access.
CVE-2026-23438: In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: guard flow control update with global_tx_fc in buffer switching mvpp2_bm_switch_buffers() unconditionally calls mvpp2_bm_pool_update_priv_fc() when switching between per-cpu and shared buffer pool modes. This function programs CM3 flow control registers via mvpp2_cm3_read()/mvpp2_cm3_write(), which dereference priv->cm3_base without any NULL check. When the CM3 SRAM resource is not present in the device tree (the third reg entry added by commit 60523583b07c ("dts: marvell: add CM3 SRAM memory to cp11x ethernet device tree")), priv->cm3_base remains NULL and priv->global_tx_fc is false. Any operation that triggers mvpp2_bm_switch_buffers(), for example an MTU change that crosses the jumbo frame threshold, will crash: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits pc : readl+0x0/0x18 lr : mvpp2_cm3_read.isra.0+0x14/0x20 Call trace: readl+0x0/0x18 mvpp2_bm_pool_update_fc+0x40/0x12c mvpp2_bm_pool_update_priv_fc+0x94/0xd8 mvpp2_bm_switch_buffers.isra.0+0x80/0x1c0 mvpp2_change_mtu+0x140/0x380 __dev_set_mtu+0x1c/0x38 dev_set_mtu_ext+0x78/0x118 dev_set_mtu+0x48/0xa8 dev_ifsioc+0x21c/0x43c dev_ioctl+0x2d8/0x42c sock_ioctl+0x314/0x378 Every other flow control call site in the driver already guards hardware access with either priv->global_tx_fc or port->tx_fc. mvpp2_bm_switch_buffers() is the only place that omits this check. Add the missing priv->global_tx_fc guard to both the disable and re-enable calls in mvpp2_bm_switch_buffers(), consistent with the rest of the driver.
CVE-2026-23439: In the Linux kernel, the following vulnerability has been resolved: udp_tunnel: fix NULL deref caused by udp_sock_create6 when CONFIG_IPV6=n When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0 (success) without actually creating a socket. Callers such as fou_create() then proceed to dereference the uninitialized socket pointer, resulting in a NULL pointer dereference. The captured NULL deref crash: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764) [...] Call Trace: <TASK> genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114) genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209) [...] netlink_rcv_skb (net/netlink/af_netlink.c:2550) genl_rcv (net/netlink/genetlink.c:1219) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) __sock_sendmsg (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1)) __sys_sendto (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:2183 (discriminator 1)) __x64_sys_sendto (net/socket.c:2213 (discriminator 1) net/socket.c:2209 (discriminator 1) net/socket.c:2209 (discriminator 1)) do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) entry_SYSCALL_64_after_hwframe (net/arch/x86/entry/entry_64.S:130) This patch makes udp_sock_create6 return -EPFNOSUPPORT instead, so callers correctly take their error paths. There is only one caller of the vulnerable function and only privileged users can trigger it.
CVE-2026-23442: In the Linux kernel, the following vulnerability has been resolved: ipv6: add NULL checks for idev in SRv6 paths __in6_dev_get() can return NULL when the device has no IPv6 configuration (e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER). Add NULL checks for idev returned by __in6_dev_get() in both seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL pointer dereferences.
CVE-2026-23444: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure ieee80211_tx_prepare_skb() has three error paths, but only two of them free the skb. The first error path (ieee80211_tx_prepare() returning TX_DROP) does not free it, while invoke_tx_handlers() failure and the fragmentation check both do. Add kfree_skb() to the first error path so all three are consistent, and remove the now-redundant frees in callers (ath9k, mt76, mac80211_hwsim) to avoid double-free. Document the skb ownership guarantee in the function's kdoc.
CVE-2026-23446: In the Linux kernel, the following vulnerability has been resolved: net: usb: aqc111: Do not perform PM inside suspend callback syzbot reports "task hung in rpm_resume" This is caused by aqc111_suspend calling the PM variant of its write_cmd routine. The simplified call trace looks like this: rpm_suspend() usb_suspend_both() - here udev->dev.power.runtime_status == RPM_SUSPENDING aqc111_suspend() - called for the usb device interface aqc111_write32_cmd() usb_autopm_get_interface() pm_runtime_resume_and_get() rpm_resume() - here we call rpm_resume() on our parent rpm_resume() - Here we wait for a status change that will never happen. At this point we block another task which holds rtnl_lock and locks up the whole networking stack. Fix this by replacing the write_cmd calls with their _nopm variants
CVE-2026-23447: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check The same bounds-check bug fixed for NDP16 in the previous patch also exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated against the total skb length without accounting for ndpoffset, allowing out-of-bounds reads when the NDP32 is placed near the end of the NTB. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly. Compile-tested only.
CVE-2026-23448: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE entries fit within the skb. The first check correctly accounts for ndpoffset: if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len) but the second check omits it: if ((sizeof(struct usb_cdc_ncm_ndp16) + ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len) This validates the DPE array size against the total skb length as if the NDP were at offset 0, rather than at ndpoffset. When the NDP is placed near the end of the NTB (large wNdpIndex), the DPE entries can extend past the skb data buffer even though the check passes. cdc_ncm_rx_fixup() then reads out-of-bounds memory when iterating the DPE array. Add ndpoffset to the nframes bounds check and use struct_size_t() to express the NDP-plus-DPE-array size more clearly.
CVE-2026-23449: In the Linux kernel, the following vulnerability has been resolved: net/sched: teql: Fix double-free in teql_master_xmit Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should be called using the seq_lock to avoid racing with the datapath. Failure to do so may cause crashes like the following: [ 238.028993][ T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139) [ 238.029328][ T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318 [ 238.029749][ T318] [ 238.029900][ T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full) [ 238.029906][ T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 238.029910][ T318] Call Trace: [ 238.029913][ T318] <TASK> [ 238.029916][ T318] dump_stack_lvl (lib/dump_stack.c:122) [ 238.029928][ T318] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 238.029940][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029944][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.029957][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029969][ T318] kasan_report_invalid_free (mm/kasan/report.c:221 mm/kasan/report.c:563) [ 238.029979][ T318] ? skb_release_data (net/core/skbuff.c:1139) [ 238.029989][ T318] check_slab_allocation (mm/kasan/common.c:231) [ 238.029995][ T318] kmem_cache_free (mm/slub.c:2637 (discriminator 1) mm/slub.c:6168 (discriminator 1) mm/slub.c:6298 (discriminator 1)) [ 238.030004][ T318] skb_release_data (net/core/skbuff.c:1139) ... [ 238.030025][ T318] sk_skb_reason_drop (net/core/skbuff.c:1256) [ 238.030032][ T318] pfifo_fast_reset (./include/linux/ptr_ring.h:171 ./include/linux/ptr_ring.h:309 ./include/linux/skb_array.h:98 net/sched/sch_generic.c:827) [ 238.030039][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) ... [ 238.030054][ T318] qdisc_reset (net/sched/sch_generic.c:1034) [ 238.030062][ T318] teql_destroy (./include/linux/spinlock.h:395 net/sched/sch_teql.c:157) [ 238.030071][ T318] __qdisc_destroy (./include/net/pkt_sched.h:328 net/sched/sch_generic.c:1077) [ 238.030077][ T318] qdisc_graft (net/sched/sch_api.c:1062 net/sched/sch_api.c:1053 net/sched/sch_api.c:1159) [ 238.030089][ T318] ? __pfx_qdisc_graft (net/sched/sch_api.c:1091) [ 238.030095][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030102][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030106][ T318] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 238.030114][ T318] tc_get_qdisc (net/sched/sch_api.c:1529 net/sched/sch_api.c:1556) ... [ 238.072958][ T318] Allocated by task 303 on cpu 5 at 238.026275s: [ 238.073392][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.073884][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.074230][ T318] __kasan_slab_alloc (mm/kasan/common.c:369) [ 238.074578][ T318] kmem_cache_alloc_node_noprof (./include/linux/kasan.h:253 mm/slub.c:4542 mm/slub.c:4869 mm/slub.c:4921) [ 238.076091][ T318] kmalloc_reserve (net/core/skbuff.c:616 (discriminator 107)) [ 238.076450][ T318] __alloc_skb (net/core/skbuff.c:713) [ 238.076834][ T318] alloc_skb_with_frags (./include/linux/skbuff.h:1383 net/core/skbuff.c:6763) [ 238.077178][ T318] sock_alloc_send_pskb (net/core/sock.c:2997) [ 238.077520][ T318] packet_sendmsg (net/packet/af_packet.c:2926 net/packet/af_packet.c:3019 net/packet/af_packet.c:3108) [ 238.081469][ T318] [ 238.081870][ T318] Freed by task 299 on cpu 1 at 238.028496s: [ 238.082761][ T318] kasan_save_stack (mm/kasan/common.c:58) [ 238.083481][ T318] kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5)) [ 238.085348][ T318] kasan_save_free_info (mm/kasan/generic.c:587 (discriminator 1)) [ 238.085900][ T318] __kasan_slab_free (mm/ ---truncated---
CVE-2026-23450: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix NULL dereference and UAF in smc_tcp_syn_recv_sock() Syzkaller reported a panic in smc_tcp_syn_recv_sock() [1]. smc_tcp_syn_recv_sock() is called in the TCP receive path (softirq) via icsk_af_ops->syn_recv_sock on the clcsock (TCP listening socket). It reads sk_user_data to get the smc_sock pointer. However, when the SMC listen socket is being closed concurrently, smc_close_active() sets clcsock->sk_user_data to NULL under sk_callback_lock, and then the smc_sock itself can be freed via sock_put() in smc_release(). This leads to two issues: 1) NULL pointer dereference: sk_user_data is NULL when accessed. 2) Use-after-free: sk_user_data is read as non-NULL, but the smc_sock is freed before its fields (e.g., queued_smc_hs, ori_af_ops) are accessed. The race window looks like this (the syzkaller crash [1] triggers via the SYN cookie path: tcp_get_cookie_sock() -> smc_tcp_syn_recv_sock(), but the normal tcp_check_req() path has the same race): CPU A (softirq) CPU B (process ctx) tcp_v4_rcv() TCP_NEW_SYN_RECV: sk = req->rsk_listener sock_hold(sk) /* No lock on listener */ smc_close_active(): write_lock_bh(cb_lock) sk_user_data = NULL write_unlock_bh(cb_lock) ... smc_clcsock_release() sock_put(smc->sk) x2 -> smc_sock freed! tcp_check_req() smc_tcp_syn_recv_sock(): smc = user_data(sk) -> NULL or dangling smc->queued_smc_hs -> crash! Note that the clcsock and smc_sock are two independent objects with separate refcounts. TCP stack holds a reference on the clcsock, which keeps it alive, but this does NOT prevent the smc_sock from being freed. Fix this by using RCU and refcount_inc_not_zero() to safely access smc_sock. Since smc_tcp_syn_recv_sock() is called in the TCP three-way handshake path, taking read_lock_bh on sk_callback_lock is too heavy and would not survive a SYN flood attack. Using rcu_read_lock() is much more lightweight. - Set SOCK_RCU_FREE on the SMC listen socket so that smc_sock freeing is deferred until after the RCU grace period. This guarantees the memory is still valid when accessed inside rcu_read_lock(). - Use rcu_read_lock() to protect reading sk_user_data. - Use refcount_inc_not_zero(&smc->sk.sk_refcnt) to pin the smc_sock. If the refcount has already reached zero (close path completed), it returns false and we bail out safely. Note: smc_hs_congested() has a similar lockless read of sk_user_data without rcu_read_lock(), but it only checks for NULL and accesses the global smc_hs_wq, never dereferencing any smc_sock field, so it is not affected. Reproducer was verified with mdelay injection and smc_run, the issue no longer occurs with this patch applied. [1] https://syzkaller.appspot.com/bug?extid=827ae2bfb3a3529333e9
CVE-2026-23452: In the Linux kernel, the following vulnerability has been resolved: PM: runtime: Fix a race condition related to device removal The following code in pm_runtime_work() may dereference the dev->parent pointer after the parent device has been freed: /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } Fix this by inserting a flush_work() call in pm_runtime_remove(). Without this patch blktest block/001 triggers the following complaint sporadically: BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160 Read of size 1 at addr ffff88812bef7198 by task kworker/u553:1/3081 Workqueue: pm pm_runtime_work Call Trace: <TASK> dump_stack_lvl+0x61/0x80 print_address_description.constprop.0+0x8b/0x310 print_report+0xfd/0x1d7 kasan_report+0xd8/0x1d0 __kasan_check_byte+0x42/0x60 lock_acquire.part.0+0x38/0x230 lock_acquire+0x70/0x160 _raw_spin_lock+0x36/0x50 rpm_suspend+0xc6a/0xfe0 rpm_idle+0x578/0x770 pm_runtime_work+0xee/0x120 process_one_work+0xde3/0x1410 worker_thread+0x5eb/0xfe0 kthread+0x37b/0x480 ret_from_fork+0x6cb/0x920 ret_from_fork_asm+0x11/0x20 </TASK> Allocated by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_alloc_info+0x3d/0x50 __kasan_kmalloc+0xa0/0xb0 __kmalloc_noprof+0x311/0x990 scsi_alloc_target+0x122/0xb60 [scsi_mod] __scsi_scan_target+0x101/0x460 [scsi_mod] scsi_scan_channel+0x179/0x1c0 [scsi_mod] scsi_scan_host_selected+0x259/0x2d0 [scsi_mod] store_scan+0x2d2/0x390 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810 do_syscall_64+0xee/0xfc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Freed by task 4314: kasan_save_stack+0x2a/0x50 kasan_save_track+0x18/0x40 kasan_save_free_info+0x3f/0x50 __kasan_slab_free+0x67/0x80 kfree+0x225/0x6c0 scsi_target_dev_release+0x3d/0x60 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_dev_release+0xacf/0x12c0 [scsi_mod] device_release+0xa3/0x220 kobject_cleanup+0x105/0x3a0 kobject_put+0x72/0xd0 put_device+0x17/0x20 scsi_device_put+0x7f/0xc0 [scsi_mod] sdev_store_delete+0xa5/0x120 [scsi_mod] dev_attr_store+0x43/0x80 sysfs_kf_write+0xde/0x140 kernfs_fop_write_iter+0x3ef/0x670 vfs_write+0x506/0x1470 ksys_write+0xfd/0x230 __x64_sys_write+0x76/0xc0 x64_sys_call+0x213/0x1810
CVE-2026-23454: In the Linux kernel, the following vulnerability has been resolved: net: mana: fix use-after-free in mana_hwc_destroy_channel() by reordering teardown A potential race condition exists in mana_hwc_destroy_channel() where hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt handler to dereference freed memory, leading to a use-after-free or NULL pointer dereference in mana_hwc_handle_resp(). mana_smc_teardown_hwc() signals the hardware to stop but does not synchronize against IRQ handlers already executing on other CPUs. The IRQ synchronization only happens in mana_hwc_destroy_cq() via mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler() can dereference freed caller_ctx (and rxq->msg_buf) in mana_hwc_handle_resp(). Fix this by reordering teardown to reverse-of-creation order: destroy the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This ensures all in-flight interrupt handlers complete before the memory they access is freed.
CVE-2026-23455: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931() In DecodeQ931(), the UserUserIE code path reads a 16-bit length from the packet, then decrements it by 1 to skip the protocol discriminator byte before passing it to DecodeH323_UserInformation(). If the encoded length is 0, the decrement wraps to -1, which is then passed as a large value to the decoder, leading to an out-of-bounds read. Add a check to ensure len is positive after the decrement.
CVE-2026-23456: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case In decode_int(), the CONS case calls get_bits(bs, 2) to read a length value, then calls get_uint(bs, len) without checking that len bytes remain in the buffer. The existing boundary check only validates the 2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint() reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte slab-out-of-bounds read. Add a boundary check for len bytes after get_bits() and before get_uint().
CVE-2026-23457: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length.
CVE-2026-23458: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct() ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the conntrack reference immediately after netlink_dump_start(). When the dump spans multiple rounds, the second recvmsg() triggers the dump callback which dereferences the now-freed conntrack via nfct_help(ct), leading to a use-after-free on ct->ext. The bug is that the netlink_dump_control has no .start or .done callbacks to manage the conntrack reference across dump rounds. Other dump functions in the same file (e.g. ctnetlink_get_conntrack) properly use .start/.done callbacks for this purpose. Fix this by adding .start and .done callbacks that hold and release the conntrack reference for the duration of the dump, and move the nfct_help() call after the cb->args[0] early-return check in the dump callback to avoid dereferencing ct->ext unnecessarily. BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY Call Trace: <TASK> ctnetlink_exp_ct_dump_table+0x4f/0x2e0 netlink_dump+0x333/0x880 netlink_recvmsg+0x3e2/0x4b0 ? aa_sk_perm+0x184/0x450 sock_recvmsg+0xde/0xf0 Allocated by task 133: kmem_cache_alloc_noprof+0x134/0x440 __nf_conntrack_alloc+0xa8/0x2b0 ctnetlink_create_conntrack+0xa1/0x900 ctnetlink_new_conntrack+0x3cf/0x7d0 nfnetlink_rcv_msg+0x48e/0x510 netlink_rcv_skb+0xc9/0x1f0 nfnetlink_rcv+0xdb/0x220 netlink_unicast+0x3ec/0x590 netlink_sendmsg+0x397/0x690 __sys_sendmsg+0xf4/0x180 Freed by task 0: slab_free_after_rcu_debug+0xad/0x1e0 rcu_core+0x5c3/0x9c0
CVE-2026-23460: In the Linux kernel, the following vulnerability has been resolved: net/rose: fix NULL pointer dereference in rose_transmit_link on reconnect syzkaller reported a bug [1], and the reproducer is available at [2]. ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN, TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING (-ECONNREFUSED), but lacks a check for TCP_SYN_SENT. When rose_connect() is called a second time while the first connection attempt is still in progress (TCP_SYN_SENT), it overwrites rose->neighbour via rose_get_neigh(). If that returns NULL, the socket is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL. When the socket is subsequently closed, rose_release() sees ROSE_STATE_1 and calls rose_write_internal() -> rose_transmit_link(skb, NULL), causing a NULL pointer dereference. Per connect(2), a second connect() while a connection is already in progress should return -EALREADY. Add this missing check for TCP_SYN_SENT to complete the state validation in rose_connect(). [1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271 [2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516
CVE-2026-23462: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HIDP: Fix possible UAF This fixes the following trace caused by not dropping l2cap_conn reference when user->remove callback is called: [ 97.809249] l2cap_conn_free: freeing conn ffff88810a171c00 [ 97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy) [ 97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 97.809947] Call Trace: [ 97.809954] <TASK> [ 97.809961] dump_stack_lvl (lib/dump_stack.c:122) [ 97.809990] l2cap_conn_free (net/bluetooth/l2cap_core.c:1808) [ 97.810017] l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798) [ 97.810055] l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1)) [ 97.810086] ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341) [ 97.810117] hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2)) [ 97.810148] hci_dev_close_sync (net/bluetooth/hci_sync.c:5360) [ 97.810180] ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285) [ 97.810212] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810242] ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5)) [ 97.810267] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810290] ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752) [ 97.810320] hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716) [ 97.810346] vhci_release (drivers/bluetooth/hci_vhci.c:691) [ 97.810375] ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678) [ 97.810404] __fput (fs/file_table.c:470) [ 97.810430] task_work_run (kernel/task_work.c:235) [ 97.810451] ? __pfx_task_work_run (kernel/task_work.c:201) [ 97.810472] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810495] ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5)) [ 97.810527] do_exit (kernel/exit.c:972) [ 97.810547] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810574] ? __pfx_do_exit (kernel/exit.c:897) [ 97.810594] ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6)) [ 97.810616] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810639] ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4)) [ 97.810664] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810688] ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1)) [ 97.810721] do_group_exit (kernel/exit.c:1093) [ 97.810745] get_signal (kernel/signal.c:3007 (discriminator 1)) [ 97.810772] ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366) [ 97.810803] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810826] ? vfs_read (fs/read_write.c:555) [ 97.810854] ? __pfx_get_signal (kernel/signal.c:2800) [ 97.810880] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810905] ? __pfx_vfs_read (fs/read_write.c:555) [ 97.810932] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 97.810960] arch_do_signal_or_restart (arch/ ---truncated---
CVE-2026-23463: In the Linux kernel, the following vulnerability has been resolved: soc: fsl: qbman: fix race condition in qman_destroy_fq When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between fq_table[fq->idx] state and freeing/allocating from the pool and WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered. Indeed, we can have: Thread A Thread B qman_destroy_fq() qman_create_fq() qman_release_fqid() qman_shutdown_fq() gen_pool_free() -- At this point, the fqid is available again -- qman_alloc_fqid() -- so, we can get the just-freed fqid in thread B -- fq->fqid = fqid; fq->idx = fqid * 2; WARN_ON(fq_table[fq->idx]); fq_table[fq->idx] = fq; fq_table[fq->idx] = NULL; And adding some logs between qman_release_fqid() and fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more. To prevent that, ensure that fq_table[fq->idx] is set to NULL before gen_pool_free() is called by using smp_wmb().
CVE-2026-23465: In the Linux kernel, the following vulnerability has been resolved: btrfs: log new dentries when logging parent dir of a conflicting inode If we log the parent directory of a conflicting inode, we are not logging the new dentries of the directory, so when we finish we have the parent directory's inode marked as logged but we did not log its new dentries. As a consequence if the parent directory is explicitly fsynced later and it does not have any new changes since we logged it, the fsync is a no-op and after a power failure the new dentries are missing. Example scenario: $ mkdir foo $ sync $rmdir foo $ mkdir dir1 $ mkdir dir2 # A file with the same name and parent as the directory we just deleted # and was persisted in a past transaction. So the deleted directory's # inode is a conflicting inode of this new file's inode. $ touch foo $ ln foo dir2/link # The fsync on dir2 will log the parent directory (".") because the # conflicting inode (deleted directory) does not exists anymore, but it # it does not log its new dentries (dir1). $ xfs_io -c "fsync" dir2 # This fsync on the parent directory is no-op, since the previous fsync # logged it (but without logging its new dentries). $ xfs_io -c "fsync" . <power failure> # After log replay dir1 is missing. Fix this by ensuring we log new dir dentries whenever we log the parent directory of a no longer existing conflicting inode. A test case for fstests will follow soon.
CVE-2026-23468: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion Userspace can pass an arbitrary number of BO list entries via the bo_number field. Although the previous multiplication overflow check prevents out-of-bounds allocation, a large number of entries could still cause excessive memory allocation (up to potentially gigabytes) and unnecessarily long list processing times. Introduce a hard limit of 128k entries per BO list, which is more than sufficient for any realistic use case (e.g., a single list containing all buffers in a large scene). This prevents memory exhaustion attacks and ensures predictable performance. Return -EINVAL if the requested entry count exceeds the limit (cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332)
CVE-2026-23472: In the Linux kernel, the following vulnerability has been resolved: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN uart_write_room() and uart_write() behave inconsistently when xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were never properly initialized): - uart_write_room() returns kfifo_avail() which can be > 0 - uart_write() checks xmit_buf and returns 0 if NULL This inconsistency causes an infinite loop in drivers that rely on tty_write_room() to determine if they can write: while (tty_write_room(tty) > 0) { written = tty->ops->write(...); // written is always 0, loop never exits } For example, caif_serial's handle_tx() enters an infinite loop when used with PORT_UNKNOWN serial ports, causing system hangs. Fix by making uart_write_room() also check xmit_buf and return 0 if it's NULL, consistent with uart_write(). Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13
CVE-2026-23473: In the Linux kernel, the following vulnerability has been resolved: io_uring/poll: fix multishot recv missing EOF on wakeup race When a socket send and shutdown() happen back-to-back, both fire wake-ups before the receiver's task_work has a chance to run. The first wake gets poll ownership (poll_refs=1), and the second bumps it to 2. When io_poll_check_events() runs, it calls io_poll_issue() which does a recv that reads the data and returns IOU_RETRY. The loop then drains all accumulated refs (atomic_sub_return(2) -> 0) and exits, even though only the first event was consumed. Since the shutdown is a persistent state change, no further wakeups will happen, and the multishot recv can hang forever. Check specifically for HUP in the poll loop, and ensure that another loop is done to check for status if more than a single poll activation is pending. This ensures we don't lose the shutdown event.
CVE-2026-23474: In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds.
CVE-2026-23475: In the Linux kernel, the following vulnerability has been resolved: spi: fix statistics allocation The controller per-cpu statistics is not allocated until after the controller has been registered with driver core, which leaves a window where accessing the sysfs attributes can trigger a NULL-pointer dereference. Fix this by moving the statistics allocation to controller allocation while tying its lifetime to that of the controller (rather than using implicit devres).
CVE-2026-31389: In the Linux kernel, the following vulnerability has been resolved: spi: fix use-after-free on controller registration failure Make sure to deregister from driver core also in the unlikely event that per-cpu statistics allocation fails during controller registration to avoid use-after-free (of driver resources) and unclocked register accesses.
CVE-2026-31391: In the Linux kernel, the following vulnerability has been resolved: crypto: atmel-sha204a - Fix OOM ->tfm_count leak If memory allocation fails, decrement ->tfm_count to avoid blocking future reads.
CVE-2026-31392: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix krb5 mount with username option Customer reported that some of their krb5 mounts were failing against a single server as the client was trying to mount the shares with wrong credentials. It turned out the client was reusing SMB session from first mount to try mounting the other shares, even though a different username= option had been specified to the other mounts. By using username mount option along with sec=krb5 to search for principals from keytab is supported by cifs.upcall(8) since cifs-utils-4.8. So fix this by matching username mount option in match_session() even with Kerberos. For example, the second mount below should fail with -ENOKEY as there is no 'foobar' principal in keytab (/etc/krb5.keytab). The client ends up reusing SMB session from first mount to perform the second one, which is wrong. ``` $ ktutil ktutil: add_entry -password -p testuser -k 1 -e aes256-cts Password for testuser@ZELDA.TEST: ktutil: write_kt /etc/krb5.keytab ktutil: quit $ klist -ke Keytab name: FILE:/etc/krb5.keytab KVNO Principal ---- ---------------------------------------------------------------- 1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96) $ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser $ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar $ mount -t cifs | grep -Po 'username=\K\w+' testuser testuser ```
CVE-2026-31393: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access l2cap_information_rsp() checks that cmd_len covers the fixed l2cap_info_rsp header (type + result, 4 bytes) but then reads rsp->data without verifying that the payload is present: - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads 4 bytes past the header (needs cmd_len >= 8). - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header (needs cmd_len >= 5). A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an out-of-bounds read of adjacent skb data. Guard each data access with the required payload length check. If the payload is too short, skip the read and let the state machine complete with safe defaults (feat_mask and remote_fixed_chan remain zero from kzalloc), so the info timer cleanup and l2cap_conn_start() still run and the connection is not stalled.
CVE-2026-31396: In the Linux kernel, the following vulnerability has been resolved: net: macb: fix use-after-free access to PTP clock PTP clock is registered on every opening of the interface and destroyed on every closing. However it may be accessed via get_ts_info ethtool call which is possible while the interface is just present in the kernel. BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 Read of size 4 at addr ffff8880194345cc by task syz.0.6/948 CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106 print_address_description mm/kasan/report.c:316 [inline] print_report+0x17f/0x496 mm/kasan/report.c:420 kasan_report+0xd9/0x180 mm/kasan/report.c:524 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558 ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline] __dev_ethtool net/ethtool/ioctl.c:3017 [inline] dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215 sock_ioctl+0x577/0x6d0 net/socket.c:1320 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 </TASK> Allocated by task 457: kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:699 [inline] ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920 __dev_open+0x2ce/0x500 net/core/dev.c:1501 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651 dev_change_flags+0x92/0x170 net/core/dev.c:8722 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline] netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x14b/0x180 net/socket.c:730 __sys_sendto+0x320/0x3b0 net/socket.c:2152 __do_sys_sendto net/socket.c:2164 [inline] __se_sys_sendto net/socket.c:2160 [inline] __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160 do_syscall_x64 arch/x86/entry/common.c:46 [inline] do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 938: kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1729 [inline] slab_free_freelist_hook mm/slub.c:1755 [inline] slab_free mm/slub.c:3687 [inline] __kmem_cache_free+0xbc/0x320 mm/slub.c:3700 device_release+0xa0/0x240 drivers/base/core.c:2507 kobject_cleanup lib/kobject.c:681 [inline] kobject_release lib/kobject.c:712 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x1cd/0x350 lib/kobject.c:729 put_device+0x1b/0x30 drivers/base/core.c:3805 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585 __dev_close net/core/dev.c:1597 [inline] __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649 dev_change_fl ---truncated---
CVE-2026-31399: In the Linux kernel, the following vulnerability has been resolved: nvdimm/bus: Fix potential use after free in asynchronous initialization Dingisoul with KASAN reports a use after free if device_add() fails in nd_async_device_register(). Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while scheduling async init") correctly added a reference on the parent device to be held until asynchronous initialization was complete. However, if device_add() results in an allocation failure the ref count of the device drops to 0 prior to the parent pointer being accessed. Thus resulting in use after free. The bug bot AI correctly identified the fix. Save a reference to the parent pointer to be used to drop the parent reference regardless of the outcome of device_add().
CVE-2026-31400: In the Linux kernel, the following vulnerability has been resolved: sunrpc: fix cache_request leak in cache_release When a reader's file descriptor is closed while in the middle of reading a cache_request (rp->offset != 0), cache_release() decrements the request's readers count but never checks whether it should free the request. In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the cache_request is removed from the queue and freed along with its buffer and cache_head reference. cache_release() lacks this cleanup. The only other path that frees requests with readers == 0 is cache_dequeue(), but it runs only when CACHE_PENDING transitions from set to clear. If that transition already happened while readers was still non-zero, cache_dequeue() will have skipped the request, and no subsequent call will clean it up. Add the same cleanup logic from cache_read() to cache_release(): after decrementing readers, check if it reached 0 with CACHE_PENDING clear, and if so, dequeue and free the cache_request.
CVE-2026-31402: In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request.
CVE-2026-31403: In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/exports proc entry is created at module init and persists for the module's lifetime. exports_proc_open() captures the caller's current network namespace and stores its svc_export_cache in seq->private, but takes no reference on the namespace. If the namespace is subsequently torn down (e.g. container destruction after the opener does setns() to a different namespace), nfsd_net_exit() calls nfsd_export_shutdown() which frees the cache. Subsequent reads on the still-open fd dereference the freed cache_detail, walking a freed hash table. Hold a reference on the struct net for the lifetime of the open file descriptor. This prevents nfsd_net_exit() from running -- and thus prevents nfsd_export_shutdown() from freeing the cache -- while any exports fd is open. cache_detail already stores its net pointer (cd->net, set by cache_create_net()), so exports_release() can retrieve it without additional per-file storage.
CVE-2026-31405: In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded.
CVE-2026-31407: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.
CVE-2026-31408: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.
CVE-2026-31409: In the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multichannel SMB2_SESSION_SETUP request with SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true but never clears it on the error path. This leaves the connection in a binding state where all subsequent ksmbd_session_lookup_all() calls fall back to the global sessions table. This fix it by clearing conn->binding = false in the error path.
CVE-2026-31410: In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs().
CVE-2026-31411: In the Linux kernel, the following vulnerability has been resolved: net: atm: fix crash due to unvalidated vcc pointer in sigd_send() Reproducer available at [1]. The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc pointer from msg->vcc and uses it directly without any validation. This pointer comes from userspace via sendmsg() and can be arbitrarily forged: int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0); ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon struct msghdr msg = { .msg_iov = &iov, ... }; *(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef In normal operation, the kernel sends the vcc pointer to the signaling daemon via sigd_enq() when processing operations like connect(), bind(), or listen(). The daemon is expected to return the same pointer when responding. However, a malicious daemon can send arbitrary pointer values. Fix this by introducing find_get_vcc() which validates the pointer by searching through vcc_hash (similar to how sigd_close() iterates over all VCCs), and acquires a reference via sock_hold() if found. Since struct atm_vcc embeds struct sock as its first member, they share the same lifetime. Therefore using sock_hold/sock_put is sufficient to keep the vcc alive while it is being used. Note that there may be a race with sigd_close() which could mark the vcc with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns. However, sock_hold() guarantees the memory remains valid, so this race only affects the logical state, not memory safety. [1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3
CVE-2026-31412: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks() The `check_command_size_in_blocks()` function calculates the data size in bytes by left shifting `common->data_size_from_cmnd` by the block size (`common->curlun->blkbits`). However, it does not validate whether this shift operation will cause an integer overflow. Initially, the block size is set up in `fsg_lun_open()` , and the `common->data_size_from_cmnd` is set up in `do_scsi_command()`. During initialization, there is no integer overflow check for the interaction between two variables. So if a malicious USB host sends a SCSI READ or WRITE command requesting a large amount of data (`common->data_size_from_cmnd`), the left shift operation can wrap around. This results in a truncated data size, which can bypass boundary checks and potentially lead to memory corruption or out-of-bounds accesses. Fix this by using the check_shl_overflow() macro to safely perform the shift and catch any overflows.
CVE-2026-31414: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: use expect->helper Use expect->helper in ctnetlink and /proc to dump the helper name. Using nfct_help() without holding a reference to the master conntrack is unsafe. Use exp->master->helper in ctnetlink path if userspace does not provide an explicit helper when creating an expectation to retain the existing behaviour. The ctnetlink expectation path holds the reference on the master conntrack and nf_conntrack_expect lock and the nfnetlink glue path refers to the master ct that is attached to the skb.
CVE-2026-31415: In the Linux kernel, the following vulnerability has been resolved: ipv6: avoid overflows in ip6_datagram_send_ctl() Yiming Qian reported : <quote> I believe I found a locally triggerable kernel bug in the IPv6 sendmsg ancillary-data path that can panic the kernel via `skb_under_panic()` (local DoS). The core issue is a mismatch between: - a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type `__u16`) and - a pointer to the *last* provided destination-options header (`opt->dst1opt`) when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided. - `include/net/ipv6.h`: - `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible). (lines 291-307, especially 298) - `net/ipv6/datagram.c:ip6_datagram_send_ctl()`: - Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen` without rejecting duplicates. (lines 909-933) - `net/ipv6/ip6_output.c:__ip6_append_data()`: - Uses `opt->opt_flen + opt->opt_nflen` to compute header sizes/headroom decisions. (lines 1448-1466, especially 1463-1465) - `net/ipv6/ip6_output.c:__ip6_make_skb()`: - Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero. (lines 1930-1934) - `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`: - Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the pointed-to header). (lines 1179-1185 and 1206-1211) 1. `opt_flen` is a 16-bit accumulator: - `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr */`. 2. `ip6_datagram_send_ctl()` accepts *repeated* `IPV6_DSTOPTS` cmsgs and increments `opt_flen` each time: - In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`: - It computes `len = ((hdr->hdrlen + 1) << 3);` - It checks `CAP_NET_RAW` using `ns_capable(net->user_ns, CAP_NET_RAW)`. (line 922) - Then it does: - `opt->opt_flen += len;` (line 927) - `opt->dst1opt = hdr;` (line 928) There is no duplicate rejection here (unlike the legacy `IPV6_2292DSTOPTS` path which rejects duplicates at `net/ipv6/datagram.c:901-904`). If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps while `dst1opt` still points to a large (2048-byte) destination-options header. In the attached PoC (`poc.c`): - 32 cmsgs with `hdrlen=255` => `len = (255+1)*8 = 2048` - 1 cmsg with `hdrlen=0` => `len = 8` - Total increment: `32*2048 + 8 = 65544`, so `(__u16)opt_flen == 8` - The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header. 3. The transmit path sizes headers using the wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1463-1465`: - `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + ...;` With wrapped `opt_flen`, `headersize`/headroom decisions underestimate what will be pushed later. 4. When building the final skb, the actual push length comes from `dst1opt` and is not limited by wrapped `opt_flen`: - In `net/ipv6/ip6_output.c:1930-1934`: - `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);` - In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes `dst1opt` via `ipv6_push_exthdr()`. - In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does: - `skb_push(skb, ipv6_optlen(opt));` - `memcpy(h, opt, ipv6_optlen(opt));` With insufficient headroom, `skb_push()` underflows and triggers `skb_under_panic()` -> `BUG()`: - `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`) - `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`) - The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`). - Root (or any task with `CAP_NET_RAW`) can trigger this without user namespaces. - An unprivileged `uid=1000` user can trigger this if unprivileged user namespaces are enabled and it can create a userns+netns to obtain namespaced `CAP_NET_RAW` (the attached PoC does this). - Local denial of service: kernel BUG/panic (system crash). - ---truncated---
CVE-2026-31416: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: account for netlink header size This is a followup to an old bug fix: NLMSG_DONE needs to account for the netlink header size, not just the attribute size. This can result in a WARN splat + drop of the netlink message, but other than this there are no ill effects.
CVE-2026-31417: In the Linux kernel, the following vulnerability has been resolved: net/x25: Fix overflow when accumulating packets Add a check to ensure that `x25_sock.fraglen` does not overflow. The `fraglen` also needs to be resetted when purging `fragment_queue` in `x25_clear_queues()`.
CVE-2026-31418: In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: drop logically empty buckets in mtype_del mtype_del() counts empty slots below n->pos in k, but it only drops the bucket when both n->pos and k are zero. This misses buckets whose live entries have all been removed while n->pos still points past deleted slots. Treat a bucket as empty when all positions below n->pos are unused and release it directly instead of shrinking it further.
CVE-2026-31419: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix use-after-free in bond_xmit_broadcast() bond_xmit_broadcast() reuses the original skb for the last slave (determined by bond_is_last_slave()) and clones it for others. Concurrent slave enslave/release can mutate the slave list during RCU-protected iteration, changing which slave is "last" mid-loop. This causes the original skb to be double-consumed (double-freed). Replace the racy bond_is_last_slave() check with a simple index comparison (i + 1 == slaves_count) against the pre-snapshot slave count taken via READ_ONCE() before the loop. This preserves the zero-copy optimization for the last slave while making the "last" determination stable against concurrent list mutations. The UAF can trigger the following crash: ================================================================== BUG: KASAN: slab-use-after-free in skb_clone Read of size 8 at addr ffff888100ef8d40 by task exploit/147 CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:597) skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334) bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593) dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887) __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838) ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136) ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219) ip6_output (net/ipv6/ip6_output.c:250) ip6_send_skb (net/ipv6/ip6_output.c:1985) udp_v6_send_skb (net/ipv6/udp.c:1442) udpv6_sendmsg (net/ipv6/udp.c:1733) __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206) __x64_sys_sendto (net/socket.c:2209) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Allocated by task 147: Freed by task 147: The buggy address belongs to the object at ffff888100ef8c80 which belongs to the cache skbuff_head_cache of size 224 The buggy address is located 192 bytes inside of freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60) Memory state around the buggy address: ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ==================================================================
CVE-2026-31420: In the Linux kernel, the following vulnerability has been resolved: bridge: mrp: reject zero test interval to avoid OOM panic br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied interval value from netlink without validation. When interval is 0, usecs_to_jiffies(0) yields 0, causing the delayed work (br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule itself with zero delay. This creates a tight loop on system_percpu_wq that allocates and transmits MRP test frames at maximum rate, exhausting all system memory and causing a kernel panic via OOM deadlock. The same zero-interval issue applies to br_mrp_start_in_test_parse() for interconnect test frames. Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both IFLA_BRIDGE_MRP_START_TEST_INTERVAL and IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the netlink attribute parsing layer before the value ever reaches the workqueue scheduling code. This is consistent with how other bridge subsystems (br_fdb, br_mst) enforce range constraints on netlink attributes.
CVE-2026-31421: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_fw: fix NULL pointer dereference on shared blocks The old-method path in fw_classify() calls tcf_block_q() and dereferences q->handle. Shared blocks leave block->q NULL, causing a NULL deref when an empty cls_fw filter is attached to a shared block and a packet with a nonzero major skb mark is classified. Reject the configuration in fw_change() when the old method (no TCA_OPTIONS) is used on a shared block, since fw_classify()'s old-method path needs block->q which is NULL for shared blocks. The fixed null-ptr-deref calling stack: KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:fw_classify (net/sched/cls_fw.c:81) Call Trace: tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860) tc_run (net/core/dev.c:4401) __dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790)
CVE-2026-31422: In the Linux kernel, the following vulnerability has been resolved: net/sched: cls_flow: fix NULL pointer dereference on shared blocks flow_change() calls tcf_block_q() and dereferences q->handle to derive a default baseclass. Shared blocks leave block->q NULL, causing a NULL deref when a flow filter without a fully qualified baseclass is created on a shared block. Check tcf_block_shared() before accessing block->q and return -EINVAL for shared blocks. This avoids the null-deref shown below: ======================================================================= KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f] RIP: 0010:flow_change (net/sched/cls_flow.c:508) Call Trace: tc_new_tfilter (net/sched/cls_api.c:2432) rtnetlink_rcv_msg (net/core/rtnetlink.c:6980) [...] =======================================================================
CVE-2026-31423: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_hfsc: fix divide-by-zero in rtsc_min() m2sm() converts a u32 slope to a u64 scaled value. For large inputs (e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores the difference of two such u64 values in a u32 variable `dsm` and uses it as a divisor. When the difference is exactly 2^32 the truncation yields zero, causing a divide-by-zero oops in the concave-curve intersection path: Oops: divide error: 0000 RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601) Call Trace: init_ed (net/sched/sch_hfsc.c:629) hfsc_enqueue (net/sched/sch_hfsc.c:1569) [...] Widen `dsm` to u64 and replace do_div() with div64_u64() so the full difference is preserved.
CVE-2026-31424: In the Linux kernel, the following vulnerability has been resolved: netfilter: x_tables: restrict xt_check_match/xt_check_target extensions for NFPROTO_ARP Weiming Shi says: xt_match and xt_target structs registered with NFPROTO_UNSPEC can be loaded by any protocol family through nft_compat. When such a match/target sets .hooks to restrict which hooks it may run on, the bitmask uses NF_INET_* constants. This is only correct for families whose hook layout matches NF_INET_*: IPv4, IPv6, INET, and bridge all share the same five hooks (PRE_ROUTING ... POST_ROUTING). ARP only has three hooks (IN=0, OUT=1, FORWARD=2) with different semantics. Because NF_ARP_OUT == 1 == NF_INET_LOCAL_IN, the .hooks validation silently passes for the wrong reasons, allowing matches to run on ARP chains where the hook assumptions (e.g. state->in being set on input hooks) do not hold. This leads to NULL pointer dereferences; xt_devgroup is one concrete example: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000044: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000220-0x0000000000000227] RIP: 0010:devgroup_mt+0xff/0x350 Call Trace: <TASK> nft_match_eval (net/netfilter/nft_compat.c:407) nft_do_chain (net/netfilter/nf_tables_core.c:285) nft_do_chain_arp (net/netfilter/nft_chain_filter.c:61) nf_hook_slow (net/netfilter/core.c:623) arp_xmit (net/ipv4/arp.c:666) </TASK> Kernel panic - not syncing: Fatal exception in interrupt Fix it by restricting arptables to NFPROTO_ARP extensions only. Note that arptables-legacy only supports: - arpt_CLASSIFY - arpt_mangle - arpt_MARK that provide explicit NFPROTO_ARP match/target declarations.
CVE-2026-31425: In the Linux kernel, the following vulnerability has been resolved: rds: ib: reject FRMR registration before IB connection is established rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with i_cm_id = NULL because the connection worker has not yet called rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses the control message before any connection establishment, allowing rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the kernel. The existing guard in rds_ib_reg_frmr() only checks for !ic (added in commit 9e630bcb7701), which does not catch this case since ic is allocated early and is always non-NULL once the connection object exists. KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920 Call Trace: rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167) rds_ib_map_frmr (net/rds/ib_frmr.c:252) rds_ib_reg_frmr (net/rds/ib_frmr.c:430) rds_ib_get_mr (net/rds/ib_rdma.c:615) __rds_rdma_map (net/rds/rdma.c:295) rds_cmsg_rdma_map (net/rds/rdma.c:860) rds_sendmsg (net/rds/send.c:1363) ____sys_sendmsg do_syscall_64 Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all non-NULL before proceeding with FRMR registration, mirroring the guard already present in rds_ib_post_inv(). Return -ENODEV when the connection is not ready, which the existing error handling in rds_cmsg_send() converts to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to start the connection worker.
CVE-2026-31426: In the Linux kernel, the following vulnerability has been resolved: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup() When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware platforms, it has already started the EC and installed the address space handler with the struct acpi_ec pointer as handler context. However, acpi_ec_setup() propagates the error without any cleanup. The caller acpi_ec_add() then frees the struct acpi_ec for non-boot instances, leaving a dangling handler context in ACPICA. Any subsequent AML evaluation that accesses an EC OpRegion field dispatches into acpi_ec_space_handler() with the freed pointer, causing a use-after-free: BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289) Write of size 8 at addr ffff88800721de38 by task init/1 Call Trace: <TASK> mutex_lock (kernel/locking/mutex.c:289) acpi_ec_space_handler (drivers/acpi/ec.c:1362) acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293) acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246) acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509) acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700) acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327) acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392) </TASK> Allocated by task 1: acpi_ec_alloc (drivers/acpi/ec.c:1424) acpi_ec_add (drivers/acpi/ec.c:1692) Freed by task 1: kfree (mm/slub.c:6876) acpi_ec_add (drivers/acpi/ec.c:1751) The bug triggers on reduced-hardware EC platforms (ec->gpe < 0) when the GPIO IRQ provider defers probing. Once the stale handler exists, any unprivileged sysfs read that causes AML to touch an EC OpRegion (battery, thermal, backlight) exercises the dangling pointer. Fix this by calling ec_remove_handlers() in the error path of acpi_ec_setup() before clearing first_ec. ec_remove_handlers() checks each EC_FLAGS_* bit before acting, so it is safe to call regardless of how far ec_install_handlers() progressed: -ENODEV (handler not installed): only calls acpi_ec_stop() -EPROBE_DEFER (handler installed): removes handler, stops EC
CVE-2026-31427: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp process_sdp() declares union nf_inet_addr rtp_addr on the stack and passes it to the nf_nat_sip sdp_session hook after walking the SDP media descriptions. However rtp_addr is only initialized inside the media loop when a recognized media type with a non-zero port is found. If the SDP body contains no m= lines, only inactive media sections (m=audio 0 ...) or only unrecognized media types, rtp_addr is never assigned. Despite that, the function still calls hooks->sdp_session() with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack value as an IP address and rewrite the SDP session owner and connection lines with it. With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this results in the session-level o= and c= addresses being rewritten to 0.0.0.0 for inactive SDP sessions. Without stack auto-init the rewritten address is whatever happened to be on the stack. Fix this by pre-initializing rtp_addr from the session-level connection address (caddr) when available, and tracking via a have_rtp_addr flag whether any valid address was established. Skip the sdp_session hook entirely when no valid address exists.
CVE-2026-31428: In the Linux kernel, the following vulnerability has been resolved: netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD __build_packet_message() manually constructs the NFULA_PAYLOAD netlink attribute using skb_put() and skb_copy_bits(), bypassing the standard nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes are allocated (including NLA alignment padding), only data_len bytes of actual packet data are copied. The trailing nla_padlen(data_len) bytes (1-3 when data_len is not 4-byte aligned) are never initialized, leaking stale heap contents to userspace via the NFLOG netlink socket. Replace the manual attribute construction with nla_reserve(), which handles the tailroom check, header setup, and padding zeroing via __nla_reserve(). The subsequent skb_copy_bits() fills in the payload data on top of the properly initialized attribute.
CVE-2026-31431: In the Linux kernel, the following vulnerability has been resolved: crypto: algif_aead - Revert to operating out-of-place This mostly reverts commit 72548b093ee3 except for the copying of the associated data. There is no benefit in operating in-place in algif_aead since the source and destination come from different mappings. Get rid of all the complexity added for in-place operation and just copy the AD directly.
CVE-2026-31432: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix OOB write in QUERY_INFO for compound requests When a compound request such as READ + QUERY_INFO(Security) is received, and the first command (READ) consumes most of the response buffer, ksmbd could write beyond the allocated buffer while building a security descriptor. The root cause was that smb2_get_info_sec() checked buffer space using ppntsd_size from xattr, while build_sec_desc() often synthesized a significantly larger descriptor from POSIX ACLs. This patch introduces smb_acl_sec_desc_scratch_len() to accurately compute the final descriptor size beforehand, performs proper buffer checking with smb2_calc_max_out_buf_len(), and uses exact-sized allocation + iov pinning.
CVE-2026-31433: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix potencial OOB in get_file_all_info() for compound requests When a compound request consists of QUERY_DIRECTORY + QUERY_INFO (FILE_ALL_INFORMATION) and the first command consumes nearly the entire max_trans_size, get_file_all_info() would blindly call smbConvertToUTF16() with PATH_MAX, causing out-of-bounds write beyond the response buffer. In get_file_all_info(), there was a missing validation check for the client-provided OutputBufferLength before copying the filename into FileName field of the smb2_file_all_info structure. If the filename length exceeds the available buffer space, it could lead to potential buffer overflows or memory corruption during smbConvertToUTF16 conversion. This calculating the actual free buffer size using smb2_calc_max_out_buf_len() and returning -EINVAL if the buffer is insufficient and updating smbConvertToUTF16 to use the actual filename length (clamped by PATH_MAX) to ensure a safe copy operation.
CVE-2026-31434: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix leak of kobject name for sub-group space_info When create_space_info_sub_group() allocates elements of space_info->sub_group[], kobject_init_and_add() is called for each element via btrfs_sysfs_add_space_info_type(). However, when check_removing_space_info() frees these elements, it does not call btrfs_sysfs_remove_space_info() on them. As a result, kobject_put() is not called and the associated kobj->name objects are leaked. This memory leak is reproduced by running the blktests test case zbd/009 on kernels built with CONFIG_DEBUG_KMEMLEAK. The kmemleak feature reports the following error: unreferenced object 0xffff888112877d40 (size 16): comm "mount", pid 1244, jiffies 4294996972 hex dump (first 16 bytes): 64 61 74 61 2d 72 65 6c 6f 63 00 c4 c6 a7 cb 7f data-reloc...... backtrace (crc 53ffde4d): __kmalloc_node_track_caller_noprof+0x619/0x870 kstrdup+0x42/0xc0 kobject_set_name_vargs+0x44/0x110 kobject_init_and_add+0xcf/0x150 btrfs_sysfs_add_space_info_type+0xfc/0x210 [btrfs] create_space_info_sub_group.constprop.0+0xfb/0x1b0 [btrfs] create_space_info+0x211/0x320 [btrfs] btrfs_init_space_info+0x15a/0x1b0 [btrfs] open_ctree+0x33c7/0x4a50 [btrfs] btrfs_get_tree.cold+0x9f/0x1ee [btrfs] vfs_get_tree+0x87/0x2f0 vfs_cmd_create+0xbd/0x280 __do_sys_fsconfig+0x3df/0x990 do_syscall_64+0x136/0x1540 entry_SYSCALL_64_after_hwframe+0x76/0x7e To avoid the leak, call btrfs_sysfs_remove_space_info() instead of kfree() for the elements.
CVE-2026-31441: In the Linux kernel, the following vulnerability has been resolved: dmaengine: idxd: Fix memory leak when a wq is reset idxd_wq_disable_cleanup() which is called from the reset path for a workqueue, sets the wq type to NONE, which for other parts of the driver mean that the wq is empty (all its resources were released). Only set the wq type to NONE after its resources are released.
CVE-2026-31446: In the Linux kernel, the following vulnerability has been resolved: ext4: fix use-after-free in update_super_work when racing with umount Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups reads during unmount. However, this introduced a use-after-free because update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which accesses the kobject's kernfs_node after it has been freed by kobject_del() in ext4_unregister_sysfs(): update_super_work ext4_put_super ----------------- -------------- ext4_unregister_sysfs(sb) kobject_del(&sbi->s_kobj) __kobject_del() sysfs_remove_dir() kobj->sd = NULL sysfs_put(sd) kernfs_put() // RCU free ext4_notify_error_sysfs(sbi) sysfs_notify(&sbi->s_kobj) kn = kobj->sd // stale pointer kernfs_get(kn) // UAF on freed kernfs_node ext4_journal_destroy() flush_work(&sbi->s_sb_upd_work) Instead of reordering the teardown sequence, fix this by making ext4_notify_error_sysfs() detect that sysfs has already been torn down by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call in that case. A dedicated mutex (s_error_notify_mutex) serializes ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs() to prevent TOCTOU races where the kobject could be deleted between the state_in_sysfs check and the sysfs_notify() call.
CVE-2026-31447: In the Linux kernel, the following vulnerability has been resolved: ext4: reject mount if bigalloc with s_first_data_block != 0 bigalloc with s_first_data_block != 0 is not supported, reject mounting it.
CVE-2026-31448: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid infinite loops caused by residual data On the mkdir/mknod path, when mapping logical blocks to physical blocks, if inserting a new extent into the extent tree fails (in this example, because the file system disabled the huge file feature when marking the inode as dirty), ext4_ext_map_blocks() only calls ext4_free_blocks() to reclaim the physical block without deleting the corresponding data in the extent tree. This causes subsequent mkdir operations to reference the previously reclaimed physical block number again, even though this physical block is already being used by the xattr block. Therefore, a situation arises where both the directory and xattr are using the same buffer head block in memory simultaneously. The above causes ext4_xattr_block_set() to enter an infinite loop about "inserted" and cannot release the inode lock, ultimately leading to the 143s blocking problem mentioned in [1]. If the metadata is corrupted, then trying to remove some extent space can do even more harm. Also in case EXT4_GET_BLOCKS_DELALLOC_RESERVE was passed, remove space wrongly update quota information. Jan Kara suggests distinguishing between two cases: 1) The error is ENOSPC or EDQUOT - in this case the filesystem is fully consistent and we must maintain its consistency including all the accounting. However these errors can happen only early before we've inserted the extent into the extent tree. So current code works correctly for this case. 2) Some other error - this means metadata is corrupted. We should strive to do as few modifications as possible to limit damage. So I'd just skip freeing of allocated blocks. [1] INFO: task syz.0.17:5995 blocked for more than 143 seconds. Call Trace: inode_lock_nested include/linux/fs.h:1073 [inline] __start_dirop fs/namei.c:2923 [inline] start_dirop fs/namei.c:2934 [inline]
CVE-2026-31449: In the Linux kernel, the following vulnerability has been resolved: ext4: validate p_idx bounds in ext4_ext_correct_indexes ext4_ext_correct_indexes() walks up the extent tree correcting index entries when the first extent in a leaf is modified. Before accessing path[k].p_idx->ei_block, there is no validation that p_idx falls within the valid range of index entries for that level. If the on-disk extent header contains a corrupted or crafted eh_entries value, p_idx can point past the end of the allocated buffer, causing a slab-out-of-bounds read. Fix this by validating path[k].p_idx against EXT_LAST_INDEX() at both access sites: before the while loop and inside it. Return -EFSCORRUPTED if the index pointer is out of range, consistent with how other bounds violations are handled in the ext4 extent tree code.
CVE-2026-31450: In the Linux kernel, the following vulnerability has been resolved: ext4: publish jinode after initialization ext4_inode_attach_jinode() publishes ei->jinode to concurrent users. It used to set ei->jinode before jbd2_journal_init_jbd_inode(), allowing a reader to observe a non-NULL jinode with i_vfs_inode still unset. The fast commit flush path can then pass this jinode to jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and may crash. Below is the crash I observe: ``` BUG: unable to handle page fault for address: 000000010beb47f4 PGD 110e51067 P4D 110e51067 PUD 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014 RIP: 0010:xas_find_marked+0x3d/0x2e0 Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02 RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246 RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003 RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10 RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000 R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88 FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> filemap_get_folios_tag+0x87/0x2a0 __filemap_fdatawait_range+0x5f/0xd0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __schedule+0x3e7/0x10c0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? cap_safe_nice+0x37/0x70 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 filemap_fdatawait_range_keep_errors+0x12/0x40 ext4_fc_commit+0x697/0x8b0 ? ext4_file_write_iter+0x64b/0x950 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? vfs_write+0x356/0x480 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ext4_sync_file+0xf7/0x370 do_fsync+0x3b/0x80 ? syscall_trace_enter+0x108/0x1d0 __x64_sys_fdatasync+0x16/0x20 do_syscall_64+0x62/0x2c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... ``` Fix this by initializing the jbd2_inode first. Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after initialization. Readers use READ_ONCE() to fetch the pointer.
CVE-2026-31451: In the Linux kernel, the following vulnerability has been resolved: ext4: replace BUG_ON with proper error handling in ext4_read_inline_folio Replace BUG_ON() with proper error handling when inline data size exceeds PAGE_SIZE. This prevents kernel panic and allows the system to continue running while properly reporting the filesystem corruption. The error is logged via ext4_error_inode(), the buffer head is released to prevent memory leak, and -EFSCORRUPTED is returned to indicate filesystem corruption.
CVE-2026-31452: In the Linux kernel, the following vulnerability has been resolved: ext4: convert inline data to extents when truncate exceeds inline size Add a check in ext4_setattr() to convert files from inline data storage to extent-based storage when truncate() grows the file size beyond the inline capacity. This prevents the filesystem from entering an inconsistent state where the inline data flag is set but the file size exceeds what can be stored inline. Without this fix, the following sequence causes a kernel BUG_ON(): 1. Mount filesystem with inode that has inline flag set and small size 2. truncate(file, 50MB) - grows size but inline flag remains set 3. sendfile() attempts to write data 4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity) The crash occurs because ext4_write_inline_data() expects inline storage to accommodate the write, but the actual inline capacity (~60 bytes for i_block + ~96 bytes for xattrs) is far smaller than the file size and write request. The fix checks if the new size from setattr exceeds the inode's actual inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to extent-based storage before proceeding with the size change. This addresses the root cause by ensuring the inline data flag and file size remain consistent during truncate operations.
CVE-2026-31453: In the Linux kernel, the following vulnerability has been resolved: xfs: avoid dereferencing log items after push callbacks After xfsaild_push_item() calls iop_push(), the log item may have been freed if the AIL lock was dropped during the push. Background inode reclaim or the dquot shrinker can free the log item while the AIL lock is not held, and the tracepoints in the switch statement dereference the log item after iop_push() returns. Fix this by capturing the log item type, flags, and LSN before calling xfsaild_push_item(), and introducing a new xfs_ail_push_class trace event class that takes these pre-captured values and the ailp pointer instead of the log item pointer.
CVE-2026-31454: In the Linux kernel, the following vulnerability has been resolved: xfs: save ailp before dropping the AIL lock in push callbacks In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock is dropped to perform buffer IO. Once the cluster buffer no longer protects the log item from reclaim, the log item may be freed by background reclaim or the dquot shrinker. The subsequent spin_lock() call dereferences lip->li_ailp, which is a use-after-free. Fix this by saving the ailp pointer in a local variable while the AIL lock is held and the log item is guaranteed to be valid.
CVE-2026-31455: In the Linux kernel, the following vulnerability has been resolved: xfs: stop reclaim before pushing AIL during unmount The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while background reclaim and inodegc are still running. This is broken independently of any use-after-free issues - background reclaim and inodegc should not be running while the AIL is being pushed during unmount, as inodegc can dirty and insert inodes into the AIL during the flush, and background reclaim can race to abort and free dirty inodes. Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background reclaim before pushing the AIL. Stop inodegc before cancelling m_reclaim_work because the inodegc worker can re-queue m_reclaim_work via xfs_inodegc_set_reclaimable.
CVE-2026-31458: In the Linux kernel, the following vulnerability has been resolved: mm/damon/sysfs: check contexts->nr before accessing contexts_arr[0] Multiple sysfs command paths dereference contexts_arr[0] without first verifying that kdamond->contexts->nr == 1. A user can set nr_contexts to 0 via sysfs while DAMON is running, causing NULL pointer dereferences. In more detail, the issue can be triggered by privileged users like below. First, start DAMON and make contexts directory empty (kdamond->contexts->nr == 0). # damo start # cd /sys/kernel/mm/damon/admin/kdamonds/0 # echo 0 > contexts/nr_contexts Then, each of below commands will cause the NULL pointer dereference. # echo update_schemes_stats > state # echo update_schemes_tried_regions > state # echo update_schemes_tried_bytes > state # echo update_schemes_effective_quotas > state # echo update_tuned_intervals > state Guard all commands (except OFF) at the entry point of damon_sysfs_handle_cmd().
CVE-2026-31462: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: prevent immediate PASID reuse case PASID resue could cause interrupt issue when process immediately runs into hw state left by previous process exited with the same PASID, it's possible that page faults are still pending in the IH ring buffer when the process exits and frees up its PASID. To prevent the case, it uses idr cyclic allocator same as kernel pid's. (cherry picked from commit 8f1de51f49be692de137c8525106e0fce2d1912d)
CVE-2026-31464: In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Fix OOB access in ibmvfc_discover_targets_done() A malicious or compromised VIO server can return a num_written value in the discover targets MAD response that exceeds max_targets. This value is stored directly in vhost->num_targets without validation, and is then used as the loop bound in ibmvfc_alloc_targets() to index into disc_buf[], which is only allocated for max_targets entries. Indices at or beyond max_targets access kernel memory outside the DMA-coherent allocation. The out-of-bounds data is subsequently embedded in Implicit Logout and PLOGI MADs that are sent back to the VIO server, leaking kernel memory. Fix by clamping num_written to max_targets before storing it.
CVE-2026-31466: In the Linux kernel, the following vulnerability has been resolved: mm/huge_memory: fix folio isn't locked in softleaf_to_folio() On arm64 server, we found folio that get from migration entry isn't locked in softleaf_to_folio(). This issue triggers when mTHP splitting and zap_nonpresent_ptes() races, and the root cause is lack of memory barrier in softleaf_to_folio(). The race is as follows: CPU0 CPU1 deferred_split_scan() zap_nonpresent_ptes() lock folio split_folio() unmap_folio() change ptes to migration entries __split_folio_to_order() softleaf_to_folio() set flags(including PG_locked) for tail pages folio = pfn_folio(softleaf_to_pfn(entry)) smp_wmb() VM_WARN_ON_ONCE(!folio_test_locked(folio)) prep_compound_page() for tail pages In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages are visible before the tail page becomes non-compound. smp_wmb() should be paired with smp_rmb() in softleaf_to_folio(), which is missed. As a result, if zap_nonpresent_ptes() accesses migration entry that stores tail pfn, softleaf_to_folio() may see the updated compound_head of tail page before page->flags. This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio() because of the race between folio split and zap_nonpresent_ptes() leading to a folio incorrectly undergoing modification without a folio lock being held. This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further swapops predicates"), which in merged in v6.19-rc1. To fix it, add missing smp_rmb() if the softleaf entry is migration entry in softleaf_to_folio() and softleaf_to_page(). [tujinjiang@huawei.com: update function name and comments]
CVE-2026-31467: In the Linux kernel, the following vulnerability has been resolved: erofs: add GFP_NOIO in the bio completion if needed The bio completion path in the process context (e.g. dm-verity) will directly call into decompression rather than trigger another workqueue context for minimal scheduling latencies, which can then call vm_map_ram() with GFP_KERNEL. Due to insufficient memory, vm_map_ram() may generate memory swapping I/O, which can cause submit_bio_wait to deadlock in some scenarios. Trimmed down the call stack, as follows: f2fs_submit_read_io submit_bio //bio_list is initialized. mmc_blk_mq_recovery z_erofs_endio vm_map_ram __pte_alloc_kernel __alloc_pages_direct_reclaim shrink_folio_list __swap_writepage submit_bio_wait //bio_list is non-NULL, hang!!! Use memalloc_noio_{save,restore}() to wrap up this path.
CVE-2026-31469: In the Linux kernel, the following vulnerability has been resolved: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared and napi_tx is false A UAF issue occurs when the virtio_net driver is configured with napi_tx=N and the device's IFF_XMIT_DST_RELEASE flag is cleared (e.g., during the configuration of tc route filter rules). When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack expects the driver to hold the reference to skb->dst until the packet is fully transmitted and freed. In virtio_net with napi_tx=N, skbs may remain in the virtio transmit ring for an extended period. If the network namespace is destroyed while these skbs are still pending, the corresponding dst_ops structure has freed. When a subsequent packet is transmitted, free_old_xmit() is triggered to clean up old skbs. It then calls dst_release() on the skb associated with the stale dst_entry. Since the dst_ops (referenced by the dst_entry) has already been freed, a UAF kernel paging request occurs. fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release the dst reference before the skb is queued in virtio_net. Call Trace: Unable to handle kernel paging request at virtual address ffff80007e150000 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT ... percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P) dst_release+0xe0/0x110 net/core/dst.c:177 skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177 sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255 dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469 napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527 __free_old_xmit+0x164/0x230 drivers/net/virtio_net.c:611 [virtio_net] free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net] start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net] ... Reproduction Steps: NETDEV="enp3s0" config_qdisc_route_filter() { tc qdisc del dev $NETDEV root tc qdisc add dev $NETDEV root handle 1: prio tc filter add dev $NETDEV parent 1:0 \ protocol ip prio 100 route to 100 flowid 1:1 ip route add 192.168.1.100/32 dev $NETDEV realm 100 } test_ns() { ip netns add testns ip link set $NETDEV netns testns ip netns exec testns ifconfig $NETDEV 10.0.32.46/24 ip netns exec testns ping -c 1 10.0.32.1 ip netns del testns } config_qdisc_route_filter test_ns sleep 2 test_ns
CVE-2026-31473: In the Linux kernel, the following vulnerability has been resolved: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0) queue teardown paths. This can race request object cleanup against vb2 queue cancellation and lead to use-after-free reports. We already serialize request queueing against STREAMON/OFF with req_queue_mutex. Extend that serialization to REQBUFS, and also take the same mutex in media_request_ioctl_reinit() so REINIT is in the same exclusion domain. This keeps request cleanup and queue cancellation from running in parallel for request-capable devices.
CVE-2026-31476: In the Linux kernel, the following vulnerability has been resolved: ksmbd: do not expire session on binding failure When a multichannel session binding request fails (e.g. wrong password), the error path unconditionally sets sess->state = SMB2_SESSION_EXPIRED. However, during binding, sess points to the target session looked up via ksmbd_session_lookup_slowpath() -- which belongs to another connection's user. This allows a remote attacker to invalidate any active session by simply sending a binding request with a wrong password (DoS). Fix this by skipping session expiration when the failed request was a binding attempt, since the session does not belong to the current connection. The reference taken by ksmbd_session_lookup_slowpath() is still correctly released via ksmbd_user_session_put().
CVE-2026-31477: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix memory leaks and NULL deref in smb2_lock() smb2_lock() has three error handling issues after list_del() detaches smb_lock from lock_list at no_check_cl: 1) If vfs_lock_file() returns an unexpected error in the non-UNLOCK path, goto out leaks smb_lock and its flock because the out: handler only iterates lock_list and rollback_list, neither of which contains the detached smb_lock. 2) If vfs_lock_file() returns -ENOENT in the UNLOCK path, goto out leaks smb_lock and flock for the same reason. The error code returned to the dispatcher is also stale. 3) In the rollback path, smb_flock_init() can return NULL on allocation failure. The result is dereferenced unconditionally, causing a kernel NULL pointer dereference. Add a NULL check to prevent the crash and clean up the bookkeeping; the VFS lock itself cannot be rolled back without the allocation and will be released at file or connection teardown. Fix cases 1 and 2 by hoisting the locks_free_lock()/kfree() to before the if(!rc) check in the UNLOCK branch so all exit paths share one free site, and by freeing smb_lock and flock before goto out in the non-UNLOCK branch. Propagate the correct error code in both cases. Fix case 3 by wrapping the VFS unlock in an if(rlock) guard and adding a NULL check for locks_free_lock(rlock) in the shared cleanup. Found via call-graph analysis using sqry.
CVE-2026-31478: In the Linux kernel, the following vulnerability has been resolved: ksmbd: replace hardcoded hdr2_len with offsetof() in smb2_calc_max_out_buf_len() After this commit (e2b76ab8b5c9 "ksmbd: add support for read compound"), response buffer management was changed to use dynamic iov array. In the new design, smb2_calc_max_out_buf_len() expects the second argument (hdr2_len) to be the offset of ->Buffer field in the response structure, not a hardcoded magic number. Fix the remaining call sites to use the correct offsetof() value.
CVE-2026-31480: In the Linux kernel, the following vulnerability has been resolved: tracing: Fix potential deadlock in cpu hotplug with osnoise The following sequence may leads deadlock in cpu hotplug: task1 task2 task3 ----- ----- ----- mutex_lock(&interface_lock) [CPU GOING OFFLINE] cpus_write_lock(); osnoise_cpu_die(); kthread_stop(task3); wait_for_completion(); osnoise_sleep(); mutex_lock(&interface_lock); cpus_read_lock(); [DEAD LOCK] Fix by swap the order of cpus_read_lock() and mutex_lock(&interface_lock).
CVE-2026-31483: In the Linux kernel, the following vulnerability has been resolved: s390/syscalls: Add spectre boundary for syscall dispatch table The s390 syscall number is directly controlled by userspace, but does not have an array_index_nospec() boundary to prevent access past the syscall function pointer tables.
CVE-2026-31485: In the Linux kernel, the following vulnerability has been resolved: spi: spi-fsl-lpspi: fix teardown order issue (UAF) There is a teardown order issue in the driver. The SPI controller is registered using devm_spi_register_controller(), which delays unregistration of the SPI controller until after the fsl_lpspi_remove() function returns. As the fsl_lpspi_remove() function synchronously tears down the DMA channels, a running SPI transfer triggers the following NULL pointer dereference due to use after free: | fsl_lpspi 42550000.spi: I/O Error in DMA RX | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [...] | Call trace: | fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi] | fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi] | spi_transfer_one_message+0x49c/0x7c8 | __spi_pump_transfer_message+0x120/0x420 | __spi_sync+0x2c4/0x520 | spi_sync+0x34/0x60 | spidev_message+0x20c/0x378 [spidev] | spidev_ioctl+0x398/0x750 [spidev] [...] Switch from devm_spi_register_controller() to spi_register_controller() in fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in fsl_lpspi_remove().
CVE-2026-31486: In the Linux kernel, the following vulnerability has been resolved: hwmon: (pmbus/core) Protect regulator operations with mutex The regulator operations pmbus_regulator_get_voltage(), pmbus_regulator_set_voltage(), and pmbus_regulator_list_voltage() access PMBus registers and shared data but were not protected by the update_lock mutex. This could lead to race conditions. However, adding mutex protection directly to these functions causes a deadlock because pmbus_regulator_notify() (which calls regulator_notifier_call_chain()) is often called with the mutex already held (e.g., from pmbus_fault_handler()). If a regulator callback then calls one of the now-protected voltage functions, it will attempt to acquire the same mutex. Rework pmbus_regulator_notify() to utilize a worker function to send notifications outside of the mutex protection. Events are stored as atomics in a per-page bitmask and processed by the worker. Initialize the worker and its associated data during regulator registration, and ensure it is cancelled on device removal using devm_add_action_or_reset(). While at it, remove the unnecessary include of linux/of.h.
CVE-2026-31487: In the Linux kernel, the following vulnerability has been resolved: spi: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Also note that we do not enable the driver_override feature of struct bus_type, as SPI - in contrast to most other buses - passes "" to sysfs_emit() when the driver_override pointer is NULL. Thus, printing "\n" instead of "(null)\n".
CVE-2026-31488: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Do not skip unrelated mode changes in DSC validation Starting with commit 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in atomic check"), amdgpu resets the CRTC state mode_changed flag to false when recomputing the DSC configuration results in no timing change for a particular stream. However, this is incorrect in scenarios where a change in MST/DSC configuration happens in the same KMS commit as another (unrelated) mode change. For example, the integrated panel of a laptop may be configured differently (e.g., HDR enabled/disabled) depending on whether external screens are attached. In this case, plugging in external DP-MST screens may result in the mode_changed flag being dropped incorrectly for the integrated panel if its DSC configuration did not change during precomputation in pre_validate_dsc(). At this point, however, dm_update_crtc_state() has already created new streams for CRTCs with DSC-independent mode changes. In turn, amdgpu_dm_commit_streams() will never release the old stream, resulting in a memory leak. amdgpu_dm_atomic_commit_tail() will never acquire a reference to the new stream either, which manifests as a use-after-free when the stream gets disabled later on: BUG: KASAN: use-after-free in dc_stream_release+0x25/0x90 [amdgpu] Write of size 4 at addr ffff88813d836524 by task kworker/9:9/29977 Workqueue: events drm_mode_rmfb_work_fn Call Trace: <TASK> dump_stack_lvl+0x6e/0xa0 print_address_description.constprop.0+0x88/0x320 ? dc_stream_release+0x25/0x90 [amdgpu] print_report+0xfc/0x1ff ? srso_alias_return_thunk+0x5/0xfbef5 ? __virt_addr_valid+0x225/0x4e0 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_report+0xe1/0x180 ? dc_stream_release+0x25/0x90 [amdgpu] kasan_check_range+0x125/0x200 dc_stream_release+0x25/0x90 [amdgpu] dc_state_destruct+0x14d/0x5c0 [amdgpu] dc_state_release.part.0+0x4e/0x130 [amdgpu] dm_atomic_destroy_state+0x3f/0x70 [amdgpu] drm_atomic_state_default_clear+0x8ee/0xf30 ? drm_mode_object_put.part.0+0xb1/0x130 __drm_atomic_state_free+0x15c/0x2d0 atomic_remove_fb+0x67e/0x980 Since there is no reliable way of figuring out whether a CRTC has unrelated mode changes pending at the time of DSC validation, remember the value of the mode_changed flag from before the point where a CRTC was marked as potentially affected by a change in DSC configuration. Reset the mode_changed flag to this earlier value instead in pre_validate_dsc(). (cherry picked from commit cc7c7121ae082b7b82891baa7280f1ff2608f22b)
CVE-2026-31489: In the Linux kernel, the following vulnerability has been resolved: spi: meson-spicc: Fix double-put in remove path meson_spicc_probe() registers the controller with devm_spi_register_controller(), so teardown already drops the controller reference via devm cleanup. Calling spi_controller_put() again in meson_spicc_remove() causes a double-put.
CVE-2026-31492: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Initialize free_qp completion before using it In irdma_create_qp, if ib_copy_to_udata fails, it will call irdma_destroy_qp to clean up which will attempt to wait on the free_qp completion, which is not initialized yet. Fix this by initializing the completion before the ib_copy_to_udata call.
CVE-2026-31493: In the Linux kernel, the following vulnerability has been resolved: RDMA/efa: Fix use of completion ctx after free On admin queue completion handling, if the admin command completed with error we print data from the completion context. The issue is that we already freed the completion context in polling/interrupts handler which means we print data from context in an unknown state (it might be already used again). Change the admin submission flow so alloc/dealloc of the context will be symmetric and dealloc will be called after any potential use of the context.
CVE-2026-31494: In the Linux kernel, the following vulnerability has been resolved: net: macb: use the current queue number for stats There's a potential mismatch between the memory reserved for statistics and the amount of memory written. gem_get_sset_count() correctly computes the number of stats based on the active queues, whereas gem_get_ethtool_stats() indiscriminately copies data using the maximum number of queues, and in the case the number of active queues is less than MACB_MAX_QUEUES, this results in a OOB write as observed in the KASAN splat. ================================================================== BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78 [macb] Write of size 760 at addr ffff80008080b000 by task ethtool/1027 CPU: [...] Tainted: [E]=UNSIGNED_MODULE Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 print_report+0x384/0x5e0 kasan_report+0xa0/0xf0 kasan_check_range+0xe8/0x190 __asan_memcpy+0x54/0x98 gem_get_ethtool_stats+0x54/0x78 [macb 926c13f3af83b0c6fe64badb21ec87d5e93fcf65] dev_ethtool+0x1220/0x38c0 dev_ioctl+0x4ac/0xca8 sock_do_ioctl+0x170/0x1d8 sock_ioctl+0x484/0x5d8 __arm64_sys_ioctl+0x12c/0x1b8 invoke_syscall+0xd4/0x258 el0_svc_common.constprop.0+0xb4/0x240 do_el0_svc+0x48/0x68 el0_svc+0x40/0xf8 el0t_64_sync_handler+0xa0/0xe8 el0t_64_sync+0x1b0/0x1b8 The buggy address belongs to a 1-page vmalloc region starting at 0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff00000a333000 pfn:0xa333 flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff) raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ================================================================== Fix it by making sure the copied size only considers the active number of queues.
CVE-2026-31495: In the Linux kernel, the following vulnerability has been resolved: netfilter: ctnetlink: use netlink policy range checks Replace manual range and mask validations with netlink policy annotations in ctnetlink code paths, so that the netlink core rejects invalid values early and can generate extack errors. - CTA_PROTOINFO_TCP_STATE: reject values > TCP_CONNTRACK_SYN_SENT2 at policy level, removing the manual >= TCP_CONNTRACK_MAX check. - CTA_PROTOINFO_TCP_WSCALE_ORIGINAL/REPLY: reject values > TCP_MAX_WSCALE (14). The normal TCP option parsing path already clamps to this value, but the ctnetlink path accepted 0-255, causing undefined behavior when used as a u32 shift count. - CTA_FILTER_ORIG_FLAGS/REPLY_FLAGS: use NLA_POLICY_MASK with CTA_FILTER_F_ALL, removing the manual mask checks. - CTA_EXPECT_FLAGS: use NLA_POLICY_MASK with NF_CT_EXPECT_MASK, adding a new mask define grouping all valid expect flags. Extracted from a broader nf-next patch by Florian Westphal, scoped to ctnetlink for the fixes tree.
CVE-2026-31496: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_expect: skip expectations in other netns via proc Skip expectations that do not reside in this netns. Similar to e77e6ff502ea ("netfilter: conntrack: do not dump other netns's conntrack entries via proc").
CVE-2026-31497: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: clamp SCO altsetting table indices btusb_work() maps the number of active SCO links to USB alternate settings through a three-entry lookup table when CVSD traffic uses transparent voice settings. The lookup currently indexes alts[] with data->sco_num - 1 without first constraining sco_num to the number of available table entries. While the table only defines alternate settings for up to three SCO links, data->sco_num comes from hci_conn_num() and is used directly. Cap the lookup to the last table entry before indexing it so the driver keeps selecting the highest supported alternate setting without reading past alts[].
CVE-2026-31498: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop l2cap_config_req() processes CONFIG_REQ for channels in BT_CONNECTED state to support L2CAP reconfiguration (e.g. MTU changes). However, since both CONF_INPUT_DONE and CONF_OUTPUT_DONE are already set from the initial configuration, the reconfiguration path falls through to l2cap_ertm_init(), which re-initializes tx_q, srej_q, srej_list, and retrans_list without freeing the previous allocations and sets chan->sdu to NULL without freeing the existing skb. This leaks all previously allocated ERTM resources. Additionally, l2cap_parse_conf_req() does not validate the minimum value of remote_mps derived from the RFC max_pdu_size option. A zero value propagates to l2cap_segment_sdu() where pdu_len becomes zero, causing the while loop to never terminate since len is never decremented, exhausting all available memory. Fix the double-init by skipping l2cap_ertm_init() and l2cap_chan_ready() when the channel is already in BT_CONNECTED state, while still allowing the reconfiguration parameters to be updated through l2cap_parse_conf_req(). Also add a pdu_len zero check in l2cap_segment_sdu() as a safeguard.
CVE-2026-31500: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btintel: serialize btintel_hw_error() with hci_req_sync_lock btintel_hw_error() issues two __hci_cmd_sync() calls (HCI_OP_RESET and Intel exception-info retrieval) without holding hci_req_sync_lock(). This lets it race against hci_dev_do_close() -> btintel_shutdown_combined(), which also runs __hci_cmd_sync() under the same lock. When both paths manipulate hdev->req_status/req_rsp concurrently, the close path may free the response skb first, and the still-running hw_error path hits a slab-use-after-free in kfree_skb(). Wrap the whole recovery sequence in hci_req_sync_lock/unlock so it is serialized with every other synchronous HCI command issuer. Below is the data race report and the kasan report: BUG: data-race in __hci_cmd_sync_sk / btintel_shutdown_combined read of hdev->req_rsp at net/bluetooth/hci_sync.c:199 by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x114/0x670 drivers/bluetooth/btintel.c:254 hci_error_reset+0x348/0xa30 net/bluetooth/hci_core.c:1030 write/free by task ioctl/22580: btintel_shutdown_combined+0xd0/0x360 drivers/bluetooth/btintel.c:3648 hci_dev_close_sync+0x9ae/0x2c10 net/bluetooth/hci_sync.c:5246 hci_dev_do_close+0x232/0x460 net/bluetooth/hci_core.c:526 BUG: KASAN: slab-use-after-free in sk_skb_reason_drop+0x43/0x380 net/core/skbuff.c:1202 Read of size 4 at addr ffff888144a738dc by task kworker/u17:1/83: __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200 __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223 btintel_hw_error+0x186/0x670 drivers/bluetooth/btintel.c:260
CVE-2026-31502: In the Linux kernel, the following vulnerability has been resolved: team: fix header_ops type confusion with non-Ethernet ports Similar to commit 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()") team has the same class of header_ops type confusion. For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops directly. When the team device later calls dev_hard_header() or dev_parse_header(), these callbacks can run with the team net_device instead of the real lower device, so netdev_priv(dev) is interpreted as the wrong private type and can crash. The syzbot report shows a crash in bond_header_create(), but the root cause is in team: the topology is gre -> bond -> team, and team calls the inherited header_ops with its own net_device instead of the lower device, so bond_header_create() receives a team device and interprets netdev_priv() as bonding private data, causing a type confusion crash. Fix this by introducing team header_ops wrappers for create/parse, selecting a team port under RCU, and calling the lower device callbacks with port->dev, so each callback always sees the correct net_device context. Also pass the selected lower device to the lower parse callback, so recursion is bounded in stacked non-Ethernet topologies and parse callbacks always run with the correct device context.
CVE-2026-31503: In the Linux kernel, the following vulnerability has been resolved: udp: Fix wildcard bind conflict check when using hash2 When binding a udp_sock to a local address and port, UDP uses two hashes (udptable->hash and udptable->hash2) for collision detection. The current code switches to "hash2" when hslot->count > 10. "hash2" is keyed by local address and local port. "hash" is keyed by local port only. The issue can be shown in the following bind sequence (pseudo code): bind(fd1, "[fd00::1]:8888") bind(fd2, "[fd00::2]:8888") bind(fd3, "[fd00::3]:8888") bind(fd4, "[fd00::4]:8888") bind(fd5, "[fd00::5]:8888") bind(fd6, "[fd00::6]:8888") bind(fd7, "[fd00::7]:8888") bind(fd8, "[fd00::8]:8888") bind(fd9, "[fd00::9]:8888") bind(fd10, "[fd00::10]:8888") /* Correctly return -EADDRINUSE because "hash" is used * instead of "hash2". udp_lib_lport_inuse() detects the * conflict. */ bind(fail_fd, "[::]:8888") /* After one more socket is bound to "[fd00::11]:8888", * hslot->count exceeds 10 and "hash2" is used instead. */ bind(fd11, "[fd00::11]:8888") bind(fail_fd, "[::]:8888") /* succeeds unexpectedly */ The same issue applies to the IPv4 wildcard address "0.0.0.0" and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For example, if there are existing sockets bound to "192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or "[::ffff:0.0.0.0]:8888" can also miss the conflict when hslot->count > 10. TCP inet_csk_get_port() already has the correct check in inet_use_bhash2_on_bind(). Rename it to inet_use_hash2_on_bind() and move it to inet_hashtables.h so udp.c can reuse it in this fix.
CVE-2026-31504: In the Linux kernel, the following vulnerability has been resolved: net: fix fanout UAF in packet_release() via NETDEV_UP race `packet_release()` has a race window where `NETDEV_UP` can re-register a socket into a fanout group's `arr[]` array. The re-registration is not cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout array. `packet_release()` does NOT zero `po->num` in its `bind_lock` section. After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex` still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)` that already found the socket in `sklist` can re-register the hook. For fanout sockets, this re-registration calls `__fanout_link(sk, po)` which adds the socket back into `f->arr[]` and increments `f->num_members`, but does NOT increment `f->sk_ref`. The fix sets `po->num` to zero in `packet_release` while `bind_lock` is held to prevent NETDEV_UP from linking, preventing the race window. This bug was found following an additional audit with Claude Code based on CVE-2025-38617.
CVE-2026-31505: In the Linux kernel, the following vulnerability has been resolved: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats() iavf incorrectly uses real_num_tx_queues for ETH_SS_STATS. Since the value could change in runtime, we should use num_tx_queues instead. Moreover iavf_get_ethtool_stats() uses num_active_queues while iavf_get_sset_count() and iavf_get_stat_strings() use real_num_tx_queues, which triggers out-of-bounds writes when we do "ethtool -L" and "ethtool -S" simultaneously [1]. For example when we change channels from 1 to 8, Thread 3 could be scheduled before Thread 2, and out-of-bounds writes could be triggered in Thread 3: Thread 1 (ethtool -L) Thread 2 (work) Thread 3 (ethtool -S) iavf_set_channels() ... iavf_alloc_queues() -> num_active_queues = 8 iavf_schedule_finish_config() iavf_get_sset_count() real_num_tx_queues: 1 -> buffer for 1 queue iavf_get_ethtool_stats() num_active_queues: 8 -> out-of-bounds! iavf_finish_config() -> real_num_tx_queues = 8 Use immutable num_tx_queues in all related functions to avoid the issue. [1] BUG: KASAN: vmalloc-out-of-bounds in iavf_add_one_ethtool_stat+0x200/0x270 Write of size 8 at addr ffffc900031c9080 by task ethtool/5800 CPU: 1 UID: 0 PID: 5800 Comm: ethtool Not tainted 6.19.0-enjuk-08403-g8137e3db7f1c #241 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x6f/0xb0 print_report+0x170/0x4f3 kasan_report+0xe1/0x180 iavf_add_one_ethtool_stat+0x200/0x270 iavf_get_ethtool_stats+0x14c/0x2e0 __dev_ethtool+0x3d0c/0x5830 dev_ethtool+0x12d/0x270 dev_ioctl+0x53c/0xe30 sock_do_ioctl+0x1a9/0x270 sock_ioctl+0x3d4/0x5e0 __x64_sys_ioctl+0x137/0x1c0 do_syscall_64+0xf3/0x690 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7da0e6e36d ... </TASK> The buggy address belongs to a 1-page vmalloc region starting at 0xffffc900031c9000 allocated at __dev_ethtool+0x3cc9/0x5830 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88813a013de0 pfn:0x13a013 flags: 0x200000000000000(node=0|zone=2) raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000 raw: ffff88813a013de0 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffc900031c8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffc900031c9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ^ ffffc900031c9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 ffffc900031c9180: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
CVE-2026-31507: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice pipe buffer smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores the pointer in pipe_buffer.private. The pipe_buf_operations for these buffers used .get = generic_pipe_buf_get, which only increments the page reference count when tee(2) duplicates a pipe buffer. The smc_spd_priv pointer itself was not handled, so after tee() both the original and the cloned pipe_buffer share the same smc_spd_priv *. When both pipes are subsequently released, smc_rx_pipe_buf_release() is called twice against the same object: 1st call: kfree(priv) sock_put(sk) smc_rx_update_cons() [correct] 2nd call: kfree(priv) sock_put(sk) smc_rx_update_cons() [UAF] KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which then escalates to a NULL-pointer dereference and kernel panic via smc_rx_update_consumer() when it chases the freed priv->smc pointer: BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0 Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_report+0xce/0x650 kasan_report+0xc6/0x100 smc_rx_pipe_buf_release+0x78/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:smc_rx_update_consumer+0x8d/0x350 Call Trace: <TASK> smc_rx_pipe_buf_release+0x121/0x2a0 free_pipe_info+0xd4/0x130 pipe_release+0x142/0x160 __fput+0x1c6/0x490 __x64_sys_close+0x4f/0x90 do_syscall_64+0xa6/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f </TASK> Kernel panic - not syncing: Fatal exception Beyond the memory-safety problem, duplicating an SMC splice buffer is semantically questionable: smc_rx_update_cons() would advance the consumer cursor twice for the same data, corrupting receive-window accounting. A refcount on smc_spd_priv could fix the double-free, but the cursor-accounting issue would still need to be addressed separately. The .get callback is invoked by both tee(2) and splice_pipe_to_pipe() for partial transfers; both will now return -EFAULT. Users who need to duplicate SMC socket data must use a copy-based read path.
CVE-2026-31508: In the Linux kernel, the following vulnerability has been resolved: net: openvswitch: Avoid releasing netdev before teardown completes The patch cited in the Fixes tag below changed the teardown code for OVS ports to no longer unconditionally take the RTNL. After this change, the netdev_destroy() callback can proceed immediately to the call_rcu() invocation if the IFF_OVS_DATAPATH flag is already cleared on the netdev. The ovs_netdev_detach_dev() function clears the flag before completing the unregistration, and if it gets preempted after clearing the flag (as can happen on an -rt kernel), netdev_destroy() can complete and the device can be freed before the unregistration completes. This leads to a splat like: [ 998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI [ 998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT [ 998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025 [ 998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0 [ 998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90 [ 998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246 [ 998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000 [ 998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05 [ 998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000 [ 998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006 [ 998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000 [ 998.393931] FS: 00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000 [ 998.393936] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0 [ 998.393944] PKRU: 55555554 [ 998.393946] Call Trace: [ 998.393949] <TASK> [ 998.393952] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393961] ? show_trace_log_lvl+0x1b0/0x2f0 [ 998.393975] ? dp_device_event+0x41/0x80 [openvswitch] [ 998.394009] ? __die_body.cold+0x8/0x12 [ 998.394016] ? die_addr+0x3c/0x60 [ 998.394027] ? exc_general_protection+0x16d/0x390 [ 998.394042] ? asm_exc_general_protection+0x26/0x30 [ 998.394058] ? dev_set_promiscuity+0x8d/0xa0 [ 998.394066] ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch] [ 998.394092] dp_device_event+0x41/0x80 [openvswitch] [ 998.394102] notifier_call_chain+0x5a/0xd0 [ 998.394106] unregister_netdevice_many_notify+0x51b/0xa60 [ 998.394110] rtnl_dellink+0x169/0x3e0 [ 998.394121] ? rt_mutex_slowlock.constprop.0+0x95/0xd0 [ 998.394125] rtnetlink_rcv_msg+0x142/0x3f0 [ 998.394128] ? avc_has_perm_noaudit+0x69/0xf0 [ 998.394130] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 998.394132] netlink_rcv_skb+0x50/0x100 [ 998.394138] netlink_unicast+0x292/0x3f0 [ 998.394141] netlink_sendmsg+0x21b/0x470 [ 998.394145] ____sys_sendmsg+0x39d/0x3d0 [ 998.394149] ___sys_sendmsg+0x9a/0xe0 [ 998.394156] __sys_sendmsg+0x7a/0xd0 [ 998.394160] do_syscall_64+0x7f/0x170 [ 998.394162] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 998.394165] RIP: 0033:0x7fad61bf4724 [ 998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89 [ 998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e [ 998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724 [ 998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003 [ 998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f [ 998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2 ---truncated---
CVE-2026-31509: In the Linux kernel, the following vulnerability has been resolved: nfc: nci: fix circular locking dependency in nci_close_device nci_close_device() flushes rx_wq and tx_wq while holding req_lock. This causes a circular locking dependency because nci_rx_work() running on rx_wq can end up taking req_lock too: nci_rx_work -> nci_rx_data_packet -> nci_data_exchange_complete -> __sk_destruct -> rawsock_destruct -> nfc_deactivate_target -> nci_deactivate_target -> nci_request -> mutex_lock(&ndev->req_lock) Move the flush of rx_wq after req_lock has been released. This should safe (I think) because NCI_UP has already been cleared and the transport is closed, so the work will see it and return -ENETDOWN. NIPA has been hitting this running the nci selftest with a debug kernel on roughly 4% of the runs.
CVE-2026-31510: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix null-ptr-deref on l2cap_sock_ready_cb Before using sk pointer, check if it is null. Fix the following: KASAN: null-ptr-deref in range [0x0000000000000260-0x0000000000000267] CPU: 0 UID: 0 PID: 5985 Comm: kworker/0:5 Not tainted 7.0.0-rc4-00029-ga989fde763f4 #1 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-9.fc43 06/10/2025 Workqueue: events l2cap_info_timeout RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce veth0_macvtap: entered promiscuous mode RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005582615a5008 CR3: 000000007007e000 CR4: 0000000000752ef0 PKRU: 55555554 Call Trace: <TASK> __kasan_check_byte+0x12/0x40 lock_acquire+0x79/0x2e0 lock_sock_nested+0x48/0x100 ? l2cap_sock_ready_cb+0x46/0x160 l2cap_sock_ready_cb+0x46/0x160 l2cap_conn_start+0x779/0xff0 ? __pfx_l2cap_conn_start+0x10/0x10 ? l2cap_info_timeout+0x60/0xa0 ? __pfx___mutex_lock+0x10/0x10 l2cap_info_timeout+0x68/0xa0 ? process_scheduled_works+0xa8d/0x18c0 process_scheduled_works+0xb6e/0x18c0 ? __pfx_process_scheduled_works+0x10/0x10 ? assign_work+0x3d5/0x5e0 worker_thread+0xa53/0xfc0 kthread+0x388/0x470 ? __pfx_worker_thread+0x10/0x10 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x51e/0xb90 ? __pfx_ret_from_fork+0x10/0x10 veth1_macvtap: entered promiscuous mode ? __switch_to+0xc7d/0x1450 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- batman_adv: batadv0: Interface activated: batadv_slave_0 batman_adv: batadv0: Interface activated: batadv_slave_1 netdevsim netdevsim7 netdevsim0: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim1: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim2: set [1, 0] type 2 family 0 port 6081 - 0 netdevsim netdevsim7 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0 RIP: 0010:kasan_byte_accessible+0x12/0x30 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce ieee80211 phy39: Selected rate control algorithm 'minstrel_ht' RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f7e16139e9c CR3: 000000000e74e000 CR4: 0000000000752ef0 PKRU: 55555554 Kernel panic - not syncing: Fatal exception
CVE-2026-31512: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Validate PDU length before reading SDU length in l2cap_ecred_data_rcv() l2cap_ecred_data_rcv() reads the SDU length field from skb->data using get_unaligned_le16() without first verifying that skb contains at least L2CAP_SDULEN_SIZE (2) bytes. When skb->len is less than 2, this reads past the valid data in the skb. The ERTM reassembly path correctly calls pskb_may_pull() before reading the SDU length (l2cap_reassemble_sdu, L2CAP_SAR_START case). Apply the same validation to the Enhanced Credit Based Flow Control data path.
CVE-2026-31515: In the Linux kernel, the following vulnerability has been resolved: af_key: validate families in pfkey_send_migrate() syzbot was able to trigger a crash in skb_put() [1] Issue is that pfkey_send_migrate() does not check old/new families, and that set_ipsecrequest() @family argument was truncated, thus possibly overfilling the skb. Validate families early, do not wait set_ipsecrequest(). [1] skbuff: skb_over_panic: text:ffffffff8a752120 len:392 put:16 head:ffff88802a4ad040 data:ffff88802a4ad040 tail:0x188 end:0x180 dev:<NULL> kernel BUG at net/core/skbuff.c:214 ! Call Trace: <TASK> skb_over_panic net/core/skbuff.c:219 [inline] skb_put+0x159/0x210 net/core/skbuff.c:2655 skb_put_zero include/linux/skbuff.h:2788 [inline] set_ipsecrequest net/key/af_key.c:3532 [inline] pfkey_send_migrate+0x1270/0x2e50 net/key/af_key.c:3636 km_migrate+0x155/0x260 net/xfrm/xfrm_state.c:2848 xfrm_migrate+0x2140/0x2450 net/xfrm/xfrm_policy.c:4705 xfrm_do_migrate+0x8ff/0xaa0 net/xfrm/xfrm_user.c:3150
CVE-2026-31516: In the Linux kernel, the following vulnerability has been resolved: xfrm: prevent policy_hthresh.work from racing with netns teardown A XFRM_MSG_NEWSPDINFO request can queue the per-net work item policy_hthresh.work onto the system workqueue. The queued callback, xfrm_hash_rebuild(), retrieves the enclosing struct net via container_of(). If the net namespace is torn down before that work runs, the associated struct net may already have been freed, and xfrm_hash_rebuild() may then dereference stale memory. xfrm_policy_fini() already flushes policy_hash_work during teardown, but it does not synchronize policy_hthresh.work. Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the queued work cannot outlive the net namespace teardown and access a freed struct net.
CVE-2026-31518: In the Linux kernel, the following vulnerability has been resolved: esp: fix skb leak with espintcp and async crypto When the TX queue for espintcp is full, esp_output_tail_tcp will return an error and not free the skb, because with synchronous crypto, the common xfrm output code will drop the packet for us. With async crypto (esp_output_done), we need to drop the skb when esp_output_tail_tcp returns an error.
CVE-2026-31519: In the Linux kernel, the following vulnerability has been resolved: btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create We have recently observed a number of subvolumes with broken dentries. ls-ing the parent dir looks like: drwxrwxrwt 1 root root 16 Jan 23 16:49 . drwxr-xr-x 1 root root 24 Jan 23 16:48 .. d????????? ? ? ? ? ? broken_subvol and similarly stat-ing the file fails. In this state, deleting the subvol fails with ENOENT, but attempting to create a new file or subvol over it errors out with EEXIST and even aborts the fs. Which leaves us a bit stuck. dmesg contains a single notable error message reading: "could not do orphan cleanup -2" 2 is ENOENT and the error comes from the failure handling path of btrfs_orphan_cleanup(), with the stack leading back up to btrfs_lookup(). btrfs_lookup btrfs_lookup_dentry btrfs_orphan_cleanup // prints that message and returns -ENOENT After some detailed inspection of the internal state, it became clear that: - there are no orphan items for the subvol - the subvol is otherwise healthy looking, it is not half-deleted or anything, there is no drop progress, etc. - the subvol was created a while ago and does the meaningful first btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much later. - after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT, which results in a negative dentry for the subvolume via d_splice_alias(NULL, dentry), leading to the observed behavior. The bug can be mitigated by dropping the dentry cache, at which point we can successfully delete the subvolume if we want. i.e., btrfs_lookup() btrfs_lookup_dentry() if (!sb_rdonly(inode->vfs_inode)->vfs_inode) btrfs_orphan_cleanup(sub_root) test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) btrfs_search_slot() // finds orphan item for inode N ... prints "could not do orphan cleanup -2" if (inode == ERR_PTR(-ENOENT)) inode = NULL; return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP) on the root when it runs, so it cannot run more than once on a given root, so something else must run concurrently. However, the obvious routes to deleting an orphan when nlinks goes to 0 should not be able to run without first doing a lookup into the subvolume, which should run btrfs_orphan_cleanup() and set the bit. The final important observation is that create_subvol() calls d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if the dentry cache gets dropped, the next lookup into the subvolume will make a real call into btrfs_orphan_cleanup() for the first time. This opens up the possibility of concurrently deleting the inode/orphan items but most typical evict() paths will be holding a reference on the parent dentry (child dentry holds parent->d_lockref.count via dget in d_alloc(), released in __dentry_kill()) and prevent the parent from being removed from the dentry cache. The one exception is delayed iputs. Ordered extent creation calls igrab() on the inode. If the file is unlinked and closed while those refs are held, iput() in __dentry_kill() decrements i_count but does not trigger eviction (i_count > 0). The child dentry is freed and the subvol dentry's d_lockref.count drops to 0, making it evictable while the inode is still alive. Since there are two races (the race between writeback and unlink and the race between lookup and delayed iputs), and there are too many moving parts, the following three diagrams show the complete picture. (Only the second and third are races) Phase 1: Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set btrfs_mksubvol() lookup_one_len() __lookup_slow() d_alloc_parallel() __d_alloc() // d_lockref.count = 1 create_subvol(dentry) // doesn't touch the bit.. d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.c ---truncated---
CVE-2026-31520: In the Linux kernel, the following vulnerability has been resolved: HID: apple: avoid memory leak in apple_report_fixup() The apple_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it *is* permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.
CVE-2026-31521: In the Linux kernel, the following vulnerability has been resolved: module: Fix kernel panic when a symbol st_shndx is out of bounds The module loader doesn't check for bounds of the ELF section index in simplify_symbols(): for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char *name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: [...] default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else /** HERE --> **/ secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } A symbol with an out-of-bounds st_shndx value, for example 0xffff (known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic: BUG: unable to handle page fault for address: ... RIP: 0010:simplify_symbols+0x2b2/0x480 ... Kernel panic - not syncing: Fatal exception This can happen when module ELF is legitimately using SHN_XINDEX or when it is corrupted. Add a bounds check in simplify_symbols() to validate that st_shndx is within the valid range before using it. This issue was discovered due to a bug in llvm-objcopy, see relevant discussion for details [1]. [1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/
CVE-2026-31522: In the Linux kernel, the following vulnerability has been resolved: HID: magicmouse: avoid memory leak in magicmouse_report_fixup() The magicmouse_report_fixup() function was returning a newly kmemdup()-allocated buffer, but never freeing it. The caller of report_fixup() does not take ownership of the returned pointer, but it *is* permitted to return a sub-portion of the input rdesc, whose lifetime is managed by the caller.
CVE-2026-31523: In the Linux kernel, the following vulnerability has been resolved: nvme-pci: ensure we're polling a polled queue A user can change the polled queue count at run time. There's a brief window during a reset where a hipri task may try to poll that queue before the block layer has updated the queue maps, which would race with the now interrupt driven queue and may cause double completions.
CVE-2026-31524: In the Linux kernel, the following vulnerability has been resolved: HID: asus: avoid memory leak in asus_report_fixup() The asus_report_fixup() function was returning a newly allocated kmemdup()-allocated buffer, but never freeing it. Switch to devm_kzalloc() to ensure the memory is managed and freed automatically when the device is removed. The caller of report_fixup() does not take ownership of the returned pointer, but it is permitted to return a pointer whose lifetime is at least that of the input buffer. Also fix a harmless out-of-bounds read by copying only the original descriptor size.
CVE-2026-31527: In the Linux kernel, the following vulnerability has been resolved: driver core: platform: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1]
CVE-2026-31531: In the Linux kernel, the following vulnerability has been resolved: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop() When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for single nexthops and small Equal-Cost Multi-Path groups, this fixed allocation fails for large nexthop groups like 512 nexthops. This results in the following warning splat: WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608 [...] RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395) [...] Call Trace: <TASK> rtnetlink_rcv_msg (net/core/rtnetlink.c:6989) netlink_rcv_skb (net/netlink/af_netlink.c:2550) netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344) netlink_sendmsg (net/netlink/af_netlink.c:1894) ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585) ___sys_sendmsg (net/socket.c:2641) __sys_sendmsg (net/socket.c:2671) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> Fix this by allocating the size dynamically using nh_nlmsg_size() and using nlmsg_new(), this is consistent with nexthop_notify() behavior. In addition, adjust nh_nlmsg_size_grp() so it calculates the size needed based on flags passed. While at it, also add the size of NHA_FDB for nexthop group size calculation as it was missing too. This cannot be reproduced via iproute2 as the group size is currently limited and the command fails as follows: addattr_l ERROR: message exceeded bound of 1048
CVE-2026-31532: In the Linux kernel, the following vulnerability has been resolved: can: raw: fix ro->uniq use-after-free in raw_rcv() raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage. Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained. [mkl: applied manually]
CVE-2026-31533: In the Linux kernel, the following vulnerability has been resolved: net/tls: fix use-after-free in -EBUSY error path of tls_do_encryption The -EBUSY handling in tls_do_encryption(), introduced by commit 859054147318 ("net: tls: handle backlogging of crypto requests"), has a use-after-free due to double cleanup of encrypt_pending and the scatterlist entry. When crypto_aead_encrypt() returns -EBUSY, the request is enqueued to the cryptd backlog and the async callback tls_encrypt_done() will be invoked upon completion. That callback unconditionally restores the scatterlist entry (sge->offset, sge->length) and decrements ctx->encrypt_pending. However, if tls_encrypt_async_wait() returns an error, the synchronous error path in tls_do_encryption() performs the same cleanup again, double-decrementing encrypt_pending and double-restoring the scatterlist. The double-decrement corrupts the encrypt_pending sentinel (initialized to 1), making tls_encrypt_async_wait() permanently skip the wait for pending async callbacks. A subsequent sendmsg can then free the tls_rec via bpf_exec_tx_verdict() while a cryptd callback is still pending, resulting in a use-after-free when the callback fires on the freed record. Fix this by skipping the synchronous cleanup when the -EBUSY async wait returns an error, since the callback has already handled encrypt_pending and sge restoration.
CVE-2026-31536: In the Linux kernel, the following vulnerability has been resolved: smb: server: let send_done handle a completion without IB_SEND_SIGNALED With smbdirect_send_batch processing we likely have requests without IB_SEND_SIGNALED, which will be destroyed in the final request that has IB_SEND_SIGNALED set. If the connection is broken all requests are signaled even without explicit IB_SEND_SIGNALED.
CVE-2026-31537: In the Linux kernel, the following vulnerability has been resolved: smb: server: make use of smbdirect_socket.send_io.bcredits It turns out that our code will corrupt the stream of reassabled data transfer messages when we trigger an immendiate (empty) send. In order to fix this we'll have a single 'batch' credit per connection. And code getting that credit is free to use as much messages until remaining_length reaches 0, then the batch credit it given back and the next logical send can happen.
CVE-2026-31540: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: Check set_default_submission() before deferencing When the i915 driver firmware binaries are not present, the set_default_submission pointer is not set. This pointer is dereferenced during suspend anyways. Add a check to make sure it is set before dereferencing. [ 23.289926] PM: suspend entry (deep) [ 23.293558] Filesystems sync: 0.000 seconds [ 23.298010] Freezing user space processes [ 23.302771] Freezing user space processes completed (elapsed 0.000 seconds) [ 23.309766] OOM killer disabled. [ 23.313027] Freezing remaining freezable tasks [ 23.318540] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 23.342038] serial 00:05: disabled [ 23.345719] serial 00:02: disabled [ 23.349342] serial 00:01: disabled [ 23.353782] sd 0:0:0:0: [sda] Synchronizing SCSI cache [ 23.358993] sd 1:0:0:0: [sdb] Synchronizing SCSI cache [ 23.361635] ata1.00: Entering standby power mode [ 23.368863] ata2.00: Entering standby power mode [ 23.445187] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 23.452194] #PF: supervisor instruction fetch in kernel mode [ 23.457896] #PF: error_code(0x0010) - not-present page [ 23.463065] PGD 0 P4D 0 [ 23.465640] Oops: Oops: 0010 [#1] SMP NOPTI [ 23.469869] CPU: 8 UID: 0 PID: 211 Comm: kworker/u48:18 Tainted: G S W 6.19.0-rc4-00020-gf0b9d8eb98df #10 PREEMPT(voluntary) [ 23.482512] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 23.496511] Workqueue: async async_run_entry_fn [ 23.501087] RIP: 0010:0x0 [ 23.503755] Code: Unable to access opcode bytes at 0xffffffffffffffd6. [ 23.510324] RSP: 0018:ffffb4a60065fca8 EFLAGS: 00010246 [ 23.515592] RAX: 0000000000000000 RBX: ffff9f428290e000 RCX: 000000000000000f [ 23.522765] RDX: 0000000000000000 RSI: 0000000000000282 RDI: ffff9f428290e000 [ 23.529937] RBP: ffff9f4282907070 R08: ffff9f4281130428 R09: 00000000ffffffff [ 23.537111] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f42829070f8 [ 23.544284] R13: ffff9f4282906028 R14: ffff9f4282900000 R15: ffff9f4282906b68 [ 23.551457] FS: 0000000000000000(0000) GS:ffff9f466b2cf000(0000) knlGS:0000000000000000 [ 23.559588] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 23.565365] CR2: ffffffffffffffd6 CR3: 000000031c230001 CR4: 0000000000f70ef0 [ 23.572539] PKRU: 55555554 [ 23.575281] Call Trace: [ 23.577770] <TASK> [ 23.579905] intel_engines_reset_default_submission+0x42/0x60 [ 23.585695] __intel_gt_unset_wedged+0x191/0x200 [ 23.590360] intel_gt_unset_wedged+0x20/0x40 [ 23.594675] gt_sanitize+0x15e/0x170 [ 23.598290] i915_gem_suspend_late+0x6b/0x180 [ 23.602692] i915_drm_suspend_late+0x35/0xf0 [ 23.607008] ? __pfx_pci_pm_suspend_late+0x10/0x10 [ 23.611843] dpm_run_callback+0x78/0x1c0 [ 23.615817] device_suspend_late+0xde/0x2e0 [ 23.620037] async_suspend_late+0x18/0x30 [ 23.624082] async_run_entry_fn+0x25/0xa0 [ 23.628129] process_one_work+0x15b/0x380 [ 23.632182] worker_thread+0x2a5/0x3c0 [ 23.635973] ? __pfx_worker_thread+0x10/0x10 [ 23.640279] kthread+0xf6/0x1f0 [ 23.643464] ? __pfx_kthread+0x10/0x10 [ 23.647263] ? __pfx_kthread+0x10/0x10 [ 23.651045] ret_from_fork+0x131/0x190 [ 23.654837] ? __pfx_kthread+0x10/0x10 [ 23.658634] ret_from_fork_asm+0x1a/0x30 [ 23.662597] </TASK> [ 23.664826] Modules linked in: [ 23.667914] CR2: 0000000000000000 [ 23.671271] ------------[ cut here ]------------ (cherry picked from commit daa199abc3d3d1740c9e3a2c3e9216ae5b447cad)
CVE-2026-31545: In the Linux kernel, the following vulnerability has been resolved: NFC: nxp-nci: allow GPIOs to sleep Allow the firmware and enable GPIOs to sleep. This fixes a `WARN_ON' and allows the driver to operate GPIOs which are connected to I2C GPIO expanders. -- >8 -- kernel: WARNING: CPU: 3 PID: 2636 at drivers/gpio/gpiolib.c:3880 gpiod_set_value+0x88/0x98 -- >8 --
CVE-2026-31546: In the Linux kernel, the following vulnerability has been resolved: net: bonding: fix NULL deref in bond_debug_rlb_hash_show rlb_clear_slave intentionally keeps RLB hash-table entries on the rx_hashtbl_used_head list with slave set to NULL when no replacement slave is available. However, bond_debug_rlb_hash_show visites client_info->slave without checking if it's NULL. Other used-list iterators in bond_alb.c already handle this NULL-slave state safely: - rlb_update_client returns early on !client_info->slave - rlb_req_update_slave_clients, rlb_clear_slave, and rlb_rebalance compare slave values before visiting - lb_req_update_subnet_clients continues if slave is NULL The following NULL deref crash can be trigger in bond_debug_rlb_hash_show: [ 1.289791] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 1.292058] RIP: 0010:bond_debug_rlb_hash_show (drivers/net/bonding/bond_debugfs.c:41) [ 1.293101] RSP: 0018:ffffc900004a7d00 EFLAGS: 00010286 [ 1.293333] RAX: 0000000000000000 RBX: ffff888102b48200 RCX: ffff888102b48204 [ 1.293631] RDX: ffff888102b48200 RSI: ffffffff839daad5 RDI: ffff888102815078 [ 1.293924] RBP: ffff888102815078 R08: ffff888102b4820e R09: 0000000000000000 [ 1.294267] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100f929c0 [ 1.294564] R13: ffff888100f92a00 R14: 0000000000000001 R15: ffffc900004a7ed8 [ 1.294864] FS: 0000000001395380(0000) GS:ffff888196e75000(0000) knlGS:0000000000000000 [ 1.295239] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.295480] CR2: 0000000000000000 CR3: 0000000102adc004 CR4: 0000000000772ef0 [ 1.295897] Call Trace: [ 1.296134] seq_read_iter (fs/seq_file.c:231) [ 1.296341] seq_read (fs/seq_file.c:164) [ 1.296493] full_proxy_read (fs/debugfs/file.c:378 (discriminator 1)) [ 1.296658] vfs_read (fs/read_write.c:572) [ 1.296981] ksys_read (fs/read_write.c:717) [ 1.297132] do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1)) [ 1.297325] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Add a NULL check and print "(none)" for entries with no assigned slave.
CVE-2026-31548: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: cancel pmsr_free_wk in cfg80211_pmsr_wdev_down When the nl80211 socket that originated a PMSR request is closed, cfg80211_release_pmsr() sets the request's nl_portid to zero and schedules pmsr_free_wk to process the abort asynchronously. If the interface is concurrently torn down before that work runs, cfg80211_pmsr_wdev_down() calls cfg80211_pmsr_process_abort() directly. However, the already- scheduled pmsr_free_wk work item remains pending and may run after the interface has been removed from the driver. This could cause the driver's abort_pmsr callback to operate on a torn-down interface, leading to undefined behavior and potential crashes. Cancel pmsr_free_wk synchronously in cfg80211_pmsr_wdev_down() before calling cfg80211_pmsr_process_abort(). This ensures any pending or in-progress work is drained before interface teardown proceeds, preventing the work from invoking the driver abort callback after the interface is gone.
CVE-2026-31549: In the Linux kernel, the following vulnerability has been resolved: i2c: cp2615: fix serial string NULL-deref at probe The cp2615 driver uses the USB device serial string as the i2c adapter name but does not make sure that the string exists. Verify that the device has a serial number before accessing it to avoid triggering a NULL-pointer dereference (e.g. with malicious devices).
CVE-2026-31550: In the Linux kernel, the following vulnerability has been resolved: pmdomain: bcm: bcm2835-power: Increase ASB control timeout The bcm2835_asb_control() function uses a tight polling loop to wait for the ASB bridge to acknowledge a request. During intensive workloads, this handshake intermittently fails for V3D's master ASB on BCM2711, resulting in "Failed to disable ASB master for v3d" errors during runtime PM suspend. As a consequence, the failed power-off leaves V3D in a broken state, leading to bus faults or system hangs on later accesses. As the timeout is insufficient in some scenarios, increase the polling timeout from 1us to 5us, which is still negligible in the context of a power domain transition. Also, replace the open-coded ktime_get_ns()/ cpu_relax() polling loop with readl_poll_timeout_atomic().
CVE-2026-31551: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: Fix static_branch_dec() underflow for aql_disable. syzbot reported static_branch_dec() underflow in aql_enable_write(). [0] The problem is that aql_enable_write() does not serialise concurrent write()s to the debugfs. aql_enable_write() checks static_key_false(&aql_disable.key) and later calls static_branch_inc() or static_branch_dec(), but the state may change between the two calls. aql_disable does not need to track inc/dec. Let's use static_branch_enable() and static_branch_disable(). [0]: val == 0 WARNING: kernel/jump_label.c:311 at __static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311, CPU#0: syz.1.3155/20288 Modules linked in: CPU: 0 UID: 0 PID: 20288 Comm: syz.1.3155 Tainted: G U L syzkaller #0 PREEMPT(full) Tainted: [U]=USER, [L]=SOFTLOCKUP Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/24/2026 RIP: 0010:__static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311 Code: f2 c9 ff 5b 5d c3 cc cc cc cc e8 54 f2 c9 ff 48 89 df e8 ac f9 ff ff eb ad e8 45 f2 c9 ff 90 0f 0b 90 eb a2 e8 3a f2 c9 ff 90 <0f> 0b 90 eb 97 48 89 df e8 5c 4b 33 00 e9 36 ff ff ff 0f 1f 80 00 RSP: 0018:ffffc9000b9f7c10 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffffffff9b3e5d40 RCX: ffffffff823c57b4 RDX: ffff8880285a0000 RSI: ffffffff823c5846 RDI: ffff8880285a0000 RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000000a R13: 1ffff9200173ef88 R14: 0000000000000001 R15: ffffc9000b9f7e98 FS: 00007f530dd726c0(0000) GS:ffff8881245e3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000200000001140 CR3: 000000007cc4a000 CR4: 00000000003526f0 Call Trace: <TASK> __static_key_slow_dec_cpuslocked kernel/jump_label.c:297 [inline] __static_key_slow_dec kernel/jump_label.c:321 [inline] static_key_slow_dec+0x7c/0xc0 kernel/jump_label.c:336 aql_enable_write+0x2b2/0x310 net/mac80211/debugfs.c:343 short_proxy_write+0x133/0x1a0 fs/debugfs/file.c:383 vfs_write+0x2aa/0x1070 fs/read_write.c:684 ksys_pwrite64 fs/read_write.c:793 [inline] __do_sys_pwrite64 fs/read_write.c:801 [inline] __se_sys_pwrite64 fs/read_write.c:798 [inline] __x64_sys_pwrite64+0x1eb/0x250 fs/read_write.c:798 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xc9/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f530cf9aeb9 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f530dd72028 EFLAGS: 00000246 ORIG_RAX: 0000000000000012 RAX: ffffffffffffffda RBX: 00007f530d215fa0 RCX: 00007f530cf9aeb9 RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000010 RBP: 00007f530d008c1f R08: 0000000000000000 R09: 0000000000000000 R10: 4200000000000005 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f530d216038 R14: 00007f530d215fa0 R15: 00007ffde89fb978 </TASK>
CVE-2026-31552: In the Linux kernel, the following vulnerability has been resolved: wifi: wlcore: Return -ENOMEM instead of -EAGAIN if there is not enough headroom Since upstream commit e75665dd0968 ("wifi: wlcore: ensure skb headroom before skb_push"), wl1271_tx_allocate() and with it wl1271_prepare_tx_frame() returns -EAGAIN if pskb_expand_head() fails. However, in wlcore_tx_work_locked(), a return value of -EAGAIN from wl1271_prepare_tx_frame() is interpreted as the aggregation buffer being full. This causes the code to flush the buffer, put the skb back at the head of the queue, and immediately retry the same skb in a tight while loop. Because wlcore_tx_work_locked() holds wl->mutex, and the retry happens immediately with GFP_ATOMIC, this will result in an infinite loop and a CPU soft lockup. Return -ENOMEM instead so the packet is dropped and the loop terminates. The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y.
CVE-2026-31555: In the Linux kernel, the following vulnerability has been resolved: futex: Clear stale exiting pointer in futex_lock_pi() retry path Fuzzying/stressing futexes triggered: WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524 When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY and stores a refcounted task pointer in 'exiting'. After wait_for_owner_exiting() consumes that reference, the local pointer is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a different error, the bogus pointer is passed to wait_for_owner_exiting(). CPU0 CPU1 CPU2 futex_lock_pi(uaddr) // acquires the PI futex exit() futex_cleanup_begin() futex_state = EXITING; futex_lock_pi(uaddr) futex_lock_pi_atomic() attach_to_pi_owner() // observes EXITING *exiting = owner; // takes ref return -EBUSY wait_for_owner_exiting(-EBUSY, owner) put_task_struct(); // drops ref // exiting still points to owner goto retry; futex_lock_pi_atomic() lock_pi_update_atomic() cmpxchg(uaddr) *uaddr ^= WAITERS // whatever // value changed return -EAGAIN; wait_for_owner_exiting(-EAGAIN, exiting) // stale WARN_ON_ONCE(exiting) Fix this by resetting upon retry, essentially aligning it with requeue_pi.
CVE-2026-31557: In the Linux kernel, the following vulnerability has been resolved: nvmet: move async event work off nvmet-wq For target nvmet_ctrl_free() flushes ctrl->async_event_work. If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue completion for the same worker:- A. Async event work queued on nvmet-wq (prior to disconnect): nvmet_execute_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) nvmet_add_async_event() queue_work(nvmet_wq, &ctrl->async_event_work) B. Full pre-work chain (RDMA CM path): nvmet_rdma_cm_handler() nvmet_rdma_queue_disconnect() __nvmet_rdma_queue_disconnect() queue_work(nvmet_wq, &queue->release_work) process_one_work() lock((wq_completion)nvmet-wq) <--------- 1st nvmet_rdma_release_queue_work() C. Recursive path (same worker): nvmet_rdma_release_queue_work() nvmet_rdma_free_queue() nvmet_sq_destroy() nvmet_ctrl_put() nvmet_ctrl_free() flush_work(&ctrl->async_event_work) __flush_work() touch_wq_lockdep_map() lock((wq_completion)nvmet-wq) <--------- 2nd Lockdep splat: ============================================ WARNING: possible recursive locking detected 6.19.0-rc3nvme+ #14 Tainted: G N -------------------------------------------- kworker/u192:42/44933 is trying to acquire lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90 but task is already holding lock: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 3 locks held by kworker/u192:42/44933: #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660 #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660 #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530 Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma] Call Trace: __flush_work+0x268/0x530 nvmet_ctrl_free+0x140/0x310 [nvmet] nvmet_cq_put+0x74/0x90 [nvmet] nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma] nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma] process_one_work+0x206/0x660 worker_thread+0x184/0x320 kthread+0x10c/0x240 ret_from_fork+0x319/0x390 Move async event work to a dedicated nvmet-aen-wq to avoid reentrant flush on nvmet-wq.
CVE-2026-31560: In the Linux kernel, the following vulnerability has been resolved: spi: spi-dw-dma: fix print error log when wait finish transaction If an error occurs, the device may not have a current message. In this case, the system will crash. In this case, it's better to use dev from the struct ctlr (struct spi_controller*).
CVE-2026-31563: In the Linux kernel, the following vulnerability has been resolved: net: macb: Use dev_consume_skb_any() to free TX SKBs The napi_consume_skb() function is not intended to be called in an IRQ disabled context. However, after commit 6bc8a5098bf4 ("net: macb: Fix tx_ptr_lock locking"), the freeing of TX SKBs is performed with IRQs disabled. To resolve the following call trace, use dev_consume_skb_any() for freeing TX SKBs: WARNING: kernel/softirq.c:430 at __local_bh_enable_ip+0x174/0x188, CPU#0: ksoftirqd/0/15 Modules linked in: CPU: 0 UID: 0 PID: 15 Comm: ksoftirqd/0 Not tainted 7.0.0-rc4-next-20260319-yocto-standard-dirty #37 PREEMPT Hardware name: ZynqMP ZCU102 Rev1.1 (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __local_bh_enable_ip+0x174/0x188 lr : local_bh_enable+0x24/0x38 sp : ffff800082b3bb10 x29: ffff800082b3bb10 x28: ffff0008031f3c00 x27: 000000000011ede0 x26: ffff000800a7ff00 x25: ffff800083937ce8 x24: 0000000000017a80 x23: ffff000803243a78 x22: 0000000000000040 x21: 0000000000000000 x20: ffff000800394c80 x19: 0000000000000200 x18: 0000000000000001 x17: 0000000000000001 x16: ffff000803240000 x15: 0000000000000000 x14: ffffffffffffffff x13: 0000000000000028 x12: ffff000800395650 x11: ffff8000821d1528 x10: ffff800081c2bc08 x9 : ffff800081c1e258 x8 : 0000000100000301 x7 : ffff8000810426ec x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000008 x1 : 0000000000000200 x0 : ffff8000810428dc Call trace: __local_bh_enable_ip+0x174/0x188 (P) local_bh_enable+0x24/0x38 skb_attempt_defer_free+0x190/0x1d8 napi_consume_skb+0x58/0x108 macb_tx_poll+0x1a4/0x558 __napi_poll+0x50/0x198 net_rx_action+0x1f4/0x3d8 handle_softirqs+0x16c/0x560 run_ksoftirqd+0x44/0x80 smpboot_thread_fn+0x1d8/0x338 kthread+0x120/0x150 ret_from_fork+0x10/0x20 irq event stamp: 29751 hardirqs last enabled at (29750): [<ffff8000813be184>] _raw_spin_unlock_irqrestore+0x44/0x88 hardirqs last disabled at (29751): [<ffff8000813bdf60>] _raw_spin_lock_irqsave+0x38/0x98 softirqs last enabled at (29150): [<ffff8000800f1aec>] handle_softirqs+0x504/0x560 softirqs last disabled at (29153): [<ffff8000800f2fec>] run_ksoftirqd+0x44/0x80
CVE-2026-31565: In the Linux kernel, the following vulnerability has been resolved: RDMA/irdma: Fix deadlock during netdev reset with active connections Resolve deadlock that occurs when user executes netdev reset while RDMA applications (e.g., rping) are active. The netdev reset causes ice driver to remove irdma auxiliary driver, triggering device_delete and subsequent client removal. During client removal, uverbs_client waits for QP reference count to reach zero while cma_client holds the final reference, creating circular dependency and indefinite wait in iWARP mode. Skip QP reference count wait during device reset to prevent deadlock.
CVE-2026-31566: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix fence put before wait in amdgpu_amdkfd_submit_ib amdgpu_amdkfd_submit_ib() submits a GPU job and gets a fence from amdgpu_ib_schedule(). This fence is used to wait for job completion. Currently, the code drops the fence reference using dma_fence_put() before calling dma_fence_wait(). If dma_fence_put() releases the last reference, the fence may be freed before dma_fence_wait() is called. This can lead to a use-after-free. Fix this by waiting on the fence first and releasing the reference only after dma_fence_wait() completes. Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:697 amdgpu_amdkfd_submit_ib() warn: passing freed memory 'f' (line 696) (cherry picked from commit 8b9e5259adc385b61a6590a13b82ae0ac2bd3482)
CVE-2026-31568: In the Linux kernel, the following vulnerability has been resolved: s390/mm: Add missing secure storage access fixups for donated memory There are special cases where secure storage access exceptions happen in a kernel context for pages that don't have the PG_arch_1 bit set. That bit is set for non-exported guest secure storage (memory) but is absent on storage donated to the Ultravisor since the kernel isn't allowed to export donated pages. Prior to this patch we would try to export the page by calling arch_make_folio_accessible() which would instantly return since the arch bit is absent signifying that the page was already exported and no further action is necessary. This leads to secure storage access exception loops which can never be resolved. With this patch we unconditionally try to export and if that fails we fixup.
CVE-2026-31570: In the Linux kernel, the following vulnerability has been resolved: can: gw: fix OOB heap access in cgw_csum_crc8_rel() cgw_csum_crc8_rel() correctly computes bounds-safe indices via calc_idx(): int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); if (from < 0 || to < 0 || res < 0) return; However, the loop and the result write then use the raw s8 fields directly instead of the computed variables: for (i = crc8->from_idx; ...) /* BUG: raw negative index */ cf->data[crc8->result_idx] = ...; /* BUG: raw negative index */ With from_idx = to_idx = result_idx = -64 on a 64-byte CAN FD frame, calc_idx(-64, 64) = 0 so the guard passes, but the loop iterates with i = -64, reading cf->data[-64], and the write goes to cf->data[-64]. This write might end up to 56 (7.0-rc) or 40 (<= 6.19) bytes before the start of the canfd_frame on the heap. The companion function cgw_csum_xor_rel() uses `from`/`to`/`res` correctly throughout; fix cgw_csum_crc8_rel() to match. Confirmed with KASAN on linux-7.0-rc2: BUG: KASAN: slab-out-of-bounds in cgw_csum_crc8_rel+0x515/0x5b0 Read of size 1 at addr ffff8880076619c8 by task poc_cgw_oob/62 To configure the can-gw crc8 checksums CAP_NET_ADMIN is needed.
CVE-2026-31574: In the Linux kernel, the following vulnerability has been resolved: clockevents: Add missing resets of the next_event_forced flag The prevention mechanism against timer interrupt starvation missed to reset the next_event_forced flag in a couple of places: - When the clock event state changes. That can cause the flag to be stale over a shutdown/startup sequence - When a non-forced event is armed, which then prevents rearming before that event. If that event is far out in the future this will cause missed timer interrupts. - In the suspend wakeup handler. That led to stalls which have been reported by several people. Add the missing resets, which fixes the problems for the reporters.
CVE-2026-31575: In the Linux kernel, the following vulnerability has been resolved: mm/userfaultfd: fix hugetlb fault mutex hash calculation In mfill_atomic_hugetlb(), linear_page_index() is used to calculate the page index for hugetlb_fault_mutex_hash(). However, linear_page_index() returns the index in PAGE_SIZE units, while hugetlb_fault_mutex_hash() expects the index in huge page units. This mismatch means that different addresses within the same huge page can produce different hash values, leading to the use of different mutexes for the same huge page. This can cause races between faulting threads, which can corrupt the reservation map and trigger the BUG_ON in resv_map_release(). Fix this by introducing hugetlb_linear_page_index(), which returns the page index in huge page granularity, and using it in place of linear_page_index().
CVE-2026-31576: In the Linux kernel, the following vulnerability has been resolved: media: hackrf: fix to not free memory after the device is registered in hackrf_probe() In hackrf driver, the following race condition occurs: ``` CPU0 CPU1 hackrf_probe() kzalloc(); // alloc hackrf_dev .... v4l2_device_register(); .... fd = sys_open("/path/to/dev"); // open hackrf fd .... v4l2_device_unregister(); .... kfree(); // free hackrf_dev .... sys_ioctl(fd, ...); v4l2_ioctl(); video_is_registered() // UAF!! .... sys_close(fd); v4l2_release() // UAF!! hackrf_video_release() kfree(); // DFB!! ``` When a V4L2 or video device is unregistered, the device node is removed so new open() calls are blocked. However, file descriptors that are already open-and any in-flight I/O-do not terminate immediately; they remain valid until the last reference is dropped and the driver's release() is invoked. Therefore, freeing device memory on the error path after hackrf_probe() has registered dev it will lead to a race to use-after-free vuln, since those already-open handles haven't been released yet. And since release() free memory too, race to use-after-free and double-free vuln occur. To prevent this, if device is registered from probe(), it should be modified to free memory only through release() rather than calling kfree() directly.
CVE-2026-31577: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map The DAT inode's btree node cache (i_assoc_inode) is initialized lazily during btree operations. However, nilfs_mdt_save_to_shadow_map() assumes i_assoc_inode is already initialized when copying dirty pages to the shadow map during GC. If NILFS_IOCTL_CLEAN_SEGMENTS is called immediately after mount before any btree operation has occurred on the DAT inode, i_assoc_inode is NULL leading to a general protection fault. Fix this by calling nilfs_attach_btree_node_cache() on the DAT inode in nilfs_dat_read() at mount time, ensuring i_assoc_inode is always initialized before any GC operation can use it.
CVE-2026-31578: In the Linux kernel, the following vulnerability has been resolved: media: as102: fix to not free memory after the device is registered in as102_usb_probe() In as102_usb driver, the following race condition occurs: ``` CPU0 CPU1 as102_usb_probe() kzalloc(); // alloc as102_dev_t .... usb_register_dev(); fd = sys_open("/path/to/dev"); // open as102 fd .... usb_deregister_dev(); .... kfree(); // free as102_dev_t .... sys_close(fd); as102_release() // UAF!! as102_usb_release() kfree(); // DFB!! ``` When a USB character device registered with usb_register_dev() is later unregistered (via usb_deregister_dev() or disconnect), the device node is removed so new open() calls fail. However, file descriptors that are already open do not go away immediately: they remain valid until the last reference is dropped and the driver's .release() is invoked. In as102, as102_usb_probe() calls usb_register_dev() and then, on an error path, does usb_deregister_dev() and frees as102_dev_t right away. If userspace raced a successful open() before the deregistration, that open FD will later hit as102_release() --> as102_usb_release() and access or free as102_dev_t again, occur a race to use-after-free and double-free vuln. The fix is to never kfree(as102_dev_t) directly once usb_register_dev() has succeeded. After deregistration, defer freeing memory to .release(). In other words, let release() perform the last kfree when the final open FD is closed.
CVE-2026-31579: In the Linux kernel, the following vulnerability has been resolved: wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit wg_netns_pre_exit() manually acquires rtnl_lock() inside the pernet .pre_exit callback. This causes a hung task when another thread holds rtnl_mutex - the cleanup_net workqueue (or the setup_net failure rollback path) blocks indefinitely in wg_netns_pre_exit() waiting to acquire the lock. Convert to .exit_rtnl, introduced in commit 7a60d91c690b ("net: Add ->exit_rtnl() hook to struct pernet_operations."), where the framework already holds RTNL and batches all callbacks under a single rtnl_lock()/rtnl_unlock() pair, eliminating the contention window. The rcu_assign_pointer(wg->creating_net, NULL) is safe to move from .pre_exit to .exit_rtnl (which runs after synchronize_rcu()) because all RCU readers of creating_net either use maybe_get_net() - which returns NULL for a dying namespace with zero refcount - or access net->user_ns which remains valid throughout the entire ops_undo_list sequence. [ Jason: added __net_exit and __read_mostly annotations that were missing. ]
CVE-2026-31580: In the Linux kernel, the following vulnerability has been resolved: bcache: fix cached_dev.sb_bio use-after-free and crash In our production environment, we have received multiple crash reports regarding libceph, which have caught our attention: ``` [6888366.280350] Call Trace: [6888366.280452] blk_update_request+0x14e/0x370 [6888366.280561] blk_mq_end_request+0x1a/0x130 [6888366.280671] rbd_img_handle_request+0x1a0/0x1b0 [rbd] [6888366.280792] rbd_obj_handle_request+0x32/0x40 [rbd] [6888366.280903] __complete_request+0x22/0x70 [libceph] [6888366.281032] osd_dispatch+0x15e/0xb40 [libceph] [6888366.281164] ? inet_recvmsg+0x5b/0xd0 [6888366.281272] ? ceph_tcp_recvmsg+0x6f/0xa0 [libceph] [6888366.281405] ceph_con_process_message+0x79/0x140 [libceph] [6888366.281534] ceph_con_v1_try_read+0x5d7/0xf30 [libceph] [6888366.281661] ceph_con_workfn+0x329/0x680 [libceph] ``` After analyzing the coredump file, we found that the address of dc->sb_bio has been freed. We know that cached_dev is only freed when it is stopped. Since sb_bio is a part of struct cached_dev, rather than an alloc every time. If the device is stopped while writing to the superblock, the released address will be accessed at endio. This patch hopes to wait for sb_write to complete in cached_dev_free. It should be noted that we analyzed the cause of the problem, then tell all details to the QWEN and adopted the modifications it made.
CVE-2026-31581: In the Linux kernel, the following vulnerability has been resolved: ALSA: 6fire: fix use-after-free on disconnect In usb6fire_chip_abort(), the chip struct is allocated as the card's private data (via snd_card_new with sizeof(struct sfire_chip)). When snd_card_free_when_closed() is called and no file handles are open, the card and embedded chip are freed synchronously. The subsequent chip->card = NULL write then hits freed slab memory. Call trace: usb6fire_chip_abort sound/usb/6fire/chip.c:59 [inline] usb6fire_chip_disconnect+0x348/0x358 sound/usb/6fire/chip.c:182 usb_unbind_interface+0x1a8/0x88c drivers/usb/core/driver.c:458 ... hub_event+0x1a04/0x4518 drivers/usb/core/hub.c:5953 Fix by moving the card lifecycle out of usb6fire_chip_abort() and into usb6fire_chip_disconnect(). The card pointer is saved in a local before any teardown, snd_card_disconnect() is called first to prevent new opens, URBs are aborted while chip is still valid, and snd_card_free_when_closed() is called last so chip is never accessed after the card may be freed.
CVE-2026-31582: In the Linux kernel, the following vulnerability has been resolved: hwmon: (powerz) Fix use-after-free on USB disconnect After powerz_disconnect() frees the URB and releases the mutex, a subsequent powerz_read() call can acquire the mutex and call powerz_read_data(), which dereferences the freed URB pointer. Fix by: - Setting priv->urb to NULL in powerz_disconnect() so that powerz_read_data() can detect the disconnected state. - Adding a !priv->urb check at the start of powerz_read_data() to return -ENODEV on a disconnected device. - Moving usb_set_intfdata() before hwmon registration so the disconnect handler can always find the priv pointer.
CVE-2026-31583: In the Linux kernel, the following vulnerability has been resolved: media: em28xx: fix use-after-free in em28xx_v4l2_open() em28xx_v4l2_open() reads dev->v4l2 without holding dev->lock, creating a race with em28xx_v4l2_init()'s error path and em28xx_v4l2_fini(), both of which free the em28xx_v4l2 struct and set dev->v4l2 to NULL under dev->lock. This race leads to two issues: - use-after-free in v4l2_fh_init() when accessing vdev->ctrl_handler, since the video_device is embedded in the freed em28xx_v4l2 struct. - NULL pointer dereference in em28xx_resolution_set() when accessing v4l2->norm, since dev->v4l2 has been set to NULL. Fix this by moving the mutex_lock() before the dev->v4l2 read and adding a NULL check for dev->v4l2 under the lock.
CVE-2026-31584: In the Linux kernel, the following vulnerability has been resolved: media: mediatek: vcodec: fix use-after-free in encoder release path The fops_vcodec_release() function frees the context structure (ctx) without first cancelling any pending or running work in ctx->encode_work. This creates a race window where the workqueue handler (mtk_venc_worker) may still be accessing the context memory after it has been freed. Race condition: CPU 0 (release path) CPU 1 (workqueue) --------------------- ------------------ fops_vcodec_release() v4l2_m2m_ctx_release() v4l2_m2m_cancel_job() // waits for m2m job "done" mtk_venc_worker() v4l2_m2m_job_finish() // m2m job "done" // BUT worker still running! // post-job_finish access: other ctx dereferences // UAF if ctx already freed // returns (job "done") kfree(ctx) // ctx freed Root cause: The v4l2_m2m_ctx_release() only waits for the m2m job lifecycle (via TRANS_RUNNING flag), not the workqueue lifecycle. After v4l2_m2m_job_finish() is called, the m2m framework considers the job complete and v4l2_m2m_ctx_release() returns, but the worker function continues executing and may still access ctx. The work is queued during encode operations via: queue_work(ctx->dev->encode_workqueue, &ctx->encode_work) The worker function accesses ctx->m2m_ctx, ctx->dev, and other ctx fields even after calling v4l2_m2m_job_finish(). This vulnerability was confirmed with KASAN by running an instrumented test module that widens the post-job_finish race window. KASAN detected: BUG: KASAN: slab-use-after-free in mtk_venc_worker+0x159/0x180 Read of size 4 at addr ffff88800326e000 by task kworker/u8:0/12 Workqueue: mtk_vcodec_enc_wq mtk_venc_worker Allocated by task 47: __kasan_kmalloc+0x7f/0x90 fops_vcodec_open+0x85/0x1a0 Freed by task 47: __kasan_slab_free+0x43/0x70 kfree+0xee/0x3a0 fops_vcodec_release+0xb7/0x190 Fix this by calling cancel_work_sync(&ctx->encode_work) before kfree(ctx). This ensures the workqueue handler is both cancelled (if pending) and synchronized (waits for any running handler to complete) before the context is freed. Placement rationale: The fix is placed after v4l2_ctrl_handler_free() and before list_del_init(&ctx->list). At this point, all m2m operations are done (v4l2_m2m_ctx_release() has returned), and we need to ensure the workqueue is synchronized before removing ctx from the list and freeing it. Note: The open error path does NOT need cancel_work_sync() because INIT_WORK() only initializes the work structure - it does not schedule it. Work is only scheduled later during device_run() operations.
CVE-2026-31585: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix nfeeds state corruption on start_streaming failure syzbot reported a memory leak in vidtv_psi_service_desc_init [1]. When vidtv_start_streaming() fails inside vidtv_start_feed(), the nfeeds counter is left incremented even though no feed was actually started. This corrupts the driver state: subsequent start_feed calls see nfeeds > 1 and skip starting the mux, while stop_feed calls eventually try to stop a non-existent stream. This state corruption can also lead to memory leaks, since the mux and channel resources may be partially allocated during a failed start_streaming but never cleaned up, as the stop path finds dvb->streaming == false and returns early. Fix by decrementing nfeeds back when start_streaming fails, keeping the counter in sync with the actual number of active feeds. [1] BUG: memory leak unreferenced object 0xffff888145b50820 (size 32): comm "syz.0.17", pid 6068, jiffies 4294944486 backtrace (crc 90a0c7d4): vidtv_psi_service_desc_init+0x74/0x1b0 drivers/media/test-drivers/vidtv/vidtv_psi.c:288 vidtv_channel_s302m_init+0xb1/0x2a0 drivers/media/test-drivers/vidtv/vidtv_channel.c:83 vidtv_channels_init+0x1b/0x40 drivers/media/test-drivers/vidtv/vidtv_channel.c:524 vidtv_mux_init+0x516/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:518 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31586: In the Linux kernel, the following vulnerability has been resolved: mm: blk-cgroup: fix use-after-free in cgwb_release_workfn() cgwb_release_workfn() calls css_put(wb->blkcg_css) and then later accesses wb->blkcg_css again via blkcg_unpin_online(). If css_put() drops the last reference, the blkcg can be freed asynchronously (css_free_rwork_fn -> blkcg_css_free -> kfree) before blkcg_unpin_online() dereferences the pointer to access blkcg->online_pin, resulting in a use-after-free: BUG: KASAN: slab-use-after-free in blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) Write of size 4 at addr ff11000117aa6160 by task kworker/71:1/531 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> blkcg_unpin_online (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 block/blk-cgroup.c:1367) cgwb_release_workfn (mm/backing-dev.c:629) process_scheduled_works (kernel/workqueue.c:3278 kernel/workqueue.c:3385) Freed by task 1016: kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6246 mm/slub.c:6561) css_free_rwork_fn (kernel/cgroup/cgroup.c:5542) process_scheduled_works (kernel/workqueue.c:3302 kernel/workqueue.c:3385) ** Stack based on commit 66672af7a095 ("Add linux-next specific files for 20260410") I am seeing this crash sporadically in Meta fleet across multiple kernel versions. A full reproducer is available at: https://github.com/leitao/debug/blob/main/reproducers/repro_blkcg_uaf.sh (The race window is narrow. To make it easily reproducible, inject a msleep(100) between css_put() and blkcg_unpin_online() in cgwb_release_workfn(). With that delay and a KASAN-enabled kernel, the reproducer triggers the splat reliably in less than a second.) Fix this by moving blkcg_unpin_online() before css_put(), so the cgwb's CSS reference keeps the blkcg alive while blkcg_unpin_online() accesses it.
CVE-2026-31587: In the Linux kernel, the following vulnerability has been resolved: ASoC: qcom: q6apm: move component registration to unmanaged version q6apm component registers dais dynamically from ASoC toplology, which are allocated using device managed version apis. Allocating both component and dynamic dais using managed version could lead to incorrect free ordering, dai will be freed while component still holding references to it. Fix this issue by moving component to unmanged version so that the dai pointers are only freeded after the component is removed. ================================================================== BUG: KASAN: slab-use-after-free in snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] Read of size 8 at addr ffff00084493a6e8 by task kworker/u48:0/3426 Tainted: [W]=WARN Hardware name: LENOVO 21N2ZC5PUS/21N2ZC5PUS, BIOS N42ET57W (1.31 ) 08/08/2024 Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface] Call trace: show_stack+0x28/0x7c (C) dump_stack_lvl+0x60/0x80 print_report+0x160/0x4b4 kasan_report+0xac/0xfc __asan_report_load8_noabort+0x20/0x34 snd_soc_del_component_unlocked+0x3d4/0x400 [snd_soc_core] snd_soc_unregister_component_by_driver+0x50/0x88 [snd_soc_core] devm_component_release+0x30/0x5c [snd_soc_core] devres_release_all+0x13c/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Allocated by task 77: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 kasan_save_alloc_info+0x44/0x58 __kasan_kmalloc+0xbc/0xdc __kmalloc_node_track_caller_noprof+0x1f4/0x620 devm_kmalloc+0x7c/0x1c8 snd_soc_register_dai+0x50/0x4f0 [snd_soc_core] soc_tplg_pcm_elems_load+0x55c/0x1eb8 [snd_soc_core] snd_soc_tplg_component_load+0x4f8/0xb60 [snd_soc_core] audioreach_tplg_init+0x124/0x1fc [snd_q6apm] q6apm_audio_probe+0x10/0x1c [snd_q6apm] snd_soc_component_probe+0x5c/0x118 [snd_soc_core] soc_probe_component+0x44c/0xaf0 [snd_soc_core] snd_soc_bind_card+0xad0/0x2370 [snd_soc_core] snd_soc_register_card+0x3b0/0x4c0 [snd_soc_core] devm_snd_soc_register_card+0x50/0xc8 [snd_soc_core] x1e80100_platform_probe+0x208/0x368 [snd_soc_x1e80100] platform_probe+0xc0/0x188 really_probe+0x188/0x804 __driver_probe_device+0x158/0x358 driver_probe_device+0x60/0x190 __device_attach_driver+0x16c/0x2a8 bus_for_each_drv+0x100/0x194 __device_attach+0x174/0x380 device_initial_probe+0x14/0x20 bus_probe_device+0x124/0x154 deferred_probe_work_func+0x140/0x220 process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20 Freed by task 3426: kasan_save_stack+0x40/0x68 kasan_save_track+0x20/0x40 __kasan_save_free_info+0x4c/0x80 __kasan_slab_free+0x78/0xa0 kfree+0x100/0x4a4 devres_release_all+0x144/0x210 device_unbind_cleanup+0x20/0x190 device_release_driver_internal+0x350/0x468 device_release_driver+0x18/0x30 bus_remove_device+0x1a0/0x35c device_del+0x314/0x7f0 device_unregister+0x20/0xbc apr_remove_device+0x5c/0x7c [apr] device_for_each_child+0xd8/0x160 apr_pd_status+0x7c/0xa8 [apr] pdr_notifier_work+0x114/0x240 [pdr_interface] process_one_work+0x500/0xb70 worker_thread+0x630/0xfb0 kthread+0x370/0x6c0 ret_from_fork+0x10/0x20
CVE-2026-31588: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Use scratch field in MMIO fragment to hold small write values When exiting to userspace to service an emulated MMIO write, copy the to-be-written value to a scratch field in the MMIO fragment if the size of the data payload is 8 bytes or less, i.e. can fit in a single chunk, instead of pointing the fragment directly at the source value. This fixes a class of use-after-free bugs that occur when the emulator initiates a write using an on-stack, local variable as the source, the write splits a page boundary, *and* both pages are MMIO pages. Because KVM's ABI only allows for physically contiguous MMIO requests, accesses that split MMIO pages are separated into two fragments, and are sent to userspace one at a time. When KVM attempts to complete userspace MMIO in response to KVM_RUN after the first fragment, KVM will detect the second fragment and generate a second userspace exit, and reference the on-stack variable. The issue is most visible if the second KVM_RUN is performed by a separate task, in which case the stack of the initiating task can show up as truly freed data. ================================================================== BUG: KASAN: use-after-free in complete_emulated_mmio+0x305/0x420 Read of size 1 at addr ffff888009c378d1 by task syz-executor417/984 CPU: 1 PID: 984 Comm: syz-executor417 Not tainted 5.10.0-182.0.0.95.h2627.eulerosv2r13.x86_64 #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0xbe/0xfd print_address_description.constprop.0+0x19/0x170 __kasan_report.cold+0x6c/0x84 kasan_report+0x3a/0x50 check_memory_region+0xfd/0x1f0 memcpy+0x20/0x60 complete_emulated_mmio+0x305/0x420 kvm_arch_vcpu_ioctl_run+0x63f/0x6d0 kvm_vcpu_ioctl+0x413/0xb20 __se_sys_ioctl+0x111/0x160 do_syscall_64+0x30/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 RIP: 0033:0x42477d Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007faa8e6890e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000004d7338 RCX: 000000000042477d RDX: 0000000000000000 RSI: 000000000000ae80 RDI: 0000000000000005 RBP: 00000000004d7330 R08: 00007fff28d546df R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d733c R13: 0000000000000000 R14: 000000000040a200 R15: 00007fff28d54720 The buggy address belongs to the page: page:0000000029f6a428 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x9c37 flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea0000270dc8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888009c37780: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37800: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff888009c37880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff888009c37900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888009c37980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== The bug can also be reproduced with a targeted KVM-Unit-Test by hacking KVM to fill a large on-stack variable in complete_emulated_mmio(), i.e. by overwrite the data value with garbage. Limit the use of the scratch fields to 8-byte or smaller accesses, and to just writes, as larger accesses and reads are not affected thanks to implementation details in the emulator, but add a sanity check to ensure those details don't change in the future. Specifically, KVM never uses on-stack variables for accesses larger that 8 bytes, e.g. uses an operand in the emulator context, and *al ---truncated---
CVE-2026-31589: In the Linux kernel, the following vulnerability has been resolved: mm: call ->free_folio() directly in folio_unmap_invalidate() We can only call filemap_free_folio() if we have a reference to (or hold a lock on) the mapping. Otherwise, we've already removed the folio from the mapping so it no longer pins the mapping and the mapping can be removed, causing a use-after-free when accessing mapping->a_ops. Follow the same pattern as __remove_mapping() and load the free_folio function pointer before dropping the lock on the mapping. That lets us make filemap_free_folio() static as this was the only caller outside filemap.c.
CVE-2026-31590: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing: struct kvm_enc_region range = { .addr = 0, .size = -1ul, }; __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range); Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future. if (range->addr > ULONG_MAX || range->size > ULONG_MAX) return -EINVAL; Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.
CVE-2026-31591: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel. Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).
CVE-2026-31592: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Protect *all* of sev_mem_enc_register_region() with kvm->lock Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G U W O 6.16.0-smp-DEV #1 NONE Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024 RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83 Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00 RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256 RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000 RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000 RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000 R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000 R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000 FS: 00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0 Call Trace: <TASK> kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371 kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363 __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51 do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f34e9f7e9a9 Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9 RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007 RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8 </TASK> with a syzlang reproducer that looks like: syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async) r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0) r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0) r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0) r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0) ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async) ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async) r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0) openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async) ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2) close(r0) (async) openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async) ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0) Opportunistically use guard() to avoid having to define a new error label and goto usage.
CVE-2026-31593: In the Linux kernel, the following vulnerability has been resolved: KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host. BUG: unable to handle page fault for address: ff1276cbfdf36000 #PF: supervisor write access in kernel mode #PF: error_code(0x80000003) - RMP violation PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163 SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f] Oops: Oops: 0003 [#1] SMP NOPTI CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G OE Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023 RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd] Call Trace: <TASK> snp_launch_update_vmsa+0x19d/0x290 [kvm_amd] snp_launch_finish+0xb6/0x380 [kvm_amd] sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd] kvm_arch_vm_ioctl+0x837/0xcf0 [kvm] kvm_vm_ioctl+0x3fd/0xcc0 [kvm] __x64_sys_ioctl+0xa3/0x100 x64_sys_call+0xfe0/0x2350 do_syscall_64+0x81/0x10f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7ffff673287d </TASK> Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().
CVE-2026-31594: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case: Unable to handle kernel paging request at virtual address dead000000000108 [...] [dead000000000108] address between user and kernel address ranges Internal error: Oops: 0000000096000044 [#1] SMP [...] Call trace: pci_epc_remove_epf+0x78/0xe0 (P) pci_primary_epc_epf_link+0x88/0xa8 configfs_symlink+0x1f4/0x5a0 vfs_symlink+0x134/0x1d8 do_symlinkat+0x88/0x138 __arm64_sys_symlinkat+0x74/0xe0 [...] Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.
CVE-2026-31595: In the Linux kernel, the following vulnerability has been resolved: PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down. Unable to handle kernel paging request at virtual address ffff800083f46004 [...] Internal error: Oops: 0000000096000007 [#1] SMP [...] Call trace: epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P) process_one_work+0x154/0x3b0 worker_thread+0x2c8/0x400 kthread+0x148/0x210 ret_from_fork+0x10/0x20
CVE-2026-31596: In the Linux kernel, the following vulnerability has been resolved: ocfs2: handle invalid dinode in ocfs2_group_extend [BUG] kernel BUG at fs/ocfs2/resize.c:308! Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308 Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe Call Trace: ... ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... [CAUSE] ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl. [FIX] Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.
CVE-2026-31597: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c: "If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()." When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free. Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.
CVE-2026-31598: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix possible deadlock between unlink and dio_end_io_write ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key. Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem): ocfs2_unlink ocfs2_prepare_orphan_dir ocfs2_lookup_lock_orphan_dir inode_lock(orphan_dir_inode) <- lock A __ocfs2_prepare_orphan_dir ocfs2_prepare_dir_for_insert ocfs2_extend_dir ocfs2_expand_inline_dir down_write(&oi->ip_alloc_sem) <- Lock B Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock): ocfs2_dio_end_io_write down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan() inode_lock(orphan_dir_inode) <- Lock A Deadlock Scenario: CPU0 (unlink) CPU1 (dio_end_io_write) ------ ------ inode_lock(orphan_dir_inode) down_write(ip_alloc_sem) down_write(ip_alloc_sem) inode_lock(orphan_dir_inode) Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.
CVE-2026-31599: In the Linux kernel, the following vulnerability has been resolved: media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections syzbot reported a general protection fault in vidtv_psi_desc_assign [1]. vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault. Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return. [1] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629 Call Trace: <TASK> vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline] vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline] vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239
CVE-2026-31600: In the Linux kernel, the following vulnerability has been resolved: arm64: mm: Handle invalid large leaf mappings correctly It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way. It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result: [ 15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers [ 15.476896] Unable to handle kernel paging request at virtual address ffff000019600000 [ 15.513762] Mem abort info: [ 15.527245] ESR = 0x0000000096000046 [ 15.548553] EC = 0x25: DABT (current EL), IL = 32 bits [ 15.572146] SET = 0, FnV = 0 [ 15.592141] EA = 0, S1PTW = 0 [ 15.612694] FSC = 0x06: level 2 translation fault [ 15.640644] Data abort info: [ 15.661983] ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000 [ 15.694875] CM = 0, WnR = 1, TnD = 0, TagAccess = 0 [ 15.723740] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000 [ 15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704 [ 15.855046] Internal error: Oops: 0000000096000046 [#1] SMP [ 15.886394] Modules linked in: [ 15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT [ 15.935258] Hardware name: linux,dummy-virt (DT) [ 15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--) [ 15.986009] pc : __pi_memcpy_generic+0x128/0x22c [ 16.006163] lr : swiotlb_bounce+0xf4/0x158 [ 16.024145] sp : ffff80008000b8f0 [ 16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000 [ 16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000 [ 16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0 [ 16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc [ 16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974 [ 16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018 [ 16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000 [ 16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000 [ 16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000 [ 16.349071] Call trace: [ 16.360143] __pi_memcpy_generic+0x128/0x22c (P) [ 16.380310] swiotlb_tbl_map_single+0x154/0x2b4 [ 16.400282] swiotlb_map+0x5c/0x228 [ 16.415984] dma_map_phys+0x244/0x2b8 [ 16.432199] dma_map_page_attrs+0x44/0x58 [ 16.449782] virtqueue_map_page_attrs+0x38/0x44 [ 16.469596] virtqueue_map_single_attrs+0xc0/0x130 [ 16.490509] virtnet_rq_alloc.isra.0+0xa4/0x1fc [ 16.510355] try_fill_recv+0x2a4/0x584 [ 16.526989] virtnet_open+0xd4/0x238 [ 16.542775] __dev_open+0x110/0x24c [ 16.558280] __dev_change_flags+0x194/0x20c [ 16.576879] netif_change_flags+0x24/0x6c [ 16.594489] dev_change_flags+0x48/0x7c [ 16.611462] ip_auto_config+0x258/0x1114 [ 16.628727] do_one_initcall+0x80/0x1c8 [ 16.645590] kernel_init_freeable+0x208/0x2f0 [ 16.664917] kernel_init+0x24/0x1e0 [ 16.680295] ret_from_fork+0x10/0x20 [ 16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c) [ 16.723106] ---[ end trace 0000000000000000 ]--- [ 16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 16.792556] Kernel Offset: 0x3396ea200000 from 0xffff8000800000 ---truncated---
CVE-2026-31601: In the Linux kernel, the following vulnerability has been resolved: vfio/xe: Reorganize the init to decouple migration from reset Attempting to issue reset on VF devices that don't support migration leads to the following: BUG: unable to handle page fault for address: 00000000000011f8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 2 UID: 0 PID: 7443 Comm: xe_sriov_flr Tainted: G S U 7.0.0-rc1-lgci-xe-xe-4588-cec43d5c2696af219-nodebug+ #1 PREEMPT(lazy) Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR4 RVP, BIOS RPLPFWI1.R00.4035.A00.2301200723 01/20/2023 RIP: 0010:xe_sriov_vfio_wait_flr_done+0xc/0x80 [xe] Code: ff c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 54 53 <83> bf f8 11 00 00 02 75 61 41 89 f4 85 f6 74 52 48 8b 47 08 48 89 RSP: 0018:ffffc9000f7c39b8 EFLAGS: 00010202 RAX: ffffffffa04d8660 RBX: ffff88813e3e4000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc9000f7c39c8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff888101a48800 R13: ffff88813e3e4150 R14: ffff888130d0d008 R15: ffff88813e3e40d0 FS: 00007877d3d0d940(0000) GS:ffff88890b6d3000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000011f8 CR3: 000000015a762000 CR4: 0000000000f52ef0 PKRU: 55555554 Call Trace: <TASK> xe_vfio_pci_reset_done+0x49/0x120 [xe_vfio_pci] pci_dev_restore+0x3b/0x80 pci_reset_function+0x109/0x140 reset_store+0x5c/0xb0 dev_attr_store+0x17/0x40 sysfs_kf_write+0x72/0x90 kernfs_fop_write_iter+0x161/0x1f0 vfs_write+0x261/0x440 ksys_write+0x69/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x259/0x26e0 do_syscall_64+0xcb/0x1500 ? __fput+0x1a2/0x2d0 ? fput_close_sync+0x3d/0xa0 ? __x64_sys_close+0x3e/0x90 ? x64_sys_call+0x1b7c/0x26e0 ? do_syscall_64+0x109/0x1500 ? __task_pid_nr_ns+0x68/0x100 ? __do_sys_getpid+0x1d/0x30 ? x64_sys_call+0x10b5/0x26e0 ? do_syscall_64+0x109/0x1500 ? putname+0x41/0x90 ? do_faccessat+0x1e8/0x300 ? __x64_sys_access+0x1c/0x30 ? x64_sys_call+0x1822/0x26e0 ? do_syscall_64+0x109/0x1500 ? tick_program_event+0x43/0xa0 ? hrtimer_interrupt+0x126/0x260 ? irqentry_exit+0xb2/0x710 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7877d5f1c5a4 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fff48e5f908 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007877d5f1c5a4 RDX: 0000000000000001 RSI: 00007877d621b0c9 RDI: 0000000000000009 RBP: 0000000000000001 R08: 00005fb49113b010 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000202 R12: 00007877d621b0c9 R13: 0000000000000009 R14: 00007fff48e5fac0 R15: 00007fff48e5fac0 </TASK> This is caused by the fact that some of the xe_vfio_pci_core_device members needed for handling reset are only initialized as part of migration init. Fix the problem by reorganizing the code to decouple VF init from migration init.
CVE-2026-31602: In the Linux kernel, the following vulnerability has been resolved: ALSA: ctxfi: Limit PTP to a single page Commit 391e69143d0a increased CT_PTP_NUM from 1 to 4 to support 256 playback streams, but the additional pages are not used by the card correctly. The CT20K2 hardware already has multiple VMEM_PTPAL registers, but using them separately would require refactoring the entire virtual memory allocation logic. ct_vm_map() always uses PTEs in vm->ptp[0].area regardless of CT_PTP_NUM. On AMD64 systems, a single PTP covers 512 PTEs (2M). When aggregate memory allocations exceed this limit, ct_vm_map() tries to access beyond the allocated space and causes a page fault: BUG: unable to handle page fault for address: ffffd4ae8a10a000 Oops: Oops: 0002 [#1] SMP PTI RIP: 0010:ct_vm_map+0x17c/0x280 [snd_ctxfi] Call Trace: atc_pcm_playback_prepare+0x225/0x3b0 ct_pcm_playback_prepare+0x38/0x60 snd_pcm_do_prepare+0x2f/0x50 snd_pcm_action_single+0x36/0x90 snd_pcm_action_nonatomic+0xbf/0xd0 snd_pcm_ioctl+0x28/0x40 __x64_sys_ioctl+0x97/0xe0 do_syscall_64+0x81/0x610 entry_SYSCALL_64_after_hwframe+0x76/0x7e Revert CT_PTP_NUM to 1. The 256 SRC_RESOURCE_NUM and playback_count remain unchanged.
CVE-2026-31603: In the Linux kernel, the following vulnerability has been resolved: staging: sm750fb: fix division by zero in ps_to_hz() ps_to_hz() is called from hw_sm750_crtc_set_mode() without validating that pixclock is non-zero. A zero pixclock passed via FBIOPUT_VSCREENINFO causes a division by zero. Fix by rejecting zero pixclock in lynxfb_ops_check_var(), consistent with other framebuffer drivers.
CVE-2026-31604: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw88: fix device leak on probe failure Driver core holds a reference to the USB interface and its parent USB device while the interface is bound to a driver and there is no need to take additional references unless the structures are needed after disconnect. This driver takes a reference to the USB device during probe but does not to release it on all probe errors (e.g. when descriptor parsing fails). Drop the redundant device reference to fix the leak, reduce cargo culting, make it easier to spot drivers where an extra reference is needed, and reduce the risk of further memory leaks.
CVE-2026-31605: In the Linux kernel, the following vulnerability has been resolved: fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31606: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_hid: don't call cdev_init while cdev in use When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes. This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.
CVE-2026-31607: In the Linux kernel, the following vulnerability has been resolved: usbip: validate number_of_packets in usbip_pack_ret_submit() When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the *original* number_of_packets from the CMD_SUBMIT. A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region. KASAN confirmed this with kernel 7.0.0-rc5: BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640 Write of size 4 at addr ffff888106351d40 by task vhci_rx/69 The buggy address is located 0 bytes to the right of allocated 320-byte region [ffff888106351c00, ffff888106351d40) The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter bound: the response must not exceed the original number_of_packets. This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size. Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit. Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.
CVE-2026-31608: In the Linux kernel, the following vulnerability has been resolved: smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list() smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg() moved it to the batch list.
CVE-2026-31609: In the Linux kernel, the following vulnerability has been resolved: smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush() smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.
CVE-2026-31610: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix mechToken leak when SPNEGO decode fails after token alloc The kernel ASN.1 BER decoder calls action callbacks incrementally as it walks the input. When ksmbd_decode_negTokenInit() reaches the mechToken [2] OCTET STRING element, ksmbd_neg_token_alloc() allocates conn->mechToken immediately via kmemdup_nul(). If a later element in the same blob is malformed, then the decoder will return nonzero after the allocation is already live. This could happen if mechListMIC [3] overrunse the enclosing SEQUENCE. decode_negotiation_token() then sets conn->use_spnego = false because both the negTokenInit and negTokenTarg grammars failed. The cleanup at the bottom of smb2_sess_setup() is gated on use_spnego: if (conn->use_spnego && conn->mechToken) { kfree(conn->mechToken); conn->mechToken = NULL; } so the kfree is skipped, causing the mechToken to never be freed. This codepath is reachable pre-authentication, so untrusted clients can cause slow memory leaks on a server without even being properly authenticated. Fix this up by not checking check for use_spnego, as it's not required, so the memory will always be properly freed. At the same time, always free the memory in ksmbd_conn_free() incase some other failure path forgot to free it.
CVE-2026-31611: In the Linux kernel, the following vulnerability has been resolved: ksmbd: require 3 sub-authorities before reading sub_auth[2] parse_dacl() compares each ACE SID against sid_unix_NFS_mode and on match reads sid.sub_auth[2] as the file mode. If sid_unix_NFS_mode is the prefix S-1-5-88-3 with num_subauth = 2 then compare_sids() compares only min(num_subauth, 2) sub-authorities so a client SID with num_subauth = 2 and sub_auth = {88, 3} will match. If num_subauth = 2 and the ACE is placed at the very end of the security descriptor, sub_auth[2] will be 4 bytes past end_of_acl. The out-of-band bytes will then be masked to the low 9 bits and applied as the file's POSIX mode, probably not something that is good to have happen. Fix this up by forcing the SID to actually carry a third sub-authority before reading it at all.
CVE-2026-31612: In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate EaNameLength in smb2_get_ea() smb2_get_ea() reads ea_req->EaNameLength from the client request and passes it directly to strncmp() as the comparison length without verifying that the length of the name really is the size of the input buffer received. Fix this up by properly checking the size of the name based on the value received and the overall size of the request, to prevent a later strncmp() call to use the length as a "trusted" size of the buffer. Without this check, uninitialized heap values might be slowly leaked to the client.
CVE-2026-31613: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix OOB reads parsing symlink error response When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server. symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset 0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits. smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0. With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2). Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset. Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than.
CVE-2026-31615: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: renesas_usb3: validate endpoint index in standard request handlers The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math. This is just like what was done in commit ee0d382feb44 ("usb: gadget: aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.
CVE-2026-31616: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete() A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers. pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap. Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path").
CVE-2026-31617: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb() The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of: ndp_index > (block_len - opts->ndp_size) will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely. The same underflow occurs in the datagram index checks against block_len - opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb. Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined. Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.
CVE-2026-31618: In the Linux kernel, the following vulnerability has been resolved: fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.
CVE-2026-31619: In the Linux kernel, the following vulnerability has been resolved: ALSA: fireworks: bound device-supplied status before string array lookup The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value. Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings. Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.
CVE-2026-31620: In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0 A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly. Fix this up by checking the return value properly.
CVE-2026-31621: In the Linux kernel, the following vulnerability has been resolved: bnge: return after auxiliary_device_uninit() in error path When auxiliary_device_add() fails, the error block calls auxiliary_device_uninit() but does not return. The uninit drops the last reference and synchronously runs bnge_aux_dev_release(), which sets bd->auxr_dev = NULL and frees the underlying object. The subsequent bd->auxr_dev->net = bd->netdev then dereferences NULL, which is not a good thing to have happen when trying to clean up from an error. Add the missing return, as the auxiliary bus documentation states is a requirement (seems that LLM tools read documentation better than humans do...)
CVE-2026-31622: In the Linux kernel, the following vulnerability has been resolved: NFC: digital: Bounds check NFC-A cascade depth in SDD response handler The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows). ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round. Fix this by rejecting the response when the accumulated UID would exceed the buffer. Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.
CVE-2026-31623: In the Linux kernel, the following vulnerability has been resolved: net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete() A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers. Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net: wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.
CVE-2026-31624: In the Linux kernel, the following vulnerability has been resolved: HID: core: clamp report_size in s32ton() to avoid undefined shift s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field(). Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way. Fix this up by just clamping the max value of n, just like snto32() does.
CVE-2026-31625: In the Linux kernel, the following vulnerability has been resolved: HID: alps: fix NULL pointer dereference in alps_raw_event() Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), but the alps driver was missed. Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.
CVE-2026-31626: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify() Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data. Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized: drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify() warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes) Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.
CVE-2026-31627: In the Linux kernel, the following vulnerability has been resolved: i2c: s3c24xx: check the size of the SMBUS message before using it The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it. This is the same logic that was added in commit a6e04f05ce0b ("i2c: tegra: check msg length in SMBUS block read") to the i2c tegra driver.
CVE-2026-31628: In the Linux kernel, the following vulnerability has been resolved: x86/CPU: Fix FPDSS on Zen1 Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread. Fix that with a chicken bit.
CVE-2026-31629: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: add missing return after LLCP_CLOSED checks In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free. Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.
CVE-2026-31630: In the Linux kernel, the following vulnerability has been resolved: rxrpc: proc: size address buffers for %pISpc output The AF_RXRPC procfs helpers format local and remote socket addresses into fixed 50-byte stack buffers with "%pISpc". That is too small for the longest current-tree IPv6-with-port form the formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a dotted-quad tail not only for v4mapped addresses, but also for ISATAP addresses via ipv6_addr_is_isatap(). As a result, a case such as [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535 is possible with the current formatter. That is 50 visible characters, so 51 bytes including the trailing NUL, which does not fit in the existing char[50] buffers used by net/rxrpc/proc.c. Size the buffers from the formatter's maximum textual form and switch the call sites to scnprintf(). Changes since v1: - correct the changelog to cite the actual maximum current-tree case explicitly - frame the proof around the ISATAP formatting path instead of the earlier mapped-v4 example
CVE-2026-31634: In the Linux kernel, the following vulnerability has been resolved: rxrpc: fix reference count leak in rxrpc_server_keyring() This patch fixes a reference count leak in rxrpc_server_keyring() by checking if rx->securities is already set.
CVE-2026-31637: In the Linux kernel, the following vulnerability has been resolved: rxrpc: reject undecryptable rxkad response tickets rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then parses the buffer as plaintext without checking whether crypto_skcipher_decrypt() succeeded. A malformed RESPONSE can therefore use a non-block-aligned ticket length, make the decrypt operation fail, and still drive the ticket parser with attacker-controlled bytes. Check the decrypt result and abort the connection with RXKADBADTICKET when ticket decryption fails.
CVE-2026-31642: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix call removal to use RCU safe deletion Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu() rather than list_del_init() to prevent stuffing up reading /proc/net/rxrpc/calls from potentially getting into an infinite loop. This, however, means that list_empty() no longer works on an entry that's been deleted from the list, making it harder to detect prior deletion. Fix this by: Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that are unexpectedly still on the list. Limiting the number of steps means there's no need to call cond_resched() or to remove calls from the list here, thereby eliminating the need for rxrpc_put_call() to check for that. rxrpc_put_call() can then be fixed to unconditionally delete the call from the list as it is the only place that the deletion occurs.
CVE-2026-31648: In the Linux kernel, the following vulnerability has been resolved: mm: filemap: fix nr_pages calculation overflow in filemap_map_pages() When running stress-ng on my Arm64 machine with v7.0-rc3 kernel, I encountered some very strange crash issues showing up as "Bad page state": " [ 734.496287] BUG: Bad page state in process stress-ng-env pfn:415735fb [ 734.496427] page: refcount:0 mapcount:1 mapping:0000000000000000 index:0x4cf316 pfn:0x415735fb [ 734.496434] flags: 0x57fffe000000800(owner_2|node=1|zone=2|lastcpupid=0x3ffff) [ 734.496439] raw: 057fffe000000800 0000000000000000 dead000000000122 0000000000000000 [ 734.496440] raw: 00000000004cf316 0000000000000000 0000000000000000 0000000000000000 [ 734.496442] page dumped because: nonzero mapcount " After analyzing this page’s state, it is hard to understand why the mapcount is not 0 while the refcount is 0, since this page is not where the issue first occurred. By enabling the CONFIG_DEBUG_VM config, I can reproduce the crash as well and captured the first warning where the issue appears: " [ 734.469226] page: refcount:33 mapcount:0 mapping:00000000bef2d187 index:0x81a0 pfn:0x415735c0 [ 734.469304] head: order:5 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 734.469315] memcg:ffff000807a8ec00 [ 734.469320] aops:ext4_da_aops ino:100b6f dentry name(?):"stress-ng-mmaptorture-9397-0-2736200540" [ 734.469335] flags: 0x57fffe400000069(locked|uptodate|lru|head|node=1|zone=2|lastcpupid=0x3ffff) ...... [ 734.469364] page dumped because: VM_WARN_ON_FOLIO((_Generic((page + nr_pages - 1), const struct page *: (const struct folio *)_compound_head(page + nr_pages - 1), struct page *: (struct folio *)_compound_head(page + nr_pages - 1))) != folio) [ 734.469390] ------------[ cut here ]------------ [ 734.469393] WARNING: ./include/linux/rmap.h:351 at folio_add_file_rmap_ptes+0x3b8/0x468, CPU#90: stress-ng-mlock/9430 [ 734.469551] folio_add_file_rmap_ptes+0x3b8/0x468 (P) [ 734.469555] set_pte_range+0xd8/0x2f8 [ 734.469566] filemap_map_folio_range+0x190/0x400 [ 734.469579] filemap_map_pages+0x348/0x638 [ 734.469583] do_fault_around+0x140/0x198 ...... [ 734.469640] el0t_64_sync+0x184/0x188 " The code that triggers the warning is: "VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio)", which indicates that set_pte_range() tried to map beyond the large folio’s size. By adding more debug information, I found that 'nr_pages' had overflowed in filemap_map_pages(), causing set_pte_range() to establish mappings for a range exceeding the folio size, potentially corrupting fields of pages that do not belong to this folio (e.g., page->_mapcount). After above analysis, I think the possible race is as follows: CPU 0 CPU 1 filemap_map_pages() ext4_setattr() //get and lock folio with old inode->i_size next_uptodate_folio() ....... //shrink the inode->i_size i_size_write(inode, attr->ia_size); //calculate the end_pgoff with the new inode->i_size file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); ...... //nr_pages can be overflowed, cause xas.xa_index > end_pgoff end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; ...... //map large folio filemap_map_folio_range() ...... //truncate folios truncate_pagecache(inode, inode->i_size); To fix this issue, move the 'end_pgoff' calculation before next_uptodate_folio(), so the retrieved folio stays consistent with the file end to avoid ---truncated---
CVE-2026-31649: In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix integer underflow in chain mode The jumbo_frm() chain-mode implementation unconditionally computes len = nopaged_len - bmax; where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is BUF_SIZE_8KiB or BUF_SIZE_2KiB. However, the caller stmmac_xmit() decides to invoke jumbo_frm() based on skb->len (total length including page fragments): is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); When a packet has a small linear portion (nopaged_len <= bmax) but a large total length due to page fragments (skb->len > bmax), the subtraction wraps as an unsigned integer, producing a huge len value (~0xFFFFxxxx). This causes the while (len != 0) loop to execute hundreds of thousands of iterations, passing skb->data + bmax * i pointers far beyond the skb buffer to dma_map_single(). On IOMMU-less SoCs (the typical deployment for stmmac), this maps arbitrary kernel memory to the DMA engine, constituting a kernel memory disclosure and potential memory corruption from hardware. Fix this by introducing a buf_len local variable clamped to min(nopaged_len, bmax). Computing len = nopaged_len - buf_len is then always safe: it is zero when the linear portion fits within a single descriptor, causing the while (len != 0) loop to be skipped naturally, and the fragment loop in stmmac_xmit() handles page fragments afterward.
CVE-2026-31651: In the Linux kernel, the following vulnerability has been resolved: mmc: vub300: fix NULL-deref on disconnect Make sure to deregister the controller before dropping the reference to the driver data on disconnect to avoid NULL-pointer dereferences or use-after-free.
CVE-2026-31655: In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx8mp-blk-ctrl: Keep the NOC_HDCP clock enabled Keep the NOC_HDCP clock always enabled to fix the potential hang caused by the NoC ADB400 port power down handshake.
CVE-2026-31656: In the Linux kernel, the following vulnerability has been resolved: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat A use-after-free / refcount underflow is possible when the heartbeat worker and intel_engine_park_heartbeat() race to release the same engine->heartbeat.systole request. The heartbeat worker reads engine->heartbeat.systole and calls i915_request_put() on it when the request is complete, but clears the pointer in a separate, non-atomic step. Concurrently, a request retirement on another CPU can drop the engine wakeref to zero, triggering __engine_park() -> intel_engine_park_heartbeat(). If the heartbeat timer is pending at that point, cancel_delayed_work() returns true and intel_engine_park_heartbeat() reads the stale non-NULL systole pointer and calls i915_request_put() on it again, causing a refcount underflow: ``` <4> [487.221889] Workqueue: i915-unordered engine_retire [i915] <4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0 ... <4> [487.222707] Call Trace: <4> [487.222711] <TASK> <4> [487.222716] intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915] <4> [487.223115] intel_engine_park_heartbeat+0x25/0x40 [i915] <4> [487.223566] __engine_park+0xb9/0x650 [i915] <4> [487.223973] ____intel_wakeref_put_last+0x2e/0xb0 [i915] <4> [487.224408] __intel_wakeref_put_last+0x72/0x90 [i915] <4> [487.224797] intel_context_exit_engine+0x7c/0x80 [i915] <4> [487.225238] intel_context_exit+0xf1/0x1b0 [i915] <4> [487.225695] i915_request_retire.part.0+0x1b9/0x530 [i915] <4> [487.226178] i915_request_retire+0x1c/0x40 [i915] <4> [487.226625] engine_retire+0x122/0x180 [i915] <4> [487.227037] process_one_work+0x239/0x760 <4> [487.227060] worker_thread+0x200/0x3f0 <4> [487.227068] ? __pfx_worker_thread+0x10/0x10 <4> [487.227075] kthread+0x10d/0x150 <4> [487.227083] ? __pfx_kthread+0x10/0x10 <4> [487.227092] ret_from_fork+0x3d4/0x480 <4> [487.227099] ? __pfx_kthread+0x10/0x10 <4> [487.227107] ret_from_fork_asm+0x1a/0x30 <4> [487.227141] </TASK> ``` Fix this by replacing the non-atomic pointer read + separate clear with xchg() in both racing paths. xchg() is a single indivisible hardware instruction that atomically reads the old pointer and writes NULL. This guarantees only one of the two concurrent callers obtains the non-NULL pointer and performs the put, the other gets NULL and skips it. (cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)
CVE-2026-31657: In the Linux kernel, the following vulnerability has been resolved: batman-adv: hold claim backbone gateways by reference batadv_bla_add_claim() can replace claim->backbone_gw and drop the old gateway's last reference while readers still follow the pointer. The netlink claim dump path dereferences claim->backbone_gw->orig and takes claim->backbone_gw->crc_lock without pinning the underlying backbone gateway. batadv_bla_check_claim() still has the same naked pointer access pattern. Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate on a stable gateway reference until the read-side work is complete. This keeps the dump and claim-check paths aligned with the lifetime rules introduced for the other BLA claim readers.
CVE-2026-31658: In the Linux kernel, the following vulnerability has been resolved: net: altera-tse: fix skb leak on DMA mapping error in tse_start_xmit() When dma_map_single() fails in tse_start_xmit(), the function returns NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the stack the packet was consumed, the skb is never freed, leaking memory on every DMA mapping failure. Add dev_kfree_skb_any() before returning to properly free the skb.
CVE-2026-31659: In the Linux kernel, the following vulnerability has been resolved: batman-adv: reject oversized global TT response buffers batadv_tt_prepare_tvlv_global_data() builds the allocation length for a global TT response in 16-bit temporaries. When a remote originator advertises a large enough global TT, the TT payload length plus the VLAN header offset can exceed 65535 and wrap before kmalloc(). The full-table response path still uses the original TT payload length when it fills tt_change, so the wrapped allocation is too small and batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object before the later packet-size check runs. Fix this by rejecting TT responses whose TVLV value length cannot fit in the 16-bit TVLV payload length field.
CVE-2026-31660: In the Linux kernel, the following vulnerability has been resolved: nfc: pn533: allocate rx skb before consuming bytes pn532_receive_buf() reports the number of accepted bytes to the serdev core. The current code consumes bytes into recv_skb and may already hand a complete frame to pn533_recv_frame() before allocating a fresh receive buffer. If that alloc_skb() fails, the callback returns 0 even though it has already consumed bytes, and it leaves recv_skb as NULL for the next receive callback. That breaks the receive_buf() accounting contract and can also lead to a NULL dereference on the next skb_put_u8(). Allocate the receive skb lazily before consuming the next byte instead. If allocation fails, return the number of bytes already accepted.
CVE-2026-31661: In the Linux kernel, the following vulnerability has been resolved: wifi: brcmsmac: Fix dma_free_coherent() size dma_alloc_consistent() may change the size to align it. The new size is saved in alloced. Change the free size to match the allocation size.
CVE-2026-31662: In the Linux kernel, the following vulnerability has been resolved: tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements bc_ackers on every inbound group ACK, even when the same member has already acknowledged the current broadcast round. Because bc_ackers is a u16, a duplicate ACK received after the last legitimate ACK wraps the counter to 65535. Once wrapped, tipc_group_bc_cong() keeps reporting congestion and later group broadcasts on the affected socket stay blocked until the group is recreated. Fix this by ignoring duplicate or stale ACKs before touching bc_acked or bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and prevents the underflow path.
CVE-2026-31663: In the Linux kernel, the following vulnerability has been resolved: xfrm: hold dev ref until after transport_finish NF_HOOK After async crypto completes, xfrm_input_resume() calls dev_put() immediately on re-entry before the skb reaches transport_finish. The skb->dev pointer is then used inside NF_HOOK and its okfn, which can race with device teardown. Remove the dev_put from the async resumption entry and instead drop the reference after the NF_HOOK call in transport_finish, using a saved device pointer since NF_HOOK may consume the skb. This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip the okfn. For non-transport exits (decaps, gro, drop) and secondary async return points, release the reference inline when async is set.
CVE-2026-31664: In the Linux kernel, the following vulnerability has been resolved: xfrm: clear trailing padding in build_polexpire() build_expire() clears the trailing padding bytes of struct xfrm_user_expire after setting the hard field via memset_after(), but the analogous function build_polexpire() does not do this for struct xfrm_user_polexpire. The padding bytes after the __u8 hard field are left uninitialized from the heap allocation, and are then sent to userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners, leaking kernel heap memory contents. Add the missing memset_after() call, matching build_expire().
CVE-2026-31665: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_ct: fix use-after-free in timeout object destroy nft_ct_timeout_obj_destroy() frees the timeout object with kfree() immediately after nf_ct_untimeout(), without waiting for an RCU grace period. Concurrent packet processing on other CPUs may still hold RCU-protected references to the timeout object obtained via rcu_dereference() in nf_ct_timeout_data(). Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer freeing until after an RCU grace period, matching the approach already used in nfnetlink_cttimeout.c. KASAN report: BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0 Read of size 4 at addr ffff8881035fe19c by task exploit/80 Call Trace: nf_conntrack_tcp_packet+0x1381/0x29d0 nf_conntrack_in+0x612/0x8b0 nf_hook_slow+0x70/0x100 __ip_local_out+0x1b2/0x210 tcp_sendmsg_locked+0x722/0x1580 __sys_sendto+0x2d8/0x320 Allocated by task 75: nft_ct_timeout_obj_init+0xf6/0x290 nft_obj_init+0x107/0x1b0 nf_tables_newobj+0x680/0x9c0 nfnetlink_rcv_batch+0xc29/0xe00 Freed by task 26: nft_obj_destroy+0x3f/0xa0 nf_tables_trans_destroy_work+0x51c/0x5c0 process_one_work+0x2c4/0x5a0
CVE-2026-31667: In the Linux kernel, the following vulnerability has been resolved: Input: uinput - fix circular locking dependency with ff-core A lockdep circular locking dependency warning can be triggered reproducibly when using a force-feedback gamepad with uinput (for example, playing ELDEN RING under Wine with a Flydigi Vader 5 controller): ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex The cycle is caused by four lock acquisition paths: 1. ff upload: input_ff_upload() holds ff->mutex and calls uinput_dev_upload_effect() -> uinput_request_submit() -> uinput_request_send(), which acquires udev->mutex. 2. device create: uinput_ioctl_handler() holds udev->mutex and calls uinput_create_device() -> input_register_device(), which acquires input_mutex. 3. device register: input_register_device() holds input_mutex and calls kbd_connect() -> input_register_handle(), which acquires dev->mutex. 4. evdev release: evdev_release() calls input_flush_device() under dev->mutex, which calls input_ff_flush() acquiring ff->mutex. Fix this by introducing a new state_lock spinlock to protect udev->state and udev->dev access in uinput_request_send() instead of acquiring udev->mutex. The function only needs to atomically check device state and queue an input event into the ring buffer via uinput_dev_event() -- both operations are safe under a spinlock (ktime_get_ts64() and wake_up_interruptible() do not sleep). This breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in the lock ordering and cannot form cycles with mutexes. To keep state transitions visible to uinput_request_send(), protect writes to udev->state in uinput_create_device() and uinput_destroy_device() with the same state_lock spinlock. Additionally, move init_completion(&request->done) from uinput_request_send() to uinput_request_submit() before uinput_request_reserve_slot(). Once the slot is allocated, uinput_flush_requests() may call complete() on it at any time from the destroy path, so the completion must be initialised before the request becomes visible. Lock ordering after the fix: ff->mutex -> state_lock (spinlock, leaf) udev->mutex -> state_lock (spinlock, leaf) udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)
CVE-2026-31668: In the Linux kernel, the following vulnerability has been resolved: seg6: separate dst_cache for input and output paths in seg6 lwtunnel The seg6 lwtunnel uses a single dst_cache per encap route, shared between seg6_input_core() and seg6_output_core(). These two paths can perform the post-encap SID lookup in different routing contexts (e.g., ip rules matching on the ingress interface, or VRF table separation). Whichever path runs first populates the cache, and the other reuses it blindly, bypassing its own lookup. Fix this by splitting the cache into cache_input and cache_output, so each path maintains its own cached dst independently.
CVE-2026-31669: In the Linux kernel, the following vulnerability has been resolved: mptcp: fix slab-use-after-free in __inet_lookup_established The ehash table lookups are lockless and rely on SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability during RCU read-side critical sections. Both tcp_prot and tcpv6_prot have their slab caches created with this flag via proto_register(). However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into tcpv6_prot_override during inet_init() (fs_initcall, level 5), before inet6_init() (module_init/device_initcall, level 6) has called proto_register(&tcpv6_prot). At that point, tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab remains NULL permanently. This causes MPTCP v6 subflow child sockets to be allocated via kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so when these sockets are freed without SOCK_RCU_FREE (which is cleared for child sockets by design), the memory can be immediately reused. Concurrent ehash lookups under rcu_read_lock can then access freed memory, triggering a slab-use-after-free in __inet_lookup_established. Fix this by splitting the IPv6-specific initialization out of mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called from mptcp_proto_v6_init() before protocol registration. This ensures tcpv6_prot_override.slab correctly inherits the SLAB_TYPESAFE_BY_RCU slab cache.
CVE-2026-31670: In the Linux kernel, the following vulnerability has been resolved: net: rfkill: prevent unlimited numbers of rfkill events from being created Userspace can create an unlimited number of rfkill events if the system is so configured, while not consuming them from the rfkill file descriptor, causing a potential out of memory situation. Prevent this from bounding the number of pending rfkill events at a "large" number (i.e. 1000) to prevent abuses like this.
CVE-2026-31671: In the Linux kernel, the following vulnerability has been resolved: xfrm_user: fix info leak in build_report() struct xfrm_user_report is a __u8 proto field followed by a struct xfrm_selector which means there is three "empty" bytes of padding, but the padding is never zeroed before copying to userspace. Fix that up by zeroing the structure before setting individual member variables.
CVE-2026-31672: In the Linux kernel, the following vulnerability has been resolved: wifi: rt2x00usb: fix devres lifetime USB drivers bind to USB interfaces and any device managed resources should have their lifetime tied to the interface rather than parent USB device. This avoids issues like memory leaks when drivers are unbound without their devices being physically disconnected (e.g. on probe deferral or configuration changes). Fix the USB anchor lifetime so that it is released on driver unbind.
CVE-2026-31673: In the Linux kernel, the following vulnerability has been resolved: af_unix: read UNIX_DIAG_VFS data under unix_state_lock Exact UNIX diag lookups hold a reference to the socket, but not to u->path. Meanwhile, unix_release_sock() clears u->path under unix_state_lock() and drops the path reference after unlocking. Read the inode and device numbers for UNIX_DIAG_VFS while holding unix_state_lock(), then emit the netlink attribute after dropping the lock. This keeps the VFS data stable while the reply is being built.
CVE-2026-31674: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check() Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS. rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[]. Validate addrnr during rule installation so malformed rules are rejected before the match logic can use an out-of-range value.
CVE-2026-31675: In the Linux kernel, the following vulnerability has been resolved: net/sched: sch_netem: fix out-of-bounds access in packet corruption In netem_enqueue(), the packet corruption logic uses get_random_u32_below(skb_headlen(skb)) to select an index for modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0. Passing 0 to get_random_u32_below() takes the variable-ceil slow path which returns an unconstrained 32-bit random integer. Using this unconstrained value as an offset into skb->data results in an out-of-bounds memory access. Fix this by verifying skb_headlen(skb) is non-zero before attempting to corrupt the linear data area. Fully non-linear packets will silently bypass the corruption logic.
CVE-2026-31676: In the Linux kernel, the following vulnerability has been resolved: rxrpc: only handle RESPONSE during service challenge Only process RESPONSE packets while the service connection is still in RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before running response verification and security initialization, then use a local secured flag to decide whether to queue the secured-connection work after the state transition. This keeps duplicate or late RESPONSE packets from re-running the setup path and removes the unlocked post-transition state test.
CVE-2026-31677: In the Linux kernel, the following vulnerability has been resolved: crypto: af_alg - limit RX SG extraction by receive buffer budget Make af_alg_get_rsgl() limit each RX scatterlist extraction to the remaining receive buffer budget. af_alg_get_rsgl() currently uses af_alg_readable() only as a gate before extracting data into the RX scatterlist. Limit each extraction to the remaining af_alg_rcvbuf(sk) budget so that receive-side accounting matches the amount of data attached to the request. If skcipher cannot obtain enough RX space for at least one chunk while more data remains to be processed, reject the recvmsg call instead of rounding the request length down to zero.
CVE-2026-31678: In the Linux kernel, the following vulnerability has been resolved: openvswitch: defer tunnel netdev_put to RCU release ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already detached the device. Dropping the netdev reference in destroy can race with concurrent readers that still observe vport->dev. Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let vport_netdev_free() drop the reference from the RCU callback, matching the non-tunnel destroy path and avoiding additional synchronization under RTNL.
CVE-2026-31679: In the Linux kernel, the following vulnerability has been resolved: openvswitch: validate MPLS set/set_masked payload length validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for SET/SET_MASKED actions. In action handling, OVS expects fixed-size MPLS key data (struct ovs_key_mpls). Use the already normalized key_len (masked case included) and reject non-matching MPLS action key sizes. Reject invalid MPLS action payload lengths early.
CVE-2026-31680: In the Linux kernel, the following vulnerability has been resolved: net: ipv6: flowlabel: defer exclusive option free until RCU teardown `ip6fl_seq_show()` walks the global flowlabel hash under the seq-file RCU read-side lock and prints `fl->opt->opt_nflen` when an option block is present. Exclusive flowlabels currently free `fl->opt` as soon as `fl->users` drops to zero in `fl_release()`. However, the surrounding `struct ip6_flowlabel` remains visible in the global hash table until later garbage collection removes it and `fl_free_rcu()` finally tears it down. A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that early `kfree()` and dereference freed option state, triggering a crash in `ip6fl_seq_show()`. Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches the lifetime already required for the enclosing flowlabel while readers can still reach it under RCU.
CVE-2026-31681: In the Linux kernel, the following vulnerability has been resolved: netfilter: xt_multiport: validate range encoding in checkentry ports_match_v1() treats any non-zero pflags entry as the start of a port range and unconditionally consumes the next ports[] element as the range end. The checkentry path currently validates protocol, flags and count, but it does not validate the range encoding itself. As a result, malformed rules can mark the last slot as a range start or place two range starts back to back, leaving ports_match_v1() to step past the last valid ports[] element while interpreting the rule. Reject malformed multiport v1 rules in checkentry by validating that each range start has a following element and that the following element is not itself marked as another range start.
CVE-2026-31682: In the Linux kernel, the following vulnerability has been resolved: bridge: br_nd_send: linearize skb before parsing ND options br_nd_send() parses neighbour discovery options from ns->opt[] and assumes that these options are in the linear part of request. Its callers only guarantee that the ICMPv6 header and target address are available, so the option area can still be non-linear. Parsing ns->opt[] in that case can access data past the linear buffer. Linearize request before option parsing and derive ns from the linear network header.
CVE-2026-31683: In the Linux kernel, the following vulnerability has been resolved: batman-adv: avoid OGM aggregation when skb tailroom is insufficient When OGM aggregation state is toggled at runtime, an existing forwarded packet may have been allocated with only packet_len bytes, while a later packet can still be selected for aggregation. Appending in this case can hit skb_put overflow conditions. Reject aggregation when the target skb tailroom cannot accommodate the new packet. The caller then falls back to creating a new forward packet instead of appending.
CVE-2026-31684: In the Linux kernel, the following vulnerability has been resolved: net: sched: act_csum: validate nested VLAN headers tcf_csum_act() walks nested VLAN headers directly from skb->data when an skb still carries in-payload VLAN tags. The current code reads vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without first ensuring that the full VLAN header is present in the linear area. If only part of an inner VLAN header is linearized, accessing h_vlan_encapsulated_proto reads past the linear area, and the following skb_pull(VLAN_HLEN) may violate skb invariants. Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and pulling each nested VLAN header. If the header still is not fully available, drop the packet through the existing error path.
CVE-2026-31685: In the Linux kernel, the following vulnerability has been resolved: netfilter: ip6t_eui64: reject invalid MAC header for all packets `eui64_mt6()` derives a modified EUI-64 from the Ethernet source address and compares it with the low 64 bits of the IPv6 source address. The existing guard only rejects an invalid MAC header when `par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()` can still reach `eth_hdr(skb)` even when the MAC header is not valid. Fix this by removing the `par->fragoff != 0` condition so that packets with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.
CVE-2026-31788: In the Linux kernel, the following vulnerability has been resolved: xen/privcmd: restrict usage in unprivileged domU The Xen privcmd driver allows to issue arbitrary hypercalls from user space processes. This is normally no problem, as access is usually limited to root and the hypervisor will deny any hypercalls affecting other domains. In case the guest is booted using secure boot, however, the privcmd driver would be enabling a root user process to modify e.g. kernel memory contents, thus breaking the secure boot feature. The only known case where an unprivileged domU is really needing to use the privcmd driver is the case when it is acting as the device model for another guest. In this case all hypercalls issued via the privcmd driver will target that other guest. Fortunately the privcmd driver can already be locked down to allow only hypercalls targeting a specific domain, but this mode can be activated from user land only today. The target domain can be obtained from Xenstore, so when not running in dom0 restrict the privcmd driver to that target domain from the beginning, resolving the potential problem of breaking secure boot. This is XSA-482 --- V2: - defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich) - wait in open() if target domain isn't known yet - issue message in case no target domain found (Jan Beulich)

5 issues left for the package maintainer to handle:

CVE-2019-15213: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-16089: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: (postponed; to be fixed through a stable update) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: (needs triaging) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.

You can find information about how to handle these issues in the security team's documentation.

4 ignored issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2025-71188: In the Linux kernel, the following vulnerability has been resolved: dmaengine: lpc18xx-dmamux: fix device leak on route allocation Make sure to drop the reference taken when looking up the DMA mux platform device during route allocation. Note that holding a reference to a device does not prevent its driver data from going away so there is no point in keeping the reference.

Created: 2022-07-04 Last update: 2026-04-26 05:02

636 security issues in buster high

There are 636 open security issues in buster.

604 important issues:

CVE-2020-0347: In iptables, there is a possible out of bounds write due to an incorrect bounds check. This could lead to local escalation of privilege with System execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android-11Android ID: A-136658008
CVE-2021-3493: The overlayfs implementation in the linux kernel did not properly validate with respect to user namespaces the setting of file capabilities on files in an underlying file system. Due to the combination of unprivileged user namespaces along with a patch carried in the Ubuntu kernel to allow unprivileged overlay mounts, an attacker could use this to gain elevated privileges.
CVE-2021-3669: A flaw was found in the Linux kernel. Measuring usage of the shared memory does not scale with large shared memory segment counts which could lead to resource exhaustion and DoS.
CVE-2021-3759: A memory overflow vulnerability was found in the Linux kernel’s ipc functionality of the memcg subsystem, in the way a user calls the semget function multiple times, creating semaphores. This flaw allows a local user to starve the resources, causing a denial of service. The highest threat from this vulnerability is to system availability.
CVE-2021-3847: An unauthorized access to the execution of the setuid file with capabilities flaw in the Linux kernel OverlayFS subsystem was found in the way user copying a capable file from a nosuid mount into another mount. A local user could use this flaw to escalate their privileges on the system.
CVE-2021-3864: A flaw was found in the way the dumpable flag setting was handled when certain SUID binaries executed its descendants. The prerequisite is a SUID binary that sets real UID equal to effective UID, and real GID equal to effective GID. The descendant will then have a dumpable value set to 1. As a result, if the descendant process crashes and core_pattern is set to a relative value, its core dump is stored in the current directory with uid:gid permissions. An unprivileged local user with eligible root SUID binary could use this flaw to place core dumps into root-owned directories, potentially resulting in escalation of privileges.
CVE-2021-4037: A vulnerability was found in the fs/inode.c:inode_init_owner() function logic of the LInux kernel that allows local users to create files for the XFS file-system with an unintended group ownership and with group execution and SGID permission bits set, in a scenario where a directory is SGID and belongs to a certain group and is writable by a user who is not a member of this group. This can lead to excessive permissions granted in case when they should not. This vulnerability is similar to the previous CVE-2018-13405 and adds the missed fix for the XFS.
CVE-2022-1184: A use-after-free flaw was found in fs/ext4/namei.c:dx_insert_block() in the Linux kernel’s filesystem sub-component. This flaw allows a local attacker with a user privilege to cause a denial of service.
CVE-2022-1280: A use-after-free vulnerability was found in drm_lease_held in drivers/gpu/drm/drm_lease.c in the Linux kernel due to a race problem. This flaw allows a local user privilege attacker to cause a denial of service (DoS) or a kernel information leak.
CVE-2022-3061: Found Linux Kernel flaw in the i740 driver. The Userspace program could pass any values to the driver through ioctl() interface. The driver doesn't check the value of 'pixclock', so it may cause a divide by zero error.
CVE-2022-3108: An issue was discovered in the Linux kernel through 5.16-rc6. kfd_parse_subtype_iolink in drivers/gpu/drm/amd/amdkfd/kfd_crat.c lacks check of the return value of kmemdup().
CVE-2022-3115: An issue was discovered in the Linux kernel through 5.16-rc6. malidp_crtc_reset in drivers/gpu/drm/arm/malidp_crtc.c lacks check of the return value of kzalloc() and will cause the null pointer dereference.
CVE-2022-3169: A flaw was found in the Linux kernel. A denial of service flaw may occur if there is a consecutive request of the NVME_IOCTL_RESET and the NVME_IOCTL_SUBSYS_RESET through the device file of the driver, resulting in a PCIe link disconnect.
CVE-2022-3176: There exists a use-after-free in io_uring in the Linux kernel. Signalfd_poll() and binder_poll() use a waitqueue whose lifetime is the current task. It will send a POLLFREE notification to all waiters before the queue is freed. Unfortunately, the io_uring poll doesn't handle POLLFREE. This allows a use-after-free to occur if a signalfd or binder fd is polled with io_uring poll, and the waitqueue gets freed. We recommend upgrading past commit fc78b2fc21f10c4c9c4d5d659a685710ffa63659
CVE-2022-3303: A race condition flaw was found in the Linux kernel sound subsystem due to improper locking. It could lead to a NULL pointer dereference while handling the SNDCTL_DSP_SYNC ioctl. A privileged local user (root or member of the audio group) could use this flaw to crash the system, resulting in a denial of service condition
CVE-2022-3344: A flaw was found in the KVM's AMD nested virtualization (SVM). A malicious L1 guest could purposely fail to intercept the shutdown of a cooperative nested guest (L2), possibly leading to a page fault and kernel panic in the host (L0).
CVE-2022-3523: A vulnerability was found in Linux Kernel. It has been classified as problematic. Affected is an unknown function of the file mm/memory.c of the component Driver Handler. The manipulation leads to use after free. It is possible to launch the attack remotely. It is recommended to apply a patch to fix this issue. The identifier of this vulnerability is VDB-211020.
CVE-2022-3566: A vulnerability, which was classified as problematic, was found in Linux Kernel. This affects the function tcp_getsockopt/tcp_setsockopt of the component TCP Handler. The manipulation leads to race condition. It is recommended to apply a patch to fix this issue. The identifier VDB-211089 was assigned to this vulnerability.
CVE-2022-3567: A vulnerability has been found in Linux Kernel and classified as problematic. This vulnerability affects the function inet6_stream_ops/inet6_dgram_ops of the component IPv6 Handler. The manipulation leads to race condition. It is recommended to apply a patch to fix this issue. VDB-211090 is the identifier assigned to this vulnerability.
CVE-2022-3903: An incorrect read request flaw was found in the Infrared Transceiver USB driver in the Linux kernel. This issue occurs when a user attaches a malicious USB device. A local user could use this flaw to starve the resources, causing denial of service or potentially crashing the system.
CVE-2022-4129: A flaw was found in the Linux kernel's Layer 2 Tunneling Protocol (L2TP). A missing lock when clearing sk_user_data can lead to a race condition and NULL pointer dereference. A local user could use this flaw to potentially crash the system causing a denial of service.
CVE-2022-4269: A flaw was found in the Linux kernel Traffic Control (TC) subsystem. Using a specific networking configuration (redirecting egress packets to ingress using TC action "mirred") a local unprivileged user could trigger a CPU soft lockup (ABBA deadlock) when the transport protocol in use (TCP or SCTP) does a retransmission, resulting in a denial of service condition.
CVE-2022-4382: A use-after-free flaw caused by a race among the superblock operations in the gadgetfs Linux driver was found. It could be triggered by yanking out a device that is running the gadgetfs side.
CVE-2022-4543: A flaw named "EntryBleed" was found in the Linux Kernel Page Table Isolation (KPTI). This issue could allow a local attacker to leak KASLR base via prefetch side-channels based on TLB timing for Intel systems.
CVE-2023-0030: A use-after-free flaw was found in the Linux kernel’s nouveau driver in how a user triggers a memory overflow that causes the nvkm_vma_tail function to fail. This flaw allows a local user to crash or potentially escalate their privileges on the system.
CVE-2023-0160: A deadlock flaw was found in the Linux kernel’s BPF subsystem. This flaw allows a local user to potentially crash the system.
CVE-2023-0597: A flaw possibility of memory leak in the Linux kernel cpu_entry_area mapping of X86 CPU data to memory was found in the way user can guess location of exception stack(s) or other important data. A local user could use this flaw to get access to some important data with expected location in memory.
CVE-2023-1076: A flaw was found in the Linux Kernel. The tun/tap sockets have their socket UID hardcoded to 0 due to a type confusion in their initialization function. While it will be often correct, as tuntap devices require CAP_NET_ADMIN, it may not always be the case, e.g., a non-root user only having that capability. This would make tun/tap sockets being incorrectly treated in filtering/routing decisions, possibly bypassing network filters.
CVE-2023-1249: A use-after-free flaw was found in the Linux kernel’s core dump subsystem. This flaw allows a local user to crash the system. Only if patch 390031c94211 ("coredump: Use the vma snapshot in fill_files_note") not applied yet, then kernel could be affected.
CVE-2023-1582: A race problem was found in fs/proc/task_mmu.c in the memory management sub-component in the Linux kernel. This issue may allow a local attacker with user privilege to cause a denial of service.
CVE-2023-2124: An out-of-bounds memory access flaw was found in the Linux kernel’s XFS file system in how a user restores an XFS image after failure (with a dirty log journal). This flaw allows a local user to crash or potentially escalate their privileges on the system.
CVE-2023-2177: A null pointer dereference issue was found in the sctp network protocol in net/sctp/stream_sched.c in Linux Kernel. If stream_in allocation is failed, stream_out is freed which would further be accessed. A local user could use this flaw to crash the system or potentially cause a denial of service.
CVE-2023-3022: A flaw was found in the IPv6 module of the Linux kernel. The arg.result was not used consistently in fib6_rule_lookup, sometimes holding rt6_info and other times fib6_info. This was not accounted for in other parts of the code where rt6_info was expected unconditionally, potentially leading to a kernel panic in fib6_rule_suppress.
CVE-2023-3397: A race condition occurred between the functions lmLogClose and txEnd in JFS, in the Linux Kernel, executed in different threads. This flaw allows a local attacker with normal user privileges to crash the system or leak internal kernel information.
CVE-2023-3863: A use-after-free flaw was found in nfc_llcp_find_local in net/nfc/llcp_core.c in NFC in the Linux kernel. This flaw allows a local user with special privileges to impact a kernel information leak issue.
CVE-2023-4010: A flaw was found in the USB Host Controller Driver framework in the Linux kernel. The usb_giveback_urb function has a logic loophole in its implementation. Due to the inappropriate judgment condition of the goto statement, the function cannot return under the input of a specific malformed descriptor file, so it falls into an endless loop, resulting in a denial of service.
CVE-2023-4132: A use-after-free vulnerability was found in the siano smsusb module in the Linux kernel. The bug occurs during device initialization when the siano device is plugged in. This flaw allows a local user to crash the system, causing a denial of service condition.
CVE-2023-4133: A use-after-free vulnerability was found in the cxgb4 driver in the Linux kernel. The bug occurs when the cxgb4 device is detaching due to a possible rearming of the flower_stats_timer from the work queue. This flaw allows a local user to crash the system, causing a denial of service condition.
CVE-2023-4194: A flaw was found in the Linux kernel's TUN/TAP functionality. This issue could allow a local user to bypass network filters and gain unauthorized access to some resources. The original patches fixing CVE-2023-1076 are incorrect or incomplete. The problem is that the following upstream commits - a096ccca6e50 ("tun: tun_chr_open(): correctly initialize socket uid"), - 66b2c338adce ("tap: tap_open(): correctly initialize socket uid"), pass "inode->i_uid" to sock_init_data_uid() as the last parameter and that turns out to not be accurate.
CVE-2023-4569: A memory leak flaw was found in nft_set_catchall_flush in net/netfilter/nf_tables_api.c in the Linux Kernel. This issue may allow a local attacker to cause double-deactivations of catchall elements, which can result in a memory leak.
CVE-2023-6121: An out-of-bounds read vulnerability was found in the NVMe-oF/TCP subsystem in the Linux kernel. This issue may allow a remote attacker to send a crafted TCP packet, triggering a heap-based buffer overflow that results in kmalloc data being printed and potentially leaked to the kernel ring buffer (dmesg).
CVE-2023-6240: A Marvin vulnerability side-channel leakage was found in the RSA decryption operation in the Linux Kernel. This issue may allow a network attacker to decrypt ciphertexts or forge signatures, limiting the services that use that private key.
CVE-2023-6356: A flaw was found in the Linux kernel's NVMe driver. This issue may allow an unauthenticated malicious actor to send a set of crafted TCP packages when using NVMe over TCP, leading the NVMe driver to a NULL pointer dereference in the NVMe driver and causing kernel panic and a denial of service.
CVE-2023-6535: A flaw was found in the Linux kernel's NVMe driver. This issue may allow an unauthenticated malicious actor to send a set of crafted TCP packages when using NVMe over TCP, leading the NVMe driver to a NULL pointer dereference in the NVMe driver, causing kernel panic and a denial of service.
CVE-2023-6536: A flaw was found in the Linux kernel's NVMe driver. This issue may allow an unauthenticated malicious actor to send a set of crafted TCP packages when using NVMe over TCP, leading the NVMe driver to a NULL pointer dereference in the NVMe driver, causing kernel panic and a denial of service.
CVE-2023-6915: A Null pointer dereference problem was found in ida_free in lib/idr.c in the Linux Kernel. This issue may allow an attacker using this library to cause a denial of service problem due to a missing check at a function return.
CVE-2024-0564: A flaw was found in the Linux kernel's memory deduplication mechanism. The max page sharing of Kernel Samepage Merging (KSM), added in Linux kernel version 4.4.0-96.119, can create a side channel. When the attacker and the victim share the same host and the default setting of KSM is "max page sharing=256", it is possible for the attacker to time the unmap to merge with the victim's page. The unmapping time depends on whether it merges with the victim's page and additional physical pages are created beyond the KSM's "max page share". Through these operations, the attacker can leak the victim's page.
CVE-2024-0565: An out-of-bounds memory read flaw was found in receive_encrypted_standard in fs/smb/client/smb2ops.c in the SMB Client sub-component in the Linux Kernel. This issue occurs due to integer underflow on the memcpy length, leading to a denial of service.
CVE-2024-1151: A vulnerability was reported in the Open vSwitch sub-component in the Linux Kernel. The flaw occurs when a recursive operation of code push recursively calls into the code block. The OVS module does not validate the stack depth, pushing too many frames and causing a stack overflow. As a result, this can lead to a crash or other related issues.
CVE-2024-2193: A Speculative Race Condition (SRC) vulnerability that impacts modern CPU architectures supporting speculative execution (related to Spectre V1) has been disclosed. An unauthenticated attacker can exploit this vulnerability to disclose arbitrary data from the CPU using race conditions to access the speculative executable code paths.
CVE-2024-2201:
CVE-2019-15213: An issue was discovered in the Linux kernel before 5.2.3. There is a use-after-free caused by a malicious USB device in the drivers/media/usb/dvb-usb/dvb-usb-init.c driver.
CVE-2019-15794: Overlayfs in the Linux kernel and shiftfs, a non-upstream patch to the Linux kernel included in the Ubuntu 5.0 and 5.3 kernel series, both replace vma->vm_file in their mmap handlers. On error the original value is not restored, and the reference is put for the file to which vm_file points. On upstream kernels this is not an issue, as no callers dereference vm_file following after call_mmap() returns an error. However, the aufs patchs change mmap_region() to replace the fput() using a local variable with vma_fput(), which will fput() vm_file, leading to a refcount underflow.
CVE-2020-16120: Overlayfs did not properly perform permission checking when copying up files in an overlayfs and could be exploited from within a user namespace, if, for example, unprivileged user namespaces were allowed. It was possible to have a file not readable by an unprivileged user to be copied to a mountpoint controlled by the user, like a removable device. This was introduced in kernel version 4.19 by commit d1d04ef ("ovl: stack file ops"). This was fixed in kernel version 5.8 by commits 56230d9 ("ovl: verify permissions in ovl_path_open()"), 48bd024 ("ovl: switch to mounter creds in readdir") and 05acefb ("ovl: check permission to open real file"). Additionally, commits 130fdbc ("ovl: pass correct flags for opening real directory") and 292f902 ("ovl: call secutiry hook in ovl_real_ioctl()") in kernel 5.8 might also be desired or necessary. These additional commits introduced a regression in overlay mounts within user namespaces which prevented access to files with ownership outside of the user namespace. This regression was mitigated by subsequent commit b6650da ("ovl: do not fail because of O_NOATIMEi") in kernel 5.11.
CVE-2020-26141: An issue was discovered in the ALFA Windows 10 driver 6.1316.1209 for AWUS036H. The Wi-Fi implementation does not verify the Message Integrity Check (authenticity) of fragmented TKIP frames. An adversary can abuse this to inject and possibly decrypt packets in WPA or WPA2 networks that support the TKIP data-confidentiality protocol.
CVE-2020-26145: An issue was discovered on Samsung Galaxy S3 i9305 4.4.4 devices. The WEP, WPA, WPA2, and WPA3 implementations accept second (or subsequent) broadcast fragments even when sent in plaintext and process them as full unfragmented frames. An adversary can abuse this to inject arbitrary network packets independent of the network configuration.
CVE-2020-26541: The Linux kernel through 5.8.13 does not properly enforce the Secure Boot Forbidden Signature Database (aka dbx) protection mechanism. This affects certs/blacklist.c and certs/system_keyring.c.
CVE-2020-27835: A use after free in the Linux kernel infiniband hfi1 driver in versions prior to 5.10-rc6 was found in the way user calls Ioctl after open dev file and fork. A local user could use this flaw to crash the system.
CVE-2020-36310: An issue was discovered in the Linux kernel before 5.8. arch/x86/kvm/svm/svm.c allows a set_memory_region_test infinite loop for certain nested page faults, aka CID-e72436bc3a52.
CVE-2020-36385: An issue was discovered in the Linux kernel before 5.10. drivers/infiniband/core/ucma.c has a use-after-free because the ctx is reached via the ctx_list in some ucma_migrate_id situations where ucma_close is called, aka CID-f5449e74802c.
CVE-2020-36691: An issue was discovered in the Linux kernel before 5.8. lib/nlattr.c allows attackers to cause a denial of service (unbounded recursion) via a nested Netlink policy with a back reference.
CVE-2020-36694: An issue was discovered in netfilter in the Linux kernel before 5.10. There can be a use-after-free in the packet processing context, because the per-CPU sequence count is mishandled during concurrent iptables rules replacement. This could be exploited with the CAP_NET_ADMIN capability in an unprivileged namespace. NOTE: cc00bca was reverted in 5.12.
CVE-2020-36775: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid potential deadlock Using f2fs_trylock_op() in f2fs_write_compressed_pages() to avoid potential deadlock like we did in f2fs_write_single_data_page().
CVE-2020-36776: In the Linux kernel, the following vulnerability has been resolved: thermal/drivers/cpufreq_cooling: Fix slab OOB issue Slab OOB issue is scanned by KASAN in cpu_power_to_freq(). If power is limited below the power of OPP0 in EM table, it will cause slab out-of-bound issue with negative array index. Return the lowest frequency if limited power cannot found a suitable OPP in EM table to fix this issue. Backtrace: [<ffffffd02d2a37f0>] die+0x104/0x5ac [<ffffffd02d2a5630>] bug_handler+0x64/0xd0 [<ffffffd02d288ce4>] brk_handler+0x160/0x258 [<ffffffd02d281e5c>] do_debug_exception+0x248/0x3f0 [<ffffffd02d284488>] el1_dbg+0x14/0xbc [<ffffffd02d75d1d4>] __kasan_report+0x1dc/0x1e0 [<ffffffd02d75c2e0>] kasan_report+0x10/0x20 [<ffffffd02d75def8>] __asan_report_load8_noabort+0x18/0x28 [<ffffffd02e6fce5c>] cpufreq_power2state+0x180/0x43c [<ffffffd02e6ead80>] power_actor_set_power+0x114/0x1d4 [<ffffffd02e6fac24>] allocate_power+0xaec/0xde0 [<ffffffd02e6f9f80>] power_allocator_throttle+0x3ec/0x5a4 [<ffffffd02e6ea888>] handle_thermal_trip+0x160/0x294 [<ffffffd02e6edd08>] thermal_zone_device_check+0xe4/0x154 [<ffffffd02d351cb4>] process_one_work+0x5e4/0xe28 [<ffffffd02d352f44>] worker_thread+0xa4c/0xfac [<ffffffd02d360124>] kthread+0x33c/0x358 [<ffffffd02d289940>] ret_from_fork+0xc/0x18
CVE-2020-36780: In the Linux kernel, the following vulnerability has been resolved: i2c: sprd: fix reference leak when pm_runtime_get_sync fails The PM reference count is not expected to be incremented on return in sprd_i2c_master_xfer() and sprd_i2c_remove(). However, pm_runtime_get_sync will increment the PM reference count even failed. Forgetting to putting operation will result in a reference leak here. Replace it with pm_runtime_resume_and_get to keep usage counter balanced.
CVE-2020-36782: In the Linux kernel, the following vulnerability has been resolved: i2c: imx-lpi2c: fix reference leak when pm_runtime_get_sync fails The PM reference count is not expected to be incremented on return in lpi2c_imx_master_enable. However, pm_runtime_get_sync will increment the PM reference count even failed. Forgetting to putting operation will result in a reference leak here. Replace it with pm_runtime_resume_and_get to keep usage counter balanced.
CVE-2020-36783: In the Linux kernel, the following vulnerability has been resolved: i2c: img-scb: fix reference leak when pm_runtime_get_sync fails The PM reference count is not expected to be incremented on return in functions img_i2c_xfer and img_i2c_init. However, pm_runtime_get_sync will increment the PM reference count even failed. Forgetting to putting operation will result in a reference leak here. Replace it with pm_runtime_resume_and_get to keep usage counter balanced.
CVE-2020-36784: In the Linux kernel, the following vulnerability has been resolved: i2c: cadence: fix reference leak when pm_runtime_get_sync fails The PM reference count is not expected to be incremented on return in functions cdns_i2c_master_xfer and cdns_reg_slave. However, pm_runtime_get_sync will increment pm usage counter even failed. Forgetting to putting operation will result in a reference leak here. Replace it with pm_runtime_resume_and_get to keep usage counter balanced.
CVE-2021-33061: Insufficient control flow management for the Intel(R) 82599 Ethernet Controllers and Adapters may allow an authenticated user to potentially enable denial of service via local access.
CVE-2021-46925: In the Linux kernel, the following vulnerability has been resolved: net/smc: fix kernel panic caused by race of smc_sock A crash occurs when smc_cdc_tx_handler() tries to access smc_sock but smc_release() has already freed it. [ 4570.695099] BUG: unable to handle page fault for address: 000000002eae9e88 [ 4570.696048] #PF: supervisor write access in kernel mode [ 4570.696728] #PF: error_code(0x0002) - not-present page [ 4570.697401] PGD 0 P4D 0 [ 4570.697716] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 4570.698228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-rc4+ #111 [ 4570.699013] Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 8c24b4c 04/0 [ 4570.699933] RIP: 0010:_raw_spin_lock+0x1a/0x30 <...> [ 4570.711446] Call Trace: [ 4570.711746] <IRQ> [ 4570.711992] smc_cdc_tx_handler+0x41/0xc0 [ 4570.712470] smc_wr_tx_tasklet_fn+0x213/0x560 [ 4570.712981] ? smc_cdc_tx_dismisser+0x10/0x10 [ 4570.713489] tasklet_action_common.isra.17+0x66/0x140 [ 4570.714083] __do_softirq+0x123/0x2f4 [ 4570.714521] irq_exit_rcu+0xc4/0xf0 [ 4570.714934] common_interrupt+0xba/0xe0 Though smc_cdc_tx_handler() checked the existence of smc connection, smc_release() may have already dismissed and released the smc socket before smc_cdc_tx_handler() further visits it. smc_cdc_tx_handler() |smc_release() if (!conn) | | |smc_cdc_tx_dismiss_slots() | smc_cdc_tx_dismisser() | |sock_put(&smc->sk) <- last sock_put, | smc_sock freed bh_lock_sock(&smc->sk) (panic) | To make sure we won't receive any CDC messages after we free the smc_sock, add a refcount on the smc_connection for inflight CDC message(posted to the QP but haven't received related CQE), and don't release the smc_connection until all the inflight CDC messages haven been done, for both success or failed ones. Using refcount on CDC messages brings another problem: when the link is going to be destroyed, smcr_link_clear() will reset the QP, which then remove all the pending CQEs related to the QP in the CQ. To make sure all the CQEs will always come back so the refcount on the smc_connection can always reach 0, smc_ib_modify_qp_reset() was replaced by smc_ib_modify_qp_error(). And remove the timeout in smc_wr_tx_wait_no_pending_sends() since we need to wait for all pending WQEs done, or we may encounter use-after- free when handling CQEs. For IB device removal routine, we need to wait for all the QPs on that device been destroyed before we can destroy CQs on the device, or the refcount on smc_connection won't reach 0 and smc_sock cannot be released.
CVE-2021-46926: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: intel-sdw-acpi: harden detection of controller The existing code currently sets a pointer to an ACPI handle before checking that it's actually a SoundWire controller. This can lead to issues where the graph walk continues and eventually fails, but the pointer was set already. This patch changes the logic so that the information provided to the caller is set when a controller is found.
CVE-2021-46928: In the Linux kernel, the following vulnerability has been resolved: parisc: Clear stale IIR value on instruction access rights trap When a trap 7 (Instruction access rights) occurs, this means the CPU couldn't execute an instruction due to missing execute permissions on the memory region. In this case it seems the CPU didn't even fetched the instruction from memory and thus did not store it in the cr19 (IIR) register before calling the trap handler. So, the trap handler will find some random old stale value in cr19. This patch simply overwrites the stale IIR value with a constant magic "bad food" value (0xbaadf00d), in the hope people don't start to try to understand the various random IIR values in trap 7 dumps.
CVE-2021-46941: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: core: Do core softreset when switch mode According to the programming guide, to switch mode for DRD controller, the driver needs to do the following. To switch from device to host: 1. Reset controller with GCTL.CoreSoftReset 2. Set GCTL.PrtCapDir(host mode) 3. Reset the host with USBCMD.HCRESET 4. Then follow up with the initializing host registers sequence To switch from host to device: 1. Reset controller with GCTL.CoreSoftReset 2. Set GCTL.PrtCapDir(device mode) 3. Reset the device with DCTL.CSftRst 4. Then follow up with the initializing registers sequence Currently we're missing step 1) to do GCTL.CoreSoftReset and step 3) of switching from host to device. John Stult reported a lockup issue seen with HiKey960 platform without these steps[1]. Similar issue is observed with Ferry's testing platform[2]. So, apply the required steps along with some fixes to Yu Chen's and John Stultz's version. The main fixes to their versions are the missing wait for clocks synchronization before clearing GCTL.CoreSoftReset and only apply DCTL.CSftRst when switching from host to device. [1] https://lore.kernel.org/linux-usb/20210108015115.27920-1-john.stultz@linaro.org/ [2] https://lore.kernel.org/linux-usb/0ba7a6ba-e6a7-9cd4-0695-64fc927e01f1@gmail.com/
CVE-2021-46981: In the Linux kernel, the following vulnerability has been resolved: nbd: Fix NULL pointer in flush_workqueue Open /dev/nbdX first, the config_refs will be 1 and the pointers in nbd_device are still null. Disconnect /dev/nbdX, then reference a null recv_workq. The protection by config_refs in nbd_genl_disconnect is useless. [ 656.366194] BUG: kernel NULL pointer dereference, address: 0000000000000020 [ 656.368943] #PF: supervisor write access in kernel mode [ 656.369844] #PF: error_code(0x0002) - not-present page [ 656.370717] PGD 10cc87067 P4D 10cc87067 PUD 1074b4067 PMD 0 [ 656.371693] Oops: 0002 [#1] SMP [ 656.372242] CPU: 5 PID: 7977 Comm: nbd-client Not tainted 5.11.0-rc5-00040-g76c057c84d28 #1 [ 656.373661] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 [ 656.375904] RIP: 0010:mutex_lock+0x29/0x60 [ 656.376627] Code: 00 0f 1f 44 00 00 55 48 89 fd 48 83 05 6f d7 fe 08 01 e8 7a c3 ff ff 48 83 05 6a d7 fe 08 01 31 c0 65 48 8b 14 25 00 6d 01 00 <f0> 48 0f b1 55 d [ 656.378934] RSP: 0018:ffffc900005eb9b0 EFLAGS: 00010246 [ 656.379350] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 656.379915] RDX: ffff888104cf2600 RSI: ffffffffaae8f452 RDI: 0000000000000020 [ 656.380473] RBP: 0000000000000020 R08: 0000000000000000 R09: ffff88813bd6b318 [ 656.381039] R10: 00000000000000c7 R11: fefefefefefefeff R12: ffff888102710b40 [ 656.381599] R13: ffffc900005eb9e0 R14: ffffffffb2930680 R15: ffff88810770ef00 [ 656.382166] FS: 00007fdf117ebb40(0000) GS:ffff88813bd40000(0000) knlGS:0000000000000000 [ 656.382806] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 656.383261] CR2: 0000000000000020 CR3: 0000000100c84000 CR4: 00000000000006e0 [ 656.383819] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 656.384370] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 656.384927] Call Trace: [ 656.385111] flush_workqueue+0x92/0x6c0 [ 656.385395] nbd_disconnect_and_put+0x81/0xd0 [ 656.385716] nbd_genl_disconnect+0x125/0x2a0 [ 656.386034] genl_family_rcv_msg_doit.isra.0+0x102/0x1b0 [ 656.386422] genl_rcv_msg+0xfc/0x2b0 [ 656.386685] ? nbd_ioctl+0x490/0x490 [ 656.386954] ? genl_family_rcv_msg_doit.isra.0+0x1b0/0x1b0 [ 656.387354] netlink_rcv_skb+0x62/0x180 [ 656.387638] genl_rcv+0x34/0x60 [ 656.387874] netlink_unicast+0x26d/0x590 [ 656.388162] netlink_sendmsg+0x398/0x6c0 [ 656.388451] ? netlink_rcv_skb+0x180/0x180 [ 656.388750] ____sys_sendmsg+0x1da/0x320 [ 656.389038] ? ____sys_recvmsg+0x130/0x220 [ 656.389334] ___sys_sendmsg+0x8e/0xf0 [ 656.389605] ? ___sys_recvmsg+0xa2/0xf0 [ 656.389889] ? handle_mm_fault+0x1671/0x21d0 [ 656.390201] __sys_sendmsg+0x6d/0xe0 [ 656.390464] __x64_sys_sendmsg+0x23/0x30 [ 656.390751] do_syscall_64+0x45/0x70 [ 656.391017] entry_SYSCALL_64_after_hwframe+0x44/0xa9 To fix it, just add if (nbd->recv_workq) to nbd_disconnect_and_put().
CVE-2021-46984: In the Linux kernel, the following vulnerability has been resolved: kyber: fix out of bounds access when preempted __blk_mq_sched_bio_merge() gets the ctx and hctx for the current CPU and passes the hctx to ->bio_merge(). kyber_bio_merge() then gets the ctx for the current CPU again and uses that to get the corresponding Kyber context in the passed hctx. However, the thread may be preempted between the two calls to blk_mq_get_ctx(), and the ctx returned the second time may no longer correspond to the passed hctx. This "works" accidentally most of the time, but it can cause us to read garbage if the second ctx came from an hctx with more ctx's than the first one (i.e., if ctx->index_hw[hctx->type] > hctx->nr_ctx). This manifested as this UBSAN array index out of bounds error reported by Jakub: UBSAN: array-index-out-of-bounds in ../kernel/locking/qspinlock.c:130:9 index 13106 is out of range for type 'long unsigned int [128]' Call Trace: dump_stack+0xa4/0xe5 ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds.cold.13+0x2a/0x34 queued_spin_lock_slowpath+0x476/0x480 do_raw_spin_lock+0x1c2/0x1d0 kyber_bio_merge+0x112/0x180 blk_mq_submit_bio+0x1f5/0x1100 submit_bio_noacct+0x7b0/0x870 submit_bio+0xc2/0x3a0 btrfs_map_bio+0x4f0/0x9d0 btrfs_submit_data_bio+0x24e/0x310 submit_one_bio+0x7f/0xb0 submit_extent_page+0xc4/0x440 __extent_writepage_io+0x2b8/0x5e0 __extent_writepage+0x28d/0x6e0 extent_write_cache_pages+0x4d7/0x7a0 extent_writepages+0xa2/0x110 do_writepages+0x8f/0x180 __writeback_single_inode+0x99/0x7f0 writeback_sb_inodes+0x34e/0x790 __writeback_inodes_wb+0x9e/0x120 wb_writeback+0x4d2/0x660 wb_workfn+0x64d/0xa10 process_one_work+0x53a/0xa80 worker_thread+0x69/0x5b0 kthread+0x20b/0x240 ret_from_fork+0x1f/0x30 Only Kyber uses the hctx, so fix it by passing the request_queue to ->bio_merge() instead. BFQ and mq-deadline just use that, and Kyber can map the queues itself to avoid the mismatch.
CVE-2021-47015: In the Linux kernel, the following vulnerability has been resolved: bnxt_en: Fix RX consumer index logic in the error path. In bnxt_rx_pkt(), the RX buffers are expected to complete in order. If the RX consumer index indicates an out of order buffer completion, it means we are hitting a hardware bug and the driver will abort all remaining RX packets and reset the RX ring. The RX consumer index that we pass to bnxt_discard_rx() is not correct. We should be passing the current index (tmp_raw_cons) instead of the old index (raw_cons). This bug can cause us to be at the wrong index when trying to abort the next RX packet. It can crash like this: #0 [ffff9bbcdf5c39a8] machine_kexec at ffffffff9b05e007 #1 [ffff9bbcdf5c3a00] __crash_kexec at ffffffff9b111232 #2 [ffff9bbcdf5c3ad0] panic at ffffffff9b07d61e #3 [ffff9bbcdf5c3b50] oops_end at ffffffff9b030978 #4 [ffff9bbcdf5c3b78] no_context at ffffffff9b06aaf0 #5 [ffff9bbcdf5c3bd8] __bad_area_nosemaphore at ffffffff9b06ae2e #6 [ffff9bbcdf5c3c28] bad_area_nosemaphore at ffffffff9b06af24 #7 [ffff9bbcdf5c3c38] __do_page_fault at ffffffff9b06b67e #8 [ffff9bbcdf5c3cb0] do_page_fault at ffffffff9b06bb12 #9 [ffff9bbcdf5c3ce0] page_fault at ffffffff9bc015c5 [exception RIP: bnxt_rx_pkt+237] RIP: ffffffffc0259cdd RSP: ffff9bbcdf5c3d98 RFLAGS: 00010213 RAX: 000000005dd8097f RBX: ffff9ba4cb11b7e0 RCX: ffffa923cf6e9000 RDX: 0000000000000fff RSI: 0000000000000627 RDI: 0000000000001000 RBP: ffff9bbcdf5c3e60 R8: 0000000000420003 R9: 000000000000020d R10: ffffa923cf6ec138 R11: ffff9bbcdf5c3e83 R12: ffff9ba4d6f928c0 R13: ffff9ba4cac28080 R14: ffff9ba4cb11b7f0 R15: ffff9ba4d5a30000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
CVE-2021-47024: In the Linux kernel, the following vulnerability has been resolved: vsock/virtio: free queued packets when closing socket As reported by syzbot [1], there is a memory leak while closing the socket. We partially solved this issue with commit ac03046ece2b ("vsock/virtio: free packets during the socket release"), but we forgot to drain the RX queue when the socket is definitely closed by the scheduled work. To avoid future issues, let's use the new virtio_transport_remove_sock() to drain the RX queue before removing the socket from the af_vsock lists calling vsock_remove_sock(). [1] https://syzkaller.appspot.com/bug?extid=24452624fc4c571eedd9
CVE-2021-47049: In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Use after free in __vmbus_open() The "open_info" variable is added to the &vmbus_connection.chn_msg_list, but the error handling frees "open_info" without removing it from the list. This will result in a use after free. First remove it from the list, and then free it.
CVE-2021-47060: In the Linux kernel, the following vulnerability has been resolved: KVM: Stop looking for coalesced MMIO zones if the bus is destroyed Abort the walk of coalesced MMIO zones if kvm_io_bus_unregister_dev() fails to allocate memory for the new instance of the bus. If it can't instantiate a new bus, unregister_dev() destroys all devices _except_ the target device. But, it doesn't tell the caller that it obliterated the bus and invoked the destructor for all devices that were on the bus. In the coalesced MMIO case, this can result in a deleted list entry dereference due to attempting to continue iterating on coalesced_zones after future entries (in the walk) have been deleted. Opportunistically add curly braces to the for-loop, which encompasses many lines but sneaks by without braces due to the guts being a single if statement.
CVE-2021-47061: In the Linux kernel, the following vulnerability has been resolved: KVM: Destroy I/O bus devices on unregister failure _after_ sync'ing SRCU If allocating a new instance of an I/O bus fails when unregistering a device, wait to destroy the device until after all readers are guaranteed to see the new null bus. Destroying devices before the bus is nullified could lead to use-after-free since readers expect the devices on their reference of the bus to remain valid.
CVE-2021-47063: In the Linux kernel, the following vulnerability has been resolved: drm: bridge/panel: Cleanup connector on bridge detach If we don't call drm_connector_cleanup() manually in panel_bridge_detach(), the connector will be cleaned up with the other DRM objects in the call to drm_mode_config_cleanup(). However, since our drm_connector is devm-allocated, by the time drm_mode_config_cleanup() will be called, our connector will be long gone. Therefore, the connector must be cleaned up when the bridge is detached to avoid use-after-free conditions. v2: Cleanup connector only if it was created v3: Add FIXME v4: (Use connector->dev) directly in if() block
CVE-2021-47074: In the Linux kernel, the following vulnerability has been resolved: nvme-loop: fix memory leak in nvme_loop_create_ctrl() When creating loop ctrl in nvme_loop_create_ctrl(), if nvme_init_ctrl() fails, the loop ctrl should be freed before jumping to the "out" label.
CVE-2021-47076: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Return CQE error if invalid lkey was supplied RXE is missing update of WQE status in LOCAL_WRITE failures. This caused the following kernel panic if someone sent an atomic operation with an explicitly wrong lkey. [leonro@vm ~]$ mkt test test_atomic_invalid_lkey (tests.test_atomic.AtomicTest) ... WARNING: CPU: 5 PID: 263 at drivers/infiniband/sw/rxe/rxe_comp.c:740 rxe_completer+0x1a6d/0x2e30 [rdma_rxe] Modules linked in: crc32_generic rdma_rxe ip6_udp_tunnel udp_tunnel rdma_ucm rdma_cm ib_umad ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core mlx5_core ptp pps_core CPU: 5 PID: 263 Comm: python3 Not tainted 5.13.0-rc1+ #2936 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:rxe_completer+0x1a6d/0x2e30 [rdma_rxe] Code: 03 0f 8e 65 0e 00 00 3b 93 10 06 00 00 0f 84 82 0a 00 00 4c 89 ff 4c 89 44 24 38 e8 2d 74 a9 e1 4c 8b 44 24 38 e9 1c f5 ff ff <0f> 0b e9 0c e8 ff ff b8 05 00 00 00 41 bf 05 00 00 00 e9 ab e7 ff RSP: 0018:ffff8880158af090 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888016a78000 RCX: ffffffffa0cf1652 RDX: 1ffff9200004b442 RSI: 0000000000000004 RDI: ffffc9000025a210 RBP: dffffc0000000000 R08: 00000000ffffffea R09: ffff88801617740b R10: ffffed1002c2ee81 R11: 0000000000000007 R12: ffff88800f3b63e8 R13: ffff888016a78008 R14: ffffc9000025a180 R15: 000000000000000c FS: 00007f88b622a740(0000) GS:ffff88806d540000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f88b5a1fa10 CR3: 000000000d848004 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: rxe_do_task+0x130/0x230 [rdma_rxe] rxe_rcv+0xb11/0x1df0 [rdma_rxe] rxe_loopback+0x157/0x1e0 [rdma_rxe] rxe_responder+0x5532/0x7620 [rdma_rxe] rxe_do_task+0x130/0x230 [rdma_rxe] rxe_rcv+0x9c8/0x1df0 [rdma_rxe] rxe_loopback+0x157/0x1e0 [rdma_rxe] rxe_requester+0x1efd/0x58c0 [rdma_rxe] rxe_do_task+0x130/0x230 [rdma_rxe] rxe_post_send+0x998/0x1860 [rdma_rxe] ib_uverbs_post_send+0xd5f/0x1220 [ib_uverbs] ib_uverbs_write+0x847/0xc80 [ib_uverbs] vfs_write+0x1c5/0x840 ksys_write+0x176/0x1d0 do_syscall_64+0x3f/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2021-47077: In the Linux kernel, the following vulnerability has been resolved: scsi: qedf: Add pointer checks in qedf_update_link_speed() The following trace was observed: [ 14.042059] Call Trace: [ 14.042061] <IRQ> [ 14.042068] qedf_link_update+0x144/0x1f0 [qedf] [ 14.042117] qed_link_update+0x5c/0x80 [qed] [ 14.042135] qed_mcp_handle_link_change+0x2d2/0x410 [qed] [ 14.042155] ? qed_set_ptt+0x70/0x80 [qed] [ 14.042170] ? qed_set_ptt+0x70/0x80 [qed] [ 14.042186] ? qed_rd+0x13/0x40 [qed] [ 14.042205] qed_mcp_handle_events+0x437/0x690 [qed] [ 14.042221] ? qed_set_ptt+0x70/0x80 [qed] [ 14.042239] qed_int_sp_dpc+0x3a6/0x3e0 [qed] [ 14.042245] tasklet_action_common.isra.14+0x5a/0x100 [ 14.042250] __do_softirq+0xe4/0x2f8 [ 14.042253] irq_exit+0xf7/0x100 [ 14.042255] do_IRQ+0x7f/0xd0 [ 14.042257] common_interrupt+0xf/0xf [ 14.042259] </IRQ> API qedf_link_update() is getting called from QED but by that time shost_data is not initialised. This results in a NULL pointer dereference when we try to dereference shost_data while updating supported_speeds. Add a NULL pointer check before dereferencing shost_data.
CVE-2021-47083: In the Linux kernel, the following vulnerability has been resolved: pinctrl: mediatek: fix global-out-of-bounds issue When eint virtual eint number is greater than gpio number, it maybe produce 'desc[eint_n]' size globle-out-of-bounds issue.
CVE-2021-47101: In the Linux kernel, the following vulnerability has been resolved: asix: fix uninit-value in asix_mdio_read() asix_read_cmd() may read less than sizeof(smsr) bytes and in this case smsr will be uninitialized. Fail log: BUG: KMSAN: uninit-value in asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] BUG: KMSAN: uninit-value in asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] drivers/net/usb/asix_common.c:497 BUG: KMSAN: uninit-value in asix_mdio_read+0x3c1/0xb00 drivers/net/usb/asix_common.c:497 drivers/net/usb/asix_common.c:497 asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] asix_check_host_enable drivers/net/usb/asix_common.c:82 [inline] drivers/net/usb/asix_common.c:497 asix_mdio_read+0x3c1/0xb00 drivers/net/usb/asix_common.c:497 drivers/net/usb/asix_common.c:497
CVE-2021-47110: In the Linux kernel, the following vulnerability has been resolved: x86/kvm: Disable kvmclock on all CPUs on shutdown Currenly, we disable kvmclock from machine_shutdown() hook and this only happens for boot CPU. We need to disable it for all CPUs to guard against memory corruption e.g. on restore from hibernate. Note, writing '0' to kvmclock MSR doesn't clear memory location, it just prevents hypervisor from updating the location so for the short while after write and while CPU is still alive, the clock remains usable and correct so we don't need to switch to some other clocksource.
CVE-2021-47112: In the Linux kernel, the following vulnerability has been resolved: x86/kvm: Teardown PV features on boot CPU as well Various PV features (Async PF, PV EOI, steal time) work through memory shared with hypervisor and when we restore from hibernation we must properly teardown all these features to make sure hypervisor doesn't write to stale locations after we jump to the previously hibernated kernel (which can try to place anything there). For secondary CPUs the job is already done by kvm_cpu_down_prepare(), register syscore ops to do the same for boot CPU.
CVE-2021-47113: In the Linux kernel, the following vulnerability has been resolved: btrfs: abort in rename_exchange if we fail to insert the second ref Error injection stress uncovered a problem where we'd leave a dangling inode ref if we failed during a rename_exchange. This happens because we insert the inode ref for one side of the rename, and then for the other side. If this second inode ref insert fails we'll leave the first one dangling and leave a corrupt file system behind. Fix this by aborting if we did the insert for the first inode ref.
CVE-2021-47116: In the Linux kernel, the following vulnerability has been resolved: ext4: fix memory leak in ext4_mb_init_backend on error path. Fix a memory leak discovered by syzbot when a file system is corrupted with an illegally large s_log_groups_per_flex.
CVE-2021-47119: In the Linux kernel, the following vulnerability has been resolved: ext4: fix memory leak in ext4_fill_super Buffer head references must be released before calling kill_bdev(); otherwise the buffer head (and its page referenced by b_data) will not be freed by kill_bdev, and subsequently that bh will be leaked. If blocksizes differ, sb_set_blocksize() will kill current buffers and page cache by using kill_bdev(). And then super block will be reread again but using correct blocksize this time. sb_set_blocksize() didn't fully free superblock page and buffer head, and being busy, they were not freed and instead leaked. This can easily be reproduced by calling an infinite loop of: systemctl start <ext4_on_lvm>.mount, and systemctl stop <ext4_on_lvm>.mount ... since systemd creates a cgroup for each slice which it mounts, and the bh leak get amplified by a dying memory cgroup that also never gets freed, and memory consumption is much more easily noticed.
CVE-2021-47131: In the Linux kernel, the following vulnerability has been resolved: net/tls: Fix use-after-free after the TLS device goes down and up When a netdev with active TLS offload goes down, tls_device_down is called to stop the offload and tear down the TLS context. However, the socket stays alive, and it still points to the TLS context, which is now deallocated. If a netdev goes up, while the connection is still active, and the data flow resumes after a number of TCP retransmissions, it will lead to a use-after-free of the TLS context. This commit addresses this bug by keeping the context alive until its normal destruction, and implements the necessary fallbacks, so that the connection can resume in software (non-offloaded) kTLS mode. On the TX side tls_sw_fallback is used to encrypt all packets. The RX side already has all the necessary fallbacks, because receiving non-decrypted packets is supported. The thing needed on the RX side is to block resync requests, which are normally produced after receiving non-decrypted packets. The necessary synchronization is implemented for a graceful teardown: first the fallbacks are deployed, then the driver resources are released (it used to be possible to have a tls_dev_resync after tls_dev_del). A new flag called TLS_RX_DEV_DEGRADED is added to indicate the fallback mode. It's used to skip the RX resync logic completely, as it becomes useless, and some objects may be released (for example, resync_async, which is allocated and freed by the driver).
CVE-2021-47143: In the Linux kernel, the following vulnerability has been resolved: net/smc: remove device from smcd_dev_list after failed device_add() If the device_add() for a smcd_dev fails, there's no cleanup step that rolls back the earlier list_add(). The device subsequently gets freed, and we end up with a corrupted list. Add some error handling that removes the device from the list.
CVE-2021-47163: In the Linux kernel, the following vulnerability has been resolved: tipc: wait and exit until all work queues are done On some host, a crash could be triggered simply by repeating these commands several times: # modprobe tipc # tipc bearer enable media udp name UDP1 localip 127.0.0.1 # rmmod tipc [] BUG: unable to handle kernel paging request at ffffffffc096bb00 [] Workqueue: events 0xffffffffc096bb00 [] Call Trace: [] ? process_one_work+0x1a7/0x360 [] ? worker_thread+0x30/0x390 [] ? create_worker+0x1a0/0x1a0 [] ? kthread+0x116/0x130 [] ? kthread_flush_work_fn+0x10/0x10 [] ? ret_from_fork+0x35/0x40 When removing the TIPC module, the UDP tunnel sock will be delayed to release in a work queue as sock_release() can't be done in rtnl_lock(). If the work queue is schedule to run after the TIPC module is removed, kernel will crash as the work queue function cleanup_beareri() code no longer exists when trying to invoke it. To fix it, this patch introduce a member wq_count in tipc_net to track the numbers of work queues in schedule, and wait and exit until all work queues are done in tipc_exit_net().
CVE-2021-47167: In the Linux kernel, the following vulnerability has been resolved: NFS: Fix an Oopsable condition in __nfs_pageio_add_request() Ensure that nfs_pageio_error_cleanup() resets the mirror array contents, so that the structure reflects the fact that it is now empty. Also change the test in nfs_pageio_do_add_request() to be more robust by checking whether or not the list is empty rather than relying on the value of pg_count.
CVE-2021-47182: In the Linux kernel, the following vulnerability has been resolved: scsi: core: Fix scsi_mode_sense() buffer length handling Several problems exist with scsi_mode_sense() buffer length handling: 1) The allocation length field of the MODE SENSE(10) command is 16-bits, occupying bytes 7 and 8 of the CDB. With this command, access to mode pages larger than 255 bytes is thus possible. However, the CDB allocation length field is set by assigning len to byte 8 only, thus truncating buffer length larger than 255. 2) If scsi_mode_sense() is called with len smaller than 8 with sdev->use_10_for_ms set, or smaller than 4 otherwise, the buffer length is increased to 8 and 4 respectively, and the buffer is zero filled with these increased values, thus corrupting the memory following the buffer. Fix these 2 problems by using put_unaligned_be16() to set the allocation length field of MODE SENSE(10) CDB and by returning an error when len is too small. Furthermore, if len is larger than 255B, always try MODE SENSE(10) first, even if the device driver did not set sdev->use_10_for_ms. In case of invalid opcode error for MODE SENSE(10), access to mode pages larger than 255 bytes are not retried using MODE SENSE(6). To avoid buffer length overflows for the MODE_SENSE(10) case, check that len is smaller than 65535 bytes. While at it, also fix the folowing: * Use get_unaligned_be16() to retrieve the mode data length and block descriptor length fields of the mode sense reply header instead of using an open coded calculation. * Fix the kdoc dbd argument explanation: the DBD bit stands for Disable Block Descriptor, which is the opposite of what the dbd argument description was.
CVE-2021-47183: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Fix link down processing to address NULL pointer dereference If an FC link down transition while PLOGIs are outstanding to fabric well known addresses, outstanding ABTS requests may result in a NULL pointer dereference. Driver unload requests may hang with repeated "2878" log messages. The Link down processing results in ABTS requests for outstanding ELS requests. The Abort WQEs are sent for the ELSs before the driver had set the link state to down. Thus the driver is sending the Abort with the expectation that an ABTS will be sent on the wire. The Abort request is stalled waiting for the link to come up. In some conditions the driver may auto-complete the ELSs thus if the link does come up, the Abort completions may reference an invalid structure. Fix by ensuring that Abort set the flag to avoid link traffic if issued due to conditions where the link failed.
CVE-2021-47186: In the Linux kernel, the following vulnerability has been resolved: tipc: check for null after calling kmemdup kmemdup can return a null pointer so need to check for it, otherwise the null key will be dereferenced later in tipc_crypto_key_xmit as can be seen in the trace [1]. [1] https://syzkaller.appspot.com/bug?id=bca180abb29567b189efdbdb34cbf7ba851c2a58
CVE-2021-47187: In the Linux kernel, the following vulnerability has been resolved: arm64: dts: qcom: msm8998: Fix CPU/L2 idle state latency and residency The entry/exit latency and minimum residency in state for the idle states of MSM8998 were ..bad: first of all, for all of them the timings were written for CPU sleep but the min-residency-us param was miscalculated (supposedly, while porting this from downstream); Then, the power collapse states are setting PC on both the CPU cluster *and* the L2 cache, which have different timings: in the specific case of L2 the times are higher so these ones should be taken into account instead of the CPU ones. This parameter misconfiguration was not giving particular issues because on MSM8998 there was no CPU scaling at all, so cluster/L2 power collapse was rarely (if ever) hit. When CPU scaling is enabled, though, the wrong timings will produce SoC unstability shown to the user as random, apparently error-less, sudden reboots and/or lockups. This set of parameters are stabilizing the SoC when CPU scaling is ON and when power collapse is frequently hit.
CVE-2021-47188: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Improve SCSI abort handling The following has been observed on a test setup: WARNING: CPU: 4 PID: 250 at drivers/scsi/ufs/ufshcd.c:2737 ufshcd_queuecommand+0x468/0x65c Call trace: ufshcd_queuecommand+0x468/0x65c scsi_send_eh_cmnd+0x224/0x6a0 scsi_eh_test_devices+0x248/0x418 scsi_eh_ready_devs+0xc34/0xe58 scsi_error_handler+0x204/0x80c kthread+0x150/0x1b4 ret_from_fork+0x10/0x30 That warning is triggered by the following statement: WARN_ON(lrbp->cmd); Fix this warning by clearing lrbp->cmd from the abort handler.
CVE-2021-47191: In the Linux kernel, the following vulnerability has been resolved: scsi: scsi_debug: Fix out-of-bound read in resp_readcap16() The following warning was observed running syzkaller: [ 3813.830724] sg_write: data in/out 65466/242 bytes for SCSI command 0x9e-- guessing data in; [ 3813.830724] program syz-executor not setting count and/or reply_len properly [ 3813.836956] ================================================================== [ 3813.839465] BUG: KASAN: stack-out-of-bounds in sg_copy_buffer+0x157/0x1e0 [ 3813.841773] Read of size 4096 at addr ffff8883cf80f540 by task syz-executor/1549 [ 3813.846612] Call Trace: [ 3813.846995] dump_stack+0x108/0x15f [ 3813.847524] print_address_description+0xa5/0x372 [ 3813.848243] kasan_report.cold+0x236/0x2a8 [ 3813.849439] check_memory_region+0x240/0x270 [ 3813.850094] memcpy+0x30/0x80 [ 3813.850553] sg_copy_buffer+0x157/0x1e0 [ 3813.853032] sg_copy_from_buffer+0x13/0x20 [ 3813.853660] fill_from_dev_buffer+0x135/0x370 [ 3813.854329] resp_readcap16+0x1ac/0x280 [ 3813.856917] schedule_resp+0x41f/0x1630 [ 3813.858203] scsi_debug_queuecommand+0xb32/0x17e0 [ 3813.862699] scsi_dispatch_cmd+0x330/0x950 [ 3813.863329] scsi_request_fn+0xd8e/0x1710 [ 3813.863946] __blk_run_queue+0x10b/0x230 [ 3813.864544] blk_execute_rq_nowait+0x1d8/0x400 [ 3813.865220] sg_common_write.isra.0+0xe61/0x2420 [ 3813.871637] sg_write+0x6c8/0xef0 [ 3813.878853] __vfs_write+0xe4/0x800 [ 3813.883487] vfs_write+0x17b/0x530 [ 3813.884008] ksys_write+0x103/0x270 [ 3813.886268] __x64_sys_write+0x77/0xc0 [ 3813.886841] do_syscall_64+0x106/0x360 [ 3813.887415] entry_SYSCALL_64_after_hwframe+0x44/0xa9 This issue can be reproduced with the following syzkaller log: r0 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x26e1, 0x0) r1 = syz_open_procfs(0xffffffffffffffff, &(0x7f0000000000)='fd/3\x00') open_by_handle_at(r1, &(0x7f00000003c0)=ANY=[@ANYRESHEX], 0x602000) r2 = syz_open_dev$sg(&(0x7f0000000000), 0x0, 0x40782) write$binfmt_aout(r2, &(0x7f0000000340)=ANY=[@ANYBLOB="00000000deff000000000000000000000000000000000000000000000000000047f007af9e107a41ec395f1bded7be24277a1501ff6196a83366f4e6362bc0ff2b247f68a972989b094b2da4fb3607fcf611a22dd04310d28c75039d"], 0x126) In resp_readcap16() we get "int alloc_len" value -1104926854, and then pass the huge arr_len to fill_from_dev_buffer(), but arr is only 32 bytes. This leads to OOB in sg_copy_buffer(). To solve this issue, define alloc_len as u32.
CVE-2021-47193: In the Linux kernel, the following vulnerability has been resolved: scsi: pm80xx: Fix memory leak during rmmod Driver failed to release all memory allocated. This would lead to memory leak during driver removal. Properly free memory when the module is removed.
CVE-2021-47198: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Fix use-after-free in lpfc_unreg_rpi() routine An error is detected with the following report when unloading the driver: "KASAN: use-after-free in lpfc_unreg_rpi+0x1b1b" The NLP_REG_LOGIN_SEND nlp_flag is set in lpfc_reg_fab_ctrl_node(), but the flag is not cleared upon completion of the login. This allows a second call to lpfc_unreg_rpi() to proceed with nlp_rpi set to LPFC_RPI_ALLOW_ERROR. This results in a use after free access when used as an rpi_ids array index. Fix by clearing the NLP_REG_LOGIN_SEND nlp_flag in lpfc_mbx_cmpl_fc_reg_login().
CVE-2021-47201: In the Linux kernel, the following vulnerability has been resolved: iavf: free q_vectors before queues in iavf_disable_vf iavf_free_queues() clears adapter->num_active_queues, which iavf_free_q_vectors() relies on, so swap the order of these two function calls in iavf_disable_vf(). This resolves a panic encountered when the interface is disabled and then later brought up again after PF communication is restored.
CVE-2021-47202: In the Linux kernel, the following vulnerability has been resolved: thermal: Fix NULL pointer dereferences in of_thermal_ functions of_parse_thermal_zones() parses the thermal-zones node and registers a thermal_zone device for each subnode. However, if a thermal zone is consuming a thermal sensor and that thermal sensor device hasn't probed yet, an attempt to set trip_point_*_temp for that thermal zone device can cause a NULL pointer dereference. Fix it. console:/sys/class/thermal/thermal_zone87 # echo 120000 > trip_point_0_temp ... Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 ... Call trace: of_thermal_set_trip_temp+0x40/0xc4 trip_point_temp_store+0xc0/0x1dc dev_attr_store+0x38/0x88 sysfs_kf_write+0x64/0xc0 kernfs_fop_write_iter+0x108/0x1d0 vfs_write+0x2f4/0x368 ksys_write+0x7c/0xec __arm64_sys_write+0x20/0x30 el0_svc_common.llvm.7279915941325364641+0xbc/0x1bc do_el0_svc+0x28/0xa0 el0_svc+0x14/0x24 el0_sync_handler+0x88/0xec el0_sync+0x1c0/0x200 While at it, fix the possible NULL pointer dereference in other functions as well: of_thermal_get_temp(), of_thermal_set_emul_temp(), of_thermal_get_trend().
CVE-2021-47204: In the Linux kernel, the following vulnerability has been resolved: net: dpaa2-eth: fix use-after-free in dpaa2_eth_remove Access to netdev after free_netdev() will cause use-after-free bug. Move debug log before free_netdev() call to avoid it.
CVE-2021-47205: In the Linux kernel, the following vulnerability has been resolved: clk: sunxi-ng: Unregister clocks/resets when unbinding Currently, unbinding a CCU driver unmaps the device's MMIO region, while leaving its clocks/resets and their providers registered. This can cause a page fault later when some clock operation tries to perform MMIO. Fix this by separating the CCU initialization from the memory allocation, and then using a devres callback to unregister the clocks and resets. This also fixes a memory leak of the `struct ccu_reset`, and uses the correct owner (the specific platform driver) for the clocks and resets. Early OF clock providers are never unregistered, and limited error handling is possible, so they are mostly unchanged. The error reporting is made more consistent by moving the message inside of_sunxi_ccu_probe.
CVE-2021-47211: In the Linux kernel, the following vulnerability has been resolved: ALSA: usb-audio: fix null pointer dereference on pointer cs_desc The pointer cs_desc return from snd_usb_find_clock_source could be null, so there is a potential null pointer dereference issue. Fix this by adding a null check before dereference.
CVE-2021-47219: In the Linux kernel, the following vulnerability has been resolved: scsi: scsi_debug: Fix out-of-bound read in resp_report_tgtpgs() The following issue was observed running syzkaller: BUG: KASAN: slab-out-of-bounds in memcpy include/linux/string.h:377 [inline] BUG: KASAN: slab-out-of-bounds in sg_copy_buffer+0x150/0x1c0 lib/scatterlist.c:831 Read of size 2132 at addr ffff8880aea95dc8 by task syz-executor.0/9815 CPU: 0 PID: 9815 Comm: syz-executor.0 Not tainted 4.19.202-00874-gfc0fe04215a9 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xe4/0x14a lib/dump_stack.c:118 print_address_description+0x73/0x280 mm/kasan/report.c:253 kasan_report_error mm/kasan/report.c:352 [inline] kasan_report+0x272/0x370 mm/kasan/report.c:410 memcpy+0x1f/0x50 mm/kasan/kasan.c:302 memcpy include/linux/string.h:377 [inline] sg_copy_buffer+0x150/0x1c0 lib/scatterlist.c:831 fill_from_dev_buffer+0x14f/0x340 drivers/scsi/scsi_debug.c:1021 resp_report_tgtpgs+0x5aa/0x770 drivers/scsi/scsi_debug.c:1772 schedule_resp+0x464/0x12f0 drivers/scsi/scsi_debug.c:4429 scsi_debug_queuecommand+0x467/0x1390 drivers/scsi/scsi_debug.c:5835 scsi_dispatch_cmd+0x3fc/0x9b0 drivers/scsi/scsi_lib.c:1896 scsi_request_fn+0x1042/0x1810 drivers/scsi/scsi_lib.c:2034 __blk_run_queue_uncond block/blk-core.c:464 [inline] __blk_run_queue+0x1a4/0x380 block/blk-core.c:484 blk_execute_rq_nowait+0x1c2/0x2d0 block/blk-exec.c:78 sg_common_write.isra.19+0xd74/0x1dc0 drivers/scsi/sg.c:847 sg_write.part.23+0x6e0/0xd00 drivers/scsi/sg.c:716 sg_write+0x64/0xa0 drivers/scsi/sg.c:622 __vfs_write+0xed/0x690 fs/read_write.c:485 kill_bdev:block_device:00000000e138492c vfs_write+0x184/0x4c0 fs/read_write.c:549 ksys_write+0x107/0x240 fs/read_write.c:599 do_syscall_64+0xc2/0x560 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x49/0xbe We get 'alen' from command its type is int. If userspace passes a large length we will get a negative 'alen'. Switch n, alen, and rlen to u32.
CVE-2021-47224: In the Linux kernel, the following vulnerability has been resolved: net: ll_temac: Make sure to free skb when it is completely used With the skb pointer piggy-backed on the TX BD, we have a simple and efficient way to free the skb buffer when the frame has been transmitted. But in order to avoid freeing the skb while there are still fragments from the skb in use, we need to piggy-back on the TX BD of the skb, not the first. Without this, we are doing use-after-free on the DMA side, when the first BD of a multi TX BD packet is seen as completed in xmit_done, and the remaining BDs are still being processed.
CVE-2021-47233: In the Linux kernel, the following vulnerability has been resolved: regulator: rt4801: Fix NULL pointer dereference if priv->enable_gpios is NULL devm_gpiod_get_array_optional may return NULL if no GPIO was assigned.
CVE-2021-47234: In the Linux kernel, the following vulnerability has been resolved: phy: phy-mtk-tphy: Fix some resource leaks in mtk_phy_init() Use clk_disable_unprepare() in the error path of mtk_phy_init() to fix some resource leaks.
CVE-2021-47246: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix page reclaim for dead peer hairpin When adding a hairpin flow, a firmware-side send queue is created for the peer net device, which claims some host memory pages for its internal ring buffer. If the peer net device is removed/unbound before the hairpin flow is deleted, then the send queue is not destroyed which leads to a stack trace on pci device remove: [ 748.005230] mlx5_core 0000:08:00.2: wait_func:1094:(pid 12985): MANAGE_PAGES(0x108) timeout. Will cause a leak of a command resource [ 748.005231] mlx5_core 0000:08:00.2: reclaim_pages:514:(pid 12985): failed reclaiming pages: err -110 [ 748.001835] mlx5_core 0000:08:00.2: mlx5_reclaim_root_pages:653:(pid 12985): failed reclaiming pages (-110) for func id 0x0 [ 748.002171] ------------[ cut here ]------------ [ 748.001177] FW pages counter is 4 after reclaiming all pages [ 748.001186] WARNING: CPU: 1 PID: 12985 at drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:685 mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ +0.002771] Modules linked in: cls_flower mlx5_ib mlx5_core ptp pps_core act_mirred sch_ingress openvswitch nsh xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_umad ib_ipoib iw_cm ib_cm ib_uverbs ib_core overlay fuse [last unloaded: pps_core] [ 748.007225] CPU: 1 PID: 12985 Comm: tee Not tainted 5.12.0+ #1 [ 748.001376] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 748.002315] RIP: 0010:mlx5_reclaim_startup_pages+0x34b/0x460 [mlx5_core] [ 748.001679] Code: 28 00 00 00 0f 85 22 01 00 00 48 81 c4 b0 00 00 00 31 c0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 48 c7 c7 40 cc 19 a1 e8 9f 71 0e e2 <0f> 0b e9 30 ff ff ff 48 c7 c7 a0 cc 19 a1 e8 8c 71 0e e2 0f 0b e9 [ 748.003781] RSP: 0018:ffff88815220faf8 EFLAGS: 00010286 [ 748.001149] RAX: 0000000000000000 RBX: ffff8881b4900280 RCX: 0000000000000000 [ 748.001445] RDX: 0000000000000027 RSI: 0000000000000004 RDI: ffffed102a441f51 [ 748.001614] RBP: 00000000000032b9 R08: 0000000000000001 R09: ffffed1054a15ee8 [ 748.001446] R10: ffff8882a50af73b R11: ffffed1054a15ee7 R12: fffffbfff07c1e30 [ 748.001447] R13: dffffc0000000000 R14: ffff8881b492cba8 R15: 0000000000000000 [ 748.001429] FS: 00007f58bd08b580(0000) GS:ffff8882a5080000(0000) knlGS:0000000000000000 [ 748.001695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 748.001309] CR2: 000055a026351740 CR3: 00000001d3b48006 CR4: 0000000000370ea0 [ 748.001506] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 748.001483] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 748.001654] Call Trace: [ 748.000576] ? mlx5_satisfy_startup_pages+0x290/0x290 [mlx5_core] [ 748.001416] ? mlx5_cmd_teardown_hca+0xa2/0xd0 [mlx5_core] [ 748.001354] ? mlx5_cmd_init_hca+0x280/0x280 [mlx5_core] [ 748.001203] mlx5_function_teardown+0x30/0x60 [mlx5_core] [ 748.001275] mlx5_uninit_one+0xa7/0xc0 [mlx5_core] [ 748.001200] remove_one+0x5f/0xc0 [mlx5_core] [ 748.001075] pci_device_remove+0x9f/0x1d0 [ 748.000833] device_release_driver_internal+0x1e0/0x490 [ 748.001207] unbind_store+0x19f/0x200 [ 748.000942] ? sysfs_file_ops+0x170/0x170 [ 748.001000] kernfs_fop_write_iter+0x2bc/0x450 [ 748.000970] new_sync_write+0x373/0x610 [ 748.001124] ? new_sync_read+0x600/0x600 [ 748.001057] ? lock_acquire+0x4d6/0x700 [ 748.000908] ? lockdep_hardirqs_on_prepare+0x400/0x400 [ 748.001126] ? fd_install+0x1c9/0x4d0 [ 748.000951] vfs_write+0x4d0/0x800 [ 748.000804] ksys_write+0xf9/0x1d0 [ 748.000868] ? __x64_sys_read+0xb0/0xb0 [ 748.000811] ? filp_open+0x50/0x50 [ 748.000919] ? syscall_enter_from_user_mode+0x1d/0x50 [ 748.001223] do_syscall_64+0x3f/0x80 [ 748.000892] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 748.00 ---truncated---
CVE-2021-47253: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix potential memory leak in DMUB hw_init [Why] On resume we perform DMUB hw_init which allocates memory: dm_resume->dm_dmub_hw_init->dc_dmub_srv_create->kzalloc That results in memory leak in suspend/resume scenarios. [How] Allocate memory for the DC wrapper to DMUB only if it was not allocated before. No need to reallocate it on suspend/resume.
CVE-2021-47265: In the Linux kernel, the following vulnerability has been resolved: RDMA: Verify port when creating flow rule Validate port value provided by the user and with that remove no longer needed validation by the driver. The missing check in the mlx5_ib driver could cause to the below oops. Call trace: _create_flow_rule+0x2d4/0xf28 [mlx5_ib] mlx5_ib_create_flow+0x2d0/0x5b0 [mlx5_ib] ib_uverbs_ex_create_flow+0x4cc/0x624 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xd4/0x150 [ib_uverbs] ib_uverbs_cmd_verbs.isra.7+0xb28/0xc50 [ib_uverbs] ib_uverbs_ioctl+0x158/0x1d0 [ib_uverbs] do_vfs_ioctl+0xd0/0xaf0 ksys_ioctl+0x84/0xb4 __arm64_sys_ioctl+0x28/0xc4 el0_svc_common.constprop.3+0xa4/0x254 el0_svc_handler+0x84/0xa0 el0_svc+0x10/0x26c Code: b9401260 f9615681 51000400 8b001c20 (f9403c1a)
CVE-2021-47275: In the Linux kernel, the following vulnerability has been resolved: bcache: avoid oversized read request in cache missing code path In the cache missing code path of cached device, if a proper location from the internal B+ tree is matched for a cache miss range, function cached_dev_cache_miss() will be called in cache_lookup_fn() in the following code block, [code block 1] 526 unsigned int sectors = KEY_INODE(k) == s->iop.inode 527 ? min_t(uint64_t, INT_MAX, 528 KEY_START(k) - bio->bi_iter.bi_sector) 529 : INT_MAX; 530 int ret = s->d->cache_miss(b, s, bio, sectors); Here s->d->cache_miss() is the call backfunction pointer initialized as cached_dev_cache_miss(), the last parameter 'sectors' is an important hint to calculate the size of read request to backing device of the missing cache data. Current calculation in above code block may generate oversized value of 'sectors', which consequently may trigger 2 different potential kernel panics by BUG() or BUG_ON() as listed below, 1) BUG_ON() inside bch_btree_insert_key(), [code block 2] 886 BUG_ON(b->ops->is_extents && !KEY_SIZE(k)); 2) BUG() inside biovec_slab(), [code block 3] 51 default: 52 BUG(); 53 return NULL; All the above panics are original from cached_dev_cache_miss() by the oversized parameter 'sectors'. Inside cached_dev_cache_miss(), parameter 'sectors' is used to calculate the size of data read from backing device for the cache missing. This size is stored in s->insert_bio_sectors by the following lines of code, [code block 4] 909 s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada); Then the actual key inserting to the internal B+ tree is generated and stored in s->iop.replace_key by the following lines of code, [code block 5] 911 s->iop.replace_key = KEY(s->iop.inode, 912 bio->bi_iter.bi_sector + s->insert_bio_sectors, 913 s->insert_bio_sectors); The oversized parameter 'sectors' may trigger panic 1) by BUG_ON() from the above code block. And the bio sending to backing device for the missing data is allocated with hint from s->insert_bio_sectors by the following lines of code, [code block 6] 926 cache_bio = bio_alloc_bioset(GFP_NOWAIT, 927 DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS), 928 &dc->disk.bio_split); The oversized parameter 'sectors' may trigger panic 2) by BUG() from the agove code block. Now let me explain how the panics happen with the oversized 'sectors'. In code block 5, replace_key is generated by macro KEY(). From the definition of macro KEY(), [code block 7] 71 #define KEY(inode, offset, size) \ 72 ((struct bkey) { \ 73 .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ 74 .low = (offset) \ 75 }) Here 'size' is 16bits width embedded in 64bits member 'high' of struct bkey. But in code block 1, if "KEY_START(k) - bio->bi_iter.bi_sector" is very probably to be larger than (1<<16) - 1, which makes the bkey size calculation in code block 5 is overflowed. In one bug report the value of parameter 'sectors' is 131072 (= 1 << 17), the overflowed 'sectors' results the overflowed s->insert_bio_sectors in code block 4, then makes size field of s->iop.replace_key to be 0 in code block 5. Then the 0- sized s->iop.replace_key is inserted into the internal B+ tree as cache missing check key (a special key to detect and avoid a racing between normal write request and cache missing read request) as, [code block 8] 915 ret = bch_btree_insert_check_key(b, &s->op, &s->iop.replace_key); Then the 0-sized s->iop.replace_key as 3rd parameter triggers the bkey size check BUG_ON() in code block 2, and causes the kernel panic 1). Another ke ---truncated---
CVE-2021-47281: In the Linux kernel, the following vulnerability has been resolved: ALSA: seq: Fix race of snd_seq_timer_open() The timer instance per queue is exclusive, and snd_seq_timer_open() should have managed the concurrent accesses. It looks as if it's checking the already existing timer instance at the beginning, but it's not right, because there is no protection, hence any later concurrent call of snd_seq_timer_open() may override the timer instance easily. This may result in UAF, as the leftover timer instance can keep running while the queue itself gets closed, as spotted by syzkaller recently. For avoiding the race, add a proper check at the assignment of tmr->timeri again, and return -EBUSY if it's been already registered.
CVE-2021-47283: In the Linux kernel, the following vulnerability has been resolved: net:sfc: fix non-freed irq in legacy irq mode SFC driver can be configured via modparam to work using MSI-X, MSI or legacy IRQ interrupts. In the last one, the interrupt was not properly released on module remove. It was not freed because the flag irqs_hooked was not set during initialization in the case of using legacy IRQ. Example of (trimmed) trace during module remove without this fix: remove_proc_entry: removing non-empty directory 'irq/125', leaking at least '0000:3b:00.1' WARNING: CPU: 39 PID: 3658 at fs/proc/generic.c:715 remove_proc_entry+0x15c/0x170 ...trimmed... Call Trace: unregister_irq_proc+0xe3/0x100 free_desc+0x29/0x70 irq_free_descs+0x47/0x70 mp_unmap_irq+0x58/0x60 acpi_unregister_gsi_ioapic+0x2a/0x40 acpi_pci_irq_disable+0x78/0xb0 pci_disable_device+0xd1/0x100 efx_pci_remove+0xa1/0x1e0 [sfc] pci_device_remove+0x38/0xa0 __device_release_driver+0x177/0x230 driver_detach+0xcb/0x110 bus_remove_driver+0x58/0xd0 pci_unregister_driver+0x2a/0xb0 efx_exit_module+0x24/0xf40 [sfc] __do_sys_delete_module.constprop.0+0x171/0x280 ? exit_to_user_mode_prepare+0x83/0x1d0 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f9f9385800b ...trimmed...
CVE-2021-47289: In the Linux kernel, the following vulnerability has been resolved: ACPI: fix NULL pointer dereference Commit 71f642833284 ("ACPI: utils: Fix reference counting in for_each_acpi_dev_match()") started doing "acpi_dev_put()" on a pointer that was possibly NULL. That fails miserably, because that helper inline function is not set up to handle that case. Just make acpi_dev_put() silently accept a NULL pointer, rather than calling down to put_device() with an invalid offset off that NULL pointer.
CVE-2021-47295: In the Linux kernel, the following vulnerability has been resolved: net: sched: fix memory leak in tcindex_partial_destroy_work Syzbot reported memory leak in tcindex_set_parms(). The problem was in non-freed perfect hash in tcindex_partial_destroy_work(). In tcindex_set_parms() new tcindex_data is allocated and some fields from old one are copied to new one, but not the perfect hash. Since tcindex_partial_destroy_work() is the destroy function for old tcindex_data, we need to free perfect hash to avoid memory leak.
CVE-2021-47307: In the Linux kernel, the following vulnerability has been resolved: cifs: prevent NULL deref in cifs_compose_mount_options() The optional @ref parameter might contain an NULL node_name, so prevent dereferencing it in cifs_compose_mount_options(). Addresses-Coverity: 1476408 ("Explicit null dereferenced")
CVE-2021-47325: In the Linux kernel, the following vulnerability has been resolved: iommu/arm-smmu: Fix arm_smmu_device refcount leak in address translation The reference counting issue happens in several exception handling paths of arm_smmu_iova_to_phys_hard(). When those error scenarios occur, the function forgets to decrease the refcount of "smmu" increased by arm_smmu_rpm_get(), causing a refcount leak. Fix this issue by jumping to "out" label when those error scenarios occur.
CVE-2021-47327: In the Linux kernel, the following vulnerability has been resolved: iommu/arm-smmu: Fix arm_smmu_device refcount leak when arm_smmu_rpm_get fails arm_smmu_rpm_get() invokes pm_runtime_get_sync(), which increases the refcount of the "smmu" even though the return value is less than 0. The reference counting issue happens in some error handling paths of arm_smmu_rpm_get() in its caller functions. When arm_smmu_rpm_get() fails, the caller functions forget to decrease the refcount of "smmu" increased by arm_smmu_rpm_get(), causing a refcount leak. Fix this issue by calling pm_runtime_resume_and_get() instead of pm_runtime_get_sync() in arm_smmu_rpm_get(), which can keep the refcount balanced in case of failure.
CVE-2021-47329: In the Linux kernel, the following vulnerability has been resolved: scsi: megaraid_sas: Fix resource leak in case of probe failure The driver doesn't clean up all the allocated resources properly when scsi_add_host(), megasas_start_aen() function fails during the PCI device probe. Clean up all those resources.
CVE-2021-47331: In the Linux kernel, the following vulnerability has been resolved: usb: common: usb-conn-gpio: fix NULL pointer dereference of charger When power on system with OTG cable, IDDIG's interrupt arises before the charger registration, it will cause a NULL pointer dereference, fix the issue by registering the power supply before requesting IDDIG/VBUS irq.
CVE-2021-47332: In the Linux kernel, the following vulnerability has been resolved: ALSA: usx2y: Don't call free_pages_exact() with NULL address Unlike some other functions, we can't pass NULL pointer to free_pages_exact(). Add a proper NULL check for avoiding possible Oops.
CVE-2021-47333: In the Linux kernel, the following vulnerability has been resolved: misc: alcor_pci: fix null-ptr-deref when there is no PCI bridge There is an issue with the ASPM(optional) capability checking function. A device might be attached to root complex directly, in this case, bus->self(bridge) will be NULL, thus priv->parent_pdev is NULL. Since alcor_pci_init_check_aspm(priv->parent_pdev) checks the PCI link's ASPM capability and populate parent_cap_off, which will be used later by alcor_pci_aspm_ctrl() to dynamically turn on/off device, what we can do here is to avoid checking the capability if we are on the root complex. This will make pdev_cap_off 0 and alcor_pci_aspm_ctrl() will simply return when bring called, effectively disable ASPM for the device. [ 1.246492] BUG: kernel NULL pointer dereference, address: 00000000000000c0 [ 1.248731] RIP: 0010:pci_read_config_byte+0x5/0x40 [ 1.253998] Call Trace: [ 1.254131] ? alcor_pci_find_cap_offset.isra.0+0x3a/0x100 [alcor_pci] [ 1.254476] alcor_pci_probe+0x169/0x2d5 [alcor_pci]
CVE-2021-47335: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid racing on fsync_entry_slab by multi filesystem instances As syzbot reported, there is an use-after-free issue during f2fs recovery: Use-after-free write at 0xffff88823bc16040 (in kfence-#10): kmem_cache_destroy+0x1f/0x120 mm/slab_common.c:486 f2fs_recover_fsync_data+0x75b0/0x8380 fs/f2fs/recovery.c:869 f2fs_fill_super+0x9393/0xa420 fs/f2fs/super.c:3945 mount_bdev+0x26c/0x3a0 fs/super.c:1367 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x86/0x270 fs/super.c:1497 do_new_mount fs/namespace.c:2905 [inline] path_mount+0x196f/0x2be0 fs/namespace.c:3235 do_mount fs/namespace.c:3248 [inline] __do_sys_mount fs/namespace.c:3456 [inline] __se_sys_mount+0x2f9/0x3b0 fs/namespace.c:3433 do_syscall_64+0x3f/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae The root cause is multi f2fs filesystem instances can race on accessing global fsync_entry_slab pointer, result in use-after-free issue of slab cache, fixes to init/destroy this slab cache only once during module init/destroy procedure to avoid this issue.
CVE-2021-47339: In the Linux kernel, the following vulnerability has been resolved: media: v4l2-core: explicitly clear ioctl input data As seen from a recent syzbot bug report, mistakes in the compat ioctl implementation can lead to uninitialized kernel stack data getting used as input for driver ioctl handlers. The reported bug is now fixed, but it's possible that other related bugs are still present or get added in the future. As the drivers need to check user input already, the possible impact is fairly low, but it might still cause an information leak. To be on the safe side, always clear the entire ioctl buffer before calling the conversion handler functions that are meant to initialize them.
CVE-2021-47342: In the Linux kernel, the following vulnerability has been resolved: ext4: fix possible UAF when remounting r/o a mmp-protected file system After commit 618f003199c6 ("ext4: fix memory leak in ext4_fill_super"), after the file system is remounted read-only, there is a race where the kmmpd thread can exit, causing sbi->s_mmp_tsk to point at freed memory, which the call to ext4_stop_mmpd() can trip over. Fix this by only allowing kmmpd() to exit when it is stopped via ext4_stop_mmpd(). Bug-Report-Link: <20210629143603.2166962-1-yebin10@huawei.com>
CVE-2021-47348: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Avoid HDCP over-read and corruption Instead of reading the desired 5 bytes of the actual target field, the code was reading 8. This could result in a corrupted value if the trailing 3 bytes were non-zero, so instead use an appropriately sized and zero-initialized bounce buffer, and read only 5 bytes before casting to u64.
CVE-2021-47350: In the Linux kernel, the following vulnerability has been resolved: powerpc/mm: Fix lockup on kernel exec fault The powerpc kernel is not prepared to handle exec faults from kernel. Especially, the function is_exec_fault() will return 'false' when an exec fault is taken by kernel, because the check is based on reading current->thread.regs->trap which contains the trap from user. For instance, when provoking a LKDTM EXEC_USERSPACE test, current->thread.regs->trap is set to SYSCALL trap (0xc00), and the fault taken by the kernel is not seen as an exec fault by set_access_flags_filter(). Commit d7df2443cd5f ("powerpc/mm: Fix spurious segfaults on radix with autonuma") made it clear and handled it properly. But later on commit d3ca587404b3 ("powerpc/mm: Fix reporting of kernel execute faults") removed that handling, introducing test based on error_code. And here is the problem, because on the 603 all upper bits of SRR1 get cleared when the TLB instruction miss handler bails out to ISI. Until commit cbd7e6ca0210 ("powerpc/fault: Avoid heavy search_exception_tables() verification"), an exec fault from kernel at a userspace address was indirectly caught by the lack of entry for that address in the exception tables. But after that commit the kernel mainly relies on KUAP or on core mm handling to catch wrong user accesses. Here the access is not wrong, so mm handles it. It is a minor fault because PAGE_EXEC is not set, set_access_flags_filter() should set PAGE_EXEC and voila. But as is_exec_fault() returns false as explained in the beginning, set_access_flags_filter() bails out without setting PAGE_EXEC flag, which leads to a forever minor exec fault. As the kernel is not prepared to handle such exec faults, the thing to do is to fire in bad_kernel_fault() for any exec fault taken by the kernel, as it was prior to commit d3ca587404b3.
CVE-2021-47351: In the Linux kernel, the following vulnerability has been resolved: ubifs: Fix races between xattr_{set|get} and listxattr operations UBIFS may occur some problems with concurrent xattr_{set|get} and listxattr operations, such as assertion failure, memory corruption, stale xattr value[1]. Fix it by importing a new rw-lock in @ubifs_inode to serilize write operations on xattr, concurrent read operations are still effective, just like ext4. [1] https://lore.kernel.org/linux-mtd/20200630130438.141649-1-houtao1@huawei.com
CVE-2021-47352: In the Linux kernel, the following vulnerability has been resolved: virtio-net: Add validation for used length This adds validation for used length (might come from an untrusted device) to avoid data corruption or loss.
CVE-2021-47354: In the Linux kernel, the following vulnerability has been resolved: drm/sched: Avoid data corruptions Wait for all dependencies of a job to complete before killing it to avoid data corruptions.
CVE-2021-47359: In the Linux kernel, the following vulnerability has been resolved: cifs: Fix soft lockup during fsstress Below traces are observed during fsstress and system got hung. [ 130.698396] watchdog: BUG: soft lockup - CPU#6 stuck for 26s!
CVE-2021-47362: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: Update intermediate power state for SI Update the current state as boot state during dpm initialization. During the subsequent initialization, set_power_state gets called to transition to the final power state. set_power_state refers to values from the current state and without current state populated, it could result in NULL pointer dereference. For ex: on platforms where PCI speed change is supported through ACPI ATCS method, the link speed of current state needs to be queried before deciding on changing to final power state's link speed. The logic to query ATCS-support was broken on certain platforms. The issue became visible when broken ATCS-support logic got fixed with commit f9b7f3703ff9 ("drm/amdgpu/acpi: make ATPX/ATCS structures global (v2)"). Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1698
CVE-2021-47366: In the Linux kernel, the following vulnerability has been resolved: afs: Fix corruption in reads at fpos 2G-4G from an OpenAFS server AFS-3 has two data fetch RPC variants, FS.FetchData and FS.FetchData64, and Linux's afs client switches between them when talking to a non-YFS server if the read size, the file position or the sum of the two have the upper 32 bits set of the 64-bit value. This is a problem, however, since the file position and length fields of FS.FetchData are *signed* 32-bit values. Fix this by capturing the capability bits obtained from the fileserver when it's sent an FS.GetCapabilities RPC, rather than just discarding them, and then picking out the VICED_CAPABILITY_64BITFILES flag. This can then be used to decide whether to use FS.FetchData or FS.FetchData64 - and also FS.StoreData or FS.StoreData64 - rather than using upper_32_bits() to switch on the parameter values. This capabilities flag could also be used to limit the maximum size of the file, but all servers must be checked for that. Note that the issue does not exist with FS.StoreData - that uses *unsigned* 32-bit values. It's also not a problem with Auristor servers as its YFS.FetchData64 op uses unsigned 64-bit values. This can be tested by cloning a git repo through an OpenAFS client to an OpenAFS server and then doing "git status" on it from a Linux afs client[1]. Provided the clone has a pack file that's in the 2G-4G range, the git status will show errors like: error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index This can be observed in the server's FileLog with something like the following appearing: Sun Aug 29 19:31:39 2021 SRXAFS_FetchData, Fid = 2303380852.491776.3263114, Host 192.168.11.201:7001, Id 1001 Sun Aug 29 19:31:39 2021 CheckRights: len=0, for host=192.168.11.201:7001 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: Pos 18446744071815340032, Len 3154 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: file size 2400758866 ... Sun Aug 29 19:31:40 2021 SRXAFS_FetchData returns 5 Note the file position of 18446744071815340032. This is the requested file position sign-extended.
CVE-2021-47374: In the Linux kernel, the following vulnerability has been resolved: dma-debug: prevent an error message from causing runtime problems For some drivers, that use the DMA API. This error message can be reached several millions of times per second, causing spam to the kernel's printk buffer and bringing the CPU usage up to 100% (so, it should be rate limited). However, since there is at least one driver that is in the mainline and suffers from the error condition, it is more useful to err_printk() here instead of just rate limiting the error message (in hopes that it will make it easier for other drivers that suffer from this issue to be spotted).
CVE-2021-47376: In the Linux kernel, the following vulnerability has been resolved: bpf: Add oversize check before call kvcalloc() Commit 7661809d493b ("mm: don't allow oversized kvmalloc() calls") add the oversize check. When the allocation is larger than what kmalloc() supports, the following warning triggered: WARNING: CPU: 0 PID: 8408 at mm/util.c:597 kvmalloc_node+0x108/0x110 mm/util.c:597 Modules linked in: CPU: 0 PID: 8408 Comm: syz-executor221 Not tainted 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:kvmalloc_node+0x108/0x110 mm/util.c:597 Call Trace: kvmalloc include/linux/mm.h:806 [inline] kvmalloc_array include/linux/mm.h:824 [inline] kvcalloc include/linux/mm.h:829 [inline] check_btf_line kernel/bpf/verifier.c:9925 [inline] check_btf_info kernel/bpf/verifier.c:10049 [inline] bpf_check+0xd634/0x150d0 kernel/bpf/verifier.c:13759 bpf_prog_load kernel/bpf/syscall.c:2301 [inline] __sys_bpf+0x11181/0x126e0 kernel/bpf/syscall.c:4587 __do_sys_bpf kernel/bpf/syscall.c:4691 [inline] __se_sys_bpf kernel/bpf/syscall.c:4689 [inline] __x64_sys_bpf+0x78/0x90 kernel/bpf/syscall.c:4689 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2021-47378: In the Linux kernel, the following vulnerability has been resolved: nvme-rdma: destroy cm id before destroy qp to avoid use after free We should always destroy cm_id before destroy qp to avoid to get cma event after qp was destroyed, which may lead to use after free. In RDMA connection establishment error flow, don't destroy qp in cm event handler.Just report cm_error to upper level, qp will be destroy in nvme_rdma_alloc_queue() after destroy cm id.
CVE-2021-47379: In the Linux kernel, the following vulnerability has been resolved: blk-cgroup: fix UAF by grabbing blkcg lock before destroying blkg pd KASAN reports a use-after-free report when doing fuzz test: [693354.104835] ================================================================== [693354.105094] BUG: KASAN: use-after-free in bfq_io_set_weight_legacy+0xd3/0x160 [693354.105336] Read of size 4 at addr ffff888be0a35664 by task sh/1453338 [693354.105607] CPU: 41 PID: 1453338 Comm: sh Kdump: loaded Not tainted 4.18.0-147 [693354.105610] Hardware name: Huawei 2288H V5/BC11SPSCB0, BIOS 0.81 07/02/2018 [693354.105612] Call Trace: [693354.105621] dump_stack+0xf1/0x19b [693354.105626] ? show_regs_print_info+0x5/0x5 [693354.105634] ? printk+0x9c/0xc3 [693354.105638] ? cpumask_weight+0x1f/0x1f [693354.105648] print_address_description+0x70/0x360 [693354.105654] kasan_report+0x1b2/0x330 [693354.105659] ? bfq_io_set_weight_legacy+0xd3/0x160 [693354.105665] ? bfq_io_set_weight_legacy+0xd3/0x160 [693354.105670] bfq_io_set_weight_legacy+0xd3/0x160 [693354.105675] ? bfq_cpd_init+0x20/0x20 [693354.105683] cgroup_file_write+0x3aa/0x510 [693354.105693] ? ___slab_alloc+0x507/0x540 [693354.105698] ? cgroup_file_poll+0x60/0x60 [693354.105702] ? 0xffffffff89600000 [693354.105708] ? usercopy_abort+0x90/0x90 [693354.105716] ? mutex_lock+0xef/0x180 [693354.105726] kernfs_fop_write+0x1ab/0x280 [693354.105732] ? cgroup_file_poll+0x60/0x60 [693354.105738] vfs_write+0xe7/0x230 [693354.105744] ksys_write+0xb0/0x140 [693354.105749] ? __ia32_sys_read+0x50/0x50 [693354.105760] do_syscall_64+0x112/0x370 [693354.105766] ? syscall_return_slowpath+0x260/0x260 [693354.105772] ? do_page_fault+0x9b/0x270 [693354.105779] ? prepare_exit_to_usermode+0xf9/0x1a0 [693354.105784] ? enter_from_user_mode+0x30/0x30 [693354.105793] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.105875] Allocated by task 1453337: [693354.106001] kasan_kmalloc+0xa0/0xd0 [693354.106006] kmem_cache_alloc_node_trace+0x108/0x220 [693354.106010] bfq_pd_alloc+0x96/0x120 [693354.106015] blkcg_activate_policy+0x1b7/0x2b0 [693354.106020] bfq_create_group_hierarchy+0x1e/0x80 [693354.106026] bfq_init_queue+0x678/0x8c0 [693354.106031] blk_mq_init_sched+0x1f8/0x460 [693354.106037] elevator_switch_mq+0xe1/0x240 [693354.106041] elevator_switch+0x25/0x40 [693354.106045] elv_iosched_store+0x1a1/0x230 [693354.106049] queue_attr_store+0x78/0xb0 [693354.106053] kernfs_fop_write+0x1ab/0x280 [693354.106056] vfs_write+0xe7/0x230 [693354.106060] ksys_write+0xb0/0x140 [693354.106064] do_syscall_64+0x112/0x370 [693354.106069] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.106114] Freed by task 1453336: [693354.106225] __kasan_slab_free+0x130/0x180 [693354.106229] kfree+0x90/0x1b0 [693354.106233] blkcg_deactivate_policy+0x12c/0x220 [693354.106238] bfq_exit_queue+0xf5/0x110 [693354.106241] blk_mq_exit_sched+0x104/0x130 [693354.106245] __elevator_exit+0x45/0x60 [693354.106249] elevator_switch_mq+0xd6/0x240 [693354.106253] elevator_switch+0x25/0x40 [693354.106257] elv_iosched_store+0x1a1/0x230 [693354.106261] queue_attr_store+0x78/0xb0 [693354.106264] kernfs_fop_write+0x1ab/0x280 [693354.106268] vfs_write+0xe7/0x230 [693354.106271] ksys_write+0xb0/0x140 [693354.106275] do_syscall_64+0x112/0x370 [693354.106280] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.106329] The buggy address belongs to the object at ffff888be0a35580 which belongs to the cache kmalloc-1k of size 1024 [693354.106736] The buggy address is located 228 bytes inside of 1024-byte region [ffff888be0a35580, ffff888be0a35980) [693354.107114] The buggy address belongs to the page: [693354.107273] page:ffffea002f828c00 count:1 mapcount:0 mapping:ffff888107c17080 index:0x0 compound_mapcount: 0 [693354.107606] flags: 0x17ffffc0008100(slab|head) [693354.107760] raw: 0017ffffc0008100 ffffea002fcbc808 ffffea0030bd3a08 ffff888107c17080 [693354.108020] r ---truncated---
CVE-2021-47380: In the Linux kernel, the following vulnerability has been resolved: HID: amd_sfh: Fix potential NULL pointer dereference devm_add_action_or_reset() can suddenly invoke amd_mp2_pci_remove() at registration that will cause NULL pointer dereference since corresponding data is not initialized yet. The patch moves initialization of data before devm_add_action_or_reset(). Found by Linux Driver Verification project (linuxtesting.org). [jkosina@suse.cz: rebase]
CVE-2021-47384: In the Linux kernel, the following vulnerability has been resolved: hwmon: (w83793) Fix NULL pointer dereference by removing unnecessary structure field If driver read tmp value sufficient for (tmp & 0x08) && (!(tmp & 0x80)) && ((tmp & 0x7) == ((tmp >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). [groeck: Dropped unnecessary continuation lines, fixed multi-line alignments]
CVE-2021-47385: In the Linux kernel, the following vulnerability has been resolved: hwmon: (w83792d) Fix NULL pointer dereference by removing unnecessary structure field If driver read val value sufficient for (val & 0x08) && (!(val & 0x80)) && ((val & 0x7) == ((val >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). [groeck: Dropped unnecessary continuation lines, fixed multipline alignment]
CVE-2021-47386: In the Linux kernel, the following vulnerability has been resolved: hwmon: (w83791d) Fix NULL pointer dereference by removing unnecessary structure field If driver read val value sufficient for (val & 0x08) && (!(val & 0x80)) && ((val & 0x7) == ((val >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). [groeck: Dropped unnecessary continuation lines, fixed multi-line alignment]
CVE-2021-47391: In the Linux kernel, the following vulnerability has been resolved: RDMA/cma: Ensure rdma_addr_cancel() happens before issuing more requests The FSM can run in a circle allowing rdma_resolve_ip() to be called twice on the same id_priv. While this cannot happen without going through the work, it violates the invariant that the same address resolution background request cannot be active twice. CPU 1 CPU 2 rdma_resolve_addr(): RDMA_CM_IDLE -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) #1 process_one_req(): for #1 addr_handler(): RDMA_CM_ADDR_QUERY -> RDMA_CM_ADDR_BOUND mutex_unlock(&id_priv->handler_mutex); [.. handler still running ..] rdma_resolve_addr(): RDMA_CM_ADDR_BOUND -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) !! two requests are now on the req_list rdma_destroy_id(): destroy_id_handler_unlock(): _destroy_id(): cma_cancel_operation(): rdma_addr_cancel() // process_one_req() self removes it spin_lock_bh(&lock); cancel_delayed_work(&req->work); if (!list_empty(&req->list)) == true ! rdma_addr_cancel() returns after process_on_req #1 is done kfree(id_priv) process_one_req(): for #2 addr_handler(): mutex_lock(&id_priv->handler_mutex); !! Use after free on id_priv rdma_addr_cancel() expects there to be one req on the list and only cancels the first one. The self-removal behavior of the work only happens after the handler has returned. This yields a situations where the req_list can have two reqs for the same "handle" but rdma_addr_cancel() only cancels the first one. The second req remains active beyond rdma_destroy_id() and will use-after-free id_priv once it inevitably triggers. Fix this by remembering if the id_priv has called rdma_resolve_ip() and always cancel before calling it again. This ensures the req_list never gets more than one item in it and doesn't cost anything in the normal flow that never uses this strange error path.
CVE-2021-47396: In the Linux kernel, the following vulnerability has been resolved: mac80211-hwsim: fix late beacon hrtimer handling Thomas explained in https://lore.kernel.org/r/87mtoeb4hb.ffs@tglx that our handling of the hrtimer here is wrong: If the timer fires late (e.g. due to vCPU scheduling, as reported by Dmitry/syzbot) then it tries to actually rearm the timer at the next deadline, which might be in the past already: 1 2 3 N N+1 | | | ... | | ^ intended to fire here (1) ^ next deadline here (2) ^ actually fired here The next time it fires, it's later, but will still try to schedule for the next deadline (now 3), etc. until it catches up with N, but that might take a long time, causing stalls etc. Now, all of this is simulation, so we just have to fix it, but note that the behaviour is wrong even per spec, since there's no value then in sending all those beacons unaligned - they should be aligned to the TBTT (1, 2, 3, ... in the picture), and if we're a bit (or a lot) late, then just resume at that point. Therefore, change the code to use hrtimer_forward_now() which will ensure that the next firing of the timer would be at N+1 (in the picture), i.e. the next interval point after the current time.
CVE-2021-47407: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Handle SRCU initialization failure during page track init Check the return of init_srcu_struct(), which can fail due to OOM, when initializing the page track mechanism. Lack of checking leads to a NULL pointer deref found by a modified syzkaller. [Move the call towards the beginning of kvm_arch_init_vm. - Paolo]
CVE-2021-47408: In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: serialize hash resizes and cleanups Syzbot was able to trigger the following warning [1] No repro found by syzbot yet but I was able to trigger similar issue by having 2 scripts running in parallel, changing conntrack hash sizes, and: for j in `seq 1 1000` ; do unshare -n /bin/true >/dev/null ; done It would take more than 5 minutes for net_namespace structures to be cleaned up. This is because nf_ct_iterate_cleanup() has to restart everytime a resize happened. By adding a mutex, we can serialize hash resizes and cleanups and also make get_next_corpse() faster by skipping over empty buckets. Even without resizes in the picture, this patch considerably speeds up network namespace dismantles. [1] INFO: task syz-executor.0:8312 can't die for more than 144 seconds. task:syz-executor.0 state:R running task stack:25672 pid: 8312 ppid: 6573 flags:0x00004006 Call Trace: context_switch kernel/sched/core.c:4955 [inline] __schedule+0x940/0x26f0 kernel/sched/core.c:6236 preempt_schedule_common+0x45/0xc0 kernel/sched/core.c:6408 preempt_schedule_thunk+0x16/0x18 arch/x86/entry/thunk_64.S:35 __local_bh_enable_ip+0x109/0x120 kernel/softirq.c:390 local_bh_enable include/linux/bottom_half.h:32 [inline] get_next_corpse net/netfilter/nf_conntrack_core.c:2252 [inline] nf_ct_iterate_cleanup+0x15a/0x450 net/netfilter/nf_conntrack_core.c:2275 nf_conntrack_cleanup_net_list+0x14c/0x4f0 net/netfilter/nf_conntrack_core.c:2469 ops_exit_list+0x10d/0x160 net/core/net_namespace.c:171 setup_net+0x639/0xa30 net/core/net_namespace.c:349 copy_net_ns+0x319/0x760 net/core/net_namespace.c:470 create_new_namespaces+0x3f6/0xb20 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc1/0x1f0 kernel/nsproxy.c:226 ksys_unshare+0x445/0x920 kernel/fork.c:3128 __do_sys_unshare kernel/fork.c:3202 [inline] __se_sys_unshare kernel/fork.c:3200 [inline] __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3200 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f63da68e739 RSP: 002b:00007f63d7c05188 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007f63da792f80 RCX: 00007f63da68e739 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000040000000 RBP: 00007f63da6e8cc4 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f63da792f80 R13: 00007fff50b75d3f R14: 00007f63d7c05300 R15: 0000000000022000 Showing all locks held in the system: 1 lock held by khungtaskd/27: #0: ffffffff8b980020 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x53/0x260 kernel/locking/lockdep.c:6446 2 locks held by kworker/u4:2/153: #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: arch_atomic_long_set include/linux/atomic/atomic-long.h:41 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: atomic_long_set include/linux/atomic/atomic-instrumented.h:1198 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: set_work_data kernel/workqueue.c:634 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: set_work_pool_and_clear_pending kernel/workqueue.c:661 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x896/0x1690 kernel/workqueue.c:2268 #1: ffffc9000140fdb0 ((kfence_timer).work){+.+.}-{0:0}, at: process_one_work+0x8ca/0x1690 kernel/workqueue.c:2272 1 lock held by systemd-udevd/2970: 1 lock held by in:imklog/6258: #0: ffff88807f970ff0 (&f->f_pos_lock){+.+.}-{3:3}, at: __fdget_pos+0xe9/0x100 fs/file.c:990 3 locks held by kworker/1:6/8158: 1 lock held by syz-executor.0/8312: 2 locks held by kworker/u4:13/9320: 1 lock held by ---truncated---
CVE-2021-47410: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: fix svm_migrate_fini warning Device manager releases device-specific resources when a driver disconnects from a device, devm_memunmap_pages and devm_release_mem_region calls in svm_migrate_fini are redundant. It causes below warning trace after patch "drm/amdgpu: Split amdgpu_device_fini into early and late", so remove function svm_migrate_fini. BUG: https://gitlab.freedesktop.org/drm/amd/-/issues/1718 WARNING: CPU: 1 PID: 3646 at drivers/base/devres.c:795 devm_release_action+0x51/0x60 Call Trace: ? memunmap_pages+0x360/0x360 svm_migrate_fini+0x2d/0x60 [amdgpu] kgd2kfd_device_exit+0x23/0xa0 [amdgpu] amdgpu_amdkfd_device_fini_sw+0x1d/0x30 [amdgpu] amdgpu_device_fini_sw+0x45/0x290 [amdgpu] amdgpu_driver_release_kms+0x12/0x30 [amdgpu] drm_dev_release+0x20/0x40 [drm] release_nodes+0x196/0x1e0 device_release_driver_internal+0x104/0x1d0 driver_detach+0x47/0x90 bus_remove_driver+0x7a/0xd0 pci_unregister_driver+0x3d/0x90 amdgpu_exit+0x11/0x20 [amdgpu]
CVE-2021-47412: In the Linux kernel, the following vulnerability has been resolved: block: don't call rq_qos_ops->done_bio if the bio isn't tracked rq_qos framework is only applied on request based driver, so: 1) rq_qos_done_bio() needn't to be called for bio based driver 2) rq_qos_done_bio() needn't to be called for bio which isn't tracked, such as bios ended from error handling code. Especially in bio_endio(): 1) request queue is referred via bio->bi_bdev->bd_disk->queue, which may be gone since request queue refcount may not be held in above two cases 2) q->rq_qos may be freed in blk_cleanup_queue() when calling into __rq_qos_done_bio() Fix the potential kernel panic by not calling rq_qos_ops->done_bio if the bio isn't tracked. This way is safe because both ioc_rqos_done_bio() and blkcg_iolatency_done_bio() are nop if the bio isn't tracked.
CVE-2021-47414: In the Linux kernel, the following vulnerability has been resolved: riscv: Flush current cpu icache before other cpus On SiFive Unmatched, I recently fell onto the following BUG when booting: [ 0.000000] ftrace: allocating 36610 entries in 144 pages [ 0.000000] Oops - illegal instruction [#1] [ 0.000000] Modules linked in: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 5.13.1+ #5 [ 0.000000] Hardware name: SiFive HiFive Unmatched A00 (DT) [ 0.000000] epc : riscv_cpuid_to_hartid_mask+0x6/0xae [ 0.000000] ra : __sbi_rfence_v02+0xc8/0x10a [ 0.000000] epc : ffffffff80007240 ra : ffffffff80009964 sp : ffffffff81803e10 [ 0.000000] gp : ffffffff81a1ea70 tp : ffffffff8180f500 t0 : ffffffe07fe30000 [ 0.000000] t1 : 0000000000000004 t2 : 0000000000000000 s0 : ffffffff81803e60 [ 0.000000] s1 : 0000000000000000 a0 : ffffffff81a22238 a1 : ffffffff81803e10 [ 0.000000] a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 [ 0.000000] a5 : 0000000000000000 a6 : ffffffff8000989c a7 : 0000000052464e43 [ 0.000000] s2 : ffffffff81a220c8 s3 : 0000000000000000 s4 : 0000000000000000 [ 0.000000] s5 : 0000000000000000 s6 : 0000000200000100 s7 : 0000000000000001 [ 0.000000] s8 : ffffffe07fe04040 s9 : ffffffff81a22c80 s10: 0000000000001000 [ 0.000000] s11: 0000000000000004 t3 : 0000000000000001 t4 : 0000000000000008 [ 0.000000] t5 : ffffffcf04000808 t6 : ffffffe3ffddf188 [ 0.000000] status: 0000000200000100 badaddr: 0000000000000000 cause: 0000000000000002 [ 0.000000] [<ffffffff80007240>] riscv_cpuid_to_hartid_mask+0x6/0xae [ 0.000000] [<ffffffff80009474>] sbi_remote_fence_i+0x1e/0x26 [ 0.000000] [<ffffffff8000b8f4>] flush_icache_all+0x12/0x1a [ 0.000000] [<ffffffff8000666c>] patch_text_nosync+0x26/0x32 [ 0.000000] [<ffffffff8000884e>] ftrace_init_nop+0x52/0x8c [ 0.000000] [<ffffffff800f051e>] ftrace_process_locs.isra.0+0x29c/0x360 [ 0.000000] [<ffffffff80a0e3c6>] ftrace_init+0x80/0x130 [ 0.000000] [<ffffffff80a00f8c>] start_kernel+0x5c4/0x8f6 [ 0.000000] ---[ end trace f67eb9af4d8d492b ]--- [ 0.000000] Kernel panic - not syncing: Attempted to kill the idle task! [ 0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]--- While ftrace is looping over a list of addresses to patch, it always failed when patching the same function: riscv_cpuid_to_hartid_mask. Looking at the backtrace, the illegal instruction is encountered in this same function. However, patch_text_nosync, after patching the instructions, calls flush_icache_range. But looking at what happens in this function: flush_icache_range -> flush_icache_all -> sbi_remote_fence_i -> __sbi_rfence_v02 -> riscv_cpuid_to_hartid_mask The icache and dcache of the current cpu are never synchronized between the patching of riscv_cpuid_to_hartid_mask and calling this same function. So fix this by flushing the current cpu's icache before asking for the other cpus to do the same.
CVE-2021-47431: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix gart.bo pin_count leak gmc_v{9,10}_0_gart_disable() isn't called matched with correspoding gart_enbale function in SRIOV case. This will lead to gart.bo pin_count leak on driver unload.
CVE-2021-47432: In the Linux kernel, the following vulnerability has been resolved: lib/generic-radix-tree.c: Don't overflow in peek() When we started spreading new inode numbers throughout most of the 64 bit inode space, that triggered some corner case bugs, in particular some integer overflows related to the radix tree code. Oops.
CVE-2021-47433: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix abort logic in btrfs_replace_file_extents Error injection testing uncovered a case where we'd end up with a corrupt file system with a missing extent in the middle of a file. This occurs because the if statement to decide if we should abort is wrong. The only way we would abort in this case is if we got a ret != -EOPNOTSUPP and we called from the file clone code. However the prealloc code uses this path too. Instead we need to abort if there is an error, and the only error we _don't_ abort on is -EOPNOTSUPP and only if we came from the clone file code.
CVE-2021-47438: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix memory leak in mlx5_core_destroy_cq() error path Prior to this patch in case mlx5_core_destroy_cq() failed it returns without completing all destroy operations and that leads to memory leak. Instead, complete the destroy flow before return error. Also move mlx5_debug_cq_remove() to the beginning of mlx5_core_destroy_cq() to be symmetrical with mlx5_core_create_cq(). kmemleak complains on: unreferenced object 0xc000000038625100 (size 64): comm "ethtool", pid 28301, jiffies 4298062946 (age 785.380s) hex dump (first 32 bytes): 60 01 48 94 00 00 00 c0 b8 05 34 c3 00 00 00 c0 `.H.......4..... 02 00 00 00 00 00 00 00 00 db 7d c1 00 00 00 c0 ..........}..... backtrace: [<000000009e8643cb>] add_res_tree+0xd0/0x270 [mlx5_core] [<00000000e7cb8e6c>] mlx5_debug_cq_add+0x5c/0xc0 [mlx5_core] [<000000002a12918f>] mlx5_core_create_cq+0x1d0/0x2d0 [mlx5_core] [<00000000cef0a696>] mlx5e_create_cq+0x210/0x3f0 [mlx5_core] [<000000009c642c26>] mlx5e_open_cq+0xb4/0x130 [mlx5_core] [<0000000058dfa578>] mlx5e_ptp_open+0x7f4/0xe10 [mlx5_core] [<0000000081839561>] mlx5e_open_channels+0x9cc/0x13e0 [mlx5_core] [<0000000009cf05d4>] mlx5e_switch_priv_channels+0xa4/0x230 [mlx5_core] [<0000000042bbedd8>] mlx5e_safe_switch_params+0x14c/0x300 [mlx5_core] [<0000000004bc9db8>] set_pflag_tx_port_ts+0x9c/0x160 [mlx5_core] [<00000000a0553443>] mlx5e_set_priv_flags+0xd0/0x1b0 [mlx5_core] [<00000000a8f3d84b>] ethnl_set_privflags+0x234/0x2d0 [<00000000fd27f27c>] genl_family_rcv_msg_doit+0x108/0x1d0 [<00000000f495e2bb>] genl_family_rcv_msg+0xe4/0x1f0 [<00000000646c5c2c>] genl_rcv_msg+0x78/0x120 [<00000000d53e384e>] netlink_rcv_skb+0x74/0x1a0
CVE-2021-47441: In the Linux kernel, the following vulnerability has been resolved: mlxsw: thermal: Fix out-of-bounds memory accesses Currently, mlxsw allows cooling states to be set above the maximum cooling state supported by the driver: # cat /sys/class/thermal/thermal_zone2/cdev0/type mlxsw_fan # cat /sys/class/thermal/thermal_zone2/cdev0/max_state 10 # echo 18 > /sys/class/thermal/thermal_zone2/cdev0/cur_state # echo $? 0 This results in out-of-bounds memory accesses when thermal state transition statistics are enabled (CONFIG_THERMAL_STATISTICS=y), as the transition table is accessed with a too large index (state) [1]. According to the thermal maintainer, it is the responsibility of the driver to reject such operations [2]. Therefore, return an error when the state to be set exceeds the maximum cooling state supported by the driver. To avoid dead code, as suggested by the thermal maintainer [3], partially revert commit a421ce088ac8 ("mlxsw: core: Extend cooling device with cooling levels") that tried to interpret these invalid cooling states (above the maximum) in a special way. The cooling levels array is not removed in order to prevent the fans going below 20% PWM, which would cause them to get stuck at 0% PWM. [1] BUG: KASAN: slab-out-of-bounds in thermal_cooling_device_stats_update+0x271/0x290 Read of size 4 at addr ffff8881052f7bf8 by task kworker/0:0/5 CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.15.0-rc3-custom-45935-gce1adf704b14 #122 Hardware name: Mellanox Technologies Ltd. "MSN2410-CB2FO"/"SA000874", BIOS 4.6.5 03/08/2016 Workqueue: events_freezable_power_ thermal_zone_device_check Call Trace: dump_stack_lvl+0x8b/0xb3 print_address_description.constprop.0+0x1f/0x140 kasan_report.cold+0x7f/0x11b thermal_cooling_device_stats_update+0x271/0x290 __thermal_cdev_update+0x15e/0x4e0 thermal_cdev_update+0x9f/0xe0 step_wise_throttle+0x770/0xee0 thermal_zone_device_update+0x3f6/0xdf0 process_one_work+0xa42/0x1770 worker_thread+0x62f/0x13e0 kthread+0x3ee/0x4e0 ret_from_fork+0x1f/0x30 Allocated by task 1: kasan_save_stack+0x1b/0x40 __kasan_kmalloc+0x7c/0x90 thermal_cooling_device_setup_sysfs+0x153/0x2c0 __thermal_cooling_device_register.part.0+0x25b/0x9c0 thermal_cooling_device_register+0xb3/0x100 mlxsw_thermal_init+0x5c5/0x7e0 __mlxsw_core_bus_device_register+0xcb3/0x19c0 mlxsw_core_bus_device_register+0x56/0xb0 mlxsw_pci_probe+0x54f/0x710 local_pci_probe+0xc6/0x170 pci_device_probe+0x2b2/0x4d0 really_probe+0x293/0xd10 __driver_probe_device+0x2af/0x440 driver_probe_device+0x51/0x1e0 __driver_attach+0x21b/0x530 bus_for_each_dev+0x14c/0x1d0 bus_add_driver+0x3ac/0x650 driver_register+0x241/0x3d0 mlxsw_sp_module_init+0xa2/0x174 do_one_initcall+0xee/0x5f0 kernel_init_freeable+0x45a/0x4de kernel_init+0x1f/0x210 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff8881052f7800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 1016 bytes inside of 1024-byte region [ffff8881052f7800, ffff8881052f7c00) The buggy address belongs to the page: page:0000000052355272 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1052f0 head:0000000052355272 order:3 compound_mapcount:0 compound_pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffffea0005034800 0000000300000003 ffff888100041dc0 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881052f7a80: 00 00 00 00 00 00 04 fc fc fc fc fc fc fc fc fc ffff8881052f7b00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff8881052f7b80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff8881052f7c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8881052f7c80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [2] https://lore.kernel.org/linux-pm/9aca37cb-1629-5c67- ---truncated---
CVE-2021-47455: In the Linux kernel, the following vulnerability has been resolved: ptp: Fix possible memory leak in ptp_clock_register() I got memory leak as follows when doing fault injection test: unreferenced object 0xffff88800906c618 (size 8): comm "i2c-idt82p33931", pid 4421, jiffies 4294948083 (age 13.188s) hex dump (first 8 bytes): 70 74 70 30 00 00 00 00 ptp0.... backtrace: [<00000000312ed458>] __kmalloc_track_caller+0x19f/0x3a0 [<0000000079f6e2ff>] kvasprintf+0xb5/0x150 [<0000000026aae54f>] kvasprintf_const+0x60/0x190 [<00000000f323a5f7>] kobject_set_name_vargs+0x56/0x150 [<000000004e35abdd>] dev_set_name+0xc0/0x100 [<00000000f20cfe25>] ptp_clock_register+0x9f4/0xd30 [ptp] [<000000008bb9f0de>] idt82p33_probe.cold+0x8b6/0x1561 [ptp_idt82p33] When posix_clock_register() returns an error, the name allocated in dev_set_name() will be leaked, the put_device() should be used to give up the device reference, then the name will be freed in kobject_cleanup() and other memory will be freed in ptp_clock_release().
CVE-2021-47466: In the Linux kernel, the following vulnerability has been resolved: mm, slub: fix potential memoryleak in kmem_cache_open() In error path, the random_seq of slub cache might be leaked. Fix this by using __kmem_cache_release() to release all the relevant resources.
CVE-2021-47467: In the Linux kernel, the following vulnerability has been resolved: kunit: fix reference count leak in kfree_at_end The reference counting issue happens in the normal path of kfree_at_end(). When kunit_alloc_and_get_resource() is invoked, the function forgets to handle the returned resource object, whose refcount increased inside, causing a refcount leak. Fix this issue by calling kunit_alloc_resource() instead of kunit_alloc_and_get_resource(). Fixed the following when applying: Shuah Khan <skhan@linuxfoundation.org> CHECK: Alignment should match open parenthesis + kunit_alloc_resource(test, NULL, kfree_res_free, GFP_KERNEL, (void *)to_free);
CVE-2021-47469: In the Linux kernel, the following vulnerability has been resolved: spi: Fix deadlock when adding SPI controllers on SPI buses Currently we have a global spi_add_lock which we take when adding new devices so that we can check that we're not trying to reuse a chip select that's already controlled. This means that if the SPI device is itself a SPI controller and triggers the instantiation of further SPI devices we trigger a deadlock as we try to register and instantiate those devices while in the process of doing so for the parent controller and hence already holding the global spi_add_lock. Since we only care about concurrency within a single SPI bus move the lock to be per controller, avoiding the deadlock. This can be easily triggered in the case of spi-mux.
CVE-2021-47473: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix a memory leak in an error path of qla2x00_process_els() Commit 8c0eb596baa5 ("[SCSI] qla2xxx: Fix a memory leak in an error path of qla2x00_process_els()"), intended to change: bsg_job->request->msgcode == FC_BSG_HST_ELS_NOLOGIN bsg_job->request->msgcode != FC_BSG_RPT_ELS but changed it to: bsg_job->request->msgcode == FC_BSG_RPT_ELS instead. Change the == to a != to avoid leaking the fcport structure or freeing unallocated memory.
CVE-2021-47479: In the Linux kernel, the following vulnerability has been resolved: staging: rtl8712: fix use-after-free in rtl8712_dl_fw Syzbot reported use-after-free in rtl8712_dl_fw(). The problem was in race condition between r871xu_dev_remove() ->ndo_open() callback. It's easy to see from crash log, that driver accesses released firmware in ->ndo_open() callback. It may happen, since driver was releasing firmware _before_ unregistering netdev. Fix it by moving unregister_netdev() before cleaning up resources. Call Trace: ... rtl871x_open_fw drivers/staging/rtl8712/hal_init.c:83 [inline] rtl8712_dl_fw+0xd95/0xe10 drivers/staging/rtl8712/hal_init.c:170 rtl8712_hal_init drivers/staging/rtl8712/hal_init.c:330 [inline] rtl871x_hal_init+0xae/0x180 drivers/staging/rtl8712/hal_init.c:394 netdev_open+0xe6/0x6c0 drivers/staging/rtl8712/os_intfs.c:380 __dev_open+0x2bc/0x4d0 net/core/dev.c:1484 Freed by task 1306: ... release_firmware+0x1b/0x30 drivers/base/firmware_loader/main.c:1053 r871xu_dev_remove+0xcc/0x2c0 drivers/staging/rtl8712/usb_intf.c:599 usb_unbind_interface+0x1d8/0x8d0 drivers/usb/core/driver.c:458
CVE-2021-47490: In the Linux kernel, the following vulnerability has been resolved: drm/ttm: fix memleak in ttm_transfered_destroy We need to cleanup the fences for ghost objects as well. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=214029 Bug: https://bugzilla.kernel.org/show_bug.cgi?id=214447
CVE-2021-47493: In the Linux kernel, the following vulnerability has been resolved: ocfs2: fix race between searching chunks and release journal_head from buffer_head Encountered a race between ocfs2_test_bg_bit_allocatable() and jbd2_journal_put_journal_head() resulting in the below vmcore. PID: 106879 TASK: ffff880244ba9c00 CPU: 2 COMMAND: "loop3" Call trace: panic oops_end no_context __bad_area_nosemaphore bad_area_nosemaphore __do_page_fault do_page_fault page_fault [exception RIP: ocfs2_block_group_find_clear_bits+316] ocfs2_block_group_find_clear_bits [ocfs2] ocfs2_cluster_group_search [ocfs2] ocfs2_search_chain [ocfs2] ocfs2_claim_suballoc_bits [ocfs2] __ocfs2_claim_clusters [ocfs2] ocfs2_claim_clusters [ocfs2] ocfs2_local_alloc_slide_window [ocfs2] ocfs2_reserve_local_alloc_bits [ocfs2] ocfs2_reserve_clusters_with_limit [ocfs2] ocfs2_reserve_clusters [ocfs2] ocfs2_lock_refcount_allocators [ocfs2] ocfs2_make_clusters_writable [ocfs2] ocfs2_replace_cow [ocfs2] ocfs2_refcount_cow [ocfs2] ocfs2_file_write_iter [ocfs2] lo_rw_aio loop_queue_work kthread_worker_fn kthread ret_from_fork When ocfs2_test_bg_bit_allocatable() called bh2jh(bg_bh), the bg_bh->b_private NULL as jbd2_journal_put_journal_head() raced and released the jounal head from the buffer head. Needed to take bit lock for the bit 'BH_JournalHead' to fix this race.
CVE-2021-47496: In the Linux kernel, the following vulnerability has been resolved: net/tls: Fix flipped sign in tls_err_abort() calls sk->sk_err appears to expect a positive value, a convention that ktls doesn't always follow and that leads to memory corruption in other code. For instance, [kworker] tls_encrypt_done(..., err=<negative error from crypto request>) tls_err_abort(.., err) sk->sk_err = err; [task] splice_from_pipe_feed ... tls_sw_do_sendpage if (sk->sk_err) { ret = -sk->sk_err; // ret is positive splice_from_pipe_feed (continued) ret = actor(...) // ret is still positive and interpreted as bytes // written, resulting in underflow of buf->len and // sd->len, leading to huge buf->offset and bogus // addresses computed in later calls to actor() Fix all tls_err_abort() callers to pass a negative error code consistently and centralize the error-prone sign flip there, throwing in a warning to catch future misuse and uninlining the function so it really does only warn once.
CVE-2021-47498: In the Linux kernel, the following vulnerability has been resolved: dm rq: don't queue request to blk-mq during DM suspend DM uses blk-mq's quiesce/unquiesce to stop/start device mapper queue. But blk-mq's unquiesce may come from outside events, such as elevator switch, updating nr_requests or others, and request may come during suspend, so simply ask for blk-mq to requeue it. Fixes one kernel panic issue when running updating nr_requests and dm-mpath suspend/resume stress test.
CVE-2021-47501: In the Linux kernel, the following vulnerability has been resolved: i40e: Fix NULL pointer dereference in i40e_dbg_dump_desc When trying to dump VFs VSI RX/TX descriptors using debugfs there was a crash due to NULL pointer dereference in i40e_dbg_dump_desc. Added a check to i40e_dbg_dump_desc that checks if VSI type is correct for dumping RX/TX descriptors.
CVE-2021-47504: In the Linux kernel, the following vulnerability has been resolved: io_uring: ensure task_work gets run as part of cancelations If we successfully cancel a work item but that work item needs to be processed through task_work, then we can be sleeping uninterruptibly in io_uring_cancel_generic() and never process it. Hence we don't make forward progress and we end up with an uninterruptible sleep warning. While in there, correct a comment that should be IFF, not IIF.
CVE-2021-47508: In the Linux kernel, the following vulnerability has been resolved: btrfs: free exchange changeset on failures Fstests runs on my VMs have show several kmemleak reports like the following. unreferenced object 0xffff88811ae59080 (size 64): comm "xfs_io", pid 12124, jiffies 4294987392 (age 6.368s) hex dump (first 32 bytes): 00 c0 1c 00 00 00 00 00 ff cf 1c 00 00 00 00 00 ................ 90 97 e5 1a 81 88 ff ff 90 97 e5 1a 81 88 ff ff ................ backtrace: [<00000000ac0176d2>] ulist_add_merge+0x60/0x150 [btrfs] [<0000000076e9f312>] set_state_bits+0x86/0xc0 [btrfs] [<0000000014fe73d6>] set_extent_bit+0x270/0x690 [btrfs] [<000000004f675208>] set_record_extent_bits+0x19/0x20 [btrfs] [<00000000b96137b1>] qgroup_reserve_data+0x274/0x310 [btrfs] [<0000000057e9dcbb>] btrfs_check_data_free_space+0x5c/0xa0 [btrfs] [<0000000019c4511d>] btrfs_delalloc_reserve_space+0x1b/0xa0 [btrfs] [<000000006d37e007>] btrfs_dio_iomap_begin+0x415/0x970 [btrfs] [<00000000fb8a74b8>] iomap_iter+0x161/0x1e0 [<0000000071dff6ff>] __iomap_dio_rw+0x1df/0x700 [<000000002567ba53>] iomap_dio_rw+0x5/0x20 [<0000000072e555f8>] btrfs_file_write_iter+0x290/0x530 [btrfs] [<000000005eb3d845>] new_sync_write+0x106/0x180 [<000000003fb505bf>] vfs_write+0x24d/0x2f0 [<000000009bb57d37>] __x64_sys_pwrite64+0x69/0xa0 [<000000003eba3fdf>] do_syscall_64+0x43/0x90 In case brtfs_qgroup_reserve_data() or btrfs_delalloc_reserve_metadata() fail the allocated extent_changeset will not be freed. So in btrfs_check_data_free_space() and btrfs_delalloc_reserve_space() free the allocated extent_changeset to get rid of the allocated memory. The issue currently only happens in the direct IO write path, but only after 65b3c08606e5 ("btrfs: fix ENOSPC failure when attempting direct IO write into NOCOW range"), and also at defrag_one_locked_target(). Every other place is always calling extent_changeset_free() even if its call to btrfs_delalloc_reserve_space() or btrfs_check_data_free_space() has failed.
CVE-2021-47522: In the Linux kernel, the following vulnerability has been resolved: HID: bigbenff: prevent null pointer dereference When emulating the device through uhid, there is a chance we don't have output reports and so report_field is null.
CVE-2021-47523: In the Linux kernel, the following vulnerability has been resolved: IB/hfi1: Fix leak of rcvhdrtail_dummy_kvaddr This buffer is currently allocated in hfi1_init(): if (reinit) ret = init_after_reset(dd); else ret = loadtime_init(dd); if (ret) goto done; /* allocate dummy tail memory for all receive contexts */ dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64), &dd->rcvhdrtail_dummy_dma, GFP_KERNEL); if (!dd->rcvhdrtail_dummy_kvaddr) { dd_dev_err(dd, "cannot allocate dummy tail memory\n"); ret = -ENOMEM; goto done; } The reinit triggered path will overwrite the old allocation and leak it. Fix by moving the allocation to hfi1_alloc_devdata() and the deallocation to hfi1_free_devdata().
CVE-2021-47544: In the Linux kernel, the following vulnerability has been resolved: tcp: fix page frag corruption on page fault Steffen reported a TCP stream corruption for HTTP requests served by the apache web-server using a cifs mount-point and memory mapping the relevant file. The root cause is quite similar to the one addressed by commit 20eb4f29b602 ("net: fix sk_page_frag() recursion from memory reclaim"). Here the nested access to the task page frag is caused by a page fault on the (mmapped) user-space memory buffer coming from the cifs file. The page fault handler performs an smb transaction on a different socket, inside the same process context. Since sk->sk_allaction for such socket does not prevent the usage for the task_frag, the nested allocation modify "under the hood" the page frag in use by the outer sendmsg call, corrupting the stream. The overall relevant stack trace looks like the following: httpd 78268 [001] 3461630.850950: probe:tcp_sendmsg_locked: ffffffff91461d91 tcp_sendmsg_locked+0x1 ffffffff91462b57 tcp_sendmsg+0x27 ffffffff9139814e sock_sendmsg+0x3e ffffffffc06dfe1d smb_send_kvec+0x28 [...] ffffffffc06cfaf8 cifs_readpages+0x213 ffffffff90e83c4b read_pages+0x6b ffffffff90e83f31 __do_page_cache_readahead+0x1c1 ffffffff90e79e98 filemap_fault+0x788 ffffffff90eb0458 __do_fault+0x38 ffffffff90eb5280 do_fault+0x1a0 ffffffff90eb7c84 __handle_mm_fault+0x4d4 ffffffff90eb8093 handle_mm_fault+0xc3 ffffffff90c74f6d __do_page_fault+0x1ed ffffffff90c75277 do_page_fault+0x37 ffffffff9160111e page_fault+0x1e ffffffff9109e7b5 copyin+0x25 ffffffff9109eb40 _copy_from_iter_full+0xe0 ffffffff91462370 tcp_sendmsg_locked+0x5e0 ffffffff91462370 tcp_sendmsg_locked+0x5e0 ffffffff91462b57 tcp_sendmsg+0x27 ffffffff9139815c sock_sendmsg+0x4c ffffffff913981f7 sock_write_iter+0x97 ffffffff90f2cc56 do_iter_readv_writev+0x156 ffffffff90f2dff0 do_iter_write+0x80 ffffffff90f2e1c3 vfs_writev+0xa3 ffffffff90f2e27c do_writev+0x5c ffffffff90c042bb do_syscall_64+0x5b ffffffff916000ad entry_SYSCALL_64_after_hwframe+0x65 The cifs filesystem rightfully sets sk_allocations to GFP_NOFS, we can avoid the nesting using the sk page frag for allocation lacking the __GFP_FS flag. Do not define an additional mm-helper for that, as this is strictly tied to the sk page frag usage. v1 -> v2: - use a stricted sk_page_frag() check instead of reordering the code (Eric)
CVE-2021-47550: In the Linux kernel, the following vulnerability has been resolved: drm/amd/amdgpu: fix potential memleak In function amdgpu_get_xgmi_hive, when kobject_init_and_add failed There is a potential memleak if not call kobject_put.
CVE-2021-47551: In the Linux kernel, the following vulnerability has been resolved: drm/amd/amdkfd: Fix kernel panic when reset failed and been triggered again In SRIOV configuration, the reset may failed to bring asic back to normal but stop cpsch already been called, the start_cpsch will not be called since there is no resume in this case. When reset been triggered again, driver should avoid to do uninitialization again.
CVE-2021-47552: In the Linux kernel, the following vulnerability has been resolved: blk-mq: cancel blk-mq dispatch work in both blk_cleanup_queue and disk_release() For avoiding to slow down queue destroy, we don't call blk_mq_quiesce_queue() in blk_cleanup_queue(), instead of delaying to cancel dispatch work in blk_release_queue(). However, this way has caused kernel oops[1], reported by Changhui. The log shows that scsi_device can be freed before running blk_release_queue(), which is expected too since scsi_device is released after the scsi disk is closed and the scsi_device is removed. Fixes the issue by canceling blk-mq dispatch work in both blk_cleanup_queue() and disk_release(): 1) when disk_release() is run, the disk has been closed, and any sync dispatch activities have been done, so canceling dispatch work is enough to quiesce filesystem I/O dispatch activity. 2) in blk_cleanup_queue(), we only focus on passthrough request, and passthrough request is always explicitly allocated & freed by its caller, so once queue is frozen, all sync dispatch activity for passthrough request has been done, then it is enough to just cancel dispatch work for avoiding any dispatch activity. [1] kernel panic log [12622.769416] BUG: kernel NULL pointer dereference, address: 0000000000000300 [12622.777186] #PF: supervisor read access in kernel mode [12622.782918] #PF: error_code(0x0000) - not-present page [12622.788649] PGD 0 P4D 0 [12622.791474] Oops: 0000 [#1] PREEMPT SMP PTI [12622.796138] CPU: 10 PID: 744 Comm: kworker/10:1H Kdump: loaded Not tainted 5.15.0+ #1 [12622.804877] Hardware name: Dell Inc. PowerEdge R730/0H21J3, BIOS 1.5.4 10/002/2015 [12622.813321] Workqueue: kblockd blk_mq_run_work_fn [12622.818572] RIP: 0010:sbitmap_get+0x75/0x190 [12622.823336] Code: 85 80 00 00 00 41 8b 57 08 85 d2 0f 84 b1 00 00 00 45 31 e4 48 63 cd 48 8d 1c 49 48 c1 e3 06 49 03 5f 10 4c 8d 6b 40 83 f0 01 <48> 8b 33 44 89 f2 4c 89 ef 0f b6 c8 e8 fa f3 ff ff 83 f8 ff 75 58 [12622.844290] RSP: 0018:ffffb00a446dbd40 EFLAGS: 00010202 [12622.850120] RAX: 0000000000000001 RBX: 0000000000000300 RCX: 0000000000000004 [12622.858082] RDX: 0000000000000006 RSI: 0000000000000082 RDI: ffffa0b7a2dfe030 [12622.866042] RBP: 0000000000000004 R08: 0000000000000001 R09: ffffa0b742721334 [12622.874003] R10: 0000000000000008 R11: 0000000000000008 R12: 0000000000000000 [12622.881964] R13: 0000000000000340 R14: 0000000000000000 R15: ffffa0b7a2dfe030 [12622.889926] FS: 0000000000000000(0000) GS:ffffa0baafb40000(0000) knlGS:0000000000000000 [12622.898956] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12622.905367] CR2: 0000000000000300 CR3: 0000000641210001 CR4: 00000000001706e0 [12622.913328] Call Trace: [12622.916055] <TASK> [12622.918394] scsi_mq_get_budget+0x1a/0x110 [12622.922969] __blk_mq_do_dispatch_sched+0x1d4/0x320 [12622.928404] ? pick_next_task_fair+0x39/0x390 [12622.933268] __blk_mq_sched_dispatch_requests+0xf4/0x140 [12622.939194] blk_mq_sched_dispatch_requests+0x30/0x60 [12622.944829] __blk_mq_run_hw_queue+0x30/0xa0 [12622.949593] process_one_work+0x1e8/0x3c0 [12622.954059] worker_thread+0x50/0x3b0 [12622.958144] ? rescuer_thread+0x370/0x370 [12622.962616] kthread+0x158/0x180 [12622.966218] ? set_kthread_struct+0x40/0x40 [12622.970884] ret_from_fork+0x22/0x30 [12622.974875] </TASK> [12622.977309] Modules linked in: scsi_debug rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs sunrpc dm_multipath intel_rapl_msr intel_rapl_common dell_wmi_descriptor sb_edac rfkill video x86_pkg_temp_thermal intel_powerclamp dcdbas coretemp kvm_intel kvm mgag200 irqbypass i2c_algo_bit rapl drm_kms_helper ipmi_ssif intel_cstate intel_uncore syscopyarea sysfillrect sysimgblt fb_sys_fops pcspkr cec mei_me lpc_ich mei ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sr_mod cdrom sd_mod t10_pi sg ixgbe ahci libahci crct10dif_pclmul crc32_pclmul crc32c_intel libata megaraid_sas ghash_clmulni_intel tg3 wdat_w ---truncated---
CVE-2021-47559: In the Linux kernel, the following vulnerability has been resolved: net/smc: Fix NULL pointer dereferencing in smc_vlan_by_tcpsk() Coverity reports a possible NULL dereferencing problem: in smc_vlan_by_tcpsk(): 6. returned_null: netdev_lower_get_next returns NULL (checked 29 out of 30 times). 7. var_assigned: Assigning: ndev = NULL return value from netdev_lower_get_next. 1623 ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); CID 1468509 (#1 of 1): Dereference null return value (NULL_RETURNS) 8. dereference: Dereferencing a pointer that might be NULL ndev when calling is_vlan_dev. 1624 if (is_vlan_dev(ndev)) { Remove the manual implementation and use netdev_walk_all_lower_dev() to iterate over the lower devices. While on it remove an obsolete function parameter comment.
CVE-2021-47577: In the Linux kernel, the following vulnerability has been resolved: io-wq: check for wq exit after adding new worker task_work We check IO_WQ_BIT_EXIT before attempting to create a new worker, and wq exit cancels pending work if we have any. But it's possible to have a race between the two, where creation checks exit finding it not set, but we're in the process of exiting. The exit side will cancel pending creation task_work, but there's a gap where we add task_work after we've canceled existing creations at exit time. Fix this by checking the EXIT bit post adding the creation task_work. If it's set, run the same cancelation that exit does.
CVE-2021-47578: In the Linux kernel, the following vulnerability has been resolved: scsi: scsi_debug: Don't call kcalloc() if size arg is zero If the size arg to kcalloc() is zero, it returns ZERO_SIZE_PTR. Because of that, for a following NULL pointer check to work on the returned pointer, kcalloc() must not be called with the size arg equal to zero. Return early without error before the kcalloc() call if size arg is zero. BUG: KASAN: null-ptr-deref in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: null-ptr-deref in sg_copy_buffer+0x138/0x240 lib/scatterlist.c:974 Write of size 4 at addr 0000000000000010 by task syz-executor.1/22789 CPU: 1 PID: 22789 Comm: syz-executor.1 Not tainted 5.15.0-syzk #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 __kasan_report mm/kasan/report.c:446 [inline] kasan_report.cold.14+0x112/0x117 mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x1a3/0x210 mm/kasan/generic.c:189 memcpy+0x3b/0x60 mm/kasan/shadow.c:66 memcpy include/linux/fortify-string.h:191 [inline] sg_copy_buffer+0x138/0x240 lib/scatterlist.c:974 do_dout_fetch drivers/scsi/scsi_debug.c:2954 [inline] do_dout_fetch drivers/scsi/scsi_debug.c:2946 [inline] resp_verify+0x49e/0x930 drivers/scsi/scsi_debug.c:4276 schedule_resp+0x4d8/0x1a70 drivers/scsi/scsi_debug.c:5478 scsi_debug_queuecommand+0x8c9/0x1ec0 drivers/scsi/scsi_debug.c:7533 scsi_dispatch_cmd drivers/scsi/scsi_lib.c:1520 [inline] scsi_queue_rq+0x16b0/0x2d40 drivers/scsi/scsi_lib.c:1699 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1639 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1761 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1838 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:62 blk_execute_rq+0xdb/0x360 block/blk-exec.c:102 sg_scsi_ioctl drivers/scsi/scsi_ioctl.c:621 [inline] scsi_ioctl+0x8bb/0x15c0 drivers/scsi/scsi_ioctl.c:930 sg_ioctl_common+0x172d/0x2710 drivers/scsi/sg.c:1112 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1165 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2021-47580: In the Linux kernel, the following vulnerability has been resolved: scsi: scsi_debug: Fix type in min_t to avoid stack OOB Change min_t() to use type "u32" instead of type "int" to avoid stack out of bounds. With min_t() type "int" the values get sign extended and the larger value gets used causing stack out of bounds. BUG: KASAN: stack-out-of-bounds in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: stack-out-of-bounds in sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 Read of size 127 at addr ffff888072607128 by task syz-executor.7/18707 CPU: 1 PID: 18707 Comm: syz-executor.7 Not tainted 5.15.0-syzk #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x1a3/0x210 mm/kasan/generic.c:189 memcpy+0x23/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 sg_copy_from_buffer+0x33/0x40 lib/scatterlist.c:1000 fill_from_dev_buffer.part.34+0x82/0x130 drivers/scsi/scsi_debug.c:1162 fill_from_dev_buffer drivers/scsi/scsi_debug.c:1888 [inline] resp_readcap16+0x365/0x3b0 drivers/scsi/scsi_debug.c:1887 schedule_resp+0x4d8/0x1a70 drivers/scsi/scsi_debug.c:5478 scsi_debug_queuecommand+0x8c9/0x1ec0 drivers/scsi/scsi_debug.c:7533 scsi_dispatch_cmd drivers/scsi/scsi_lib.c:1520 [inline] scsi_queue_rq+0x16b0/0x2d40 drivers/scsi/scsi_lib.c:1699 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1639 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1761 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1838 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:62 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:836 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:774 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:939 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1165 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
CVE-2021-47582: In the Linux kernel, the following vulnerability has been resolved: USB: core: Make do_proc_control() and do_proc_bulk() killable The USBDEVFS_CONTROL and USBDEVFS_BULK ioctls invoke usb_start_wait_urb(), which contains an uninterruptible wait with a user-specified timeout value. If timeout value is very large and the device being accessed does not respond in a reasonable amount of time, the kernel will complain about "Task X blocked for more than N seconds", as found in testing by syzbot: INFO: task syz-executor.0:8700 blocked for more than 143 seconds. Not tainted 5.14.0-rc7-syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor.0 state:D stack:23192 pid: 8700 ppid: 8455 flags:0x00004004 Call Trace: context_switch kernel/sched/core.c:4681 [inline] __schedule+0xc07/0x11f0 kernel/sched/core.c:5938 schedule+0x14b/0x210 kernel/sched/core.c:6017 schedule_timeout+0x98/0x2f0 kernel/time/timer.c:1857 do_wait_for_common+0x2da/0x480 kernel/sched/completion.c:85 __wait_for_common kernel/sched/completion.c:106 [inline] wait_for_common kernel/sched/completion.c:117 [inline] wait_for_completion_timeout+0x46/0x60 kernel/sched/completion.c:157 usb_start_wait_urb+0x167/0x550 drivers/usb/core/message.c:63 do_proc_bulk+0x978/0x1080 drivers/usb/core/devio.c:1236 proc_bulk drivers/usb/core/devio.c:1273 [inline] usbdev_do_ioctl drivers/usb/core/devio.c:2547 [inline] usbdev_ioctl+0x3441/0x6b10 drivers/usb/core/devio.c:2713 ... To fix this problem, this patch replaces usbfs's calls to usb_control_msg() and usb_bulk_msg() with special-purpose code that does essentially the same thing (as recommended in the comment for usb_start_wait_urb()), except that it always uses a killable wait and it uses GFP_KERNEL rather than GFP_NOIO.
CVE-2021-47597: In the Linux kernel, the following vulnerability has been resolved: inet_diag: fix kernel-infoleak for UDP sockets KMSAN reported a kernel-infoleak [1], that can exploited by unpriv users. After analysis it turned out UDP was not initializing r->idiag_expires. Other users of inet_sk_diag_fill() might make the same mistake in the future, so fix this in inet_sk_diag_fill(). [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:156 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 instrument_copy_to_user include/linux/instrumented.h:121 [inline] copyout lib/iov_iter.c:156 [inline] _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 copy_to_iter include/linux/uio.h:155 [inline] simple_copy_to_iter+0xf3/0x140 net/core/datagram.c:519 __skb_datagram_iter+0x2cb/0x1280 net/core/datagram.c:425 skb_copy_datagram_iter+0xdc/0x270 net/core/datagram.c:533 skb_copy_datagram_msg include/linux/skbuff.h:3657 [inline] netlink_recvmsg+0x660/0x1c60 net/netlink/af_netlink.c:1974 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] new_sync_read fs/read_write.c:400 [inline] vfs_read+0x1631/0x1980 fs/read_write.c:481 ksys_read+0x28c/0x520 fs/read_write.c:619 __do_sys_read fs/read_write.c:629 [inline] __se_sys_read fs/read_write.c:627 [inline] __x64_sys_read+0xdb/0x120 fs/read_write.c:627 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was created at: slab_post_alloc_hook mm/slab.h:524 [inline] slab_alloc_node mm/slub.c:3251 [inline] __kmalloc_node_track_caller+0xe0c/0x1510 mm/slub.c:4974 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1126 [inline] netlink_dump+0x3d5/0x16a0 net/netlink/af_netlink.c:2245 __netlink_dump_start+0xd1c/0xee0 net/netlink/af_netlink.c:2370 netlink_dump_start include/linux/netlink.h:254 [inline] inet_diag_handler_cmd+0x2e7/0x400 net/ipv4/inet_diag.c:1343 sock_diag_rcv_msg+0x24a/0x620 netlink_rcv_skb+0x447/0x800 net/netlink/af_netlink.c:2491 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:276 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x1095/0x1360 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x16f3/0x1870 net/netlink/af_netlink.c:1916 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] sock_write_iter+0x594/0x690 net/socket.c:1057 do_iter_readv_writev+0xa7f/0xc70 do_iter_write+0x52c/0x1500 fs/read_write.c:851 vfs_writev fs/read_write.c:924 [inline] do_writev+0x63f/0xe30 fs/read_write.c:967 __do_sys_writev fs/read_write.c:1040 [inline] __se_sys_writev fs/read_write.c:1037 [inline] __x64_sys_writev+0xe5/0x120 fs/read_write.c:1037 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Bytes 68-71 of 312 are uninitialized Memory access of size 312 starts at ffff88812ab54000 Data copied to user address 0000000020001440 CPU: 1 PID: 6365 Comm: syz-executor801 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
CVE-2021-47599: In the Linux kernel, the following vulnerability has been resolved: btrfs: use latest_dev in btrfs_show_devname The test case btrfs/238 reports the warning below: WARNING: CPU: 3 PID: 481 at fs/btrfs/super.c:2509 btrfs_show_devname+0x104/0x1e8 [btrfs] CPU: 2 PID: 1 Comm: systemd Tainted: G W O 5.14.0-rc1-custom #72 Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: btrfs_show_devname+0x108/0x1b4 [btrfs] show_mountinfo+0x234/0x2c4 m_show+0x28/0x34 seq_read_iter+0x12c/0x3c4 vfs_read+0x29c/0x2c8 ksys_read+0x80/0xec __arm64_sys_read+0x28/0x34 invoke_syscall+0x50/0xf8 do_el0_svc+0x88/0x138 el0_svc+0x2c/0x8c el0t_64_sync_handler+0x84/0xe4 el0t_64_sync+0x198/0x19c Reason: While btrfs_prepare_sprout() moves the fs_devices::devices into fs_devices::seed_list, the btrfs_show_devname() searches for the devices and found none, leading to the warning as in above. Fix: latest_dev is updated according to the changes to the device list. That means we could use the latest_dev->name to show the device name in /proc/self/mounts, the pointer will be always valid as it's assigned before the device is deleted from the list in remove or replace. The RCU protection is sufficient as the device structure is freed after synchronization.
CVE-2021-47610: In the Linux kernel, the following vulnerability has been resolved: drm/msm: Fix null ptr access msm_ioctl_gem_submit() Fix the below null pointer dereference in msm_ioctl_gem_submit(): 26545.260705: Call trace: 26545.263223: kref_put+0x1c/0x60 26545.266452: msm_ioctl_gem_submit+0x254/0x744 26545.270937: drm_ioctl_kernel+0xa8/0x124 26545.274976: drm_ioctl+0x21c/0x33c 26545.278478: drm_compat_ioctl+0xdc/0xf0 26545.282428: __arm64_compat_sys_ioctl+0xc8/0x100 26545.287169: el0_svc_common+0xf8/0x250 26545.291025: do_el0_svc_compat+0x28/0x54 26545.295066: el0_svc_compat+0x10/0x1c 26545.298838: el0_sync_compat_handler+0xa8/0xcc 26545.303403: el0_sync_compat+0x188/0x1c0 26545.307445: Code: d503201f d503201f 52800028 4b0803e8 (b8680008) 26545.318799: Kernel panic - not syncing: Oops: Fatal exception
CVE-2021-47618: In the Linux kernel, the following vulnerability has been resolved: ARM: 9170/1: fix panic when kasan and kprobe are enabled arm32 uses software to simulate the instruction replaced by kprobe. some instructions may be simulated by constructing assembly functions. therefore, before executing instruction simulation, it is necessary to construct assembly function execution environment in C language through binding registers. after kasan is enabled, the register binding relationship will be destroyed, resulting in instruction simulation errors and causing kernel panic. the kprobe emulate instruction function is distributed in three files: actions-common.c actions-arm.c actions-thumb.c, so disable KASAN when compiling these files. for example, use kprobe insert on cap_capable+20 after kasan enabled, the cap_capable assembly code is as follows: <cap_capable>: e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} e1a05000 mov r5, r0 e280006c add r0, r0, #108 ; 0x6c e1a04001 mov r4, r1 e1a06002 mov r6, r2 e59fa090 ldr sl, [pc, #144] ; ebfc7bf8 bl c03aa4b4 <__asan_load4> e595706c ldr r7, [r5, #108] ; 0x6c e2859014 add r9, r5, #20 ...... The emulate_ldr assembly code after enabling kasan is as follows: c06f1384 <emulate_ldr>: e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} e282803c add r8, r2, #60 ; 0x3c e1a05000 mov r5, r0 e7e37855 ubfx r7, r5, #16, #4 e1a00008 mov r0, r8 e1a09001 mov r9, r1 e1a04002 mov r4, r2 ebf35462 bl c03c6530 <__asan_load4> e357000f cmp r7, #15 e7e36655 ubfx r6, r5, #12, #4 e205a00f and sl, r5, #15 0a000001 beq c06f13bc <emulate_ldr+0x38> e0840107 add r0, r4, r7, lsl #2 ebf3545c bl c03c6530 <__asan_load4> e084010a add r0, r4, sl, lsl #2 ebf3545a bl c03c6530 <__asan_load4> e2890010 add r0, r9, #16 ebf35458 bl c03c6530 <__asan_load4> e5990010 ldr r0, [r9, #16] e12fff30 blx r0 e356000f cm r6, #15 1a000014 bne c06f1430 <emulate_ldr+0xac> e1a06000 mov r6, r0 e2840040 add r0, r4, #64 ; 0x40 ...... when running in emulate_ldr to simulate the ldr instruction, panic occurred, and the log is as follows: Unable to handle kernel NULL pointer dereference at virtual address 00000090 pgd = ecb46400 [00000090] *pgd=2e0fa003, *pmd=00000000 Internal error: Oops: 206 [#1] SMP ARM PC is at cap_capable+0x14/0xb0 LR is at emulate_ldr+0x50/0xc0 psr: 600d0293 sp : ecd63af8 ip : 00000004 fp : c0a7c30c r10: 00000000 r9 : c30897f4 r8 : ecd63cd4 r7 : 0000000f r6 : 0000000a r5 : e59fa090 r4 : ecd63c98 r3 : c06ae294 r2 : 00000000 r1 : b7611300 r0 : bf4ec008 Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment user Control: 32c5387d Table: 2d546400 DAC: 55555555 Process bash (pid: 1643, stack limit = 0xecd60190) (cap_capable) from (kprobe_handler+0x218/0x340) (kprobe_handler) from (kprobe_trap_handler+0x24/0x48) (kprobe_trap_handler) from (do_undefinstr+0x13c/0x364) (do_undefinstr) from (__und_svc_finish+0x0/0x30) (__und_svc_finish) from (cap_capable+0x18/0xb0) (cap_capable) from (cap_vm_enough_memory+0x38/0x48) (cap_vm_enough_memory) from (security_vm_enough_memory_mm+0x48/0x6c) (security_vm_enough_memory_mm) from (copy_process.constprop.5+0x16b4/0x25c8) (copy_process.constprop.5) from (_do_fork+0xe8/0x55c) (_do_fork) from (SyS_clone+0x1c/0x24) (SyS_clone) from (__sys_trace_return+0x0/0x10) Code: 0050a0e1 6c0080e2 0140a0e1 0260a0e1 (f801f0e7)
CVE-2022-27672: When SMT is enabled, certain AMD processors may speculatively execute instructions using a target from the sibling thread after an SMT mode switch potentially resulting in information disclosure.
CVE-2022-36402: An integer overflow vulnerability was found in vmwgfx driver in drivers/gpu/vmxgfx/vmxgfx_execbuf.c in GPU component of Linux kernel with device file '/dev/dri/renderD128 (or Dxxx)'. This flaw allows a local attacker with a user account on the system to gain privilege, causing a denial of service(DoS).
CVE-2022-39189: An issue was discovered the x86 KVM subsystem in the Linux kernel before 5.18.17. Unprivileged guest users can compromise the guest kernel because TLB flush operations are mishandled in certain KVM_VCPU_PREEMPTED situations.
CVE-2022-43945: The Linux kernel NFSD implementation prior to versions 5.19.17 and 6.0.2 are vulnerable to buffer overflow. NFSD tracks the number of pages held by each NFSD thread by combining the receive and send buffers of a remote procedure call (RPC) into a single array of pages. A client can force the send buffer to shrink by sending an RPC message over TCP with garbage data added at the end of the message. The RPC message with garbage data is still correctly formed according to the specification and is passed forward to handlers. Vulnerable code in NFSD is not expecting the oversized request and writes beyond the allocated buffer space. CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVE-2022-47518: An issue was discovered in the Linux kernel before 6.0.11. Missing validation of the number of channels in drivers/net/wireless/microchip/wilc1000/cfg80211.c in the WILC1000 wireless driver can trigger a heap-based buffer overflow when copying the list of operating channels from Wi-Fi management frames.
CVE-2022-47519: An issue was discovered in the Linux kernel before 6.0.11. Missing validation of IEEE80211_P2P_ATTR_OPER_CHANNEL in drivers/net/wireless/microchip/wilc1000/cfg80211.c in the WILC1000 wireless driver can trigger an out-of-bounds write when parsing the channel list attribute from Wi-Fi management frames.
CVE-2022-47520: An issue was discovered in the Linux kernel before 6.0.11. Missing offset validation in drivers/net/wireless/microchip/wilc1000/hif.c in the WILC1000 wireless driver can trigger an out-of-bounds read when parsing a Robust Security Network (RSN) information element from a Netlink packet.
CVE-2022-47521: An issue was discovered in the Linux kernel before 6.0.11. Missing validation of IEEE80211_P2P_ATTR_CHANNEL_LIST in drivers/net/wireless/microchip/wilc1000/cfg80211.c in the WILC1000 wireless driver can trigger a heap-based buffer overflow when parsing the operating channel attribute from Wi-Fi management frames.
CVE-2022-48628: In the Linux kernel, the following vulnerability has been resolved: ceph: drop messages from MDS when unmounting When unmounting all the dirty buffers will be flushed and after the last osd request is finished the last reference of the i_count will be released. Then it will flush the dirty cap/snap to MDSs, and the unmounting won't wait the possible acks, which will ihold the inodes when updating the metadata locally but makes no sense any more, of this. This will make the evict_inodes() to skip these inodes. If encrypt is enabled the kernel generate a warning when removing the encrypt keys when the skipped inodes still hold the keyring: WARNING: CPU: 4 PID: 168846 at fs/crypto/keyring.c:242 fscrypt_destroy_keyring+0x7e/0xd0 CPU: 4 PID: 168846 Comm: umount Tainted: G S 6.1.0-rc5-ceph-g72ead199864c #1 Hardware name: Supermicro SYS-5018R-WR/X10SRW-F, BIOS 2.0 12/17/2015 RIP: 0010:fscrypt_destroy_keyring+0x7e/0xd0 RSP: 0018:ffffc9000b277e28 EFLAGS: 00010202 RAX: 0000000000000002 RBX: ffff88810d52ac00 RCX: ffff88810b56aa00 RDX: 0000000080000000 RSI: ffffffff822f3a09 RDI: ffff888108f59000 RBP: ffff8881d394fb88 R08: 0000000000000028 R09: 0000000000000000 R10: 0000000000000001 R11: 11ff4fe6834fcd91 R12: ffff8881d394fc40 R13: ffff888108f59000 R14: ffff8881d394f800 R15: 0000000000000000 FS: 00007fd83f6f1080(0000) GS:ffff88885fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f918d417000 CR3: 000000017f89a005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> generic_shutdown_super+0x47/0x120 kill_anon_super+0x14/0x30 ceph_kill_sb+0x36/0x90 [ceph] deactivate_locked_super+0x29/0x60 cleanup_mnt+0xb8/0x140 task_work_run+0x67/0xb0 exit_to_user_mode_prepare+0x23d/0x240 syscall_exit_to_user_mode+0x25/0x60 do_syscall_64+0x40/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd83dc39e9b Later the kernel will crash when iput() the inodes and dereferencing the "sb->s_master_keys", which has been released by the generic_shutdown_super().
CVE-2022-48631: In the Linux kernel, the following vulnerability has been resolved: ext4: fix bug in extents parsing when eh_entries == 0 and eh_depth > 0 When walking through an inode extents, the ext4_ext_binsearch_idx() function assumes that the extent header has been previously validated. However, there are no checks that verify that the number of entries (eh->eh_entries) is non-zero when depth is > 0. And this will lead to problems because the EXT_FIRST_INDEX() and EXT_LAST_INDEX() will return garbage and result in this: [ 135.245946] ------------[ cut here ]------------ [ 135.247579] kernel BUG at fs/ext4/extents.c:2258! [ 135.249045] invalid opcode: 0000 [#1] PREEMPT SMP [ 135.250320] CPU: 2 PID: 238 Comm: tmp118 Not tainted 5.19.0-rc8+ #4 [ 135.252067] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 [ 135.255065] RIP: 0010:ext4_ext_map_blocks+0xc20/0xcb0 [ 135.256475] Code: [ 135.261433] RSP: 0018:ffffc900005939f8 EFLAGS: 00010246 [ 135.262847] RAX: 0000000000000024 RBX: ffffc90000593b70 RCX: 0000000000000023 [ 135.264765] RDX: ffff8880038e5f10 RSI: 0000000000000003 RDI: ffff8880046e922c [ 135.266670] RBP: ffff8880046e9348 R08: 0000000000000001 R09: ffff888002ca580c [ 135.268576] R10: 0000000000002602 R11: 0000000000000000 R12: 0000000000000024 [ 135.270477] R13: 0000000000000000 R14: 0000000000000024 R15: 0000000000000000 [ 135.272394] FS: 00007fdabdc56740(0000) GS:ffff88807dd00000(0000) knlGS:0000000000000000 [ 135.274510] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 135.276075] CR2: 00007ffc26bd4f00 CR3: 0000000006261004 CR4: 0000000000170ea0 [ 135.277952] Call Trace: [ 135.278635] <TASK> [ 135.279247] ? preempt_count_add+0x6d/0xa0 [ 135.280358] ? percpu_counter_add_batch+0x55/0xb0 [ 135.281612] ? _raw_read_unlock+0x18/0x30 [ 135.282704] ext4_map_blocks+0x294/0x5a0 [ 135.283745] ? xa_load+0x6f/0xa0 [ 135.284562] ext4_mpage_readpages+0x3d6/0x770 [ 135.285646] read_pages+0x67/0x1d0 [ 135.286492] ? folio_add_lru+0x51/0x80 [ 135.287441] page_cache_ra_unbounded+0x124/0x170 [ 135.288510] filemap_get_pages+0x23d/0x5a0 [ 135.289457] ? path_openat+0xa72/0xdd0 [ 135.290332] filemap_read+0xbf/0x300 [ 135.291158] ? _raw_spin_lock_irqsave+0x17/0x40 [ 135.292192] new_sync_read+0x103/0x170 [ 135.293014] vfs_read+0x15d/0x180 [ 135.293745] ksys_read+0xa1/0xe0 [ 135.294461] do_syscall_64+0x3c/0x80 [ 135.295284] entry_SYSCALL_64_after_hwframe+0x46/0xb0 This patch simply adds an extra check in __ext4_ext_check(), verifying that eh_entries is not 0 when eh_depth is > 0.
CVE-2022-48633: In the Linux kernel, the following vulnerability has been resolved: drm/gma500: Fix WARN_ON(lock->magic != lock) error psb_gem_unpin() calls dma_resv_lock() but the underlying ww_mutex gets destroyed by drm_gem_object_release() move the drm_gem_object_release() call in psb_gem_free_object() to after the unpin to fix the below warning: [ 79.693962] ------------[ cut here ]------------ [ 79.693992] DEBUG_LOCKS_WARN_ON(lock->magic != lock) [ 79.694015] WARNING: CPU: 0 PID: 240 at kernel/locking/mutex.c:582 __ww_mutex_lock.constprop.0+0x569/0xfb0 [ 79.694052] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer qrtr bnep ath9k ath9k_common ath9k_hw snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio snd_hda_codec_hdmi snd_hda_intel ath3k snd_intel_dspcfg mac80211 snd_intel_sdw_acpi btusb snd_hda_codec btrtl btbcm btintel btmtk bluetooth at24 snd_hda_core snd_hwdep uvcvideo snd_seq libarc4 videobuf2_vmalloc ath videobuf2_memops videobuf2_v4l2 videobuf2_common snd_seq_device videodev acer_wmi intel_powerclamp coretemp mc snd_pcm joydev sparse_keymap ecdh_generic pcspkr wmi_bmof cfg80211 i2c_i801 i2c_smbus snd_timer snd r8169 rfkill lpc_ich soundcore acpi_cpufreq zram rtsx_pci_sdmmc mmc_core serio_raw rtsx_pci gma500_gfx(E) video wmi ip6_tables ip_tables i2c_dev fuse [ 79.694436] CPU: 0 PID: 240 Comm: plymouthd Tainted: G W E 6.0.0-rc3+ #490 [ 79.694457] Hardware name: Packard Bell dot s/SJE01_CT, BIOS V1.10 07/23/2013 [ 79.694469] RIP: 0010:__ww_mutex_lock.constprop.0+0x569/0xfb0 [ 79.694496] Code: ff 85 c0 0f 84 15 fb ff ff 8b 05 ca 3c 11 01 85 c0 0f 85 07 fb ff ff 48 c7 c6 30 cb 84 aa 48 c7 c7 a3 e1 82 aa e8 ac 29 f8 ff <0f> 0b e9 ed fa ff ff e8 5b 83 8a ff 85 c0 74 10 44 8b 0d 98 3c 11 [ 79.694513] RSP: 0018:ffffad1dc048bbe0 EFLAGS: 00010282 [ 79.694623] RAX: 0000000000000028 RBX: 0000000000000000 RCX: 0000000000000000 [ 79.694636] RDX: 0000000000000001 RSI: ffffffffaa8b0ffc RDI: 00000000ffffffff [ 79.694650] RBP: ffffad1dc048bc80 R08: 0000000000000000 R09: ffffad1dc048ba90 [ 79.694662] R10: 0000000000000003 R11: ffffffffaad62fe8 R12: ffff9ff302103138 [ 79.694675] R13: ffff9ff306ec8000 R14: ffff9ff307779078 R15: ffff9ff3014c0270 [ 79.694690] FS: 00007ff1cccf1740(0000) GS:ffff9ff3bc200000(0000) knlGS:0000000000000000 [ 79.694705] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 79.694719] CR2: 0000559ecbcb4420 CR3: 0000000013210000 CR4: 00000000000006f0 [ 79.694734] Call Trace: [ 79.694749] <TASK> [ 79.694761] ? __schedule+0x47f/0x1670 [ 79.694796] ? psb_gem_unpin+0x27/0x1a0 [gma500_gfx] [ 79.694830] ? lock_is_held_type+0xe3/0x140 [ 79.694864] ? ww_mutex_lock+0x38/0xa0 [ 79.694885] ? __cond_resched+0x1c/0x30 [ 79.694902] ww_mutex_lock+0x38/0xa0 [ 79.694925] psb_gem_unpin+0x27/0x1a0 [gma500_gfx] [ 79.694964] psb_gem_unpin+0x199/0x1a0 [gma500_gfx] [ 79.694996] drm_gem_object_release_handle+0x50/0x60 [ 79.695020] ? drm_gem_object_handle_put_unlocked+0xf0/0xf0 [ 79.695042] idr_for_each+0x4b/0xb0 [ 79.695066] ? _raw_spin_unlock_irqrestore+0x30/0x60 [ 79.695095] drm_gem_release+0x1c/0x30 [ 79.695118] drm_file_free.part.0+0x1ea/0x260 [ 79.695150] drm_release+0x6a/0x120 [ 79.695175] __fput+0x9f/0x260 [ 79.695203] task_work_run+0x59/0xa0 [ 79.695227] do_exit+0x387/0xbe0 [ 79.695250] ? seqcount_lockdep_reader_access.constprop.0+0x82/0x90 [ 79.695275] ? lockdep_hardirqs_on+0x7d/0x100 [ 79.695304] do_group_exit+0x33/0xb0 [ 79.695331] __x64_sys_exit_group+0x14/0x20 [ 79.695353] do_syscall_64+0x58/0x80 [ 79.695376] ? up_read+0x17/0x20 [ 79.695401] ? lock_is_held_type+0xe3/0x140 [ 79.695429] ? asm_exc_page_fault+0x22/0x30 [ 79.695450] ? lockdep_hardirqs_on+0x7d/0x100 [ 79.695473] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 79.695493] RIP: 0033:0x7ff1ccefe3f1 [ 79.695516] Code: Unable to access opcode bytes at RIP 0x7ff1ccefe3c7. [ 79.695607] RSP: 002b:00007ffed4413378 EFLAGS: ---truncated---
CVE-2022-48634: In the Linux kernel, the following vulnerability has been resolved: drm/gma500: Fix BUG: sleeping function called from invalid context errors gma_crtc_page_flip() was holding the event_lock spinlock while calling crtc_funcs->mode_set_base() which takes ww_mutex. The only reason to hold event_lock is to clear gma_crtc->page_flip_event on mode_set_base() errors. Instead unlock it after setting gma_crtc->page_flip_event and on errors re-take the lock and clear gma_crtc->page_flip_event it it is still set. This fixes the following WARN/stacktrace: [ 512.122953] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:870 [ 512.123004] in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1253, name: gnome-shell [ 512.123031] preempt_count: 1, expected: 0 [ 512.123048] RCU nest depth: 0, expected: 0 [ 512.123066] INFO: lockdep is turned off. [ 512.123080] irq event stamp: 0 [ 512.123094] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [ 512.123134] hardirqs last disabled at (0): [<ffffffff8d0ec28c>] copy_process+0x9fc/0x1de0 [ 512.123176] softirqs last enabled at (0): [<ffffffff8d0ec28c>] copy_process+0x9fc/0x1de0 [ 512.123207] softirqs last disabled at (0): [<0000000000000000>] 0x0 [ 512.123233] Preemption disabled at: [ 512.123241] [<0000000000000000>] 0x0 [ 512.123275] CPU: 3 PID: 1253 Comm: gnome-shell Tainted: G W 5.19.0+ #1 [ 512.123304] Hardware name: Packard Bell dot s/SJE01_CT, BIOS V1.10 07/23/2013 [ 512.123323] Call Trace: [ 512.123346] <TASK> [ 512.123370] dump_stack_lvl+0x5b/0x77 [ 512.123412] __might_resched.cold+0xff/0x13a [ 512.123458] ww_mutex_lock+0x1e/0xa0 [ 512.123495] psb_gem_pin+0x2c/0x150 [gma500_gfx] [ 512.123601] gma_pipe_set_base+0x76/0x240 [gma500_gfx] [ 512.123708] gma_crtc_page_flip+0x95/0x130 [gma500_gfx] [ 512.123808] drm_mode_page_flip_ioctl+0x57d/0x5d0 [ 512.123897] ? drm_mode_cursor2_ioctl+0x10/0x10 [ 512.123936] drm_ioctl_kernel+0xa1/0x150 [ 512.123984] drm_ioctl+0x21f/0x420 [ 512.124025] ? drm_mode_cursor2_ioctl+0x10/0x10 [ 512.124070] ? rcu_read_lock_bh_held+0xb/0x60 [ 512.124104] ? lock_release+0x1ef/0x2d0 [ 512.124161] __x64_sys_ioctl+0x8d/0xd0 [ 512.124203] do_syscall_64+0x58/0x80 [ 512.124239] ? do_syscall_64+0x67/0x80 [ 512.124267] ? trace_hardirqs_on_prepare+0x55/0xe0 [ 512.124300] ? do_syscall_64+0x67/0x80 [ 512.124340] ? rcu_read_lock_sched_held+0x10/0x80 [ 512.124377] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 512.124411] RIP: 0033:0x7fcc4a70740f [ 512.124442] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 18 48 8b 44 24 18 64 48 2b 04 25 28 00 00 [ 512.124470] RSP: 002b:00007ffda73f5390 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 512.124503] RAX: ffffffffffffffda RBX: 000055cc9e474500 RCX: 00007fcc4a70740f [ 512.124524] RDX: 00007ffda73f5420 RSI: 00000000c01864b0 RDI: 0000000000000009 [ 512.124544] RBP: 00007ffda73f5420 R08: 000055cc9c0b0cb0 R09: 0000000000000034 [ 512.124564] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c01864b0 [ 512.124584] R13: 0000000000000009 R14: 000055cc9df484d0 R15: 000055cc9af5d0c0 [ 512.124647] </TASK>
CVE-2022-48664: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix hang during unmount when stopping a space reclaim worker Often when running generic/562 from fstests we can hang during unmount, resulting in a trace like this: Sep 07 11:52:00 debian9 unknown: run fstests generic/562 at 2022-09-07 11:52:00 Sep 07 11:55:32 debian9 kernel: INFO: task umount:49438 blocked for more than 120 seconds. Sep 07 11:55:32 debian9 kernel: Not tainted 6.0.0-rc2-btrfs-next-122 #1 Sep 07 11:55:32 debian9 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. Sep 07 11:55:32 debian9 kernel: task:umount state:D stack: 0 pid:49438 ppid: 25683 flags:0x00004000 Sep 07 11:55:32 debian9 kernel: Call Trace: Sep 07 11:55:32 debian9 kernel: <TASK> Sep 07 11:55:32 debian9 kernel: __schedule+0x3c8/0xec0 Sep 07 11:55:32 debian9 kernel: ? rcu_read_lock_sched_held+0x12/0x70 Sep 07 11:55:32 debian9 kernel: schedule+0x5d/0xf0 Sep 07 11:55:32 debian9 kernel: schedule_timeout+0xf1/0x130 Sep 07 11:55:32 debian9 kernel: ? lock_release+0x224/0x4a0 Sep 07 11:55:32 debian9 kernel: ? lock_acquired+0x1a0/0x420 Sep 07 11:55:32 debian9 kernel: ? trace_hardirqs_on+0x2c/0xd0 Sep 07 11:55:32 debian9 kernel: __wait_for_common+0xac/0x200 Sep 07 11:55:32 debian9 kernel: ? usleep_range_state+0xb0/0xb0 Sep 07 11:55:32 debian9 kernel: __flush_work+0x26d/0x530 Sep 07 11:55:32 debian9 kernel: ? flush_workqueue_prep_pwqs+0x140/0x140 Sep 07 11:55:32 debian9 kernel: ? trace_clock_local+0xc/0x30 Sep 07 11:55:32 debian9 kernel: __cancel_work_timer+0x11f/0x1b0 Sep 07 11:55:32 debian9 kernel: ? close_ctree+0x12b/0x5b3 [btrfs] Sep 07 11:55:32 debian9 kernel: ? __trace_bputs+0x10b/0x170 Sep 07 11:55:32 debian9 kernel: close_ctree+0x152/0x5b3 [btrfs] Sep 07 11:55:32 debian9 kernel: ? evict_inodes+0x166/0x1c0 Sep 07 11:55:32 debian9 kernel: generic_shutdown_super+0x71/0x120 Sep 07 11:55:32 debian9 kernel: kill_anon_super+0x14/0x30 Sep 07 11:55:32 debian9 kernel: btrfs_kill_super+0x12/0x20 [btrfs] Sep 07 11:55:32 debian9 kernel: deactivate_locked_super+0x2e/0xa0 Sep 07 11:55:32 debian9 kernel: cleanup_mnt+0x100/0x160 Sep 07 11:55:32 debian9 kernel: task_work_run+0x59/0xa0 Sep 07 11:55:32 debian9 kernel: exit_to_user_mode_prepare+0x1a6/0x1b0 Sep 07 11:55:32 debian9 kernel: syscall_exit_to_user_mode+0x16/0x40 Sep 07 11:55:32 debian9 kernel: do_syscall_64+0x48/0x90 Sep 07 11:55:32 debian9 kernel: entry_SYSCALL_64_after_hwframe+0x63/0xcd Sep 07 11:55:32 debian9 kernel: RIP: 0033:0x7fcde59a57a7 Sep 07 11:55:32 debian9 kernel: RSP: 002b:00007ffe914217c8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 Sep 07 11:55:32 debian9 kernel: RAX: 0000000000000000 RBX: 00007fcde5ae8264 RCX: 00007fcde59a57a7 Sep 07 11:55:32 debian9 kernel: RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000055b57556cdd0 Sep 07 11:55:32 debian9 kernel: RBP: 000055b57556cba0 R08: 0000000000000000 R09: 00007ffe91420570 Sep 07 11:55:32 debian9 kernel: R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 Sep 07 11:55:32 debian9 kernel: R13: 000055b57556cdd0 R14: 000055b57556ccb8 R15: 0000000000000000 Sep 07 11:55:32 debian9 kernel: </TASK> What happens is the following: 1) The cleaner kthread tries to start a transaction to delete an unused block group, but the metadata reservation can not be satisfied right away, so a reservation ticket is created and it starts the async metadata reclaim task (fs_info->async_reclaim_work); 2) Writeback for all the filler inodes with an i_size of 2K starts (generic/562 creates a lot of 2K files with the goal of filling metadata space). We try to create an inline extent for them, but we fail when trying to insert the inline extent with -ENOSPC (at cow_file_range_inline()) - since this is not critical, we fallback to non-inline mode (back to cow_file_range()), reserve extents ---truncated---
CVE-2022-48670: In the Linux kernel, the following vulnerability has been resolved: peci: cpu: Fix use-after-free in adev_release() When auxiliary_device_add() returns an error, auxiliary_device_uninit() is called, which causes refcount for device to be decremented and .release callback will be triggered. Because adev_release() re-calls auxiliary_device_uninit(), it will cause use-after-free: [ 1269.455172] WARNING: CPU: 0 PID: 14267 at lib/refcount.c:28 refcount_warn_saturate+0x110/0x15 [ 1269.464007] refcount_t: underflow; use-after-free.
CVE-2022-48673: In the Linux kernel, the following vulnerability has been resolved: net/smc: Fix possible access to freed memory in link clear After modifying the QP to the Error state, all RX WR would be completed with WC in IB_WC_WR_FLUSH_ERR status. Current implementation does not wait for it is done, but destroy the QP and free the link group directly. So there is a risk that accessing the freed memory in tasklet context. Here is a crash example: BUG: unable to handle page fault for address: ffffffff8f220860 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD f7300e067 P4D f7300e067 PUD f7300f063 PMD 8c4e45063 PTE 800ffff08c9df060 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: G S OE 5.10.0-0607+ #23 Hardware name: Inspur NF5280M4/YZMB-00689-101, BIOS 4.1.20 07/09/2018 RIP: 0010:native_queued_spin_lock_slowpath+0x176/0x1b0 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb d5 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 00 c8 02 00 48 03 04 f5 00 09 98 8e <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32 RSP: 0018:ffffb3b6c001ebd8 EFLAGS: 00010086 RAX: ffffffff8f220860 RBX: 0000000000000246 RCX: 0000000000080000 RDX: ffff91db1f86c800 RSI: 000000000000173c RDI: ffff91db62bace00 RBP: ffff91db62bacc00 R08: 0000000000000000 R09: c00000010000028b R10: 0000000000055198 R11: ffffb3b6c001ea58 R12: ffff91db80e05010 R13: 000000000000000a R14: 0000000000000006 R15: 0000000000000040 FS: 0000000000000000(0000) GS:ffff91db1f840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8f220860 CR3: 00000001f9580004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> _raw_spin_lock_irqsave+0x30/0x40 mlx5_ib_poll_cq+0x4c/0xc50 [mlx5_ib] smc_wr_rx_tasklet_fn+0x56/0xa0 [smc] tasklet_action_common.isra.21+0x66/0x100 __do_softirq+0xd5/0x29c asm_call_irq_on_stack+0x12/0x20 </IRQ> do_softirq_own_stack+0x37/0x40 irq_exit_rcu+0x9d/0xa0 sysvec_call_function_single+0x34/0x80 asm_sysvec_call_function_single+0x12/0x20
CVE-2022-48674: In the Linux kernel, the following vulnerability has been resolved: erofs: fix pcluster use-after-free on UP platforms During stress testing with CONFIG_SMP disabled, KASAN reports as below: ================================================================== BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30 Read of size 8 at addr ffff8881094223f8 by task stress/7789 CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Call Trace: <TASK> .. __mutex_lock+0xe5/0xc30 .. z_erofs_do_read_page+0x8ce/0x1560 .. z_erofs_readahead+0x31c/0x580 .. Freed by task 7787 kasan_save_stack+0x1e/0x40 kasan_set_track+0x20/0x30 kasan_set_free_info+0x20/0x40 __kasan_slab_free+0x10c/0x190 kmem_cache_free+0xed/0x380 rcu_core+0x3d5/0xc90 __do_softirq+0x12d/0x389 Last potentially related work creation: kasan_save_stack+0x1e/0x40 __kasan_record_aux_stack+0x97/0xb0 call_rcu+0x3d/0x3f0 erofs_shrink_workstation+0x11f/0x210 erofs_shrink_scan+0xdc/0x170 shrink_slab.constprop.0+0x296/0x530 drop_slab+0x1c/0x70 drop_caches_sysctl_handler+0x70/0x80 proc_sys_call_handler+0x20a/0x2f0 vfs_write+0x555/0x6c0 ksys_write+0xbe/0x160 do_syscall_64+0x3b/0x90 The root cause is that erofs_workgroup_unfreeze() doesn't reset to orig_val thus it causes a race that the pcluster reuses unexpectedly before freeing. Since UP platforms are quite rare now, such path becomes unnecessary. Let's drop such specific-designed path directly instead.
CVE-2022-48698: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix memory leak when using debugfs_lookup() When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. Fix this up by properly calling dput().
CVE-2022-48699: In the Linux kernel, the following vulnerability has been resolved: sched/debug: fix dentry leak in update_sched_domain_debugfs Kuyo reports that the pattern of using debugfs_remove(debugfs_lookup()) leaks a dentry and with a hotplug stress test, the machine eventually runs out of memory. Fix this up by using the newly created debugfs_lookup_and_remove() call instead which properly handles the dentry reference counting logic.
CVE-2022-48700: In the Linux kernel, the following vulnerability has been resolved: vfio/type1: Unpin zero pages There's currently a reference count leak on the zero page. We increment the reference via pin_user_pages_remote(), but the page is later handled as an invalid/reserved page, therefore it's not accounted against the user and not unpinned by our put_pfn(). Introducing special zero page handling in put_pfn() would resolve the leak, but without accounting of the zero page, a single user could still create enough mappings to generate a reference count overflow. The zero page is always resident, so for our purposes there's no reason to keep it pinned. Therefore, add a loop to walk pages returned from pin_user_pages_remote() and unpin any zero pages.
CVE-2022-48703: In the Linux kernel, the following vulnerability has been resolved: thermal/int340x_thermal: handle data_vault when the value is ZERO_SIZE_PTR In some case, the GDDV returns a package with a buffer which has zero length. It causes that kmemdup() returns ZERO_SIZE_PTR (0x10). Then the data_vault_read() got NULL point dereference problem when accessing the 0x10 value in data_vault. [ 71.024560] BUG: kernel NULL pointer dereference, address: 0000000000000010 This patch uses ZERO_OR_NULL_PTR() for checking ZERO_SIZE_PTR or NULL value in data_vault.
CVE-2022-48706: In the Linux kernel, the following vulnerability has been resolved: vdpa: ifcvf: Do proper cleanup if IFCVF init fails ifcvf_mgmt_dev leaks memory if it is not freed before returning. Call is made to correct return statement so memory does not leak. ifcvf_init_hw does not take care of this so it is needed to do it here.
CVE-2022-48712: In the Linux kernel, the following vulnerability has been resolved: ext4: fix error handling in ext4_fc_record_modified_inode() Current code does not fully takes care of krealloc() error case, which could lead to silent memory corruption or a kernel bug. This patch fixes that. Also it cleans up some duplicated error handling logic from various functions in fast_commit.c file.
CVE-2022-48731: In the Linux kernel, the following vulnerability has been resolved: mm/kmemleak: avoid scanning potential huge holes When using devm_request_free_mem_region() and devm_memremap_pages() to add ZONE_DEVICE memory, if requested free mem region's end pfn were huge(e.g., 0x400000000), the node_end_pfn() will be also huge (see move_pfn_range_to_zone()). Thus it creates a huge hole between node_start_pfn() and node_end_pfn(). We found on some AMD APUs, amdkfd requested such a free mem region and created a huge hole. In such a case, following code snippet was just doing busy test_bit() looping on the huge hole. for (pfn = start_pfn; pfn < end_pfn; pfn++) { struct page *page = pfn_to_online_page(pfn); if (!page) continue; ... } So we got a soft lockup: watchdog: BUG: soft lockup - CPU#6 stuck for 26s! [bash:1221] CPU: 6 PID: 1221 Comm: bash Not tainted 5.15.0-custom #1 RIP: 0010:pfn_to_online_page+0x5/0xd0 Call Trace: ? kmemleak_scan+0x16a/0x440 kmemleak_write+0x306/0x3a0 ? common_file_perm+0x72/0x170 full_proxy_write+0x5c/0x90 vfs_write+0xb9/0x260 ksys_write+0x67/0xe0 __x64_sys_write+0x1a/0x20 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae I did some tests with the patch. (1) amdgpu module unloaded before the patch: real 0m0.976s user 0m0.000s sys 0m0.968s after the patch: real 0m0.981s user 0m0.000s sys 0m0.973s (2) amdgpu module loaded before the patch: real 0m35.365s user 0m0.000s sys 0m35.354s after the patch: real 0m1.049s user 0m0.000s sys 0m1.042s
CVE-2022-48733: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix use-after-free after failure to create a snapshot At ioctl.c:create_snapshot(), we allocate a pending snapshot structure and then attach it to the transaction's list of pending snapshots. After that we call btrfs_commit_transaction(), and if that returns an error we jump to 'fail' label, where we kfree() the pending snapshot structure. This can result in a later use-after-free of the pending snapshot: 1) We allocated the pending snapshot and added it to the transaction's list of pending snapshots; 2) We call btrfs_commit_transaction(), and it fails either at the first call to btrfs_run_delayed_refs() or btrfs_start_dirty_block_groups(). In both cases, we don't abort the transaction and we release our transaction handle. We jump to the 'fail' label and free the pending snapshot structure. We return with the pending snapshot still in the transaction's list; 3) Another task commits the transaction. This time there's no error at all, and then during the transaction commit it accesses a pointer to the pending snapshot structure that the snapshot creation task has already freed, resulting in a user-after-free. This issue could actually be detected by smatch, which produced the following warning: fs/btrfs/ioctl.c:843 create_snapshot() warn: '&pending_snapshot->list' not removed from list So fix this by not having the snapshot creation ioctl directly add the pending snapshot to the transaction's list. Instead add the pending snapshot to the transaction handle, and then at btrfs_commit_transaction() we add the snapshot to the list only when we can guarantee that any error returned after that point will result in a transaction abort, in which case the ioctl code can safely free the pending snapshot and no one can access it anymore.
CVE-2022-48734: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix deadlock between quota disable and qgroup rescan worker Quota disable ioctl starts a transaction before waiting for the qgroup rescan worker completes. However, this wait can be infinite and results in deadlock because of circular dependency among the quota disable ioctl, the qgroup rescan worker and the other task with transaction such as block group relocation task. The deadlock happens with the steps following: 1) Task A calls ioctl to disable quota. It starts a transaction and waits for qgroup rescan worker completes. 2) Task B such as block group relocation task starts a transaction and joins to the transaction that task A started. Then task B commits to the transaction. In this commit, task B waits for a commit by task A. 3) Task C as the qgroup rescan worker starts its job and starts a transaction. In this transaction start, task C waits for completion of the transaction that task A started and task B committed. This deadlock was found with fstests test case btrfs/115 and a zoned null_blk device. The test case enables and disables quota, and the block group reclaim was triggered during the quota disable by chance. The deadlock was also observed by running quota enable and disable in parallel with 'btrfs balance' command on regular null_blk devices. An example report of the deadlock: [372.469894] INFO: task kworker/u16:6:103 blocked for more than 122 seconds. [372.479944] Not tainted 5.16.0-rc8 #7 [372.485067] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [372.493898] task:kworker/u16:6 state:D stack: 0 pid: 103 ppid: 2 flags:0x00004000 [372.503285] Workqueue: btrfs-qgroup-rescan btrfs_work_helper [btrfs] [372.510782] Call Trace: [372.514092] <TASK> [372.521684] __schedule+0xb56/0x4850 [372.530104] ? io_schedule_timeout+0x190/0x190 [372.538842] ? lockdep_hardirqs_on+0x7e/0x100 [372.547092] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [372.555591] schedule+0xe0/0x270 [372.561894] btrfs_commit_transaction+0x18bb/0x2610 [btrfs] [372.570506] ? btrfs_apply_pending_changes+0x50/0x50 [btrfs] [372.578875] ? free_unref_page+0x3f2/0x650 [372.585484] ? finish_wait+0x270/0x270 [372.591594] ? release_extent_buffer+0x224/0x420 [btrfs] [372.599264] btrfs_qgroup_rescan_worker+0xc13/0x10c0 [btrfs] [372.607157] ? lock_release+0x3a9/0x6d0 [372.613054] ? btrfs_qgroup_account_extent+0xda0/0xda0 [btrfs] [372.620960] ? do_raw_spin_lock+0x11e/0x250 [372.627137] ? rwlock_bug.part.0+0x90/0x90 [372.633215] ? lock_is_held_type+0xe4/0x140 [372.639404] btrfs_work_helper+0x1ae/0xa90 [btrfs] [372.646268] process_one_work+0x7e9/0x1320 [372.652321] ? lock_release+0x6d0/0x6d0 [372.658081] ? pwq_dec_nr_in_flight+0x230/0x230 [372.664513] ? rwlock_bug.part.0+0x90/0x90 [372.670529] worker_thread+0x59e/0xf90 [372.676172] ? process_one_work+0x1320/0x1320 [372.682440] kthread+0x3b9/0x490 [372.687550] ? _raw_spin_unlock_irq+0x24/0x50 [372.693811] ? set_kthread_struct+0x100/0x100 [372.700052] ret_from_fork+0x22/0x30 [372.705517] </TASK> [372.709747] INFO: task btrfs-transacti:2347 blocked for more than 123 seconds. [372.729827] Not tainted 5.16.0-rc8 #7 [372.745907] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [372.767106] task:btrfs-transacti state:D stack: 0 pid: 2347 ppid: 2 flags:0x00004000 [372.787776] Call Trace: [372.801652] <TASK> [372.812961] __schedule+0xb56/0x4850 [372.830011] ? io_schedule_timeout+0x190/0x190 [372.852547] ? lockdep_hardirqs_on+0x7e/0x100 [372.871761] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [372.886792] schedule+0xe0/0x270 [372.901685] wait_current_trans+0x22c/0x310 [btrfs] [372.919743] ? btrfs_put_transaction+0x3d0/0x3d0 [btrfs] [372.938923] ? finish_wait+0x270/0x270 [372.959085] ? join_transaction+0xc7 ---truncated---
CVE-2022-48735: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: Fix UAF of leds class devs at unbinding The LED class devices that are created by HD-audio codec drivers are registered via devm_led_classdev_register() and associated with the HD-audio codec device. Unfortunately, it turned out that the devres release doesn't work for this case; namely, since the codec resource release happens before the devm call chain, it triggers a NULL dereference or a UAF for a stale set_brightness_delay callback. For fixing the bug, this patch changes the LED class device register and unregister in a manual manner without devres, keeping the instances in hda_gen_spec.
CVE-2022-48739: In the Linux kernel, the following vulnerability has been resolved: ASoC: hdmi-codec: Fix OOB memory accesses Correct size of iec_status array by changing it to the size of status array of the struct snd_aes_iec958. This fixes out-of-bounds slab read accesses made by memcpy() of the hdmi-codec driver. This problem is reported by KASAN.
CVE-2022-48740: In the Linux kernel, the following vulnerability has been resolved: selinux: fix double free of cond_list on error paths On error path from cond_read_list() and duplicate_policydb_cond_list() the cond_list_destroy() gets called a second time in caller functions, resulting in NULL pointer deref. Fix this by resetting the cond_list_len to 0 in cond_list_destroy(), making subsequent calls a noop. Also consistently reset the cond_list pointer to NULL after freeing. [PM: fix line lengths in the description]
CVE-2022-48744: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Avoid field-overflowing memcpy() In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use flexible arrays instead of zero-element arrays (which look like they are always overflowing) and split the cross-field memcpy() into two halves that can be appropriately bounds-checked by the compiler. We were doing: #define ETH_HLEN 14 #define VLAN_HLEN 4 ... #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) ... struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); ... struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; ... memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); target is wqe->eth.inline_hdr.start (which the compiler sees as being 2 bytes in size), but copying 18, intending to write across start (really vlan_tci, 2 bytes). The remaining 16 bytes get written into wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr (8 bytes). struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; /* 0 16 */ struct mlx5_wqe_eth_seg eth; /* 16 16 */ struct mlx5_wqe_data_seg data[]; /* 32 0 */ /* size: 32, cachelines: 1, members: 3 */ /* last cacheline: 32 bytes */ }; struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; /* 0 1 */ u8 swp_outer_l3_offset; /* 1 1 */ u8 swp_inner_l4_offset; /* 2 1 */ u8 swp_inner_l3_offset; /* 3 1 */ u8 cs_flags; /* 4 1 */ u8 swp_flags; /* 5 1 */ __be16 mss; /* 6 2 */ __be32 flow_table_metadata; /* 8 4 */ union { struct { __be16 sz; /* 12 2 */ u8 start[2]; /* 14 2 */ } inline_hdr; /* 12 4 */ struct { __be16 type; /* 12 2 */ __be16 vlan_tci; /* 14 2 */ } insert; /* 12 4 */ __be32 trailer; /* 12 4 */ }; /* 12 4 */ /* size: 16, cachelines: 1, members: 9 */ /* last cacheline: 16 bytes */ }; struct mlx5_wqe_data_seg { __be32 byte_count; /* 0 4 */ __be32 lkey; /* 4 4 */ __be64 addr; /* 8 8 */ /* size: 16, cachelines: 1, members: 3 */ /* last cacheline: 16 bytes */ }; So, split the memcpy() so the compiler can reason about the buffer sizes. "pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations).
CVE-2022-48747: In the Linux kernel, the following vulnerability has been resolved: block: Fix wrong offset in bio_truncate() bio_truncate() clears the buffer outside of last block of bdev, however current bio_truncate() is using the wrong offset of page. So it can return the uninitialized data. This happened when both of truncated/corrupted FS and userspace (via bdev) are trying to read the last of bdev.
CVE-2022-48751: In the Linux kernel, the following vulnerability has been resolved: net/smc: Transitional solution for clcsock race issue We encountered a crash in smc_setsockopt() and it is caused by accessing smc->clcsock after clcsock was released. BUG: kernel NULL pointer dereference, address: 0000000000000020 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 50309 Comm: nginx Kdump: loaded Tainted: G E 5.16.0-rc4+ #53 RIP: 0010:smc_setsockopt+0x59/0x280 [smc] Call Trace: <TASK> __sys_setsockopt+0xfc/0x190 __x64_sys_setsockopt+0x20/0x30 do_syscall_64+0x34/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f16ba83918e </TASK> This patch tries to fix it by holding clcsock_release_lock and checking whether clcsock has already been released before access. In case that a crash of the same reason happens in smc_getsockopt() or smc_switch_to_fallback(), this patch also checkes smc->clcsock in them too. And the caller of smc_switch_to_fallback() will identify whether fallback succeeds according to the return value.
CVE-2022-48755: In the Linux kernel, the following vulnerability has been resolved: powerpc64/bpf: Limit 'ldbrx' to processors compliant with ISA v2.06 Johan reported the below crash with test_bpf on ppc64 e5500: test_bpf: #296 ALU_END_FROM_LE 64: 0x0123456789abcdef -> 0x67452301 jited:1 Oops: Exception in kernel mode, sig: 4 [#1] BE PAGE_SIZE=4K SMP NR_CPUS=24 QEMU e500 Modules linked in: test_bpf(+) CPU: 0 PID: 76 Comm: insmod Not tainted 5.14.0-03771-g98c2059e008a-dirty #1 NIP: 8000000000061c3c LR: 80000000006dea64 CTR: 8000000000061c18 REGS: c0000000032d3420 TRAP: 0700 Not tainted (5.14.0-03771-g98c2059e008a-dirty) MSR: 0000000080089000 <EE,ME> CR: 88002822 XER: 20000000 IRQMASK: 0 <...> NIP [8000000000061c3c] 0x8000000000061c3c LR [80000000006dea64] .__run_one+0x104/0x17c [test_bpf] Call Trace: .__run_one+0x60/0x17c [test_bpf] (unreliable) .test_bpf_init+0x6a8/0xdc8 [test_bpf] .do_one_initcall+0x6c/0x28c .do_init_module+0x68/0x28c .load_module+0x2460/0x2abc .__do_sys_init_module+0x120/0x18c .system_call_exception+0x110/0x1b8 system_call_common+0xf0/0x210 --- interrupt: c00 at 0x101d0acc <...> ---[ end trace 47b2bf19090bb3d0 ]--- Illegal instruction The illegal instruction turned out to be 'ldbrx' emitted for BPF_FROM_[L|B]E, which was only introduced in ISA v2.06. Guard use of the same and implement an alternative approach for older processors.
CVE-2022-48761: In the Linux kernel, the following vulnerability has been resolved: usb: xhci-plat: fix crash when suspend if remote wake enable Crashed at i.mx8qm platform when suspend if enable remote wakeup Internal error: synchronous external abort: 96000210 [#1] PREEMPT SMP Modules linked in: CPU: 2 PID: 244 Comm: kworker/u12:6 Not tainted 5.15.5-dirty #12 Hardware name: Freescale i.MX8QM MEK (DT) Workqueue: events_unbound async_run_entry_fn pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : xhci_disable_hub_port_wake.isra.62+0x60/0xf8 lr : xhci_disable_hub_port_wake.isra.62+0x34/0xf8 sp : ffff80001394bbf0 x29: ffff80001394bbf0 x28: 0000000000000000 x27: ffff00081193b578 x26: ffff00081193b570 x25: 0000000000000000 x24: 0000000000000000 x23: ffff00081193a29c x22: 0000000000020001 x21: 0000000000000001 x20: 0000000000000000 x19: ffff800014e90490 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000002 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000960 x9 : ffff80001394baa0 x8 : ffff0008145d1780 x7 : ffff0008f95b8e80 x6 : 000000001853b453 x5 : 0000000000000496 x4 : 0000000000000000 x3 : ffff00081193a29c x2 : 0000000000000001 x1 : 0000000000000000 x0 : ffff000814591620 Call trace: xhci_disable_hub_port_wake.isra.62+0x60/0xf8 xhci_suspend+0x58/0x510 xhci_plat_suspend+0x50/0x78 platform_pm_suspend+0x2c/0x78 dpm_run_callback.isra.25+0x50/0xe8 __device_suspend+0x108/0x3c0 The basic flow: 1. run time suspend call xhci_suspend, xhci parent devices gate the clock. 2. echo mem >/sys/power/state, system _device_suspend call xhci_suspend 3. xhci_suspend call xhci_disable_hub_port_wake, which access register, but clock already gated by run time suspend. This problem was hidden by power domain driver, which call run time resume before it. But the below commit remove it and make this issue happen. commit c1df456d0f06e ("PM: domains: Don't runtime resume devices at genpd_prepare()") This patch call run time resume before suspend to make sure clock is on before access register. Testeb-by: Abel Vesa <abel.vesa@nxp.com>
CVE-2022-48763: In the Linux kernel, the following vulnerability has been resolved: KVM: x86: Forcibly leave nested virt when SMM state is toggled Forcibly leave nested virtualization operation if userspace toggles SMM state via KVM_SET_VCPU_EVENTS or KVM_SYNC_X86_EVENTS. If userspace forces the vCPU out of SMM while it's post-VMXON and then injects an SMI, vmx_enter_smm() will overwrite vmx->nested.smm.vmxon and end up with both vmxon=false and smm.vmxon=false, but all other nVMX state allocated. Don't attempt to gracefully handle the transition as (a) most transitions are nonsencial, e.g. forcing SMM while L2 is running, (b) there isn't sufficient information to handle all transitions, e.g. SVM wants access to the SMRAM save state, and (c) KVM_SET_VCPU_EVENTS must precede KVM_SET_NESTED_STATE during state restore as the latter disallows putting the vCPU into L2 if SMM is active, and disallows tagging the vCPU as being post-VMXON in SMM if SMM is not active. Abuse of KVM_SET_VCPU_EVENTS manifests as a WARN and memory leak in nVMX due to failure to free vmcs01's shadow VMCS, but the bug goes far beyond just a memory leak, e.g. toggling SMM on while L2 is active puts the vCPU in an architecturally impossible state. WARNING: CPU: 0 PID: 3606 at free_loaded_vmcs arch/x86/kvm/vmx/vmx.c:2665 [inline] WARNING: CPU: 0 PID: 3606 at free_loaded_vmcs+0x158/0x1a0 arch/x86/kvm/vmx/vmx.c:2656 Modules linked in: CPU: 1 PID: 3606 Comm: syz-executor725 Not tainted 5.17.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:free_loaded_vmcs arch/x86/kvm/vmx/vmx.c:2665 [inline] RIP: 0010:free_loaded_vmcs+0x158/0x1a0 arch/x86/kvm/vmx/vmx.c:2656 Code: <0f> 0b eb b3 e8 8f 4d 9f 00 e9 f7 fe ff ff 48 89 df e8 92 4d 9f 00 Call Trace: <TASK> kvm_arch_vcpu_destroy+0x72/0x2f0 arch/x86/kvm/x86.c:11123 kvm_vcpu_destroy arch/x86/kvm/../../../virt/kvm/kvm_main.c:441 [inline] kvm_destroy_vcpus+0x11f/0x290 arch/x86/kvm/../../../virt/kvm/kvm_main.c:460 kvm_free_vcpus arch/x86/kvm/x86.c:11564 [inline] kvm_arch_destroy_vm+0x2e8/0x470 arch/x86/kvm/x86.c:11676 kvm_destroy_vm arch/x86/kvm/../../../virt/kvm/kvm_main.c:1217 [inline] kvm_put_kvm+0x4fa/0xb00 arch/x86/kvm/../../../virt/kvm/kvm_main.c:1250 kvm_vm_release+0x3f/0x50 arch/x86/kvm/../../../virt/kvm/kvm_main.c:1273 __fput+0x286/0x9f0 fs/file_table.c:311 task_work_run+0xdd/0x1a0 kernel/task_work.c:164 exit_task_work include/linux/task_work.h:32 [inline] do_exit+0xb29/0x2a30 kernel/exit.c:806 do_group_exit+0xd2/0x2f0 kernel/exit.c:935 get_signal+0x4b0/0x28c0 kernel/signal.c:2862 arch_do_signal_or_restart+0x2a9/0x1c40 arch/x86/kernel/signal.c:868 handle_signal_work kernel/entry/common.c:148 [inline] exit_to_user_mode_loop kernel/entry/common.c:172 [inline] exit_to_user_mode_prepare+0x17d/0x290 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:300 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK>
CVE-2022-48765: In the Linux kernel, the following vulnerability has been resolved: KVM: LAPIC: Also cancel preemption timer during SET_LAPIC The below warning is splatting during guest reboot. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1931 at arch/x86/kvm/x86.c:10322 kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm] CPU: 0 PID: 1931 Comm: qemu-system-x86 Tainted: G I 5.17.0-rc1+ #5 RIP: 0010:kvm_arch_vcpu_ioctl_run+0x874/0x880 [kvm] Call Trace: <TASK> kvm_vcpu_ioctl+0x279/0x710 [kvm] __x64_sys_ioctl+0x83/0xb0 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7fd39797350b This can be triggered by not exposing tsc-deadline mode and doing a reboot in the guest. The lapic_shutdown() function which is called in sys_reboot path will not disarm the flying timer, it just masks LVTT. lapic_shutdown() clears APIC state w/ LVT_MASKED and timer-mode bit is 0, this can trigger timer-mode switch between tsc-deadline and oneshot/periodic, which can result in preemption timer be cancelled in apic_update_lvtt(). However, We can't depend on this when not exposing tsc-deadline mode and oneshot/periodic modes emulated by preemption timer. Qemu will synchronise states around reset, let's cancel preemption timer under KVM_SET_LAPIC.
CVE-2022-48766: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wrap dcn301_calculate_wm_and_dlg for FPU. Mirrors the logic for dcn30. Cue lots of WARNs and some kernel panics without this fix.
CVE-2022-48769: In the Linux kernel, the following vulnerability has been resolved: efi: runtime: avoid EFIv2 runtime services on Apple x86 machines Aditya reports [0] that his recent MacbookPro crashes in the firmware when using the variable services at runtime. The culprit appears to be a call to QueryVariableInfo(), which we did not use to call on Apple x86 machines in the past as they only upgraded from EFI v1.10 to EFI v2.40 firmware fairly recently, and QueryVariableInfo() (along with UpdateCapsule() et al) was added in EFI v2.00. The only runtime service introduced in EFI v2.00 that we actually use in Linux is QueryVariableInfo(), as the capsule based ones are optional, generally not used at runtime (all the LVFS/fwupd firmware update infrastructure uses helper EFI programs that invoke capsule update at boot time, not runtime), and not implemented by Apple machines in the first place. QueryVariableInfo() is used to 'safely' set variables, i.e., only when there is enough space. This prevents machines with buggy firmwares from corrupting their NVRAMs when they run out of space. Given that Apple machines have been using EFI v1.10 services only for the longest time (the EFI v2.0 spec was released in 2006, and Linux support for the newly introduced runtime services was added in 2011, but the MacbookPro12,1 released in 2015 still claims to be EFI v1.10 only), let's avoid the EFI v2.0 ones on all Apple x86 machines. [0] https://lore.kernel.org/all/6D757C75-65B1-468B-842D-10410081A8E4@live.com/
CVE-2022-48772: In the Linux kernel, the following vulnerability has been resolved: media: lgdt3306a: Add a check against null-pointer-def The driver should check whether the client provides the platform_data. The following log reveals it: [ 29.610324] BUG: KASAN: null-ptr-deref in kmemdup+0x30/0x40 [ 29.610730] Read of size 40 at addr 0000000000000000 by task bash/414 [ 29.612820] Call Trace: [ 29.613030] <TASK> [ 29.613201] dump_stack_lvl+0x56/0x6f [ 29.613496] ? kmemdup+0x30/0x40 [ 29.613754] print_report.cold+0x494/0x6b7 [ 29.614082] ? kmemdup+0x30/0x40 [ 29.614340] kasan_report+0x8a/0x190 [ 29.614628] ? kmemdup+0x30/0x40 [ 29.614888] kasan_check_range+0x14d/0x1d0 [ 29.615213] memcpy+0x20/0x60 [ 29.615454] kmemdup+0x30/0x40 [ 29.615700] lgdt3306a_probe+0x52/0x310 [ 29.616339] i2c_device_probe+0x951/0xa90
CVE-2023-20588: A division-by-zero error on some AMD processors can potentially return speculative data resulting in loss of confidentiality.
CVE-2023-21255: In multiple functions of binder.c, there is a possible memory corruption due to a use after free. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation.
CVE-2023-24023: Bluetooth BR/EDR devices with Secure Simple Pairing and Secure Connections pairing in Bluetooth Core Specification 4.2 through 5.4 allow certain man-in-the-middle attacks that force a short key length, and might lead to discovery of the encryption key and live injection, aka BLUFFS.
CVE-2023-28746: Information exposure through microarchitectural state after transient execution from some register files for some Intel(R) Atom(R) Processors may allow an authenticated user to potentially enable information disclosure via local access.
CVE-2023-31082: An issue was discovered in drivers/tty/n_gsm.c in the Linux kernel 6.2. There is a sleeping function called from an invalid context in gsmld_write, which will block the kernel. Note: This has been disputed by 3rd parties as not a valid vulnerability.
CVE-2023-31083: An issue was discovered in drivers/bluetooth/hci_ldisc.c in the Linux kernel 6.2. In hci_uart_tty_ioctl, there is a race condition between HCIUARTSETPROTO and HCIUARTGETPROTO. HCI_UART_PROTO_SET is set before hu->proto is set. A NULL pointer dereference may occur.
CVE-2023-33288: An issue was discovered in the Linux kernel before 6.2.9. A use-after-free was found in bq24190_remove in drivers/power/supply/bq24190_charger.c. It could allow a local attacker to crash the system due to a race condition.
CVE-2023-35827: An issue was discovered in the Linux kernel through 6.3.8. A use-after-free was found in ravb_remove in drivers/net/ethernet/renesas/ravb_main.c.
CVE-2023-37453: An issue was discovered in the USB subsystem in the Linux kernel through 6.4.2. There is an out-of-bounds and crash in read_descriptors in drivers/usb/core/sysfs.c.
CVE-2023-37454: An issue was discovered in the Linux kernel through 6.4.2. A crafted UDF filesystem image causes a use-after-free write operation in the udf_put_super and udf_close_lvid functions in fs/udf/super.c. NOTE: the suse.com reference has a different perspective about this.
CVE-2023-39197: An out-of-bounds read vulnerability was found in Netfilter Connection Tracking (conntrack) in the Linux kernel. This flaw allows a remote user to disclose sensitive information via the DCCP protocol.
CVE-2023-39198: A race condition was found in the QXL driver in the Linux kernel. The qxl_mode_dumb_create() function dereferences the qobj returned by the qxl_gem_object_create_with_handle(), but the handle is the only one holding a reference to it. This flaw allows an attacker to guess the returned handle value and trigger a use-after-free issue, potentially leading to a denial of service or privilege escalation.
CVE-2023-51779: bt_sock_recvmsg in net/bluetooth/af_bluetooth.c in the Linux kernel through 6.6.8 has a use-after-free because of a bt_sock_ioctl race condition.
CVE-2023-52434: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential OOBs in smb2_parse_contexts() Validate offsets and lengths before dereferencing create contexts in smb2_parse_contexts(). This fixes following oops when accessing invalid create contexts from server: BUG: unable to handle page fault for address: ffff8881178d8cc3 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 4a01067 P4D 4a01067 PUD 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 1736 Comm: mount.cifs Not tainted 6.7.0-rc4 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 RIP: 0010:smb2_parse_contexts+0xa0/0x3a0 [cifs] Code: f8 10 75 13 48 b8 93 ad 25 50 9c b4 11 e7 49 39 06 0f 84 d2 00 00 00 8b 45 00 85 c0 74 61 41 29 c5 48 01 c5 41 83 fd 0f 76 55 <0f> b7 7d 04 0f b7 45 06 4c 8d 74 3d 00 66 83 f8 04 75 bc ba 04 00 RSP: 0018:ffffc900007939e0 EFLAGS: 00010216 RAX: ffffc90000793c78 RBX: ffff8880180cc000 RCX: ffffc90000793c90 RDX: ffffc90000793cc0 RSI: ffff8880178d8cc0 RDI: ffff8880180cc000 RBP: ffff8881178d8cbf R08: ffffc90000793c22 R09: 0000000000000000 R10: ffff8880180cc000 R11: 0000000000000024 R12: 0000000000000000 R13: 0000000000000020 R14: 0000000000000000 R15: ffffc90000793c22 FS: 00007f873753cbc0(0000) GS:ffff88806bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8881178d8cc3 CR3: 00000000181ca000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x181/0x480 ? search_module_extables+0x19/0x60 ? srso_alias_return_thunk+0x5/0xfbef5 ? exc_page_fault+0x1b6/0x1c0 ? asm_exc_page_fault+0x26/0x30 ? smb2_parse_contexts+0xa0/0x3a0 [cifs] SMB2_open+0x38d/0x5f0 [cifs] ? smb2_is_path_accessible+0x138/0x260 [cifs] smb2_is_path_accessible+0x138/0x260 [cifs] cifs_is_path_remote+0x8d/0x230 [cifs] cifs_mount+0x7e/0x350 [cifs] cifs_smb3_do_mount+0x128/0x780 [cifs] smb3_get_tree+0xd9/0x290 [cifs] vfs_get_tree+0x2c/0x100 ? capable+0x37/0x70 path_mount+0x2d7/0xb80 ? srso_alias_return_thunk+0x5/0xfbef5 ? _raw_spin_unlock_irqrestore+0x44/0x60 __x64_sys_mount+0x11a/0x150 do_syscall_64+0x47/0xf0 entry_SYSCALL_64_after_hwframe+0x6f/0x77 RIP: 0033:0x7f8737657b1e
CVE-2023-52435: In the Linux kernel, the following vulnerability has been resolved: net: prevent mss overflow in skb_segment() Once again syzbot is able to crash the kernel in skb_segment() [1] GSO_BY_FRAGS is a forbidden value, but unfortunately the following computation in skb_segment() can reach it quite easily : mss = mss * partial_segs; 65535 = 3 * 5 * 17 * 257, so many initial values of mss can lead to a bad final result. Make sure to limit segmentation so that the new mss value is smaller than GSO_BY_FRAGS. [1] general protection fault, probably for non-canonical address 0xdffffc000000000e: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 1 PID: 5079 Comm: syz-executor993 Not tainted 6.7.0-rc4-syzkaller-00141-g1ae4cd3cbdd0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023 RIP: 0010:skb_segment+0x181d/0x3f30 net/core/skbuff.c:4551 Code: 83 e3 02 e9 fb ed ff ff e8 90 68 1c f9 48 8b 84 24 f8 00 00 00 48 8d 78 70 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 8a 21 00 00 48 8b 84 24 f8 00 RSP: 0018:ffffc900043473d0 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 0000000000010046 RCX: ffffffff886b1597 RDX: 000000000000000e RSI: ffffffff886b2520 RDI: 0000000000000070 RBP: ffffc90004347578 R08: 0000000000000005 R09: 000000000000ffff R10: 000000000000ffff R11: 0000000000000002 R12: ffff888063202ac0 R13: 0000000000010000 R14: 000000000000ffff R15: 0000000000000046 FS: 0000555556e7e380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020010000 CR3: 0000000027ee2000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> udp6_ufo_fragment+0xa0e/0xd00 net/ipv6/udp_offload.c:109 ipv6_gso_segment+0x534/0x17e0 net/ipv6/ip6_offload.c:120 skb_mac_gso_segment+0x290/0x610 net/core/gso.c:53 __skb_gso_segment+0x339/0x710 net/core/gso.c:124 skb_gso_segment include/net/gso.h:83 [inline] validate_xmit_skb+0x36c/0xeb0 net/core/dev.c:3626 __dev_queue_xmit+0x6f3/0x3d60 net/core/dev.c:4338 dev_queue_xmit include/linux/netdevice.h:3134 [inline] packet_xmit+0x257/0x380 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3087 [inline] packet_sendmsg+0x24c6/0x5220 net/packet/af_packet.c:3119 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0xd5/0x180 net/socket.c:745 __sys_sendto+0x255/0x340 net/socket.c:2190 __do_sys_sendto net/socket.c:2202 [inline] __se_sys_sendto net/socket.c:2198 [inline] __x64_sys_sendto+0xe0/0x1b0 net/socket.c:2198 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x40/0x110 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b RIP: 0033:0x7f8692032aa9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 d1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fff8d685418 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f8692032aa9 RDX: 0000000000010048 RSI: 00000000200000c0 RDI: 0000000000000003 RBP: 00000000000f4240 R08: 0000000020000540 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fff8d685480 R13: 0000000000000001 R14: 00007fff8d685480 R15: 0000000000000003 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:skb_segment+0x181d/0x3f30 net/core/skbuff.c:4551 Code: 83 e3 02 e9 fb ed ff ff e8 90 68 1c f9 48 8b 84 24 f8 00 00 00 48 8d 78 70 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 8a 21 00 00 48 8b 84 24 f8 00 RSP: 0018:ffffc900043473d0 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 0000000000010046 RCX: ffffffff886b1597 RDX: 000000000000000e RSI: ffffffff886b2520 RDI: 0000000000000070 RBP: ffffc90004347578 R0 ---truncated---
CVE-2023-52458: In the Linux kernel, the following vulnerability has been resolved: block: add check that partition length needs to be aligned with block size Before calling add partition or resize partition, there is no check on whether the length is aligned with the logical block size. If the logical block size of the disk is larger than 512 bytes, then the partition size maybe not the multiple of the logical block size, and when the last sector is read, bio_truncate() will adjust the bio size, resulting in an IO error if the size of the read command is smaller than the logical block size.If integrity data is supported, this will also result in a null pointer dereference when calling bio_integrity_free.
CVE-2023-52474: In the Linux kernel, the following vulnerability has been resolved: IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests hfi1 user SDMA request processing has two bugs that can cause data corruption for user SDMA requests that have multiple payload iovecs where an iovec other than the tail iovec does not run up to the page boundary for the buffer pointed to by that iovec.a Here are the specific bugs: 1. user_sdma_txadd() does not use struct user_sdma_iovec->iov.iov_len. Rather, user_sdma_txadd() will add up to PAGE_SIZE bytes from iovec to the packet, even if some of those bytes are past iovec->iov.iov_len and are thus not intended to be in the packet. 2. user_sdma_txadd() and user_sdma_send_pkts() fail to advance to the next iovec in user_sdma_request->iovs when the current iovec is not PAGE_SIZE and does not contain enough data to complete the packet. The transmitted packet will contain the wrong data from the iovec pages. This has not been an issue with SDMA packets from hfi1 Verbs or PSM2 because they only produce iovecs that end short of PAGE_SIZE as the tail iovec of an SDMA request. Fixing these bugs exposes other bugs with the SDMA pin cache (struct mmu_rb_handler) that get in way of supporting user SDMA requests with multiple payload iovecs whose buffers do not end at PAGE_SIZE. So this commit fixes those issues as well. Here are the mmu_rb_handler bugs that non-PAGE_SIZE-end multi-iovec payload user SDMA requests can hit: 1. Overlapping memory ranges in mmu_rb_handler will result in duplicate pinnings. 2. When extending an existing mmu_rb_handler entry (struct mmu_rb_node), the mmu_rb code (1) removes the existing entry under a lock, (2) releases that lock, pins the new pages, (3) then reacquires the lock to insert the extended mmu_rb_node. If someone else comes in and inserts an overlapping entry between (2) and (3), insert in (3) will fail. The failure path code in this case unpins _all_ pages in either the original mmu_rb_node or the new mmu_rb_node that was inserted between (2) and (3). 3. In hfi1_mmu_rb_remove_unless_exact(), mmu_rb_node->refcount is incremented outside of mmu_rb_handler->lock. As a result, mmu_rb_node could be evicted by another thread that gets mmu_rb_handler->lock and checks mmu_rb_node->refcount before mmu_rb_node->refcount is incremented. 4. Related to #2 above, SDMA request submission failure path does not check mmu_rb_node->refcount before freeing mmu_rb_node object. If there are other SDMA requests in progress whose iovecs have pointers to the now-freed mmu_rb_node(s), those pointers to the now-freed mmu_rb nodes will be dereferenced when those SDMA requests complete.
CVE-2023-52476: In the Linux kernel, the following vulnerability has been resolved: perf/x86/lbr: Filter vsyscall addresses We found that a panic can occur when a vsyscall is made while LBR sampling is active. If the vsyscall is interrupted (NMI) for perf sampling, this call sequence can occur (most recent at top): __insn_get_emulate_prefix() insn_get_emulate_prefix() insn_get_prefixes() insn_get_opcode() decode_branch_type() get_branch_type() intel_pmu_lbr_filter() intel_pmu_handle_irq() perf_event_nmi_handler() Within __insn_get_emulate_prefix() at frame 0, a macro is called: peek_nbyte_next(insn_byte_t, insn, i) Within this macro, this dereference occurs: (insn)->next_byte Inspecting registers at this point, the value of the next_byte field is the address of the vsyscall made, for example the location of the vsyscall version of gettimeofday() at 0xffffffffff600000. The access to an address in the vsyscall region will trigger an oops due to an unhandled page fault. To fix the bug, filtering for vsyscalls can be done when determining the branch type. This patch will return a "none" branch if a kernel address if found to lie in the vsyscall region.
CVE-2023-52479: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix uaf in smb20_oplock_break_ack drop reference after use opinfo.
CVE-2023-52480: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix race condition between session lookup and expire Thread A + Thread B ksmbd_session_lookup | smb2_sess_setup sess = xa_load | | | xa_erase(&conn->sessions, sess->id); | | ksmbd_session_destroy(sess) --> kfree(sess) | // UAF! | sess->last_active = jiffies | + This patch add rwsem to fix race condition between ksmbd_session_lookup and ksmbd_expire_session.
CVE-2023-52481: In the Linux kernel, the following vulnerability has been resolved: arm64: errata: Add Cortex-A520 speculative unprivileged load workaround Implement the workaround for ARM Cortex-A520 erratum 2966298. On an affected Cortex-A520 core, a speculatively executed unprivileged load might leak data from a privileged load via a cache side channel. The issue only exists for loads within a translation regime with the same translation (e.g. same ASID and VMID). Therefore, the issue only affects the return to EL0. The workaround is to execute a TLBI before returning to EL0 after all loads of privileged data. A non-shareable TLBI to any address is sufficient. The workaround isn't necessary if page table isolation (KPTI) is enabled, but for simplicity it will be. Page table isolation should normally be disabled for Cortex-A520 as it supports the CSV3 feature and the E0PD feature (used when KASLR is enabled).
CVE-2023-52482: In the Linux kernel, the following vulnerability has been resolved: x86/srso: Add SRSO mitigation for Hygon processors Add mitigation for the speculative return stack overflow vulnerability which exists on Hygon processors too.
CVE-2023-52484: In the Linux kernel, the following vulnerability has been resolved: iommu/arm-smmu-v3: Fix soft lockup triggered by arm_smmu_mm_invalidate_range When running an SVA case, the following soft lockup is triggered: -------------------------------------------------------------------- watchdog: BUG: soft lockup - CPU#244 stuck for 26s! pstate: 83400009 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : arm_smmu_cmdq_issue_cmdlist+0x178/0xa50 lr : arm_smmu_cmdq_issue_cmdlist+0x150/0xa50 sp : ffff8000d83ef290 x29: ffff8000d83ef290 x28: 000000003b9aca00 x27: 0000000000000000 x26: ffff8000d83ef3c0 x25: da86c0812194a0e8 x24: 0000000000000000 x23: 0000000000000040 x22: ffff8000d83ef340 x21: ffff0000c63980c0 x20: 0000000000000001 x19: ffff0000c6398080 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: ffff3000b4a3bbb0 x14: ffff3000b4a30888 x13: ffff3000b4a3cf60 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : ffffc08120e4d6bc x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000048cfa x5 : 0000000000000000 x4 : 0000000000000001 x3 : 000000000000000a x2 : 0000000080000000 x1 : 0000000000000000 x0 : 0000000000000001 Call trace: arm_smmu_cmdq_issue_cmdlist+0x178/0xa50 __arm_smmu_tlb_inv_range+0x118/0x254 arm_smmu_tlb_inv_range_asid+0x6c/0x130 arm_smmu_mm_invalidate_range+0xa0/0xa4 __mmu_notifier_invalidate_range_end+0x88/0x120 unmap_vmas+0x194/0x1e0 unmap_region+0xb4/0x144 do_mas_align_munmap+0x290/0x490 do_mas_munmap+0xbc/0x124 __vm_munmap+0xa8/0x19c __arm64_sys_munmap+0x28/0x50 invoke_syscall+0x78/0x11c el0_svc_common.constprop.0+0x58/0x1c0 do_el0_svc+0x34/0x60 el0_svc+0x2c/0xd4 el0t_64_sync_handler+0x114/0x140 el0t_64_sync+0x1a4/0x1a8 -------------------------------------------------------------------- Note that since 6.6-rc1 the arm_smmu_mm_invalidate_range above is renamed to "arm_smmu_mm_arch_invalidate_secondary_tlbs", yet the problem remains. The commit 06ff87bae8d3 ("arm64: mm: remove unused functions and variable protoypes") fixed a similar lockup on the CPU MMU side. Yet, it can occur to SMMU too, since arm_smmu_mm_arch_invalidate_secondary_tlbs() is called typically next to MMU tlb flush function, e.g. tlb_flush_mmu_tlbonly { tlb_flush { __flush_tlb_range { // check MAX_TLBI_OPS } } mmu_notifier_arch_invalidate_secondary_tlbs { arm_smmu_mm_arch_invalidate_secondary_tlbs { // does not check MAX_TLBI_OPS } } } Clone a CMDQ_MAX_TLBI_OPS from the MAX_TLBI_OPS in tlbflush.h, since in an SVA case SMMU uses the CPU page table, so it makes sense to align with the tlbflush code. Then, replace per-page TLBI commands with a single per-asid TLBI command, if the request size hits this threshold.
CVE-2023-52485: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before sending a command [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] For functions that execute within a DC context or DC lock we can wrap the direct calls to dm_execute_dmub_cmd/list with code that exits idle power optimizations and reallows once we're done with the command submission on success. For DM direct submissions the DM will need to manage the enter/exit sequencing manually. We cannot invoke a DMCUB command directly within the DM execution helper or we can deadlock.
CVE-2023-52488: In the Linux kernel, the following vulnerability has been resolved: serial: sc16is7xx: convert from _raw_ to _noinc_ regmap functions for FIFO The SC16IS7XX IC supports a burst mode to access the FIFOs where the initial register address is sent ($00), followed by all the FIFO data without having to resend the register address each time. In this mode, the IC doesn't increment the register address for each R/W byte. The regmap_raw_read() and regmap_raw_write() are functions which can perform IO over multiple registers. They are currently used to read/write from/to the FIFO, and although they operate correctly in this burst mode on the SPI bus, they would corrupt the regmap cache if it was not disabled manually. The reason is that when the R/W size is more than 1 byte, these functions assume that the register address is incremented and handle the cache accordingly. Convert FIFO R/W functions to use the regmap _noinc_ versions in order to remove the manual cache control which was a workaround when using the _raw_ versions. FIFO registers are properly declared as volatile so cache will not be used/updated for FIFO accesses.
CVE-2023-52491: In the Linux kernel, the following vulnerability has been resolved: media: mtk-jpeg: Fix use after free bug due to error path handling in mtk_jpeg_dec_device_run In mtk_jpeg_probe, &jpeg->job_timeout_work is bound with mtk_jpeg_job_timeout_work. In mtk_jpeg_dec_device_run, if error happens in mtk_jpeg_set_dec_dst, it will finally start the worker while mark the job as finished by invoking v4l2_m2m_job_finish. There are two methods to trigger the bug. If we remove the module, it which will call mtk_jpeg_remove to make cleanup. The possible sequence is as follows, which will cause a use-after-free bug. CPU0 CPU1 mtk_jpeg_dec_... | start worker | |mtk_jpeg_job_timeout_work mtk_jpeg_remove | v4l2_m2m_release | kfree(m2m_dev); | | | v4l2_m2m_get_curr_priv | m2m_dev->curr_ctx //use If we close the file descriptor, which will call mtk_jpeg_release, it will have a similar sequence. Fix this bug by starting timeout worker only if started jpegdec worker successfully. Then v4l2_m2m_job_finish will only be called in either mtk_jpeg_job_timeout_work or mtk_jpeg_dec_device_run.
CVE-2023-52498: In the Linux kernel, the following vulnerability has been resolved: PM: sleep: Fix possible deadlocks in core system-wide PM code It is reported that in low-memory situations the system-wide resume core code deadlocks, because async_schedule_dev() executes its argument function synchronously if it cannot allocate memory (and not only in that case) and that function attempts to acquire a mutex that is already held. Executing the argument function synchronously from within dpm_async_fn() may also be problematic for ordering reasons (it may cause a consumer device's resume callback to be invoked before a requisite supplier device's one, for example). Address this by changing the code in question to use async_schedule_dev_nocall() for scheduling the asynchronous execution of device suspend and resume functions and to directly run them synchronously if async_schedule_dev_nocall() returns false.
CVE-2023-52500: In the Linux kernel, the following vulnerability has been resolved: scsi: pm80xx: Avoid leaking tags when processing OPC_INB_SET_CONTROLLER_CONFIG command Tags allocated for OPC_INB_SET_CONTROLLER_CONFIG command need to be freed when we receive the response.
CVE-2023-52501: In the Linux kernel, the following vulnerability has been resolved: ring-buffer: Do not attempt to read past "commit" When iterating over the ring buffer while the ring buffer is active, the writer can corrupt the reader. There's barriers to help detect this and handle it, but that code missed the case where the last event was at the very end of the page and has only 4 bytes left. The checks to detect the corruption by the writer to reads needs to see the length of the event. If the length in the first 4 bytes is zero then the length is stored in the second 4 bytes. But if the writer is in the process of updating that code, there's a small window where the length in the first 4 bytes could be zero even though the length is only 4 bytes. That will cause rb_event_length() to read the next 4 bytes which could happen to be off the allocated page. To protect against this, fail immediately if the next event pointer is less than 8 bytes from the end of the commit (last byte of data), as all events must be a minimum of 8 bytes anyway.
CVE-2023-52508: In the Linux kernel, the following vulnerability has been resolved: nvme-fc: Prevent null pointer dereference in nvme_fc_io_getuuid() The nvme_fc_fcp_op structure describing an AEN operation is initialized with a null request structure pointer. An FC LLDD may make a call to nvme_fc_io_getuuid passing a pointer to an nvmefc_fcp_req for an AEN operation. Add validation of the request structure pointer before dereference.
CVE-2023-52509: In the Linux kernel, the following vulnerability has been resolved: ravb: Fix use-after-free issue in ravb_tx_timeout_work() The ravb_stop() should call cancel_work_sync(). Otherwise, ravb_tx_timeout_work() is possible to use the freed priv after ravb_remove() was called like below: CPU0 CPU1 ravb_tx_timeout() ravb_remove() unregister_netdev() free_netdev(ndev) // free priv ravb_tx_timeout_work() // use priv unregister_netdev() will call .ndo_stop() so that ravb_stop() is called. And, after phy_stop() is called, netif_carrier_off() is also called. So that .ndo_tx_timeout() will not be called after phy_stop().
CVE-2023-52511: In the Linux kernel, the following vulnerability has been resolved: spi: sun6i: reduce DMA RX transfer width to single byte Through empirical testing it has been determined that sometimes RX SPI transfers with DMA enabled return corrupted data. This is down to single or even multiple bytes lost during DMA transfer from SPI peripheral to memory. It seems the RX FIFO within the SPI peripheral can become confused when performing bus read accesses wider than a single byte to it during an active SPI transfer. This patch reduces the width of individual DMA read accesses to the RX FIFO to a single byte to mitigate that issue.
CVE-2023-52515: In the Linux kernel, the following vulnerability has been resolved: RDMA/srp: Do not call scsi_done() from srp_abort() After scmd_eh_abort_handler() has called the SCSI LLD eh_abort_handler callback, it performs one of the following actions: * Call scsi_queue_insert(). * Call scsi_finish_command(). * Call scsi_eh_scmd_add(). Hence, SCSI abort handlers must not call scsi_done(). Otherwise all the above actions would trigger a use-after-free. Hence remove the scsi_done() call from srp_abort(). Keep the srp_free_req() call before returning SUCCESS because we may not see the command again if SUCCESS is returned.
CVE-2023-52516: In the Linux kernel, the following vulnerability has been resolved: dma-debug: don't call __dma_entry_alloc_check_leak() under free_entries_lock __dma_entry_alloc_check_leak() calls into printk -> serial console output (qcom geni) and grabs port->lock under free_entries_lock spin lock, which is a reverse locking dependency chain as qcom_geni IRQ handler can call into dma-debug code and grab free_entries_lock under port->lock. Move __dma_entry_alloc_check_leak() call out of free_entries_lock scope so that we don't acquire serial console's port->lock under it. Trimmed-down lockdep splat: The existing dependency chain (in reverse order) is: -> #2 (free_entries_lock){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 dma_entry_alloc+0x38/0x110 debug_dma_map_page+0x60/0xf8 dma_map_page_attrs+0x1e0/0x230 dma_map_single_attrs.constprop.0+0x6c/0xc8 geni_se_rx_dma_prep+0x40/0xcc qcom_geni_serial_isr+0x310/0x510 __handle_irq_event_percpu+0x110/0x244 handle_irq_event_percpu+0x20/0x54 handle_irq_event+0x50/0x88 handle_fasteoi_irq+0xa4/0xcc handle_irq_desc+0x28/0x40 generic_handle_domain_irq+0x24/0x30 gic_handle_irq+0xc4/0x148 do_interrupt_handler+0xa4/0xb0 el1_interrupt+0x34/0x64 el1h_64_irq_handler+0x18/0x24 el1h_64_irq+0x64/0x68 arch_local_irq_enable+0x4/0x8 ____do_softirq+0x18/0x24 ... -> #1 (&port_lock_key){-.-.}-{2:2}: _raw_spin_lock_irqsave+0x60/0x80 qcom_geni_serial_console_write+0x184/0x1dc console_flush_all+0x344/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 register_console+0x230/0x38c uart_add_one_port+0x338/0x494 qcom_geni_serial_probe+0x390/0x424 platform_probe+0x70/0xc0 really_probe+0x148/0x280 __driver_probe_device+0xfc/0x114 driver_probe_device+0x44/0x100 __device_attach_driver+0x64/0xdc bus_for_each_drv+0xb0/0xd8 __device_attach+0xe4/0x140 device_initial_probe+0x1c/0x28 bus_probe_device+0x44/0xb0 device_add+0x538/0x668 of_device_add+0x44/0x50 of_platform_device_create_pdata+0x94/0xc8 of_platform_bus_create+0x270/0x304 of_platform_populate+0xac/0xc4 devm_of_platform_populate+0x60/0xac geni_se_probe+0x154/0x160 platform_probe+0x70/0xc0 ... -> #0 (console_owner){-...}-{0:0}: __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 console_unlock+0x94/0xf0 vprintk_emit+0x238/0x24c vprintk_default+0x3c/0x48 vprintk+0xb4/0xbc _printk+0x68/0x90 dma_entry_alloc+0xb4/0x110 debug_dma_map_sg+0xdc/0x2f8 __dma_map_sg_attrs+0xac/0xe4 dma_map_sgtable+0x30/0x4c get_pages+0x1d4/0x1e4 [msm] msm_gem_pin_pages_locked+0x38/0xac [msm] msm_gem_pin_vma_locked+0x58/0x88 [msm] msm_ioctl_gem_submit+0xde4/0x13ac [msm] drm_ioctl_kernel+0xe0/0x15c drm_ioctl+0x2e8/0x3f4 vfs_ioctl+0x30/0x50 ... Chain exists of: console_owner --> &port_lock_key --> free_entries_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(free_entries_lock); lock(&port_lock_key); lock(free_entries_lock); lock(console_owner); *** DEADLOCK *** Call trace: dump_backtrace+0xb4/0xf0 show_stack+0x20/0x30 dump_stack_lvl+0x60/0x84 dump_stack+0x18/0x24 print_circular_bug+0x1cc/0x234 check_noncircular+0x78/0xac __lock_acquire+0xdf8/0x109c lock_acquire+0x234/0x284 console_flush_all+0x330/0x454 consol ---truncated---
CVE-2023-52517: In the Linux kernel, the following vulnerability has been resolved: spi: sun6i: fix race between DMA RX transfer completion and RX FIFO drain Previously the transfer complete IRQ immediately drained to RX FIFO to read any data remaining in FIFO to the RX buffer. This behaviour is correct when dealing with SPI in interrupt mode. However in DMA mode the transfer complete interrupt still fires as soon as all bytes to be transferred have been stored in the FIFO. At that point data in the FIFO still needs to be picked up by the DMA engine. Thus the drain procedure and DMA engine end up racing to read from RX FIFO, corrupting any data read. Additionally the RX buffer pointer is never adjusted according to DMA progress in DMA mode, thus calling the RX FIFO drain procedure in DMA mode is a bug. Fix corruptions in DMA RX mode by draining RX FIFO only in interrupt mode. Also wait for completion of RX DMA when in DMA mode before returning to ensure all data has been copied to the supplied memory buffer.
CVE-2023-52522: In the Linux kernel, the following vulnerability has been resolved: net: fix possible store tearing in neigh_periodic_work() While looking at a related syzbot report involving neigh_periodic_work(), I found that I forgot to add an annotation when deleting an RCU protected item from a list. Readers use rcu_deference(*np), we need to use either rcu_assign_pointer() or WRITE_ONCE() on writer side to prevent store tearing. I use rcu_assign_pointer() to have lockdep support, this was the choice made in neigh_flush_dev().
CVE-2023-52530: In the Linux kernel, the following vulnerability has been resolved: wifi: mac80211: fix potential key use-after-free When ieee80211_key_link() is called by ieee80211_gtk_rekey_add() but returns 0 due to KRACK protection (identical key reinstall), ieee80211_gtk_rekey_add() will still return a pointer into the key, in a potential use-after-free. This normally doesn't happen since it's only called by iwlwifi in case of WoWLAN rekey offload which has its own KRACK protection, but still better to fix, do that by returning an error code and converting that to success on the cfg80211 boundary only, leaving the error for bad callers of ieee80211_gtk_rekey_add().
CVE-2023-52531: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: Fix a memory corruption issue A few lines above, space is kzalloc()'ed for: sizeof(struct iwl_nvm_data) + sizeof(struct ieee80211_channel) + sizeof(struct ieee80211_rate) 'mvm->nvm_data' is a 'struct iwl_nvm_data', so it is fine. At the end of this structure, there is the 'channels' flex array. Each element is of type 'struct ieee80211_channel'. So only 1 element is allocated in this array. When doing: mvm->nvm_data->bands[0].channels = mvm->nvm_data->channels; We point at the first element of the 'channels' flex array. So this is fine. However, when doing: mvm->nvm_data->bands[0].bitrates = (void *)((u8 *)mvm->nvm_data->channels + 1); because of the "(u8 *)" cast, we add only 1 to the address of the beginning of the flex array. It is likely that we want point at the 'struct ieee80211_rate' allocated just after. Remove the spurious casting so that the pointer arithmetic works as expected.
CVE-2023-52561: In the Linux kernel, the following vulnerability has been resolved: arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved Adding a reserved memory region for the framebuffer memory (the splash memory region set up by the bootloader). It fixes a kernel panic (arm-smmu: Unhandled context fault at this particular memory region) reported on DB845c running v5.10.y.
CVE-2023-52569: In the Linux kernel, the following vulnerability has been resolved: btrfs: remove BUG() after failure to insert delayed dir index item Instead of calling BUG() when we fail to insert a delayed dir index item into the delayed node's tree, we can just release all the resources we have allocated/acquired before and return the error to the caller. This is fine because all existing call chains undo anything they have done before calling btrfs_insert_delayed_dir_index() or BUG_ON (when creating pending snapshots in the transaction commit path). So remove the BUG() call and do proper error handling. This relates to a syzbot report linked below, but does not fix it because it only prevents hitting a BUG(), it does not fix the issue where somehow we attempt to use twice the same index number for different index items.
CVE-2023-52572: In the Linux kernel, the following vulnerability has been resolved: cifs: Fix UAF in cifs_demultiplex_thread() There is a UAF when xfstests on cifs: BUG: KASAN: use-after-free in smb2_is_network_name_deleted+0x27/0x160 Read of size 4 at addr ffff88810103fc08 by task cifsd/923 CPU: 1 PID: 923 Comm: cifsd Not tainted 6.1.0-rc4+ #45 ... Call Trace: <TASK> dump_stack_lvl+0x34/0x44 print_report+0x171/0x472 kasan_report+0xad/0x130 kasan_check_range+0x145/0x1a0 smb2_is_network_name_deleted+0x27/0x160 cifs_demultiplex_thread.cold+0x172/0x5a4 kthread+0x165/0x1a0 ret_from_fork+0x1f/0x30 </TASK> Allocated by task 923: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_slab_alloc+0x54/0x60 kmem_cache_alloc+0x147/0x320 mempool_alloc+0xe1/0x260 cifs_small_buf_get+0x24/0x60 allocate_buffers+0xa1/0x1c0 cifs_demultiplex_thread+0x199/0x10d0 kthread+0x165/0x1a0 ret_from_fork+0x1f/0x30 Freed by task 921: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 ____kasan_slab_free+0x143/0x1b0 kmem_cache_free+0xe3/0x4d0 cifs_small_buf_release+0x29/0x90 SMB2_negotiate+0x8b7/0x1c60 smb2_negotiate+0x51/0x70 cifs_negotiate_protocol+0xf0/0x160 cifs_get_smb_ses+0x5fa/0x13c0 mount_get_conns+0x7a/0x750 cifs_mount+0x103/0xd00 cifs_smb3_do_mount+0x1dd/0xcb0 smb3_get_tree+0x1d5/0x300 vfs_get_tree+0x41/0xf0 path_mount+0x9b3/0xdd0 __x64_sys_mount+0x190/0x1d0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The UAF is because: mount(pid: 921) | cifsd(pid: 923) -------------------------------|------------------------------- | cifs_demultiplex_thread SMB2_negotiate | cifs_send_recv | compound_send_recv | smb_send_rqst | wait_for_response | wait_event_state [1] | | standard_receive3 | cifs_handle_standard | handle_mid | mid->resp_buf = buf; [2] | dequeue_mid [3] KILL the process [4] | resp_iov[i].iov_base = buf | free_rsp_buf [5] | | is_network_name_deleted [6] | callback 1. After send request to server, wait the response until mid->mid_state != SUBMITTED; 2. Receive response from server, and set it to mid; 3. Set the mid state to RECEIVED; 4. Kill the process, the mid state already RECEIVED, get 0; 5. Handle and release the negotiate response; 6. UAF. It can be easily reproduce with add some delay in [3] - [6]. Only sync call has the problem since async call's callback is executed in cifsd process. Add an extra state to mark the mid state to READY before wakeup the waitter, then it can get the resp safely.
CVE-2023-52584: In the Linux kernel, the following vulnerability has been resolved: spmi: mediatek: Fix UAF on device remove The pmif driver data that contains the clocks is allocated along with spmi_controller. On device remove, spmi_controller will be freed first, and then devres , including the clocks, will be cleanup. This leads to UAF because putting the clocks will access the clocks in the pmif driver data, which is already freed along with spmi_controller. This can be reproduced by enabling DEBUG_TEST_DRIVER_REMOVE and building the kernel with KASAN. Fix the UAF issue by using unmanaged clk_bulk_get() and putting the clocks before freeing spmi_controller.
CVE-2023-52585: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix possible NULL dereference in amdgpu_ras_query_error_status_helper() Return invalid error code -EINVAL for invalid block id. Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:1183 amdgpu_ras_query_error_status_helper() error: we previously assumed 'info' could be null (see line 1176)
CVE-2023-52586: In the Linux kernel, the following vulnerability has been resolved: drm/msm/dpu: Add mutex lock in control vblank irq Add a mutex lock to control vblank irq to synchronize vblank enable/disable operations happening from different threads to prevent race conditions while registering/unregistering the vblank irq callback. v4: -Removed vblank_ctl_lock from dpu_encoder_virt, so it is only a parameter of dpu_encoder_phys. -Switch from atomic refcnt to a simple int counter as mutex has now been added v3: Mistakenly did not change wording in last version. It is done now. v2: Slightly changed wording of commit message Patchwork: https://patchwork.freedesktop.org/patch/571854/
CVE-2023-52588: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to tag gcing flag on page during block migration It needs to add missing gcing flag on page during block migration, in order to garantee migrated data be persisted during checkpoint, otherwise out-of-order persistency between data and node may cause data corruption after SPOR. Similar issue was fixed by commit 2d1fe8a86bf5 ("f2fs: fix to tag gcing flag on page during file defragment").
CVE-2023-52589: In the Linux kernel, the following vulnerability has been resolved: media: rkisp1: Fix IRQ disable race issue In rkisp1_isp_stop() and rkisp1_csi_disable() the driver masks the interrupts and then apparently assumes that the interrupt handler won't be running, and proceeds in the stop procedure. This is not the case, as the interrupt handler can already be running, which would lead to the ISP being disabled while the interrupt handler handling a captured frame. This brings up two issues: 1) the ISP could be powered off while the interrupt handler is still running and accessing registers, leading to board lockup, and 2) the interrupt handler code and the code that disables the streaming might do things that conflict. It is not clear to me if 2) causes a real issue, but 1) can be seen with a suitable delay (or printk in my case) in the interrupt handler, leading to board lockup.
CVE-2023-52590: In the Linux kernel, the following vulnerability has been resolved: ocfs2: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change ocfs2 rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52591: In the Linux kernel, the following vulnerability has been resolved: reiserfs: Avoid touching renamed directory if parent does not change The VFS will not be locking moved directory if its parent does not change. Change reiserfs rename code to avoid touching renamed directory if its parent does not change as without locking that can corrupt the filesystem.
CVE-2023-52593: In the Linux kernel, the following vulnerability has been resolved: wifi: wfx: fix possible NULL pointer dereference in wfx_set_mfp_ap() Since 'ieee80211_beacon_get()' can return NULL, 'wfx_set_mfp_ap()' should check the return value before examining skb data. So convert the latter to return an appropriate error code and propagate it to return from 'wfx_start_ap()' as well. Compile tested only.
CVE-2023-52595: In the Linux kernel, the following vulnerability has been resolved: wifi: rt2x00: restart beacon queue when hardware reset When a hardware reset is triggered, all registers are reset, so all queues are forced to stop in hardware interface. However, mac80211 will not automatically stop the queue. If we don't manually stop the beacon queue, the queue will be deadlocked and unable to start again. This patch fixes the issue where Apple devices cannot connect to the AP after calling ieee80211_restart_hw().
CVE-2023-52596: In the Linux kernel, the following vulnerability has been resolved: sysctl: Fix out of bounds access for empty sysctl registers When registering tables to the sysctl subsystem there is a check to see if header is a permanently empty directory (used for mounts). This check evaluates the first element of the ctl_table. This results in an out of bounds evaluation when registering empty directories. The function register_sysctl_mount_point now passes a ctl_table of size 1 instead of size 0. It now relies solely on the type to identify a permanently empty register. Make sure that the ctl_table has at least one element before testing for permanent emptiness.
CVE-2023-52614: In the Linux kernel, the following vulnerability has been resolved: PM / devfreq: Fix buffer overflow in trans_stat_show Fix buffer overflow in trans_stat_show(). Convert simple snprintf to the more secure scnprintf with size of PAGE_SIZE. Add condition checking if we are exceeding PAGE_SIZE and exit early from loop. Also add at the end a warning that we exceeded PAGE_SIZE and that stats is disabled. Return -EFBIG in the case where we don't have enough space to write the full transition table. Also document in the ABI that this function can return -EFBIG error.
CVE-2023-52617: In the Linux kernel, the following vulnerability has been resolved: PCI: switchtec: Fix stdev_release() crash after surprise hot remove A PCI device hot removal may occur while stdev->cdev is held open. The call to stdev_release() then happens during close or exit, at a point way past switchtec_pci_remove(). Otherwise the last ref would vanish with the trailing put_device(), just before return. At that later point in time, the devm cleanup has already removed the stdev->mmio_mrpc mapping. Also, the stdev->pdev reference was not a counted one. Therefore, in DMA mode, the iowrite32() in stdev_release() will cause a fatal page fault, and the subsequent dma_free_coherent(), if reached, would pass a stale &stdev->pdev->dev pointer. Fix by moving MRPC DMA shutdown into switchtec_pci_remove(), after stdev_kill(). Counting the stdev->pdev ref is now optional, but may prevent future accidents. Reproducible via the script at https://lore.kernel.org/r/20231113212150.96410-1-dns@arista.com
CVE-2023-52618: In the Linux kernel, the following vulnerability has been resolved: block/rnbd-srv: Check for unlikely string overflow Since "dev_search_path" can technically be as large as PATH_MAX, there was a risk of truncation when copying it and a second string into "full_path" since it was also PATH_MAX sized. The W=1 builds were reporting this warning: drivers/block/rnbd/rnbd-srv.c: In function 'process_msg_open.isra': drivers/block/rnbd/rnbd-srv.c:616:51: warning: '%s' directive output may be truncated writing up to 254 bytes into a region of size between 0 and 4095 [-Wformat-truncation=] 616 | snprintf(full_path, PATH_MAX, "%s/%s", | ^~ In function 'rnbd_srv_get_full_path', inlined from 'process_msg_open.isra' at drivers/block/rnbd/rnbd-srv.c:721:14: drivers/block/rnbd/rnbd-srv.c:616:17: note: 'snprintf' output between 2 and 4351 bytes into a destination of size 4096 616 | snprintf(full_path, PATH_MAX, "%s/%s", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 617 | dev_search_path, dev_name); | ~~~~~~~~~~~~~~~~~~~~~~~~~~ To fix this, unconditionally check for truncation (as was already done for the case where "%SESSNAME%" was present).
CVE-2023-52621: In the Linux kernel, the following vulnerability has been resolved: bpf: Check rcu_read_lock_trace_held() before calling bpf map helpers These three bpf_map_{lookup,update,delete}_elem() helpers are also available for sleepable bpf program, so add the corresponding lock assertion for sleepable bpf program, otherwise the following warning will be reported when a sleepable bpf program manipulates bpf map under interpreter mode (aka bpf_jit_enable=0): WARNING: CPU: 3 PID: 4985 at kernel/bpf/helpers.c:40 ...... CPU: 3 PID: 4985 Comm: test_progs Not tainted 6.6.0+ #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ...... RIP: 0010:bpf_map_lookup_elem+0x54/0x60 ...... Call Trace: <TASK> ? __warn+0xa5/0x240 ? bpf_map_lookup_elem+0x54/0x60 ? report_bug+0x1ba/0x1f0 ? handle_bug+0x40/0x80 ? exc_invalid_op+0x18/0x50 ? asm_exc_invalid_op+0x1b/0x20 ? __pfx_bpf_map_lookup_elem+0x10/0x10 ? rcu_lockdep_current_cpu_online+0x65/0xb0 ? rcu_is_watching+0x23/0x50 ? bpf_map_lookup_elem+0x54/0x60 ? __pfx_bpf_map_lookup_elem+0x10/0x10 ___bpf_prog_run+0x513/0x3b70 __bpf_prog_run32+0x9d/0xd0 ? __bpf_prog_enter_sleepable_recur+0xad/0x120 ? __bpf_prog_enter_sleepable_recur+0x3e/0x120 bpf_trampoline_6442580665+0x4d/0x1000 __x64_sys_getpgid+0x5/0x30 ? do_syscall_64+0x36/0xb0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 </TASK>
CVE-2023-52624: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Wake DMCUB before executing GPINT commands [Why] DMCUB can be in idle when we attempt to interface with the HW through the GPINT mailbox resulting in a system hang. [How] Add dc_wake_and_execute_gpint() to wrap the wake, execute, sleep sequence. If the GPINT executes successfully then DMCUB will be put back into sleep after the optional response is returned. It functions similar to the inbox command interface.
CVE-2023-52625: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Refactor DMCUB enter/exit idle interface [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] We need to exit out of the idle state prior to sending a command, but the process that performs the exit also invokes a command itself. Fixing this issue involves the following: 1. Using a software state to track whether or not we need to start the process to exit idle or notify idle. It's possible for the hardware to have exited an idle state without driver knowledge, but entering one is always restricted to a driver allow - which makes the SW state vs HW state mismatch issue purely one of optimization, which should seldomly be hit, if at all. 2. Refactor any instances of exit/notify idle to use a single wrapper that maintains this SW state. This works simialr to dc_allow_idle_optimizations, but works at the DMCUB level and makes sure the state is marked prior to any notify/exit idle so we don't enter an infinite loop. 3. Make sure we exit out of idle prior to sending any commands or waiting for DMCUB idle. This patch takes care of 1/2. A future patch will take care of wrapping DMCUB command submission with calls to this new interface.
CVE-2023-52629: In the Linux kernel, the following vulnerability has been resolved: sh: push-switch: Reorder cleanup operations to avoid use-after-free bug The original code puts flush_work() before timer_shutdown_sync() in switch_drv_remove(). Although we use flush_work() to stop the worker, it could be rescheduled in switch_timer(). As a result, a use-after-free bug can occur. The details are shown below: (cpu 0) | (cpu 1) switch_drv_remove() | flush_work() | ... | switch_timer // timer | schedule_work(&psw->work) timer_shutdown_sync() | ... | switch_work_handler // worker kfree(psw) // free | | psw->state = 0 // use This patch puts timer_shutdown_sync() before flush_work() to mitigate the bugs. As a result, the worker and timer will be stopped safely before the deallocate operations.
CVE-2023-52632: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Fix lock dependency warning with srcu ====================================================== WARNING: possible circular locking dependency detected 6.5.0-kfd-yangp #2289 Not tainted ------------------------------------------------------ kworker/0:2/996 is trying to acquire lock: (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0 but task is already holding lock: ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at: process_one_work+0x211/0x560 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu] svm_range_set_attr+0xd6/0x14c0 [amdgpu] kfd_ioctl+0x1d1/0x630 [amdgpu] __x64_sys_ioctl+0x88/0xc0 -> #2 (&info->lock#2){+.+.}-{3:3}: __mutex_lock+0x99/0xc70 amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu] restore_process_helper+0x22/0x80 [amdgpu] restore_process_worker+0x2d/0xa0 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 -> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 __cancel_work_timer+0x12c/0x1c0 kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu] __mmu_notifier_release+0xad/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 do_exit+0x322/0xb90 do_group_exit+0x37/0xa0 __x64_sys_exit_group+0x18/0x20 do_syscall_64+0x38/0x80 -> #0 (srcu){.+.+}-{0:0}: __lock_acquire+0x1521/0x2510 lock_sync+0x5f/0x90 __synchronize_srcu+0x4f/0x1a0 __mmu_notifier_release+0x128/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 svm_range_deferred_list_work+0x19f/0x350 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 other info that might help us debug this: Chain exists of: srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&svms->deferred_list_work)); lock(&info->lock#2); lock((work_completion)(&svms->deferred_list_work)); sync(srcu);
CVE-2023-52633: In the Linux kernel, the following vulnerability has been resolved: um: time-travel: fix time corruption In 'basic' time-travel mode (without =inf-cpu or =ext), we still get timer interrupts. These can happen at arbitrary points in time, i.e. while in timer_read(), which pushes time forward just a little bit. Then, if we happen to get the interrupt after calculating the new time to push to, but before actually finishing that, the interrupt will set the time to a value that's incompatible with the forward, and we'll crash because time goes backwards when we do the forwarding. Fix this by reading the time_travel_time, calculating the adjustment, and doing the adjustment all with interrupts disabled.
CVE-2023-52634: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix disable_otg_wa logic [Why] When switching to another HDMI mode, we are unnecesarilly disabling/enabling FIFO causing both HPO and DIG registers to be set at the same time when only HPO is supposed to be set. This can lead to a system hang the next time we change refresh rates as there are cases when we don't disable OTG/FIFO but FIFO is enabled when it isn't supposed to be. [How] Removing the enable/disable FIFO entirely.
CVE-2023-52635: In the Linux kernel, the following vulnerability has been resolved: PM / devfreq: Synchronize devfreq_monitor_[start/stop] There is a chance if a frequent switch of the governor done in a loop result in timer list corruption where timer cancel being done from two place one from cancel_delayed_work_sync() and followed by expire_timers() can be seen from the traces[1]. while true do echo "simple_ondemand" > /sys/class/devfreq/1d84000.ufshc/governor echo "performance" > /sys/class/devfreq/1d84000.ufshc/governor done It looks to be issue with devfreq driver where device_monitor_[start/stop] need to synchronized so that delayed work should get corrupted while it is either being queued or running or being cancelled. Let's use polling flag and devfreq lock to synchronize the queueing the timer instance twice and work data being corrupted. [1] ... .. <idle>-0 [003] 9436.209662: timer_cancel timer=0xffffff80444f0428 <idle>-0 [003] 9436.209664: timer_expire_entry timer=0xffffff80444f0428 now=0x10022da1c function=__typeid__ZTSFvP10timer_listE_global_addr baseclk=0x10022da1c <idle>-0 [003] 9436.209718: timer_expire_exit timer=0xffffff80444f0428 kworker/u16:6-14217 [003] 9436.209863: timer_start timer=0xffffff80444f0428 function=__typeid__ZTSFvP10timer_listE_global_addr expires=0x10022da2b now=0x10022da1c flags=182452227 vendor.xxxyyy.ha-1593 [004] 9436.209888: timer_cancel timer=0xffffff80444f0428 vendor.xxxyyy.ha-1593 [004] 9436.216390: timer_init timer=0xffffff80444f0428 vendor.xxxyyy.ha-1593 [004] 9436.216392: timer_start timer=0xffffff80444f0428 function=__typeid__ZTSFvP10timer_listE_global_addr expires=0x10022da2c now=0x10022da1d flags=186646532 vendor.xxxyyy.ha-1593 [005] 9436.220992: timer_cancel timer=0xffffff80444f0428 xxxyyyTraceManag-7795 [004] 9436.261641: timer_cancel timer=0xffffff80444f0428 [2] 9436.261653][ C4] Unable to handle kernel paging request at virtual address dead00000000012a [ 9436.261664][ C4] Mem abort info: [ 9436.261666][ C4] ESR = 0x96000044 [ 9436.261669][ C4] EC = 0x25: DABT (current EL), IL = 32 bits [ 9436.261671][ C4] SET = 0, FnV = 0 [ 9436.261673][ C4] EA = 0, S1PTW = 0 [ 9436.261675][ C4] Data abort info: [ 9436.261677][ C4] ISV = 0, ISS = 0x00000044 [ 9436.261680][ C4] CM = 0, WnR = 1 [ 9436.261682][ C4] [dead00000000012a] address between user and kernel address ranges [ 9436.261685][ C4] Internal error: Oops: 96000044 [#1] PREEMPT SMP [ 9436.261701][ C4] Skip md ftrace buffer dump for: 0x3a982d0 ... [ 9436.262138][ C4] CPU: 4 PID: 7795 Comm: TraceManag Tainted: G S W O 5.10.149-android12-9-o-g17f915d29d0c #1 [ 9436.262141][ C4] Hardware name: Qualcomm Technologies, Inc. (DT) [ 9436.262144][ C4] pstate: 22400085 (nzCv daIf +PAN -UAO +TCO BTYPE=--) [ 9436.262161][ C4] pc : expire_timers+0x9c/0x438 [ 9436.262164][ C4] lr : expire_timers+0x2a4/0x438 [ 9436.262168][ C4] sp : ffffffc010023dd0 [ 9436.262171][ C4] x29: ffffffc010023df0 x28: ffffffd0636fdc18 [ 9436.262178][ C4] x27: ffffffd063569dd0 x26: ffffffd063536008 [ 9436.262182][ C4] x25: 0000000000000001 x24: ffffff88f7c69280 [ 9436.262185][ C4] x23: 00000000000000e0 x22: dead000000000122 [ 9436.262188][ C4] x21: 000000010022da29 x20: ffffff8af72b4e80 [ 9436.262191][ C4] x19: ffffffc010023e50 x18: ffffffc010025038 [ 9436.262195][ C4] x17: 0000000000000240 x16: 0000000000000201 [ 9436.262199][ C4] x15: ffffffffffffffff x14: ffffff889f3c3100 [ 9436.262203][ C4] x13: ffffff889f3c3100 x12: 00000000049f56b8 [ 9436.262207][ C4] x11: 00000000049f56b8 x10: 00000000ffffffff [ 9436.262212][ C4] x9 : ffffffc010023e50 x8 : dead000000000122 [ 9436.262216][ C4] x7 : ffffffffffffffff x6 : ffffffc0100239d8 [ 9436.262220][ C4] x5 : 0000000000000000 x4 : 0000000000000101 [ 9436.262223][ C4] x3 : 0000000000000080 x2 : ffffff8 ---truncated---
CVE-2023-52638: In the Linux kernel, the following vulnerability has been resolved: can: j1939: prevent deadlock by changing j1939_socks_lock to rwlock The following 3 locks would race against each other, causing the deadlock situation in the Syzbot bug report: - j1939_socks_lock - active_session_list_lock - sk_session_queue_lock A reasonable fix is to change j1939_socks_lock to an rwlock, since in the rare situations where a write lock is required for the linked list that j1939_socks_lock is protecting, the code does not attempt to acquire any more locks. This would break the circular lock dependency, where, for example, the current thread already locks j1939_socks_lock and attempts to acquire sk_session_queue_lock, and at the same time, another thread attempts to acquire j1939_socks_lock while holding sk_session_queue_lock. NOTE: This patch along does not fix the unregister_netdevice bug reported by Syzbot; instead, it solves a deadlock situation to prepare for one or more further patches to actually fix the Syzbot bug, which appears to be a reference counting problem within the j1939 codebase. [mkl: remove unrelated newline change]
CVE-2023-52639: In the Linux kernel, the following vulnerability has been resolved: KVM: s390: vsie: fix race during shadow creation Right now it is possible to see gmap->private being zero in kvm_s390_vsie_gmap_notifier resulting in a crash. This is due to the fact that we add gmap->private == kvm after creation: static int acquire_gmap_shadow(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { [...] gmap = gmap_shadow(vcpu->arch.gmap, asce, edat); if (IS_ERR(gmap)) return PTR_ERR(gmap); gmap->private = vcpu->kvm; Let children inherit the private field of the parent.
CVE-2023-52640: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Fix oob in ntfs_listxattr The length of name cannot exceed the space occupied by ea.
CVE-2023-52641: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Add NULL ptr dereference checking at the end of attr_allocate_frame() It is preferable to exit through the out: label because internal debugging functions are located there.
CVE-2023-52642: In the Linux kernel, the following vulnerability has been resolved: media: rc: bpf attach/detach requires write permission Note that bpf attach/detach also requires CAP_NET_ADMIN.
CVE-2023-52652: In the Linux kernel, the following vulnerability has been resolved: NTB: fix possible name leak in ntb_register_device() If device_register() fails in ntb_register_device(), the device name allocated by dev_set_name() should be freed. As per the comment in device_register(), callers should use put_device() to give up the reference in the error path. So fix this by calling put_device() in the error path so that the name can be freed in kobject_cleanup(). As a result of this, put_device() in the error path of ntb_register_device() is removed and the actual error is returned. [mani: reworded commit message]
CVE-2023-52653: In the Linux kernel, the following vulnerability has been resolved: SUNRPC: fix a memleak in gss_import_v2_context The ctx->mech_used.data allocated by kmemdup is not freed in neither gss_import_v2_context nor it only caller gss_krb5_import_sec_context, which frees ctx on error. Thus, this patch reform the last call of gss_import_v2_context to the gss_krb5_import_ctx_v2, preventing the memleak while keepping the return formation.
CVE-2023-52655: In the Linux kernel, the following vulnerability has been resolved: usb: aqc111: check packet for fixup for true limit If a device sends a packet that is inbetween 0 and sizeof(u64) the value passed to skb_trim() as length will wrap around ending up as some very large value. The driver will then proceed to parse the header located at that position, which will either oops or process some random value. The fix is to check against sizeof(u64) rather than 0, which the driver currently does. The issue exists since the introduction of the driver.
CVE-2023-52656: In the Linux kernel, the following vulnerability has been resolved: io_uring: drop any code related to SCM_RIGHTS This is dead code after we dropped support for passing io_uring fds over SCM_RIGHTS, get rid of it.
CVE-2023-52660: In the Linux kernel, the following vulnerability has been resolved: media: rkisp1: Fix IRQ handling due to shared interrupts The driver requests the interrupts as IRQF_SHARED, so the interrupt handlers can be called at any time. If such a call happens while the ISP is powered down, the SoC will hang as the driver tries to access the ISP registers. This can be reproduced even without the platform sharing the IRQ line: Enable CONFIG_DEBUG_SHIRQ and unload the driver, and the board will hang. Fix this by adding a new field, 'irqs_enabled', which is used to bail out from the interrupt handler when the ISP is not operational.
CVE-2023-52664: In the Linux kernel, the following vulnerability has been resolved: net: atlantic: eliminate double free in error handling logic Driver has a logic leak in ring data allocation/free, where aq_ring_free could be called multiple times on same ring, if system is under stress and got memory allocation error. Ring pointer was used as an indicator of failure, but this is not correct since only ring data is allocated/deallocated. Ring itself is an array member. Changing ring allocation functions to return error code directly. This simplifies error handling and eliminates aq_ring_free on higher layer.
CVE-2023-52669: In the Linux kernel, the following vulnerability has been resolved: crypto: s390/aes - Fix buffer overread in CTR mode When processing the last block, the s390 ctr code will always read a whole block, even if there isn't a whole block of data left. Fix this by using the actual length left and copy it into a buffer first for processing.
CVE-2023-52671: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix hang/underflow when transitioning to ODM4:1 [Why] Under some circumstances, disabling an OPTC and attempting to reclaim its OPP(s) for a different OPTC could cause a hang/underflow due to OPPs not being properly disconnected from the disabled OPTC. [How] Ensure that all OPPs are unassigned from an OPTC when it gets disabled.
CVE-2023-52673: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix a debugfs null pointer error [WHY & HOW] Check whether get_subvp_en() callback exists before calling it.
CVE-2023-52676: In the Linux kernel, the following vulnerability has been resolved: bpf: Guard stack limits against 32bit overflow This patch promotes the arithmetic around checking stack bounds to be done in the 64-bit domain, instead of the current 32bit. The arithmetic implies adding together a 64-bit register with a int offset. The register was checked to be below 1<<29 when it was variable, but not when it was fixed. The offset either comes from an instruction (in which case it is 16 bit), from another register (in which case the caller checked it to be below 1<<29 [1]), or from the size of an argument to a kfunc (in which case it can be a u32 [2]). Between the register being inconsistently checked to be below 1<<29, and the offset being up to an u32, it appears that we were open to overflowing the `int`s which were currently used for arithmetic. [1] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L7494-L7498 [2] https://github.com/torvalds/linux/blob/815fb87b753055df2d9e50f6cd80eb10235fe3e9/kernel/bpf/verifier.c#L11904
CVE-2023-52700: In the Linux kernel, the following vulnerability has been resolved: tipc: fix kernel warning when sending SYN message When sending a SYN message, this kernel stack trace is observed: ... [ 13.396352] RIP: 0010:_copy_from_iter+0xb4/0x550 ... [ 13.398494] Call Trace: [ 13.398630] <TASK> [ 13.398630] ? __alloc_skb+0xed/0x1a0 [ 13.398630] tipc_msg_build+0x12c/0x670 [tipc] [ 13.398630] ? shmem_add_to_page_cache.isra.71+0x151/0x290 [ 13.398630] __tipc_sendmsg+0x2d1/0x710 [tipc] [ 13.398630] ? tipc_connect+0x1d9/0x230 [tipc] [ 13.398630] ? __local_bh_enable_ip+0x37/0x80 [ 13.398630] tipc_connect+0x1d9/0x230 [tipc] [ 13.398630] ? __sys_connect+0x9f/0xd0 [ 13.398630] __sys_connect+0x9f/0xd0 [ 13.398630] ? preempt_count_add+0x4d/0xa0 [ 13.398630] ? fpregs_assert_state_consistent+0x22/0x50 [ 13.398630] __x64_sys_connect+0x16/0x20 [ 13.398630] do_syscall_64+0x42/0x90 [ 13.398630] entry_SYSCALL_64_after_hwframe+0x63/0xcd It is because commit a41dad905e5a ("iov_iter: saner checks for attempt to copy to/from iterator") has introduced sanity check for copying from/to iov iterator. Lacking of copy direction from the iterator viewpoint would lead to kernel stack trace like above. This commit fixes this issue by initializing the iov iterator with the correct copy direction when sending SYN or ACK without data.
CVE-2023-52708: In the Linux kernel, the following vulnerability has been resolved: mmc: mmc_spi: fix error handling in mmc_spi_probe() If mmc_add_host() fails, it doesn't need to call mmc_remove_host(), or it will cause null-ptr-deref, because of deleting a not added device in mmc_remove_host(). To fix this, goto label 'fail_glue_init', if mmc_add_host() fails, and change the label 'fail_add_host' to 'fail_gpiod_request'.
CVE-2023-52732: In the Linux kernel, the following vulnerability has been resolved: ceph: blocklist the kclient when receiving corrupted snap trace When received corrupted snap trace we don't know what exactly has happened in MDS side. And we shouldn't continue IOs and metadatas access to MDS, which may corrupt or get incorrect contents. This patch will just block all the further IO/MDS requests immediately and then evict the kclient itself. The reason why we still need to evict the kclient just after blocking all the further IOs is that the MDS could revoke the caps faster.
CVE-2023-52733: In the Linux kernel, the following vulnerability has been resolved: s390/decompressor: specify __decompress() buf len to avoid overflow Historically calls to __decompress() didn't specify "out_len" parameter on many architectures including s390, expecting that no writes beyond uncompressed kernel image are performed. This has changed since commit 2aa14b1ab2c4 ("zstd: import usptream v1.5.2") which includes zstd library commit 6a7ede3dfccb ("Reduce size of dctx by reutilizing dst buffer (#2751)"). Now zstd decompression code might store literal buffer in the unwritten portion of the destination buffer. Since "out_len" is not set, it is considered to be unlimited and hence free to use for optimization needs. On s390 this might corrupt initrd or ipl report which are often placed right after the decompressor buffer. Luckily the size of uncompressed kernel image is already known to the decompressor, so to avoid the problem simply specify it in the "out_len" parameter.
CVE-2023-52735: In the Linux kernel, the following vulnerability has been resolved: bpf, sockmap: Don't let sock_map_{close,destroy,unhash} call itself sock_map proto callbacks should never call themselves by design. Protect against bugs like [1] and break out of the recursive loop to avoid a stack overflow in favor of a resource leak. [1] https://lore.kernel.org/all/00000000000073b14905ef2e7401@google.com/
CVE-2023-52736: In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: Do not unset preset when cleaning up codec Several functions that take part in codec's initialization and removal are re-used by ASoC codec drivers implementations. Drivers mimic the behavior of hda_codec_driver_probe/remove() found in sound/pci/hda/hda_bind.c with their component->probe/remove() instead. One of the reasons for that is the expectation of snd_hda_codec_device_new() to receive a valid pointer to an instance of struct snd_card. This expectation can be met only once sound card components probing commences. As ASoC sound card may be unbound without codec device being actually removed from the system, unsetting ->preset in snd_hda_codec_cleanup_for_unbind() interferes with module unload -> load scenario causing null-ptr-deref. Preset is assigned only once, during device/driver matching whereas ASoC codec driver's module reloading may occur several times throughout the lifetime of an audio stack.
CVE-2023-52737: In the Linux kernel, the following vulnerability has been resolved: btrfs: lock the inode in shared mode before starting fiemap Currently fiemap does not take the inode's lock (VFS lock), it only locks a file range in the inode's io tree. This however can lead to a deadlock if we have a concurrent fsync on the file and fiemap code triggers a fault when accessing the user space buffer with fiemap_fill_next_extent(). The deadlock happens on the inode's i_mmap_lock semaphore, which is taken both by fsync and btrfs_page_mkwrite(). This deadlock was recently reported by syzbot and triggers a trace like the following: task:syz-executor361 state:D stack:20264 pid:5668 ppid:5119 flags:0x00004004 Call Trace: <TASK> context_switch kernel/sched/core.c:5293 [inline] __schedule+0x995/0xe20 kernel/sched/core.c:6606 schedule+0xcb/0x190 kernel/sched/core.c:6682 wait_on_state fs/btrfs/extent-io-tree.c:707 [inline] wait_extent_bit+0x577/0x6f0 fs/btrfs/extent-io-tree.c:751 lock_extent+0x1c2/0x280 fs/btrfs/extent-io-tree.c:1742 find_lock_delalloc_range+0x4e6/0x9c0 fs/btrfs/extent_io.c:488 writepage_delalloc+0x1ef/0x540 fs/btrfs/extent_io.c:1863 __extent_writepage+0x736/0x14e0 fs/btrfs/extent_io.c:2174 extent_write_cache_pages+0x983/0x1220 fs/btrfs/extent_io.c:3091 extent_writepages+0x219/0x540 fs/btrfs/extent_io.c:3211 do_writepages+0x3c3/0x680 mm/page-writeback.c:2581 filemap_fdatawrite_wbc+0x11e/0x170 mm/filemap.c:388 __filemap_fdatawrite_range mm/filemap.c:421 [inline] filemap_fdatawrite_range+0x175/0x200 mm/filemap.c:439 btrfs_fdatawrite_range fs/btrfs/file.c:3850 [inline] start_ordered_ops fs/btrfs/file.c:1737 [inline] btrfs_sync_file+0x4ff/0x1190 fs/btrfs/file.c:1839 generic_write_sync include/linux/fs.h:2885 [inline] btrfs_do_write_iter+0xcd3/0x1280 fs/btrfs/file.c:1684 call_write_iter include/linux/fs.h:2189 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x7dc/0xc50 fs/read_write.c:584 ksys_write+0x177/0x2a0 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f7d4054e9b9 RSP: 002b:00007f7d404fa2f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007f7d405d87a0 RCX: 00007f7d4054e9b9 RDX: 0000000000000090 RSI: 0000000020000000 RDI: 0000000000000006 RBP: 00007f7d405a51d0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 61635f65646f6e69 R13: 65646f7475616f6e R14: 7261637369646f6e R15: 00007f7d405d87a8 </TASK> INFO: task syz-executor361:5697 blocked for more than 145 seconds. Not tainted 6.2.0-rc3-syzkaller-00376-g7c6984405241 #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor361 state:D stack:21216 pid:5697 ppid:5119 flags:0x00004004 Call Trace: <TASK> context_switch kernel/sched/core.c:5293 [inline] __schedule+0x995/0xe20 kernel/sched/core.c:6606 schedule+0xcb/0x190 kernel/sched/core.c:6682 rwsem_down_read_slowpath+0x5f9/0x930 kernel/locking/rwsem.c:1095 __down_read_common+0x54/0x2a0 kernel/locking/rwsem.c:1260 btrfs_page_mkwrite+0x417/0xc80 fs/btrfs/inode.c:8526 do_page_mkwrite+0x19e/0x5e0 mm/memory.c:2947 wp_page_shared+0x15e/0x380 mm/memory.c:3295 handle_pte_fault mm/memory.c:4949 [inline] __handle_mm_fault mm/memory.c:5073 [inline] handle_mm_fault+0x1b79/0x26b0 mm/memory.c:5219 do_user_addr_fault+0x69b/0xcb0 arch/x86/mm/fault.c:1428 handle_page_fault arch/x86/mm/fault.c:1519 [inline] exc_page_fault+0x7a/0x110 arch/x86/mm/fault.c:1575 asm_exc_page_fault+0x22/0x30 arch/x86/include/asm/idtentry.h:570 RIP: 0010:copy_user_short_string+0xd/0x40 arch/x86/lib/copy_user_64.S:233 Code: 74 0a 89 (...) RSP: 0018:ffffc9000570f330 EFLAGS: 000502 ---truncated---
CVE-2023-52741: In the Linux kernel, the following vulnerability has been resolved: cifs: Fix use-after-free in rdata->read_into_pages() When the network status is unstable, use-after-free may occur when read data from the server. BUG: KASAN: use-after-free in readpages_fill_pages+0x14c/0x7e0 Call Trace: <TASK> dump_stack_lvl+0x38/0x4c print_report+0x16f/0x4a6 kasan_report+0xb7/0x130 readpages_fill_pages+0x14c/0x7e0 cifs_readv_receive+0x46d/0xa40 cifs_demultiplex_thread+0x121c/0x1490 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 </TASK> Allocated by task 2535: kasan_save_stack+0x22/0x50 kasan_set_track+0x25/0x30 __kasan_kmalloc+0x82/0x90 cifs_readdata_direct_alloc+0x2c/0x110 cifs_readdata_alloc+0x2d/0x60 cifs_readahead+0x393/0xfe0 read_pages+0x12f/0x470 page_cache_ra_unbounded+0x1b1/0x240 filemap_get_pages+0x1c8/0x9a0 filemap_read+0x1c0/0x540 cifs_strict_readv+0x21b/0x240 vfs_read+0x395/0x4b0 ksys_read+0xb8/0x150 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 79: kasan_save_stack+0x22/0x50 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2e/0x50 __kasan_slab_free+0x10e/0x1a0 __kmem_cache_free+0x7a/0x1a0 cifs_readdata_release+0x49/0x60 process_one_work+0x46c/0x760 worker_thread+0x2a4/0x6f0 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 Last potentially related work creation: kasan_save_stack+0x22/0x50 __kasan_record_aux_stack+0x95/0xb0 insert_work+0x2b/0x130 __queue_work+0x1fe/0x660 queue_work_on+0x4b/0x60 smb2_readv_callback+0x396/0x800 cifs_abort_connection+0x474/0x6a0 cifs_reconnect+0x5cb/0xa50 cifs_readv_from_socket.cold+0x22/0x6c cifs_read_page_from_socket+0xc1/0x100 readpages_fill_pages.cold+0x2f/0x46 cifs_readv_receive+0x46d/0xa40 cifs_demultiplex_thread+0x121c/0x1490 kthread+0x16b/0x1a0 ret_from_fork+0x2c/0x50 The following function calls will cause UAF of the rdata pointer. readpages_fill_pages cifs_read_page_from_socket cifs_readv_from_socket cifs_reconnect __cifs_reconnect cifs_abort_connection mid->callback() --> smb2_readv_callback queue_work(&rdata->work) # if the worker completes first, # the rdata is freed cifs_readv_complete kref_put cifs_readdata_release kfree(rdata) return rdata->... # UAF in readpages_fill_pages() Similarly, this problem also occurs in the uncache_fill_pages(). Fix this by adjusts the order of condition judgment in the return statement.
CVE-2023-52743: In the Linux kernel, the following vulnerability has been resolved: ice: Do not use WQ_MEM_RECLAIM flag for workqueue When both ice and the irdma driver are loaded, a warning in check_flush_dependency is being triggered. This is due to ice driver workqueue being allocated with the WQ_MEM_RECLAIM flag and the irdma one is not. According to kernel documentation, this flag should be set if the workqueue will be involved in the kernel's memory reclamation flow. Since it is not, there is no need for the ice driver's WQ to have this flag set so remove it. Example trace: [ +0.000004] workqueue: WQ_MEM_RECLAIM ice:ice_service_task [ice] is flushing !WQ_MEM_RECLAIM infiniband:0x0 [ +0.000139] WARNING: CPU: 0 PID: 728 at kernel/workqueue.c:2632 check_flush_dependency+0x178/0x1a0 [ +0.000011] Modules linked in: bonding tls xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_cha in_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink bridge stp llc rfkill vfat fat intel_rapl_msr intel _rapl_common isst_if_common skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct1 0dif_pclmul crc32_pclmul ghash_clmulni_intel rapl intel_cstate rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_ core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_cm iw_cm iTCO_wdt iTCO_vendor_support ipmi_ssif irdma mei_me ib_uverbs ib_core intel_uncore joydev pcspkr i2c_i801 acpi_ipmi mei lpc_ich i2c_smbus intel_pch_thermal ioatdma ipmi_si acpi_power_meter acpi_pad xfs libcrc32c sd_mod t10_pi crc64_rocksoft crc64 sg ahci ixgbe libahci ice i40e igb crc32c_intel mdio i2c_algo_bit liba ta dca wmi dm_mirror dm_region_hash dm_log dm_mod ipmi_devintf ipmi_msghandler fuse [ +0.000161] [last unloaded: bonding] [ +0.000006] CPU: 0 PID: 728 Comm: kworker/0:2 Tainted: G S 6.2.0-rc2_next-queue-13jan-00458-gc20aabd57164 #1 [ +0.000006] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0010.010620200716 01/06/2020 [ +0.000003] Workqueue: ice ice_service_task [ice] [ +0.000127] RIP: 0010:check_flush_dependency+0x178/0x1a0 [ +0.000005] Code: 89 8e 02 01 e8 49 3d 40 00 49 8b 55 18 48 8d 8d d0 00 00 00 48 8d b3 d0 00 00 00 4d 89 e0 48 c7 c7 e0 3b 08 9f e8 bb d3 07 01 <0f> 0b e9 be fe ff ff 80 3d 24 89 8e 02 00 0f 85 6b ff ff ff e9 06 [ +0.000004] RSP: 0018:ffff88810a39f990 EFLAGS: 00010282 [ +0.000005] RAX: 0000000000000000 RBX: ffff888141bc2400 RCX: 0000000000000000 [ +0.000004] RDX: 0000000000000001 RSI: dffffc0000000000 RDI: ffffffffa1213a80 [ +0.000003] RBP: ffff888194bf3400 R08: ffffed117b306112 R09: ffffed117b306112 [ +0.000003] R10: ffff888bd983088b R11: ffffed117b306111 R12: 0000000000000000 [ +0.000003] R13: ffff888111f84d00 R14: ffff88810a3943ac R15: ffff888194bf3400 [ +0.000004] FS: 0000000000000000(0000) GS:ffff888bd9800000(0000) knlGS:0000000000000000 [ +0.000003] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000003] CR2: 000056035b208b60 CR3: 000000017795e005 CR4: 00000000007706f0 [ +0.000003] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ +0.000003] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ +0.000002] PKRU: 55555554 [ +0.000003] Call Trace: [ +0.000002] <TASK> [ +0.000003] __flush_workqueue+0x203/0x840 [ +0.000006] ? mutex_unlock+0x84/0xd0 [ +0.000008] ? __pfx_mutex_unlock+0x10/0x10 [ +0.000004] ? __pfx___flush_workqueue+0x10/0x10 [ +0.000006] ? mutex_lock+0xa3/0xf0 [ +0.000005] ib_cache_cleanup_one+0x39/0x190 [ib_core] [ +0.000174] __ib_unregister_device+0x84/0xf0 [ib_core] [ +0.000094] ib_unregister_device+0x25/0x30 [ib_core] [ +0.000093] irdma_ib_unregister_device+0x97/0xc0 [irdma] [ +0.000064] ? __pfx_irdma_ib_unregister_device+0x10/0x10 [irdma] [ +0.000059] ? up_write+0x5c/0x90 [ +0.000005] irdma_remove+0x36/0x90 [irdma] [ +0.000062] auxiliary_bus_remove+0x32/0x50 [ +0.000007] device_r ---truncated---
CVE-2023-52745: In the Linux kernel, the following vulnerability has been resolved: IB/IPoIB: Fix legacy IPoIB due to wrong number of queues The cited commit creates child PKEY interfaces over netlink will multiple tx and rx queues, but some devices doesn't support more than 1 tx and 1 rx queues. This causes to a crash when traffic is sent over the PKEY interface due to the parent having a single queue but the child having multiple queues. This patch fixes the number of queues to 1 for legacy IPoIB at the earliest possible point in time. BUG: kernel NULL pointer dereference, address: 000000000000036b PGD 0 P4D 0 Oops: 0000 [#1] SMP CPU: 4 PID: 209665 Comm: python3 Not tainted 6.1.0_for_upstream_min_debug_2022_12_12_17_02 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:kmem_cache_alloc+0xcb/0x450 Code: ce 7e 49 8b 50 08 49 83 78 10 00 4d 8b 28 0f 84 cb 02 00 00 4d 85 ed 0f 84 c2 02 00 00 41 8b 44 24 28 48 8d 4a 01 49 8b 3c 24 <49> 8b 5c 05 00 4c 89 e8 65 48 0f c7 0f 0f 94 c0 84 c0 74 b8 41 8b RSP: 0018:ffff88822acbbab8 EFLAGS: 00010202 RAX: 0000000000000070 RBX: ffff8881c28e3e00 RCX: 00000000064f8dae RDX: 00000000064f8dad RSI: 0000000000000a20 RDI: 0000000000030d00 RBP: 0000000000000a20 R08: ffff8882f5d30d00 R09: ffff888104032f40 R10: ffff88810fade828 R11: 736f6d6570736575 R12: ffff88810081c000 R13: 00000000000002fb R14: ffffffff817fc865 R15: 0000000000000000 FS: 00007f9324ff9700(0000) GS:ffff8882f5d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000036b CR3: 00000001125af004 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> skb_clone+0x55/0xd0 ip6_finish_output2+0x3fe/0x690 ip6_finish_output+0xfa/0x310 ip6_send_skb+0x1e/0x60 udp_v6_send_skb+0x1e5/0x420 udpv6_sendmsg+0xb3c/0xe60 ? ip_mc_finish_output+0x180/0x180 ? __switch_to_asm+0x3a/0x60 ? __switch_to_asm+0x34/0x60 sock_sendmsg+0x33/0x40 __sys_sendto+0x103/0x160 ? _copy_to_user+0x21/0x30 ? kvm_clock_get_cycles+0xd/0x10 ? ktime_get_ts64+0x49/0xe0 __x64_sys_sendto+0x25/0x30 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f9374f1ed14 Code: 42 41 f8 ff 44 8b 4c 24 2c 4c 8b 44 24 20 89 c5 44 8b 54 24 28 48 8b 54 24 18 b8 2c 00 00 00 48 8b 74 24 10 8b 7c 24 08 0f 05 <48> 3d 00 f0 ff ff 77 34 89 ef 48 89 44 24 08 e8 68 41 f8 ff 48 8b RSP: 002b:00007f9324ff7bd0 EFLAGS: 00000293 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f9324ff7cc8 RCX: 00007f9374f1ed14 RDX: 00000000000002fb RSI: 00007f93000052f0 RDI: 0000000000000030 RBP: 0000000000000000 R08: 00007f9324ff7d40 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000000 R13: 000000012a05f200 R14: 0000000000000001 R15: 00007f9374d57bdc </TASK>
CVE-2023-52748: In the Linux kernel, the following vulnerability has been resolved: f2fs: avoid format-overflow warning With gcc and W=1 option, there's a warning like this: fs/f2fs/compress.c: In function ‘f2fs_init_page_array_cache’: fs/f2fs/compress.c:1984:47: error: ‘%u’ directive writing between 1 and 7 bytes into a region of size between 5 and 8 [-Werror=format-overflow=] 1984 | sprintf(slab_name, "f2fs_page_array_entry-%u:%u", MAJOR(dev), MINOR(dev)); | ^~ String "f2fs_page_array_entry-%u:%u" can up to 35. The first "%u" can up to 4 and the second "%u" can up to 7, so total size is "24 + 4 + 7 = 35". slab_name's size should be 35 rather than 32.
CVE-2023-52749: In the Linux kernel, the following vulnerability has been resolved: spi: Fix null dereference on suspend A race condition exists where a synchronous (noqueue) transfer can be active during a system suspend. This can cause a null pointer dereference exception to occur when the system resumes. Example order of events leading to the exception: 1. spi_sync() calls __spi_transfer_message_noqueue() which sets ctlr->cur_msg 2. Spi transfer begins via spi_transfer_one_message() 3. System is suspended interrupting the transfer context 4. System is resumed 6. spi_controller_resume() calls spi_start_queue() which resets cur_msg to NULL 7. Spi transfer context resumes and spi_finalize_current_message() is called which dereferences cur_msg (which is now NULL) Wait for synchronous transfers to complete before suspending by acquiring the bus mutex and setting/checking a suspend flag.
CVE-2023-52750: In the Linux kernel, the following vulnerability has been resolved: arm64: Restrict CPU_BIG_ENDIAN to GNU as or LLVM IAS 15.x or newer Prior to LLVM 15.0.0, LLVM's integrated assembler would incorrectly byte-swap NOP when compiling for big-endian, and the resulting series of bytes happened to match the encoding of FNMADD S21, S30, S0, S0. This went unnoticed until commit: 34f66c4c4d5518c1 ("arm64: Use a positive cpucap for FP/SIMD") Prior to that commit, the kernel would always enable the use of FPSIMD early in boot when __cpu_setup() initialized CPACR_EL1, and so usage of FNMADD within the kernel was not detected, but could result in the corruption of user or kernel FPSIMD state. After that commit, the instructions happen to trap during boot prior to FPSIMD being detected and enabled, e.g. | Unhandled 64-bit el1h sync exception on CPU0, ESR 0x000000001fe00000 -- ASIMD | CPU: 0 PID: 0 Comm: swapper Not tainted 6.6.0-rc3-00013-g34f66c4c4d55 #1 | Hardware name: linux,dummy-virt (DT) | pstate: 400000c9 (nZcv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : __pi_strcmp+0x1c/0x150 | lr : populate_properties+0xe4/0x254 | sp : ffffd014173d3ad0 | x29: ffffd014173d3af0 x28: fffffbfffddffcb8 x27: 0000000000000000 | x26: 0000000000000058 x25: fffffbfffddfe054 x24: 0000000000000008 | x23: fffffbfffddfe000 x22: fffffbfffddfe000 x21: fffffbfffddfe044 | x20: ffffd014173d3b70 x19: 0000000000000001 x18: 0000000000000005 | x17: 0000000000000010 x16: 0000000000000000 x15: 00000000413e7000 | x14: 0000000000000000 x13: 0000000000001bcc x12: 0000000000000000 | x11: 00000000d00dfeed x10: ffffd414193f2cd0 x9 : 0000000000000000 | x8 : 0101010101010101 x7 : ffffffffffffffc0 x6 : 0000000000000000 | x5 : 0000000000000000 x4 : 0101010101010101 x3 : 000000000000002a | x2 : 0000000000000001 x1 : ffffd014171f2988 x0 : fffffbfffddffcb8 | Kernel panic - not syncing: Unhandled exception | CPU: 0 PID: 0 Comm: swapper Not tainted 6.6.0-rc3-00013-g34f66c4c4d55 #1 | Hardware name: linux,dummy-virt (DT) | Call trace: | dump_backtrace+0xec/0x108 | show_stack+0x18/0x2c | dump_stack_lvl+0x50/0x68 | dump_stack+0x18/0x24 | panic+0x13c/0x340 | el1t_64_irq_handler+0x0/0x1c | el1_abort+0x0/0x5c | el1h_64_sync+0x64/0x68 | __pi_strcmp+0x1c/0x150 | unflatten_dt_nodes+0x1e8/0x2d8 | __unflatten_device_tree+0x5c/0x15c | unflatten_device_tree+0x38/0x50 | setup_arch+0x164/0x1e0 | start_kernel+0x64/0x38c | __primary_switched+0xbc/0xc4 Restrict CONFIG_CPU_BIG_ENDIAN to a known good assembler, which is either GNU as or LLVM's IAS 15.0.0 and newer, which contains the linked commit.
CVE-2023-52751: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free in smb2_query_info_compound() The following UAF was triggered when running fstests generic/072 with KASAN enabled against Windows Server 2022 and mount options 'multichannel,max_channels=2,vers=3.1.1,mfsymlinks,noperm' BUG: KASAN: slab-use-after-free in smb2_query_info_compound+0x423/0x6d0 [cifs] Read of size 8 at addr ffff888014941048 by task xfs_io/27534 CPU: 0 PID: 27534 Comm: xfs_io Not tainted 6.6.0-rc7 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 Call Trace: dump_stack_lvl+0x4a/0x80 print_report+0xcf/0x650 ? srso_alias_return_thunk+0x5/0x7f ? srso_alias_return_thunk+0x5/0x7f ? __phys_addr+0x46/0x90 kasan_report+0xda/0x110 ? smb2_query_info_compound+0x423/0x6d0 [cifs] ? smb2_query_info_compound+0x423/0x6d0 [cifs] smb2_query_info_compound+0x423/0x6d0 [cifs] ? __pfx_smb2_query_info_compound+0x10/0x10 [cifs] ? srso_alias_return_thunk+0x5/0x7f ? __stack_depot_save+0x39/0x480 ? kasan_save_stack+0x33/0x60 ? kasan_set_track+0x25/0x30 ? ____kasan_slab_free+0x126/0x170 smb2_queryfs+0xc2/0x2c0 [cifs] ? __pfx_smb2_queryfs+0x10/0x10 [cifs] ? __pfx___lock_acquire+0x10/0x10 smb311_queryfs+0x210/0x220 [cifs] ? __pfx_smb311_queryfs+0x10/0x10 [cifs] ? srso_alias_return_thunk+0x5/0x7f ? __lock_acquire+0x480/0x26c0 ? lock_release+0x1ed/0x640 ? srso_alias_return_thunk+0x5/0x7f ? do_raw_spin_unlock+0x9b/0x100 cifs_statfs+0x18c/0x4b0 [cifs] statfs_by_dentry+0x9b/0xf0 fd_statfs+0x4e/0xb0 __do_sys_fstatfs+0x7f/0xe0 ? __pfx___do_sys_fstatfs+0x10/0x10 ? srso_alias_return_thunk+0x5/0x7f ? lockdep_hardirqs_on_prepare+0x136/0x200 ? srso_alias_return_thunk+0x5/0x7f do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Allocated by task 27534: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 __kasan_kmalloc+0x8f/0xa0 open_cached_dir+0x71b/0x1240 [cifs] smb2_query_info_compound+0x5c3/0x6d0 [cifs] smb2_queryfs+0xc2/0x2c0 [cifs] smb311_queryfs+0x210/0x220 [cifs] cifs_statfs+0x18c/0x4b0 [cifs] statfs_by_dentry+0x9b/0xf0 fd_statfs+0x4e/0xb0 __do_sys_fstatfs+0x7f/0xe0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Freed by task 27534: kasan_save_stack+0x33/0x60 kasan_set_track+0x25/0x30 kasan_save_free_info+0x2b/0x50 ____kasan_slab_free+0x126/0x170 slab_free_freelist_hook+0xd0/0x1e0 __kmem_cache_free+0x9d/0x1b0 open_cached_dir+0xff5/0x1240 [cifs] smb2_query_info_compound+0x5c3/0x6d0 [cifs] smb2_queryfs+0xc2/0x2c0 [cifs] This is a race between open_cached_dir() and cached_dir_lease_break() where the cache entry for the open directory handle receives a lease break while creating it. And before returning from open_cached_dir(), we put the last reference of the new @cfid because of !@cfid->has_lease. Besides the UAF, while running xfstests a lot of missed lease breaks have been noticed in tests that run several concurrent statfs(2) calls on those cached fids CIFS: VFS: \\w22-root1.gandalf.test No task to wake, unknown frame... CIFS: VFS: \\w22-root1.gandalf.test Cmd: 18 Err: 0x0 Flags: 0x1... CIFS: VFS: \\w22-root1.gandalf.test smb buf 00000000715bfe83 len 108 CIFS: VFS: Dump pending requests: CIFS: VFS: \\w22-root1.gandalf.test No task to wake, unknown frame... CIFS: VFS: \\w22-root1.gandalf.test Cmd: 18 Err: 0x0 Flags: 0x1... CIFS: VFS: \\w22-root1.gandalf.test smb buf 000000005aa7316e len 108 ... To fix both, in open_cached_dir() ensure that @cfid->has_lease is set right before sending out compounded request so that any potential lease break will be get processed by demultiplex thread while we're still caching @cfid. And, if open failed for some reason, re-check @cfid->has_lease to decide whether or not put lease reference.
CVE-2023-52752: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix use-after-free bug in cifs_debug_data_proc_show() Skip SMB sessions that are being teared down (e.g. @ses->ses_status == SES_EXITING) in cifs_debug_data_proc_show() to avoid use-after-free in @ses. This fixes the following GPF when reading from /proc/fs/cifs/DebugData while mounting and umounting [ 816.251274] general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6d81: 0000 [#1] PREEMPT SMP NOPTI ... [ 816.260138] Call Trace: [ 816.260329] <TASK> [ 816.260499] ? die_addr+0x36/0x90 [ 816.260762] ? exc_general_protection+0x1b3/0x410 [ 816.261126] ? asm_exc_general_protection+0x26/0x30 [ 816.261502] ? cifs_debug_tcon+0xbd/0x240 [cifs] [ 816.261878] ? cifs_debug_tcon+0xab/0x240 [cifs] [ 816.262249] cifs_debug_data_proc_show+0x516/0xdb0 [cifs] [ 816.262689] ? seq_read_iter+0x379/0x470 [ 816.262995] seq_read_iter+0x118/0x470 [ 816.263291] proc_reg_read_iter+0x53/0x90 [ 816.263596] ? srso_alias_return_thunk+0x5/0x7f [ 816.263945] vfs_read+0x201/0x350 [ 816.264211] ksys_read+0x75/0x100 [ 816.264472] do_syscall_64+0x3f/0x90 [ 816.264750] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 [ 816.265135] RIP: 0033:0x7fd5e669d381
CVE-2023-52754: In the Linux kernel, the following vulnerability has been resolved: media: imon: fix access to invalid resource for the second interface imon driver probes two USB interfaces, and at the probe of the second interface, the driver assumes blindly that the first interface got bound with the same imon driver. It's usually true, but it's still possible that the first interface is bound with another driver via a malformed descriptor. Then it may lead to a memory corruption, as spotted by syzkaller; imon driver accesses the data from drvdata as struct imon_context object although it's a completely different one that was assigned by another driver. This patch adds a sanity check -- whether the first interface is really bound with the imon driver or not -- for avoiding the problem above at the probe time.
CVE-2023-52755: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix slab out of bounds write in smb_inherit_dacl() slab out-of-bounds write is caused by that offsets is bigger than pntsd allocation size. This patch add the check to validate 3 offsets using allocation size.
CVE-2023-52757: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential deadlock when releasing mids All release_mid() callers seem to hold a reference of @mid so there is no need to call kref_put(&mid->refcount, __release_mid) under @server->mid_lock spinlock. If they don't, then an use-after-free bug would have occurred anyways. By getting rid of such spinlock also fixes a potential deadlock as shown below CPU 0 CPU 1 ------------------------------------------------------------------ cifs_demultiplex_thread() cifs_debug_data_proc_show() release_mid() spin_lock(&server->mid_lock); spin_lock(&cifs_tcp_ses_lock) spin_lock(&server->mid_lock) __release_mid() smb2_find_smb_tcon() spin_lock(&cifs_tcp_ses_lock) *deadlock*
CVE-2023-52760: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix slab-use-after-free in gfs2_qd_dealloc In gfs2_put_super(), whether withdrawn or not, the quota should be cleaned up by gfs2_quota_cleanup(). Otherwise, struct gfs2_sbd will be freed before gfs2_qd_dealloc (rcu callback) has run for all gfs2_quota_data objects, resulting in use-after-free. Also, gfs2_destroy_threads() and gfs2_quota_cleanup() is already called by gfs2_make_fs_ro(), so in gfs2_put_super(), after calling gfs2_make_fs_ro(), there is no need to call them again.
CVE-2023-52761: In the Linux kernel, the following vulnerability has been resolved: riscv: VMAP_STACK overflow detection thread-safe commit 31da94c25aea ("riscv: add VMAP_STACK overflow detection") added support for CONFIG_VMAP_STACK. If overflow is detected, CPU switches to `shadow_stack` temporarily before switching finally to per-cpu `overflow_stack`. If two CPUs/harts are racing and end up in over flowing kernel stack, one or both will end up corrupting each other state because `shadow_stack` is not per-cpu. This patch optimizes per-cpu overflow stack switch by directly picking per-cpu `overflow_stack` and gets rid of `shadow_stack`. Following are the changes in this patch - Defines an asm macro to obtain per-cpu symbols in destination register. - In entry.S, when overflow is detected, per-cpu overflow stack is located using per-cpu asm macro. Computing per-cpu symbol requires a temporary register. x31 is saved away into CSR_SCRATCH (CSR_SCRATCH is anyways zero since we're in kernel). Please see Links for additional relevant disccussion and alternative solution. Tested by `echo EXHAUST_STACK > /sys/kernel/debug/provoke-crash/DIRECT` Kernel crash log below Insufficient stack space to handle exception!/debug/provoke-crash/DIRECT Task stack: [0xff20000010a98000..0xff20000010a9c000] Overflow stack: [0xff600001f7d98370..0xff600001f7d99370] CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) epc : __memset+0x60/0xfc ra : recursive_loop+0x48/0xc6 [lkdtm] epc : ffffffff808de0e4 ra : ffffffff0163a752 sp : ff20000010a97e80 gp : ffffffff815c0330 tp : ff600000820ea280 t0 : ff20000010a97e88 t1 : 000000000000002e t2 : 3233206874706564 s0 : ff20000010a982b0 s1 : 0000000000000012 a0 : ff20000010a97e88 a1 : 0000000000000000 a2 : 0000000000000400 a3 : ff20000010a98288 a4 : 0000000000000000 a5 : 0000000000000000 a6 : fffffffffffe43f0 a7 : 00007fffffffffff s2 : ff20000010a97e88 s3 : ffffffff01644680 s4 : ff20000010a9be90 s5 : ff600000842ba6c0 s6 : 00aaaaaac29e42b0 s7 : 00fffffff0aa3684 s8 : 00aaaaaac2978040 s9 : 0000000000000065 s10: 00ffffff8a7cad10 s11: 00ffffff8a76a4e0 t3 : ffffffff815dbaf4 t4 : ffffffff815dbaf4 t5 : ffffffff815dbab8 t6 : ff20000010a9bb48 status: 0000000200000120 badaddr: ff20000010a97e88 cause: 000000000000000f Kernel panic - not syncing: Kernel stack overflow CPU: 1 PID: 205 Comm: bash Not tainted 6.1.0-rc2-00001-g328a1f96f7b9 #34 Hardware name: riscv-virtio,qemu (DT) Call Trace: [<ffffffff80006754>] dump_backtrace+0x30/0x38 [<ffffffff808de798>] show_stack+0x40/0x4c [<ffffffff808ea2a8>] dump_stack_lvl+0x44/0x5c [<ffffffff808ea2d8>] dump_stack+0x18/0x20 [<ffffffff808dec06>] panic+0x126/0x2fe [<ffffffff800065ea>] walk_stackframe+0x0/0xf0 [<ffffffff0163a752>] recursive_loop+0x48/0xc6 [lkdtm] SMP: stopping secondary CPUs ---[ end Kernel panic - not syncing: Kernel stack overflow ]---
CVE-2023-52762: In the Linux kernel, the following vulnerability has been resolved: virtio-blk: fix implicit overflow on virtio_max_dma_size The following codes have an implicit conversion from size_t to u32: (u32)max_size = (size_t)virtio_max_dma_size(vdev); This may lead overflow, Ex (size_t)4G -> (u32)0. Once virtio_max_dma_size() has a larger size than U32_MAX, use U32_MAX instead.
CVE-2023-52763: In the Linux kernel, the following vulnerability has been resolved: i3c: master: mipi-i3c-hci: Fix a kernel panic for accessing DAT_data. The `i3c_master_bus_init` function may attach the I2C devices before the I3C bus initialization. In this flow, the DAT `alloc_entry`` will be used before the DAT `init`. Additionally, if the `i3c_master_bus_init` fails, the DAT `cleanup` will execute before the device is detached, which will execue DAT `free_entry` function. The above scenario can cause the driver to use DAT_data when it is NULL.
CVE-2023-52766: In the Linux kernel, the following vulnerability has been resolved: i3c: mipi-i3c-hci: Fix out of bounds access in hci_dma_irq_handler Do not loop over ring headers in hci_dma_irq_handler() that are not allocated and enabled in hci_dma_init(). Otherwise out of bounds access will occur from rings->headers[i] access when i >= number of allocated ring headers.
CVE-2023-52781: In the Linux kernel, the following vulnerability has been resolved: usb: config: fix iteration issue in 'usb_get_bos_descriptor()' The BOS descriptor defines a root descriptor and is the base descriptor for accessing a family of related descriptors. Function 'usb_get_bos_descriptor()' encounters an iteration issue when skipping the 'USB_DT_DEVICE_CAPABILITY' descriptor type. This results in the same descriptor being read repeatedly. To address this issue, a 'goto' statement is introduced to ensure that the pointer and the amount read is updated correctly. This ensures that the function iterates to the next descriptor instead of reading the same descriptor repeatedly.
CVE-2023-52784: In the Linux kernel, the following vulnerability has been resolved: bonding: stop the device in bond_setup_by_slave() Commit 9eed321cde22 ("net: lapbether: only support ethernet devices") has been able to keep syzbot away from net/lapb, until today. In the following splat [1], the issue is that a lapbether device has been created on a bonding device without members. Then adding a non ARPHRD_ETHER member forced the bonding master to change its type. The fix is to make sure we call dev_close() in bond_setup_by_slave() so that the potential linked lapbether devices (or any other devices having assumptions on the physical device) are removed. A similar bug has been addressed in commit 40baec225765 ("bonding: fix panic on non-ARPHRD_ETHER enslave failure") [1] skbuff: skb_under_panic: text:ffff800089508810 len:44 put:40 head:ffff0000c78e7c00 data:ffff0000c78e7bea tail:0x16 end:0x140 dev:bond0 kernel BUG at net/core/skbuff.c:192 ! Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 6007 Comm: syz-executor383 Not tainted 6.6.0-rc3-syzkaller-gbf6547d8715b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : skb_panic net/core/skbuff.c:188 [inline] pc : skb_under_panic+0x13c/0x140 net/core/skbuff.c:202 lr : skb_panic net/core/skbuff.c:188 [inline] lr : skb_under_panic+0x13c/0x140 net/core/skbuff.c:202 sp : ffff800096a06aa0 x29: ffff800096a06ab0 x28: ffff800096a06ba0 x27: dfff800000000000 x26: ffff0000ce9b9b50 x25: 0000000000000016 x24: ffff0000c78e7bea x23: ffff0000c78e7c00 x22: 000000000000002c x21: 0000000000000140 x20: 0000000000000028 x19: ffff800089508810 x18: ffff800096a06100 x17: 0000000000000000 x16: ffff80008a629a3c x15: 0000000000000001 x14: 1fffe00036837a32 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000201 x10: 0000000000000000 x9 : cb50b496c519aa00 x8 : cb50b496c519aa00 x7 : 0000000000000001 x6 : 0000000000000001 x5 : ffff800096a063b8 x4 : ffff80008e280f80 x3 : ffff8000805ad11c x2 : 0000000000000001 x1 : 0000000100000201 x0 : 0000000000000086 Call trace: skb_panic net/core/skbuff.c:188 [inline] skb_under_panic+0x13c/0x140 net/core/skbuff.c:202 skb_push+0xf0/0x108 net/core/skbuff.c:2446 ip6gre_header+0xbc/0x738 net/ipv6/ip6_gre.c:1384 dev_hard_header include/linux/netdevice.h:3136 [inline] lapbeth_data_transmit+0x1c4/0x298 drivers/net/wan/lapbether.c:257 lapb_data_transmit+0x8c/0xb0 net/lapb/lapb_iface.c:447 lapb_transmit_buffer+0x178/0x204 net/lapb/lapb_out.c:149 lapb_send_control+0x220/0x320 net/lapb/lapb_subr.c:251 __lapb_disconnect_request+0x9c/0x17c net/lapb/lapb_iface.c:326 lapb_device_event+0x288/0x4e0 net/lapb/lapb_iface.c:492 notifier_call_chain+0x1a4/0x510 kernel/notifier.c:93 raw_notifier_call_chain+0x3c/0x50 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1970 [inline] call_netdevice_notifiers_extack net/core/dev.c:2008 [inline] call_netdevice_notifiers net/core/dev.c:2022 [inline] __dev_close_many+0x1b8/0x3c4 net/core/dev.c:1508 dev_close_many+0x1e0/0x470 net/core/dev.c:1559 dev_close+0x174/0x250 net/core/dev.c:1585 lapbeth_device_event+0x2e4/0x958 drivers/net/wan/lapbether.c:466 notifier_call_chain+0x1a4/0x510 kernel/notifier.c:93 raw_notifier_call_chain+0x3c/0x50 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1970 [inline] call_netdevice_notifiers_extack net/core/dev.c:2008 [inline] call_netdevice_notifiers net/core/dev.c:2022 [inline] __dev_close_many+0x1b8/0x3c4 net/core/dev.c:1508 dev_close_many+0x1e0/0x470 net/core/dev.c:1559 dev_close+0x174/0x250 net/core/dev.c:1585 bond_enslave+0x2298/0x30cc drivers/net/bonding/bond_main.c:2332 bond_do_ioctl+0x268/0xc64 drivers/net/bonding/bond_main.c:4539 dev_ifsioc+0x754/0x9ac dev_ioctl+0x4d8/0xd34 net/core/dev_ioctl.c:786 sock_do_ioctl+0x1d4/0x2d0 net/socket.c:1217 sock_ioctl+0x4e8/0x834 net/socket.c:1322 vfs_ioctl fs/ioctl.c:51 [inline] __do_ ---truncated---
CVE-2023-52803: In the Linux kernel, the following vulnerability has been resolved: SUNRPC: Fix RPC client cleaned up the freed pipefs dentries RPC client pipefs dentries cleanup is in separated rpc_remove_pipedir() workqueue,which takes care about pipefs superblock locking. In some special scenarios, when kernel frees the pipefs sb of the current client and immediately alloctes a new pipefs sb, rpc_remove_pipedir function would misjudge the existence of pipefs sb which is not the one it used to hold. As a result, the rpc_remove_pipedir would clean the released freed pipefs dentries. To fix this issue, rpc_remove_pipedir should check whether the current pipefs sb is consistent with the original pipefs sb. This error can be catched by KASAN: ========================================================= [ 250.497700] BUG: KASAN: slab-use-after-free in dget_parent+0x195/0x200 [ 250.498315] Read of size 4 at addr ffff88800a2ab804 by task kworker/0:18/106503 [ 250.500549] Workqueue: events rpc_free_client_work [ 250.501001] Call Trace: [ 250.502880] kasan_report+0xb6/0xf0 [ 250.503209] ? dget_parent+0x195/0x200 [ 250.503561] dget_parent+0x195/0x200 [ 250.503897] ? __pfx_rpc_clntdir_depopulate+0x10/0x10 [ 250.504384] rpc_rmdir_depopulate+0x1b/0x90 [ 250.504781] rpc_remove_client_dir+0xf5/0x150 [ 250.505195] rpc_free_client_work+0xe4/0x230 [ 250.505598] process_one_work+0x8ee/0x13b0 ... [ 22.039056] Allocated by task 244: [ 22.039390] kasan_save_stack+0x22/0x50 [ 22.039758] kasan_set_track+0x25/0x30 [ 22.040109] __kasan_slab_alloc+0x59/0x70 [ 22.040487] kmem_cache_alloc_lru+0xf0/0x240 [ 22.040889] __d_alloc+0x31/0x8e0 [ 22.041207] d_alloc+0x44/0x1f0 [ 22.041514] __rpc_lookup_create_exclusive+0x11c/0x140 [ 22.041987] rpc_mkdir_populate.constprop.0+0x5f/0x110 [ 22.042459] rpc_create_client_dir+0x34/0x150 [ 22.042874] rpc_setup_pipedir_sb+0x102/0x1c0 [ 22.043284] rpc_client_register+0x136/0x4e0 [ 22.043689] rpc_new_client+0x911/0x1020 [ 22.044057] rpc_create_xprt+0xcb/0x370 [ 22.044417] rpc_create+0x36b/0x6c0 ... [ 22.049524] Freed by task 0: [ 22.049803] kasan_save_stack+0x22/0x50 [ 22.050165] kasan_set_track+0x25/0x30 [ 22.050520] kasan_save_free_info+0x2b/0x50 [ 22.050921] __kasan_slab_free+0x10e/0x1a0 [ 22.051306] kmem_cache_free+0xa5/0x390 [ 22.051667] rcu_core+0x62c/0x1930 [ 22.051995] __do_softirq+0x165/0x52a [ 22.052347] [ 22.052503] Last potentially related work creation: [ 22.052952] kasan_save_stack+0x22/0x50 [ 22.053313] __kasan_record_aux_stack+0x8e/0xa0 [ 22.053739] __call_rcu_common.constprop.0+0x6b/0x8b0 [ 22.054209] dentry_free+0xb2/0x140 [ 22.054540] __dentry_kill+0x3be/0x540 [ 22.054900] shrink_dentry_list+0x199/0x510 [ 22.055293] shrink_dcache_parent+0x190/0x240 [ 22.055703] do_one_tree+0x11/0x40 [ 22.056028] shrink_dcache_for_umount+0x61/0x140 [ 22.056461] generic_shutdown_super+0x70/0x590 [ 22.056879] kill_anon_super+0x3a/0x60 [ 22.057234] rpc_kill_sb+0x121/0x200
CVE-2023-52808: In the Linux kernel, the following vulnerability has been resolved: scsi: hisi_sas: Set debugfs_dir pointer to NULL after removing debugfs If init debugfs failed during device registration due to memory allocation failure, debugfs_remove_recursive() is called, after which debugfs_dir is not set to NULL. debugfs_remove_recursive() will be called again during device removal. As a result, illegal pointer is accessed. [ 1665.467244] hisi_sas_v3_hw 0000:b4:02.0: failed to init debugfs! ... [ 1669.836708] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0 [ 1669.872669] pc : down_write+0x24/0x70 [ 1669.876315] lr : down_write+0x1c/0x70 [ 1669.879961] sp : ffff000036f53a30 [ 1669.883260] x29: ffff000036f53a30 x28: ffffa027c31549f8 [ 1669.888547] x27: ffffa027c3140000 x26: 0000000000000000 [ 1669.893834] x25: ffffa027bf37c270 x24: ffffa027bf37c270 [ 1669.899122] x23: ffff0000095406b8 x22: ffff0000095406a8 [ 1669.904408] x21: 0000000000000000 x20: ffffa027bf37c310 [ 1669.909695] x19: 00000000000000a0 x18: ffff8027dcd86f10 [ 1669.914982] x17: 0000000000000000 x16: 0000000000000000 [ 1669.920268] x15: 0000000000000000 x14: ffffa0274014f870 [ 1669.925555] x13: 0000000000000040 x12: 0000000000000228 [ 1669.930842] x11: 0000000000000020 x10: 0000000000000bb0 [ 1669.936129] x9 : ffff000036f537f0 x8 : ffff80273088ca10 [ 1669.941416] x7 : 000000000000001d x6 : 00000000ffffffff [ 1669.946702] x5 : ffff000008a36310 x4 : ffff80273088be00 [ 1669.951989] x3 : ffff000009513e90 x2 : 0000000000000000 [ 1669.957276] x1 : 00000000000000a0 x0 : ffffffff00000001 [ 1669.962563] Call trace: [ 1669.965000] down_write+0x24/0x70 [ 1669.968301] debugfs_remove_recursive+0x5c/0x1b0 [ 1669.972905] hisi_sas_debugfs_exit+0x24/0x30 [hisi_sas_main] [ 1669.978541] hisi_sas_v3_remove+0x130/0x150 [hisi_sas_v3_hw] [ 1669.984175] pci_device_remove+0x48/0xd8 [ 1669.988082] device_release_driver_internal+0x1b4/0x250 [ 1669.993282] device_release_driver+0x28/0x38 [ 1669.997534] pci_stop_bus_device+0x84/0xb8 [ 1670.001611] pci_stop_and_remove_bus_device_locked+0x24/0x40 [ 1670.007244] remove_store+0xfc/0x140 [ 1670.010802] dev_attr_store+0x44/0x60 [ 1670.014448] sysfs_kf_write+0x58/0x80 [ 1670.018095] kernfs_fop_write+0xe8/0x1f0 [ 1670.022000] __vfs_write+0x60/0x190 [ 1670.025472] vfs_write+0xac/0x1c0 [ 1670.028771] ksys_write+0x6c/0xd8 [ 1670.032071] __arm64_sys_write+0x24/0x30 [ 1670.035977] el0_svc_common+0x78/0x130 [ 1670.039710] el0_svc_handler+0x38/0x78 [ 1670.043442] el0_svc+0x8/0xc To fix this, set debugfs_dir to NULL after debugfs_remove_recursive().
CVE-2023-52811: In the Linux kernel, the following vulnerability has been resolved: scsi: ibmvfc: Remove BUG_ON in the case of an empty event pool In practice the driver should never send more commands than are allocated to a queue's event pool. In the unlikely event that this happens, the code asserts a BUG_ON, and in the case that the kernel is not configured to crash on panic returns a junk event pointer from the empty event list causing things to spiral from there. This BUG_ON is a historical artifact of the ibmvfc driver first being upstreamed, and it is well known now that the use of BUG_ON is bad practice except in the most unrecoverable scenario. There is nothing about this scenario that prevents the driver from recovering and carrying on. Remove the BUG_ON in question from ibmvfc_get_event() and return a NULL pointer in the case of an empty event pool. Update all call sites to ibmvfc_get_event() to check for a NULL pointer and perfrom the appropriate failure or recovery action.
CVE-2023-52812: In the Linux kernel, the following vulnerability has been resolved: drm/amd: check num of link levels when update pcie param In SR-IOV environment, the value of pcie_table->num_of_link_levels will be 0, and num_of_levels - 1 will cause array index out of bounds
CVE-2023-52814: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix potential null pointer derefernce The amdgpu_ras_get_context may return NULL if device not support ras feature, so add check before using.
CVE-2023-52815: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/vkms: fix a possible null pointer dereference In amdgpu_vkms_conn_get_modes(), the return value of drm_cvt_mode() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_cvt_mode(). Add a check to avoid null pointer dereference.
CVE-2023-52816: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Fix shift out-of-bounds issue [ 567.613292] shift exponent 255 is too large for 64-bit type 'long unsigned int' [ 567.614498] CPU: 5 PID: 238 Comm: kworker/5:1 Tainted: G OE 6.2.0-34-generic #34~22.04.1-Ubuntu [ 567.614502] Hardware name: AMD Splinter/Splinter-RPL, BIOS WS43927N_871 09/25/2023 [ 567.614504] Workqueue: events send_exception_work_handler [amdgpu] [ 567.614748] Call Trace: [ 567.614750] <TASK> [ 567.614753] dump_stack_lvl+0x48/0x70 [ 567.614761] dump_stack+0x10/0x20 [ 567.614763] __ubsan_handle_shift_out_of_bounds+0x156/0x310 [ 567.614769] ? srso_alias_return_thunk+0x5/0x7f [ 567.614773] ? update_sd_lb_stats.constprop.0+0xf2/0x3c0 [ 567.614780] svm_range_split_by_granularity.cold+0x2b/0x34 [amdgpu] [ 567.615047] ? srso_alias_return_thunk+0x5/0x7f [ 567.615052] svm_migrate_to_ram+0x185/0x4d0 [amdgpu] [ 567.615286] do_swap_page+0x7b6/0xa30 [ 567.615291] ? srso_alias_return_thunk+0x5/0x7f [ 567.615294] ? __free_pages+0x119/0x130 [ 567.615299] handle_pte_fault+0x227/0x280 [ 567.615303] __handle_mm_fault+0x3c0/0x720 [ 567.615311] handle_mm_fault+0x119/0x330 [ 567.615314] ? lock_mm_and_find_vma+0x44/0x250 [ 567.615318] do_user_addr_fault+0x1a9/0x640 [ 567.615323] exc_page_fault+0x81/0x1b0 [ 567.615328] asm_exc_page_fault+0x27/0x30 [ 567.615332] RIP: 0010:__get_user_8+0x1c/0x30
CVE-2023-52821: In the Linux kernel, the following vulnerability has been resolved: drm/panel: fix a possible null pointer dereference In versatile_panel_get_modes(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd.
CVE-2023-52825: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: Fix a race condition of vram buffer unref in svm code prange->svm_bo unref can happen in both mmu callback and a callback after migrate to system ram. Both are async call in different tasks. Sync svm_bo unref operation to avoid random "use-after-free".
CVE-2023-52826: In the Linux kernel, the following vulnerability has been resolved: drm/panel/panel-tpo-tpg110: fix a possible null pointer dereference In tpg110_get_modes(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd.
CVE-2023-52827: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: fix possible out-of-bound read in ath12k_htt_pull_ppdu_stats() len is extracted from HTT message and could be an unexpected value in case errors happen, so add validation before using to avoid possible out-of-bound read in the following message iteration and parsing. The same issue also applies to ppdu_info->ppdu_stats.common.num_users, so validate it before using too. These are found during code review. Compile test only.
CVE-2023-52828: In the Linux kernel, the following vulnerability has been resolved: bpf: Detect IP == ksym.end as part of BPF program Now that bpf_throw kfunc is the first such call instruction that has noreturn semantics within the verifier, this also kicks in dead code elimination in unprecedented ways. For one, any instruction following a bpf_throw call will never be marked as seen. Moreover, if a callchain ends up throwing, any instructions after the call instruction to the eventually throwing subprog in callers will also never be marked as seen. The tempting way to fix this would be to emit extra 'int3' instructions which bump the jited_len of a program, and ensure that during runtime when a program throws, we can discover its boundaries even if the call instruction to bpf_throw (or to subprogs that always throw) is emitted as the final instruction in the program. An example of such a program would be this: do_something(): ... r0 = 0 exit foo(): r1 = 0 call bpf_throw r0 = 0 exit bar(cond): if r1 != 0 goto pc+2 call do_something exit call foo r0 = 0 // Never seen by verifier exit // main(ctx): r1 = ... call bar r0 = 0 exit Here, if we do end up throwing, the stacktrace would be the following: bpf_throw foo bar main In bar, the final instruction emitted will be the call to foo, as such, the return address will be the subsequent instruction (which the JIT emits as int3 on x86). This will end up lying outside the jited_len of the program, thus, when unwinding, we will fail to discover the return address as belonging to any program and end up in a panic due to the unreliable stack unwinding of BPF programs that we never expect. To remedy this case, make bpf_prog_ksym_find treat IP == ksym.end as part of the BPF program, so that is_bpf_text_address returns true when such a case occurs, and we are able to unwind reliably when the final instruction ends up being a call instruction.
CVE-2023-52829: In the Linux kernel, the following vulnerability has been resolved: wifi: ath12k: fix possible out-of-bound write in ath12k_wmi_ext_hal_reg_caps() reg_cap.phy_id is extracted from WMI event and could be an unexpected value in case some errors happen. As a result out-of-bound write may occur to soc->hal_reg_cap. Fix it by validating reg_cap.phy_id before using it. This is found during code review. Compile tested only.
CVE-2023-52831: In the Linux kernel, the following vulnerability has been resolved: cpu/hotplug: Don't offline the last non-isolated CPU If a system has isolated CPUs via the "isolcpus=" command line parameter, then an attempt to offline the last housekeeping CPU will result in a WARN_ON() when rebuilding the scheduler domains and a subsequent panic due to and unhandled empty CPU mas in partition_sched_domains_locked(). cpuset_hotplug_workfn() rebuild_sched_domains_locked() ndoms = generate_sched_domains(&doms, &attr); cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); Thus results in an empty CPU mask which triggers the warning and then the subsequent crash: WARNING: CPU: 4 PID: 80 at kernel/sched/topology.c:2366 build_sched_domains+0x120c/0x1408 Call trace: build_sched_domains+0x120c/0x1408 partition_sched_domains_locked+0x234/0x880 rebuild_sched_domains_locked+0x37c/0x798 rebuild_sched_domains+0x30/0x58 cpuset_hotplug_workfn+0x2a8/0x930 Unable to handle kernel paging request at virtual address fffe80027ab37080 partition_sched_domains_locked+0x318/0x880 rebuild_sched_domains_locked+0x37c/0x798 Aside of the resulting crash, it does not make any sense to offline the last last housekeeping CPU. Prevent this by masking out the non-housekeeping CPUs when selecting a target CPU for initiating the CPU unplug operation via the work queue.
CVE-2023-52833: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: btusb: Add date->evt_skb is NULL check fix crash because of null pointers [ 6104.969662] BUG: kernel NULL pointer dereference, address: 00000000000000c8 [ 6104.969667] #PF: supervisor read access in kernel mode [ 6104.969668] #PF: error_code(0x0000) - not-present page [ 6104.969670] PGD 0 P4D 0 [ 6104.969673] Oops: 0000 [#1] SMP NOPTI [ 6104.969684] RIP: 0010:btusb_mtk_hci_wmt_sync+0x144/0x220 [btusb] [ 6104.969688] RSP: 0018:ffffb8d681533d48 EFLAGS: 00010246 [ 6104.969689] RAX: 0000000000000000 RBX: ffff8ad560bb2000 RCX: 0000000000000006 [ 6104.969691] RDX: 0000000000000000 RSI: ffffb8d681533d08 RDI: 0000000000000000 [ 6104.969692] RBP: ffffb8d681533d70 R08: 0000000000000001 R09: 0000000000000001 [ 6104.969694] R10: 0000000000000001 R11: 00000000fa83b2da R12: ffff8ad461d1d7c0 [ 6104.969695] R13: 0000000000000000 R14: ffff8ad459618c18 R15: ffffb8d681533d90 [ 6104.969697] FS: 00007f5a1cab9d40(0000) GS:ffff8ad578200000(0000) knlGS:00000 [ 6104.969699] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6104.969700] CR2: 00000000000000c8 CR3: 000000018620c001 CR4: 0000000000760ef0 [ 6104.969701] PKRU: 55555554 [ 6104.969702] Call Trace: [ 6104.969708] btusb_mtk_shutdown+0x44/0x80 [btusb] [ 6104.969732] hci_dev_do_close+0x470/0x5c0 [bluetooth] [ 6104.969748] hci_rfkill_set_block+0x56/0xa0 [bluetooth] [ 6104.969753] rfkill_set_block+0x92/0x160 [ 6104.969755] rfkill_fop_write+0x136/0x1e0 [ 6104.969759] __vfs_write+0x18/0x40 [ 6104.969761] vfs_write+0xdf/0x1c0 [ 6104.969763] ksys_write+0xb1/0xe0 [ 6104.969765] __x64_sys_write+0x1a/0x20 [ 6104.969769] do_syscall_64+0x51/0x180 [ 6104.969771] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 6104.969773] RIP: 0033:0x7f5a21f18fef [ 6104.9] RSP: 002b:00007ffeefe39010 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 [ 6104.969780] RAX: ffffffffffffffda RBX: 000055c10a7560a0 RCX: 00007f5a21f18fef [ 6104.969781] RDX: 0000000000000008 RSI: 00007ffeefe39060 RDI: 0000000000000012 [ 6104.969782] RBP: 00007ffeefe39060 R08: 0000000000000000 R09: 0000000000000017 [ 6104.969784] R10: 00007ffeefe38d97 R11: 0000000000000293 R12: 0000000000000002 [ 6104.969785] R13: 00007ffeefe39220 R14: 00007ffeefe391a0 R15: 000055c10a72acf0
CVE-2023-52834: In the Linux kernel, the following vulnerability has been resolved: atl1c: Work around the DMA RX overflow issue This is based on alx driver commit 881d0327db37 ("net: alx: Work around the DMA RX overflow issue"). The alx and atl1c drivers had RX overflow error which was why a custom allocator was created to avoid certain addresses. The simpler workaround then created for alx driver, but not for atl1c due to lack of tester. Instead of using a custom allocator, check the allocated skb address and use skb_reserve() to move away from problematic 0x...fc0 address. Tested on AR8131 on Acer 4540.
CVE-2023-52854: In the Linux kernel, the following vulnerability has been resolved: padata: Fix refcnt handling in padata_free_shell() In a high-load arm64 environment, the pcrypt_aead01 test in LTP can lead to system UAF (Use-After-Free) issues. Due to the lengthy analysis of the pcrypt_aead01 function call, I'll describe the problem scenario using a simplified model: Suppose there's a user of padata named `user_function` that adheres to the padata requirement of calling `padata_free_shell` after `serial()` has been invoked, as demonstrated in the following code: ```c struct request { struct padata_priv padata; struct completion *done; }; void parallel(struct padata_priv *padata) { do_something(); } void serial(struct padata_priv *padata) { struct request *request = container_of(padata, struct request, padata); complete(request->done); } void user_function() { DECLARE_COMPLETION(done) padata->parallel = parallel; padata->serial = serial; padata_do_parallel(); wait_for_completion(&done); padata_free_shell(); } ``` In the corresponding padata.c file, there's the following code: ```c static void padata_serial_worker(struct work_struct *serial_work) { ... cnt = 0; while (!list_empty(&local_list)) { ... padata->serial(padata); cnt++; } local_bh_enable(); if (refcount_sub_and_test(cnt, &pd->refcnt)) padata_free_pd(pd); } ``` Because of the high system load and the accumulation of unexecuted softirq at this moment, `local_bh_enable()` in padata takes longer to execute than usual. Subsequently, when accessing `pd->refcnt`, `pd` has already been released by `padata_free_shell()`, resulting in a UAF issue with `pd->refcnt`. The fix is straightforward: add `refcount_dec_and_test` before calling `padata_free_pd` in `padata_free_shell`.
CVE-2023-52871: In the Linux kernel, the following vulnerability has been resolved: soc: qcom: llcc: Handle a second device without data corruption Usually there is only one llcc device. But if there were a second, even a failed probe call would modify the global drv_data pointer. So check if drv_data is valid before overwriting it.
CVE-2023-52878: In the Linux kernel, the following vulnerability has been resolved: can: dev: can_put_echo_skb(): don't crash kernel if can_priv::echo_skb is accessed out of bounds If the "struct can_priv::echoo_skb" is accessed out of bounds, this would cause a kernel crash. Instead, issue a meaningful warning message and return with an error.
CVE-2023-52882: In the Linux kernel, the following vulnerability has been resolved: clk: sunxi-ng: h6: Reparent CPUX during PLL CPUX rate change While PLL CPUX clock rate change when CPU is running from it works in vast majority of cases, now and then it causes instability. This leads to system crashes and other undefined behaviour. After a lot of testing (30+ hours) while also doing a lot of frequency switches, we can't observe any instability issues anymore when doing reparenting to stable clock like 24 MHz oscillator.
CVE-2024-21803: Use After Free vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (bluetooth modules) allows Local Execution of Code. This vulnerability is associated with program files https://gitee.Com/anolis/cloud-kernel/blob/devel-5.10/net/bluetooth/af_bluetooth.C. This issue affects Linux kernel: from v2.6.12-rc2 before v6.8-rc1.
CVE-2024-22386: A race condition was found in the Linux kernel's drm/exynos device driver in exynos_drm_crtc_atomic_disable() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-23196: A race condition was found in the Linux kernel's sound/hda device driver in snd_hdac_regmap_sync() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-23307: Integer Overflow or Wraparound vulnerability in Linux Linux kernel kernel on Linux, x86, ARM (md, raid, raid5 modules) allows Forced Integer Overflow.
CVE-2024-23848: In the Linux kernel through 6.7.1, there is a use-after-free in cec_queue_msg_fh, related to drivers/media/cec/core/cec-adap.c and drivers/media/cec/core/cec-api.c.
CVE-2024-24855: A race condition was found in the Linux kernel's scsi device driver in lpfc_unregister_fcf_rescan() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-24859: A race condition was found in the Linux kernel's net/bluetooth in sniff_{min,max}_interval_set() function. This can result in a bluetooth sniffing exception issue, possibly leading denial of service.
CVE-2024-24864: A race condition was found in the Linux kernel's media/dvb-core in dvbdmx_write() function. This can result in a null pointer dereference issue, possibly leading to a kernel panic or denial of service issue.
CVE-2024-25740: A memory leak flaw was found in the UBI driver in drivers/mtd/ubi/attach.c in the Linux kernel through 6.7.4 for UBI_IOCATT, because kobj->name is not released.
CVE-2024-25741: printer_write in drivers/usb/gadget/function/f_printer.c in the Linux kernel through 6.7.4 does not properly call usb_ep_queue, which might allow attackers to cause a denial of service or have unspecified other impact.
CVE-2024-25742: In the Linux kernel before 6.9, an untrusted hypervisor can inject virtual interrupt 29 (#VC) at any point in time and can trigger its handler. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-25743: In the Linux kernel through 6.9, an untrusted hypervisor can inject virtual interrupts 0 and 14 at any point in time and can trigger the SIGFPE signal handler in userspace applications. This affects AMD SEV-SNP and AMD SEV-ES.
CVE-2024-26584: In the Linux kernel, the following vulnerability has been resolved: net: tls: handle backlogging of crypto requests Since we're setting the CRYPTO_TFM_REQ_MAY_BACKLOG flag on our requests to the crypto API, crypto_aead_{encrypt,decrypt} can return -EBUSY instead of -EINPROGRESS in valid situations. For example, when the cryptd queue for AESNI is full (easy to trigger with an artificially low cryptd.cryptd_max_cpu_qlen), requests will be enqueued to the backlog but still processed. In that case, the async callback will also be called twice: first with err == -EINPROGRESS, which it seems we can just ignore, then with err == 0. Compared to Sabrina's original patch this version uses the new tls_*crypt_async_wait() helpers and converts the EBUSY to EINPROGRESS to avoid having to modify all the error handling paths. The handling is identical.
CVE-2024-26586: In the Linux kernel, the following vulnerability has been resolved: mlxsw: spectrum_acl_tcam: Fix stack corruption When tc filters are first added to a net device, the corresponding local port gets bound to an ACL group in the device. The group contains a list of ACLs. In turn, each ACL points to a different TCAM region where the filters are stored. During forwarding, the ACLs are sequentially evaluated until a match is found. One reason to place filters in different regions is when they are added with decreasing priorities and in an alternating order so that two consecutive filters can never fit in the same region because of their key usage. In Spectrum-2 and newer ASICs the firmware started to report that the maximum number of ACLs in a group is more than 16, but the layout of the register that configures ACL groups (PAGT) was not updated to account for that. It is therefore possible to hit stack corruption [1] in the rare case where more than 16 ACLs in a group are required. Fix by limiting the maximum ACL group size to the minimum between what the firmware reports and the maximum ACLs that fit in the PAGT register. Add a test case to make sure the machine does not crash when this condition is hit. [1] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: mlxsw_sp_acl_tcam_group_update+0x116/0x120 [...] dump_stack_lvl+0x36/0x50 panic+0x305/0x330 __stack_chk_fail+0x15/0x20 mlxsw_sp_acl_tcam_group_update+0x116/0x120 mlxsw_sp_acl_tcam_group_region_attach+0x69/0x110 mlxsw_sp_acl_tcam_vchunk_get+0x492/0xa20 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0 mlxsw_sp_acl_rule_add+0x47/0x240 mlxsw_sp_flower_replace+0x1a9/0x1d0 tc_setup_cb_add+0xdc/0x1c0 fl_hw_replace_filter+0x146/0x1f0 fl_change+0xc17/0x1360 tc_new_tfilter+0x472/0xb90 rtnetlink_rcv_msg+0x313/0x3b0 netlink_rcv_skb+0x58/0x100 netlink_unicast+0x244/0x390 netlink_sendmsg+0x1e4/0x440 ____sys_sendmsg+0x164/0x260 ___sys_sendmsg+0x9a/0xe0 __sys_sendmsg+0x7a/0xc0 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0x6b
CVE-2024-26598: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: vgic-its: Avoid potential UAF in LPI translation cache There is a potential UAF scenario in the case of an LPI translation cache hit racing with an operation that invalidates the cache, such as a DISCARD ITS command. The root of the problem is that vgic_its_check_cache() does not elevate the refcount on the vgic_irq before dropping the lock that serializes refcount changes. Have vgic_its_check_cache() raise the refcount on the returned vgic_irq and add the corresponding decrement after queueing the interrupt.
CVE-2024-26614: In the Linux kernel, the following vulnerability has been resolved: tcp: make sure init the accept_queue's spinlocks once When I run syz's reproduction C program locally, it causes the following issue: pvqspinlock: lock 0xffff9d181cd5c660 has corrupted value 0x0! WARNING: CPU: 19 PID: 21160 at __pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508) Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__pv_queued_spin_unlock_slowpath (kernel/locking/qspinlock_paravirt.h:508) Code: 73 56 3a ff 90 c3 cc cc cc cc 8b 05 bb 1f 48 01 85 c0 74 05 c3 cc cc cc cc 8b 17 48 89 fe 48 c7 c7 30 20 ce 8f e8 ad 56 42 ff <0f> 0b c3 cc cc cc cc 0f 0b 0f 1f 40 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffa8d200604cb8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9d1ef60e0908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff9d1ef60e0900 RBP: ffff9d181cd5c280 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffa8d200604b68 R11: ffffffff907dcdc8 R12: 0000000000000000 R13: ffff9d181cd5c660 R14: ffff9d1813a3f330 R15: 0000000000001000 FS: 00007fa110184640(0000) GS:ffff9d1ef60c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000011f65e000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_unlock (kernel/locking/spinlock.c:186) inet_csk_reqsk_queue_add (net/ipv4/inet_connection_sock.c:1321) inet_csk_complete_hashdance (net/ipv4/inet_connection_sock.c:1358) tcp_check_req (net/ipv4/tcp_minisocks.c:868) tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2260) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) process_backlog (./include/linux/rcupdate.h:779) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6604) __do_softirq (./arch/x86/include/asm/jump_label.h:27) do_softirq (kernel/softirq.c:454 kernel/softirq.c:441) </IRQ> <TASK> __local_bh_enable_ip (kernel/softirq.c:381) __dev_queue_xmit (net/core/dev.c:4374) ip_finish_output2 (./include/net/neighbour.h:540 net/ipv4/ip_output.c:235) __ip_queue_xmit (net/ipv4/ip_output.c:535) __tcp_transmit_skb (net/ipv4/tcp_output.c:1462) tcp_rcv_synsent_state_process (net/ipv4/tcp_input.c:6469) tcp_rcv_state_process (net/ipv4/tcp_input.c:6657) tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1929) __release_sock (./include/net/sock.h:1121 net/core/sock.c:2968) release_sock (net/core/sock.c:3536) inet_wait_for_connect (net/ipv4/af_inet.c:609) __inet_stream_connect (net/ipv4/af_inet.c:702) inet_stream_connect (net/ipv4/af_inet.c:748) __sys_connect (./include/linux/file.h:45 net/socket.c:2064) __x64_sys_connect (net/socket.c:2073 net/socket.c:2070 net/socket.c:2070) do_syscall_64 (arch/x86/entry/common.c:51 arch/x86/entry/common.c:82) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129) RIP: 0033:0x7fa10ff05a3d Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ab a3 0e 00 f7 d8 64 89 01 48 RSP: 002b:00007fa110183de8 EFLAGS: 00000202 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000020000054 RCX: 00007fa10ff05a3d RDX: 000000000000001c RSI: 0000000020000040 RDI: 0000000000000003 RBP: 00007fa110183e20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fa110184640 R13: 0000000000000000 R14: 00007fa10fe8b060 R15: 00007fff73e23b20 </TASK> The issue triggering process is analyzed as follows: Thread A Thread B tcp_v4_rcv //receive ack TCP packet inet_shutdown tcp_check_req tcp_disconnect //disconnect sock ... tcp_set_state(sk, TCP_CLOSE) inet_csk_complete_hashdance ... inet_csk_reqsk_queue_add ---truncated---
CVE-2024-26622: In the Linux kernel, the following vulnerability has been resolved: tomoyo: fix UAF write bug in tomoyo_write_control() Since tomoyo_write_control() updates head->write_buf when write() of long lines is requested, we need to fetch head->write_buf after head->io_sem is held. Otherwise, concurrent write() requests can cause use-after-free-write and double-free problems.
CVE-2024-26629: In the Linux kernel, the following vulnerability has been resolved: nfsd: fix RELEASE_LOCKOWNER The test on so_count in nfsd4_release_lockowner() is nonsense and harmful. Revert to using check_for_locks(), changing that to not sleep. First: harmful. As is documented in the kdoc comment for nfsd4_release_lockowner(), the test on so_count can transiently return a false positive resulting in a return of NFS4ERR_LOCKS_HELD when in fact no locks are held. This is clearly a protocol violation and with the Linux NFS client it can cause incorrect behaviour. If RELEASE_LOCKOWNER is sent while some other thread is still processing a LOCK request which failed because, at the time that request was received, the given owner held a conflicting lock, then the nfsd thread processing that LOCK request can hold a reference (conflock) to the lock owner that causes nfsd4_release_lockowner() to return an incorrect error. The Linux NFS client ignores that NFS4ERR_LOCKS_HELD error because it never sends NFS4_RELEASE_LOCKOWNER without first releasing any locks, so it knows that the error is impossible. It assumes the lock owner was in fact released so it feels free to use the same lock owner identifier in some later locking request. When it does reuse a lock owner identifier for which a previous RELEASE failed, it will naturally use a lock_seqid of zero. However the server, which didn't release the lock owner, will expect a larger lock_seqid and so will respond with NFS4ERR_BAD_SEQID. So clearly it is harmful to allow a false positive, which testing so_count allows. The test is nonsense because ... well... it doesn't mean anything. so_count is the sum of three different counts. 1/ the set of states listed on so_stateids 2/ the set of active vfs locks owned by any of those states 3/ various transient counts such as for conflicting locks. When it is tested against '2' it is clear that one of these is the transient reference obtained by find_lockowner_str_locked(). It is not clear what the other one is expected to be. In practice, the count is often 2 because there is precisely one state on so_stateids. If there were more, this would fail. In my testing I see two circumstances when RELEASE_LOCKOWNER is called. In one case, CLOSE is called before RELEASE_LOCKOWNER. That results in all the lock states being removed, and so the lockowner being discarded (it is removed when there are no more references which usually happens when the lock state is discarded). When nfsd4_release_lockowner() finds that the lock owner doesn't exist, it returns success. The other case shows an so_count of '2' and precisely one state listed in so_stateid. It appears that the Linux client uses a separate lock owner for each file resulting in one lock state per lock owner, so this test on '2' is safe. For another client it might not be safe. So this patch changes check_for_locks() to use the (newish) find_any_file_locked() so that it doesn't take a reference on the nfs4_file and so never calls nfsd_file_put(), and so never sleeps. With this check is it safe to restore the use of check_for_locks() rather than testing so_count against the mysterious '2'.
CVE-2024-26640: In the Linux kernel, the following vulnerability has been resolved: tcp: add sanity checks to rx zerocopy TCP rx zerocopy intent is to map pages initially allocated from NIC drivers, not pages owned by a fs. This patch adds to can_map_frag() these additional checks: - Page must not be a compound one. - page->mapping must be NULL. This fixes the panic reported by ZhangPeng. syzbot was able to loopback packets built with sendfile(), mapping pages owned by an ext4 file to TCP rx zerocopy. r3 = socket$inet_tcp(0x2, 0x1, 0x0) mmap(&(0x7f0000ff9000/0x4000)=nil, 0x4000, 0x0, 0x12, r3, 0x0) r4 = socket$inet_tcp(0x2, 0x1, 0x0) bind$inet(r4, &(0x7f0000000000)={0x2, 0x4e24, @multicast1}, 0x10) connect$inet(r4, &(0x7f00000006c0)={0x2, 0x4e24, @empty}, 0x10) r5 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00', 0x181e42, 0x0) fallocate(r5, 0x0, 0x0, 0x85b8) sendfile(r4, r5, 0x0, 0x8ba0) getsockopt$inet_tcp_TCP_ZEROCOPY_RECEIVE(r4, 0x6, 0x23, &(0x7f00000001c0)={&(0x7f0000ffb000/0x3000)=nil, 0x3000, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, &(0x7f0000000440)=0x40) r6 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00', 0x181e42, 0x0)
CVE-2024-26641: In the Linux kernel, the following vulnerability has been resolved: ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv() syzbot found __ip6_tnl_rcv() could access unitiliazed data [1]. Call pskb_inet_may_pull() to fix this, and initialize ipv6h variable after this call as it can change skb->head. [1] BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] BUG: KMSAN: uninit-value in IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] IP6_ECN_decapsulate+0x7df/0x1e50 include/net/inet_ecn.h:321 ip6ip6_dscp_ecn_decapsulate+0x178/0x1b0 net/ipv6/ip6_tunnel.c:727 __ip6_tnl_rcv+0xd4e/0x1590 net/ipv6/ip6_tunnel.c:845 ip6_tnl_rcv+0xce/0x100 net/ipv6/ip6_tunnel.c:888 gre_rcv+0x143f/0x1870 ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 ip6_input_finish net/ipv6/ip6_input.c:483 [inline] NF_HOOK include/linux/netfilter.h:314 [inline] ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 NF_HOOK include/linux/netfilter.h:314 [inline] ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 __netif_receive_skb_one_core net/core/dev.c:5532 [inline] __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646 netif_receive_skb_internal net/core/dev.c:5732 [inline] netif_receive_skb+0x58/0x660 net/core/dev.c:5791 tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555 tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:2084 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x786/0x1200 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b Uninit was created at: slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768 slab_alloc_node mm/slub.c:3478 [inline] kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560 __alloc_skb+0x318/0x740 net/core/skbuff.c:651 alloc_skb include/linux/skbuff.h:1286 [inline] alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2787 tun_alloc_skb drivers/net/tun.c:1531 [inline] tun_get_user+0x1e8a/0x66d0 drivers/net/tun.c:1846 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 call_write_iter include/linux/fs.h:2084 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x786/0x1200 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x6d/0x140 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b CPU: 0 PID: 5034 Comm: syz-executor331 Not tainted 6.7.0-syzkaller-00562-g9f8413c4a66f #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
CVE-2024-26644: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't abort filesystem when attempting to snapshot deleted subvolume If the source file descriptor to the snapshot ioctl refers to a deleted subvolume, we get the following abort: BTRFS: Transaction aborted (error -2) WARNING: CPU: 0 PID: 833 at fs/btrfs/transaction.c:1875 create_pending_snapshot+0x1040/0x1190 [btrfs] Modules linked in: pata_acpi btrfs ata_piix libata scsi_mod virtio_net blake2b_generic xor net_failover virtio_rng failover scsi_common rng_core raid6_pq libcrc32c CPU: 0 PID: 833 Comm: t_snapshot_dele Not tainted 6.7.0-rc6 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 RIP: 0010:create_pending_snapshot+0x1040/0x1190 [btrfs] RSP: 0018:ffffa09c01337af8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff9982053e7c78 RCX: 0000000000000027 RDX: ffff99827dc20848 RSI: 0000000000000001 RDI: ffff99827dc20840 RBP: ffffa09c01337c00 R08: 0000000000000000 R09: ffffa09c01337998 R10: 0000000000000003 R11: ffffffffb96da248 R12: fffffffffffffffe R13: ffff99820535bb28 R14: ffff99820b7bd000 R15: ffff99820381ea80 FS: 00007fe20aadabc0(0000) GS:ffff99827dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000559a120b502f CR3: 00000000055b6000 CR4: 00000000000006f0 Call Trace: <TASK> ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? __warn+0x81/0x130 ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? report_bug+0x171/0x1a0 ? handle_bug+0x3a/0x70 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? create_pending_snapshot+0x1040/0x1190 [btrfs] create_pending_snapshots+0x92/0xc0 [btrfs] btrfs_commit_transaction+0x66b/0xf40 [btrfs] btrfs_mksubvol+0x301/0x4d0 [btrfs] btrfs_mksnapshot+0x80/0xb0 [btrfs] __btrfs_ioctl_snap_create+0x1c2/0x1d0 [btrfs] btrfs_ioctl_snap_create_v2+0xc4/0x150 [btrfs] btrfs_ioctl+0x8a6/0x2650 [btrfs] ? kmem_cache_free+0x22/0x340 ? do_sys_openat2+0x97/0xe0 __x64_sys_ioctl+0x97/0xd0 do_syscall_64+0x46/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7fe20abe83af RSP: 002b:00007ffe6eff1360 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007fe20abe83af RDX: 00007ffe6eff23c0 RSI: 0000000050009417 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0000000000000000 R09: 00007fe20ad16cd0 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe6eff13c0 R14: 00007fe20ad45000 R15: 0000559a120b6d58 </TASK> ---[ end trace 0000000000000000 ]--- BTRFS: error (device vdc: state A) in create_pending_snapshot:1875: errno=-2 No such entry BTRFS info (device vdc: state EA): forced readonly BTRFS warning (device vdc: state EA): Skipping commit of aborted transaction. BTRFS: error (device vdc: state EA) in cleanup_transaction:2055: errno=-2 No such entry This happens because create_pending_snapshot() initializes the new root item as a copy of the source root item. This includes the refs field, which is 0 for a deleted subvolume. The call to btrfs_insert_root() therefore inserts a root with refs == 0. btrfs_get_new_fs_root() then finds the root and returns -ENOENT if refs == 0, which causes create_pending_snapshot() to abort. Fix it by checking the source root's refs before attempting the snapshot, but after locking subvol_sem to avoid racing with deletion.
CVE-2024-26646: In the Linux kernel, the following vulnerability has been resolved: thermal: intel: hfi: Add syscore callbacks for system-wide PM The kernel allocates a memory buffer and provides its location to the hardware, which uses it to update the HFI table. This allocation occurs during boot and remains constant throughout runtime. When resuming from hibernation, the restore kernel allocates a second memory buffer and reprograms the HFI hardware with the new location as part of a normal boot. The location of the second memory buffer may differ from the one allocated by the image kernel. When the restore kernel transfers control to the image kernel, its HFI buffer becomes invalid, potentially leading to memory corruption if the hardware writes to it (the hardware continues to use the buffer from the restore kernel). It is also possible that the hardware "forgets" the address of the memory buffer when resuming from "deep" suspend. Memory corruption may also occur in such a scenario. To prevent the described memory corruption, disable HFI when preparing to suspend or hibernate. Enable it when resuming. Add syscore callbacks to handle the package of the boot CPU (packages of non-boot CPUs are handled via CPU offline). Syscore ops always run on the boot CPU. Additionally, HFI only needs to be disabled during "deep" suspend and hibernation. Syscore ops only run in these cases. [ rjw: Comment adjustment, subject and changelog edits ]
CVE-2024-26647: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix late derefrence 'dsc' check in 'link_set_dsc_pps_packet()' In link_set_dsc_pps_packet(), 'struct display_stream_compressor *dsc' was dereferenced in a DC_LOGGER_INIT(dsc->ctx->logger); before the 'dsc' NULL pointer check. Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/dc/link/link_dpms.c:905 link_set_dsc_pps_packet() warn: variable dereferenced before check 'dsc' (see line 903)
CVE-2024-26648: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix variable deferencing before NULL check in edp_setup_replay() In edp_setup_replay(), 'struct dc *dc' & 'struct dmub_replay *replay' was dereferenced before the pointer 'link' & 'replay' NULL check. Fixes the below: drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_edp_panel_control.c:947 edp_setup_replay() warn: variable dereferenced before check 'link' (see line 933)
CVE-2024-26656: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: fix use-after-free bug The bug can be triggered by sending a single amdgpu_gem_userptr_ioctl to the AMDGPU DRM driver on any ASICs with an invalid address and size. The bug was reported by Joonkyo Jung <joonkyoj@yonsei.ac.kr>. For example the following code: static void Syzkaller1(int fd) { struct drm_amdgpu_gem_userptr arg; int ret; arg.addr = 0xffffffffffff0000; arg.size = 0x80000000; /*2 Gb*/ arg.flags = 0x7; ret = drmIoctl(fd, 0xc1186451/*amdgpu_gem_userptr_ioctl*/, &arg); } Due to the address and size are not valid there is a failure in amdgpu_hmm_register->mmu_interval_notifier_insert->__mmu_interval_notifier_insert-> check_shl_overflow, but we even the amdgpu_hmm_register failure we still call amdgpu_hmm_unregister into amdgpu_gem_object_free which causes access to a bad address. The following stack is below when the issue is reproduced when Kazan is enabled: [ +0.000014] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.000009] RIP: 0010:mmu_interval_notifier_remove+0x327/0x340 [ +0.000017] Code: ff ff 49 89 44 24 08 48 b8 00 01 00 00 00 00 ad de 4c 89 f7 49 89 47 40 48 83 c0 22 49 89 47 48 e8 ce d1 2d 01 e9 32 ff ff ff <0f> 0b e9 16 ff ff ff 4c 89 ef e8 fa 14 b3 ff e9 36 ff ff ff e8 80 [ +0.000014] RSP: 0018:ffffc90002657988 EFLAGS: 00010246 [ +0.000013] RAX: 0000000000000000 RBX: 1ffff920004caf35 RCX: ffffffff8160565b [ +0.000011] RDX: dffffc0000000000 RSI: 0000000000000004 RDI: ffff8881a9f78260 [ +0.000010] RBP: ffffc90002657a70 R08: 0000000000000001 R09: fffff520004caf25 [ +0.000010] R10: 0000000000000003 R11: ffffffff8161d1d6 R12: ffff88810e988c00 [ +0.000010] R13: ffff888126fb5a00 R14: ffff88810e988c0c R15: ffff8881a9f78260 [ +0.000011] FS: 00007ff9ec848540(0000) GS:ffff8883cc880000(0000) knlGS:0000000000000000 [ +0.000012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ +0.000010] CR2: 000055b3f7e14328 CR3: 00000001b5770000 CR4: 0000000000350ef0 [ +0.000010] Call Trace: [ +0.000006] <TASK> [ +0.000007] ? show_regs+0x6a/0x80 [ +0.000018] ? __warn+0xa5/0x1b0 [ +0.000019] ? mmu_interval_notifier_remove+0x327/0x340 [ +0.000018] ? report_bug+0x24a/0x290 [ +0.000022] ? handle_bug+0x46/0x90 [ +0.000015] ? exc_invalid_op+0x19/0x50 [ +0.000016] ? asm_exc_invalid_op+0x1b/0x20 [ +0.000017] ? kasan_save_stack+0x26/0x50 [ +0.000017] ? mmu_interval_notifier_remove+0x23b/0x340 [ +0.000019] ? mmu_interval_notifier_remove+0x327/0x340 [ +0.000019] ? mmu_interval_notifier_remove+0x23b/0x340 [ +0.000020] ? __pfx_mmu_interval_notifier_remove+0x10/0x10 [ +0.000017] ? kasan_save_alloc_info+0x1e/0x30 [ +0.000018] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? __kasan_kmalloc+0xb1/0xc0 [ +0.000018] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? __kasan_check_read+0x11/0x20 [ +0.000020] amdgpu_hmm_unregister+0x34/0x50 [amdgpu] [ +0.004695] amdgpu_gem_object_free+0x66/0xa0 [amdgpu] [ +0.004534] ? __pfx_amdgpu_gem_object_free+0x10/0x10 [amdgpu] [ +0.004291] ? do_syscall_64+0x5f/0xe0 [ +0.000023] ? srso_return_thunk+0x5/0x5f [ +0.000017] drm_gem_object_free+0x3b/0x50 [drm] [ +0.000489] amdgpu_gem_userptr_ioctl+0x306/0x500 [amdgpu] [ +0.004295] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004270] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? __this_cpu_preempt_check+0x13/0x20 [ +0.000015] ? srso_return_thunk+0x5/0x5f [ +0.000013] ? sysvec_apic_timer_interrupt+0x57/0xc0 [ +0.000020] ? srso_return_thunk+0x5/0x5f [ +0.000014] ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 [ +0.000022] ? drm_ioctl_kernel+0x17b/0x1f0 [drm] [ +0.000496] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004272] ? drm_ioctl_kernel+0x190/0x1f0 [drm] [ +0.000492] drm_ioctl_kernel+0x140/0x1f0 [drm] [ +0.000497] ? __pfx_amdgpu_gem_userptr_ioctl+0x10/0x10 [amdgpu] [ +0.004297] ? __pfx_drm_ioctl_kernel+0x10/0x10 [d ---truncated---
CVE-2024-26658: In the Linux kernel, the following vulnerability has been resolved: bcachefs: grab s_umount only if snapshotting When I was testing mongodb over bcachefs with compression, there is a lockdep warning when snapshotting mongodb data volume. $ cat test.sh prog=bcachefs $prog subvolume create /mnt/data $prog subvolume create /mnt/data/snapshots while true;do $prog subvolume snapshot /mnt/data /mnt/data/snapshots/$(date +%s) sleep 1s done $ cat /etc/mongodb.conf systemLog: destination: file logAppend: true path: /mnt/data/mongod.log storage: dbPath: /mnt/data/ lockdep reports: [ 3437.452330] ====================================================== [ 3437.452750] WARNING: possible circular locking dependency detected [ 3437.453168] 6.7.0-rc7-custom+ #85 Tainted: G E [ 3437.453562] ------------------------------------------------------ [ 3437.453981] bcachefs/35533 is trying to acquire lock: [ 3437.454325] ffffa0a02b2b1418 (sb_writers#10){.+.+}-{0:0}, at: filename_create+0x62/0x190 [ 3437.454875] but task is already holding lock: [ 3437.455268] ffffa0a02b2b10e0 (&type->s_umount_key#48){.+.+}-{3:3}, at: bch2_fs_file_ioctl+0x232/0xc90 [bcachefs] [ 3437.456009] which lock already depends on the new lock. [ 3437.456553] the existing dependency chain (in reverse order) is: [ 3437.457054] -> #3 (&type->s_umount_key#48){.+.+}-{3:3}: [ 3437.457507] down_read+0x3e/0x170 [ 3437.457772] bch2_fs_file_ioctl+0x232/0xc90 [bcachefs] [ 3437.458206] __x64_sys_ioctl+0x93/0xd0 [ 3437.458498] do_syscall_64+0x42/0xf0 [ 3437.458779] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 3437.459155] -> #2 (&c->snapshot_create_lock){++++}-{3:3}: [ 3437.459615] down_read+0x3e/0x170 [ 3437.459878] bch2_truncate+0x82/0x110 [bcachefs] [ 3437.460276] bchfs_truncate+0x254/0x3c0 [bcachefs] [ 3437.460686] notify_change+0x1f1/0x4a0 [ 3437.461283] do_truncate+0x7f/0xd0 [ 3437.461555] path_openat+0xa57/0xce0 [ 3437.461836] do_filp_open+0xb4/0x160 [ 3437.462116] do_sys_openat2+0x91/0xc0 [ 3437.462402] __x64_sys_openat+0x53/0xa0 [ 3437.462701] do_syscall_64+0x42/0xf0 [ 3437.462982] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 3437.463359] -> #1 (&sb->s_type->i_mutex_key#15){+.+.}-{3:3}: [ 3437.463843] down_write+0x3b/0xc0 [ 3437.464223] bch2_write_iter+0x5b/0xcc0 [bcachefs] [ 3437.464493] vfs_write+0x21b/0x4c0 [ 3437.464653] ksys_write+0x69/0xf0 [ 3437.464839] do_syscall_64+0x42/0xf0 [ 3437.465009] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 3437.465231] -> #0 (sb_writers#10){.+.+}-{0:0}: [ 3437.465471] __lock_acquire+0x1455/0x21b0 [ 3437.465656] lock_acquire+0xc6/0x2b0 [ 3437.465822] mnt_want_write+0x46/0x1a0 [ 3437.465996] filename_create+0x62/0x190 [ 3437.466175] user_path_create+0x2d/0x50 [ 3437.466352] bch2_fs_file_ioctl+0x2ec/0xc90 [bcachefs] [ 3437.466617] __x64_sys_ioctl+0x93/0xd0 [ 3437.466791] do_syscall_64+0x42/0xf0 [ 3437.466957] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 3437.467180] other info that might help us debug this: [ 3437.469670] 2 locks held by bcachefs/35533: other info that might help us debug this: [ 3437.467507] Chain exists of: sb_writers#10 --> &c->snapshot_create_lock --> &type->s_umount_key#48 [ 3437.467979] Possible unsafe locking scenario: [ 3437.468223] CPU0 CPU1 [ 3437.468405] ---- ---- [ 3437.468585] rlock(&type->s_umount_key#48); [ 3437.468758] lock(&c->snapshot_create_lock); [ 3437.469030] lock(&type->s_umount_key#48); [ 3437.469291] rlock(sb_writers#10); [ 3437.469434] *** DEADLOCK *** [ 3437.469 ---truncated---
CVE-2024-26659: In the Linux kernel, the following vulnerability has been resolved: xhci: handle isoc Babble and Buffer Overrun events properly xHCI 4.9 explicitly forbids assuming that the xHC has released its ownership of a multi-TRB TD when it reports an error on one of the early TRBs. Yet the driver makes such assumption and releases the TD, allowing the remaining TRBs to be freed or overwritten by new TDs. The xHC should also report completion of the final TRB due to its IOC flag being set by us, regardless of prior errors. This event cannot be recognized if the TD has already been freed earlier, resulting in "Transfer event TRB DMA ptr not part of current TD" error message. Fix this by reusing the logic for processing isoc Transaction Errors. This also handles hosts which fail to report the final completion. Fix transfer length reporting on Babble errors. They may be caused by device malfunction, no guarantee that the buffer has been filled.
CVE-2024-26668: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_limit: reject configurations that cause integer overflow Reject bogus configs where internal token counter wraps around. This only occurs with very very large requests, such as 17gbyte/s. Its better to reject this rather than having incorrect ratelimit.
CVE-2024-26672: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Fix variable 'mca_funcs' dereferenced before NULL check in 'amdgpu_mca_smu_get_mca_entry()' Fixes the below: drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c:377 amdgpu_mca_smu_get_mca_entry() warn: variable dereferenced before check 'mca_funcs' (see line 368) 357 int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, 358 int idx, struct mca_bank_entry *entry) 359 { 360 const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; 361 int count; 362 363 switch (type) { 364 case AMDGPU_MCA_ERROR_TYPE_UE: 365 count = mca_funcs->max_ue_count; mca_funcs is dereferenced here. 366 break; 367 case AMDGPU_MCA_ERROR_TYPE_CE: 368 count = mca_funcs->max_ce_count; mca_funcs is dereferenced here. 369 break; 370 default: 371 return -EINVAL; 372 } 373 374 if (idx >= count) 375 return -EINVAL; 376 377 if (mca_funcs && mca_funcs->mca_get_mca_entry) ^^^^^^^^^ Checked too late!
CVE-2024-26677: In the Linux kernel, the following vulnerability has been resolved: rxrpc: Fix delayed ACKs to not set the reference serial number Fix the construction of delayed ACKs to not set the reference serial number as they can't be used as an RTT reference.
CVE-2024-26686: In the Linux kernel, the following vulnerability has been resolved: fs/proc: do_task_stat: use sig->stats_lock to gather the threads/children stats lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call do_task_stat() at the same time and the process has NR_THREADS, it will spin with irqs disabled O(NR_CPUS * NR_THREADS) time. Change do_task_stat() to use sig->stats_lock to gather the statistics outside of ->siglock protected section, in the likely case this code will run lockless.
CVE-2024-26687: In the Linux kernel, the following vulnerability has been resolved: xen/events: close evtchn after mapping cleanup shutdown_pirq and startup_pirq are not taking the irq_mapping_update_lock because they can't due to lock inversion. Both are called with the irq_desc->lock being taking. The lock order, however, is first irq_mapping_update_lock and then irq_desc->lock. This opens multiple races: - shutdown_pirq can be interrupted by a function that allocates an event channel: CPU0 CPU1 shutdown_pirq { xen_evtchn_close(e) __startup_pirq { EVTCHNOP_bind_pirq -> returns just freed evtchn e set_evtchn_to_irq(e, irq) } xen_irq_info_cleanup() { set_evtchn_to_irq(e, -1) } } Assume here event channel e refers here to the same event channel number. After this race the evtchn_to_irq mapping for e is invalid (-1). - __startup_pirq races with __unbind_from_irq in a similar way. Because __startup_pirq doesn't take irq_mapping_update_lock it can grab the evtchn that __unbind_from_irq is currently freeing and cleaning up. In this case even though the event channel is allocated, its mapping can be unset in evtchn_to_irq. The fix is to first cleanup the mappings and then close the event channel. In this way, when an event channel gets allocated it's potential previous evtchn_to_irq mappings are guaranteed to be unset already. This is also the reverse order of the allocation where first the event channel is allocated and then the mappings are setup. On a 5.10 kernel prior to commit 3fcdaf3d7634 ("xen/events: modify internal [un]bind interfaces"), we hit a BUG like the following during probing of NVMe devices. The issue is that during nvme_setup_io_queues, pci_free_irq is called for every device which results in a call to shutdown_pirq. With many nvme devices it's therefore likely to hit this race during boot because there will be multiple calls to shutdown_pirq and startup_pirq are running potentially in parallel. ------------[ cut here ]------------ blkfront: xvda: barrier or flush: disabled; persistent grants: enabled; indirect descriptors: enabled; bounce buffer: enabled kernel BUG at drivers/xen/events/events_base.c:499! invalid opcode: 0000 [#1] SMP PTI CPU: 44 PID: 375 Comm: kworker/u257:23 Not tainted 5.10.201-191.748.amzn2.x86_64 #1 Hardware name: Xen HVM domU, BIOS 4.11.amazon 08/24/2006 Workqueue: nvme-reset-wq nvme_reset_work RIP: 0010:bind_evtchn_to_cpu+0xdf/0xf0 Code: 5d 41 5e c3 cc cc cc cc 44 89 f7 e8 2b 55 ad ff 49 89 c5 48 85 c0 0f 84 64 ff ff ff 4c 8b 68 30 41 83 fe ff 0f 85 60 ff ff ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00 RSP: 0000:ffffc9000d533b08 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000006 RDX: 0000000000000028 RSI: 00000000ffffffff RDI: 00000000ffffffff RBP: ffff888107419680 R08: 0000000000000000 R09: ffffffff82d72b00 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000001ed R13: 0000000000000000 R14: 00000000ffffffff R15: 0000000000000002 FS: 0000000000000000(0000) GS:ffff88bc8b500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000002610001 CR4: 00000000001706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? show_trace_log_lvl+0x1c1/0x2d9 ? show_trace_log_lvl+0x1c1/0x2d9 ? set_affinity_irq+0xdc/0x1c0 ? __die_body.cold+0x8/0xd ? die+0x2b/0x50 ? do_trap+0x90/0x110 ? bind_evtchn_to_cpu+0xdf/0xf0 ? do_error_trap+0x65/0x80 ? bind_evtchn_to_cpu+0xdf/0xf0 ? exc_invalid_op+0x4e/0x70 ? bind_evtchn_to_cpu+0xdf/0xf0 ? asm_exc_invalid_op+0x12/0x20 ? bind_evtchn_to_cpu+0xdf/0x ---truncated---
CVE-2024-26689: In the Linux kernel, the following vulnerability has been resolved: ceph: prevent use-after-free in encode_cap_msg() In fs/ceph/caps.c, in encode_cap_msg(), "use after free" error was caught by KASAN at this line - 'ceph_buffer_get(arg->xattr_buf);'. This implies before the refcount could be increment here, it was freed. In same file, in "handle_cap_grant()" refcount is decremented by this line - 'ceph_buffer_put(ci->i_xattrs.blob);'. It appears that a race occurred and resource was freed by the latter line before the former line could increment it. encode_cap_msg() is called by __send_cap() and __send_cap() is called by ceph_check_caps() after calling __prep_cap(). __prep_cap() is where arg->xattr_buf is assigned to ci->i_xattrs.blob. This is the spot where the refcount must be increased to prevent "use after free" error.
CVE-2024-26691: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Fix circular locking dependency The rule inside kvm enforces that the vcpu->mutex is taken *inside* kvm->lock. The rule is violated by the pkvm_create_hyp_vm() which acquires the kvm->lock while already holding the vcpu->mutex lock from kvm_vcpu_ioctl(). Avoid the circular locking dependency altogether by protecting the hyp vm handle with the config_lock, much like we already do for other forms of VM-scoped data.
CVE-2024-26699: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix array-index-out-of-bounds in dcn35_clkmgr [Why] There is a potential memory access violation while iterating through array of dcn35 clks. [How] Limit iteration per array size.
CVE-2024-26700: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix MST Null Ptr for RV The change try to fix below error specific to RV platform: BUG: kernel NULL pointer dereference, address: 0000000000000008 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2 Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022 RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0 Call Trace: <TASK> ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? plist_add+0xbe/0x100 ? exc_page_fault+0x7c/0x180 ? asm_exc_page_fault+0x26/0x30 ? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] ? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026] compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] ? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] drm_atomic_check_only+0x5c5/0xa40 drm_mode_atomic_ioctl+0x76e/0xbc0 ? _copy_to_user+0x25/0x30 ? drm_ioctl+0x296/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 drm_ioctl_kernel+0xcd/0x170 drm_ioctl+0x26d/0x4b0 ? __pfx_drm_mode_atomic_ioctl+0x10/0x10 amdgpu_drm_ioctl+0x4e/0x90 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054] __x64_sys_ioctl+0x94/0xd0 do_syscall_64+0x60/0x90 ? do_syscall_64+0x6c/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f4dad17f76f Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c> RSP: 002b:00007ffd9ae859f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 000055e255a55900 RCX: 00007f4dad17f76f RDX: 00007ffd9ae85a90 RSI: 00000000c03864bc RDI: 000000000000000b RBP: 00007ffd9ae85a90 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c03864bc R13: 000000000000000b R14: 000055e255a7fc60 R15: 000055e255a01eb0 </TASK> Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device ccm cmac algif_hash algif_skcipher af_alg joydev mousedev bnep > typec libphy k10temp ipmi_msghandler roles i2c_scmi acpi_cpufreq mac_hid nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_mas> CR2: 0000000000000008 ---[ end trace 0000000000000000 ]--- RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper] Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8> RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224 RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280 RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850 R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000 R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224 FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000 ---truncated---
CVE-2024-26706: In the Linux kernel, the following vulnerability has been resolved: parisc: Fix random data corruption from exception handler The current exception handler implementation, which assists when accessing user space memory, may exhibit random data corruption if the compiler decides to use a different register than the specified register %r29 (defined in ASM_EXCEPTIONTABLE_REG) for the error code. If the compiler choose another register, the fault handler will nevertheless store -EFAULT into %r29 and thus trash whatever this register is used for. Looking at the assembly I found that this happens sometimes in emulate_ldd(). To solve the issue, the easiest solution would be if it somehow is possible to tell the fault handler which register is used to hold the error code. Using %0 or %1 in the inline assembly is not posssible as it will show up as e.g. %r29 (with the "%r" prefix), which the GNU assembler can not convert to an integer. This patch takes another, better and more flexible approach: We extend the __ex_table (which is out of the execution path) by one 32-word. In this word we tell the compiler to insert the assembler instruction "or %r0,%r0,%reg", where %reg references the register which the compiler choosed for the error return code. In case of an access failure, the fault handler finds the __ex_table entry and can examine the opcode. The used register is encoded in the lowest 5 bits, and the fault handler can then store -EFAULT into this register. Since we extend the __ex_table to 3 words we can't use the BUILDTIME_TABLE_SORT config option any longer.
CVE-2024-26715: In the Linux kernel, the following vulnerability has been resolved: usb: dwc3: gadget: Fix NULL pointer dereference in dwc3_gadget_suspend In current scenario if Plug-out and Plug-In performed continuously there could be a chance while checking for dwc->gadget_driver in dwc3_gadget_suspend, a NULL pointer dereference may occur. Call Stack: CPU1: CPU2: gadget_unbind_driver dwc3_suspend_common dwc3_gadget_stop dwc3_gadget_suspend dwc3_disconnect_gadget CPU1 basically clears the variable and CPU2 checks the variable. Consider CPU1 is running and right before gadget_driver is cleared and in parallel CPU2 executes dwc3_gadget_suspend where it finds dwc->gadget_driver which is not NULL and resumes execution and then CPU1 completes execution. CPU2 executes dwc3_disconnect_gadget where it checks dwc->gadget_driver is already NULL because of which the NULL pointer deference occur.
CVE-2024-26719: In the Linux kernel, the following vulnerability has been resolved: nouveau: offload fence uevents work to workqueue This should break the deadlock between the fctx lock and the irq lock. This offloads the processing off the work from the irq into a workqueue.
CVE-2024-26726: In the Linux kernel, the following vulnerability has been resolved: btrfs: don't drop extent_map for free space inode on write error While running the CI for an unrelated change I hit the following panic with generic/648 on btrfs_holes_spacecache. assertion failed: block_start != EXTENT_MAP_HOLE, in fs/btrfs/extent_io.c:1385 ------------[ cut here ]------------ kernel BUG at fs/btrfs/extent_io.c:1385! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 2695096 Comm: fsstress Kdump: loaded Tainted: G W 6.8.0-rc2+ #1 RIP: 0010:__extent_writepage_io.constprop.0+0x4c1/0x5c0 Call Trace: <TASK> extent_write_cache_pages+0x2ac/0x8f0 extent_writepages+0x87/0x110 do_writepages+0xd5/0x1f0 filemap_fdatawrite_wbc+0x63/0x90 __filemap_fdatawrite_range+0x5c/0x80 btrfs_fdatawrite_range+0x1f/0x50 btrfs_write_out_cache+0x507/0x560 btrfs_write_dirty_block_groups+0x32a/0x420 commit_cowonly_roots+0x21b/0x290 btrfs_commit_transaction+0x813/0x1360 btrfs_sync_file+0x51a/0x640 __x64_sys_fdatasync+0x52/0x90 do_syscall_64+0x9c/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 This happens because we fail to write out the free space cache in one instance, come back around and attempt to write it again. However on the second pass through we go to call btrfs_get_extent() on the inode to get the extent mapping. Because this is a new block group, and with the free space inode we always search the commit root to avoid deadlocking with the tree, we find nothing and return a EXTENT_MAP_HOLE for the requested range. This happens because the first time we try to write the space cache out we hit an error, and on an error we drop the extent mapping. This is normal for normal files, but the free space cache inode is special. We always expect the extent map to be correct. Thus the second time through we end up with a bogus extent map. Since we're deprecating this feature, the most straightforward way to fix this is to simply skip dropping the extent map range for this failed range. I shortened the test by using error injection to stress the area to make it easier to reproduce. With this patch in place we no longer panic with my error injection test.
CVE-2024-26733: In the Linux kernel, the following vulnerability has been resolved: arp: Prevent overflow in arp_req_get(). syzkaller reported an overflown write in arp_req_get(). [0] When ioctl(SIOCGARP) is issued, arp_req_get() looks up an neighbour entry and copies neigh->ha to struct arpreq.arp_ha.sa_data. The arp_ha here is struct sockaddr, not struct sockaddr_storage, so the sa_data buffer is just 14 bytes. In the splat below, 2 bytes are overflown to the next int field, arp_flags. We initialise the field just after the memcpy(), so it's not a problem. However, when dev->addr_len is greater than 22 (e.g. MAX_ADDR_LEN), arp_netmask is overwritten, which could be set as htonl(0xFFFFFFFFUL) in arp_ioctl() before calling arp_req_get(). To avoid the overflow, let's limit the max length of memcpy(). Note that commit b5f0de6df6dc ("net: dev: Convert sa_data to flexible array in struct sockaddr") just silenced syzkaller. [0]: memcpy: detected field-spanning write (size 16) of single field "r->arp_ha.sa_data" at net/ipv4/arp.c:1128 (size 14) WARNING: CPU: 0 PID: 144638 at net/ipv4/arp.c:1128 arp_req_get+0x411/0x4a0 net/ipv4/arp.c:1128 Modules linked in: CPU: 0 PID: 144638 Comm: syz-executor.4 Not tainted 6.1.74 #31 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-debian-1.16.0-5 04/01/2014 RIP: 0010:arp_req_get+0x411/0x4a0 net/ipv4/arp.c:1128 Code: fd ff ff e8 41 42 de fb b9 0e 00 00 00 4c 89 fe 48 c7 c2 20 6d ab 87 48 c7 c7 80 6d ab 87 c6 05 25 af 72 04 01 e8 5f 8d ad fb <0f> 0b e9 6c fd ff ff e8 13 42 de fb be 03 00 00 00 4c 89 e7 e8 a6 RSP: 0018:ffffc900050b7998 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff88803a815000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8641a44a RDI: 0000000000000001 RBP: ffffc900050b7a98 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 203a7970636d656d R12: ffff888039c54000 R13: 1ffff92000a16f37 R14: ffff88803a815084 R15: 0000000000000010 FS: 00007f172bf306c0(0000) GS:ffff88805aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f172b3569f0 CR3: 0000000057f12005 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> arp_ioctl+0x33f/0x4b0 net/ipv4/arp.c:1261 inet_ioctl+0x314/0x3a0 net/ipv4/af_inet.c:981 sock_do_ioctl+0xdf/0x260 net/socket.c:1204 sock_ioctl+0x3ef/0x650 net/socket.c:1321 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x18e/0x220 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x64/0xce RIP: 0033:0x7f172b262b8d Code: 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f172bf300b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007f172b3abf80 RCX: 00007f172b262b8d RDX: 0000000020000000 RSI: 0000000000008954 RDI: 0000000000000003 RBP: 00007f172b2d3493 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007f172b3abf80 R15: 00007f172bf10000 </TASK>
CVE-2024-26736: In the Linux kernel, the following vulnerability has been resolved: afs: Increase buffer size in afs_update_volume_status() The max length of volume->vid value is 20 characters. So increase idbuf[] size up to 24 to avoid overflow. Found by Linux Verification Center (linuxtesting.org) with SVACE. [DH: Actually, it's 20 + NUL, so increase it to 24 and use snprintf()]
CVE-2024-26739: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_mirred: don't override retval if we already lost the skb If we're redirecting the skb, and haven't called tcf_mirred_forward(), yet, we need to tell the core to drop the skb by setting the retcode to SHOT. If we have called tcf_mirred_forward(), however, the skb is out of our hands and returning SHOT will lead to UaF. Move the retval override to the error path which actually need it.
CVE-2024-26740: In the Linux kernel, the following vulnerability has been resolved: net/sched: act_mirred: use the backlog for mirred ingress The test Davide added in commit ca22da2fbd69 ("act_mirred: use the backlog for nested calls to mirred ingress") hangs our testing VMs every 10 or so runs, with the familiar tcp_v4_rcv -> tcp_v4_rcv deadlock reported by lockdep. The problem as previously described by Davide (see Link) is that if we reverse flow of traffic with the redirect (egress -> ingress) we may reach the same socket which generated the packet. And we may still be holding its socket lock. The common solution to such deadlocks is to put the packet in the Rx backlog, rather than run the Rx path inline. Do that for all egress -> ingress reversals, not just once we started to nest mirred calls. In the past there was a concern that the backlog indirection will lead to loss of error reporting / less accurate stats. But the current workaround does not seem to address the issue.
CVE-2024-26743: In the Linux kernel, the following vulnerability has been resolved: RDMA/qedr: Fix qedr_create_user_qp error flow Avoid the following warning by making sure to free the allocated resources in case that qedr_init_user_queue() fail. -----------[ cut here ]----------- WARNING: CPU: 0 PID: 143192 at drivers/infiniband/core/rdma_core.c:874 uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] Modules linked in: tls target_core_user uio target_core_pscsi target_core_file target_core_iblock ib_srpt ib_srp scsi_transport_srp nfsd nfs_acl rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs 8021q garp mrp stp llc ext4 mbcache jbd2 opa_vnic ib_umad ib_ipoib sunrpc rdma_ucm ib_isert iscsi_target_mod target_core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm hfi1 intel_rapl_msr intel_rapl_common mgag200 qedr sb_edac drm_shmem_helper rdmavt x86_pkg_temp_thermal drm_kms_helper intel_powerclamp ib_uverbs coretemp i2c_algo_bit kvm_intel dell_wmi_descriptor ipmi_ssif sparse_keymap kvm ib_core rfkill syscopyarea sysfillrect video sysimgblt irqbypass ipmi_si ipmi_devintf fb_sys_fops rapl iTCO_wdt mxm_wmi iTCO_vendor_support intel_cstate pcspkr dcdbas intel_uncore ipmi_msghandler lpc_ich acpi_power_meter mei_me mei fuse drm xfs libcrc32c qede sd_mod ahci libahci t10_pi sg crct10dif_pclmul crc32_pclmul crc32c_intel qed libata tg3 ghash_clmulni_intel megaraid_sas crc8 wmi [last unloaded: ib_srpt] CPU: 0 PID: 143192 Comm: fi_rdm_tagged_p Kdump: loaded Not tainted 5.14.0-408.el9.x86_64 #1 Hardware name: Dell Inc. PowerEdge R430/03XKDV, BIOS 2.14.0 01/25/2022 RIP: 0010:uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] Code: 5d 41 5c 41 5d 41 5e e9 0f 26 1b dd 48 89 df e8 67 6a ff ff 49 8b 86 10 01 00 00 48 85 c0 74 9c 4c 89 e7 e8 83 c0 cb dd eb 92 <0f> 0b eb be 0f 0b be 04 00 00 00 48 89 df e8 8e f5 ff ff e9 6d ff RSP: 0018:ffffb7c6cadfbc60 EFLAGS: 00010286 RAX: ffff8f0889ee3f60 RBX: ffff8f088c1a5200 RCX: 00000000802a0016 RDX: 00000000802a0017 RSI: 0000000000000001 RDI: ffff8f0880042600 RBP: 0000000000000001 R08: 0000000000000001 R09: 0000000000000000 R10: ffff8f11fffd5000 R11: 0000000000039000 R12: ffff8f0d5b36cd80 R13: ffff8f088c1a5250 R14: ffff8f1206d91000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8f11d7c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000147069200e20 CR3: 00000001c7210002 CR4: 00000000001706f0 Call Trace: <TASK> ? show_trace_log_lvl+0x1c4/0x2df ? show_trace_log_lvl+0x1c4/0x2df ? ib_uverbs_close+0x1f/0xb0 [ib_uverbs] ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ? __warn+0x81/0x110 ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ? report_bug+0x10a/0x140 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? uverbs_destroy_ufile_hw+0xcf/0xf0 [ib_uverbs] ib_uverbs_close+0x1f/0xb0 [ib_uverbs] __fput+0x94/0x250 task_work_run+0x5c/0x90 do_exit+0x270/0x4a0 do_group_exit+0x2d/0x90 get_signal+0x87c/0x8c0 arch_do_signal_or_restart+0x25/0x100 ? ib_uverbs_ioctl+0xc2/0x110 [ib_uverbs] exit_to_user_mode_loop+0x9c/0x130 exit_to_user_mode_prepare+0xb6/0x100 syscall_exit_to_user_mode+0x12/0x40 do_syscall_64+0x69/0x90 ? syscall_exit_work+0x103/0x130 ? syscall_exit_to_user_mode+0x22/0x40 ? do_syscall_64+0x69/0x90 ? syscall_exit_work+0x103/0x130 ? syscall_exit_to_user_mode+0x22/0x40 ? do_syscall_64+0x69/0x90 ? do_syscall_64+0x69/0x90 ? common_interrupt+0x43/0xa0 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x1470abe3ec6b Code: Unable to access opcode bytes at RIP 0x1470abe3ec41. RSP: 002b:00007fff13ce9108 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: fffffffffffffffc RBX: 00007fff13ce9218 RCX: 00001470abe3ec6b RDX: 00007fff13ce9200 RSI: 00000000c0181b01 RDI: 0000000000000004 RBP: 00007fff13ce91e0 R08: 0000558d9655da10 R09: 0000558d9655dd00 R10: 00007fff13ce95c0 R11: 0000000000000246 R12: 00007fff13ce9358 R13: 0000000000000013 R14: 0000558d9655db50 R15: 00007fff13ce9470 </TASK> --[ end trace 888a9b92e04c5c97 ]--
CVE-2024-26747: In the Linux kernel, the following vulnerability has been resolved: usb: roles: fix NULL pointer issue when put module's reference In current design, usb role class driver will get usb_role_switch parent's module reference after the user get usb_role_switch device and put the reference after the user put the usb_role_switch device. However, the parent device of usb_role_switch may be removed before the user put the usb_role_switch. If so, then, NULL pointer issue will be met when the user put the parent module's reference. This will save the module pointer in structure of usb_role_switch. Then, we don't need to find module by iterating long relations.
CVE-2024-26756: In the Linux kernel, the following vulnerability has been resolved: md: Don't register sync_thread for reshape directly Currently, if reshape is interrupted, then reassemble the array will register sync_thread directly from pers->run(), in this case 'MD_RECOVERY_RUNNING' is set directly, however, there is no guarantee that md_do_sync() will be executed, hence stop_sync_thread() will hang because 'MD_RECOVERY_RUNNING' can't be cleared. Last patch make sure that md_do_sync() will set MD_RECOVERY_DONE, however, following hang can still be triggered by dm-raid test shell/lvconvert-raid-reshape.sh occasionally: [root@fedora ~]# cat /proc/1982/stack [<0>] stop_sync_thread+0x1ab/0x270 [md_mod] [<0>] md_frozen_sync_thread+0x5c/0xa0 [md_mod] [<0>] raid_presuspend+0x1e/0x70 [dm_raid] [<0>] dm_table_presuspend_targets+0x40/0xb0 [dm_mod] [<0>] __dm_destroy+0x2a5/0x310 [dm_mod] [<0>] dm_destroy+0x16/0x30 [dm_mod] [<0>] dev_remove+0x165/0x290 [dm_mod] [<0>] ctl_ioctl+0x4bb/0x7b0 [dm_mod] [<0>] dm_ctl_ioctl+0x11/0x20 [dm_mod] [<0>] vfs_ioctl+0x21/0x60 [<0>] __x64_sys_ioctl+0xb9/0xe0 [<0>] do_syscall_64+0xc6/0x230 [<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74 Meanwhile mddev->recovery is: MD_RECOVERY_RUNNING | MD_RECOVERY_INTR | MD_RECOVERY_RESHAPE | MD_RECOVERY_FROZEN Fix this problem by remove the code to register sync_thread directly from raid10 and raid5. And let md_check_recovery() to register sync_thread.
CVE-2024-26757: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore read-only array in md_check_recovery() Usually if the array is not read-write, md_check_recovery() won't register new sync_thread in the first place. And if the array is read-write and sync_thread is registered, md_set_readonly() will unregister sync_thread before setting the array read-only. md/raid follow this behavior hence there is no problem. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) array is read-only. dm-raid update super block: rs_update_sbs ro = mddev->ro mddev->ro = 0 -> set array read-write md_update_sb 2) register new sync thread concurrently. 3) dm-raid set array back to read-only: rs_update_sbs mddev->ro = ro 4) stop the array: raid_dtr md_stop stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 5) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 6) daemon thread can't unregister sync thread: md_check_recovery if (!md_is_rdwr(mddev) && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) return; -> -> MD_RECOVERY_RUNNING can't be cleared, hence step 4 hang; The root cause is that dm-raid manipulate 'mddev->ro' by itself, however, dm-raid really should stop sync thread before setting the array read-only. Unfortunately, I need to read more code before I can refacter the handler of 'mddev->ro' in dm-raid, hence let's fix the problem the easy way for now to prevent dm-raid regression.
CVE-2024-26758: In the Linux kernel, the following vulnerability has been resolved: md: Don't ignore suspended array in md_check_recovery() mddev_suspend() never stop sync_thread, hence it doesn't make sense to ignore suspended array in md_check_recovery(), which might cause sync_thread can't be unregistered. After commit f52f5c71f3d4 ("md: fix stopping sync thread"), following hang can be triggered by test shell/integrity-caching.sh: 1) suspend the array: raid_postsuspend mddev_suspend 2) stop the array: raid_dtr md_stop __md_stop_writes stop_sync_thread set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_wakeup_thread_directly(mddev->sync_thread); wait_event(..., !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) 3) sync thread done: md_do_sync set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); 4) daemon thread can't unregister sync thread: md_check_recovery if (mddev->suspended) return; -> return directly md_read_sync_thread clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); -> MD_RECOVERY_RUNNING can't be cleared, hence step 2 hang; This problem is not just related to dm-raid, fix it by ignoring suspended array in md_check_recovery(). And follow up patches will improve dm-raid better to frozen sync thread during suspend.
CVE-2024-26759: In the Linux kernel, the following vulnerability has been resolved: mm/swap: fix race when skipping swapcache When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads swapin the same entry at the same time, they get different pages (A, B). Before one thread (T0) finishes the swapin and installs page (A) to the PTE, another thread (T1) could finish swapin of page (B), swap_free the entry, then swap out the possibly modified page reusing the same entry. It breaks the pte_same check in (T0) because PTE value is unchanged, causing ABA problem. Thread (T0) will install a stalled page (A) into the PTE and cause data corruption. One possible callstack is like this: CPU0 CPU1 ---- ---- do_swap_page() do_swap_page() with same entry <direct swapin path> <direct swapin path> <alloc page A> <alloc page B> swap_read_folio() <- read to page A swap_read_folio() <- read to page B <slow on later locks or interrupt> <finished swapin first> ... set_pte_at() swap_free() <- entry is free <write to page B, now page A stalled> <swap out page B to same swap entry> pte_same() <- Check pass, PTE seems unchanged, but page A is stalled! swap_free() <- page B content lost! set_pte_at() <- staled page A installed! And besides, for ZRAM, swap_free() allows the swap device to discard the entry content, so even if page (B) is not modified, if swap_read_folio() on CPU0 happens later than swap_free() on CPU1, it may also cause data loss. To fix this, reuse swapcache_prepare which will pin the swap entry using the cache flag, and allow only one thread to swap it in, also prevent any parallel code from putting the entry in the cache. Release the pin after PT unlocked. Racers just loop and wait since it's a rare and very short event. A schedule_timeout_uninterruptible(1) call is added to avoid repeated page faults wasting too much CPU, causing livelock or adding too much noise to perf statistics. A similar livelock issue was described in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") Reproducer: This race issue can be triggered easily using a well constructed reproducer and patched brd (with a delay in read path) [1]: With latest 6.8 mainline, race caused data loss can be observed easily: $ gcc -g -lpthread test-thread-swap-race.c && ./a.out Polulating 32MB of memory region... Keep swapping out... Starting round 0... Spawning 65536 workers... 32746 workers spawned, wait for done... Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss! Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss! Round 0 Failed, 15 data loss! This reproducer spawns multiple threads sharing the same memory region using a small swap device. Every two threads updates mapped pages one by one in opposite direction trying to create a race, with one dedicated thread keep swapping out the data out using madvise. The reproducer created a reproduce rate of about once every 5 minutes, so the race should be totally possible in production. After this patch, I ran the reproducer for over a few hundred rounds and no data loss observed. Performance overhead is minimal, microbenchmark swapin 10G from 32G zram: Before: 10934698 us After: 11157121 us Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag) [kasong@tencent.com: v4] Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com
CVE-2024-26765: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Disable IRQ before init_fn() for nonboot CPUs Disable IRQ before init_fn() for nonboot CPUs when hotplug, in order to silence such warnings (and also avoid potential errors due to unexpected interrupts): WARNING: CPU: 1 PID: 0 at kernel/rcu/tree.c:4503 rcu_cpu_starting+0x214/0x280 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.6.17+ #1198 pc 90000000048e3334 ra 90000000047bd56c tp 900000010039c000 sp 900000010039fdd0 a0 0000000000000001 a1 0000000000000006 a2 900000000802c040 a3 0000000000000000 a4 0000000000000001 a5 0000000000000004 a6 0000000000000000 a7 90000000048e3f4c t0 0000000000000001 t1 9000000005c70968 t2 0000000004000000 t3 000000000005e56e t4 00000000000002e4 t5 0000000000001000 t6 ffffffff80000000 t7 0000000000040000 t8 9000000007931638 u0 0000000000000006 s9 0000000000000004 s0 0000000000000001 s1 9000000006356ac0 s2 9000000007244000 s3 0000000000000001 s4 0000000000000001 s5 900000000636f000 s6 7fffffffffffffff s7 9000000002123940 s8 9000000001ca55f8 ra: 90000000047bd56c tlb_init+0x24c/0x528 ERA: 90000000048e3334 rcu_cpu_starting+0x214/0x280 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 00000000 (PPLV0 -PIE -PWE) EUEN: 00000000 (-FPE -SXE -ASXE -BTE) ECFG: 00071000 (LIE=12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.6.17+ #1198 Stack : 0000000000000000 9000000006375000 9000000005b61878 900000010039c000 900000010039fa30 0000000000000000 900000010039fa38 900000000619a140 9000000006456888 9000000006456880 900000010039f950 0000000000000001 0000000000000001 cb0cb028ec7e52e1 0000000002b90000 9000000100348700 0000000000000000 0000000000000001 ffffffff916d12f1 0000000000000003 0000000000040000 9000000007930370 0000000002b90000 0000000000000004 9000000006366000 900000000619a140 0000000000000000 0000000000000004 0000000000000000 0000000000000009 ffffffffffc681f2 9000000002123940 9000000001ca55f8 9000000006366000 90000000047a4828 00007ffff057ded8 00000000000000b0 0000000000000000 0000000000000000 0000000000071000 ... Call Trace: [<90000000047a4828>] show_stack+0x48/0x1a0 [<9000000005b61874>] dump_stack_lvl+0x84/0xcc [<90000000047f60ac>] __warn+0x8c/0x1e0 [<9000000005b0ab34>] report_bug+0x1b4/0x280 [<9000000005b63110>] do_bp+0x2d0/0x480 [<90000000047a2e20>] handle_bp+0x120/0x1c0 [<90000000048e3334>] rcu_cpu_starting+0x214/0x280 [<90000000047bd568>] tlb_init+0x248/0x528 [<90000000047a4c44>] per_cpu_trap_init+0x124/0x160 [<90000000047a19f4>] cpu_probe+0x494/0xa00 [<90000000047b551c>] start_secondary+0x3c/0xc0 [<9000000005b66134>] smpboot_entry+0x50/0x58
CVE-2024-26767: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fixed integer types and null check locations [why]: issues fixed: - comparison with wider integer type in loop condition which can cause infinite loops - pointer dereference before null check
CVE-2024-26768: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Change acpi_core_pic[NR_CPUS] to acpi_core_pic[MAX_CORE_PIC] With default config, the value of NR_CPUS is 64. When HW platform has more then 64 cpus, system will crash on these platforms. MAX_CORE_PIC is the maximum cpu number in MADT table (max physical number) which can exceed the supported maximum cpu number (NR_CPUS, max logical number), but kernel should not crash. Kernel should boot cpus with NR_CPUS, let the remainder cpus stay in BIOS. The potential crash reason is that the array acpi_core_pic[NR_CPUS] can be overflowed when parsing MADT table, and it is obvious that CORE_PIC should be corresponding to physical core rather than logical core, so it is better to define the array as acpi_core_pic[MAX_CORE_PIC]. With the patch, system can boot up 64 vcpus with qemu parameter -smp 128, otherwise system will crash with the following message. [ 0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000420000004259, era == 90000000037a5f0c, ra == 90000000037a46ec [ 0.000000] Oops[#1]: [ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.8.0-rc2+ #192 [ 0.000000] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022 [ 0.000000] pc 90000000037a5f0c ra 90000000037a46ec tp 9000000003c90000 sp 9000000003c93d60 [ 0.000000] a0 0000000000000019 a1 9000000003d93bc0 a2 0000000000000000 a3 9000000003c93bd8 [ 0.000000] a4 9000000003c93a74 a5 9000000083c93a67 a6 9000000003c938f0 a7 0000000000000005 [ 0.000000] t0 0000420000004201 t1 0000000000000000 t2 0000000000000001 t3 0000000000000001 [ 0.000000] t4 0000000000000003 t5 0000000000000000 t6 0000000000000030 t7 0000000000000063 [ 0.000000] t8 0000000000000014 u0 ffffffffffffffff s9 0000000000000000 s0 9000000003caee98 [ 0.000000] s1 90000000041b0480 s2 9000000003c93da0 s3 9000000003c93d98 s4 9000000003c93d90 [ 0.000000] s5 9000000003caa000 s6 000000000a7fd000 s7 000000000f556b60 s8 000000000e0a4330 [ 0.000000] ra: 90000000037a46ec platform_init+0x214/0x250 [ 0.000000] ERA: 90000000037a5f0c efi_runtime_init+0x30/0x94 [ 0.000000] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 0.000000] PRMD: 00000000 (PPLV0 -PIE -PWE) [ 0.000000] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 0.000000] ECFG: 00070800 (LIE=11 VS=7) [ 0.000000] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) [ 0.000000] BADV: 0000420000004259 [ 0.000000] PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) [ 0.000000] Modules linked in: [ 0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____)) [ 0.000000] Stack : 9000000003c93a14 9000000003800898 90000000041844f8 90000000037a46ec [ 0.000000] 000000000a7fd000 0000000008290000 0000000000000000 0000000000000000 [ 0.000000] 0000000000000000 0000000000000000 00000000019d8000 000000000f556b60 [ 0.000000] 000000000a7fd000 000000000f556b08 9000000003ca7700 9000000003800000 [ 0.000000] 9000000003c93e50 9000000003800898 9000000003800108 90000000037a484c [ 0.000000] 000000000e0a4330 000000000f556b60 000000000a7fd000 000000000f556b08 [ 0.000000] 9000000003ca7700 9000000004184000 0000000000200000 000000000e02b018 [ 0.000000] 000000000a7fd000 90000000037a0790 9000000003800108 0000000000000000 [ 0.000000] 0000000000000000 000000000e0a4330 000000000f556b60 000000000a7fd000 [ 0.000000] 000000000f556b08 000000000eaae298 000000000eaa5040 0000000000200000 [ 0.000000] ... [ 0.000000] Call Trace: [ 0.000000] [<90000000037a5f0c>] efi_runtime_init+0x30/0x94 [ 0.000000] [<90000000037a46ec>] platform_init+0x214/0x250 [ 0.000000] [<90000000037a484c>] setup_arch+0x124/0x45c [ 0.000000] [<90000000037a0790>] start_kernel+0x90/0x670 [ 0.000000] [<900000000378b0d8>] kernel_entry+0xd8/0xdc
CVE-2024-26769: In the Linux kernel, the following vulnerability has been resolved: nvmet-fc: avoid deadlock on delete association path When deleting an association the shutdown path is deadlocking because we try to flush the nvmet_wq nested. Avoid this by deadlock by deferring the put work into its own work item.
CVE-2024-26770: In the Linux kernel, the following vulnerability has been resolved: HID: nvidia-shield: Add missing null pointer checks to LED initialization devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity. [jkosina@suse.com: tweak changelog a bit]
CVE-2024-26771: In the Linux kernel, the following vulnerability has been resolved: dmaengine: ti: edma: Add some null pointer checks to the edma_probe devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity.
CVE-2024-26774: In the Linux kernel, the following vulnerability has been resolved: ext4: avoid dividing by 0 in mb_update_avg_fragment_size() when block bitmap corrupt Determine if bb_fragments is 0 instead of determining bb_free to eliminate the risk of dividing by zero when the block bitmap is corrupted.
CVE-2024-26775: In the Linux kernel, the following vulnerability has been resolved: aoe: avoid potential deadlock at set_capacity Move set_capacity() outside of the section procected by (&d->lock). To avoid possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- [1] lock(&bdev->bd_size_lock); local_irq_disable(); [2] lock(&d->lock); [3] lock(&bdev->bd_size_lock); <Interrupt> [4] lock(&d->lock); *** DEADLOCK *** Where [1](&bdev->bd_size_lock) hold by zram_add()->set_capacity(). [2]lock(&d->lock) hold by aoeblk_gdalloc(). And aoeblk_gdalloc() is trying to acquire [3](&bdev->bd_size_lock) at set_capacity() call. In this situation an attempt to acquire [4]lock(&d->lock) from aoecmd_cfg_rsp() will lead to deadlock. So the simplest solution is breaking lock dependency [2](&d->lock) -> [3](&bdev->bd_size_lock) by moving set_capacity() outside.
CVE-2024-26776: In the Linux kernel, the following vulnerability has been resolved: spi: hisi-sfc-v3xx: Return IRQ_NONE if no interrupts were detected Return IRQ_NONE from the interrupt handler when no interrupt was detected. Because an empty interrupt will cause a null pointer error: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 Call trace: complete+0x54/0x100 hisi_sfc_v3xx_isr+0x2c/0x40 [spi_hisi_sfc_v3xx] __handle_irq_event_percpu+0x64/0x1e0 handle_irq_event+0x7c/0x1cc
CVE-2024-26804: In the Linux kernel, the following vulnerability has been resolved: net: ip_tunnel: prevent perpetual headroom growth syzkaller triggered following kasan splat: BUG: KASAN: use-after-free in __skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170 Read of size 1 at addr ffff88812fb4000e by task syz-executor183/5191 [..] kasan_report+0xda/0x110 mm/kasan/report.c:588 __skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170 skb_flow_dissect_flow_keys include/linux/skbuff.h:1514 [inline] ___skb_get_hash net/core/flow_dissector.c:1791 [inline] __skb_get_hash+0xc7/0x540 net/core/flow_dissector.c:1856 skb_get_hash include/linux/skbuff.h:1556 [inline] ip_tunnel_xmit+0x1855/0x33c0 net/ipv4/ip_tunnel.c:748 ipip_tunnel_xmit+0x3cc/0x4e0 net/ipv4/ipip.c:308 __netdev_start_xmit include/linux/netdevice.h:4940 [inline] netdev_start_xmit include/linux/netdevice.h:4954 [inline] xmit_one net/core/dev.c:3548 [inline] dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564 __dev_queue_xmit+0x7c1/0x3d60 net/core/dev.c:4349 dev_queue_xmit include/linux/netdevice.h:3134 [inline] neigh_connected_output+0x42c/0x5d0 net/core/neighbour.c:1592 ... ip_finish_output2+0x833/0x2550 net/ipv4/ip_output.c:235 ip_finish_output+0x31/0x310 net/ipv4/ip_output.c:323 .. iptunnel_xmit+0x5b4/0x9b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1dbc/0x33c0 net/ipv4/ip_tunnel.c:831 ipgre_xmit+0x4a1/0x980 net/ipv4/ip_gre.c:665 __netdev_start_xmit include/linux/netdevice.h:4940 [inline] netdev_start_xmit include/linux/netdevice.h:4954 [inline] xmit_one net/core/dev.c:3548 [inline] dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564 ... The splat occurs because skb->data points past skb->head allocated area. This is because neigh layer does: __skb_pull(skb, skb_network_offset(skb)); ... but skb_network_offset() returns a negative offset and __skb_pull() arg is unsigned. IOW, we skb->data gets "adjusted" by a huge value. The negative value is returned because skb->head and skb->data distance is more than 64k and skb->network_header (u16) has wrapped around. The bug is in the ip_tunnel infrastructure, which can cause dev->needed_headroom to increment ad infinitum. The syzkaller reproducer consists of packets getting routed via a gre tunnel, and route of gre encapsulated packets pointing at another (ipip) tunnel. The ipip encapsulation finds gre0 as next output device. This results in the following pattern: 1). First packet is to be sent out via gre0. Route lookup found an output device, ipip0. 2). ip_tunnel_xmit for gre0 bumps gre0->needed_headroom based on the future output device, rt.dev->needed_headroom (ipip0). 3). ip output / start_xmit moves skb on to ipip0. which runs the same code path again (xmit recursion). 4). Routing step for the post-gre0-encap packet finds gre0 as output device to use for ipip0 encapsulated packet. tunl0->needed_headroom is then incremented based on the (already bumped) gre0 device headroom. This repeats for every future packet: gre0->needed_headroom gets inflated because previous packets' ipip0 step incremented rt->dev (gre0) headroom, and ipip0 incremented because gre0 needed_headroom was increased. For each subsequent packet, gre/ipip0->needed_headroom grows until post-expand-head reallocations result in a skb->head/data distance of more than 64k. Once that happens, skb->network_header (u16) wraps around when pskb_expand_head tries to make sure that skb_network_offset() is unchanged after the headroom expansion/reallocation. After this skb_network_offset(skb) returns a different (and negative) result post headroom expansion. The next trip to neigh layer (or anything else that would __skb_pull the network header) makes skb->data point to a memory location outside skb->head area. v2: Cap the needed_headroom update to an arbitarily chosen upperlimit to prevent perpetual increase instead of dropping the headroom increment completely.
CVE-2024-26807: In the Linux kernel, the following vulnerability has been resolved: Both cadence-quadspi ->runtime_suspend() and ->runtime_resume() implementations start with: struct cqspi_st *cqspi = dev_get_drvdata(dev); struct spi_controller *host = dev_get_drvdata(dev); This obviously cannot be correct, unless "struct cqspi_st" is the first member of " struct spi_controller", or the other way around, but it is not the case. "struct spi_controller" is allocated by devm_spi_alloc_host(), which allocates an extra amount of memory for private data, used to store "struct cqspi_st". The ->probe() function of the cadence-quadspi driver then sets the device drvdata to store the address of the "struct cqspi_st" structure. Therefore: struct cqspi_st *cqspi = dev_get_drvdata(dev); is correct, but: struct spi_controller *host = dev_get_drvdata(dev); is not, as it makes "host" point not to a "struct spi_controller" but to the same "struct cqspi_st" structure as above. This obviously leads to bad things (memory corruption, kernel crashes) directly during ->probe(), as ->probe() enables the device using PM runtime, leading the ->runtime_resume() hook being called, which in turns calls spi_controller_resume() with the wrong pointer. This has at least been reported [0] to cause a kernel crash, but the exact behavior will depend on the memory contents. [0] https://lore.kernel.org/all/20240226121803.5a7r5wkpbbowcxgx@dhruva/ This issue potentially affects all platforms that are currently using the cadence-quadspi driver.
CVE-2024-26810: In the Linux kernel, the following vulnerability has been resolved: vfio/pci: Lock external INTx masking ops Mask operations through config space changes to DisINTx may race INTx configuration changes via ioctl. Create wrappers that add locking for paths outside of the core interrupt code. In particular, irq_type is updated holding igate, therefore testing is_intx() requires holding igate. For example clearing DisINTx from config space can otherwise race changes of the interrupt configuration. This aligns interfaces which may trigger the INTx eventfd into two camps, one side serialized by igate and the other only enabled while INTx is configured. A subsequent patch introduces synchronization for the latter flows.
CVE-2024-26811: In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate payload size in ipc response If installing malicious ksmbd-tools, ksmbd.mountd can return invalid ipc response to ksmbd kernel server. ksmbd should validate payload size of ipc response from ksmbd.mountd to avoid memory overrun or slab-out-of-bounds. This patch validate 3 ipc response that has payload.
CVE-2024-26812: In the Linux kernel, the following vulnerability has been resolved: vfio/pci: Create persistent INTx handler A vulnerability exists where the eventfd for INTx signaling can be deconfigured, which unregisters the IRQ handler but still allows eventfds to be signaled with a NULL context through the SET_IRQS ioctl or through unmask irqfd if the device interrupt is pending. Ideally this could be solved with some additional locking; the igate mutex serializes the ioctl and config space accesses, and the interrupt handler is unregistered relative to the trigger, but the irqfd path runs asynchronous to those. The igate mutex cannot be acquired from the atomic context of the eventfd wake function. Disabling the irqfd relative to the eventfd registration is potentially incompatible with existing userspace. As a result, the solution implemented here moves configuration of the INTx interrupt handler to track the lifetime of the INTx context object and irq_type configuration, rather than registration of a particular trigger eventfd. Synchronization is added between the ioctl path and eventfd_signal() wrapper such that the eventfd trigger can be dynamically updated relative to in-flight interrupts or irqfd callbacks.
CVE-2024-26813: In the Linux kernel, the following vulnerability has been resolved: vfio/platform: Create persistent IRQ handlers The vfio-platform SET_IRQS ioctl currently allows loopback triggering of an interrupt before a signaling eventfd has been configured by the user, which thereby allows a NULL pointer dereference. Rather than register the IRQ relative to a valid trigger, register all IRQs in a disabled state in the device open path. This allows mask operations on the IRQ to nest within the overall enable state governed by a valid eventfd signal. This decouples @masked, protected by the @locked spinlock from @trigger, protected via the @igate mutex. In doing so, it's guaranteed that changes to @trigger cannot race the IRQ handlers because the IRQ handler is synchronously disabled before modifying the trigger, and loopback triggering of the IRQ via ioctl is safe due to serialization with trigger changes via igate. For compatibility, request_irq() failures are maintained to be local to the SET_IRQS ioctl rather than a fatal error in the open device path. This allows, for example, a userspace driver with polling mode support to continue to work regardless of moving the request_irq() call site. This necessarily blocks all SET_IRQS access to the failed index.
CVE-2024-26828: In the Linux kernel, the following vulnerability has been resolved: cifs: fix underflow in parse_server_interfaces() In this loop, we step through the buffer and after each item we check if the size_left is greater than the minimum size we need. However, the problem is that "bytes_left" is type ssize_t while sizeof() is type size_t. That means that because of type promotion, the comparison is done as an unsigned and if we have negative bytes left the loop continues instead of ending.
CVE-2024-26830: In the Linux kernel, the following vulnerability has been resolved: i40e: Do not allow untrusted VF to remove administratively set MAC Currently when PF administratively sets VF's MAC address and the VF is put down (VF tries to delete all MACs) then the MAC is removed from MAC filters and primary VF MAC is zeroed. Do not allow untrusted VF to remove primary MAC when it was set administratively by PF. Reproducer: 1) Create VF 2) Set VF interface up 3) Administratively set the VF's MAC 4) Put VF interface down [root@host ~]# echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs [root@host ~]# ip link set enp2s0f0v0 up [root@host ~]# ip link set enp2s0f0 vf 0 mac fe:6c:b5:da:c7:7d [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether fe:6c:b5:da:c7:7d brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off [root@host ~]# ip link set enp2s0f0v0 down [root@host ~]# ip link show enp2s0f0 23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000 link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff vf 0 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
CVE-2024-26841: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Update cpu_sibling_map when disabling nonboot CPUs Update cpu_sibling_map when disabling nonboot CPUs by defining & calling clear_cpu_sibling_map(), otherwise we get such errors on SMT systems: jump label: negative count! WARNING: CPU: 6 PID: 45 at kernel/jump_label.c:263 __static_key_slow_dec_cpuslocked+0xec/0x100 CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 pc 90000000004c302c ra 90000000004c302c tp 90000001005bc000 sp 90000001005bfd20 a0 000000000000001b a1 900000000224c278 a2 90000001005bfb58 a3 900000000224c280 a4 900000000224c278 a5 90000001005bfb50 a6 0000000000000001 a7 0000000000000001 t0 ce87a4763eb5234a t1 ce87a4763eb5234a t2 0000000000000000 t3 0000000000000000 t4 0000000000000006 t5 0000000000000000 t6 0000000000000064 t7 0000000000001964 t8 000000000009ebf6 u0 9000000001f2a068 s9 0000000000000000 s0 900000000246a2d8 s1 ffffffffffffffff s2 ffffffffffffffff s3 90000000021518c0 s4 0000000000000040 s5 9000000002151058 s6 9000000009828e40 s7 00000000000000b4 s8 0000000000000006 ra: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 ERA: 90000000004c302c __static_key_slow_dec_cpuslocked+0xec/0x100 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000000 (-FPE -SXE -ASXE -BTE) ECFG: 00071c1c (LIE=2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014d000 (Loongson-64bit, Loongson-3A6000-HV) CPU: 6 PID: 45 Comm: cpuhp/6 Not tainted 6.8.0-rc5+ #1340 Stack : 0000000000000000 900000000203f258 900000000179afc8 90000001005bc000 90000001005bf980 0000000000000000 90000001005bf988 9000000001fe0be0 900000000224c280 900000000224c278 90000001005bf8c0 0000000000000001 0000000000000001 ce87a4763eb5234a 0000000007f38000 90000001003f8cc0 0000000000000000 0000000000000006 0000000000000000 4c206e6f73676e6f 6f4c203a656d616e 000000000009ec99 0000000007f38000 0000000000000000 900000000214b000 9000000001fe0be0 0000000000000004 0000000000000000 0000000000000107 0000000000000009 ffffffffffafdabe 00000000000000b4 0000000000000006 90000000004c302c 9000000000224528 00005555939a0c7c 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c ... Call Trace: [<9000000000224528>] show_stack+0x48/0x1a0 [<900000000179afc8>] dump_stack_lvl+0x78/0xa0 [<9000000000263ed0>] __warn+0x90/0x1a0 [<90000000017419b8>] report_bug+0x1b8/0x280 [<900000000179c564>] do_bp+0x264/0x420 [<90000000004c302c>] __static_key_slow_dec_cpuslocked+0xec/0x100 [<90000000002b4d7c>] sched_cpu_deactivate+0x2fc/0x300 [<9000000000266498>] cpuhp_invoke_callback+0x178/0x8a0 [<9000000000267f70>] cpuhp_thread_fun+0xf0/0x240 [<90000000002a117c>] smpboot_thread_fn+0x1dc/0x2e0 [<900000000029a720>] kthread+0x140/0x160 [<9000000000222288>] ret_from_kernel_thread+0xc/0xa4
CVE-2024-26842: In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Fix shift issue in ufshcd_clear_cmd() When task_tag >= 32 (in MCQ mode) and sizeof(unsigned int) == 4, 1U << task_tag will out of bounds for a u32 mask. Fix this up to prevent SHIFT_ISSUE (bitwise shifts that are out of bounds for their data type). [name:debug_monitors&]Unexpected kernel BRK exception at EL1 [name:traps&]Internal error: BRK handler: 00000000f2005514 [#1] PREEMPT SMP [name:mediatek_cpufreq_hw&]cpufreq stop DVFS log done [name:mrdump&]Kernel Offset: 0x1ba5800000 from 0xffffffc008000000 [name:mrdump&]PHYS_OFFSET: 0x80000000 [name:mrdump&]pstate: 22400005 (nzCv daif +PAN -UAO) [name:mrdump&]pc : [0xffffffdbaf52bb2c] ufshcd_clear_cmd+0x280/0x288 [name:mrdump&]lr : [0xffffffdbaf52a774] ufshcd_wait_for_dev_cmd+0x3e4/0x82c [name:mrdump&]sp : ffffffc0081471b0 <snip> Workqueue: ufs_eh_wq_0 ufshcd_err_handler Call trace: dump_backtrace+0xf8/0x144 show_stack+0x18/0x24 dump_stack_lvl+0x78/0x9c dump_stack+0x18/0x44 mrdump_common_die+0x254/0x480 [mrdump] ipanic_die+0x20/0x30 [mrdump] notify_die+0x15c/0x204 die+0x10c/0x5f8 arm64_notify_die+0x74/0x13c do_debug_exception+0x164/0x26c el1_dbg+0x64/0x80 el1h_64_sync_handler+0x3c/0x90 el1h_64_sync+0x68/0x6c ufshcd_clear_cmd+0x280/0x288 ufshcd_wait_for_dev_cmd+0x3e4/0x82c ufshcd_exec_dev_cmd+0x5bc/0x9ac ufshcd_verify_dev_init+0x84/0x1c8 ufshcd_probe_hba+0x724/0x1ce0 ufshcd_host_reset_and_restore+0x260/0x574 ufshcd_reset_and_restore+0x138/0xbd0 ufshcd_err_handler+0x1218/0x2f28 process_one_work+0x5fc/0x1140 worker_thread+0x7d8/0xe20 kthread+0x25c/0x468 ret_from_fork+0x10/0x20
CVE-2024-26843: In the Linux kernel, the following vulnerability has been resolved: efi: runtime: Fix potential overflow of soft-reserved region size md_size will have been narrowed if we have >= 4GB worth of pages in a soft-reserved region.
CVE-2024-26844: In the Linux kernel, the following vulnerability has been resolved: block: Fix WARNING in _copy_from_iter Syzkaller reports a warning in _copy_from_iter because an iov_iter is supposedly used in the wrong direction. The reason is that syzcaller managed to generate a request with a transfer direction of SG_DXFER_TO_FROM_DEV. This instructs the kernel to copy user buffers into the kernel, read into the copied buffers and then copy the data back to user space. Thus the iovec is used in both directions. Detect this situation in the block layer and construct a new iterator with the correct direction for the copy-in.
CVE-2024-26846: In the Linux kernel, the following vulnerability has been resolved: nvme-fc: do not wait in vain when unloading module The module exit path has race between deleting all controllers and freeing 'left over IDs'. To prevent double free a synchronization between nvme_delete_ctrl and ida_destroy has been added by the initial commit. There is some logic around trying to prevent from hanging forever in wait_for_completion, though it does not handling all cases. E.g. blktests is able to reproduce the situation where the module unload hangs forever. If we completely rely on the cleanup code executed from the nvme_delete_ctrl path, all IDs will be freed eventually. This makes calling ida_destroy unnecessary. We only have to ensure that all nvme_delete_ctrl code has been executed before we leave nvme_fc_exit_module. This is done by flushing the nvme_delete_wq workqueue. While at it, remove the unused nvme_fc_wq workqueue too.
CVE-2024-26865: In the Linux kernel, the following vulnerability has been resolved: rds: tcp: Fix use-after-free of net in reqsk_timer_handler(). syzkaller reported a warning of netns tracker [0] followed by KASAN splat [1] and another ref tracker warning [1]. syzkaller could not find a repro, but in the log, the only suspicious sequence was as follows: 18:26:22 executing program 1: r0 = socket$inet6_mptcp(0xa, 0x1, 0x106) ... connect$inet6(r0, &(0x7f0000000080)={0xa, 0x4001, 0x0, @loopback}, 0x1c) (async) The notable thing here is 0x4001 in connect(), which is RDS_TCP_PORT. So, the scenario would be: 1. unshare(CLONE_NEWNET) creates a per netns tcp listener in rds_tcp_listen_init(). 2. syz-executor connect()s to it and creates a reqsk. 3. syz-executor exit()s immediately. 4. netns is dismantled. [0] 5. reqsk timer is fired, and UAF happens while freeing reqsk. [1] 6. listener is freed after RCU grace period. [2] Basically, reqsk assumes that the listener guarantees netns safety until all reqsk timers are expired by holding the listener's refcount. However, this was not the case for kernel sockets. Commit 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()") fixed this issue only for per-netns ehash. Let's apply the same fix for the global ehash. [0]: ref_tracker: net notrefcnt@0000000065449cc3 has 1/1 users at sk_alloc (./include/net/net_namespace.h:337 net/core/sock.c:2146) inet6_create (net/ipv6/af_inet6.c:192 net/ipv6/af_inet6.c:119) __sock_create (net/socket.c:1572) rds_tcp_listen_init (net/rds/tcp_listen.c:279) rds_tcp_init_net (net/rds/tcp.c:577) ops_init (net/core/net_namespace.c:137) setup_net (net/core/net_namespace.c:340) copy_net_ns (net/core/net_namespace.c:497) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3429) __x64_sys_unshare (kernel/fork.c:3496) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:129) ... WARNING: CPU: 0 PID: 27 at lib/ref_tracker.c:179 ref_tracker_dir_exit (lib/ref_tracker.c:179) [1]: BUG: KASAN: slab-use-after-free in inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) Read of size 8 at addr ffff88801b370400 by task swapper/0/0 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:107 (discriminator 1)) print_report (mm/kasan/report.c:378 mm/kasan/report.c:488) kasan_report (mm/kasan/report.c:603) inet_csk_reqsk_queue_drop (./include/net/inet_hashtables.h:180 net/ipv4/inet_connection_sock.c:952 net/ipv4/inet_connection_sock.c:966) reqsk_timer_handler (net/ipv4/inet_connection_sock.c:979 net/ipv4/inet_connection_sock.c:1092) call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701) __run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2038) run_timer_softirq (kernel/time/timer.c:2053) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:554) irq_exit_rcu (kernel/softirq.c:427 kernel/softirq.c:632 kernel/softirq.c:644) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1076 (discriminator 14)) </IRQ> Allocated by task 258 on cpu 0 at 83.612050s: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (mm/kasan/common.c:68) __kasan_slab_alloc (mm/kasan/common.c:343) kmem_cache_alloc (mm/slub.c:3813 mm/slub.c:3860 mm/slub.c:3867) copy_net_ns (./include/linux/slab.h:701 net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_name ---truncated---
CVE-2024-26866: In the Linux kernel, the following vulnerability has been resolved: spi: lpspi: Avoid potential use-after-free in probe() fsl_lpspi_probe() is allocating/disposing memory manually with spi_alloc_host()/spi_alloc_target(), but uses devm_spi_register_controller(). In case of error after the latter call the memory will be explicitly freed in the probe function by spi_controller_put() call, but used afterwards by "devm" management outside probe() (spi_unregister_controller() <- devm_spi_unregister() below). Unable to handle kernel NULL pointer dereference at virtual address 0000000000000070 ... Call trace: kernfs_find_ns kernfs_find_and_get_ns sysfs_remove_group sysfs_remove_groups device_remove_attrs device_del spi_unregister_controller devm_spi_unregister release_nodes devres_release_all really_probe driver_probe_device __device_attach_driver bus_for_each_drv __device_attach device_initial_probe bus_probe_device deferred_probe_work_func process_one_work worker_thread kthread ret_from_fork
CVE-2024-26869: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to truncate meta inode pages forcely Below race case can cause data corruption: Thread A GC thread - gc_data_segment - ra_data_block - locked meta_inode page - f2fs_inplace_write_data - invalidate_mapping_pages : fail to invalidate meta_inode page due to lock failure or dirty|writeback status - f2fs_submit_page_bio : write last dirty data to old blkaddr - move_data_block - load old data from meta_inode page - f2fs_submit_page_write : write old data to new blkaddr Because invalidate_mapping_pages() will skip invalidating page which has unclear status including locked, dirty, writeback and so on, so we need to use truncate_inode_pages_range() instead of invalidate_mapping_pages() to make sure meta_inode page will be dropped.
CVE-2024-26872: In the Linux kernel, the following vulnerability has been resolved: RDMA/srpt: Do not register event handler until srpt device is fully setup Upon rare occasions, KASAN reports a use-after-free Write in srpt_refresh_port(). This seems to be because an event handler is registered before the srpt device is fully setup and a race condition upon error may leave a partially setup event handler in place. Instead, only register the event handler after srpt device initialization is complete.
CVE-2024-26876: In the Linux kernel, the following vulnerability has been resolved: drm/bridge: adv7511: fix crash on irq during probe Moved IRQ registration down to end of adv7511_probe(). If an IRQ already is pending during adv7511_probe (before adv7511_cec_init) then cec_received_msg_ts could crash using uninitialized data: Unable to handle kernel read from unreadable memory at virtual address 00000000000003d5 Internal error: Oops: 96000004 [#1] PREEMPT_RT SMP Call trace: cec_received_msg_ts+0x48/0x990 [cec] adv7511_cec_irq_process+0x1cc/0x308 [adv7511] adv7511_irq_process+0xd8/0x120 [adv7511] adv7511_irq_handler+0x1c/0x30 [adv7511] irq_thread_fn+0x30/0xa0 irq_thread+0x14c/0x238 kthread+0x190/0x1a8
CVE-2024-26882: In the Linux kernel, the following vulnerability has been resolved: net: ip_tunnel: make sure to pull inner header in ip_tunnel_rcv() Apply the same fix than ones found in : 8d975c15c0cd ("ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv()") 1ca1ba465e55 ("geneve: make sure to pull inner header in geneve_rx()") We have to save skb->network_header in a temporary variable in order to be able to recompute the network_header pointer after a pskb_inet_may_pull() call. pskb_inet_may_pull() makes sure the needed headers are in skb->head. syzbot reported: BUG: KMSAN: uninit-value in __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] BUG: KMSAN: uninit-value in INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] BUG: KMSAN: uninit-value in IP_ECN_decapsulate include/net/inet_ecn.h:302 [inline] BUG: KMSAN: uninit-value in ip_tunnel_rcv+0xed9/0x2ed0 net/ipv4/ip_tunnel.c:409 __INET_ECN_decapsulate include/net/inet_ecn.h:253 [inline] INET_ECN_decapsulate include/net/inet_ecn.h:275 [inline] IP_ECN_decapsulate include/net/inet_ecn.h:302 [inline] ip_tunnel_rcv+0xed9/0x2ed0 net/ipv4/ip_tunnel.c:409 __ipgre_rcv+0x9bc/0xbc0 net/ipv4/ip_gre.c:389 ipgre_rcv net/ipv4/ip_gre.c:411 [inline] gre_rcv+0x423/0x19f0 net/ipv4/ip_gre.c:447 gre_rcv+0x2a4/0x390 net/ipv4/gre_demux.c:163 ip_protocol_deliver_rcu+0x264/0x1300 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x2b8/0x440 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:314 [inline] ip_local_deliver+0x21f/0x490 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:461 [inline] ip_rcv_finish net/ipv4/ip_input.c:449 [inline] NF_HOOK include/linux/netfilter.h:314 [inline] ip_rcv+0x46f/0x760 net/ipv4/ip_input.c:569 __netif_receive_skb_one_core net/core/dev.c:5534 [inline] __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5648 netif_receive_skb_internal net/core/dev.c:5734 [inline] netif_receive_skb+0x58/0x660 net/core/dev.c:5793 tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1556 tun_get_user+0x53b9/0x66e0 drivers/net/tun.c:2009 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2055 call_write_iter include/linux/fs.h:2087 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0xb6b/0x1520 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b Uninit was created at: __alloc_pages+0x9a6/0xe00 mm/page_alloc.c:4590 alloc_pages_mpol+0x62b/0x9d0 mm/mempolicy.c:2133 alloc_pages+0x1be/0x1e0 mm/mempolicy.c:2204 skb_page_frag_refill+0x2bf/0x7c0 net/core/sock.c:2909 tun_build_skb drivers/net/tun.c:1686 [inline] tun_get_user+0xe0a/0x66e0 drivers/net/tun.c:1826 tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2055 call_write_iter include/linux/fs.h:2087 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0xb6b/0x1520 fs/read_write.c:590 ksys_write+0x20f/0x4c0 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0x93/0xd0 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b
CVE-2024-26902: In the Linux kernel, the following vulnerability has been resolved: perf: RISCV: Fix panic on pmu overflow handler (1 << idx) of int is not desired when setting bits in unsigned long overflowed_ctrs, use BIT() instead. This panic happens when running 'perf record -e branches' on sophgo sg2042. [ 273.311852] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000098 [ 273.320851] Oops [#1] [ 273.323179] Modules linked in: [ 273.326303] CPU: 0 PID: 1475 Comm: perf Not tainted 6.6.0-rc3+ #9 [ 273.332521] Hardware name: Sophgo Mango (DT) [ 273.336878] epc : riscv_pmu_ctr_get_width_mask+0x8/0x62 [ 273.342291] ra : pmu_sbi_ovf_handler+0x2e0/0x34e [ 273.347091] epc : ffffffff80aecd98 ra : ffffffff80aee056 sp : fffffff6e36928b0 [ 273.354454] gp : ffffffff821f82d0 tp : ffffffd90c353200 t0 : 0000002ade4f9978 [ 273.361815] t1 : 0000000000504d55 t2 : ffffffff8016cd8c s0 : fffffff6e3692a70 [ 273.369180] s1 : 0000000000000020 a0 : 0000000000000000 a1 : 00001a8e81800000 [ 273.376540] a2 : 0000003c00070198 a3 : 0000003c00db75a4 a4 : 0000000000000015 [ 273.383901] a5 : ffffffd7ff8804b0 a6 : 0000000000000015 a7 : 000000000000002a [ 273.391327] s2 : 000000000000ffff s3 : 0000000000000000 s4 : ffffffd7ff8803b0 [ 273.398773] s5 : 0000000000504d55 s6 : ffffffd905069800 s7 : ffffffff821fe210 [ 273.406139] s8 : 000000007fffffff s9 : ffffffd7ff8803b0 s10: ffffffd903f29098 [ 273.413660] s11: 0000000080000000 t3 : 0000000000000003 t4 : ffffffff8017a0ca [ 273.421022] t5 : ffffffff8023cfc2 t6 : ffffffd9040780e8 [ 273.426437] status: 0000000200000100 badaddr: 0000000000000098 cause: 000000000000000d [ 273.434512] [<ffffffff80aecd98>] riscv_pmu_ctr_get_width_mask+0x8/0x62 [ 273.441169] [<ffffffff80076bd8>] handle_percpu_devid_irq+0x98/0x1ee [ 273.447562] [<ffffffff80071158>] generic_handle_domain_irq+0x28/0x36 [ 273.454151] [<ffffffff8047a99a>] riscv_intc_irq+0x36/0x4e [ 273.459659] [<ffffffff80c944de>] handle_riscv_irq+0x4a/0x74 [ 273.465442] [<ffffffff80c94c48>] do_irq+0x62/0x92 [ 273.470360] Code: 0420 60a2 6402 5529 0141 8082 0013 0000 0013 0000 (6d5c) b783 [ 273.477921] ---[ end trace 0000000000000000 ]--- [ 273.482630] Kernel panic - not syncing: Fatal exception in interrupt
CVE-2024-26905: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix data races when accessing the reserved amount of block reserves At space_info.c we have several places where we access the ->reserved field of a block reserve without taking the block reserve's spinlock first, which makes KCSAN warn about a data race since that field is always updated while holding the spinlock. The reports from KCSAN are like the following: [117.193526] BUG: KCSAN: data-race in btrfs_block_rsv_release [btrfs] / need_preemptive_reclaim [btrfs] [117.195148] read to 0x000000017f587190 of 8 bytes by task 6303 on cpu 3: [117.195172] need_preemptive_reclaim+0x222/0x2f0 [btrfs] [117.195992] __reserve_bytes+0xbb0/0xdc8 [btrfs] [117.196807] btrfs_reserve_metadata_bytes+0x4c/0x120 [btrfs] [117.197620] btrfs_block_rsv_add+0x78/0xa8 [btrfs] [117.198434] btrfs_delayed_update_inode+0x154/0x368 [btrfs] [117.199300] btrfs_update_inode+0x108/0x1c8 [btrfs] [117.200122] btrfs_dirty_inode+0xb4/0x140 [btrfs] [117.200937] btrfs_update_time+0x8c/0xb0 [btrfs] [117.201754] touch_atime+0x16c/0x1e0 [117.201789] filemap_read+0x674/0x728 [117.201823] btrfs_file_read_iter+0xf8/0x410 [btrfs] [117.202653] vfs_read+0x2b6/0x498 [117.203454] ksys_read+0xa2/0x150 [117.203473] __s390x_sys_read+0x68/0x88 [117.203495] do_syscall+0x1c6/0x210 [117.203517] __do_syscall+0xc8/0xf0 [117.203539] system_call+0x70/0x98 [117.203579] write to 0x000000017f587190 of 8 bytes by task 11 on cpu 0: [117.203604] btrfs_block_rsv_release+0x2e8/0x578 [btrfs] [117.204432] btrfs_delayed_inode_release_metadata+0x7c/0x1d0 [btrfs] [117.205259] __btrfs_update_delayed_inode+0x37c/0x5e0 [btrfs] [117.206093] btrfs_async_run_delayed_root+0x356/0x498 [btrfs] [117.206917] btrfs_work_helper+0x160/0x7a0 [btrfs] [117.207738] process_one_work+0x3b6/0x838 [117.207768] worker_thread+0x75e/0xb10 [117.207797] kthread+0x21a/0x230 [117.207830] __ret_from_fork+0x6c/0xb8 [117.207861] ret_from_fork+0xa/0x30 So add a helper to get the reserved amount of a block reserve while holding the lock. The value may be not be up to date anymore when used by need_preemptive_reclaim() and btrfs_preempt_reclaim_metadata_space(), but that's ok since the worst it can do is cause more reclaim work do be done sooner rather than later. Reading the field while holding the lock instead of using the data_race() annotation is used in order to prevent load tearing.
CVE-2024-26906: In the Linux kernel, the following vulnerability has been resolved: x86/mm: Disallow vsyscall page read for copy_from_kernel_nofault() When trying to use copy_from_kernel_nofault() to read vsyscall page through a bpf program, the following oops was reported: BUG: unable to handle page fault for address: ffffffffff600000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 3231067 P4D 3231067 PUD 3233067 PMD 3235067 PTE 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 20390 Comm: test_progs ...... 6.7.0+ #58 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ...... RIP: 0010:copy_from_kernel_nofault+0x6f/0x110 ...... Call Trace: <TASK> ? copy_from_kernel_nofault+0x6f/0x110 bpf_probe_read_kernel+0x1d/0x50 bpf_prog_2061065e56845f08_do_probe_read+0x51/0x8d trace_call_bpf+0xc5/0x1c0 perf_call_bpf_enter.isra.0+0x69/0xb0 perf_syscall_enter+0x13e/0x200 syscall_trace_enter+0x188/0x1c0 do_syscall_64+0xb5/0xe0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 </TASK> ...... ---[ end trace 0000000000000000 ]--- The oops is triggered when: 1) A bpf program uses bpf_probe_read_kernel() to read from the vsyscall page and invokes copy_from_kernel_nofault() which in turn calls __get_user_asm(). 2) Because the vsyscall page address is not readable from kernel space, a page fault exception is triggered accordingly. 3) handle_page_fault() considers the vsyscall page address as a user space address instead of a kernel space address. This results in the fix-up setup by bpf not being applied and a page_fault_oops() is invoked due to SMAP. Considering handle_page_fault() has already considered the vsyscall page address as a userspace address, fix the problem by disallowing vsyscall page read for copy_from_kernel_nofault().
CVE-2024-26907: In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix fortify source warning while accessing Eth segment ------------[ cut here ]------------ memcpy: detected field-spanning write (size 56) of single field "eseg->inline_hdr.start" at /var/lib/dkms/mlnx-ofed-kernel/5.8/build/drivers/infiniband/hw/mlx5/wr.c:131 (size 2) WARNING: CPU: 0 PID: 293779 at /var/lib/dkms/mlnx-ofed-kernel/5.8/build/drivers/infiniband/hw/mlx5/wr.c:131 mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] Modules linked in: 8021q garp mrp stp llc rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) ib_uverbs(OE) ib_core(OE) mlx5_core(OE) pci_hyperv_intf mlxdevm(OE) mlx_compat(OE) tls mlxfw(OE) psample nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink mst_pciconf(OE) knem(OE) vfio_pci vfio_pci_core vfio_iommu_type1 vfio iommufd irqbypass cuse nfsv3 nfs fscache netfs xfrm_user xfrm_algo ipmi_devintf ipmi_msghandler binfmt_misc crct10dif_pclmul crc32_pclmul polyval_clmulni polyval_generic ghash_clmulni_intel sha512_ssse3 snd_pcsp aesni_intel crypto_simd cryptd snd_pcm snd_timer joydev snd soundcore input_leds serio_raw evbug nfsd auth_rpcgss nfs_acl lockd grace sch_fq_codel sunrpc drm efi_pstore ip_tables x_tables autofs4 psmouse virtio_net net_failover failover floppy [last unloaded: mlx_compat(OE)] CPU: 0 PID: 293779 Comm: ssh Tainted: G OE 6.2.0-32-generic #32~22.04.1-Ubuntu Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] Code: 0c 01 00 a8 01 75 25 48 8b 75 a0 b9 02 00 00 00 48 c7 c2 10 5b fd c0 48 c7 c7 80 5b fd c0 c6 05 57 0c 03 00 01 e8 95 4d 93 da <0f> 0b 44 8b 4d b0 4c 8b 45 c8 48 8b 4d c0 e9 49 fb ff ff 41 0f b7 RSP: 0018:ffffb5b48478b570 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffb5b48478b628 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffb5b48478b5e8 R13: ffff963a3c609b5e R14: ffff9639c3fbd800 R15: ffffb5b480475a80 FS: 00007fc03b444c80(0000) GS:ffff963a3dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556f46bdf000 CR3: 0000000006ac6003 CR4: 00000000003706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? show_regs+0x72/0x90 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] ? __warn+0x8d/0x160 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] ? report_bug+0x1bb/0x1d0 ? handle_bug+0x46/0x90 ? exc_invalid_op+0x19/0x80 ? asm_exc_invalid_op+0x1b/0x20 ? mlx5_ib_post_send+0x191b/0x1a60 [mlx5_ib] mlx5_ib_post_send_nodrain+0xb/0x20 [mlx5_ib] ipoib_send+0x2ec/0x770 [ib_ipoib] ipoib_start_xmit+0x5a0/0x770 [ib_ipoib] dev_hard_start_xmit+0x8e/0x1e0 ? validate_xmit_skb_list+0x4d/0x80 sch_direct_xmit+0x116/0x3a0 __dev_xmit_skb+0x1fd/0x580 __dev_queue_xmit+0x284/0x6b0 ? _raw_spin_unlock_irq+0xe/0x50 ? __flush_work.isra.0+0x20d/0x370 ? push_pseudo_header+0x17/0x40 [ib_ipoib] neigh_connected_output+0xcd/0x110 ip_finish_output2+0x179/0x480 ? __smp_call_single_queue+0x61/0xa0 __ip_finish_output+0xc3/0x190 ip_finish_output+0x2e/0xf0 ip_output+0x78/0x110 ? __pfx_ip_finish_output+0x10/0x10 ip_local_out+0x64/0x70 __ip_queue_xmit+0x18a/0x460 ip_queue_xmit+0x15/0x30 __tcp_transmit_skb+0x914/0x9c0 tcp_write_xmit+0x334/0x8d0 tcp_push_one+0x3c/0x60 tcp_sendmsg_locked+0x2e1/0xac0 tcp_sendmsg+0x2d/0x50 inet_sendmsg+0x43/0x90 sock_sendmsg+0x68/0x80 sock_write_iter+0x93/0x100 vfs_write+0x326/0x3c0 ksys_write+0xbd/0xf0 ? do_syscall_64+0x69/0x90 __x64_sys_write+0x19/0x30 do_syscall_ ---truncated---
CVE-2024-26910: In the Linux kernel, the following vulnerability has been resolved: netfilter: ipset: fix performance regression in swap operation The patch "netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test", commit 28628fa9 fixes a race condition. But the synchronize_rcu() added to the swap function unnecessarily slows it down: it can safely be moved to destroy and use call_rcu() instead. Eric Dumazet pointed out that simply calling the destroy functions as rcu callback does not work: sets with timeout use garbage collectors which need cancelling at destroy which can wait. Therefore the destroy functions are split into two: cancelling garbage collectors safely at executing the command received by netlink and moving the remaining part only into the rcu callback.
CVE-2024-26913: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix dcn35 8k30 Underflow/Corruption Issue [why] odm calculation is missing for pipe split policy determination and cause Underflow/Corruption issue. [how] Add the odm calculation.
CVE-2024-26914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: fix incorrect mpc_combine array size [why] MAX_SURFACES is per stream, while MAX_PLANES is per asic. The mpc_combine is an array that records all the planes per asic. Therefore MAX_PLANES should be used as the array size. Using MAX_SURFACES causes array overflow when there are more than 3 planes. [how] Use the MAX_PLANES for the mpc_combine array size.
CVE-2024-26915: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Reset IH OVERFLOW_CLEAR bit Allows us to detect subsequent IH ring buffer overflows as well.
CVE-2024-26920: In the Linux kernel, the following vulnerability has been resolved: tracing/trigger: Fix to return error if failed to alloc snapshot Fix register_snapshot_trigger() to return error code if it failed to allocate a snapshot instead of 0 (success). Unless that, it will register snapshot trigger without an error.
CVE-2024-26921: In the Linux kernel, the following vulnerability has been resolved: inet: inet_defrag: prevent sk release while still in use ip_local_out() and other functions can pass skb->sk as function argument. If the skb is a fragment and reassembly happens before such function call returns, the sk must not be released. This affects skb fragments reassembled via netfilter or similar modules, e.g. openvswitch or ct_act.c, when run as part of tx pipeline. Eric Dumazet made an initial analysis of this bug. Quoting Eric: Calling ip_defrag() in output path is also implying skb_orphan(), which is buggy because output path relies on sk not disappearing. A relevant old patch about the issue was : 8282f27449bf ("inet: frag: Always orphan skbs inside ip_defrag()") [..] net/ipv4/ip_output.c depends on skb->sk being set, and probably to an inet socket, not an arbitrary one. If we orphan the packet in ipvlan, then downstream things like FQ packet scheduler will not work properly. We need to change ip_defrag() to only use skb_orphan() when really needed, ie whenever frag_list is going to be used. Eric suggested to stash sk in fragment queue and made an initial patch. However there is a problem with this: If skb is refragmented again right after, ip_do_fragment() will copy head->sk to the new fragments, and sets up destructor to sock_wfree. IOW, we have no choice but to fix up sk_wmem accouting to reflect the fully reassembled skb, else wmem will underflow. This change moves the orphan down into the core, to last possible moment. As ip_defrag_offset is aliased with sk_buff->sk member, we must move the offset into the FRAG_CB, else skb->sk gets clobbered. This allows to delay the orphaning long enough to learn if the skb has to be queued or if the skb is completing the reasm queue. In the former case, things work as before, skb is orphaned. This is safe because skb gets queued/stolen and won't continue past reasm engine. In the latter case, we will steal the skb->sk reference, reattach it to the head skb, and fix up wmem accouting when inet_frag inflates truesize.
CVE-2024-26928: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_debug_files_proc_show() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-26929: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix double free of fcport The server was crashing after LOGO because fcport was getting freed twice. -----------[ cut here ]----------- kernel BUG at mm/slub.c:371! invalid opcode: 0000 1 SMP PTI CPU: 35 PID: 4610 Comm: bash Kdump: loaded Tainted: G OE --------- - - 4.18.0-425.3.1.el8.x86_64 #1 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021 RIP: 0010:set_freepointer.part.57+0x0/0x10 RSP: 0018:ffffb07107027d90 EFLAGS: 00010246 RAX: ffff9cb7e3150000 RBX: ffff9cb7e332b9c0 RCX: ffff9cb7e3150400 RDX: 0000000000001f37 RSI: 0000000000000000 RDI: ffff9cb7c0005500 RBP: fffff693448c5400 R08: 0000000080000000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000132af0 R12: ffff9cb7c0005500 R13: ffff9cb7e3150000 R14: ffffffffc06990e0 R15: ffff9cb7ea85ea58 FS: 00007ff6b79c2740(0000) GS:ffff9cb8f7ec0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b426b7d700 CR3: 0000000169c18002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: kfree+0x238/0x250 qla2x00_els_dcmd_sp_free+0x20/0x230 [qla2xxx] ? qla24xx_els_dcmd_iocb+0x607/0x690 [qla2xxx] qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx] ? qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx] ? kernfs_fop_write+0x11e/0x1a0 Remove one of the free calls and add check for valid fcport. Also use function qla2x00_free_fcport() instead of kfree().
CVE-2024-26930: In the Linux kernel, the following vulnerability has been resolved: scsi: qla2xxx: Fix double free of the ha->vp_map pointer Coverity scan reported potential risk of double free of the pointer ha->vp_map. ha->vp_map was freed in qla2x00_mem_alloc(), and again freed in function qla2x00_mem_free(ha). Assign NULL to vp_map and kfree take care of NULL.
CVE-2024-26933: In the Linux kernel, the following vulnerability has been resolved: USB: core: Fix deadlock in port "disable" sysfs attribute The show and store callback routines for the "disable" sysfs attribute file in port.c acquire the device lock for the port's parent hub device. This can cause problems if another process has locked the hub to remove it or change its configuration: Removing the hub or changing its configuration requires the hub interface to be removed, which requires the port device to be removed, and device_del() waits until all outstanding sysfs attribute callbacks for the ports have returned. The lock can't be released until then. But the disable_show() or disable_store() routine can't return until after it has acquired the lock. The resulting deadlock can be avoided by calling sysfs_break_active_protection(). This will cause the sysfs core not to wait for the attribute's callback routine to return, allowing the removal to proceed. The disadvantage is that after making this call, there is no guarantee that the hub structure won't be deallocated at any moment. To prevent this, we have to acquire a reference to it first by calling hub_get().
CVE-2024-26936: In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate request buffer size in smb2_allocate_rsp_buf() The response buffer should be allocated in smb2_allocate_rsp_buf before validating request. But the fields in payload as well as smb2 header is used in smb2_allocate_rsp_buf(). This patch add simple buffer size validation to avoid potencial out-of-bounds in request buffer.
CVE-2024-26938: In the Linux kernel, the following vulnerability has been resolved: drm/i915/bios: Tolerate devdata==NULL in intel_bios_encoder_supports_dp_dual_mode() If we have no VBT, or the VBT didn't declare the encoder in question, we won't have the 'devdata' for the encoder. Instead of oopsing just bail early. We won't be able to tell whether the port is DP++ or not, but so be it. (cherry picked from commit 26410896206342c8a80d2b027923e9ee7d33b733)
CVE-2024-26944: In the Linux kernel, the following vulnerability has been resolved: btrfs: zoned: fix use-after-free in do_zone_finish() Shinichiro reported the following use-after-free triggered by the device replace operation in fstests btrfs/070. BTRFS info (device nullb1): scrub: finished on devid 1 with status: 0 ================================================================== BUG: KASAN: slab-use-after-free in do_zone_finish+0x91a/0xb90 [btrfs] Read of size 8 at addr ffff8881543c8060 by task btrfs-cleaner/3494007 CPU: 0 PID: 3494007 Comm: btrfs-cleaner Tainted: G W 6.8.0-rc5-kts #1 Hardware name: Supermicro Super Server/X11SPi-TF, BIOS 3.3 02/21/2020 Call Trace: <TASK> dump_stack_lvl+0x5b/0x90 print_report+0xcf/0x670 ? __virt_addr_valid+0x200/0x3e0 kasan_report+0xd8/0x110 ? do_zone_finish+0x91a/0xb90 [btrfs] ? do_zone_finish+0x91a/0xb90 [btrfs] do_zone_finish+0x91a/0xb90 [btrfs] btrfs_delete_unused_bgs+0x5e1/0x1750 [btrfs] ? __pfx_btrfs_delete_unused_bgs+0x10/0x10 [btrfs] ? btrfs_put_root+0x2d/0x220 [btrfs] ? btrfs_clean_one_deleted_snapshot+0x299/0x430 [btrfs] cleaner_kthread+0x21e/0x380 [btrfs] ? __pfx_cleaner_kthread+0x10/0x10 [btrfs] kthread+0x2e3/0x3c0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Allocated by task 3493983: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 btrfs_alloc_device+0xb3/0x4e0 [btrfs] device_list_add.constprop.0+0x993/0x1630 [btrfs] btrfs_scan_one_device+0x219/0x3d0 [btrfs] btrfs_control_ioctl+0x26e/0x310 [btrfs] __x64_sys_ioctl+0x134/0x1b0 do_syscall_64+0x99/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 Freed by task 3494056: kasan_save_stack+0x33/0x60 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3f/0x60 poison_slab_object+0x102/0x170 __kasan_slab_free+0x32/0x70 kfree+0x11b/0x320 btrfs_rm_dev_replace_free_srcdev+0xca/0x280 [btrfs] btrfs_dev_replace_finishing+0xd7e/0x14f0 [btrfs] btrfs_dev_replace_by_ioctl+0x1286/0x25a0 [btrfs] btrfs_ioctl+0xb27/0x57d0 [btrfs] __x64_sys_ioctl+0x134/0x1b0 do_syscall_64+0x99/0x190 entry_SYSCALL_64_after_hwframe+0x6e/0x76 The buggy address belongs to the object at ffff8881543c8000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 96 bytes inside of freed 1024-byte region [ffff8881543c8000, ffff8881543c8400) The buggy address belongs to the physical page: page:00000000fe2c1285 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1543c8 head:00000000fe2c1285 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x17ffffc0000840(slab|head|node=0|zone=2|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 0017ffffc0000840 ffff888100042dc0 ffffea0019e8f200 dead000000000002 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881543c7f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8881543c7f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff8881543c8000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8881543c8080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8881543c8100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb This UAF happens because we're accessing stale zone information of a already removed btrfs_device in do_zone_finish(). The sequence of events is as follows: btrfs_dev_replace_start btrfs_scrub_dev btrfs_dev_replace_finishing btrfs_dev_replace_update_device_in_mapping_tree <-- devices replaced btrfs_rm_dev_replace_free_srcdev btrfs_free_device <-- device freed cleaner_kthread btrfs_delete_unused_bgs btrfs_zone_finish do_zone_finish <-- refers the freed device The reason for this is that we're using a ---truncated---
CVE-2024-26945: In the Linux kernel, the following vulnerability has been resolved: crypto: iaa - Fix nr_cpus < nr_iaa case If nr_cpus < nr_iaa, the calculated cpus_per_iaa will be 0, which causes a divide-by-0 in rebalance_wq_table(). Make sure cpus_per_iaa is 1 in that case, and also in the nr_iaa == 0 case, even though cpus_per_iaa is never used if nr_iaa == 0, for paranoia.
CVE-2024-26948: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Add a dc_state NULL check in dc_state_release [How] Check wheather state is NULL before releasing it.
CVE-2024-26952: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix potencial out-of-bounds when buffer offset is invalid I found potencial out-of-bounds when buffer offset fields of a few requests is invalid. This patch set the minimum value of buffer offset field to ->Buffer offset to validate buffer length.
CVE-2024-26954: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix slab-out-of-bounds in smb_strndup_from_utf16() If ->NameOffset of smb2_create_req is smaller than Buffer offset of smb2_create_req, slab-out-of-bounds read can happen from smb2_open. This patch set the minimum value of the name offset to the buffer offset to validate name length of smb2_create_req().
CVE-2024-26958: In the Linux kernel, the following vulnerability has been resolved: nfs: fix UAF in direct writes In production we have been hitting the following warning consistently ------------[ cut here ]------------ refcount_t: underflow; use-after-free. WARNING: CPU: 17 PID: 1800359 at lib/refcount.c:28 refcount_warn_saturate+0x9c/0xe0 Workqueue: nfsiod nfs_direct_write_schedule_work [nfs] RIP: 0010:refcount_warn_saturate+0x9c/0xe0 PKRU: 55555554 Call Trace: <TASK> ? __warn+0x9f/0x130 ? refcount_warn_saturate+0x9c/0xe0 ? report_bug+0xcc/0x150 ? handle_bug+0x3d/0x70 ? exc_invalid_op+0x16/0x40 ? asm_exc_invalid_op+0x16/0x20 ? refcount_warn_saturate+0x9c/0xe0 nfs_direct_write_schedule_work+0x237/0x250 [nfs] process_one_work+0x12f/0x4a0 worker_thread+0x14e/0x3b0 ? ZSTD_getCParams_internal+0x220/0x220 kthread+0xdc/0x120 ? __btf_name_valid+0xa0/0xa0 ret_from_fork+0x1f/0x30 This is because we're completing the nfs_direct_request twice in a row. The source of this is when we have our commit requests to submit, we process them and send them off, and then in the completion path for the commit requests we have if (nfs_commit_end(cinfo.mds)) nfs_direct_write_complete(dreq); However since we're submitting asynchronous requests we sometimes have one that completes before we submit the next one, so we end up calling complete on the nfs_direct_request twice. The only other place we use nfs_generic_commit_list() is in __nfs_commit_inode, which wraps this call in a nfs_commit_begin(); nfs_commit_end(); Which is a common pattern for this style of completion handling, one that is also repeated in the direct code with get_dreq()/put_dreq() calls around where we process events as well as in the completion paths. Fix this by using the same pattern for the commit requests. Before with my 200 node rocksdb stress running this warning would pop every 10ish minutes. With my patch the stress test has been running for several hours without popping.
CVE-2024-26960: In the Linux kernel, the following vulnerability has been resolved: mm: swap: fix race between free_swap_and_cache() and swapoff() There was previously a theoretical window where swapoff() could run and teardown a swap_info_struct while a call to free_swap_and_cache() was running in another thread. This could cause, amongst other bad possibilities, swap_page_trans_huge_swapped() (called by free_swap_and_cache()) to access the freed memory for swap_map. This is a theoretical problem and I haven't been able to provoke it from a test case. But there has been agreement based on code review that this is possible (see link below). Fix it by using get_swap_device()/put_swap_device(), which will stall swapoff(). There was an extra check in _swap_info_get() to confirm that the swap entry was not free. This isn't present in get_swap_device() because it doesn't make sense in general due to the race between getting the reference and swapoff. So I've added an equivalent check directly in free_swap_and_cache(). Details of how to provoke one possible issue (thanks to David Hildenbrand for deriving this): --8<----- __swap_entry_free() might be the last user and result in "count == SWAP_HAS_CACHE". swapoff->try_to_unuse() will stop as soon as soon as si->inuse_pages==0. So the question is: could someone reclaim the folio and turn si->inuse_pages==0, before we completed swap_page_trans_huge_swapped(). Imagine the following: 2 MiB folio in the swapcache. Only 2 subpages are still references by swap entries. Process 1 still references subpage 0 via swap entry. Process 2 still references subpage 1 via swap entry. Process 1 quits. Calls free_swap_and_cache(). -> count == SWAP_HAS_CACHE [then, preempted in the hypervisor etc.] Process 2 quits. Calls free_swap_and_cache(). -> count == SWAP_HAS_CACHE Process 2 goes ahead, passes swap_page_trans_huge_swapped(), and calls __try_to_reclaim_swap(). __try_to_reclaim_swap()->folio_free_swap()->delete_from_swap_cache()-> put_swap_folio()->free_swap_slot()->swapcache_free_entries()-> swap_entry_free()->swap_range_free()-> ... WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); What stops swapoff to succeed after process 2 reclaimed the swap cache but before process1 finished its call to swap_page_trans_huge_swapped()? --8<-----
CVE-2024-26961: In the Linux kernel, the following vulnerability has been resolved: mac802154: fix llsec key resources release in mac802154_llsec_key_del mac802154_llsec_key_del() can free resources of a key directly without following the RCU rules for waiting before the end of a grace period. This may lead to use-after-free in case llsec_lookup_key() is traversing the list of keys in parallel with a key deletion: refcount_t: addition on 0; use-after-free. WARNING: CPU: 4 PID: 16000 at lib/refcount.c:25 refcount_warn_saturate+0x162/0x2a0 Modules linked in: CPU: 4 PID: 16000 Comm: wpan-ping Not tainted 6.7.0 #19 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:refcount_warn_saturate+0x162/0x2a0 Call Trace: <TASK> llsec_lookup_key.isra.0+0x890/0x9e0 mac802154_llsec_encrypt+0x30c/0x9c0 ieee802154_subif_start_xmit+0x24/0x1e0 dev_hard_start_xmit+0x13e/0x690 sch_direct_xmit+0x2ae/0xbc0 __dev_queue_xmit+0x11dd/0x3c20 dgram_sendmsg+0x90b/0xd60 __sys_sendto+0x466/0x4c0 __x64_sys_sendto+0xe0/0x1c0 do_syscall_64+0x45/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 Also, ieee802154_llsec_key_entry structures are not freed by mac802154_llsec_key_del(): unreferenced object 0xffff8880613b6980 (size 64): comm "iwpan", pid 2176, jiffies 4294761134 (age 60.475s) hex dump (first 32 bytes): 78 0d 8f 18 80 88 ff ff 22 01 00 00 00 00 ad de x......."....... 00 00 00 00 00 00 00 00 03 00 cd ab 00 00 00 00 ................ backtrace: [<ffffffff81dcfa62>] __kmem_cache_alloc_node+0x1e2/0x2d0 [<ffffffff81c43865>] kmalloc_trace+0x25/0xc0 [<ffffffff88968b09>] mac802154_llsec_key_add+0xac9/0xcf0 [<ffffffff8896e41a>] ieee802154_add_llsec_key+0x5a/0x80 [<ffffffff8892adc6>] nl802154_add_llsec_key+0x426/0x5b0 [<ffffffff86ff293e>] genl_family_rcv_msg_doit+0x1fe/0x2f0 [<ffffffff86ff46d1>] genl_rcv_msg+0x531/0x7d0 [<ffffffff86fee7a9>] netlink_rcv_skb+0x169/0x440 [<ffffffff86ff1d88>] genl_rcv+0x28/0x40 [<ffffffff86fec15c>] netlink_unicast+0x53c/0x820 [<ffffffff86fecd8b>] netlink_sendmsg+0x93b/0xe60 [<ffffffff86b91b35>] ____sys_sendmsg+0xac5/0xca0 [<ffffffff86b9c3dd>] ___sys_sendmsg+0x11d/0x1c0 [<ffffffff86b9c65a>] __sys_sendmsg+0xfa/0x1d0 [<ffffffff88eadbf5>] do_syscall_64+0x45/0xf0 [<ffffffff890000ea>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 Handle the proper resource release in the RCU callback function mac802154_llsec_key_del_rcu(). Note that if llsec_lookup_key() finds a key, it gets a refcount via llsec_key_get() and locally copies key id from key_entry (which is a list element). So it's safe to call llsec_key_put() and free the list entry after the RCU grace period elapses. Found by Linux Verification Center (linuxtesting.org).
CVE-2024-26962: In the Linux kernel, the following vulnerability has been resolved: dm-raid456, md/raid456: fix a deadlock for dm-raid456 while io concurrent with reshape For raid456, if reshape is still in progress, then IO across reshape position will wait for reshape to make progress. However, for dm-raid, in following cases reshape will never make progress hence IO will hang: 1) the array is read-only; 2) MD_RECOVERY_WAIT is set; 3) MD_RECOVERY_FROZEN is set; After commit c467e97f079f ("md/raid6: use valid sector values to determine if an I/O should wait on the reshape") fix the problem that IO across reshape position doesn't wait for reshape, the dm-raid test shell/lvconvert-raid-reshape.sh start to hang: [root@fedora ~]# cat /proc/979/stack [<0>] wait_woken+0x7d/0x90 [<0>] raid5_make_request+0x929/0x1d70 [raid456] [<0>] md_handle_request+0xc2/0x3b0 [md_mod] [<0>] raid_map+0x2c/0x50 [dm_raid] [<0>] __map_bio+0x251/0x380 [dm_mod] [<0>] dm_submit_bio+0x1f0/0x760 [dm_mod] [<0>] __submit_bio+0xc2/0x1c0 [<0>] submit_bio_noacct_nocheck+0x17f/0x450 [<0>] submit_bio_noacct+0x2bc/0x780 [<0>] submit_bio+0x70/0xc0 [<0>] mpage_readahead+0x169/0x1f0 [<0>] blkdev_readahead+0x18/0x30 [<0>] read_pages+0x7c/0x3b0 [<0>] page_cache_ra_unbounded+0x1ab/0x280 [<0>] force_page_cache_ra+0x9e/0x130 [<0>] page_cache_sync_ra+0x3b/0x110 [<0>] filemap_get_pages+0x143/0xa30 [<0>] filemap_read+0xdc/0x4b0 [<0>] blkdev_read_iter+0x75/0x200 [<0>] vfs_read+0x272/0x460 [<0>] ksys_read+0x7a/0x170 [<0>] __x64_sys_read+0x1c/0x30 [<0>] do_syscall_64+0xc6/0x230 [<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74 This is because reshape can't make progress. For md/raid, the problem doesn't exist because register new sync_thread doesn't rely on the IO to be done any more: 1) If array is read-only, it can switch to read-write by ioctl/sysfs; 2) md/raid never set MD_RECOVERY_WAIT; 3) If MD_RECOVERY_FROZEN is set, mddev_suspend() doesn't hold 'reconfig_mutex', hence it can be cleared and reshape can continue by sysfs api 'sync_action'. However, I'm not sure yet how to avoid the problem in dm-raid yet. This patch on the one hand make sure raid_message() can't change sync_thread() through raid_message() after presuspend(), on the other hand detect the above 3 cases before wait for IO do be done in dm_suspend(), and let dm-raid requeue those IO.
CVE-2024-26980: In the Linux kernel, the following vulnerability has been resolved: ksmbd: fix slab-out-of-bounds in smb2_allocate_rsp_buf If ->ProtocolId is SMB2_TRANSFORM_PROTO_NUM, smb2 request size validation could be skipped. if request size is smaller than sizeof(struct smb2_query_info_req), slab-out-of-bounds read can happen in smb2_allocate_rsp_buf(). This patch allocate response buffer after decrypting transform request. smb3_decrypt_req() will validate transform request size and avoid slab-out-of-bound in smb2_allocate_rsp_buf().
CVE-2024-26982: In the Linux kernel, the following vulnerability has been resolved: Squashfs: check the inode number is not the invalid value of zero Syskiller has produced an out of bounds access in fill_meta_index(). That out of bounds access is ultimately caused because the inode has an inode number with the invalid value of zero, which was not checked. The reason this causes the out of bounds access is due to following sequence of events: 1. Fill_meta_index() is called to allocate (via empty_meta_index()) and fill a metadata index. It however suffers a data read error and aborts, invalidating the newly returned empty metadata index. It does this by setting the inode number of the index to zero, which means unused (zero is not a valid inode number). 2. When fill_meta_index() is subsequently called again on another read operation, locate_meta_index() returns the previous index because it matches the inode number of 0. Because this index has been returned it is expected to have been filled, and because it hasn't been, an out of bounds access is performed. This patch adds a sanity check which checks that the inode number is not zero when the inode is created and returns -EINVAL if it is. [phillip@squashfs.org.uk: whitespace fix] Link: https://lkml.kernel.org/r/20240409204723.446925-1-phillip@squashfs.org.uk
CVE-2024-26996: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_ncm: Fix UAF ncm object at re-bind after usb ep transport error When ncm function is working and then stop usb0 interface for link down, eth_stop() is called. At this piont, accidentally if usb transport error should happen in usb_ep_enable(), 'in_ep' and/or 'out_ep' may not be enabled. After that, ncm_disable() is called to disable for ncm unbind but gether_disconnect() is never called since 'in_ep' is not enabled. As the result, ncm object is released in ncm unbind but 'dev->port_usb' associated to 'ncm->port' is not NULL. And when ncm bind again to recover netdev, ncm object is reallocated but usb0 interface is already associated to previous released ncm object. Therefore, once usb0 interface is up and eth_start_xmit() is called, released ncm object is dereferrenced and it might cause use-after-free memory. [function unlink via configfs] usb0: eth_stop dev->port_usb=ffffff9b179c3200 --> error happens in usb_ep_enable(). NCM: ncm_disable: ncm=ffffff9b179c3200 --> no gether_disconnect() since ncm->port.in_ep->enabled is false. NCM: ncm_unbind: ncm unbind ncm=ffffff9b179c3200 NCM: ncm_free: ncm free ncm=ffffff9b179c3200 <-- released ncm [function link via configfs] NCM: ncm_alloc: ncm alloc ncm=ffffff9ac4f8a000 NCM: ncm_bind: ncm bind ncm=ffffff9ac4f8a000 NCM: ncm_set_alt: ncm=ffffff9ac4f8a000 alt=0 usb0: eth_open dev->port_usb=ffffff9b179c3200 <-- previous released ncm usb0: eth_start dev->port_usb=ffffff9b179c3200 <-- eth_start_xmit() --> dev->wrap() Unable to handle kernel paging request at virtual address dead00000000014f This patch addresses the issue by checking if 'ncm->netdev' is not NULL at ncm_disable() to call gether_disconnect() to deassociate 'dev->port_usb'. It's more reasonable to check 'ncm->netdev' to call gether_connect/disconnect rather than check 'ncm->port.in_ep->enabled' since it might not be enabled but the gether connection might be established.
CVE-2024-27004: In the Linux kernel, the following vulnerability has been resolved: clk: Get runtime PM before walking tree during disable_unused Doug reported [1] the following hung task: INFO: task swapper/0:1 blocked for more than 122 seconds. Not tainted 5.15.149-21875-gf795ebc40eb8 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:swapper/0 state:D stack: 0 pid: 1 ppid: 0 flags:0x00000008 Call trace: __switch_to+0xf4/0x1f4 __schedule+0x418/0xb80 schedule+0x5c/0x10c rpm_resume+0xe0/0x52c rpm_resume+0x178/0x52c __pm_runtime_resume+0x58/0x98 clk_pm_runtime_get+0x30/0xb0 clk_disable_unused_subtree+0x58/0x208 clk_disable_unused_subtree+0x38/0x208 clk_disable_unused_subtree+0x38/0x208 clk_disable_unused_subtree+0x38/0x208 clk_disable_unused_subtree+0x38/0x208 clk_disable_unused+0x4c/0xe4 do_one_initcall+0xcc/0x2d8 do_initcall_level+0xa4/0x148 do_initcalls+0x5c/0x9c do_basic_setup+0x24/0x30 kernel_init_freeable+0xec/0x164 kernel_init+0x28/0x120 ret_from_fork+0x10/0x20 INFO: task kworker/u16:0:9 blocked for more than 122 seconds. Not tainted 5.15.149-21875-gf795ebc40eb8 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u16:0 state:D stack: 0 pid: 9 ppid: 2 flags:0x00000008 Workqueue: events_unbound deferred_probe_work_func Call trace: __switch_to+0xf4/0x1f4 __schedule+0x418/0xb80 schedule+0x5c/0x10c schedule_preempt_disabled+0x2c/0x48 __mutex_lock+0x238/0x488 __mutex_lock_slowpath+0x1c/0x28 mutex_lock+0x50/0x74 clk_prepare_lock+0x7c/0x9c clk_core_prepare_lock+0x20/0x44 clk_prepare+0x24/0x30 clk_bulk_prepare+0x40/0xb0 mdss_runtime_resume+0x54/0x1c8 pm_generic_runtime_resume+0x30/0x44 __genpd_runtime_resume+0x68/0x7c genpd_runtime_resume+0x108/0x1f4 __rpm_callback+0x84/0x144 rpm_callback+0x30/0x88 rpm_resume+0x1f4/0x52c rpm_resume+0x178/0x52c __pm_runtime_resume+0x58/0x98 __device_attach+0xe0/0x170 device_initial_probe+0x1c/0x28 bus_probe_device+0x3c/0x9c device_add+0x644/0x814 mipi_dsi_device_register_full+0xe4/0x170 devm_mipi_dsi_device_register_full+0x28/0x70 ti_sn_bridge_probe+0x1dc/0x2c0 auxiliary_bus_probe+0x4c/0x94 really_probe+0xcc/0x2c8 __driver_probe_device+0xa8/0x130 driver_probe_device+0x48/0x110 __device_attach_driver+0xa4/0xcc bus_for_each_drv+0x8c/0xd8 __device_attach+0xf8/0x170 device_initial_probe+0x1c/0x28 bus_probe_device+0x3c/0x9c deferred_probe_work_func+0x9c/0xd8 process_one_work+0x148/0x518 worker_thread+0x138/0x350 kthread+0x138/0x1e0 ret_from_fork+0x10/0x20 The first thread is walking the clk tree and calling clk_pm_runtime_get() to power on devices required to read the clk hardware via struct clk_ops::is_enabled(). This thread holds the clk prepare_lock, and is trying to runtime PM resume a device, when it finds that the device is in the process of resuming so the thread schedule()s away waiting for the device to finish resuming before continuing. The second thread is runtime PM resuming the same device, but the runtime resume callback is calling clk_prepare(), trying to grab the prepare_lock waiting on the first thread. This is a classic ABBA deadlock. To properly fix the deadlock, we must never runtime PM resume or suspend a device with the clk prepare_lock held. Actually doing that is near impossible today because the global prepare_lock would have to be dropped in the middle of the tree, the device runtime PM resumed/suspended, and then the prepare_lock grabbed again to ensure consistency of the clk tree topology. If anything changes with the clk tree in the meantime, we've lost and will need to start the operation all over again. Luckily, most of the time we're simply incrementing or decrementing the runtime PM count on an active device, so we don't have the chance to schedule away with the prepare_lock held. Let's fix this immediate problem that can be ---truncated---
CVE-2024-27010: In the Linux kernel, the following vulnerability has been resolved: net/sched: Fix mirred deadlock on device recursion When the mirred action is used on a classful egress qdisc and a packet is mirrored or redirected to self we hit a qdisc lock deadlock. See trace below. [..... other info removed for brevity....] [ 82.890906] [ 82.890906] ============================================ [ 82.890906] WARNING: possible recursive locking detected [ 82.890906] 6.8.0-05205-g77fadd89fe2d-dirty #213 Tainted: G W [ 82.890906] -------------------------------------------- [ 82.890906] ping/418 is trying to acquire lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] but task is already holding lock: [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at: __dev_queue_xmit+0x1778/0x3550 [ 82.890906] [ 82.890906] other info that might help us debug this: [ 82.890906] Possible unsafe locking scenario: [ 82.890906] [ 82.890906] CPU0 [ 82.890906] ---- [ 82.890906] lock(&sch->q.lock); [ 82.890906] lock(&sch->q.lock); [ 82.890906] [ 82.890906] *** DEADLOCK *** [ 82.890906] [..... other info removed for brevity....] Example setup (eth0->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 Another example(eth0->eth1->eth0) to recreate tc qdisc add dev eth0 root handle 1: htb default 30 tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth1 tc qdisc add dev eth1 root handle 1: htb default 30 tc filter add dev eth1 handle 1: protocol ip prio 2 matchall \ action mirred egress redirect dev eth0 We fix this by adding an owner field (CPU id) to struct Qdisc set after root qdisc is entered. When the softirq enters it a second time, if the qdisc owner is the same CPU, the packet is dropped to break the loop.
CVE-2024-27011: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: fix memleak in map from abort path The delete set command does not rely on the transaction object for element removal, therefore, a combination of delete element + delete set from the abort path could result in restoring twice the refcount of the mapping. Check for inactive element in the next generation for the delete element command in the abort path, skip restoring state if next generation bit has been already cleared. This is similar to the activate logic using the set walk iterator. [ 6170.286929] ------------[ cut here ]------------ [ 6170.286939] WARNING: CPU: 6 PID: 790302 at net/netfilter/nf_tables_api.c:2086 nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287071] Modules linked in: [...] [ 6170.287633] CPU: 6 PID: 790302 Comm: kworker/6:2 Not tainted 6.9.0-rc3+ #365 [ 6170.287768] RIP: 0010:nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.287886] Code: df 48 8d 7d 58 e8 69 2e 3b df 48 8b 7d 58 e8 80 1b 37 df 48 8d 7d 68 e8 57 2e 3b df 48 8b 7d 68 e8 6e 1b 37 df 48 89 ef eb c4 <0f> 0b 48 83 c4 08 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 0f [ 6170.287895] RSP: 0018:ffff888134b8fd08 EFLAGS: 00010202 [ 6170.287904] RAX: 0000000000000001 RBX: ffff888125bffb28 RCX: dffffc0000000000 [ 6170.287912] RDX: 0000000000000003 RSI: ffffffffa20298ab RDI: ffff88811ebe4750 [ 6170.287919] RBP: ffff88811ebe4700 R08: ffff88838e812650 R09: fffffbfff0623a55 [ 6170.287926] R10: ffffffff8311d2af R11: 0000000000000001 R12: ffff888125bffb10 [ 6170.287933] R13: ffff888125bffb10 R14: dead000000000122 R15: dead000000000100 [ 6170.287940] FS: 0000000000000000(0000) GS:ffff888390b00000(0000) knlGS:0000000000000000 [ 6170.287948] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6170.287955] CR2: 00007fd31fc00710 CR3: 0000000133f60004 CR4: 00000000001706f0 [ 6170.287962] Call Trace: [ 6170.287967] <TASK> [ 6170.287973] ? __warn+0x9f/0x1a0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.287986] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288092] ? report_bug+0x1b1/0x1e0 [ 6170.288104] ? handle_bug+0x3c/0x70 [ 6170.288112] ? exc_invalid_op+0x17/0x40 [ 6170.288120] ? asm_exc_invalid_op+0x1a/0x20 [ 6170.288132] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288243] ? nf_tables_chain_destroy+0x1f7/0x220 [nf_tables] [ 6170.288366] ? nf_tables_chain_destroy+0x2b/0x220 [nf_tables] [ 6170.288483] nf_tables_trans_destroy_work+0x588/0x590 [nf_tables]
CVE-2024-27014: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Prevent deadlock while disabling aRFS When disabling aRFS under the `priv->state_lock`, any scheduled aRFS works are canceled using the `cancel_work_sync` function, which waits for the work to end if it has already started. However, while waiting for the work handler, the handler will try to acquire the `state_lock` which is already acquired. The worker acquires the lock to delete the rules if the state is down, which is not the worker's responsibility since disabling aRFS deletes the rules. Add an aRFS state variable, which indicates whether the aRFS is enabled and prevent adding rules when the aRFS is disabled. Kernel log: ====================================================== WARNING: possible circular locking dependency detected 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Tainted: G I ------------------------------------------------------ ethtool/386089 is trying to acquire lock: ffff88810f21ce68 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}, at: __flush_work+0x74/0x4e0 but task is already holding lock: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&priv->state_lock){+.+.}-{3:3}: __mutex_lock+0x80/0xc90 arfs_handle_work+0x4b/0x3b0 [mlx5_core] process_one_work+0x1dc/0x4a0 worker_thread+0x1bf/0x3c0 kthread+0xd7/0x100 ret_from_fork+0x2d/0x50 ret_from_fork_asm+0x11/0x20 -> #0 ((work_completion)(&rule->arfs_work)){+.+.}-{0:0}: __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 __flush_work+0x7a/0x4e0 __cancel_work_timer+0x131/0x1c0 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x1a1/0x270 netlink_sendmsg+0x214/0x460 __sock_sendmsg+0x38/0x60 __sys_sendto+0x113/0x170 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x40/0xe0 entry_SYSCALL_64_after_hwframe+0x46/0x4e other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work)); lock(&priv->state_lock); lock((work_completion)(&rule->arfs_work)); *** DEADLOCK *** 3 locks held by ethtool/386089: #0: ffffffff82ea7210 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 #1: ffffffff82e94c88 (rtnl_mutex){+.+.}-{3:3}, at: ethnl_default_set_doit+0xd3/0x240 #2: ffff8884a1808cc0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_ethtool_set_channels+0x53/0x200 [mlx5_core] stack backtrace: CPU: 15 PID: 386089 Comm: ethtool Tainted: G I 6.7.0-rc4_net_next_mlx5_5483eb2 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x60/0xa0 check_noncircular+0x144/0x160 __lock_acquire+0x17b4/0x2c80 lock_acquire+0xd0/0x2b0 ? __flush_work+0x74/0x4e0 ? save_trace+0x3e/0x360 ? __flush_work+0x74/0x4e0 __flush_work+0x7a/0x4e0 ? __flush_work+0x74/0x4e0 ? __lock_acquire+0xa78/0x2c80 ? lock_acquire+0xd0/0x2b0 ? mark_held_locks+0x49/0x70 __cancel_work_timer+0x131/0x1c0 ? mark_held_locks+0x49/0x70 arfs_del_rules+0x143/0x1e0 [mlx5_core] mlx5e_arfs_disable+0x1b/0x30 [mlx5_core] mlx5e_ethtool_set_channels+0xcb/0x200 [mlx5_core] ethnl_set_channels+0x28f/0x3b0 ethnl_default_set_doit+0xec/0x240 genl_family_rcv_msg_doit+0xd0/0x120 genl_rcv_msg+0x188/0x2c0 ? ethn ---truncated---
CVE-2024-27019: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: Fix potential data-race in __nft_obj_type_get() nft_unregister_obj() can concurrent with __nft_obj_type_get(), and there is not any protection when iterate over nf_tables_objects list in __nft_obj_type_get(). Therefore, there is potential data-race of nf_tables_objects list entry. Use list_for_each_entry_rcu() to iterate over nf_tables_objects list in __nft_obj_type_get(), and use rcu_read_lock() in the caller nft_obj_type_get() to protect the entire type query process.
CVE-2024-27025: In the Linux kernel, the following vulnerability has been resolved: nbd: null check for nla_nest_start nla_nest_start() may fail and return NULL. Insert a check and set errno based on other call sites within the same source code.
CVE-2024-27032: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to avoid potential panic during recovery During recovery, if FAULT_BLOCK is on, it is possible that f2fs_reserve_new_block() will return -ENOSPC during recovery, then it may trigger panic. Also, if fault injection rate is 1 and only FAULT_BLOCK fault type is on, it may encounter deadloop in loop of block reservation. Let's change as below to fix these issues: - remove bug_on() to avoid panic. - limit the loop count of block reservation to avoid potential deadloop.
CVE-2024-27037: In the Linux kernel, the following vulnerability has been resolved: clk: zynq: Prevent null pointer dereference caused by kmalloc failure The kmalloc() in zynq_clk_setup() will return null if the physical memory has run out. As a result, if we use snprintf() to write data to the null address, the null pointer dereference bug will happen. This patch uses a stack variable to replace the kmalloc().
CVE-2024-27051: In the Linux kernel, the following vulnerability has been resolved: cpufreq: brcmstb-avs-cpufreq: add check for cpufreq_cpu_get's return value cpufreq_cpu_get may return NULL. To avoid NULL-dereference check it and return 0 in case of error. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2024-27054: In the Linux kernel, the following vulnerability has been resolved: s390/dasd: fix double module refcount decrement Once the discipline is associated with the device, deleting the device takes care of decrementing the module's refcount. Doing it manually on this error path causes refcount to artificially decrease on each error while it should just stay the same.
CVE-2024-27056: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: ensure offloading TID queue exists The resume code path assumes that the TX queue for the offloading TID has been configured. At resume time it then tries to sync the write pointer as it may have been updated by the firmware. In the unusual event that no packets have been send on TID 0, the queue will not have been allocated and this causes a crash. Fix this by ensuring the queue exist at suspend time.
CVE-2024-27057: In the Linux kernel, the following vulnerability has been resolved: ASoC: SOF: ipc4-pcm: Workaround for crashed firmware on system suspend When the system is suspended while audio is active, the sof_ipc4_pcm_hw_free() is invoked to reset the pipelines since during suspend the DSP is turned off, streams will be re-started after resume. If the firmware crashes during while audio is running (or when we reset the stream before suspend) then the sof_ipc4_set_multi_pipeline_state() will fail with IPC error and the state change is interrupted. This will cause misalignment between the kernel and firmware state on next DSP boot resulting errors returned by firmware for IPC messages, eventually failing the audio resume. On stream close the errors are ignored so the kernel state will be corrected on the next DSP boot, so the second boot after the DSP panic. If sof_ipc4_trigger_pipelines() is called from sof_ipc4_pcm_hw_free() then state parameter is SOF_IPC4_PIPE_RESET and only in this case. Treat a forced pipeline reset similarly to how we treat a pcm_free by ignoring error on state sending to allow the kernel's state to be consistent with the state the firmware will have after the next boot.
CVE-2024-27062: In the Linux kernel, the following vulnerability has been resolved: nouveau: lock the client object tree. It appears the client object tree has no locking unless I've missed something else. Fix races around adding/removing client objects, mostly vram bar mappings. 4562.099306] general protection fault, probably for non-canonical address 0x6677ed422bceb80c: 0000 [#1] PREEMPT SMP PTI [ 4562.099314] CPU: 2 PID: 23171 Comm: deqp-vk Not tainted 6.8.0-rc6+ #27 [ 4562.099324] Hardware name: Gigabyte Technology Co., Ltd. Z390 I AORUS PRO WIFI/Z390 I AORUS PRO WIFI-CF, BIOS F8 11/05/2021 [ 4562.099330] RIP: 0010:nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099503] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 48 89 f8 48 85 f6 74 39 48 8b 87 a0 00 00 00 48 85 c0 74 12 <48> 8b 48 f8 48 39 ce 73 15 48 8b 40 10 48 85 c0 75 ee 48 c7 c0 fe [ 4562.099506] RSP: 0000:ffffa94cc420bbf8 EFLAGS: 00010206 [ 4562.099512] RAX: 6677ed422bceb814 RBX: ffff98108791f400 RCX: ffff9810f26b8f58 [ 4562.099517] RDX: 0000000000000000 RSI: ffff9810f26b9158 RDI: ffff98108791f400 [ 4562.099519] RBP: ffff9810f26b9158 R08: 0000000000000000 R09: 0000000000000000 [ 4562.099521] R10: ffffa94cc420bc48 R11: 0000000000000001 R12: ffff9810f02a7cc0 [ 4562.099526] R13: 0000000000000000 R14: 00000000000000ff R15: 0000000000000007 [ 4562.099528] FS: 00007f629c5017c0(0000) GS:ffff98142c700000(0000) knlGS:0000000000000000 [ 4562.099534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4562.099536] CR2: 00007f629a882000 CR3: 000000017019e004 CR4: 00000000003706f0 [ 4562.099541] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4562.099542] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4562.099544] Call Trace: [ 4562.099555] <TASK> [ 4562.099573] ? die_addr+0x36/0x90 [ 4562.099583] ? exc_general_protection+0x246/0x4a0 [ 4562.099593] ? asm_exc_general_protection+0x26/0x30 [ 4562.099600] ? nvkm_object_search+0x1d/0x70 [nouveau] [ 4562.099730] nvkm_ioctl+0xa1/0x250 [nouveau] [ 4562.099861] nvif_object_map_handle+0xc8/0x180 [nouveau] [ 4562.099986] nouveau_ttm_io_mem_reserve+0x122/0x270 [nouveau] [ 4562.100156] ? dma_resv_test_signaled+0x26/0xb0 [ 4562.100163] ttm_bo_vm_fault_reserved+0x97/0x3c0 [ttm] [ 4562.100182] ? __mutex_unlock_slowpath+0x2a/0x270 [ 4562.100189] nouveau_ttm_fault+0x69/0xb0 [nouveau] [ 4562.100356] __do_fault+0x32/0x150 [ 4562.100362] do_fault+0x7c/0x560 [ 4562.100369] __handle_mm_fault+0x800/0xc10 [ 4562.100382] handle_mm_fault+0x17c/0x3e0 [ 4562.100388] do_user_addr_fault+0x208/0x860 [ 4562.100395] exc_page_fault+0x7f/0x200 [ 4562.100402] asm_exc_page_fault+0x26/0x30 [ 4562.100412] RIP: 0033:0x9b9870 [ 4562.100419] Code: 85 a8 f7 ff ff 8b 8d 80 f7 ff ff 89 08 e9 18 f2 ff ff 0f 1f 84 00 00 00 00 00 44 89 32 e9 90 fa ff ff 0f 1f 84 00 00 00 00 00 <44> 89 32 e9 f8 f1 ff ff 0f 1f 84 00 00 00 00 00 66 44 89 32 e9 e7 [ 4562.100422] RSP: 002b:00007fff9ba2dc70 EFLAGS: 00010246 [ 4562.100426] RAX: 0000000000000004 RBX: 000000000dd65e10 RCX: 000000fff0000000 [ 4562.100428] RDX: 00007f629a882000 RSI: 00007f629a882000 RDI: 0000000000000066 [ 4562.100432] RBP: 00007fff9ba2e570 R08: 0000000000000000 R09: 0000000123ddf000 [ 4562.100434] R10: 0000000000000001 R11: 0000000000000246 R12: 000000007fffffff [ 4562.100436] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 4562.100446] </TASK> [ 4562.100448] Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables libcrc32c nfnetlink cmac bnep sunrpc iwlmvm intel_rapl_msr intel_rapl_common snd_sof_pci_intel_cnl x86_pkg_temp_thermal intel_powerclamp snd_sof_intel_hda_common mac80211 coretemp snd_soc_acpi_intel_match kvm_intel snd_soc_acpi snd_soc_hdac_hda snd_sof_pci snd_sof_xtensa_dsp snd_sof_intel_hda_mlink ---truncated---
CVE-2024-27072: In the Linux kernel, the following vulnerability has been resolved: media: usbtv: Remove useless locks in usbtv_video_free() Remove locks calls in usbtv_video_free() because are useless and may led to a deadlock as reported here: https://syzkaller.appspot.com/x/bisect.txt?x=166dc872180000 Also remove usbtv_stop() call since it will be called when unregistering the device. Before 'c838530d230b' this issue would only be noticed if you disconnect while streaming and now it is noticeable even when disconnecting while not streaming. [hverkuil: fix minor spelling mistake in log message]
CVE-2024-27073: In the Linux kernel, the following vulnerability has been resolved: media: ttpci: fix two memleaks in budget_av_attach When saa7146_register_device and saa7146_vv_init fails, budget_av_attach should free the resources it allocates, like the error-handling of ttpci_budget_init does. Besides, there are two fixme comment refers to such deallocations.
CVE-2024-27397: In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_tables: use timestamp to check for set element timeout Add a timestamp field at the beginning of the transaction, store it in the nftables per-netns area. Update set backend .insert, .deactivate and sync gc path to use the timestamp, this avoids that an element expires while control plane transaction is still unfinished. .lookup and .update, which are used from packet path, still use the current time to check if the element has expired. And .get path and dump also since this runs lockless under rcu read size lock. Then, there is async gc which also needs to check the current time since it runs asynchronously from a workqueue.
CVE-2024-27402: In the Linux kernel, the following vulnerability has been resolved: phonet/pep: fix racy skb_queue_empty() use The receive queues are protected by their respective spin-lock, not the socket lock. This could lead to skb_peek() unexpectedly returning NULL or a pointer to an already dequeued socket buffer.
CVE-2024-27403: In the Linux kernel, the following vulnerability has been resolved: netfilter: nft_flow_offload: reset dst in route object after setting up flow dst is transferred to the flow object, route object does not own it anymore. Reset dst in route object, otherwise if flow_offload_add() fails, error path releases dst twice, leading to a refcount underflow.
CVE-2024-27407: In the Linux kernel, the following vulnerability has been resolved: fs/ntfs3: Fixed overflow check in mi_enum_attr()
CVE-2024-27415: In the Linux kernel, the following vulnerability has been resolved: netfilter: bridge: confirm multicast packets before passing them up the stack conntrack nf_confirm logic cannot handle cloned skbs referencing the same nf_conn entry, which will happen for multicast (broadcast) frames on bridges. Example: macvlan0 | br0 / \ ethX ethY ethX (or Y) receives a L2 multicast or broadcast packet containing an IP packet, flow is not yet in conntrack table. 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. -> skb->_nfct now references a unconfirmed entry 2. skb is broad/mcast packet. bridge now passes clones out on each bridge interface. 3. skb gets passed up the stack. 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb and schedules a work queue to send them out on the lower devices. The clone skb->_nfct is not a copy, it is the same entry as the original skb. The macvlan rx handler then returns RX_HANDLER_PASS. 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. The Macvlan broadcast worker and normal confirm path will race. This race will not happen if step 2 already confirmed a clone. In that case later steps perform skb_clone() with skb->_nfct already confirmed (in hash table). This works fine. But such confirmation won't happen when eb/ip/nftables rules dropped the packets before they reached the nf_confirm step in postrouting. Pablo points out that nf_conntrack_bridge doesn't allow use of stateful nat, so we can safely discard the nf_conn entry and let inet call conntrack again. This doesn't work for bridge netfilter: skb could have a nat transformation. Also bridge nf prevents re-invocation of inet prerouting via 'sabotage_in' hook. Work around this problem by explicit confirmation of the entry at LOCAL_IN time, before upper layer has a chance to clone the unconfirmed entry. The downside is that this disables NAT and conntrack helpers. Alternative fix would be to add locking to all code parts that deal with unconfirmed packets, but even if that could be done in a sane way this opens up other problems, for example: -m physdev --physdev-out eth0 -j SNAT --snat-to 1.2.3.4 -m physdev --physdev-out eth1 -j SNAT --snat-to 1.2.3.5 For multicast case, only one of such conflicting mappings will be created, conntrack only handles 1:1 NAT mappings. Users should set create a setup that explicitly marks such traffic NOTRACK (conntrack bypass) to avoid this, but we cannot auto-bypass them, ruleset might have accept rules for untracked traffic already, so user-visible behaviour would change.
CVE-2024-27437: In the Linux kernel, the following vulnerability has been resolved: vfio/pci: Disable auto-enable of exclusive INTx IRQ Currently for devices requiring masking at the irqchip for INTx, ie. devices without DisINTx support, the IRQ is enabled in request_irq() and subsequently disabled as necessary to align with the masked status flag. This presents a window where the interrupt could fire between these events, resulting in the IRQ incrementing the disable depth twice. This would be unrecoverable for a user since the masked flag prevents nested enables through vfio. Instead, invert the logic using IRQF_NO_AUTOEN such that exclusive INTx is never auto-enabled, then unmask as required.
CVE-2024-35247: In the Linux kernel, the following vulnerability has been resolved: fpga: region: add owner module and take its refcount The current implementation of the fpga region assumes that the low-level module registers a driver for the parent device and uses its owner pointer to take the module's refcount. This approach is problematic since it can lead to a null pointer dereference while attempting to get the region during programming if the parent device does not have a driver. To address this problem, add a module owner pointer to the fpga_region struct and use it to take the module's refcount. Modify the functions for registering a region to take an additional owner module parameter and rename them to avoid conflicts. Use the old function names for helper macros that automatically set the module that registers the region as the owner. This ensures compatibility with existing low-level control modules and reduces the chances of registering a region without setting the owner. Also, update the documentation to keep it consistent with the new interface for registering an fpga region.
CVE-2024-35784: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix deadlock with fiemap and extent locking While working on the patchset to remove extent locking I got a lockdep splat with fiemap and pagefaulting with my new extent lock replacement lock. This deadlock exists with our normal code, we just don't have lockdep annotations with the extent locking so we've never noticed it. Since we're copying the fiemap extent to user space on every iteration we have the chance of pagefaulting. Because we hold the extent lock for the entire range we could mkwrite into a range in the file that we have mmap'ed. This would deadlock with the following stack trace [<0>] lock_extent+0x28d/0x2f0 [<0>] btrfs_page_mkwrite+0x273/0x8a0 [<0>] do_page_mkwrite+0x50/0xb0 [<0>] do_fault+0xc1/0x7b0 [<0>] __handle_mm_fault+0x2fa/0x460 [<0>] handle_mm_fault+0xa4/0x330 [<0>] do_user_addr_fault+0x1f4/0x800 [<0>] exc_page_fault+0x7c/0x1e0 [<0>] asm_exc_page_fault+0x26/0x30 [<0>] rep_movs_alternative+0x33/0x70 [<0>] _copy_to_user+0x49/0x70 [<0>] fiemap_fill_next_extent+0xc8/0x120 [<0>] emit_fiemap_extent+0x4d/0xa0 [<0>] extent_fiemap+0x7f8/0xad0 [<0>] btrfs_fiemap+0x49/0x80 [<0>] __x64_sys_ioctl+0x3e1/0xb50 [<0>] do_syscall_64+0x94/0x1a0 [<0>] entry_SYSCALL_64_after_hwframe+0x6e/0x76 I wrote an fstest to reproduce this deadlock without my replacement lock and verified that the deadlock exists with our existing locking. To fix this simply don't take the extent lock for the entire duration of the fiemap. This is safe in general because we keep track of where we are when we're searching the tree, so if an ordered extent updates in the middle of our fiemap call we'll still emit the correct extents because we know what offset we were on before. The only place we maintain the lock is searching delalloc. Since the delalloc stuff can change during writeback we want to lock the extent range so we have a consistent view of delalloc at the time we're checking to see if we need to set the delalloc flag. With this patch applied we no longer deadlock with my testcase.
CVE-2024-35790: In the Linux kernel, the following vulnerability has been resolved: usb: typec: altmodes/displayport: create sysfs nodes as driver's default device attribute group The DisplayPort driver's sysfs nodes may be present to the userspace before typec_altmode_set_drvdata() completes in dp_altmode_probe. This means that a sysfs read can trigger a NULL pointer error by deferencing dp->hpd in hpd_show or dp->lock in pin_assignment_show, as dev_get_drvdata() returns NULL in those cases. Remove manual sysfs node creation in favor of adding attribute group as default for devices bound to the driver. The ATTRIBUTE_GROUPS() macro is not used here otherwise the path to the sysfs nodes is no longer compliant with the ABI.
CVE-2024-35791: In the Linux kernel, the following vulnerability has been resolved: KVM: SVM: Flush pages under kvm->lock to fix UAF in svm_register_enc_region() Do the cache flush of converted pages in svm_register_enc_region() before dropping kvm->lock to fix use-after-free issues where region and/or its array of pages could be freed by a different task, e.g. if userspace has __unregister_enc_region_locked() already queued up for the region. Note, the "obvious" alternative of using local variables doesn't fully resolve the bug, as region->pages is also dynamically allocated. I.e. the region structure itself would be fine, but region->pages could be freed. Flushing multiple pages under kvm->lock is unfortunate, but the entire flow is a rare slow path, and the manual flush is only needed on CPUs that lack coherency for encrypted memory.
CVE-2024-35794: In the Linux kernel, the following vulnerability has been resolved: dm-raid: really frozen sync_thread during suspend 1) commit f52f5c71f3d4 ("md: fix stopping sync thread") remove MD_RECOVERY_FROZEN from __md_stop_writes() and doesn't realize that dm-raid relies on __md_stop_writes() to frozen sync_thread indirectly. Fix this problem by adding MD_RECOVERY_FROZEN in md_stop_writes(), and since stop_sync_thread() is only used for dm-raid in this case, also move stop_sync_thread() to md_stop_writes(). 2) The flag MD_RECOVERY_FROZEN doesn't mean that sync thread is frozen, it only prevent new sync_thread to start, and it can't stop the running sync thread; In order to frozen sync_thread, after seting the flag, stop_sync_thread() should be used. 3) The flag MD_RECOVERY_FROZEN doesn't mean that writes are stopped, use it as condition for md_stop_writes() in raid_postsuspend() doesn't look correct. Consider that reentrant stop_sync_thread() do nothing, always call md_stop_writes() in raid_postsuspend(). 4) raid_message can set/clear the flag MD_RECOVERY_FROZEN at anytime, and if MD_RECOVERY_FROZEN is cleared while the array is suspended, new sync_thread can start unexpected. Fix this by disallow raid_message() to change sync_thread status during suspend. Note that after commit f52f5c71f3d4 ("md: fix stopping sync thread"), the test shell/lvconvert-raid-reshape.sh start to hang in stop_sync_thread(), and with previous fixes, the test won't hang there anymore, however, the test will still fail and complain that ext4 is corrupted. And with this patch, the test won't hang due to stop_sync_thread() or fail due to ext4 is corrupted anymore. However, there is still a deadlock related to dm-raid456 that will be fixed in following patches.
CVE-2024-35799: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Prevent crash when disable stream [Why] Disabling stream encoder invokes a function that no longer exists. [How] Check if the function declaration is NULL in disable stream encoder.
CVE-2024-35803: In the Linux kernel, the following vulnerability has been resolved: x86/efistub: Call mixed mode boot services on the firmware's stack Normally, the EFI stub calls into the EFI boot services using the stack that was live when the stub was entered. According to the UEFI spec, this stack needs to be at least 128k in size - this might seem large but all asynchronous processing and event handling in EFI runs from the same stack and so quite a lot of space may be used in practice. In mixed mode, the situation is a bit different: the bootloader calls the 32-bit EFI stub entry point, which calls the decompressor's 32-bit entry point, where the boot stack is set up, using a fixed allocation of 16k. This stack is still in use when the EFI stub is started in 64-bit mode, and so all calls back into the EFI firmware will be using the decompressor's limited boot stack. Due to the placement of the boot stack right after the boot heap, any stack overruns have gone unnoticed. However, commit 5c4feadb0011983b ("x86/decompressor: Move global symbol references to C code") moved the definition of the boot heap into C code, and now the boot stack is placed right at the base of BSS, where any overruns will corrupt the end of the .data section. While it would be possible to work around this by increasing the size of the boot stack, doing so would affect all x86 systems, and mixed mode systems are a tiny (and shrinking) fraction of the x86 installed base. So instead, record the firmware stack pointer value when entering from the 32-bit firmware, and switch to this stack every time a EFI boot service call is made.
CVE-2024-35805: In the Linux kernel, the following vulnerability has been resolved: dm snapshot: fix lockup in dm_exception_table_exit There was reported lockup when we exit a snapshot with many exceptions. Fix this by adding "cond_resched" to the loop that frees the exceptions.
CVE-2024-35808: In the Linux kernel, the following vulnerability has been resolved: md/dm-raid: don't call md_reap_sync_thread() directly Currently md_reap_sync_thread() is called from raid_message() directly without holding 'reconfig_mutex', this is definitely unsafe because md_reap_sync_thread() can change many fields that is protected by 'reconfig_mutex'. However, hold 'reconfig_mutex' here is still problematic because this will cause deadlock, for example, commit 130443d60b1b ("md: refactor idle/frozen_sync_thread() to fix deadlock"). Fix this problem by using stop_sync_thread() to unregister sync_thread, like md/raid did.
CVE-2024-35817: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: amdgpu_ttm_gart_bind set gtt bound flag Otherwise after the GTT bo is released, the GTT and gart space is freed but amdgpu_ttm_backend_unbind will not clear the gart page table entry and leave valid mapping entry pointing to the stale system page. Then if GPU access the gart address mistakely, it will read undefined value instead page fault, harder to debug and reproduce the real issue.
CVE-2024-35818: In the Linux kernel, the following vulnerability has been resolved: LoongArch: Define the __io_aw() hook as mmiowb() Commit fb24ea52f78e0d595852e ("drivers: Remove explicit invocations of mmiowb()") remove all mmiowb() in drivers, but it says: "NOTE: mmiowb() has only ever guaranteed ordering in conjunction with spin_unlock(). However, pairing each mmiowb() removal in this patch with the corresponding call to spin_unlock() is not at all trivial, so there is a small chance that this change may regress any drivers incorrectly relying on mmiowb() to order MMIO writes between CPUs using lock-free synchronisation." The mmio in radeon_ring_commit() is protected by a mutex rather than a spinlock, but in the mutex fastpath it behaves similar to spinlock. We can add mmiowb() calls in the radeon driver but the maintainer says he doesn't like such a workaround, and radeon is not the only example of mutex protected mmio. So we should extend the mmiowb tracking system from spinlock to mutex, and maybe other locking primitives. This is not easy and error prone, so we solve it in the architectural code, by simply defining the __io_aw() hook as mmiowb(). And we no longer need to override queued_spin_unlock() so use the generic definition. Without this, we get such an error when run 'glxgears' on weak ordering architectures such as LoongArch: radeon 0000:04:00.0: ring 0 stalled for more than 10324msec radeon 0000:04:00.0: ring 3 stalled for more than 10240msec radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000001f412 last fence id 0x000000000001f414 on ring 3) radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000000f940 last fence id 0x000000000000f941 on ring 0) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35)
CVE-2024-35826: In the Linux kernel, the following vulnerability has been resolved: block: Fix page refcounts for unaligned buffers in __bio_release_pages() Fix an incorrect number of pages being released for buffers that do not start at the beginning of a page.
CVE-2024-35832: In the Linux kernel, the following vulnerability has been resolved: bcachefs: kvfree bch_fs::snapshots in bch2_fs_snapshots_exit bch_fs::snapshots is allocated by kvzalloc in __snapshot_t_mut. It should be freed by kvfree not kfree. Or umount will triger: [ 406.829178 ] BUG: unable to handle page fault for address: ffffe7b487148008 [ 406.830676 ] #PF: supervisor read access in kernel mode [ 406.831643 ] #PF: error_code(0x0000) - not-present page [ 406.832487 ] PGD 0 P4D 0 [ 406.832898 ] Oops: 0000 [#1] PREEMPT SMP PTI [ 406.833512 ] CPU: 2 PID: 1754 Comm: umount Kdump: loaded Tainted: G OE 6.7.0-rc7-custom+ #90 [ 406.834746 ] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014 [ 406.835796 ] RIP: 0010:kfree+0x62/0x140 [ 406.836197 ] Code: 80 48 01 d8 0f 82 e9 00 00 00 48 c7 c2 00 00 00 80 48 2b 15 78 9f 1f 01 48 01 d0 48 c1 e8 0c 48 c1 e0 06 48 03 05 56 9f 1f 01 <48> 8b 50 08 48 89 c7 f6 c2 01 0f 85 b0 00 00 00 66 90 48 8b 07 f6 [ 406.837810 ] RSP: 0018:ffffb9d641607e48 EFLAGS: 00010286 [ 406.838213 ] RAX: ffffe7b487148000 RBX: ffffb9d645200000 RCX: ffffb9d641607dc4 [ 406.838738 ] RDX: 000065bb00000000 RSI: ffffffffc0d88b84 RDI: ffffb9d645200000 [ 406.839217 ] RBP: ffff9a4625d00068 R08: 0000000000000001 R09: 0000000000000001 [ 406.839650 ] R10: 0000000000000001 R11: 000000000000001f R12: ffff9a4625d4da80 [ 406.840055 ] R13: ffff9a4625d00000 R14: ffffffffc0e2eb20 R15: 0000000000000000 [ 406.840451 ] FS: 00007f0a264ffb80(0000) GS:ffff9a4e2d500000(0000) knlGS:0000000000000000 [ 406.840851 ] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 406.841125 ] CR2: ffffe7b487148008 CR3: 000000018c4d2000 CR4: 00000000000006f0 [ 406.841464 ] Call Trace: [ 406.841583 ] <TASK> [ 406.841682 ] ? __die+0x1f/0x70 [ 406.841828 ] ? page_fault_oops+0x159/0x470 [ 406.842014 ] ? fixup_exception+0x22/0x310 [ 406.842198 ] ? exc_page_fault+0x1ed/0x200 [ 406.842382 ] ? asm_exc_page_fault+0x22/0x30 [ 406.842574 ] ? bch2_fs_release+0x54/0x280 [bcachefs] [ 406.842842 ] ? kfree+0x62/0x140 [ 406.842988 ] ? kfree+0x104/0x140 [ 406.843138 ] bch2_fs_release+0x54/0x280 [bcachefs] [ 406.843390 ] kobject_put+0xb7/0x170 [ 406.843552 ] deactivate_locked_super+0x2f/0xa0 [ 406.843756 ] cleanup_mnt+0xba/0x150 [ 406.843917 ] task_work_run+0x59/0xa0 [ 406.844083 ] exit_to_user_mode_prepare+0x197/0x1a0 [ 406.844302 ] syscall_exit_to_user_mode+0x16/0x40 [ 406.844510 ] do_syscall_64+0x4e/0xf0 [ 406.844675 ] entry_SYSCALL_64_after_hwframe+0x6e/0x76 [ 406.844907 ] RIP: 0033:0x7f0a2664e4fb
CVE-2024-35837: In the Linux kernel, the following vulnerability has been resolved: net: mvpp2: clear BM pool before initialization Register value persist after booting the kernel using kexec which results in kernel panic. Thus clear the BM pool registers before initialisation to fix the issue.
CVE-2024-35839: In the Linux kernel, the following vulnerability has been resolved: netfilter: bridge: replace physindev with physinif in nf_bridge_info An skb can be added to a neigh->arp_queue while waiting for an arp reply. Where original skb's skb->dev can be different to neigh's neigh->dev. For instance in case of bridging dnated skb from one veth to another, the skb would be added to a neigh->arp_queue of the bridge. As skb->dev can be reset back to nf_bridge->physindev and used, and as there is no explicit mechanism that prevents this physindev from been freed under us (for instance neigh_flush_dev doesn't cleanup skbs from different device's neigh queue) we can crash on e.g. this stack: arp_process neigh_update skb = __skb_dequeue(&neigh->arp_queue) neigh_resolve_output(..., skb) ... br_nf_dev_xmit br_nf_pre_routing_finish_bridge_slow skb->dev = nf_bridge->physindev br_handle_frame_finish Let's use plain ifindex instead of net_device link. To peek into the original net_device we will use dev_get_by_index_rcu(). Thus either we get device and are safe to use it or we don't get it and drop skb.
CVE-2024-35843: In the Linux kernel, the following vulnerability has been resolved: iommu/vt-d: Use device rbtree in iopf reporting path The existing I/O page fault handler currently locates the PCI device by calling pci_get_domain_bus_and_slot(). This function searches the list of all PCI devices until the desired device is found. To improve lookup efficiency, replace it with device_rbtree_find() to search the device within the probed device rbtree. The I/O page fault is initiated by the device, which does not have any synchronization mechanism with the software to ensure that the device stays in the probed device tree. Theoretically, a device could be released by the IOMMU subsystem after device_rbtree_find() and before iopf_get_dev_fault_param(), which would cause a use-after-free problem. Add a mutex to synchronize the I/O page fault reporting path and the IOMMU release device path. This lock doesn't introduce any performance overhead, as the conflict between I/O page fault reporting and device releasing is very rare.
CVE-2024-35861: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_signal_cifsd_for_reconnect() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35862: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_is_network_name_deleted() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35863: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in is_valid_oplock_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35864: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_is_valid_lease_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35865: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in smb2_is_valid_oplock_break() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35866: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_dump_full_key() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35867: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_stats_proc_show() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35868: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix potential UAF in cifs_stats_proc_write() Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF.
CVE-2024-35869: In the Linux kernel, the following vulnerability has been resolved: smb: client: guarantee refcounted children from parent session Avoid potential use-after-free bugs when walking DFS referrals, mounting and performing DFS failover by ensuring that all children from parent @tcon->ses are also refcounted. They're all needed across the entire DFS mount. Get rid of @tcon->dfs_ses_list while we're at it, too.
CVE-2024-35870: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix UAF in smb2_reconnect_server() The UAF bug is due to smb2_reconnect_server() accessing a session that is already being teared down by another thread that is executing __cifs_put_smb_ses(). This can happen when (a) the client has connection to the server but no session or (b) another thread ends up setting @ses->ses_status again to something different than SES_EXITING. To fix this, we need to make sure to unconditionally set @ses->ses_status to SES_EXITING and prevent any other threads from setting a new status while we're still tearing it down. The following can be reproduced by adding some delay to right after the ipc is freed in __cifs_put_smb_ses() - which will give smb2_reconnect_server() worker a chance to run and then accessing @ses->ipc: kinit ... mount.cifs //srv/share /mnt/1 -o sec=krb5,nohandlecache,echo_interval=10 [disconnect srv] ls /mnt/1 &>/dev/null sleep 30 kdestroy [reconnect srv] sleep 10 umount /mnt/1 ... CIFS: VFS: Verify user has a krb5 ticket and keyutils is installed CIFS: VFS: \\srv Send error in SessSetup = -126 CIFS: VFS: Verify user has a krb5 ticket and keyutils is installed CIFS: VFS: \\srv Send error in SessSetup = -126 general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] PREEMPT SMP NOPTI CPU: 3 PID: 50 Comm: kworker/3:1 Not tainted 6.9.0-rc2 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39 04/01/2014 Workqueue: cifsiod smb2_reconnect_server [cifs] RIP: 0010:__list_del_entry_valid_or_report+0x33/0xf0 Code: 4f 08 48 85 d2 74 42 48 85 c9 74 59 48 b8 00 01 00 00 00 00 ad de 48 39 c2 74 61 48 b8 22 01 00 00 00 00 74 69 <48> 8b 01 48 39 f8 75 7b 48 8b 72 08 48 39 c6 0f 85 88 00 00 00 b8 RSP: 0018:ffffc900001bfd70 EFLAGS: 00010a83 RAX: dead000000000122 RBX: ffff88810da53838 RCX: 6b6b6b6b6b6b6b6b RDX: 6b6b6b6b6b6b6b6b RSI: ffffffffc02f6878 RDI: ffff88810da53800 RBP: ffff88810da53800 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: ffff88810c064000 R13: 0000000000000001 R14: ffff88810c064000 R15: ffff8881039cc000 FS: 0000000000000000(0000) GS:ffff888157c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe3728b1000 CR3: 000000010caa4000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: <TASK> ? die_addr+0x36/0x90 ? exc_general_protection+0x1c1/0x3f0 ? asm_exc_general_protection+0x26/0x30 ? __list_del_entry_valid_or_report+0x33/0xf0 __cifs_put_smb_ses+0x1ae/0x500 [cifs] smb2_reconnect_server+0x4ed/0x710 [cifs] process_one_work+0x205/0x6b0 worker_thread+0x191/0x360 ? __pfx_worker_thread+0x10/0x10 kthread+0xe2/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>
CVE-2024-35871: In the Linux kernel, the following vulnerability has been resolved: riscv: process: Fix kernel gp leakage childregs represents the registers which are active for the new thread in user context. For a kernel thread, childregs->gp is never used since the kernel gp is not touched by switch_to. For a user mode helper, the gp value can be observed in user space after execve or possibly by other means. [From the email thread] The /* Kernel thread */ comment is somewhat inaccurate in that it is also used for user_mode_helper threads, which exec a user process, e.g. /sbin/init or when /proc/sys/kernel/core_pattern is a pipe. Such threads do not have PF_KTHREAD set and are valid targets for ptrace etc. even before they exec. childregs is the *user* context during syscall execution and it is observable from userspace in at least five ways: 1. kernel_execve does not currently clear integer registers, so the starting register state for PID 1 and other user processes started by the kernel has sp = user stack, gp = kernel __global_pointer$, all other integer registers zeroed by the memset in the patch comment. This is a bug in its own right, but I'm unwilling to bet that it is the only way to exploit the issue addressed by this patch. 2. ptrace(PTRACE_GETREGSET): you can PTRACE_ATTACH to a user_mode_helper thread before it execs, but ptrace requires SIGSTOP to be delivered which can only happen at user/kernel boundaries. 3. /proc/*/task/*/syscall: this is perfectly happy to read pt_regs for user_mode_helpers before the exec completes, but gp is not one of the registers it returns. 4. PERF_SAMPLE_REGS_USER: LOCKDOWN_PERF normally prevents access to kernel addresses via PERF_SAMPLE_REGS_INTR, but due to this bug kernel addresses are also exposed via PERF_SAMPLE_REGS_USER which is permitted under LOCKDOWN_PERF. I have not attempted to write exploit code. 5. Much of the tracing infrastructure allows access to user registers. I have not attempted to determine which forms of tracing allow access to user registers without already allowing access to kernel registers.
CVE-2024-35875: In the Linux kernel, the following vulnerability has been resolved: x86/coco: Require seeding RNG with RDRAND on CoCo systems There are few uses of CoCo that don't rely on working cryptography and hence a working RNG. Unfortunately, the CoCo threat model means that the VM host cannot be trusted and may actively work against guests to extract secrets or manipulate computation. Since a malicious host can modify or observe nearly all inputs to guests, the only remaining source of entropy for CoCo guests is RDRAND. If RDRAND is broken -- due to CPU hardware fault -- the RNG as a whole is meant to gracefully continue on gathering entropy from other sources, but since there aren't other sources on CoCo, this is catastrophic. This is mostly a concern at boot time when initially seeding the RNG, as after that the consequences of a broken RDRAND are much more theoretical. So, try at boot to seed the RNG using 256 bits of RDRAND output. If this fails, panic(). This will also trigger if the system is booted without RDRAND, as RDRAND is essential for a safe CoCo boot. Add this deliberately to be "just a CoCo x86 driver feature" and not part of the RNG itself. Many device drivers and platforms have some desire to contribute something to the RNG, and add_device_randomness() is specifically meant for this purpose. Any driver can call it with seed data of any quality, or even garbage quality, and it can only possibly make the quality of the RNG better or have no effect, but can never make it worse. Rather than trying to build something into the core of the RNG, consider the particular CoCo issue just a CoCo issue, and therefore separate it all out into driver (well, arch/platform) code. [ bp: Massage commit message. ]
CVE-2024-35878: In the Linux kernel, the following vulnerability has been resolved: of: module: prevent NULL pointer dereference in vsnprintf() In of_modalias(), we can get passed the str and len parameters which would cause a kernel oops in vsnprintf() since it only allows passing a NULL ptr when the length is also 0. Also, we need to filter out the negative values of the len parameter as these will result in a really huge buffer since snprintf() takes size_t parameter while ours is ssize_t... Found by Linux Verification Center (linuxtesting.org) with the Svace static analysis tool.
CVE-2024-35887: In the Linux kernel, the following vulnerability has been resolved: ax25: fix use-after-free bugs caused by ax25_ds_del_timer When the ax25 device is detaching, the ax25_dev_device_down() calls ax25_ds_del_timer() to cleanup the slave_timer. When the timer handler is running, the ax25_ds_del_timer() that calls del_timer() in it will return directly. As a result, the use-after-free bugs could happen, one of the scenarios is shown below: (Thread 1) | (Thread 2) | ax25_ds_timeout() ax25_dev_device_down() | ax25_ds_del_timer() | del_timer() | ax25_dev_put() //FREE | | ax25_dev-> //USE In order to mitigate bugs, when the device is detaching, use timer_shutdown_sync() to stop the timer.
CVE-2024-35896: In the Linux kernel, the following vulnerability has been resolved: netfilter: validate user input for expected length I got multiple syzbot reports showing old bugs exposed by BPF after commit 20f2505fb436 ("bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt") setsockopt() @optlen argument should be taken into account before copying data. BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in do_replace net/ipv4/netfilter/ip_tables.c:1111 [inline] BUG: KASAN: slab-out-of-bounds in do_ipt_set_ctl+0x902/0x3dd0 net/ipv4/netfilter/ip_tables.c:1627 Read of size 96 at addr ffff88802cd73da0 by task syz-executor.4/7238 CPU: 1 PID: 7238 Comm: syz-executor.4 Not tainted 6.9.0-rc2-next-20240403-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 kasan_check_range+0x282/0x290 mm/kasan/generic.c:189 __asan_memcpy+0x29/0x70 mm/kasan/shadow.c:105 copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] copy_from_sockptr include/linux/sockptr.h:55 [inline] do_replace net/ipv4/netfilter/ip_tables.c:1111 [inline] do_ipt_set_ctl+0x902/0x3dd0 net/ipv4/netfilter/ip_tables.c:1627 nf_setsockopt+0x295/0x2c0 net/netfilter/nf_sockopt.c:101 do_sock_setsockopt+0x3af/0x720 net/socket.c:2311 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x72/0x7a RIP: 0033:0x7fd22067dde9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fd21f9ff0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00007fd2207abf80 RCX: 00007fd22067dde9 RDX: 0000000000000040 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00007fd2206ca47a R08: 0000000000000001 R09: 0000000000000000 R10: 0000000020000880 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fd2207abf80 R15: 00007ffd2d0170d8 </TASK> Allocated by task 7238: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:370 [inline] __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slub.c:4069 [inline] __kmalloc_noprof+0x200/0x410 mm/slub.c:4082 kmalloc_noprof include/linux/slab.h:664 [inline] __cgroup_bpf_run_filter_setsockopt+0xd47/0x1050 kernel/bpf/cgroup.c:1869 do_sock_setsockopt+0x6b4/0x720 net/socket.c:2293 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x72/0x7a The buggy address belongs to the object at ffff88802cd73da0 which belongs to the cache kmalloc-8 of size 8 The buggy address is located 0 bytes inside of allocated 1-byte region [ffff88802cd73da0, ffff88802cd73da1) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88802cd73020 pfn:0x2cd73 flags: 0xfff80000000000(node=0|zone=1|lastcpupid=0xfff) page_type: 0xffffefff(slab) raw: 00fff80000000000 ffff888015041280 dead000000000100 dead000000000122 raw: ffff88802cd73020 000000008080007f 00000001ffffefff 00 ---truncated---
CVE-2024-35904: In the Linux kernel, the following vulnerability has been resolved: selinux: avoid dereference of garbage after mount failure In case kern_mount() fails and returns an error pointer return in the error branch instead of continuing and dereferencing the error pointer. While on it drop the never read static variable selinuxfs_mount.
CVE-2024-35924: In the Linux kernel, the following vulnerability has been resolved: usb: typec: ucsi: Limit read size on v1.2 Between UCSI 1.2 and UCSI 2.0, the size of the MESSAGE_IN region was increased from 16 to 256. In order to avoid overflowing reads for older systems, add a mechanism to use the read UCSI version to truncate read sizes on UCSI v1.2.
CVE-2024-35926: In the Linux kernel, the following vulnerability has been resolved: crypto: iaa - Fix async_disable descriptor leak The disable_async paths of iaa_compress/decompress() don't free idxd descriptors in the async_disable case. Currently this only happens in the testcases where req->dst is set to null. Add a test to free them in those paths.
CVE-2024-35927: In the Linux kernel, the following vulnerability has been resolved: drm: Check output polling initialized before disabling In drm_kms_helper_poll_disable() check if output polling support is initialized before disabling polling. If not flag this as a warning. Additionally in drm_mode_config_helper_suspend() and drm_mode_config_helper_resume() calls, that re the callers of these functions, avoid invoking them if polling is not initialized. For drivers like hyperv-drm, that do not initialize connector polling, if suspend is called without this check, it leads to suspend failure with following stack [ 770.719392] Freezing remaining freezable tasks ... (elapsed 0.001 seconds) done. [ 770.720592] printk: Suspending console(s) (use no_console_suspend to debug) [ 770.948823] ------------[ cut here ]------------ [ 770.948824] WARNING: CPU: 1 PID: 17197 at kernel/workqueue.c:3162 __flush_work.isra.0+0x212/0x230 [ 770.948831] Modules linked in: rfkill nft_counter xt_conntrack xt_owner udf nft_compat crc_itu_t nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables nfnetlink vfat fat mlx5_ib ib_uverbs ib_core mlx5_core intel_rapl_msr intel_rapl_common kvm_amd ccp mlxfw kvm psample hyperv_drm tls drm_shmem_helper drm_kms_helper irqbypass pcspkr syscopyarea sysfillrect sysimgblt hv_balloon hv_utils joydev drm fuse xfs libcrc32c pci_hyperv pci_hyperv_intf sr_mod sd_mod cdrom t10_pi sg hv_storvsc scsi_transport_fc hv_netvsc serio_raw hyperv_keyboard hid_hyperv crct10dif_pclmul crc32_pclmul crc32c_intel hv_vmbus ghash_clmulni_intel dm_mirror dm_region_hash dm_log dm_mod [ 770.948863] CPU: 1 PID: 17197 Comm: systemd-sleep Not tainted 5.14.0-362.2.1.el9_3.x86_64 #1 [ 770.948865] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 05/09/2022 [ 770.948866] RIP: 0010:__flush_work.isra.0+0x212/0x230 [ 770.948869] Code: 8b 4d 00 4c 8b 45 08 89 ca 48 c1 e9 04 83 e2 08 83 e1 0f 83 ca 02 89 c8 48 0f ba 6d 00 03 e9 25 ff ff ff 0f 0b e9 4e ff ff ff <0f> 0b 45 31 ed e9 44 ff ff ff e8 8f 89 b2 00 66 66 2e 0f 1f 84 00 [ 770.948870] RSP: 0018:ffffaf4ac213fb10 EFLAGS: 00010246 [ 770.948871] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff8c992857 [ 770.948872] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff9aad82b00330 [ 770.948873] RBP: ffff9aad82b00330 R08: 0000000000000000 R09: ffff9aad87ee3d10 [ 770.948874] R10: 0000000000000200 R11: 0000000000000000 R12: ffff9aad82b00330 [ 770.948874] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000001 [ 770.948875] FS: 00007ff1b2f6bb40(0000) GS:ffff9aaf37d00000(0000) knlGS:0000000000000000 [ 770.948878] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 770.948878] CR2: 0000555f345cb666 CR3: 00000001462dc005 CR4: 0000000000370ee0 [ 770.948879] Call Trace: [ 770.948880] <TASK> [ 770.948881] ? show_trace_log_lvl+0x1c4/0x2df [ 770.948884] ? show_trace_log_lvl+0x1c4/0x2df [ 770.948886] ? __cancel_work_timer+0x103/0x190 [ 770.948887] ? __flush_work.isra.0+0x212/0x230 [ 770.948889] ? __warn+0x81/0x110 [ 770.948891] ? __flush_work.isra.0+0x212/0x230 [ 770.948892] ? report_bug+0x10a/0x140 [ 770.948895] ? handle_bug+0x3c/0x70 [ 770.948898] ? exc_invalid_op+0x14/0x70 [ 770.948899] ? asm_exc_invalid_op+0x16/0x20 [ 770.948903] ? __flush_work.isra.0+0x212/0x230 [ 770.948905] __cancel_work_timer+0x103/0x190 [ 770.948907] ? _raw_spin_unlock_irqrestore+0xa/0x30 [ 770.948910] drm_kms_helper_poll_disable+0x1e/0x40 [drm_kms_helper] [ 770.948923] drm_mode_config_helper_suspend+0x1c/0x80 [drm_kms_helper] [ 770.948933] ? __pfx_vmbus_suspend+0x10/0x10 [hv_vmbus] [ 770.948942] hyperv_vmbus_suspend+0x17/0x40 [hyperv_drm] [ 770.948944] ? __pfx_vmbus_suspend+0x10/0x10 [hv_vmbus] [ 770.948951] dpm_run_callback+0x4c/0x140 [ 770.948954] __device_suspend_noir ---truncated---
CVE-2024-35928: In the Linux kernel, the following vulnerability has been resolved: drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init() This ensures that the memory mapped by ioremap for adev->rmmio, is properly handled in amdgpu_device_init(). If the function exits early due to an error, the memory is unmapped. If the function completes successfully, the memory remains mapped. Reported by smatch: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:4337 amdgpu_device_init() warn: 'adev->rmmio' from ioremap() not released on lines: 4035,4045,4051,4058,4068,4337
CVE-2024-35929: In the Linux kernel, the following vulnerability has been resolved: rcu/nocb: Fix WARN_ON_ONCE() in the rcu_nocb_bypass_lock() For the kernels built with CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y and CONFIG_RCU_LAZY=y, the following scenarios will trigger WARN_ON_ONCE() in the rcu_nocb_bypass_lock() and rcu_nocb_wait_contended() functions: CPU2 CPU11 kthread rcu_nocb_cb_kthread ksys_write rcu_do_batch vfs_write rcu_torture_timer_cb proc_sys_write __kmem_cache_free proc_sys_call_handler kmemleak_free drop_caches_sysctl_handler delete_object_full drop_slab __delete_object shrink_slab put_object lazy_rcu_shrink_scan call_rcu rcu_nocb_flush_bypass __call_rcu_commn rcu_nocb_bypass_lock raw_spin_trylock(&rdp->nocb_bypass_lock) fail atomic_inc(&rdp->nocb_lock_contended); rcu_nocb_wait_contended WARN_ON_ONCE(smp_processor_id() != rdp->cpu); WARN_ON_ONCE(atomic_read(&rdp->nocb_lock_contended)) | |_ _ _ _ _ _ _ _ _ _same rdp and rdp->cpu != 11_ _ _ _ _ _ _ _ _ __| Reproduce this bug with "echo 3 > /proc/sys/vm/drop_caches". This commit therefore uses rcu_nocb_try_flush_bypass() instead of rcu_nocb_flush_bypass() in lazy_rcu_shrink_scan(). If the nocb_bypass queue is being flushed, then rcu_nocb_try_flush_bypass will return directly.
CVE-2024-35931: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Skip do PCI error slot reset during RAS recovery Why: The PCI error slot reset maybe triggered after inject ue to UMC multi times, this caused system hang. [ 557.371857] amdgpu 0000:af:00.0: amdgpu: GPU reset succeeded, trying to resume [ 557.373718] [drm] PCIE GART of 512M enabled. [ 557.373722] [drm] PTB located at 0x0000031FED700000 [ 557.373788] [drm] VRAM is lost due to GPU reset! [ 557.373789] [drm] PSP is resuming... [ 557.547012] mlx5_core 0000:55:00.0: mlx5_pci_err_detected Device state = 1 pci_status: 0. Exit, result = 3, need reset [ 557.547067] [drm] PCI error: detected callback, state(1)!! [ 557.547069] [drm] No support for XGMI hive yet... [ 557.548125] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 0. Enter [ 557.607763] mlx5_core 0000:55:00.0: wait vital counter value 0x16b5b after 1 iterations [ 557.607777] mlx5_core 0000:55:00.0: mlx5_pci_slot_reset Device state = 1 pci_status: 1. Exit, err = 0, result = 5, recovered [ 557.610492] [drm] PCI error: slot reset callback!! ... [ 560.689382] amdgpu 0000:3f:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689546] amdgpu 0000:5a:00.0: amdgpu: GPU reset(2) succeeded! [ 560.689562] general protection fault, probably for non-canonical address 0x5f080b54534f611f: 0000 [#1] SMP NOPTI [ 560.701008] CPU: 16 PID: 2361 Comm: kworker/u448:9 Tainted: G OE 5.15.0-91-generic #101-Ubuntu [ 560.712057] Hardware name: Microsoft C278A/C278A, BIOS C2789.5.BS.1C11.AG.1 11/08/2023 [ 560.720959] Workqueue: amdgpu-reset-hive amdgpu_ras_do_recovery [amdgpu] [ 560.728887] RIP: 0010:amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.736891] Code: ff 41 89 c6 e9 1b ff ff ff 44 0f b6 45 b0 e9 4f ff ff ff be 01 00 00 00 4c 89 e7 e8 76 c9 8b ff 44 0f b6 45 b0 e9 3c fd ff ff <48> 83 ba 18 02 00 00 00 0f 84 6a f8 ff ff 48 8d 7a 78 be 01 00 00 [ 560.757967] RSP: 0018:ffa0000032e53d80 EFLAGS: 00010202 [ 560.763848] RAX: ffa00000001dfd10 RBX: ffa0000000197090 RCX: ffa0000032e53db0 [ 560.771856] RDX: 5f080b54534f5f07 RSI: 0000000000000000 RDI: ff11000128100010 [ 560.779867] RBP: ffa0000032e53df0 R08: 0000000000000000 R09: ffffffffffe77f08 [ 560.787879] R10: 0000000000ffff0a R11: 0000000000000001 R12: 0000000000000000 [ 560.795889] R13: ffa0000032e53e00 R14: 0000000000000000 R15: 0000000000000000 [ 560.803889] FS: 0000000000000000(0000) GS:ff11007e7e800000(0000) knlGS:0000000000000000 [ 560.812973] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 560.819422] CR2: 000055a04c118e68 CR3: 0000000007410005 CR4: 0000000000771ee0 [ 560.827433] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 560.835433] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [ 560.843444] PKRU: 55555554 [ 560.846480] Call Trace: [ 560.849225] <TASK> [ 560.851580] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.856488] ? show_trace_log_lvl+0x1d6/0x2ea [ 560.861379] ? amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.867778] ? show_regs.part.0+0x23/0x29 [ 560.872293] ? __die_body.cold+0x8/0xd [ 560.876502] ? die_addr+0x3e/0x60 [ 560.880238] ? exc_general_protection+0x1c5/0x410 [ 560.885532] ? asm_exc_general_protection+0x27/0x30 [ 560.891025] ? amdgpu_device_gpu_recover.cold+0xbf1/0xcf5 [amdgpu] [ 560.898323] amdgpu_ras_do_recovery+0x1b2/0x210 [amdgpu] [ 560.904520] process_one_work+0x228/0x3d0 How: In RAS recovery, mode-1 reset is issued from RAS fatal error handling and expected all the nodes in a hive to be reset. no need to issue another mode-1 during this procedure.
CVE-2024-35932: In the Linux kernel, the following vulnerability has been resolved: drm/vc4: don't check if plane->state->fb == state->fb Currently, when using non-blocking commits, we can see the following kernel warning: [ 110.908514] ------------[ cut here ]------------ [ 110.908529] refcount_t: underflow; use-after-free. [ 110.908620] WARNING: CPU: 0 PID: 1866 at lib/refcount.c:87 refcount_dec_not_one+0xb8/0xc0 [ 110.908664] Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device cmac algif_hash aes_arm64 aes_generic algif_skcipher af_alg bnep hid_logitech_hidpp vc4 brcmfmac hci_uart btbcm brcmutil bluetooth snd_soc_hdmi_codec cfg80211 cec drm_display_helper drm_dma_helper drm_kms_helper snd_soc_core snd_compress snd_pcm_dmaengine fb_sys_fops sysimgblt syscopyarea sysfillrect raspberrypi_hwmon ecdh_generic ecc rfkill libaes i2c_bcm2835 binfmt_misc joydev snd_bcm2835(C) bcm2835_codec(C) bcm2835_isp(C) v4l2_mem2mem videobuf2_dma_contig snd_pcm bcm2835_v4l2(C) raspberrypi_gpiomem bcm2835_mmal_vchiq(C) videobuf2_v4l2 snd_timer videobuf2_vmalloc videobuf2_memops videobuf2_common snd videodev vc_sm_cma(C) mc hid_logitech_dj uio_pdrv_genirq uio i2c_dev drm fuse dm_mod drm_panel_orientation_quirks backlight ip_tables x_tables ipv6 [ 110.909086] CPU: 0 PID: 1866 Comm: kodi.bin Tainted: G C 6.1.66-v8+ #32 [ 110.909104] Hardware name: Raspberry Pi 3 Model B Rev 1.2 (DT) [ 110.909114] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 110.909132] pc : refcount_dec_not_one+0xb8/0xc0 [ 110.909152] lr : refcount_dec_not_one+0xb4/0xc0 [ 110.909170] sp : ffffffc00913b9c0 [ 110.909177] x29: ffffffc00913b9c0 x28: 000000556969bbb0 x27: 000000556990df60 [ 110.909205] x26: 0000000000000002 x25: 0000000000000004 x24: ffffff8004448480 [ 110.909230] x23: ffffff800570b500 x22: ffffff802e03a7bc x21: ffffffecfca68c78 [ 110.909257] x20: ffffff8002b42000 x19: ffffff802e03a600 x18: 0000000000000000 [ 110.909283] x17: 0000000000000011 x16: ffffffffffffffff x15: 0000000000000004 [ 110.909308] x14: 0000000000000fff x13: ffffffed577e47e0 x12: 0000000000000003 [ 110.909333] x11: 0000000000000000 x10: 0000000000000027 x9 : c912d0d083728c00 [ 110.909359] x8 : c912d0d083728c00 x7 : 65646e75203a745f x6 : 746e756f63666572 [ 110.909384] x5 : ffffffed579f62ee x4 : ffffffed579eb01e x3 : 0000000000000000 [ 110.909409] x2 : 0000000000000000 x1 : ffffffc00913b750 x0 : 0000000000000001 [ 110.909434] Call trace: [ 110.909441] refcount_dec_not_one+0xb8/0xc0 [ 110.909461] vc4_bo_dec_usecnt+0x4c/0x1b0 [vc4] [ 110.909903] vc4_cleanup_fb+0x44/0x50 [vc4] [ 110.910315] drm_atomic_helper_cleanup_planes+0x88/0xa4 [drm_kms_helper] [ 110.910669] vc4_atomic_commit_tail+0x390/0x9dc [vc4] [ 110.911079] commit_tail+0xb0/0x164 [drm_kms_helper] [ 110.911397] drm_atomic_helper_commit+0x1d0/0x1f0 [drm_kms_helper] [ 110.911716] drm_atomic_commit+0xb0/0xdc [drm] [ 110.912569] drm_mode_atomic_ioctl+0x348/0x4b8 [drm] [ 110.913330] drm_ioctl_kernel+0xec/0x15c [drm] [ 110.914091] drm_ioctl+0x24c/0x3b0 [drm] [ 110.914850] __arm64_sys_ioctl+0x9c/0xd4 [ 110.914873] invoke_syscall+0x4c/0x114 [ 110.914897] el0_svc_common+0xd0/0x118 [ 110.914917] do_el0_svc+0x38/0xd0 [ 110.914936] el0_svc+0x30/0x8c [ 110.914958] el0t_64_sync_handler+0x84/0xf0 [ 110.914979] el0t_64_sync+0x18c/0x190 [ 110.914996] ---[ end trace 0000000000000000 ]--- This happens because, although `prepare_fb` and `cleanup_fb` are perfectly balanced, we cannot guarantee consistency in the check plane->state->fb == state->fb. This means that sometimes we can increase the refcount in `prepare_fb` and don't decrease it in `cleanup_fb`. The opposite can also be true. In fact, the struct drm_plane .state shouldn't be accessed directly but instead, the `drm_atomic_get_new_plane_state()` helper function should be used. So, we could stick to this check, but using `drm_atomic_get_new_plane_state()`. But actually, this check is not re ---truncated---
CVE-2024-35934: In the Linux kernel, the following vulnerability has been resolved: net/smc: reduce rtnl pressure in smc_pnet_create_pnetids_list() Many syzbot reports show extreme rtnl pressure, and many of them hint that smc acquires rtnl in netns creation for no good reason [1] This patch returns early from smc_pnet_net_init() if there is no netdevice yet. I am not even sure why smc_pnet_create_pnetids_list() even exists, because smc_pnet_netdev_event() is also calling smc_pnet_add_base_pnetid() when handling NETDEV_UP event. [1] extract of typical syzbot reports 2 locks held by syz-executor.3/12252: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.4/12253: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.1/12257: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.2/12261: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.0/12265: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.3/12268: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.4/12271: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.1/12274: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878 2 locks held by syz-executor.2/12280: #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491 #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline] #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
CVE-2024-35937: In the Linux kernel, the following vulnerability has been resolved: wifi: cfg80211: check A-MSDU format more carefully If it looks like there's another subframe in the A-MSDU but the header isn't fully there, we can end up reading data out of bounds, only to discard later. Make this a bit more careful and check if the subframe header can even be present.
CVE-2024-35938: In the Linux kernel, the following vulnerability has been resolved: wifi: ath11k: decrease MHI channel buffer length to 8KB Currently buf_len field of ath11k_mhi_config_qca6390 is assigned with 0, making MHI use a default size, 64KB, to allocate channel buffers. This is likely to fail in some scenarios where system memory is highly fragmented and memory compaction or reclaim is not allowed. There is a fail report which is caused by it: kworker/u32:45: page allocation failure: order:4, mode:0x40c00(GFP_NOIO|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 CPU: 0 PID: 19318 Comm: kworker/u32:45 Not tainted 6.8.0-rc3-1.gae4495f-default #1 openSUSE Tumbleweed (unreleased) 493b6d5b382c603654d7a81fc3c144d59a1dfceb Workqueue: events_unbound async_run_entry_fn Call Trace: <TASK> dump_stack_lvl+0x47/0x60 warn_alloc+0x13a/0x1b0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __alloc_pages_direct_compact+0xab/0x210 __alloc_pages_slowpath.constprop.0+0xd3e/0xda0 __alloc_pages+0x32d/0x350 ? mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] __kmalloc_large_node+0x72/0x110 __kmalloc+0x37c/0x480 ? mhi_map_single_no_bb+0x77/0xf0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] ? mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] mhi_prepare_channel+0x127/0x2d0 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] __mhi_prepare_for_transfer+0x44/0x80 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] ? __pfx_____mhi_prepare_for_transfer+0x10/0x10 [mhi 40df44e07c05479f7a6e7b90fba9f0e0031a7814] device_for_each_child+0x5c/0xa0 ? __pfx_pci_pm_resume+0x10/0x10 ath11k_core_resume+0x65/0x100 [ath11k a5094e22d7223135c40d93c8f5321cf09fd85e4e] ? srso_alias_return_thunk+0x5/0xfbef5 ath11k_pci_pm_resume+0x32/0x60 [ath11k_pci 830b7bfc3ea80ebef32e563cafe2cb55e9cc73ec] ? srso_alias_return_thunk+0x5/0xfbef5 dpm_run_callback+0x8c/0x1e0 device_resume+0x104/0x340 ? __pfx_dpm_watchdog_handler+0x10/0x10 async_resume+0x1d/0x30 async_run_entry_fn+0x32/0x120 process_one_work+0x168/0x330 worker_thread+0x2f5/0x410 ? __pfx_worker_thread+0x10/0x10 kthread+0xe8/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x34/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Actually those buffers are used only by QMI target -> host communication. And for WCN6855 and QCA6390, the largest packet size for that is less than 6KB. So change buf_len field to 8KB, which results in order 1 allocation if page size is 4KB. In this way, we can at least save some memory, and as well as decrease the possibility of allocation failure in those scenarios. Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
CVE-2024-35939: In the Linux kernel, the following vulnerability has been resolved: dma-direct: Leak pages on dma_set_decrypted() failure On TDX it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. DMA could free decrypted/shared pages if dma_set_decrypted() fails. This should be a rare case. Just leak the pages in this case instead of freeing them.
CVE-2024-35940: In the Linux kernel, the following vulnerability has been resolved: pstore/zone: Add a null pointer check to the psz_kmsg_read kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity.
CVE-2024-35942: In the Linux kernel, the following vulnerability has been resolved: pmdomain: imx8mp-blk-ctrl: imx8mp_blk: Add fdcc clock to hdmimix domain According to i.MX8MP RM and HDMI ADD, the fdcc clock is part of hdmi rx verification IP that should not enable for HDMI TX. But actually if the clock is disabled before HDMI/LCDIF probe, LCDIF will not get pixel clock from HDMI PHY and print the error logs: [CRTC:39:crtc-2] vblank wait timed out WARNING: CPU: 2 PID: 9 at drivers/gpu/drm/drm_atomic_helper.c:1634 drm_atomic_helper_wait_for_vblanks.part.0+0x23c/0x260 Add fdcc clock to LCDIF and HDMI TX power domains to fix the issue.
CVE-2024-35943: In the Linux kernel, the following vulnerability has been resolved: pmdomain: ti: Add a null pointer check to the omap_prm_domain_init devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity.
CVE-2024-35945: In the Linux kernel, the following vulnerability has been resolved: net: phy: phy_device: Prevent nullptr exceptions on ISR If phydev->irq is set unconditionally, check for valid interrupt handler or fall back to polling mode to prevent nullptr exceptions in interrupt service routine.
CVE-2024-35946: In the Linux kernel, the following vulnerability has been resolved: wifi: rtw89: fix null pointer access when abort scan During cancel scan we might use vif that weren't scanning. Fix this by using the actual scanning vif.
CVE-2024-35948: In the Linux kernel, the following vulnerability has been resolved: bcachefs: Check for journal entries overruning end of sb clean section Fix a missing bounds check in superblock validation. Note that we don't yet have repair code for this case - repair code for individual items is generally low priority, since the whole superblock is checksummed, validated prior to write, and we have backups.
CVE-2024-35949: In the Linux kernel, the following vulnerability has been resolved: btrfs: make sure that WRITTEN is set on all metadata blocks We previously would call btrfs_check_leaf() if we had the check integrity code enabled, which meant that we could only run the extended leaf checks if we had WRITTEN set on the header flags. This leaves a gap in our checking, because we could end up with corruption on disk where WRITTEN isn't set on the leaf, and then the extended leaf checks don't get run which we rely on to validate all of the item pointers to make sure we don't access memory outside of the extent buffer. However, since 732fab95abe2 ("btrfs: check-integrity: remove CONFIG_BTRFS_FS_CHECK_INTEGRITY option") we no longer call btrfs_check_leaf() from btrfs_mark_buffer_dirty(), which means we only ever call it on blocks that are being written out, and thus have WRITTEN set, or that are being read in, which should have WRITTEN set. Add checks to make sure we have WRITTEN set appropriately, and then make sure __btrfs_check_leaf() always does the item checking. This will protect us from file systems that have been corrupted and no longer have WRITTEN set on some of the blocks. This was hit on a crafted image tweaking the WRITTEN bit and reported by KASAN as out-of-bound access in the eb accessors. The example is a dir item at the end of an eb. [2.042] BTRFS warning (device loop1): bad eb member start: ptr 0x3fff start 30572544 member offset 16410 size 2 [2.040] general protection fault, probably for non-canonical address 0xe0009d1000000003: 0000 [#1] PREEMPT SMP KASAN NOPTI [2.537] KASAN: maybe wild-memory-access in range [0x0005088000000018-0x000508800000001f] [2.729] CPU: 0 PID: 2587 Comm: mount Not tainted 6.8.2 #1 [2.729] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [2.621] RIP: 0010:btrfs_get_16+0x34b/0x6d0 [2.621] RSP: 0018:ffff88810871fab8 EFLAGS: 00000206 [2.621] RAX: 0000a11000000003 RBX: ffff888104ff8720 RCX: ffff88811b2288c0 [2.621] RDX: dffffc0000000000 RSI: ffffffff81dd8aca RDI: ffff88810871f748 [2.621] RBP: 000000000000401a R08: 0000000000000001 R09: ffffed10210e3ee9 [2.621] R10: ffff88810871f74f R11: 205d323430333737 R12: 000000000000001a [2.621] R13: 000508800000001a R14: 1ffff110210e3f5d R15: ffffffff850011e8 [2.621] FS: 00007f56ea275840(0000) GS:ffff88811b200000(0000) knlGS:0000000000000000 [2.621] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [2.621] CR2: 00007febd13b75c0 CR3: 000000010bb50000 CR4: 00000000000006f0 [2.621] Call Trace: [2.621] <TASK> [2.621] ? show_regs+0x74/0x80 [2.621] ? die_addr+0x46/0xc0 [2.621] ? exc_general_protection+0x161/0x2a0 [2.621] ? asm_exc_general_protection+0x26/0x30 [2.621] ? btrfs_get_16+0x33a/0x6d0 [2.621] ? btrfs_get_16+0x34b/0x6d0 [2.621] ? btrfs_get_16+0x33a/0x6d0 [2.621] ? __pfx_btrfs_get_16+0x10/0x10 [2.621] ? __pfx_mutex_unlock+0x10/0x10 [2.621] btrfs_match_dir_item_name+0x101/0x1a0 [2.621] btrfs_lookup_dir_item+0x1f3/0x280 [2.621] ? __pfx_btrfs_lookup_dir_item+0x10/0x10 [2.621] btrfs_get_tree+0xd25/0x1910 [ copy more details from report ]
CVE-2024-35950: In the Linux kernel, the following vulnerability has been resolved: drm/client: Fully protect modes[] with dev->mode_config.mutex The modes[] array contains pointers to modes on the connectors' mode lists, which are protected by dev->mode_config.mutex. Thus we need to extend modes[] the same protection or by the time we use it the elements may already be pointing to freed/reused memory.
CVE-2024-35965: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix not validating setsockopt user input Check user input length before copying data.
CVE-2024-35966: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: RFCOMM: Fix not validating setsockopt user input syzbot reported rfcomm_sock_setsockopt_old() is copying data without checking user input length. BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in rfcomm_sock_setsockopt_old net/bluetooth/rfcomm/sock.c:632 [inline] BUG: KASAN: slab-out-of-bounds in rfcomm_sock_setsockopt+0x893/0xa70 net/bluetooth/rfcomm/sock.c:673 Read of size 4 at addr ffff8880209a8bc3 by task syz-executor632/5064
CVE-2024-35967: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix not validating setsockopt user input syzbot reported sco_sock_setsockopt() is copying data without checking user input length. BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in sco_sock_setsockopt+0xc0b/0xf90 net/bluetooth/sco.c:893 Read of size 4 at addr ffff88805f7b15a3 by task syz-executor.5/12578
CVE-2024-35976: In the Linux kernel, the following vulnerability has been resolved: xsk: validate user input for XDP_{UMEM|COMPLETION}_FILL_RING syzbot reported an illegal copy in xsk_setsockopt() [1] Make sure to validate setsockopt() @optlen parameter. [1] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in xsk_setsockopt+0x909/0xa40 net/xdp/xsk.c:1420 Read of size 4 at addr ffff888028c6cde3 by task syz-executor.0/7549 CPU: 0 PID: 7549 Comm: syz-executor.0 Not tainted 6.8.0-syzkaller-08951-gfe46a7dd189e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] copy_from_sockptr include/linux/sockptr.h:55 [inline] xsk_setsockopt+0x909/0xa40 net/xdp/xsk.c:1420 do_sock_setsockopt+0x3af/0x720 net/socket.c:2311 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x6d/0x75 RIP: 0033:0x7fb40587de69 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb40665a0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00007fb4059abf80 RCX: 00007fb40587de69 RDX: 0000000000000005 RSI: 000000000000011b RDI: 0000000000000006 RBP: 00007fb4058ca47a R08: 0000000000000002 R09: 0000000000000000 R10: 0000000020001980 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fb4059abf80 R15: 00007fff57ee4d08 </TASK> Allocated by task 7549: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 poison_kmalloc_redzone mm/kasan/common.c:370 [inline] __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387 kasan_kmalloc include/linux/kasan.h:211 [inline] __do_kmalloc_node mm/slub.c:3966 [inline] __kmalloc+0x233/0x4a0 mm/slub.c:3979 kmalloc include/linux/slab.h:632 [inline] __cgroup_bpf_run_filter_setsockopt+0xd2f/0x1040 kernel/bpf/cgroup.c:1869 do_sock_setsockopt+0x6b4/0x720 net/socket.c:2293 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfb/0x240 entry_SYSCALL_64_after_hwframe+0x6d/0x75 The buggy address belongs to the object at ffff888028c6cde0 which belongs to the cache kmalloc-8 of size 8 The buggy address is located 1 bytes to the right of allocated 2-byte region [ffff888028c6cde0, ffff888028c6cde2) The buggy address belongs to the physical page: page:ffffea0000a31b00 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888028c6c9c0 pfn:0x28c6c anon flags: 0xfff00000000800(slab|node=0|zone=1|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 00fff00000000800 ffff888014c41280 0000000000000000 dead000000000001 raw: ffff888028c6c9c0 0000000080800057 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112cc0(GFP_USER|__GFP_NOWARN|__GFP_NORETRY), pid 6648, tgid 6644 (syz-executor.0), ts 133906047828, free_ts 133859922223 set_page_owner include/linux/page_owner.h:31 [inline] post_alloc_hook+0x1ea/0x210 mm/page_alloc.c:1533 prep_new_page mm/page_alloc.c: ---truncated---
CVE-2024-35995: In the Linux kernel, the following vulnerability has been resolved: ACPI: CPPC: Use access_width over bit_width for system memory accesses To align with ACPI 6.3+, since bit_width can be any 8-bit value, it cannot be depended on to be always on a clean 8b boundary. This was uncovered on the Cobalt 100 platform. SError Interrupt on CPU26, code 0xbe000011 -- SError CPU: 26 PID: 1510 Comm: systemd-udevd Not tainted 5.15.2.1-13 #1 Hardware name: MICROSOFT CORPORATION, BIOS MICROSOFT CORPORATION pstate: 62400009 (nZCv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--) pc : cppc_get_perf_caps+0xec/0x410 lr : cppc_get_perf_caps+0xe8/0x410 sp : ffff8000155ab730 x29: ffff8000155ab730 x28: ffff0080139d0038 x27: ffff0080139d0078 x26: 0000000000000000 x25: ffff0080139d0058 x24: 00000000ffffffff x23: ffff0080139d0298 x22: ffff0080139d0278 x21: 0000000000000000 x20: ffff00802b251910 x19: ffff0080139d0000 x18: ffffffffffffffff x17: 0000000000000000 x16: ffffdc7e111bad04 x15: ffff00802b251008 x14: ffffffffffffffff x13: ffff013f1fd63300 x12: 0000000000000006 x11: ffffdc7e128f4420 x10: 0000000000000000 x9 : ffffdc7e111badec x8 : ffff00802b251980 x7 : 0000000000000000 x6 : ffff0080139d0028 x5 : 0000000000000000 x4 : ffff0080139d0018 x3 : 00000000ffffffff x2 : 0000000000000008 x1 : ffff8000155ab7a0 x0 : 0000000000000000 Kernel panic - not syncing: Asynchronous SError Interrupt CPU: 26 PID: 1510 Comm: systemd-udevd Not tainted 5.15.2.1-13 #1 Hardware name: MICROSOFT CORPORATION, BIOS MICROSOFT CORPORATION Call trace: dump_backtrace+0x0/0x1e0 show_stack+0x24/0x30 dump_stack_lvl+0x8c/0xb8 dump_stack+0x18/0x34 panic+0x16c/0x384 add_taint+0x0/0xc0 arm64_serror_panic+0x7c/0x90 arm64_is_fatal_ras_serror+0x34/0xa4 do_serror+0x50/0x6c el1h_64_error_handler+0x40/0x74 el1h_64_error+0x7c/0x80 cppc_get_perf_caps+0xec/0x410 cppc_cpufreq_cpu_init+0x74/0x400 [cppc_cpufreq] cpufreq_online+0x2dc/0xa30 cpufreq_add_dev+0xc0/0xd4 subsys_interface_register+0x134/0x14c cpufreq_register_driver+0x1b0/0x354 cppc_cpufreq_init+0x1a8/0x1000 [cppc_cpufreq] do_one_initcall+0x50/0x250 do_init_module+0x60/0x27c load_module+0x2300/0x2570 __do_sys_finit_module+0xa8/0x114 __arm64_sys_finit_module+0x2c/0x3c invoke_syscall+0x78/0x100 el0_svc_common.constprop.0+0x180/0x1a0 do_el0_svc+0x84/0xa0 el0_svc+0x2c/0xc0 el0t_64_sync_handler+0xa4/0x12c el0t_64_sync+0x1a4/0x1a8 Instead, use access_width to determine the size and use the offset and width to shift and mask the bits to read/write out. Make sure to add a check for system memory since pcc redefines the access_width to subspace id. If access_width is not set, then fall back to using bit_width. [ rjw: Subject and changelog edits, comment adjustments ]
CVE-2024-35998: In the Linux kernel, the following vulnerability has been resolved: smb3: fix lock ordering potential deadlock in cifs_sync_mid_result Coverity spotted that the cifs_sync_mid_result function could deadlock "Thread deadlock (ORDER_REVERSAL) lock_order: Calling spin_lock acquires lock TCP_Server_Info.srv_lock while holding lock TCP_Server_Info.mid_lock" Addresses-Coverity: 1590401 ("Thread deadlock (ORDER_REVERSAL)")
CVE-2024-35999: In the Linux kernel, the following vulnerability has been resolved: smb3: missing lock when picking channel Coverity spotted a place where we should have been holding the channel lock when accessing the ses channel index. Addresses-Coverity: 1582039 ("Data race condition (MISSING_LOCK)")
CVE-2024-36009: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix netdev refcount issue The dev_tracker is added to ax25_cb in ax25_bind(). When the ax25 device is detaching, the dev_tracker of ax25_cb should be deallocated in ax25_kill_by_device() instead of the dev_tracker of ax25_dev. The log reported by ref_tracker is shown below: [ 80.884935] ref_tracker: reference already released. [ 80.885150] ref_tracker: allocated in: [ 80.885349] ax25_dev_device_up+0x105/0x540 [ 80.885730] ax25_device_event+0xa4/0x420 [ 80.885730] notifier_call_chain+0xc9/0x1e0 [ 80.885730] __dev_notify_flags+0x138/0x280 [ 80.885730] dev_change_flags+0xd7/0x180 [ 80.885730] dev_ifsioc+0x6a9/0xa30 [ 80.885730] dev_ioctl+0x4d8/0xd90 [ 80.885730] sock_do_ioctl+0x1c2/0x2d0 [ 80.885730] sock_ioctl+0x38b/0x4f0 [ 80.885730] __se_sys_ioctl+0xad/0xf0 [ 80.885730] do_syscall_64+0xc4/0x1b0 [ 80.885730] entry_SYSCALL_64_after_hwframe+0x67/0x6f [ 80.885730] ref_tracker: freed in: [ 80.885730] ax25_device_event+0x272/0x420 [ 80.885730] notifier_call_chain+0xc9/0x1e0 [ 80.885730] dev_close_many+0x272/0x370 [ 80.885730] unregister_netdevice_many_notify+0x3b5/0x1180 [ 80.885730] unregister_netdev+0xcf/0x120 [ 80.885730] sixpack_close+0x11f/0x1b0 [ 80.885730] tty_ldisc_kill+0xcb/0x190 [ 80.885730] tty_ldisc_hangup+0x338/0x3d0 [ 80.885730] __tty_hangup+0x504/0x740 [ 80.885730] tty_release+0x46e/0xd80 [ 80.885730] __fput+0x37f/0x770 [ 80.885730] __x64_sys_close+0x7b/0xb0 [ 80.885730] do_syscall_64+0xc4/0x1b0 [ 80.885730] entry_SYSCALL_64_after_hwframe+0x67/0x6f [ 80.893739] ------------[ cut here ]------------ [ 80.894030] WARNING: CPU: 2 PID: 140 at lib/ref_tracker.c:255 ref_tracker_free+0x47b/0x6b0 [ 80.894297] Modules linked in: [ 80.894929] CPU: 2 PID: 140 Comm: ax25_conn_rel_6 Not tainted 6.9.0-rc4-g8cd26fd90c1a #11 [ 80.895190] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qem4 [ 80.895514] RIP: 0010:ref_tracker_free+0x47b/0x6b0 [ 80.895808] Code: 83 c5 18 4c 89 eb 48 c1 eb 03 8a 04 13 84 c0 0f 85 df 01 00 00 41 83 7d 00 00 75 4b 4c 89 ff 9 [ 80.896171] RSP: 0018:ffff888009edf8c0 EFLAGS: 00000286 [ 80.896339] RAX: 1ffff1100141ac00 RBX: 1ffff1100149463b RCX: dffffc0000000000 [ 80.896502] RDX: 0000000000000001 RSI: 0000000000000246 RDI: ffff88800a0d6518 [ 80.896925] RBP: ffff888009edf9b0 R08: ffff88806d3288d3 R09: 1ffff1100da6511a [ 80.897212] R10: dffffc0000000000 R11: ffffed100da6511b R12: ffff88800a4a31d4 [ 80.897859] R13: ffff88800a4a31d8 R14: dffffc0000000000 R15: ffff88800a0d6518 [ 80.898279] FS: 00007fd88b7fe700(0000) GS:ffff88806d300000(0000) knlGS:0000000000000000 [ 80.899436] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 80.900181] CR2: 00007fd88c001d48 CR3: 000000000993e000 CR4: 00000000000006f0 ... [ 80.935774] ref_tracker: sp%d@000000000bb9df3d has 1/1 users at [ 80.935774] ax25_bind+0x424/0x4e0 [ 80.935774] __sys_bind+0x1d9/0x270 [ 80.935774] __x64_sys_bind+0x75/0x80 [ 80.935774] do_syscall_64+0xc4/0x1b0 [ 80.935774] entry_SYSCALL_64_after_hwframe+0x67/0x6f Change ax25_dev->dev_tracker to the dev_tracker of ax25_cb in order to mitigate the bug.
CVE-2024-36013: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix slab-use-after-free in l2cap_connect() Extend a critical section to prevent chan from early freeing. Also make the l2cap_connect() return type void. Nothing is using the returned value but it is ugly to return a potentially freed pointer. Making it void will help with backports because earlier kernels did use the return value. Now the compile will break for kernels where this patch is not a complete fix. Call stack summary: [use] l2cap_bredr_sig_cmd l2cap_connect ┌ mutex_lock(&conn->chan_lock); │ chan = pchan->ops->new_connection(pchan); <- alloc chan │ __l2cap_chan_add(conn, chan); │ l2cap_chan_hold(chan); │ list_add(&chan->list, &conn->chan_l); ... (1) └ mutex_unlock(&conn->chan_lock); chan->conf_state ... (4) <- use after free [free] l2cap_conn_del ┌ mutex_lock(&conn->chan_lock); │ foreach chan in conn->chan_l: ... (2) │ l2cap_chan_put(chan); │ l2cap_chan_destroy │ kfree(chan) ... (3) <- chan freed └ mutex_unlock(&conn->chan_lock); ================================================================== BUG: KASAN: slab-use-after-free in instrument_atomic_read include/linux/instrumented.h:68 [inline] BUG: KASAN: slab-use-after-free in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline] BUG: KASAN: slab-use-after-free in l2cap_connect+0xa67/0x11a0 net/bluetooth/l2cap_core.c:4260 Read of size 8 at addr ffff88810bf040a0 by task kworker/u3:1/311
CVE-2024-36022: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Init zone device and drm client after mode-1 reset on reload In passthrough environment, when amdgpu is reloaded after unload, mode-1 is triggered after initializing the necessary IPs, That init does not include KFD, and KFD init waits until the reset is completed. KFD init is called in the reset handler, but in this case, the zone device and drm client is not initialized, causing app to create kernel panic. v2: Removing the init KFD condition from amdgpu_amdkfd_drm_client_create. As the previous version has the potential of creating DRM client twice. v3: v2 patch results in SDMA engine hung as DRM open causes VM clear to SDMA before SDMA init. Adding the condition to in drm client creation, on top of v1, to guard against drm client creation call multiple times.
CVE-2024-36023: In the Linux kernel, the following vulnerability has been resolved: Julia Lawall reported this null pointer dereference, this should fix it.
CVE-2024-36024: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Disable idle reallow as part of command/gpint execution [Why] Workaroud for a race condition where DMCUB is in the process of committing to IPS1 during the handshake causing us to miss the transition into IPS2 and touch the INBOX1 RPTR causing a HW hang. [How] Disable the reallow to ensure that we have enough of a gap between entry and exit and we're not seeing back-to-back wake_and_executes.
CVE-2024-36026: In the Linux kernel, the following vulnerability has been resolved: drm/amd/pm: fixes a random hang in S4 for SMU v13.0.4/11 While doing multiple S4 stress tests, GC/RLC/PMFW get into an invalid state resulting into hard hangs. Adding a GFX reset as workaround just before sending the MP1_UNLOAD message avoids this failure.
CVE-2024-36029: In the Linux kernel, the following vulnerability has been resolved: mmc: sdhci-msm: pervent access to suspended controller Generic sdhci code registers LED device and uses host->runtime_suspended flag to protect access to it. The sdhci-msm driver doesn't set this flag, which causes a crash when LED is accessed while controller is runtime suspended. Fix this by setting the flag correctly.
CVE-2024-36270: In the Linux kernel, the following vulnerability has been resolved: netfilter: tproxy: bail out if IP has been disabled on the device syzbot reports: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] [..] RIP: 0010:nf_tproxy_laddr4+0xb7/0x340 net/ipv4/netfilter/nf_tproxy_ipv4.c:62 Call Trace: nft_tproxy_eval_v4 net/netfilter/nft_tproxy.c:56 [inline] nft_tproxy_eval+0xa9a/0x1a00 net/netfilter/nft_tproxy.c:168 __in_dev_get_rcu() can return NULL, so check for this.
CVE-2024-36479: In the Linux kernel, the following vulnerability has been resolved: fpga: bridge: add owner module and take its refcount The current implementation of the fpga bridge assumes that the low-level module registers a driver for the parent device and uses its owner pointer to take the module's refcount. This approach is problematic since it can lead to a null pointer dereference while attempting to get the bridge if the parent device does not have a driver. To address this problem, add a module owner pointer to the fpga_bridge struct and use it to take the module's refcount. Modify the function for registering a bridge to take an additional owner module parameter and rename it to avoid conflicts. Use the old function name for a helper macro that automatically sets the module that registers the bridge as the owner. This ensures compatibility with existing low-level control modules and reduces the chances of registering a bridge without setting the owner. Also, update the documentation to keep it consistent with the new interface for registering an fpga bridge. Other changes: opportunistically move put_device() from __fpga_bridge_get() to fpga_bridge_get() and of_fpga_bridge_get() to improve code clarity since the bridge device is taken in these functions.
CVE-2024-36484: In the Linux kernel, the following vulnerability has been resolved: net: relax socket state check at accept time. Christoph reported the following splat: WARNING: CPU: 1 PID: 772 at net/ipv4/af_inet.c:761 __inet_accept+0x1f4/0x4a0 Modules linked in: CPU: 1 PID: 772 Comm: syz-executor510 Not tainted 6.9.0-rc7-g7da7119fe22b #56 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:__inet_accept+0x1f4/0x4a0 net/ipv4/af_inet.c:759 Code: 04 38 84 c0 0f 85 87 00 00 00 41 c7 04 24 03 00 00 00 48 83 c4 10 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 ec b7 da fd <0f> 0b e9 7f fe ff ff e8 e0 b7 da fd 0f 0b e9 fe fe ff ff 89 d9 80 RSP: 0018:ffffc90000c2fc58 EFLAGS: 00010293 RAX: ffffffff836bdd14 RBX: 0000000000000000 RCX: ffff888104668000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff836bdb89 R09: fffff52000185f64 R10: dffffc0000000000 R11: fffff52000185f64 R12: dffffc0000000000 R13: 1ffff92000185f98 R14: ffff88810754d880 R15: ffff8881007b7800 FS: 000000001c772880(0000) GS:ffff88811b280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fb9fcf2e178 CR3: 00000001045d2002 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_accept+0x138/0x1d0 net/ipv4/af_inet.c:786 do_accept+0x435/0x620 net/socket.c:1929 __sys_accept4_file net/socket.c:1969 [inline] __sys_accept4+0x9b/0x110 net/socket.c:1999 __do_sys_accept net/socket.c:2016 [inline] __se_sys_accept net/socket.c:2013 [inline] __x64_sys_accept+0x7d/0x90 net/socket.c:2013 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x58/0x100 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x4315f9 Code: fd ff 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 ab b4 fd ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffdb26d9c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002b RAX: ffffffffffffffda RBX: 0000000000400300 RCX: 00000000004315f9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00000000006e1018 R08: 0000000000400300 R09: 0000000000400300 R10: 0000000000400300 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000040cdf0 R14: 000000000040ce80 R15: 0000000000000055 </TASK> The reproducer invokes shutdown() before entering the listener status. After commit 94062790aedb ("tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets"), the above causes the child to reach the accept syscall in FIN_WAIT1 status. Eric noted we can relax the existing assertion in __inet_accept()
CVE-2024-36880: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: qca: add missing firmware sanity checks Add the missing sanity checks when parsing the firmware files before downloading them to avoid accessing and corrupting memory beyond the vmalloced buffer.
CVE-2024-36885: In the Linux kernel, the following vulnerability has been resolved: drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor() Currently, enabling SG_DEBUG in the kernel will cause nouveau to hit a BUG() on startup: kernel BUG at include/linux/scatterlist.h:187! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 7 PID: 930 Comm: (udev-worker) Not tainted 6.9.0-rc3Lyude-Test+ #30 Hardware name: MSI MS-7A39/A320M GAMING PRO (MS-7A39), BIOS 1.I0 01/22/2019 RIP: 0010:sg_init_one+0x85/0xa0 Code: 69 88 32 01 83 e1 03 f6 c3 03 75 20 a8 01 75 1e 48 09 cb 41 89 54 24 08 49 89 1c 24 41 89 6c 24 0c 5b 5d 41 5c e9 7b b9 88 00 <0f> 0b 0f 0b 0f 0b 48 8b 05 5e 46 9a 01 eb b2 66 66 2e 0f 1f 84 00 RSP: 0018:ffffa776017bf6a0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa77600d87000 RCX: 000000000000002b RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffa77680d87000 RBP: 000000000000e000 R08: 0000000000000000 R09: 0000000000000000 R10: ffff98f4c46aa508 R11: 0000000000000000 R12: ffff98f4c46aa508 R13: ffff98f4c46aa008 R14: ffffa77600d4a000 R15: ffffa77600d4a018 FS: 00007feeb5aae980(0000) GS:ffff98f5c4dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f22cb9a4520 CR3: 00000001043ba000 CR4: 00000000003506f0 Call Trace: <TASK> ? die+0x36/0x90 ? do_trap+0xdd/0x100 ? sg_init_one+0x85/0xa0 ? do_error_trap+0x65/0x80 ? sg_init_one+0x85/0xa0 ? exc_invalid_op+0x50/0x70 ? sg_init_one+0x85/0xa0 ? asm_exc_invalid_op+0x1a/0x20 ? sg_init_one+0x85/0xa0 nvkm_firmware_ctor+0x14a/0x250 [nouveau] nvkm_falcon_fw_ctor+0x42/0x70 [nouveau] ga102_gsp_booter_ctor+0xb4/0x1a0 [nouveau] r535_gsp_oneinit+0xb3/0x15f0 [nouveau] ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f ? nvkm_udevice_new+0x95/0x140 [nouveau] ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f ? ktime_get+0x47/0xb0 ? srso_return_thunk+0x5/0x5f nvkm_subdev_oneinit_+0x4f/0x120 [nouveau] nvkm_subdev_init_+0x39/0x140 [nouveau] ? srso_return_thunk+0x5/0x5f nvkm_subdev_init+0x44/0x90 [nouveau] nvkm_device_init+0x166/0x2e0 [nouveau] nvkm_udevice_init+0x47/0x70 [nouveau] nvkm_object_init+0x41/0x1c0 [nouveau] nvkm_ioctl_new+0x16a/0x290 [nouveau] ? __pfx_nvkm_client_child_new+0x10/0x10 [nouveau] ? __pfx_nvkm_udevice_new+0x10/0x10 [nouveau] nvkm_ioctl+0x126/0x290 [nouveau] nvif_object_ctor+0x112/0x190 [nouveau] nvif_device_ctor+0x23/0x60 [nouveau] nouveau_cli_init+0x164/0x640 [nouveau] nouveau_drm_device_init+0x97/0x9e0 [nouveau] ? srso_return_thunk+0x5/0x5f ? pci_update_current_state+0x72/0xb0 ? srso_return_thunk+0x5/0x5f nouveau_drm_probe+0x12c/0x280 [nouveau] ? srso_return_thunk+0x5/0x5f local_pci_probe+0x45/0xa0 pci_device_probe+0xc7/0x270 really_probe+0xe6/0x3a0 __driver_probe_device+0x87/0x160 driver_probe_device+0x1f/0xc0 __driver_attach+0xec/0x1f0 ? __pfx___driver_attach+0x10/0x10 bus_for_each_dev+0x88/0xd0 bus_add_driver+0x116/0x220 driver_register+0x59/0x100 ? __pfx_nouveau_drm_init+0x10/0x10 [nouveau] do_one_initcall+0x5b/0x320 do_init_module+0x60/0x250 init_module_from_file+0x86/0xc0 idempotent_init_module+0x120/0x2b0 __x64_sys_finit_module+0x5e/0xb0 do_syscall_64+0x83/0x160 ? srso_return_thunk+0x5/0x5f entry_SYSCALL_64_after_hwframe+0x71/0x79 RIP: 0033:0x7feeb5cc20cd Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1b cd 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffcf220b2c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000055fdd2916aa0 RCX: 00007feeb5cc20cd RDX: 0000000000000000 RSI: 000055fdd29161e0 RDI: 0000000000000035 RBP: 00007ffcf220b380 R08: 00007feeb5d8fb20 R09: 00007ffcf220b310 R10: 000055fdd2909dc0 R11: 0000000000000246 R12: 000055 ---truncated---
CVE-2024-36894: In the Linux kernel, the following vulnerability has been resolved: usb: gadget: f_fs: Fix race between aio_cancel() and AIO request complete FFS based applications can utilize the aio_cancel() callback to dequeue pending USB requests submitted to the UDC. There is a scenario where the FFS application issues an AIO cancel call, while the UDC is handling a soft disconnect. For a DWC3 based implementation, the callstack looks like the following: DWC3 Gadget FFS Application dwc3_gadget_soft_disconnect() ... --> dwc3_stop_active_transfers() --> dwc3_gadget_giveback(-ESHUTDOWN) --> ffs_epfile_async_io_complete() ffs_aio_cancel() --> usb_ep_free_request() --> usb_ep_dequeue() There is currently no locking implemented between the AIO completion handler and AIO cancel, so the issue occurs if the completion routine is running in parallel to an AIO cancel call coming from the FFS application. As the completion call frees the USB request (io_data->req) the FFS application is also referencing it for the usb_ep_dequeue() call. This can lead to accessing a stale/hanging pointer. commit b566d38857fc ("usb: gadget: f_fs: use io_data->status consistently") relocated the usb_ep_free_request() into ffs_epfile_async_io_complete(). However, in order to properly implement locking to mitigate this issue, the spinlock can't be added to ffs_epfile_async_io_complete(), as usb_ep_dequeue() (if successfully dequeuing a USB request) will call the function driver's completion handler in the same context. Hence, leading into a deadlock. Fix this issue by moving the usb_ep_free_request() back to ffs_user_copy_worker(), and ensuring that it explicitly sets io_data->req to NULL after freeing it within the ffs->eps_lock. This resolves the race condition above, as the ffs_aio_cancel() routine will not continue attempting to dequeue a request that has already been freed, or the ffs_user_copy_work() not freeing the USB request until the AIO cancel is done referencing it. This fix depends on commit b566d38857fc ("usb: gadget: f_fs: use io_data->status consistently")
CVE-2024-36897: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Atom Integrated System Info v2_2 for DCN35 New request from KMD/VBIOS in order to support new UMA carveout model. This fixes a null dereference from accessing Ctx->dc_bios->integrated_info while it was NULL. DAL parses through the BIOS and extracts the necessary integrated_info but was missing a case for the new BIOS version 2.3.
CVE-2024-36901: In the Linux kernel, the following vulnerability has been resolved: ipv6: prevent NULL dereference in ip6_output() According to syzbot, there is a chance that ip6_dst_idev() returns NULL in ip6_output(). Most places in IPv6 stack deal with a NULL idev just fine, but not here. syzbot reported: general protection fault, probably for non-canonical address 0xdffffc00000000bc: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x00000000000005e0-0x00000000000005e7] CPU: 0 PID: 9775 Comm: syz-executor.4 Not tainted 6.9.0-rc5-syzkaller-00157-g6a30653b604a #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 RIP: 0010:ip6_output+0x231/0x3f0 net/ipv6/ip6_output.c:237 Code: 3c 1e 00 49 89 df 74 08 4c 89 ef e8 19 58 db f7 48 8b 44 24 20 49 89 45 00 49 89 c5 48 8d 9d e0 05 00 00 48 89 d8 48 c1 e8 03 <42> 0f b6 04 38 84 c0 4c 8b 74 24 28 0f 85 61 01 00 00 8b 1b 31 ff RSP: 0018:ffffc9000927f0d8 EFLAGS: 00010202 RAX: 00000000000000bc RBX: 00000000000005e0 RCX: 0000000000040000 RDX: ffffc900131f9000 RSI: 0000000000004f47 RDI: 0000000000004f48 RBP: 0000000000000000 R08: ffffffff8a1f0b9a R09: 1ffffffff1f51fad R10: dffffc0000000000 R11: fffffbfff1f51fae R12: ffff8880293ec8c0 R13: ffff88805d7fc000 R14: 1ffff1100527d91a R15: dffffc0000000000 FS: 00007f135c6856c0(0000) GS:ffff8880b9400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000080 CR3: 0000000064096000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> NF_HOOK include/linux/netfilter.h:314 [inline] ip6_xmit+0xefe/0x17f0 net/ipv6/ip6_output.c:358 sctp_v6_xmit+0x9f2/0x13f0 net/sctp/ipv6.c:248 sctp_packet_transmit+0x26ad/0x2ca0 net/sctp/output.c:653 sctp_packet_singleton+0x22c/0x320 net/sctp/outqueue.c:783 sctp_outq_flush_ctrl net/sctp/outqueue.c:914 [inline] sctp_outq_flush+0x6d5/0x3e20 net/sctp/outqueue.c:1212 sctp_side_effects net/sctp/sm_sideeffect.c:1198 [inline] sctp_do_sm+0x59cc/0x60c0 net/sctp/sm_sideeffect.c:1169 sctp_primitive_ASSOCIATE+0x95/0xc0 net/sctp/primitive.c:73 __sctp_connect+0x9cd/0xe30 net/sctp/socket.c:1234 sctp_connect net/sctp/socket.c:4819 [inline] sctp_inet_connect+0x149/0x1f0 net/sctp/socket.c:4834 __sys_connect_file net/socket.c:2048 [inline] __sys_connect+0x2df/0x310 net/socket.c:2065 __do_sys_connect net/socket.c:2075 [inline] __se_sys_connect net/socket.c:2072 [inline] __x64_sys_connect+0x7a/0x90 net/socket.c:2072 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
CVE-2024-36903: In the Linux kernel, the following vulnerability has been resolved: ipv6: Fix potential uninit-value access in __ip6_make_skb() As it was done in commit fc1092f51567 ("ipv4: Fix uninit-value access in __ip_make_skb()") for IPv4, check FLOWI_FLAG_KNOWN_NH on fl6->flowi6_flags instead of testing HDRINCL on the socket to avoid a race condition which causes uninit-value access.
CVE-2024-36908: In the Linux kernel, the following vulnerability has been resolved: blk-iocost: do not WARN if iocg was already offlined In iocg_pay_debt(), warn is triggered if 'active_list' is empty, which is intended to confirm iocg is active when it has debt. However, warn can be triggered during a blkcg or disk removal, if iocg_waitq_timer_fn() is run at that time: WARNING: CPU: 0 PID: 2344971 at block/blk-iocost.c:1402 iocg_pay_debt+0x14c/0x190 Call trace: iocg_pay_debt+0x14c/0x190 iocg_kick_waitq+0x438/0x4c0 iocg_waitq_timer_fn+0xd8/0x130 __run_hrtimer+0x144/0x45c __hrtimer_run_queues+0x16c/0x244 hrtimer_interrupt+0x2cc/0x7b0 The warn in this situation is meaningless. Since this iocg is being removed, the state of the 'active_list' is irrelevant, and 'waitq_timer' is canceled after removing 'active_list' in ioc_pd_free(), which ensures iocg is freed after iocg_waitq_timer_fn() returns. Therefore, add the check if iocg was already offlined to avoid warn when removing a blkcg or disk.
CVE-2024-36909: In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Don't free ring buffers that couldn't be re-encrypted In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. The VMBus ring buffer code could free decrypted/shared pages if set_memory_decrypted() fails. Check the decrypted field in the struct vmbus_gpadl for the ring buffers to decide whether to free the memory.
CVE-2024-36910: In the Linux kernel, the following vulnerability has been resolved: uio_hv_generic: Don't free decrypted memory In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. The VMBus device UIO driver could free decrypted/shared pages if set_memory_decrypted() fails. Check the decrypted field in the gpadl to decide whether to free the memory.
CVE-2024-36911: In the Linux kernel, the following vulnerability has been resolved: hv_netvsc: Don't free decrypted memory In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. The netvsc driver could free decrypted/shared pages if set_memory_decrypted() fails. Check the decrypted field in the gpadl to decide whether to free the memory.
CVE-2024-36912: In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Track decrypted status in vmbus_gpadl In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. In order to make sure callers of vmbus_establish_gpadl() and vmbus_teardown_gpadl() don't return decrypted/shared pages to allocators, add a field in struct vmbus_gpadl to keep track of the decryption status of the buffers. This will allow the callers to know if they should free or leak the pages.
CVE-2024-36913: In the Linux kernel, the following vulnerability has been resolved: Drivers: hv: vmbus: Leak pages if set_memory_encrypted() fails In CoCo VMs it is possible for the untrusted host to cause set_memory_encrypted() or set_memory_decrypted() to fail such that an error is returned and the resulting memory is shared. Callers need to take care to handle these errors to avoid returning decrypted (shared) memory to the page allocator, which could lead to functional or security issues. VMBus code could free decrypted pages if set_memory_encrypted()/decrypted() fails. Leak the pages if this happens.
CVE-2024-36914: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Skip on writeback when it's not applicable [WHY] dynamic memory safety error detector (KASAN) catches and generates error messages "BUG: KASAN: slab-out-of-bounds" as writeback connector does not support certain features which are not initialized. [HOW] Skip them when connector type is DRM_MODE_CONNECTOR_WRITEBACK.
CVE-2024-36915: In the Linux kernel, the following vulnerability has been resolved: nfc: llcp: fix nfc_llcp_setsockopt() unsafe copies syzbot reported unsafe calls to copy_from_sockptr() [1] Use copy_safe_from_sockptr() instead. [1] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline] BUG: KASAN: slab-out-of-bounds in nfc_llcp_setsockopt+0x6c2/0x850 net/nfc/llcp_sock.c:255 Read of size 4 at addr ffff88801caa1ec3 by task syz-executor459/5078 CPU: 0 PID: 5078 Comm: syz-executor459 Not tainted 6.8.0-syzkaller-08951-gfe46a7dd189e #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 copy_from_sockptr_offset include/linux/sockptr.h:49 [inline] copy_from_sockptr include/linux/sockptr.h:55 [inline] nfc_llcp_setsockopt+0x6c2/0x850 net/nfc/llcp_sock.c:255 do_sock_setsockopt+0x3b1/0x720 net/socket.c:2311 __sys_setsockopt+0x1ae/0x250 net/socket.c:2334 __do_sys_setsockopt net/socket.c:2343 [inline] __se_sys_setsockopt net/socket.c:2340 [inline] __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340 do_syscall_64+0xfd/0x240 entry_SYSCALL_64_after_hwframe+0x6d/0x75 RIP: 0033:0x7f7fac07fd89 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 91 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fff660eb788 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f7fac07fd89 RDX: 0000000000000000 RSI: 0000000000000118 RDI: 0000000000000004 RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000000 R10: 0000000020000a80 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
CVE-2024-36916: In the Linux kernel, the following vulnerability has been resolved: blk-iocost: avoid out of bounds shift UBSAN catches undefined behavior in blk-iocost, where sometimes iocg->delay is shifted right by a number that is too large, resulting in undefined behavior on some architectures. [ 186.556576] ------------[ cut here ]------------ UBSAN: shift-out-of-bounds in block/blk-iocost.c:1366:23 shift exponent 64 is too large for 64-bit type 'u64' (aka 'unsigned long long') CPU: 16 PID: 0 Comm: swapper/16 Tainted: G S E N 6.9.0-0_fbk700_debug_rc2_kbuilder_0_gc85af715cac0 #1 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A23 12/08/2020 Call Trace: <IRQ> dump_stack_lvl+0x8f/0xe0 __ubsan_handle_shift_out_of_bounds+0x22c/0x280 iocg_kick_delay+0x30b/0x310 ioc_timer_fn+0x2fb/0x1f80 __run_timer_base+0x1b6/0x250 ... Avoid that undefined behavior by simply taking the "delay = 0" branch if the shift is too large. I am not sure what the symptoms of an undefined value delay will be, but I suspect it could be more than a little annoying to debug.
CVE-2024-36917: In the Linux kernel, the following vulnerability has been resolved: block: fix overflow in blk_ioctl_discard() There is no check for overflow of 'start + len' in blk_ioctl_discard(). Hung task occurs if submit an discard ioctl with the following param: start = 0x80000000000ff000, len = 0x8000000000fff000; Add the overflow validation now.
CVE-2024-36918: In the Linux kernel, the following vulnerability has been resolved: bpf: Check bloom filter map value size This patch adds a missing check to bloom filter creating, rejecting values above KMALLOC_MAX_SIZE. This brings the bloom map in line with many other map types. The lack of this protection can cause kernel crashes for value sizes that overflow int's. Such a crash was caught by syzkaller. The next patch adds more guard-rails at a lower level.
CVE-2024-36920: In the Linux kernel, the following vulnerability has been resolved: scsi: mpi3mr: Avoid memcpy field-spanning write WARNING When the "storcli2 show" command is executed for eHBA-9600, mpi3mr driver prints this WARNING message: memcpy: detected field-spanning write (size 128) of single field "bsg_reply_buf->reply_buf" at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 (size 1) WARNING: CPU: 0 PID: 12760 at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 mpi3mr_bsg_request+0x6b12/0x7f10 [mpi3mr] The cause of the WARN is 128 bytes memcpy to the 1 byte size array "__u8 replay_buf[1]" in the struct mpi3mr_bsg_in_reply_buf. The array is intended to be a flexible length array, so the WARN is a false positive. To suppress the WARN, remove the constant number '1' from the array declaration and clarify that it has flexible length. Also, adjust the memory allocation size to match the change.
CVE-2024-36921: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: mvm: guard against invalid STA ID on removal Guard against invalid station IDs in iwl_mvm_mld_rm_sta_id as that would result in out-of-bounds array accesses. This prevents issues should the driver get into a bad state during error handling.
CVE-2024-36922: In the Linux kernel, the following vulnerability has been resolved: wifi: iwlwifi: read txq->read_ptr under lock If we read txq->read_ptr without lock, we can read the same value twice, then obtain the lock, and reclaim from there to two different places, but crucially reclaim the same entry twice, resulting in the WARN_ONCE() a little later. Fix that by reading txq->read_ptr under lock.
CVE-2024-36923: In the Linux kernel, the following vulnerability has been resolved: fs/9p: fix uninitialized values during inode evict If an iget fails due to not being able to retrieve information from the server then the inode structure is only partially initialized. When the inode gets evicted, references to uninitialized structures (like fscache cookies) were being made. This patch checks for a bad_inode before doing anything other than clearing the inode from the cache. Since the inode is bad, it shouldn't have any state associated with it that needs to be written back (and there really isn't a way to complete those anyways).
CVE-2024-36924: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Release hbalock before calling lpfc_worker_wake_up() lpfc_worker_wake_up() calls the lpfc_work_done() routine, which takes the hbalock. Thus, lpfc_worker_wake_up() should not be called while holding the hbalock to avoid potential deadlock.
CVE-2024-36927: In the Linux kernel, the following vulnerability has been resolved: ipv4: Fix uninit-value access in __ip_make_skb() KMSAN reported uninit-value access in __ip_make_skb() [1]. __ip_make_skb() tests HDRINCL to know if the skb has icmphdr. However, HDRINCL can cause a race condition. If calling setsockopt(2) with IP_HDRINCL changes HDRINCL while __ip_make_skb() is running, the function will access icmphdr in the skb even if it is not included. This causes the issue reported by KMSAN. Check FLOWI_FLAG_KNOWN_NH on fl4->flowi4_flags instead of testing HDRINCL on the socket. Also, fl4->fl4_icmp_type and fl4->fl4_icmp_code are not initialized. These are union in struct flowi4 and are implicitly initialized by flowi4_init_output(), but we should not rely on specific union layout. Initialize these explicitly in raw_sendmsg(). [1] BUG: KMSAN: uninit-value in __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 __ip_make_skb+0x2b74/0x2d20 net/ipv4/ip_output.c:1481 ip_finish_skb include/net/ip.h:243 [inline] ip_push_pending_frames+0x4c/0x5c0 net/ipv4/ip_output.c:1508 raw_sendmsg+0x2381/0x2690 net/ipv4/raw.c:654 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 Uninit was created at: slab_post_alloc_hook mm/slub.c:3804 [inline] slab_alloc_node mm/slub.c:3845 [inline] kmem_cache_alloc_node+0x5f6/0xc50 mm/slub.c:3888 kmalloc_reserve+0x13c/0x4a0 net/core/skbuff.c:577 __alloc_skb+0x35a/0x7c0 net/core/skbuff.c:668 alloc_skb include/linux/skbuff.h:1318 [inline] __ip_append_data+0x49ab/0x68c0 net/ipv4/ip_output.c:1128 ip_append_data+0x1e7/0x260 net/ipv4/ip_output.c:1365 raw_sendmsg+0x22b1/0x2690 net/ipv4/raw.c:648 inet_sendmsg+0x27b/0x2a0 net/ipv4/af_inet.c:851 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x274/0x3c0 net/socket.c:745 __sys_sendto+0x62c/0x7b0 net/socket.c:2191 __do_sys_sendto net/socket.c:2203 [inline] __se_sys_sendto net/socket.c:2199 [inline] __x64_sys_sendto+0x130/0x200 net/socket.c:2199 do_syscall_64+0xd8/0x1f0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x6d/0x75 CPU: 1 PID: 15709 Comm: syz-executor.7 Not tainted 6.8.0-11567-gb3603fcb79b1 #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014
CVE-2024-36939: In the Linux kernel, the following vulnerability has been resolved: nfs: Handle error of rpc_proc_register() in nfs_net_init(). syzkaller reported a warning [0] triggered while destroying immature netns. rpc_proc_register() was called in init_nfs_fs(), but its error has been ignored since at least the initial commit 1da177e4c3f4 ("Linux-2.6.12-rc2"). Recently, commit d47151b79e32 ("nfs: expose /proc/net/sunrpc/nfs in net namespaces") converted the procfs to per-netns and made the problem more visible. Even when rpc_proc_register() fails, nfs_net_init() could succeed, and thus nfs_net_exit() will be called while destroying the netns. Then, remove_proc_entry() will be called for non-existing proc directory and trigger the warning below. Let's handle the error of rpc_proc_register() properly in nfs_net_init(). [0]: name 'nfs' WARNING: CPU: 1 PID: 1710 at fs/proc/generic.c:711 remove_proc_entry+0x1bb/0x2d0 fs/proc/generic.c:711 Modules linked in: CPU: 1 PID: 1710 Comm: syz-executor.2 Not tainted 6.8.0-12822-gcd51db110a7e #12 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:remove_proc_entry+0x1bb/0x2d0 fs/proc/generic.c:711 Code: 41 5d 41 5e c3 e8 85 09 b5 ff 48 c7 c7 88 58 64 86 e8 09 0e 71 02 e8 74 09 b5 ff 4c 89 e6 48 c7 c7 de 1b 80 84 e8 c5 ad 97 ff <0f> 0b eb b1 e8 5c 09 b5 ff 48 c7 c7 88 58 64 86 e8 e0 0d 71 02 eb RSP: 0018:ffffc9000c6d7ce0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8880422b8b00 RCX: ffffffff8110503c RDX: ffff888030652f00 RSI: ffffffff81105045 RDI: 0000000000000001 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff81bb62cb R12: ffffffff84807ffc R13: ffff88804ad6fcc0 R14: ffffffff84807ffc R15: ffffffff85741ff8 FS: 00007f30cfba8640(0000) GS:ffff88807dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ff51afe8000 CR3: 000000005a60a005 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> rpc_proc_unregister+0x64/0x70 net/sunrpc/stats.c:310 nfs_net_exit+0x1c/0x30 fs/nfs/inode.c:2438 ops_exit_list+0x62/0xb0 net/core/net_namespace.c:170 setup_net+0x46c/0x660 net/core/net_namespace.c:372 copy_net_ns+0x244/0x590 net/core/net_namespace.c:505 create_new_namespaces+0x2ed/0x770 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xae/0x160 kernel/nsproxy.c:228 ksys_unshare+0x342/0x760 kernel/fork.c:3322 __do_sys_unshare kernel/fork.c:3393 [inline] __se_sys_unshare kernel/fork.c:3391 [inline] __x64_sys_unshare+0x1f/0x30 kernel/fork.c:3391 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0x4f/0x110 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x46/0x4e RIP: 0033:0x7f30d0febe5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007f30cfba7cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00000000004bbf80 RCX: 00007f30d0febe5d RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000006c020600 RBP: 00000000004bbf80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000002 R13: 000000000000000b R14: 00007f30d104c530 R15: 0000000000000000 </TASK>
CVE-2024-36942: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: qca: fix firmware check error path A recent commit fixed the code that parses the firmware files before downloading them to the controller but introduced a memory leak in case the sanity checks ever fail. Make sure to free the firmware buffer before returning on errors.
CVE-2024-36944: In the Linux kernel, the following vulnerability has been resolved: Reapply "drm/qxl: simplify qxl_fence_wait" This reverts commit 07ed11afb68d94eadd4ffc082b97c2331307c5ea. Stephen Rostedt reports: "I went to run my tests on my VMs and the tests hung on boot up. Unfortunately, the most I ever got out was: [ 93.607888] Testing event system initcall: OK [ 93.667730] Running tests on all trace events: [ 93.669757] Testing all events: OK [ 95.631064] ------------[ cut here ]------------ Timed out after 60 seconds" and further debugging points to a possible circular locking dependency between the console_owner locking and the worker pool locking. Reverting the commit allows Steve's VM to boot to completion again. [ This may obviously result in the "[TTM] Buffer eviction failed" messages again, which was the reason for that original revert. But at this point this seems preferable to a non-booting system... ]
CVE-2024-36948: In the Linux kernel, the following vulnerability has been resolved: drm/xe/xe_migrate: Cast to output precision before multiplying operands Addressing potential overflow in result of multiplication of two lower precision (u32) operands before widening it to higher precision (u64). -v2 Fix commit message and description. (Rodrigo) (cherry picked from commit 34820967ae7b45411f8f4f737c2d63b0c608e0d7)
CVE-2024-36949: In the Linux kernel, the following vulnerability has been resolved: amd/amdkfd: sync all devices to wait all processes being evicted If there are more than one device doing reset in parallel, the first device will call kfd_suspend_all_processes() to evict all processes on all devices, this call takes time to finish. other device will start reset and recover without waiting. if the process has not been evicted before doing recover, it will be restored, then caused page fault.
CVE-2024-36951: In the Linux kernel, the following vulnerability has been resolved: drm/amdkfd: range check cp bad op exception interrupts Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well.
CVE-2024-36952: In the Linux kernel, the following vulnerability has been resolved: scsi: lpfc: Move NPIV's transport unregistration to after resource clean up There are cases after NPIV deletion where the fabric switch still believes the NPIV is logged into the fabric. This occurs when a vport is unregistered before the Remove All DA_ID CT and LOGO ELS are sent to the fabric. Currently fc_remove_host(), which calls dev_loss_tmo for all D_IDs including the fabric D_ID, removes the last ndlp reference and frees the ndlp rport object. This sometimes causes the race condition where the final DA_ID and LOGO are skipped from being sent to the fabric switch. Fix by moving the fc_remove_host() and scsi_remove_host() calls after DA_ID and LOGO are sent.
CVE-2024-36953: In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: vgic-v2: Check for non-NULL vCPU in vgic_v2_parse_attr() vgic_v2_parse_attr() is responsible for finding the vCPU that matches the user-provided CPUID, which (of course) may not be valid. If the ID is invalid, kvm_get_vcpu_by_id() returns NULL, which isn't handled gracefully. Similar to the GICv3 uaccess flow, check that kvm_get_vcpu_by_id() actually returns something and fail the ioctl if not.
CVE-2024-36968: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() l2cap_le_flowctl_init() can cause both div-by-zero and an integer overflow since hdev->le_mtu may not fall in the valid range. Move MTU from hci_dev to hci_conn to validate MTU and stop the connection process earlier if MTU is invalid. Also, add a missing validation in read_buffer_size() and make it return an error value if the validation fails. Now hci_conn_add() returns ERR_PTR() as it can fail due to the both a kzalloc failure and invalid MTU value. divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 67 Comm: kworker/u5:0 Tainted: G W 6.9.0-rc5+ #20 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: hci0 hci_rx_work RIP: 0010:l2cap_le_flowctl_init+0x19e/0x3f0 net/bluetooth/l2cap_core.c:547 Code: e8 17 17 0c 00 66 41 89 9f 84 00 00 00 bf 01 00 00 00 41 b8 02 00 00 00 4c 89 fe 4c 89 e2 89 d9 e8 27 17 0c 00 44 89 f0 31 d2 <66> f7 f3 89 c3 ff c3 4d 8d b7 88 00 00 00 4c 89 f0 48 c1 e8 03 42 RSP: 0018:ffff88810bc0f858 EFLAGS: 00010246 RAX: 00000000000002a0 RBX: 0000000000000000 RCX: dffffc0000000000 RDX: 0000000000000000 RSI: ffff88810bc0f7c0 RDI: ffffc90002dcb66f RBP: ffff88810bc0f880 R08: aa69db2dda70ff01 R09: 0000ffaaaaaaaaaa R10: 0084000000ffaaaa R11: 0000000000000000 R12: ffff88810d65a084 R13: dffffc0000000000 R14: 00000000000002a0 R15: ffff88810d65a000 FS: 0000000000000000(0000) GS:ffff88811ac00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000100 CR3: 0000000103268003 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: <TASK> l2cap_le_connect_req net/bluetooth/l2cap_core.c:4902 [inline] l2cap_le_sig_cmd net/bluetooth/l2cap_core.c:5420 [inline] l2cap_le_sig_channel net/bluetooth/l2cap_core.c:5486 [inline] l2cap_recv_frame+0xe59d/0x11710 net/bluetooth/l2cap_core.c:6809 l2cap_recv_acldata+0x544/0x10a0 net/bluetooth/l2cap_core.c:7506 hci_acldata_packet net/bluetooth/hci_core.c:3939 [inline] hci_rx_work+0x5e5/0xb20 net/bluetooth/hci_core.c:4176 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0x90f/0x1530 kernel/workqueue.c:3335 worker_thread+0x926/0xe70 kernel/workqueue.c:3416 kthread+0x2e3/0x380 kernel/kthread.c:388 ret_from_fork+0x5c/0x90 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]---
CVE-2024-36969: In the Linux kernel, the following vulnerability has been resolved: drm/amd/display: Fix division by zero in setup_dsc_config When slice_height is 0, the division by slice_height in the calculation of the number of slices will cause a division by zero driver crash. This leaves the kernel in a state that requires a reboot. This patch adds a check to avoid the division by zero. The stack trace below is for the 6.8.4 Kernel. I reproduced the issue on a Z16 Gen 2 Lenovo Thinkpad with a Apple Studio Display monitor connected via Thunderbolt. The amdgpu driver crashed with this exception when I rebooted the system with the monitor connected. kernel: ? die (arch/x86/kernel/dumpstack.c:421 arch/x86/kernel/dumpstack.c:434 arch/x86/kernel/dumpstack.c:447) kernel: ? do_trap (arch/x86/kernel/traps.c:113 arch/x86/kernel/traps.c:154) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? do_error_trap (./arch/x86/include/asm/traps.h:58 arch/x86/kernel/traps.c:175) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? exc_divide_error (arch/x86/kernel/traps.c:194 (discriminator 2)) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: ? asm_exc_divide_error (./arch/x86/include/asm/idtentry.h:548) kernel: ? setup_dsc_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1053) amdgpu kernel: dc_dsc_compute_config (drivers/gpu/drm/amd/amdgpu/../display/dc/dsc/dc_dsc.c:1109) amdgpu After applying this patch, the driver no longer crashes when the monitor is connected and the system is rebooted. I believe this is the same issue reported for 3113.
CVE-2024-37021: In the Linux kernel, the following vulnerability has been resolved: fpga: manager: add owner module and take its refcount The current implementation of the fpga manager assumes that the low-level module registers a driver for the parent device and uses its owner pointer to take the module's refcount. This approach is problematic since it can lead to a null pointer dereference while attempting to get the manager if the parent device does not have a driver. To address this problem, add a module owner pointer to the fpga_manager struct and use it to take the module's refcount. Modify the functions for registering the manager to take an additional owner module parameter and rename them to avoid conflicts. Use the old function names for helper macros that automatically set the module that registers the manager as the owner. This ensures compatibility with existing low-level control modules and reduces the chances of registering a manager without setting the owner. Also, update the documentation to keep it consistent with the new interface for registering an fpga manager. Other changes: opportunistically move put_device() from __fpga_mgr_get() to fpga_mgr_get() and of_fpga_mgr_get() to improve code clarity since the manager device is taken in these functions.
CVE-2024-37078: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix potential kernel bug due to lack of writeback flag waiting Destructive writes to a block device on which nilfs2 is mounted can cause a kernel bug in the folio/page writeback start routine or writeback end routine (__folio_start_writeback in the log below): kernel BUG at mm/page-writeback.c:3070! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI ... RIP: 0010:__folio_start_writeback+0xbaa/0x10e0 Code: 25 ff 0f 00 00 0f 84 18 01 00 00 e8 40 ca c6 ff e9 17 f6 ff ff e8 36 ca c6 ff 4c 89 f7 48 c7 c6 80 c0 12 84 e8 e7 b3 0f 00 90 <0f> 0b e8 1f ca c6 ff 4c 89 f7 48 c7 c6 a0 c6 12 84 e8 d0 b3 0f 00 ... Call Trace: <TASK> nilfs_segctor_do_construct+0x4654/0x69d0 [nilfs2] nilfs_segctor_construct+0x181/0x6b0 [nilfs2] nilfs_segctor_thread+0x548/0x11c0 [nilfs2] kthread+0x2f0/0x390 ret_from_fork+0x4b/0x80 ret_from_fork_asm+0x1a/0x30 </TASK> This is because when the log writer starts a writeback for segment summary blocks or a super root block that use the backing device's page cache, it does not wait for the ongoing folio/page writeback, resulting in an inconsistent writeback state. Fix this issue by waiting for ongoing writebacks when putting folios/pages on the backing device into writeback state.
CVE-2024-37354: In the Linux kernel, the following vulnerability has been resolved: btrfs: fix crash on racing fsync and size-extending write into prealloc We have been seeing crashes on duplicate keys in btrfs_set_item_key_safe(): BTRFS critical (device vdb): slot 4 key (450 108 8192) new key (450 108 8192) ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.c:2620! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 3139 Comm: xfs_io Kdump: loaded Not tainted 6.9.0 #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:btrfs_set_item_key_safe+0x11f/0x290 [btrfs] With the following stack trace: #0 btrfs_set_item_key_safe (fs/btrfs/ctree.c:2620:4) #1 btrfs_drop_extents (fs/btrfs/file.c:411:4) #2 log_one_extent (fs/btrfs/tree-log.c:4732:9) #3 btrfs_log_changed_extents (fs/btrfs/tree-log.c:4955:9) #4 btrfs_log_inode (fs/btrfs/tree-log.c:6626:9) #5 btrfs_log_inode_parent (fs/btrfs/tree-log.c:7070:8) #6 btrfs_log_dentry_safe (fs/btrfs/tree-log.c:7171:8) #7 btrfs_sync_file (fs/btrfs/file.c:1933:8) #8 vfs_fsync_range (fs/sync.c:188:9) #9 vfs_fsync (fs/sync.c:202:9) #10 do_fsync (fs/sync.c:212:9) #11 __do_sys_fdatasync (fs/sync.c:225:9) #12 __se_sys_fdatasync (fs/sync.c:223:1) #13 __x64_sys_fdatasync (fs/sync.c:223:1) #14 do_syscall_x64 (arch/x86/entry/common.c:52:14) #15 do_syscall_64 (arch/x86/entry/common.c:83:7) #16 entry_SYSCALL_64+0xaf/0x14c (arch/x86/entry/entry_64.S:121) So we're logging a changed extent from fsync, which is splitting an extent in the log tree. But this split part already exists in the tree, triggering the BUG(). This is the state of the log tree at the time of the crash, dumped with drgn (https://github.com/osandov/drgn/blob/main/contrib/btrfs_tree.py) to get more details than btrfs_print_leaf() gives us: >>> print_extent_buffer(prog.crashed_thread().stack_trace()[0]["eb"]) leaf 33439744 level 0 items 72 generation 9 owner 18446744073709551610 leaf 33439744 flags 0x100000000000000 fs uuid e5bd3946-400c-4223-8923-190ef1f18677 chunk uuid d58cb17e-6d02-494a-829a-18b7d8a399da item 0 key (450 INODE_ITEM 0) itemoff 16123 itemsize 160 generation 7 transid 9 size 8192 nbytes 8473563889606862198 block group 0 mode 100600 links 1 uid 0 gid 0 rdev 0 sequence 204 flags 0x10(PREALLOC) atime 1716417703.220000000 (2024-05-22 15:41:43) ctime 1716417704.983333333 (2024-05-22 15:41:44) mtime 1716417704.983333333 (2024-05-22 15:41:44) otime 17592186044416.000000000 (559444-03-08 01:40:16) item 1 key (450 INODE_REF 256) itemoff 16110 itemsize 13 index 195 namelen 3 name: 193 item 2 key (450 XATTR_ITEM 1640047104) itemoff 16073 itemsize 37 location key (0 UNKNOWN.0 0) type XATTR transid 7 data_len 1 name_len 6 name: user.a data a item 3 key (450 EXTENT_DATA 0) itemoff 16020 itemsize 53 generation 9 type 1 (regular) extent data disk byte 303144960 nr 12288 extent data offset 0 nr 4096 ram 12288 extent compression 0 (none) item 4 key (450 EXTENT_DATA 4096) itemoff 15967 itemsize 53 generation 9 type 2 (prealloc) prealloc data disk byte 303144960 nr 12288 prealloc data offset 4096 nr 8192 item 5 key (450 EXTENT_DATA 8192) itemoff 15914 itemsize 53 generation 9 type 2 (prealloc) prealloc data disk byte 303144960 nr 12288 prealloc data offset 8192 nr 4096 ... So the real problem happened earlier: notice that items 4 (4k-12k) and 5 (8k-12k) overlap. Both are prealloc extents. Item 4 straddles i_size and item 5 starts at i_size. Here is the state of ---truncated---
CVE-2024-38538: In the Linux kernel, the following vulnerability has been resolved: net: bridge: xmit: make sure we have at least eth header len bytes syzbot triggered an uninit value[1] error in bridge device's xmit path by sending a short (less than ETH_HLEN bytes) skb. To fix it check if we can actually pull that amount instead of assuming. Tested with dropwatch: drop at: br_dev_xmit+0xb93/0x12d0 [bridge] (0xffffffffc06739b3) origin: software timestamp: Mon May 13 11:31:53 2024 778214037 nsec protocol: 0x88a8 length: 2 original length: 2 drop reason: PKT_TOO_SMALL [1] BUG: KMSAN: uninit-value in br_dev_xmit+0x61d/0x1cb0 net/bridge/br_device.c:65 br_dev_xmit+0x61d/0x1cb0 net/bridge/br_device.c:65 __netdev_start_xmit include/linux/netdevice.h:4903 [inline] netdev_start_xmit include/linux/netdevice.h:4917 [inline] xmit_one net/core/dev.c:3531 [inline] dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3547 __dev_queue_xmit+0x34db/0x5350 net/core/dev.c:4341 dev_queue_xmit include/linux/netdevice.h:3091 [inline] __bpf_tx_skb net/core/filter.c:2136 [inline] __bpf_redirect_common net/core/filter.c:2180 [inline] __bpf_redirect+0x14a6/0x1620 net/core/filter.c:2187 ____bpf_clone_redirect net/core/filter.c:2460 [inline] bpf_clone_redirect+0x328/0x470 net/core/filter.c:2432 ___bpf_prog_run+0x13fe/0xe0f0 kernel/bpf/core.c:1997 __bpf_prog_run512+0xb5/0xe0 kernel/bpf/core.c:2238 bpf_dispatcher_nop_func include/linux/bpf.h:1234 [inline] __bpf_prog_run include/linux/filter.h:657 [inline] bpf_prog_run include/linux/filter.h:664 [inline] bpf_test_run+0x499/0xc30 net/bpf/test_run.c:425 bpf_prog_test_run_skb+0x14ea/0x1f20 net/bpf/test_run.c:1058 bpf_prog_test_run+0x6b7/0xad0 kernel/bpf/syscall.c:4269 __sys_bpf+0x6aa/0xd90 kernel/bpf/syscall.c:5678 __do_sys_bpf kernel/bpf/syscall.c:5767 [inline] __se_sys_bpf kernel/bpf/syscall.c:5765 [inline] __x64_sys_bpf+0xa0/0xe0 kernel/bpf/syscall.c:5765 x64_sys_call+0x96b/0x3b50 arch/x86/include/generated/asm/syscalls_64.h:322 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
CVE-2024-38541: In the Linux kernel, the following vulnerability has been resolved: of: module: add buffer overflow check in of_modalias() In of_modalias(), if the buffer happens to be too small even for the 1st snprintf() call, the len parameter will become negative and str parameter (if not NULL initially) will point beyond the buffer's end. Add the buffer overflow check after the 1st snprintf() call and fix such check after the strlen() call (accounting for the terminating NUL char).
CVE-2024-38544: In the Linux kernel, the following vulnerability has been resolved: RDMA/rxe: Fix seg fault in rxe_comp_queue_pkt In rxe_comp_queue_pkt() an incoming response packet skb is enqueued to the resp_pkts queue and then a decision is made whether to run the completer task inline or schedule it. Finally the skb is dereferenced to bump a 'hw' performance counter. This is wrong because if the completer task is already running in a separate thread it may have already processed the skb and freed it which can cause a seg fault. This has been observed infrequently in testing at high scale. This patch fixes this by changing the order of enqueuing the packet until after the counter is accessed.
CVE-2024-38545: In the Linux kernel, the following vulnerability has been resolved: RDMA/hns: Fix UAF for cq async event The refcount of CQ is not protected by locks. When CQ asynchronous events and CQ destruction are concurrent, CQ may have been released, which will cause UAF. Use the xa_lock() to protect the CQ refcount.
CVE-2024-38546: In the Linux kernel, the following vulnerability has been resolved: drm: vc4: Fix possible null pointer dereference In vc4_hdmi_audio_init() of_get_address() may return NULL which is later dereferenced. Fix this bug by adding NULL check. Found by Linux Verification Center (linuxtesting.org) with SVACE.
CVE-2024-38547: In the Linux kernel, the following vulnerability has been resolved: media: atomisp: ssh_css: Fix a null-pointer dereference in load_video_binaries The allocation failure of mycs->yuv_scaler_binary in load_video_binaries() is followed with a dereference of mycs->yuv_scaler_binary after the following call chain: sh_css_pipe_load_binaries() |-> load_video_binaries(mycs->yuv_scaler_binary == NULL) | |-> sh_css_pipe_unload_binaries() |-> unload_video_binaries() In unload_video_binaries(), it calls to ia_css_binary_unload with argument &pipe->pipe_settings.video.yuv_scaler_binary[i], which refers to the same memory slot as mycs->yuv_scaler_binary. Thus, a null-pointer dereference is triggered.
CVE-2024-38553: In the Linux kernel, the following vulnerability has been resolved: net: fec: remove .ndo_poll_controller to avoid deadlocks There is a deadlock issue found in sungem driver, please refer to the commit ac0a230f719b ("eth: sungem: remove .ndo_poll_controller to avoid deadlocks"). The root cause of the issue is that netpoll is in atomic context and disable_irq() is called by .ndo_poll_controller interface of sungem driver, however, disable_irq() might sleep. After analyzing the implementation of fec_poll_controller(), the fec driver should have the same issue. Due to the fec driver uses NAPI for TX completions, the .ndo_poll_controller is unnecessary to be implemented in the fec driver, so fec_poll_controller() can be safely removed.
CVE-2024-38554: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix reference count leak issue of net_device There is a reference count leak issue of the object "net_device" in ax25_dev_device_down(). When the ax25 device is shutting down, the ax25_dev_device_down() drops the reference count of net_device one or zero times depending on if we goto unlock_put or not, which will cause memory leak. In order to solve the above issue, decrease the reference count of net_device after dev->ax25_ptr is set to null.
CVE-2024-38570: In the Linux kernel, the following vulnerability has been resolved: gfs2: Fix potential glock use-after-free on unmount When a DLM lockspace is released and there ares still locks in that lockspace, DLM will unlock those locks automatically. Commit fb6791d100d1b started exploiting this behavior to speed up filesystem unmount: gfs2 would simply free glocks it didn't want to unlock and then release the lockspace. This didn't take the bast callbacks for asynchronous lock contention notifications into account, which remain active until until a lock is unlocked or its lockspace is released. To prevent those callbacks from accessing deallocated objects, put the glocks that should not be unlocked on the sd_dead_glocks list, release the lockspace, and only then free those glocks. As an additional measure, ignore unexpected ast and bast callbacks if the receiving glock is dead.
CVE-2024-38580: In the Linux kernel, the following vulnerability has been resolved: epoll: be better about file lifetimes epoll can call out to vfs_poll() with a file pointer that may race with the last 'fput()'. That would make f_count go down to zero, and while the ep->mtx locking means that the resulting file pointer tear-down will be blocked until the poll returns, it means that f_count is already dead, and any use of it won't actually get a reference to the file any more: it's dead regardless. Make sure we have a valid ref on the file pointer before we call down to vfs_poll() from the epoll routines.
CVE-2024-38581: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu/mes: fix use-after-free issue Delete fence fallback timer to fix the ramdom use-after-free issue. v2: move to amdgpu_mes.c
CVE-2024-38588: In the Linux kernel, the following vulnerability has been resolved: ftrace: Fix possible use-after-free issue in ftrace_location() KASAN reports a bug: BUG: KASAN: use-after-free in ftrace_location+0x90/0x120 Read of size 8 at addr ffff888141d40010 by task insmod/424 CPU: 8 PID: 424 Comm: insmod Tainted: G W 6.9.0-rc2+ [...] Call Trace: <TASK> dump_stack_lvl+0x68/0xa0 print_report+0xcf/0x610 kasan_report+0xb5/0xe0 ftrace_location+0x90/0x120 register_kprobe+0x14b/0xa40 kprobe_init+0x2d/0xff0 [kprobe_example] do_one_initcall+0x8f/0x2d0 do_init_module+0x13a/0x3c0 load_module+0x3082/0x33d0 init_module_from_file+0xd2/0x130 __x64_sys_finit_module+0x306/0x440 do_syscall_64+0x68/0x140 entry_SYSCALL_64_after_hwframe+0x71/0x79 The root cause is that, in lookup_rec(), ftrace record of some address is being searched in ftrace pages of some module, but those ftrace pages at the same time is being freed in ftrace_release_mod() as the corresponding module is being deleted: CPU1 | CPU2 register_kprobes() { | delete_module() { check_kprobe_address_safe() { | arch_check_ftrace_location() { | ftrace_location() { | lookup_rec() // USE! | ftrace_release_mod() // Free! To fix this issue: 1. Hold rcu lock as accessing ftrace pages in ftrace_location_range(); 2. Use ftrace_location_range() instead of lookup_rec() in ftrace_location(); 3. Call synchronize_rcu() before freeing any ftrace pages both in ftrace_process_locs()/ftrace_release_mod()/ftrace_free_mem().
CVE-2024-38597: In the Linux kernel, the following vulnerability has been resolved: eth: sungem: remove .ndo_poll_controller to avoid deadlocks Erhard reports netpoll warnings from sungem: netpoll_send_skb_on_dev(): eth0 enabled interrupts in poll (gem_start_xmit+0x0/0x398) WARNING: CPU: 1 PID: 1 at net/core/netpoll.c:370 netpoll_send_skb+0x1fc/0x20c gem_poll_controller() disables interrupts, which may sleep. We can't sleep in netpoll, it has interrupts disabled completely. Strangely, gem_poll_controller() doesn't even poll the completions, and instead acts as if an interrupt has fired so it just schedules NAPI and exits. None of this has been necessary for years, since netpoll invokes NAPI directly.
CVE-2024-38600: In the Linux kernel, the following vulnerability has been resolved: ALSA: Fix deadlocks with kctl removals at disconnection In snd_card_disconnect(), we set card->shutdown flag at the beginning, call callbacks and do sync for card->power_ref_sleep waiters at the end. The callback may delete a kctl element, and this can lead to a deadlock when the device was in the suspended state. Namely: * A process waits for the power up at snd_power_ref_and_wait() in snd_ctl_info() or read/write() inside card->controls_rwsem. * The system gets disconnected meanwhile, and the driver tries to delete a kctl via snd_ctl_remove*(); it tries to take card->controls_rwsem again, but this is already locked by the above. Since the sleeper isn't woken up, this deadlocks. An easy fix is to wake up sleepers before processing the driver disconnect callbacks but right after setting the card->shutdown flag. Then all sleepers will abort immediately, and the code flows again. So, basically this patch moves the wait_event() call at the right timing. While we're at it, just to be sure, call wait_event_all() instead of wait_event(), although we don't use exclusive events on this queue for now.
CVE-2024-38602: In the Linux kernel, the following vulnerability has been resolved: ax25: Fix reference count leak issues of ax25_dev The ax25_addr_ax25dev() and ax25_dev_device_down() exist a reference count leak issue of the object "ax25_dev". Memory leak issue in ax25_addr_ax25dev(): The reference count of the object "ax25_dev" can be increased multiple times in ax25_addr_ax25dev(). This will cause a memory leak. Memory leak issues in ax25_dev_device_down(): The reference count of ax25_dev is set to 1 in ax25_dev_device_up() and then increase the reference count when ax25_dev is added to ax25_dev_list. As a result, the reference count of ax25_dev is 2. But when the device is shutting down. The ax25_dev_device_down() drops the reference count once or twice depending on if we goto unlock_put or not, which will cause memory leak. As for the issue of ax25_addr_ax25dev(), it is impossible for one pointer to be on a list twice. So add a break in ax25_addr_ax25dev(). As for the issue of ax25_dev_device_down(), increase the reference count of ax25_dev once in ax25_dev_device_up() and decrease the reference count of ax25_dev after it is removed from the ax25_dev_list.
CVE-2024-38608: In the Linux kernel, the following vulnerability has been resolved: net/mlx5e: Fix netif state handling mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]---
CVE-2024-38611: In the Linux kernel, the following vulnerability has been resolved: media: i2c: et8ek8: Don't strip remove function when driver is builtin Using __exit for the remove function results in the remove callback being discarded with CONFIG_VIDEO_ET8EK8=y. When such a device gets unbound (e.g. using sysfs or hotplug), the driver is just removed without the cleanup being performed. This results in resource leaks. Fix it by compiling in the remove callback unconditionally. This also fixes a W=1 modpost warning: WARNING: modpost: drivers/media/i2c/et8ek8/et8ek8: section mismatch in reference: et8ek8_i2c_driver+0x10 (section: .data) -> et8ek8_remove (section: .exit.text)
CVE-2024-38619: In the Linux kernel, the following vulnerability has been resolved: usb-storage: alauda: Check whether the media is initialized The member "uzonesize" of struct alauda_info will remain 0 if alauda_init_media() fails, potentially causing divide errors in alauda_read_data() and alauda_write_lba(). - Add a member "media_initialized" to struct alauda_info. - Change a condition in alauda_check_media() to ensure the first initialization. - Add an error check for the return value of alauda_init_media().
CVE-2024-38620: In the Linux kernel, the following vulnerability has been resolved: Bluetooth: HCI: Remove HCI_AMP support Since BT_HS has been remove HCI_AMP controllers no longer has any use so remove it along with the capability of creating AMP controllers. Since we no longer need to differentiate between AMP and Primary controllers, as only HCI_PRIMARY is left, this also remove hdev->dev_type altogether.
CVE-2024-38630: In the Linux kernel, the following vulnerability has been resolved: watchdog: cpu5wdt.c: Fix use-after-free bug caused by cpu5wdt_trigger When the cpu5wdt module is removing, the origin code uses del_timer() to de-activate the timer. If the timer handler is running, del_timer() could not stop it and will return directly. If the port region is released by release_region() and then the timer handler cpu5wdt_trigger() calls outb() to write into the region that is released, the use-after-free bug will happen. Change del_timer() to timer_shutdown_sync() in order that the timer handler could be finished before the port region is released.
CVE-2024-38635: In the Linux kernel, the following vulnerability has been resolved: soundwire: cadence: fix invalid PDI offset For some reason, we add an offset to the PDI, presumably to skip the PDI0 and PDI1 which are reserved for BPT. This code is however completely wrong and leads to an out-of-bounds access. We were just lucky so far since we used only a couple of PDIs and remained within the PDI array bounds. A Fixes: tag is not provided since there are no known platforms where the out-of-bounds would be accessed, and the initial code had problems as well. A follow-up patch completely removes this useless offset.
CVE-2024-39293: In the Linux kernel, the following vulnerability has been resolved: Revert "xsk: Support redirect to any socket bound to the same umem" This reverts commit 2863d665ea41282379f108e4da6c8a2366ba66db. This patch introduced a potential kernel crash when multiple napi instances redirect to the same AF_XDP socket. By removing the queue_index check, it is possible for multiple napi instances to access the Rx ring at the same time, which will result in a corrupted ring state which can lead to a crash when flushing the rings in __xsk_flush(). This can happen when the linked list of sockets to flush gets corrupted by concurrent accesses. A quick and small fix is not possible, so let us revert this for now.
CVE-2024-39362: In the Linux kernel, the following vulnerability has been resolved: i2c: acpi: Unbind mux adapters before delete There is an issue with ACPI overlay table removal specifically related to I2C multiplexers. Consider an ACPI SSDT Overlay that defines a PCA9548 I2C mux on an existing I2C bus. When this table is loaded we see the creation of a device for the overall PCA9548 chip and 8 further devices - one i2c_adapter each for the mux channels. These are all bound to their ACPI equivalents via an eventual invocation of acpi_bind_one(). When we unload the SSDT overlay we run into the problem. The ACPI devices are deleted as normal via acpi_device_del_work_fn() and the acpi_device_del_list. However, the following warning and stack trace is output as the deletion does not go smoothly: ------------[ cut here ]------------ kernfs: can not remove 'physical_node', no directory WARNING: CPU: 1 PID: 11 at fs/kernfs/dir.c:1674 kernfs_remove_by_name_ns+0xb9/0xc0 Modules linked in: CPU: 1 PID: 11 Comm: kworker/u128:0 Not tainted 6.8.0-rc6+ #1 Hardware name: congatec AG conga-B7E3/conga-B7E3, BIOS 5.13 05/16/2023 Workqueue: kacpi_hotplug acpi_device_del_work_fn RIP: 0010:kernfs_remove_by_name_ns+0xb9/0xc0 Code: e4 00 48 89 ef e8 07 71 db ff 5b b8 fe ff ff ff 5d 41 5c 41 5d e9 a7 55 e4 00 0f 0b eb a6 48 c7 c7 f0 38 0d 9d e8 97 0a d5 ff <0f> 0b eb dc 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 0018:ffff9f864008fb28 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8ef90a8d4940 RCX: 0000000000000000 RDX: ffff8f000e267d10 RSI: ffff8f000e25c780 RDI: ffff8f000e25c780 RBP: ffff8ef9186f9870 R08: 0000000000013ffb R09: 00000000ffffbfff R10: 00000000ffffbfff R11: ffff8f000e0a0000 R12: ffff9f864008fb50 R13: ffff8ef90c93dd60 R14: ffff8ef9010d0958 R15: ffff8ef9186f98c8 FS: 0000000000000000(0000) GS:ffff8f000e240000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f48f5253a08 CR3: 00000003cb82e000 CR4: 00000000003506f0 Call Trace: <TASK> ? kernfs_remove_by_name_ns+0xb9/0xc0 ? __warn+0x7c/0x130 ? kernfs_remove_by_name_ns+0xb9/0xc0 ? report_bug+0x171/0x1a0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? kernfs_remove_by_name_ns+0xb9/0xc0 ? kernfs_remove_by_name_ns+0xb9/0xc0 acpi_unbind_one+0x108/0x180 device_del+0x18b/0x490 ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f device_unregister+0xd/0x30 i2c_del_adapter.part.0+0x1bf/0x250 i2c_mux_del_adapters+0xa1/0xe0 i2c_device_remove+0x1e/0x80 device_release_driver_internal+0x19a/0x200 bus_remove_device+0xbf/0x100 device_del+0x157/0x490 ? __pfx_device_match_fwnode+0x10/0x10 ? srso_return_thunk+0x5/0x5f device_unregister+0xd/0x30 i2c_acpi_notify+0x10f/0x140 notifier_call_chain+0x58/0xd0 blocking_notifier_call_chain+0x3a/0x60 acpi_device_del_work_fn+0x85/0x1d0 process_one_work+0x134/0x2f0 worker_thread+0x2f0/0x410 ? __pfx_worker_thread+0x10/0x10 kthread+0xe3/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> ---[ end trace 0000000000000000 ]--- ... repeated 7 more times, 1 for each channel of the mux ... The issue is that the binding of the ACPI devices to their peer I2C adapters is not correctly cleaned up. Digging deeper into the issue we see that the deletion order is such that the ACPI devices matching the mux channel i2c adapters are deleted first during the SSDT overlay removal. For each of the channels we see a call to i2c_acpi_notify() with ACPI_RECONFIG_DEVICE_REMOVE but, because these devices are not actually i2c_clients, nothing is done for them. Later on, after each of the mux channels has been dealt with, we come to delete the i2c_client representing the PCA9548 device. This is the call stack we see above, whereby the kernel cleans up the i2c_client including destruction of the mux and its channel adapters. At this point we do attempt to unbind from the ACPI peers but those peers ---truncated---
CVE-2024-39467: In the Linux kernel, the following vulnerability has been resolved: f2fs: fix to do sanity check on i_xattr_nid in sanity_check_inode() syzbot reports a kernel bug as below: F2FS-fs (loop0): Mounted with checkpoint version = 48b305e4 ================================================================== BUG: KASAN: slab-out-of-bounds in f2fs_test_bit fs/f2fs/f2fs.h:2933 [inline] BUG: KASAN: slab-out-of-bounds in current_nat_addr fs/f2fs/node.h:213 [inline] BUG: KASAN: slab-out-of-bounds in f2fs_get_node_info+0xece/0x1200 fs/f2fs/node.c:600 Read of size 1 at addr ffff88807a58c76c by task syz-executor280/5076 CPU: 1 PID: 5076 Comm: syz-executor280 Not tainted 6.9.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 f2fs_test_bit fs/f2fs/f2fs.h:2933 [inline] current_nat_addr fs/f2fs/node.h:213 [inline] f2fs_get_node_info+0xece/0x1200 fs/f2fs/node.c:600 f2fs_xattr_fiemap fs/f2fs/data.c:1848 [inline] f2fs_fiemap+0x55d/0x1ee0 fs/f2fs/data.c:1925 ioctl_fiemap fs/ioctl.c:220 [inline] do_vfs_ioctl+0x1c07/0x2e50 fs/ioctl.c:838 __do_sys_ioctl fs/ioctl.c:902 [inline] __se_sys_ioctl+0x81/0x170 fs/ioctl.c:890 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is we missed to do sanity check on i_xattr_nid during f2fs_iget(), so that in fiemap() path, current_nat_addr() will access nat_bitmap w/ offset from invalid i_xattr_nid, result in triggering kasan bug report, fix it.
CVE-2024-39468: In the Linux kernel, the following vulnerability has been resolved: smb: client: fix deadlock in smb2_find_smb_tcon() Unlock cifs_tcp_ses_lock before calling cifs_put_smb_ses() to avoid such deadlock.
CVE-2024-39469: In the Linux kernel, the following vulnerability has been resolved: nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors The error handling in nilfs_empty_dir() when a directory folio/page read fails is incorrect, as in the old ext2 implementation, and if the folio/page cannot be read or nilfs_check_folio() fails, it will falsely determine the directory as empty and corrupt the file system. In addition, since nilfs_empty_dir() does not immediately return on a failed folio/page read, but continues to loop, this can cause a long loop with I/O if i_size of the directory's inode is also corrupted, causing the log writer thread to wait and hang, as reported by syzbot. Fix these issues by making nilfs_empty_dir() immediately return a false value (0) if it fails to get a directory folio/page.
CVE-2024-39471: In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: add error handle to avoid out-of-bounds if the sdma_v4_0_irq_id_to_seq return -EINVAL, the process should be stop to avoid out-of-bounds read, so directly return -EINVAL.

4 issues postponed or untriaged:

CVE-2019-16089: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel through 5.2.13. nbd_genl_status in drivers/block/nbd.c does not check the nla_nest_start_noflag return value.
CVE-2019-19449: (postponed; to be fixed through a stable update) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can lead to slab-out-of-bounds read access in f2fs_build_segment_manager in fs/f2fs/segment.c, related to init_min_max_mtime in fs/f2fs/segment.c (because the second argument to get_seg_entry is not validated).
CVE-2019-19814: (needs triaging) In the Linux kernel 5.0.21, mounting a crafted f2fs filesystem image can cause __remove_dirty_segment slab-out-of-bounds write access because an array is bounded by the number of dirty types (8) but the array index can exceed this.
CVE-2019-20794: (postponed; to be fixed through a stable update) An issue was discovered in the Linux kernel 4.18 through 5.6.11 when unprivileged user namespaces are allowed. A user can create their own PID namespace, and mount a FUSE filesystem. Upon interaction with this FUSE filesystem, if the userspace component is terminated via a kill of the PID namespace's pid 1, it will result in a hung task, and resources being permanently locked up until system reboot. This can result in resource exhaustion.

28 ignored issues:

CVE-2013-7445: The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated by JavaScript code that creates many CANVAS elements for rendering by Chrome or Firefox.
CVE-2022-0480: A flaw was found in the filelock_init in fs/locks.c function in the Linux kernel. This issue can lead to host memory exhaustion due to memcg not limiting the number of Portable Operating System Interface (POSIX) file locks.
CVE-2023-3006: A known cache speculation vulnerability, known as Branch History Injection (BHI) or Spectre-BHB, becomes actual again for the new hw AmpereOne. Spectre-BHB is similar to Spectre v2, except that malicious code uses the shared branch history (stored in the CPU Branch History Buffer, or BHB) to influence mispredicted branches within the victim's hardware context. Once that occurs, speculation caused by the mispredicted branches can cause cache allocation. This issue leads to obtaining information that should not be accessible.
CVE-2018-12928: In the Linux kernel 4.15.0, a NULL pointer dereference was discovered in hfs_ext_read_extent in hfs.ko. This can occur during a mount of a crafted hfs filesystem.
CVE-2020-12362: Integer overflow in the firmware for some Intel(R) Graphics Drivers for Windows * before version 26.20.100.7212 and before Linux kernel version 5.5 may allow a privileged user to potentially enable an escalation of privilege via local access.
CVE-2020-12363: Improper input validation in some Intel(R) Graphics Drivers for Windows* before version 26.20.100.7212 and before Linux kernel version 5.5 may allow a privileged user to potentially enable a denial of service via local access.
CVE-2020-12364: Null pointer reference in some Intel(R) Graphics Drivers for Windows* before version 26.20.100.7212 and before version Linux kernel version 5.5 may allow a privileged user to potentially enable a denial of service via local access.
CVE-2020-14304: A memory disclosure flaw was found in the Linux kernel's ethernet drivers, in the way it read data from the EEPROM of the device. This flaw allows a local user to read uninitialized values from the kernel memory. The highest threat from this vulnerability is to confidentiality.
CVE-2021-38207: drivers/net/ethernet/xilinx/ll_temac_main.c in the Linux kernel before 5.12.13 allows remote attackers to cause a denial of service (buffer overflow and lockup) by sending heavy network traffic for about ten minutes.
CVE-2022-21499: KGDB and KDB allow read and write access to kernel memory, and thus should be restricted during lockdown. An attacker with access to a serial port could trigger the debugger so it is important that the debugger respect the lockdown mode when/if it is triggered. CVSS 3.1 Base Score 6.7 (Confidentiality, Integrity and Availability impacts). CVSS Vector: (CVSS:3.1/AV:L/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H).
CVE-2022-29900: Mis-trained branch predictions for return instructions may allow arbitrary speculative code execution under certain microarchitecture-dependent conditions.
CVE-2023-20569: A side channel vulnerability on some of the AMD CPUs may allow an attacker to influence the return address prediction. This may result in speculative execution at an attacker-controlled address, potentially leading to information disclosure.
CVE-2023-20938: In binder_transaction_buffer_release of binder.c, there is a possible use after free due to improper input validation. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation.Product: AndroidVersions: Android kernelAndroid ID: A-257685302References: Upstream kernel
CVE-2023-28466: do_tls_getsockopt in net/tls/tls_main.c in the Linux kernel through 6.2.6 lacks a lock_sock call, leading to a race condition (with a resultant use-after-free or NULL pointer dereference).
CVE-2023-52451: In the Linux kernel, the following vulnerability has been resolved: powerpc/pseries/memhp: Fix access beyond end of drmem array dlpar_memory_remove_by_index() may access beyond the bounds of the drmem lmb array when the LMB lookup fails to match an entry with the given DRC index. When the search fails, the cursor is left pointing to &drmem_info->lmbs[drmem_info->n_lmbs], which is one element past the last valid entry in the array. The debug message at the end of the function then dereferences this pointer: pr_debug("Failed to hot-remove memory at %llx\n", lmb->base_addr); This was found by inspection and confirmed with KASAN: pseries-hotplug-mem: Attempting to hot-remove LMB, drc index 1234 ================================================================== BUG: KASAN: slab-out-of-bounds in dlpar_memory+0x298/0x1658 Read of size 8 at addr c000000364e97fd0 by task bash/949 dump_stack_lvl+0xa4/0xfc (unreliable) print_report+0x214/0x63c kasan_report+0x140/0x2e0 __asan_load8+0xa8/0xe0 dlpar_memory+0x298/0x1658 handle_dlpar_errorlog+0x130/0x1d0 dlpar_store+0x18c/0x3e0 kobj_attr_store+0x68/0xa0 sysfs_kf_write+0xc4/0x110 kernfs_fop_write_iter+0x26c/0x390 vfs_write+0x2d4/0x4e0 ksys_write+0xac/0x1a0 system_call_exception+0x268/0x530 system_call_vectored_common+0x15c/0x2ec Allocated by task 1: kasan_save_stack+0x48/0x80 kasan_set_track+0x34/0x50 kasan_save_alloc_info+0x34/0x50 __kasan_kmalloc+0xd0/0x120 __kmalloc+0x8c/0x320 kmalloc_array.constprop.0+0x48/0x5c drmem_init+0x2a0/0x41c do_one_initcall+0xe0/0x5c0 kernel_init_freeable+0x4ec/0x5a0 kernel_init+0x30/0x1e0 ret_from_kernel_user_thread+0x14/0x1c The buggy address belongs to the object at c000000364e80000 which belongs to the cache kmalloc-128k of size 131072 The buggy address is located 0 bytes to the right of allocated 98256-byte region [c000000364e80000, c000000364e97fd0) ================================================================== pseries-hotplug-mem: Failed to hot-remove memory at 0 Log failed lookups with a separate message and dereference the cursor only when it points to a valid entry.
CVE-2023-52597: In the Linux kernel, the following vulnerability has been resolved: KVM: s390: fix setting of fpc register kvm_arch_vcpu_ioctl_set_fpu() allows to set the floating point control (fpc) register of a guest cpu. The new value is tested for validity by temporarily loading it into the fpc register. This may lead to corruption of the fpc register of the host process: if an interrupt happens while the value is temporarily loaded into the fpc register, and within interrupt context floating point or vector registers are used, the current fp/vx registers are saved with save_fpu_regs() assuming they belong to user space and will be loaded into fp/vx registers when returning to user space. test_fp_ctl() restores the original user space / host process fpc register value, however it will be discarded, when returning to user space. In result the host process will incorrectly continue to run with the value that was supposed to be used for a guest cpu. Fix this by simply removing the test. There is another test right before the SIE context is entered which will handles invalid values. This results in a change of behaviour: invalid values will now be accepted instead of that the ioctl fails with -EINVAL. This seems to be acceptable, given that this interface is most likely not used anymore, and this is in addition the same behaviour implemented with the memory mapped interface (replace invalid values with zero) - see sync_regs() in kvm-s390.c.
CVE-2023-52598: In the Linux kernel, the following vulnerability has been resolved: s390/ptrace: handle setting of fpc register correctly If the content of the floating point control (fpc) register of a traced process is modified with the ptrace interface the new value is tested for validity by temporarily loading it into the fpc register. This may lead to corruption of the fpc register of the tracing process: if an interrupt happens while the value is temporarily loaded into the fpc register, and within interrupt context floating point or vector registers are used, the current fp/vx registers are saved with save_fpu_regs() assuming they belong to user space and will be loaded into fp/vx registers when returning to user space. test_fp_ctl() restores the original user space fpc register value, however it will be discarded, when returning to user space. In result the tracer will incorrectly continue to run with the value that was supposed to be used for the traced process. Fix this by saving fpu register contents with save_fpu_regs() before using test_fp_ctl().
CVE-2023-52606: In the Linux kernel, the following vulnerability has been resolved: powerpc/lib: Validate size for vector operations Some of the fp/vmx code in sstep.c assume a certain maximum size for the instructions being emulated. The size of those operations however is determined separately in analyse_instr(). Add a check to validate the assumption on the maximum size of the operations, so as to prevent any unintended kernel stack corruption.
CVE-2023-52607: In the Linux kernel, the following vulnerability has been resolved: powerpc/mm: Fix null-pointer dereference in pgtable_cache_add kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity.
CVE-2023-52675: In the Linux kernel, the following vulnerability has been resolved: powerpc/imc-pmu: Add a null pointer check in update_events_in_group() kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure.
CVE-2023-52686: In the Linux kernel, the following vulnerability has been resolved: powerpc/powernv: Add a null pointer check in opal_event_init() kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure.
CVE-2024-26654: In the Linux kernel, the following vulnerability has been resolved: ALSA: sh: aica: reorder cleanup operations to avoid UAF bugs The dreamcastcard->timer could schedule the spu_dma_work and the spu_dma_work could also arm the dreamcastcard->timer. When the snd_pcm_substream is closing, the aica_channel will be deallocated. But it could still be dereferenced in the worker thread. The reason is that del_timer() will return directly regardless of whether the timer handler is running or not and the worker could be rescheduled in the timer handler. As a result, the UAF bug will happen. The racy situation is shown below: (Thread 1) | (Thread 2) snd_aicapcm_pcm_close() | ... | run_spu_dma() //worker | mod_timer() flush_work() | del_timer() | aica_period_elapsed() //timer kfree(dreamcastcard->channel) | schedule_work() | run_spu_dma() //worker ... | dreamcastcard->channel-> //USE In order to mitigate this bug and other possible corner cases, call mod_timer() conditionally in run_spu_dma(), then implement PCM sync_stop op to cancel both the timer and worker. The sync_stop op will be called from PCM core appropriately when needed.
CVE-2024-26751: In the Linux kernel, the following vulnerability has been resolved: ARM: ep93xx: Add terminator to gpiod_lookup_table Without the terminator, if a con_id is passed to gpio_find() that does not exist in the lookup table the function will not stop looping correctly, and eventually cause an oops.
CVE-2024-26957: In the Linux kernel, the following vulnerability has been resolved: s390/zcrypt: fix reference counting on zcrypt card objects Tests with hot-plugging crytpo cards on KVM guests with debug kernel build revealed an use after free for the load field of the struct zcrypt_card. The reason was an incorrect reference handling of the zcrypt card object which could lead to a free of the zcrypt card object while it was still in use. This is an example of the slab message: kernel: 0x00000000885a7512-0x00000000885a7513 @offset=1298. First byte 0x68 instead of 0x6b kernel: Allocated in zcrypt_card_alloc+0x36/0x70 [zcrypt] age=18046 cpu=3 pid=43 kernel: kmalloc_trace+0x3f2/0x470 kernel: zcrypt_card_alloc+0x36/0x70 [zcrypt] kernel: zcrypt_cex4_card_probe+0x26/0x380 [zcrypt_cex4] kernel: ap_device_probe+0x15c/0x290 kernel: really_probe+0xd2/0x468 kernel: driver_probe_device+0x40/0xf0 kernel: __device_attach_driver+0xc0/0x140 kernel: bus_for_each_drv+0x8c/0xd0 kernel: __device_attach+0x114/0x198 kernel: bus_probe_device+0xb4/0xc8 kernel: device_add+0x4d2/0x6e0 kernel: ap_scan_adapter+0x3d0/0x7c0 kernel: ap_scan_bus+0x5a/0x3b0 kernel: ap_scan_bus_wq_callback+0x40/0x60 kernel: process_one_work+0x26e/0x620 kernel: worker_thread+0x21c/0x440 kernel: Freed in zcrypt_card_put+0x54/0x80 [zcrypt] age=9024 cpu=3 pid=43 kernel: kfree+0x37e/0x418 kernel: zcrypt_card_put+0x54/0x80 [zcrypt] kernel: ap_device_remove+0x4c/0xe0 kernel: device_release_driver_internal+0x1c4/0x270 kernel: bus_remove_device+0x100/0x188 kernel: device_del+0x164/0x3c0 kernel: device_unregister+0x30/0x90 kernel: ap_scan_adapter+0xc8/0x7c0 kernel: ap_scan_bus+0x5a/0x3b0 kernel: ap_scan_bus_wq_callback+0x40/0x60 kernel: process_one_work+0x26e/0x620 kernel: worker_thread+0x21c/0x440 kernel: kthread+0x150/0x168 kernel: __ret_from_fork+0x3c/0x58 kernel: ret_from_fork+0xa/0x30 kernel: Slab 0x00000372022169c0 objects=20 used=18 fp=0x00000000885a7c88 flags=0x3ffff00000000a00(workingset|slab|node=0|zone=1|lastcpupid=0x1ffff) kernel: Object 0x00000000885a74b8 @offset=1208 fp=0x00000000885a7c88 kernel: Redzone 00000000885a74b0: bb bb bb bb bb bb bb bb ........ kernel: Object 00000000885a74b8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk kernel: Object 00000000885a74c8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk kernel: Object 00000000885a74d8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk kernel: Object 00000000885a74e8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk kernel: Object 00000000885a74f8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk kernel: Object 00000000885a7508: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 68 4b 6b 6b 6b a5 kkkkkkkkkkhKkkk. kernel: Redzone 00000000885a7518: bb bb bb bb bb bb bb bb ........ kernel: Padding 00000000885a756c: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZZZZZ kernel: CPU: 0 PID: 387 Comm: systemd-udevd Not tainted 6.8.0-HF #2 kernel: Hardware name: IBM 3931 A01 704 (KVM/Linux) kernel: Call Trace: kernel: [<00000000ca5ab5b8>] dump_stack_lvl+0x90/0x120 kernel: [<00000000c99d78bc>] check_bytes_and_report+0x114/0x140 kernel: [<00000000c99d53cc>] check_object+0x334/0x3f8 kernel: [<00000000c99d820c>] alloc_debug_processing+0xc4/0x1f8 kernel: [<00000000c99d852e>] get_partial_node.part.0+0x1ee/0x3e0 kernel: [<00000000c99d94ec>] ___slab_alloc+0xaf4/0x13c8 kernel: [<00000000c99d9e38>] __slab_alloc.constprop.0+0x78/0xb8 kernel: [<00000000c99dc8dc>] __kmalloc+0x434/0x590 kernel: [<00000000c9b4c0ce>] ext4_htree_store_dirent+0x4e/0x1c0 kernel: [<00000000c9b908a2>] htree_dirblock_to_tree+0x17a/0x3f0 kernel: ---truncated---
CVE-2024-26999: In the Linux kernel, the following vulnerability has been resolved: serial/pmac_zilog: Remove flawed mitigation for rx irq flood The mitigation was intended to stop the irq completely. That may be better than a hard lock-up but it turns out that you get a crash anyway if you're using pmac_zilog as a serial console: ttyPZ0: pmz: rx irq flood ! BUG: spinlock recursion on CPU#0, swapper/0 That's because the pr_err() call in pmz_receive_chars() results in pmz_console_write() attempting to lock a spinlock already locked in pmz_interrupt(). With CONFIG_DEBUG_SPINLOCK=y, this produces a fatal BUG splat. The spinlock in question is the one in struct uart_port. Even when it's not fatal, the serial port rx function ceases to work. Also, the iteration limit doesn't play nicely with QEMU, as can be seen in the bug report linked below. A web search for other reports of the error message "pmz: rx irq flood" didn't produce anything. So I don't think this code is needed any more. Remove it.
CVE-2024-27000: In the Linux kernel, the following vulnerability has been resolved: serial: mxs-auart: add spinlock around changing cts state The uart_handle_cts_change() function in serial_core expects the caller to hold uport->lock. For example, I have seen the below kernel splat, when the Bluetooth driver is loaded on an i.MX28 board. [ 85.119255] ------------[ cut here ]------------ [ 85.124413] WARNING: CPU: 0 PID: 27 at /drivers/tty/serial/serial_core.c:3453 uart_handle_cts_change+0xb4/0xec [ 85.134694] Modules linked in: hci_uart bluetooth ecdh_generic ecc wlcore_sdio configfs [ 85.143314] CPU: 0 PID: 27 Comm: kworker/u3:0 Not tainted 6.6.3-00021-gd62a2f068f92 #1 [ 85.151396] Hardware name: Freescale MXS (Device Tree) [ 85.156679] Workqueue: hci0 hci_power_on [bluetooth] (...) [ 85.191765] uart_handle_cts_change from mxs_auart_irq_handle+0x380/0x3f4 [ 85.198787] mxs_auart_irq_handle from __handle_irq_event_percpu+0x88/0x210 (...)
CVE-2024-38607: In the Linux kernel, the following vulnerability has been resolved: macintosh/via-macii: Fix "BUG: sleeping function called from invalid context" The via-macii ADB driver calls request_irq() after disabling hard interrupts. But disabling interrupts isn't necessary here because the VIA shift register interrupt was masked during VIA1 initialization.
CVE-2024-38613: In the Linux kernel, the following vulnerability has been resolved: m68k: Fix spinlock race in kernel thread creation Context switching does take care to retain the correct lock owner across the switch from 'prev' to 'next' tasks. This does rely on interrupts remaining disabled for the entire duration of the switch. This condition is guaranteed for normal process creation and context switching between already running processes, because both 'prev' and 'next' already have interrupts disabled in their saved copies of the status register. The situation is different for newly created kernel threads. The status register is set to PS_S in copy_thread(), which does leave the IPL at 0. Upon restoring the 'next' thread's status register in switch_to() aka resume(), interrupts then become enabled prematurely. resume() then returns via ret_from_kernel_thread() and schedule_tail() where run queue lock is released (see finish_task_switch() and finish_lock_switch()). A timer interrupt calling scheduler_tick() before the lock is released in finish_task_switch() will find the lock already taken, with the current task as lock owner. This causes a spinlock recursion warning as reported by Guenter Roeck. As far as I can ascertain, this race has been opened in commit 533e6903bea0 ("m68k: split ret_from_fork(), simplify kernel_thread()") but I haven't done a detailed study of kernel history so it may well predate that commit. Interrupts cannot be disabled in the saved status register copy for kernel threads (init will complain about interrupts disabled when finally starting user space). Disable interrupts temporarily when switching the tasks' register sets in resume(). Note that a simple oriw 0x700,%sr after restoring sr is not enough here - this leaves enough of a race for the 'spinlock recursion' warning to still be observed. Tested on ARAnyM and qemu (Quadra 800 emulation).

Created: 2022-07-04 Last update: 2024-06-29 13:15

13 bugs tagged patch in the BTS normal

The BTS contains patches fixing 13 bugs (15 if counting merged bugs), consider including or untagging them.

Created: 2026-04-06 Last update: 2026-04-26 21:00

Fails to build during reproducibility testing normal

A package building reproducibly enables third parties to verify that the source matches the distributed binaries. It has been identified that this source package produced different results, failed to build or had other issues in a test environment. Please read about how to improve the situation!

Created: 2026-03-22 Last update: 2026-04-26 19:31

version in VCS is newer than in repository, is it time to upload? normal

vcswatch reports that this package seems to have a new changelog entry (version 7.0.1-1~exp2, distribution UNRELEASED) and new commits in its VCS. You should consider whether it's time to make an upload.

Here are the relevant commit messages:

commit dd9f3c5e98e0fc8ec9d08a4bf38403974b402eea
Merge: d66e0cb13 12193e022
Author: Salvatore Bonaccorso <carnil@debian.org>
Date:   Sun Apr 26 14:30:38 2026 +0200

    Merge branch 'milkv-jupiter' into 'debian/latest'
    
    [riscv64] Backport support for additional devices on the Milk-V Jupiter board from 7.1
    
    See merge request kernel-team/linux!1882

commit 12193e02292f1fe065cde72cabdb5e77eab66d2a
Author: Aurelien Jarno <aurelien@aurel32.net>
Date:   Fri Apr 17 19:25:25 2026 +0200

    [riscv64] Backport support for additional devices on the Milk-V Jupiter board from 7.1

Created: 2026-04-26 Last update: 2026-04-26 18:32

20 open merge requests in Salsa normal

There are 20 open merge requests for this package on Salsa. You should consider reviewing and/or merging these merge requests.

Created: 2025-09-16 Last update: 2026-04-26 14:02

debian/patches: 35 patches to forward upstream low

Among the 79 debian patches available in version 6.19.14-1 of the package, we noticed the following issues:

35 patches where the metadata indicates that the patch has not yet been forwarded upstream. You should either forward the patch upstream or update the metadata to document its real status.

Created: 2023-02-26 Last update: 2026-04-25 23:03

Standards version of the package is outdated. wishlist

The package should be updated to follow the last version of Debian Policy (Standards-Version 4.7.4 instead of 4.2.0).

Created: 2017-12-02 Last update: 2026-04-25 15:17

testing migrations

This package will soon be part of the auto-libconfig transition. You might want to ensure that your package is ready for it. You can probably find supplementary information in the debian-release archives or in the corresponding release.debian.org bug.
This package will soon be part of the auto-openssl transition. You might want to ensure that your package is ready for it. You can probably find supplementary information in the debian-release archives or in the corresponding release.debian.org bug.
excuses:
- Migrates after: linux-signed-amd64, linux-signed-arm64
- Migration status for linux (6.19.13-1 to 6.19.14-1): BLOCKED: Maybe temporary, maybe blocked but Britney is missing information (check below)
- Issues preventing migration:
- ∙ ∙ Lintian triggered tags: aliased-location - info
- ∙ ∙ Missing build on riscv64
- ∙ ∙ Autopkgtest deferred on riscv64: missing arch:riscv64 build
- ∙ ∙ Autopkgtest for cryptsetup/2:2.8.6-1: amd64: Failed (not a regression) ♻ (reference ♻), arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for debvm/0.5.2: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for dracut/110-12: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for genext2fs/1.5.0-3: amd64: Pass, arm64: Pass, i386: Failed (not a regression) ♻ (reference ♻), ppc64el: Reference test triggered, but real test failed already ♻, s390x: Test triggered (will not be considered a regression) ♻ (reference ♻)
- ∙ ∙ Autopkgtest for glibc/2.42-15: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for golang-github-gopacket-gopacket/1.3.0-2: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for golang-gvisor-gvisor/0.0~20240729.0-7: amd64: Failed (not a regression) ♻ (reference ♻), arm64: Failed (not a regression) ♻ (reference ♻), i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for gopacket/1.1.19-6.2: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for iproute2/7.0.0-1: amd64: Pass, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for klibc/2.0.14-1: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for lava/2026.02-3: amd64: Pass, arm64: Pass, i386: Failed (not a regression) ♻ (reference ♻), ppc64el: Failed (not a regression) ♻ (reference ♻), s390x: Test triggered
- ∙ ∙ Autopkgtest for leds-alix/0.0.1-6: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for libguestfs/1:1.58.1-5: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for liburing/2.14-1: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for linux/6.19.14-1: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for lxcfs/6.0.6-1: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for mimic/0.7.0+ds-2: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for miniramfs/1.0.6: amd64: Pass, arm64: Pass, i386: Failed (not a regression) ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for mkosi/26-3: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for multipath-tools/0.14.3-2: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: No tests, superficial or marked flaky ♻ (reference ♻), s390x: Test triggered
- ∙ ∙ Autopkgtest for open-iscsi/2.1.11-4: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for rust-virtiofsd/1.13.2-6: amd64: Pass, arm64: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for sbuild/0.91.8: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for v4l2loopback/0.15.3-1: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for west-chamber/20100405+svn20111107.r124-14.3: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for wireguard/1.0.20250521-1: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for wireless-regdb/2026.02.04-1: amd64: Pass, arm64: Pass, i386: Pass, ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for xone-dkms/0.5.8-1: amd64: Pass, arm64: Pass, i386: Failed (not a regression) ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for xpadneo-dkms/0.10.1-1: amd64: Pass, arm64: Pass, i386: Failed (not a regression) ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Autopkgtest for xtables-addons/3.30-1: amd64: No tests, superficial or marked flaky ♻, arm64: No tests, superficial or marked flaky ♻, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: No tests, superficial or marked flaky ♻, s390x: Test triggered
- ∙ ∙ Autopkgtest for zfs-linux/2.4.1-1: amd64: Pass, arm64: Pass, i386: No tests, superficial or marked flaky ♻ (reference ♻), ppc64el: Pass, s390x: Test triggered
- ∙ ∙ Too young, only 2 of 5 days old
- ∙ ∙ Depends: linux linux-signed-amd64
- ∙ ∙ Depends: linux linux-signed-arm64
- Additional info (not blocking):
- ∙ ∙ Piuparts tested OK - https://piuparts.debian.org/sid/source/l/linux.html
- ∙ ∙ Lintian issues ignored as requested by elbrus
- ∙ ∙ Reproducibility check waiting for results on amd64
- ∙ ∙ Reproducibility check waiting for results on arm64
- ∙ ∙ Reproducibility check waiting for results on armhf
- ∙ ∙ Not reproduced on i386 (not a regression): linux-doc-6.19
- ∙ ∙ Reproducibility check waiting for results on ppc64el
- Not considered

news

[rss feed]

[2026-04-25] Accepted linux 6.19.14-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-04-25] linux 6.19.13-1 MIGRATED to testing (Debian testing watch)
[2026-04-23] Accepted linux 7.0.1-1~exp1 (source) into experimental (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-04-18] Accepted linux 6.19.13-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-04-16] Accepted linux 6.19.11-1~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-04-14] Accepted linux 7.0-1~exp1 (source) into experimental (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-04-13] Accepted linux 6.19.12-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-04-11] linux 6.19.11-1 MIGRATED to testing (Debian testing watch)
[2026-04-05] Accepted linux 6.19.10-1~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-04-05] Accepted linux 6.19.11-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-04-02] linux 6.19.10-1 MIGRATED to testing (Debian testing watch)
[2026-03-30] Accepted linux 6.19.8-1~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-03-27] Accepted linux 6.19.10-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-21] linux 6.19.8-1 MIGRATED to testing (Debian testing watch)
[2026-03-15] Accepted linux 6.19.6-2~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-03-15] Accepted linux 6.12.74-2~bpo12+1 (source) into oldstable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-03-15] Accepted linux 6.19.8-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-15] linux 6.19.6-2 MIGRATED to testing (Debian testing watch)
[2026-03-14] Accepted linux 6.12.74-2 (source) into proposed-updates (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-14] Accepted linux 6.18.15-1~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-03-13] Accepted linux 6.1.164-1 (source) into oldstable-proposed-updates (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-13] Accepted linux 5.10.251-1 (source) into oldoldstable-security (Debian FTP Masters) (signed by: Ben Hutchings)
[2026-03-13] linux 6.19.6-1 MIGRATED to testing (Debian testing watch)
[2026-03-13] Accepted linux 6.19.6-2 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-12] Accepted linux 6.12.74-1 (source) into stable-security (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-12] Accepted linux 6.12.74-2 (source) into stable-security (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-12] Accepted linux 6.1.164-1 (source) into oldstable-security (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-06] Accepted linux 6.19.6-1 (source) into unstable (Debian FTP Masters) (signed by: Salvatore Bonaccorso)
[2026-03-05] linux 6.18.15-1 MIGRATED to testing (Debian testing watch)
[2026-02-28] Accepted linux 6.18.12-1~bpo13+1 (source) into stable-backports (Debian FTP Masters) (signed by: Ben Hutchings)

bugs [bug history graph]

all: 298 325
RC: 1
I&N: 256 282
M&W: 40 41
F&P: 1
patch: 13 15

links

homepage
lintian (8149, 61)
buildd: logs, exp, reproducibility
popcon
browse source code
other distros
security tracker
l10n (-, 57)
debian patches
debci

ubuntu

[Information about Ubuntu for Debian Developers]

version: 7.0.0-14.14
2606 bugs (78 patches)