- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 0/5] drm: LoongArch: fix rx550/gfx6/gfx7/gfx8 error
by Hongchen Zhang 21 Apr '25

21 Apr '25

Tianrui Zhao (3): drm/amdgpu: Fix pcie order dislocation drm/amdgpu: make duplicated EOP packet for GFX6 have real content drm/amdgpu: Fix RX550 pcie order dislocation. lvjianmin (2): drm/radeon: repeat the same EOP packet for EOP workaround on CIK drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 + drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c | 159 ++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 6 + drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 4 + drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h | 3 + drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 19 +++ drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 13 +- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 13 +- drivers/gpu/drm/radeon/cik.c | 9 +- 9 files changed, 216 insertions(+), 15 deletions(-) -- 2.33.0

2 6

[PATCH OLK-6.6 0/5] drm: LoongArch: fix rx550/gfx6/gfx7/gfx8 error
by Hongchen Zhang 21 Apr '25

21 Apr '25

Tianrui Zhao (3): drm/amdgpu: Fix pcie order dislocation drm/amdgpu: make duplicated EOP packet for GFX6 have real content drm/amdgpu: Fix RX550 pcie order dislocation. lvjianmin (2): drm/radeon: repeat the same EOP packet for EOP workaround on CIK drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 + drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c | 159 ++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 6 + drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 4 + drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h | 3 + drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 19 +++ drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 13 +- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 13 +- drivers/gpu/drm/radeon/cik.c | 9 +- 9 files changed, 216 insertions(+), 15 deletions(-) -- 2.33.0

2 6

[PATCH OLK-6.6 v3 00/18] fs/resctrl: Introduce the resctrl_feat_type
by Zeng Heng 21 Apr '25

21 Apr '25

Compare to v2: Patch 09: Merge the changes related to the impact on the common layer in Patch 10. Patch 18: New patch added. Compare to v1: Patch 5: Update the condition for MPAM to determine whether to perform MBM overflow checking. Patch 15: Split the original patch and merge part of the fix content into Patch 9. Jason Zeng (1): fs/resctrl: Support arch specific struct resctrl_arch_staged_config Zeng Heng (17): arm64/mpam: fix memleak in resctrl_arch_mon_ctx_alloc_no_wait() arm64/mpam: fix impossible condition in get_cpumask_from_cache_id() arm64/mpam: fix impossible condition in resctrl_arch_rmid_read() arm64/mpam: Optimize CSU/MBWU monitor multiplexing fs/resctrl: Determine whether the MBM monitors require overflow checking arm64/mpam: Set the cpbm width of msc class with the minimum arm64/mpam: Correct the judgment condition of the CMAX feature fs/resctrl: Fix kmemleak caused by closid_init() fs/resctrl: Introduce the resctrl_feat_type arm64/mpam: Add mbw_min and cmin features arm64/mpam: Add PRIO feature arm64/mpam: Add CMAX feature arm64/mpam: Add PBM feature arm64/mpam: Add limit feature arm64/mpam: Fix allocated cache size information fs/resctrl: Fix configuration to wrong control group when CDP is enabled arm64/mpam: Add debugging information about CDP monitor value arch/x86/include/asm/resctrl.h | 33 ++ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 16 +- drivers/platform/mpam/mpam_devices.c | 111 +++++-- drivers/platform/mpam/mpam_internal.h | 25 +- drivers/platform/mpam/mpam_resctrl.c | 355 +++++++++++++++++----- fs/resctrl/ctrlmondata.c | 141 ++++++++- fs/resctrl/monitor.c | 5 +- fs/resctrl/rdtgroup.c | 135 ++++---- include/linux/arm_mpam.h | 11 + include/linux/resctrl.h | 32 +- include/linux/resctrl_types.h | 20 ++ 11 files changed, 692 insertions(+), 192 deletions(-) -- 2.25.1

2 19

[openeuler:OLK-6.6 2139/2139] drivers/cpufreq/cppc_cpufreq.c:852:19: error: dereferencing pointer to incomplete type 'struct fb_ctr_pair'
by kernel test robot 21 Apr '25

21 Apr '25

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: bf197758b04f43e61ebab66520f1420c1b64853c commit: 12f136b2134d4ded731c3ef23ac08c85b9c0b1fa [2139/2139] cpufreq: CPPC: Keep the target core awake when reading its cpufreq rate config: arm64-randconfig-002-20250421 (https://download.01.org/0day-ci/archive/20250421/202504211352.ik4vkTIa-lkp@…) compiler: aarch64-linux-gcc (GCC) 7.5.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250421/202504211352.ik4vkTIa-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202504211352.ik4vkTIa-lkp@intel.com/ All errors (new ones prefixed by >>): drivers/cpufreq/cppc_cpufreq.c: In function 'cppc_get_perf_ctrs_pair': >> drivers/cpufreq/cppc_cpufreq.c:852:19: error: dereferencing pointer to incomplete type 'struct fb_ctr_pair' int cpu = fb_ctrs->cpu; ^~ drivers/cpufreq/cppc_cpufreq.c: In function 'cppc_cpufreq_get_rate': drivers/cpufreq/cppc_cpufreq.c:866:9: error: variable 'fb_ctrs' has initializer but incomplete type struct fb_ctr_pair fb_ctrs = { .cpu = cpu, }; ^~~~~~~~~~~ drivers/cpufreq/cppc_cpufreq.c:866:34: error: 'struct fb_ctr_pair' has no member named 'cpu' struct fb_ctr_pair fb_ctrs = { .cpu = cpu, }; ^~~ drivers/cpufreq/cppc_cpufreq.c:866:40: warning: excess elements in struct initializer struct fb_ctr_pair fb_ctrs = { .cpu = cpu, }; ^~~ drivers/cpufreq/cppc_cpufreq.c:866:40: note: (near initialization for 'fb_ctrs') drivers/cpufreq/cppc_cpufreq.c:866:21: error: storage size of 'fb_ctrs' isn't known struct fb_ctr_pair fb_ctrs = { .cpu = cpu, }; ^~~~~~~ drivers/cpufreq/cppc_cpufreq.c:866:21: warning: unused variable 'fb_ctrs' [-Wunused-variable] vim +852 drivers/cpufreq/cppc_cpufreq.c 848 849 static int cppc_get_perf_ctrs_pair(void *val) 850 { 851 struct fb_ctr_pair *fb_ctrs = val; > 852 int cpu = fb_ctrs->cpu; 853 int ret; 854 855 ret = cppc_get_perf_ctrs(cpu, &fb_ctrs->fb_ctrs_t0); 856 if (ret) 857 return ret; 858 859 udelay(2); /* 2usec delay between sampling */ 860 861 return cppc_get_perf_ctrs(cpu, &fb_ctrs->fb_ctrs_t1); 862 } 863 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[OLK-6.6 00/10] crypto: hisilicon - some bugfix
by Weili Qian 21 Apr '25

21 Apr '25

From: JiangShui Yang <yangjiangshui(a)h-partners.com> Weili Qian (8): crypto: hisilicon/sec2: fix memory use-after-free issue crypto: hisilicon/qm - invalidate queues in use crypto: hisilicon/qm - mask axi error before memory init crypto: hisilicon/qm - modify interrupt processing resource application crypto: hisilicon/qm - fix the pf2vf timeout when global reset crypto: hisilicon/qm - obtain the mailbox configuration at one time hisi_acc_vfio_pci: obtain the mailbox configuration at one time crypto: hisilicon/qm - disable error report before flr Wenkai Lin (1): crypto: hisilicon/sec2 - fix for gcm spec check Zhiqi Song (1): crypto: hisilicon/hpre - fix dma unmap sequence drivers/crypto/hisilicon/hpre/hpre_crypto.c | 8 +- drivers/crypto/hisilicon/hpre/hpre_main.c | 103 ++-- drivers/crypto/hisilicon/qm.c | 561 ++++++++++++------ drivers/crypto/hisilicon/sec2/sec_crypto.c | 53 +- drivers/crypto/hisilicon/sec2/sec_main.c | 92 ++- drivers/crypto/hisilicon/zip/zip_main.c | 104 ++-- .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 45 +- include/linux/hisi_acc_qm.h | 33 +- 8 files changed, 604 insertions(+), 395 deletions(-) -- 2.43.0

1 10

[PATCH OLK-6.6 v3 00/18] fs/resctrl: Introduce the resctrl_feat_type
by Zeng Heng 21 Apr '25

21 Apr '25

Compare to v2: Patch 09: Merge the changes related to the impact on the common layer in Patch 10. Patch 18: New patch added. Compare to v1: Patch 5: Update the condition for MPAM to determine whether to perform MBM overflow checking. Patch 15: Split the original patch and merge part of the fix content into Patch 9. Jason Zeng (1): fs/resctrl: Support arch specific struct resctrl_arch_staged_config Zeng Heng (17): arm64/mpam: fix memleak in resctrl_arch_mon_ctx_alloc_no_wait() arm64/mpam: fix impossible condition in get_cpumask_from_cache_id() arm64/mpam: fix impossible condition in resctrl_arch_rmid_read() arm64/mpam: Optimize CSU/MBWU monitor multiplexing fs/resctrl: Determine whether the MBM monitors require overflow checking arm64/mpam: Set the cpbm width of msc class with the minimum arm64/mpam: Correct the judgment condition of the CMAX feature fs/resctrl: Fix kmemleak caused by closid_init() fs/resctrl: Introduce the resctrl_feat_type arm64/mpam: Add mbw_min and cmin features arm64/mpam: Add PRIO feature arm64/mpam: Add CMAX feature arm64/mpam: Add PBM feature arm64/mpam: Add limit feature arm64/mpam: Fix allocated cache size information fs/resctrl: Fix configuration to wrong control group when CDP is enabled arm64/mpam: Add debugging information about CDP monitor value arch/x86/include/asm/resctrl.h | 33 ++ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 16 +- drivers/platform/mpam/mpam_devices.c | 111 +++++-- drivers/platform/mpam/mpam_internal.h | 25 +- drivers/platform/mpam/mpam_resctrl.c | 355 +++++++++++++++++----- fs/resctrl/ctrlmondata.c | 141 ++++++++- fs/resctrl/monitor.c | 5 +- fs/resctrl/rdtgroup.c | 135 ++++---- include/linux/arm_mpam.h | 11 + include/linux/resctrl.h | 32 +- include/linux/resctrl_types.h | 20 ++ 11 files changed, 692 insertions(+), 192 deletions(-) -- 2.25.1

2 19

[PATCH OLK-6.6 v3 00/18] fs/resctrl: Introduce the resctrl_feat_type
by Zeng Heng 21 Apr '25

21 Apr '25

Compare to v2: Patch 09: Merge the changes related to the impact on the common layer in Patch 10. Patch 18: New patch added. Compare to v1: Patch 5: Update the condition for MPAM to determine whether to perform MBM overflow checking. Patch 15: Split the original patch and merge part of the fix content into Patch 9. Jason Zeng (1): fs/resctrl: Support arch specific struct resctrl_arch_staged_config Zeng Heng (17): arm64/mpam: fix memleak in resctrl_arch_mon_ctx_alloc_no_wait() arm64/mpam: fix impossible condition in get_cpumask_from_cache_id() arm64/mpam: fix impossible condition in resctrl_arch_rmid_read() arm64/mpam: Optimize CSU/MBWU monitor multiplexing fs/resctrl: Determine whether the MBM monitors require overflow checking arm64/mpam: Set the cpbm width of msc class with the minimum arm64/mpam: Correct the judgment condition of the CMAX feature fs/resctrl: Fix kmemleak caused by closid_init() fs/resctrl: Introduce the resctrl_feat_type arm64/mpam: Add mbw_min and cmin features arm64/mpam: Add PRIO feature arm64/mpam: Add CMAX feature arm64/mpam: Add PBM feature arm64/mpam: Add limit feature arm64/mpam: Fix allocated cache size information fs/resctrl: Fix configuration to wrong control group when CDP is enabled arm64/mpam: Add debugging information about CDP monitor value arch/x86/include/asm/resctrl.h | 33 ++ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 16 +- drivers/platform/mpam/mpam_devices.c | 111 +++++-- drivers/platform/mpam/mpam_internal.h | 25 +- drivers/platform/mpam/mpam_resctrl.c | 355 +++++++++++++++++----- fs/resctrl/ctrlmondata.c | 141 ++++++++- fs/resctrl/monitor.c | 5 +- fs/resctrl/rdtgroup.c | 135 ++++---- include/linux/arm_mpam.h | 11 + include/linux/resctrl.h | 32 +- include/linux/resctrl_types.h | 20 ++ 11 files changed, 692 insertions(+), 192 deletions(-) -- 2.25.1

2 19

[PATCH OLK-5.10 0/4] block: fix UAF in blk_mq_has_sqsched()
by Zheng Qixing 21 Apr '25

21 Apr '25

The issue occurs in blk_mq_has_sqsched() function which accesses q->elevator pointer and its members without any protection. During device state changes, related memory structures might be freed, causing a Use-After-Free vulnerability. This patch introduces a QUEUE_FLAG_SQ_SCHED flag that is set during scheduler initialization, eliminating the need for runtime checks of scheduler features. This removes the need to access q->elevator at unsafe moments, resolving the UAF issue. Bart Van Assche (1): block: Decode all flag names in the debugfs output Christoph Hellwig (1): block: remove QUEUE_FLAG_DEAD Ming Lei (2): blk-mq: protect q->elevator by ->sysfs_lock in blk_mq_elv_switch_none blk-mq: avoid to touch q->elevator without any protection block/bfq-iosched.c | 3 +++ block/blk-core.c | 2 -- block/blk-mq-debugfs.c | 9 ++++----- block/blk-mq-sched.c | 1 + block/blk-mq.c | 22 +++++----------------- block/kyber-iosched.c | 3 ++- block/mq-deadline.c | 3 +++ drivers/block/mtip32xx/mtip32xx.c | 2 +- include/linux/blkdev.h | 4 ++-- include/linux/elevator.h | 2 -- 10 files changed, 21 insertions(+), 30 deletions(-) -- 2.39.2

2 5

[PATCH OLK-5.10] md/raid1: fix bitmap update when all write requests fail
by Zheng Qixing 21 Apr '25

21 Apr '25

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBKHTZ ------------------------ When writing to a RAID1 array where all member disks have bad sectors at the target location, the bitmap update is skipped because all bios[] are NULL, leading to bitmap counter inconsistency. This can cause subsequent I/O operations to hang while waiting for bitmap counter to reach the expected value. Fix this by updating the bitmap when all member disks have bad sectors. Fixes: 1f68f0c4b677 ("md/raid1: avoid writing to known-bad blocks on known-bad drives.") Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/md/raid1.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7c9155a5a468..11f649ed2466 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1537,6 +1537,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, } } + /* + * Corresponding to md_bitmap_endwrite() from close_write(), in the case + * io range from all member disks are badblocks. + */ + if (first_clone) + md_bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors, 0); + r1_bio_write_done(r1_bio); /* In case raid1d snuck in to freeze_array */ -- 2.39.2

2 1

[PATCH OLK-5.10] md/raid1: fix memory leak in raid1_run() if no active rdev
by Zheng Qixing 21 Apr '25

21 Apr '25

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBKXOB Reference: https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux.git/commit/?h=… ---------------------- When `raid1_set_limits()` fails or when the array has no active `rdev`, the allocated memory for `conf` is not properly freed. Add raid1_free() call to properly free the conf in error path. Fixes: 799af947ed13 ("md/raid1: don't free conf on raid0_run failure") Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> Conflicts: drivers/md/raid1.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/md/raid1.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 333b611aa152..7c9155a5a468 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -45,6 +45,7 @@ static void allow_barrier(struct r1conf *conf, sector_t sector_nr); static void lower_barrier(struct r1conf *conf, sector_t sector_nr); +static void raid1_free(struct mddev *mddev, void *priv); #define raid1_log(md, fmt, args...) \ do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0) @@ -3127,6 +3128,8 @@ static int raid1_run(struct mddev *mddev) */ if (conf->raid_disks - mddev->degraded < 1) { md_unregister_thread(&conf->thread); + if (!mddev->private) + raid1_free(mddev, conf); return -EINVAL; } -- 2.39.2

2 1