- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] sched/soft_domain: Increasing NR_MAX_CLUSTER to 32
by Zhang Qiao 25 Feb '26

25 Feb '26

hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8540 -------------------------------- Bumped the maximum number of clusters per node from 16 to 32 to resolve an out-of-bounds/array overflow issue. Fixes: 645a1ba256ef ("sched: topology: Build soft domain for LLC") Signed-off-by: Zhang Qiao <zhangqiao22(a)huawei.com> --- kernel/sched/soft_domain.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/sched/soft_domain.c b/kernel/sched/soft_domain.c index 3c52680ca82f..7b569fdb2c6e 100644 --- a/kernel/sched/soft_domain.c +++ b/kernel/sched/soft_domain.c @@ -17,6 +17,8 @@ #include <linux/sort.h> +#define NR_MAX_CLUSTER 32 + static DEFINE_STATIC_KEY_TRUE(__soft_domain_switch); static int __init soft_domain_switch_setup(char *str) @@ -50,6 +52,7 @@ static int build_soft_sub_domain(int nid, struct cpumask *cpus) const struct cpumask *span = cpumask_of_node(nid); struct soft_domain *sf_d = NULL; int i; + int cls_cnt = 0; sf_d = kzalloc_node(sizeof(struct soft_domain) + cpumask_size(), GFP_KERNEL, nid); @@ -63,6 +66,12 @@ static int build_soft_sub_domain(int nid, struct cpumask *cpus) for_each_cpu_and(i, span, cpus) { struct soft_subdomain *sub_d = NULL; + cls_cnt++; + if (cls_cnt > NR_MAX_CLUSTER) { + pr_info("clsuter number > %d, unsupport soft domain.\n", NR_MAX_CLUSTER); + return -EINVAL; + } + sub_d = kzalloc_node(sizeof(struct soft_subdomain) + cpumask_size(), GFP_KERNEL, nid); if (!sub_d) { @@ -138,8 +147,6 @@ void build_soft_domain(void) static DEFINE_MUTEX(soft_domain_mutex); -#define NR_MAX_CLUSTER 16 - struct domain_node { struct soft_subdomain *sud_d; unsigned int attached; -- 2.18.0.huawei.25

1 0

[PATCH OLK-6.6] sched/soft_domain: Increasing NR_MAX_CLUSTER to 32
by Zhang Qiao 25 Feb '26

25 Feb '26

hulk inclusion category: bugfix bugzilla: https://gitcode.com/openeuler/kernel/issues/8540 -------------------------------- Bumped the maximum number of clusters per node from 16 to 32 to resolve an out-of-bounds/array overflow issue. Fixes: 645a1ba256ef ("sched: topology: Build soft domain for LLC") Signed-off-by: Zhang Qiao <zhangqiao22(a)huawei.com> --- kernel/sched/soft_domain.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/kernel/sched/soft_domain.c b/kernel/sched/soft_domain.c index 3c52680ca82f..7b569fdb2c6e 100644 --- a/kernel/sched/soft_domain.c +++ b/kernel/sched/soft_domain.c @@ -17,6 +17,8 @@ #include <linux/sort.h> +#define NR_MAX_CLUSTER 32 + static DEFINE_STATIC_KEY_TRUE(__soft_domain_switch); static int __init soft_domain_switch_setup(char *str) @@ -50,6 +52,7 @@ static int build_soft_sub_domain(int nid, struct cpumask *cpus) const struct cpumask *span = cpumask_of_node(nid); struct soft_domain *sf_d = NULL; int i; + int cls_cnt = 0; sf_d = kzalloc_node(sizeof(struct soft_domain) + cpumask_size(), GFP_KERNEL, nid); @@ -63,6 +66,12 @@ static int build_soft_sub_domain(int nid, struct cpumask *cpus) for_each_cpu_and(i, span, cpus) { struct soft_subdomain *sub_d = NULL; + cls_cnt++; + if (cls_cnt > NR_MAX_CLUSTER) { + pr_info("clsuter number > %d, unsupport soft domain.\n", NR_MAX_CLUSTER); + return -EINVAL; + } + sub_d = kzalloc_node(sizeof(struct soft_subdomain) + cpumask_size(), GFP_KERNEL, nid); if (!sub_d) { @@ -138,8 +147,6 @@ void build_soft_domain(void) static DEFINE_MUTEX(soft_domain_mutex); -#define NR_MAX_CLUSTER 16 - struct domain_node { struct soft_subdomain *sud_d; unsigned int attached; -- 2.18.0.huawei.25

1 0

[PATCH openEuler-1.0-LTS] squashfs: fix memory leak in squashfs_fill_super
by Long Li 25 Feb '26

25 Feb '26

From: Phillip Lougher <phillip(a)squashfs.org.uk> stable inclusion from stable-v5.10.240 commit 9bdb2e7f9b11a1c9bb7096d5726fe5a738fa5d73 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/9383 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- commit b64700d41bdc4e9f82f1346c15a3678ebb91a89c upstream. If sb_min_blocksize returns 0, squashfs_fill_super exits without freeing allocated memory (sb->s_fs_info). Fix this by moving the call to sb_min_blocksize to before memory is allocated. Link: https://lkml.kernel.org/r/20250811223740.110392-1-phillip@squashfs.org.uk Fixes: 734aa85390ea ("Squashfs: check return result of sb_min_blocksize") Signed-off-by: Phillip Lougher <phillip(a)squashfs.org.uk> Reported-by: Scott GUO <scottzhguo(a)tencent.com> Closes: https://lore.kernel.org/all/20250811061921.3807353-1-scott_gzh@163.com Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: fs/squashfs/super.c [Context conflicts] Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/squashfs/super.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 41756ca57ff2..119c0d63dafc 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -85,10 +85,15 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) unsigned short flags; unsigned int fragments; u64 lookup_table_start, xattr_id_table_start, next_table; - int err; + int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); TRACE("Entered squashfs_fill_superblock\n"); + if (!devblksize) { + ERROR("squashfs: unable to set blocksize\n"); + return -EINVAL; + } + sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL); if (sb->s_fs_info == NULL) { ERROR("Failed to allocate squashfs_sb_info\n"); @@ -96,12 +101,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) } msblk = sb->s_fs_info; - msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); - if (!msblk->devblksize) { - ERROR("squashfs: unable to set blocksize\n"); - return -EINVAL; - } - + msblk->devblksize = devblksize; msblk->devblksize_log2 = ffz(~msblk->devblksize); mutex_init(&msblk->meta_index_mutex); -- 2.39.2

2 1

[PATCH OLK-6.6] efivarfs: fix error propagation in efivar_entry_get()
by Yongjian Sun 25 Feb '26

25 Feb '26

From: Kohei Enju <kohei(a)enjuk.jp> mainline inclusion from mainline-v6.19-rc8 commit 4b22ec1685ce1fc0d862dcda3225d852fb107995 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13706 CVE: CVE-2026-23156 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- efivar_entry_get() always returns success even if the underlying __efivar_entry_get() fails, masking errors. This may result in uninitialized heap memory being copied to userspace in the efivarfs_file_read() path. Fix it by returning the error from __efivar_entry_get(). Fixes: 2d82e6227ea1 ("efi: vars: Move efivar caching layer into efivarfs") Cc: <stable(a)vger.kernel.org> # v6.1+ Signed-off-by: Kohei Enju <kohei(a)enjuk.jp> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/efivarfs/vars.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 13bc60698955..b10aa5afd7f7 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -609,7 +609,7 @@ int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, err = __efivar_entry_get(entry, attributes, size, data); efivar_unlock(); - return 0; + return err; } /** -- 2.39.2

2 1

[PATCH OLK-6.6] io_uring/io-wq: check IO_WQ_BIT_EXIT inside work run loop
by Yongjian Sun 25 Feb '26

25 Feb '26

From: Jens Axboe <axboe(a)kernel.dk> mainline inclusion from mainline-v6.19-rc7 commit 10dc959398175736e495f71c771f8641e1ca1907 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13663 CVE: CVE-2026-23113 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/all/68a2decc.050a0220.e29e5.0099.GAE@google.com/ Reported-by: syzbot+4eb282331cab6d5b6588(a)syzkaller.appspotmail.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- io_uring/io-wq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 1c4ef4e4eb52..c848a5018d12 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -554,9 +554,9 @@ static void io_worker_handle_work(struct io_wq_acct *acct, __releases(&acct->lock) { struct io_wq *wq = worker->wq; - bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); struct io_wq_work *work; /* -- 2.39.2

2 1

[PATCH OLK-6.6] dmaengine: mmp_pdma: Fix race condition in mmp_pdma_residue()
by Zhang Yuwei 25 Feb '26

25 Feb '26

From: Guodong Xu <guodong(a)riscstar.com> mainline inclusion from mainline-v6.19-rc6 commit a143545855bc2c6e1330f6f57ae375ac44af00a7 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13727 CVE: CVE-2025-71221 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Signed-off-by: Juan Li <lijuan(a)linux.spacemit.com> Signed-off-by: Guodong Xu <guodong(a)riscstar.com> Link: https://patch.msgid.link/20251216-mmp-pdma-race-v1-1-976a224bb622@riscstar.… Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Conflicts: drivers/dma/mmp_pdma.c [commit 35e40bf761fcb not merged] Signed-off-by: Zhang Yuwei <zhangyuwei20(a)huawei.com> --- drivers/dma/mmp_pdma.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index ebdfdcbb4f7a..3a035a31bec5 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -763,6 +763,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, dma_cookie_t cookie) { struct mmp_pdma_desc_sw *sw; + unsigned long flags; u32 curr, residue = 0; bool passed = false; bool cyclic = chan->cyclic_first != NULL; @@ -779,6 +780,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, else curr = readl(chan->phy->base + DSADR(chan->phy->idx)); + spin_lock_irqsave(&chan->desc_lock, flags); + list_for_each_entry(sw, &chan->chain_running, node) { u32 start, end, len; @@ -822,6 +825,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, continue; if (sw->async_tx.cookie == cookie) { + spin_unlock_irqrestore(&chan->desc_lock, flags); return residue; } else { residue = 0; @@ -829,6 +833,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, } } + spin_unlock_irqrestore(&chan->desc_lock, flags); + /* We should only get here in case of cyclic transactions */ return residue; } -- 2.22.0

2 1

[PATCH OLK-5.10] dmaengine: mmp_pdma: Fix race condition in mmp_pdma_residue()
by Zhang Yuwei 25 Feb '26

25 Feb '26

From: Guodong Xu <guodong(a)riscstar.com> mainline inclusion from mainline-v6.19-rc6 commit a143545855bc2c6e1330f6f57ae375ac44af00a7 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13727 CVE: CVE-2025-71221 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Signed-off-by: Juan Li <lijuan(a)linux.spacemit.com> Signed-off-by: Guodong Xu <guodong(a)riscstar.com> Link: https://patch.msgid.link/20251216-mmp-pdma-race-v1-1-976a224bb622@riscstar.… Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Conflicts: drivers/dma/mmp_pdma.c [commit 35e40bf761fcb not merged] Signed-off-by: Zhang Yuwei <zhangyuwei20(a)huawei.com> --- drivers/dma/mmp_pdma.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index 4eb63f1ad224..c56cb954b392 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -764,6 +764,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, dma_cookie_t cookie) { struct mmp_pdma_desc_sw *sw; + unsigned long flags; u32 curr, residue = 0; bool passed = false; bool cyclic = chan->cyclic_first != NULL; @@ -780,6 +781,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, else curr = readl(chan->phy->base + DSADR(chan->phy->idx)); + spin_lock_irqsave(&chan->desc_lock, flags); + list_for_each_entry(sw, &chan->chain_running, node) { u32 start, end, len; @@ -823,6 +826,7 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, continue; if (sw->async_tx.cookie == cookie) { + spin_unlock_irqrestore(&chan->desc_lock, flags); return residue; } else { residue = 0; @@ -830,6 +834,8 @@ static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan, } } + spin_unlock_irqrestore(&chan->desc_lock, flags); + /* We should only get here in case of cyclic transactions */ return residue; } -- 2.22.0

2 1

[PATCH] Prefer steal task within LLC and fallback to native newidle_balance on failure
by Chen Jinghuang 25 Feb '26

25 Feb '26

--- kernel/sched/fair.c | 15 +++++++++++++-- kernel/sched/features.h | 1 + 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e60f19cb0fee..70ba6ee3c058 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10343,9 +10343,15 @@ done: __maybe_unused; */ rq_idle_stamp_update(rq); - new_tasks = newidle_balance(rq, rf); - if (new_tasks == 0) + if (sched_feat(STEALPOC)) { new_tasks = try_steal(rq, rf); + if (new_tasks == 0) + new_tasks = newidle_balance(rq, rf); + } else { + new_tasks = newidle_balance(rq, rf); + if (new_tasks == 0) + new_tasks = try_steal(rq, rf); + } schedstat_end_time(rq, time); if (new_tasks) @@ -14313,6 +14319,11 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) int continue_balancing = 1; u64 domain_cost; + if (sched_feat(STEALPOC)) { + if (sd->flags & SD_SHARE_PKG_RESOURCES) + continue; + } + update_next_balance(sd, &next_balance); if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 1f665fbf0137..c74329fd86b9 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -63,6 +63,7 @@ SCHED_FEAT(SIS_UTIL, true) * Improves CPU utilization. */ SCHED_FEAT(STEAL, false) +SCHED_FEAT(STEALPOC, false) #endif #ifdef CONFIG_SCHED_PARAL -- 2.34.1

1 0

[PATCH OLK-6.6 0/2] CVE-2026-23094
by Liu Kai 25 Feb '26

25 Feb '26

CVE-2026-23094 Chenghai Huang (1): uacce: fix isolate sysfs check condition Liu Kai (1): Revert "uacce: fix isolate sysfs check condition" drivers/misc/uacce/uacce.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) -- 2.34.1

2 3

[PATCH OLK-5.10] migrate: correct lock ordering for hugetlb file folios
by Jinjiang Tu 24 Feb '26

24 Feb '26

From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> stable inclusion from stable-v5.10.249 commit e7396d23f9d5739f56cf9ab430c3a169f5508394 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13630 CVE: CVE-2026-23097 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit b7880cb166ab62c2409046b2347261abf701530e upstream. Syzbot has found a deadlock (analyzed by Lance Yang): 1) Task (5749): Holds folio_lock, then tries to acquire i_mmap_rwsem(read lock). 2) Task (5754): Holds i_mmap_rwsem(write lock), then tries to acquire folio_lock. migrate_pages() -> migrate_hugetlbs() -> unmap_and_move_huge_page() <- Takes folio_lock! -> remove_migration_ptes() -> __rmap_walk_file() -> i_mmap_lock_read() <- Waits for i_mmap_rwsem(read lock)! hugetlbfs_fallocate() -> hugetlbfs_punch_hole() <- Takes i_mmap_rwsem(write lock)! -> hugetlbfs_zero_partial_page() -> filemap_lock_hugetlb_folio() -> filemap_lock_folio() -> __filemap_get_folio <- Waits for folio_lock! The migration path is the one taking locks in the wrong order according to the documentation at the top of mm/rmap.c. So expand the scope of the existing i_mmap_lock to cover the calls to remove_migration_ptes() too. This is (mostly) how it used to be after commit c0d0381ade79. That was removed by 336bf30eb765 for both file & anon hugetlb pages when it should only have been removed for anon hugetlb pages. Link: https://lkml.kernel.org/r/20260109041345.3863089-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Fixes: 336bf30eb765 ("hugetlbfs: fix anon huge page migration race") Reported-by: syzbot+2d9c96466c978346b55f(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/68e9715a.050a0220.1186a4.000d.GAE@google.com Debugged-by: Lance Yang <lance.yang(a)linux.dev> Acked-by: David Hildenbrand (Red Hat) <david(a)kernel.org> Acked-by: Zi Yan <ziy(a)nvidia.com> Cc: Alistair Popple <apopple(a)nvidia.com> Cc: Byungchul Park <byungchul(a)sk.com> Cc: Gregory Price <gourry(a)gourry.net> Cc: Jann Horn <jannh(a)google.com> Cc: Joshua Hahn <joshua.hahnjy(a)gmail.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: Rakie Kim <rakie.kim(a)sk.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Ying Huang <ying.huang(a)linux.alibaba.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/migrate.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index cf8c05ea821e..7dc6846af90e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1342,6 +1342,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, struct page *new_hpage; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK; /* * Migratability of hugepages depends on architectures and their size. @@ -1389,9 +1390,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - bool mapping_locked = false; - enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK; - if (!PageAnon(hpage)) { /* * In shared mappings, try_to_unmap could potentially @@ -1403,15 +1401,11 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (unlikely(!mapping)) goto unlock_put_anon; - mapping_locked = true; ttu |= TTU_RMAP_LOCKED; } try_to_unmap(hpage, ttu); page_was_mapped = 1; - - if (mapping_locked) - i_mmap_unlock_write(mapping); } if (!page_mapped(hpage)) @@ -1419,7 +1413,11 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (page_was_mapped) remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); + rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, + (ttu & TTU_RMAP_LOCKED) ? true : false); + + if (ttu & TTU_RMAP_LOCKED) + i_mmap_unlock_write(mapping); unlock_put_anon: unlock_page(new_hpage); -- 2.43.0

2 1

[PATCH OLK-6.6] migrate: correct lock ordering for hugetlb file folios
by Jinjiang Tu 24 Feb '26

24 Feb '26

From: "Matthew Wilcox (Oracle)" <willy(a)infradead.org> stable inclusion from stable-v6.6.122 commit 526394af4e8ade89cacd1a9ce2b97712712fcc34 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13630 CVE: CVE-2026-23097 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit b7880cb166ab62c2409046b2347261abf701530e upstream. Syzbot has found a deadlock (analyzed by Lance Yang): 1) Task (5749): Holds folio_lock, then tries to acquire i_mmap_rwsem(read lock). 2) Task (5754): Holds i_mmap_rwsem(write lock), then tries to acquire folio_lock. migrate_pages() -> migrate_hugetlbs() -> unmap_and_move_huge_page() <- Takes folio_lock! -> remove_migration_ptes() -> __rmap_walk_file() -> i_mmap_lock_read() <- Waits for i_mmap_rwsem(read lock)! hugetlbfs_fallocate() -> hugetlbfs_punch_hole() <- Takes i_mmap_rwsem(write lock)! -> hugetlbfs_zero_partial_page() -> filemap_lock_hugetlb_folio() -> filemap_lock_folio() -> __filemap_get_folio <- Waits for folio_lock! The migration path is the one taking locks in the wrong order according to the documentation at the top of mm/rmap.c. So expand the scope of the existing i_mmap_lock to cover the calls to remove_migration_ptes() too. This is (mostly) how it used to be after commit c0d0381ade79. That was removed by 336bf30eb765 for both file & anon hugetlb pages when it should only have been removed for anon hugetlb pages. Link: https://lkml.kernel.org/r/20260109041345.3863089-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Fixes: 336bf30eb765 ("hugetlbfs: fix anon huge page migration race") Reported-by: syzbot+2d9c96466c978346b55f(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/all/68e9715a.050a0220.1186a4.000d.GAE@google.com Debugged-by: Lance Yang <lance.yang(a)linux.dev> Acked-by: David Hildenbrand (Red Hat) <david(a)kernel.org> Acked-by: Zi Yan <ziy(a)nvidia.com> Cc: Alistair Popple <apopple(a)nvidia.com> Cc: Byungchul Park <byungchul(a)sk.com> Cc: Gregory Price <gourry(a)gourry.net> Cc: Jann Horn <jannh(a)google.com> Cc: Joshua Hahn <joshua.hahnjy(a)gmail.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: Rakie Kim <rakie.kim(a)sk.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Ying Huang <ying.huang(a)linux.alibaba.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: mm/migrate.c [Context conflicts due to 3f6171ebb378 ("mm: try skipping pinned page before unmapping in migration").] Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/migrate.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 216f45c9570f..2ca451efaaad 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1438,6 +1438,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + enum ttu_flags ttu = 0; if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ @@ -1479,8 +1480,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, goto put_anon; if (folio_mapped(src)) { - enum ttu_flags ttu = 0; - /* * Racy check folio is pinned, try to avoid unnecessary page * table unmapping and restoring, because the subsequent @@ -1505,9 +1504,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, try_to_migrate(src, ttu); page_was_mapped = 1; - - if (ttu & TTU_RMAP_LOCKED) - i_mmap_unlock_write(mapping); } if (!folio_mapped(src)) @@ -1515,7 +1511,11 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, + ttu ? true : false); + + if (ttu & TTU_RMAP_LOCKED) + i_mmap_unlock_write(mapping); unlock_put_anon: folio_unlock(dst); -- 2.43.0

2 1

[PATCH OLK-6.6] libceph: make calc_target() set t->paused, not just clear it
by Jinjiang Tu 24 Feb '26

24 Feb '26

From: Ilya Dryomov <idryomov(a)gmail.com> stable inclusion from stable-v6.6.121 commit 4ebc711b738d139cabe2fc9e7e7749847676a342 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13573 CVE: CVE-2026-23047 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit c0fe2994f9a9d0a2ec9e42441ea5ba74b6a16176 upstream. Currently calc_target() clears t->paused if the request shouldn't be paused anymore, but doesn't ever set t->paused even though it's able to determine when the request should be paused. Setting t->paused is left to __submit_request() which is fine for regular requests but doesn't work for linger requests -- since __submit_request() doesn't operate on linger requests, there is nowhere for lreq->t.paused to be set. One consequence of this is that watches don't get reestablished on paused -> unpaused transitions in cases where requests have been paused long enough for the (paused) unwatch request to time out and for the subsequent (re)watch request to enter the paused state. On top of the watch not getting reestablished, rbd_reregister_watch() gets stuck with rbd_dev->watch_mutex held: rbd_register_watch __rbd_register_watch ceph_osdc_watch linger_reg_commit_wait It's waiting for lreq->reg_commit_wait to be completed, but for that to happen the respective request needs to end up on need_resend_linger list and be kicked when requests are unpaused. There is no chance for that if the request in question is never marked paused in the first place. The fact that rbd_dev->watch_mutex remains taken out forever then prevents the image from getting unmapped -- "rbd unmap" would inevitably hang in D state on an attempt to grab the mutex. Cc: stable(a)vger.kernel.org Reported-by: Raphael Zimmer <raphael.zimmer(a)tu-ilmenau.de> Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com> Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko(a)ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- net/ceph/osd_client.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0b6a8bb0642f..866cef26ce2a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1611,6 +1611,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; + bool should_be_paused; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; @@ -1679,10 +1680,16 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, &last_pgid)) force_resend = true; - if (t->paused && !target_should_be_paused(osdc, t, pi)) { - t->paused = false; + should_be_paused = target_should_be_paused(osdc, t, pi); + if (t->paused && !should_be_paused) { unpaused = true; } + if (t->paused != should_be_paused) { + dout("%s t %p paused %d -> %d\n", __func__, t, t->paused, + should_be_paused); + t->paused = should_be_paused; + } + legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); -- 2.43.0

2 1

[PATCH OLK-6.6] smb/server: fix refcount leak in smb2_open()
by Li Lingfeng 24 Feb '26

24 Feb '26

From: ZhangGuoDong <zhangguodong(a)kylinos.cn> stable inclusion from stable-v6.6.124 commit 2456fde2b137703328f1695f60c68fe488d17e36 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13729 CVE: CVE-2025-71223 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f416c556997aa56ec4384c6b6efd6a0e6ac70aa7 ] When ksmbd_vfs_getattr() fails, the reference count of ksmbd_file must be released. Suggested-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: ZhangGuoDong <zhangguodong(a)kylinos.cn> Signed-off-by: ChenXiaoSong <chenxiaosong(a)kylinos.cn> Acked-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/smb/server/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 1ec50a9272ea..6ac7efc835de 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2986,10 +2986,10 @@ int smb2_open(struct ksmbd_work *work) file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); + ksmbd_put_durable_fd(fp); if (rc) goto err_out2; - ksmbd_put_durable_fd(fp); goto reconnected_fp; } } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) -- 2.52.0

2 1

[PATCH OLK-6.6] smb/server: call ksmbd_session_rpc_close() on error path in create_smb2_pipe()
by Li Lingfeng 24 Feb '26

24 Feb '26

From: ZhangGuoDong <zhangguodong(a)kylinos.cn> stable inclusion from stable-v6.6.124 commit 04dd114b682a4ccaeba2c2bad049c8b50ce740d8 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13726 CVE: CVE-2025-71220 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7c28f8eef5ac5312794d8a52918076dcd787e53b ] When ksmbd_iov_pin_rsp() fails, we should call ksmbd_session_rpc_close(). Signed-off-by: ZhangGuoDong <zhangguodong(a)kylinos.cn> Signed-off-by: ChenXiaoSong <chenxiaosong(a)kylinos.cn> Acked-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/smb/server/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 1ec50a9272ea..4fd2d02acacd 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2264,7 +2264,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) { struct smb2_create_rsp *rsp; struct smb2_create_req *req; - int id; + int id = -1; int err; char *name; @@ -2321,6 +2321,9 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) break; } + if (id >= 0) + ksmbd_session_rpc_close(work->sess, id); + if (!IS_ERR(name)) kfree(name); -- 2.52.0

2 1

[PATCH OLK-6.6] smb: server: fix leak of active_num_conn in ksmbd_tcp_new_connection()
by Li Lingfeng 24 Feb '26

24 Feb '26

From: Henrique Carvalho <henrique.carvalho(a)suse.com> stable inclusion from stable-v6.6.125 commit 787769c8cc50416af7b8b1a36e6bcd6aaa7680aa category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13789 CVE: CVE-2026-23228 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 77ffbcac4e569566d0092d5f22627dfc0896b553 upstream. On kthread_run() failure in ksmbd_tcp_new_connection(), the transport is freed via free_transport(), which does not decrement active_num_conn, leaking this counter. Replace free_transport() with ksmbd_tcp_disconnect(). Fixes: 0d0d4680db22e ("ksmbd: add max connections parameter") Cc: stable(a)vger.kernel.org Signed-off-by: Henrique Carvalho <henrique.carvalho(a)suse.com> Acked-by: Namjae Jeon <linkinjeon(a)kernel.org> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/smb/server/transport_tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index c43a46511428..ee881e8f027f 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -41,6 +41,7 @@ static struct ksmbd_transport_ops ksmbd_tcp_transport_ops; static void tcp_stop_kthread(struct task_struct *kthread); static struct interface *alloc_iface(char *ifname); +static void ksmbd_tcp_disconnect(struct ksmbd_transport *t); #define KSMBD_TRANS(t) (&(t)->transport) #define TCP_TRANS(t) ((struct tcp_transport *)container_of(t, \ @@ -219,7 +220,7 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) if (IS_ERR(handler)) { pr_err("cannot start conn thread\n"); rc = PTR_ERR(handler); - free_transport(t); + ksmbd_tcp_disconnect(KSMBD_TRANS(t)); } return rc; -- 2.52.0

2 1

[PATCH OLK-5.10] nvmet-tcp: add bounds checks in nvmet_tcp_build_pdu_iovec
by Zizhi Wo 24 Feb '26

24 Feb '26

From: YunJe Shin <yjshin0438(a)gmail.com> stable inclusion from stable-v5.10.250 commit 043b4307a99f902697349128fde93b2ddde4686c category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13660 CVE: CVE-2026-23112 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 52a0a98549344ca20ad81a4176d68d28e3c05a5c ] nvmet_tcp_build_pdu_iovec() could walk past cmd->req.sg when a PDU length or offset exceeds sg_cnt and then use bogus sg->length/offset values, leading to _copy_to_iter() GPF/KASAN. Guard sg_idx, remaining entries, and sg->length/offset before building the bvec. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Signed-off-by: YunJe Shin <ioerts(a)kookmin.ac.kr> Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me> Reviewed-by: Joonkyo Jung <joonkyoj(a)yonsei.ac.kr> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/nvme/target/tcp.c [Due to commit 5bfaba275ae6 ("nvmet-tcp: don't map pages which can't come from HIGHMEM") not been merged, which is not related to this patch.] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- drivers/nvme/target/tcp.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index da2f9c9e0a6d..a470ffb93f66 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -286,6 +286,8 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) return 0; } +static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue); + static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd) { struct scatterlist *sg; @@ -302,22 +304,38 @@ static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) struct kvec *iov = cmd->iov; struct scatterlist *sg; u32 length, offset, sg_offset; + unsigned int sg_remaining; length = cmd->pdu_len; cmd->nr_mapped = DIV_ROUND_UP(length, PAGE_SIZE); offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; + if (!cmd->req.sg_cnt || cmd->sg_idx >= cmd->req.sg_cnt) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } sg = &cmd->req.sg[cmd->sg_idx]; + sg_remaining = cmd->req.sg_cnt - cmd->sg_idx; while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); + if (!sg_remaining) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } + if (!sg->length || sg->length <= sg_offset) { + nvmet_tcp_fatal_error(cmd->queue); + return; + } + iov->iov_base = kmap(sg_page(sg)) + sg->offset + sg_offset; iov->iov_len = iov_len; length -= iov_len; sg = sg_next(sg); + sg_remaining--; iov++; sg_offset = 0; } -- 2.39.2

2 1

[PATCH OLK-6.6] net: hv_netvsc: reject RSS hash key programming without RX indirection table
by Wupeng Ma 24 Feb '26

24 Feb '26

From: Aditya Garg <gargaditya(a)linux.microsoft.com> stable inclusion from stable-v6.6.122 commit 82c9039c8ebb715753a40434df714f865a3aec9c category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13587 CVE: CVE-2026-23054 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d23564955811da493f34412d7de60fa268c8cb50 ] 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. Fixes: 962f3fee83a4 ("netvsc: add ethtool ops to get/set RSS key") Signed-off-by: Aditya Garg <gargaditya(a)linux.microsoft.com> Reviewed-by: Dipayaan Roy <dipayanroy(a)linux.microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz(a)microsoft.com> Link: https://patch.msgid.link/1768212093-1594-1-git-send-email-gargaditya@linux.… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- drivers/net/hyperv/netvsc_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index aa114240e340d..af001e2e688b2 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1762,6 +1762,9 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; + if (!ndc->rx_table_sz) + return -EOPNOTSUPP; + rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ndc->rx_table_sz; i++) -- 2.43.0

2 1

[PATCH OLK-5.10 0/2] ACPI/IORT: Add PMCG platform information for 162001900
by Zeng Heng 24 Feb '26

24 Feb '26

Qinxin Xia (2): arm-smmu-v3: add HIP09A, HIP09B, HIP10C, HIP10CA for 162100602 errata ACPI/IORT: Add PMCG platform information for 162001900 Documentation/arm64/silicon-errata.rst | 6 +++--- drivers/acpi/arm64/iort.c | 4 ++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 8 ++++++++ 3 files changed, 15 insertions(+), 3 deletions(-) -- 2.25.1

2 3

[PATCH OLK-5.10 0/2] fix CVE-2026-23054
by Wupeng Ma 24 Feb '26

24 Feb '26

fix CVE-2026-23054. Aditya Garg (1): net: hv_netvsc: reject RSS hash key programming without RX indirection table Shradha Gupta (1): hv_netvsc: Allocate rx indirection table size dynamically drivers/net/hyperv/hyperv_net.h | 5 ++++- drivers/net/hyperv/netvsc_drv.c | 13 +++++++++---- drivers/net/hyperv/rndis_filter.c | 28 ++++++++++++++++++++++++---- 3 files changed, 37 insertions(+), 9 deletions(-) -- 2.43.0

2 3

[PATCH OLK-5.10] ACPI/IORT: Add PMCG platform information for 162001900
by Zeng Heng 12 Feb '26

12 Feb '26

From: Qinxin Xia <xiaqinxin(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/7640 ------------------ Some HiSilicon platforms using the same SMMU PMCG with HIP09 and thus suffers the same erratum. List them in the PMCG platform information list without introducing a new SMMU PMCG Model. Update the silicon-errata.rst as well. Fixes: 28396fe25d85 ("Add PMCG platform information for HiSilicon HIP09A") Signed-off-by: Qinxin Xia <xiaqinxin(a)huawei.com> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- Documentation/arm64/silicon-errata.rst | 6 +++--- drivers/acpi/arm64/iort.c | 4 ++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 65c5c284893c..f8857b6698cc 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -147,9 +147,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A | +----------------+-----------------+-----------------+-----------------------------+ -| Hisilicon | Hip{08,09,09A,10| #162001900 | N/A | -| | ,10C,11} | | | -| | SMMU PMCG | | | +| Hisilicon | Hip{08,09,09A, | #162001900 | N/A | +| | 09B,10,10C,10CA,| | | +| | 11} SMMU PMCG | | | +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | TSV{110,200} | #1980005 | HISILICON_ERRATUM_1980005 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index f3e44b95368a..c8b20e4589a0 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1567,11 +1567,15 @@ static struct acpi_platform_list pmcg_plat_info[] __initdata = { "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, {"HISI ", "HIP09A ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, + {"HISI ", "HIP09B ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, /* HiSilicon Hip10/11 Platform uses the same SMMU IP with Hip09 */ {"HISI ", "HIP10 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, {"HISI ", "HIP10C ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, + {"HISI ", "HIP10CA ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, {"HISI ", "HIP11 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, { } -- 2.25.1

2 1

[PATCH OLK-5.10] arm-smmu-v3: add HIP09A, HIP09B, HIP10C, HIP10CA for 162100602 errata
by Zeng Heng 12 Feb '26

12 Feb '26

From: Qinxin Xia <xiaqinxin(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/7640 ------------------ Add HIP09A, HIP09B, HIP10C, HIP10CA for 162100602 errata Fixes: c20cd1f88a57 ("iommu/arm-smmu-v3: Change the style to identify the the hisi_platform") Signed-off-by: Qinxin Xia <xiaqinxin(a)huawei.com> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index e67c1feeca5f..1528661f98dd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -5265,8 +5265,16 @@ static struct acpi_platform_list arm_smmu_v3_plat_info[] = { /* HiSilicon Hip09 Platform */ {"HISI ", "HIP09 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162100602", 0}, + {"HISI ", "HIP09A ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, + {"HISI ", "HIP09B ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, {"HISI ", "HIP10 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162100602", 0}, + {"HISI ", "HIP10C ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, + {"HISI ", "HIP10CA ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, {"HISI ", "HIP11 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162100602", 0}, { } -- 2.25.1

2 1

[PATCH v5 0/4] arm64/riscv: Add support for crashkernel CMA reservation
by Jinjie Ruan 12 Feb '26

12 Feb '26

Exclude crash kernel memory in crash core to avoid duplication. Also move the size calculation (and the realloc if needed) into crash core. And add support for crashkernel CMA reservation for arm64 and riscv. Changes in v5: - Fix the kernel test robot build warnings. - Sort crash memory ranges before preparing elfcorehdr for powerpc - Link to v4: https://lore.kernel.org/all/20260209095931.2813152-1-ruanjinjie@huawei.com/ Changes in v4: - Move the size calculation (and the realloc if needed) into the generic crash. - Link to v3: https://lore.kernel.org/all/20260204093728.1447527-1-ruanjinjie@huawei.com/ Changs in v3: - Exclude crash kernel memory in crash core as Mike suggested. - Add acked-by. Jinjie Ruan (3): crash: Exclude crash kernel memory in crash core arm64: kexec: Add support for crashkernel CMA reservation riscv: kexec: Add support for crashkernel CMA reservation Sourabh Jain (1): powerpc/crash: sort crash memory ranges before preparing elfcorehdr .../admin-guide/kernel-parameters.txt | 16 +-- arch/arm64/include/asm/kexec.h | 9 +- arch/arm64/kernel/machine_kexec_file.c | 43 +++----- arch/arm64/mm/init.c | 5 +- arch/loongarch/include/asm/kexec.h | 9 +- arch/loongarch/kernel/machine_kexec_file.c | 41 +++---- arch/powerpc/include/asm/kexec.h | 13 +++ arch/powerpc/include/asm/kexec_ranges.h | 1 - arch/powerpc/kexec/crash.c | 67 ++++++----- arch/powerpc/kexec/file_load_64.c | 17 +-- arch/powerpc/kexec/ranges.c | 103 +---------------- arch/riscv/include/asm/kexec.h | 9 +- arch/riscv/kernel/machine_kexec_file.c | 39 +++---- arch/riscv/mm/init.c | 5 +- arch/x86/include/asm/kexec.h | 9 ++ arch/x86/kernel/crash.c | 104 ++---------------- include/linux/crash_core.h | 75 ++++++++++++- kernel/crash_core.c | 85 ++++++++++++-- 18 files changed, 314 insertions(+), 336 deletions(-) -- 2.34.1

1 4

[PATCH OLK-6.6] dm: use bio_clone_blkg_association
by Zhihao Cheng 12 Feb '26

12 Feb '26

From: Mikulas Patocka <mpatocka(a)redhat.com> mainline inclusion from mainline-v7.0-rc1 commit 2df8b310bcfe76827fd71092f58a2493ee6590b0 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13467 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The origin bio carries blk-cgroup information which could be set from foreground(task_css(css) - wbc->wb->blkcg_css), so the blkcg won't control buffer io since commit ca522482e3eaf ("dm: pass NULL bdev to bio_alloc_clone"). The synchronous io is still under control by blkcg, because 'bio->bi_blkg' is set by io submitting task which has been added into 'cgroup.procs'. Fix it by using bio_clone_blkg_association when submitting a cloned bio. Link: https://bugzilla.kernel.org/show_bug.cgi?id=220985 Fixes: ca522482e3eaf ("dm: pass NULL bdev to bio_alloc_clone") Reported-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Tested-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> --- drivers/md/dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 96f050891ec0..670460ade280 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1365,6 +1365,8 @@ void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone) if (!tgt_clone) tgt_clone = clone; + bio_clone_blkg_association(tgt_clone, io->orig_bio); + /* * Account io->origin_bio to DM dev on behalf of target * that took ownership of IO with DM_MAPIO_SUBMITTED. -- 2.52.0

2 1

[PATCH OLK-6.6] gic: Add hip09 support for HISILICON_ERRATUM_165010801
by Zeng Heng 12 Feb '26

12 Feb '26

From: Yifan Wu <wuyifan50(a)huawei.com> driver inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/7023 ---------------------------------------------------------------------- Add hip09 support for HISILICON_ERRATUM_165010801 Fixes: f0f9be237c22 ("gic: increase the arch_timer priority to avoid hardlockup") Signed-off-by: Yifan Wu <wuyifan50(a)huawei.com> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- arch/arm64/Kconfig | 11 ++++++----- drivers/clocksource/arm_arch_timer.c | 5 +++++ 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ef8c524a296d..2a4a729ef8f7 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1309,11 +1309,12 @@ config HISILICON_ERRATUM_165010801 depends on ARCH_HISI default y help - On HIP12, when GIC receives multiple interrupts of the same priority and - different types, the interrupts are selected in the following sequence: - SPI > LPI > SGI > PPI. This scheduling rule may cause PPI starvation. - To prevent starvation from triggering system watchdog hardlockup, the - interrupt priority is explicitly increased in the arch_timer driver. + On HIP09/12 hardware, observations indicate that the GIC's handling of + equal-priority interrupts across different interrupt types may not always + provide balanced servicing. In some cases, this could result in prolonged + service delays for particular interrupt types, creating conditions where + system watchdog hardlockup detection might be triggered. The arch_timer + driver addresses this by proactively increasing affected interrupt priorities. config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 095238032ac0..7ffca7cc5c53 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -369,6 +369,11 @@ static struct ate_acpi_oem_info hisi_161010101_oem_info[] = { #ifdef CONFIG_HISILICON_ERRATUM_165010801 static struct ate_acpi_oem_info hisi_165010801_oem_info[] = { + { + .oem_id = "HISI ", + .oem_table_id = "HIP09 ", + .oem_revision = 0, + }, { .oem_id = "HISI ", .oem_table_id = "HIP12 ", -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] irqchip/gic-v3-its: Avoid truncating memory addresses
by Jinjie Ruan 12 Feb '26

12 Feb '26

From: Arnd Bergmann <arnd(a)arndb.de> stable inclusion from stable-v6.6.122 commit 1b323391560354d8c515de8658b057a1daa82adb category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13618 CVE: CVE-2026-23085 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 8d76a7d89c12d08382b66e2f21f20d0627d14859 upstream. On 32-bit machines with CONFIG_ARM_LPAE, it is possible for lowmem allocations to be backed by addresses physical memory above the 32-bit address limit, as found while experimenting with larger VMSPLIT configurations. This caused the qemu virt model to crash in the GICv3 driver, which allocates the 'itt' object using GFP_KERNEL. Since all memory below the 4GB physical address limit is in ZONE_DMA in this configuration, kmalloc() defaults to higher addresses for ZONE_NORMAL, and the ITS driver stores the physical address in a 32-bit 'unsigned long' variable. Change the itt_addr variable to the correct phys_addr_t type instead, along with all other variables in this driver that hold a physical address. The gicv5 driver correctly uses u64 variables, while all other irqchip drivers don't call virt_to_phys or similar interfaces. It's expected that other device drivers have similar issues, but fixing this one is sufficient for booting a virtio based guest. Fixes: cc2d3216f53c ("irqchip: GICv3: ITS command queue") Signed-off-by: Arnd Bergmann <arnd(a)arndb.de> Signed-off-by: Thomas Gleixner <tglx(a)kernel.org> Reviewed-by: Marc Zyngier <maz(a)kernel.org> Cc: stable(a)vger.kernel.org Link: https://patch.msgid.link/20260119201603.2713066-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/irqchip/irq-gic-v3-its.c [ Conflict because 64edfaa9a234 ("irqchip/gic-v4.1: Implement the v4.1 flavour of VMAPP") not merged. ] Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- drivers/irqchip/irq-gic-v3-its.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 65306a1ed3dc..750fcb25574a 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -459,7 +459,7 @@ static struct its_collection *its_build_mapd_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { - unsigned long itt_addr; + phys_addr_t itt_addr; u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites); itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt); @@ -629,7 +629,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { - unsigned long vpt_addr; + phys_addr_t vpt_addr; u64 target; vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page)); @@ -2023,10 +2023,10 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, baser->psz = psz; tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz; - pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n", + pr_info("ITS@%pa: allocated %d %s @%llx (%s, esz %d, psz %dK, shr %d)\n", &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / (int)tmp), its_base_type_string[type], - (unsigned long)virt_to_phys(base), + (u64)virt_to_phys(base), indirect ? "indirect" : "flat", (int)esz, psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); -- 2.34.1

2 1

[PATCH OLK-6.6] tracing: Fix soft lockup when lseeking trace file
by Tengda Wu 12 Feb '26

12 Feb '26

From: Tengda Wu <wutengda(a)huaweicloud.com> maillist inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8522 Reference: https://lore.kernel.org/all/20260209093101.1623454-1-wutengda@huaweicloud.c… -------------------------------- A soft lockup may occur when accessing trace file via lseek while tracing is active and a large offset is provided. The call trace is shown below: watchdog: BUG: soft lockup - CPU#3 stuck for 26s! [poc:141] CPU: 3 UID: 0 PID: 141 Comm: poc Not tainted 6.19.0 #1 PREEMPT(none) Call Trace: ring_buffer_iter_peek peek_next_entry __find_next_entry trace_find_next_entry_inc s_next traverse.part.0 seq_lseek tracing_lseek __x64_sys_lseek do_syscall_64 entry_SYSCALL_64_after_hwframe The root cause is that the lseek implementation for trace files is based on seq_lseek, which contains a loop that repeatedly calls show() and next() functions until the position reaches the target offset. Since no scheduling point is set within this loop, a large offset can cause the CPU to be stuck in the loop for an extended period, triggering the soft lockup detector. Fixed by adding cond_resched() in s_next(). Fixes: bc0c38d139ec ("ftrace: latency tracer infrastructure") Signed-off-by: Tengda Wu <wutengda2(a)huawei.com> --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b0751e52d40e..95ede691941c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4037,6 +4037,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) iter->pos = *pos; + cond_resched(); + return ent; } -- 2.34.1

2 1

[PATCH OLK-5.10] tracing: Fix soft lockup when lseeking trace file
by Tengda Wu 12 Feb '26

12 Feb '26

From: Tengda Wu <wutengda(a)huaweicloud.com> maillist inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8522 Reference: https://lore.kernel.org/all/20260209093101.1623454-1-wutengda@huaweicloud.c… -------------------------------- A soft lockup may occur when accessing trace file via lseek while tracing is active and a large offset is provided. The call trace is shown below: watchdog: BUG: soft lockup - CPU#3 stuck for 26s! [poc:141] CPU: 3 UID: 0 PID: 141 Comm: poc Not tainted 6.19.0 #1 PREEMPT(none) Call Trace: ring_buffer_iter_peek peek_next_entry __find_next_entry trace_find_next_entry_inc s_next traverse.part.0 seq_lseek tracing_lseek __x64_sys_lseek do_syscall_64 entry_SYSCALL_64_after_hwframe The root cause is that the lseek implementation for trace files is based on seq_lseek, which contains a loop that repeatedly calls show() and next() functions until the position reaches the target offset. Since no scheduling point is set within this loop, a large offset can cause the CPU to be stuck in the loop for an extended period, triggering the soft lockup detector. Fixed by adding cond_resched() in s_next(). Fixes: bc0c38d139ec ("ftrace: latency tracer infrastructure") Signed-off-by: Tengda Wu <wutengda2(a)huawei.com> --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c5a503987e7..631a9d263e57 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3678,6 +3678,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) iter->pos = *pos; + cond_resched(); + return ent; } -- 2.34.1

2 1

[PATCH OLK-5.10] uacce: fix cdev handling in the cleanup path
by Wang Tao 11 Feb '26

11 Feb '26

From: Wenkai Lin <linwenkai6(a)hisilicon.com> mainline inclusion from mainline-v6.19-rc7 commit a3bece3678f6c88db1f44c602b2a63e84b4040ac category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13629 CVE: CVE-2026-23096 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When cdev_device_add fails, it internally releases the cdev memory, and if cdev_device_del is then executed, it will cause a hang error. To fix it, we check the return value of cdev_device_add() and clear uacce->cdev to avoid calling cdev_device_del in the uacce_remove. Fixes: 015d239ac014 ("uacce: add uacce driver") Cc: stable(a)vger.kernel.org Signed-off-by: Wenkai Lin <linwenkai6(a)hisilicon.com> Signed-off-by: Chenghai Huang <huangchenghai2(a)huawei.com> Acked-by: Zhangfei Gao <zhangfei.gao(a)linaro.org> Link: https://patch.msgid.link/20251202061256.4158641-2-huangchenghai2@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Tao <wangtao554(a)huawei.com> --- drivers/misc/uacce/uacce.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 687b7fad9a29..b50ddd46fd72 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -982,6 +982,8 @@ EXPORT_SYMBOL_GPL(uacce_alloc); */ int uacce_register(struct uacce_device *uacce) { + int ret; + if (!uacce) return -ENODEV; @@ -992,7 +994,11 @@ int uacce_register(struct uacce_device *uacce) uacce->cdev->ops = &uacce_fops; uacce->cdev->owner = THIS_MODULE; - return cdev_device_add(uacce->cdev, &uacce->dev); + ret = cdev_device_add(uacce->cdev, &uacce->dev); + if (ret) + uacce->cdev = NULL; + + return ret; } EXPORT_SYMBOL_GPL(uacce_register); -- 2.34.1

2 1

[PATCH OLK-5.10 0/2] Revert hibmc patches to fix null-ptr-deref
by Tengda Wu 11 Feb '26

11 Feb '26

This patch series is going to revert pull requests: !19950 and !20738. Tengda Wu (2): Revert "!20738 drm/hisilicon: Using the to_hibmc_drm_private to convert" Revert "!19950 【OLK-5.10】 Drivers GPU Patches from 6.6" drivers/gpu/drm/drm_connector.c | 9 - drivers/gpu/drm/drm_internal.h | 2 - drivers/gpu/drm/drm_probe_helper.c | 29 -- drivers/gpu/drm/drm_sysfs.c | 17 +- drivers/gpu/drm/hisilicon/hibmc/Kconfig | 2 - drivers/gpu/drm/hisilicon/hibmc/Makefile | 4 +- drivers/gpu/drm/hisilicon/hibmc/dp/dp_aux.c | 167 ------- drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h | 73 --- .../gpu/drm/hisilicon/hibmc/dp/dp_config.h | 21 - drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c | 338 -------------- drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h | 74 ---- drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c | 415 ------------------ drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h | 140 ------ .../gpu/drm/hisilicon/hibmc/dp/dp_serdes.c | 59 --- .../gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 24 +- .../drm/hisilicon/hibmc/hibmc_drm_debugfs.c | 149 ------- .../gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c | 257 ----------- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 176 +++----- .../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 35 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c | 48 +- .../gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 64 +-- drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c | 8 +- include/drm/drm_probe_helper.h | 3 - 23 files changed, 126 insertions(+), 1988 deletions(-) delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_aux.c delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_comm.h delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_config.h delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.c delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_hw.h delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_reg.h delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/dp/dp_serdes.c delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_debugfs.c delete mode 100644 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_dp.c -- 2.34.1

2 3

[PATCH OLK-6.6] net: usb: asix: validate PHY address before use
by Wupeng Ma 11 Feb '26

11 Feb '26

From: Deepanshu Kartikey <kartikey406(a)gmail.com> stable inclusion from stable-v6.6.120 commit 38722e69ee64dbb020028c93898d25d6f4c0e0b2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/8372 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a1e077a3f76eea0dc671ed6792e7d543946227e8 ] The ASIX driver reads the PHY address from the USB device via asix_read_phy_addr(). A malicious or faulty device can return an invalid address (>= PHY_MAX_ADDR), which causes a warning in mdiobus_get_phy(): addr 207 out of range WARNING: drivers/net/phy/mdio_bus.c:76 Validate the PHY address in asix_read_phy_addr() and remove the now-redundant check in ax88172a.c. Reported-by: syzbot+3d43c9066a5b54902232(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=3d43c9066a5b54902232 Tested-by: syzbot+3d43c9066a5b54902232(a)syzkaller.appspotmail.com Fixes: 7e88b11a862a ("net: usb: asix: refactor asix_read_phy_addr() and handle errors on return") Link: https://lore.kernel.org/all/20251217085057.270704-1-kartikey406@gmail.com/T/ [v1] Signed-off-by: Deepanshu Kartikey <kartikey406(a)gmail.com> Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> Link: https://patch.msgid.link/20251218011156.276824-1-kartikey406@gmail.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yuan can <yuancan(a)huawei.com> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- drivers/net/usb/asix_common.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7fd763917ae2c..6ab3486072cb0 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -335,6 +335,11 @@ int asix_read_phy_addr(struct usbnet *dev, bool internal) offset = (internal ? 1 : 0); ret = buf[offset]; + if (ret >= PHY_MAX_ADDR) { + netdev_err(dev->net, "invalid PHY address: %d\n", ret); + return -ENODEV; + } + netdev_dbg(dev->net, "%s PHY address 0x%x\n", internal ? "internal" : "external", ret); -- 2.43.0

2 1

[PATCH OLK-6.6] smc91x: fix broken irq-context in PREEMPT_RT
by Wupeng Ma 11 Feb '26

11 Feb '26

From: Yeoreum Yun <yeoreum.yun(a)arm.com> stable inclusion from stable-v6.6.120 commit ef277ae121b3249c99994652210a326b52d527b0 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/8372 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 6402078bd9d1ed46e79465e1faaa42e3458f8a33 ] When smc91x.c is built with PREEMPT_RT, the following splat occurs in FVP_RevC: [ 13.055000] smc91x LNRO0003:00 eth0: link up, 10Mbps, half-duplex, lpa 0x0000 [ 13.062137] BUG: workqueue leaked atomic, lock or RCU: kworker/2:1[106] [ 13.062137] preempt=0x00000000 lock=0->0 RCU=0->1 workfn=mld_ifc_work [ 13.062266] C ** replaying previous printk message ** [ 13.062266] CPU: 2 UID: 0 PID: 106 Comm: kworker/2:1 Not tainted 6.18.0-dirty #179 PREEMPT_{RT,(full)} [ 13.062353] Hardware name: , BIOS [ 13.062382] Workqueue: mld mld_ifc_work [ 13.062469] Call trace: [ 13.062494] show_stack+0x24/0x40 (C) [ 13.062602] __dump_stack+0x28/0x48 [ 13.062710] dump_stack_lvl+0x7c/0xb0 [ 13.062818] dump_stack+0x18/0x34 [ 13.062926] process_scheduled_works+0x294/0x450 [ 13.063043] worker_thread+0x260/0x3d8 [ 13.063124] kthread+0x1c4/0x228 [ 13.063235] ret_from_fork+0x10/0x20 This happens because smc_special_trylock() disables IRQs even on PREEMPT_RT, but smc_special_unlock() does not restore IRQs on PREEMPT_RT. The reason is that smc_special_unlock() calls spin_unlock_irqrestore(), and rcu_read_unlock_bh() in __dev_queue_xmit() cannot invoke rcu_read_unlock() through __local_bh_enable_ip() when current->softirq_disable_cnt becomes zero. To address this issue, replace smc_special_trylock() with spin_trylock_irqsave(). Fixes: 342a93247e08 ("locking/spinlock: Provide RT variant header: <linux/spinlock_rt.h>") Signed-off-by: Yeoreum Yun <yeoreum.yun(a)arm.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20251217085115.1730036-1-yeoreum.yun@arm.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yuan can <yuancan(a)huawei.com> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- drivers/net/ethernet/smsc/smc91x.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 032eccf8eb428..7c2fdd02f1d34 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -515,15 +515,7 @@ static inline void smc_rcv(struct net_device *dev) * any other concurrent access and C would always interrupt B. But life * isn't that easy in a SMP world... */ -#define smc_special_trylock(lock, flags) \ -({ \ - int __ret; \ - local_irq_save(flags); \ - __ret = spin_trylock(lock); \ - if (!__ret) \ - local_irq_restore(flags); \ - __ret; \ -}) +#define smc_special_trylock(lock, flags) spin_trylock_irqsave(lock, flags) #define smc_special_lock(lock, flags) spin_lock_irqsave(lock, flags) #define smc_special_unlock(lock, flags) spin_unlock_irqrestore(lock, flags) #else -- 2.43.0

2 1

[PATCH OLK-6.6] dm-thin: Add support for split cache
by Zhang Zekun 11 Feb '26

11 Feb '26

hulk inclusion category: feature bugzilla: NA CVE: NA -------------------------------------------------------- The cache of dm-thin is common used for first level btree and the second level btree, however the first level btree has less dm-buffer than the second level btree, which might cause extra look up steps for the first level btree when accessing the cache of the dm pool. Thus, add support for spliting the first level btree and the second level btree' cache, which might speed up the look up process of the first level btree routine. Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/md/dm-bufio.c | 167 ++++++++++++++---- drivers/md/dm-thin-metadata.c | 4 + drivers/md/dm.h | 17 +- drivers/md/persistent-data/dm-block-manager.c | 11 ++ drivers/md/persistent-data/dm-block-manager.h | 2 + include/linux/dm-bufio.h | 4 + 6 files changed, 174 insertions(+), 31 deletions(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 8ce77aec05d2..206c7c00be88 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -254,9 +254,9 @@ enum evict_result { ER_STOP, /* stop looking for something to evict */ }; -typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context); +typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context, void *bc); -static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep) +static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep, void *bc) { unsigned long tested = 0; struct list_head *h = lru->cursor; @@ -276,7 +276,7 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con atomic_set(&le->referenced, 0); } else { tested++; - switch (pred(le, context)) { + switch (pred(le, context, bc)) { case ER_EVICT: /* * Adjust the cursor, so we start the next @@ -362,6 +362,7 @@ struct dm_buffer { unsigned int stack_len; unsigned long stack_entries[MAX_STACK]; #endif + bool special; }; /*--------------------------------------------------------------*/ @@ -399,47 +400,93 @@ struct dm_buffer_cache { * on the locks. */ unsigned int num_locks; + unsigned long special; bool no_sleep; struct buffer_tree trees[]; }; static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); +static inline unsigned int cache_index_special(sector_t block, unsigned int num_locks, unsigned long special) +{ + return dm_hash_locks_index_special(block, num_locks, special); +} + static inline unsigned int cache_index(sector_t block, unsigned int num_locks) { return dm_hash_locks_index(block, num_locks); } +static inline void cache_read_lock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + down_read(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); +} + static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + read_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_read(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); } static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + read_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); + else + up_read(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); +} + +static inline void cache_read_unlock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + up_read(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); +} + +static inline void cache_write_lock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); else - up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_write(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); } static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + write_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_write(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); +} + +static inline void cache_write_unlock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + up_write(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); } static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + write_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + up_write(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); } /* @@ -506,9 +553,9 @@ static void lh_exit(struct lock_history *lh) * Named 'next' because there is no corresponding * 'up/unlock' call since it's done automatically. */ -static void lh_next(struct lock_history *lh, sector_t b) +static void lh_next(struct lock_history *lh, sector_t b, unsigned long special) { - unsigned int index = cache_index(b, lh->no_previous); /* no_previous is num_locks */ + unsigned int index = cache_index_special(b, lh->no_previous, special); /* no_previous is num_locks */ if (lh->previous != lh->no_previous) { if (lh->previous != index) { @@ -614,12 +661,23 @@ static void __cache_inc_buffer(struct dm_buffer *b) WRITE_ONCE(b->last_accessed, jiffies); } +static struct dm_buffer *cache_get_noref(struct dm_buffer_cache *bc, sector_t block) +{ + struct dm_buffer *b; + + cache_read_lock(bc, block); + b = __cache_get(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].root, block); + cache_read_unlock(bc, block); + + return b; +} + static struct dm_buffer *cache_get(struct dm_buffer_cache *bc, sector_t block) { struct dm_buffer *b; cache_read_lock(bc, block); - b = __cache_get(&bc->trees[cache_index(block, bc->num_locks)].root, block); + b = __cache_get(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].root, block); if (b) { lru_reference(&b->lru); __cache_inc_buffer(b); @@ -666,12 +724,13 @@ struct evict_wrapper { * Wraps the buffer predicate turning it into an lru predicate. Adds * extra test for hold_count. */ -static enum evict_result __evict_pred(struct lru_entry *le, void *context) +static enum evict_result __evict_pred(struct lru_entry *le, void *context, void *bc) { struct evict_wrapper *w = context; struct dm_buffer *b = le_to_buffer(le); + struct dm_buffer_cache *bcc = (struct dm_buffer_cache *)bc; - lh_next(w->lh, b->block); + lh_next(w->lh, b->block, b->special ? b->block : bcc->special); if (atomic_read(&b->hold_count)) return ER_DONT_EVICT; @@ -687,13 +746,13 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode struct lru_entry *le; struct dm_buffer *b; - le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep); + le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep, (void *) bc); if (!le) return NULL; b = le_to_buffer(le); /* __evict_pred will have locked the appropriate tree. */ - rb_erase(&b->node, &bc->trees[cache_index(b->block, bc->num_locks)].root); + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, b->special ? b->block : bc->special)].root); return b; } @@ -741,7 +800,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_ struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context}; while (true) { - le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep); + le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep, (void *)bc); if (!le) break; @@ -792,7 +851,7 @@ static void __cache_iterate(struct dm_buffer_cache *bc, int list_mode, do { struct dm_buffer *b = le_to_buffer(le); - lh_next(lh, b->block); + lh_next(lh, b->block, bc->special); switch (fn(b, context)) { case IT_NEXT: @@ -858,8 +917,8 @@ static bool cache_insert(struct dm_buffer_cache *bc, struct dm_buffer *b) return false; cache_write_lock(bc, b->block); - BUG_ON(atomic_read(&b->hold_count) != 1); - r = __cache_insert(&bc->trees[cache_index(b->block, bc->num_locks)].root, b); + //BUG_ON(atomic_read(&b->hold_count) != 1); + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); if (r) lru_insert(&bc->lru[b->list_mode], &b->lru); cache_write_unlock(bc, b->block); @@ -867,14 +926,42 @@ static bool cache_insert(struct dm_buffer_cache *bc, struct dm_buffer *b) return r; } -/*--------------*/ +static bool cache_remove_nolru_new(struct dm_buffer_cache *bc, struct dm_buffer *b) +{ + bool r; + + cache_write_lock_special(bc, b->block, false); + cache_write_lock_special(bc, b->block, true); + + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); + bc->special = b->block; + b->special = true; + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); + + cache_write_unlock_special(bc, b->block, true); + cache_write_unlock_special(bc, b->block, false); + + return r; +} + +static bool cache_remove_nolru_old(struct dm_buffer_cache *bc, struct dm_buffer *b) +{ + bool r; + + cache_write_lock_special(bc, b->block, true); + cache_write_lock_special(bc, b->block, false); + + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); + bc->special = ULONG_MAX; + b->special = false; + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); + + cache_write_unlock_special(bc, b->block, false); + cache_write_unlock_special(bc, b->block, true); + + return r; +} -/* - * Removes buffer from cache, ownership of the buffer passes back to the caller. - * Fails if the hold_count is not one (ie. the caller holds the only reference). - * - * Not threadsafe. - */ static bool cache_remove(struct dm_buffer_cache *bc, struct dm_buffer *b) { bool r; @@ -885,7 +972,7 @@ static bool cache_remove(struct dm_buffer_cache *bc, struct dm_buffer *b) r = false; } else { r = true; - rb_erase(&b->node, &bc->trees[cache_index(b->block, bc->num_locks)].root); + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); lru_remove(&bc->lru[b->list_mode], &b->lru); } @@ -1019,6 +1106,12 @@ struct dm_bufio_client { struct dm_buffer_cache cache; /* must be last member */ }; +void dm_setup_buffer_cache(struct dm_bufio_client *bc, unsigned long block) +{ + bc->cache.special = block; +} +EXPORT_SYMBOL_GPL(dm_setup_buffer_cache); + /*----------------------------------------------------------------*/ #define dm_bufio_in_request() (!!current->bio_list) @@ -1792,6 +1885,7 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block, b->read_error = 0; b->write_error = 0; b->list_mode = LIST_CLEAN; + b->special = (block == c->cache.special); if (nf == NF_FRESH) b->state = 0; @@ -2642,6 +2736,19 @@ void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start) } EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset); +void dm_move_cache(struct dm_bufio_client *bc, unsigned long new) +{ + struct dm_buffer *b; + unsigned long old = bc->cache.special; + + b = cache_get_noref(&bc->cache, old); + cache_remove_nolru_old(&bc->cache, b); + + b = cache_get_noref(&bc->cache, new); + cache_remove_nolru_new(&bc->cache, b); +} +EXPORT_SYMBOL_GPL(dm_move_cache); + /*--------------------------------------------------------------*/ static unsigned int get_max_age_hz(void) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 6022189c1388..f485504d40f3 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -747,6 +747,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd) * root to avoid accessing broken btree. */ pmd->root = le64_to_cpu(disk_super->data_mapping_root); + dm_setup_bm_cache(pmd->bm, pmd->root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); __setup_btree_details(pmd); @@ -837,6 +838,7 @@ static int __begin_transaction(struct dm_pool_metadata *pmd) disk_super = dm_block_data(sblock); pmd->time = le32_to_cpu(disk_super->time); pmd->root = le64_to_cpu(disk_super->data_mapping_root); + dm_setup_bm_cache(pmd->bm, pmd->root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); pmd->trans_id = le64_to_cpu(disk_super->trans_id); pmd->flags = le32_to_cpu(disk_super->flags); @@ -1678,6 +1680,8 @@ static int __insert(struct dm_thin_device *td, dm_block_t block, if (r) return r; + dm_move_bm_cache(pmd->bm, pmd->root); + td->changed = true; if (inserted) td->mapped_blocks++; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index f682295af91f..1b2da00d9016 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -232,12 +232,27 @@ static inline unsigned int dm_num_hash_locks(void) { unsigned int num_locks = roundup_pow_of_two(num_online_cpus()) << 1; - return min_t(unsigned int, num_locks, DM_HASH_LOCKS_MAX); + return min_t(unsigned int, num_locks, DM_HASH_LOCKS_MAX) + 32; } #define DM_HASH_LOCKS_MULT 4294967291ULL #define DM_HASH_LOCKS_SHIFT 6 +static inline unsigned int dm_hash_locks_index_special(sector_t block, + unsigned int num_locks, + unsigned long special) +{ + + + sector_t h1 = (block * DM_HASH_LOCKS_MULT) >> DM_HASH_LOCKS_SHIFT; + sector_t h2 = h1 >> DM_HASH_LOCKS_SHIFT; + + if (block == special) + return ((h1 ^ h2) & 31) + num_locks - 32; + + return (h1 ^ h2) & (num_locks - 33); +} + static inline unsigned int dm_hash_locks_index(sector_t block, unsigned int num_locks) { diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 0e010e1204aa..da560f825298 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -414,6 +414,17 @@ struct dm_block_manager *dm_block_manager_create(struct block_device *bdev, } EXPORT_SYMBOL_GPL(dm_block_manager_create); +void dm_setup_bm_cache(struct dm_block_manager *bm, unsigned long block) +{ + dm_setup_buffer_cache(bm->bufio, block); +} +EXPORT_SYMBOL_GPL(dm_setup_bm_cache); + +void dm_move_bm_cache(struct dm_block_manager *bm, unsigned long block) +{ + dm_move_cache(bm->bufio, block); +} + void dm_block_manager_destroy(struct dm_block_manager *bm) { dm_bufio_client_destroy(bm->bufio); diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index f706d3de8d5a..25121bbc58d7 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -35,7 +35,9 @@ struct dm_block_manager; struct dm_block_manager *dm_block_manager_create( struct block_device *bdev, unsigned int block_size, unsigned int max_held_per_thread); +void dm_move_bm_cache(struct dm_block_manager *bm, unsigned long block); void dm_block_manager_destroy(struct dm_block_manager *bm); +void dm_setup_bm_cache(struct dm_block_manager *bm, unsigned long block); void dm_block_manager_reset(struct dm_block_manager *bm); unsigned int dm_bm_block_size(struct dm_block_manager *bm); diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 75e7d8cbb532..d7d7a33cc685 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -71,6 +71,8 @@ void *dm_bufio_read(struct dm_bufio_client *c, sector_t block, void *dm_bufio_get(struct dm_bufio_client *c, sector_t block, struct dm_buffer **bp); +void dm_setup_buffer_cache(struct dm_bufio_client *bc, unsigned long block); + /* * Like dm_bufio_read, but don't read anything from the disk. It is * expected that the caller initializes the buffer and marks it dirty. @@ -139,6 +141,8 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c */ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block); +void dm_move_cache(struct dm_bufio_client *bc, unsigned long block); + /* * Free the given range of buffers. * This is just a hint, if the buffer is in use or dirty, this function -- 2.43.0

2 1

[PATCH OLK-6.6] dm-thin: Add support for split cache
by Zhang Zekun 11 Feb '26

11 Feb '26

hulk inclusion category: feature bugzilla: NA CVE: NA -------------------------------------------------------- The cache of dm-thin is common used for first level btree and the second level btree, however the first level btree has less dm-buffer than the second level btree, which might cause extra look up steps for the first level btree when accessing the cache of the dm pool. Thus, add support for spliting the first level btree and the second level btree' cache, which might speed up the look up process of the first level btree routine. Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/md/dm-bufio.c | 167 ++++++++++++++---- drivers/md/dm-thin-metadata.c | 4 + drivers/md/dm.h | 17 +- drivers/md/persistent-data/dm-block-manager.c | 11 ++ drivers/md/persistent-data/dm-block-manager.h | 2 + include/linux/dm-bufio.h | 4 + 6 files changed, 174 insertions(+), 31 deletions(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 8ce77aec05d2..206c7c00be88 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -254,9 +254,9 @@ enum evict_result { ER_STOP, /* stop looking for something to evict */ }; -typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context); +typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context, void *bc); -static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep) +static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep, void *bc) { unsigned long tested = 0; struct list_head *h = lru->cursor; @@ -276,7 +276,7 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con atomic_set(&le->referenced, 0); } else { tested++; - switch (pred(le, context)) { + switch (pred(le, context, bc)) { case ER_EVICT: /* * Adjust the cursor, so we start the next @@ -362,6 +362,7 @@ struct dm_buffer { unsigned int stack_len; unsigned long stack_entries[MAX_STACK]; #endif + bool special; }; /*--------------------------------------------------------------*/ @@ -399,47 +400,93 @@ struct dm_buffer_cache { * on the locks. */ unsigned int num_locks; + unsigned long special; bool no_sleep; struct buffer_tree trees[]; }; static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); +static inline unsigned int cache_index_special(sector_t block, unsigned int num_locks, unsigned long special) +{ + return dm_hash_locks_index_special(block, num_locks, special); +} + static inline unsigned int cache_index(sector_t block, unsigned int num_locks) { return dm_hash_locks_index(block, num_locks); } +static inline void cache_read_lock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + down_read(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); +} + static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + read_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_read(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); } static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + read_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); + else + up_read(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); +} + +static inline void cache_read_unlock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + up_read(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); +} + +static inline void cache_write_lock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); else - up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_write(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); } static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + write_lock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + down_write(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); +} + +static inline void cache_write_unlock_special(struct dm_buffer_cache *bc, sector_t block, bool special) +{ + sector_t nb = special ? block : ULONG_MAX; + + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.spinlock); + else + up_write(&bc->trees[cache_index_special(block, bc->num_locks, nb)].u.lock); } static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block) { if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) - write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + write_unlock_bh(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.spinlock); else - up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); + up_write(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].u.lock); } /* @@ -506,9 +553,9 @@ static void lh_exit(struct lock_history *lh) * Named 'next' because there is no corresponding * 'up/unlock' call since it's done automatically. */ -static void lh_next(struct lock_history *lh, sector_t b) +static void lh_next(struct lock_history *lh, sector_t b, unsigned long special) { - unsigned int index = cache_index(b, lh->no_previous); /* no_previous is num_locks */ + unsigned int index = cache_index_special(b, lh->no_previous, special); /* no_previous is num_locks */ if (lh->previous != lh->no_previous) { if (lh->previous != index) { @@ -614,12 +661,23 @@ static void __cache_inc_buffer(struct dm_buffer *b) WRITE_ONCE(b->last_accessed, jiffies); } +static struct dm_buffer *cache_get_noref(struct dm_buffer_cache *bc, sector_t block) +{ + struct dm_buffer *b; + + cache_read_lock(bc, block); + b = __cache_get(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].root, block); + cache_read_unlock(bc, block); + + return b; +} + static struct dm_buffer *cache_get(struct dm_buffer_cache *bc, sector_t block) { struct dm_buffer *b; cache_read_lock(bc, block); - b = __cache_get(&bc->trees[cache_index(block, bc->num_locks)].root, block); + b = __cache_get(&bc->trees[cache_index_special(block, bc->num_locks, bc->special)].root, block); if (b) { lru_reference(&b->lru); __cache_inc_buffer(b); @@ -666,12 +724,13 @@ struct evict_wrapper { * Wraps the buffer predicate turning it into an lru predicate. Adds * extra test for hold_count. */ -static enum evict_result __evict_pred(struct lru_entry *le, void *context) +static enum evict_result __evict_pred(struct lru_entry *le, void *context, void *bc) { struct evict_wrapper *w = context; struct dm_buffer *b = le_to_buffer(le); + struct dm_buffer_cache *bcc = (struct dm_buffer_cache *)bc; - lh_next(w->lh, b->block); + lh_next(w->lh, b->block, b->special ? b->block : bcc->special); if (atomic_read(&b->hold_count)) return ER_DONT_EVICT; @@ -687,13 +746,13 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode struct lru_entry *le; struct dm_buffer *b; - le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep); + le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep, (void *) bc); if (!le) return NULL; b = le_to_buffer(le); /* __evict_pred will have locked the appropriate tree. */ - rb_erase(&b->node, &bc->trees[cache_index(b->block, bc->num_locks)].root); + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, b->special ? b->block : bc->special)].root); return b; } @@ -741,7 +800,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_ struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context}; while (true) { - le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep); + le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep, (void *)bc); if (!le) break; @@ -792,7 +851,7 @@ static void __cache_iterate(struct dm_buffer_cache *bc, int list_mode, do { struct dm_buffer *b = le_to_buffer(le); - lh_next(lh, b->block); + lh_next(lh, b->block, bc->special); switch (fn(b, context)) { case IT_NEXT: @@ -858,8 +917,8 @@ static bool cache_insert(struct dm_buffer_cache *bc, struct dm_buffer *b) return false; cache_write_lock(bc, b->block); - BUG_ON(atomic_read(&b->hold_count) != 1); - r = __cache_insert(&bc->trees[cache_index(b->block, bc->num_locks)].root, b); + //BUG_ON(atomic_read(&b->hold_count) != 1); + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); if (r) lru_insert(&bc->lru[b->list_mode], &b->lru); cache_write_unlock(bc, b->block); @@ -867,14 +926,42 @@ static bool cache_insert(struct dm_buffer_cache *bc, struct dm_buffer *b) return r; } -/*--------------*/ +static bool cache_remove_nolru_new(struct dm_buffer_cache *bc, struct dm_buffer *b) +{ + bool r; + + cache_write_lock_special(bc, b->block, false); + cache_write_lock_special(bc, b->block, true); + + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); + bc->special = b->block; + b->special = true; + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); + + cache_write_unlock_special(bc, b->block, true); + cache_write_unlock_special(bc, b->block, false); + + return r; +} + +static bool cache_remove_nolru_old(struct dm_buffer_cache *bc, struct dm_buffer *b) +{ + bool r; + + cache_write_lock_special(bc, b->block, true); + cache_write_lock_special(bc, b->block, false); + + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); + bc->special = ULONG_MAX; + b->special = false; + r = __cache_insert(&bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root, b); + + cache_write_unlock_special(bc, b->block, false); + cache_write_unlock_special(bc, b->block, true); + + return r; +} -/* - * Removes buffer from cache, ownership of the buffer passes back to the caller. - * Fails if the hold_count is not one (ie. the caller holds the only reference). - * - * Not threadsafe. - */ static bool cache_remove(struct dm_buffer_cache *bc, struct dm_buffer *b) { bool r; @@ -885,7 +972,7 @@ static bool cache_remove(struct dm_buffer_cache *bc, struct dm_buffer *b) r = false; } else { r = true; - rb_erase(&b->node, &bc->trees[cache_index(b->block, bc->num_locks)].root); + rb_erase(&b->node, &bc->trees[cache_index_special(b->block, bc->num_locks, bc->special)].root); lru_remove(&bc->lru[b->list_mode], &b->lru); } @@ -1019,6 +1106,12 @@ struct dm_bufio_client { struct dm_buffer_cache cache; /* must be last member */ }; +void dm_setup_buffer_cache(struct dm_bufio_client *bc, unsigned long block) +{ + bc->cache.special = block; +} +EXPORT_SYMBOL_GPL(dm_setup_buffer_cache); + /*----------------------------------------------------------------*/ #define dm_bufio_in_request() (!!current->bio_list) @@ -1792,6 +1885,7 @@ static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block, b->read_error = 0; b->write_error = 0; b->list_mode = LIST_CLEAN; + b->special = (block == c->cache.special); if (nf == NF_FRESH) b->state = 0; @@ -2642,6 +2736,19 @@ void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start) } EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset); +void dm_move_cache(struct dm_bufio_client *bc, unsigned long new) +{ + struct dm_buffer *b; + unsigned long old = bc->cache.special; + + b = cache_get_noref(&bc->cache, old); + cache_remove_nolru_old(&bc->cache, b); + + b = cache_get_noref(&bc->cache, new); + cache_remove_nolru_new(&bc->cache, b); +} +EXPORT_SYMBOL_GPL(dm_move_cache); + /*--------------------------------------------------------------*/ static unsigned int get_max_age_hz(void) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 6022189c1388..f485504d40f3 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -747,6 +747,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd) * root to avoid accessing broken btree. */ pmd->root = le64_to_cpu(disk_super->data_mapping_root); + dm_setup_bm_cache(pmd->bm, pmd->root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); __setup_btree_details(pmd); @@ -837,6 +838,7 @@ static int __begin_transaction(struct dm_pool_metadata *pmd) disk_super = dm_block_data(sblock); pmd->time = le32_to_cpu(disk_super->time); pmd->root = le64_to_cpu(disk_super->data_mapping_root); + dm_setup_bm_cache(pmd->bm, pmd->root); pmd->details_root = le64_to_cpu(disk_super->device_details_root); pmd->trans_id = le64_to_cpu(disk_super->trans_id); pmd->flags = le32_to_cpu(disk_super->flags); @@ -1678,6 +1680,8 @@ static int __insert(struct dm_thin_device *td, dm_block_t block, if (r) return r; + dm_move_bm_cache(pmd->bm, pmd->root); + td->changed = true; if (inserted) td->mapped_blocks++; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index f682295af91f..1b2da00d9016 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -232,12 +232,27 @@ static inline unsigned int dm_num_hash_locks(void) { unsigned int num_locks = roundup_pow_of_two(num_online_cpus()) << 1; - return min_t(unsigned int, num_locks, DM_HASH_LOCKS_MAX); + return min_t(unsigned int, num_locks, DM_HASH_LOCKS_MAX) + 32; } #define DM_HASH_LOCKS_MULT 4294967291ULL #define DM_HASH_LOCKS_SHIFT 6 +static inline unsigned int dm_hash_locks_index_special(sector_t block, + unsigned int num_locks, + unsigned long special) +{ + + + sector_t h1 = (block * DM_HASH_LOCKS_MULT) >> DM_HASH_LOCKS_SHIFT; + sector_t h2 = h1 >> DM_HASH_LOCKS_SHIFT; + + if (block == special) + return ((h1 ^ h2) & 31) + num_locks - 32; + + return (h1 ^ h2) & (num_locks - 33); +} + static inline unsigned int dm_hash_locks_index(sector_t block, unsigned int num_locks) { diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 0e010e1204aa..da560f825298 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -414,6 +414,17 @@ struct dm_block_manager *dm_block_manager_create(struct block_device *bdev, } EXPORT_SYMBOL_GPL(dm_block_manager_create); +void dm_setup_bm_cache(struct dm_block_manager *bm, unsigned long block) +{ + dm_setup_buffer_cache(bm->bufio, block); +} +EXPORT_SYMBOL_GPL(dm_setup_bm_cache); + +void dm_move_bm_cache(struct dm_block_manager *bm, unsigned long block) +{ + dm_move_cache(bm->bufio, block); +} + void dm_block_manager_destroy(struct dm_block_manager *bm) { dm_bufio_client_destroy(bm->bufio); diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h index f706d3de8d5a..25121bbc58d7 100644 --- a/drivers/md/persistent-data/dm-block-manager.h +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -35,7 +35,9 @@ struct dm_block_manager; struct dm_block_manager *dm_block_manager_create( struct block_device *bdev, unsigned int block_size, unsigned int max_held_per_thread); +void dm_move_bm_cache(struct dm_block_manager *bm, unsigned long block); void dm_block_manager_destroy(struct dm_block_manager *bm); +void dm_setup_bm_cache(struct dm_block_manager *bm, unsigned long block); void dm_block_manager_reset(struct dm_block_manager *bm); unsigned int dm_bm_block_size(struct dm_block_manager *bm); diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 75e7d8cbb532..d7d7a33cc685 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -71,6 +71,8 @@ void *dm_bufio_read(struct dm_bufio_client *c, sector_t block, void *dm_bufio_get(struct dm_bufio_client *c, sector_t block, struct dm_buffer **bp); +void dm_setup_buffer_cache(struct dm_bufio_client *bc, unsigned long block); + /* * Like dm_bufio_read, but don't read anything from the disk. It is * expected that the caller initializes the buffer and marks it dirty. @@ -139,6 +141,8 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c */ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block); +void dm_move_cache(struct dm_bufio_client *bc, unsigned long block); + /* * Free the given range of buffers. * This is just a hint, if the buffer is in use or dirty, this function -- 2.43.0

2 1

[PATCH OLK-6.6 0/3] fix CVE-2025-38449
by Wupeng Ma 10 Feb '26

10 Feb '26

fix CVE-2025-38449. Thomas Zimmermann (2): drm/gem: Acquire references on GEM handles for framebuffers drm/framebuffer: Acquire internal references on GEM handles Wupeng Ma (1): drm: fix kabi for struct drm_framebuffer drivers/gpu/drm/drm_framebuffer.c | 31 ++++++++++++++- drivers/gpu/drm/drm_gem.c | 64 ++++++++++++++++++++++++++----- drivers/gpu/drm/drm_internal.h | 2 + include/drm/drm_framebuffer.h | 9 +++++ 4 files changed, 95 insertions(+), 11 deletions(-) -- 2.43.0

2 4

[PATCH OLK-6.6] mm: slub: avoid wake up kswapd in set_track_prepare
by Wupeng Ma 10 Feb '26

10 Feb '26

From: yangshiguang <yangshiguang(a)xiaomi.com> stable inclusion from stable-v6.6.105 commit 522ffe298627cfe72539d72167c2e20e72b5e856 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/8442 CVE: CVE-2025-39843 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f ] set_track_prepare() can incur lock recursion. The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock. Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags, which do not contain __GFP_KSWAPD_RECLAIM in the debug_objects_fill_pool() case. Inside stack depot they are processed by gfp_nested_mask(). Since ___slab_alloc() has preemption disabled, we mask out __GFP_DIRECT_RECLAIM from the flags there. The oops looks something like: BUG: spinlock recursion on CPU#3, swapper/3/0 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3 Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT) Call trace: spin_bug+0x0 _raw_spin_lock_irqsave+0x80 hrtimer_try_to_cancel+0x94 task_contending+0x10c enqueue_dl_entity+0x2a4 dl_server_start+0x74 enqueue_task_fair+0x568 enqueue_task+0xac do_activate_task+0x14c ttwu_do_activate+0xcc try_to_wake_up+0x6c8 default_wake_function+0x20 autoremove_wake_function+0x1c __wake_up+0xac wakeup_kswapd+0x19c wake_all_kswapds+0x78 __alloc_pages_slowpath+0x1ac __alloc_pages_noprof+0x298 stack_depot_save_flags+0x6b0 stack_depot_save+0x14 set_track_prepare+0x5c ___slab_alloc+0xccc __kmalloc_cache_noprof+0x470 __set_page_owner+0x2bc post_alloc_hook[jt]+0x1b8 prep_new_page+0x28 get_page_from_freelist+0x1edc __alloc_pages_noprof+0x13c alloc_slab_page+0x244 allocate_slab+0x7c ___slab_alloc+0x8e8 kmem_cache_alloc_noprof+0x450 debug_objects_fill_pool+0x22c debug_object_activate+0x40 enqueue_hrtimer[jt]+0xdc hrtimer_start_range_ns+0x5f8 ... Signed-off-by: yangshiguang <yangshiguang(a)xiaomi.com> Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects") Cc: stable(a)vger.kernel.org Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: mm/slub.c [Wupeng Ma: context conflicts] Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- mm/slub.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 25516a5cbf04d..7458569c81400 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -830,19 +830,19 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -864,9 +864,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1748,9 +1748,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3232,9 +3232,14 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * For debug caches here we had to go through * alloc_single_from_partial() so just store the * tracking info and return the object. + * + * Due to disabled preemption we need to disallow + * blocking. The flags are further adjusted by + * gfp_nested_mask() in stack_depot itself. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -3266,7 +3271,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -3553,8 +3559,12 @@ static noinline void free_to_partial_list( unsigned long flags; depot_stack_handle_t handle = 0; + /* + * We cannot use GFP_NOWAIT as there are callsites where waking up + * kswapd could deadlock + */ if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); -- 2.43.0

2 1

[PATCH OLK-6.6] scsi: qla2xxx: Sanitize payload size to prevent member overflow
by Yongjian Sun 10 Feb '26

10 Feb '26

From: Jiasheng Jiang <jiashengjiangcool(a)gmail.com> mainline inclusion from mainline-v6.19-rc7 commit 19bc5f2a6962dfaa0e32d0e0bc2271993d85d414 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13592 CVE: CVE-2026-23059 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- In qla27xx_copy_fpin_pkt() and qla27xx_copy_multiple_pkt(), the frame_size reported by firmware is used to calculate the copy length into item->iocb. However, the iocb member is defined as a fixed-size 64-byte array within struct purex_item. If the reported frame_size exceeds 64 bytes, subsequent memcpy calls will overflow the iocb member boundary. While extra memory might be allocated, this cross-member write is unsafe and triggers warnings under CONFIG_FORTIFY_SOURCE. Fix this by capping total_bytes to the size of the iocb member (64 bytes) before allocation and copying. This ensures all copies remain within the bounds of the destination structure member. Fixes: 875386b98857 ("scsi: qla2xxx: Add Unsolicited LS Request and Response Support for NVMe") Signed-off-by: Jiasheng Jiang <jiashengjiangcool(a)gmail.com> Reviewed-by: Himanshu Madhani <hmadhani2024(a)gmail.com> Link: https://patch.msgid.link/20260106205344.18031-1-jiashengjiangcool@gmail.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- drivers/scsi/qla2xxx/qla_isr.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index d48007e18288..c025e853101d 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -878,6 +878,9 @@ qla27xx_copy_multiple_pkt(struct scsi_qla_host *vha, void **pkt, payload_size = sizeof(purex->els_frame_payload); } + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; no_bytes = (pending_bytes > payload_size) ? payload_size : pending_bytes; @@ -1163,6 +1166,10 @@ qla27xx_copy_fpin_pkt(struct scsi_qla_host *vha, void **pkt, total_bytes = (le16_to_cpu(purex->frame_size) & 0x0FFF) - PURX_ELS_HEADER_SIZE; + + if (total_bytes > sizeof(item->iocb.iocb)) + total_bytes = sizeof(item->iocb.iocb); + pending_bytes = total_bytes; entry_count = entry_count_remaining = purex->entry_count; no_bytes = (pending_bytes > sizeof(purex->els_frame_payload)) ? -- 2.39.2

2 1

[PATCH OLK-5.10] pNFS: Fix a deadlock when returning a delegation during open()
by Li Lingfeng 10 Feb '26

10 Feb '26

From: Trond Myklebust <trond.myklebust(a)hammerspace.com> mainline inclusion from mainline-v6.19-rc6 commit 857bf9056291a16785ae3be1d291026b2437fc48 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13583 CVE: CVE-2026-23050 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Reported-by: Benjamin Coddington <bcodding(a)hammerspace.com> Fixes: 29ade5db1293 ("pNFS: Wait on outstanding layoutreturns to complete in pnfs_roc()") Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Conflicts: fs/nfs/pnfs.c [Commit 5468fc8298a9 ("NFSv4/pNFS: Do layout state recovery upon reboot") add definition of pnfs_layout_return_on_reboot() before pnfs_roc().] Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/nfs/nfs4proc.c | 6 ++--- fs/nfs/pnfs.c | 58 +++++++++++++++++++++++++++++++++-------------- fs/nfs/pnfs.h | 17 ++++++-------- 3 files changed, 51 insertions(+), 30 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 39a337c00c5a..4b3c614361bd 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3771,8 +3771,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -6566,7 +6566,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 47787a5f999d..de00ef7484d8 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1420,10 +1420,9 @@ pnfs_commit_and_return_layout(struct inode *inode) return ret; } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1434,7 +1433,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1447,20 +1446,14 @@ bool pnfs_roc(struct inode *ino, lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1469,12 +1462,43 @@ bool pnfs_roc(struct inode *ino, if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1514,7 +1538,7 @@ bool pnfs_roc(struct inode *ino, out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a7cf84a6673b..5adb7aad89a3 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -294,10 +294,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -760,12 +759,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } -- 2.52.0

2 1

[PATCH OLK-6.6] netfilter: nf_tables: remove redundant chain validation on register store
by Dong Chenchen 10 Feb '26

10 Feb '26

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v6.6.119 commit a9c87779df20f0e07c0354aeecc52fc1a30ae798 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8497 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a67fd55f6a09f4119b7232c19e0f348fe31ab0db ] This validation predates the introduction of the state machine that determines when to enter slow path validation for error reporting. Currently, table validation is perform when: - new rule contains expressions that need validation. - new set element with jump/goto verdict. Validation on register store skips most checks with no basechains, still this walks the graph searching for loops and ensuring expressions are called from the right hook. Remove this. Fixes: a654de8fdc18 ("netfilter: nf_tables: fix chain dependency validation") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: net/netfilter/nf_tables_api.c [commit 14fb07130c7d and 7ea0522ef81a are not backport] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nf_tables_api.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ae06f28f0c55..0f0648986710 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -11007,21 +11007,10 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_data_types type, unsigned int len) { - int err; - switch (reg) { case NFT_REG_VERDICT: if (type != NFT_DATA_VERDICT) return -EINVAL; - - if (data != NULL && - (data->verdict.code == NFT_GOTO || - data->verdict.code == NFT_JUMP)) { - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - } - return 0; default: if (type != NFT_DATA_VALUE) -- 2.25.1

2 1

[PATCH OLK-6.6] smc91x: fix broken irq-context in PREEMPT_RT
by Wupeng Ma 10 Feb '26

10 Feb '26

From: Yeoreum Yun <yeoreum.yun(a)arm.com> stable inclusion from stable-v6.6.120 commit ef277ae121b3249c99994652210a326b52d527b0 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8372 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 6402078bd9d1ed46e79465e1faaa42e3458f8a33 ] When smc91x.c is built with PREEMPT_RT, the following splat occurs in FVP_RevC: [ 13.055000] smc91x LNRO0003:00 eth0: link up, 10Mbps, half-duplex, lpa 0x0000 [ 13.062137] BUG: workqueue leaked atomic, lock or RCU: kworker/2:1[106] [ 13.062137] preempt=0x00000000 lock=0->0 RCU=0->1 workfn=mld_ifc_work [ 13.062266] C ** replaying previous printk message ** [ 13.062266] CPU: 2 UID: 0 PID: 106 Comm: kworker/2:1 Not tainted 6.18.0-dirty #179 PREEMPT_{RT,(full)} [ 13.062353] Hardware name: , BIOS [ 13.062382] Workqueue: mld mld_ifc_work [ 13.062469] Call trace: [ 13.062494] show_stack+0x24/0x40 (C) [ 13.062602] __dump_stack+0x28/0x48 [ 13.062710] dump_stack_lvl+0x7c/0xb0 [ 13.062818] dump_stack+0x18/0x34 [ 13.062926] process_scheduled_works+0x294/0x450 [ 13.063043] worker_thread+0x260/0x3d8 [ 13.063124] kthread+0x1c4/0x228 [ 13.063235] ret_from_fork+0x10/0x20 This happens because smc_special_trylock() disables IRQs even on PREEMPT_RT, but smc_special_unlock() does not restore IRQs on PREEMPT_RT. The reason is that smc_special_unlock() calls spin_unlock_irqrestore(), and rcu_read_unlock_bh() in __dev_queue_xmit() cannot invoke rcu_read_unlock() through __local_bh_enable_ip() when current->softirq_disable_cnt becomes zero. To address this issue, replace smc_special_trylock() with spin_trylock_irqsave(). Fixes: 342a93247e08 ("locking/spinlock: Provide RT variant header: <linux/spinlock_rt.h>") Signed-off-by: Yeoreum Yun <yeoreum.yun(a)arm.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20251217085115.1730036-1-yeoreum.yun@arm.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yuan can <yuancan(a)huawei.com> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- drivers/net/ethernet/smsc/smc91x.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 032eccf8eb428..7c2fdd02f1d34 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -515,15 +515,7 @@ static inline void smc_rcv(struct net_device *dev) * any other concurrent access and C would always interrupt B. But life * isn't that easy in a SMP world... */ -#define smc_special_trylock(lock, flags) \ -({ \ - int __ret; \ - local_irq_save(flags); \ - __ret = spin_trylock(lock); \ - if (!__ret) \ - local_irq_restore(flags); \ - __ret; \ -}) +#define smc_special_trylock(lock, flags) spin_trylock_irqsave(lock, flags) #define smc_special_lock(lock, flags) spin_lock_irqsave(lock, flags) #define smc_special_unlock(lock, flags) spin_unlock_irqrestore(lock, flags) #else -- 2.43.0

2 1

[PATCH OLK-6.6] net: usb: asix: validate PHY address before use
by Wupeng Ma 10 Feb '26

10 Feb '26

From: Deepanshu Kartikey <kartikey406(a)gmail.com> stable inclusion from stable-v6.6.120 commit 38722e69ee64dbb020028c93898d25d6f4c0e0b2 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8372 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a1e077a3f76eea0dc671ed6792e7d543946227e8 ] The ASIX driver reads the PHY address from the USB device via asix_read_phy_addr(). A malicious or faulty device can return an invalid address (>= PHY_MAX_ADDR), which causes a warning in mdiobus_get_phy(): addr 207 out of range WARNING: drivers/net/phy/mdio_bus.c:76 Validate the PHY address in asix_read_phy_addr() and remove the now-redundant check in ax88172a.c. Reported-by: syzbot+3d43c9066a5b54902232(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=3d43c9066a5b54902232 Tested-by: syzbot+3d43c9066a5b54902232(a)syzkaller.appspotmail.com Fixes: 7e88b11a862a ("net: usb: asix: refactor asix_read_phy_addr() and handle errors on return") Link: https://lore.kernel.org/all/20251217085057.270704-1-kartikey406@gmail.com/T/ [v1] Signed-off-by: Deepanshu Kartikey <kartikey406(a)gmail.com> Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> Link: https://patch.msgid.link/20251218011156.276824-1-kartikey406@gmail.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yuan can <yuancan(a)huawei.com> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- drivers/net/usb/asix_common.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7fd763917ae2c..6ab3486072cb0 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -335,6 +335,11 @@ int asix_read_phy_addr(struct usbnet *dev, bool internal) offset = (internal ? 1 : 0); ret = buf[offset]; + if (ret >= PHY_MAX_ADDR) { + netdev_err(dev->net, "invalid PHY address: %d\n", ret); + return -ENODEV; + } + netdev_dbg(dev->net, "%s PHY address 0x%x\n", internal ? "internal" : "external", ret); -- 2.43.0

2 1

[PATCH OLK-6.6] mm: slub: avoid wake up kswapd in set_track_prepare
by Wupeng Ma 10 Feb '26

10 Feb '26

From: yangshiguang <yangshiguang(a)xiaomi.com> stable inclusion from stable-v6.6.105 commit 522ffe298627cfe72539d72167c2e20e72b5e856 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICYXVB CVE: CVE-2025-39843 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f ] set_track_prepare() can incur lock recursion. The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock. Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags, which do not contain __GFP_KSWAPD_RECLAIM in the debug_objects_fill_pool() case. Inside stack depot they are processed by gfp_nested_mask(). Since ___slab_alloc() has preemption disabled, we mask out __GFP_DIRECT_RECLAIM from the flags there. The oops looks something like: BUG: spinlock recursion on CPU#3, swapper/3/0 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3 Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT) Call trace: spin_bug+0x0 _raw_spin_lock_irqsave+0x80 hrtimer_try_to_cancel+0x94 task_contending+0x10c enqueue_dl_entity+0x2a4 dl_server_start+0x74 enqueue_task_fair+0x568 enqueue_task+0xac do_activate_task+0x14c ttwu_do_activate+0xcc try_to_wake_up+0x6c8 default_wake_function+0x20 autoremove_wake_function+0x1c __wake_up+0xac wakeup_kswapd+0x19c wake_all_kswapds+0x78 __alloc_pages_slowpath+0x1ac __alloc_pages_noprof+0x298 stack_depot_save_flags+0x6b0 stack_depot_save+0x14 set_track_prepare+0x5c ___slab_alloc+0xccc __kmalloc_cache_noprof+0x470 __set_page_owner+0x2bc post_alloc_hook[jt]+0x1b8 prep_new_page+0x28 get_page_from_freelist+0x1edc __alloc_pages_noprof+0x13c alloc_slab_page+0x244 allocate_slab+0x7c ___slab_alloc+0x8e8 kmem_cache_alloc_noprof+0x450 debug_objects_fill_pool+0x22c debug_object_activate+0x40 enqueue_hrtimer[jt]+0xdc hrtimer_start_range_ns+0x5f8 ... Signed-off-by: yangshiguang <yangshiguang(a)xiaomi.com> Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects") Cc: stable(a)vger.kernel.org Signed-off-by: Vlastimil Babka <vbabka(a)suse.cz> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: mm/slub.c [Wupeng Ma: context conflicts] Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- mm/slub.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 25516a5cbf04d..7458569c81400 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -830,19 +830,19 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -864,9 +864,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1748,9 +1748,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3232,9 +3232,14 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * For debug caches here we had to go through * alloc_single_from_partial() so just store the * tracking info and return the object. + * + * Due to disabled preemption we need to disallow + * blocking. The flags are further adjusted by + * gfp_nested_mask() in stack_depot itself. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -3266,7 +3271,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -3553,8 +3559,12 @@ static noinline void free_to_partial_list( unsigned long flags; depot_stack_handle_t handle = 0; + /* + * We cannot use GFP_NOWAIT as there are callsites where waking up + * kswapd could deadlock + */ if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); -- 2.43.0

2 1

[PATCH OLK-6.6] libceph: return the handler error from mon_handle_auth_done()
by Wupeng Ma 10 Feb '26

10 Feb '26

From: Ilya Dryomov <idryomov(a)gmail.com> stable inclusion from stable-v6.6.121 commit e097cd858196b1914309e7e3d79b4fa79383754d category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13501 CVE: CVE-2026-22992 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit e84b48d31b5008932c0a0902982809fbaa1d3b70 upstream. Currently any error from ceph_auth_handle_reply_done() is propagated via finish_auth() but isn't returned from mon_handle_auth_done(). This results in higher layers learning that (despite the monitor considering us to be successfully authenticated) something went wrong in the authentication phase and reacting accordingly, but msgr2 still trying to proceed with establishing the session in the background. In the case of secure mode this can trigger a WARN in setup_crypto() and later lead to a NULL pointer dereference inside of prepare_auth_signature(). Cc: stable(a)vger.kernel.org Fixes: cd1a677cad99 ("libceph, ceph: implement msgr2.1 protocol (crc and secure modes)") Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com> Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko(a)ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- net/ceph/mon_client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 68f9552931776..0f8b8335981cf 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1417,7 +1417,7 @@ static int mon_handle_auth_done(struct ceph_connection *con, if (!ret) finish_hunting(monc); mutex_unlock(&monc->mutex); - return 0; + return ret; } static int mon_handle_auth_bad_method(struct ceph_connection *con, -- 2.43.0

2 1

[PATCH OLK-6.6] devlink: rate: Unset parent pointer in devl_rate_nodes_destroy
by Wupeng Ma 10 Feb '26

10 Feb '26

From: Shay Drory <shayd(a)nvidia.com> stable inclusion from stable-v6.6.118 commit 715d9cda646a8a38ea8b2bb5afb679a7464055e2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11217 CVE: CVE-2025-40251 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f94c1a114ac209977bdf5ca841b98424295ab1f0 ] The function devl_rate_nodes_destroy is documented to "Unset parent for all rate objects". However, it was only calling the driver-specific `rate_leaf_parent_set` or `rate_node_parent_set` ops and decrementing the parent's refcount, without actually setting the `devlink_rate->parent` pointer to NULL. This leaves a dangling pointer in the `devlink_rate` struct, which cause refcount error in netdevsim[1] and mlx5[2]. In addition, this is inconsistent with the behavior of `devlink_nl_rate_parent_node_set`, where the parent pointer is correctly cleared. This patch fixes the issue by explicitly setting `devlink_rate->parent` to NULL after notifying the driver, thus fulfilling the function's documented behavior for all rate objects. [1] repro steps: echo 1 > /sys/bus/netdevsim/new_device devlink dev eswitch set netdevsim/netdevsim1 mode switchdev echo 1 > /sys/bus/netdevsim/devices/netdevsim1/sriov_numvfs devlink port function rate add netdevsim/netdevsim1/test_node devlink port function rate set netdevsim/netdevsim1/128 parent test_node echo 1 > /sys/bus/netdevsim/del_device dmesg: refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 8 PID: 1530 at lib/refcount.c:31 refcount_warn_saturate+0x42/0xe0 CPU: 8 UID: 0 PID: 1530 Comm: bash Not tainted 6.18.0-rc4+ #1 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:refcount_warn_saturate+0x42/0xe0 Call Trace: <TASK> devl_rate_leaf_destroy+0x8d/0x90 __nsim_dev_port_del+0x6c/0x70 [netdevsim] nsim_dev_reload_destroy+0x11c/0x140 [netdevsim] nsim_drv_remove+0x2b/0xb0 [netdevsim] device_release_driver_internal+0x194/0x1f0 bus_remove_device+0xc6/0x130 device_del+0x159/0x3c0 device_unregister+0x1a/0x60 del_device_store+0x111/0x170 [netdevsim] kernfs_fop_write_iter+0x12e/0x1e0 vfs_write+0x215/0x3d0 ksys_write+0x5f/0xd0 do_syscall_64+0x55/0x10f0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 [2] devlink dev eswitch set pci/0000:08:00.0 mode switchdev devlink port add pci/0000:08:00.0 flavour pcisf pfnum 0 sfnum 1000 devlink port function rate add pci/0000:08:00.0/group1 devlink port function rate set pci/0000:08:00.0/32768 parent group1 modprobe -r mlx5_ib mlx5_fwctl mlx5_core dmesg: refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 7 PID: 16151 at lib/refcount.c:31 refcount_warn_saturate+0x42/0xe0 CPU: 7 UID: 0 PID: 16151 Comm: bash Not tainted 6.17.0-rc7_for_upstream_min_debug_2025_10_02_12_44 #1 NONE Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:refcount_warn_saturate+0x42/0xe0 Call Trace: <TASK> devl_rate_leaf_destroy+0x8d/0x90 mlx5_esw_offloads_devlink_port_unregister+0x33/0x60 [mlx5_core] mlx5_esw_offloads_unload_rep+0x3f/0x50 [mlx5_core] mlx5_eswitch_unload_sf_vport+0x40/0x90 [mlx5_core] mlx5_sf_esw_event+0xc4/0x120 [mlx5_core] notifier_call_chain+0x33/0xa0 blocking_notifier_call_chain+0x3b/0x50 mlx5_eswitch_disable_locked+0x50/0x110 [mlx5_core] mlx5_eswitch_disable+0x63/0x90 [mlx5_core] mlx5_unload+0x1d/0x170 [mlx5_core] mlx5_uninit_one+0xa2/0x130 [mlx5_core] remove_one+0x78/0xd0 [mlx5_core] pci_device_remove+0x39/0xa0 device_release_driver_internal+0x194/0x1f0 unbind_store+0x99/0xa0 kernfs_fop_write_iter+0x12e/0x1e0 vfs_write+0x215/0x3d0 ksys_write+0x5f/0xd0 do_syscall_64+0x53/0x1f0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Fixes: d75559845078 ("devlink: Allow setting parent node of rate objects") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Reviewed-by: Carolina Jubran <cjubran(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Link: https://patch.msgid.link/1763381149-1234377-1-git-send-email-tariqt@nvidia.… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> --- net/devlink/rate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/devlink/rate.c b/net/devlink/rate.c index dff1593b8406a..e7e80af4abaf6 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -702,13 +702,15 @@ void devl_rate_nodes_destroy(struct devlink *devlink) if (!devlink_rate->parent) continue; - refcount_dec(&devlink_rate->parent->refcnt); if (devlink_rate_is_leaf(devlink_rate)) ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); else if (devlink_rate_is_node(devlink_rate)) ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); + + refcount_dec(&devlink_rate->parent->refcnt); + devlink_rate->parent = NULL; } list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate)) { -- 2.43.0

2 1

[PATCH OLK-6.6 0/3] fix CVE-2025-38449
by Wupeng Ma 10 Feb '26

10 Feb '26

fix CVE-2025-38449. Thomas Zimmermann (2): drm/gem: Acquire references on GEM handles for framebuffers drm/framebuffer: Acquire internal references on GEM handles Wupeng Ma (1): drm: fix kabi for struct drm_framebuffer drivers/gpu/drm/drm_framebuffer.c | 31 ++++++++++++++- drivers/gpu/drm/drm_gem.c | 64 ++++++++++++++++++++++++++----- drivers/gpu/drm/drm_internal.h | 2 + include/drm/drm_framebuffer.h | 9 +++++ 4 files changed, 95 insertions(+), 11 deletions(-) -- 2.43.0

2 4

[PATCH OLK-6.6 v2 0/4] bpf: sockmap fixes
by Dong Chenchen 10 Feb '26

10 Feb '26

patch of sockmap fixes Dong Chenchen (1): Revert "bpf, sockmap: Add sk_rmem_alloc check for sockmap" Levi Zim (2): skmsg: Return copied bytes in sk_msg_memcopy_from_iter tcp_bpf: Fix copied value in tcp_bpf_sendmsg Zijian Zhang (1): tcp_bpf: Add sk_rmem_alloc related logic for tcp_bpf ingress redirection include/linux/skmsg.h | 11 ++++++++--- net/core/skmsg.c | 11 ++++------- net/ipv4/tcp_bpf.c | 23 +++++++---------------- 3 files changed, 19 insertions(+), 26 deletions(-) -- 2.25.1

2 5

[PATCH OLK-6.6] tracing: Add recursion protection in kernel stack trace recording
by Tengda Wu 10 Feb '26

10 Feb '26

From: Steven Rostedt <rostedt(a)goodmis.org> mainline inclusion from mainline-v6.19-rc5 commit 5f1ef0dfcb5b7f4a91a9b0e0ba533efd9f7e2cdb category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8496 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Link: https://lore.kernel.org/all/20260102122807.7025fc87@gandalf.local.home/ Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Joel Fernandes <joel(a)joelfernandes.org> Cc: "Paul E. McKenney" <paulmck(a)kernel.org> Cc: Boqun Feng <boqun.feng(a)gmail.com> Link: https://patch.msgid.link/20260105203141.515cd49f@gandalf.local.home Reported-by: Yao Kai <yaokai34(a)huawei.com> Tested-by: Yao Kai <yaokai34(a)huawei.com> Fixes: 5f5fa7ea89dc ("rcu: Don't use negative nesting depth in __rcu_read_unlock()") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Conflicts: kernel/trace/trace.c [Context conflict] Signed-off-by: Tengda Wu <wutengda(a)huaweicloud.com> --- include/linux/trace_recursion.h | 9 +++++++++ kernel/trace/trace.c | 6 ++++++ 2 files changed, 15 insertions(+) diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index d48cd92d2364..67e6a9923d56 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -34,6 +34,13 @@ enum { TRACE_INTERNAL_SIRQ_BIT, TRACE_INTERNAL_TRANSITION_BIT, + /* Internal event use recursion bits */ + TRACE_INTERNAL_EVENT_BIT, + TRACE_INTERNAL_EVENT_NMI_BIT, + TRACE_INTERNAL_EVENT_IRQ_BIT, + TRACE_INTERNAL_EVENT_SIRQ_BIT, + TRACE_INTERNAL_EVENT_TRANSITION_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. @@ -97,6 +104,8 @@ enum { #define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_EVENT_START TRACE_INTERNAL_EVENT_BIT + #define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b0751e52d40e..4c9bcb08d947 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3126,6 +3126,11 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; + int bit; + + bit = trace_test_and_set_recursion(_THIS_IP_, _RET_IP_, TRACE_EVENT_START); + if (bit < 0) + return; /* * Add one, for this function and the call to save_stack_trace() @@ -3181,6 +3186,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); + trace_clear_recursion(bit); preempt_enable_notrace(); } -- 2.34.1

2 2

[PATCH OLK-5.10] tracing: Add recursion protection in kernel stack trace recording
by Tengda Wu 10 Feb '26

10 Feb '26

From: Steven Rostedt <rostedt(a)goodmis.org> mainline inclusion from mainline-v6.19-rc5 commit 5f1ef0dfcb5b7f4a91a9b0e0ba533efd9f7e2cdb category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8496 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 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. Link: https://lore.kernel.org/all/20260102122807.7025fc87@gandalf.local.home/ Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Joel Fernandes <joel(a)joelfernandes.org> Cc: "Paul E. McKenney" <paulmck(a)kernel.org> Cc: Boqun Feng <boqun.feng(a)gmail.com> Link: https://patch.msgid.link/20260105203141.515cd49f@gandalf.local.home Reported-by: Yao Kai <yaokai34(a)huawei.com> Tested-by: Yao Kai <yaokai34(a)huawei.com> Fixes: 5f5fa7ea89dc ("rcu: Don't use negative nesting depth in __rcu_read_unlock()") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Conflicts: kernel/trace/trace.c kernel/trace/trace.h include/linux/trace_recursion.h [The conflicts are due to we did not backport 0264c8c9e1b5 ("ftrace: Move the recursion testing into global headers"), which is a cleanup patch] Signed-off-by: Tengda Wu <wutengda(a)huaweicloud.com> --- kernel/trace/trace.c | 6 ++++++ kernel/trace/trace.h | 9 +++++++++ 2 files changed, 15 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6c5a503987e7..50dda48f6e6b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2994,6 +2994,11 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; + int bit; + + bit = trace_test_and_set_recursion(TRACE_EVENT_START); + if (bit < 0) + return; /* * Add one, for this function and the call to save_stack_trace() @@ -3049,6 +3054,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); + trace_clear_recursion(bit); preempt_enable_notrace(); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 139d4e47489d..27e9d7659a48 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -599,6 +599,13 @@ enum { TRACE_INTERNAL_SIRQ_BIT, TRACE_INTERNAL_TRANSITION_BIT, + /* Internal event use recursion bits */ + TRACE_INTERNAL_EVENT_BIT, + TRACE_INTERNAL_EVENT_NMI_BIT, + TRACE_INTERNAL_EVENT_IRQ_BIT, + TRACE_INTERNAL_EVENT_SIRQ_BIT, + TRACE_INTERNAL_EVENT_TRANSITION_BIT, + TRACE_BRANCH_BIT, /* * Abuse of the trace_recursion. @@ -659,6 +666,8 @@ enum { #define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_EVENT_START TRACE_INTERNAL_EVENT_BIT + #define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) enum { -- 2.34.1

2 1

[PATCH OLK-6.6 00/12] arm_mpam: Introduce the Narrow-PARTID feature for MPAM driver
by Zeng Heng 09 Feb '26

09 Feb '26

The narrow-partid feature in MPAM allows for a more efficient use of PARTIDs by enabling a many-to-one mapping of reqpartids (requested PARTIDs) to intpartids (internal PARTIDs). This mapping reduces the number of unique PARTIDs needed, thus allowing more tasks or processes to be monitored and managed with the available resources. For a mixture of MSCs system, for MSCs that do not support narrow-partid, we use the PARTIDs exceeding the number of closids as reqPARTIDs for expanding the monitoring groups. Therefore, we will expand the information contained in the RMID, so that it includes not only PMG, but also reqPARTIDs information. The new RMID would be like: RMID = (reqPARTID << shift | PMG). Each control group has m (req)PARTIDs, which are used to expand the number of monitoring groups under one control group. Therefore, the number of monitoring groups is no longer limited by the range of MPAM's PMG, which enhances the extensibility of the system's monitoring capabilities. Dave Martin (1): arm_mpam: Set INTERNAL as needed when setting MSC controls Zeng Heng (11): arm_mpam: Introduce the definitions of intPARTID and reqPARTID arm_mpam: Expand the composition of RMID arm_mpam: Automatically synchronize the configuration of all sub-monitoring groups fs/resctrl: Implementing the dynamic allocation of reqPARTIDs fs/resctrl: Deploy resctrl_arch_expand_rmid() arm64/mpam: Add limitation for the Narrow-PARTID feature fs/resctrl: Fix limit of root group Revert "fs/resctrl: Fix configuration to wrong control group when CDP is enabled" arm64/mpam: Fix rdtgroup_init_res() arm64/mpam: Add mpam_sync_config() fs/resctrl: rdt_destroy_limbo() after umount arch/x86/include/asm/resctrl.h | 11 +- drivers/platform/mpam/mpam_devices.c | 86 ++++- drivers/platform/mpam/mpam_internal.h | 7 +- drivers/platform/mpam/mpam_resctrl.c | 454 +++++++++++++++++++++----- fs/resctrl/ctrlmondata.c | 28 +- fs/resctrl/monitor.c | 50 ++- fs/resctrl/rdtgroup.c | 38 ++- include/linux/arm_mpam.h | 17 +- include/linux/resctrl.h | 18 + 9 files changed, 569 insertions(+), 140 deletions(-) -- 2.25.1

2 13

[PATCH v3 OLK-6.6 0/4] Fix CVE-2025-21696
by Ze Zuo 09 Feb '26

09 Feb '26

Fix CVE-2025-21696. change since v2: - add debug fix patch for second patch. David Hildenbrand (1): mm/mremap: fix WARN with uffd that has remap events disabled Lokesh Gidra (1): userfaultfd: move userfaultfd_ctx struct to header file Ryan Roberts (1): mm: clear uffd-wp PTE/PMD state on mremap() Ze Zuo (1): userfaultfd: fix kabi breakage due to struct userfaultfd_ctx fs/userfaultfd.c | 39 ------------------- include/linux/userfaultfd_k.h | 53 +++++++++++++++++++++++++ mm/huge_memory.c | 12 ++++++ mm/hugetlb.c | 14 ++++++- mm/mremap.c | 73 ++++++++++++++++++++++++++--------- 5 files changed, 132 insertions(+), 59 deletions(-) -- 2.25.1

2 5

[PATCH v4 0/3] arm64/riscv: Add support for crashkernel CMA reservation
by Jinjie Ruan 09 Feb '26

09 Feb '26

Add support for crashkernel CMA reservation for arm64 and riscv. By the way, exclude crash kernel memory in crash core to avoid duplication. Changes in v4: - Move the size calculation (and the realloc if needed) into the generic crash. Changs in v3: - Exclude crash kernel memory in crash core as Mike suggested. - Add acked-by. Jinjie Ruan (3): crash: Exclude crash kernel memory in crash core arm64: kexec: Add support for crashkernel CMA reservation riscv: kexec: Add support for crashkernel CMA reservation .../admin-guide/kernel-parameters.txt | 16 ++-- arch/arm64/include/asm/kexec.h | 9 ++ arch/arm64/kernel/machine_kexec_file.c | 43 ++++----- arch/arm64/mm/init.c | 5 +- arch/loongarch/include/asm/kexec.h | 9 +- arch/loongarch/kernel/machine_kexec_file.c | 41 +++----- arch/powerpc/include/asm/kexec.h | 13 +++ arch/powerpc/kexec/crash.c | 48 ++++++---- arch/powerpc/kexec/file_load_64.c | 17 ++-- arch/powerpc/kexec/ranges.c | 18 +--- arch/riscv/include/asm/kexec.h | 8 ++ arch/riscv/kernel/machine_kexec_file.c | 39 ++++---- arch/riscv/mm/init.c | 5 +- arch/x86/include/asm/kexec.h | 7 ++ arch/x86/kernel/crash.c | 95 ++----------------- include/linux/crash_core.h | 89 ++++++++++++++++- kernel/crash_core.c | 71 ++++++++++++-- 17 files changed, 307 insertions(+), 226 deletions(-) -- 2.34.1

1 3