From b777b5e09eabeefc6ba80f4296366a4742701103 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Feb 2026 17:02:25 +0000 Subject: time/jiffies: Inline jiffies_to_msecs() and jiffies_to_usecs() For common cases (HZ=100, 250 or 1000), these helpers are at most one multiply, so there is no point calling a tiny function. Keep them out of line for HZ=300 and others. This saves cycles in TCP fast path, among other things. $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 0/8 grow/shrink: 25/89 up/down: 530/-3474 (-2944) ... nla_put_msecs 193 - -193 message_stats_print 2131 920 -1211 Total: Before=25365208, After=25362264, chg -0.01% Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260210170226.57209-1-edumazet@google.com --- kernel/time/time.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 0ba8e3c50d62..36fd2313ae7e 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -365,20 +365,16 @@ SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) } #endif +#if HZ > MSEC_PER_SEC || (MSEC_PER_SEC % HZ) /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * - * Avoid unnecessary multiplications/divisions in the - * two most common HZ cases. - * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { -#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) - return (MSEC_PER_SEC / HZ) * j; -#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) +#if HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 @@ -390,7 +386,9 @@ unsigned int jiffies_to_msecs(const unsigned long j) #endif } EXPORT_SYMBOL(jiffies_to_msecs); +#endif +#if (USEC_PER_SEC % HZ) /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value @@ -405,17 +403,14 @@ unsigned int jiffies_to_usecs(const unsigned long j) */ BUILD_BUG_ON(HZ > USEC_PER_SEC); -#if !(USEC_PER_SEC % HZ) - return (USEC_PER_SEC / HZ) * j; -#else -# if BITS_PER_LONG == 32 +#if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; -# else +#else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; -# endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); +#endif /** * mktime64 - Converts date to seconds. -- cgit v1.2.3 From 5ee01f1a7343d6a3547b6802ca2d4cdce0edacb1 Mon Sep 17 00:00:00 2001 From: Qingye Zhao Date: Wed, 11 Feb 2026 09:24:04 +0000 Subject: cgroup: fix race between task migration and iteration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a task is migrated out of a css_set, cgroup_migrate_add_task() first moves it from cset->tasks to cset->mg_tasks via: list_move_tail(&task->cg_list, &cset->mg_tasks); If a css_task_iter currently has it->task_pos pointing to this task, css_set_move_task() calls css_task_iter_skip() to keep the iterator valid. However, since the task has already been moved to ->mg_tasks, the iterator is advanced relative to the mg_tasks list instead of the original tasks list. As a result, remaining tasks on cset->tasks, as well as tasks queued on cset->mg_tasks, can be skipped by iteration. Fix this by calling css_set_skip_task_iters() before unlinking task->cg_list from cset->tasks. This advances all active iterators to the next task on cset->tasks, so iteration continues correctly even when a task is concurrently being migrated. This race is hard to hit in practice without instrumentation, but it can be reproduced by artificially slowing down cgroup_procs_show(). For example, on an Android device a temporary /sys/kernel/cgroup/cgroup_test knob can be added to inject a delay into cgroup_procs_show(), and then: 1) Spawn three long-running tasks (PIDs 101, 102, 103). 2) Create a test cgroup and move the tasks into it. 3) Enable a large delay via /sys/kernel/cgroup/cgroup_test. 4) In one shell, read cgroup.procs from the test cgroup. 5) Within the delay window, in another shell migrate PID 102 by writing it to a different cgroup.procs file. Under this setup, cgroup.procs can intermittently show only PID 101 while skipping PID 103. Once the migration completes, reading the file again shows all tasks as expected. Note that this change does not allow removing the existing css_set_skip_task_iters() call in css_set_move_task(). The new call in cgroup_migrate_add_task() only handles iterators that are racing with migration while the task is still on cset->tasks. Iterators may also start after the task has been moved to cset->mg_tasks. If we dropped css_set_skip_task_iters() from css_set_move_task(), such iterators could keep task_pos pointing to a migrating task, causing css_task_iter_advance() to malfunction on the destination css_set, up to and including crashes or infinite loops. The race window between migration and iteration is very small, and css_task_iter is not on a hot path. In the worst case, when an iterator is positioned on the first thread of the migrating process, cgroup_migrate_add_task() may have to skip multiple tasks via css_set_skip_task_iters(). However, this only happens when migration and iteration actually race, so the performance impact is negligible compared to the correctness fix provided here. Fixes: b636fd38dc40 ("cgroup: Implement css_task_iter_skip()") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Qingye Zhao Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8af4351536cf..49da0874a023 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task, mgctx->tset.nr_tasks++; + css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, -- cgit v1.2.3 From 6c4b2243cb6c0755159bd567130d5e12e7b10d9f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 7 Feb 2026 08:25:24 +0000 Subject: unshare: fix unshare_fs() handling There's an unpleasant corner case in unshare(2), when we have a CLONE_NEWNS in flags and current->fs hadn't been shared at all; in that case copy_mnt_ns() gets passed current->fs instead of a private copy, which causes interesting warts in proof of correctness] > I guess if private means fs->users == 1, the condition could still be true. Unfortunately, it's worse than just a convoluted proof of correctness. Consider the case when we have CLONE_NEWCGROUP in addition to CLONE_NEWNS (and current->fs->users == 1). We pass current->fs to copy_mnt_ns(), all right. Suppose it succeeds and flips current->fs->{pwd,root} to corresponding locations in the new namespace. Now we proceed to copy_cgroup_ns(), which fails (e.g. with -ENOMEM). We call put_mnt_ns() on the namespace created by copy_mnt_ns(), it's destroyed and its mount tree is dissolved, but... current->fs->root and current->fs->pwd are both left pointing to now detached mounts. They are pinning those, so it's not a UAF, but it leaves the calling process with unshare(2) failing with -ENOMEM _and_ leaving it with pwd and root on detached isolated mounts. The last part is clearly a bug. There is other fun related to that mess (races with pivot_root(), including the one between pivot_root() and fork(), of all things), but this one is easy to isolate and fix - treat CLONE_NEWNS as "allocate a new fs_struct even if it hadn't been shared in the first place". Sure, we could go for something like "if both CLONE_NEWNS *and* one of the things that might end up failing after copy_mnt_ns() call in create_new_namespaces() are set, force allocation of new fs_struct", but let's keep it simple - the cost of copy_fs_struct() is trivial. Another benefit is that copy_mnt_ns() with CLONE_NEWNS *always* gets a freshly allocated fs_struct, yet to be attached to anything. That seriously simplifies the analysis... FWIW, that bug had been there since the introduction of unshare(2) ;-/ Signed-off-by: Al Viro Link: https://patch.msgid.link/20260207082524.GE3183987@ZenIV Tested-by: Waiman Long Signed-off-by: Christian Brauner --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index e832da9d15a4..65113a304518 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -3085,7 +3085,7 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) return 0; /* don't need lock here; in the worst case we'll do useless copy */ - if (fs->users == 1) + if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); -- cgit v1.2.3 From 47322c469d4a63ac45b705ca83680671ff71c975 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 9 Feb 2026 16:38:05 +0100 Subject: dma-mapping: avoid random addr value print out on error path dma_addr is unitialized in dma_direct_map_phys() when swiotlb is forced and DMA_ATTR_MMIO is set which leads to random value print out in warning. Fix that by just returning DMA_MAPPING_ERROR. Fixes: e53d29f957b3 ("dma-mapping: convert dma_direct_*map_page to be phys_addr_t based") Signed-off-by: Jiri Pirko Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20260209153809.250835-2-jiri@resnulli.us --- kernel/dma/direct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index f476c63b668c..e89f175e9c2d 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -85,7 +85,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev, if (is_swiotlb_force_bounce(dev)) { if (attrs & DMA_ATTR_MMIO) - goto err_overflow; + return DMA_MAPPING_ERROR; return swiotlb_map(dev, phys, size, dir, attrs); } -- cgit v1.2.3 From b3d99f43c72b56cf7a104a364e7fb34b0702828b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 9 Feb 2026 15:28:16 +0100 Subject: sched/fair: Fix zero_vruntime tracking It turns out that zero_vruntime tracking is broken when there is but a single task running. Current update paths are through __{en,de}queue_entity(), and when there is but a single task, pick_next_task() will always return that one task, and put_prev_set_next_task() will end up in neither function. This can cause entity_key() to grow indefinitely large and cause overflows, leading to much pain and suffering. Furtermore, doing update_zero_vruntime() from __{de,en}queue_entity(), which are called from {set_next,put_prev}_entity() has problems because: - set_next_entity() calls __dequeue_entity() before it does cfs_rq->curr = se. This means the avg_vruntime() will see the removal but not current, missing the entity for accounting. - put_prev_entity() calls __enqueue_entity() before it does cfs_rq->curr = NULL. This means the avg_vruntime() will see the addition *and* current, leading to double accounting. Both cases are incorrect/inconsistent. Noting that avg_vruntime is already called on each {en,de}queue, remove the explicit avg_vruntime() calls (which removes an extra 64bit division for each {en,de}queue) and have avg_vruntime() update zero_vruntime itself. Additionally, have the tick call avg_vruntime() -- discarding the result, but for the side-effect of updating zero_vruntime. While there, optimize avg_vruntime() by noting that the average of one value is rather trivial to compute. Test case: # taskset -c -p 1 $$ # taskset -c 2 bash -c 'while :; do :; done&' # cat /sys/kernel/debug/sched/debug | awk '/^cpu#/ {P=0} /^cpu#2,/ {P=1} {if (P) print $0}' | grep -e zero_vruntime -e "^>" PRE: .zero_vruntime : 31316.407903 >R bash 487 50787.345112 E 50789.145972 2.800000 50780.298364 16 120 0.000000 0.000000 0.000000 / .zero_vruntime : 382548.253179 >R bash 487 427275.204288 E 427276.003584 2.800000 427268.157540 23 120 0.000000 0.000000 0.000000 / POST: .zero_vruntime : 17259.709467 >R bash 526 17259.709467 E 17262.509467 2.800000 16915.031624 9 120 0.000000 0.000000 0.000000 / .zero_vruntime : 18702.723356 >R bash 526 18702.723356 E 18705.523356 2.800000 18358.045513 9 120 0.000000 0.000000 0.000000 / Fixes: 79f3f9bedd14 ("sched/eevdf: Fix min_vruntime vs avg_vruntime") Reported-by: K Prateek Nayak Signed-off-by: Peter Zijlstra (Intel) Tested-by: K Prateek Nayak Tested-by: Shubhang Kaushik Link: https://patch.msgid.link/20260219080624.438854780%40infradead.org --- kernel/sched/fair.c | 84 ++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 57 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index eea99ec01a3f..56dddd4fd208 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -589,6 +589,21 @@ static inline bool entity_before(const struct sched_entity *a, return vruntime_cmp(a->deadline, "<", b->deadline); } +/* + * Per avg_vruntime() below, cfs_rq::zero_vruntime is only slightly stale + * and this value should be no more than two lag bounds. Which puts it in the + * general order of: + * + * (slice + TICK_NSEC) << NICE_0_LOAD_SHIFT + * + * which is around 44 bits in size (on 64bit); that is 20 for + * NICE_0_LOAD_SHIFT, another 20 for NSEC_PER_MSEC and then a handful for + * however many msec the actual slice+tick ends up begin. + * + * (disregarding the actual divide-by-weight part makes for the worst case + * weight of 2, which nicely cancels vs the fuzz in zero_vruntime not actually + * being the zero-lag point). + */ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) { return vruntime_op(se->vruntime, "-", cfs_rq->zero_vruntime); @@ -676,39 +691,61 @@ sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se) } static inline -void sum_w_vruntime_update(struct cfs_rq *cfs_rq, s64 delta) +void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta) { /* - * v' = v + d ==> sum_w_vruntime' = sum_runtime - d*sum_weight + * v' = v + d ==> sum_w_vruntime' = sum_w_vruntime - d*sum_weight */ cfs_rq->sum_w_vruntime -= cfs_rq->sum_weight * delta; + cfs_rq->zero_vruntime += delta; } /* - * Specifically: avg_runtime() + 0 must result in entity_eligible() := true + * Specifically: avg_vruntime() + 0 must result in entity_eligible() := true * For this to be so, the result of this function must have a left bias. + * + * Called in: + * - place_entity() -- before enqueue + * - update_entity_lag() -- before dequeue + * - entity_tick() + * + * This means it is one entry 'behind' but that puts it close enough to where + * the bound on entity_key() is at most two lag bounds. */ u64 avg_vruntime(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; - s64 avg = cfs_rq->sum_w_vruntime; - long load = cfs_rq->sum_weight; + long weight = cfs_rq->sum_weight; + s64 delta = 0; - if (curr && curr->on_rq) { - unsigned long weight = scale_load_down(curr->load.weight); + if (curr && !curr->on_rq) + curr = NULL; - avg += entity_key(cfs_rq, curr) * weight; - load += weight; - } + if (weight) { + s64 runtime = cfs_rq->sum_w_vruntime; + + if (curr) { + unsigned long w = scale_load_down(curr->load.weight); + + runtime += entity_key(cfs_rq, curr) * w; + weight += w; + } - if (load) { /* sign flips effective floor / ceiling */ - if (avg < 0) - avg -= (load - 1); - avg = div_s64(avg, load); + if (runtime < 0) + runtime -= (weight - 1); + + delta = div_s64(runtime, weight); + } else if (curr) { + /* + * When there is but one element, it is the average. + */ + delta = curr->vruntime - cfs_rq->zero_vruntime; } - return cfs_rq->zero_vruntime + avg; + update_zero_vruntime(cfs_rq, delta); + + return cfs_rq->zero_vruntime; } /* @@ -777,16 +814,6 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) return vruntime_eligible(cfs_rq, se->vruntime); } -static void update_zero_vruntime(struct cfs_rq *cfs_rq) -{ - u64 vruntime = avg_vruntime(cfs_rq); - s64 delta = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime); - - sum_w_vruntime_update(cfs_rq, delta); - - cfs_rq->zero_vruntime = vruntime; -} - static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) { struct sched_entity *root = __pick_root_entity(cfs_rq); @@ -856,7 +883,6 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { sum_w_vruntime_add(cfs_rq, se); - update_zero_vruntime(cfs_rq); se->min_vruntime = se->vruntime; se->min_slice = se->slice; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, @@ -868,7 +894,6 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, &min_vruntime_cb); sum_w_vruntime_sub(cfs_rq, se); - update_zero_vruntime(cfs_rq); } struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq) @@ -5524,6 +5549,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) update_load_avg(cfs_rq, curr, UPDATE_TG); update_cfs_group(curr); + /* + * Pulls along cfs_rq::zero_vruntime. + */ + avg_vruntime(cfs_rq); + #ifdef CONFIG_SCHED_HRTICK /* * queued ticks are scheduled to match the slice, so don't bother -- cgit v1.2.3 From bcd74b2ffdd0a2233adbf26b65c62fc69a809c8e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 23 Jan 2026 16:49:09 +0100 Subject: sched/fair: Only set slice protection at pick time We should not (re)set slice protection in the sched_change pattern which calls put_prev_task() / set_next_task(). Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption") Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Tested-by: K Prateek Nayak Tested-by: Shubhang Kaushik Link: https://patch.msgid.link/20260219080624.561421378%40infradead.org --- kernel/sched/fair.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56dddd4fd208..f2b46c33a8c5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5445,7 +5445,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) } static void -set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first) { clear_buddies(cfs_rq, se); @@ -5460,7 +5460,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) __dequeue_entity(cfs_rq, se); update_load_avg(cfs_rq, se, UPDATE_TG); - set_protect_slice(cfs_rq, se); + if (first) + set_protect_slice(cfs_rq, se); } update_stats_curr_start(cfs_rq, se); @@ -8978,13 +8979,13 @@ again: pse = parent_entity(pse); } if (se_depth >= pse_depth) { - set_next_entity(cfs_rq_of(se), se); + set_next_entity(cfs_rq_of(se), se, true); se = parent_entity(se); } } put_prev_entity(cfs_rq, pse); - set_next_entity(cfs_rq, se); + set_next_entity(cfs_rq, se, true); __set_next_task_fair(rq, p, true); } @@ -13598,7 +13599,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - set_next_entity(cfs_rq, se); + set_next_entity(cfs_rq, se, first); /* ensure bandwidth has been allocated on our new cfs_rq */ account_cfs_rq_runtime(cfs_rq, 0); } -- cgit v1.2.3 From ff38424030f98976150e42ca35f4b00e6ab8fa23 Mon Sep 17 00:00:00 2001 From: Wang Tao Date: Tue, 20 Jan 2026 12:31:13 +0000 Subject: sched/eevdf: Update se->vprot in reweight_entity() In the EEVDF framework with Run-to-Parity protection, `se->vprot` is an independent variable defining the virtual protection timestamp. When `reweight_entity()` is called (e.g., via nice/renice), it performs the following actions to preserve Lag consistency: 1. Scales `se->vlag` based on the new weight. 2. Calls `place_entity()`, which recalculates `se->vruntime` based on the new weight and scaled lag. However, the current implementation fails to update `se->vprot`, leading to mismatches between the task's actual runtime and its expected duration. Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption") Suggested-by: Zhang Qiao Signed-off-by: Wang Tao Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Tested-by: K Prateek Nayak Tested-by: Shubhang Kaushik Link: https://patch.msgid.link/20260120123113.3518950-1-wangtao554@huawei.com --- kernel/sched/fair.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f2b46c33a8c5..93fa5b8313e4 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3815,6 +3815,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; + bool rel_vprot = false; + u64 vprot; if (se->on_rq) { /* commit outstanding execution time */ @@ -3822,6 +3824,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, update_entity_lag(cfs_rq, se); se->deadline -= se->vruntime; se->rel_deadline = 1; + if (curr && protect_slice(se)) { + vprot = se->vprot - se->vruntime; + rel_vprot = true; + } + cfs_rq->nr_queued--; if (!curr) __dequeue_entity(cfs_rq, se); @@ -3837,6 +3844,9 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, if (se->rel_deadline) se->deadline = div_s64(se->deadline * se->load.weight, weight); + if (rel_vprot) + vprot = div_s64(vprot * se->load.weight, weight); + update_load_set(&se->load, weight); do { @@ -3848,6 +3858,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { place_entity(cfs_rq, se, 0); + if (rel_vprot) + se->vprot = se->vruntime + vprot; update_load_add(&cfs_rq->load, se->load.weight); if (!curr) __enqueue_entity(cfs_rq, se); -- cgit v1.2.3 From 6e3c0a4e1ad1e0455b7880fad02b3ee179f56c09 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Apr 2025 12:16:28 +0200 Subject: sched/fair: Fix lag clamp Vincent reported that he was seeing undue lag clamping in a mixed slice workload. Implement the max_slice tracking as per the todo comment. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Reported-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Tested-by: Vincent Guittot Tested-by: K Prateek Nayak Tested-by: Shubhang Kaushik Link: https://patch.msgid.link/20250422101628.GA33555@noisy.programming.kicks-ass.net --- kernel/sched/fair.c | 39 +++++++++++++++++++++++++++++++++++---- 1 file changed, 35 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 93fa5b8313e4..f4446cbe8ffa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -748,6 +748,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) return cfs_rq->zero_vruntime; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq); + /* * lag_i = S - s_i = w_i * (V - v_i) * @@ -761,17 +763,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * EEVDF gives the following limit for a steady state system: * * -r_max < lag < max(r_max, q) - * - * XXX could add max_slice to the augmented data to track this. */ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { + u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC; s64 vlag, limit; WARN_ON_ONCE(!se->on_rq); vlag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + limit = calc_delta_fair(max_slice, se); se->vlag = clamp(vlag, -limit, limit); } @@ -829,6 +830,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) return min_slice; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq) +{ + struct sched_entity *root = __pick_root_entity(cfs_rq); + struct sched_entity *curr = cfs_rq->curr; + u64 max_slice = 0ULL; + + if (curr && curr->on_rq) + max_slice = curr->slice; + + if (root) + max_slice = max(max_slice, root->max_slice); + + return max_slice; +} + static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) { return entity_before(__node_2_se(a), __node_2_se(b)); @@ -853,6 +869,15 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n } } +static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node) +{ + if (node) { + struct sched_entity *rse = __node_2_se(node); + if (rse->max_slice > se->max_slice) + se->max_slice = rse->max_slice; + } +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ @@ -860,6 +885,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) { u64 old_min_vruntime = se->min_vruntime; u64 old_min_slice = se->min_slice; + u64 old_max_slice = se->max_slice; struct rb_node *node = &se->run_node; se->min_vruntime = se->vruntime; @@ -870,8 +896,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) __min_slice_update(se, node->rb_right); __min_slice_update(se, node->rb_left); + se->max_slice = se->slice; + __max_slice_update(se, node->rb_right); + __max_slice_update(se, node->rb_left); + return se->min_vruntime == old_min_vruntime && - se->min_slice == old_min_slice; + se->min_slice == old_min_slice && + se->max_slice == old_max_slice; } RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, -- cgit v1.2.3 From 5324953c06bd929c135d9e04be391ee2c11b5a19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Feb 2026 17:33:29 +0100 Subject: sched/core: Fix wakeup_preempt's next_class tracking Kernel test robot reported that tools/testing/selftests/kvm/hardware_disable_test was failing due to commit 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt() and rq_modified_*()") It turns out there were two related problems that could lead to a missed preemption: - when hitting newidle balance from the idle thread, it would elevate rb->next_class from &idle_sched_class to &fair_sched_class, causing later wakeup_preempt() calls to not hit the sched_class_above() case, and not issue resched_curr(). Notably, this modification pattern should only lower the next_class, and never raise it. Create two new helper functions to wrap this. - when doing schedule_idle(), it was possible to miss (re)setting rq->next_class to &idle_sched_class, leading to the very same problem. Cc: Sean Christopherson Fixes: 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt() and rq_modified_*()") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202602122157.4e861298-lkp@intel.com Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260218163329.GQ1395416@noisy.programming.kicks-ass.net --- kernel/sched/core.c | 1 + kernel/sched/ext.c | 4 ++-- kernel/sched/fair.c | 4 ++-- kernel/sched/sched.h | 11 +++++++++++ 4 files changed, 16 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 759777694c78..b7f77c165a6e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6830,6 +6830,7 @@ static void __sched notrace __schedule(int sched_mode) /* SCX must consult the BPF scheduler to tell if rq is empty */ if (!rq->nr_running && !scx_enabled()) { next = prev; + rq->next_class = &idle_sched_class; goto picked; } } else if (!preempt && prev_state) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 62b1f3ac5630..06cc0a4aec66 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2460,7 +2460,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) /* see kick_cpus_irq_workfn() */ smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1); - rq->next_class = &ext_sched_class; + rq_modified_begin(rq, &ext_sched_class); rq_unpin_lock(rq, rf); balance_one(rq, prev); @@ -2475,7 +2475,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) * If @force_scx is true, always try to pick a SCHED_EXT task, * regardless of any higher-priority sched classes activity. */ - if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class)) + if (!force_scx && rq_modified_above(rq, &ext_sched_class)) return RETRY_TASK; keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f4446cbe8ffa..bf948db905ed 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -12982,7 +12982,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) t0 = sched_clock_cpu(this_cpu); __sched_balance_update_blocked_averages(this_rq); - this_rq->next_class = &fair_sched_class; + rq_modified_begin(this_rq, &fair_sched_class); raw_spin_rq_unlock(this_rq); for_each_domain(this_cpu, sd) { @@ -13049,7 +13049,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) pulled_task = 1; /* If a higher prio class was modified, restart the pick */ - if (sched_class_above(this_rq->next_class, &fair_sched_class)) + if (rq_modified_above(this_rq, &fair_sched_class)) pulled_task = -1; out: diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b82fb70a9d54..43bbf0693cca 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2748,6 +2748,17 @@ static inline const struct sched_class *next_active_class(const struct sched_cla #define sched_class_above(_a, _b) ((_a) < (_b)) +static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class) +{ + if (sched_class_above(rq->next_class, class)) + rq->next_class = class; +} + +static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class) +{ + return sched_class_above(rq->next_class, class); +} + static inline bool sched_stop_runnable(struct rq *rq) { return rq->stop && task_on_rq_queued(rq->stop); -- cgit v1.2.3 From 26d43a90be81fc90e26688a51d3ec83188602731 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 20 Feb 2026 15:06:40 -0500 Subject: rseq: Clarify rseq registration rseq_size bound check comment The rseq registration validates that the rseq_size argument is greater or equal to 32 (the original rseq size), but the comment associated with this check does not clearly state this. Clarify the comment to that effect. Fixes: ee3e3ac05c26 ("rseq: Introduce extensible rseq ABI") Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260220200642.1317826-2-mathieu.desnoyers@efficios.com --- kernel/rseq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rseq.c b/kernel/rseq.c index b0973d19f366..e349f86cc945 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -449,8 +449,9 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq * size, the required alignment is the original struct rseq alignment. * - * In order to be valid, rseq_len is either the original rseq size, or - * large enough to contain all supported fields, as communicated to + * The rseq_len is required to be greater or equal to the original rseq + * size. In order to be valid, rseq_len is either the original rseq size, + * or large enough to contain all supported fields, as communicated to * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. */ if (rseq_len < ORIG_RSEQ_SIZE || -- cgit v1.2.3 From 3b68df978133ac3d46d570af065a73debbb68248 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 20 Feb 2026 15:06:41 -0500 Subject: rseq: slice ext: Ensure rseq feature size differs from original rseq size Before rseq became extensible, its original size was 32 bytes even though the active rseq area was only 20 bytes. This had the following impact in terms of userspace ecosystem evolution: * The GNU libc between 2.35 and 2.39 expose a __rseq_size symbol set to 32, even though the size of the active rseq area is really 20. * The GNU libc 2.40 changes this __rseq_size to 20, thus making it express the active rseq area. * Starting from glibc 2.41, __rseq_size corresponds to the AT_RSEQ_FEATURE_SIZE from getauxval(3). This means that users of __rseq_size can always expect it to correspond to the active rseq area, except for the value 32, for which the active rseq area is 20 bytes. Exposing a 32 bytes feature size would make life needlessly painful for userspace. Therefore, add a reserved field at the end of the rseq area to bump the feature size to 33 bytes. This reserved field is expected to be replaced with whatever field will come next, expecting that this field will be larger than 1 byte. The effect of this change is to increase the size from 32 to 64 bytes before we actually have fields using that memory. Clarify the allocation size and alignment requirements in the struct rseq uapi comment. Change the value returned by getauxval(AT_RSEQ_ALIGN) to return the value of the active rseq area size rounded up to next power of 2, which guarantees that the rseq structure will always be aligned on the nearest power of two large enough to contain it, even as it grows. Change the alignment check in the rseq registration accordingly. This will minimize the amount of ABI corner-cases we need to document and require userspace to play games with. The rule stays simple when __rseq_size != 32: #define rseq_field_available(field) (__rseq_size >= offsetofend(struct rseq_abi, field)) Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260220200642.1317826-3-mathieu.desnoyers@efficios.com --- kernel/rseq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rseq.c b/kernel/rseq.c index e349f86cc945..38d3ef540760 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -456,7 +457,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 */ if (rseq_len < ORIG_RSEQ_SIZE || (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || + (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || rseq_len < offsetof(struct rseq, end)))) return -EINVAL; if (!access_ok(rseq, rseq_len)) -- cgit v1.2.3 From 486ff5ad49bc50315bcaf6d45f04a33ef0a45ced Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 2 Jun 2025 21:51:05 -0700 Subject: perf/core: Fix invalid wait context in ctx_sched_in() Lockdep found a bug in the event scheduling when a pinned event was failed and wakes up the threads in the ring buffer like below. It seems it should not grab a wait-queue lock under perf-context lock. Let's do it with irq_work. [ 39.913691] ============================= [ 39.914157] [ BUG: Invalid wait context ] [ 39.914623] 6.15.0-next-20250530-next-2025053 #1 Not tainted [ 39.915271] ----------------------------- [ 39.915731] repro/837 is trying to lock: [ 39.916191] ffff88801acfabd8 (&event->waitq){....}-{3:3}, at: __wake_up+0x26/0x60 [ 39.917182] other info that might help us debug this: [ 39.917761] context-{5:5} [ 39.918079] 4 locks held by repro/837: [ 39.918530] #0: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: __perf_event_task_sched_in+0xd1/0xbc0 [ 39.919612] #1: ffff88806ca3c6f8 (&cpuctx_lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1a7/0xbc0 [ 39.920748] #2: ffff88800d91fc18 (&ctx->lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1f9/0xbc0 [ 39.921819] #3: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: perf_event_wakeup+0x6c/0x470 Fixes: f4b07fd62d4d ("perf/core: Use POLLHUP for a pinned event in error") Closes: https://lore.kernel.org/lkml/aD2w50VDvGIH95Pf@ly-workstation Reported-by: "Lai, Yi" Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Tested-by: "Lai, Yi" Link: https://patch.msgid.link/20250603045105.1731451-1-namhyung@kernel.org --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index ac70d68217b6..4f86d22f281a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4138,7 +4138,8 @@ static int merge_sched_in(struct perf_event *event, void *data) if (*perf_event_fasync(event)) event->pending_kill = POLL_ERR; - perf_event_wakeup(event); + event->pending_wakeup = 1; + irq_work_queue(&event->pending_irq); } else { struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu); -- cgit v1.2.3 From 77de62ad3de3967818c3dbe656b7336ebee461d2 Mon Sep 17 00:00:00 2001 From: Haocheng Yu Date: Tue, 3 Feb 2026 00:20:56 +0800 Subject: perf/core: Fix refcount bug and potential UAF in perf_mmap Syzkaller reported a refcount_t: addition on 0; use-after-free warning in perf_mmap. The issue is caused by a race condition between a failing mmap() setup and a concurrent mmap() on a dependent event (e.g., using output redirection). In perf_mmap(), the ring_buffer (rb) is allocated and assigned to event->rb with the mmap_mutex held. The mutex is then released to perform map_range(). If map_range() fails, perf_mmap_close() is called to clean up. However, since the mutex was dropped, another thread attaching to this event (via inherited events or output redirection) can acquire the mutex, observe the valid event->rb pointer, and attempt to increment its reference count. If the cleanup path has already dropped the reference count to zero, this results in a use-after-free or refcount saturation warning. Fix this by extending the scope of mmap_mutex to cover the map_range() call. This ensures that the ring buffer initialization and mapping (or cleanup on failure) happens atomically effectively, preventing other threads from accessing a half-initialized or dying ring buffer. Closes: https://lore.kernel.org/oe-kbuild-all/202602020208.m7KIjdzW-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Haocheng Yu Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260202162057.7237-1-yuhaocheng035@gmail.com --- kernel/events/core.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 4f86d22f281a..22a0f405585b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7465,28 +7465,28 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) ret = perf_mmap_aux(vma, event, nr_pages); if (ret) return ret; - } - /* - * Since pinned accounting is per vm we cannot allow fork() to copy our - * vma. - */ - vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); - vma->vm_ops = &perf_mmap_vmops; + /* + * Since pinned accounting is per vm we cannot allow fork() to copy our + * vma. + */ + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); + vma->vm_ops = &perf_mmap_vmops; - mapped = get_mapped(event, event_mapped); - if (mapped) - mapped(event, vma->vm_mm); + mapped = get_mapped(event, event_mapped); + if (mapped) + mapped(event, vma->vm_mm); - /* - * Try to map it into the page table. On fail, invoke - * perf_mmap_close() to undo the above, as the callsite expects - * full cleanup in this case and therefore does not invoke - * vmops::close(). - */ - ret = map_range(event->rb, vma); - if (ret) - perf_mmap_close(vma); + /* + * Try to map it into the page table. On fail, invoke + * perf_mmap_close() to undo the above, as the callsite expects + * full cleanup in this case and therefore does not invoke + * vmops::close(). + */ + ret = map_range(event->rb, vma); + if (ret) + perf_mmap_close(vma); + } return ret; } -- cgit v1.2.3 From a7b4bc094fbaa7dc7b7b91ae33549bbd7eefaac1 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Wed, 7 Jan 2026 13:22:57 +0100 Subject: module: Remove duplicate freeing of lockdep classes In the error path of load_module(), under the free_module label, the code calls lockdep_free_key_range() to release lock classes associated with the MOD_DATA, MOD_RODATA and MOD_RO_AFTER_INIT module regions, and subsequently invokes module_deallocate(). Since commit ac3b43283923 ("module: replace module_layout with module_memory"), the module_deallocate() function calls free_mod_mem(), which releases the lock classes as well and considers all module regions. Attempting to free these classes twice is unnecessary. Remove the redundant code in load_module(). Fixes: ac3b43283923 ("module: replace module_layout with module_memory") Signed-off-by: Petr Pavlu Reviewed-by: Daniel Gomez Reviewed-by: Aaron Tomlin Acked-by: Song Liu Acked-by: Peter Zijlstra (Intel) Signed-off-by: Sami Tolvanen --- kernel/module/main.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel') diff --git a/kernel/module/main.c b/kernel/module/main.c index 2bac4c7cd019..eec6c9cf8dbb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3544,12 +3544,6 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: mod_stat_bump_invalid(info, flags); - /* Free lock-classes; relies on the preceding sync_rcu() */ - for_class_mod_mem_type(type, core_data) { - lockdep_free_key_range(mod->mem[type].base, - mod->mem[type].size); - } - module_memory_restore_rox(mod); module_deallocate(mod, info); free_copy: -- cgit v1.2.3 From 8d597ba6ec18dae2eec143d4e1c9d81441ca0dda Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 5 Feb 2026 15:37:08 +0100 Subject: module: Fix the modversions and signing submenus The module Kconfig file contains a set of options related to "Module versioning support" (depends on MODVERSIONS) and "Module signature verification" (depends on MODULE_SIG). The Kconfig tool automatically creates submenus when an entry for a symbol is followed by consecutive items that all depend on the symbol. However, this functionality doesn't work for the mentioned module options. The MODVERSIONS options are interleaved with ASM_MODVERSIONS, which has no 'depends on MODVERSIONS' but instead uses 'default HAVE_ASM_MODVERSIONS && MODVERSIONS'. Similarly, the MODULE_SIG options are interleaved by a comment warning not to forget signing modules with scripts/sign-file, which uses the condition 'depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL'. The result is that the options are confusingly shown when using a menuconfig tool, as follows: [*] Module versioning support Module versioning implementation (genksyms (from source code)) ---> [ ] Extended Module Versioning Support [*] Basic Module Versioning Support [*] Source checksum for all modules [*] Module signature verification [ ] Require modules to be validly signed [ ] Automatically sign all modules Hash algorithm to sign modules (SHA-256) ---> Fix the issue by using if/endif to group related options together in kernel/module/Kconfig, similarly to how the MODULE_DEBUG options are already grouped. Note that the signing-related options depend on 'MODULE_SIG || IMA_APPRAISE_MODSIG', with the exception of MODULE_SIG_FORCE, which is valid only for MODULE_SIG and is therefore kept separately. For consistency, do the same for the MODULE_COMPRESS entries. The options are then properly placed into submenus, as follows: [*] Module versioning support Module versioning implementation (genksyms (from source code)) ---> [ ] Extended Module Versioning Support [*] Basic Module Versioning Support [*] Source checksum for all modules [*] Module signature verification [ ] Require modules to be validly signed [ ] Automatically sign all modules Hash algorithm to sign modules (SHA-256) ---> Signed-off-by: Petr Pavlu Reviewed-by: Daniel Gomez Signed-off-by: Sami Tolvanen --- kernel/module/Kconfig | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index be74917802ad..43b1bb01fd27 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,9 +169,10 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +if MODVERSIONS + choice prompt "Module versioning implementation" - depends on MODVERSIONS help Select the tool used to calculate symbol versions for modules. @@ -206,7 +207,7 @@ endchoice config ASM_MODVERSIONS bool - default HAVE_ASM_MODVERSIONS && MODVERSIONS + default HAVE_ASM_MODVERSIONS help This enables module versioning for exported symbols also from assembly. This can be enabled only when the target architecture @@ -214,7 +215,6 @@ config ASM_MODVERSIONS config EXTENDED_MODVERSIONS bool "Extended Module Versioning Support" - depends on MODVERSIONS help This enables extended MODVERSIONs support, allowing long symbol names to be versioned. @@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS config BASIC_MODVERSIONS bool "Basic Module Versioning Support" - depends on MODVERSIONS default y help This enables basic MODVERSIONS support, allowing older tools or @@ -237,6 +236,8 @@ config BASIC_MODVERSIONS This is enabled by default when MODVERSIONS are enabled. If unsure, say Y. +endif # MODVERSIONS + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help @@ -277,10 +278,11 @@ config MODULE_SIG_FORCE Reject unsigned modules or signed modules for which we don't have a key. Without this, such modules will simply taint the kernel. +if MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_SIG_ALL bool "Automatically sign all modules" default y - depends on MODULE_SIG || IMA_APPRAISE_MODSIG help Sign all modules during make modules_install. Without this option, modules must be signed manually, using the scripts/sign-file tool. @@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file" choice prompt "Hash algorithm to sign modules" - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default MODULE_SIG_SHA512 help This determines which sort of hashing algorithm will be used during @@ -327,7 +328,6 @@ endchoice config MODULE_SIG_HASH string - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 @@ -335,6 +335,8 @@ config MODULE_SIG_HASH default "sha3-384" if MODULE_SIG_SHA3_384 default "sha3-512" if MODULE_SIG_SHA3_512 +endif # MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_COMPRESS bool "Module compression" help @@ -350,9 +352,10 @@ config MODULE_COMPRESS If unsure, say N. +if MODULE_COMPRESS + choice prompt "Module compression type" - depends on MODULE_COMPRESS help Choose the supported algorithm for module compression. @@ -379,7 +382,6 @@ endchoice config MODULE_COMPRESS_ALL bool "Automatically compress all modules" default y - depends on MODULE_COMPRESS help Compress all modules during 'make modules_install'. @@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD @@ -400,6 +401,8 @@ config MODULE_DECOMPRESS If unsure, say N. +endif # MODULE_COMPRESS + config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS bool "Allow loading of modules with missing namespace imports" help -- cgit v1.2.3 From 7dff99b354601dd01829e1511711846e04340a69 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 23 Feb 2026 11:18:48 -0800 Subject: Remove WARN_ALL_UNSEEDED_RANDOM kernel config option This config option goes way back - it used to be an internal debug option to random.c (at that point called DEBUG_RANDOM_BOOT), then was renamed and exposed as a config option as CONFIG_WARN_UNSEEDED_RANDOM, and then further renamed to the current CONFIG_WARN_ALL_UNSEEDED_RANDOM. It was all done with the best of intentions: the more limited rate-limited reports were reporting some cases, but if you wanted to see all the gory details, you'd enable this "ALL" option. However, it turns out - perhaps not surprisingly - that when people don't care about and fix the first rate-limited cases, they most certainly don't care about any others either, and so warning about all of them isn't actually helping anything. And the non-ratelimited reporting causes problems, where well-meaning people enable debug options, but the excessive flood of messages that nobody cares about will hide actual real information when things go wrong. I just got a kernel bug report (which had nothing to do with randomness) where two thirds of the the truncated dmesg was just variations of random: get_random_u32 called from __get_random_u32_below+0x10/0x70 with crng_init=0 and in the process early boot messages had been lost (in addition to making the messages that _hadn't_ been lost harder to read). The proper way to find these things for the hypothetical developer that cares - if such a person exists - is almost certainly with boot time tracing. That gives you the option to get call graphs etc too, which is likely a requirement for fixing any problems anyway. See Documentation/trace/boottime-trace.rst for that option. And if we for some reason do want to re-introduce actual printing of these things, it will need to have some uniqueness filtering rather than this "just print it all" model. Fixes: cc1e127bfa95 ("random: remove ratelimiting for in-kernel unseeded randomness") Acked-by: Jason Donenfeld Signed-off-by: Linus Torvalds --- kernel/configs/debug.config | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index 774702591d26..307c97ac5fa9 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -29,7 +29,6 @@ CONFIG_SECTION_MISMATCH_WARN_ONLY=y # CONFIG_UBSAN_ALIGNMENT is not set # CONFIG_UBSAN_DIV_ZERO is not set # CONFIG_UBSAN_TRAP is not set -# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set CONFIG_DEBUG_FS=y CONFIG_DEBUG_FS_ALLOW_ALL=y CONFIG_DEBUG_IRQFLAGS=y -- cgit v1.2.3 From f9d69d5e7bde2295eb7488a56f094ac8f5383b92 Mon Sep 17 00:00:00 2001 From: Ihor Solodrai Date: Tue, 30 Dec 2025 10:32:08 -0800 Subject: module: Fix kernel panic when a symbol st_shndx is out of bounds The module loader doesn't check for bounds of the ELF section index in simplify_symbols(): for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { const char *name = info->strtab + sym[i].st_name; switch (sym[i].st_shndx) { case SHN_COMMON: [...] default: /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else /** HERE --> **/ secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } } A symbol with an out-of-bounds st_shndx value, for example 0xffff (known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic: BUG: unable to handle page fault for address: ... RIP: 0010:simplify_symbols+0x2b2/0x480 ... Kernel panic - not syncing: Fatal exception This can happen when module ELF is legitimately using SHN_XINDEX or when it is corrupted. Add a bounds check in simplify_symbols() to validate that st_shndx is within the valid range before using it. This issue was discovered due to a bug in llvm-objcopy, see relevant discussion for details [1]. [1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/ Signed-off-by: Ihor Solodrai Reviewed-by: Daniel Gomez Reviewed-by: Petr Pavlu Signed-off-by: Sami Tolvanen --- kernel/module/main.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/module/main.c b/kernel/module/main.c index eec6c9cf8dbb..c3ce106c70af 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) break; default: + if (sym[i].st_shndx >= info->hdr->e_shnum) { + pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n", + mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1); + ret = -ENOEXEC; + break; + } + /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); -- cgit v1.2.3 From f9a1767ce3a34bc33c3d33473f65dc13a380e379 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:11 -0500 Subject: cgroup/cpuset: Fix incorrect change to effective_xcpus in partition_xcpus_del() The effective_xcpus of a cpuset can contain offline CPUs. In partition_xcpus_del(), the xcpus parameter is incorrectly used as a temporary cpumask to mask out offline CPUs. As xcpus can be the effective_xcpus of a cpuset, this can result in unexpected changes in that cpumask. Fix this problem by not making any changes to the xcpus parameter. Fixes: 11e5f407b64a ("cgroup/cpuset: Keep track of CPUs in isolated partitions") Reviewed-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c43efef7df71..a366ef84f982 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1221,8 +1221,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent, isolated_cpus_update(old_prs, parent->partition_root_state, xcpus); - cpumask_and(xcpus, xcpus, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask); } /* -- cgit v1.2.3 From 68230aac8b9aad243626fbaf3ca170012c17fec5 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:12 -0500 Subject: cgroup/cpuset: Fix incorrect use of cpuset_update_tasks_cpumask() in update_cpumasks_hier() Commit e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2") incorrectly changed the 2nd parameter of cpuset_update_tasks_cpumask() from tmp->new_cpus to cp->effective_cpus. This second parameter is just a temporary cpumask for internal use. The cpuset_update_tasks_cpumask() function was originally called update_tasks_cpumask() before commit 381b53c3b549 ("cgroup/cpuset: rename functions shared between v1 and v2"). This mistake can incorrectly change the effective_cpus of the cpuset when it is the top_cpuset or in arm64 architecture where task_cpu_possible_mask() may differ from cpu_possible_mask. So far top_cpuset hasn't been passed to update_cpumasks_hier() yet, but arm64 arch can still be impacted. Fix it by reverting the incorrect change. Fixes: e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a366ef84f982..8dfffe2dc9ed 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2157,7 +2157,7 @@ get_css: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - cpuset_update_tasks_cpumask(cp, cp->effective_cpus); + cpuset_update_tasks_cpumask(cp, tmp->new_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE -- cgit v1.2.3 From 17b1860034c769c9f7669ae2612e91ef8fdde769 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:13 -0500 Subject: cgroup/cpuset: Clarify exclusion rules for cpuset internal variables Clarify the locking rules associated with file level internal variables inside the cpuset code. There is no functional change. Reviewed-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 105 ++++++++++++++++++++++++++++--------------------- 1 file changed, 61 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8dfffe2dc9ed..165e2967025b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -61,6 +61,58 @@ static const char * const perr_strings[] = { [PERR_REMOTE] = "Have remote partition underneath", }; +/* + * CPUSET Locking Convention + * ------------------------- + * + * Below are the three global locks guarding cpuset structures in lock + * acquisition order: + * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) + * - cpuset_mutex + * - callback_lock (raw spinlock) + * + * A task must hold all the three locks to modify externally visible or + * used fields of cpusets, though some of the internally used cpuset fields + * and internal variables can be modified without holding callback_lock. If only + * reliable read access of the externally used fields are needed, a task can + * hold either cpuset_mutex or callback_lock which are exposed to other + * external subsystems. + * + * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others, + * ensuring that it is the only task able to also acquire callback_lock and + * be able to modify cpusets. It can perform various checks on the cpuset + * structure first, knowing nothing will change. It can also allocate memory + * without holding callback_lock. While it is performing these checks, various + * callback routines can briefly acquire callback_lock to query cpusets. Once + * it is ready to make the changes, it takes callback_lock, blocking everyone + * else. + * + * Calls to the kernel memory allocator cannot be made while holding + * callback_lock which is a spinlock, as the memory allocator may sleep or + * call back into cpuset code and acquire callback_lock. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_seq_show() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + */ + +static DEFINE_MUTEX(cpuset_mutex); + +/* + * File level internal variables below follow one of the following exclusion + * rules. + * + * RWCS: Read/write-able by holding either cpus_write_lock (and optionally + * cpuset_mutex) or both cpus_read_lock and cpuset_mutex. + * + * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable + * by holding both cpuset_mutex and callback_lock. + */ + /* * For local partitions, update to subpartitions_cpus & isolated_cpus is done * in update_parent_effective_cpumask(). For remote partitions, it is done in @@ -70,19 +122,18 @@ static const char * const perr_strings[] = { * Exclusive CPUs distributed out to local or remote sub-partitions of * top_cpuset */ -static cpumask_var_t subpartitions_cpus; +static cpumask_var_t subpartitions_cpus; /* RWCS */ /* - * Exclusive CPUs in isolated partitions + * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated) */ -static cpumask_var_t isolated_cpus; +static cpumask_var_t isolated_cpus; /* CSCB */ /* - * isolated_cpus updating flag (protected by cpuset_mutex) - * Set if isolated_cpus is going to be updated in the current - * cpuset_mutex crtical section. + * Set if isolated_cpus is being updated in the current cpuset_mutex + * critical section. */ -static bool isolated_cpus_updating; +static bool isolated_cpus_updating; /* RWCS */ /* * A flag to force sched domain rebuild at the end of an operation. @@ -98,7 +149,7 @@ static bool isolated_cpus_updating; * Note that update_relax_domain_level() in cpuset-v1.c can still call * rebuild_sched_domains_locked() directly without using this flag. */ -static bool force_sd_rebuild; +static bool force_sd_rebuild; /* RWCS */ /* * Partition root states: @@ -218,42 +269,6 @@ struct cpuset top_cpuset = { .partition_root_state = PRS_ROOT, }; -/* - * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel - * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset - * structures. Note that cpuset_mutex needs to be a mutex as it is used in - * paths that rely on priority inheritance (e.g. scheduler - on RT) for - * correctness. - * - * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, it blocks others, ensuring that it is the only task able to - * also acquire callback_lock and be able to modify cpusets. It can perform - * various checks on the cpuset structure first, knowing nothing will change. - * It can also allocate memory while just holding cpuset_mutex. While it is - * performing these checks, various callback routines can briefly acquire - * callback_lock to query cpusets. Once it is ready to make the changes, it - * takes callback_lock, blocking everyone else. - * - * Calls to the kernel memory allocator can not be made while holding - * callback_lock, as that would risk double tripping on callback_lock - * from one of the callbacks into the cpuset code from within - * __alloc_pages(). - * - * If a task is only holding callback_lock, then it has read-only - * access to cpusets. - * - * Now, the task_struct fields mems_allowed and mempolicy may be changed - * by other task, we use alloc_lock in the task_struct fields to protect - * them. - * - * The cpuset_common_seq_show() handlers only hold callback_lock across - * small pieces of code, such as when reading out possibly multi-word - * cpumasks and nodemasks. - */ - -static DEFINE_MUTEX(cpuset_mutex); - /** * cpuset_lock - Acquire the global cpuset mutex * @@ -1163,6 +1178,8 @@ static void reset_partition_data(struct cpuset *cs) static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs == new_prs); + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); if (new_prs == PRS_ISOLATED) cpumask_or(isolated_cpus, isolated_cpus, xcpus); else -- cgit v1.2.3 From 14713ed9e9291813849018f32edbf5f6de362088 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:14 -0500 Subject: cgroup/cpuset: Set isolated_cpus_updating only if isolated_cpus is changed As cpuset is updating HK_TYPE_DOMAIN housekeeping mask when there is a change in the set of isolated CPUs, making this change is now more costly than before. Right now, the isolated_cpus_updating flag can be set even if there is no real change in isolated_cpus. Put in additional checks to make sure that isolated_cpus_updating is set only if there is a real change in isolated_cpus. Reviewed-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 165e2967025b..edc67c6aa553 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1180,11 +1180,15 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus WARN_ON_ONCE(old_prs == new_prs); lockdep_assert_held(&callback_lock); lockdep_assert_held(&cpuset_mutex); - if (new_prs == PRS_ISOLATED) + if (new_prs == PRS_ISOLATED) { + if (cpumask_subset(xcpus, isolated_cpus)) + return; cpumask_or(isolated_cpus, isolated_cpus, xcpus); - else + } else { + if (!cpumask_intersects(xcpus, isolated_cpus)) + return; cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - + } isolated_cpus_updating = true; } -- cgit v1.2.3 From 3bfe47967191f42d17510713b31a47d9284b8c5a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:16 -0500 Subject: cgroup/cpuset: Move housekeeping_update()/rebuild_sched_domains() together With the latest changes in sched/isolation.c, rebuild_sched_domains*() requires the HK_TYPE_DOMAIN housekeeping cpumask to be properly updated first, if needed, before the sched domains can be rebuilt. So the two naturally fit together. Do that by creating a new update_hk_sched_domains() helper to house both actions. The name of the isolated_cpus_updating flag to control the call to housekeeping_update() is now outdated. So change it to update_housekeeping to better reflect its purpose. Also move the call to update_hk_sched_domains() to the end of cpuset and hotplug operations before releasing the cpuset_mutex. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 51 ++++++++++++++++++++++++-------------------------- 1 file changed, 24 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index edc67c6aa553..14b07a283a2c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -130,10 +130,9 @@ static cpumask_var_t subpartitions_cpus; /* RWCS */ static cpumask_var_t isolated_cpus; /* CSCB */ /* - * Set if isolated_cpus is being updated in the current cpuset_mutex - * critical section. + * Set if housekeeping cpumasks are to be updated. */ -static bool isolated_cpus_updating; /* RWCS */ +static bool update_housekeeping; /* RWCS */ /* * A flag to force sched domain rebuild at the end of an operation. @@ -1189,7 +1188,7 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus return; cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); } - isolated_cpus_updating = true; + update_housekeeping = true; } /* @@ -1307,22 +1306,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_isolation_cpumasks - Update external isolation related CPU masks + * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains * - * The following external CPU masks will be updated if necessary: - * - workqueue unbound cpumask + * Update housekeeping cpumasks and rebuild sched domains if necessary. + * This should be called at the end of cpuset or hotplug actions. */ -static void update_isolation_cpumasks(void) +static void update_hk_sched_domains(void) { - int ret; - - if (!isolated_cpus_updating) - return; - - ret = housekeeping_update(isolated_cpus); - WARN_ON_ONCE(ret < 0); - - isolated_cpus_updating = false; + if (update_housekeeping) { + /* Updating HK cpumasks implies rebuild sched domains */ + WARN_ON_ONCE(housekeeping_update(isolated_cpus)); + update_housekeeping = false; + force_sd_rebuild = true; + } + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); } /** @@ -1473,7 +1472,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, cs->remote_partition = true; cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); cs->prs_err = 0; @@ -1518,7 +1516,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) compute_excpus(cs, cs->effective_xcpus); reset_partition_data(cs); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); /* @@ -1589,7 +1586,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus, if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if (adding || deleting) cpuset_force_rebuild(); @@ -1933,7 +1929,6 @@ write_error: partition_xcpus_add(new_prs, parent, tmp->delmask); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive_flag(cs, new_prs); @@ -2901,7 +2896,6 @@ out: else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); @@ -3191,9 +3185,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, } free_cpuset(trialcs); - if (force_sd_rebuild) - rebuild_sched_domains_locked(); out_unlock: + update_hk_sched_domains(); cpuset_full_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); @@ -3301,6 +3294,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); + update_hk_sched_domains(); cpuset_full_unlock(); return retval ?: nbytes; } @@ -3475,6 +3469,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); + update_hk_sched_domains(); cpuset_full_unlock(); } @@ -3882,10 +3877,12 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* rebuild sched domains if necessary */ - if (force_sd_rebuild) - rebuild_sched_domains_cpuslocked(); + if (update_housekeeping || force_sd_rebuild) { + mutex_lock(&cpuset_mutex); + update_hk_sched_domains(); + mutex_unlock(&cpuset_mutex); + } free_tmpmasks(ptmp); } -- cgit v1.2.3 From 6df415aa46ec10d607da5063d88492a7c7762074 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:17 -0500 Subject: cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue The cpuset_handle_hotplug() may need to invoke housekeeping_update(), for instance, when an isolated partition is invalidated because its last active CPU has been put offline. As we are going to enable dynamic update to the nozh_full housekeeping cpumask (HK_TYPE_KERNEL_NOISE) soon with the help of CPU hotplug, allowing the CPU hotplug path to call into housekeeping_update() directly from update_isolation_cpumasks() will likely cause deadlock. So we have to defer any call to housekeeping_update() after the CPU hotplug operation has finished. This is now done via the workqueue where the update_hk_sched_domains() function will be invoked via the hk_sd_workfn(). An concurrent cpuset control file write may have executed the required update_hk_sched_domains() function before the work function is called. So the work function call may become a no-op when it is invoked. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 14b07a283a2c..aa915e9b588f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1324,6 +1324,16 @@ static void update_hk_sched_domains(void) rebuild_sched_domains_locked(); } +/* + * Work function to invoke update_hk_sched_domains() + */ +static void hk_sd_workfn(struct work_struct *work) +{ + cpuset_full_lock(); + update_hk_sched_domains(); + cpuset_full_unlock(); +} + /** * rm_siblings_excl_cpus - Remove exclusive CPUs that are used by sibling cpusets * @parent: Parent cpuset containing all siblings @@ -3796,6 +3806,7 @@ unlock: */ static void cpuset_handle_hotplug(void) { + static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; @@ -3878,11 +3889,21 @@ static void cpuset_handle_hotplug(void) } - if (update_housekeeping || force_sd_rebuild) { - mutex_lock(&cpuset_mutex); - update_hk_sched_domains(); - mutex_unlock(&cpuset_mutex); - } + /* + * Queue a work to call housekeeping_update() & rebuild_sched_domains() + * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping + * cpumask can correctly reflect what is in isolated_cpus. + * + * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that + * is still pending. Before the pending bit is cleared, the work data + * is copied out and work item dequeued. So it is possible to queue + * the work again before the hk_sd_workfn() is invoked to process the + * previously queued work. Since hk_sd_workfn() doesn't use the work + * item at all, this is not a problem. + */ + if (update_housekeeping || force_sd_rebuild) + queue_work(system_unbound_wq, &hk_sd_work); + free_tmpmasks(ptmp); } -- cgit v1.2.3 From a84097e625f2b9e7f273161c004f34b7be63b348 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:18 -0500 Subject: cgroup/cpuset: Call housekeeping_update() without holding cpus_read_lock The current cpuset partition code is able to dynamically update the sched domains of a running system and the corresponding HK_TYPE_DOMAIN housekeeping cpumask to perform what is essentially the "isolcpus=domain,..." boot command line feature at run time. The housekeeping cpumask update requires flushing a number of different workqueues which may not be safe with cpus_read_lock() held as the workqueue flushing code may acquire cpus_read_lock() or acquiring locks which have locking dependency with cpus_read_lock() down the chain. Below is an example of such circular locking problem. ====================================================== WARNING: possible circular locking dependency detected 6.18.0-test+ #2 Tainted: G S ------------------------------------------------------ test_cpuset_prs/10971 is trying to acquire lock: ffff888112ba4958 ((wq_completion)sync_wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x7a/0x180 but task is already holding lock: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 (cpuset_mutex){+.+.}-{4:4}: -> #3 (cpu_hotplug_lock){++++}-{0:0}: -> #2 (rtnl_mutex){+.+.}-{4:4}: -> #1 ((work_completion)(&arg.work)){+.+.}-{0:0}: -> #0 ((wq_completion)sync_wq){+.+.}-{0:0}: Chain exists of: (wq_completion)sync_wq --> cpu_hotplug_lock --> cpuset_mutex 5 locks held by test_cpuset_prs/10971: #0: ffff88816810e440 (sb_writers#7){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0 #1: ffff8891ab620890 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x260/0x5f0 #2: ffff8890a78b83e8 (kn->active#187){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x2b6/0x5f0 #3: ffffffffadf32900 (cpu_hotplug_lock){++++}-{0:0}, at: cpuset_partition_write+0x77/0x130 #4: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130 Call Trace: : touch_wq_lockdep_map+0x93/0x180 __flush_workqueue+0x111/0x10b0 housekeeping_update+0x12d/0x2d0 update_parent_effective_cpumask+0x595/0x2440 update_prstate+0x89d/0xce0 cpuset_partition_write+0xc5/0x130 cgroup_file_write+0x1a5/0x680 kernfs_fop_write_iter+0x3df/0x5f0 vfs_write+0x525/0xfd0 ksys_write+0xf9/0x1d0 do_syscall_64+0x95/0x520 entry_SYSCALL_64_after_hwframe+0x76/0x7e To avoid such a circular locking dependency problem, we have to call housekeeping_update() without holding the cpus_read_lock() and cpuset_mutex. The current set of wq's flushed by housekeeping_update() may not have work functions that call cpus_read_lock() directly, but we are likely to extend the list of wq's that are flushed in the future. Moreover, the current set of work functions may hold locks that may have cpu_hotplug_lock down the dependency chain. So housekeeping_update() is now called after releasing cpus_read_lock and cpuset_mutex at the end of a cpuset operation. These two locks are then re-acquired later before calling rebuild_sched_domains_locked(). To enable mutual exclusion between the housekeeping_update() call and other cpuset control file write actions, a new top level cpuset_top_mutex is introduced. This new mutex will be acquired first to allow sharing variables used by both code paths. However, cpuset update from CPU hotplug can still happen in parallel with the housekeeping_update() call, though that should be rare in production environment. As cpus_read_lock() is now no longer held when tmigr_isolated_exclude_cpumask() is called, it needs to acquire it directly. The lockdep_is_cpuset_held() is also updated to return true if either cpuset_top_mutex or cpuset_mutex is held. Fixes: 03ff73510169 ("cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 47 ++++++++++++++++++++++++++++++++++++++----- kernel/sched/isolation.c | 4 +--- kernel/time/timer_migration.c | 4 +--- 3 files changed, 44 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index aa915e9b588f..aa45351c6f38 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -65,14 +65,28 @@ static const char * const perr_strings[] = { * CPUSET Locking Convention * ------------------------- * - * Below are the three global locks guarding cpuset structures in lock + * Below are the four global/local locks guarding cpuset structures in lock * acquisition order: + * - cpuset_top_mutex * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) * - cpuset_mutex * - callback_lock (raw spinlock) * - * A task must hold all the three locks to modify externally visible or - * used fields of cpusets, though some of the internally used cpuset fields + * As cpuset will now indirectly flush a number of different workqueues in + * housekeeping_update() to update housekeeping cpumasks when the set of + * isolated CPUs is going to be changed, it may be vulnerable to deadlock + * if we hold cpus_read_lock while calling into housekeeping_update(). + * + * The first cpuset_top_mutex will be held except when calling into + * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock + * and cpuset_mutex will be held instead. The main purpose of this mutex + * is to prevent regular cpuset control file write actions from interfering + * with the call to housekeeping_update(), though CPU hotplug operation can + * still happen in parallel. This mutex also provides protection for some + * internal variables. + * + * A task must hold all the remaining three locks to modify externally visible + * or used fields of cpusets, though some of the internally used cpuset fields * and internal variables can be modified without holding callback_lock. If only * reliable read access of the externally used fields are needed, a task can * hold either cpuset_mutex or callback_lock which are exposed to other @@ -100,6 +114,7 @@ static const char * const perr_strings[] = { * cpumasks and nodemasks. */ +static DEFINE_MUTEX(cpuset_top_mutex); static DEFINE_MUTEX(cpuset_mutex); /* @@ -111,6 +126,8 @@ static DEFINE_MUTEX(cpuset_mutex); * * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable * by holding both cpuset_mutex and callback_lock. + * + * T: Read/write-able by holding the cpuset_top_mutex. */ /* @@ -134,6 +151,11 @@ static cpumask_var_t isolated_cpus; /* CSCB */ */ static bool update_housekeeping; /* RWCS */ +/* + * Copy of isolated_cpus to be passed to housekeeping_update() + */ +static cpumask_var_t isolated_hk_cpus; /* T */ + /* * A flag to force sched domain rebuild at the end of an operation. * It can be set in @@ -297,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void) */ void cpuset_full_lock(void) { + mutex_lock(&cpuset_top_mutex); cpus_read_lock(); mutex_lock(&cpuset_mutex); } @@ -305,12 +328,14 @@ void cpuset_full_unlock(void) { mutex_unlock(&cpuset_mutex); cpus_read_unlock(); + mutex_unlock(&cpuset_top_mutex); } #ifdef CONFIG_LOCKDEP bool lockdep_is_cpuset_held(void) { - return lockdep_is_held(&cpuset_mutex); + return lockdep_is_held(&cpuset_mutex) || + lockdep_is_held(&cpuset_top_mutex); } #endif @@ -1315,9 +1340,20 @@ static void update_hk_sched_domains(void) { if (update_housekeeping) { /* Updating HK cpumasks implies rebuild sched domains */ - WARN_ON_ONCE(housekeeping_update(isolated_cpus)); update_housekeeping = false; force_sd_rebuild = true; + cpumask_copy(isolated_hk_cpus, isolated_cpus); + + /* + * housekeeping_update() is now called without holding + * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex + * is still being held for mutual exclusion. + */ + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); + cpus_read_lock(); + mutex_lock(&cpuset_mutex); } /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ if (force_sd_rebuild) @@ -3635,6 +3671,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 3b725d39c06e..ef152d401fe2 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask) struct cpumask *trial, *old = NULL; int err; - lockdep_assert_cpus_held(); - trial = kmalloc(cpumask_size(), GFP_KERNEL); if (!trial) return -ENOMEM; @@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask) } if (!housekeeping.flags) - static_branch_enable_cpuslocked(&housekeeping_overridden); + static_branch_enable(&housekeeping_overridden); if (housekeeping.flags & HK_FLAG_DOMAIN) old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 6da9cd562b20..83428aa03aef 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu; - lockdep_assert_cpus_held(); - if (!works) return -ENOMEM; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) @@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) * First set previously isolated CPUs as available (unisolate). * This cpumask contains only CPUs that switched to available now. */ + guard(cpus_read_lock)(); cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); @@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void) cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); /* Protect against RCU torture hotplug testing */ - guard(cpus_read_lock)(); return tmigr_isolated_exclude_cpumask(cpumask); } late_initcall(tmigr_init_isolation); -- cgit v1.2.3 From f85b1c6af5bc3872f994df0a5688c1162de07a62 Mon Sep 17 00:00:00 2001 From: "Pratyush Yadav (Google)" Date: Mon, 16 Feb 2026 14:22:19 +0100 Subject: liveupdate: luo_file: remember retrieve() status LUO keeps track of successful retrieve attempts on a LUO file. It does so to avoid multiple retrievals of the same file. Multiple retrievals cause problems because once the file is retrieved, the serialized data structures are likely freed and the file is likely in a very different state from what the code expects. The retrieve boolean in struct luo_file keeps track of this, and is passed to the finish callback so it knows what work was already done and what it has left to do. All this works well when retrieve succeeds. When it fails, luo_retrieve_file() returns the error immediately, without ever storing anywhere that a retrieve was attempted or what its error code was. This results in an errored LIVEUPDATE_SESSION_RETRIEVE_FD ioctl to userspace, but nothing prevents it from trying this again. The retry is problematic for much of the same reasons listed above. The file is likely in a very different state than what the retrieve logic normally expects, and it might even have freed some serialization data structures. Attempting to access them or free them again is going to break things. For example, if memfd managed to restore 8 of its 10 folios, but fails on the 9th, a subsequent retrieve attempt will try to call kho_restore_folio() on the first folio again, and that will fail with a warning since it is an invalid operation. Apart from the retry, finish() also breaks. Since on failure the retrieved bool in luo_file is never touched, the finish() call on session close will tell the file handler that retrieve was never attempted, and it will try to access or free the data structures that might not exist, much in the same way as the retry attempt. There is no sane way of attempting the retrieve again. Remember the error retrieve returned and directly return it on a retry. Also pass this status code to finish() so it can make the right decision on the work it needs to do. This is done by changing the bool to an integer. A value of 0 means retrieve was never attempted, a positive value means it succeeded, and a negative value means it failed and the error code is the value. Link: https://lkml.kernel.org/r/20260216132221.987987-1-pratyush@kernel.org Fixes: 7c722a7f44e0 ("liveupdate: luo_file: implement file systems callbacks") Signed-off-by: Pratyush Yadav (Google) Reviewed-by: Mike Rapoport (Microsoft) Cc: Pasha Tatashin Cc: Signed-off-by: Andrew Morton --- kernel/liveupdate/luo_file.c | 41 +++++++++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index 8c79058253e1..5acee4174bf0 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -134,9 +134,12 @@ static LIST_HEAD(luo_file_handler_list); * state that is not preserved. Set by the handler's .preserve() * callback, and must be freed in the handler's .unpreserve() * callback. - * @retrieved: A flag indicating whether a user/kernel in the new kernel has + * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has * successfully called retrieve() on this file. This prevents - * multiple retrieval attempts. + * multiple retrieval attempts. A value of 0 means a retrieve() + * has not been attempted, a positive value means the retrieve() + * was successful, and a negative value means the retrieve() + * failed, and the value is the error code of the call. * @mutex: A mutex that protects the fields of this specific instance * (e.g., @retrieved, @file), ensuring that operations like * retrieving or finishing a file are atomic. @@ -161,7 +164,7 @@ struct luo_file { struct file *file; u64 serialized_data; void *private_data; - bool retrieved; + int retrieve_status; struct mutex mutex; struct list_head list; u64 token; @@ -298,7 +301,6 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd) luo_file->file = file; luo_file->fh = fh; luo_file->token = token; - luo_file->retrieved = false; mutex_init(&luo_file->mutex); args.handler = fh; @@ -577,7 +579,12 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token, return -ENOENT; guard(mutex)(&luo_file->mutex); - if (luo_file->retrieved) { + if (luo_file->retrieve_status < 0) { + /* Retrieve was attempted and it failed. Return the error code. */ + return luo_file->retrieve_status; + } + + if (luo_file->retrieve_status > 0) { /* * Someone is asking for this file again, so get a reference * for them. @@ -590,16 +597,19 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token, args.handler = luo_file->fh; args.serialized_data = luo_file->serialized_data; err = luo_file->fh->ops->retrieve(&args); - if (!err) { - luo_file->file = args.file; - - /* Get reference so we can keep this file in LUO until finish */ - get_file(luo_file->file); - *filep = luo_file->file; - luo_file->retrieved = true; + if (err) { + /* Keep the error code for later use. */ + luo_file->retrieve_status = err; + return err; } - return err; + luo_file->file = args.file; + /* Get reference so we can keep this file in LUO until finish */ + get_file(luo_file->file); + *filep = luo_file->file; + luo_file->retrieve_status = 1; + + return 0; } static int luo_file_can_finish_one(struct luo_file_set *file_set, @@ -615,7 +625,7 @@ static int luo_file_can_finish_one(struct luo_file_set *file_set, args.handler = luo_file->fh; args.file = luo_file->file; args.serialized_data = luo_file->serialized_data; - args.retrieved = luo_file->retrieved; + args.retrieve_status = luo_file->retrieve_status; can_finish = luo_file->fh->ops->can_finish(&args); } @@ -632,7 +642,7 @@ static void luo_file_finish_one(struct luo_file_set *file_set, args.handler = luo_file->fh; args.file = luo_file->file; args.serialized_data = luo_file->serialized_data; - args.retrieved = luo_file->retrieved; + args.retrieve_status = luo_file->retrieve_status; luo_file->fh->ops->finish(&args); luo_flb_file_finish(luo_file->fh); @@ -788,7 +798,6 @@ int luo_file_deserialize(struct luo_file_set *file_set, luo_file->file = NULL; luo_file->serialized_data = file_ser[i].data; luo_file->token = file_ser[i].token; - luo_file->retrieved = false; mutex_init(&luo_file->mutex); list_add_tail(&luo_file->list, &file_set->files_list); } -- cgit v1.2.3 From 83236b2e43dba00bee5b82eb5758816b1a674f6a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Feb 2026 21:39:58 -1000 Subject: sched_ext: Disable preemption between scx_claim_exit() and kicking helper work scx_claim_exit() atomically sets exit_kind, which prevents scx_error() from triggering further error handling. After claiming exit, the caller must kick the helper kthread work which initiates bypass mode and teardown. If the calling task gets preempted between claiming exit and kicking the helper work, and the BPF scheduler fails to schedule it back (since error handling is now disabled), the helper work is never queued, bypass mode never activates, tasks stop being dispatched, and the system wedges. Disable preemption across scx_claim_exit() and the subsequent work kicking in all callers - scx_disable() and scx_vexit(). Add lockdep_assert_preemption_disabled() to scx_claim_exit() to enforce the requirement. Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c18e81e8ef51..9280381f8923 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4423,10 +4423,19 @@ done: scx_bypass(false); } +/* + * Claim the exit on @sch. The caller must ensure that the helper kthread work + * is kicked before the current task can be preempted. Once exit_kind is + * claimed, scx_error() can no longer trigger, so if the current task gets + * preempted and the BPF scheduler fails to schedule it back, the helper work + * will never be kicked and the whole system can wedge. + */ static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind) { int none = SCX_EXIT_NONE; + lockdep_assert_preemption_disabled(); + if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind)) return false; @@ -4449,6 +4458,7 @@ static void scx_disable(enum scx_exit_kind kind) rcu_read_lock(); sch = rcu_dereference(scx_root); if (sch) { + guard(preempt)(); scx_claim_exit(sch, kind); kthread_queue_work(sch->helper, &sch->disable_work); } @@ -4771,6 +4781,8 @@ static bool scx_vexit(struct scx_sched *sch, { struct scx_exit_info *ei = sch->exit_info; + guard(preempt)(); + if (!scx_claim_exit(sch, kind)) return false; -- cgit v1.2.3 From c9bc1753b3cc41d0e01fbca7f035258b5f4db0ae Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 Feb 2026 13:29:09 +0100 Subject: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race Make sure that __perf_event_overflow() runs with IRQs disabled for all possible callchains. Specifically the software events can end up running it with only preemption disabled. This opens up a race vs perf_event_exit_event() and friends that will go and free various things the overflow path expects to be present, like the BPF program. Fixes: 592903cdcbf6 ("perf_counter: add an event_list") Reported-by: Simond Hu Signed-off-by: Peter Zijlstra (Intel) Tested-by: Simond Hu Link: https://patch.msgid.link/20260224122909.GV1395416@noisy.programming.kicks-ass.net --- kernel/events/core.c | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 22a0f405585b..1f5699b339ec 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10777,6 +10777,13 @@ int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { + /* + * Entry point from hardware PMI, interrupts should be disabled here. + * This serializes us against perf_event_remove_from_context() in + * things like perf_event_release_kernel(). + */ + lockdep_assert_irqs_disabled(); + return __perf_event_overflow(event, 1, data, regs); } @@ -10853,6 +10860,19 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, { struct hw_perf_event *hwc = &event->hw; + /* + * This is: + * - software preempt + * - tracepoint preempt + * - tp_target_task irq (ctx->lock) + * - uprobes preempt/irq + * - kprobes preempt/irq + * - hw_breakpoint irq + * + * Any of these are sufficient to hold off RCU and thus ensure @event + * exists. + */ + lockdep_assert_preemption_disabled(); local64_add(nr, &event->count); if (!regs) @@ -10861,6 +10881,16 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, if (!is_sampling_event(event)) return; + /* + * Serialize against event_function_call() IPIs like normal overflow + * event handling. Specifically, must not allow + * perf_event_release_kernel() -> perf_remove_from_context() to make + * progress and 'release' the event from under us. + */ + guard(irqsave)(); + if (event->state != PERF_EVENT_STATE_ACTIVE) + return; + if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) { data->period = nr; return perf_swevent_overflow(event, 1, data, regs); @@ -11359,6 +11389,11 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct perf_sample_data data; struct perf_event *event; + /* + * Per being a tracepoint, this runs with preemption disabled. + */ + lockdep_assert_preemption_disabled(); + struct perf_raw_record raw = { .frag = { .size = entry_size, @@ -11691,6 +11726,11 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; + /* + * Exception context, will have interrupts disabled. + */ + lockdep_assert_irqs_disabled(); + perf_sample_data_init(&sample, bp->attr.bp_addr, 0); if (!bp->hw.state && !perf_exclude_event(bp, regs)) @@ -12155,7 +12195,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) if (regs && !perf_exclude_event(event, regs)) { if (!(event->attr.exclude_idle && is_idle_task(current))) - if (__perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) ret = HRTIMER_NORESTART; } -- cgit v1.2.3 From 085f067389d12bd9800c0a9672a174c1de7a8069 Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Wed, 25 Feb 2026 01:15:23 +0000 Subject: cgroup/cpuset: fix null-ptr-deref in rebuild_sched_domains_cpuslocked A null-pointer-dereference bug was reported by syzbot: Oops: general protection fault, probably for address 0xdffffc0000000000: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:bitmap_subset include/linux/bitmap.h:433 [inline] RIP: 0010:cpumask_subset include/linux/cpumask.h:836 [inline] RIP: 0010:rebuild_sched_domains_locked kernel/cgroup/cpuset.c:967 RSP: 0018:ffffc90003ecfbc0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000020 RDX: ffff888028de0000 RSI: ffffffff8200f003 RDI: ffffffff8df14f28 RBP: 0000000000000000 R08: 0000000000000cc0 R09: 00000000ffffffff R10: ffffffff8e7d95b3 R11: 0000000000000001 R12: 0000000000000000 R13: 00000000000f4240 R14: dffffc0000000000 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2f463fff CR3: 000000003704c000 CR4: 00000000003526f0 Call Trace: rebuild_sched_domains_cpuslocked kernel/cgroup/cpuset.c:983 [inline] rebuild_sched_domains+0x21/0x40 kernel/cgroup/cpuset.c:990 sched_rt_handler+0xb5/0xe0 kernel/sched/rt.c:2911 proc_sys_call_handler+0x47f/0x5a0 fs/proc/proc_sysctl.c:600 new_sync_write fs/read_write.c:595 [inline] vfs_write+0x6ac/0x1070 fs/read_write.c:688 ksys_write+0x12a/0x250 fs/read_write.c:740 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The issue occurs when generate_sched_domains() returns ndoms = 1 and doms = NULL due to a kmalloc failure. This leads to a null-pointer dereference when accessing doms in rebuild_sched_domains_locked(). Fix this by adding a NULL check for doms before accessing it. Fixes: 6ee43047e8ad ("cpuset: Remove unnecessary checks in rebuild_sched_domains_locked") Reported-by: syzbot+460792609a79c085f79f@syzkaller.appspotmail.com Acked-by: Waiman Long Signed-off-by: Chen Ridong Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index aa45351c6f38..271bb99b1b9d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1002,7 +1002,7 @@ void rebuild_sched_domains_locked(void) * offline CPUs, a warning is emitted and we return directly to * prevent the panic. */ - for (i = 0; i < ndoms; ++i) { + for (i = 0; doms && i < ndoms; i++) { if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) return; } -- cgit v1.2.3 From 2a064262eb378263792cf1fb044de631ac41bcc5 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Wed, 25 Feb 2026 21:15:23 +0000 Subject: sched_ext: Fix out-of-bounds access in scx_idle_init_masks() scx_idle_node_masks is allocated with num_possible_nodes() elements but indexed by NUMA node IDs via for_each_node(). On systems with non-contiguous NUMA node numbering (e.g. nodes 0 and 4), node IDs can exceed the array size, causing out-of-bounds memory corruption. Use nr_node_ids instead, which represents the maximum node ID range and is the correct size for arrays indexed by node ID. Fixes: 7c60329e3521 ("sched_ext: Add NUMA-awareness to the default idle selection policy") Signed-off-by: David Carlier Signed-off-by: Tejun Heo --- kernel/sched/ext_idle.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 3d9d404d5cd2..e2da6c3968a6 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -663,8 +663,8 @@ void scx_idle_init_masks(void) BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL)); - /* Allocate per-node idle cpumasks */ - scx_idle_node_masks = kcalloc(num_possible_nodes(), + /* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */ + scx_idle_node_masks = kcalloc(nr_node_ids, sizeof(*scx_idle_node_masks), GFP_KERNEL); BUG_ON(!scx_idle_node_masks); -- cgit v1.2.3 From 28aaa9c39945b7925a1cc1d513c8f21ed38f5e4f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 10:43:55 +0100 Subject: kthread: consolidate kthread exit paths to prevent use-after-free Guillaume reported crashes via corrupted RCU callback function pointers during KUnit testing. The crash was traced back to the pidfs rhashtable conversion which replaced the 24-byte rb_node with an 8-byte rhash_head in struct pid, shrinking it from 160 to 144 bytes. struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to 192 bytes and share the same slab cache. struct pid.rcu.func and struct kthread.affinity_node both sit at offset 0x78. When a kthread exits via make_task_dead() it bypasses kthread_exit() and misses the affinity_node cleanup. free_kthread_struct() frees the memory while the node is still linked into the global kthread_affinity_list. A subsequent list_del() by another kthread writes through dangling list pointers into the freed and reused memory, corrupting the pid's rcu.func pointer. Instead of patching free_kthread_struct() to handle the missed cleanup, consolidate all kthread exit paths. Turn kthread_exit() into a macro that calls do_exit() and add kthread_do_exit() which is called from do_exit() for any task with PF_KTHREAD set. This guarantees that kthread-specific cleanup always happens regardless of the exit path - make_task_dead(), direct do_exit(), or kthread_exit(). Replace __to_kthread() with a new tsk_is_kthread() accessor in the public header. Export do_exit() since module code using the kthread_exit() macro now needs it directly. Reported-by: Guillaume Tucker Tested-by: Guillaume Tucker Tested-by: Mark Brown Tested-by: David Gow Cc: Link: https://lore.kernel.org/all/20260224-mittlerweile-besessen-2738831ae7f6@brauner Co-developed-by: Linus Torvalds Fixes: 4d13f4304fa4 ("kthread: Implement preferred affinity") Signed-off-by: Linus Torvalds Signed-off-by: Christian Brauner --- kernel/exit.c | 6 ++++++ kernel/kthread.c | 41 +++++------------------------------------ 2 files changed, 11 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 8a87021211ae..ede3117fa7d4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code) void __noreturn do_exit(long code) { struct task_struct *tsk = current; + struct kthread *kthread; int group_dead; WARN_ON(irqs_disabled()); WARN_ON(tsk->plug); + kthread = tsk_is_kthread(tsk); + if (unlikely(kthread)) + kthread_do_exit(kthread, code); + kcov_task_exit(tsk); kmsan_task_exit(tsk); @@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } +EXPORT_SYMBOL(do_exit); void __noreturn make_task_dead(int signr) { diff --git a/kernel/kthread.c b/kernel/kthread.c index 20451b624b67..791210daf8b4 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k) return k->worker_private; } -/* - * Variant of to_kthread() that doesn't assume @p is a kthread. - * - * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will - * always remain a kthread. For kthreads p->worker_private always - * points to a struct kthread. For tasks that are not kthreads - * p->worker_private is used to point to other things. - * - * Return NULL for any task that is not a kthread. - */ -static inline struct kthread *__to_kthread(struct task_struct *p) -{ - void *kthread = p->worker_private; - if (kthread && !(p->flags & PF_KTHREAD)) - kthread = NULL; - return kthread; -} - void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); @@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { - struct kthread *kthread = __to_kthread(current); + struct kthread *kthread = tsk_is_kthread(current); if (!kthread) return false; @@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); */ void *kthread_func(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); if (kthread) return kthread->threadfn; return NULL; @@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data); */ void *kthread_probe_data(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); void *data = NULL; if (kthread) @@ -309,19 +291,8 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -/** - * kthread_exit - Cause the current kthread return @result to kthread_stop(). - * @result: The integer value to return to kthread_stop(). - * - * While kthread_exit can be called directly, it exists so that - * functions which do some additional work in non-modular code such as - * module_put_and_kthread_exit can be implemented. - * - * Does not return. - */ -void __noreturn kthread_exit(long result) +void kthread_do_exit(struct kthread *kthread, long result) { - struct kthread *kthread = to_kthread(current); kthread->result = result; if (!list_empty(&kthread->affinity_node)) { mutex_lock(&kthread_affinity_lock); @@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result) kthread->preferred_affinity = NULL; } } - do_exit(0); } -EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. @@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu) bool kthread_is_per_cpu(struct task_struct *p) { - struct kthread *kthread = __to_kthread(p); + struct kthread *kthread = tsk_is_kthread(p); if (!kthread) return false; -- cgit v1.2.3 From 795469820c638b4449f3bb90ee5e98ebccfbc480 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 23 Feb 2026 14:01:56 -0800 Subject: kcsan: test: Adjust "expect" allocation type for kmalloc_obj The call to kmalloc_obj(observed.lines) returns "char (*)[3][512]", a pointer to the whole 2D array. But "expect" wants to be "char (*)[512]", the decayed pointer type, as if it were observed.lines itself (though without the "3" bounds). This produces the following build error: ../kernel/kcsan/kcsan_test.c: In function '__report_matches': ../kernel/kcsan/kcsan_test.c:171:16: error: assignment to 'char (*)[512]' from incompatible pointer type 'char (*)[3][512]' [-Wincompatible-pointer-types] 171 | expect = kmalloc_obj(observed.lines); | ^ Instead of changing the "expect" type to "char (*)[3][512]" and requiring a dereference at each use (e.g. "(expect*)[0]"), just explicitly cast the return to the desired type. Note that I'm intentionally not switching back to byte-based "kmalloc" here because I cannot find a way for the Coccinelle script (which will be used going forward to catch future conversions) to exclude this case. Tested with: $ ./tools/testing/kunit/kunit.py run \ --kconfig_add CONFIG_DEBUG_KERNEL=y \ --kconfig_add CONFIG_KCSAN=y \ --kconfig_add CONFIG_KCSAN_KUNIT_TEST=y \ --arch=x86_64 --qemu_args '-smp 2' kcsan Reported-by: Nathan Chancellor Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types") Signed-off-by: Kees Cook --- kernel/kcsan/kcsan_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index 79e655ea4ca1..ae758150ccb9 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -168,7 +168,7 @@ static bool __report_matches(const struct expect_report *r) if (!report_available()) return false; - expect = kmalloc_obj(observed.lines); + expect = (typeof(expect))kmalloc_obj(observed.lines); if (WARN_ON(!expect)) return false; -- cgit v1.2.3 From ad6fface76da42721c15e8fb281570aaa44a2c01 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 25 Feb 2026 12:12:49 +0100 Subject: bpf: Fix kprobe_multi cookies access in show_fdinfo callback We don't check if cookies are available on the kprobe_multi link before accessing them in show_fdinfo callback, we should. Cc: stable@vger.kernel.org Fixes: da7e9c0a7fbc ("bpf: Add show_fdinfo for kprobe_multi") Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20260225111249.186230-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9bc0dfd235af..0b040a417442 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2454,8 +2454,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_kprobe_multi_link *kmulti_link; + bool has_cookies; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + has_cookies = !!kmulti_link->cookies; seq_printf(seq, "kprobe_cnt:\t%u\n" @@ -2467,7 +2469,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, for (int i = 0; i < kmulti_link->cnt; i++) { seq_printf(seq, "%llu\t %pS\n", - kmulti_link->cookies[i], + has_cookies ? kmulti_link->cookies[i] : 0, (void *)kmulti_link->addrs[i]); } } -- cgit v1.2.3 From b7bf516c3ecd9a2aae2dc2635178ab87b734fef1 Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Wed, 25 Feb 2026 05:34:44 +0000 Subject: bpf: Fix stack-out-of-bounds write in devmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit get_upper_ifindexes() iterates over all upper devices and writes their indices into an array without checking bounds. Also the callers assume that the max number of upper devices is MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack, but that assumption is not correct and the number of upper devices could be larger than MAX_NEST_DEV (e.g., many macvlans), causing a stack-out-of-bounds write. Add a max parameter to get_upper_ifindexes() to avoid the issue. When there are too many upper devices, return -EOVERFLOW and abort the redirect. To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS. Then send a packet to the device to trigger the XDP redirect path. Reported-by: syzbot+10cc7f13760b31bd2e61@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/698c4ce3.050a0220.340abe.000b.GAE@google.com/T/ Fixes: aeea1b86f936 ("bpf, devmap: Exclude XDP broadcast to master device") Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Kohei Enju Link: https://lore.kernel.org/r/20260225053506.4738-1-kohei@enjuk.jp Signed-off-by: Alexei Starovoitov --- kernel/bpf/devmap.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2625601de76e..2984e938f94d 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -588,18 +588,22 @@ static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifin } /* Get ifindex of each upper device. 'indexes' must be able to hold at - * least MAX_NEST_DEV elements. - * Returns the number of ifindexes added. + * least 'max' elements. + * Returns the number of ifindexes added, or -EOVERFLOW if there are too + * many upper devices. */ -static int get_upper_ifindexes(struct net_device *dev, int *indexes) +static int get_upper_ifindexes(struct net_device *dev, int *indexes, int max) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { + if (n >= max) + return -EOVERFLOW; indexes[n++] = upper->ifindex; } + return n; } @@ -615,7 +619,11 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, int err; if (exclude_ingress) { - num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); + num_excluded = get_upper_ifindexes(dev_rx, excluded_devices, + ARRAY_SIZE(excluded_devices) - 1); + if (num_excluded < 0) + return num_excluded; + excluded_devices[num_excluded++] = dev_rx->ifindex; } @@ -733,7 +741,11 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, int err; if (exclude_ingress) { - num_excluded = get_upper_ifindexes(dev, excluded_devices); + num_excluded = get_upper_ifindexes(dev, excluded_devices, + ARRAY_SIZE(excluded_devices) - 1); + if (num_excluded < 0) + return num_excluded; + excluded_devices[num_excluded++] = dev->ifindex; } -- cgit v1.2.3 From 749989b2d90ddc7dd253ad3b11a77cf882721acf Mon Sep 17 00:00:00 2001 From: David Carlier Date: Thu, 26 Feb 2026 12:45:17 +0000 Subject: sched_ext: Fix SCX_EFLAG_INITIALIZED being a no-op flag SCX_EFLAG_INITIALIZED is the sole member of enum scx_exit_flags with no explicit value, so the compiler assigns it 0. This makes the bitwise OR in scx_ops_init() a no-op: sch->exit_info->flags |= SCX_EFLAG_INITIALIZED; /* |= 0 */ As a result, BPF schedulers cannot distinguish whether ops.init() completed successfully by inspecting exit_info->flags. Assign the value 1LLU << 0 so the flag is actually set. Fixes: f3aec2adce8d ("sched_ext: Add SCX_EFLAG_INITIALIZED to indicate successful ops.init()") Signed-off-by: David Carlier Signed-off-by: Tejun Heo --- kernel/sched/ext_internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 386c677e4c9a..11ebb744d893 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -74,7 +74,7 @@ enum scx_exit_flags { * info communication. The following flag indicates whether ops.init() * finished successfully. */ - SCX_EFLAG_INITIALIZED, + SCX_EFLAG_INITIALIZED = 1LLU << 0, }; /* -- cgit v1.2.3 From e6b899f08066e744f89df16ceb782e06868bd148 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:50:09 +0100 Subject: nsfs: tighten permission checks for ns iteration ioctls Even privileged services should not necessarily be able to see other privileged service's namespaces so they can't leak information to each other. Use may_see_all_namespaces() helper that centralizes this policy until the nstree adapts. Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-1-d2c2853313bd@kernel.org Fixes: a1d220d9dafa ("nsfs: iterate through mount namespaces") Reviewed-by: Jeff Layton Cc: stable@kernel.org # v6.12+ Signed-off-by: Christian Brauner --- kernel/nscommon.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/nscommon.c b/kernel/nscommon.c index bdc3c86231d3..3166c1fd844a 100644 --- a/kernel/nscommon.c +++ b/kernel/nscommon.c @@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns) return; } } + +bool may_see_all_namespaces(void) +{ + return (task_active_pid_ns(current) == &init_pid_ns) && + ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN); +} -- cgit v1.2.3 From 8d76afe84fa2babf604b3c173730d4d2b067e361 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:50:11 +0100 Subject: nstree: tighten permission checks for listing Even privileged services should not necessarily be able to see other privileged service's namespaces so they can't leak information to each other. Use may_see_all_namespaces() helper that centralizes this policy until the nstree adapts. Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-3-d2c2853313bd@kernel.org Fixes: 76b6f5dfb3fd ("nstree: add listns()") Reviewed-by: Jeff Layton Cc: stable@kernel.org # v6.19+ Signed-off-by: Christian Brauner --- kernel/nstree.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/kernel/nstree.c b/kernel/nstree.c index f36c59e6951d..6d12e5900ac0 100644 --- a/kernel/nstree.c +++ b/kernel/nstree.c @@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls, static inline bool __must_check may_list_ns(const struct klistns *kls, struct ns_common *ns) { - if (kls->user_ns) { - if (kls->userns_capable) - return true; - } else { - struct ns_common *owner; - struct user_namespace *user_ns; - - owner = ns_owner(ns); - if (owner) - user_ns = to_user_ns(owner); - else - user_ns = &init_user_ns; - if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN)) - return true; - } - - if (is_current_namespace(ns)) + if (kls->user_ns && kls->userns_capable) return true; - - if (ns->ns_type != CLONE_NEWUSER) - return false; - - if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN)) + if (is_current_namespace(ns)) return true; - - return false; + return may_see_all_namespaces(); } static inline void ns_put(struct ns_common *ns) @@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls) ret = 0; head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head; - kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN); + kls->userns_capable = may_see_all_namespaces(); rcu_read_lock(); -- cgit v1.2.3 From 1df97a7453eec80c1912c2d0360290a3970a7671 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:01 -0800 Subject: bpf: Register dtor for freeing special fields There is a race window where BPF hash map elements can leak special fields if the program with access to the map value recreates these special fields between the check_and_free_fields done on the map value and its eventual return to the memory allocator. Several ways were explored prior to this patch, most notably [0] tried to use a poison value to reject attempts to recreate special fields for map values that have been logically deleted but still accessible to BPF programs (either while sitting in the free list or when reused). While this approach works well for task work, timers, wq, etc., it is harder to apply the idea to kptrs, which have a similar race and failure mode. Instead, we change bpf_mem_alloc to allow registering destructor for allocated elements, such that when they are returned to the allocator, any special fields created while they were accessible to programs in the mean time will be freed. If these values get reused, we do not free the fields again before handing the element back. The special fields thus may remain initialized while the map value sits in a free list. When bpf_mem_alloc is retired in the future, a similar concept can be introduced to kmalloc_nolock-backed kmem_cache, paired with the existing idea of a constructor. Note that the destructor registration happens in map_check_btf, after the BTF record is populated and (at that point) avaiable for inspection and duplication. Duplication is necessary since the freeing of embedded bpf_mem_alloc can be decoupled from actual map lifetime due to logic introduced to reduce the cost of rcu_barrier()s in mem alloc free path in 9f2c6e96c65e ("bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc."). As such, once all callbacks are done, we must also free the duplicated record. To remove dependency on the bpf_map itself, also stash the key size of the map to obtain value from htab_elem long after the map is gone. [0]: https://lore.kernel.org/bpf/20260216131341.1285427-1-mykyta.yatsenko5@gmail.com Fixes: 14a324f6a67e ("bpf: Wire up freeing of referenced kptr") Fixes: 1bfbc267ec91 ("bpf: Enable bpf_timer and bpf_wq in any context") Reported-by: Alexei Starovoitov Tested-by: syzbot@syzkaller.appspotmail.com Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/hashtab.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/memalloc.c | 58 +++++++++++++++++++++++++++------- 2 files changed, 134 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3b9d297a53be..582f0192b7e1 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -125,6 +125,11 @@ struct htab_elem { char key[] __aligned(8); }; +struct htab_btf_record { + struct btf_record *record; + u32 key_size; +}; + static inline bool htab_is_prealloc(const struct bpf_htab *htab) { return !(htab->map.map_flags & BPF_F_NO_PREALLOC); @@ -457,6 +462,84 @@ static int htab_map_alloc_check(union bpf_attr *attr) return 0; } +static void htab_mem_dtor(void *obj, void *ctx) +{ + struct htab_btf_record *hrec = ctx; + struct htab_elem *elem = obj; + void *map_value; + + if (IS_ERR_OR_NULL(hrec->record)) + return; + + map_value = htab_elem_value(elem, hrec->key_size); + bpf_obj_free_fields(hrec->record, map_value); +} + +static void htab_pcpu_mem_dtor(void *obj, void *ctx) +{ + void __percpu *pptr = *(void __percpu **)obj; + struct htab_btf_record *hrec = ctx; + int cpu; + + if (IS_ERR_OR_NULL(hrec->record)) + return; + + for_each_possible_cpu(cpu) + bpf_obj_free_fields(hrec->record, per_cpu_ptr(pptr, cpu)); +} + +static void htab_dtor_ctx_free(void *ctx) +{ + struct htab_btf_record *hrec = ctx; + + btf_record_free(hrec->record); + kfree(ctx); +} + +static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *)) +{ + u32 key_size = htab->map.key_size; + const struct bpf_mem_alloc *ma; + struct htab_btf_record *hrec; + int err; + + /* No need for dtors. */ + if (IS_ERR_OR_NULL(htab->map.record)) + return 0; + + hrec = kzalloc(sizeof(*hrec), GFP_KERNEL); + if (!hrec) + return -ENOMEM; + hrec->key_size = key_size; + hrec->record = btf_record_dup(htab->map.record); + if (IS_ERR(hrec->record)) { + err = PTR_ERR(hrec->record); + kfree(hrec); + return err; + } + ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma; + /* Kinda sad, but cast away const-ness since we change ma->dtor. */ + bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec); + return 0; +} + +static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + if (htab_is_prealloc(htab)) + return 0; + /* + * We must set the dtor using this callback, as map's BTF record is not + * populated in htab_map_alloc(), so it will always appear as NULL. + */ + if (htab_is_percpu(htab)) + return htab_set_dtor(htab, htab_pcpu_mem_dtor); + else + return htab_set_dtor(htab, htab_mem_dtor); +} + static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -2281,6 +2364,7 @@ const struct bpf_map_ops htab_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], @@ -2303,6 +2387,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru), .map_btf_id = &htab_map_btf_ids[0], @@ -2482,6 +2567,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_percpu), .map_btf_id = &htab_map_btf_ids[0], @@ -2502,6 +2588,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru_percpu), .map_btf_id = &htab_map_btf_ids[0], diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index bd45dda9dc35..682a9f34214b 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -102,6 +102,8 @@ struct bpf_mem_cache { int percpu_size; bool draining; struct bpf_mem_cache *tgt; + void (*dtor)(void *obj, void *ctx); + void *dtor_ctx; /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; @@ -260,12 +262,14 @@ static void free_one(void *obj, bool percpu) kfree(obj); } -static int free_all(struct llist_node *llnode, bool percpu) +static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool percpu) { struct llist_node *pos, *t; int cnt = 0; llist_for_each_safe(pos, t, llnode) { + if (c->dtor) + c->dtor((void *)pos + LLIST_NODE_SZ, c->dtor_ctx); free_one(pos, percpu); cnt++; } @@ -276,7 +280,7 @@ static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); - free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); + free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); atomic_set(&c->call_rcu_ttrace_in_progress, 0); } @@ -308,7 +312,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c) if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { if (unlikely(READ_ONCE(c->draining))) { llnode = llist_del_all(&c->free_by_rcu_ttrace); - free_all(llnode, !!c->percpu_size); + free_all(c, llnode, !!c->percpu_size); } return; } @@ -417,7 +421,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c) dec_active(c, &flags); if (unlikely(READ_ONCE(c->draining))) { - free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); + free_all(c, llist_del_all(&c->waiting_for_gp), !!c->percpu_size); atomic_set(&c->call_rcu_in_progress, 0); } else { call_rcu_hurry(&c->rcu, __free_by_rcu); @@ -635,13 +639,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c) * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ - free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); - free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); - free_all(__llist_del_all(&c->free_llist), percpu); - free_all(__llist_del_all(&c->free_llist_extra), percpu); - free_all(__llist_del_all(&c->free_by_rcu), percpu); - free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); - free_all(llist_del_all(&c->waiting_for_gp), percpu); + free_all(c, llist_del_all(&c->free_by_rcu_ttrace), percpu); + free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), percpu); + free_all(c, __llist_del_all(&c->free_llist), percpu); + free_all(c, __llist_del_all(&c->free_llist_extra), percpu); + free_all(c, __llist_del_all(&c->free_by_rcu), percpu); + free_all(c, __llist_del_all(&c->free_llist_extra_rcu), percpu); + free_all(c, llist_del_all(&c->waiting_for_gp), percpu); } static void check_mem_cache(struct bpf_mem_cache *c) @@ -680,6 +684,9 @@ static void check_leaked_objs(struct bpf_mem_alloc *ma) static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { + /* We can free dtor ctx only once all callbacks are done using it. */ + if (ma->dtor_ctx_free) + ma->dtor_ctx_free(ma->dtor_ctx); check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); @@ -1014,3 +1021,32 @@ int bpf_mem_alloc_check_size(bool percpu, size_t size) return 0; } + +void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, void (*dtor)(void *obj, void *ctx), + void (*dtor_ctx_free)(void *ctx), void *ctx) +{ + struct bpf_mem_caches *cc; + struct bpf_mem_cache *c; + int cpu, i; + + ma->dtor_ctx_free = dtor_ctx_free; + ma->dtor_ctx = ctx; + + if (ma->cache) { + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(ma->cache, cpu); + c->dtor = dtor; + c->dtor_ctx = ctx; + } + } + if (ma->caches) { + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(ma->caches, cpu); + for (i = 0; i < NUM_CACHES; i++) { + c = &cc->cache[i]; + c->dtor = dtor; + c->dtor_ctx = ctx; + } + } + } +} -- cgit v1.2.3 From ae51772b1e94ba1d76db19085957dbccac189c1c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:02 -0800 Subject: bpf: Lose const-ness of map in map_check_btf() BPF hash map may now use the map_check_btf() callback to decide whether to set a dtor on its bpf_mem_alloc or not. Unlike C++ where members can opt out of const-ness using mutable, we must lose the const qualifier on the callback such that we can avoid the ugly cast. Make the change and adjust all existing users, and lose the comment in hashtab.c. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/arena.c | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/bloom_filter.c | 2 +- kernel/bpf/bpf_insn_array.c | 2 +- kernel/bpf/bpf_local_storage.c | 2 +- kernel/bpf/hashtab.c | 9 ++++----- kernel/bpf/local_storage.c | 2 +- kernel/bpf/lpm_trie.c | 2 +- kernel/bpf/syscall.c | 2 +- 9 files changed, 12 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 144f30e740e8..f355cf1c1a16 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -303,7 +303,7 @@ static long arena_map_update_elem(struct bpf_map *map, void *key, return -EOPNOTSUPP; } -static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, +static int arena_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return 0; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 26763df6134a..33de68c95ad8 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -548,7 +548,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int array_map_check_btf(const struct bpf_map *map, +static int array_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 35e1ddca74d2..b73336c976b7 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -180,7 +180,7 @@ static long bloom_map_update_elem(struct bpf_map *map, void *key, return -EINVAL; } -static int bloom_map_check_btf(const struct bpf_map *map, +static int bloom_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bpf_insn_array.c b/kernel/bpf/bpf_insn_array.c index c0286f25ca3c..a2f84afe6f7c 100644 --- a/kernel/bpf/bpf_insn_array.c +++ b/kernel/bpf/bpf_insn_array.c @@ -98,7 +98,7 @@ static long insn_array_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } -static int insn_array_check_btf(const struct bpf_map *map, +static int insn_array_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b28f07d3a0db..2bf5ca5ae0df 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -797,7 +797,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -int bpf_local_storage_map_check_btf(const struct bpf_map *map, +int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 582f0192b7e1..bc6bc8bb871d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -496,10 +496,10 @@ static void htab_dtor_ctx_free(void *ctx) kfree(ctx); } -static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *)) +static int htab_set_dtor(struct bpf_htab *htab, void (*dtor)(void *, void *)) { u32 key_size = htab->map.key_size; - const struct bpf_mem_alloc *ma; + struct bpf_mem_alloc *ma; struct htab_btf_record *hrec; int err; @@ -518,12 +518,11 @@ static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void return err; } ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma; - /* Kinda sad, but cast away const-ness since we change ma->dtor. */ - bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec); + bpf_mem_alloc_set_dtor(ma, dtor, htab_dtor_ctx_free, hrec); return 0; } -static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf, +static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 1ccbf28b2ad9..8fca0c64f7b1 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -364,7 +364,7 @@ static long cgroup_storage_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } -static int cgroup_storage_check_btf(const struct bpf_map *map, +static int cgroup_storage_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1adeb4d3b8cf..0f57608b385d 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -751,7 +751,7 @@ free_stack: return err; } -static int trie_check_btf(const struct bpf_map *map, +static int trie_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0378e83b4099..274039e36465 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1234,7 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) } EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); -int map_check_no_btf(const struct bpf_map *map, +int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) -- cgit v1.2.3 From f41deee082dc7b1c198de21710cb5cb9c604cae0 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:03 -0800 Subject: bpf: Delay freeing fields in local storage Currently, when use_kmalloc_nolock is false, the freeing of fields for a local storage selem is done eagerly before waiting for the RCU or RCU tasks trace grace period to elapse. This opens up a window where the program which has access to the selem can recreate the fields after the freeing of fields is done eagerly, causing memory leaks when the element is finally freed and returned to the kernel. Make a few changes to address this. First, delay the freeing of fields until after the grace periods have expired using a __bpf_selem_free_rcu wrapper which is eventually invoked after transitioning through the necessary number of grace period waits. Replace usage of the kfree_rcu with call_rcu to be able to take a custom callback. Finally, care needs to be taken to extend the rcu barriers for all cases, and not just when use_kmalloc_nolock is true, as RCU and RCU tasks trace callbacks can be in flight for either case and access the smap field, which is used to obtain the BTF record to walk over special fields in the map value. While we're at it, drop migrate_disable() from bpf_selem_free_rcu, since migration should be disabled for RCU callbacks already. Fixes: 9bac675e6368 ("bpf: Postpone bpf_obj_free_fields to the rcu callback") Reviewed-by: Amery Hung Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/bpf_local_storage.c | 40 +++++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 2bf5ca5ae0df..d7db1ada2dad 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -164,16 +164,28 @@ static void bpf_local_storage_free(struct bpf_local_storage *local_storage, bpf_local_storage_free_trace_rcu); } -/* rcu tasks trace callback for use_kmalloc_nolock == false */ -static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) +/* rcu callback for use_kmalloc_nolock == false */ +static void __bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + /* bpf_selem_unlink_nofail may have already cleared smap and freed fields. */ + smap = rcu_dereference_check(SDATA(selem)->smap, 1); + + if (smap) + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + kfree(selem); +} + +/* rcu tasks trace callback for use_kmalloc_nolock == false */ +static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) +{ if (rcu_trace_implies_rcu_gp()) - kfree(selem); + __bpf_selem_free_rcu(rcu); else - kfree_rcu(selem, rcu); + call_rcu(rcu, __bpf_selem_free_rcu); } /* Handle use_kmalloc_nolock == false */ @@ -181,7 +193,7 @@ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, bool vanilla_rcu) { if (vanilla_rcu) - kfree_rcu(selem, rcu); + call_rcu(&selem->rcu, __bpf_selem_free_rcu); else call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); } @@ -195,11 +207,8 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); - if (smap) { - migrate_disable(); + if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); - migrate_enable(); - } kfree_nolock(selem); } @@ -214,18 +223,12 @@ static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) void bpf_selem_free(struct bpf_local_storage_elem *selem, bool reuse_now) { - struct bpf_local_storage_map *smap; - - smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); - if (!selem->use_kmalloc_nolock) { /* * No uptr will be unpin even when reuse_now == false since uptr * is only supported in task local storage, where * smap->use_kmalloc_nolock == true. */ - if (smap) - bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); __bpf_selem_free(selem, reuse_now); return; } @@ -958,10 +961,9 @@ restart: */ synchronize_rcu(); - if (smap->use_kmalloc_nolock) { - rcu_barrier_tasks_trace(); - rcu_barrier(); - } + /* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */ + rcu_barrier_tasks_trace(); + rcu_barrier(); kvfree(smap->buckets); bpf_map_area_free(smap); } -- cgit v1.2.3 From baa35b3cb6b642b903162aacff13181e170c4ecc Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:04 -0800 Subject: bpf: Retire rcu_trace_implies_rcu_gp() from local storage This assumption will always hold going forward, hence just remove the various checks and assume it is true with a comment for the uninformed reader. Reviewed-by: Paul E. McKenney Reviewed-by: Amery Hung Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/bpf_local_storage.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index d7db1ada2dad..9c96a4477f81 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -107,14 +107,12 @@ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; - /* If RCU Tasks Trace grace period implies RCU grace period, do - * kfree(), else do kfree_rcu(). + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); - if (rcu_trace_implies_rcu_gp()) - kfree(local_storage); - else - kfree_rcu(local_storage, rcu); + kfree(local_storage); } /* Handle use_kmalloc_nolock == false */ @@ -138,10 +136,11 @@ static void bpf_local_storage_free_rcu(struct rcu_head *rcu) static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { - if (rcu_trace_implies_rcu_gp()) - bpf_local_storage_free_rcu(rcu); - else - call_rcu(rcu, bpf_local_storage_free_rcu); + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + bpf_local_storage_free_rcu(rcu); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, @@ -182,10 +181,11 @@ static void __bpf_selem_free_rcu(struct rcu_head *rcu) /* rcu tasks trace callback for use_kmalloc_nolock == false */ static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { - if (rcu_trace_implies_rcu_gp()) - __bpf_selem_free_rcu(rcu); - else - call_rcu(rcu, __bpf_selem_free_rcu); + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + __bpf_selem_free_rcu(rcu); } /* Handle use_kmalloc_nolock == false */ @@ -214,10 +214,11 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { - if (rcu_trace_implies_rcu_gp()) - bpf_selem_free_rcu(rcu); - else - call_rcu(rcu, bpf_selem_free_rcu); + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + bpf_selem_free_rcu(rcu); } void bpf_selem_free(struct bpf_local_storage_elem *selem, -- cgit v1.2.3 From 869c63d5975d55e97f6b168e885452b3da20ea47 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 25 Feb 2026 20:14:55 +0800 Subject: bpf: Fix race in cpumap on PREEMPT_RT On PREEMPT_RT kernels, the per-CPU xdp_bulk_queue (bq) can be accessed concurrently by multiple preemptible tasks on the same CPU. The original code assumes bq_enqueue() and __cpu_map_flush() run atomically with respect to each other on the same CPU, relying on local_bh_disable() to prevent preemption. However, on PREEMPT_RT, local_bh_disable() only calls migrate_disable() (when PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable preemption, which allows CFS scheduling to preempt a task during bq_flush_to_queue(), enabling another task on the same CPU to enter bq_enqueue() and operate on the same per-CPU bq concurrently. This leads to several races: 1. Double __list_del_clearprev(): after bq->count is reset in bq_flush_to_queue(), a preempting task can call bq_enqueue() -> bq_flush_to_queue() on the same bq when bq->count reaches CPU_MAP_BULK_SIZE. Both tasks then call __list_del_clearprev() on the same bq->flush_node, the second call dereferences the prev pointer that was already set to NULL by the first. 2. bq->count and bq->q[] races: concurrent bq_enqueue() can corrupt the packet queue while bq_flush_to_queue() is processing it. The race between task A (__cpu_map_flush -> bq_flush_to_queue) and task B (bq_enqueue -> bq_flush_to_queue) on the same CPU: Task A (xdp_do_flush) Task B (cpu_map_enqueue) ---------------------- ------------------------ bq_flush_to_queue(bq) spin_lock(&q->producer_lock) /* flush bq->q[] to ptr_ring */ bq->count = 0 spin_unlock(&q->producer_lock) bq_enqueue(rcpu, xdpf) <-- CFS preempts Task A --> bq->q[bq->count++] = xdpf /* ... more enqueues until full ... */ bq_flush_to_queue(bq) spin_lock(&q->producer_lock) /* flush to ptr_ring */ spin_unlock(&q->producer_lock) __list_del_clearprev(flush_node) /* sets flush_node.prev = NULL */ <-- Task A resumes --> __list_del_clearprev(flush_node) flush_node.prev->next = ... /* prev is NULL -> kernel oops */ Fix this by adding a local_lock_t to xdp_bulk_queue and acquiring it in bq_enqueue() and __cpu_map_flush(). These paths already run under local_bh_disable(), so use local_lock_nested_bh() which on non-RT is a pure annotation with no overhead, and on PREEMPT_RT provides a per-CPU sleeping lock that serializes access to the bq. To reproduce, insert an mdelay(100) between bq->count = 0 and __list_del_clearprev() in bq_flush_to_queue(), then run reproducer provided by syzkaller. Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT") Reported-by: syzbot+2b3391f44313b3983e91@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/69369331.a70a0220.38f243.009d.GAE@google.com/T/ Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Jiayuan Chen Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260225121459.183121-2-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/cpumap.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 04171fbc39cb..32b43cb9061b 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -52,6 +53,7 @@ struct xdp_bulk_queue { struct list_head flush_node; struct bpf_cpu_map_entry *obj; unsigned int count; + local_lock_t bq_lock; }; /* Struct for every remote "destination" CPU in map */ @@ -451,6 +453,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, for_each_possible_cpu(i) { bq = per_cpu_ptr(rcpu->bulkq, i); bq->obj = rcpu; + local_lock_init(&bq->bq_lock); } /* Alloc queue */ @@ -722,6 +725,8 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) struct ptr_ring *q; int i; + lockdep_assert_held(&bq->bq_lock); + if (unlikely(!bq->count)) return; @@ -749,11 +754,15 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) } /* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. + * Thus, safe percpu variable access. PREEMPT_RT relies on + * local_lock_nested_bh() to serialise access to the per-CPU bq. */ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + struct xdp_bulk_queue *bq; + + local_lock_nested_bh(&rcpu->bulkq->bq_lock); + bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) bq_flush_to_queue(bq); @@ -774,6 +783,8 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) list_add(&bq->flush_node, flush_list); } + + local_unlock_nested_bh(&rcpu->bulkq->bq_lock); } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, @@ -810,7 +821,9 @@ void __cpu_map_flush(struct list_head *flush_list) struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + local_lock_nested_bh(&bq->obj->bulkq->bq_lock); bq_flush_to_queue(bq); + local_unlock_nested_bh(&bq->obj->bulkq->bq_lock); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(bq->obj->kthread); -- cgit v1.2.3 From 1872e75375c40add4a35990de3be77b5741c252c Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Wed, 25 Feb 2026 20:14:56 +0800 Subject: bpf: Fix race in devmap on PREEMPT_RT On PREEMPT_RT kernels, the per-CPU xdp_dev_bulk_queue (bq) can be accessed concurrently by multiple preemptible tasks on the same CPU. The original code assumes bq_enqueue() and __dev_flush() run atomically with respect to each other on the same CPU, relying on local_bh_disable() to prevent preemption. However, on PREEMPT_RT, local_bh_disable() only calls migrate_disable() (when PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable preemption, which allows CFS scheduling to preempt a task during bq_xmit_all(), enabling another task on the same CPU to enter bq_enqueue() and operate on the same per-CPU bq concurrently. This leads to several races: 1. Double-free / use-after-free on bq->q[]: bq_xmit_all() snapshots cnt = bq->count, then iterates bq->q[0..cnt-1] to transmit frames. If preempted after the snapshot, a second task can call bq_enqueue() -> bq_xmit_all() on the same bq, transmitting (and freeing) the same frames. When the first task resumes, it operates on stale pointers in bq->q[], causing use-after-free. 2. bq->count and bq->q[] corruption: concurrent bq_enqueue() modifying bq->count and bq->q[] while bq_xmit_all() is reading them. 3. dev_rx/xdp_prog teardown race: __dev_flush() clears bq->dev_rx and bq->xdp_prog after bq_xmit_all(). If preempted between bq_xmit_all() return and bq->dev_rx = NULL, a preempting bq_enqueue() sees dev_rx still set (non-NULL), skips adding bq to the flush_list, and enqueues a frame. When __dev_flush() resumes, it clears dev_rx and removes bq from the flush_list, orphaning the newly enqueued frame. 4. __list_del_clearprev() on flush_node: similar to the cpumap race, both tasks can call __list_del_clearprev() on the same flush_node, the second dereferences the prev pointer already set to NULL. The race between task A (__dev_flush -> bq_xmit_all) and task B (bq_enqueue -> bq_xmit_all) on the same CPU: Task A (xdp_do_flush) Task B (ndo_xdp_xmit redirect) ---------------------- -------------------------------- __dev_flush(flush_list) bq_xmit_all(bq) cnt = bq->count /* e.g. 16 */ /* start iterating bq->q[] */ <-- CFS preempts Task A --> bq_enqueue(dev, xdpf) bq->count == DEV_MAP_BULK_SIZE bq_xmit_all(bq, 0) cnt = bq->count /* same 16! */ ndo_xdp_xmit(bq->q[]) /* frames freed by driver */ bq->count = 0 <-- Task A resumes --> ndo_xdp_xmit(bq->q[]) /* use-after-free: frames already freed! */ Fix this by adding a local_lock_t to xdp_dev_bulk_queue and acquiring it in bq_enqueue() and __dev_flush(). These paths already run under local_bh_disable(), so use local_lock_nested_bh() which on non-RT is a pure annotation with no overhead, and on PREEMPT_RT provides a per-CPU sleeping lock that serializes access to the bq. Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT") Reported-by: Sebastian Andrzej Siewior Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Jiayuan Chen Signed-off-by: Jiayuan Chen Link: https://lore.kernel.org/r/20260225121459.183121-3-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov --- kernel/bpf/devmap.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2984e938f94d..3d619d01088e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -45,6 +45,7 @@ * types of devmap; only the lookup and insertion is different. */ #include +#include #include #include #include @@ -60,6 +61,7 @@ struct xdp_dev_bulk_queue { struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; + local_lock_t bq_lock; }; struct bpf_dtab_netdev { @@ -381,6 +383,8 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) int to_send = cnt; int i; + lockdep_assert_held(&bq->bq_lock); + if (unlikely(!cnt)) return; @@ -425,10 +429,12 @@ void __dev_flush(struct list_head *flush_list) struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + local_lock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); + local_unlock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); } } @@ -451,12 +457,16 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above - * xdp_do_flush() in filter.c. + * xdp_do_flush() in filter.c. PREEMPT_RT relies on local_lock_nested_bh() + * to serialise access to the per-CPU bq. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); + struct xdp_dev_bulk_queue *bq; + + local_lock_nested_bh(&dev->xdp_bulkq->bq_lock); + bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); @@ -477,6 +487,8 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, } bq->q[bq->count++] = xdpf; + + local_unlock_nested_bh(&dev->xdp_bulkq->bq_lock); } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, @@ -1127,8 +1139,13 @@ static int dev_map_notification(struct notifier_block *notifier, if (!netdev->xdp_bulkq) return NOTIFY_BAD; - for_each_possible_cpu(cpu) - per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + for_each_possible_cpu(cpu) { + struct xdp_dev_bulk_queue *bq; + + bq = per_cpu_ptr(netdev->xdp_bulkq, cpu); + bq->dev = netdev; + local_lock_init(&bq->bq_lock); + } break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because -- cgit v1.2.3 From 76e954155b45294c502e3d3a9e15757c858ca55e Mon Sep 17 00:00:00 2001 From: Harishankar Vishwanathan Date: Fri, 27 Feb 2026 22:32:21 +0100 Subject: bpf: Introduce tnum_step to step through tnum's members This commit introduces tnum_step(), a function that, when given t, and a number z returns the smallest member of t larger than z. The number z must be greater or equal to the smallest member of t and less than the largest member of t. The first step is to compute j, a number that keeps all of t's known bits, and matches all unknown bits to z's bits. Since j is a member of the t, it is already a candidate for result. However, we want our result to be (minimally) greater than z. There are only two possible cases: (1) Case j <= z. In this case, we want to increase the value of j and make it > z. (2) Case j > z. In this case, we want to decrease the value of j while keeping it > z. (Case 1) j <= z t = xx11x0x0 z = 10111101 (189) j = 10111000 (184) ^ k (Case 1.1) Let's first consider the case where j < z. We will address j == z later. Since z > j, there had to be a bit position that was 1 in z and a 0 in j, beyond which all positions of higher significance are equal in j and z. Further, this position could not have been unknown in a, because the unknown positions of a match z. This position had to be a 1 in z and known 0 in t. Let k be position of the most significant 1-to-0 flip. In our example, k = 3 (starting the count at 1 at the least significant bit). Setting (to 1) the unknown bits of t in positions of significance smaller than k will not produce a result > z. Hence, we must set/unset the unknown bits at positions of significance higher than k. Specifically, we look for the next larger combination of 1s and 0s to place in those positions, relative to the combination that exists in z. We can achieve this by concatenating bits at unknown positions of t into an integer, adding 1, and writing the bits of that result back into the corresponding bit positions previously extracted from z. >From our example, considering only positions of significance greater than k: t = xx..x z = 10..1 + 1 ----- 11..0 This is the exact combination 1s and 0s we need at the unknown bits of t in positions of significance greater than k. Further, our result must only increase the value minimally above z. Hence, unknown bits in positions of significance smaller than k should remain 0. We finally have, result = 11110000 (240) (Case 1.2) Now consider the case when j = z, for example t = 1x1x0xxx z = 10110100 (180) j = 10110100 (180) Matching the unknown bits of the t to the bits of z yielded exactly z. To produce a number greater than z, we must set/unset the unknown bits in t, and *all* the unknown bits of t candidates for being set/unset. We can do this similar to Case 1.1, by adding 1 to the bits extracted from the masked bit positions of z. Essentially, this case is equivalent to Case 1.1, with k = 0. t = 1x1x0xxx z = .0.1.100 + 1 --------- .0.1.101 This is the exact combination of bits needed in the unknown positions of t. After recalling the known positions of t, we get result = 10110101 (181) (Case 2) j > z t = x00010x1 z = 10000010 (130) j = 10001011 (139) ^ k Since j > z, there had to be a bit position which was 0 in z, and a 1 in j, beyond which all positions of higher significance are equal in j and z. This position had to be a 0 in z and known 1 in t. Let k be the position of the most significant 0-to-1 flip. In our example, k = 4. Because of the 0-to-1 flip at position k, a member of t can become greater than z if the bits in positions greater than k are themselves >= to z. To make that member *minimally* greater than z, the bits in positions greater than k must be exactly = z. Hence, we simply match all of t's unknown bits in positions more significant than k to z's bits. In positions less significant than k, we set all t's unknown bits to 0 to retain minimality. In our example, in positions of greater significance than k (=4), t=x000. These positions are matched with z (1000) to produce 1000. In positions of lower significance than k, t=10x1. All unknown bits are set to 0 to produce 1001. The final result is: result = 10001001 (137) This concludes the computation for a result > z that is a member of t. The procedure for tnum_step() in this commit implements the idea described above. As a proof of correctness, we verified the algorithm against a logical specification of tnum_step. The specification asserts the following about the inputs t, z and output res that: 1. res is a member of t, and 2. res is strictly greater than z, and 3. there does not exist another value res2 such that 3a. res2 is also a member of t, and 3b. res2 is greater than z 3c. res2 is smaller than res We checked the implementation against this logical specification using an SMT solver. The verification formula in SMTLIB format is available at [1]. The verification returned an "unsat": indicating that no input assignment exists for which the implementation and the specification produce different outputs. In addition, we also automatically generated the logical encoding of the C implementation using Agni [2] and verified it against the same specification. This verification also returned an "unsat", confirming that the implementation is equivalent to the specification. The formula for this check is also available at [3]. Link: https://pastebin.com/raw/2eRWbiit [1] Link: https://github.com/bpfverif/agni [2] Link: https://pastebin.com/raw/EztVbBJ2 [3] Co-developed-by: Srinivas Narayana Signed-off-by: Srinivas Narayana Co-developed-by: Santosh Nagarakatte Signed-off-by: Santosh Nagarakatte Signed-off-by: Harishankar Vishwanathan Link: https://lore.kernel.org/r/93fdf71910411c0f19e282ba6d03b4c65f9c5d73.1772225741.git.paul.chaignon@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/tnum.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 26fbfbb01700..4abc359b3db0 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -269,3 +269,59 @@ struct tnum tnum_bswap64(struct tnum a) { return TNUM(swab64(a.value), swab64(a.mask)); } + +/* Given tnum t, and a number z such that tmin <= z < tmax, where tmin + * is the smallest member of the t (= t.value) and tmax is the largest + * member of t (= t.value | t.mask), returns the smallest member of t + * larger than z. + * + * For example, + * t = x11100x0 + * z = 11110001 (241) + * result = 11110010 (242) + * + * Note: if this function is called with z >= tmax, it just returns + * early with tmax; if this function is called with z < tmin, the + * algorithm already returns tmin. + */ +u64 tnum_step(struct tnum t, u64 z) +{ + u64 tmax, j, p, q, r, s, v, u, w, res; + u8 k; + + tmax = t.value | t.mask; + + /* if z >= largest member of t, return largest member of t */ + if (z >= tmax) + return tmax; + + /* if z < smallest member of t, return smallest member of t */ + if (z < t.value) + return t.value; + + /* keep t's known bits, and match all unknown bits to z */ + j = t.value | (z & t.mask); + + if (j > z) { + p = ~z & t.value & ~t.mask; + k = fls64(p); /* k is the most-significant 0-to-1 flip */ + q = U64_MAX << k; + r = q & z; /* positions > k matched to z */ + s = ~q & t.value; /* positions <= k matched to t.value */ + v = r | s; + res = v; + } else { + p = z & ~t.value & ~t.mask; + k = fls64(p); /* k is the most-significant 1-to-0 flip */ + q = U64_MAX << k; + r = q & t.mask & z; /* unknown positions > k, matched to z */ + s = q & ~t.mask; /* known positions > k, set to 1 */ + v = r | s; + /* add 1 to unknown positions > k to make value greater than z */ + u = v + (1ULL << k); + /* extract bits in unknown positions > k from u, rest from t.value */ + w = (u & t.mask) | t.value; + res = w; + } + return res; +} -- cgit v1.2.3 From efc11a667878a1d655ff034a93a539debbfedb12 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Fri, 27 Feb 2026 22:35:02 +0100 Subject: bpf: Improve bounds when tnum has a single possible value We're hitting an invariant violation in Cilium that sometimes leads to BPF programs being rejected and Cilium failing to start [1]. The following extract from verifier logs shows what's happening: from 201 to 236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0 236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0 ; if (magic == MARK_MAGIC_HOST || magic == MARK_MAGIC_OVERLAY || magic == MARK_MAGIC_ENCRYPT) @ bpf_host.c:1337 236: (16) if w9 == 0xe00 goto pc+45 ; R9=scalar(smin=umin=smin32=umin32=3585,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) 237: (16) if w9 == 0xf00 goto pc+1 verifier bug: REG INVARIANTS VIOLATION (false_reg1): range bounds violation u64=[0xe01, 0xe00] s64=[0xe01, 0xe00] u32=[0xe01, 0xe00] s32=[0xe01, 0xe00] var_off=(0xe00, 0x0) We reach instruction 236 with two possible values for R9, 0xe00 and 0xf00. This is perfectly reflected in the tnum, but of course the ranges are less accurate and cover [0xe00; 0xf00]. Taking the fallthrough path at instruction 236 allows the verifier to reduce the range to [0xe01; 0xf00]. The tnum is however not updated. With these ranges, at instruction 237, the verifier is not able to deduce that R9 is always equal to 0xf00. Hence the fallthrough pass is explored first, the verifier refines the bounds using the assumption that R9 != 0xf00, and ends up with an invariant violation. This pattern of impossible branch + bounds refinement is common to all invariant violations seen so far. The long-term solution is likely to rely on the refinement + invariant violation check to detect dead branches, as started by Eduard. To fix the current issue, we need something with less refactoring that we can backport. This patch uses the tnum_step helper introduced in the previous patch to detect the above situation. In particular, three cases are now detected in the bounds refinement: 1. The u64 range and the tnum only overlap in umin. u64: ---[xxxxxx]----- tnum: --xx----------x- 2. The u64 range and the tnum only overlap in the maximum value represented by the tnum, called tmax. u64: ---[xxxxxx]----- tnum: xx-----x-------- 3. The u64 range and the tnum only overlap in between umin (excluded) and umax. u64: ---[xxxxxx]----- tnum: xx----x-------x- To detect these three cases, we call tnum_step(tnum, umin), which returns the smallest member of the tnum greater than umin, called tnum_next here. We're in case (1) if umin is part of the tnum and tnum_next is greater than umax. We're in case (2) if umin is not part of the tnum and tnum_next is equal to tmax. Finally, we're in case (3) if umin is not part of the tnum, tnum_next is inferior or equal to umax, and calling tnum_step a second time gives us a value past umax. This change implements these three cases. With it, the above bytecode looks as follows: 0: (85) call bpf_get_prandom_u32#7 ; R0=scalar() 1: (47) r0 |= 3584 ; R0=scalar(smin=0x8000000000000e00,umin=umin32=3584,smin32=0x80000e00,var_off=(0xe00; 0xfffffffffffff1ff)) 2: (57) r0 &= 3840 ; R0=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) 3: (15) if r0 == 0xe00 goto pc+2 ; R0=3840 4: (15) if r0 == 0xf00 goto pc+1 4: R0=3840 6: (95) exit In addition to the new selftests, this change was also verified with Agni [3]. For the record, the raw SMT is available at [4]. The property it verifies is that: If a concrete value x is contained in all input abstract values, after __update_reg_bounds, it will continue to be contained in all output abstract values. Link: https://github.com/cilium/cilium/issues/44216 [1] Link: https://pchaigno.github.io/test-verifier-complexity.html [2] Link: https://github.com/bpfverif/agni [3] Link: https://pastebin.com/raw/naCfaqNx [4] Fixes: 0df1a55afa83 ("bpf: Warn on internal verifier errors") Acked-by: Eduard Zingerman Tested-by: Marco Schirrmeister Co-developed-by: Harishankar Vishwanathan Signed-off-by: Harishankar Vishwanathan Signed-off-by: Paul Chaignon Link: https://lore.kernel.org/r/ef254c4f68be19bd393d450188946821c588565d.1772225741.git.paul.chaignon@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bb12ba020649..401d6c4960ec 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2379,6 +2379,9 @@ static void __update_reg32_bounds(struct bpf_reg_state *reg) static void __update_reg64_bounds(struct bpf_reg_state *reg) { + u64 tnum_next, tmax; + bool umin_in_tnum; + /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); @@ -2388,6 +2391,33 @@ static void __update_reg64_bounds(struct bpf_reg_state *reg) reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); + + /* Check if u64 and tnum overlap in a single value */ + tnum_next = tnum_step(reg->var_off, reg->umin_value); + umin_in_tnum = (reg->umin_value & ~reg->var_off.mask) == reg->var_off.value; + tmax = reg->var_off.value | reg->var_off.mask; + if (umin_in_tnum && tnum_next > reg->umax_value) { + /* The u64 range and the tnum only overlap in umin. + * u64: ---[xxxxxx]----- + * tnum: --xx----------x- + */ + ___mark_reg_known(reg, reg->umin_value); + } else if (!umin_in_tnum && tnum_next == tmax) { + /* The u64 range and the tnum only overlap in the maximum value + * represented by the tnum, called tmax. + * u64: ---[xxxxxx]----- + * tnum: xx-----x-------- + */ + ___mark_reg_known(reg, tmax); + } else if (!umin_in_tnum && tnum_next <= reg->umax_value && + tnum_step(reg->var_off, tnum_next) > reg->umax_value) { + /* The u64 range and the tnum only overlap in between umin + * (excluded) and umax. + * u64: ---[xxxxxx]----- + * tnum: xx----x-------x- + */ + ___mark_reg_known(reg, tnum_next); + } } static void __update_reg_bounds(struct bpf_reg_state *reg) -- cgit v1.2.3 From da46b5dfef48658d03347cda21532bcdbb521e67 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 1 Mar 2026 16:22:07 -0800 Subject: blktrace: fix __this_cpu_read/write in preemptible context tracing_record_cmdline() internally uses __this_cpu_read() and __this_cpu_write() on the per-CPU variable trace_cmdline_save, and trace_save_cmdline() explicitly asserts preemption is disabled via lockdep_assert_preemption_disabled(). These operations are only safe when preemption is off, as they were designed to be called from the scheduler context (probe_wakeup_sched_switch() / probe_wakeup()). __blk_add_trace() was calling tracing_record_cmdline(current) early in the blk_tracer path, before ring buffer reservation, from process context where preemption is fully enabled. This triggers the following using blktests/blktrace/002: blktrace/002 (blktrace ftrace corruption with sysfs trace) [failed] runtime 0.367s ... 0.437s something found in dmesg: [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] [ 81.362886] dump_stack_lvl+0x8d/0xb0 ... (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message) [ 81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33 [ 81.239580] null_blk: disk nullb1 created [ 81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516 [ 81.362842] caller is tracing_record_cmdline+0x10/0x40 [ 81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G N 7.0.0-rc1lblk+ #84 PREEMPT(full) [ 81.362877] Tainted: [N]=TEST [ 81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014 [ 81.362881] Call Trace: [ 81.362884] [ 81.362886] dump_stack_lvl+0x8d/0xb0 [ 81.362895] check_preemption_disabled+0xce/0xe0 [ 81.362902] tracing_record_cmdline+0x10/0x40 [ 81.362923] __blk_add_trace+0x307/0x5d0 [ 81.362934] ? lock_acquire+0xe0/0x300 [ 81.362940] ? iov_iter_extract_pages+0x101/0xa30 [ 81.362959] blk_add_trace_bio+0x106/0x1e0 [ 81.362968] submit_bio_noacct_nocheck+0x24b/0x3a0 [ 81.362979] ? lockdep_init_map_type+0x58/0x260 [ 81.362988] submit_bio_wait+0x56/0x90 [ 81.363009] __blkdev_direct_IO_simple+0x16c/0x250 [ 81.363026] ? __pfx_submit_bio_wait_endio+0x10/0x10 [ 81.363038] ? rcu_read_lock_any_held+0x73/0xa0 [ 81.363051] blkdev_read_iter+0xc1/0x140 [ 81.363059] vfs_read+0x20b/0x330 [ 81.363083] ksys_read+0x67/0xe0 [ 81.363090] do_syscall_64+0xbf/0xf00 [ 81.363102] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 81.363106] RIP: 0033:0x7f281906029d [ 81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec [ 81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d [ 81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000 [ 81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000 [ 81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000 [ 81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a [ 81.363142] The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(), and blk_add_trace_rq() paths as well. The purpose of tracing_record_cmdline() is to cache the task->comm for a given PID so that the trace can later resolve it. It is only meaningful when a trace event is actually being recorded. Ring buffer reservation via ring_buffer_lock_reserve() disables preemption, and preemption remains disabled until the event is committed :- __blk_add_trace() __trace_buffer_lock_reserve() __trace_buffer_lock_reserve() ring_buffer_lock_reserve() preempt_disable_notrace(); <--- With this fix blktests for blktrace pass: blktests (master) # ./check blktrace blktrace/001 (blktrace zone management command tracing) [passed] runtime 3.650s ... 3.647s blktrace/002 (blktrace ftrace corruption with sysfs trace) [passed] runtime 0.411s ... 0.384s Fixes: 7ffbd48d5cab ("tracing: Cache comms only after an event occurred") Reported-by: Shinichiro Kawasaki Suggested-by: Steven Rostedt Signed-off-by: Chaitanya Kulkarni Reviewed-by: Steven Rostedt (Google) Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index e6988929ead2..18a9b84cc768 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -383,8 +383,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, cpu = raw_smp_processor_id(); if (blk_tracer) { - tracing_record_cmdline(current); - buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); switch (bt->version) { @@ -419,6 +417,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (!event) return; + tracing_record_cmdline(current); switch (bt->version) { case 1: record_blktrace_event(ring_buffer_event_data(event), -- cgit v1.2.3 From 9adfcef334bf9c6ef68eaecfca5f45d18614efe0 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Mon, 2 Mar 2026 17:14:39 +0800 Subject: sched_ext: Use READ_ONCE() for the read side of dsq->nr update scx_bpf_dsq_nr_queued() reads dsq->nr via READ_ONCE() without holding any lock, making dsq->nr a lock-free concurrently accessed variable. However, dsq_mod_nr(), the sole writer of dsq->nr, only uses WRITE_ONCE() on the write side without the matching READ_ONCE() on the read side: WRITE_ONCE(dsq->nr, dsq->nr + delta); ^^^^^^^ plain read -- KCSAN data race The KCSAN documentation requires that if one accessor uses READ_ONCE() or WRITE_ONCE() on a variable to annotate lock-free access, all other accesses must also use the appropriate accessor. A plain read on the right-hand side of WRITE_ONCE() leaves the pair incomplete and will trigger KCSAN warnings. Fix by using READ_ONCE() for the read side of the update: WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta); This is consistent with scx_bpf_dsq_nr_queued() and makes the concurrent access annotation complete and KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 9280381f8923..4c2cf0d7d495 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -976,8 +976,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a, static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) { - /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ - WRITE_ONCE(dsq->nr, dsq->nr + delta); + /* + * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE() + * on the read side and WRITE_ONCE() on the write side to properly + * annotate the concurrent lockless access and avoid KCSAN warnings. + */ + WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta); } static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p) -- cgit v1.2.3 From 494eaf4651975127d34d5ae6555c72dedba092c9 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Mon, 2 Mar 2026 17:14:40 +0800 Subject: sched_ext: Replace naked scx_root dereferences in kobject callbacks scx_attr_ops_show() and scx_uevent() access scx_root->ops.name directly. This is problematic for two reasons: 1. The file-level comment explicitly identifies naked scx_root dereferences as a temporary measure that needs to be replaced with proper per-instance access. 2. scx_attr_events_show(), the neighboring sysfs show function in the same group, already uses the correct pattern: struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); Having inconsistent access patterns in the same sysfs/uevent group is error-prone. The kobject embedded in struct scx_sched is initialized as: kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); so container_of(kobj, struct scx_sched, kobj) correctly retrieves the owning scx_sched instance in both callbacks. Replace the naked scx_root dereferences with container_of()-based access, consistent with scx_attr_events_show() and in preparation for proper multi-instance scx_sched support. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 4c2cf0d7d495..a566d2cc8a43 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3712,7 +3712,9 @@ static void scx_kobj_release(struct kobject *kobj) static ssize_t scx_attr_ops_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { - return sysfs_emit(buf, "%s\n", scx_root->ops.name); + struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return sysfs_emit(buf, "%s\n", sch->ops.name); } SCX_ATTR(ops); @@ -3756,7 +3758,9 @@ static const struct kobj_type scx_ktype = { static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name); + const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return add_uevent_var(env, "SCXOPS=%s", sch->ops.name); } static const struct kset_uevent_ops scx_uevent_ops = { -- cgit v1.2.3 From 3ebc98c1ae7efda949a015990280a097f4a5453a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 2 Mar 2026 09:16:22 +0100 Subject: ftrace: Add missing ftrace_lock to update_ftrace_direct_add/del Ihor and Kumar reported splat from ftrace_get_addr_curr [1], which happened because of the missing ftrace_lock in update_ftrace_direct_add/del functions allowing concurrent access to ftrace internals. The ftrace_update_ops function must be guarded by ftrace_lock, adding that. Fixes: 05dc5e9c1fe1 ("ftrace: Add update_ftrace_direct_add function") Fixes: 8d2c1233f371 ("ftrace: Add update_ftrace_direct_del function") Reported-by: Ihor Solodrai Reported-by: Kumar Kartikeya Dwivedi Closes: https://lore.kernel.org/bpf/1b58ffb2-92ae-433a-ba46-95294d6edea2@linux.dev/ Tested-by: Ihor Solodrai Signed-off-by: Jiri Olsa Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20260302081622.165713-1-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 827fb9a0bf0d..8baf61c9be6d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6404,6 +6404,7 @@ int update_ftrace_direct_add(struct ftrace_ops *ops, struct ftrace_hash *hash) new_filter_hash = old_filter_hash; } } else { + guard(mutex)(&ftrace_lock); err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); /* * new_filter_hash is dup-ed, so we need to release it anyway, @@ -6530,6 +6531,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash) ops->func_hash->filter_hash = NULL; } } else { + guard(mutex)(&ftrace_lock); err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH); /* * new_filter_hash is dup-ed, so we need to release it anyway, -- cgit v1.2.3 From 3f27958b729a2337336a6b50e0d9aee5fbbce816 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Tue, 3 Mar 2026 14:09:58 +0800 Subject: sched_ext: Use READ_ONCE() for plain reads of scx_watchdog_timeout scx_watchdog_timeout is written with WRITE_ONCE() in scx_enable(): WRITE_ONCE(scx_watchdog_timeout, timeout); However, three read-side accesses use plain reads without the matching READ_ONCE(): /* check_rq_for_timeouts() - L2824 */ last_runnable + scx_watchdog_timeout /* scx_watchdog_workfn() - L2852 */ scx_watchdog_timeout / 2 /* scx_enable() - L5179 */ scx_watchdog_timeout / 2 The KCSAN documentation requires that if one accessor uses WRITE_ONCE() to annotate lock-free access, all other accesses must also use the appropriate accessor. Plain reads alongside WRITE_ONCE() leave the pair incomplete and can trigger KCSAN warnings. Note that scx_tick() already uses the correct READ_ONCE() annotation: last_check + READ_ONCE(scx_watchdog_timeout) Fix the three remaining plain reads to match, making all accesses to scx_watchdog_timeout consistently annotated and KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index a566d2cc8a43..2ba69b302368 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2739,7 +2739,7 @@ static bool check_rq_for_timeouts(struct rq *rq) unsigned long last_runnable = p->scx.runnable_at; if (unlikely(time_after(jiffies, - last_runnable + scx_watchdog_timeout))) { + last_runnable + READ_ONCE(scx_watchdog_timeout)))) { u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable); scx_exit(sch, SCX_EXIT_ERROR_STALL, 0, @@ -2767,7 +2767,7 @@ static void scx_watchdog_workfn(struct work_struct *work) cond_resched(); } queue_delayed_work(system_unbound_wq, to_delayed_work(work), - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); } void scx_tick(struct rq *rq) @@ -5081,7 +5081,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) WRITE_ONCE(scx_watchdog_timeout, timeout); WRITE_ONCE(scx_watchdog_timestamp, jiffies); queue_delayed_work(system_unbound_wq, &scx_watchdog_work, - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); /* * Once __scx_enabled is set, %current can be switched to SCX anytime. -- cgit v1.2.3 From 1336b579f6079fb8520be03624fcd9ba443c930b Mon Sep 17 00:00:00 2001 From: Cheng-Yang Chou Date: Tue, 3 Mar 2026 22:35:30 +0800 Subject: sched_ext: Remove redundant css_put() in scx_cgroup_init() The iterator css_for_each_descendant_pre() walks the cgroup hierarchy under cgroup_lock(). It does not increment the reference counts on yielded css structs. According to the cgroup documentation, css_put() should only be used to release a reference obtained via css_get() or css_tryget_online(). Since the iterator does not use either of these to acquire a reference, calling css_put() in the error path of scx_cgroup_init() causes a refcount underflow. Remove the unbalanced css_put() to prevent a potential Use-After-Free (UAF) vulnerability. Fixes: 819513666966 ("sched_ext: Add cgroup support") Cc: stable@vger.kernel.org # v6.12+ Signed-off-by: Cheng-Yang Chou Reviewed-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 2ba69b302368..eab6e09b6442 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3589,7 +3589,6 @@ static int scx_cgroup_init(struct scx_sched *sch) ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { - css_put(css); scx_error(sch, "ops.cgroup_init() failed (%d)", ret); return ret; } -- cgit v1.2.3 From b06ccbabe2506fd70b9167a644978b049150224a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Mar 2026 01:01:15 -1000 Subject: sched_ext: Fix starvation of scx_enable() under fair-class saturation During scx_enable(), the READY -> ENABLED task switching loop changes the calling thread's sched_class from fair to ext. Since fair has higher priority than ext, saturating fair-class workloads can indefinitely starve the enable thread, hanging the system. This was introduced when the enable path switched from preempt_disable() to scx_bypass() which doesn't protect against fair-class starvation. Note that the original preempt_disable() protection wasn't complete either - in partial switch modes, the calling thread could still be starved after preempt_enable() as it may have been switched to ext class. Fix it by offloading the enable body to a dedicated system-wide RT (SCHED_FIFO) kthread which cannot be starved by either fair or ext class tasks. scx_enable() lazily creates the kthread on first use and passes the ops pointer through a struct scx_enable_cmd containing the kthread_work, then synchronously waits for completion. The workfn runs on a different kthread from sch->helper (which runs disable_work), so it can safely flush disable_work on the error path without deadlock. Fixes: 8c2090c504e9 ("sched_ext: Initialize in bypass mode") Cc: stable@vger.kernel.org # v6.12+ Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 66 +++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 56 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index eab6e09b6442..ba51969718f5 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4975,20 +4975,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops) return 0; } -static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +/* + * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid + * starvation. During the READY -> ENABLED task switching loop, the calling + * thread's sched_class gets switched from fair to ext. As fair has higher + * priority than ext, the calling thread can be indefinitely starved under + * fair-class saturation, leading to a system hang. + */ +struct scx_enable_cmd { + struct kthread_work work; + struct sched_ext_ops *ops; + int ret; +}; + +static void scx_enable_workfn(struct kthread_work *work) { + struct scx_enable_cmd *cmd = + container_of(work, struct scx_enable_cmd, work); + struct sched_ext_ops *ops = cmd->ops; struct scx_sched *sch; struct scx_task_iter sti; struct task_struct *p; unsigned long timeout; int i, cpu, ret; - if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), - cpu_possible_mask)) { - pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); - return -EINVAL; - } - mutex_lock(&scx_enable_mutex); if (scx_enable_state() != SCX_DISABLED) { @@ -5205,13 +5215,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) atomic_long_inc(&scx_enable_seq); - return 0; + cmd->ret = 0; + return; err_free_ksyncs: free_kick_syncs(); err_unlock: mutex_unlock(&scx_enable_mutex); - return ret; + cmd->ret = ret; + return; err_disable_unlock_all: scx_cgroup_unlock(); @@ -5230,7 +5242,41 @@ err_disable: */ scx_error(sch, "scx_enable() failed (%d)", ret); kthread_flush_work(&sch->disable_work); - return 0; + cmd->ret = 0; +} + +static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +{ + static struct kthread_worker *helper; + static DEFINE_MUTEX(helper_mutex); + struct scx_enable_cmd cmd; + + if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), + cpu_possible_mask)) { + pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); + return -EINVAL; + } + + if (!READ_ONCE(helper)) { + mutex_lock(&helper_mutex); + if (!helper) { + helper = kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(helper)) { + helper = NULL; + mutex_unlock(&helper_mutex); + return -ENOMEM; + } + sched_set_fifo(helper->task); + } + mutex_unlock(&helper_mutex); + } + + kthread_init_work(&cmd.work, scx_enable_workfn); + cmd.ops = ops; + + kthread_queue_work(READ_ONCE(helper), &cmd.work); + kthread_flush_work(&cmd.work); + return cmd.ret; } -- cgit v1.2.3 From 56145d237385ca0e7ca9ff7b226aaf2eb8ef368b Mon Sep 17 00:00:00 2001 From: Lang Xu Date: Tue, 3 Mar 2026 17:52:17 +0800 Subject: bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim The root cause of this bug is that when 'bpf_link_put' reduces the refcount of 'shim_link->link.link' to zero, the resource is considered released but may still be referenced via 'tr->progs_hlist' in 'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in 'bpf_shim_tramp_link_release' is deferred. During this window, another process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'. Based on Martin KaFai Lau's suggestions, I have created a simple patch. To fix this: Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'. Only increment the refcount if it is not already zero. Testing: I verified the fix by adding a delay in 'bpf_shim_tramp_link_release' to make the bug easier to trigger: static void bpf_shim_tramp_link_release(struct bpf_link *link) { /* ... */ if (!shim_link->trampoline) return; + msleep(100); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } Before the patch, running a PoC easily reproduced the crash(almost 100%) with a call trace similar to KaiyanM's report. After the patch, the bug no longer occurs even after millions of iterations. Fixes: 69fd337a975c ("bpf: per-cgroup lsm flavor") Reported-by: Kaiyan Mei Closes: https://lore.kernel.org/bpf/3c4ebb0b.46ff8.19abab8abe2.Coremail.kaiyanm@hust.edu.cn/ Signed-off-by: Lang Xu Signed-off-by: Martin KaFai Lau Link: https://patch.msgid.link/279EEE1BA1DDB49D+20260303095217.34436-1-xulang@uniontech.com --- kernel/bpf/trampoline.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 84db9e658e52..f02254a21585 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1002,10 +1002,8 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, mutex_lock(&tr->mutex); shim_link = cgroup_shim_find(tr, bpf_func); - if (shim_link) { + if (shim_link && !IS_ERR(bpf_link_inc_not_zero(&shim_link->link.link))) { /* Reusing existing shim attached by the other program. */ - bpf_link_inc(&shim_link->link.link); - mutex_unlock(&tr->mutex); bpf_trampoline_put(tr); /* bpf_trampoline_get above */ return 0; -- cgit v1.2.3 From 6ca8379b5d36e22b04e6315c3e49a6083377c862 Mon Sep 17 00:00:00 2001 From: Shengming Hu Date: Sat, 21 Feb 2026 11:30:07 +0800 Subject: fgraph: Fix thresh_return clear per-task notrace When tracing_thresh is enabled, function graph tracing uses trace_graph_thresh_return() as the return handler. Unlike trace_graph_return(), it did not clear the per-task TRACE_GRAPH_NOTRACE flag set by the entry handler for set_graph_notrace addresses. This could leave the task permanently in "notrace" state and effectively disable function graph tracing for that task. Mirror trace_graph_return()'s per-task notrace handling by clearing TRACE_GRAPH_NOTRACE and returning early when set. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260221113007819YgrZsMGABff4Rc-O_fZxL@zte.com.cn Fixes: b84214890a9bc ("function_graph: Move graph notrace bit to shadow stack global var") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Shengming Hu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 3d8239fee004..817d0f1696b6 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -400,14 +400,15 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs) { + unsigned long *task_var = fgraph_get_task_var(gops); struct fgraph_times *ftimes; struct trace_array *tr; int size; ftrace_graph_addr_finish(gops, trace); - if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { - trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + if (*task_var & TRACE_GRAPH_NOTRACE) { + *task_var &= ~TRACE_GRAPH_NOTRACE; return; } -- cgit v1.2.3 From b96d0c59cdbb2a22b2545f6f3d5c6276b05761dd Mon Sep 17 00:00:00 2001 From: Shengming Hu Date: Sat, 21 Feb 2026 11:33:14 +0800 Subject: fgraph: Fix thresh_return nosleeptime double-adjust trace_graph_thresh_return() called handle_nosleeptime() and then delegated to trace_graph_return(), which calls handle_nosleeptime() again. When sleep-time accounting is disabled this double-adjusts calltime and can produce bogus durations (including underflow). Fix this by computing rettime once, applying handle_nosleeptime() only once, using the adjusted calltime for threshold comparison, and writing the return event directly via __trace_graph_return() when the threshold is met. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260221113314048jE4VRwIyZEALiYByGK0My@zte.com.cn Fixes: 3c9880f3ab52b ("ftrace: Use a running sleeptime instead of saving on shadow stack") Acked-by: Masami Hiramatsu (Google) Signed-off-by: Shengming Hu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 817d0f1696b6..0d2d3a2ea7dd 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -403,8 +403,12 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, unsigned long *task_var = fgraph_get_task_var(gops); struct fgraph_times *ftimes; struct trace_array *tr; + unsigned int trace_ctx; + u64 calltime, rettime; int size; + rettime = trace_clock_local(); + ftrace_graph_addr_finish(gops, trace); if (*task_var & TRACE_GRAPH_NOTRACE) { @@ -419,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, tr = gops->private; handle_nosleeptime(tr, trace, ftimes, size); - if (tracing_thresh && - (trace_clock_local() - ftimes->calltime < tracing_thresh)) + calltime = ftimes->calltime; + + if (tracing_thresh && (rettime - calltime < tracing_thresh)) return; - else - trace_graph_return(trace, gops, fregs); + + trace_ctx = tracing_gen_ctx(); + __trace_graph_return(tr, trace, trace_ctx, calltime, rettime); } static struct fgraph_ops funcgraph_ops = { -- cgit v1.2.3 From 0a663b764dbdf135a126284f454c9f01f95a87d4 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Tue, 24 Feb 2026 10:35:44 +0800 Subject: tracing: Fix syscall events activation by ensuring refcount hits zero When multiple syscall events are specified in the kernel command line (e.g., trace_event=syscalls:sys_enter_openat,syscalls:sys_enter_close), they are often not captured after boot, even though they appear enabled in the tracing/set_event file. The issue stems from how syscall events are initialized. Syscall tracepoints require the global reference count (sys_tracepoint_refcount) to transition from 0 to 1 to trigger the registration of the syscall work (TIF_SYSCALL_TRACEPOINT) for tasks, including the init process (pid 1). The current implementation of early_enable_events() with disable_first=true used an interleaved sequence of "Disable A -> Enable A -> Disable B -> Enable B". If multiple syscalls are enabled, the refcount never drops to zero, preventing the 0->1 transition that triggers actual registration. Fix this by splitting early_enable_events() into two distinct phases: 1. Disable all events specified in the buffer. 2. Enable all events specified in the buffer. This ensures the refcount hits zero before re-enabling, allowing syscall events to be properly activated during early boot. The code is also refactored to use a helper function to avoid logic duplication between the disable and enable phases. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260224023544.1250787-1-hehuiwen@kylinos.cn Fixes: ce1039bd3a89 ("tracing: Fix enabling of syscall events on the command line") Signed-off-by: Huiwen He Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 52 ++++++++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9928da636c9d..9c7f26cbe171 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4668,26 +4668,22 @@ static __init int event_trace_memsetup(void) return 0; } -__init void -early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +/* + * Helper function to enable or disable a comma-separated list of events + * from the bootup buffer. + */ +static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable) { char *token; - int ret; - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; + while ((token = strsep(&buf, ","))) { if (*token) { - /* Restarting syscalls requires that we stop them first */ - if (disable_first) + if (enable) { + if (ftrace_set_clr_event(tr, token, 1)) + pr_warn("Failed to enable trace event: %s\n", token); + } else { ftrace_set_clr_event(tr, token, 0); - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); + } } /* Put back the comma to allow this to be called again */ @@ -4696,6 +4692,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first) } } +/** + * early_enable_events - enable events from the bootup buffer + * @tr: The trace array to enable the events in + * @buf: The buffer containing the comma separated list of events + * @disable_first: If true, disable all events in @buf before enabling them + * + * This function enables events from the bootup buffer. If @disable_first + * is true, it will first disable all events in the buffer before enabling + * them. + * + * For syscall events, which rely on a global refcount to register the + * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must + * ensure the refcount hits zero before re-enabling them. A simple + * "disable then enable" per-event is not enough if multiple syscalls are + * used, as the refcount will stay above zero. Thus, we need a two-phase + * approach: disable all, then enable all. + */ +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +{ + if (disable_first) + __early_set_events(tr, buf, false); + + __early_set_events(tr, buf, true); +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); -- cgit v1.2.3 From cc337974cd1084f9821179eb66f4e470d9fd2ed8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 2 Mar 2026 21:35:46 -0500 Subject: ftrace: Disable preemption in the tracepoint callbacks handling filtered pids When function trace PID filtering is enabled, the function tracer will attach a callback to the fork tracepoint as well as the exit tracepoint that will add the forked child PID to the PID filtering list as well as remove the PID that is exiting. Commit a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast") removed the disabling of preemption when calling tracepoint callbacks. The callbacks used for the PID filtering accounting depended on preemption being disabled, and now the trigger a "suspicious RCU usage" warning message. Make them explicitly disable preemption. Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260302213546.156e3e4f@gandalf.local.home Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 827fb9a0bf0d..2f72af0357e5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, self, task); @@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, NULL, task); -- cgit v1.2.3 From a5dd6f58666f22ae16b98a2177bebc3340d38fe9 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 3 Mar 2026 21:57:38 -0500 Subject: tracing: Disable preemption in the tracepoint callbacks handling filtered pids Filtering PIDs for events triggered the following during selftests: [37] event tracing - restricts events based on pid notrace filtering [ 155.874095] [ 155.874869] ============================= [ 155.876037] WARNING: suspicious RCU usage [ 155.877287] 7.0.0-rc1-00004-g8cd473a19bc7 #7 Not tainted [ 155.879263] ----------------------------- [ 155.882839] kernel/trace/trace_events.c:1057 suspicious rcu_dereference_check() usage! [ 155.889281] [ 155.889281] other info that might help us debug this: [ 155.889281] [ 155.894519] [ 155.894519] rcu_scheduler_active = 2, debug_locks = 1 [ 155.898068] no locks held by ftracetest/4364. [ 155.900524] [ 155.900524] stack backtrace: [ 155.902645] CPU: 1 UID: 0 PID: 4364 Comm: ftracetest Not tainted 7.0.0-rc1-00004-g8cd473a19bc7 #7 PREEMPT(lazy) [ 155.902648] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 155.902651] Call Trace: [ 155.902655] [ 155.902659] dump_stack_lvl+0x67/0x90 [ 155.902665] lockdep_rcu_suspicious+0x154/0x1a0 [ 155.902672] event_filter_pid_sched_process_fork+0x9a/0xd0 [ 155.902678] kernel_clone+0x367/0x3a0 [ 155.902689] __x64_sys_clone+0x116/0x140 [ 155.902696] do_syscall_64+0x158/0x460 [ 155.902700] ? entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 155.902702] ? trace_irq_disable+0x1d/0xc0 [ 155.902709] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 155.902711] RIP: 0033:0x4697c3 [ 155.902716] Code: 1f 84 00 00 00 00 00 64 48 8b 04 25 10 00 00 00 45 31 c0 31 d2 31 f6 bf 11 00 20 01 4c 8d 90 d0 02 00 00 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 89 c2 85 c0 75 2c 64 48 8b 04 25 10 00 00 [ 155.902718] RSP: 002b:00007ffc41150428 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 155.902721] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004697c3 [ 155.902722] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 155.902724] RBP: 0000000000000000 R08: 0000000000000000 R09: 000000003fccf990 [ 155.902725] R10: 000000003fccd690 R11: 0000000000000246 R12: 0000000000000001 [ 155.902726] R13: 000000003fce8103 R14: 0000000000000001 R15: 0000000000000000 [ 155.902733] [ 155.902747] The tracepoint callbacks recently were changed to allow preemption. The event PID filtering callbacks that were attached to the fork and exit tracepoints expected preemption disabled in order to access the RCU protected PID lists. Add a guard(preempt)() to protect the references to the PID list. Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260303215738.6ab275af@fedora Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast") Link: https://patch.msgid.link/20260303131706.96057f61a48a34c43ce1e396@kernel.org Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9c7f26cbe171..b7343fdfd7b0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); @@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); -- cgit v1.2.3 From e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e Mon Sep 17 00:00:00 2001 From: Qing Wang Date: Fri, 27 Feb 2026 10:58:42 +0800 Subject: tracing: Fix WARN_ON in tracing_buffers_mmap_close When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON. Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork. Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Cc: Lorenzo Stoakes Link: https://patch.msgid.link/20260227025842.1085206-1-wangqing7171@gmail.com Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer") Reported-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=3b5dd2030fe08afdf65d Tested-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com Signed-off-by: Qing Wang Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 21 +++++++++++++++++++++ kernel/trace/trace.c | 13 +++++++++++++ 2 files changed, 34 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f16f053ef77d..17d0ea0cc3e6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, return err; } +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask))) + return; + + cpu_buffer = buffer->buffers[cpu]; + + guard(mutex)(&cpu_buffer->mapping_lock); + + if (cpu_buffer->user_mapped) + __rb_inc_dec_mapped(cpu_buffer, true); + else + WARN(1, "Unexpected buffer stat, it should be mapped"); +} + int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 23de3719f495..1e7c032a72d2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; } static inline void put_snapshot_map(struct trace_array *tr) { } #endif +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +static void tracing_buffers_mmap_open(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file); +} + static void tracing_buffers_mmap_close(struct vm_area_struct *vma) { struct ftrace_buffer_info *info = vma->vm_file->private_data; @@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a } static const struct vm_operations_struct tracing_buffers_vmops = { + .open = tracing_buffers_mmap_open, .close = tracing_buffers_mmap_close, .may_split = tracing_buffers_may_split, }; -- cgit v1.2.3 From 6932256d3a3764f3a5e06e2cb8603be45b6a9fef Mon Sep 17 00:00:00 2001 From: Gerd Rausch Date: Wed, 25 Feb 2026 15:37:49 -0800 Subject: time/jiffies: Fix sysctl file error on configurations where USER_HZ < HZ Commit 2dc164a48e6fd ("sysctl: Create converter functions with two new macros") incorrectly returns error to user space when jiffies sysctl converter is used. The old overflow check got replaced with an unconditional one: + if (USER_HZ < HZ) + return -EINVAL; which will always be true on configurations with "USER_HZ < HZ". Remove the check; it is no longer needed as clock_t_to_jiffies() returns ULONG_MAX for the overflow case and proc_int_u2k_conv_uop() checks for "> INT_MAX" after conversion Fixes: 2dc164a48e6fd ("sysctl: Create converter functions with two new macros") Reported-by: Colm Harrington Signed-off-by: Gerd Rausch Signed-off-by: Joel Granados --- kernel/time/jiffies.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a5c7d15fce72..9daf8c5d9687 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies); int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ) - return -EINVAL; return proc_dointvec_conv(table, dir, buffer, lenp, ppos, do_proc_int_conv_userhz_jiffies); } -- cgit v1.2.3 From d658686a1331db3bb108ca079d76deb3208ed949 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Mon, 2 Mar 2026 16:45:40 +0100 Subject: sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting Running stress-ng --schedpolicy 0 on an RT kernel on a big machine might lead to the following WARNINGs (edited). sched: DL de-boosted task PID 22725: REPLENISH flag missing WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8 ... (running_bw underflow) Call trace: dequeue_task_dl+0x15c/0x1f8 (P) dequeue_task+0x80/0x168 deactivate_task+0x24/0x50 push_dl_task+0x264/0x2e0 dl_task_timer+0x1b0/0x228 __hrtimer_run_queues+0x188/0x378 hrtimer_interrupt+0xfc/0x260 ... The problem is that when a SCHED_DEADLINE task (lock holder) is changed to a lower priority class via sched_setscheduler(), it may fail to properly inherit the parameters of potential DEADLINE donors if it didn't already inherit them in the past (shorter deadline than donor's at that time). This might lead to bandwidth accounting corruption, as enqueue_task_dl() won't recognize the lock holder as boosted. The scenario occurs when: 1. A DEADLINE task (donor) blocks on a PI mutex held by another DEADLINE task (holder), but the holder doesn't inherit parameters (e.g., it already has a shorter deadline) 2. sched_setscheduler() changes the holder from DEADLINE to a lower class while still holding the mutex 3. The holder should now inherit DEADLINE parameters from the donor and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen Fix the issue by introducing __setscheduler_dl_pi(), which detects when a DEADLINE (proper or boosted) task gets setscheduled to a lower priority class. In case, the function makes the task inherit DEADLINE parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to ensure proper bandwidth accounting during the next enqueue operation. Fixes: 2279f540ea7d ("sched/deadline: Fix priority inheritance with multiple scheduling classes") Reported-by: Bruno Goncalves Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260302-upstream-fix-deadline-piboost-b4-v3-1-6ba32184a9e0@redhat.com --- kernel/sched/syscalls.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 6f10db3646e7..cadb0e9fe19b 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -284,6 +284,35 @@ static bool check_same_owner(struct task_struct *p) uid_eq(cred->euid, pcred->uid)); } +#ifdef CONFIG_RT_MUTEXES +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ + /* + * In case a DEADLINE task (either proper or boosted) gets + * setscheduled to a lower priority class, check if it neeeds to + * inherit parameters from a potential pi_task. In that case make + * sure replenishment happens with the next enqueue. + */ + + if (dl_prio(newprio) && !dl_policy(policy)) { + struct task_struct *pi_task = rt_mutex_get_top_task(p); + + if (pi_task) { + p->dl.pi_se = pi_task->dl.pi_se; + scope->flags |= ENQUEUE_REPLENISH; + } + } +} +#else /* !CONFIG_RT_MUTEXES */ +static inline void __setscheduler_dl_pi(int newprio, int policy, + struct task_struct *p, + struct sched_change_ctx *scope) +{ +} +#endif /* !CONFIG_RT_MUTEXES */ + #ifdef CONFIG_UCLAMP_TASK static int uclamp_validate(struct task_struct *p, @@ -655,6 +684,7 @@ change: __setscheduler_params(p, attr); p->sched_class = next_class; p->prio = newprio; + __setscheduler_dl_pi(newprio, policy, p, scope); } __setscheduler_uclamp(p, attr); -- cgit v1.2.3 From 7a8464555d2e5f038758bb19e72ab4710b79e9cd Mon Sep 17 00:00:00 2001 From: zhidao su Date: Wed, 4 Mar 2026 13:37:30 +0800 Subject: sched_ext: Use WRITE_ONCE() for the write side of dsq->seq update bpf_iter_scx_dsq_new() reads dsq->seq via READ_ONCE() without holding any lock, making dsq->seq a lock-free concurrently accessed variable. However, dispatch_enqueue(), the sole writer of dsq->seq, uses a plain increment without the matching WRITE_ONCE() on the write side: dsq->seq++; ^^^^^^^^^^^ plain write -- KCSAN data race The KCSAN documentation requires that if one accessor uses READ_ONCE() or WRITE_ONCE() on a variable to annotate lock-free access, all other accesses must also use the appropriate accessor. A plain write leaves the pair incomplete and will trigger KCSAN warnings. Fix by using WRITE_ONCE() for the write side of the update: WRITE_ONCE(dsq->seq, dsq->seq + 1); This is consistent with bpf_iter_scx_dsq_new() and makes the concurrent access annotation complete and KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 1594987d637b..c56de568ed94 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq, } /* seq records the order tasks are queued, used by BPF DSQ iterator */ - dsq->seq++; + WRITE_ONCE(dsq->seq, dsq->seq + 1); p->scx.dsq_seq = dsq->seq; dsq_mod_nr(dsq, 1); -- cgit v1.2.3 From e48a869957a70cc39b4090cd27c36a86f8db9b92 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Wed, 25 Feb 2026 09:51:35 +0100 Subject: timekeeping: Fix timex status validation for auxiliary clocks The timekeeping_validate_timex() function validates the timex status of an auxiliary system clock even when the status is not to be changed, which causes unexpected errors for applications that make read-only clock_adjtime() calls, or set some other timex fields, but without clearing the status field. Do the AUX-specific status validation only when the modes field contains ADJ_STATUS, i.e. the application is actually trying to change the status. This makes the AUX-specific clock_adjtime() behavior consistent with CLOCK_REALTIME. Fixes: 4eca49d0b621 ("timekeeping: Prepare do_adtimex() for auxiliary clocks") Signed-off-by: Miroslav Lichvar Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260225085231.276751-1-mlichvar@redhat.com --- kernel/time/timekeeping.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 91fa2003351c..c07e562ee4c1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2653,7 +2653,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux if (aux_clock) { /* Auxiliary clocks are similar to TAI and do not have leap seconds */ - if (txc->status & (STA_INS | STA_DEL)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_INS | STA_DEL)) return -EINVAL; /* No TAI offset setting */ @@ -2661,7 +2662,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux return -EINVAL; /* No PPS support either */ - if (txc->status & (STA_PPSFREQ | STA_PPSTIME)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_PPSFREQ | STA_PPSTIME)) return -EINVAL; } -- cgit v1.2.3 From 0927780c90ce551869fb692279d66387a4b66af5 Mon Sep 17 00:00:00 2001 From: zhidao su Date: Thu, 5 Mar 2026 14:18:56 +0800 Subject: sched_ext: Use READ_ONCE() for lock-free reads of module param variables bypass_lb_cpu() reads scx_bypass_lb_intv_us and scx_slice_bypass_us without holding any lock, in timer callback context where module parameter writes via sysfs can happen concurrently: min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV; ^^^^^^^^^^^^^^^^^^^^ plain read -- KCSAN data race if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us)) ^^^^^^^^^^^^^^^^^ plain read -- KCSAN data race scx_bypass_lb_intv_us already uses READ_ONCE() in scx_bypass_lb_timerfn() and scx_bypass() for its other lock-free read sites, leaving bypass_lb_cpu() inconsistent. scx_slice_bypass_us has the same lock-free access pattern in the same function. Fix both plain reads by using READ_ONCE() to complete the concurrent access annotation and make the code KCSAN-clean. Signed-off-by: zhidao su Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index c56de568ed94..10866bfb88bf 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3908,8 +3908,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq, * consider offloading iff the total queued duration is over the * threshold. */ - min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV; - if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us)) + min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV; + if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us))) return 0; raw_spin_rq_lock_irq(rq); -- cgit v1.2.3 From 70f54f61a3d52af13b72248a63e98eddf4c990ac Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Thu, 5 Mar 2026 07:29:00 +0100 Subject: sched_ext: Document task ownership state machine The task ownership state machine in sched_ext is quite hard to follow from the code alone. The interaction of ownership states, memory ordering rules and cross-CPU "lock dancing" makes the overall model subtle. Extend the documentation next to scx_ops_state to provide a more structured and self-contained description of the state transitions and their synchronization rules. The new reference should make the code easier to reason about and maintain and can help future contributors understand the overall task-ownership workflow. Signed-off-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext_internal.h | 114 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 98 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 11ebb744d893..00b450597f3e 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = { }; /* - * sched_ext_entity->ops_state + * Task Ownership State Machine (sched_ext_entity->ops_state) * - * Used to track the task ownership between the SCX core and the BPF scheduler. - * State transitions look as follows: + * The sched_ext core uses this state machine to track task ownership + * between the SCX core and the BPF scheduler. This allows the BPF + * scheduler to dispatch tasks without strict ordering requirements, while + * the SCX core safely rejects invalid dispatches. * - * NONE -> QUEUEING -> QUEUED -> DISPATCHING - * ^ | | - * | v v - * \-------------------------------/ + * State Transitions * - * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call - * sites for explanations on the conditions being waited upon and why they are - * safe. Transitions out of them into NONE or QUEUED must store_release and the - * waiters should load_acquire. + * .------------> NONE (owned by SCX core) + * | | ^ + * | enqueue | | direct dispatch + * | v | + * | QUEUEING -------' + * | | + * | enqueue | + * | completes | + * | v + * | QUEUED (owned by BPF scheduler) + * | | + * | dispatch | + * | | + * | v + * | DISPATCHING + * | | + * | dispatch | + * | completes | + * `---------------' * - * Tracking scx_ops_state enables sched_ext core to reliably determine whether - * any given task can be dispatched by the BPF scheduler at all times and thus - * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler - * to try to dispatch any task anytime regardless of its state as the SCX core - * can safely reject invalid dispatches. + * State Descriptions + * + * - %SCX_OPSS_NONE: + * Task is owned by the SCX core. It's either on a run queue, running, + * or being manipulated by the core scheduler. The BPF scheduler has no + * claim on this task. + * + * - %SCX_OPSS_QUEUEING: + * Transitional state while transferring a task from the SCX core to + * the BPF scheduler. The task's rq lock is held during this state. + * Since QUEUEING is both entered and exited under the rq lock, dequeue + * can never observe this state (it would be a BUG). When finishing a + * dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion + * path busy-waits for it to leave this state (via wait_ops_state()) + * before retrying. + * + * - %SCX_OPSS_QUEUED: + * Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue) + * and the BPF scheduler is responsible for dispatching it. A QSEQ + * (queue sequence number) is embedded in this state to detect + * dispatch/dequeue races: if a task is dequeued and re-enqueued, the + * QSEQ changes and any in-flight dispatch operations targeting the old + * QSEQ are safely ignored. + * + * - %SCX_OPSS_DISPATCHING: + * Transitional state while transferring a task from the BPF scheduler + * back to the SCX core. This state indicates the BPF scheduler has + * selected the task for execution. When dequeue needs to take the task + * off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path + * busy-waits for it to leave this state (via wait_ops_state()) before + * proceeding. Exits to %SCX_OPSS_NONE when dispatch completes. + * + * Memory Ordering + * + * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into + * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release() + * and waiters must use atomic_long_read_acquire(). This ensures proper + * synchronization between concurrent operations. + * + * Cross-CPU Task Migration + * + * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply + * grab the target CPU's rq lock because a concurrent dequeue might be + * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock + * (deadlock). + * + * The sched_ext core uses a "lock dancing" protocol coordinated by + * p->scx.holding_cpu. When moving a task to a different rq: + * + * 1. Verify task can be moved (CPU affinity, migration_disabled, etc.) + * 2. Set p->scx.holding_cpu to the current CPU + * 3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING + * is set, so clearing DISPATCHING first prevents the circular wait + * (safe to lock the rq we need) + * 4. Unlock the current CPU's rq + * 5. Lock src_rq (where the task currently lives) + * 6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the + * race (dequeue clears holding_cpu to -1 when it takes the task), in + * this case migration is aborted + * 7. If src_rq == dst_rq: clear holding_cpu and enqueue directly + * into dst_rq's local DSQ (no lock swap needed) + * 8. Otherwise: call move_remote_task_to_local_dsq(), which releases + * src_rq, locks dst_rq, and performs the deactivate/activate + * migration cycle (dst_rq is held on return) + * 9. Unlock dst_rq and re-lock the current CPU's rq to restore + * the lock state expected by the caller + * + * If any verification fails, abort the migration. + * + * This state tracking allows the BPF scheduler to try to dispatch any task + * at any time regardless of its state. The SCX core can safely + * reject/ignore invalid dispatches, simplifying the BPF scheduler + * implementation. */ enum scx_ops_state { SCX_OPSS_NONE, /* owned by the SCX core */ -- cgit v1.2.3 From f42f9091be9e5ff57567a3945cfcdd498f475348 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:37 -0800 Subject: workqueue: Use POOL_BH instead of WQ_BH when checking pool flags pr_cont_worker_id() checks pool->flags against WQ_BH, which is a workqueue-level flag (defined in workqueue.h). Pool flags use a separate namespace with POOL_* constants (defined in workqueue.c). The correct constant is POOL_BH. Both WQ_BH and POOL_BH are defined as (1 << 0) so this has no behavioral impact, but it is semantically wrong and inconsistent with every other pool-level BH check in the file. Fixes: 4cb1ef64609f ("workqueue: Implement BH workqueues to eventually replace tasklets") Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeaec79bc09c..1e5b6cb0fbda 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6274,7 +6274,7 @@ static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; - if (pool->flags & WQ_BH) + if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else -- cgit v1.2.3 From 6037160e52d72028da68546fd270a7dcac130d85 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:38 -0800 Subject: workqueue: Rename pool->watchdog_ts to pool->last_progress_ts The watchdog_ts name doesn't convey what the timestamp actually tracks. This field tracks the last time a workqueue got progress. Rename it to last_progress_ts to make it clear that it records when the pool last made forward progress (started processing new work items). No functional change. Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1e5b6cb0fbda..687d5c55c617 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -190,7 +190,7 @@ struct worker_pool { int id; /* I: pool ID */ unsigned int flags; /* L: flags */ - unsigned long watchdog_ts; /* L: watchdog timestamp */ + unsigned long last_progress_ts; /* L: last forward progress timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* @@ -1697,7 +1697,7 @@ static void __pwq_activate_work(struct pool_workqueue *pwq, WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) - pwq->pool->watchdog_ts = jiffies; + pwq->pool->last_progress_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } @@ -2348,7 +2348,7 @@ retry: */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); @@ -3352,7 +3352,7 @@ static void process_scheduled_works(struct worker *worker) while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { - worker->pool->watchdog_ts = jiffies; + worker->pool->last_progress_ts = jiffies; first = false; } process_one_work(worker, work); @@ -4850,7 +4850,7 @@ static int init_worker_pool(struct worker_pool *pool) pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; - pool->watchdog_ts = jiffies; + pool->last_progress_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); @@ -6462,7 +6462,7 @@ static void show_one_worker_pool(struct worker_pool *pool) /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) - hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that @@ -7691,7 +7691,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); - pool_ts = READ_ONCE(pool->watchdog_ts); + pool_ts = READ_ONCE(pool->last_progress_ts); if (time_after(pool_ts, touched)) ts = pool_ts; -- cgit v1.2.3 From e8e14ac7cfe437b896838e7f7d07c573965b4e4e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:39 -0800 Subject: workqueue: Show in-flight work item duration in stall diagnostics When diagnosing workqueue stalls, knowing how long each in-flight work item has been executing is valuable. Add a current_start timestamp (jiffies) to struct worker, set it when a work item begins execution in process_one_work(), and print the elapsed wall-clock time in show_pwq(). Unlike current_at (which tracks CPU runtime and resets on wakeup for CPU-intensive detection), current_start is never reset because the diagnostic cares about total wall-clock time including sleeps. Before: in-flight: 165:stall_work_fn [wq_stall] After: in-flight: 165:stall_work_fn [wq_stall] for 100s Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 3 +++ kernel/workqueue_internal.h | 1 + 2 files changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 687d5c55c617..56d8af13843f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3204,6 +3204,7 @@ __acquires(&pool->lock) worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; + worker->current_start = jiffies; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); @@ -6359,6 +6360,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); + pr_cont(" for %us", + jiffies_to_msecs(jiffies - worker->current_start) / 1000); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index f6275944ada7..8def1ddc5a1b 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -32,6 +32,7 @@ struct worker { work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ + unsigned long current_start; /* K: start time of current work item */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ -- cgit v1.2.3 From 8823eaef45da7f156a1396f40d53b985c511edef Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 5 Mar 2026 08:15:40 -0800 Subject: workqueue: Show all busy workers in stall diagnostics MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit show_cpu_pool_hog() only prints workers whose task is currently running on the CPU (task_is_running()). This misses workers that are busy processing a work item but are sleeping or blocked — for example, a worker that clears PF_WQ_WORKER and enters wait_event_idle(). Such a worker still occupies a pool slot and prevents progress, yet produces an empty backtrace section in the watchdog output. This is happening on real arm64 systems, where toggle_allocation_gate() IPIs every single CPU in the machine (which lacks NMI), causing workqueue stalls that show empty backtraces because toggle_allocation_gate() is sleeping in wait_event_idle(). Remove the task_is_running() filter so every in-flight worker in the pool's busy_hash is dumped. The busy_hash is protected by pool->lock, which is already held. Signed-off-by: Breno Leitao Acked-by: Song Liu Signed-off-by: Tejun Heo --- kernel/workqueue.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 56d8af13843f..09b9ad78d566 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7583,9 +7583,9 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds /* * Show workers that might prevent the processing of pending work items. - * The only candidates are CPU-bound workers in the running state. - * Pending work items should be handled by another idle worker - * in all other situations. + * A busy worker that is not running on the CPU (e.g. sleeping in + * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as + * effectively as a CPU-bound one, so dump every in-flight worker. */ static void show_cpu_pool_hog(struct worker_pool *pool) { @@ -7596,19 +7596,17 @@ static void show_cpu_pool_hog(struct worker_pool *pool) raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { - if (task_is_running(worker->task)) { - /* - * Defer printing to avoid deadlocks in console - * drivers that queue work while holding locks - * also taken in their write paths. - */ - printk_deferred_enter(); + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); - pr_info("pool %d:\n", pool->id); - sched_show_task(worker->task); + pr_info("pool %d:\n", pool->id); + sched_show_task(worker->task); - printk_deferred_exit(); - } + printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); @@ -7619,7 +7617,7 @@ static void show_cpu_pools_hogs(void) struct worker_pool *pool; int pi; - pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); + pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); -- cgit v1.2.3 From 7fe44c4388146bdbb3c5932d81a26d9fa0fd3ec9 Mon Sep 17 00:00:00 2001 From: Christian Loehle Date: Fri, 6 Mar 2026 10:49:18 +0000 Subject: bpf: drop kthread_exit from noreturn_deny kthread_exit became a macro to do_exit in commit 28aaa9c39945 ("kthread: consolidate kthread exit paths to prevent use-after-free"), so there is no kthread_exit function BTF ID to resolve. Remove it from noreturn_deny to avoid resolve_btfids unresolved symbol warnings. Signed-off-by: Christian Loehle Signed-off-by: Linus Torvalds --- kernel/bpf/verifier.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 401d6c4960ec..8db79e593156 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -25261,7 +25261,6 @@ BTF_ID(func, __x64_sys_exit_group) BTF_ID(func, do_exit) BTF_ID(func, do_group_exit) BTF_ID(func, kthread_complete_and_exit) -BTF_ID(func, kthread_exit) BTF_ID(func, make_task_dead) BTF_SET_END(noreturn_deny) -- cgit v1.2.3 From 98c790b100764102d877e9339471b8c4c9233f2c Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 6 Mar 2026 02:46:42 -0800 Subject: workqueue: Rename show_cpu_pool{s,}_hog{s,}() to reflect broadened scope MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit show_cpu_pool_hog() and show_cpu_pools_hogs() no longer only dump CPU hogs — since commit 8823eaef45da ("workqueue: Show all busy workers in stall diagnostics"), they dump every in-flight worker in the pool's busy_hash. Rename them to show_cpu_pool_busy_workers() and show_cpu_pools_busy_workers() to accurately describe what they do. Also fix the pr_info() message to say "stalled worker pools" instead of "stalled CPU-bound worker pools", since sleeping/blocked workers are now included. No functional change. Suggested-by: Tejun Heo Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- kernel/workqueue.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 09b9ad78d566..b77119d71641 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -7587,7 +7587,7 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as * effectively as a CPU-bound one, so dump every in-flight worker. */ -static void show_cpu_pool_hog(struct worker_pool *pool) +static void show_cpu_pool_busy_workers(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; @@ -7612,18 +7612,18 @@ static void show_cpu_pool_hog(struct worker_pool *pool) raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } -static void show_cpu_pools_hogs(void) +static void show_cpu_pools_busy_workers(void) { struct worker_pool *pool; int pi; - pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n"); + pr_info("Showing backtraces of busy workers in stalled worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) - show_cpu_pool_hog(pool); + show_cpu_pool_busy_workers(pool); } @@ -7720,7 +7720,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) show_all_workqueues(); if (cpu_pool_stall) - show_cpu_pools_hogs(); + show_cpu_pools_busy_workers(); if (lockup_detected) panic_on_wq_watchdog(max_stall_time); -- cgit v1.2.3 From 1dde502587657045b267f179d7a1ecc7b8a1a265 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 6 Mar 2026 04:50:55 +0000 Subject: sched_ext: Use READ_ONCE() for scx_slice_bypass_us in scx_bypass() Commit 0927780c90ce ("sched_ext: Use READ_ONCE() for lock-free reads of module param variables") annotated the plain reads of scx_slice_bypass_us and scx_bypass_lb_intv_us in bypass_lb_cpu(), but missed a third site in scx_bypass(): WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC); scx_slice_bypass_us is a module parameter writable via sysfs in process context through set_slice_us() -> param_set_uint_minmax(), which performs a plain store without holding bypass_lock. scx_bypass() reads the variable under bypass_lock, but since the writer does not take that lock, the two accesses are concurrent. WRITE_ONCE() only applies volatile semantics to the store of scx_slice_dfl -- the val expression containing scx_slice_bypass_us is evaluated as a plain read, providing no protection against concurrent writes. Wrap the read with READ_ONCE() to complete the annotation started by commit 0927780c90ce and make the access KCSAN-clean, consistent with the existing READ_ONCE(scx_slice_bypass_us) in bypass_lb_cpu(). Signed-off-by: David Carlier Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 10866bfb88bf..f323df7be180 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4137,7 +4137,7 @@ static void scx_bypass(bool bypass) WARN_ON_ONCE(scx_bypass_depth <= 0); if (scx_bypass_depth != 1) goto unlock; - WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC); + WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC); bypass_timestamp = ktime_get_ns(); if (sch) scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1); -- cgit v1.2.3 From ca174c705db52db3cc842e754fd25a5f50eb702d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 5 Mar 2026 14:53:29 -0500 Subject: cgroup/cpuset: Call rebuild_sched_domains() directly in hotplug Besides deferring the call to housekeeping_update(), commit 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue") also defers the rebuild_sched_domains() call to the workqueue. So a new offline CPU may still be in a sched domain or new online CPU not showing up in the sched domains for a short transition period. That could be a problem in some corner cases and can be the cause of a reported test failure[1]. Fix it by calling rebuild_sched_domains_cpuslocked() directly in hotplug as before. If isolated partition invalidation or recreation is being done, the housekeeping_update() call to update the housekeeping cpumasks will still be deferred to a workqueue. In commit 3bfe47967191 ("cgroup/cpuset: Move housekeeping_update()/rebuild_sched_domains() together"), housekeeping_update() is called before rebuild_sched_domains() because it needs to access the HK_TYPE_DOMAIN housekeeping cpumask. That is now changed to use the static HK_TYPE_DOMAIN_BOOT cpumask as HK_TYPE_DOMAIN cpumask is now changeable at run time. As a result, we can move the rebuild_sched_domains() call before housekeeping_update() with the slight advantage that it will be done in the same cpus_read_lock critical section without the possibility of interference by a concurrent cpu hot add/remove operation. As it doesn't make sense to acquire cpuset_mutex/cpuset_top_mutex after calling housekeeping_update() and immediately release them again, move the cpuset_full_unlock() operation inside update_hk_sched_domains() and rename it to cpuset_update_sd_hk_unlock() to signify that it will release the full set of locks. [1] https://lore.kernel.org/lkml/1a89aceb-48db-4edd-a730-b445e41221fe@nvidia.com Fixes: 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue") Tested-by: Jon Hunter Reviewed-by: Chen Ridong Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 59 ++++++++++++++++++++++++++------------------------ 1 file changed, 31 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e200de7c60b6..d21868455341 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -879,7 +879,7 @@ generate_doms: /* * Cgroup v2 doesn't support domain attributes, just set all of them * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a - * subset of HK_TYPE_DOMAIN housekeeping CPUs. + * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs. */ for (i = 0; i < ndoms; i++) { /* @@ -888,7 +888,7 @@ generate_doms: */ if (!csa || csa[i] == &top_cpuset) cpumask_and(doms[i], top_cpuset.effective_cpus, - housekeeping_cpumask(HK_TYPE_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT)); else cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) @@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains + * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock * - * Update housekeeping cpumasks and rebuild sched domains if necessary. - * This should be called at the end of cpuset or hotplug actions. + * Update housekeeping cpumasks and rebuild sched domains if necessary and + * then do a cpuset_full_unlock(). + * This should be called at the end of cpuset operation. */ -static void update_hk_sched_domains(void) +static void cpuset_update_sd_hk_unlock(void) + __releases(&cpuset_mutex) + __releases(&cpuset_top_mutex) { + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); + if (update_housekeeping) { - /* Updating HK cpumasks implies rebuild sched domains */ update_housekeeping = false; - force_sd_rebuild = true; cpumask_copy(isolated_hk_cpus, isolated_cpus); /* @@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void) mutex_unlock(&cpuset_mutex); cpus_read_unlock(); WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); - cpus_read_lock(); - mutex_lock(&cpuset_mutex); + mutex_unlock(&cpuset_top_mutex); + } else { + cpuset_full_unlock(); } - /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ - if (force_sd_rebuild) - rebuild_sched_domains_locked(); } /* - * Work function to invoke update_hk_sched_domains() + * Work function to invoke cpuset_update_sd_hk_unlock() */ static void hk_sd_workfn(struct work_struct *work) { cpuset_full_lock(); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } /** @@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_cpuset(trialcs); out_unlock: - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); return retval ?: nbytes; @@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); return retval ?: nbytes; } @@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); - update_hk_sched_domains(); - cpuset_full_unlock(); + cpuset_update_sd_hk_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) @@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* - * Queue a work to call housekeeping_update() & rebuild_sched_domains() - * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping - * cpumask can correctly reflect what is in isolated_cpus. + * rebuild_sched_domains() will always be called directly if needed + * to make sure that newly added or removed CPU will be reflected in + * the sched domains. However, if isolated partition invalidation + * or recreation is being done (update_housekeeping set), a work item + * will be queued to call housekeeping_update() to update the + * corresponding housekeeping cpumasks after some slight delay. * * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that * is still pending. Before the pending bit is cleared, the work data @@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void) * previously queued work. Since hk_sd_workfn() doesn't use the work * item at all, this is not a problem. */ - if (update_housekeeping || force_sd_rebuild) - queue_work(system_unbound_wq, &hk_sd_work); + if (force_sd_rebuild) + rebuild_sched_domains_cpuslocked(); + if (update_housekeeping) + queue_work(system_dfl_wq, &hk_sd_work); free_tmpmasks(ptmp); } -- cgit v1.2.3 From 457965c13f0837a289c9164b842d0860133f6274 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 5 Mar 2026 11:33:39 -0800 Subject: tracing: Add NULL pointer check to trigger_data_free() If trigger_data_alloc() fails and returns NULL, event_hist_trigger_parse() jumps to the out_free error path. While kfree() safely handles a NULL pointer, trigger_data_free() does not. This causes a NULL pointer dereference in trigger_data_free() when evaluating data->cmd_ops->set_filter. Fix the problem by adding a NULL pointer check to trigger_data_free(). The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y. Cc: Miaoqian Lin Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Steven Rostedt (Google) Link: https://patch.msgid.link/20260305193339.2810953-1-linux@roeck-us.net Fixes: 0550069cc25f ("tracing: Properly process error handling in event_hist_trigger_parse()") Assisted-by: Gemini:gemini-3.1-pro Signed-off-by: Guenter Roeck Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_trigger.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index fecbd679d432..d5230b759a2d 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -50,6 +50,9 @@ static int trigger_kthread_fn(void *ignore) void trigger_data_free(struct event_trigger_data *data) { + if (!data) + return; + if (data->cmd_ops->set_filter) data->cmd_ops->set_filter(NULL, data, NULL); -- cgit v1.2.3 From 3b1679e086bb869ca02722f6bd29b3573a6a0e7e Mon Sep 17 00:00:00 2001 From: Andrei-Alexandru Tachici Date: Mon, 2 Mar 2026 11:27:34 +0100 Subject: tracing: Fix enabling multiple events on the kernel command line and bootconfig Multiple events can be enabled on the kernel command line via a comma separator. But if the are specified one at a time, then only the last event is enabled. This is because the event names are saved in a temporary buffer, and each call by the init cmdline code will reset that buffer. This also affects names in the boot config file, as it may call the callback multiple times with an example of: kernel.trace_event = ":mod:rproc_qcom_common", ":mod:qrtr", ":mod:qcom_aoss" Change the cmdline callback function to append a comma and the next value if the temporary buffer already has content. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260302-trace-events-allow-multiple-modules-v1-1-ce4436e37fb8@oss.qualcomm.com Signed-off-by: Andrei-Alexandru Tachici Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b7343fdfd7b0..249d1cba72c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4493,7 +4493,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { - strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + if (bootup_event_buf[0] != '\0') + strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE); + + strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE); + trace_set_ring_buffer_expanded(NULL); disable_tracing_selftest("running event tracing"); -- cgit v1.2.3 From a72f73c4dd9b209c53cf8b03b6e97fcefad4262c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 6 Mar 2026 20:22:35 +0100 Subject: cgroup: Don't expose dead tasks in cgroup Once a task exits it has its state set to TASK_DEAD and then it is removed from the cgroup it belonged to. The last step happens on the task gets out of its last schedule() invocation and is delayed on PREEMPT_RT due to locking constraints. As a result it is possible to receive a pid via waitpid() of a task which is still listed in cgroup.procs for the cgroup it belonged to. This is something that systemd does not expect and as a result it waits for its exit until a time out occurs. This can also be reproduced on !PREEMPT_RT kernel with a significant delay in do_exit() after exit_notify(). Hide the task from the output which have PF_EXITING set which is done before the parent is notified. Keeping zombies with live threads shouldn't break anything (suggested by Tejun). Reported-by: Bert Karwatzki Closes: https://lore.kernel.org/all/20260219164648.3014-1-spasswolf@web.de/ Tested-by: Bert Karwatzki Fixes: 9311e6c29b34 ("cgroup: Fix sleeping from invalid context warning on PREEMPT_RT") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index be1d71dda317..01fc2a93f3ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5109,6 +5109,12 @@ repeat: return; task = list_entry(it->task_pos, struct task_struct, cg_list); + /* + * Hide tasks that are exiting but not yet removed. Keep zombie + * leaders with live threads visible. + */ + if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live)) + goto repeat; if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ -- cgit v1.2.3 From fbc7aef517d8765e4c425d2792409bb9bf2e1f13 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 6 Mar 2026 16:54:24 -0800 Subject: bpf: Fix u32/s32 bounds when ranges cross min/max boundary MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Same as in __reg64_deduce_bounds(), refine s32/u32 ranges in __reg32_deduce_bounds() in the following situations: - s32 range crosses U32_MAX/0 boundary, positive part of the s32 range overlaps with u32 range: 0 U32_MAX | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | |----------------------------|----------------------------| |xxxxx s32 range xxxxxxxxx] [xxxxxxx| 0 S32_MAX S32_MIN -1 - s32 range crosses U32_MAX/0 boundary, negative part of the s32 range overlaps with u32 range: 0 U32_MAX | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | |----------------------------|----------------------------| |xxxxxxxxx] [xxxxxxxxxxxx s32 range | 0 S32_MAX S32_MIN -1 - No refinement if ranges overlap in two intervals. This helps for e.g. consider the following program: call %[bpf_get_prandom_u32]; w0 &= 0xffffffff; if w0 < 0x3 goto 1f; // on fall-through u32 range [3..U32_MAX] if w0 s> 0x1 goto 1f; // on fall-through s32 range [S32_MIN..1] if w0 s< 0x0 goto 1f; // range can be narrowed to [S32_MIN..-1] r10 = 0; 1: ...; The reg_bounds.c selftest is updated to incorporate identical logic, refinement based on non-overflowing range halves: ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪ ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1])) Reported-by: Andrea Righi Reported-by: Emil Tsalapatis Closes: https://lore.kernel.org/bpf/aakqucg4vcujVwif@gpd4/T/ Reviewed-by: Emil Tsalapatis Acked-by: Shung-Hsi Yu Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-1-f7f67e060a6b@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 401d6c4960ec..f960b382fdb3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2511,6 +2511,30 @@ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) { reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); + } else { + if (reg->u32_max_value < (u32)reg->s32_min_value) { + /* See __reg64_deduce_bounds() for detailed explanation. + * Refine ranges in the following situation: + * + * 0 U32_MAX + * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxx s32 range xxxxxxxxx] [xxxxxxx| + * 0 S32_MAX S32_MIN -1 + */ + reg->s32_min_value = (s32)reg->u32_min_value; + reg->u32_max_value = min_t(u32, reg->u32_max_value, reg->s32_max_value); + } else if ((u32)reg->s32_max_value < reg->u32_min_value) { + /* + * 0 U32_MAX + * | [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx] | + * |----------------------------|----------------------------| + * |xxxxxxxxx] [xxxxxxxxxxxx s32 range | + * 0 S32_MAX S32_MIN -1 + */ + reg->s32_max_value = (s32)reg->u32_max_value; + reg->u32_min_value = max_t(u32, reg->u32_min_value, reg->s32_min_value); + } } } -- cgit v1.2.3 From d008ba8be8984760e36d7dcd4adbd5a41a645708 Mon Sep 17 00:00:00 2001 From: Calvin Owens Date: Fri, 6 Mar 2026 19:19:25 -0800 Subject: tracing: Fix trace_buf_size= cmdline parameter with sizes >= 2G Some of the sizing logic through tracer_alloc_buffers() uses int internally, causing unexpected behavior if the user passes a value that does not fit in an int (on my x86 machine, the result is uselessly tiny buffers). Fix by plumbing the parameter's real type (unsigned long) through to the ring buffer allocation functions, which already use unsigned long. It has always been possible to create larger ring buffers via the sysfs interface: this only affects the cmdline parameter. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/bff42a4288aada08bdf74da3f5b67a2c28b761f8.1772852067.git.calvin@wbinvd.org Fixes: 73c5162aa362 ("tracing: keep ring buffer to minimum size till used") Signed-off-by: Calvin Owens Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1e7c032a72d2..ebd996f8710e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9350,7 +9350,7 @@ static void setup_trace_scratch(struct trace_array *tr, } static int -allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) +allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size) { enum ring_buffer_flags rb_flags; struct trace_scratch *tscratch; @@ -9405,7 +9405,7 @@ static void free_trace_buffer(struct array_buffer *buf) } } -static int allocate_trace_buffers(struct trace_array *tr, int size) +static int allocate_trace_buffers(struct trace_array *tr, unsigned long size) { int ret; @@ -10769,7 +10769,7 @@ __init static void enable_instances(void) __init static int tracer_alloc_buffers(void) { - int ring_buf_size; + unsigned long ring_buf_size; int ret = -ENOMEM; -- cgit v1.2.3 From 2658a1720a1944fbaeda937000ad2b3c3dfaf1bb Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 6 Mar 2026 16:02:47 -0800 Subject: bpf: collect only live registers in linked regs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix an inconsistency between func_states_equal() and collect_linked_regs(): - regsafe() uses check_ids() to verify that cached and current states have identical register id mapping. - func_states_equal() calls regsafe() only for registers computed as live by compute_live_registers(). - clean_live_states() is supposed to remove dead registers from cached states, but it can skip states belonging to an iterator-based loop. - collect_linked_regs() collects all registers sharing the same id, ignoring the marks computed by compute_live_registers(). Linked registers are stored in the state's jump history. - backtrack_insn() marks all linked registers for an instruction as precise whenever one of the linked registers is precise. The above might lead to a scenario: - There is an instruction I with register rY known to be dead at I. - Instruction I is reached via two paths: first A, then B. - On path A: - There is an id link between registers rX and rY. - Checkpoint C is created at I. - Linked register set {rX, rY} is saved to the jump history. - rX is marked as precise at I, causing both rX and rY to be marked precise at C. - On path B: - There is no id link between registers rX and rY, otherwise register states are sub-states of those in C. - Because rY is dead at I, check_ids() returns true. - Current state is considered equal to checkpoint C, propagate_precision() propagates spurious precision mark for register rY along the path B. - Depending on a program, this might hit verifier_bug() in the backtrack_insn(), e.g. if rY ∈ [r1..r5] and backtrack_insn() spots a function call. The reproducer program is in the next patch. This was hit by sched_ext scx_lavd scheduler code. Changes in tests: - verifier_scalar_ids.c selftests need modification to preserve some registers as live for __msg() checks. - exceptions_assert.c adjusted to match changes in the verifier log, R0 is dead after conditional instruction and thus does not get range. - precise.c adjusted to match changes in the verifier log, register r9 is dead after comparison and it's range is not important for test. Reported-by: Emil Tsalapatis Fixes: 0fb3cf6110a5 ("bpf: use register liveness information for func_states_equal") Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20260306-linked-regs-and-propagate-precision-v1-1-18e859be570d@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f960b382fdb3..836ceb128d19 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17359,17 +17359,24 @@ static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_st * in verifier state, save R in linked_regs if R->id == id. * If there are too many Rs sharing same id, reset id for leftover Rs. */ -static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id, +static void collect_linked_regs(struct bpf_verifier_env *env, + struct bpf_verifier_state *vstate, + u32 id, struct linked_regs *linked_regs) { + struct bpf_insn_aux_data *aux = env->insn_aux_data; struct bpf_func_state *func; struct bpf_reg_state *reg; + u16 live_regs; int i, j; id = id & ~BPF_ADD_CONST; for (i = vstate->curframe; i >= 0; i--) { + live_regs = aux[frame_insn_idx(vstate, i)].live_regs_before; func = vstate->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { + if (!(live_regs & BIT(j))) + continue; reg = &func->regs[j]; __collect_linked_regs(linked_regs, reg, id, i, j, true); } @@ -17584,9 +17591,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, * if parent state is created. */ if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id) - collect_linked_regs(this_branch, src_reg->id, &linked_regs); + collect_linked_regs(env, this_branch, src_reg->id, &linked_regs); if (dst_reg->type == SCALAR_VALUE && dst_reg->id) - collect_linked_regs(this_branch, dst_reg->id, &linked_regs); + collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs); if (linked_regs.cnt > 1) { err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs)); if (err) -- cgit v1.2.3 From 57ccf5ccdc56954f2a91a7f66684fd31c566bde5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 7 Mar 2026 04:53:32 -1000 Subject: sched_ext: Fix enqueue_task_scx() truncation of upper enqueue flags enqueue_task_scx() takes int enq_flags from the sched_class interface. SCX enqueue flags starting at bit 32 (SCX_ENQ_PREEMPT and above) are silently truncated when passed through activate_task(). extra_enq_flags was added as a workaround - storing high bits in rq->scx.extra_enq_flags and OR-ing them back in enqueue_task_scx(). However, the OR target is still the int parameter, so the high bits are lost anyway. The current impact is limited as the only affected flag is SCX_ENQ_PREEMPT which is informational to the BPF scheduler - its loss means the scheduler doesn't know about preemption but doesn't cause incorrect behavior. Fix by renaming the int parameter to core_enq_flags and introducing a u64 enq_flags local that merges both sources. All downstream functions already take u64 enq_flags. Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class") Cc: stable@vger.kernel.org # v6.12+ Acked-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index f323df7be180..174e3650d7fe 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; } -static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags) { struct scx_sched *sch = scx_root; int sticky_cpu = p->scx.sticky_cpu; + u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags; if (enq_flags & ENQUEUE_WAKEUP) rq->scx.flags |= SCX_RQ_IN_WAKEUP; - enq_flags |= rq->scx.extra_enq_flags; - if (sticky_cpu >= 0) p->scx.sticky_cpu = -1; -- cgit v1.2.3 From 2fcfe5951eb2e8440fc5e1dd6ea977336ff83a1d Mon Sep 17 00:00:00 2001 From: zhidao su Date: Mon, 9 Mar 2026 10:46:12 +0800 Subject: sched_ext: Use WRITE_ONCE() for the write side of scx_enable helper pointer scx_enable() uses double-checked locking to lazily initialize a static kthread_worker pointer. The fast path reads helper locklessly: if (!READ_ONCE(helper)) { // lockless read -- no helper_mutex The write side initializes helper under helper_mutex, but previously used a plain assignment: helper = kthread_run_worker(0, "scx_enable_helper"); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ plain write -- KCSAN data race with READ_ONCE() above Since READ_ONCE() on the fast path and the plain write on the initialization path access the same variable without a common lock, they constitute a data race. KCSAN requires that all sides of a lock-free access use READ_ONCE()/WRITE_ONCE() consistently. Use a temporary variable to stage the result of kthread_run_worker(), and only WRITE_ONCE() into helper after confirming the pointer is valid. This avoids a window where a concurrent caller on the fast path could observe an ERR pointer via READ_ONCE(helper) before the error check completes. Fixes: b06ccbabe250 ("sched_ext: Fix starvation of scx_enable() under fair-class saturation") Signed-off-by: zhidao su Acked-by: Andrea Righi Signed-off-by: Tejun Heo --- kernel/sched/ext.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 174e3650d7fe..26a6ac2f8826 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5258,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (!READ_ONCE(helper)) { mutex_lock(&helper_mutex); if (!helper) { - helper = kthread_run_worker(0, "scx_enable_helper"); - if (IS_ERR_OR_NULL(helper)) { - helper = NULL; + struct kthread_worker *w = + kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(w)) { mutex_unlock(&helper_mutex); return -ENOMEM; } - sched_set_fifo(helper->task); + sched_set_fifo(w->task); + WRITE_ONCE(helper, w); } mutex_unlock(&helper_mutex); } -- cgit v1.2.3 From d557640e4ce589a24dca5ca7ce3b9680f471325f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 7 Mar 2026 17:12:05 +0100 Subject: sched: idle: Make skipping governor callbacks more consistent If the cpuidle governor .select() callback is skipped because there is only one idle state in the cpuidle driver, the .reflect() callback should be skipped as well, at least for consistency (if not for correctness), so do it. Fixes: e5c9ffc6ae1b ("cpuidle: Skip governor when only one idle state is available") Signed-off-by: Rafael J. Wysocki Reviewed-by: Christian Loehle Reviewed-by: Aboorva Devarajan Reviewed-by: Frederic Weisbecker Link: https://patch.msgid.link/12857700.O9o76ZdvQC@rafael.j.wysocki --- kernel/sched/idle.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 3681b6ad9276..b95449165122 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -221,7 +221,7 @@ static void cpuidle_idle_call(void) next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); - } else { + } else if (drv->state_count > 1) { bool stop_tick = true; /* @@ -239,6 +239,15 @@ static void cpuidle_idle_call(void) * Give the governor an opportunity to reflect on the outcome */ cpuidle_reflect(dev, entered_state); + } else { + tick_nohz_idle_retain_tick(); + + /* + * If there is only a single idle state (or none), there is + * nothing meaningful for the governor to choose. Skip the + * governor and always use state 0. + */ + call_cpuidle(drv, dev, 0); } exit_idle: -- cgit v1.2.3 From 755a648e78f12574482d4698d877375793867fa1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 6 Mar 2026 21:24:03 -0500 Subject: time/jiffies: Mark jiffies_64_to_clock_t() notrace The trace_clock_jiffies() function that handles the "uptime" clock for tracing calls jiffies_64_to_clock_t(). This causes the function tracer to constantly recurse when the tracing clock is set to "uptime". Mark it notrace to prevent unnecessary recursion when using the "uptime" clock. Fixes: 58d4e21e50ff3 ("tracing: Fix wraparound problems in "uptime" trace clock") Signed-off-by: Steven Rostedt (Google) Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260306212403.72270bb2@robin --- kernel/time/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 36fd2313ae7e..0d832317d576 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -697,7 +697,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies); * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ -u64 jiffies_64_to_clock_t(u64 x) +notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ -- cgit v1.2.3 From b2e48c429ec54715d16fefa719dd2fbded2e65be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:28:53 +0100 Subject: sched/mmcid: Prevent CID stalls due to concurrent forks A newly forked task is accounted as MMCID user before the task is visible in the process' thread list and the global task list. This creates the following problem: CPU1 CPU2 fork() sched_mm_cid_fork(tnew1) tnew1->mm.mm_cid_users++; tnew1->mm_cid.cid = getcid() -> preemption fork() sched_mm_cid_fork(tnew2) tnew2->mm.mm_cid_users++; // Reaches the per CPU threshold mm_cid_fixup_tasks_to_cpus() for_each_other(current, p) .... As tnew1 is not visible yet, this fails to fix up the already allocated CID of tnew1. As a consequence a subsequent schedule in might fail to acquire a (transitional) CID and the machine stalls. Move the invocation of sched_mm_cid_fork() after the new task becomes visible in the thread and the task list to prevent this. This also makes it symmetrical vs. exit() where the task is removed as CID user before the task is removed from the thread and task lists. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202525.969061974@kernel.org --- kernel/fork.c | 2 -- kernel/sched/core.c | 22 +++++++++++++++------- 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 65113a304518..7febf4c2889e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1586,7 +1586,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk) tsk->mm = mm; tsk->active_mm = mm; - sched_mm_cid_fork(tsk); return 0; } @@ -2498,7 +2497,6 @@ bad_fork_cleanup_namespaces: exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { - sched_mm_cid_exit(p); mm_clear_owner(p->mm, p); mmput(p->mm); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7f77c165a6e..d25427855b5d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4729,8 +4729,11 @@ void sched_cancel_fork(struct task_struct *p) scx_cancel_fork(p); } +static void sched_mm_cid_fork(struct task_struct *t); + void sched_post_fork(struct task_struct *p) { + sched_mm_cid_fork(p); uclamp_post_fork(p); scx_post_fork(p); } @@ -10646,12 +10649,13 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) * possible switch back to per task mode happens either in the * deferred handler function or in the next fork()/exit(). * - * The caller has already transferred. The newly incoming task is - * already accounted for, but not yet visible. + * The caller has already transferred so remove it from the users + * count. The incoming task is already visible and has mm_cid.active, + * but has task::mm_cid::cid == UNSET. Still it needs to be accounted + * for. Concurrent fork()s might add more threads, but all of them have + * task::mm_cid::active = 0, so they don't affect the accounting here. */ - users = mm->mm_cid.users - 2; - if (!users) - return; + users = mm->mm_cid.users - 1; guard(rcu)(); for_other_threads(current, t) { @@ -10688,12 +10692,15 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) return mm_update_max_cids(mm); } -void sched_mm_cid_fork(struct task_struct *t) +static void sched_mm_cid_fork(struct task_struct *t) { struct mm_struct *mm = t->mm; bool percpu; - WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET); + if (!mm) + return; + + WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET); guard(mutex)(&mm->mm_cid.mutex); scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { @@ -10885,6 +10892,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p) } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } #endif /* !CONFIG_SCHED_MM_CID */ static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx); -- cgit v1.2.3 From 28b5a1395036d6c7a6c8034d85ad3d7d365f192c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:28:58 +0100 Subject: sched/mmcid: Handle vfork()/CLONE_VM correctly Matthieu and Jiri reported stalls where a task endlessly loops in mm_get_cid() when scheduling in. It turned out that the logic which handles vfork()'ed tasks is broken. It is invoked when the number of tasks associated to a process is smaller than the number of MMCID users. It then walks the task list to find the vfork()'ed task, but accounts all the already processed tasks as well. If that double processing brings the number of to be handled tasks to 0, the walk stops and the vfork()'ed task's CID is not fixed up. As a consequence a subsequent schedule in fails to acquire a (transitional) CID and the machine stalls. Cure this by removing the accounting condition and make the fixup always walk the full task list if it could not find the exact number of users in the process' thread list. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Closes: https://lore.kernel.org/b24ffcb3-09d5-4e48-9070-0b69bc654281@kernel.org Reported-by: Matthieu Baerts Reported-by: Jiri Slaby Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.048657665@kernel.org --- kernel/sched/core.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d25427855b5d..ee59cd19b9a8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10670,10 +10670,7 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) for_each_process_thread(p, t) { if (t == current || t->mm != mm) continue; - if (mm_cid_fixup_task_to_cpu(t, mm)) { - if (--users == 0) - return; - } + mm_cid_fixup_task_to_cpu(t, mm); } } -- cgit v1.2.3 From 7574ac6e49789ddee1b1be9b2afb42b4a1b4b1f4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:29:04 +0100 Subject: sched/mmcid: Remove pointless preempt guard This is a leftover from the early versions of this function where it could be invoked without mm::mm_cid::lock held. Remove it and add lockdep asserts instead. Fixes: 653fda7ae73d ("sched/mmcid: Switch over to the new mechanism") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.116363613@kernel.org --- kernel/sched/core.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ee59cd19b9a8..f56156f91d08 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10684,6 +10684,8 @@ static void mm_cid_fixup_tasks_to_cpus(void) static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) { + lockdep_assert_held(&mm->mm_cid.lock); + t->mm_cid.active = 1; mm->mm_cid.users++; return mm_update_max_cids(mm); @@ -10736,12 +10738,12 @@ static void sched_mm_cid_fork(struct task_struct *t) static bool sched_mm_cid_remove_user(struct task_struct *t) { + lockdep_assert_held(&t->mm->mm_cid.lock); + t->mm_cid.active = 0; - scoped_guard(preempt) { - /* Clear the transition bit */ - t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); - mm_unset_cid_on_task(t); - } + /* Clear the transition bit */ + t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); + mm_unset_cid_on_task(t); t->mm->mm_cid.users--; return mm_update_max_cids(t->mm); } -- cgit v1.2.3 From 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:29:09 +0100 Subject: sched/mmcid: Avoid full tasklist walks Chasing vfork()'ed tasks on a CID ownership mode switch requires a full task list walk, which is obviously expensive on large systems. Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid and walk this list instead. This removes the proven to be flaky counting logic and avoids a full task list walk in the case of vfork()'ed tasks. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.183824481@kernel.org --- kernel/fork.c | 1 + kernel/sched/core.c | 54 ++++++++++++----------------------------------------- 2 files changed, 13 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 7febf4c2889e..bc2bf58b93b6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1000,6 +1000,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid.cid = MM_CID_UNSET; tsk->mm_cid.active = 0; + INIT_HLIST_NODE(&tsk->mm_cid.node); #endif return tsk; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f56156f91d08..496dff740dca 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10620,13 +10620,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc } } -static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) +static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) { /* Remote access to mm::mm_cid::pcpu requires rq_lock */ guard(task_rq_lock)(t); - /* If the task is not active it is not in the users count */ - if (!t->mm_cid.active) - return false; if (cid_on_task(t->mm_cid.cid)) { /* If running on the CPU, put the CID in transit mode, otherwise drop it */ if (task_rq(t)->curr == t) @@ -10634,51 +10631,21 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm else mm_unset_cid_on_task(t); } - return true; } -static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm) +static void mm_cid_fixup_tasks_to_cpus(void) { - struct task_struct *p, *t; - unsigned int users; - - /* - * This can obviously race with a concurrent affinity change, which - * increases the number of allowed CPUs for this mm, but that does - * not affect the mode and only changes the CID constraints. A - * possible switch back to per task mode happens either in the - * deferred handler function or in the next fork()/exit(). - * - * The caller has already transferred so remove it from the users - * count. The incoming task is already visible and has mm_cid.active, - * but has task::mm_cid::cid == UNSET. Still it needs to be accounted - * for. Concurrent fork()s might add more threads, but all of them have - * task::mm_cid::active = 0, so they don't affect the accounting here. - */ - users = mm->mm_cid.users - 1; - - guard(rcu)(); - for_other_threads(current, t) { - if (mm_cid_fixup_task_to_cpu(t, mm)) - users--; - } + struct mm_struct *mm = current->mm; + struct task_struct *t; - if (!users) - return; + lockdep_assert_held(&mm->mm_cid.mutex); - /* Happens only for VM_CLONE processes. */ - for_each_process_thread(p, t) { - if (t == current || t->mm != mm) - continue; - mm_cid_fixup_task_to_cpu(t, mm); + hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) { + /* Current has already transferred before invoking the fixup. */ + if (t != current) + mm_cid_fixup_task_to_cpu(t, mm); } -} - -static void mm_cid_fixup_tasks_to_cpus(void) -{ - struct mm_struct *mm = current->mm; - mm_cid_do_fixup_tasks_to_cpus(mm); mm_cid_complete_transit(mm, MM_CID_ONCPU); } @@ -10687,6 +10654,7 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) lockdep_assert_held(&mm->mm_cid.lock); t->mm_cid.active = 1; + hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list); mm->mm_cid.users++; return mm_update_max_cids(mm); } @@ -10744,6 +10712,7 @@ static bool sched_mm_cid_remove_user(struct task_struct *t) /* Clear the transition bit */ t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); mm_unset_cid_on_task(t); + hlist_del_init(&t->mm_cid.node); t->mm->mm_cid.users--; return mm_update_max_cids(t->mm); } @@ -10886,6 +10855,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p) mutex_init(&mm->mm_cid.mutex); mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work); INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn); + INIT_HLIST_HEAD(&mm->mm_cid.user_list); cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); bitmap_zero(mm_cidmask(mm), num_possible_cpus()); } -- cgit v1.2.3 From e113f0b46d19626ec15388bcb91432c9a4fd6261 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 13 Mar 2026 23:14:14 +0900 Subject: kprobes: avoid crash when rmmod/insmod after ftrace killed After we hit ftrace is killed by some errors, the kernel crash if we remove modules in which kprobe probes. BUG: unable to handle page fault for address: fffffbfff805000d PGD 817fcc067 P4D 817fcc067 PUD 817fc8067 PMD 101555067 PTE 0 Oops: Oops: 0000 [#1] SMP KASAN PTI CPU: 4 UID: 0 PID: 2012 Comm: rmmod Tainted: G W OE Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE RIP: 0010:kprobes_module_callback+0x89/0x790 RSP: 0018:ffff88812e157d30 EFLAGS: 00010a02 RAX: 1ffffffff805000d RBX: dffffc0000000000 RCX: ffffffff86a8de90 RDX: ffffed1025c2af9b RSI: 0000000000000008 RDI: ffffffffc0280068 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed1025c2af9a R10: ffff88812e157cd7 R11: 205d323130325420 R12: 0000000000000002 R13: ffffffffc0290488 R14: 0000000000000002 R15: ffffffffc0280040 FS: 00007fbc450dd740(0000) GS:ffff888420331000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff805000d CR3: 000000010f624000 CR4: 00000000000006f0 Call Trace: notifier_call_chain+0xc6/0x280 blocking_notifier_call_chain+0x60/0x90 __do_sys_delete_module.constprop.0+0x32a/0x4e0 do_syscall_64+0x5d/0xfa0 entry_SYSCALL_64_after_hwframe+0x76/0x7e This is because the kprobe on ftrace does not correctly handles the kprobe_ftrace_disabled flag set by ftrace_kill(). To prevent this error, check kprobe_ftrace_disabled in __disarm_kprobe_ftrace() and skip all ftrace related operations. Link: https://lore.kernel.org/all/176473947565.1727781.13110060700668331950.stgit@mhiramat.tok.corp.google.com/ Reported-by: Ye Bin Closes: https://lore.kernel.org/all/20251125020536.2484381-1-yebin@huaweicloud.com/ Fixes: ae6aa16fdc16 ("kprobes: introduce ftrace based optimization") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) Acked-by: Steven Rostedt (Google) --- kernel/kprobes.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ab25b4aa9095..025af57ad3ed 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1178,6 +1178,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int ret; lockdep_assert_held(&kprobe_mutex); + if (unlikely(kprobe_ftrace_disabled)) { + /* Now ftrace is disabled forever, disarm is already done. */ + return 0; + } if (*cnt == 1) { ret = unregister_ftrace_function(ops); -- cgit v1.2.3 From 5ef268cb7a0aac55521fd9881f1939fa94a8988e Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 13 Mar 2026 23:04:11 +0900 Subject: kprobes: Remove unneeded warnings from __arm_kprobe_ftrace() Remove unneeded warnings for handled errors from __arm_kprobe_ftrace() because all caller handled the error correctly. Link: https://lore.kernel.org/all/177261531182.1312989.8737778408503961141.stgit@mhiramat.tok.corp.google.com/ Reported-by: Zw Tang Closes: https://lore.kernel.org/all/CAPHJ_V+J6YDb_wX2nhXU6kh466Dt_nyDSas-1i_Y8s7tqY-Mzw@mail.gmail.com/ Fixes: 9c89bb8e3272 ("kprobes: treewide: Cleanup the error messages for kprobes") Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/kprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 025af57ad3ed..bfc89083daa9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1144,12 +1144,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, lockdep_assert_held(&kprobe_mutex); ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); - if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret)) + if (ret < 0) return ret; if (*cnt == 0) { ret = register_ftrace_function(ops); - if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) { + if (ret < 0) { /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. -- cgit v1.2.3