From 0de4cb473aed57ee4ba7e0551ad27bddc19fc519 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 28 Apr 2026 08:10:43 -0700 Subject: workqueue: fix devm_alloc_workqueue() va_list misuse devm_alloc_workqueue() built a va_list and passed it as a single positional argument to the variadic alloc_workqueue() macro: va_start(args, max_active); wq = alloc_workqueue(fmt, flags, max_active, args); va_end(args); C does not allow forwarding a va_list through a ... parameter. alloc_workqueue() expands to alloc_workqueue_noprof(), which runs its own va_start() over its ... params, so the inner vsnprintf(wq->name, sizeof(wq->name), fmt, args) in __alloc_workqueue() received the outer va_list object as the first variadic slot rather than the caller's actual format arguments. Add a new static helper alloc_workqueue_va() that wraps __alloc_workqueue() and runs wq_init_lockdep() on success, and fold both alloc_workqueue_noprof() and devm_alloc_workqueue_noprof() onto it as suggested by Tejun. The wq_init_lockdep() step is required on the devm path too, otherwise __flush_workqueue()'s on-stack COMPLETION_INITIALIZER_ONSTACK_MAP would NULL-deref wq->lockdep_map. No caller changes are required. devm_alloc_ordered_workqueue() is a macro forwarding to devm_alloc_workqueue() and inherits the fix. Two in-tree callers actively trigger the broken path on every probe: drivers/power/supply/mt6370-charger.c:889 drivers/power/supply/max77705_charger.c:649 both of which use devm_alloc_ordered_workqueue(dev, "%s", 0, dev_name(dev)). A standalone reproducer module is available at[1]. Link: https://github.com/leitao/debug/blob/main/workqueue/valist/wq_va_test.c [1] Fixes: 1dfc9d60a69e ("workqueue: devres: Add device-managed allocate workqueue") Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- kernel/workqueue.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5f747f241a5f..24d0265191d4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5906,6 +5906,20 @@ err_destroy: return NULL; } +static struct workqueue_struct *alloc_workqueue_va(const char *fmt, + unsigned int flags, + int max_active, + va_list args) +{ + struct workqueue_struct *wq; + + wq = __alloc_workqueue(fmt, flags, max_active, args); + if (wq) + wq_init_lockdep(wq); + + return wq; +} + __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, @@ -5915,12 +5929,8 @@ struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, va_list args; va_start(args, max_active); - wq = __alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); - if (!wq) - return NULL; - - wq_init_lockdep(wq); return wq; } @@ -5932,15 +5942,15 @@ static void devm_workqueue_release(void *res) } __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...) +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; int ret; va_start(args, max_active); - wq = alloc_workqueue(fmt, flags, max_active, args); + wq = alloc_workqueue_va(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; @@ -5951,7 +5961,7 @@ devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, return wq; } -EXPORT_SYMBOL_GPL(devm_alloc_workqueue); +EXPORT_SYMBOL_GPL(devm_alloc_workqueue_noprof); #ifdef CONFIG_LOCKDEP __printf(1, 5) -- cgit v1.2.3 From 20e81c64c905bd765e69ef07920d2b1130dc79b6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 29 Apr 2026 09:44:16 -1000 Subject: workqueue: Annotate alloc_workqueue_va() with __printf(1, 0) alloc_workqueue_va() forwards its va_list to __alloc_workqueue() which ultimately feeds vsnprintf(). __alloc_workqueue() already carries __printf(1, 0); the new wrapper needs the same annotation so format string checking propagates through the forwarding. Fixes: 0de4cb473aed ("workqueue: fix devm_alloc_workqueue() va_list misuse") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202604300347.2LgXyteh-lkp@intel.com/ Signed-off-by: Tejun Heo --- kernel/workqueue.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 24d0265191d4..3d2e3b2ec528 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5906,6 +5906,7 @@ err_destroy: return NULL; } +__printf(1, 0) static struct workqueue_struct *alloc_workqueue_va(const char *fmt, unsigned int flags, int max_active, -- cgit v1.2.3 From a7488f089bdfa87c4fef1744d4dca9f4f8b46f8b Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 7 May 2026 04:04:46 -0700 Subject: workqueue: Release PENDING in __queue_work() drain/destroy reject path The caller of __queue_work() owns WORK_STRUCT_PENDING, won via test_and_set_bit() in queue_work_on()/__queue_delayed_work(). The state machine documented above __queue_work() requires that owner to either hand the token to a pwq (insert_work() -> set_work_pwq()), hand it to a timer, or release it via set_work_pool_and_clear_pending(). try_to_grab_pending() relies on this: when it observes "PENDING && off-queue" it busy-loops, trusting the current owner to make progress. The (__WQ_DESTROYING | __WQ_DRAINING) early-return path violates that contract. It WARN_ONCE()s and bare-returns, leaving work->data with PENDING set, WORK_STRUCT_PWQ clear, and work->entry empty. The path is reachable without explicit API abuse: queue_delayed_work() arms a timer with PENDING set; if drain_workqueue() runs while the timer is still pending, delayed_work_timer_fn() -> __queue_work() in softirq context hits the WARN, current is not a wq worker so is_chained_work() is false, and the work is silently dropped with PENDING leaked. Mirror what clear_pending_if_disabled() already does on its analogous reject path: unpack the off-queue data and call set_work_pool_and_clear_pending() to release the token before returning. I was able to reproduce this by queueing several slow works on a max_active=1 wq, arm a delayed_work whose timer fires while drain_workqueue() is blocked, then call cancel_delayed_work_sync(). Without this patch the cancel livelocks at 100% CPU; with it the cancel returns immediately. Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- kernel/workqueue.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3d2e3b2ec528..c0e58f877e08 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2296,6 +2296,18 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { + struct work_offq_data offqd; + + /* + * State on entry: PENDING is set, work is off-queue (no + * insert_work() has run). + * + * Returning without clearing PENDING would leave the work + * in a weird state (PENDING=1, PWQ=0, entry empty) + */ + work_offqd_unpack(&offqd, *work_data_bits(work)); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); return; } rcu_read_lock(); -- cgit v1.2.3 From 0143033dc22cdff912cfc13419f5db92fea3b4cb Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 8 May 2026 09:22:03 -0700 Subject: workqueue: Fix wq->cpu_pwq leak in alloc_and_link_pwqs() WQ_UNBOUND path For WQ_UNBOUND workqueues, alloc_and_link_pwqs() allocates wq->cpu_pwq via alloc_percpu() and then calls apply_workqueue_attrs_locked(). On failure it returns the error directly, bypassing the enomem: label which holds the only free_percpu(wq->cpu_pwq) in this function. The caller's error path kfree()s wq without touching wq->cpu_pwq, leaking one percpu pointer table (nr_cpu_ids * sizeof(void *) bytes) per failed call. If kmemleak is enabled, we can see: unreferenced object (percpu) 0xc0fffa5b121048 (size 8): comm "insmod", pid 776, jiffies 4294682844 backtrace (crc 0): pcpu_alloc_noprof+0x665/0xac0 __alloc_workqueue+0x33f/0xa20 alloc_workqueue_noprof+0x60/0x100 Route the error through the existing enomem: cleanup and any error before this one. Cc: stable@kernel.org Fixes: 636b927eba5b ("workqueue: Make unbound workqueues to use per-cpu pool_workqueues") Signed-off-by: Breno Leitao Signed-off-by: Tejun Heo --- kernel/workqueue.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c0e58f877e08..33b721a9af02 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5654,7 +5654,9 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } - return ret; + if (ret) + goto enomem; + return 0; enomem: if (wq->cpu_pwq) { -- cgit v1.2.3