Frederic Weisbecker 56799bc035 perf: Fix hang while freeing sigtrap event ... Perf can hang while freeing a sigtrap event if a related deferred signal hadn't managed to be sent before the file got closed: perf_event_overflow() task_work_add(perf_pending_task) fput() task_work_add(____fput()) task_work_run() ____fput() perf_release() perf_event_release_kernel() _free_event() perf_pending_task_sync() task_work_cancel() -> FAILED rcuwait_wait_event() Once task_work_run() is running, the list of pending callbacks is removed from the task_struct and from this point on task_work_cancel() can't remove any pending and not yet started work items, hence the task_work_cancel() failure and the hang on rcuwait_wait_event(). Task work could be changed to remove one work at a time, so a work running on the current task can always cancel a pending one, however the wait / wake design is still subject to inverted dependencies when remote targets are involved, as pictured by Oleg: T1 T2 fd = perf_event_open(pid => T2->pid); fd = perf_event_open(pid => T1->pid); close(fd) close(fd) <IRQ> <IRQ> perf_event_overflow() perf_event_overflow() task_work_add(perf_pending_task) task_work_add(perf_pending_task) </IRQ> </IRQ> fput() fput() task_work_add(____fput()) task_work_add(____fput()) task_work_run() task_work_run() ____fput() ____fput() perf_release() perf_release() perf_event_release_kernel() perf_event_release_kernel() _free_event() _free_event() perf_pending_task_sync() perf_pending_task_sync() rcuwait_wait_event() rcuwait_wait_event() Therefore the only option left is to acquire the event reference count upon queueing the perf task work and release it from the task work, just like it was done before 3a5465418f ("perf: Fix event leak upon exec and file release") but without the leaks it fixed. Some adjustments are necessary to make it work: * A child event might dereference its parent upon freeing. Care must be taken to release the parent last. * Some places assuming the event doesn't have any reference held and therefore can be freed right away must instead put the reference and let the reference counting to its job. Reported-by: "Yi Lai" <yi1.lai@linux.intel.com> Closes: https://lore.kernel.org/all/Zx9Losv4YcJowaP%2F@ly-workstation/ Reported-by: syzbot+3c4321e10eea460eb606@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/673adf75.050a0220.87769.0024.GAE@google.com/ Fixes: 3a5465418f ("perf: Fix event leak upon exec and file release") Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20250304135446.18905-1-frederic@kernel.org		2025-04-08 20:55:43 +02:00
..
acpi	misc: Constify amba_id table	2025-03-29 18:25:34 -07:00
asm-generic	RISC-V Patches for the 6.15 Merge Window, Part 1	2025-04-04 09:49:17 -07:00
clocksource
crypto	This update includes the following changes:	2025-03-29 10:01:55 -07:00
cxl	cxl for v6.15	2025-04-02 20:04:43 -07:00
drm	Rust changes for v6.15	2025-03-30 17:03:26 -07:00
dt-bindings	Char/Misc/IIO driver updates for 6.15-rc1	2025-04-01 11:26:08 -07:00
hyperv
keys
kunit
kvm
linux	perf: Fix hang while freeing sigtrap event	2025-04-08 20:55:43 +02:00
math-emu
media
memory
misc
net	treewide: Switch/rename to timer_delete[_sync]()	2025-04-05 10:30:12 +02:00
pcmcia
ras
rdma
rv
scsi
soc	soc: driver updates for 6.15, part 1	2025-03-27 09:05:55 -07:00
sound	soundwire updates for 6.15	2025-04-01 12:43:13 -07:00
target
trace	tracing/timers: Rename the hrtimer_init event to hrtimer_setup	2025-04-05 10:30:17 +02:00
uapi	io_uring-6.15-20250403	2025-04-03 15:48:58 -07:00
ufs
vdso
video
xen
Kbuild