diff options
| author | Jens Axboe <axboe@kernel.dk> | 2024-12-17 08:21:46 -0700 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2024-12-17 08:21:46 -0700 |
| commit | 020b40f3562495f3c703a283ece145ffec19e82d (patch) | |
| tree | 983daa3943d6eea57d102822c68de4dd37af9aa4 /io_uring/io_uring.c | |
| parent | 99d6af6e8a22b792e1845b186f943cd10bb4b7b0 (diff) | |
| download | lwn-020b40f3562495f3c703a283ece145ffec19e82d.tar.gz lwn-020b40f3562495f3c703a283ece145ffec19e82d.zip | |
io_uring: make ctx->timeout_lock a raw spinlock
Chase reports that their tester complaints about a locking context
mismatch:
=============================
[ BUG: Invalid wait context ]
6.13.0-rc1-gf137f14b7ccb-dirty #9 Not tainted
-----------------------------
syz.1.25198/182604 is trying to lock:
ffff88805e66a358 (&ctx->timeout_lock){-.-.}-{3:3}, at: spin_lock_irq
include/linux/spinlock.h:376 [inline]
ffff88805e66a358 (&ctx->timeout_lock){-.-.}-{3:3}, at:
io_match_task_safe io_uring/io_uring.c:218 [inline]
ffff88805e66a358 (&ctx->timeout_lock){-.-.}-{3:3}, at:
io_match_task_safe+0x187/0x250 io_uring/io_uring.c:204
other info that might help us debug this:
context-{5:5}
1 lock held by syz.1.25198/182604:
#0: ffff88802b7d48c0 (&acct->lock){+.+.}-{2:2}, at:
io_acct_cancel_pending_work+0x2d/0x6b0 io_uring/io-wq.c:1049
stack backtrace:
CPU: 0 UID: 0 PID: 182604 Comm: syz.1.25198 Not tainted
6.13.0-rc1-gf137f14b7ccb-dirty #9
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:94 [inline]
dump_stack_lvl+0x82/0xd0 lib/dump_stack.c:120
print_lock_invalid_wait_context kernel/locking/lockdep.c:4826 [inline]
check_wait_context kernel/locking/lockdep.c:4898 [inline]
__lock_acquire+0x883/0x3c80 kernel/locking/lockdep.c:5176
lock_acquire.part.0+0x11b/0x370 kernel/locking/lockdep.c:5849
__raw_spin_lock_irq include/linux/spinlock_api_smp.h:119 [inline]
_raw_spin_lock_irq+0x36/0x50 kernel/locking/spinlock.c:170
spin_lock_irq include/linux/spinlock.h:376 [inline]
io_match_task_safe io_uring/io_uring.c:218 [inline]
io_match_task_safe+0x187/0x250 io_uring/io_uring.c:204
io_acct_cancel_pending_work+0xb8/0x6b0 io_uring/io-wq.c:1052
io_wq_cancel_pending_work io_uring/io-wq.c:1074 [inline]
io_wq_cancel_cb+0xb0/0x390 io_uring/io-wq.c:1112
io_uring_try_cancel_requests+0x15e/0xd70 io_uring/io_uring.c:3062
io_uring_cancel_generic+0x6ec/0x8c0 io_uring/io_uring.c:3140
io_uring_files_cancel include/linux/io_uring.h:20 [inline]
do_exit+0x494/0x27a0 kernel/exit.c:894
do_group_exit+0xb3/0x250 kernel/exit.c:1087
get_signal+0x1d77/0x1ef0 kernel/signal.c:3017
arch_do_signal_or_restart+0x79/0x5b0 arch/x86/kernel/signal.c:337
exit_to_user_mode_loop kernel/entry/common.c:111 [inline]
exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
__syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
syscall_exit_to_user_mode+0x150/0x2a0 kernel/entry/common.c:218
do_syscall_64+0xd8/0x250 arch/x86/entry/common.c:89
entry_SYSCALL_64_after_hwframe+0x77/0x7f
which is because io_uring has ctx->timeout_lock nesting inside the
io-wq acct lock, the latter of which is used from inside the scheduler
and hence is a raw spinlock, while the former is a "normal" spinlock
and can hence be sleeping on PREEMPT_RT.
Change ctx->timeout_lock to be a raw spinlock to solve this nesting
dependency on PREEMPT_RT=y.
Reported-by: chase xd <sl1589472800@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'io_uring/io_uring.c')
| -rw-r--r-- | io_uring/io_uring.c | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 06ff41484e29..605625e932eb 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -215,9 +215,9 @@ bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } @@ -333,7 +333,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->cq_wait); init_waitqueue_head(&ctx->poll_wq); spin_lock_init(&ctx->completion_lock); - spin_lock_init(&ctx->timeout_lock); + raw_spin_lock_init(&ctx->timeout_lock); INIT_WQ_LIST(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->io_buffers_comp); INIT_LIST_HEAD(&ctx->defer_list); @@ -498,10 +498,10 @@ static void io_prep_async_link(struct io_kiocb *req) if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); |