From 3b33e3f4a6c0296812a7ee757bdae83290e64aed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 8 Sep 2021 19:57:26 -0600 Subject: io-wq: fix silly logic error in io_task_work_match() We check for the func with an OR condition, which means it always ends up being false and we never match the task_work we want to cancel. In the unexpected case that we do exit with that pending, we can trigger a hang waiting for a worker to exit, but it was never created. syzbot reports that as such: INFO: task syz-executor687:8514 blocked for more than 143 seconds. Not tainted 5.14.0-syzkaller #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor687 state:D stack:27296 pid: 8514 ppid: 8479 flags:0x00024004 Call Trace: context_switch kernel/sched/core.c:4940 [inline] __schedule+0x940/0x26f0 kernel/sched/core.c:6287 schedule+0xd3/0x270 kernel/sched/core.c:6366 schedule_timeout+0x1db/0x2a0 kernel/time/timer.c:1857 do_wait_for_common kernel/sched/completion.c:85 [inline] __wait_for_common kernel/sched/completion.c:106 [inline] wait_for_common kernel/sched/completion.c:117 [inline] wait_for_completion+0x176/0x280 kernel/sched/completion.c:138 io_wq_exit_workers fs/io-wq.c:1162 [inline] io_wq_put_and_exit+0x40c/0xc70 fs/io-wq.c:1197 io_uring_clean_tctx fs/io_uring.c:9607 [inline] io_uring_cancel_generic+0x5fe/0x740 fs/io_uring.c:9687 io_uring_files_cancel include/linux/io_uring.h:16 [inline] do_exit+0x265/0x2a30 kernel/exit.c:780 do_group_exit+0x125/0x310 kernel/exit.c:922 get_signal+0x47f/0x2160 kernel/signal.c:2868 arch_do_signal_or_restart+0x2a9/0x1c40 arch/x86/kernel/signal.c:865 handle_signal_work kernel/entry/common.c:148 [inline] exit_to_user_mode_loop kernel/entry/common.c:172 [inline] exit_to_user_mode_prepare+0x17d/0x290 kernel/entry/common.c:209 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:302 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x445cd9 RSP: 002b:00007fc657f4b308 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: 0000000000000001 RBX: 00000000004cb448 RCX: 0000000000445cd9 RDX: 00000000000f4240 RSI: 0000000000000081 RDI: 00000000004cb44c RBP: 00000000004cb440 R08: 000000000000000e R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000049b154 R13: 0000000000000003 R14: 00007fc657f4b400 R15: 0000000000022000 While in there, also decrement accr->nr_workers. This isn't strictly needed as we're exiting, but let's make sure the accounting matches up. Fixes: 3146cba99aa2 ("io-wq: make worker creation resilient against signals") Reported-by: syzbot+f62d3e0a4ea4f38f5326@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'fs/io-wq.c') diff --git a/fs/io-wq.c b/fs/io-wq.c index 35e7ee26f7ea..c2e73ce6888a 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -1133,7 +1133,7 @@ static bool io_task_work_match(struct callback_head *cb, void *data) { struct io_worker *worker; - if (cb->func != create_worker_cb || cb->func != create_worker_cont) + if (cb->func != create_worker_cb && cb->func != create_worker_cont) return false; worker = container_of(cb, struct io_worker, create_work); return worker->wqe->wq == data; @@ -1154,9 +1154,14 @@ static void io_wq_exit_workers(struct io_wq *wq) while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; + struct io_wqe_acct *acct; worker = container_of(cb, struct io_worker, create_work); - atomic_dec(&worker->wqe->acct[worker->create_index].nr_running); + acct = io_wqe_get_acct(worker); + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); -- cgit v1.2.3