io_uring/io-wq: don't trigger hung task for syzbot craziness

Use the same trick that blk_io_schedule() does to avoid triggering the
hung task warning (and potential reboot/panic, depending on system
settings), and only wait for half the hung task timeout at the time.
If we exceed the default IO_URING_EXIT_WAIT_MAX period where we expect
things to certainly have finished unless there's a bug, then throw a
WARN_ON_ONCE() for that case.

Reported-by: syzbot+4eb282331cab6d5b6588@syzkaller.appspotmail.com
Tested-by: syzbot+4eb282331cab6d5b6588@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index cd13d8aac3d26d8a27030a146fd675071d9e5be8..aaf1dfc2176367ee2880828657f097b949df9405 100644 (file)
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -17,6 +17,7 @@
 #include <linux/task_work.h>
 #include <linux/audit.h>
 #include <linux/mmu_context.h>
+#include <linux/sched/sysctl.h>
 #include <uapi/linux/io_uring.h>
 
 #include "io-wq.h"
@@ -1316,6 +1317,8 @@ static void io_wq_cancel_tw_create(struct io_wq *wq)
 
 static void io_wq_exit_workers(struct io_wq *wq)
 {
+       unsigned long timeout, warn_timeout;
+
        if (!wq->task)
                return;
 
@@ -1325,7 +1328,24 @@ static void io_wq_exit_workers(struct io_wq *wq)
        io_wq_for_each_worker(wq, io_wq_worker_wake, NULL);
        rcu_read_unlock();
        io_worker_ref_put(wq);
-       wait_for_completion(&wq->worker_done);
+
+       /*
+        * Shut up hung task complaint, see for example
+        *
+        * https://lore.kernel.org/all/696fc9e7.a70a0220.111c58.0006.GAE@google.com/
+        *
+        * where completely overloading the system with tons of long running
+        * io-wq items can easily trigger the hung task timeout. Only sleep
+        * uninterruptibly for half that time, and warn if we exceeded end
+        * up waiting more than IO_URING_EXIT_WAIT_MAX.
+        */
+       timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+       warn_timeout = jiffies + IO_URING_EXIT_WAIT_MAX;
+       do {
+               if (wait_for_completion_timeout(&wq->worker_done, timeout))
+                       break;
+               WARN_ON_ONCE(time_after(jiffies, warn_timeout));
+       } while (1);
 
        spin_lock_irq(&wq->hash->wait.lock);
        list_del_init(&wq->wait.entry);