syzbot reports an issue with overflow filling for IOPOLL:

WARNING: CPU: 0 PID: 28 at io_uring/io_uring.c:734 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734
CPU: 0 PID: 28 Comm: kworker/u4:1 Not tainted 6.2.0-rc3-syzkaller-16369-g358a161a6a9e #0
Workqueue: events_unbound io_ring_exit_work
Call trace:
 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734
 io_req_cqe_overflow+0x5c/0x70 io_uring/io_uring.c:773
 io_fill_cqe_req io_uring/io_uring.h:168 [inline]
 io_do_iopoll+0x474/0x62c io_uring/rw.c:1065
 io_iopoll_try_reap_events+0x6c/0x108 io_uring/io_uring.c:1513
 io_uring_try_cancel_requests+0x13c/0x258 io_uring/io_uring.c:3056
 io_ring_exit_work+0xec/0x390 io_uring/io_uring.c:2869
 process_one_work+0x2d8/0x504 kernel/workqueue.c:2289
 worker_thread+0x340/0x610 kernel/workqueue.c:2436
 kthread+0x12c/0x158 kernel/kthread.c:376
 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:863

There is no real problem for normal IOPOLL as flush is also called with
uring_lock taken, but it's getting more complicated for IOPOLL|SQPOLL,
for which __io_cqring_overflow_flush() happens from the CQ waiting path.

Reported-and-tested-by: syzbot+6805087452d72929404e@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org # 5.10+
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

If we have multiple requests waiting on the same target poll waitqueue,
then it's quite possible to get a request triggered and get disappointed
in not being able to make any progress with it. If we race in doing so,
we'll potentially leave the poll request on the internal tables, but
removed from the waitqueue. That means that any subsequent trigger of
the poll waitqueue will not kick that request into action, causing an
application to potentially wait for completion of a request that will
never happen.

Fix this by adding a new poll return state, IOU_POLL_REISSUE. Rather
than have complicated logic for how to re-arm a given type of request,
just punt it for a reissue.

While in there, move the 'ret' variable to the only section where it
gets used. This avoids confusion the scope of it.

Cc: stable@vger.kernel.org
Fixes: eb0089d629ba ("io_uring: single shot poll removal optimisation")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

A previous commit split the hash table for polled requests into two
parts, but didn't get the fdinfo output updated. This means that it's
less useful for debugging, as we may think a given request is not pending
poll.

Fix this up by dumping the locked hash table contents too.

Fixes: 9ca9fb24d5fe ("io_uring: mutex locked poll hashing")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

If we don't, then we may lose access to it completely, leading to a
request leak. This will eventually stall the ring exit process as
well.

Cc: stable@vger.kernel.org
Fixes: 49f1c68e048f ("io_uring: optimise submission side poll_refs")
Reported-and-tested-by: syzbot+6c95df01470a47fc3af4@syzkaller.appspotmail.com
Link: https://lore.kernel.org/io-uring/0000000000009f829805f1ce87b2@google.com/
Suggested-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We have two types of task_work based creation, one is using an existing
worker to setup a new one (eg when going to sleep and we have no free
workers), and the other is allocating a new worker. Only the latter
should be freed when we cancel task_work creation for a new worker.

Fixes: af82425c6a2d ("io_uring/io-wq: free worker if task_work creation is canceled")
Reported-by: syzbot+d56ec896af3637bdb7e4@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in
particular we rearm it anew every time we get into
io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2
CQEs and getting a task_work in the middle may double the timeout value,
or even worse in some cases task may wait indefinitely.

Cc: stable@vger.kernel.org
Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.1672915663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Locking around CQE posting is complex and depends on options the ring is
created with, add more thorough lockdep annotations checking all
invariants.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/aa3770b4eacae3915d782cc2ab2f395a99b4b232.1672795976.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Unlike normal tw, nothing prevents deferred tw to be executed right
after an tw item added to ->work_llist in io_req_local_work_add(). For
instance, the waiting task may get waken up by CQ posting or a normal
tw. Thus we need to pin the ring for the rest of io_req_local_work_add()

Cc: stable@vger.kernel.org
Fixes: c0e0d6ba25f18 ("io_uring: add IORING_SETUP_DEFER_TASKRUN")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/1a79362b9c10b8523ef70b061d96523650a23344.1672795998.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

If we cancel the task_work, the worker will never come into existance.
As this is the last reference to it, ensure that we get it freed
appropriately.

Cc: stable@vger.kernel.org
Reported-by: 진호 <wnwlsgh98@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We only check the register opcode value inside the restricted ring
section, move it into the main io_uring_register() function instead
and check it up front.

Signed-off-by: Jens Axboe <axboe@kernel.dk>