Deduplicate call to io_cqring_fill_event(), plain and easy
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Add support for splice(2).

- output file is specified as sqe->fd, so it's handled by generic code
- hash_reg_file handled by generic code as well
- len is 32bit, but should be fine
- the fd_in is registered file, when SPLICE_F_FD_IN_FIXED is set, which
is a splice flag (i.e. sqe->splice_flags).
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Preparation without functional changes. Adds io_get_file(), that allows
to grab files not only into req->file.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

req->in_async is not really needed, it only prevents propagation of
@nxt for fast not-blocked submissions. Remove it.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

io_prep_async_worker() called io_wq_assign_next() do many useless checks:
io_req_work_grab_env() was already called during prep, and @do_hashed
is not ever used. Add io_prep_next_work() -- simplified version, that
can be called io-wq.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Many operations define custom work.func before getting into an io-wq.
There are several points against:
- it calls io_wq_assign_next() from outside io-wq, that may be confusing
- sync context would go unnecessary through io_req_cancelled()
- prototypes are quite different, so work!=old_work looks strange
- makes async/sync responsibilities fuzzy
- adds extra overhead

Don't call generic path and io-wq handlers from each other, but use
helpers instead
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Don't drop an early reference, hang on to it and let the caller drop
it. This makes it behave more like "regular" requests.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If the -EAGAIN happens because of a static condition, then a poll
or later retry won't fix it. We must call it again from blocking
condition. Play it safe and ensure that any -EAGAIN condition from read
or write must retry from async context.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We must set MSG_CMSG_COMPAT if we're in compatability mode, otherwise
the iovec import for these commands will not do the right thing and fail
the command with -EINVAL.

Found by running the test suite compiled as 32-bit.

Cc: stable@vger.kernel.org
Fixes: aa1fa28f ("io_uring: add support for recvmsg()")
Fixes: 0fa03c62 ("io_uring: add support for sendmsg()")
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Follow the pattern used with other *_show_fdinfo functions and only
define and use io_uring_show_fdinfo and its helper functions if
CONFIG_PROC_FS is set.

Fixes: 87ce955b ("io_uring: add ->show_fdinfo() for the io_uring file descriptor")
Signed-off-by: NTobias Klauser <tklauser@distanz.ch>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Dan reports that he triggered a warning on ring exit doing some testing:

percpu ref (io_file_data_ref_zero) <= 0 (0) after switching to atomic
WARNING: CPU: 3 PID: 0 at lib/percpu-refcount.c:160 percpu_ref_switch_to_atomic_rcu+0xe8/0xf0
Modules linked in:
CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.6.0-rc3+ #5648
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
RIP: 0010:percpu_ref_switch_to_atomic_rcu+0xe8/0xf0
Code: e7 ff 55 e8 eb d2 80 3d bd 02 d2 00 00 75 8b 48 8b 55 d8 48 c7 c7 e8 70 e6 81 c6 05 a9 02 d2 00 01 48 8b 75 e8 e8 3a d0 c5 ff <0f> 0b e9 69 ff ff ff 90 55 48 89 fd 53 48 89 f3 48 83 ec 28 48 83
RSP: 0018:ffffc90000110ef8 EFLAGS: 00010292
RAX: 0000000000000045 RBX: 7fffffffffffffff RCX: 0000000000000000
RDX: 0000000000000045 RSI: ffffffff825be7a5 RDI: ffffffff825bc32c
RBP: ffff8881b75eac38 R08: 000000042364b941 R09: 0000000000000045
R10: ffffffff825beb40 R11: ffffffff825be78a R12: 0000607e46005aa0
R13: ffff888107dcdd00 R14: 0000000000000000 R15: 0000000000000009
FS:  0000000000000000(0000) GS:ffff8881b9d80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f49e6a5ea20 CR3: 00000001b747c004 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 rcu_core+0x1e4/0x4d0
 __do_softirq+0xdb/0x2f1
 irq_exit+0xa0/0xb0
 smp_apic_timer_interrupt+0x60/0x140
 apic_timer_interrupt+0xf/0x20
 </IRQ>
RIP: 0010:default_idle+0x23/0x170
Code: ff eb ab cc cc cc cc 0f 1f 44 00 00 41 54 55 53 65 8b 2d 10 96 92 7e 0f 1f 44 00 00 e9 07 00 00 00 0f 00 2d 21 d0 51 00 fb f4 <65> 8b 2d f6 95 92 7e 0f 1f 44 00 00 5b 5d 41 5c c3 65 8b 05 e5 95

Turns out that this is due to percpu_ref_switch_to_atomic() only
grabbing a reference to the percpu refcount if it's not already in
atomic mode. io_uring drops a ref and re-gets it when switching back to
percpu mode. We attempt to protect against this with the FFD_F_ATOMIC
bit, but that isn't reliable.

We don't actually need to juggle these refcounts between atomic and
percpu switch, we can just do them when we've switched to atomic mode.
This removes the need for FFD_F_ATOMIC, which wasn't reliable.

Fixes: 05f3fb3c ("io_uring: avoid ring quiesce for fixed file set unregister and update")
Reported-by: NDan Melnic <dmm@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Unlike the other core import helpers, import_single_range() returns 0 on
success, not the length imported. This means that links that depend on
the result of non-vec based IORING_OP_{READ,WRITE} that were added for
5.5 get errored when they should not be.

Fixes: 3a6820f2 ("io_uring: add non-vectored read/write commands")
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If work completes inline, then we should pick up a dependent link item
in __io_queue_sqe() as well. If we don't do so, we're forced to go async
with that item, which is suboptimal.

This also fixes an issue with io_put_req_find_next(), which always looks
up the next work item. That should only be done if we're dropping the
last reference to the request, to prevent multiple lookups of the same
work item.

Outside of being a fix, this also enables a good cleanup series for 5.7,
where we never have to pass 'nxt' around or into the work handlers.
Reviewed-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

After making ext4 support iopoll method:
  let ext4_file_operations's iopoll method be iomap_dio_iopoll(),
we found fio can easily hang in fio_ioring_getevents() with below fio
job:
    rm -f testfile; sync;
    sudo fio -name=fiotest -filename=testfile -iodepth=128 -thread
-rw=write -ioengine=io_uring  -hipri=1 -sqthread_poll=1 -direct=1
-bs=4k -size=10G -numjobs=8 -runtime=2000 -group_reporting
with IORING_SETUP_SQPOLL and IORING_SETUP_IOPOLL enabled.

There are two issues that results in this hang, one reason is that
when IORING_SETUP_SQPOLL and IORING_SETUP_IOPOLL are enabled, fio
does not use io_uring_enter to get completed events, it relies on
kernel io_sq_thread to poll for completed events.

Another reason is that there is a race: when io_submit_sqes() in
io_sq_thread() submits a batch of sqes, variable 'inflight' will
record the number of submitted reqs, then io_sq_thread will poll for
reqs which have been added to poll_list. But note, if some previous
reqs have been punted to io worker, these reqs will won't be in
poll_list timely. io_sq_thread() will only poll for a part of previous
submitted reqs, and then find poll_list is empty, reset variable
'inflight' to be zero. If app just waits these deferred reqs and does
not wake up io_sq_thread again, then hang happens.

For app that entirely relies on io_sq_thread to poll completed requests,
let io_iopoll_req_issued() wake up io_sq_thread properly when adding new
element to poll_list, and when io_sq_thread prepares to sleep, check
whether poll_list is empty again, if not empty, continue to poll.
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We somehow never free the idr, even though we init it for every ctx.
Free it when the rest of the ring data is freed.

Fixes: 071698e1 ("io_uring: allow registering credentials")
Reviewed-by: NStefano Garzarella <sgarzare@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If we have a chain of requests and they don't all use the same
credentials, then the head of the chain will be issued with the
credentails of the tail of the chain.

Ensure __io_queue_sqe() overrides the credentials, if they are different.

Once we do that, we can clean up the creds handling as well, by only
having io_submit_sqe() do the lookup of a personality. It doesn't need
to assign it, since __io_queue_sqe() now always does the right thing.

Fixes: 75c6a039 ("io_uring: support using a registered personality for commands")
Reported-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit a3a0e43f ("io_uring: don't enter poll loop if we have
CQEs pending"), if we already events pending, we won't enter poll loop.
In case SETUP_IOPOLL and SETUP_SQPOLL are both enabled, if app has
been terminated and don't reap pending events which are already in cq
ring, and there are some reqs in poll_list, io_sq_thread will enter
__io_iopoll_check(), and find pending events, then return, this loop
will never have a chance to exit.

I have seen this issue in fio stress tests, to fix this issue, let
io_sq_thread call io_iopoll_getevents() with argument 'min' being zero,
and remove __io_iopoll_check().

Fixes: a3a0e43f ("io_uring: don't enter poll loop if we have CQEs pending")
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch drops 'cur_mm' before calling cond_resched(), to prevent
the sq_thread from spinning even when the user process is finished.

Before this patch, if the user process ended without closing the
io_uring fd, the sq_thread continues to spin until the
'sq_thread_idle' timeout ends.

In the worst case where the 'sq_thread_idle' parameter is bigger than
INT_MAX, the sq_thread will spin forever.

Fixes: 6c271ce2 ("io_uring: add submission polling")
Signed-off-by: NStefano Garzarella <sgarzare@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

io_cleanup_req() should be called before req->io is freed, and so
shouldn't be after __io_free_req() -> __io_req_aux_free(). Also,
it will be ignored for in io_free_req_many(), which use
__io_req_aux_free().

Place cleanup_req() into __io_req_aux_free().

Fixes: 99bc4c38 ("io_uring: fix iovec leaks")
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The "kmsg" pointer can't be NULL and we have already dereferenced it so
a check here would be useless.
Reviewed-by: NStefano Garzarella <sgarzare@redhat.com>
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

fallocate_finish() is missing cancellation check. Add it.
It's safe to do that, as only flags setup and sqe fields copy are done
before it gets into __io_fallocate().
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Carter reported an issue where he could produce a stall on ring exit,
when we're cleaning up requests that match the given file table. For
this particular test case, a combination of a few things caused the
issue:

- The cq ring was overflown
- The request being canceled was in the overflow list

The combination of the above means that the cq overflow list holds a
reference to the request. The request is canceled correctly, but since
the overflow list holds a reference to it, the final put won't happen.
Since the final put doesn't happen, the request remains in the inflight.
Hence we never finish the cancelation flush.

Fix this by removing requests from the overflow list if we're canceling
them.

Cc: stable@vger.kernel.org # 5.5
Reported-by: NCarter Li 李通洲 <carter.li@eoitek.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Jonas reports that he sometimes sees -97/-22 error returns from
sendmsg, if it gets punted async. This is due to not retaining the
sockaddr_storage between calls. Include that in the state we copy when
going async.

Cc: stable@vger.kernel.org # 5.3+
Reported-by: NJonas Bonn <jonas@norrbonn.se>
Tested-by: NJonas Bonn <jonas@norrbonn.se>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Normally we cancel all work we track, but for untracked work we could
leave the async worker behind until that work completes. This is totally
fine, but does leave resources pending after the task is gone until that
work completes.

Cancel work that this task queued up when it goes away.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

As in the previous patch, make openat*_prep() and statx_prep() handle
double preparation to avoid resource leakage.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Requests may be prepared multiple times with ->io allocated (i.e. async
prepared). Preparation functions don't handle it and forget about
previously allocated resources. This may happen in case of:
- spurious defer_check
- non-head (i.e. async prepared) request executed in sync (via nxt).

Make the handlers check, whether they already allocated resources, which
is true IFF REQ_F_NEED_CLEANUP is set.

Cc: stable@vger.kernel.org # 5.5
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

First, io_close() misses filp_close() and io_cqring_add_event(), when
f_op->flush is defined. That's because in this case it will
io_queue_async_work() itself not grabbing files, so the corresponding
chunk in io_close_finish() won't be executed.

Second, when submitted through io_wq_submit_work(), it will do
filp_close() and *_add_event() twice: first inline in io_close(),
and the second one in call to io_close_finish() from io_close().
The second one will also fire, because it was submitted async through
generic path, and so have grabbed files.

And the last nice thing is to remove this weird pilgrimage with checking
work/old_work and casting it to nxt. Just use a helper instead.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Don't just check for dirfd == -1, we should allow AT_FDCWD as well for
relative lookups.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This passes it in to io-wq, so it assumes the right fs_struct when
executing async work that may need to do lookups.

Cc: stable@vger.kernel.org # 5.3+
Signed-off-by: NJens Axboe <axboe@kernel.dk>

For non-blocking issue, we set IOCB_NOWAIT in the kiocb. However, on a
raw block device, this yields an -EOPNOTSUPP return, as non-blocking
writes aren't supported. Turn this -EOPNOTSUPP into -EAGAIN, so we retry
from blocking context with IOCB_NOWAIT cleared.

Cc: stable@vger.kernel.org # 5.5
Signed-off-by: NJens Axboe <axboe@kernel.dk>

openat() and statx() may have allocated ->open.filename, which should be
be put. Add cleanup handlers for them.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Allocated iovec is freed only in io_{read,write,send,recv)(), and just
leaves it if an error occured. There are plenty of such cases:
- cancellation of non-head requests
- fail grabbing files in __io_queue_sqe()
- set REQ_F_NOWAIT and returning in __io_queue_sqe()

Add REQ_F_NEED_CLEANUP, which will force such requests with custom
allocated resourses go through cleanup handlers on put.

Cc: stable@vger.kernel.org # 5.5
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

struct io_async_open is unused, remove it.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In io_uring_poll() we must flush overflowed CQ events before to
check if there are CQ events available, to avoid missing events.

We call the io_cqring_events() that checks and flushes any overflow
and returns the number of CQ events available.
Signed-off-by: NStefano Garzarella <sgarzare@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

All of these opcodes take a directory file descriptor. We can't easily
support fixed files for these operations, and the use case for that
probably isn't all that clear (or sensible) anyway.

Disable IOSQE_FIXED_FILE for these operations.
Reported-by: NStefan Metzmacher <metze@samba.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

After defer, a request will be prepared, that includes allocating iovec
if needed, and then submitted through io_wq_submit_work() but not custom
handler (e.g. io_rw_async()/io_sendrecv_async()). However, it'll leak
iovec, as it's in io-wq and the code goes as follows:

io_read() {
	if (!io_wq_current_is_worker())
		kfree(iovec);
}

Put all deallocation logic in io_{read,write,send,recv}(), which will
leave the memory, if going async with -EAGAIN.

It also fixes a leak after failed io_alloc_async_ctx() in
io_{recv,send}_msg().

Cc: stable@vger.kernel.org # 5.5
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Make bitfields of size 1 bit be unsigned (since there is no room
for the sign bit).
This clears up the sparse warnings:

  CHECK   ../fs/io_uring.c
../fs/io_uring.c:207:50: error: dubious one-bit signed bitfield
../fs/io_uring.c:208:55: error: dubious one-bit signed bitfield
../fs/io_uring.c:209:63: error: dubious one-bit signed bitfield
../fs/io_uring.c:210:54: error: dubious one-bit signed bitfield
../fs/io_uring.c:211:57: error: dubious one-bit signed bitfield

Found by sight and then verified with sparse.

Fixes: 69b3e546 ("io_uring: change io_ring_ctx bool fields into bit fields")
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: io-uring@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Fail fast if can't grab mm, so past that requests always have an mm
when required. This allows us to remove req->user altogether.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

syzbot reports a use-after-free in io_ring_file_ref_switch() when it
tries to switch back to percpu mode. When we put the final reference to
the table by calling percpu_ref_kill_and_confirm(), we don't want the
zero reference to queue async work for flushing the potentially queued
up items. We currently do a few flush_work(), but they merely paper
around the issue, since the work item may not have been queued yet
depending on the when the percpu-ref callback gets run.

Coming into the file unregister, we know we have the ring quiesced.
io_ring_file_ref_switch() can check for whether or not the ref is dying
or not, and not queue anything async at that point. Once the ref has
been confirmed killed, flush any potential items manually.

Reported-by: syzbot+7caeaea49c2c8a591e3d@syzkaller.appspotmail.com
Fixes: 05f3fb3c ("io_uring: avoid ring quiesce for fixed file set unregister and update")
Signed-off-by: NJens Axboe <axboe@kernel.dk>

As part of io_uring shutdown, we cancel work that is pending and won't
necessarily complete on its own. That includes requests like poll
commands and timeouts.

If we're using SQPOLL for kernel side submission and we shutdown the
ring immediately after queueing such work, we can race with the sqthread
doing the submission. This means we may miss cancelling some work, which
results in the io_uring shutdown hanging forever.

Cc: stable@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@kernel.dk>