Timeouts' sequence offset (i.e. sqe->off) is stored in
req->submit.sequence under a false name. Keep it in timeout.data
instead. The unused space for sequence will be reclaimed in the
following patches.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This field contains a pointer to addrlen and checking to see if it's set
returns -EINVAL if the caller sets addr & addrlen pointers.
Fixes: 17f2fe35d0 ("io_uring: add support for IORING_OP_ACCEPT")
Signed-off-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently pass in 4 arguments outside of the bounded size. In
preparation for adding one more argument, let's bundle them up in
a struct to make it more readable.
No functional changes in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Read/write requests to devices without implemented read/write_iter
using fixed buffers can cause general protection fault, which totally
hangs a machine.
io_import_fixed() initialises iov_iter with bvec, but loop_rw_iter()
accesses it as iovec, dereferencing random address.
kmap() page by page in this case
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This allows an application to call connect() in an async fashion. Like
other opcodes, we first try a non-blocking connect, then punt to async
context if we have to.
Note that we can still return -EINPROGRESS, and in that case the caller
should use IORING_OP_POLL_ADD to do an async wait for completion of the
connect request (just like for regular connect(2), except we can do it
async here too).
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We return -EBUSY on submit when we have a CQ ring overflow backlog, but
that can be a bit problematic if the application is using pure userspace
poll of the CQ ring. For that case, if the ring briefly overflowed and
we have pending entries in the backlog, the submit flushes the backlog
successfully but still returns -EBUSY. If we're able to fully flush the
CQ ring backlog, let the submission proceed.
Reported-by: Dan Melnic <dmm@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pass only non-null @nxt to io_issue_sqe() and handle it at the caller's
side. And propagate it.
- kiocb_done() is only called from io_read() and io_write(), which are
only called from io_issue_sqe(), so it's @nxt != NULL
- io_put_req_find_next() is called either with explicitly non-null local
nxt, or from one of the functions in io_issue_sqe() switch (or their
callees).
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
"if (nxt)" is always true, as it was checked in the while's condition.
io_wq_current_is_worker() is unnecessary, as non-async callers don't
pass nxt, so io_queue_async_work() will be called for them anyway.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make io_req_find_next() and io_req_link_next() to accept only non-null
nxt, and handle it in callers.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is only one one-liner user of io_free_req_find_next(). Inline it.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The number of SQEs to submit is specified by a user, so io_get_sqring()
in most of the cases succeeds. Hint compilers about that.
Checking ASM genereted by gcc 9.2.0 for x64, there is one branch
misprediction.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
__io_submit_sqe() is issuing requests, so call it as
such. Moreover, it ends by calling io_iopoll_req_issued().
Rename it and make terminology clearer.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't have shadow requests anymore, so get rid of the shadow
argument. Add the user_data argument, as that's often useful to easily
match up requests, instead of having to look at request pointers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There's an issue with the shadow drain logic in that we drop the
completion lock after deciding to defer a request, then re-grab it later
and assume that the state is still the same. In the mean time, someone
else completing a request could have found and issued it. This can cause
a stall in the queue, by having a shadow request inserted that nobody is
going to drain.
Additionally, if we fail allocating the shadow request, we simply ignore
the drain.
Instead of using a shadow request, defer the next request/link instead.
This also has the following advantages:
- removes semi-duplicated code
- doesn't allocate memory for shadows
- works better if only the head marked for drain
- doesn't need complex synchronisation
On the flip side, it removes the shadow->seq ==
last_drain_in_in_link->seq optimization. That shouldn't be a common
case, and can always be added back, if needed.
Fixes: 4fe2c96315 ("io_uring: add support for link with drain")
Cc: Jackie Liu <liuyun01@kylinos.cn>
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we find new work to process within the work handler, we queue the
linked timeout before we have issued the new work. This can be
problematic for very short timeouts, as we have a window where the new
work isn't visible.
Allow the work handler to store a callback function for this in the work
item, and flag it with IO_WQ_WORK_CB if the caller has done so. If that
is set, then io-wq will call the callback when it has setup the new work
item.
Reported-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently try and start the next link when we put the request, and
only if we were going to free it. This means that the optimization to
continue executing requests from the same context often fails, as we're
not putting the final reference.
Add REQ_F_LINK_NEXT to keep track of this, and allow io_uring to find the
next request more efficiently.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently rely on the ring destroy on cleaning things up in case of
failure, but io_allocate_scq_urings() can leave things half initialized
if only parts of it fails.
Be nice and return with either everything setup in success, or return an
error with things nicely cleaned up.
Reported-by: syzbot+0d818c0d39399188f393@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Always mark requests with allocated sqe and deallocate it in
__io_free_req(). It's easier to follow and doesn't add edge cases.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently clear the linked timeout field if we cancel such a timeout,
but we should only attempt to cancel if it's the first one we see.
Others should simply be freed like other requests, as they haven't
been started yet.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
let have a dependant link: REQ -> LINK_TIMEOUT -> LINK_TIMEOUT
1. submission stage: submission references for REQ and LINK_TIMEOUT
are dropped. So, references respectively (1,1,2)
2. io_put(REQ) + FAIL_LINKS stage: calls io_fail_links(), which for all
linked timeouts will call cancel_timeout() and drop 1 reference.
So, references after: (0,0,1). That's a leak.
Make it treat only the first linked timeout as such, and pass others
through __io_double_put_req().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pass any IORING_OP_LINK_TIMEOUT request further, where it will
eventually fail in io_issue_sqe().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If io_req_defer() failed, it needs to cancel a dependant link.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently don't explicitly break links if a request is cancelled, but
we should. Add explicitly link breakage for all types of request
cancellations that we support.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently a poll request fills a completion entry of 0, even if it got
cancelled. This is odd, and it makes it harder to support with chains.
Ensure that it returns -ECANCELED in the completions events if it got
cancelled, and furthermore ensure that the linked timeout that triggered
it completes with -ETIME if we did indeed trigger the completions
through a timeout.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the conversion to io-wq, we no longer use that flag. Kill it.
Fixes: 561fb04a6a ("io_uring: replace workqueue usage with io-wq")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We have an issue with timeout links that are deeper in the submit chain,
because we only handle it upfront, not from later submissions. Move the
prep + issue of the timeout link to the async work prep handler, and do
it normally for non-async queue. If we validate and prepare the timeout
links upfront when we first see them, there's nothing stopping us from
supporting any sort of nesting.
Fixes: 2665abfd75 ("io_uring: add support for linked SQE timeouts")
Reported-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are a few reasons for this:
- As a prep to improving the linked timeout logic
- io_timeout is the biggest member in the io_kiocb opcode union
This also enables a few cleanups, like unifying the timer setup between
IORING_OP_TIMEOUT and IORING_OP_LINK_TIMEOUT, and not needing multiple
arguments to the link/prep helpers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we don't use the normal completion path, we may skip killing links
that should be errored and freed. Add __io_double_put_req() for use
within the completion path itself, other calls should just use
io_double_put_req().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
__io_queue_sqe(), io_queue_sqe(), io_queue_link_head() all return 0/err,
but the caller doesn't care since the errors are handled inline. Clean
these up and just make them void.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have a linked request, this enables us to pass it back directly
without having to go through async context.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=YZ9s
-----END PGP SIGNATURE-----
Merge tag 'for-5.5/io_uring-20191121' of git://git.kernel.dk/linux-block
Pull io_uring updates from Jens Axboe:
"A lot of stuff has been going on this cycle, with improving the
support for networked IO (and hence unbounded request completion
times) being one of the major themes. There's been a set of fixes done
this week, I'll send those out as well once we're certain we're fully
happy with them.
This contains:
- Unification of the "normal" submit path and the SQPOLL path (Pavel)
- Support for sparse (and bigger) file sets, and updating of those
file sets without needing to unregister/register again.
- Independently sized CQ ring, instead of just making it always 2x
the SQ ring size. This makes it more flexible for networked
applications.
- Support for overflowed CQ ring, never dropping events but providing
backpressure on submits.
- Add support for absolute timeouts, not just relative ones.
- Support for generic cancellations. This divorces io_uring from
workqueues as well, which additionally gets us one step closer to
generic async system call support.
- With cancellations, we can support grabbing the process file table
as well, just like we do mm context. This allows support for system
calls that create file descriptors, like accept4() support that's
built on top of that.
- Support for io_uring tracing (Dmitrii)
- Support for linked timeouts. These abort an operation if it isn't
completed by the time noted in the linke timeout.
- Speedup tracking of poll requests
- Various cleanups making the coder easier to follow (Jackie, Pavel,
Bob, YueHaibing, me)
- Update MAINTAINERS with new io_uring list"
* tag 'for-5.5/io_uring-20191121' of git://git.kernel.dk/linux-block: (64 commits)
io_uring: make POLL_ADD/POLL_REMOVE scale better
io-wq: remove now redundant struct io_wq_nulls_list
io_uring: Fix getting file for non-fd opcodes
io_uring: introduce req_need_defer()
io_uring: clean up io_uring_cancel_files()
io-wq: ensure free/busy list browsing see all items
io-wq: ensure we have a stable view of ->cur_work for cancellations
io_wq: add get/put_work handlers to io_wq_create()
io_uring: check for validity of ->rings in teardown
io_uring: fix potential deadlock in io_poll_wake()
io_uring: use correct "is IO worker" helper
io_uring: fix -ENOENT issue with linked timer with short timeout
io_uring: don't do flush cancel under inflight_lock
io_uring: flag SQPOLL busy condition to userspace
io_uring: make ASYNC_CANCEL work with poll and timeout
io_uring: provide fallback request for OOM situations
io_uring: convert accept4() -ERESTARTSYS into -EINTR
io_uring: fix error clear of ->file_table in io_sqe_files_register()
io_uring: separate the io_free_req and io_free_req_find_next interface
io_uring: keep io_put_req only responsible for release and put req
...
One of the obvious use cases for these commands is networking, where
it's not uncommon to have tons of sockets open and polled for. The
current implementation uses a list for insertion and lookup, which works
fine for file based use cases where the count is usually low, it breaks
down somewhat for higher number of files / sockets. A test case with
30k sockets being polled for and cancelled takes:
real 0m6.968s
user 0m0.002s
sys 0m6.936s
with the patch it takes:
real 0m0.233s
user 0m0.010s
sys 0m0.176s
If you go to 50k sockets, it gets even more abysmal with the current
code:
real 0m40.602s
user 0m0.010s
sys 0m40.555s
with the patch it takes:
real 0m0.398s
user 0m0.000s
sys 0m0.341s
Change is pretty straight forward, just replace the cancel_list with
a red/black tree instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For timeout requests and bunch of others io_uring tries to grab a file
with specified fd, which is usually stdin/fd=0.
Update io_op_needs_file()
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't use the return value anymore, drop it. Also drop the
unecessary double cancel_req value check.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A test case was reported where two linked reads with registered buffers
failed the second link always. This is because we set the expected value
of a request in req->result, and if we don't get this result, then we
fail the dependent links. For some reason the registered buffer import
returned -ERROR/0, while the normal import returns -ERROR/length. This
broke linked commands with registered buffers.
Fix this by making io_import_fixed() correctly return the mapped length.
Cc: stable@vger.kernel.org # v5.3
Reported-by: 李通洲 <carter.li@eoitek.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For timeout requests io_uring tries to grab a file with specified fd,
which is usually stdin/fd=0.
Update io_op_needs_file()
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For cancellation, we need to ensure that the work item stays valid for
as long as ->cur_work is valid. Right now we can't safely dereference
the work item even under the wqe->lock, because while the ->cur_work
pointer will remain valid, the work could be completing and be freed
in parallel.
Only invoke ->get/put_work() on items we know that the caller queued
themselves. Add IO_WQ_WORK_INTERNAL for io-wq to use, which is needed
when we're queueing a flush item, for instance.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We attempt to run the poll completion inline, but we're using trylock to
do so. This avoids a deadlock since we're grabbing the locks in reverse
order at this point, we already hold the poll wq lock and we're trying
to grab the completion lock, while the normal rules are the reverse of
that order.
IO completion for a timeout link will need to grab the completion lock,
but that's not safe from this context. Put the completion under the
completion_lock in io_poll_wake(), and mark the request as entering
the completion with the completion_lock already held.
Fixes: 2665abfd75 ("io_uring: add support for linked SQE timeouts")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since we switched to io-wq, the dependent link optimization for when to
pass back work inline has been broken. Fix this by providing a suitable
io-wq helper for io_uring to use to detect when to do this.
Fixes: 561fb04a6a ("io_uring: replace workqueue usage with io-wq")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we make sequence == 0 be the same as sequence == 1, but that's
not super useful if the intent is really to have a timeout that's just
a pure timeout.
If the user passes in sqe->off == 0, then don't apply any sequence logic
to the request, let it purely be driven by the timeout specified.
Reported-by: 李通洲 <carter.li@eoitek.com>
Reviewed-by: 李通洲 <carter.li@eoitek.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If you prep a read (for example) that needs to get punted to async
context with a timer, if the timeout is sufficiently short, the timer
request will get completed with -ENOENT as it could not find the read.
The issue is that we prep and start the timer before we start the read.
Hence the timer can trigger before the read is even started, and the end
result is then that the timer completes with -ENOENT, while the read
starts instead of being cancelled by the timer.
Fix this by splitting the linked timer into two parts:
1) Prep and validate the linked timer
2) Start timer
The read is then started between steps 1 and 2, so we know that the
timer will always have a consistent view of the read request state.
Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can't safely cancel under the inflight lock. If the work hasn't been
started yet, then io_wq_cancel_work() simply marks the work as cancelled
and invokes the work handler. But if the work completion needs to grab
the inflight lock because it's grabbing user files, then we'll deadlock
trying to finish the work as we already hold that lock.
Instead grab a reference to the request, if it isn't already zero. If
it's zero, then we know it's going through completion anyway, and we
can safely ignore it. If it's not zero, then we can drop the lock and
attempt to cancel from there.
This also fixes a missing finish_wait() at the end of
io_uring_cancel_files().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now that we have backpressure, for SQPOLL, we have one more condition
that warrants flagging that the application needs to enter the kernel:
we failed to submit IO due to backpressure. Make sure we catch that
and flag it appropriately.
If we run into backpressure issues with the SQPOLL thread, flag it
as such to the application by setting IORING_SQ_NEED_WAKEUP. This will
cause the application to enter the kernel, and that will flush the
backlog and clear the condition.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It's a little confusing that we have multiple types of command
cancellation opcodes now that we have a generic one. Make the generic
one work with POLL_ADD and TIMEOUT commands as well, that makes for an
easier to use API for the application. The fact that they currently
don't is a bit confusing.
Add a helper that takes care of it, so we can user it from both
IORING_OP_ASYNC_CANCEL and from the linked timeout cancellation.
Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
One thing that really sucks for userspace APIs is if the kernel passes
back -ENOMEM/-EAGAIN for resource shortages. The application really has
no idea of what to do in those cases. Should it try and reap
completions? Probably a good idea. Will it solve the issue? Who knows.
This patch adds a simple fallback mechanism if we fail to allocate
memory for a request. If we fail allocating memory from the slab for a
request, we punt to a pre-allocated request. There's just one of these
per io_ring_ctx, but the important part is if we ever return -EBUSY to
the application, the applications knows that it can wait for events and
make forward progress when events have completed. This is the important
part.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we cancel a pending accept operating with a signal, we get
-ERESTARTSYS returned. Turn that into -EINTR for userspace, we should
not be return -ERESTARTSYS.
Fixes: 17f2fe35d0 ("io_uring: add support for IORING_OP_ACCEPT")
Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Similar to the distinction between io_put_req and io_put_req_find_next,
io_free_req has been modified similarly, with no functional changes.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We already have io_put_req_find_next to find the next req of the link.
we should not use the io_put_req function to find them. They should be
functions of the same level.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Many times, the core of the function is req, and req has already set
req->ctx at initialization time, so there is no need to pass in the
ctx from the caller.
Cleanup, no functional change.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the recent flurry of additions and changes to io_uring, the
layout of io_ring_ctx has become a bit stale. We're right now at
704 bytes in size on my x86-64 build, or 11 cachelines. This
patch does two things:
- We have to completion structs embedded, that we only use for
quiesce of the ctx (or shutdown) and for sqthread init cases.
That 2x32 bytes right there, let's dynamically allocate them.
- Reorder the struct a bit with an eye on cachelines, use cases,
and holes.
With this patch, we're down to 512 bytes, or 8 cachelines.
Reviewed-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now that io-wq supports separating the two request lifetime types, mark
the following IO as having unbounded runtimes:
- Any read/write to a non-regular file
- Any specific networked IO
- Any poll command
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring supports request types that basically have two different
lifetimes:
1) Bounded completion time. These are requests like disk reads or writes,
which we know will finish in a finite amount of time.
2) Unbounded completion time. These are generally networked IO, where we
have no idea how long they will take to complete. Another example is
POLL commands.
This patch provides support for io-wq to handle these differently, so we
don't starve bounded requests by tying up workers for too long. By default
all work is bounded, unless otherwise specified in the work item.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we drop completion events, if the CQ ring is full. That's fine
for requests with bounded completion times, but it may make it harder or
impossible to use io_uring with networked IO where request completion
times are generally unbounded. Or with POLL, for example, which is also
unbounded.
After this patch, we never overflow the ring, we simply store requests
in a backlog for later flushing. This flushing is done automatically by
the kernel. To prevent the backlog from growing indefinitely, if the
backlog is non-empty, we apply back pressure on IO submissions. Any
attempt to submit new IO with a non-empty backlog will get an -EBUSY
return from the kernel. This is a signal to the application that it has
backlogged CQ events, and that it must reap those before being allowed
to submit more IO.
Note that if we do return -EBUSY, we will have filled whatever
backlogged events into the CQ ring first, if there's room. This means
the application can safely reap events WITHOUT entering the kernel and
waiting for them, they are already available in the CQ ring.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is in preparation for handling CQ ring overflow a bit smarter. We
should not have any functional changes in this patch. Most of the
changes are fairly straight forward, the only ones that stick out a bit
are the ones that change __io_free_req() to take the reference count
into account. If the request hasn't been submitted yet, we know it's
safe to simply ignore references and free it. But let's clean these up
too, as later patches will depend on the caller doing the right thing if
the completion logging grabs a reference to the request.
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The rings can be derived from the ctx, and we need the ctx there for
a future change.
No functional changes in this patch.
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
While we have support for generic timeouts, we don't have a way to tie
a timeout to a specific SQE. The generic timeouts simply trigger wakeups
on the CQ ring.
This adds support for IORING_OP_LINK_TIMEOUT. This command is only valid
as a link to a previous command. The timeout specific can be either
relative or absolute, following the same rules as IORING_OP_TIMEOUT. If
the timeout triggers before the dependent command completes, it will
attempt to cancel that command. Likewise, if the dependent command
completes before the timeout triggers, it will cancel the timeout.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We're going to need this helper in a future patch, so move it out
of io_async_cancel() and into its own separate function.
No functional changes in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Stack allocated struct sqe_submit is passed down to the submission path
along with a request (a.k.a. struct io_kiocb), and will be copied into
req->submit for async requests.
As space for it is already allocated, fill req->submit in the first
place instead of using on-stack one. As a result:
1. sqe->submit is the only place for sqe_submit and is always valid,
so we don't need to track which one to use.
2. don't need to copy in case of async
3. allows to simplify the code by not carrying it as an argument all
the way down
4. allows to reduce number of function arguments / potentially improve
spilling
The downside is that stack is most probably be cached, that's not true
for just allocated memory for a request. Another concern is cache
pollution. Though, a request would be touched and fetched along with
req->submit at some point anyway, so shouldn't be a problem.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Let io_submit_sqes() to allocate io_kiocb before fetching an sqe.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
After a call to io_submit_sqe(), it's already known whether it needs
to queue a link or not. Do it there, as it's simplier and doesn't keep
an extra variable across the loop.
Reviewed-by：Bob Liu <bob.liu@oracle.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_submit_sqes() and io_ring_submit() are doing the same stuff with
a little difference. Deduplicate them.
Reviewed-by：Bob Liu <bob.liu@oracle.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We had no more use for this flag after the conversion to io-wq, kill it
off.
Fixes: 561fb04a6a ("io_uring: replace workqueue usage with io-wq")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a request fails, we need to ensure we set REQ_F_FAIL_LINK on it if
REQ_F_LINK is set. Any failure in the chain should break the chain.
We were missing a few spots where this should be done. It might be nice
to generalize this somewhat at some point, as long as we factor in the
fact that failure looks different for each request type.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
As introduced by commit:
ba816ad61f ("io_uring: run dependent links inline if possible")
enable inline dependent link running for poll commands.
io_poll_complete_work() is the most important change, as it allows a
linked sequence of { POLL, READ } (for example) to proceed inline
instead of needing to get punted to another async context. The
submission side only potentially matters for sqthread, but may as well
include that bit.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently don't have a completion event trace, add one of those. And
to better be able to match up submissions and completions, add user_data
to the submission trace as well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We didn't use -ERESTARTSYS to tell the application layer to restart the
system call, but instead return -EINTR. we can set -EINTR directly when
wakeup by the signal, which can help us save an assignment operation and
comparison operation.
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds support for IORING_OP_ASYNC_CANCEL, which will attempt to
cancel requests that have been punted to async context and are now
in-flight. This works for regular read/write requests to files, as
long as they haven't been started yet. For socket based IO (or things
like accept4(2)), we can cancel work that is already running as well.
To cancel a request, the sqe must have ->addr set to the user_data of
the request it wishes to cancel. If the request is cancelled
successfully, the original request is completed with -ECANCELED
and the cancel request is completed with a result of 0. If the
request was already running, the original may or may not complete
in error. The cancel request will complete with -EALREADY for that
case. And finally, if the request to cancel wasn't found, the cancel
request is completed with -ENOENT.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We use io_kiocb->result == -EAGAIN as a way to know if we need to
re-submit a polled request, as -EAGAIN reporting happens out-of-line
for IO submission failures. This field is cleared when we originally
allocate the request, but it isn't reset when we retry the submission
from async context. This can cause issues where we think something
needs a re-issue, but we're really just reading stale data.
Reset ->result whenever we re-prep a request for polled submission.
Cc: stable@vger.kernel.org
Fixes: 9e645e1105 ("io_uring: add support for sqe links")
Reported-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
syzbot reported an issue where we crash at setup time if failslab is
used. The issue is that io_wq_create() returns an error pointer on
failure, not NULL. Hence io_uring thought the io-wq was setup just
fine, but in reality it's a garbage error pointer.
Use IS_ERR() instead of a NULL check, and assign ret appropriately.
Reported-by: syzbot+221cc24572a2fed23b6b@syzkaller.appspotmail.com
Fixes: 561fb04a6a ("io_uring: replace workqueue usage with io-wq")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we get -1 from hrtimer_try_to_cancel(), we know that the timer
is running. Hence leave all completion to the timeout handler. If
we don't, we can corrupt the list and miss a completion.
Fixes: 11365043e5 ("io_uring: add support for canceling timeout requests")
Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Tested-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There's been a few requests for supporting more fixed files than 1024.
This isn't really tricky to do, we just need to split up the file table
into multiple tables and index appropriately. As we do so, reduce the
max single file table to 512. This enables us to do single page allocs
always for the tables, which is an improvement over the situation prior.
This patch adds support for up to 64K files, which should be enough for
everyone.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We index the file tables with a user given value. After we check
it's within our limits, use array_index_nospec() to prevent any
spectre attacks here.
Suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This allows an application to call accept4() in an async fashion. Like
other opcodes, we first try a non-blocking accept, then punt to async
context if we have to.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is in preparation for adding opcodes that need to add new files
in a process file table, system calls like open(2) or accept4(2).
If an opcode needs this, it must set IO_WQ_WORK_NEEDS_FILES in the work
item. If work that needs to get punted to async context have this
set, the async worker will assume the original task file table before
executing the work.
Note that opcodes that need access to the current files of an
application cannot be done through IORING_SETUP_SQPOLL.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Drop various work-arounds we have for workqueues:
- We no longer need the async_list for tracking sequential IO.
- We don't have to maintain our own mm tracking/setting.
- We don't need a separate workqueue for buffered writes. This didn't
even work that well to begin with, as it was suboptimal for multiple
buffered writers on multiple files.
- We can properly cancel pending interruptible work. This fixes
deadlocks with particularly socket IO, where we cannot cancel them
when the io_uring is closed. Hence the ring will wait forever for
these requests to complete, which may never happen. This is different
from disk IO where we know requests will complete in a finite amount
of time.
- Due to being able to cancel work interruptible work that is already
running, we can implement file table support for work. We need that
for supporting system calls that add to a process file table.
- It gets us one step closer to adding async support for any system
call.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit fb5ccc9878 ("io_uring: Fix broken links with offloading")
introduced a potential performance regression with unconditionally
taking mm even for READ/WRITE_FIXED operations.
Return the logic handling it back. mm-faulted requests will go through
the generic submission path, so honoring links and drains, but will
fail further on req->has_user check.
Fixes: fb5ccc9878 ("io_uring: Fix broken links with offloading")
Cc: stable@vger.kernel.org # v5.4
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
submit->index is used only for inbound check in submission path (i.e.
head < ctx->sq_entries). However, it always will be true, as
1. it's already validated by io_get_sqring()
2. ctx->sq_entries can't be changedd in between, because of held
ctx->uring_lock and ctx->refs.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To trace io_uring activity one can get an information from workqueue and
io trace events, but looks like some parts could be hard to identify via
this approach. Making what happens inside io_uring more transparent is
important to be able to reason about many aspects of it, hence introduce
the set of tracing events.
All such events could be roughly divided into two categories:
* those, that are helping to understand correctness (from both kernel
and an application point of view). E.g. a ring creation, file
registration, or waiting for available CQE. Proposed approach is to
get a pointer to an original structure of interest (ring context, or
request), and then find relevant events. io_uring_queue_async_work
also exposes a pointer to work_struct, to be able to track down
corresponding workqueue events.
* those, that provide performance related information. Mostly it's about
events that change the flow of requests, e.g. whether an async work
was queued, or delayed due to some dependencies. Another important
case is how io_uring optimizations (e.g. registered files) are
utilized.
Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We might have cases where the need for a specific timeout is gone, add
support for canceling an existing timeout operation. This works like the
POLL_REMOVE command, where the application passes in the user_data of
the timeout it wishes to cancel in the sqe->addr field.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is a pretty trivial addition on top of the relative timeouts
we have now, but it's handy for ensuring tighter timing for those
that are building scheduling primitives on top of io_uring.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is no function change, just to clean up the code, use s->in_async
to make the code know where it is.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently size the CQ ring as twice the SQ ring, to allow some
flexibility in not overflowing the CQ ring. This is done because the
SQE life time is different than that of the IO request itself, the SQE
is consumed as soon as the kernel has seen the entry.
Certain application don't need a huge SQ ring size, since they just
submit IO in batches. But they may have a lot of requests pending, and
hence need a big CQ ring to hold them all. By allowing the application
to control the CQ ring size multiplier, we can cater to those
applications more efficiently.
If an application wants to define its own CQ ring size, it must set
IORING_SETUP_CQSIZE in the setup flags, and fill out
io_uring_params->cq_entries. The value must be a power of two.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Allows the application to remove/replace/add files to/from a file set.
Passes in a struct:
struct io_uring_files_update {
__u32 offset;
__s32 *fds;
};
that holds an array of fds, size of array passed in through the usual
nr_args part of the io_uring_register() system call. The logic is as
follows:
1) If ->fds[i] is -1, the existing file at i + ->offset is removed from
the set.
2) If ->fds[i] is a valid fd, the existing file at i + ->offset is
replaced with ->fds[i].
For case #2, is the existing file is currently empty (fd == -1), the
new fd is simply added to the array.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is in preparation for allowing updates to fixed file sets without
requiring a full unregister+register.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently any dependent link is executed from a new workqueue context,
which means that we'll be doing a context switch per link in the chain.
If we are running the completion of the current request from our async
workqueue and find that the next request is a link, then run it directly
from the workqueue context instead of forcing another switch.
This improves the performance of linked SQEs, and reduces the CPU
overhead.
Reviewed-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
syzkaller reported an issue where it looks like a malicious app can
trigger a use-after-free of reading the ctx ->sq_array and ->rings
value right after having installed the ring fd in the process file
table.
Defer ring fd installation until after we're done reading those
values.
Fixes: 75b28affdd ("io_uring: allocate the two rings together")
Reported-by: syzbot+6f03d895a6cd0d06187f@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_queue_link_head() owns shadow_req after taking it as an argument.
By not freeing it in case of an error, it can leak the request along
with taken ctx->refs.
Reviewed-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently assume that submissions from the sqthread are successful,
and if IO polling is enabled, we use that value for knowing how many
completions to look for. But if we overflowed the CQ ring or some
requests simply got errored and already completed, they won't be
available for polling.
For the case of IO polling and SQTHREAD usage, look at the pending
poll list. If it ever hits empty then we know that we don't have
anymore pollable requests inflight. For that case, simply reset
the inflight count to zero.
Reported-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently use the ring values directly, but that can lead to issues
if the application is malicious and changes these values on our behalf.
Created in-kernel cached versions of them, and just overwrite the user
side when we update them. This is similar to how we treat the sq/cq
ring tail/head updates.
Reported-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_ring_submit() finalises with
1. io_commit_sqring(), which releases sqes to the userspace
2. Then calls to io_queue_link_head(), accessing released head's sqe
Reorder them.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_sq_thread() processes sqes by 8 without considering links. As a
result, links will be randomely subdivided.
The easiest way to fix it is to call io_get_sqring() inside
io_submit_sqes() as do io_ring_submit().
Downsides:
1. This removes optimisation of not grabbing mm_struct for fixed files
2. It submitting all sqes in one go, without finer-grained sheduling
with cq processing.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a bug, where failed linked requests are returned not with
specified @user_data, but with garbage from a kernel stack.
The reason is that io_fail_links() uses req->user_data, which is
uninitialised when called from io_queue_sqe() on fail path.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The sequence number of the timeout req (req->sequence) indicate the
expected completion request. Because of each timeout req consume a
sequence number, so the sequence of each timeout req on the timeout
list shouldn't be the same. But now, we may get the same number (also
incorrect) if we insert a new entry before the last one, such as submit
such two timeout reqs on a new ring instance below.
req->sequence
req_1 (count = 2): 2
req_2 (count = 1): 2
Then, if we submit a nop req, req_2 will still timeout even the nop req
finished. This patch fix this problem by adjust the sequence number of
each reordered reqs when inserting a new entry.
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The sequence number of reqs on the timeout_list before the timeout req
should be adjusted in io_timeout_fn(), because the current timeout req
will consumes a slot in the cq_ring and cq_tail pointer will be
increased, otherwise other timeout reqs may return in advance without
waiting for enough wait_nr.
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are cases where it isn't always safe to block for submission,
even if the caller asked to wait for events as well. Revert the
previous optimization of doing that.
This reverts two commits:
bf7ec93c64c576666863
Fixes: c576666863 ("io_uring: optimize submit_and_wait API")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
