For each IOSQE_* flag there is a corresponding REQ_F_* flag. And there
is a repetitive pattern of their translation:
e.g. if (sqe->flags & SQE_FLAG*) req->flags |= REQ_F_FLAG*
Use same numeric values/bits for them and copy instead of manual
handling.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The application currently has no way of knowing if a given opcode is
supported or not without having to try and issue one and see if we get
-EINVAL or not. And even this approach is fraught with peril, as maybe
we're getting -EINVAL due to some fields being missing, or maybe it's
just not that easy to issue that particular command without doing some
other leg work in terms of setup first.
This adds IORING_REGISTER_PROBE, which fills in a structure with info
on what it supported or not. This will work even with sparse opcode
fields, which may happen in the future or even today if someone
backports specific features to older kernels.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add support for the new openat2(2) system call. It's trivial to do, as
we can have openat(2) just be wrapped around it.
Suggested-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If an application is using eventfd notifications with poll to know when
new SQEs can be issued, it's expecting the following read/writes to
complete inline. And with that, it knows that there are events available,
and don't want spurious wakeups on the eventfd for those requests.
This adds IORING_REGISTER_EVENTFD_ASYNC, which works just like
IORING_REGISTER_EVENTFD, except it only triggers notifications for events
that happen from async completions (IRQ, or io-wq worker completions).
Any completions inline from the submission itself will not trigger
notifications.
Suggested-by: Mark Papadakis <markuspapadakis@icloud.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some applications like to start small in terms of ring size, and then
ramp up as needed. This is a bit tricky to do currently, since we don't
advertise the max ring size.
This adds IORING_SETUP_CLAMP. If set, and the values for SQ or CQ ring
size exceed what we support, then clamp them at the max values instead
of returning -EINVAL. Since we return the chosen ring sizes after setup,
no further changes are needed on the application side. io_uring already
changes the ring sizes if the application doesn't ask for power-of-two
sizes, for example.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds support for doing madvise(2) through io_uring. We assume that
any operation can block, and hence punt everything async. This could be
improved, but hard to make bullet proof. The async punt ensures it's
safe.
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds support for doing fadvise through io_uring. We assume that
WILLNEED doesn't block, but that DONTNEED may block.
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This behaves like preadv2/pwritev2 with offset == -1, it'll use (and
update) the current file position. This obviously comes with the caveat
that if the application has multiple read/writes in flight, then the
end result will not be as expected. This is similar to threads sharing
a file descriptor and doing IO using the current file position.
Since this feature isn't easily detectable by doing a read or write,
add a feature flags, IORING_FEAT_RW_CUR_POS, to allow applications to
detect presence of this feature.
Reported-by: 李通洲 <carter.li@eoitek.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For uses cases that don't already naturally have an iovec, it's easier
(or more convenient) to just use a buffer address + length. This is
particular true if the use case is from languages that want to create
a memory safe abstraction on top of io_uring, and where introducing
the need for the iovec may impose an ownership issue. For those cases,
they currently need an indirection buffer, which means allocating data
just for this purpose.
Add basic read/write that don't require the iovec.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring defaults to always doing inline submissions, if at all
possible. But for larger copies, even if the data is fully cached, that
can take a long time. Add an IOSQE_ASYNC flag that the application can
set on the SQE - if set, it'll ensure that we always go async for those
kinds of requests. Use the io-wq IO_WQ_WORK_CONCURRENT flag to ensure we
get the concurrency we desire for this case.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently fully quiesce the ring before an unregister or update of
the fixed fileset. This is very expensive, and we can be a bit smarter
about this.
Add a percpu refcount for the file tables as a whole. Grab a percpu ref
when we use a registered file, and put it on completion. This is cheap
to do. Upon removal of a file from a set, switch the ref count to atomic
mode. When we hit zero ref on the completion side, then we know we can
drop the previously registered files. When the old files have been
dropped, switch the ref back to percpu mode for normal operation.
Since there's a period between doing the update and the kernel being
done with it, add a IORING_OP_FILES_UPDATE opcode that can perform the
same action. The application knows the update has completed when it gets
the CQE for it. Between doing the update and receiving this completion,
the application must continue to use the unregistered fd if submitting
IO on this particular file.
This takes the runtime of test/file-register from liburing from 14s to
about 0.7s.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This works just like close(2), unsurprisingly. We remove the file
descriptor and post the completion inline, then offload the actual
(potential) last file put to async context.
Mark the async part of this work as uncancellable, as we really must
guarantee that the latter part of the close is run.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This works just like openat(2), except it can be performed async. For
the normal case of a non-blocking path lookup this will complete
inline. If we have to do IO to perform the open, it'll be done from
async context.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
fds field of struct io_uring_files_update is problematic with regards
to compat user space, as pointer size is different in 32-bit, 32-on-64-bit,
and 64-bit user space. In order to avoid custom handling of compat in
the syscall implementation, make fds __u64 and use u64_to_user_ptr in
order to retrieve it. Also, align the field naturally and check that
no garbage is passed there.
Fixes: c3a31e6056 ("io_uring: add support for IORING_REGISTER_FILES_UPDATE")
Signed-off-by: Eugene Syromiatnikov <esyr@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we submit an unknown opcode and have fd == -1, io_op_needs_file()
will return true as we default to needing a file. Then when we go and
assign the file, we find the 'fd' invalid and return -EBADF. We really
should be returning -EINVAL for that case, as we normally do for
unsupported opcodes.
Change io_op_needs_file() to have the following return values:
0 - does not need a file
1 - does need a file
< 0 - error value
and use this to pass back the right value for this invalid case.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some commands will invariably end in a failure in the sense that the
completion result will be less than zero. One such example is timeouts
that don't have a completion count set, they will always complete with
-ETIME unless cancelled.
For linked commands, we sever links and fail the rest of the chain if
the result is less than zero. Since we have commands where we know that
will happen, add IOSQE_IO_HARDLINK as a stronger link that doesn't sever
regardless of the completion result. Note that the link will still sever
if we fail submitting the parent request, hard links are only resilient
in the presence of completion results for requests that did submit
correctly.
Cc: stable@vger.kernel.org # v5.4
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reported-by: 李通洲 <carter.li@eoitek.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If this flag is set, applications can be certain that any data for
async offload has been consumed when the kernel has consumed the
SQE.
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>
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>
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>
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>
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>
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>
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>
There's been a few requests for functionality similar to io_getevents()
and epoll_wait(), where the user can specify a timeout for waiting on
events. I deliberately did not add support for this through the system
call initially to avoid overloading the args, but I can see that the use
cases for this are valid.
This adds support for IORING_OP_TIMEOUT. If a user wants to get woken
when waiting for events, simply submit one of these timeout commands
with your wait call (or before). This ensures that the application
sleeping on the CQ ring waiting for events will get woken. The timeout
command is passed in as a pointer to a struct timespec. Timeouts are
relative. The timeout command also includes a way to auto-cancel after
N events has passed.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
After commit 75b28affdd we can get by with just a single mmap to
map both the sq and cq ring. However, userspace doesn't know that.
Add a features variable to io_uring_params, and notify userspace
that the kernel has this ability. This can then be used in liburing
(or in applications directly) to avoid the second mmap.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is done through IORING_OP_RECVMSG. This opcode uses the same
sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the
msghdr struct in the sqe->addr field as well.
We use MSG_DONTWAIT to force an inline fast path if recvmsg() doesn't
block, and punt to async execution if it would have.
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags
for the flags argument, and the msghdr struct is passed in the
sqe->addr field.
We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't
block, and punt to async execution if it would have.
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With SQE links, we can create chains of dependent SQEs. One example
would be queueing an SQE that's a read from one file descriptor, with
the linked SQE being a write to another with the same set of buffers.
An SQE link will not stall the pipeline, it'll just ensure that
dependent SQEs aren't issued before the previous link has completed.
Any error at submission or completion time will break the chain of SQEs.
For completions, this also includes short reads or writes, as the next
SQE could depend on the previous one being fully completed.
Any SQE in a chain that gets canceled due to any of the above errors,
will get an CQE fill with -ECANCELED as the error value.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Allow registration of an eventfd, which will trigger an event every
time a completion event happens for this io_uring instance.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are no ordering constraints between the submission and completion
side of io_uring. But sometimes that would be useful to have. One common
example is doing an fsync, for instance, and have it ordered with
previous writes. Without support for that, the application must do this
tracking itself.
This adds a general SQE flag, IOSQE_IO_DRAIN. If a command is marked
with this flag, then it will not be issued before previous commands have
completed, and subsequent commands submitted after the drain will not be
issued before the drain is started.. If there are no pending commands,
setting this flag will not change the behavior of the issue of the
command.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is basically a direct port of bfe4037e72, which implements a
one-shot poll command through aio. Description below is based on that
commit as well. However, instead of adding a POLL command and relying
on io_cancel(2) to remove it, we mimic the epoll(2) interface of
having a command to add a poll notification, IORING_OP_POLL_ADD,
and one to remove it again, IORING_OP_POLL_REMOVE.
To poll for a file descriptor the application should submit an sqe of
type IORING_OP_POLL. It will poll the fd for the events specified in the
poll_events field.
Unlike poll or epoll without EPOLLONESHOT this interface always works in
one shot mode, that is once the sqe is completed, it will have to be
resubmitted.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Based-on-code-from: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This enables an application to do IO, without ever entering the kernel.
By using the SQ ring to fill in new sqes and watching for completions
on the CQ ring, we can submit and reap IOs without doing a single system
call. The kernel side thread will poll for new submissions, and in case
of HIPRI/polled IO, it'll also poll for completions.
By default, we allow 1 second of active spinning. This can by changed
by passing in a different grace period at io_uring_register(2) time.
If the thread exceeds this idle time without having any work to do, it
will set:
sq_ring->flags |= IORING_SQ_NEED_WAKEUP.
The application will have to call io_uring_enter() to start things back
up again. If IO is kept busy, that will never be needed. Basically an
application that has this feature enabled will guard it's
io_uring_enter(2) call with:
read_barrier();
if (*sq_ring->flags & IORING_SQ_NEED_WAKEUP)
io_uring_enter(fd, 0, 0, IORING_ENTER_SQ_WAKEUP);
instead of calling it unconditionally.
It's mandatory to use fixed files with this feature. Failure to do so
will result in the application getting an -EBADF CQ entry when
submitting IO.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We normally have to fget/fput for each IO we do on a file. Even with
the batching we do, the cost of the atomic inc/dec of the file usage
count adds up.
This adds IORING_REGISTER_FILES, and IORING_UNREGISTER_FILES opcodes
for the io_uring_register(2) system call. The arguments passed in must
be an array of __s32 holding file descriptors, and nr_args should hold
the number of file descriptors the application wishes to pin for the
duration of the io_uring instance (or until IORING_UNREGISTER_FILES is
called).
When used, the application must set IOSQE_FIXED_FILE in the sqe->flags
member. Then, instead of setting sqe->fd to the real fd, it sets sqe->fd
to the index in the array passed in to IORING_REGISTER_FILES.
Files are automatically unregistered when the io_uring instance is torn
down. An application need only unregister if it wishes to register a new
set of fds.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have fixed user buffers, we can map them into the kernel when we
setup the io_uring. That avoids the need to do get_user_pages() for
each and every IO.
To utilize this feature, the application must call io_uring_register()
after having setup an io_uring instance, passing in
IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to
an iovec array, and the nr_args should contain how many iovecs the
application wishes to map.
If successful, these buffers are now mapped into the kernel, eligible
for IO. To use these fixed buffers, the application must use the
IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then
set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len
must point to somewhere inside the indexed buffer.
The application may register buffers throughout the lifetime of the
io_uring instance. It can call io_uring_register() with
IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of
buffers, and then register a new set. The application need not
unregister buffers explicitly before shutting down the io_uring
instance.
It's perfectly valid to setup a larger buffer, and then sometimes only
use parts of it for an IO. As long as the range is within the originally
mapped region, it will work just fine.
For now, buffers must not be file backed. If file backed buffers are
passed in, the registration will fail with -1/EOPNOTSUPP. This
restriction may be relaxed in the future.
RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat
arbitrary 1G per buffer size is also imposed.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add support for a polled io_uring instance. When a read or write is
submitted to a polled io_uring, the application must poll for
completions on the CQ ring through io_uring_enter(2). Polled IO may not
generate IRQ completions, hence they need to be actively found by the
application itself.
To use polling, io_uring_setup() must be used with the
IORING_SETUP_IOPOLL flag being set. It is illegal to mix and match
polled and non-polled IO on an io_uring.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a new fsync opcode, which either syncs a range if one is passed,
or the whole file if the offset and length fields are both cleared
to zero. A flag is provided to use fdatasync semantics, that is only
force out metadata which is required to retrieve the file data, but
not others like metadata.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The submission queue (SQ) and completion queue (CQ) rings are shared
between the application and the kernel. This eliminates the need to
copy data back and forth to submit and complete IO.
IO submissions use the io_uring_sqe data structure, and completions
are generated in the form of io_uring_cqe data structures. The SQ
ring is an index into the io_uring_sqe array, which makes it possible
to submit a batch of IOs without them being contiguous in the ring.
The CQ ring is always contiguous, as completion events are inherently
unordered, and hence any io_uring_cqe entry can point back to an
arbitrary submission.
Two new system calls are added for this:
io_uring_setup(entries, params)
Sets up an io_uring instance for doing async IO. On success,
returns a file descriptor that the application can mmap to
gain access to the SQ ring, CQ ring, and io_uring_sqes.
io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize)
Initiates IO against the rings mapped to this fd, or waits for
them to complete, or both. The behavior is controlled by the
parameters passed in. If 'to_submit' is non-zero, then we'll
try and submit new IO. If IORING_ENTER_GETEVENTS is set, the
kernel will wait for 'min_complete' events, if they aren't
already available. It's valid to set IORING_ENTER_GETEVENTS
and 'min_complete' == 0 at the same time, this allows the
kernel to return already completed events without waiting
for them. This is useful only for polling, as for IRQ
driven IO, the application can just check the CQ ring
without entering the kernel.
With this setup, it's possible to do async IO with a single system
call. Future developments will enable polled IO with this interface,
and polled submission as well. The latter will enable an application
to do IO without doing ANY system calls at all.
For IRQ driven IO, an application only needs to enter the kernel for
completions if it wants to wait for them to occur.
Each io_uring is backed by a workqueue, to support buffered async IO
as well. We will only punt to an async context if the command would
need to wait for IO on the device side. Any data that can be accessed
directly in the page cache is done inline. This avoids the slowness
issue of usual threadpools, since cached data is accessed as quickly
as a sync interface.
Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov