Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCYpz/IQAKCRBZ7Krx/gZQ
666mAPwKOC/voemjl2m+RpSruxAbdlRvKei3IY8YxLfyv+rmUQD9HKLJJtQX2VRF
QTFmQ3p7kx30ydwSbyY8Kpw3VMCDxgs=
=1ZKm
-----END PGP SIGNATURE-----
Merge tag 'pull-work.fd-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull file descriptor fix from Al Viro:
"Fix for breakage in #work.fd this window"
* tag 'pull-work.fd-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
fix the breakage in close_fd_get_file() calling conventions change
It used to grab an extra reference to struct file rather than
just transferring to caller the one it had removed from descriptor
table. New variant doesn't, and callers need to be adjusted.
Reported-and-tested-by: syzbot+47dd250f527cb7bebf24@syzkaller.appspotmail.com
Fixes: 6319194ec5 ("Unify the primitives for file descriptor closing")
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
After some debugging, it was realized that we really do still need the
old inflight tracking for any file type that has io_uring_fops assigned.
If we don't, then trivial circular references will mean that we never get
the ctx cleaned up and hence it'll leak.
Just bring back the inflight tracking, which then also means we can
eliminate the conditional dropping of the file when task_work is queued.
Fixes: d5361233e9 ("io_uring: drop the old style inflight file tracking")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_fixed_fd_install() can grab uring_lock in the slot allocation path
when called from io-wq, and then call into io_install_fixed_file(),
which will lock it again. Pull all locking out of
io_install_fixed_file() into io_fixed_fd_install().
Fixes: 1339f24b33 ("io_uring: allow allocated fixed files for openat/openat2")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/64116172a9d0b85b85300346bb280f3657aafc26.1654087283.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
One big issue with the file registration feature is that it needs user
space apps to maintain free slot info about io_uring's fixed file table,
which really is a burden for development. io_uring now supports choosing
free file slot for user space apps by using IORING_FILE_INDEX_ALLOC flag
in accept, open, and socket operations, but they need the app to use
direct accept or direct open, which not all apps are prepared to use yet.
To support apps that still need real fds, make use of the registration
feature easier. Let IORING_OP_FILES_UPDATE support choosing fixed file
slots, which will store picked fixed files slots in fd array and let cqe
return the number of slots allocated.
Suggested-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
[axboe: move flag to uapi io_uring header, change goto to break, init]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_file_bitmap_get() returns a free bitmap slot, but if it isn't
used later, such as io_queue_rsrc_removal() returns error, in this
case, we should not update alloc_hint at all, which still should
be considered as a valid candidate for next io_file_bitmap_get()
calls.
To fix this issue, only update alloc_hint in io_file_bitmap_set().
Signed-off-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220528015109.48039-1-xiaoguang.wang@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The socket support was merged in an earlier branch that didn't yet
have support for allocating direct descriptors, hence only open
and accept got support for that.
Do the one-liner to enable it now, so we have consistent support for
any request that can instantiate a file/direct descriptor.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we use a buffer group ID that is large enough to require io_uring
to allocate it, then we don't correctly free it if the cleanup is
deferred to the ring exit. The explicit removal paths are fine.
Fixes: 9cfc7e94e4 ("io_uring: get rid of hashed provided buffer groups")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make them consistent in preparation for defining a req async prep
handler. The readv/writev requests share a prep handler, move it one
level down so the initial one is consistent with the others.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Define and set it when appropriate, and use it consistently in the
function rather than using io_op_defs[opcode].
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Almost all of them are, the odd ones out are the poll remove and the
files update request. Name them like the others, which is:
io_#cmdname_prep for request preparation
io_#cmdname for request issue
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
All other opcodes take a {req, sqe} set for prep handling, split out
a timeout prep handler so that timeout and linked timeouts can use
the same one.
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=/peE
-----END PGP SIGNATURE-----
Merge tag 'for-5.19/io_uring-passthrough-2022-05-22' of git://git.kernel.dk/linux-block
Pull io_uring NVMe command passthrough from Jens Axboe:
"On top of everything else, this adds support for passthrough for
io_uring.
The initial feature for this is NVMe passthrough support, which allows
non-filesystem based IO commands and admin commands.
To support this, io_uring grows support for SQE and CQE members that
are twice as big, allowing to pass in a full NVMe command without
having to copy data around. And to complete with more than just a
single 32-bit value as the output"
* tag 'for-5.19/io_uring-passthrough-2022-05-22' of git://git.kernel.dk/linux-block: (22 commits)
io_uring: cleanup handling of the two task_work lists
nvme: enable uring-passthrough for admin commands
nvme: helper for uring-passthrough checks
blk-mq: fix passthrough plugging
nvme: add vectored-io support for uring-cmd
nvme: wire-up uring-cmd support for io-passthru on char-device.
nvme: refactor nvme_submit_user_cmd()
block: wire-up support for passthrough plugging
fs,io_uring: add infrastructure for uring-cmd
io_uring: support CQE32 for nop operation
io_uring: enable CQE32
io_uring: support CQE32 in /proc info
io_uring: add tracing for additional CQE32 fields
io_uring: overflow processing for CQE32
io_uring: flush completions for CQE32
io_uring: modify io_get_cqe for CQE32
io_uring: add CQE32 completion processing
io_uring: add CQE32 setup processing
io_uring: change ring size calculation for CQE32
io_uring: store add. return values for CQE32
...
-----BEGIN PGP SIGNATURE-----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=PUw1
-----END PGP SIGNATURE-----
Merge tag 'for-5.19/io_uring-net-2022-05-22' of git://git.kernel.dk/linux-block
Pull io_uring 'more data in socket' support from Jens Axboe:
"To be able to fully utilize the 'poll first' support in the core
io_uring branch, it's advantageous knowing if the socket was empty
after a receive. This adds support for that"
* tag 'for-5.19/io_uring-net-2022-05-22' of git://git.kernel.dk/linux-block:
io_uring: return hint on whether more data is available after receive
tcp: pass back data left in socket after receive
-----BEGIN PGP SIGNATURE-----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=nb5i
-----END PGP SIGNATURE-----
Merge tag 'for-5.19/io_uring-socket-2022-05-22' of git://git.kernel.dk/linux-block
Pull io_uring socket() support from Jens Axboe:
"This adds support for socket(2) for io_uring. This is handy when using
direct / registered file descriptors with io_uring.
Outside of those two patches, a small series from Dylan on top that
improves the tracing by providing a text representation of the opcode
rather than needing to decode this by reading the header file every
time.
That sits in this branch as it was the last opcode added (until it
wasn't...)"
* tag 'for-5.19/io_uring-socket-2022-05-22' of git://git.kernel.dk/linux-block:
io_uring: use the text representation of ops in trace
io_uring: rename op -> opcode
io_uring: add io_uring_get_opcode
io_uring: add type to op enum
io_uring: add socket(2) support
net: add __sys_socket_file()
-----BEGIN PGP SIGNATURE-----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=CfhD
-----END PGP SIGNATURE-----
Merge tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block
Pull io_uring xattr support from Jens Axboe:
"Support for the xattr variants"
* tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block:
io_uring: cleanup error-handling around io_req_complete
io_uring: fix trace for reduced sqe padding
io_uring: add fgetxattr and getxattr support
io_uring: add fsetxattr and setxattr support
fs: split off do_getxattr from getxattr
fs: split off setxattr_copy and do_setxattr function from setxattr
-----BEGIN PGP SIGNATURE-----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=S+Uf
-----END PGP SIGNATURE-----
Merge tag 'for-5.19/io_uring-2022-05-22' of git://git.kernel.dk/linux-block
Pull io_uring updates from Jens Axboe:
"Here are the main io_uring changes for 5.19. This contains:
- Fixes for sparse type warnings (Christoph, Vasily)
- Support for multi-shot accept (Hao)
- Support for io_uring managed fixed files, rather than always
needing the applicationt o manage the indices (me)
- Fix for a spurious poll wakeup (Dylan)
- CQE overflow fixes (Dylan)
- Support more types of cancelations (me)
- Support for co-operative task_work signaling, rather than always
forcing an IPI (me)
- Support for doing poll first when appropriate, rather than always
attempting a transfer first (me)
- Provided buffer cleanups and support for mapped buffers (me)
- Improve how io_uring handles inflight SCM files (Pavel)
- Speedups for registered files (Pavel, me)
- Organize the completion data in a struct in io_kiocb rather than
keep it in separate spots (Pavel)
- task_work improvements (Pavel)
- Cleanup and optimize the submission path, in general and for
handling links (Pavel)
- Speedups for registered resource handling (Pavel)
- Support sparse buffers and file maps (Pavel, me)
- Various fixes and cleanups (Almog, Pavel, me)"
* tag 'for-5.19/io_uring-2022-05-22' of git://git.kernel.dk/linux-block: (111 commits)
io_uring: fix incorrect __kernel_rwf_t cast
io_uring: disallow mixed provided buffer group registrations
io_uring: initialize io_buffer_list head when shared ring is unregistered
io_uring: add fully sparse buffer registration
io_uring: use rcu_dereference in io_close
io_uring: consistently use the EPOLL* defines
io_uring: make apoll_events a __poll_t
io_uring: drop a spurious inline on a forward declaration
io_uring: don't use ERR_PTR for user pointers
io_uring: use a rwf_t for io_rw.flags
io_uring: add support for ring mapped supplied buffers
io_uring: add io_pin_pages() helper
io_uring: add buffer selection support to IORING_OP_NOP
io_uring: fix locking state for empty buffer group
io_uring: implement multishot mode for accept
io_uring: let fast poll support multishot
io_uring: add REQ_F_APOLL_MULTISHOT for requests
io_uring: add IORING_ACCEPT_MULTISHOT for accept
io_uring: only wake when the correct events are set
io_uring: avoid io-wq -EAGAIN looping for !IOPOLL
...
Rather than pass in a bool for whether or not this work item needs to go
into the priority list or not, provide separate helpers for it. For most
use cases, this also then gets rid of the branch for non-priority task
work.
While at it, rename the prior_task_list to prio_task_list. Prior is
a confusing name for it, as it would seem to indicate that this is the
previous task_work list. prio makes it clear that this is a priority
task_work list.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It's nonsensical to register a provided buffer ring, if a classic
provided buffer group with the same ID exists. Depending on the order of
which we decide what type to pick, the other type will never get used.
Explicitly disallow it and return an error if this is attempted.
Fixes: c7fb19428d ("io_uring: add support for ring mapped supplied buffers")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We use ->buf_pages != 0 to tell if this is a shared buffer ring or a
classic provided buffer group. If we unregister the shared ring and
then attempt to use it, buf_pages is zero yet the classic list head
isn't properly initialized. This causes io_buffer_select() to think
that we have classic buffers available, but then we crash when we try
and get one from the list.
Just initialize the list if we unregister a shared buffer ring, leaving
it in a sane state for either re-registration or for attempting to use
it. And do the same for the initial setup from the classic path.
Fixes: c7fb19428d ("io_uring: add support for ring mapped supplied buffers")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
POLL* are unannotated values for the userspace ABI, while everything
in-kernel should use EPOLL* and the __poll_t type.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220518084005.3255380-6-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_file_get_normal isn't marked inline, so don't claim it as such in the
forward declaration.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220518084005.3255380-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
ERR_PTR abuses the high bits of a pointer to transport error information.
This is only safe for kernel pointers and not user pointers. Fix
io_buffer_select and its helpers to just return NULL for failure and get
rid of this abuse.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220518084005.3255380-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Provided buffers allow an application to supply io_uring with buffers
that can then be grabbed for a read/receive request, when the data
source is ready to deliver data. The existing scheme relies on using
IORING_OP_PROVIDE_BUFFERS to do that, but it can be difficult to use
in real world applications. It's pretty efficient if the application
is able to supply back batches of provided buffers when they have been
consumed and the application is ready to recycle them, but if
fragmentation occurs in the buffer space, it can become difficult to
supply enough buffers at the time. This hurts efficiency.
Add a register op, IORING_REGISTER_PBUF_RING, which allows an application
to setup a shared queue for each buffer group of provided buffers. The
application can then supply buffers simply by adding them to this ring,
and the kernel can consume then just as easily. The ring shares the head
with the application, the tail remains private in the kernel.
Provided buffers setup with IORING_REGISTER_PBUF_RING cannot use
IORING_OP_{PROVIDE,REMOVE}_BUFFERS for adding or removing entries to the
ring, they must use the mapped ring. Mapped provided buffer rings can
co-exist with normal provided buffers, just not within the same group ID.
To gauge overhead of the existing scheme and evaluate the mapped ring
approach, a simple NOP benchmark was written. It uses a ring of 128
entries, and submits/completes 32 at the time. 'Replenish' is how
many buffers are provided back at the time after they have been
consumed:
Test Replenish NOPs/sec
================================================================
No provided buffers NA ~30M
Provided buffers 32 ~16M
Provided buffers 1 ~10M
Ring buffers 32 ~27M
Ring buffers 1 ~27M
The ring mapped buffers perform almost as well as not using provided
buffers at all, and they don't care if you provided 1 or more back at
the same time. This means application can just replenish as they go,
rather than need to batch and compact, further reducing overhead in the
application. The NOP benchmark above doesn't need to do any compaction,
so that overhead isn't even reflected in the above test.
Co-developed-by: Dylan Yudaken <dylany@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Abstract this out from io_sqe_buffer_register() so we can use it
elsewhere too without duplicating this code.
No intended functional changes in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Obviously not really useful since it's not transferring data, but it
is helpful in benchmarking overhead of provided buffers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_provided_buffer_select() must drop the submit lock, if needed, even
in the error handling case. Failure to do so will leave us with the
ctx->uring_lock held, causing spew like:
====================================
WARNING: iou-wrk-366/368 still has locks held!
5.18.0-rc6-00294-gdf8dc7004331 #994 Not tainted
------------------------------------
1 lock held by iou-wrk-366/368:
#0: ffff0000c72598a8 (&ctx->uring_lock){+.+.}-{3:3}, at: io_ring_submit_lock+0x20/0x48
stack backtrace:
CPU: 4 PID: 368 Comm: iou-wrk-366 Not tainted 5.18.0-rc6-00294-gdf8dc7004331 #994
Hardware name: linux,dummy-virt (DT)
Call trace:
dump_backtrace.part.0+0xa4/0xd4
show_stack+0x14/0x5c
dump_stack_lvl+0x88/0xb0
dump_stack+0x14/0x2c
debug_check_no_locks_held+0x84/0x90
try_to_freeze.isra.0+0x18/0x44
get_signal+0x94/0x6ec
io_wqe_worker+0x1d8/0x2b4
ret_from_fork+0x10/0x20
and triggering later hangs off get_signal() because we attempt to
re-grab the lock.
Reported-by: syzbot+987d7bb19195ae45208c@syzkaller.appspotmail.com
Fixes: 149c69b04a ("io_uring: abstract out provided buffer list selection")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We gate whether to IOPOLL for a request on whether the opcode is allowed
on a ring setup for IOPOLL and if it's got a file assigned. MSG_RING
is the only one that allows a file yet isn't pollable, it's merely
supported to allow communication on an IOPOLL ring, not because we can
poll for completion of it.
Put the assigned file early and clear it, so we don't attempt to poll
for it.
Reported-by: syzbot+1a0a53300ce782f8b3ad@syzkaller.appspotmail.com
Fixes: 3f1d52abf0 ("io_uring: defer msg-ring file validity check until command issue")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we have 3 primitives for removing an opened file from descriptor
table - pick_file(), __close_fd_get_file() and close_fd_get_file(). Their
calling conventions are rather odd and there's a code duplication for no
good reason. They can be unified -
1) have __range_close() cap max_fd in the very beginning; that way
we don't need separate way for pick_file() to report being past the end
of descriptor table.
2) make {__,}close_fd_get_file() return file (or NULL) directly, rather
than returning it via struct file ** argument. Don't bother with
(bogus) return value - nobody wants that -ENOENT.
3) make pick_file() return NULL on unopened descriptor - the only caller
that used to care about the distinction between descriptor past the end
of descriptor table and finding NULL in descriptor table doesn't give
a damn after (1).
4) lift ->files_lock out of pick_file()
That actually simplifies the callers, as well as the primitives themselves.
Code duplication is also gone...
Reviewed-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Refactor io_accept() to support multishot mode.
theoretical analysis:
1) when connections come in fast
- singleshot:
add accept sqe(userspace) --> accept inline
^ |
|-----------------|
- multishot:
add accept sqe(userspace) --> accept inline
^ |
|--*--|
we do accept repeatedly in * place until get EAGAIN
2) when connections come in at a low pressure
similar thing like 1), we reduce a lot of userspace-kernel context
switch and useless vfs_poll()
tests:
Did some tests, which goes in this way:
server client(multiple)
accept connect
read write
write read
close close
Basically, raise up a number of clients(on same machine with server) to
connect to the server, and then write some data to it, the server will
write those data back to the client after it receives them, and then
close the connection after write return. Then the client will read the
data and then close the connection. Here I test 10000 clients connect
one server, data size 128 bytes. And each client has a go routine for
it, so they come to the server in short time.
test 20 times before/after this patchset, time spent:(unit cycle, which
is the return value of clock())
before:
1930136+1940725+1907981+1947601+1923812+1928226+1911087+1905897+1941075
+1934374+1906614+1912504+1949110+1908790+1909951+1941672+1969525+1934984
+1934226+1914385)/20.0 = 1927633.75
after:
1858905+1917104+1895455+1963963+1892706+1889208+1874175+1904753+1874112
+1874985+1882706+1884642+1864694+1906508+1916150+1924250+1869060+1889506
+1871324+1940803)/20.0 = 1894750.45
(1927633.75 - 1894750.45) / 1927633.75 = 1.65%
Signed-off-by: Hao Xu <howeyxu@tencent.com>
Link: https://lore.kernel.org/r/20220514142046.58072-5-haoxu.linux@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For operations like accept, multishot is a useful feature, since we can
reduce a number of accept sqe. Let's integrate it to fast poll, it may
be good for other operations in the future.
Signed-off-by: Hao Xu <howeyxu@tencent.com>
Link: https://lore.kernel.org/r/20220514142046.58072-4-haoxu.linux@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a flag to indicate multishot mode for fast poll. currently only
accept use it, but there may be more operations leveraging it in the
future. Also add a mask IO_APOLL_MULTI_POLLED which stands for
REQ_F_APOLL_MULTI | REQ_F_POLLED, to make the code short and cleaner.
Signed-off-by: Hao Xu <howeyxu@tencent.com>
Link: https://lore.kernel.org/r/20220514142046.58072-3-haoxu.linux@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The check for waking up a request compares the poll_t bits, however this
will always contain some common flags so this always wakes up.
For files with single wait queues such as sockets this can cause the
request to be sent to the async worker unnecesarily. Further if it is
non-blocking will complete the request with EAGAIN which is not desired.
Here exclude these common events, making sure to not exclude POLLERR which
might be important.
Fixes: d7718a9d25 ("io_uring: use poll driven retry for files that support it")
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Link: https://lore.kernel.org/r/20220512091834.728610-3-dylany@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If an opcode handler semi-reliably returns -EAGAIN, io_wq_submit_work()
might continue busily hammer the same handler over and over again, which
is not ideal. The -EAGAIN handling in question was put there only for
IOPOLL, so restrict it to IOPOLL mode only where there is no other
recourse than to retry as we cannot wait.
Fixes: def596e955 ("io_uring: support for IO polling")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f168b4f24181942f3614dd8ff648221736f572e6.1652433740.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently to setup a fully sparse descriptor space upfront, the app needs
to alloate an array of the full size and memset it to -1 and then pass
that in. Make this a bit easier by allowing a flag that simply does
this internally rather than needing to copy each slot separately.
This works with IORING_REGISTER_FILES2 as the flag is set in struct
io_uring_rsrc_register, and is only allow when the type is
IORING_RSRC_FILE as this doesn't make sense for registered buffers.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently limit these to 32K, but since we're now backing the table
space with vmalloc when needed, there's no reason why we can't make it
bigger. The total space is limited by RLIMIT_NOFILE as well.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If the application passes in IORING_FILE_INDEX_ALLOC as the file_slot,
then that's a hint to allocate a fixed file descriptor rather than have
one be passed in directly.
This can be useful for having io_uring manage the direct descriptor space,
and also allows multi-shot support to work with fixed files.
Normal accept direct requests will complete with 0 for success, and < 0
in case of error. If io_uring is asked to allocated the direct descriptor,
then the direct descriptor is returned in case of success.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If the application passes in IORING_FILE_INDEX_ALLOC as the file_slot,
then that's a hint to allocate a fixed file descriptor rather than have
one be passed in directly.
This can be useful for having io_uring manage the direct descriptor space.
Normal open direct requests will complete with 0 for success, and < 0
in case of error. If io_uring is asked to allocated the direct descriptor,
then the direct descriptor is returned in case of success.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Applications currently always pick where they want fixed files to go.
In preparation for allowing these types of commands with multishot
support, add a basic allocator in the fixed file table.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In preparation for adding a basic allocator for direct descriptors,
add helpers that set/clear whether a file slot is used.
Reviewed-by: Hao Xu <howeyxu@tencent.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
file_operations->uring_cmd is a file private handler.
This is somewhat similar to ioctl but hopefully a lot more sane and
useful as it can be used to enable many io_uring capabilities for the
underlying operation.
IORING_OP_URING_CMD is a file private kind of request. io_uring doesn't
know what is in this command type, it's for the provider of ->uring_cmd()
to deal with.
Co-developed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220511054750.20432-2-joshi.k@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds support for filling the extra1 and extra2 fields for large
CQE's.
Co-developed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/r/20220426182134.136504-13-shr@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Linus Torvalds