If preempt isn't enabled in the kernel, we can run into hang issues with
sqthread submissions. Use cond_resched() to play nice instead of
cpu_relax(), if we end up starting the loop and not having any events
pending for submissions.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Sometimes io_get_req will return a NUL, then we need to do the
correct error handling, otherwise it will cause the kernel null
pointer exception.
Fixes: 4fe2c96315 ("io_uring: add support for link with drain")
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we end up getting woken in poll (due to a signal), then we may need
to punt the poll request to an async worker. When we do that, we look up
the list to queue at, deferefencing req->submit.sqe, however that is
only set for requests we initially decided to queue async.
This fixes a crash with poll command usage and wakeups that need to punt
to async context.
Fixes: 54a91f3bb9 ("io_uring: limit parallelism of buffered writes")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a potential dangling pointer problem. we never clean
shadow_req, if there are multiple link lists in this series of
sqes, then the shadow_req will not reallocate, and continue to
use the last one. but in the previous, his memory has been
released, thus forming a dangling pointer. let's clean up him
and make sure that every new link list can reapply for a new
shadow_req.
Fixes: 4fe2c96315 ("io_uring: add support for link with drain")
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some workloads can require far more than 4K oustanding entries. For
example memcached can have ~300K sockets over ~40 cores. Bumping the max
to 32K seems to work pretty well.
Reported-by: Dan Melnic <dmm@fb.com>
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The way the logic is setup in io_uring_enter() means that you can't wake
up the SQ poller thread while at the same time waiting (or polling) for
completions afterwards. There's no reason for that to be the case.
Reported-by: Lewis Baker <lbaker@fb.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently merge async work items if we see a strict sequential hit.
This helps avoid unnecessary workqueue switches when we don't need
them. We can extend this merging to cover cases where it's not a strict
sequential hit, but the IO still fits within the same page. If an
application is doing multiple requests within the same page, we don't
want separate workers waiting on the same page to complete IO. It's much
faster to let the first worker bring in the page, then operate on that
page from the same worker to complete the next request(s).
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
All the popular filesystems need to grab the inode lock for buffered
writes. With io_uring punting buffered writes to async context, we
observe a lot of contention with all workers hamming this mutex.
For buffered writes, we generally don't need a lot of parallelism on
the submission side, as the flushing will take care of that for us.
Hence we don't need a deep queue on the write side, as long as we
can safely punt from the original submission context.
Add a workqueue with a limit of 2 that we can use for buffered writes.
This greatly improves the performance and efficiency of higher queue
depth buffered async writes with io_uring.
Reported-by: Andres Freund <andres@anarazel.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a helper for queueing a request for async execution, in preparation
for optimizing it.
No functional change in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For some applications that end up using a submit-and-wait type of
approach for certain batches of IO, we can make that a bit more
efficient by allowing the application to block for the last IO
submission. This prevents an async when we don't need it, as the
application will be blocking for the completion event(s) anyway.
Typical use cases are using the liburing
io_uring_submit_and_wait() API, or just using io_uring_enter()
doing both submissions and completions. As a specific example,
RocksDB doing MultiGet() is sped up quite a bit with this
change.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To support the link with drain, we need to do two parts.
There is an sqes:
0 1 2 3 4 5 6
+-----+-----+-----+-----+-----+-----+-----+
| N | L | L | L+D | N | N | N |
+-----+-----+-----+-----+-----+-----+-----+
First, we need to ensure that the io before the link is completed,
there is a easy way is set drain flag to the link list's head, so
all subsequent io will be inserted into the defer_list.
+-----+
(0) | N |
+-----+
| (2) (3) (4)
+-----+ +-----+ +-----+ +-----+
(1) | L+D | --> | L | --> | L+D | --> | N |
+-----+ +-----+ +-----+ +-----+
|
+-----+
(5) | N |
+-----+
|
+-----+
(6) | N |
+-----+
Second, ensure that the following IO will not be completed first,
an easy way is to create a mirror of drain io and insert it into
defer_list, in this way, as long as drain io is not processed, the
following io in the defer_list will not be actively process.
+-----+
(0) | N |
+-----+
| (2) (3) (4)
+-----+ +-----+ +-----+ +-----+
(1) | L+D | --> | L | --> | L+D | --> | N |
+-----+ +-----+ +-----+ +-----+
|
+-----+
('3) | D | <== This is a shadow of (3)
+-----+
|
+-----+
(5) | N |
+-----+
|
+-----+
(6) | N |
+-----+
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Sqo_thread will get sqring in batches, which will cause
ctx->cached_sq_head to be added in batches. if one of these
sqes is set with the DRAIN flag, then he will never get a
chance to process, and finally sqo_thread will not exit.
Fixes: de0617e467 ("io_uring: add support for marking commands as draining")
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
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>
Both the sq and the cq rings have sizes just over a power of two, and
the sq ring is significantly smaller. By bundling them in a single
alllocation, we get the sq ring for free.
This also means that IORING_OFF_SQ_RING and IORING_OFF_CQ_RING now mean
the same thing. If we indicate this to userspace, we can save a mmap
call.
Signed-off-by: Hristo Venev <hristo@venev.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For pages that were retained via get_user_pages*(), release those pages
via the new put_user_page*() routines, instead of via put_page() or
release_pages().
This is part a tree-wide conversion, as described in commit fc1d8e7cca
("mm: introduce put_user_page*(), placeholder versions").
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-block@vger.kernel.org
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The outer poll loop checks for whether we need to reschedule, and
returns to userspace if we do. However, it's possible to get stuck
in the inner loop as well, if the CPU we are running on needs to
reschedule to finish the IO work.
Add the need_resched() check in the inner loop as well. This fixes
a potential hang if the kernel is configured with
CONFIG_PREEMPT_VOLUNTARY=y.
Reported-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Tested-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We need to check if we have CQEs pending before starting a poll loop,
as those could be the events we will be spinning for (and hence we'll
find none). This can happen if a CQE triggers an error, or if it is
found by eg an IRQ before we get a chance to find it through polling.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a request issue ends up being punted to async context to avoid
blocking, we can get into a situation where the original application
enters the poll loop for that very request before it has been issued.
This should not be an issue, except that the polling will hold the
io_uring uring_ctx mutex for the duration of the poll. When the async
worker has actually issued the request, it needs to acquire this mutex
to add the request to the poll issued list. Since the application
polling is already holding this mutex, the workqueue sleeps on the
mutex forever, and the application thus never gets a chance to poll for
the very request it was interested in.
Fix this by ensuring that the polling drops the uring_ctx occasionally
if it's not making any progress.
Reported-by: Jeffrey M. Birnbaum <jmbnyc@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch may fix two issues:
First, when IOSQE_IO_DRAIN set, the next IOs need to be inserted into
defer list to delay execution, but link io will be actively scheduled to
run by calling io_queue_sqe.
Second, when multiple LINK_IOs are inserted together with defer_list,
the LINK_IO is no longer keep order.
|-------------|
| LINK_IO | ----> insert to defer_list -----------
|-------------| |
| LINK_IO | ----> insert to defer_list ----------|
|-------------| |
| LINK_IO | ----> insert to defer_list ----------|
|-------------| |
| NORMAL_IO | ----> insert to defer_list ----------|
|-------------| |
|
queue_work at same time <-----|
Fixes: 9e645e1105 ("io_uring: add support for sqe links")
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit bd11b3a391 ("io_uring: don't use iov_iter_advance() for fixed
buffers") introduced an optimization to avoid using the slow
iov_iter_advance by manually populating the iov_iter iterator in some
cases.
However, the computation of the iterator count field was erroneous: The
first bvec was always accounted for an extent of page size even if the
bvec length was smaller.
In consequence, some I/O operations on fixed buffers were unable to
operate on the full extent of the buffer, consistently skipping some
bytes at the end of it.
Fixes: bd11b3a391 ("io_uring: don't use iov_iter_advance() for fixed buffers")
Cc: stable@vger.kernel.org
Signed-off-by: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=HIzH
-----END PGP SIGNATURE-----
Merge tag 'for-linus-20190726' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
- Several io_uring fixes/improvements:
- Blocking fix for O_DIRECT (me)
- Latter page slowness for registered buffers (me)
- Fix poll hang under certain conditions (me)
- Defer sequence check fix for wrapped rings (Zhengyuan)
- Mismatch in async inc/dec accounting (Zhengyuan)
- Memory ordering issue that could cause stall (Zhengyuan)
- Track sequential defer in bytes, not pages (Zhengyuan)
- NVMe pull request from Christoph
- Set of hang fixes for wbt (Josef)
- Redundant error message kill for libahci (Ding)
- Remove unused blk_mq_sched_started_request() and related ops (Marcos)
- drbd dynamic alloc shash descriptor to reduce stack use (Arnd)
- blkcg ->pd_stat() non-debug print (Tejun)
- bcache memory leak fix (Wei)
- Comment fix (Akinobu)
- BFQ perf regression fix (Paolo)
* tag 'for-linus-20190726' of git://git.kernel.dk/linux-block: (24 commits)
io_uring: ensure ->list is initialized for poll commands
Revert "nvme-pci: don't create a read hctx mapping without read queues"
nvme: fix multipath crash when ANA is deactivated
nvme: fix memory leak caused by incorrect subsystem free
nvme: ignore subnqn for ADATA SX6000LNP
drbd: dynamically allocate shash descriptor
block: blk-mq: Remove blk_mq_sched_started_request and started_request
bcache: fix possible memory leak in bch_cached_dev_run()
io_uring: track io length in async_list based on bytes
io_uring: don't use iov_iter_advance() for fixed buffers
block: properly handle IOCB_NOWAIT for async O_DIRECT IO
blk-mq: allow REQ_NOWAIT to return an error inline
io_uring: add a memory barrier before atomic_read
rq-qos: use a mb for got_token
rq-qos: set ourself TASK_UNINTERRUPTIBLE after we schedule
rq-qos: don't reset has_sleepers on spurious wakeups
rq-qos: fix missed wake-ups in rq_qos_throttle
wait: add wq_has_single_sleeper helper
block, bfq: check also in-flight I/O in dispatch plugging
block: fix sysfs module parameters directory path in comment
...
Daniel reports that when testing an http server that uses io_uring
to poll for incoming connections, sometimes it hard crashes. This is
due to an uninitialized list member for the io_uring request. Normally
this doesn't trigger and none of the test cases caught it.
Reported-by: Daniel Kozak <kozzi11@gmail.com>
Tested-by: Daniel Kozak <kozzi11@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We are using PAGE_SIZE as the unit to determine if the total len in
async_list has exceeded max_pages, it's not fair for smaller io sizes.
For example, if we are doing 1k-size io streams, we will never exceed
max_pages since len >>= PAGE_SHIFT always gets zero. So use original
bytes to make it more accurate.
Signed-off-by: Zhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Hrvoje reports that when a large fixed buffer is registered and IO is
being done to the latter pages of said buffer, the IO submission time
is much worse:
reading to the start of the buffer: 11238 ns
reading to the end of the buffer: 1039879 ns
In fact, it's worse by two orders of magnitude. The reason for that is
how io_uring figures out how to setup the iov_iter. We point the iter
at the first bvec, and then use iov_iter_advance() to fast-forward to
the offset within that buffer we need.
However, that is abysmally slow, as it entails iterating the bvecs
that we setup as part of buffer registration. There's really no need
to use this generic helper, as we know it's a BVEC type iterator, and
we also know that each bvec is PAGE_SIZE in size, apart from possibly
the first and last. Hence we can just use a shift on the offset to
find the right index, and then adjust the iov_iter appropriately.
After this fix, the timings are:
reading to the start of the buffer: 10135 ns
reading to the end of the buffer: 1377 ns
Or about an 755x improvement for the tail page.
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 is a hang issue while using fio to do some basic test. The issue
can be easily reproduced using the below script:
while true
do
fio --ioengine=io_uring -rw=write -bs=4k -numjobs=1 \
-size=1G -iodepth=64 -name=uring --filename=/dev/zero
done
After several minutes (or more), fio would block at
io_uring_enter->io_cqring_wait in order to waiting for previously
committed sqes to be completed and can't return to user anymore until
we send a SIGTERM to fio. After receiving SIGTERM, fio hangs at
io_ring_ctx_wait_and_kill with a backtrace like this:
[54133.243816] Call Trace:
[54133.243842] __schedule+0x3a0/0x790
[54133.243868] schedule+0x38/0xa0
[54133.243880] schedule_timeout+0x218/0x3b0
[54133.243891] ? sched_clock+0x9/0x10
[54133.243903] ? wait_for_completion+0xa3/0x130
[54133.243916] ? _raw_spin_unlock_irq+0x2c/0x40
[54133.243930] ? trace_hardirqs_on+0x3f/0xe0
[54133.243951] wait_for_completion+0xab/0x130
[54133.243962] ? wake_up_q+0x70/0x70
[54133.243984] io_ring_ctx_wait_and_kill+0xa0/0x1d0
[54133.243998] io_uring_release+0x20/0x30
[54133.244008] __fput+0xcf/0x270
[54133.244029] ____fput+0xe/0x10
[54133.244040] task_work_run+0x7f/0xa0
[54133.244056] do_exit+0x305/0xc40
[54133.244067] ? get_signal+0x13b/0xbd0
[54133.244088] do_group_exit+0x50/0xd0
[54133.244103] get_signal+0x18d/0xbd0
[54133.244112] ? _raw_spin_unlock_irqrestore+0x36/0x60
[54133.244142] do_signal+0x34/0x720
[54133.244171] ? exit_to_usermode_loop+0x7e/0x130
[54133.244190] exit_to_usermode_loop+0xc0/0x130
[54133.244209] do_syscall_64+0x16b/0x1d0
[54133.244221] entry_SYSCALL_64_after_hwframe+0x49/0xbe
The reason is that we had added a req to ctx->pending_async at the very
end, but it didn't get a chance to be processed. How could this happen?
fio#cpu0 wq#cpu1
io_add_to_prev_work io_sq_wq_submit_work
atomic_read() <<< 1
atomic_dec_return() << 1->0
list_empty(); <<< true;
list_add_tail()
atomic_read() << 0 or 1?
As atomic_ops.rst states, atomic_read does not guarantee that the
runtime modification by any other thread is visible yet, so we must take
care of that with a proper implicit or explicit memory barrier.
This issue was detected with the help of Jackie's <liuyun01@kylinos.cn>
Fixes: 31b5151064 ("io_uring: allow workqueue item to handle multiple buffered requests")
Signed-off-by: Zhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
task->saved_sigmask and ->restore_sigmask are only used in the ret-from-
syscall paths. This means that set_user_sigmask() can save ->blocked in
->saved_sigmask and do set_restore_sigmask() to indicate that ->blocked
was modified.
This way the callers do not need 2 sigset_t's passed to set/restore and
restore_user_sigmask() renamed to restore_saved_sigmask_unless() turns
into the trivial helper which just calls restore_saved_sigmask().
Link: http://lkml.kernel.org/r/20190606113206.GA9464@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Wong <e@80x24.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: David Laight <David.Laight@aculab.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We could queue a work for each req in defer and link list without
increasing async_list->cnt, so we shouldn't decrease it while exiting
from workqueue as well if we didn't process the req in async list.
Thanks to Jens Axboe <axboe@kernel.dk> for his guidance.
Fixes: 31b5151064 ("io_uring: allow workqueue item to handle multiple buffered requests")
Signed-off-by: Zhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
sq->cached_sq_head and cq->cached_cq_tail are both unsigned int. If
cached_sq_head overflows before cached_cq_tail, then we may miss a
barrier req. As cached_cq_tail always follows cached_sq_head, the NQ
should be enough.
Cc: stable@vger.kernel.org
Fixes: de0617e467 ("io_uring: add support for marking commands as draining")
Signed-off-by: Zhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull percpu updates from Dennis Zhou:
"This includes changes to let percpu_ref release the backing percpu
memory earlier after it has been switched to atomic in cases where the
percpu ref is not revived.
This will help recycle percpu memory earlier in cases where the
refcounts are pinned for prolonged periods of time"
* 'for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu:
percpu_ref: release percpu memory early without PERCPU_REF_ALLOW_REINIT
md: initialize percpu refcounters using PERCU_REF_ALLOW_REINIT
io_uring: initialize percpu refcounters using PERCU_REF_ALLOW_REINIT
percpu_ref: introduce PERCPU_REF_ALLOW_REINIT flag
-----BEGIN PGP SIGNATURE-----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=jDiB
-----END PGP SIGNATURE-----
Merge tag 'for-5.3/io_uring-20190711' of git://git.kernel.dk/linux-block
Pull io_uring updates from Jens Axboe:
"This contains:
- Support for recvmsg/sendmsg as first class opcodes.
I don't envision going much further down this path, as there are
plans in progress to support potentially any system call in an
async fashion through io_uring. But I think it does make sense to
have certain core ops available directly, especially those that can
support a "try this non-blocking" flag/mode. (me)
- Handle generic short reads automatically.
This can happen fairly easily if parts of the buffered read is
cached. Since the application needs to issue another request for
the remainder, just do this internally and save kernel/user
roundtrip while providing a nicer more robust API. (me)
- Support for linked SQEs.
This allows SQEs to depend on each other, enabling an application
to eg queue a read-from-this-file,write-to-that-file pair. (me)
- Fix race in stopping SQ thread (Jackie)"
* tag 'for-5.3/io_uring-20190711' of git://git.kernel.dk/linux-block:
io_uring: fix io_sq_thread_stop running in front of io_sq_thread
io_uring: add support for recvmsg()
io_uring: add support for sendmsg()
io_uring: add support for sqe links
io_uring: punt short reads to async context
uio: make import_iovec()/compat_import_iovec() return bytes on success
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>
-----BEGIN PGP SIGNATURE-----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=VSYT
-----END PGP SIGNATURE-----
Merge tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
"This is the main block updates for 5.3. Nothing earth shattering or
major in here, just fixes, additions, and improvements all over the
map. This contains:
- Series of documentation fixes (Bart)
- Optimization of the blk-mq ctx get/put (Bart)
- null_blk removal race condition fix (Bob)
- req/bio_op() cleanups (Chaitanya)
- Series cleaning up the segment accounting, and request/bio mapping
(Christoph)
- Series cleaning up the page getting/putting for bios (Christoph)
- block cgroup cleanups and moving it to where it is used (Christoph)
- block cgroup fixes (Tejun)
- Series of fixes and improvements to bcache, most notably a write
deadlock fix (Coly)
- blk-iolatency STS_AGAIN and accounting fixes (Dennis)
- Series of improvements and fixes to BFQ (Douglas, Paolo)
- debugfs_create() return value check removal for drbd (Greg)
- Use struct_size(), where appropriate (Gustavo)
- Two lighnvm fixes (Heiner, Geert)
- MD fixes, including a read balance and corruption fix (Guoqing,
Marcos, Xiao, Yufen)
- block opal shadow mbr additions (Jonas, Revanth)
- sbitmap compare-and-exhange improvemnts (Pavel)
- Fix for potential bio->bi_size overflow (Ming)
- NVMe pull requests:
- improved PCIe suspent support (Keith Busch)
- error injection support for the admin queue (Akinobu Mita)
- Fibre Channel discovery improvements (James Smart)
- tracing improvements including nvmetc tracing support (Minwoo Im)
- misc fixes and cleanups (Anton Eidelman, Minwoo Im, Chaitanya
Kulkarni)"
- Various little fixes and improvements to drivers and core"
* tag 'for-5.3/block-20190708' of git://git.kernel.dk/linux-block: (153 commits)
blk-iolatency: fix STS_AGAIN handling
block: nr_phys_segments needs to be zero for REQ_OP_WRITE_ZEROES
blk-mq: simplify blk_mq_make_request()
blk-mq: remove blk_mq_put_ctx()
sbitmap: Replace cmpxchg with xchg
block: fix .bi_size overflow
block: sed-opal: check size of shadow mbr
block: sed-opal: ioctl for writing to shadow mbr
block: sed-opal: add ioctl for done-mark of shadow mbr
block: never take page references for ITER_BVEC
direct-io: use bio_release_pages in dio_bio_complete
block_dev: use bio_release_pages in bio_unmap_user
block_dev: use bio_release_pages in blkdev_bio_end_io
iomap: use bio_release_pages in iomap_dio_bio_end_io
block: use bio_release_pages in bio_map_user_iov
block: use bio_release_pages in bio_unmap_user
block: optionally mark pages dirty in bio_release_pages
block: move the BIO_NO_PAGE_REF check into bio_release_pages
block: skd_main.c: Remove call to memset after dma_alloc_coherent
block: mtip32xx: Remove call to memset after dma_alloc_coherent
...
If we pass pages through an iov_iter we always already have a reference
in the caller. Thus remove the ITER_BVEC_FLAG_NO_REF and don't take
reference to pages by default for bvec backed iov_iters.
Reviewed-by: Minwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Merge misc fixes from Andrew Morton:
"15 fixes"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
linux/kernel.h: fix overflow for DIV_ROUND_UP_ULL
mm, swap: fix THP swap out
fork,memcg: alloc_thread_stack_node needs to set tsk->stack
MAINTAINERS: add CLANG/LLVM BUILD SUPPORT info
mm/vmalloc.c: avoid bogus -Wmaybe-uninitialized warning
mm/page_idle.c: fix oops because end_pfn is larger than max_pfn
initramfs: fix populate_initrd_image() section mismatch
mm/oom_kill.c: fix uninitialized oc->constraint
mm: hugetlb: soft-offline: dissolve_free_huge_page() return zero on !PageHuge
mm: soft-offline: return -EBUSY if set_hwpoison_free_buddy_page() fails
signal: remove the wrong signal_pending() check in restore_user_sigmask()
fs/binfmt_flat.c: make load_flat_shared_library() work
mm/mempolicy.c: fix an incorrect rebind node in mpol_rebind_nodemask
fs/proc/array.c: allow reporting eip/esp for all coredumping threads
mm/dev_pfn: exclude MEMORY_DEVICE_PRIVATE while computing virtual address
This is the minimal fix for stable, I'll send cleanups later.
Commit 854a6ed568 ("signal: Add restore_user_sigmask()") introduced
the visible change which breaks user-space: a signal temporary unblocked
by set_user_sigmask() can be delivered even if the caller returns
success or timeout.
Change restore_user_sigmask() to accept the additional "interrupted"
argument which should be used instead of signal_pending() check, and
update the callers.
Eric said:
: For clarity. I don't think this is required by posix, or fundamentally to
: remove the races in select. It is what linux has always done and we have
: applications who care so I agree this fix is needed.
:
: Further in any case where the semantic change that this patch rolls back
: (aka where allowing a signal to be delivered and the select like call to
: complete) would be advantage we can do as well if not better by using
: signalfd.
:
: Michael is there any chance we can get this guarantee of the linux
: implementation of pselect and friends clearly documented. The guarantee
: that if the system call completes successfully we are guaranteed that no
: signal that is unblocked by using sigmask will be delivered?
Link: http://lkml.kernel.org/r/20190604134117.GA29963@redhat.com
Fixes: 854a6ed568 ("signal: Add restore_user_sigmask()")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Eric Wong <e@80x24.org>
Tested-by: Eric Wong <e@80x24.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: <stable@vger.kernel.org> [5.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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>
Stephen reports:
I hit the following General Protection Fault when testing io_uring via
the io_uring engine in fio. This was on a VM running 5.2-rc5 and the
latest version of fio. The issue occurs for both null_blk and fake NVMe
drives. I have not tested bare metal or real NVMe SSDs. The fio script
used is given below.
[io_uring]
time_based=1
runtime=60
filename=/dev/nvme2n1 (note /dev/nullb0 also fails)
ioengine=io_uring
bs=4k
rw=readwrite
direct=1
fixedbufs=1
sqthread_poll=1
sqthread_poll_cpu=0
general protection fault: 0000 [#1] SMP PTI
CPU: 0 PID: 872 Comm: io_uring-sq Not tainted 5.2.0-rc5-cpacket-io-uring #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
RIP: 0010:fput_many+0x7/0x90
Code: 01 48 85 ff 74 17 55 48 89 e5 53 48 8b 1f e8 a0 f9 ff ff 48 85 db 48 89 df 75 f0 5b 5d f3 c3 0f 1f 40 00 0f 1f 44 00 00 89 f6 <f0> 48 29 77 38 74 01 c3 55 48 89 e5 53 48 89 fb 65 48 \
RSP: 0018:ffffadeb817ebc50 EFLAGS: 00010246
RAX: 0000000000000004 RBX: ffff8f46ad477480 RCX: 0000000000001805
RDX: 0000000000000000 RSI: 0000000000000001 RDI: f18b51b9a39552b5
RBP: ffffadeb817ebc58 R08: ffff8f46b7a318c0 R09: 000000000000015d
R10: ffffadeb817ebce8 R11: 0000000000000020 R12: ffff8f46ad4cd000
R13: 00000000fffffff7 R14: ffffadeb817ebe30 R15: 0000000000000004
FS: 0000000000000000(0000) GS:ffff8f46b7a00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055828f0bbbf0 CR3: 0000000232176004 CR4: 00000000003606f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
? fput+0x13/0x20
io_free_req+0x20/0x40
io_put_req+0x1b/0x20
io_submit_sqe+0x40a/0x680
? __switch_to_asm+0x34/0x70
? __switch_to_asm+0x40/0x70
io_submit_sqes+0xb9/0x160
? io_submit_sqes+0xb9/0x160
? __switch_to_asm+0x40/0x70
? __switch_to_asm+0x34/0x70
? __schedule+0x3f2/0x6a0
? __switch_to_asm+0x34/0x70
io_sq_thread+0x1af/0x470
? __switch_to_asm+0x34/0x70
? wait_woken+0x80/0x80
? __switch_to+0x85/0x410
? __switch_to_asm+0x40/0x70
? __switch_to_asm+0x34/0x70
? __schedule+0x3f2/0x6a0
kthread+0x105/0x140
? io_submit_sqes+0x160/0x160
? kthread+0x105/0x140
? io_submit_sqes+0x160/0x160
? kthread_destroy_worker+0x50/0x50
ret_from_fork+0x35/0x40
which occurs because using a kernel side submission thread isn't valid
without using fixed files (registered through io_uring_register()). This
causes io_uring to put the request after logging an error, but before
the file field is set in the request. If it happens to be non-zero, we
attempt to fput() garbage.
Fix this by ensuring that req->file is initialized when the request is
allocated.
Cc: stable@vger.kernel.org # 5.1+
Reported-by: Stephen Bates <sbates@raithlin.com>
Tested-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Opening and closing an io_uring instance leaks a UNIX domain socket
inode. This is because the ->file of the io_uring instance's internal
UNIX domain socket is set to point to the io_uring file, but then
sock_release() sees the non-NULL ->file and assumes the inode reference
is held by the file so doesn't call iput(). That's not the case here,
since the reference is still meant to be held by the socket; the actual
inode of the io_uring file is different.
Fix this leak by NULL-ing out ->file before releasing the socket.
Reported-by: syzbot+111cb28d9f583693aefa@syzkaller.appspotmail.com
Fixes: 2b188cc1bb ("Add io_uring IO interface")
Cc: <stable@vger.kernel.org> # v5.1+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can encounter a short read when we're doing buffered reads and the
data is partially cached. Right now we just return the short read, but
that forces the application to read that CQE, then issue another SQE
to finish the read. That read will not be cached, and hence will result
in an async punt.
It's more efficient to do that async punt from within the kernel, as
that will the not need two round trips more to the kernel.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently these functions return < 0 on error, and 0 for success.
Change that so that we return < 0 on error, but number of bytes
for success.
Some callers already treat the return value that way, others need a
slight tweak.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If io_copy_iov() fails, it will break the loop and report success,
albeit partially completed operation.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The previous patch has ensured that io_cqring_events contain
smp_rmb memory barriers, Now we can use wait_event_interruptible
to keep the code simple.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Whenever smp_rmb is required to use io_cqring_events,
keep smp_rmb inside the function io_cqring_events.
Signed-off-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This fixes couple of races which lead to infinite wait of park completion
with the following backtraces:
[20801.303319] Call Trace:
[20801.303321] ? __schedule+0x284/0x650
[20801.303323] schedule+0x33/0xc0
[20801.303324] schedule_timeout+0x1bc/0x210
[20801.303326] ? schedule+0x3d/0xc0
[20801.303327] ? schedule_timeout+0x1bc/0x210
[20801.303329] ? preempt_count_add+0x79/0xb0
[20801.303330] wait_for_completion+0xa5/0x120
[20801.303331] ? wake_up_q+0x70/0x70
[20801.303333] kthread_park+0x48/0x80
[20801.303335] io_finish_async+0x2c/0x70
[20801.303336] io_ring_ctx_wait_and_kill+0x95/0x180
[20801.303338] io_uring_release+0x1c/0x20
[20801.303339] __fput+0xad/0x210
[20801.303341] task_work_run+0x8f/0xb0
[20801.303342] exit_to_usermode_loop+0xa0/0xb0
[20801.303343] do_syscall_64+0xe0/0x100
[20801.303349] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[20801.303380] Call Trace:
[20801.303383] ? __schedule+0x284/0x650
[20801.303384] schedule+0x33/0xc0
[20801.303386] io_sq_thread+0x38a/0x410
[20801.303388] ? __switch_to_asm+0x40/0x70
[20801.303390] ? wait_woken+0x80/0x80
[20801.303392] ? _raw_spin_lock_irqsave+0x17/0x40
[20801.303394] ? io_submit_sqes+0x120/0x120
[20801.303395] kthread+0x112/0x130
[20801.303396] ? kthread_create_on_node+0x60/0x60
[20801.303398] ret_from_fork+0x35/0x40
o kthread_park() waits for park completion, so io_sq_thread() loop
should check kthread_should_park() along with khread_should_stop(),
otherwise if kthread_park() is called before prepare_to_wait()
the following schedule() never returns:
CPU#0 CPU#1
io_sq_thread_stop(): io_sq_thread():
while(!kthread_should_stop() && !ctx->sqo_stop) {
ctx->sqo_stop = 1;
kthread_park()
prepare_to_wait();
if (kthread_should_stop() {
}
schedule(); <<< nobody checks park flag,
<<< so schedule and never return
o if the flag ctx->sqo_stop is observed by the io_sq_thread() loop
it is quite possible, that kthread_should_park() check and the
following kthread_parkme() is never called, because kthread_park()
has not been yet called, but few moments later is is called and
waits there for park completion, which never happens, because
kthread has already exited:
CPU#0 CPU#1
io_sq_thread_stop(): io_sq_thread():
ctx->sqo_stop = 1;
while(!kthread_should_stop() && !ctx->sqo_stop) {
<<< observe sqo_stop and exit the loop
}
if (kthread_should_park())
kthread_parkme(); <<< never called, since was
<<< never parked
kthread_park() <<< waits forever for park completion
In the current patch we quit the loop by only kthread_should_park()
check (kthread_park() is synchronous, so kthread_should_stop() is
never observed), and we abandon ->sqo_stop flag, since it is racy.
At the end of the io_sq_thread() we unconditionally call parmke(),
since we've exited the loop by the park flag.
Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We always pass in 0 for the cqe flags argument, since the support for
"this read hit page cache" hint was dropped.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The test case we have is rightfully failing with the current kernel:
io_uring_setup(1, 0x7ffe2cafebe0), flags: IORING_SETUP_SQPOLL|IORING_SETUP_SQ_AFF, resv: 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000, sq_thread_cpu: 4
expected -1, got 3
This is in a vm, and CPU3 is the last valid one, hence asking for 4
should fail the setup with -EINVAL, not succeed. The problem is that
we're using array_index_nospec() with nr_cpu_ids as the index, hence we
wrap and end up using CPU0 instead of CPU4. This makes the setup
succeed where it should be failing.
We don't need to use array_index_nospec() as we're not indexing any
array with this. Instead just compare with nr_cpu_ids directly. This
is fine as we're checking with cpu_online() afterwards.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pach series "Add FOLL_LONGTERM to GUP fast and use it".
HFI1, qib, and mthca, use get_user_pages_fast() due to its performance
advantages. These pages can be held for a significant time. But
get_user_pages_fast() does not protect against mapping FS DAX pages.
Introduce FOLL_LONGTERM and use this flag in get_user_pages_fast() which
retains the performance while also adding the FS DAX checks. XDP has also
shown interest in using this functionality.[1]
In addition we change get_user_pages() to use the new FOLL_LONGTERM flag
and remove the specialized get_user_pages_longterm call.
[1] https://lkml.org/lkml/2019/3/19/939
"longterm" is a relative thing and at this point is probably a misnomer.
This is really flagging a pin which is going to be given to hardware and
can't move. I've thought of a couple of alternative names but I think we
have to settle on if we are going to use FL_LAYOUT or something else to
solve the "longterm" problem. Then I think we can change the flag to a
better name.
Secondly, it depends on how often you are registering memory. I have
spoken with some RDMA users who consider MR in the performance path...
For the overall application performance. I don't have the numbers as the
tests for HFI1 were done a long time ago. But there was a significant
advantage. Some of which is probably due to the fact that you don't have
to hold mmap_sem.
Finally, architecturally I think it would be good for everyone to use
*_fast. There are patches submitted to the RDMA list which would allow
the use of *_fast (they reworking the use of mmap_sem) and as soon as they
are accepted I'll submit a patch to convert the RDMA core as well. Also
to this point others are looking to use *_fast.
As an aside, Jasons pointed out in my previous submission that *_fast and
*_unlocked look very much the same. I agree and I think further cleanup
will be coming. But I'm focused on getting the final solution for DAX at
the moment.
This patch (of 7):
This patch starts a series which aims to support FOLL_LONGTERM in
get_user_pages_fast(). Some callers who would like to do a longterm (user
controlled pin) of pages with the fast variant of GUP for performance
purposes.
Rather than have a separate get_user_pages_longterm() call, introduce
FOLL_LONGTERM and change the longterm callers to use it.
This patch does not change any functionality. In the short term
"longterm" or user controlled pins are unsafe for Filesystems and FS DAX
in particular has been blocked. However, callers of get_user_pages_fast()
were not "protected".
FOLL_LONGTERM can _only_ be supported with get_user_pages[_fast]() as it
requires vmas to determine if DAX is in use.
NOTE: In merging with the CMA changes we opt to change the
get_user_pages() call in check_and_migrate_cma_pages() to a call of
__get_user_pages_locked() on the newly migrated pages. This makes the
code read better in that we are calling __get_user_pages_locked() on the
pages before and after a potential migration.
As a side affect some of the interfaces are cleaned up but this is not the
primary purpose of the series.
In review[1] it was asked:
<quote>
> This I don't get - if you do lock down long term mappings performance
> of the actual get_user_pages call shouldn't matter to start with.
>
> What do I miss?
A couple of points.
First "longterm" is a relative thing and at this point is probably a
misnomer. This is really flagging a pin which is going to be given to
hardware and can't move. I've thought of a couple of alternative names
but I think we have to settle on if we are going to use FL_LAYOUT or
something else to solve the "longterm" problem. Then I think we can
change the flag to a better name.
Second, It depends on how often you are registering memory. I have spoken
with some RDMA users who consider MR in the performance path... For the
overall application performance. I don't have the numbers as the tests
for HFI1 were done a long time ago. But there was a significant
advantage. Some of which is probably due to the fact that you don't have
to hold mmap_sem.
Finally, architecturally I think it would be good for everyone to use
*_fast. There are patches submitted to the RDMA list which would allow
the use of *_fast (they reworking the use of mmap_sem) and as soon as they
are accepted I'll submit a patch to convert the RDMA core as well. Also
to this point others are looking to use *_fast.
As an asside, Jasons pointed out in my previous submission that *_fast and
*_unlocked look very much the same. I agree and I think further cleanup
will be coming. But I'm focused on getting the final solution for DAX at
the moment.
</quote>
[1] https://lore.kernel.org/lkml/20190220180255.GA12020@iweiny-DESK2.sc.intel.com/T/#md6abad2569f3bf6c1f03686c8097ab6563e94965
[ira.weiny@intel.com: v3]
Link: http://lkml.kernel.org/r/20190328084422.29911-2-ira.weiny@intel.com
Link: http://lkml.kernel.org/r/20190328084422.29911-2-ira.weiny@intel.com
Link: http://lkml.kernel.org/r/20190317183438.2057-2-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When punting to workers the SQE gets copied after the initial try.
There is a race condition between reading SQE data for the initial try
and copying it for punting it to the workers.
For example io_rw_done calls kiocb->ki_complete even if it was prepared
for IORING_OP_FSYNC (and would be NULL).
The easiest solution for now is to alway prepare again in the worker.
req->file is safe to prepare though as long as it is checked before use.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Percpu reference counters should now be initialized with the
PERCPU_REF_ALLOW_REINIT in order to allow switching them to the
percpu mode from the atomic mode. This is exactly what
percpu_ref_reinit() called from __io_uring_register() is supposed to
do. So let's initialize percpu refcounters with the
PERCU_REF_ALLOW_REINIT flag.
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
This issue is found by running liburing/test/io_uring_setup test.
When test run, the testcase "attempt to bind to invalid cpu" would not
pass with messages like:
io_uring_setup(1, 0xbfc2f7c8), \
flags: IORING_SETUP_SQPOLL|IORING_SETUP_SQ_AFF, \
resv: 0x00000000 0x00000000 0x00000000 0x00000000 0x00000000, \
sq_thread_cpu: 2
expected -1, got 3
FAIL
On my system, there is:
CPU(s) possible : 0-3
CPU(s) online : 0-1
CPU(s) offline : 2-3
CPU(s) present : 0-1
The sq_thread_cpu 2 is offline on my system, so the bind should fail.
But cpu_possible() will pass the check. We shouldn't be able to bind
to an offline cpu. Use cpu_online() to do the check.
After the change, the testcase run as expected: EINVAL will be returned
for cpu offlined.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Shenghui Wang <shhuiw@foxmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently variable ret is declared in a while-loop code block that
shadows another variable ret. When an error occurs in the while-loop
the error return in ret is not being set in the outer code block and
so the error check on ret is always going to be checking on the wrong
ret variable resulting in check that is always going to be true and
a premature return occurs.
Fix this by removing the declaration of the inner while-loop variable
ret so that shadowing does not occur.
Addresses-Coverity: ("'Constant' variable guards dead code")
Fixes: 6b06314c47 ("io_uring: add file set registration")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No need to set it in io_poll_add; io_poll_complete doesn't use it to set
the result in the CQE.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
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>
In io_sqe_buffer_register() we allocate a number of arrays based on the
iov_len from the user-provided iov. While we limit iov_len to SZ_1G,
we can still attempt to allocate arrays exceeding MAX_ORDER.
On a 64-bit system with 4KiB pages, for an iov where iov_base = 0x10 and
iov_len = SZ_1G, we'll calculate that nr_pages = 262145. When we try to
allocate a corresponding array of (16-byte) bio_vecs, requiring 4194320
bytes, which is greater than 4MiB. This results in SLUB warning that
we're trying to allocate greater than MAX_ORDER, and failing the
allocation.
Avoid this by using kvmalloc() for allocations dependent on the
user-provided iov_len. At the same time, fix a leak of imu->bvec when
registration fails.
Full splat from before this patch:
WARNING: CPU: 1 PID: 2314 at mm/page_alloc.c:4595 __alloc_pages_nodemask+0x7ac/0x2938 mm/page_alloc.c:4595
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 2314 Comm: syz-executor326 Not tainted 5.1.0-rc7-dirty #4
Hardware name: linux,dummy-virt (DT)
Call trace:
dump_backtrace+0x0/0x2f0 include/linux/compiler.h:193
show_stack+0x20/0x30 arch/arm64/kernel/traps.c:158
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x110/0x190 lib/dump_stack.c:113
panic+0x384/0x68c kernel/panic.c:214
__warn+0x2bc/0x2c0 kernel/panic.c:571
report_bug+0x228/0x2d8 lib/bug.c:186
bug_handler+0xa0/0x1a0 arch/arm64/kernel/traps.c:956
call_break_hook arch/arm64/kernel/debug-monitors.c:301 [inline]
brk_handler+0x1d4/0x388 arch/arm64/kernel/debug-monitors.c:316
do_debug_exception+0x1a0/0x468 arch/arm64/mm/fault.c:831
el1_dbg+0x18/0x8c
__alloc_pages_nodemask+0x7ac/0x2938 mm/page_alloc.c:4595
alloc_pages_current+0x164/0x278 mm/mempolicy.c:2132
alloc_pages include/linux/gfp.h:509 [inline]
kmalloc_order+0x20/0x50 mm/slab_common.c:1231
kmalloc_order_trace+0x30/0x2b0 mm/slab_common.c:1243
kmalloc_large include/linux/slab.h:480 [inline]
__kmalloc+0x3dc/0x4f0 mm/slub.c:3791
kmalloc_array include/linux/slab.h:670 [inline]
io_sqe_buffer_register fs/io_uring.c:2472 [inline]
__io_uring_register fs/io_uring.c:2962 [inline]
__do_sys_io_uring_register fs/io_uring.c:3008 [inline]
__se_sys_io_uring_register fs/io_uring.c:2990 [inline]
__arm64_sys_io_uring_register+0x9e0/0x1bc8 fs/io_uring.c:2990
__invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
invoke_syscall arch/arm64/kernel/syscall.c:47 [inline]
el0_svc_common.constprop.0+0x148/0x2e0 arch/arm64/kernel/syscall.c:83
el0_svc_handler+0xdc/0x100 arch/arm64/kernel/syscall.c:129
el0_svc+0x8/0xc arch/arm64/kernel/entry.S:948
SMP: stopping secondary CPUs
Dumping ftrace buffer:
(ftrace buffer empty)
Kernel Offset: disabled
CPU features: 0x002,23000438
Memory Limit: none
Rebooting in 1 seconds..
Fixes: edafccee56 ("io_uring: add support for pre-mapped user IO buffers")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-block@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we don't end up actually calling submit in io_sq_wq_submit_work(),
we still need to drop the submit reference to the request. If we
don't, then we can leak the request. This can happen if we race
with ring shutdown while flushing the workqueue for requests that
require use of the mm_struct.
Fixes: e65ef56db4 ("io_uring: use regular request ref counts")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In io_sq_offload_start(), we call cpu_possible() on an unbounded cpu
value from userspace. On v5.1-rc7 on arm64 with
CONFIG_DEBUG_PER_CPU_MAPS, this results in a splat:
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 cpu_max_bits_warn include/linux/cpumask.h:121 [inline]
There was an attempt to fix this in commit:
917257daa0 ("io_uring: only test SQPOLL cpu after we've verified it")
... by adding a check after the cpu value had been limited to NR_CPU_IDS
using array_index_nospec(). However, this left an unbound check at the
start of the function, for which the warning still fires.
Let's fix this correctly by checking that the cpu value is bound by
nr_cpu_ids before passing it to cpu_possible(). Note that only
nr_cpu_ids of a cpumask are guaranteed to exist at runtime, and
nr_cpu_ids can be significantly smaller than NR_CPUs. For example, an
arm64 defconfig has NR_CPUS=256, while my test VM has 4 vCPUs.
Following the intent from the commit message for 917257daa0, the
check is moved under the SQ_AFF branch, which is the only branch where
the cpu values is consumed. The check is performed before bounding the
value with array_index_nospec() so that we don't silently accept bogus
cpu values from userspace, where array_index_nospec() would force these
values to 0.
I suspect we can remove the array_index_nospec() call entirely, but I've
conservatively left that in place, updated to use nr_cpu_ids to match
the prior check.
Tested on arm64 with the Syzkaller reproducer:
https://syzkaller.appspot.com/bug?extid=cd714a07c6de2bc34293https://syzkaller.appspot.com/x/repro.syz?x=15d8b397200000
Full splat from before this patch:
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 cpu_max_bits_warn include/linux/cpumask.h:121 [inline]
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 cpumask_check include/linux/cpumask.h:128 [inline]
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 cpumask_test_cpu include/linux/cpumask.h:344 [inline]
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 io_sq_offload_start fs/io_uring.c:2244 [inline]
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 io_uring_create fs/io_uring.c:2864 [inline]
WARNING: CPU: 1 PID: 27601 at include/linux/cpumask.h:121 io_uring_setup+0x1108/0x15a0 fs/io_uring.c:2916
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 27601 Comm: syz-executor.0 Not tainted 5.1.0-rc7 #3
Hardware name: linux,dummy-virt (DT)
Call trace:
dump_backtrace+0x0/0x2f0 include/linux/compiler.h:193
show_stack+0x20/0x30 arch/arm64/kernel/traps.c:158
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x110/0x190 lib/dump_stack.c:113
panic+0x384/0x68c kernel/panic.c:214
__warn+0x2bc/0x2c0 kernel/panic.c:571
report_bug+0x228/0x2d8 lib/bug.c:186
bug_handler+0xa0/0x1a0 arch/arm64/kernel/traps.c:956
call_break_hook arch/arm64/kernel/debug-monitors.c:301 [inline]
brk_handler+0x1d4/0x388 arch/arm64/kernel/debug-monitors.c:316
do_debug_exception+0x1a0/0x468 arch/arm64/mm/fault.c:831
el1_dbg+0x18/0x8c
cpu_max_bits_warn include/linux/cpumask.h:121 [inline]
cpumask_check include/linux/cpumask.h:128 [inline]
cpumask_test_cpu include/linux/cpumask.h:344 [inline]
io_sq_offload_start fs/io_uring.c:2244 [inline]
io_uring_create fs/io_uring.c:2864 [inline]
io_uring_setup+0x1108/0x15a0 fs/io_uring.c:2916
__do_sys_io_uring_setup fs/io_uring.c:2929 [inline]
__se_sys_io_uring_setup fs/io_uring.c:2926 [inline]
__arm64_sys_io_uring_setup+0x50/0x70 fs/io_uring.c:2926
__invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
invoke_syscall arch/arm64/kernel/syscall.c:47 [inline]
el0_svc_common.constprop.0+0x148/0x2e0 arch/arm64/kernel/syscall.c:83
el0_svc_handler+0xdc/0x100 arch/arm64/kernel/syscall.c:129
el0_svc+0x8/0xc arch/arm64/kernel/entry.S:948
SMP: stopping secondary CPUs
Dumping ftrace buffer:
(ftrace buffer empty)
Kernel Offset: disabled
CPU features: 0x002,23000438
Memory Limit: none
Rebooting in 1 seconds..
Fixes: 917257daa0 ("io_uring: only test SQPOLL cpu after we've verified it")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: linux-block@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Simplied the logic
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we only post a cqe if we get an error OUTSIDE of submission.
For submission, we return the error directly through io_uring_enter().
This is a bit awkward for applications, and it makes more sense to
always post a cqe with an error, if the error happens on behalf of an
sqe.
This changes submission behavior a bit. io_uring_enter() returns -ERROR
for an error, and > 0 for number of sqes submitted. Before this change,
if you wanted to submit 8 entries and had an error on the 5th entry,
io_uring_enter() would return 4 (for number of entries successfully
submitted) and rewind the sqring. The application would then have to
peek at the sqring and figure out what was wrong with the head sqe, and
then skip it itself. With this change, we'll return 5 since we did
consume 5 sqes, and the last sqe (with the error) will result in a cqe
being posted with the error.
This makes the logic easier to handle in the application, and it cleans
up the submission part.
Suggested-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is no operation to order with afterwards, and removing the flag is
not critical in any way.
There will always be a "race condition" where the application will
trigger IORING_ENTER_SQ_WAKEUP when it isn't actually needed.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
smp_store_release in io_commit_sqring already orders the store to
dropped before the update to SQ head.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The memory operations before reading cq head are unrelated and we
don't care about their order.
Document that the control dependency in combination with READ_ONCE and
WRITE_ONCE forms a barrier we need.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
wq_has_sleeper has a full barrier internally. The smp_rmb barrier in
io_uring_poll synchronizes with it.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The application reading the CQ ring needs a barrier to pair with the
smp_store_release in io_commit_cqring, not the barrier after it.
Also a write barrier *after* writing something (but not *before*
writing anything interesting) doesn't order anything, so an smp_wmb()
after writing SQ tail is not needed.
Additionally consider reading SQ head and writing CQ tail in the notes.
Also add some clarifications how the various other fields in the ring
buffers are used.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Not all request types set REQ_F_FORCE_NONBLOCK when they needed async
punting; reverse logic instead and set REQ_F_NOWAIT if request mustn't
be punted.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Merged with my previous patch for this.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since commit 09bb839434 we don't use the state argument for any sort
of on-stack caching in the io read and write path. Remove the stale
and unused argument from them, and bubble it up to __io_submit_sqe()
and down to io_prep_rw().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring_poll shouldn't signal EPOLLOUT | EPOLLWRNORM if the queue is
full; the old check would always signal EPOLLOUT | EPOLLWRNORM (unless
there were U32_MAX - 1 entries in the SQ queue).
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reading the SQ tail needs to come after setting IORING_SQ_NEED_WAKEUP in
flags; there is no cheap barrier for ordering a store before a load, a
full memory barrier is required.
Userspace needs a full memory barrier between updating SQ tail and
checking for the IORING_SQ_NEED_WAKEUP too.
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A read memory barrier is required between reading SQ tail and reading
the actual data belonging to the SQ entry.
Userspace needs a matching write barrier between writing SQ entries and
updating SQ tail (using smp_store_release to update tail will do).
Signed-off-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have multiple threads doing io_uring_register(2) on an io_uring
fd, then we can potentially try and kill the percpu reference while
someone else has already killed it.
Prevent this race by failing io_uring_register(2) if the ref is marked
dying. This is safe since we're inside the io_uring mutex.
Fixes: b19062a567 ("io_uring: fix possible deadlock between io_uring_{enter,register}")
Reported-by: syzbot <syzbot+10d25e23199614b7721f@syzkaller.appspotmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is a leftover from when the rings initially were not free flowing,
and hence a test for tail + 1 == head would indicate full. Since we now
let them wrap instead of mask them with the size, we need to check if
they drift more than the ring size from each other.
This fixes a case where we'd overwrite CQ ring entries, if the user
failed to reap completions. Both cases would ultimately result in lost
completions as the application violated the depth it asked for. The only
difference is that before this fix we'd return invalid entries for the
overflowed completions, instead of properly flagging it in the
cq_ring->overflow variable.
Reported-by: Stefan Bühler <source@stbuehler.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If we have multiple threads, one doing io_uring_enter() while the other
is doing io_uring_register(), we can run into a deadlock between the
two. io_uring_register() must wait for existing users of the io_uring
instance to exit. But it does so while holding the io_uring mutex.
Callers of io_uring_enter() may need this mutex to make progress (and
eventually exit). If we wait for users to exit in io_uring_register(),
we can't do so with the io_uring mutex held without potentially risking
a deadlock.
Drop the io_uring mutex while waiting for existing callers to exit. This
is safe and guaranteed to make forward progress, since we already killed
the percpu ref before doing so. Hence later callers of io_uring_enter()
will be rejected.
Reported-by: syzbot+16dc03452dee970a0c3e@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since the fget/fput handling was reworked in commit 09bb839434, we
never call io_file_put() with state == NULL (and hence file != NULL)
anymore. Remove that case.
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently call cpu_possible() even if we don't use the CPU. Move the
test under the SQ_AFF branch, which is the only place where we'll use
the value. Do the cpu_possible() test AFTER we've limited it to a max
of NR_CPUS. This avoids triggering the following warning:
WARNING: CPU: 1 PID: 7600 at include/linux/cpumask.h:121 cpu_max_bits_warn
if CONFIG_DEBUG_PER_CPU_MAPS is enabled.
While in there, also move the SQ thread idle period assignment inside
SETUP_SQPOLL, as we don't use it otherwise either.
Reported-by: syzbot+cd714a07c6de2bc34293@syzkaller.appspotmail.com
Fixes: 6c271ce2f1 ("io_uring: add submission polling")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This options spawns a kernel side thread that will poll for submissions
(and completions, if IORING_SETUP_IOPOLL is set). As this allows a user
to potentially use more cycles outside of the normal hierarchy,
restrict the use of this feature to root.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Will Deacon reported the following KASAN complaint:
[ 149.890370] ==================================================================
[ 149.891266] BUG: KASAN: double-free or invalid-free in io_sqe_files_unregister+0xa8/0x140
[ 149.892218]
[ 149.892411] CPU: 113 PID: 3974 Comm: io_uring_regist Tainted: G B 5.1.0-rc3-00012-g40b114779944 #3
[ 149.893623] Hardware name: linux,dummy-virt (DT)
[ 149.894169] Call trace:
[ 149.894539] dump_backtrace+0x0/0x228
[ 149.895172] show_stack+0x14/0x20
[ 149.895747] dump_stack+0xe8/0x124
[ 149.896335] print_address_description+0x60/0x258
[ 149.897148] kasan_report_invalid_free+0x78/0xb8
[ 149.897936] __kasan_slab_free+0x1fc/0x228
[ 149.898641] kasan_slab_free+0x10/0x18
[ 149.899283] kfree+0x70/0x1f8
[ 149.899798] io_sqe_files_unregister+0xa8/0x140
[ 149.900574] io_ring_ctx_wait_and_kill+0x190/0x3c0
[ 149.901402] io_uring_release+0x2c/0x48
[ 149.902068] __fput+0x18c/0x510
[ 149.902612] ____fput+0xc/0x18
[ 149.903146] task_work_run+0xf0/0x148
[ 149.903778] do_notify_resume+0x554/0x748
[ 149.904467] work_pending+0x8/0x10
[ 149.905060]
[ 149.905331] Allocated by task 3974:
[ 149.905934] __kasan_kmalloc.isra.0.part.1+0x48/0xf8
[ 149.906786] __kasan_kmalloc.isra.0+0xb8/0xd8
[ 149.907531] kasan_kmalloc+0xc/0x18
[ 149.908134] __kmalloc+0x168/0x248
[ 149.908724] __arm64_sys_io_uring_register+0x2b8/0x15a8
[ 149.909622] el0_svc_common+0x100/0x258
[ 149.910281] el0_svc_handler+0x48/0xc0
[ 149.910928] el0_svc+0x8/0xc
[ 149.911425]
[ 149.911696] Freed by task 3974:
[ 149.912242] __kasan_slab_free+0x114/0x228
[ 149.912955] kasan_slab_free+0x10/0x18
[ 149.913602] kfree+0x70/0x1f8
[ 149.914118] __arm64_sys_io_uring_register+0xc2c/0x15a8
[ 149.915009] el0_svc_common+0x100/0x258
[ 149.915670] el0_svc_handler+0x48/0xc0
[ 149.916317] el0_svc+0x8/0xc
[ 149.916817]
[ 149.917101] The buggy address belongs to the object at ffff8004ce07ed00
[ 149.917101] which belongs to the cache kmalloc-128 of size 128
[ 149.919197] The buggy address is located 0 bytes inside of
[ 149.919197] 128-byte region [ffff8004ce07ed00, ffff8004ce07ed80)
[ 149.921142] The buggy address belongs to the page:
[ 149.921953] page:ffff7e0013381f00 count:1 mapcount:0 mapping:ffff800503417c00 index:0x0 compound_mapcount: 0
[ 149.923595] flags: 0x1ffff00000010200(slab|head)
[ 149.924388] raw: 1ffff00000010200 dead000000000100 dead000000000200 ffff800503417c00
[ 149.925706] raw: 0000000000000000 0000000080400040 00000001ffffffff 0000000000000000
[ 149.927011] page dumped because: kasan: bad access detected
[ 149.927956]
[ 149.928224] Memory state around the buggy address:
[ 149.929054] ffff8004ce07ec00: 00 00 00 00 00 00 00 00 fc fc fc fc fc fc fc fc
[ 149.930274] ffff8004ce07ec80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 149.931494] >ffff8004ce07ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 149.932712] ^
[ 149.933281] ffff8004ce07ed80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 149.934508] ffff8004ce07ee00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 149.935725] ==================================================================
which is due to a failure in registrering a fileset. This frees the
ctx->user_files pointer, but doesn't clear it. When the io_uring
instance is later freed through the normal channels, we free this
pointer again. At this point it's invalid.
Ensure we clear the pointer when we free it for the error case.
Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In case of direct write -EAGAIN will be returned if page cache was
previously populated. To avoid immediate completion of a request
with -EAGAIN error write has to be offloaded to the async worker,
like io_read() does.
Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On big-endian architectures, the signal masks are differnet
between 32-bit and 64-bit tasks, so we have to use a different
function for reading them from user space.
io_cqring_wait() initially got this wrong, and always interprets
this as a native structure. This is ok on x86 and most arm64,
but not on s390, ppc64be, mips64be, sparc64 and parisc.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----
iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlyWVysQHGF4Ym9lQGtl
cm5lbC5kawAKCRD301j7KXHgpn5lD/0bEg76kbuwOUy5+FDqOpF0MNOU7xZcYcsI
YkkaKkUi2YQL6NJlkU7AhtPwep+J2sgSnDW9Ho9WIXbsnsO6UF79uIdcix6zJGIl
WnZZ3BLgWeciCfrzFpn3FFZnm/AKJSPWPmllUFvmUYT9GdRgN4ZnHBsS1HTlJ1m5
5HhwLtaYOsZ75NxWBRqWspmtFe+XZ/CrjGgmvIF8FjSuIP2q0RrOmCF1XAA82umd
ehiU1ZtQ+v4FHxmJWjzMWhrCj2y0gmPb+DotIqefFjVnd/G+LrFGMD1fsLoQVFDy
L5VzSOGj1E4KXfDpIeGnz/08dpqXmOkvsSaNnv1U7vA7SCkbodR/BA1EKJrvk5v7
MGkkcQDaU/WzC41RCyVQNWAWjzNLKbruXQ+1HqCx5eh7uthvMQMXDvGf4Jgeq+/E
vGzrEKZ6qI78Vy0mXSy4dfFbFaNTjCkE2jbIG7BQx5zdtnS9/VPXNkpZxPrGLM+P
/fTsLXghU9lKn6WHVtLpQsfJr0OMjyC9JA23pTX2G9MtBhDcyuRs+uCeQgG6cIkl
F15LGuOY7YGYxRsegdinFaoldnHersUDx19c+uFdrB0k0A/A6KeGHuZx7aJPkW1L
M89FkyJr2ZBgc26PvKz6j1Hwl2MKJC5h8TpPES/QnulWh4FbqqH3a501Qa1AQuxC
1me95iy74w==
=l4lx
-----END PGP SIGNATURE-----
Merge tag 'io_uring-20190323' of git://git.kernel.dk/linux-block
Pull io_uring fixes and improvements from Jens Axboe:
"The first five in this series are heavily inspired by the work Al did
on the aio side to fix the races there.
The last two re-introduce a feature that was in io_uring before it got
merged, but which I pulled since we didn't have a good way to have
BVEC iters that already have a stable reference. These aren't
necessarily related to block, it's just how io_uring pins fixed
buffers"
* tag 'io_uring-20190323' of git://git.kernel.dk/linux-block:
block: add BIO_NO_PAGE_REF flag
iov_iter: add ITER_BVEC_FLAG_NO_REF flag
io_uring: mark me as the maintainer
io_uring: retry bulk slab allocs as single allocs
io_uring: fix poll races
io_uring: fix fget/fput handling
io_uring: add prepped flag
io_uring: make io_read/write return an integer
io_uring: use regular request ref counts
For ITER_BVEC, if we're holding on to kernel pages, the caller
doesn't need to grab a reference to the bvec pages, and drop that
same reference on IO completion. This is essentially safe for any
ITER_BVEC, but some use cases end up reusing pages and uncondtionally
dropping a page reference on completion. And example of that is
sendfile(2), that ends up being a splice_in + splice_out on the
pipe pages.
Add a flag that tells us it's fine to not grab a page reference
to the bvec pages, since that caller knows not to drop a reference
when it's done with the pages.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
I've seen cases where bulk alloc fails, since the bulk alloc API
is all-or-nothing - either we get the number we ask for, or it
returns 0 as number of entries.
If we fail a batch bulk alloc, retry a "normal" kmem_cache_alloc()
and just use that instead of failing with -EAGAIN.
While in there, ensure we use GFP_KERNEL. That was an oversight in
the original code, when we switched away from GFP_ATOMIC.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is a straight port of Al's fix for the aio poll implementation,
since the io_uring version is heavily based on that. The below
description is almost straight from that patch, just modified to
fit the io_uring situation.
io_poll() has to cope with several unpleasant problems:
* requests that might stay around indefinitely need to
be made visible for io_cancel(2); that must not be done to
a request already completed, though.
* in cases when ->poll() has placed us on a waitqueue,
wakeup might have happened (and request completed) before ->poll()
returns.
* worse, in some early wakeup cases request might end
up re-added into the queue later - we can't treat "woken up and
currently not in the queue" as "it's not going to stick around
indefinitely"
* ... moreover, ->poll() might have decided not to
put it on any queues to start with, and that needs to be distinguished
from the previous case
* ->poll() might have tried to put us on more than one queue.
Only the first will succeed for io poll, so we might end up missing
wakeups. OTOH, we might very well notice that only after the
wakeup hits and request gets completed (all before ->poll() gets
around to the second poll_wait()). In that case it's too late to
decide that we have an error.
req->woken was an attempt to deal with that. Unfortunately, it was
broken. What we need to keep track of is not that wakeup has happened -
the thing might come back after that. It's that async reference is
already gone and won't come back, so we can't (and needn't) put the
request on the list of cancellables.
The easiest case is "request hadn't been put on any waitqueues"; we
can tell by seeing NULL apt.head, and in that case there won't be
anything async. We should either complete the request ourselves
(if vfs_poll() reports anything of interest) or return an error.
In all other cases we get exclusion with wakeups by grabbing the
queue lock.
If request is currently on queue and we have something interesting
from vfs_poll(), we can steal it and complete the request ourselves.
If it's on queue and vfs_poll() has not reported anything interesting,
we either put it on the cancellable list, or, if we know that it
hadn't been put on all queues ->poll() wanted it on, we steal it and
return an error.
If it's _not_ on queue, it's either been already dealt with (in which
case we do nothing), or there's io_poll_complete_work() about to be
executed. In that case we either put it on the cancellable list,
or, if we know it hadn't been put on all queues ->poll() wanted it on,
simulate what cancel would've done.
Fixes: 221c5eb233 ("io_uring: add support for IORING_OP_POLL")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This isn't a straight port of commit 84c4e1f89f for aio.c, since
io_uring doesn't use files in exactly the same way. But it's pretty
close. See the commit message for that commit.
This essentially fixes a use-after-free with the poll command
handling, but it takes cue from Linus's approach to just simplifying
the file handling. We move the setup of the file into a higher level
location, so the individual commands don't have to deal with it. And
then we release the reference when we free the associated io_kiocb.
Fixes: 221c5eb233 ("io_uring: add support for IORING_OP_POLL")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently use the fact that if ->ki_filp is already set, then we've
done the prep. In preparation for moving the file assignment earlier,
use a separate flag to tell whether the request has been prepped for
IO or not.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Get rid of the special casing of "normal" requests not having
any references to the io_kiocb. We initialize the ref count to 2,
one for the submission side, and one or the completion side.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
All users of VM_MAX_READAHEAD actually convert it to kbytes and then to
pages. Define the macro explicitly as (SZ_128K / PAGE_SIZE). This
simplifies the expression in every filesystem. Also rename the macro to
VM_READAHEAD_PAGES to properly convey its meaning. Finally remove unused
VM_MIN_READAHEAD
[akpm@linux-foundation.org: fix fs/io_uring.c, per Stephen]
Link: http://lkml.kernel.org/r/20181221144053.24318-1-nborisov@suse.com
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Eric Van Hensbergen <ericvh@gmail.com>
Cc: Latchesar Ionkov <lucho@ionkov.net>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Chris Mason <clm@fb.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Right now we punt any buffered request that ends up triggering an
-EAGAIN to an async workqueue. This works fine in terms of providing
async execution of them, but it also can create quite a lot of work
queue items. For sequentially buffered IO, it's advantageous to
serialize the issue of them. For reads, the first one will trigger a
read-ahead, and subsequent request merely end up waiting on later pages
to complete. For writes, devices usually respond better to streamed
sequential writes.
Add state to track the last buffered request we punted to a work queue,
and if the next one is sequential to the previous, attempt to get the
previous work item to handle it. We limit the number of sequential
add-ons to the a multiple (8) of the max read-ahead size of the file.
This should be a good number for both reads and wries, as it defines the
max IO size the device can do directly.
This drastically cuts down on the number of context switches we need to
handle buffered sequential IO, and a basic test case of copying a big
file with io_uring sees a 5x speedup.
Reviewed-by: Hannes Reinecke <hare@suse.com>
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>
We'll use this for the POLL implementation. Regular requests will
NOT be using references, so initialize it to 0. Any real use of
the io_kiocb ref will initialize it to at least 2.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: 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>
Similarly to how we use the state->ios_left to know how many references
to get to a file, we can use it to allocate the io_kiocb's we need in
bulk.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a separate io_submit_state structure, to cache some of the things
we need for IO submission.
One such example is file reference batching. io_submit_state. We get as
many references as the number of sqes we are submitting, and drop
unused ones if we end up switching files. The assumption here is that
we're usually only dealing with one fd, and if there are multiple,
hopefuly they are at least somewhat ordered. Could trivially be extended
to cover multiple fds, if needed.
On the completion side we do the same thing, except this is trivially
done just locally in io_iopoll_reap().
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>
Jens Axboe