linux-toradex.git/io_uring, branch v6.15-rc7 Linux kernel for Apalis and Colibri modules io_uring/fdinfo: grab ctx->uring_lock around io_uring_show_fdinfo() 2025-05-14T13:15:28+00:00 Jens Axboe axboe@kernel.dk 2025-05-13T21:02:23+00:00 d871198ee431d90f5308d53998c1ba1d5db5619a Not everything requires locking in there, which is why the 'has_lock' variable exists. But enough does that it's a bit unwieldy to manage. Wrap the whole thing in a ->uring_lock trylock, and just return with no output if we fail to grab it. The existing trylock() will already have greatly diminished utility/output for the failure case. This fixes an issue with reading the SQE fields, if the ring is being actively resized at the same time. Reported-by: Jann Horn <jannh@google.com> Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS") Signed-off-by: Jens Axboe <axboe@kernel.dk> 
Not everything requires locking in there, which is why the 'has_lock'
variable exists. But enough does that it's a bit unwieldy to manage.
Wrap the whole thing in a ->uring_lock trylock, and just return
with no output if we fail to grab it. The existing trylock() will
already have greatly diminished utility/output for the failure case.

This fixes an issue with reading the SQE fields, if the ring is being
actively resized at the same time.

Reported-by: Jann Horn <jannh@google.com>
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/memmap: don't use page_address() on a highmem page 2025-05-12T15:27:41+00:00 Jens Axboe axboe@kernel.dk 2025-05-12T15:06:06+00:00 f446c6311e86618a1f81eb576b56a6266307238f For older/32-bit systems with highmem, don't assume that the pages in a mapped region are always going to be mapped. If io_region_init_ptr() finds that the pages are coalescable, also check if the first page is a HighMem page or not. If it is, fall through to the usual vmap() mapping rather than attempt to get the unmapped page address. Cc: stable@vger.kernel.org Fixes: c4d0ac1c1567 ("io_uring/memmap: optimise single folio regions") Link: https://lore.kernel.org/all/681fe2fb.050a0220.f2294.001a.GAE@google.com/ Reported-by: syzbot+5b8c4abafcb1d791ccfc@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/681fed0a.050a0220.f2294.001c.GAE@google.com/ Reported-by: syzbot+6456a99dfdc2e78c4feb@syzkaller.appspotmail.com Tested-by: syzbot+6456a99dfdc2e78c4feb@syzkaller.appspotmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
For older/32-bit systems with highmem, don't assume that the pages in
a mapped region are always going to be mapped. If io_region_init_ptr()
finds that the pages are coalescable, also check if the first page is
a HighMem page or not. If it is, fall through to the usual vmap()
mapping rather than attempt to get the unmapped page address.

Cc: stable@vger.kernel.org
Fixes: c4d0ac1c1567 ("io_uring/memmap: optimise single folio regions")
Link: https://lore.kernel.org/all/681fe2fb.050a0220.f2294.001a.GAE@google.com/
Reported-by: syzbot+5b8c4abafcb1d791ccfc@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/681fed0a.050a0220.f2294.001c.GAE@google.com/
Reported-by: syzbot+6456a99dfdc2e78c4feb@syzkaller.appspotmail.com
Tested-by: syzbot+6456a99dfdc2e78c4feb@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/uring_cmd: fix hybrid polling initialization issue 2025-05-12T13:17:02+00:00 hexue xue01.he@samsung.com 2025-05-12T05:20:25+00:00 63166b815dc163b2e46426cecf707dc5923d6d13 Modify the check for whether the timer is initialized during IO transfer when passthrough is used with hybrid polling, to ensure that it's always setup correctly. Cc: stable@vger.kernel.org Fixes: 01ee194d1aba ("io_uring: add support for hybrid IOPOLL") Signed-off-by: hexue <xue01.he@samsung.com> Link: https://lore.kernel.org/r/20250512052025.293031-1-xue01.he@samsung.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
Modify the check for whether the timer is initialized during IO transfer
when passthrough is used with hybrid polling, to ensure that it's always
setup correctly.

Cc: stable@vger.kernel.org
Fixes: 01ee194d1aba ("io_uring: add support for hybrid IOPOLL")
Signed-off-by: hexue <xue01.he@samsung.com>
Link: https://lore.kernel.org/r/20250512052025.293031-1-xue01.he@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/sqpoll: Increase task_work submission batch size 2025-05-09T13:56:53+00:00 Gabriel Krisman Bertazi krisman@suse.de 2025-05-08T18:12:03+00:00 92835cebab120f8a5f023a26a792a2ac3f816c4f Our QA team reported a 10%-23%, throughput reduction on an io_uring sqpoll testcase doing IO to a null_blk, that I traced back to a reduction of the device submission queue depth utilization. It turns out that, after commit af5d68f8892f ("io_uring/sqpoll: manage task_work privately"), we capped the number of task_work entries that can be completed from a single spin of sqpoll to only 8 entries, before the sqpoll goes around to (potentially) sleep. While this cap doesn't drive the submission side directly, it impacts the completion behavior, which affects the number of IO queued by fio per sqpoll cycle on the submission side, and io_uring ends up seeing less ios per sqpoll cycle. As a result, block layer plugging is less effective, and we see more time spent inside the block layer in profilings charts, and increased submission latency measured by fio. There are other places that have increased overhead once sqpoll sleeps more often, such as the sqpoll utilization calculation. But, in this microbenchmark, those were not representative enough in perf charts, and their removal didn't yield measurable changes in throughput. The major overhead comes from the fact we plug less, and less often, when submitting to the block layer. My benchmark is: fio --ioengine=io_uring --direct=1 --iodepth=128 --runtime=300 --bs=4k \ --invalidate=1 --time_based --ramp_time=10 --group_reporting=1 \ --filename=/dev/nullb0 --name=RandomReads-direct-nullb-sqpoll-4k-1 \ --rw=randread --numjobs=1 --sqthread_poll In one machine, tested on top of Linux 6.15-rc1, we have the following baseline: READ: bw=4994MiB/s (5236MB/s), 4994MiB/s-4994MiB/s (5236MB/s-5236MB/s), io=439GiB (471GB), run=90001-90001msec With this patch: READ: bw=5762MiB/s (6042MB/s), 5762MiB/s-5762MiB/s (6042MB/s-6042MB/s), io=506GiB (544GB), run=90001-90001msec which is a 15% improvement in measured bandwidth. The average submission latency is noticeably lowered too. As measured by fio: Baseline: lat (usec): min=20, max=241, avg=99.81, stdev=3.38 Patched: lat (usec): min=26, max=226, avg=86.48, stdev=4.82 If we look at blktrace, we can also see the plugging behavior is improved. In the baseline, we end up limited to plugging 8 requests in the block layer regardless of the device queue depth size, while after patching we can drive more io, and we manage to utilize the full device queue. In the baseline, after a stabilization phase, an ordinary submission looks like: 254,0 1 49942 0.016028795 5977 U N [iou-sqp-5976] 7 After patching, I see consistently more requests per unplug. 254,0 1 4996 0.001432872 3145 U N [iou-sqp-3144] 32 Ideally, the cap size would at least be the deep enough to fill the device queue, but we can't predict that behavior, or assume all IO goes to a single device, and thus can't guess the ideal batch size. We also don't want to let the tw run unbounded, though I'm not sure it would really be a problem. Instead, let's just give it a more sensible value that will allow for more efficient batching. I've tested with different cap values, and initially proposed to increase the cap to 1024. Jens argued it is too big of a bump and I observed that, with 32, I'm no longer able to observe this bottleneck in any of my machines. Fixes: af5d68f8892f ("io_uring/sqpoll: manage task_work privately") Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de> Link: https://lore.kernel.org/r/20250508181203.3785544-1-krisman@suse.de Signed-off-by: Jens Axboe <axboe@kernel.dk> 
Our QA team reported a 10%-23%, throughput reduction on an io_uring
sqpoll testcase doing IO to a null_blk, that I traced back to a
reduction of the device submission queue depth utilization. It turns out
that, after commit af5d68f8892f ("io_uring/sqpoll: manage task_work
privately"), we capped the number of task_work entries that can be
completed from a single spin of sqpoll to only 8 entries, before the
sqpoll goes around to (potentially) sleep.  While this cap doesn't drive
the submission side directly, it impacts the completion behavior, which
affects the number of IO queued by fio per sqpoll cycle on the
submission side, and io_uring ends up seeing less ios per sqpoll cycle.
As a result, block layer plugging is less effective, and we see more
time spent inside the block layer in profilings charts, and increased
submission latency measured by fio.

There are other places that have increased overhead once sqpoll sleeps
more often, such as the sqpoll utilization calculation.  But, in this
microbenchmark, those were not representative enough in perf charts, and
their removal didn't yield measurable changes in throughput.  The major
overhead comes from the fact we plug less, and less often, when submitting
to the block layer.

My benchmark is:

fio --ioengine=io_uring --direct=1 --iodepth=128 --runtime=300 --bs=4k \
    --invalidate=1 --time_based  --ramp_time=10 --group_reporting=1 \
    --filename=/dev/nullb0 --name=RandomReads-direct-nullb-sqpoll-4k-1 \
    --rw=randread --numjobs=1 --sqthread_poll

In one machine, tested on top of Linux 6.15-rc1, we have the following
baseline:
  READ: bw=4994MiB/s (5236MB/s), 4994MiB/s-4994MiB/s (5236MB/s-5236MB/s), io=439GiB (471GB), run=90001-90001msec

With this patch:
  READ: bw=5762MiB/s (6042MB/s), 5762MiB/s-5762MiB/s (6042MB/s-6042MB/s), io=506GiB (544GB), run=90001-90001msec

which is a 15% improvement in measured bandwidth.  The average
submission latency is noticeably lowered too.  As measured by
fio:

Baseline:
   lat (usec): min=20, max=241, avg=99.81, stdev=3.38
Patched:
   lat (usec): min=26, max=226, avg=86.48, stdev=4.82

If we look at blktrace, we can also see the plugging behavior is
improved. In the baseline, we end up limited to plugging 8 requests in
the block layer regardless of the device queue depth size, while after
patching we can drive more io, and we manage to utilize the full device
queue.

In the baseline, after a stabilization phase, an ordinary submission
looks like:
  254,0    1    49942     0.016028795  5977  U   N [iou-sqp-5976] 7

After patching, I see consistently more requests per unplug.
  254,0    1     4996     0.001432872  3145  U   N [iou-sqp-3144] 32

Ideally, the cap size would at least be the deep enough to fill the
device queue, but we can't predict that behavior, or assume all IO goes
to a single device, and thus can't guess the ideal batch size.  We also
don't want to let the tw run unbounded, though I'm not sure it would
really be a problem.  Instead, let's just give it a more sensible value
that will allow for more efficient batching.  I've tested with different
cap values, and initially proposed to increase the cap to 1024.  Jens
argued it is too big of a bump and I observed that, with 32, I'm no
longer able to observe this bottleneck in any of my machines.

Fixes: af5d68f8892f ("io_uring/sqpoll: manage task_work privately")
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/20250508181203.3785544-1-krisman@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: ensure deferred completions are flushed for multishot 2025-05-07T13:55:15+00:00 Jens Axboe axboe@kernel.dk 2025-05-07T13:34:24+00:00 687b2bae0efff9b25e071737d6af5004e6e35af5 Multishot normally uses io_req_post_cqe() to post completions, but when stopping it, it may finish up with a deferred completion. This is fine, except if another multishot event triggers before the deferred completions get flushed. If this occurs, then CQEs may get reordered in the CQ ring, as new multishot completions get posted before the deferred ones are flushed. This can cause confusion on the application side, if strict ordering is required for the use case. When multishot posting via io_req_post_cqe(), flush any pending deferred completions first, if any. Cc: stable@vger.kernel.org # 6.1+ Reported-by: Norman Maurer <norman_maurer@apple.com> Reported-by: Christian Mazakas <christian.mazakas@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> 
Multishot normally uses io_req_post_cqe() to post completions, but when
stopping it, it may finish up with a deferred completion. This is fine,
except if another multishot event triggers before the deferred completions
get flushed. If this occurs, then CQEs may get reordered in the CQ ring,
as new multishot completions get posted before the deferred ones are
flushed. This can cause confusion on the application side, if strict
ordering is required for the use case.

When multishot posting via io_req_post_cqe(), flush any pending deferred
completions first, if any.

Cc: stable@vger.kernel.org # 6.1+
Reported-by: Norman Maurer <norman_maurer@apple.com>
Reported-by: Christian Mazakas <christian.mazakas@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: always arm linked timeouts prior to issue 2025-05-04T15:15:58+00:00 Jens Axboe axboe@kernel.dk 2025-05-04T14:06:28+00:00 b53e523261bf058ea4a518b482222e7a277b186b There are a few spots where linked timeouts are armed, and not all of them adhere to the pre-arm, attempt issue, post-arm pattern. This can be problematic if the linked request returns that it will trigger a callback later, and does so before the linked timeout is fully armed. Consolidate all the linked timeout handling into __io_issue_sqe(), rather than have it spread throughout the various issue entry points. Cc: stable@vger.kernel.org Link: https://github.com/axboe/liburing/issues/1390 Reported-by: Chase Hiltz <chase@path.net> Signed-off-by: Jens Axboe <axboe@kernel.dk> 
There are a few spots where linked timeouts are armed, and not all of
them adhere to the pre-arm, attempt issue, post-arm pattern. This can
be problematic if the linked request returns that it will trigger a
callback later, and does so before the linked timeout is fully armed.

Consolidate all the linked timeout handling into __io_issue_sqe(),
rather than have it spread throughout the various issue entry points.

Cc: stable@vger.kernel.org
Link: https://github.com/axboe/liburing/issues/1390
Reported-by: Chase Hiltz <chase@path.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/fdinfo: annotate racy sq/cq head/tail reads 2025-04-30T13:17:17+00:00 Jens Axboe axboe@kernel.dk 2025-04-30T13:17:17+00:00 f024d3a8ded0d8d2129ae123d7a5305c29ca44ce syzbot complains about the cached sq head read, and it's totally right. But we don't need to care, it's just reading fdinfo, and reading the CQ or SQ tail/head entries are known racy in that they are just a view into that very instant and may of course be outdated by the time they are reported. Annotate both the SQ head and CQ tail read with data_race() to avoid this syzbot complaint. Link: https://lore.kernel.org/io-uring/6811f6dc.050a0220.39e3a1.0d0e.GAE@google.com/ Reported-by: syzbot+3e77fd302e99f5af9394@syzkaller.appspotmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
syzbot complains about the cached sq head read, and it's totally right.
But we don't need to care, it's just reading fdinfo, and reading the
CQ or SQ tail/head entries are known racy in that they are just a view
into that very instant and may of course be outdated by the time they
are reported.

Annotate both the SQ head and CQ tail read with data_race() to avoid
this syzbot complaint.

Link: https://lore.kernel.org/io-uring/6811f6dc.050a0220.39e3a1.0d0e.GAE@google.com/
Reported-by: syzbot+3e77fd302e99f5af9394@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: fix 'sync' handling of io_fallback_tw() 2025-04-24T16:32:43+00:00 Jens Axboe axboe@kernel.dk 2025-04-24T16:28:14+00:00 edd43f4d6f50ec3de55a0c9e9df6348d1da51965 A previous commit added a 'sync' parameter to io_fallback_tw(), which if true, means the caller wants to wait on the fallback thread handling it. But the logic is somewhat messed up, ensure that ctxs are swapped and flushed appropriately. Cc: stable@vger.kernel.org Fixes: dfbe5561ae93 ("io_uring: flush offloaded and delayed task_work on exit") Signed-off-by: Jens Axboe <axboe@kernel.dk> 
A previous commit added a 'sync' parameter to io_fallback_tw(), which if
true, means the caller wants to wait on the fallback thread handling it.
But the logic is somewhat messed up, ensure that ctxs are swapped and
flushed appropriately.

Cc: stable@vger.kernel.org
Fixes: dfbe5561ae93 ("io_uring: flush offloaded and delayed task_work on exit")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring: don't duplicate flushing in io_req_post_cqe 2025-04-24T12:28:43+00:00 Pavel Begunkov asml.silence@gmail.com 2025-04-24T11:28:39+00:00 5e16f1a68d28965c12b6fa227a306fef8a680f84 io_req_post_cqe() sets submit_state.cq_flush so that *flush_completions() can take care of batch commiting CQEs. Don't commit it twice by using __io_cq_unlock_post(). Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/41c416660c509cee676b6cad96081274bcb459f3.1745493861.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
io_req_post_cqe() sets submit_state.cq_flush so that
*flush_completions() can take care of batch commiting CQEs. Don't commit
it twice by using __io_cq_unlock_post().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/41c416660c509cee676b6cad96081274bcb459f3.1745493861.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_uring/zcrx: fix late dma unmap for a dead dev 2025-04-18T12:12:10+00:00 Pavel Begunkov asml.silence@gmail.com 2025-04-18T12:02:27+00:00 f12ecf5e1c5eca48b8652e893afcdb730384a6aa There is a problem with page pools not dma-unmapping immediately when the device is going down, and delaying it until the page pool is destroyed, which is not allowed (see links). That just got fixed for normal page pools, and we need to address memory providers as well. Unmap pages in the memory provider uninstall callback, and protect it with a new lock. There is also a gap between when a dma mapping is created and the mp is installed, so if the device is killed in between, io_uring would be holding on to dma mappings to a dead device with no one to call ->uninstall. Move it to page pool init and rely on ->is_mapped to make sure it's only done once. Link: https://lore.kernel.org/lkml/8067f204-1380-4d37-8ffd-007fc6f26738@kernel.org/T/ Link: https://lore.kernel.org/all/20250409-page-pool-track-dma-v9-0-6a9ef2e0cba8@redhat.com/ Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider") Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Link: https://lore.kernel.org/r/ef9b7db249b14f6e0b570a1bb77ff177389f881c.1744965853.git.asml.silence@gmail.com Signed-off-by: Jens Axboe <axboe@kernel.dk> 
There is a problem with page pools not dma-unmapping immediately when
the device is going down, and delaying it until the page pool is
destroyed, which is not allowed (see links). That just got fixed for
normal page pools, and we need to address memory providers as well.

Unmap pages in the memory provider uninstall callback, and protect it
with a new lock. There is also a gap between when a dma mapping is
created and the mp is installed, so if the device is killed in between,
io_uring would be holding on to dma mappings to a dead device with no
one to call ->uninstall. Move it to page pool init and rely on
->is_mapped to make sure it's only done once.

Link: https://lore.kernel.org/lkml/8067f204-1380-4d37-8ffd-007fc6f26738@kernel.org/T/
Link: https://lore.kernel.org/all/20250409-page-pool-track-dma-v9-0-6a9ef2e0cba8@redhat.com/
Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/ef9b7db249b14f6e0b570a1bb77ff177389f881c.1744965853.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>