kernel/linux.git/io_uring/rsrc.c, branch v6.2-rc2

io_uring: use tw for putting rsrc

2022-12-07T13:47:13+00:00

Use task_work for completing rsrc removals, it'll be needed later for spinlock optimisations. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/cbba5d53a11ee6fc2194dacea262c1d733c8b529.1670384893.git.asml.silence@gmail.com Signed-off-by: Jens Axboe

io_uring: don't reinstall quiesce node for each tw

2022-11-30T17:29:07+00:00

There is no need to reinit data and install a new rsrc node every time we get a task_work, it's detrimental, just execute it and conitnue waiting. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3895d3344164cd9b3a0bbb24a6e357e20a13434b.1669821213.git.asml.silence@gmail.com Signed-off-by: Jens Axboe

io_uring: improve rsrc quiesce refs checks

2022-11-30T17:29:07+00:00

Do a little bit of refactoring of io_rsrc_ref_quiesce(), flatten the data refs checks and so get rid of a conditional weird unlock-else-break construct. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/d21283e9f88a77612c746ed526d86fe3bfb58a70.1669821213.git.asml.silence@gmail.com Signed-off-by: Jens Axboe

io_uring: remove overflow param from io_post_aux_cqe

2022-11-25T13:10:04+00:00

The only call sites which would not allow overflow are also call sites which would use the io_aux_cqe as they care about ordering. So remove this parameter from io_post_aux_cqe. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20221124093559.3780686-9-dylany@meta.com Signed-off-by: Jens Axboe

io_uring: do not always force run task_work in io_uring_register

2022-11-21T14:38:54+00:00

Running task work when not needed can unnecessarily delay operations. Specifically IORING_SETUP_DEFER_TASKRUN tries to avoid running task work until the user requests it. Therefore do not run it in io_uring_register any more. The one catch is that io_rsrc_ref_quiesce expects it to have run in order to process all outstanding references, and so reorder it's loop to do this. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20221107123349.4106213-1-dylany@meta.com Signed-off-by: Jens Axboe

io_uring: remove FFS_SCM

2022-10-16T23:07:12+00:00

THe lifetime of SCM'ed files is bound to ring_sock, which is destroyed strictly after we're done with registered file tables. This means there is no need for the FFS_SCM hack, which was not available on 32-bit builds anyway. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/984226a1045adf42dc35d8bd7fb5a8bbfa472ce1.1665891182.git.asml.silence@gmail.com Signed-off-by: Jens Axboe

io_uring/af_unix: defer registered files gc to io_uring release

2022-10-12T22:30:34+00:00

Instead of putting io_uring's registered files in unix_gc() we want it to be done by io_uring itself. The trick here is to consider io_uring registered files for cycle detection but not actually putting them down. Because io_uring can't register other ring instances, this will remove all refs to the ring file triggering the ->release path and clean up with io_ring_ctx_free(). Cc: stable@vger.kernel.org Fixes: 6b06314c47e1 ("io_uring: add file set registration") Reported-and-tested-by: David Bouman Signed-off-by: Pavel Begunkov Signed-off-by: Thadeu Lima de Souza Cascardo [axboe: add kerneldoc comment to skb, fold in skb leak fix] Signed-off-by: Jens Axboe

io_uring: add IORING_SETUP_DEFER_TASKRUN

2022-09-21T16:30:42+00:00

Allow deferring async tasks until the user calls io_uring_enter(2) with the IORING_ENTER_GETEVENTS flag. Enable this mode with a flag at io_uring_setup time. This functionality requires that the later io_uring_enter will be called from the same submission task, and therefore restrict this flag to work only when IORING_SETUP_SINGLE_ISSUER is also set. Being able to hand pick when tasks are run prevents the problem where there is current work to be done, however task work runs anyway. For example, a common workload would obtain a batch of CQEs, and process each one. Interrupting this to additional taskwork would add latency but not gain anything. If instead task work is deferred to just before more CQEs are obtained then no additional latency is added. The way this is implemented is by trying to keep task work local to a io_ring_ctx, rather than to the submission task. This is required, as the application will want to wake up only a single io_ring_ctx at a time to process work, and so the lists of work have to be kept separate. This has some other benefits like not having to check the task continually in handle_tw_list (and potentially unlocking/locking those), and reducing locks in the submit & process completions path. There are networking cases where using this option can reduce request latency by 50%. For example a contrived example using [1] where the client sends 2k data and receives the same data back while doing some system calls (to trigger task work) shows this reduction. The reason ends up being that if sending responses is delayed by processing task work, then the client side sits idle. Whereas reordering the sends first means that the client runs it's workload in parallel with the local task work. [1]: Using https://github.com/DylanZA/netbench/tree/defer_run Client: ./netbench --client_only 1 --control_port 10000 --host --tx "epoll --threads 16 --per_thread 1 --size 2048 --resp 2048 --workload 1000" Server: ./netbench --server_only 1 --control_port 10000 --rx "io_uring --defer_taskrun 0 --workload 100" --rx "io_uring --defer_taskrun 1 --workload 100" Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220830125013.570060-5-dylany@fb.com Signed-off-by: Jens Axboe

Revert "io_uring: rename IORING_OP_FILES_UPDATE"

2022-09-01T15:13:33+00:00

This reverts commit 4379d5f15b3fd4224c37841029178aa8082a242e. We removed notification flushing, also cleanup uapi preparation changes to not pollute it. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/89edc3905350f91e1b6e26d9dbf42ee44fd451a2.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe

Revert "io_uring: add zc notification flush requests"

2022-09-01T15:13:33+00:00

This reverts commit 492dddb4f6e3a5839c27d41ff1fecdbe6c3ab851. Soon we won't have the very notion of notification flushing, so remove notification flushing requests. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8850334ca56e65b413cb34fd158db81d7b2865a3.1662027856.git.asml.silence@gmail.com Signed-off-by: Jens Axboe