From da12d9ab5889b87429d9375748dcd1485b6241f3 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 18 Mar 2024 22:00:23 +0000 Subject: io_uring/cmd: move io_uring_try_cancel_uring_cmd() io_uring_try_cancel_uring_cmd() is a part of the cmd handling so let's move it closer to all cmd bits into uring_cmd.c Signed-off-by: Pavel Begunkov Reviewed-by: Ming Lei Tested-by: Ming Lei Link: https://lore.kernel.org/r/43a3937af4933655f0fd9362c381802f804f43de.1710799188.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/uring_cmd.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'io_uring/uring_cmd.c') diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 42f63adfa54a..1551848a9394 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -14,6 +14,36 @@ #include "rsrc.h" #include "uring_cmd.h" +bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, + struct task_struct *task, bool cancel_all) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + bool ret = false; + + lockdep_assert_held(&ctx->uring_lock); + + hlist_for_each_entry_safe(req, tmp, &ctx->cancelable_uring_cmd, + hash_node) { + struct io_uring_cmd *cmd = io_kiocb_to_cmd(req, + struct io_uring_cmd); + struct file *file = req->file; + + if (!cancel_all && req->task != task) + continue; + + if (cmd->flags & IORING_URING_CMD_CANCELABLE) { + /* ->sqe isn't available if no async data */ + if (!req_has_async_data(req)) + cmd->sqe = NULL; + file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL); + ret = true; + } + } + io_submit_flush_completions(ctx); + return ret; +} + static void io_uring_cmd_del_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags) { -- cgit v1.2.3-59-g8ed1b From 6edd953b6ec758c98e9dba7234634831f1f6510d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 18 Mar 2024 22:00:24 +0000 Subject: io_uring/cmd: kill one issue_flags to tw conversion io_uring cmd converts struct io_tw_state to issue_flags and later back to io_tw_state, it's awfully ill-fated, not to mention that intermediate issue_flags state is not correct. Get rid of the last conversion, drag through tw everything that came with IO_URING_F_UNLOCKED, and replace io_req_complete_defer() with a direct call to io_req_complete_defer(), at least for the time being. Signed-off-by: Pavel Begunkov Reviewed-by: Ming Lei Tested-by: Ming Lei Link: https://lore.kernel.org/r/c53fa3df749752bd058cf6f824a90704822d6bcc.1710799188.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/uring_cmd.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 1551848a9394..7c1c58c5837e 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -130,11 +130,11 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, if (req->ctx->flags & IORING_SETUP_IOPOLL) { /* order with io_iopoll_req_issued() checking ->iopoll_complete */ smp_store_release(&req->iopoll_completed, 1); + } else if (!(issue_flags & IO_URING_F_UNLOCKED)) { + io_req_complete_defer(req); } else { - struct io_tw_state ts = { - .locked = !(issue_flags & IO_URING_F_UNLOCKED), - }; - io_req_task_complete(req, &ts); + req->io_task_work.func = io_req_task_complete; + io_req_task_work_add(req); } } EXPORT_SYMBOL_GPL(io_uring_cmd_done); -- cgit v1.2.3-59-g8ed1b From e1eef2e56cb0db143c731b1cdc220980256d2d99 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 18 Mar 2024 22:00:25 +0000 Subject: io_uring/cmd: fix tw <-> issue_flags conversion !IO_URING_F_UNLOCKED does not translate to availability of the deferred completion infra, IO_URING_F_COMPLETE_DEFER does, that what we should pass and look for to use io_req_complete_defer() and other variants. Luckily, it's not a real problem as two wrongs actually made it right, at least as far as io_uring_cmd_work() goes. Signed-off-by: Pavel Begunkov Reviewed-by: Ming Lei Tested-by: Ming Lei Link: https://lore.kernel.org/r/aef76d34fe9410df8ecc42a14544fd76cd9d8b9e.1710799188.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/uring_cmd.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 7c1c58c5837e..759f919b14a9 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -36,7 +36,8 @@ bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, /* ->sqe isn't available if no async data */ if (!req_has_async_data(req)) cmd->sqe = NULL; - file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL); + file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL | + IO_URING_F_COMPLETE_DEFER); ret = true; } } @@ -86,7 +87,11 @@ EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable); static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED; + unsigned issue_flags = IO_URING_F_UNLOCKED; + + /* locked task_work executor checks the deffered list completion */ + if (ts->locked) + issue_flags = IO_URING_F_COMPLETE_DEFER; ioucmd->task_work_cb(ioucmd, issue_flags); } @@ -130,7 +135,9 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, if (req->ctx->flags & IORING_SETUP_IOPOLL) { /* order with io_iopoll_req_issued() checking ->iopoll_complete */ smp_store_release(&req->iopoll_completed, 1); - } else if (!(issue_flags & IO_URING_F_UNLOCKED)) { + } else if (issue_flags & IO_URING_F_COMPLETE_DEFER) { + if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED)) + return; io_req_complete_defer(req); } else { req->io_task_work.func = io_req_task_complete; -- cgit v1.2.3-59-g8ed1b From 8e5b3b89ecaf6d9295e561c225b35c574a5e0fe7 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 18 Mar 2024 22:00:30 +0000 Subject: io_uring: remove struct io_tw_state::locked ctx is always locked for task_work now, so get rid of struct io_tw_state::locked. Note I'm stopping one step before removing io_tw_state altogether, which is not empty, because it still serves the purpose of indicating which function is a tw callback and forcing users not to invoke them carelessly out of a wrong context. The removal can always be done later. Signed-off-by: Pavel Begunkov Tested-by: Ming Lei Link: https://lore.kernel.org/r/e95e1ea116d0bfa54b656076e6a977bc221392a4.1710799188.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 -- io_uring/io_uring.c | 31 ++++++++----------------------- io_uring/io_uring.h | 5 +---- io_uring/poll.c | 2 +- io_uring/rw.c | 6 ++---- io_uring/timeout.c | 8 ++------ io_uring/uring_cmd.c | 8 ++------ io_uring/waitid.c | 2 +- 8 files changed, 17 insertions(+), 47 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index ac333ea81d31..90e5af401800 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -438,8 +438,6 @@ struct io_ring_ctx { }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 13fb5958454f..ecb59bb2418b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -247,14 +247,12 @@ static __cold void io_fallback_req_func(struct work_struct *work) fallback_work.work); struct llist_node *node = llist_del_all(&ctx->fallback_llist); struct io_kiocb *req, *tmp; - struct io_tw_state ts = { .locked = true, }; + struct io_tw_state ts = {}; percpu_ref_get(&ctx->refs); mutex_lock(&ctx->uring_lock); llist_for_each_entry_safe(req, tmp, node, io_task_work.node) req->io_task_work.func(req, &ts); - if (WARN_ON_ONCE(!ts.locked)) - return; io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); percpu_ref_put(&ctx->refs); @@ -1157,11 +1155,9 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts) return; if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); - if (ts->locked) { - io_submit_flush_completions(ctx); - mutex_unlock(&ctx->uring_lock); - ts->locked = false; - } + + io_submit_flush_completions(ctx); + mutex_unlock(&ctx->uring_lock); percpu_ref_put(&ctx->refs); } @@ -1185,8 +1181,6 @@ struct llist_node *io_handle_tw_list(struct llist_node *node, if (req->ctx != ctx) { ctx_flush_and_put(ctx, &ts); ctx = req->ctx; - - ts.locked = true; mutex_lock(&ctx->uring_lock); percpu_ref_get(&ctx->refs); } @@ -1459,22 +1453,16 @@ again: static inline int io_run_local_work_locked(struct io_ring_ctx *ctx, int min_events) { - struct io_tw_state ts = { .locked = true, }; - int ret; + struct io_tw_state ts = {}; if (llist_empty(&ctx->work_llist)) return 0; - - ret = __io_run_local_work(ctx, &ts, min_events); - /* shouldn't happen! */ - if (WARN_ON_ONCE(!ts.locked)) - mutex_lock(&ctx->uring_lock); - return ret; + return __io_run_local_work(ctx, &ts, min_events); } static int io_run_local_work(struct io_ring_ctx *ctx, int min_events) { - struct io_tw_state ts = { .locked = true }; + struct io_tw_state ts = {}; int ret; mutex_lock(&ctx->uring_lock); @@ -1702,10 +1690,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts) { - if (ts->locked) - io_req_complete_defer(req); - else - io_req_complete_post(req, IO_URING_F_UNLOCKED); + io_req_complete_defer(req); } /* diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 0861d49e83de..7f921daae9c3 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -351,10 +351,7 @@ static inline bool io_task_work_pending(struct io_ring_ctx *ctx) static inline void io_tw_lock(struct io_ring_ctx *ctx, struct io_tw_state *ts) { - if (!ts->locked) { - mutex_lock(&ctx->uring_lock); - ts->locked = true; - } + lockdep_assert_held(&ctx->uring_lock); } /* diff --git a/io_uring/poll.c b/io_uring/poll.c index 6db1dcb2c797..8901dd118e50 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -322,7 +322,7 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) __poll_t mask = mangle_poll(req->cqe.res & req->apoll_events); - if (!io_fill_cqe_req_aux(req, ts->locked, mask, + if (!io_fill_cqe_req_aux(req, true, mask, IORING_CQE_F_MORE)) { io_req_set_res(req, mask, 0); return IOU_POLL_REMOVE_POLL_USE_RES; diff --git a/io_uring/rw.c b/io_uring/rw.c index 0afe4f9e0e3f..674581bda8d7 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -305,11 +305,9 @@ void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts) io_req_io_end(req); - if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) { - unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED; + if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) + req->cqe.flags |= io_put_kbuf(req, 0); - req->cqe.flags |= io_put_kbuf(req, issue_flags); - } io_req_task_complete(req, ts); } diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 7fd7dbb211d6..0a48e6acd0b2 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -72,10 +72,7 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) struct io_ring_ctx *ctx = req->ctx; if (!io_timeout_finish(timeout, data)) { - bool filled; - filled = io_fill_cqe_req_aux(req, ts->locked, -ETIME, - IORING_CQE_F_MORE); - if (filled) { + if (io_fill_cqe_req_aux(req, true, -ETIME, IORING_CQE_F_MORE)) { /* re-arm timer */ spin_lock_irq(&ctx->timeout_lock); list_add(&timeout->list, ctx->timeout_list.prev); @@ -301,7 +298,6 @@ int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) static void io_req_task_link_timeout(struct io_kiocb *req, struct io_tw_state *ts) { - unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED; struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); struct io_kiocb *prev = timeout->prev; int ret = -ENOENT; @@ -313,7 +309,7 @@ static void io_req_task_link_timeout(struct io_kiocb *req, struct io_tw_state *t .data = prev->cqe.user_data, }; - ret = io_try_cancel(req->task->io_uring, &cd, issue_flags); + ret = io_try_cancel(req->task->io_uring, &cd, 0); } io_req_set_res(req, ret ?: -ETIME, 0); io_req_task_complete(req, ts); diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 759f919b14a9..4614ce734fee 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -87,13 +87,9 @@ EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable); static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - unsigned issue_flags = IO_URING_F_UNLOCKED; - /* locked task_work executor checks the deffered list completion */ - if (ts->locked) - issue_flags = IO_URING_F_COMPLETE_DEFER; - - ioucmd->task_work_cb(ioucmd, issue_flags); + /* task_work executor checks the deffered list completion */ + ioucmd->task_work_cb(ioucmd, IO_URING_F_COMPLETE_DEFER); } void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 77d340666cb9..6362ec20abc0 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -118,7 +118,7 @@ static int io_waitid_finish(struct io_kiocb *req, int ret) static void io_waitid_complete(struct io_kiocb *req, int ret) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); - struct io_tw_state ts = { .locked = true }; + struct io_tw_state ts = {}; /* anyone completing better be holding a reference */ WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); -- cgit v1.2.3-59-g8ed1b From d10f19dff56eac5ae44dc270336b18071a8bd51c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Mar 2024 20:41:58 -0600 Subject: io_uring/uring_cmd: switch to always allocating async data Basic conversion ensuring async_data is allocated off the prep path. Adds a basic alloc cache as well, as passthrough IO can be quite high in rate. Tested-by: Anuj Gupta Reviewed-by: Anuj Gupta Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + io_uring/io_uring.c | 3 ++ io_uring/opdef.c | 1 - io_uring/uring_cmd.c | 77 ++++++++++++++++++++++++++++++------------ io_uring/uring_cmd.h | 10 +++++- 5 files changed, 69 insertions(+), 23 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 60d7e35fc303..0f24fdad19c2 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -301,6 +301,7 @@ struct io_ring_ctx { struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; struct io_alloc_cache rw_cache; + struct io_alloc_cache uring_cache; /* * Any cancelable uring_cmd is added to this list in diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b0554d122931..a868c0a253a6 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -313,6 +313,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) sizeof(struct io_async_msghdr)); io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_rw)); + io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, + sizeof(struct uring_cache)); io_futex_cache_init(ctx); init_completion(&ctx->ref_comp); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); @@ -2826,6 +2828,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); + io_alloc_cache_free(&ctx->uring_cache, io_uring_cache_free); io_futex_cache_free(ctx); io_destroy_buffers(ctx); mutex_unlock(&ctx->uring_lock); diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 1951107210d4..745246086c23 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -677,7 +677,6 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_URING_CMD] = { .name = "URING_CMD", .async_size = 2 * sizeof(struct io_uring_sqe), - .prep_async = io_uring_cmd_prep_async, }, [IORING_OP_SEND_ZC] = { .name = "SEND_ZC", diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 4614ce734fee..9bd0ba87553f 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -14,6 +14,38 @@ #include "rsrc.h" #include "uring_cmd.h" +static struct uring_cache *io_uring_async_get(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_cache_entry *entry; + struct uring_cache *cache; + + entry = io_alloc_cache_get(&ctx->uring_cache); + if (entry) { + cache = container_of(entry, struct uring_cache, cache); + req->flags |= REQ_F_ASYNC_DATA; + req->async_data = cache; + return cache; + } + if (!io_alloc_async_data(req)) + return req->async_data; + return NULL; +} + +static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); + struct uring_cache *cache = req->async_data; + + if (issue_flags & IO_URING_F_UNLOCKED) + return; + if (io_alloc_cache_put(&req->ctx->uring_cache, &cache->cache)) { + ioucmd->sqe = NULL; + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; + } +} + bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all) { @@ -128,6 +160,7 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, io_req_set_res(req, ret, 0); if (req->ctx->flags & IORING_SETUP_CQE32) io_req_set_cqe32_extra(req, res2, 0); + io_req_uring_cleanup(req, issue_flags); if (req->ctx->flags & IORING_SETUP_IOPOLL) { /* order with io_iopoll_req_issued() checking ->iopoll_complete */ smp_store_release(&req->iopoll_completed, 1); @@ -142,13 +175,19 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, } EXPORT_SYMBOL_GPL(io_uring_cmd_done); -int io_uring_cmd_prep_async(struct io_kiocb *req) +static int io_uring_cmd_prep_setup(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); + struct uring_cache *cache; - memcpy(req->async_data, ioucmd->sqe, uring_sqe_size(req->ctx)); - ioucmd->sqe = req->async_data; - return 0; + cache = io_uring_async_get(req); + if (cache) { + memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx)); + ioucmd->sqe = req->async_data; + return 0; + } + return -ENOMEM; } int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -173,9 +212,9 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = ctx->user_bufs[index]; io_req_set_rsrc_node(req, ctx, 0); } - ioucmd->sqe = sqe; ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); - return 0; + + return io_uring_cmd_prep_setup(req, sqe); } int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) @@ -206,23 +245,14 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) } ret = file->f_op->uring_cmd(ioucmd, issue_flags); - if (ret == -EAGAIN) { - if (!req_has_async_data(req)) { - if (io_alloc_async_data(req)) - return -ENOMEM; - io_uring_cmd_prep_async(req); - } - return -EAGAIN; - } - - if (ret != -EIOCBQUEUED) { - if (ret < 0) - req_set_fail(req); - io_req_set_res(req, ret, 0); + if (ret == -EAGAIN || ret == -EIOCBQUEUED) return ret; - } - return IOU_ISSUE_SKIP_COMPLETE; + if (ret < 0) + req_set_fail(req); + io_req_uring_cleanup(req, issue_flags); + io_req_set_res(req, ret, 0); + return ret; } int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, @@ -311,3 +341,8 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) } EXPORT_SYMBOL_GPL(io_uring_cmd_sock); #endif + +void io_uring_cache_free(struct io_cache_entry *entry) +{ + kfree(container_of(entry, struct uring_cache, cache)); +} diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 7356bf9aa655..b0ccff7091ee 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -1,8 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 +struct uring_cache { + union { + struct io_cache_entry cache; + struct io_uring_sqe sqes[2]; + }; +}; + int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_uring_cmd_prep_async(struct io_kiocb *req); +void io_uring_cache_free(struct io_cache_entry *entry); bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, - struct task_struct *task, bool cancel_all); \ No newline at end of file + struct task_struct *task, bool cancel_all); -- cgit v1.2.3-59-g8ed1b From 5eff57fa9f3aae3acbcaf196af507eec58955f3b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 20 Mar 2024 15:23:47 -0600 Subject: io_uring/uring_cmd: defer SQE copying until it's needed The previous commit turned on async data for uring_cmd, and did the basic conversion of setting everything up on the prep side. However, for a lot of use cases, -EIOCBQUEUED will get returned on issue, as the operation got successfully queued. For that case, a persistent SQE isn't needed, as it's just used for issue. Unless execution goes async immediately, defer copying the double SQE until it's necessary. This greatly reduces the overhead of such commands, as evidenced by a perf diff from before and after this change: 10.60% -8.58% [kernel.vmlinux] [k] io_uring_cmd_prep where the prep side drops from 10.60% to ~2%, which is more expected. Performance also rises from ~113M IOPS to ~122M IOPS, bringing us back to where it was before the async command prep. Tested-by: Anuj Gupta Reviewed-by: Anuj Gupta Signed-off-by: Jens Axboe --- io_uring/uring_cmd.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 9bd0ba87553f..92346b5d9f5b 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -182,12 +182,18 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, struct uring_cache *cache; cache = io_uring_async_get(req); - if (cache) { - memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx)); - ioucmd->sqe = req->async_data; + if (unlikely(!cache)) + return -ENOMEM; + + if (!(req->flags & REQ_F_FORCE_ASYNC)) { + /* defer memcpy until we need it */ + ioucmd->sqe = sqe; return 0; } - return -ENOMEM; + + memcpy(req->async_data, sqe, uring_sqe_size(req->ctx)); + ioucmd->sqe = req->async_data; + return 0; } int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -245,8 +251,15 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) } ret = file->f_op->uring_cmd(ioucmd, issue_flags); - if (ret == -EAGAIN || ret == -EIOCBQUEUED) - return ret; + if (ret == -EAGAIN) { + struct uring_cache *cache = req->async_data; + + if (ioucmd->sqe != (void *) cache) + memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx)); + return -EAGAIN; + } else if (ret == -EIOCBQUEUED) { + return -EIOCBQUEUED; + } if (ret < 0) req_set_fail(req); -- cgit v1.2.3-59-g8ed1b From 414d0f45c316221acbf066658afdbae5b354a5cc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 20 Mar 2024 15:19:44 -0600 Subject: io_uring/alloc_cache: switch to array based caching Currently lists are being used to manage this, but best practice is usually to have these in an array instead as that it cheaper to manage. Outside of that detail, games are also played with KASAN as the list is inside the cached entry itself. Finally, all users of this need a struct io_cache_entry embedded in their struct, which is union'ized with something else in there that isn't used across the free -> realloc cycle. Get rid of all of that, and simply have it be an array. This will not change the memory used, as we're just trading an 8-byte member entry for the per-elem array size. This reduces the overhead of the recycled allocations, and it reduces the amount of code code needed to support recycling to about half of what it currently is. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 +- io_uring/alloc_cache.h | 57 +++++++++++++++++++----------------------- io_uring/futex.c | 30 +++++++++------------- io_uring/futex.h | 5 ++-- io_uring/io_uring.c | 34 ++++++++++++++----------- io_uring/net.c | 13 ++++------ io_uring/net.h | 18 ++++--------- io_uring/poll.c | 12 +++------ io_uring/poll.h | 9 +------ io_uring/rsrc.c | 10 +++----- io_uring/rsrc.h | 7 +----- io_uring/rw.c | 14 +++++------ io_uring/rw.h | 7 ++---- io_uring/uring_cmd.c | 14 +++-------- io_uring/uring_cmd.h | 6 +---- 15 files changed, 93 insertions(+), 145 deletions(-) (limited to 'io_uring/uring_cmd.c') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 0f24fdad19c2..ef45b8bd1b35 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -220,7 +220,7 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; size_t elem_size; diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h index 138ad14b0b12..b7a38a2069cf 100644 --- a/io_uring/alloc_cache.h +++ b/io_uring/alloc_cache.h @@ -6,61 +6,56 @@ */ #define IO_ALLOC_CACHE_MAX 128 -struct io_cache_entry { - struct io_wq_work_node node; -}; - static inline bool io_alloc_cache_put(struct io_alloc_cache *cache, - struct io_cache_entry *entry) + void *entry) { if (cache->nr_cached < cache->max_cached) { - cache->nr_cached++; - wq_stack_add_head(&entry->node, &cache->list); - kasan_mempool_poison_object(entry); + if (!kasan_mempool_poison_object(entry)) + return false; + cache->entries[cache->nr_cached++] = entry; return true; } return false; } -static inline bool io_alloc_cache_empty(struct io_alloc_cache *cache) -{ - return !cache->list.next; -} - -static inline struct io_cache_entry *io_alloc_cache_get(struct io_alloc_cache *cache) +static inline void *io_alloc_cache_get(struct io_alloc_cache *cache) { - if (cache->list.next) { - struct io_cache_entry *entry; + if (cache->nr_cached) { + void *entry = cache->entries[--cache->nr_cached]; - entry = container_of(cache->list.next, struct io_cache_entry, node); kasan_mempool_unpoison_object(entry, cache->elem_size); - cache->list.next = cache->list.next->next; - cache->nr_cached--; return entry; } return NULL; } -static inline void io_alloc_cache_init(struct io_alloc_cache *cache, +/* returns false if the cache was initialized properly */ +static inline bool io_alloc_cache_init(struct io_alloc_cache *cache, unsigned max_nr, size_t size) { - cache->list.next = NULL; - cache->nr_cached = 0; - cache->max_cached = max_nr; - cache->elem_size = size; + cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); + if (cache->entries) { + cache->nr_cached = 0; + cache->max_cached = max_nr; + cache->elem_size = size; + return false; + } + return true; } static inline void io_alloc_cache_free(struct io_alloc_cache *cache, - void (*free)(struct io_cache_entry *)) + void (*free)(const void *)) { - while (1) { - struct io_cache_entry *entry = io_alloc_cache_get(cache); + void *entry; + + if (!cache->entries) + return; - if (!entry) - break; + while ((entry = io_alloc_cache_get(cache)) != NULL) free(entry); - } - cache->nr_cached = 0; + + kvfree(cache->entries); + cache->entries = NULL; } #endif diff --git a/io_uring/futex.c b/io_uring/futex.c index 792a03df58de..914848f46beb 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -9,7 +9,7 @@ #include "../kernel/futex/futex.h" #include "io_uring.h" -#include "rsrc.h" +#include "alloc_cache.h" #include "futex.h" struct io_futex { @@ -27,27 +27,21 @@ struct io_futex { }; struct io_futex_data { - union { - struct futex_q q; - struct io_cache_entry cache; - }; + struct futex_q q; struct io_kiocb *req; }; -void io_futex_cache_init(struct io_ring_ctx *ctx) -{ - io_alloc_cache_init(&ctx->futex_cache, IO_NODE_ALLOC_CACHE_MAX, - sizeof(struct io_futex_data)); -} +#define IO_FUTEX_ALLOC_CACHE_MAX 32 -static void io_futex_cache_entry_free(struct io_cache_entry *entry) +bool io_futex_cache_init(struct io_ring_ctx *ctx) { - kfree(container_of(entry, struct io_futex_data, cache)); + return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX, + sizeof(struct io_futex_data)); } void io_futex_cache_free(struct io_ring_ctx *ctx) { - io_alloc_cache_free(&ctx->futex_cache, io_futex_cache_entry_free); + io_alloc_cache_free(&ctx->futex_cache, kfree); } static void __io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) @@ -63,7 +57,7 @@ static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) struct io_ring_ctx *ctx = req->ctx; io_tw_lock(ctx, ts); - if (!io_alloc_cache_put(&ctx->futex_cache, &ifd->cache)) + if (!io_alloc_cache_put(&ctx->futex_cache, ifd)) kfree(ifd); __io_futex_complete(req, ts); } @@ -259,11 +253,11 @@ static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx) { - struct io_cache_entry *entry; + struct io_futex_data *ifd; - entry = io_alloc_cache_get(&ctx->futex_cache); - if (entry) - return container_of(entry, struct io_futex_data, cache); + ifd = io_alloc_cache_get(&ctx->futex_cache); + if (ifd) + return ifd; return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT); } diff --git a/io_uring/futex.h b/io_uring/futex.h index 0847e9e8a127..b8bb09873d57 100644 --- a/io_uring/futex.h +++ b/io_uring/futex.h @@ -13,7 +13,7 @@ int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags); bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all); -void io_futex_cache_init(struct io_ring_ctx *ctx); +bool io_futex_cache_init(struct io_ring_ctx *ctx); void io_futex_cache_free(struct io_ring_ctx *ctx); #else static inline int io_futex_cancel(struct io_ring_ctx *ctx, @@ -27,8 +27,9 @@ static inline bool io_futex_remove_all(struct io_ring_ctx *ctx, { return false; } -static inline void io_futex_cache_init(struct io_ring_ctx *ctx) +static inline bool io_futex_cache_init(struct io_ring_ctx *ctx) { + return false; } static inline void io_futex_cache_free(struct io_ring_ctx *ctx) { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 579618fad833..1d453eb8e49f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -276,6 +276,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; int hash_bits; + bool ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -305,17 +306,19 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->cq_overflow_list); INIT_LIST_HEAD(&ctx->io_buffers_cache); INIT_HLIST_HEAD(&ctx->io_buf_list); - io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX, + ret = io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX, sizeof(struct io_rsrc_node)); - io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX, + ret |= io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX, sizeof(struct async_poll)); - io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, + ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_msghdr)); - io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, + ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_rw)); - io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, + ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, sizeof(struct uring_cache)); - io_futex_cache_init(ctx); + ret |= io_futex_cache_init(ctx); + if (ret) + goto err; init_completion(&ctx->ref_comp); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); @@ -345,6 +348,12 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) return ctx; err: + io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); + io_alloc_cache_free(&ctx->apoll_cache, kfree); + io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); + io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); + io_alloc_cache_free(&ctx->uring_cache, kfree); + io_futex_cache_free(ctx); kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); xa_destroy(&ctx->io_bl_xa); @@ -1482,7 +1491,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx, if (apoll->double_poll) kfree(apoll->double_poll); - if (!io_alloc_cache_put(&ctx->apoll_cache, &apoll->cache)) + if (!io_alloc_cache_put(&ctx->apoll_cache, apoll)) kfree(apoll); req->flags &= ~REQ_F_POLLED; } @@ -2778,11 +2787,6 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static void io_rsrc_node_cache_free(struct io_cache_entry *entry) -{ - kfree(container_of(entry, struct io_rsrc_node, cache)); -} - static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); @@ -2797,10 +2801,10 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) __io_sqe_files_unregister(ctx); io_cqring_overflow_kill(ctx); io_eventfd_unregister(ctx); - io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free); + io_alloc_cache_free(&ctx->apoll_cache, kfree); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); - io_alloc_cache_free(&ctx->uring_cache, io_uring_cache_free); + io_alloc_cache_free(&ctx->uring_cache, kfree); io_futex_cache_free(ctx); io_destroy_buffers(ctx); mutex_unlock(&ctx->uring_lock); @@ -2816,7 +2820,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); - io_alloc_cache_free(&ctx->rsrc_node_cache, io_rsrc_node_cache_free); + io_alloc_cache_free(&ctx->rsrc_node_cache, kfree); if (ctx->mm_account) { mmdrop(ctx->mm_account); ctx->mm_account = NULL; diff --git a/io_uring/net.c b/io_uring/net.c index 3bef562b67de..d0abc5689066 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -137,7 +137,7 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) /* Let normal cleanup path reap it if we fail adding to the cache */ iov = hdr->free_iov; - if (io_alloc_cache_put(&req->ctx->netmsg_cache, &hdr->cache)) { + if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) { if (iov) kasan_mempool_poison_object(iov); req->async_data = NULL; @@ -148,12 +148,10 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct io_cache_entry *entry; struct io_async_msghdr *hdr; - entry = io_alloc_cache_get(&ctx->netmsg_cache); - if (entry) { - hdr = container_of(entry, struct io_async_msghdr, cache); + hdr = io_alloc_cache_get(&ctx->netmsg_cache); + if (hdr) { if (hdr->free_iov) { kasan_mempool_unpoison_object(hdr->free_iov, hdr->free_iov_nr * sizeof(struct iovec)); @@ -1490,11 +1488,10 @@ out: return IOU_OK; } -void io_netmsg_cache_free(struct io_cache_entry *entry) +void io_netmsg_cache_free(const void *entry) { - struct io_async_msghdr *kmsg; + struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; - kmsg = container_of(entry, struct io_async_msghdr, cache); if (kmsg->free_iov) { kasan_mempool_unpoison_object(kmsg->free_iov, kmsg->free_iov_nr * sizeof(struct iovec)); diff --git a/io_uring/net.h b/io_uring/net.h index b47b43ec6459..0eb1c1920fc9 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -3,23 +3,15 @@ #include #include -#include "alloc_cache.h" - struct io_async_msghdr { #if defined(CONFIG_NET) - union { - struct iovec fast_iov; - struct { - struct io_cache_entry cache; - /* entry size of ->free_iov, if valid */ - int free_iov_nr; - }; - }; + struct iovec fast_iov; /* points to an allocated iov, if NULL we use fast_iov instead */ struct iovec *free_iov; + int free_iov_nr; + int namelen; __kernel_size_t controllen; __kernel_size_t payloadlen; - int namelen; struct sockaddr __user *uaddr; struct msghdr msg; struct sockaddr_storage addr; @@ -57,9 +49,9 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags); int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); void io_send_zc_cleanup(struct io_kiocb *req); -void io_netmsg_cache_free(struct io_cache_entry *entry); +void io_netmsg_cache_free(const void *entry); #else -static inline void io_netmsg_cache_free(struct io_cache_entry *entry) +static inline void io_netmsg_cache_free(const void *entry) { } #endif diff --git a/io_uring/poll.c b/io_uring/poll.c index 5d55bbf1de15..0a8e02944689 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -14,6 +14,7 @@ #include #include "io_uring.h" +#include "alloc_cache.h" #include "refs.h" #include "napi.h" #include "opdef.h" @@ -686,17 +687,15 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; - struct io_cache_entry *entry; struct async_poll *apoll; if (req->flags & REQ_F_POLLED) { apoll = req->apoll; kfree(apoll->double_poll); } else if (!(issue_flags & IO_URING_F_UNLOCKED)) { - entry = io_alloc_cache_get(&ctx->apoll_cache); - if (entry == NULL) + apoll = io_alloc_cache_get(&ctx->apoll_cache); + if (!apoll) goto alloc_apoll; - apoll = container_of(entry, struct async_poll, cache); apoll->poll.retries = APOLL_MAX_RETRY; } else { alloc_apoll: @@ -1055,8 +1054,3 @@ out: io_req_set_res(req, ret, 0); return IOU_OK; } - -void io_apoll_cache_free(struct io_cache_entry *entry) -{ - kfree(container_of(entry, struct async_poll, cache)); -} diff --git a/io_uring/poll.h b/io_uring/poll.h index 1dacae9e816c..5c240f11069a 100644 --- a/io_uring/poll.h +++ b/io_uring/poll.h @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "alloc_cache.h" - enum { IO_APOLL_OK, IO_APOLL_ABORTED, @@ -17,10 +15,7 @@ struct io_poll { }; struct async_poll { - union { - struct io_poll poll; - struct io_cache_entry cache; - }; + struct io_poll poll; struct io_poll *double_poll; }; @@ -46,6 +41,4 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags); bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, bool cancel_all); -void io_apoll_cache_free(struct io_cache_entry *entry); - void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 4818b79231dd..7b8a056f98ed 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -13,6 +13,7 @@ #include #include "io_uring.h" +#include "alloc_cache.h" #include "openclose.h" #include "rsrc.h" @@ -169,7 +170,7 @@ static void io_rsrc_put_work(struct io_rsrc_node *node) void io_rsrc_node_destroy(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { - if (!io_alloc_cache_put(&ctx->rsrc_node_cache, &node->cache)) + if (!io_alloc_cache_put(&ctx->rsrc_node_cache, node)) kfree(node); } @@ -197,12 +198,9 @@ void io_rsrc_node_ref_zero(struct io_rsrc_node *node) struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) { struct io_rsrc_node *ref_node; - struct io_cache_entry *entry; - entry = io_alloc_cache_get(&ctx->rsrc_node_cache); - if (entry) { - ref_node = container_of(entry, struct io_rsrc_node, cache); - } else { + ref_node = io_alloc_cache_get(&ctx->rsrc_node_cache); + if (!ref_node) { ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); if (!ref_node) return NULL; diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index e21000238954..83c079a707f8 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -2,8 +2,6 @@ #ifndef IOU_RSRC_H #define IOU_RSRC_H -#include "alloc_cache.h" - #define IO_NODE_ALLOC_CACHE_MAX 32 #define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) @@ -36,10 +34,7 @@ struct io_rsrc_data { }; struct io_rsrc_node { - union { - struct io_cache_entry cache; - struct io_ring_ctx *ctx; - }; + struct io_ring_ctx *ctx; int refs; bool empty; u16 type; diff --git a/io_uring/rw.c b/io_uring/rw.c index e84d322a6150..3134a6ece1be 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -18,6 +18,7 @@ #include "io_uring.h" #include "opdef.h" #include "kbuf.h" +#include "alloc_cache.h" #include "rsrc.h" #include "poll.h" #include "rw.h" @@ -154,7 +155,7 @@ static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) return; } iov = rw->free_iovec; - if (io_alloc_cache_put(&req->ctx->rw_cache, &rw->cache)) { + if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) { if (iov) kasan_mempool_poison_object(iov); req->async_data = NULL; @@ -200,12 +201,10 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) static int io_rw_alloc_async(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct io_cache_entry *entry; struct io_async_rw *rw; - entry = io_alloc_cache_get(&ctx->rw_cache); - if (entry) { - rw = container_of(entry, struct io_async_rw, cache); + rw = io_alloc_cache_get(&ctx->rw_cache); + if (rw) { if (rw->free_iovec) { kasan_mempool_unpoison_object(rw->free_iovec, rw->free_iov_nr * sizeof(struct iovec)); @@ -1168,11 +1167,10 @@ int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) return nr_events; } -void io_rw_cache_free(struct io_cache_entry *entry) +void io_rw_cache_free(const void *entry) { - struct io_async_rw *rw; + struct io_async_rw *rw = (struct io_async_rw *) entry; - rw = container_of(entry, struct io_async_rw, cache); if (rw->free_iovec) { kasan_mempool_unpoison_object(rw->free_iovec, rw->free_iov_nr * sizeof(struct iovec)); diff --git a/io_uring/rw.h b/io_uring/rw.h index cf51d0eb407a..3f432dc75441 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -3,10 +3,7 @@ #include struct io_async_rw { - union { - size_t bytes_done; - struct io_cache_entry cache; - }; + size_t bytes_done; struct iov_iter iter; struct iov_iter_state iter_state; struct iovec fast_iov; @@ -28,4 +25,4 @@ void io_rw_fail(struct io_kiocb *req); void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts); int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags); -void io_rw_cache_free(struct io_cache_entry *entry); +void io_rw_cache_free(const void *entry); diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 92346b5d9f5b..334d31dd6628 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -11,18 +11,17 @@ #include #include "io_uring.h" +#include "alloc_cache.h" #include "rsrc.h" #include "uring_cmd.h" static struct uring_cache *io_uring_async_get(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct io_cache_entry *entry; struct uring_cache *cache; - entry = io_alloc_cache_get(&ctx->uring_cache); - if (entry) { - cache = container_of(entry, struct uring_cache, cache); + cache = io_alloc_cache_get(&ctx->uring_cache); + if (cache) { req->flags |= REQ_F_ASYNC_DATA; req->async_data = cache; return cache; @@ -39,7 +38,7 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) if (issue_flags & IO_URING_F_UNLOCKED) return; - if (io_alloc_cache_put(&req->ctx->uring_cache, &cache->cache)) { + if (io_alloc_cache_put(&req->ctx->uring_cache, cache)) { ioucmd->sqe = NULL; req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; @@ -354,8 +353,3 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) } EXPORT_SYMBOL_GPL(io_uring_cmd_sock); #endif - -void io_uring_cache_free(struct io_cache_entry *entry) -{ - kfree(container_of(entry, struct uring_cache, cache)); -} diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 477ea8865639..a361f98664d2 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -1,15 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 struct uring_cache { - union { - struct io_cache_entry cache; - struct io_uring_sqe sqes[2]; - }; + struct io_uring_sqe sqes[2]; }; int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); -void io_uring_cache_free(struct io_cache_entry *entry); bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all); -- cgit v1.2.3-59-g8ed1b From 8c9a6f549e65912825e31dc1e0e3f7995984649d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 9 Apr 2024 14:05:53 -0700 Subject: io_uring: separate header for exported net bits We're exporting some io_uring bits to networking, e.g. for implementing a net callback for io_uring cmds, but we don't want to expose more than needed. Add a separate header for networking. Signed-off-by: Pavel Begunkov Signed-off-by: David Wei Link: https://lore.kernel.org/r/20240409210554.1878789-1-dw@davidwei.uk Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 6 ------ include/linux/io_uring/net.h | 18 ++++++++++++++++++ io_uring/uring_cmd.c | 1 + net/socket.c | 2 +- 4 files changed, 20 insertions(+), 7 deletions(-) create mode 100644 include/linux/io_uring/net.h (limited to 'io_uring/uring_cmd.c') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 68ed6697fece..e123d5e17b52 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,7 +11,6 @@ void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) @@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode) { return ""; } -static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ - return -EOPNOTSUPP; -} static inline bool io_is_uring_fops(struct file *file) { return false; diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h new file mode 100644 index 000000000000..b58f39fed4d5 --- /dev/null +++ b/include/linux/io_uring/net.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_NET_H +#define _LINUX_IO_URING_NET_H + +struct io_uring_cmd; + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); + +#else +static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 334d31dd6628..21ac5fb2d5f0 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include diff --git a/net/socket.c b/net/socket.c index e5f3af49a8b6..01a71ae10c35 100644 --- a/net/socket.c +++ b/net/socket.c @@ -88,7 +88,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.3-59-g8ed1b