From 521223d7c229f83915619f888c99e952f24dc39f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 28 Jan 2024 20:11:55 -0700 Subject: io_uring/cancel: don't default to setting req->work.cancel_seq Just leave it unset by default, avoiding dipping into the last cacheline (which is otherwise untouched) for the fast path of using poll to drive networked traffic. Add a flag that tells us if the sequence is valid or not, and then we can defer actually assigning the flag and sequence until someone runs cancelations. Signed-off-by: Jens Axboe --- io_uring/poll.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'io_uring/poll.c') diff --git a/io_uring/poll.c b/io_uring/poll.c index 7513afc7b702..c2b0a2d0762b 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -588,10 +588,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, struct io_poll_table *ipt, __poll_t mask, unsigned issue_flags) { - struct io_ring_ctx *ctx = req->ctx; - INIT_HLIST_NODE(&req->hash_node); - req->work.cancel_seq = atomic_read(&ctx->cancel_seq); io_init_poll_iocb(poll, mask); poll->file = req->file; req->apoll_events = poll->events; @@ -818,9 +815,8 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, if (poll_only && req->opcode != IORING_OP_POLL_ADD) continue; if (cd->flags & IORING_ASYNC_CANCEL_ALL) { - if (cd->seq == req->work.cancel_seq) + if (io_cancel_match_sequence(req, cd->seq)) continue; - req->work.cancel_seq = cd->seq; } *out_bucket = hb; return req; -- cgit v1.2.3-70-g09d2 From 95041b93e90a06bb613ec4bef9cd4d61570f68e4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 28 Jan 2024 20:08:24 -0700 Subject: io_uring: add io_file_can_poll() helper This adds a flag to avoid dipping dereferencing file and then f_op to figure out if the file has a poll handler defined or not. We generally call this at least twice for networked workloads, and if using ring provided buffers, we do it on every buffer selection. Particularly the latter is troublesome, as it's otherwise a very fast operation. Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 +++ io_uring/io_uring.c | 2 +- io_uring/io_uring.h | 12 ++++++++++++ io_uring/kbuf.c | 2 +- io_uring/poll.c | 2 +- io_uring/rw.c | 6 +++--- 6 files changed, 21 insertions(+), 6 deletions(-) (limited to 'io_uring/poll.c') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e19698daae1a..4ddc7b3168f3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -464,6 +464,7 @@ enum { REQ_F_ISREG_BIT, REQ_F_POLL_NO_LAZY_BIT, REQ_F_CANCEL_SEQ_BIT, + REQ_F_CAN_POLL_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -538,6 +539,8 @@ enum { REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), /* cancel sequence is set and valid */ REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT), + /* file is pollable */ + REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fd552b260eef..17bd16be1dfd 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1968,7 +1968,7 @@ fail: if (req->flags & REQ_F_FORCE_ASYNC) { bool opcode_poll = def->pollin || def->pollout; - if (opcode_poll && file_can_poll(req->file)) { + if (opcode_poll && io_file_can_poll(req)) { needs_poll = true; issue_flags |= IO_URING_F_NONBLOCK; } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index d5495710c178..2952551fe345 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include "io-wq.h" @@ -398,4 +399,15 @@ static inline size_t uring_sqe_size(struct io_ring_ctx *ctx) return 2 * sizeof(struct io_uring_sqe); return sizeof(struct io_uring_sqe); } + +static inline bool io_file_can_poll(struct io_kiocb *req) +{ + if (req->flags & REQ_F_CAN_POLL) + return true; + if (file_can_poll(req->file)) { + req->flags |= REQ_F_CAN_POLL; + return true; + } + return false; +} #endif diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 18df5a9d2f5e..71880615bb78 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -180,7 +180,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->buf_list = bl; req->buf_index = buf->bid; - if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) { + if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { /* * If we came in unlocked, we have no choice but to consume the * buffer here, otherwise nothing ensures that the buffer won't diff --git a/io_uring/poll.c b/io_uring/poll.c index c2b0a2d0762b..3f3380dc5f68 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -724,7 +724,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; - if (!file_can_poll(req->file)) + if (!io_file_can_poll(req)) return IO_APOLL_ABORTED; if (!(req->flags & REQ_F_APOLL_MULTISHOT)) mask |= EPOLLONESHOT; diff --git a/io_uring/rw.c b/io_uring/rw.c index d5e79d9bdc71..0fb7a045163a 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -682,7 +682,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks */ - if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) + if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; wait->wait.func = io_async_buf_func; @@ -831,7 +831,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) * If we can poll, just do that. For a vectored read, we'll * need to copy state first. */ - if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored) + if (io_file_can_poll(req) && !io_issue_defs[req->opcode].vectored) return -EAGAIN; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) @@ -930,7 +930,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) /* * Multishot MUST be used on a pollable file */ - if (!file_can_poll(req->file)) + if (!io_file_can_poll(req)) return -EBADFD; ret = __io_read(req, issue_flags); -- cgit v1.2.3-70-g09d2 From 3cdc4be114a9be61b7041a53e44aa71718a7cf28 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 1 Feb 2024 12:49:37 -0700 Subject: io_uring/poll: improve readability of poll reference decrementing This overly long line is hard to read. Break it up by AND'ing the ref mask first, then perform the atomic_sub_return() with the value itself. Signed-off-by: Jens Axboe --- io_uring/poll.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'io_uring/poll.c') diff --git a/io_uring/poll.c b/io_uring/poll.c index 3f3380dc5f68..8e01c2672df4 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -343,8 +343,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) * Release all references, retry if someone tried to restart * task_work while we were executing it. */ - } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & - IO_POLL_REF_MASK); + v &= IO_POLL_REF_MASK; + } while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK); return IOU_POLL_NO_ACTION; } -- cgit v1.2.3-70-g09d2 From 8d0c12a80cdeb80d5e0510e96d38fe551ed8e9b5 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Thu, 8 Jun 2023 09:38:36 -0700 Subject: io-uring: add napi busy poll support This adds the napi busy polling support in io_uring.c. It adds a new napi_list to the io_ring_ctx structure. This list contains the list of napi_id's that are currently enabled for busy polling. The list is synchronized by the new napi_lock spin lock. The current default napi busy polling time is stored in napi_busy_poll_to. If napi busy polling is not enabled, the value is 0. In addition there is also a hash table. The hash table store the napi id and the pointer to the above list nodes. The hash table is used to speed up the lookup to the list elements. The hash table is synchronized with rcu. The NAPI_TIMEOUT is stored as a timeout to make sure that the time a napi entry is stored in the napi list is limited. The busy poll timeout is also stored as part of the io_wait_queue. This is necessary as for sq polling the poll interval needs to be adjusted and the napi callback allows only to pass in one value. This has been tested with two simple programs from the liburing library repository: the napi client and the napi server program. The client sends a request, which has a timestamp in its payload and the server replies with the same payload. The client calculates the roundtrip time and stores it to calculate the results. The client is running on host1 and the server is running on host 2 (in the same rack). The measured times below are roundtrip times. They are average times over 5 runs each. Each run measures 1 million roundtrips. no rx coal rx coal: frames=88,usecs=33 Default 57us 56us client_poll=100us 47us 46us server_poll=100us 51us 46us client_poll=100us+ 40us 40us server_poll=100us client_poll=100us+ 41us 39us server_poll=100us+ prefer napi busy poll on client client_poll=100us+ 41us 39us server_poll=100us+ prefer napi busy poll on server client_poll=100us+ 41us 39us server_poll=100us+ prefer napi busy poll on client + server Signed-off-by: Stefan Roesch Suggested-by: Olivier Langlois Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230608163839.2891748-5-shr@devkernel.io Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 15 ++- io_uring/Makefile | 1 + io_uring/io_uring.c | 8 ++ io_uring/io_uring.h | 4 + io_uring/napi.c | 255 +++++++++++++++++++++++++++++++++++++++++ io_uring/napi.h | 89 ++++++++++++++ io_uring/poll.c | 2 + 7 files changed, 373 insertions(+), 1 deletion(-) create mode 100644 io_uring/napi.c create mode 100644 io_uring/napi.h (limited to 'io_uring/poll.c') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index addfcc74d851..4fe7af8a4907 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -2,6 +2,7 @@ #define IO_URING_TYPES_H #include +#include #include #include #include @@ -247,6 +248,7 @@ struct io_ring_ctx { struct percpu_ref refs; enum task_work_notify_mode notify_method; + unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; /* submission data */ @@ -410,7 +412,18 @@ struct io_ring_ctx { struct callback_head poll_wq_task_work; struct list_head defer_list; - unsigned sq_thread_idle; + +#ifdef CONFIG_NET_RX_BUSY_POLL + struct list_head napi_list; /* track busy poll napi_id */ + spinlock_t napi_lock; /* napi_list lock */ + + /* napi busy poll default timeout */ + unsigned int napi_busy_poll_to; + bool napi_prefer_busy_poll; + + DECLARE_HASHTABLE(napi_ht, 4); +#endif + /* protected by ->completion_lock */ unsigned evfd_last_cq_tail; diff --git a/io_uring/Makefile b/io_uring/Makefile index 42afe4a1ff31..2e1d4e03799c 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ notif.o waitid.o register.o truncate.o obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FUTEX) += futex.o +obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 5311f19faa4c..479f610e314f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -95,6 +95,7 @@ #include "notif.h" #include "waitid.h" #include "futex.h" +#include "napi.h" #include "timeout.h" #include "poll.h" @@ -349,6 +350,8 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd); + io_napi_init(ctx); + return ctx; err: kfree(ctx->cancel_table.hbs); @@ -2602,9 +2605,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, if (get_timespec64(&ts, uts)) return -EFAULT; + iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); + io_napi_adjust_timeout(ctx, &iowq, &ts); } + io_napi_busy_loop(ctx, &iowq); + trace_io_uring_cqring_wait(ctx, min_events); do { int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail); @@ -2897,6 +2904,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); + io_napi_free(ctx); kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); kfree(ctx->io_bl); diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 859f6e0580e3..1ca99522811b 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -42,6 +42,10 @@ struct io_wait_queue { unsigned nr_timeouts; ktime_t timeout; +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int napi_busy_poll_to; + bool napi_prefer_busy_poll; +#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) diff --git a/io_uring/napi.c b/io_uring/napi.c new file mode 100644 index 000000000000..1112cc39153c --- /dev/null +++ b/io_uring/napi.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "io_uring.h" +#include "napi.h" + +#ifdef CONFIG_NET_RX_BUSY_POLL + +/* Timeout for cleanout of stale entries. */ +#define NAPI_TIMEOUT (60 * SEC_CONVERSION) + +struct io_napi_entry { + unsigned int napi_id; + struct list_head list; + + unsigned long timeout; + struct hlist_node node; + + struct rcu_head rcu; +}; + +static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list, + unsigned int napi_id) +{ + struct io_napi_entry *e; + + hlist_for_each_entry_rcu(e, hash_list, node) { + if (e->napi_id != napi_id) + continue; + e->timeout = jiffies + NAPI_TIMEOUT; + return e; + } + + return NULL; +} + +void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) +{ + struct hlist_head *hash_list; + unsigned int napi_id; + struct sock *sk; + struct io_napi_entry *e; + + sk = sock->sk; + if (!sk) + return; + + napi_id = READ_ONCE(sk->sk_napi_id); + + /* Non-NAPI IDs can be rejected. */ + if (napi_id < MIN_NAPI_ID) + return; + + hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; + + rcu_read_lock(); + e = io_napi_hash_find(hash_list, napi_id); + if (e) { + e->timeout = jiffies + NAPI_TIMEOUT; + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + e = kmalloc(sizeof(*e), GFP_NOWAIT); + if (!e) + return; + + e->napi_id = napi_id; + e->timeout = jiffies + NAPI_TIMEOUT; + + spin_lock(&ctx->napi_lock); + if (unlikely(io_napi_hash_find(hash_list, napi_id))) { + spin_unlock(&ctx->napi_lock); + kfree(e); + return; + } + + hlist_add_tail_rcu(&e->node, hash_list); + list_add_tail(&e->list, &ctx->napi_list); + spin_unlock(&ctx->napi_lock); +} + +static void __io_napi_remove_stale(struct io_ring_ctx *ctx) +{ + struct io_napi_entry *e; + unsigned int i; + + spin_lock(&ctx->napi_lock); + hash_for_each(ctx->napi_ht, i, e, node) { + if (time_after(jiffies, e->timeout)) { + list_del(&e->list); + hash_del_rcu(&e->node); + kfree_rcu(e, rcu); + } + } + spin_unlock(&ctx->napi_lock); +} + +static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale) +{ + if (is_stale) + __io_napi_remove_stale(ctx); +} + +static inline bool io_napi_busy_loop_timeout(unsigned long start_time, + unsigned long bp_usec) +{ + if (bp_usec) { + unsigned long end_time = start_time + bp_usec; + unsigned long now = busy_loop_current_time(); + + return time_after(now, end_time); + } + + return true; +} + +static bool io_napi_busy_loop_should_end(void *data, + unsigned long start_time) +{ + struct io_wait_queue *iowq = data; + + if (signal_pending(current)) + return true; + if (io_should_wake(iowq)) + return true; + if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to)) + return true; + + return false; +} + +static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx, + void *loop_end_arg) +{ + struct io_napi_entry *e; + bool (*loop_end)(void *, unsigned long) = NULL; + bool is_stale = false; + + if (loop_end_arg) + loop_end = io_napi_busy_loop_should_end; + + list_for_each_entry_rcu(e, &ctx->napi_list, list) { + napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg, + ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET); + + if (time_after(jiffies, e->timeout)) + is_stale = true; + } + + return is_stale; +} + +static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq) +{ + unsigned long start_time = busy_loop_current_time(); + void *loop_end_arg = NULL; + bool is_stale = false; + + /* Singular lists use a different napi loop end check function and are + * only executed once. + */ + if (list_is_singular(&ctx->napi_list)) + loop_end_arg = iowq; + + rcu_read_lock(); + do { + is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg); + } while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg); + rcu_read_unlock(); + + io_napi_remove_stale(ctx, is_stale); +} + +/* + * io_napi_init() - Init napi settings + * @ctx: pointer to io-uring context structure + * + * Init napi settings in the io-uring context. + */ +void io_napi_init(struct io_ring_ctx *ctx) +{ + INIT_LIST_HEAD(&ctx->napi_list); + spin_lock_init(&ctx->napi_lock); + ctx->napi_prefer_busy_poll = false; + ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll); +} + +/* + * io_napi_free() - Deallocate napi + * @ctx: pointer to io-uring context structure + * + * Free the napi list and the hash table in the io-uring context. + */ +void io_napi_free(struct io_ring_ctx *ctx) +{ + struct io_napi_entry *e; + LIST_HEAD(napi_list); + unsigned int i; + + spin_lock(&ctx->napi_lock); + hash_for_each(ctx->napi_ht, i, e, node) { + hash_del_rcu(&e->node); + kfree_rcu(e, rcu); + } + spin_unlock(&ctx->napi_lock); +} + +/* + * __io_napi_adjust_timeout() - Add napi id to the busy poll list + * @ctx: pointer to io-uring context structure + * @iowq: pointer to io wait queue + * @ts: pointer to timespec or NULL + * + * Adjust the busy loop timeout according to timespec and busy poll timeout. + */ +void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, + struct timespec64 *ts) +{ + unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to); + + if (ts) { + struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to); + + if (timespec64_compare(ts, &poll_to_ts) > 0) { + *ts = timespec64_sub(*ts, poll_to_ts); + } else { + u64 to = timespec64_to_ns(ts); + + do_div(to, 1000); + ts->tv_sec = 0; + ts->tv_nsec = 0; + } + } + + iowq->napi_busy_poll_to = poll_to; +} + +/* + * __io_napi_busy_loop() - execute busy poll loop + * @ctx: pointer to io-uring context structure + * @iowq: pointer to io wait queue + * + * Execute the busy poll loop and merge the spliced off list. + */ +void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) +{ + iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll); + + if (!(ctx->flags & IORING_SETUP_SQPOLL) && iowq->napi_busy_poll_to) + io_napi_blocking_busy_loop(ctx, iowq); +} + +#endif diff --git a/io_uring/napi.h b/io_uring/napi.h new file mode 100644 index 000000000000..be8aa8ee32d9 --- /dev/null +++ b/io_uring/napi.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef IOU_NAPI_H +#define IOU_NAPI_H + +#include +#include +#include + +#ifdef CONFIG_NET_RX_BUSY_POLL + +void io_napi_init(struct io_ring_ctx *ctx); +void io_napi_free(struct io_ring_ctx *ctx); + +void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock); + +void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, struct timespec64 *ts); +void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq); + +static inline bool io_napi(struct io_ring_ctx *ctx) +{ + return !list_empty(&ctx->napi_list); +} + +static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + struct timespec64 *ts) +{ + if (!io_napi(ctx)) + return; + __io_napi_adjust_timeout(ctx, iowq, ts); +} + +static inline void io_napi_busy_loop(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq) +{ + if (!io_napi(ctx)) + return; + __io_napi_busy_loop(ctx, iowq); +} + +/* + * io_napi_add() - Add napi id to the busy poll list + * @req: pointer to io_kiocb request + * + * Add the napi id of the socket to the napi busy poll list and hash table. + */ +static inline void io_napi_add(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct socket *sock; + + if (!READ_ONCE(ctx->napi_busy_poll_to)) + return; + + sock = sock_from_file(req->file); + if (sock) + __io_napi_add(ctx, sock); +} + +#else + +static inline void io_napi_init(struct io_ring_ctx *ctx) +{ +} +static inline void io_napi_free(struct io_ring_ctx *ctx) +{ +} +static inline bool io_napi(struct io_ring_ctx *ctx) +{ + return false; +} +static inline void io_napi_add(struct io_kiocb *req) +{ +} +static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq, + struct timespec64 *ts) +{ +} +static inline void io_napi_busy_loop(struct io_ring_ctx *ctx, + struct io_wait_queue *iowq) +{ +} + +#endif /* CONFIG_NET_RX_BUSY_POLL */ + +#endif diff --git a/io_uring/poll.c b/io_uring/poll.c index 8e01c2672df4..053d738c330c 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -15,6 +15,7 @@ #include "io_uring.h" #include "refs.h" +#include "napi.h" #include "opdef.h" #include "kbuf.h" #include "poll.h" @@ -649,6 +650,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask); return 0; } + io_napi_add(req); if (ipt->owning) { /* -- cgit v1.2.3-70-g09d2 From 1a8ec63b2b6c91caec87d4e132b1f71b5df342be Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 7 Mar 2024 18:06:32 +0000 Subject: io_uring: fix io_queue_proc modifying req->flags With multiple poll entries __io_queue_proc() might be running in parallel with poll handlers and possibly task_work, we should not be carelessly modifying req->flags there. io_poll_double_prepare() handles a similar case with locking but it's much easier to move it into __io_arm_poll_handler(). Cc: stable@vger.kernel.org Fixes: 595e52284d24a ("io_uring/poll: don't enable lazy wake for POLLEXCLUSIVE") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/455cc49e38cf32026fa1b49670be8c162c2cb583.1709834755.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/poll.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'io_uring/poll.c') diff --git a/io_uring/poll.c b/io_uring/poll.c index 053d738c330c..5f779139cae1 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -540,14 +540,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt, poll->wait.private = (void *) wqe_private; if (poll->events & EPOLLEXCLUSIVE) { - /* - * Exclusive waits may only wake a limited amount of entries - * rather than all of them, this may interfere with lazy - * wake if someone does wait(events > 1). Ensure we don't do - * lazy wake for those, as we need to process each one as they - * come in. - */ - req->flags |= REQ_F_POLL_NO_LAZY; add_wait_queue_exclusive(head, &poll->wait); } else { add_wait_queue(head, &poll->wait); @@ -616,6 +608,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (issue_flags & IO_URING_F_UNLOCKED) req->flags &= ~REQ_F_HASH_LOCKED; + + /* + * Exclusive waits may only wake a limited amount of entries + * rather than all of them, this may interfere with lazy + * wake if someone does wait(events > 1). Ensure we don't do + * lazy wake for those, as we need to process each one as they + * come in. + */ + if (poll->events & EPOLLEXCLUSIVE) + req->flags |= REQ_F_POLL_NO_LAZY; + mask = vfs_poll(req->file, &ipt->pt) & poll->events; if (unlikely(ipt->error || !ipt->nr_entries)) { -- cgit v1.2.3-70-g09d2