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 --- io_uring/napi.h | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 io_uring/napi.h (limited to 'io_uring/napi.h') 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 -- cgit v1.2.3 From ff183d427da0a733b0dbe11bd7acaf2dcb37b4cc Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Thu, 8 Jun 2023 09:38:37 -0700 Subject: io-uring: add sqpoll support for napi busy poll This adds the sqpoll support to the io-uring napi. Signed-off-by: Stefan Roesch Suggested-by: Olivier Langlois Link: https://lore.kernel.org/r/20230608163839.2891748-6-shr@devkernel.io Signed-off-by: Jens Axboe --- io_uring/napi.c | 24 ++++++++++++++++++++++++ io_uring/napi.h | 6 +++++- io_uring/sqpoll.c | 4 ++++ 3 files changed, 33 insertions(+), 1 deletion(-) (limited to 'io_uring/napi.h') diff --git a/io_uring/napi.c b/io_uring/napi.c index 1112cc39153c..3e578df36cc5 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -252,4 +252,28 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) io_napi_blocking_busy_loop(ctx, iowq); } +/* + * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll + * @ctx: pointer to io-uring context structure + * + * Splice of the napi list and execute the napi busy poll loop. + */ +int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) +{ + LIST_HEAD(napi_list); + bool is_stale = false; + + if (!READ_ONCE(ctx->napi_busy_poll_to)) + return 0; + if (list_empty_careful(&ctx->napi_list)) + return 0; + + rcu_read_lock(); + is_stale = __io_napi_do_busy_loop(ctx, NULL); + rcu_read_unlock(); + + io_napi_remove_stale(ctx, is_stale); + return 1; +} + #endif diff --git a/io_uring/napi.h b/io_uring/napi.h index be8aa8ee32d9..b6d6243fc7fe 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -17,6 +17,7 @@ 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); +int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx); static inline bool io_napi(struct io_ring_ctx *ctx) { @@ -83,7 +84,10 @@ static inline void io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { } - +static inline int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) +{ + return 0; +} #endif /* CONFIG_NET_RX_BUSY_POLL */ #endif diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 28bf0e085d31..f3979cacda13 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -15,6 +15,7 @@ #include #include "io_uring.h" +#include "napi.h" #include "sqpoll.h" #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 @@ -194,6 +195,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); + if (io_napi(ctx)) + ret += io_napi_sqpoll_busy_poll(ctx); + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) -- cgit v1.2.3 From ef1186c1a875bfa8a8cbfc2a9670b14b082187a9 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Thu, 8 Jun 2023 09:38:38 -0700 Subject: io_uring: add register/unregister napi function This adds an api to register and unregister the napi for io-uring. If the arg value is specified when unregistering, the current napi setting for the busy poll timeout is copied into the user structure. If this is not required, NULL can be passed as the arg value. Signed-off-by: Stefan Roesch Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230608163839.2891748-7-shr@devkernel.io Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 12 ++++++++++ io_uring/napi.c | 52 +++++++++++++++++++++++++++++++++++++++++++ io_uring/napi.h | 11 +++++++++ io_uring/register.c | 13 +++++++++++ 4 files changed, 88 insertions(+) (limited to 'io_uring/napi.h') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index fb812f1b6bb5..7bd10201a02b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -571,6 +571,10 @@ enum { /* return status information for a buffer group */ IORING_REGISTER_PBUF_STATUS = 26, + /* set/clear busy poll settings */ + IORING_REGISTER_NAPI = 27, + IORING_UNREGISTER_NAPI = 28, + /* this goes last */ IORING_REGISTER_LAST, @@ -704,6 +708,14 @@ struct io_uring_buf_status { __u32 resv[8]; }; +/* argument for IORING_(UN)REGISTER_NAPI */ +struct io_uring_napi { + __u32 busy_poll_to; + __u8 prefer_busy_poll; + __u8 pad[3]; + __u64 resv; +}; + /* * io_uring_restriction->opcode values */ diff --git a/io_uring/napi.c b/io_uring/napi.c index 3e578df36cc5..8ec016899539 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -207,6 +207,58 @@ void io_napi_free(struct io_ring_ctx *ctx) spin_unlock(&ctx->napi_lock); } +/* + * io_napi_register() - Register napi with io-uring + * @ctx: pointer to io-uring context structure + * @arg: pointer to io_uring_napi structure + * + * Register napi in the io-uring context. + */ +int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll + }; + struct io_uring_napi napi; + + if (copy_from_user(&napi, arg, sizeof(napi))) + return -EFAULT; + if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv) + return -EINVAL; + + WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to); + WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll); + + if (copy_to_user(arg, &curr, sizeof(curr))) + return -EFAULT; + + return 0; +} + +/* + * io_napi_unregister() - Unregister napi with io-uring + * @ctx: pointer to io-uring context structure + * @arg: pointer to io_uring_napi structure + * + * Unregister napi. If arg has been specified copy the busy poll timeout and + * prefer busy poll setting to the passed in structure. + */ +int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + const struct io_uring_napi curr = { + .busy_poll_to = ctx->napi_busy_poll_to, + .prefer_busy_poll = ctx->napi_prefer_busy_poll + }; + + if (arg && copy_to_user(arg, &curr, sizeof(curr))) + return -EFAULT; + + WRITE_ONCE(ctx->napi_busy_poll_to, 0); + WRITE_ONCE(ctx->napi_prefer_busy_poll, false); + return 0; +} + /* * __io_napi_adjust_timeout() - Add napi id to the busy poll list * @ctx: pointer to io-uring context structure diff --git a/io_uring/napi.h b/io_uring/napi.h index b6d6243fc7fe..6fc0393d0dbe 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -12,6 +12,9 @@ void io_napi_init(struct io_ring_ctx *ctx); void io_napi_free(struct io_ring_ctx *ctx); +int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); +int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); + void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock); void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, @@ -68,6 +71,14 @@ static inline void io_napi_init(struct io_ring_ctx *ctx) static inline void io_napi_free(struct io_ring_ctx *ctx) { } +static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + return -EOPNOTSUPP; +} +static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) +{ + return -EOPNOTSUPP; +} static inline bool io_napi(struct io_ring_ctx *ctx) { return false; diff --git a/io_uring/register.c b/io_uring/register.c index 5e62c1208996..99c37775f974 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -26,6 +26,7 @@ #include "register.h" #include "cancel.h" #include "kbuf.h" +#include "napi.h" #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) @@ -550,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_register_pbuf_status(ctx, arg); break; + case IORING_REGISTER_NAPI: + ret = -EINVAL; + if (!arg || nr_args != 1) + break; + ret = io_register_napi(ctx, arg); + break; + case IORING_UNREGISTER_NAPI: + ret = -EINVAL; + if (nr_args != 1) + break; + ret = io_unregister_napi(ctx, arg); + break; default: ret = -EINVAL; break; -- cgit v1.2.3