From 194bb58c6090e39bd7d9b9c888a079213628e1f6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Jun 2023 11:57:40 -0600 Subject: io_uring: add support for futex wake and wait Add support for FUTEX_WAKE/WAIT primitives. IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as it does support passing in a bitset. Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and FUTEX_WAIT_BITSET. For both of them, they are using the futex2 interface. FUTEX_WAKE is straight forward, as those can always be done directly from the io_uring submission without needing async handling. For FUTEX_WAIT, things are a bit more complicated. If the futex isn't ready, then we rely on a callback via futex_queue->wake() when someone wakes up the futex. From that calback, we queue up task_work with the original task, which will post a CQE and wake it, if necessary. Cancelations are supported, both from the application point-of-view, but also to be able to cancel pending waits if the ring exits before all events have occurred. The return value of futex_unqueue() is used to gate who wins the potential race between cancelation and futex wakeups. Whomever gets a 'ret == 1' return from that claims ownership of the io_uring futex request. This is just the barebones wait/wake support. PI or REQUEUE support is not added at this point, unclear if we might look into that later. Likewise, explicit timeouts are not supported either. It is expected that users that need timeouts would do so via the usual io_uring mechanism to do that using linked timeouts. The SQE format is as follows: `addr` Address of futex `fd` futex2(2) FUTEX2_* flags `futex_flags` io_uring specific command flags. None valid now. `addr2` Value of futex `addr3` Mask to wake/wait Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 425f64eee44e..04f9fba38d4b 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -66,6 +66,7 @@ struct io_uring_sqe { __u32 msg_ring_flags; __u32 uring_cmd_flags; __u32 waitid_flags; + __u32 futex_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -243,6 +244,8 @@ enum io_uring_op { IORING_OP_SENDMSG_ZC, IORING_OP_READ_MULTISHOT, IORING_OP_WAITID, + IORING_OP_FUTEX_WAIT, + IORING_OP_FUTEX_WAKE, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 8f350194d5cfd7016d4cd44e433df0faa4d4a703 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 12 Jun 2023 19:04:32 -0600 Subject: io_uring: add support for vectored futex waits This adds support for IORING_OP_FUTEX_WAITV, which allows registering a notification for a number of futexes at once. If one of the futexes are woken, then the request will complete with the index of the futex that got woken as the result. This is identical to what the normal vectored futex waitv operation does. Use like IORING_OP_FUTEX_WAIT, except sqe->addr must now contain a pointer to a struct futex_waitv array, and sqe->off must now contain the number of elements in that array. As flags are passed in the futex_vector array, and likewise for the value and futex address(es), sqe->addr2 and sqe->addr3 are also reserved for IORING_OP_FUTEX_WAITV. For cancelations, FUTEX_WAITV does not rely on the futex_unqueue() return value as we're dealing with multiple futexes. Instead, a separate per io_uring request atomic is used to claim ownership of the request. Waiting on N futexes could be done with IORING_OP_FUTEX_WAIT as well, but that punts a lot of the work to the application: 1) Application would need to submit N IORING_OP_FUTEX_WAIT requests, rather than just a single IORING_OP_FUTEX_WAITV. 2) When one futex is woken, application would need to cancel the remaining N-1 requests that didn't trigger. While this is of course doable, having a single vectored futex wait makes for much simpler application code. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + io_uring/futex.c | 169 +++++++++++++++++++++++++++++++++++++++--- io_uring/futex.h | 2 + io_uring/opdef.c | 11 +++ 4 files changed, 174 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 04f9fba38d4b..92be89a871fc 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -246,6 +246,7 @@ enum io_uring_op { IORING_OP_WAITID, IORING_OP_FUTEX_WAIT, IORING_OP_FUTEX_WAKE, + IORING_OP_FUTEX_WAITV, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/futex.c b/io_uring/futex.c index eb4406ac46fb..3c3575303c3d 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -14,10 +14,16 @@ struct io_futex { struct file *file; - u32 __user *uaddr; + union { + u32 __user *uaddr; + struct futex_waitv __user *uwaitv; + }; unsigned long futex_val; unsigned long futex_mask; + unsigned long futexv_owned; u32 futex_flags; + unsigned int futex_nr; + bool futexv_unqueued; }; struct io_futex_data { @@ -44,6 +50,13 @@ void io_futex_cache_free(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->futex_cache, io_futex_cache_entry_free); } +static void __io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) +{ + req->async_data = NULL; + hlist_del_init(&req->hash_node); + io_req_task_complete(req, ts); +} + static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) { struct io_futex_data *ifd = req->async_data; @@ -52,22 +65,56 @@ static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts) io_tw_lock(ctx, ts); if (!io_alloc_cache_put(&ctx->futex_cache, &ifd->cache)) kfree(ifd); - req->async_data = NULL; - hlist_del_init(&req->hash_node); - io_req_task_complete(req, ts); + __io_futex_complete(req, ts); } -static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +static void io_futexv_complete(struct io_kiocb *req, struct io_tw_state *ts) { - struct io_futex_data *ifd = req->async_data; + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv = req->async_data; - /* futex wake already done or in progress */ - if (!futex_unqueue(&ifd->q)) + io_tw_lock(req->ctx, ts); + + if (!iof->futexv_unqueued) { + int res; + + res = futex_unqueue_multiple(futexv, iof->futex_nr); + if (res != -1) + io_req_set_res(req, res, 0); + } + + kfree(req->async_data); + req->flags &= ~REQ_F_ASYNC_DATA; + __io_futex_complete(req, ts); +} + +static bool io_futexv_claim(struct io_futex *iof) +{ + if (test_bit(0, &iof->futexv_owned) || + test_and_set_bit_lock(0, &iof->futexv_owned)) return false; + return true; +} + +static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + /* futex wake already done or in progress */ + if (req->opcode == IORING_OP_FUTEX_WAIT) { + struct io_futex_data *ifd = req->async_data; + + if (!futex_unqueue(&ifd->q)) + return false; + req->io_task_work.func = io_futex_complete; + } else { + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + + if (!io_futexv_claim(iof)) + return false; + req->io_task_work.func = io_futexv_complete; + } hlist_del_init(&req->hash_node); io_req_set_res(req, -ECANCELED, 0); - req->io_task_work.func = io_futex_complete; io_req_task_work_add(req); return true; } @@ -147,6 +194,55 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +static void io_futex_wakev_fn(struct wake_q_head *wake_q, struct futex_q *q) +{ + struct io_kiocb *req = q->wake_data; + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + + if (!io_futexv_claim(iof)) + return; + if (unlikely(!__futex_wake_mark(q))) + return; + + io_req_set_res(req, 0, 0); + req->io_task_work.func = io_futexv_complete; + io_req_task_work_add(req); +} + +int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv; + int ret; + + /* No flags or mask supported for waitv */ + if (unlikely(sqe->fd || sqe->buf_index || sqe->file_index || + sqe->addr2 || sqe->futex_flags || sqe->addr3)) + return -EINVAL; + + iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + iof->futex_nr = READ_ONCE(sqe->len); + if (!iof->futex_nr || iof->futex_nr > FUTEX_WAITV_MAX) + return -EINVAL; + + futexv = kcalloc(iof->futex_nr, sizeof(*futexv), GFP_KERNEL); + if (!futexv) + return -ENOMEM; + + ret = futex_parse_waitv(futexv, iof->uwaitv, iof->futex_nr, + io_futex_wakev_fn, req); + if (ret) { + kfree(futexv); + return ret; + } + + iof->futexv_owned = 0; + iof->futexv_unqueued = 0; + req->flags |= REQ_F_ASYNC_DATA; + req->async_data = futexv; + return 0; +} + static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) { struct io_futex_data *ifd = container_of(q, struct io_futex_data, q); @@ -171,6 +267,61 @@ static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx) return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT); } +int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); + struct futex_vector *futexv = req->async_data; + struct io_ring_ctx *ctx = req->ctx; + int ret, woken = -1; + + io_ring_submit_lock(ctx, issue_flags); + + ret = futex_wait_multiple_setup(futexv, iof->futex_nr, &woken); + + /* + * Error case, ret is < 0. Mark the request as failed. + */ + if (unlikely(ret < 0)) { + io_ring_submit_unlock(ctx, issue_flags); + req_set_fail(req); + io_req_set_res(req, ret, 0); + kfree(futexv); + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; + return IOU_OK; + } + + /* + * 0 return means that we successfully setup the waiters, and that + * nobody triggered a wakeup while we were doing so. If the wakeup + * happened post setup, the task_work will be run post this issue and + * under the submission lock. 1 means We got woken while setting up, + * let that side do the completion. Note that + * futex_wait_multiple_setup() will have unqueued all the futexes in + * this case. Mark us as having done that already, since this is + * different from normal wakeup. + */ + if (!ret) { + /* + * If futex_wait_multiple_setup() returns 0 for a + * successful setup, then the task state will not be + * runnable. This is fine for the sync syscall, as + * it'll be blocking unless we already got one of the + * futexes woken, but it obviously won't work for an + * async invocation. Mark us runnable again. + */ + __set_current_state(TASK_RUNNING); + hlist_add_head(&req->hash_node, &ctx->futex_list); + } else { + iof->futexv_unqueued = 1; + if (woken != -1) + io_req_set_res(req, woken, 0); + } + + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; +} + int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); diff --git a/io_uring/futex.h b/io_uring/futex.h index ddc9e0d73c52..0847e9e8a127 100644 --- a/io_uring/futex.h +++ b/io_uring/futex.h @@ -3,7 +3,9 @@ #include "cancel.h" int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags); +int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags); int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags); #if defined(CONFIG_FUTEX) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 31a3a421e94d..25a3515a177c 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -459,6 +459,14 @@ const struct io_issue_def io_issue_defs[] = { .issue = io_futex_wake, #else .prep = io_eopnotsupp_prep, +#endif + }, + [IORING_OP_FUTEX_WAITV] = { +#if defined(CONFIG_FUTEX) + .prep = io_futexv_prep, + .issue = io_futexv_wait, +#else + .prep = io_eopnotsupp_prep, #endif }, }; @@ -693,6 +701,9 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_FUTEX_WAKE] = { .name = "FUTEX_WAKE", }, + [IORING_OP_FUTEX_WAITV] = { + .name = "FUTEX_WAITV", + }, }; const char *io_uring_get_opcode(u8 opcode) -- cgit v1.2.3