public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: [email protected], [email protected]
Cc: [email protected], [email protected], Jens Axboe <[email protected]>
Subject: [PATCH 10/10] io_uring: add support for vectored futex waits
Date: Thu, 20 Jul 2023 16:18:58 -0600	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

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 the a
pointer to a struct futex_waitv array, and sqe->off must now contain the
number of elements in that array.

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.

Signed-off-by: Jens Axboe <[email protected]>
---
 include/uapi/linux/io_uring.h |   1 +
 io_uring/futex.c              | 164 +++++++++++++++++++++++++++++++---
 io_uring/futex.h              |   2 +
 io_uring/opdef.c              |  11 +++
 4 files changed, 168 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 3bd2d765f593..420f38675769 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -238,6 +238,7 @@ enum io_uring_op {
 	IORING_OP_SENDMSG_ZC,
 	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 0114fda797e1..93df54dffaa0 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -14,10 +14,15 @@
 
 struct io_futex {
 	struct file	*file;
-	u32 __user	*uaddr;
+	union {
+		u32 __user			*uaddr;
+		struct futex_waitv __user	*uwaitv;
+	};
 	unsigned int	futex_val;
 	unsigned int	futex_flags;
 	unsigned int	futex_mask;
+	unsigned int	futex_nr;
+	unsigned long	futexv_owned;
 };
 
 struct io_futex_data {
@@ -44,6 +49,13 @@ 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 +64,59 @@ 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;
+	struct io_ring_ctx *ctx = req->ctx;
+	int res = 0;
 
-	/* futex wake already done or in progress */
-	if (!futex_unqueue(&ifd->q))
+	io_tw_lock(ctx, ts);
+
+	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_claimed(struct io_futex *iof)
+{
+	return test_bit(0, &iof->futexv_owned);
+}
+
+static bool io_futexv_claim(struct io_futex *iof)
+{
+	if (test_bit(0, &iof->futexv_owned) ||
+	    test_and_set_bit(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;
 }
@@ -123,7 +172,7 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
 
-	if (unlikely(sqe->fd || sqe->addr2 || sqe->buf_index || sqe->addr3))
+	if (unlikely(sqe->fd || sqe->buf_index || sqe->addr3))
 		return -EINVAL;
 
 	iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -133,6 +182,52 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	if (iof->futex_flags & FUTEX_CMD_MASK)
 		return -EINVAL;
 
+	iof->futexv_owned = 0;
+	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;
+
+	ret = io_futex_prep(req, sqe);
+	if (ret)
+		return ret;
+
+	iof->futex_nr = READ_ONCE(sqe->off);
+	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;
+	}
+
+	req->flags |= REQ_F_ASYNC_DATA;
+	req->async_data = futexv;
 	return 0;
 }
 
@@ -160,6 +255,55 @@ 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);
+
+	/*
+	 * The above call leaves us potentially non-running. 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 is runnable again.
+	 */
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * We got woken while setting up, let that side do the completion
+	 */
+	if (io_futexv_claimed(iof)) {
+skip:
+		io_ring_submit_unlock(ctx, issue_flags);
+		return IOU_ISSUE_SKIP_COMPLETE;
+	}
+
+	/*
+	 * 0 return means that we successfully setup the waiters, and that
+	 * nobody triggered a wakeup while we were doing so. < 0 or 1 return
+	 * is either an error or we got a wakeup while setting up.
+	 */
+	if (!ret) {
+		hlist_add_head(&req->hash_node, &ctx->futex_list);
+		goto skip;
+	}
+
+	io_ring_submit_unlock(ctx, issue_flags);
+	if (ret < 0)
+		req_set_fail(req);
+	else if (woken != -1)
+		ret = woken;
+	io_req_set_res(req, ret, 0);
+	kfree(futexv);
+	req->flags &= ~REQ_F_ASYNC_DATA;
+	return IOU_OK;
+}
+
 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 c9f23c21a031..b9e1e12cac9c 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -443,6 +443,14 @@ 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
 	},
 };
@@ -670,6 +678,9 @@ 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)
-- 
2.40.1


      parent reply	other threads:[~2023-07-20 22:19 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-20 22:18 [PATCHSET v3 0/10] Add io_uring futex/futexv support Jens Axboe
2023-07-20 22:18 ` [PATCH 01/10] futex: Clarify FUTEX2 flags Jens Axboe
2023-07-20 22:18 ` [PATCH 02/10] futex: Extend the " Jens Axboe
2023-07-20 22:18 ` [PATCH 03/10] futex: Flag conversion Jens Axboe
2023-07-20 22:18 ` [PATCH 04/10] futex: factor out the futex wake handling Jens Axboe
2023-07-20 22:18 ` [PATCH 05/10] futex: abstract out a __futex_wake_mark() helper Jens Axboe
2023-07-20 22:18 ` [PATCH 06/10] io_uring: add support for futex wake and wait Jens Axboe
2023-07-21 11:30   ` Peter Zijlstra
2023-07-21 11:37     ` Peter Zijlstra
2023-07-21 14:43       ` Jens Axboe
2023-07-21 15:29         ` Jens Axboe
2023-07-25 13:00           ` Peter Zijlstra
2023-07-25 13:48             ` Jens Axboe
2023-07-25 13:57               ` Jens Axboe
2023-07-25 15:19                 ` Peter Zijlstra
2023-07-25 20:42                   ` Jens Axboe
2023-07-25 21:24                     ` Jens Axboe
2023-07-25 14:06               ` Peter Zijlstra
2023-07-20 22:18 ` [PATCH 07/10] futex: add wake_data to struct futex_q Jens Axboe
2023-07-20 22:18 ` [PATCH 08/10] futex: make futex_parse_waitv() available as a helper Jens Axboe
2023-07-20 22:18 ` [PATCH 09/10] futex: make the vectored futex operations available Jens Axboe
2023-07-20 22:18 ` Jens Axboe [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox