Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: linux-aio@kvack.org, linux-block@vger.kernel.org,
	linux-api@vger.kernel.org
Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com,
	jannh@google.com, viro@ZenIV.linux.org.uk,
	Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 09/19] io_uring: use fget/fput_many() for file references
Date: Fri,  8 Feb 2019 10:34:13 -0700
Message-ID: <20190208173423.27014-10-axboe@kernel.dk> (raw)
In-Reply-To: <20190208173423.27014-1-axboe@kernel.dk>

Add a separate io_submit_state structure, to cache some of the things
we need for IO submission.

One such example is file reference batching. io_submit_state. We get as
many references as the number of sqes we are submitting, and drop
unused ones if we end up switching files. The assumption here is that
we're usually only dealing with one fd, and if there are multiple,
hopefuly they are at least somewhat ordered. Could trivially be extended
to cover multiple fds, if needed.

On the completion side we do the same thing, except this is trivially
done just locally in io_iopoll_reap().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 142 ++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 121 insertions(+), 21 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 036230ebd33d..b7b8e9dd0c7a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -144,6 +144,19 @@ struct io_kiocb {
 #define IO_PLUG_THRESHOLD		2
 #define IO_IOPOLL_BATCH			8
 
+struct io_submit_state {
+	struct blk_plug plug;
+
+	/*
+	 * File reference cache
+	 */
+	struct file *file;
+	unsigned int fd;
+	unsigned int has_refs;
+	unsigned int used_refs;
+	unsigned int ios_left;
+};
+
 static struct kmem_cache *req_cachep;
 
 static const struct file_operations io_uring_fops;
@@ -304,9 +317,11 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			       struct list_head *done)
 {
 	void *reqs[IO_IOPOLL_BATCH];
+	int file_count, to_free;
+	struct file *file = NULL;
 	struct io_kiocb *req;
-	int to_free = 0;
 
+	file_count = to_free = 0;
 	while (!list_empty(done)) {
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
@@ -316,12 +331,28 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		reqs[to_free++] = req;
 		(*nr_events)++;
 
-		fput(req->rw.ki_filp);
+		/*
+		 * Batched puts of the same file, to avoid dirtying the
+		 * file usage count multiple times, if avoidable.
+		 */
+		if (!file) {
+			file = req->rw.ki_filp;
+			file_count = 1;
+		} else if (file == req->rw.ki_filp) {
+			file_count++;
+		} else {
+			fput_many(file, file_count);
+			file = req->rw.ki_filp;
+			file_count = 1;
+		}
+
 		if (to_free == ARRAY_SIZE(reqs))
 			io_free_req_many(ctx, reqs, &to_free);
 	}
 	io_commit_cqring(ctx);
 
+	if (file)
+		fput_many(file, file_count);
 	io_free_req_many(ctx, reqs, &to_free);
 }
 
@@ -502,6 +533,48 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
 		list_add_tail(&req->list, &ctx->poll_list);
 }
 
+static void io_file_put(struct io_submit_state *state, struct file *file)
+{
+	if (!state) {
+		fput(file);
+	} else if (state->file) {
+		int diff = state->has_refs - state->used_refs;
+
+		if (diff)
+			fput_many(state->file, diff);
+		state->file = NULL;
+	}
+}
+
+/*
+ * Get as many references to a file as we have IOs left in this submission,
+ * assuming most submissions are for one file, or at least that each file
+ * has more than one submission.
+ */
+static struct file *io_file_get(struct io_submit_state *state, int fd)
+{
+	if (!state)
+		return fget(fd);
+
+	if (state->file) {
+		if (state->fd == fd) {
+			state->used_refs++;
+			state->ios_left--;
+			return state->file;
+		}
+		io_file_put(state, NULL);
+	}
+	state->file = fget_many(fd, state->ios_left);
+	if (!state->file)
+		return NULL;
+
+	state->fd = fd;
+	state->has_refs = state->ios_left;
+	state->used_refs = 1;
+	state->ios_left--;
+	return state->file;
+}
+
 /*
  * If we tracked the file through the SCM inflight mechanism, we could support
  * any file. For now, just ensure that anything potentially problematic is done
@@ -520,7 +593,7 @@ static bool io_file_supports_async(struct file *file)
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
-		      bool force_nonblock)
+		      bool force_nonblock, struct io_submit_state *state)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct kiocb *kiocb = &req->rw;
@@ -532,7 +605,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		return 0;
 
 	fd = READ_ONCE(sqe->fd);
-	kiocb->ki_filp = fget(fd);
+	kiocb->ki_filp = io_file_get(state, fd);
 	if (unlikely(!kiocb->ki_filp))
 		return -EBADF;
 	if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
@@ -576,7 +649,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	}
 	return 0;
 out_fput:
-	fput(kiocb->ki_filp);
+	/* in case of error, we didn't use this file reference. drop it. */
+	if (state)
+		state->used_refs--;
+	io_file_put(state, kiocb->ki_filp);
 	return ret;
 }
 
@@ -622,7 +698,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
 }
 
 static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
-		       bool force_nonblock)
+		       bool force_nonblock, struct io_submit_state *state)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -630,7 +706,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	struct file *file;
 	ssize_t ret;
 
-	ret = io_prep_rw(req, s->sqe, force_nonblock);
+	ret = io_prep_rw(req, s->sqe, force_nonblock, state);
 	if (ret)
 		return ret;
 	file = kiocb->ki_filp;
@@ -666,7 +742,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
 }
 
 static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
-			bool force_nonblock)
+			bool force_nonblock, struct io_submit_state *state)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -674,7 +750,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	struct file *file;
 	ssize_t ret;
 
-	ret = io_prep_rw(req, s->sqe, force_nonblock);
+	ret = io_prep_rw(req, s->sqe, force_nonblock, state);
 	if (ret)
 		return ret;
 	/* Hold on to the file for -EAGAIN */
@@ -773,7 +849,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 }
 
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			   const struct sqe_submit *s, bool force_nonblock)
+			   const struct sqe_submit *s, bool force_nonblock,
+			   struct io_submit_state *state)
 {
 	ssize_t ret;
 	int opcode;
@@ -788,10 +865,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		ret = io_nop(req, req->user_data);
 		break;
 	case IORING_OP_READV:
-		ret = io_read(req, s, force_nonblock);
+		ret = io_read(req, s, force_nonblock, state);
 		break;
 	case IORING_OP_WRITEV:
-		ret = io_write(req, s, force_nonblock);
+		ret = io_write(req, s, force_nonblock, state);
 		break;
 	case IORING_OP_FSYNC:
 		ret = io_fsync(req, s->sqe, force_nonblock);
@@ -843,7 +920,7 @@ static void io_sq_wq_submit_work(struct work_struct *work)
 	s->needs_lock = true;
 
 	do {
-		ret = __io_submit_sqe(ctx, req, s, false);
+		ret = __io_submit_sqe(ctx, req, s, false, NULL);
 		/*
 		 * We can get EAGAIN for polled IO even though we're forcing
 		 * a sync submission from here, since we can't wait for
@@ -864,7 +941,8 @@ static void io_sq_wq_submit_work(struct work_struct *work)
 	}
 }
 
-static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
+static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s,
+			 struct io_submit_state *state)
 {
 	struct io_kiocb *req;
 	ssize_t ret;
@@ -879,7 +957,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
 
 	req->rw.ki_filp = NULL;
 
-	ret = __io_submit_sqe(ctx, req, s, true);
+	ret = __io_submit_sqe(ctx, req, s, true, state);
 	if (ret == -EAGAIN) {
 		memcpy(&req->submit, s, sizeof(*s));
 		INIT_WORK(&req->work, io_sq_wq_submit_work);
@@ -892,6 +970,26 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
 	return ret;
 }
 
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void io_submit_state_end(struct io_submit_state *state)
+{
+	blk_finish_plug(&state->plug);
+	io_file_put(state, NULL);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void io_submit_state_start(struct io_submit_state *state,
+				  struct io_ring_ctx *ctx, unsigned max_ios)
+{
+	blk_start_plug(&state->plug);
+	state->file = NULL;
+	state->ios_left = max_ios;
+}
+
 static void io_commit_sqring(struct io_ring_ctx *ctx)
 {
 	struct io_sq_ring *ring = ctx->sq_ring;
@@ -954,11 +1052,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
+	struct io_submit_state state, *statep = NULL;
 	int i, ret = 0, submit = 0;
-	struct blk_plug plug;
 
-	if (to_submit > IO_PLUG_THRESHOLD)
-		blk_start_plug(&plug);
+	if (to_submit > IO_PLUG_THRESHOLD) {
+		io_submit_state_start(&state, ctx, to_submit);
+		statep = &state;
+	}
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
@@ -969,7 +1069,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		s.has_user = true;
 		s.needs_lock = false;
 
-		ret = io_submit_sqe(ctx, &s);
+		ret = io_submit_sqe(ctx, &s, statep);
 		if (ret) {
 			io_drop_sqring(ctx);
 			break;
@@ -979,8 +1079,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 	}
 	io_commit_sqring(ctx);
 
-	if (to_submit > IO_PLUG_THRESHOLD)
-		blk_finish_plug(&plug);
+	if (statep)
+		io_submit_state_end(statep);
 
 	return submit ? submit : ret;
 }
-- 
2.17.1


  parent reply index

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-08 17:34 [PATCHSET v13] io_uring IO interface Jens Axboe
2019-02-08 17:34 ` [PATCH 01/19] fs: add an iopoll method to struct file_operations Jens Axboe
2019-02-09  9:20   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 02/19] block: wire up block device iopoll method Jens Axboe
2019-02-09  9:22   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 03/19] block: add bio_set_polled() helper Jens Axboe
2019-02-09  9:24   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 04/19] iomap: wire up the iopoll method Jens Axboe
2019-02-09  9:25   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 05/19] Add io_uring IO interface Jens Axboe
2019-02-08 22:12   ` Jann Horn
2019-02-09  4:15     ` Jens Axboe
2019-02-12 21:42       ` Jann Horn
2019-02-12 22:03         ` Jens Axboe
2019-02-12 22:06           ` Jens Axboe
2019-02-12 22:40             ` Jann Horn
2019-02-12 22:45               ` Jens Axboe
2019-02-12 22:52                 ` Jens Axboe
2019-02-12 22:57                   ` Jann Horn
2019-02-12 23:00                     ` Jens Axboe
2019-02-12 23:11                       ` Jann Horn
2019-02-12 23:19                         ` Jens Axboe
2019-02-12 23:28                           ` Jann Horn
2019-02-12 23:46                             ` Jens Axboe
2019-02-12 23:53                               ` Jens Axboe
2019-02-13  0:07                                 ` Andy Lutomirski
2019-02-13  0:14                                   ` Jann Horn
2019-02-13  0:24                                   ` Jens Axboe
2019-02-09  9:35   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 06/19] io_uring: add fsync support Jens Axboe
2019-02-08 22:36   ` Jann Horn
2019-02-08 23:31     ` Jens Axboe
2019-02-09  9:37   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 07/19] io_uring: support for IO polling Jens Axboe
2019-02-09  9:39   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 08/19] fs: add fget_many() and fput_many() Jens Axboe
2019-02-09  9:41   ` Hannes Reinecke
2019-02-08 17:34 ` Jens Axboe [this message]
2019-02-09  9:42   ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Hannes Reinecke
2019-02-08 17:34 ` [PATCH 10/19] io_uring: batch io_kiocb allocation Jens Axboe
2019-02-09  9:43   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-02-09  9:45   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 12/19] io_uring: add support for pre-mapped user IO buffers Jens Axboe
2019-02-08 22:54   ` Jann Horn
2019-02-08 23:38     ` Jens Axboe
2019-02-09 16:50       ` Jens Axboe
2019-02-09  9:48   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 13/19] net: split out functions related to registering inflight socket files Jens Axboe
2019-02-08 19:49   ` David Miller
2019-02-08 19:51     ` Jens Axboe
2019-02-09  9:49   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 14/19] io_uring: add file set registration Jens Axboe
2019-02-08 20:26   ` Jann Horn
2019-02-09  0:16     ` Jens Axboe
2019-02-09  9:50   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 15/19] io_uring: add submission polling Jens Axboe
2019-02-09  9:53   ` Hannes Reinecke
2019-02-08 17:34 ` [PATCH 16/19] io_uring: add io_kiocb ref count Jens Axboe
2019-02-08 17:34 ` [PATCH 17/19] io_uring: add support for IORING_OP_POLL Jens Axboe
2019-02-08 17:34 ` [PATCH 18/19] io_uring: allow workqueue item to handle multiple buffered requests Jens Axboe
2019-02-08 17:34 ` [PATCH 19/19] io_uring: add io_uring_event cache hit information Jens Axboe
2019-02-09 21:13 [PATCHSET v14] io_uring IO interface Jens Axboe
2019-02-09 21:13 ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Jens Axboe
2019-02-11 19:00 [PATCHSET v15] io_uring IO interface Jens Axboe
2019-02-11 19:00 ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Jens Axboe

Reply instructions:

You may reply publically 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 \
    --in-reply-to=20190208173423.27014-10-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=avi@scylladb.com \
    --cc=hch@lst.de \
    --cc=jannh@google.com \
    --cc=jmoyer@redhat.com \
    --cc=linux-aio@kvack.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=viro@ZenIV.linux.org.uk \
    /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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org linux-block@archiver.kernel.org
	public-inbox-index linux-block


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/ public-inbox