public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jens Axboe <[email protected]>
To: unlisted-recipients:; (no To-header on input)
Cc: "[email protected]" <[email protected]>,
	[email protected]
Subject: [PATCH] io_uring: enable optimized link handling for IORING_OP_POLL_ADD
Date: Tue, 5 Nov 2019 15:23:09 -0700	[thread overview]
Message-ID: <[email protected]> (raw)

As introduced by commit:

ba816ad61fdf ("io_uring: run dependent links inline if possible")

enable inline dependent link running for poll commands.
io_poll_complete_work() is the most important change, as it allows a
linked sequence of { POLL, READ } (for example) to proceed inline
instead of needing to get punted to another async context. The
submission side only potentially matters for sqthread, but may as well
include that bit.

Signed-off-by: Jens Axboe <[email protected]>

---

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d4ff3e49a78c..d074f3f04a63 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1862,6 +1862,7 @@ static void io_poll_complete_work(struct io_wq_work **workptr)
 	struct io_poll_iocb *poll = &req->poll;
 	struct poll_table_struct pt = { ._key = poll->events };
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_kiocb *nxt = NULL;
 	__poll_t mask = 0;
 
 	if (work->flags & IO_WQ_WORK_CANCEL)
@@ -1888,7 +1889,10 @@ static void io_poll_complete_work(struct io_wq_work **workptr)
 	spin_unlock_irq(&ctx->completion_lock);
 
 	io_cqring_ev_posted(ctx);
-	io_put_req(req, NULL);
+
+	io_put_req(req, &nxt);
+	if (nxt)
+		*workptr = &nxt->work;
 }
 
 static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
@@ -1942,7 +1946,8 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 	add_wait_queue(head, &pt->req->poll.wait);
 }
 
-static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+		       struct io_kiocb **nxt)
 {
 	struct io_poll_iocb *poll = &req->poll;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -2005,7 +2010,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	if (mask) {
 		io_cqring_ev_posted(ctx);
-		io_put_req(req, NULL);
+		io_put_req(req, nxt);
 	}
 	return ipt.error;
 }
@@ -2303,7 +2308,7 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		ret = io_fsync(req, s->sqe, nxt, force_nonblock);
 		break;
 	case IORING_OP_POLL_ADD:
-		ret = io_poll_add(req, s->sqe);
+		ret = io_poll_add(req, s->sqe, nxt);
 		break;
 	case IORING_OP_POLL_REMOVE:
 		ret = io_poll_remove(req, s->sqe);

-- 
Jens Axboe


                 reply	other threads:[~2019-11-05 22:23 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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] \
    /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