public inbox for [email protected]
 help / color / mirror / Atom feed
From: Pavel Begunkov <[email protected]>
To: [email protected]
Cc: Jens Axboe <[email protected]>, Pavel Begunkov <[email protected]>
Subject: [PATCH 3/4] io_uring: clusterise ki_flags access in rw_prep
Date: Mon, 18 Oct 2021 00:29:35 +0000	[thread overview]
Message-ID: <6b5cadc21f4124f037861d12af6aa99066016fe7.1634516914.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>

ioprio setup doesn't depend on other fields that are modified in
io_prep_rw() and we can move it down in the function without worrying
about performance. It's useful as it makes iocb->ki_flags
accesses/modifications closer together, so it's more likely the compiler
will cache it in a register and avoid extra reloads.

Signed-off-by: Pavel Begunkov <[email protected]>
---
 fs/io_uring.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d7f38074211b..4507b711a688 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2845,16 +2845,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
 		req->flags |= REQ_F_NOWAIT;
 
-	ioprio = READ_ONCE(sqe->ioprio);
-	if (ioprio) {
-		ret = ioprio_check_cap(ioprio);
-		if (ret)
-			return ret;
-
-		kiocb->ki_ioprio = ioprio;
-	} else
-		kiocb->ki_ioprio = get_current_ioprio();
-
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
 			return -EOPNOTSUPP;
@@ -2868,6 +2858,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		kiocb->ki_complete = io_complete_rw;
 	}
 
+	ioprio = READ_ONCE(sqe->ioprio);
+	if (ioprio) {
+		ret = ioprio_check_cap(ioprio);
+		if (ret)
+			return ret;
+
+		kiocb->ki_ioprio = ioprio;
+	} else {
+		kiocb->ki_ioprio = get_current_ioprio();
+	}
+
 	req->imu = NULL;
 	req->rw.addr = READ_ONCE(sqe->addr);
 	req->rw.len = READ_ONCE(sqe->len);
-- 
2.33.1


  parent reply	other threads:[~2021-10-18  0:29 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-18  0:29 [PATCH 0/4] for-next cleanups Pavel Begunkov
2021-10-18  0:29 ` [PATCH 1/4] io_uring: clean up timeout async_data allocation Pavel Begunkov
2021-10-18  0:29 ` [PATCH 2/4] io_uring: kill unused param from io_file_supports_nowait Pavel Begunkov
2021-10-18  0:29 ` Pavel Begunkov [this message]
2021-10-18  0:29 ` [PATCH 4/4] io_uring: typed ->async_data Pavel Begunkov

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 \
    --in-reply-to=6b5cadc21f4124f037861d12af6aa99066016fe7.1634516914.git.asml.silence@gmail.com \
    [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