linux-api.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Goldwyn Rodrigues <rgoldwyn@suse.de>
To: linux-fsdevel@vger.kernel.org
Cc: jack@suse.com, hch@infradead.org, linux-block@vger.kernel.org,
	axboe@kernel.dk, linux-api@vger.kernel.org,
	viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
	Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH 05/10] fs: return if direct write will trigger writeback
Date: Thu, 15 Jun 2017 10:59:57 -0500	[thread overview]
Message-ID: <20170615160002.17233-6-rgoldwyn@suse.de> (raw)
In-Reply-To: <20170615160002.17233-1-rgoldwyn@suse.de>

From: Goldwyn Rodrigues <rgoldwyn@suse.com>

Find out if the write will trigger a wait due to writeback. If yes,
return -EAGAIN.

Return -EINVAL for buffered AIO: there are multiple causes of
delay such as page locks, dirty throttling logic, page loading
from disk etc. which cannot be taken care of.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
 mm/filemap.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 87aba7698584..c6fd1977a280 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2675,6 +2675,9 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 
 	pos = iocb->ki_pos;
 
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
 	if (limit != RLIM_INFINITY) {
 		if (iocb->ki_pos >= limit) {
 			send_sig(SIGXFSZ, current, 0);
@@ -2743,9 +2746,17 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_SHIFT;
 
-	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
-	if (written)
-		goto out;
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/* If there are pages to writeback, return */
+		if (filemap_range_has_page(inode->i_mapping, pos,
+					   pos + iov_iter_count(from)))
+			return -EAGAIN;
+	} else {
+		written = filemap_write_and_wait_range(mapping, pos,
+							pos + write_len - 1);
+		if (written)
+			goto out;
+	}
 
 	/*
 	 * After a write we want buffered reads to be sure to go to disk to get
-- 
2.12.0

  parent reply	other threads:[~2017-06-15 15:59 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-15 15:59 [PATCH 0/10 v12] No wait AIO Goldwyn Rodrigues
2017-06-15 15:59 ` [PATCH 01/10] fs: Separate out kiocb flags setup based on RWF_* flags Goldwyn Rodrigues
2017-06-15 15:59 ` [PATCH 02/10] fs: Introduce filemap_range_has_page() Goldwyn Rodrigues
     [not found]   ` <20170615160002.17233-3-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-06-15 18:25     ` Andrew Morton
2017-06-15 15:59 ` [PATCH 03/10] fs: Use RWF_* flags for AIO operations Goldwyn Rodrigues
2017-06-15 15:59 ` [PATCH 04/10] fs: Introduce RWF_NOWAIT and FMODE_AIO_NOWAIT Goldwyn Rodrigues
     [not found]   ` <20170615160002.17233-5-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-06-17  4:09     ` Al Viro
2017-06-17 11:53       ` Christoph Hellwig
2017-06-15 15:59 ` Goldwyn Rodrigues [this message]
     [not found] ` <20170615160002.17233-1-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-06-15 15:59   ` [PATCH 06/10] fs: Introduce IOMAP_NOWAIT Goldwyn Rodrigues
2017-06-15 18:25   ` [PATCH 0/10 v12] No wait AIO Andrew Morton
2017-06-15 21:51     ` Goldwyn Rodrigues
     [not found]       ` <1003b3e8-a775-e8ac-d1ca-11055d941a98-l3A5Bk7waGM@public.gmane.org>
2017-06-15 22:01         ` Andrew Morton
     [not found]           ` <20170615150100.52c0387406e6ce5167dc098e-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2017-06-15 23:49             ` Goldwyn Rodrigues
2017-06-16  8:54     ` Jan Kara
2017-06-15 15:59 ` [PATCH 07/10] block: return on congested block device Goldwyn Rodrigues
2017-06-15 16:42   ` Jens Axboe
2017-06-15 16:00 ` [PATCH 08/10] ext4: nowait aio support Goldwyn Rodrigues
2017-06-15 16:00 ` [PATCH 09/10] xfs: " Goldwyn Rodrigues
2017-06-15 16:00 ` [PATCH 10/10] btrfs: " Goldwyn Rodrigues
  -- strict thread matches above, loose matches on Subject: below --
2017-06-06 11:19 [PATCH 0/10 v11] No wait AIO Goldwyn Rodrigues
2017-06-06 11:19 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-06-05  5:35 [PATCH 0/10 v10] No wait AIO Goldwyn Rodrigues
2017-06-05  5:35 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-05-24 16:41 [PATCH 0/10 v9] No wait AIO Goldwyn Rodrigues
     [not found] ` <20170524164150.9492-1-rgoldwyn-l3A5Bk7waGM@public.gmane.org>
2017-05-24 16:41   ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues
2017-05-25  8:32     ` Jan Kara
2017-05-11 19:17 [PATCH 0/10 v8] No wait AIO Goldwyn Rodrigues
2017-05-11 19:17 ` [PATCH 05/10] fs: return if direct write will trigger writeback Goldwyn Rodrigues

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=20170615160002.17233-6-rgoldwyn@suse.de \
    --to=rgoldwyn@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=hch@infradead.org \
    --cc=jack@suse.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=rgoldwyn@suse.com \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [PATCH 05/10] fs: return if direct write will trigger writeback' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).