linux-f2fs-devel.lists.sourceforge.net archive mirror
 help / color / mirror / Atom feed
From: Jaegeuk Kim <jaegeuk@kernel.org>
To: Chao Yu <chao2.yu@samsung.com>
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net
Subject: Re: [f2fs-dev] [PATCH 6/6 v2] f2fs: avoid double lock for cp_rwsem
Date: Tue, 23 Dec 2014 11:08:38 -0800	[thread overview]
Message-ID: <20141223190838.GA13638@jaegeuk-mac02> (raw)
In-Reply-To: <20141223190537.GB12880@jaegeuk-mac02>

Change log from v1:
 o fix description

>From fc897d61c01acc19dba434cd4aa29baeb1537b60 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Thu, 18 Dec 2014 19:32:36 -0800
Subject: [PATCH] f2fs: avoid double lock for cp_rwsem

The __f2fs_add_link is covered by cp_rwsem all the time.
This calls init_inode_metadata, which conducts some acl operations including
memory allocation with GFP_KERNEL previously.
But, under memory pressure, f2fs_write_data_page can be called, which also
grabs cp_rwsem too.

In this case, this incurs a deadlock pointed by Chao.
Thread #1        Thread #2
 down_read
                 down_write
  down_read
 -> here down_read should wait forever.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/acl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 1ccb26b..7f12d28 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 	if (count == 0)
 		return NULL;
 
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	int i;
 
 	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
-- 
2.1.1



  reply	other threads:[~2014-12-23 19:08 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-12-21 16:35 [PATCH 1/6] f2fs: use f2fs_io_info to clean up messy parameters during IO path Jaegeuk Kim
2014-12-21 16:35 ` [PATCH 2/6] f2fs: add f2fs_io_tracer support Jaegeuk Kim
2014-12-21 16:35 ` [PATCH 3/6] f2fs: add key functions for f2fs_io_tracer Jaegeuk Kim
2014-12-21 16:35 ` [PATCH 4/6] f2fs: activate f2fs_trace_pid Jaegeuk Kim
2014-12-21 16:35 ` [PATCH 5/6] f2fs: activate f2fs_trace_ios Jaegeuk Kim
2014-12-21 16:35 ` [PATCH 6/6] f2fs: avoid double lock for cp_rwsem Jaegeuk Kim
2014-12-23  7:01   ` [f2fs-dev] " Chao Yu
2014-12-23  7:40     ` Jaegeuk Kim
2014-12-23  8:58       ` Chao Yu
2014-12-23 19:05         ` Jaegeuk Kim
2014-12-23 19:08           ` Jaegeuk Kim [this message]
2014-12-23  7:00 ` [f2fs-dev] [PATCH 1/6] f2fs: use f2fs_io_info to clean up messy parameters during IO path Chao Yu

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=20141223190838.GA13638@jaegeuk-mac02 \
    --to=jaegeuk@kernel.org \
    --cc=chao2.yu@samsung.com \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /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;
as well as URLs for NNTP newsgroup(s).