linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dmitry Monakhov <dmonakhov@openvz.org>
To: linux-kernel@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, viro@zeniv.linux.org.uk,
	Dmitry Monakhov <dmonakhov@openvz.org>
Subject: [PATCH] fs: fix differed error reporting
Date: Thu, 11 Apr 2013 16:47:59 +0400	[thread overview]
Message-ID: <1365684479-29187-1-git-send-email-dmonakhov@openvz.org> (raw)

There are two convenient ways to report errors to userspace
1) retun error to original syscall for example write(2)
2) mark mapping with error flag and return it on later fsync(2)

Second one is broken if (mapping->nrpages == 0)
This is real-life situation because after error pages are likey
to be truncated or invalidated.

We have to return an error regardless to number of pages in the mapping.

#Original testcase: git@github.com:dmonakhov/xfstests.git
MOUNT_OPTIONS="-b1024"
./check shared/305

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
---
 mm/filemap.c |   29 +++++++++++++++++++++--------
 1 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index e1979fd..ca47f0b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -184,6 +184,17 @@ static int sleep_on_page_killable(void *word)
 	return fatal_signal_pending(current) ? -EINTR : 0;
 }
 
+static int filemap_check_errors(struct address_space *mapping)
+{
+	int ret = 0;
+	/* Check for outstanding write errors */
+	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+		ret = -ENOSPC;
+	if (test_and_clear_bit(AS_EIO, &mapping->flags))
+		ret = -EIO;
+	return ret;
+}
+
 /**
  * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
  * @mapping:	address space structure to write
@@ -265,10 +276,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 	pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;
 	struct pagevec pvec;
 	int nr_pages;
-	int ret = 0;
+	int ret2, ret = 0;
 
 	if (end_byte < start_byte)
-		return 0;
+		goto out;
 
 	pagevec_init(&pvec, 0);
 	while ((index <= end) &&
@@ -291,12 +302,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-
-	/* Check for outstanding write errors */
-	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
-		ret = -ENOSPC;
-	if (test_and_clear_bit(AS_EIO, &mapping->flags))
-		ret = -EIO;
+out:
+	ret2 = filemap_check_errors(mapping);
+	if (!ret)
+		ret = ret2;
 
 	return ret;
 }
@@ -337,6 +346,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 			if (!err)
 				err = err2;
 		}
+	} else {
+		err = filemap_check_errors(mapping);
 	}
 	return err;
 }
@@ -368,6 +379,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 			if (!err)
 				err = err2;
 		}
+	} else {
+		err = filemap_check_errors(mapping);
 	}
 	return err;
 }
-- 
1.7.1

             reply	other threads:[~2013-04-11 12:47 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-11 12:47 Dmitry Monakhov [this message]
2013-04-15 14:53 ` [PATCH] fs: fix differed error reporting Jan Kara

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=1365684479-29187-1-git-send-email-dmonakhov@openvz.org \
    --to=dmonakhov@openvz.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@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
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).