Skip to contentSkip to conversation

Fix hang with BSD process accounting and fs freezing

PATCH RESEND Superseded Jan Kara 1 participant 4 messages Dec 22, 2012

Subsystems (8)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Jan Kara

author maintainer
#0 lore raw

cover Fix hang with BSD process accounting and fs freezing

Hello,

I'm resending my patch series to fix a deadlock when BSD process accounting
is logging into a filesystem that is frozen since I didn't see it in your last pull request. Is there any problem with the patches or you just missed them?

Honza

author maintainer
#1 lore raw

PATCH 1/3 fs: Return EAGAIN when O_NONBLOCK write should block on frozen fs

When user asks for O_NONBLOCK behavior for a file descriptor, return EAGAIN instead of blocking on a frozen filesystem.

---
 fs/btrfs/file.c    |    3 ++-
 fs/cifs/file.c     |    3 ++-
 fs/fuse/file.c     |    3 ++-
 fs/ntfs/file.c     |    3 ++-
 fs/ocfs2/file.c    |    3 ++-
 fs/splice.c        |    3 ++-
 fs/xfs/xfs_file.c  |    3 ++-
 include/linux/fs.h |   10 ++++++++++
 mm/filemap.c       |    3 ++-
 9 files changed, 26 insertions(+), 8 deletions(-)
fs/btrfs/file.c +2 -1
index 77061bf..8418825 100644
@@ -1495,7 +1495,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	size_t count, ocount;
 	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 
 	mutex_lock(&inode->i_mutex);
 
fs/cifs/file.c +2 -1
index 0a6677b..b2c55ff 100644
@@ -2474,7 +2474,8 @@ cifs_pagecache_writev(struct kiocb *iocb, const struct iovec *iov,
 
 	BUG_ON(iocb->ki_pos != pos);
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
fs/fuse/file.c +2 -1
index e21d4d8..13a6d4b 100644
@@ -947,7 +947,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
fs/ntfs/file.c +2 -1
index 5b2d4f0..67fd7f9 100644
@@ -2129,7 +2129,8 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	BUG_ON(iocb->ki_pos != pos);
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 	mutex_lock(&inode->i_mutex);
 	ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
fs/ocfs2/file.c +2 -1
index 37d313e..3898499 100644
@@ -2247,7 +2247,8 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	if (iocb->ki_left == 0)
 		return 0;
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 
 	appending = file->f_flags & O_APPEND ? 1 : 0;
 	direct_io = file->f_flags & O_DIRECT ? 1 : 0;
fs/splice.c +2 -1
index 8890604..5213a9a 100644
@@ -996,7 +996,8 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	};
 	ssize_t ret;
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(out))
+		return -EAGAIN;
 
 	pipe_lock(pipe);
 
fs/xfs/xfs_file.c +2 -1
index 67284ed..8299734 100644
@@ -775,7 +775,8 @@ xfs_file_aio_write(
 	if (ocount == 0)
 		return 0;
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		ret = -EIO;
include/linux/fs.h +10 -0
index 7617ee0..9f5e27c 100644
@@ -1400,6 +1400,16 @@ static inline int sb_start_write_trylock(struct super_block *sb)
 	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
 }
 
+/*
+ * sb_start_write() for writing into a file. When file has O_NONBLOCK set,
+ * we use trylock semantics, otherwise we block on frozen filesystem.
+ */
+static inline int sb_start_file_write(struct file *file)
+{
+	return __sb_start_write(file->f_mapping->host->i_sb, SB_FREEZE_WRITE,
+				!(file->f_flags & O_NONBLOCK));
+}
+
 /**
  * sb_start_pagefault - get write access to a superblock from a page fault
  * @sb: the super we write to
mm/filemap.c +2 -1
index 83efee7..3b2812b 100644
@@ -2527,7 +2527,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	BUG_ON(iocb->ki_pos != pos);
 
-	sb_start_write(inode->i_sb);
+	if (!sb_start_file_write(file))
+		return -EAGAIN;
 	mutex_lock(&inode->i_mutex);
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
Signature · 1 line
1.7.1
author maintainer
#2 lore raw

PATCH 2/3 fs: Fix hang with BSD accounting on frozen filesystem

In reply to Jan Kara

When BSD process accounting is enabled and logs information to a filesystem which gets frozen, system easily becomes unusable because each attempt to account process information blocks. Thus e.g. every task gets blocked in exit.

It seems better to drop accounting information (which can already happen when filesystem is running out of space) instead of locking system up. So we open the accounting file with O_NONBLOCK.

---
 kernel/acct.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)
kernel/acct.c +2 -1
index 051e071..a061116 100644
@@ -201,7 +201,8 @@ static int acct_on(struct filename *pathname)
 	struct bsd_acct_struct *acct = NULL;
 
 	/* Difference from BSD - they don't do O_APPEND */
-	file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+	file = file_open_name(pathname,
+			      O_WRONLY|O_APPEND|O_LARGEFILE|O_NONBLOCK, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
Signature · 1 line
1.7.1
author maintainer
#3 lore raw

PATCH 3/3 ocfs2: Add freeze protection to ocfs2_file_splice_write()

In reply to Jan Kara

ocfs2_file_splice_write() was missed when adding freeze protection to all write paths. Fix that.

CC Joel Becker <[email protected]>
CC ocfs2-devel at oss.oracle.com
---
 fs/ocfs2/file.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)
fs/ocfs2/file.c +4 -0
index 3898499..1f6916c 100644
@@ -2468,6 +2468,9 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 			out->f_path.dentry->d_name.len,
 			out->f_path.dentry->d_name.name, len);
 
+	if (!sb_start_file_write(out))
+		return -EAGAIN;
+
 	if (pipe->inode)
 		mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_PARENT);
 
@@ -2506,6 +2509,7 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 
 		balance_dirty_pages_ratelimited(mapping);
 	}
+	sb_end_write(inode->i_sb);
 
 	return ret;
 }
Signature · 1 line
1.7.1