Skip to contentSkip to conversation

fs: Return EAGAIN when O_NONBLOCK write should block on frozen fs

PATCH Superseded Jan Kara 2 participants 6 messages Nov 12, 2012 – Dec 5, 2012

Subsystems (8)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Jan Kara

author maintainer
#0 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 9ab1bed..6eb2e30 100644
@@ -1411,7 +1411,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	ssize_t err = 0;
 	size_t count, ocount;
 
-	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 edb25b4..1629e47 100644
@@ -2448,7 +2448,8 @@ cifs_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 78d2837..641df9e 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 1ecf464..028b349 100644
@@ -2118,7 +2118,8 @@ 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 5a4ee77..93ef34d 100644
@@ -2265,7 +2265,8 @@ 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 13e5b47..a5ae831 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 aa473fa..7d8af61 100644
@@ -771,7 +771,8 @@ 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 b33cfc9..2325e95 100644
@@ -1401,6 +1401,16 @@ 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
#1 lore raw

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

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
#2 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 93ef34d..9907243 100644
@@ -2486,6 +2486,9 @@ 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);
 
@@ -2527,6 +2530,7 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 
 		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
 	}
+	sb_end_write(inode->i_sb);
 
 	return ret;
 }
Signature · 1 line
1.7.1
author maintainer
#3 lore raw
In reply to Jan Kara
Quoted 2 lines · Jan Kara

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

Ups, forgot to add version into the subject. This is v3 of the series.

Honza

Quoted 153 lines
---
 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 9ab1bed..6eb2e30 100644
@@ -1411,7 +1411,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	ssize_t err = 0;
 	size_t count, ocount;
 
-	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 edb25b4..1629e47 100644
@@ -2448,7 +2448,8 @@ cifs_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 78d2837..641df9e 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 1ecf464..028b349 100644
@@ -2118,7 +2118,8 @@ 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 5a4ee77..93ef34d 100644
@@ -2265,7 +2265,8 @@ 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 13e5b47..a5ae831 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 aa473fa..7d8af61 100644
@@ -771,7 +771,8 @@ 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 b33cfc9..2325e95 100644
@@ -1401,6 +1401,16 @@ 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 · 6 lines
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Signature · 2 lines
Jan Kara <[email protected]>
SUSE Labs, CR
author maintainer
#5 lore raw
In reply to Jan Kara
Quoted 2 lines · Jan Kara

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

Al, what do you think about these patches? They fix deadlock with BSD
process accounting and fs freezing...

Honza

Quoted 149 lines
---
 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 9ab1bed..6eb2e30 100644
@@ -1411,7 +1411,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	ssize_t err = 0;
 	size_t count, ocount;
 
-	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 edb25b4..1629e47 100644
@@ -2448,7 +2448,8 @@ cifs_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 78d2837..641df9e 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 1ecf464..028b349 100644
@@ -2118,7 +2118,8 @@ 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 5a4ee77..93ef34d 100644
@@ -2265,7 +2265,8 @@ 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 13e5b47..a5ae831 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 aa473fa..7d8af61 100644
@@ -771,7 +771,8 @@ 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 b33cfc9..2325e95 100644
@@ -1401,6 +1401,16 @@ 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
Signature · 2 lines
Jan Kara <[email protected]>
SUSE Labs, CR