[PATCH 07/16] vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode

[PATCH 07/16] vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode

[Jan Kara]

Introduce new function for generic inode syncing (vfs_fsync_range) and use
it from fsync() path. Introduce also new helper for syncing after a sync
write (generic_write_sync) using the generic function.

Use these new helpers for syncing from generic VFS functions. This makes
O_SYNC writes to block devices acquire i_mutex for syncing. If we really
care about this, we can make block_fsync() drop the i_mutex and reacquire
it before it returns.

CC: Evgeniy Polyakov <zbr@ioremap.net>
CC: ocfs2-devel@oss.oracle.com
CC: Joel Becker <joel.becker@oracle.com>
CC: Felix Blyakher <felixb@sgi.com>
CC: xfs@oss.sgi.com
CC: Anton Altaparmakov <aia21@cantab.net>
CC: linux-ntfs-dev@lists.sourceforge.net
CC: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
CC: linux-ext4@vger.kernel.org
CC: tytso@mit.edu
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/splice.c        |   22 +++++---------------
 fs/sync.c          |   55 +++++++++++++++++++++++++++++++++++++++++++++------
 include/linux/fs.h |    3 ++
 mm/filemap.c       |   18 +++++-----------
 4 files changed, 63 insertions(+), 35 deletions(-)

diff --git a/fs/splice.c b/fs/splice.c
index 73766d2..8190237 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -976,25 +976,15 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 	if (ret > 0) {
 		unsigned long nr_pages;
+		int err;
 
-		*ppos += ret;
 		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-		/*
-		 * If file or inode is SYNC and we actually wrote some data,
-		 * sync it.
-		 */
-		if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
-			int err;
-
-			mutex_lock(&inode->i_mutex);
-			err = generic_osync_inode(inode, mapping,
-						  OSYNC_METADATA|OSYNC_DATA);
-			mutex_unlock(&inode->i_mutex);
-
-			if (err)
-				ret = err;
-		}
+		err = generic_write_sync(out, *ppos, ret);
+		if (err)
+			ret = err;
+		else
+			*ppos += ret;
 		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
 	}
 
diff --git a/fs/sync.c b/fs/sync.c
index 3422ba6..6fe72e6 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -176,19 +176,23 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
 }
 
 /**
- * vfs_fsync - perform a fsync or fdatasync on a file
+ * vfs_fsync_range - helper to sync a range of data & metadata to disk
  * @file:		file to sync
  * @dentry:		dentry of @file
- * @data:		only perform a fdatasync operation
+ * @start:		offset in bytes of the beginning of data range to sync
+ * @end:		offset in bytes of the end of data range (inclusive)
+ * @datasync:		perform only datasync
  *
- * Write back data and metadata for @file to disk.  If @datasync is
- * set only metadata needed to access modified file data is written.
+ * Write back data in range @start..@end and metadata for @file to disk.  If
+ * @datasync is set only metadata needed to access modified file data is
+ * written.
  *
  * In case this function is called from nfsd @file may be %NULL and
  * only @dentry is set.  This can only happen when the filesystem
  * implements the export_operations API.
  */
-int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
+int vfs_fsync_range(struct file *file, struct dentry *dentry, loff_t start,
+		    loff_t end, int datasync)
 {
 	const struct file_operations *fop;
 	struct address_space *mapping;
@@ -212,7 +216,7 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 		goto out;
 	}
 
-	ret = filemap_fdatawrite(mapping);
+	ret = filemap_fdatawrite_range(mapping, start, end);
 
 	/*
 	 * We need to protect against concurrent writers, which could cause
@@ -223,12 +227,32 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 	if (!ret)
 		ret = err;
 	mutex_unlock(&mapping->host->i_mutex);
-	err = filemap_fdatawait(mapping);
+
+	err = filemap_fdatawait_range(mapping, start, end);
 	if (!ret)
 		ret = err;
 out:
 	return ret;
 }
+EXPORT_SYMBOL(vfs_fsync_range);
+
+/**
+ * vfs_fsync - perform a fsync or fdatasync on a file
+ * @file:		file to sync
+ * @dentry:		dentry of @file
+ * @datasync:		only perform a fdatasync operation
+ *
+ * Write back data and metadata for @file to disk.  If @datasync is
+ * set only metadata needed to access modified file data is written.
+ *
+ * In case this function is called from nfsd @file may be %NULL and
+ * only @dentry is set.  This can only happen when the filesystem
+ * implements the export_operations API.
+ */
+int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+	return vfs_fsync_range(file, dentry, 0, LLONG_MAX, datasync);
+}
 EXPORT_SYMBOL(vfs_fsync);
 
 static int do_fsync(unsigned int fd, int datasync)
@@ -254,6 +278,23 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
 	return do_fsync(fd, 1);
 }
 
+/**
+ * generic_write_sync - perform syncing after a write if file / inode is sync
+ * @file:	file to which the write happened
+ * @pos:	offset where the write started
+ * @count:	length of the write
+ *
+ * This is just a simple wrapper about our general syncing function.
+ */
+int generic_write_sync(struct file *file, loff_t pos, loff_t count)
+{
+	if (!(file->f_flags & O_SYNC) && !IS_SYNC(file->f_mapping->host))
+		return 0;
+	return vfs_fsync_range(file, file->f_path.dentry, pos,
+			       pos + count - 1, 1);
+}
+EXPORT_SYMBOL(generic_write_sync);
+
 /*
  * sys_sync_file_range() permits finely controlled syncing over a segment of
  * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc7f0f1..18acaec 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2088,7 +2088,10 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping,
 extern int filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end);
 
+extern int vfs_fsync_range(struct file *file, struct dentry *dentry,
+			   loff_t start, loff_t end, int datasync);
 extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
+extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
 extern void sync_supers(void);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
diff --git a/mm/filemap.c b/mm/filemap.c
index 3955f7e..70988a1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -39,11 +39,10 @@
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
-#include <linux/buffer_head.h> /* for generic_osync_inode */
+#include <linux/buffer_head.h> /* for try_to_free_buffers */
 
 #include <asm/mman.h>
 
-
 /*
  * Shared mappings implemented 30.11.1994. It's not fully working yet,
  * though.
@@ -2480,19 +2479,16 @@ ssize_t device_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
 	ssize_t ret;
 
 	BUG_ON(iocb->ki_pos != pos);
 
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 
-	if ((ret > 0 || ret == -EIOCBQUEUED) &&
-	    ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+	if (ret > 0 || ret == -EIOCBQUEUED) {
 		ssize_t err;
 
-		err = sync_page_range_nolock(inode, mapping, pos, ret);
+		err = generic_write_sync(file, pos, ret);
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
@@ -2515,8 +2511,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
+	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
 	BUG_ON(iocb->ki_pos != pos);
@@ -2525,11 +2520,10 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
-	if ((ret > 0 || ret == -EIOCBQUEUED) &&
-	    ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+	if (ret > 0 || ret == -EIOCBQUEUED) {
 		ssize_t err;
 
-		err = sync_page_range(inode, mapping, pos, ret);
+		err = generic_write_sync(file, pos, ret);
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
-- 
1.6.0.2

[PATCH 08/16] ext2: Update comment about generic_osync_inode

[Jan Kara]

We rely on generic_write_sync() now.

CC: linux-ext4@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext2/inode.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index e271303..1c1638f 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -482,7 +482,7 @@ static int ext2_alloc_branch(struct inode *inode,
 		unlock_buffer(bh);
 		mark_buffer_dirty_inode(bh, inode);
 		/* We used to sync bh here if IS_SYNC(inode).
-		 * But we now rely upon generic_osync_inode()
+		 * But we now rely upon generic_write_sync()
 		 * and b_inode_buffers.  But not for directories.
 		 */
 		if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
-- 
1.6.0.2

[PATCH 09/16] ext3: Remove syncing logic from ext3_file_write

[Jan Kara]

Syncing is now properly done by generic_file_aio_write() so no special logic is
needed in ext3.

CC: linux-ext4@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext3/file.c |   61 +-------------------------------------------------------
 1 files changed, 1 insertions(+), 60 deletions(-)

diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 5b49704..51fee5f 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -51,71 +51,12 @@ static int ext3_release_file (struct inode * inode, struct file * filp)
 	return 0;
 }
 
-static ssize_t
-ext3_file_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_path.dentry->d_inode;
-	ssize_t ret;
-	int err;
-
-	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
-
-	/*
-	 * Skip flushing if there was an error, or if nothing was written.
-	 */
-	if (ret <= 0)
-		return ret;
-
-	/*
-	 * If the inode is IS_SYNC, or is O_SYNC and we are doing data
-	 * journalling then we need to make sure that we force the transaction
-	 * to disk to keep all metadata uptodate synchronously.
-	 */
-	if (file->f_flags & O_SYNC) {
-		/*
-		 * If we are non-data-journaled, then the dirty data has
-		 * already been flushed to backing store by generic_osync_inode,
-		 * and the inode has been flushed too if there have been any
-		 * modifications other than mere timestamp updates.
-		 *
-		 * Open question --- do we care about flushing timestamps too
-		 * if the inode is IS_SYNC?
-		 */
-		if (!ext3_should_journal_data(inode))
-			return ret;
-
-		goto force_commit;
-	}
-
-	/*
-	 * So we know that there has been no forced data flush.  If the inode
-	 * is marked IS_SYNC, we need to force one ourselves.
-	 */
-	if (!IS_SYNC(inode))
-		return ret;
-
-	/*
-	 * Open question #2 --- should we force data to disk here too?  If we
-	 * don't, the only impact is that data=writeback filesystems won't
-	 * flush data to disk automatically on IS_SYNC, only metadata (but
-	 * historically, that is what ext2 has done.)
-	 */
-
-force_commit:
-	err = ext3_force_commit(inode->i_sb);
-	if (err)
-		return err;
-	return ret;
-}
-
 const struct file_operations ext3_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= generic_file_aio_read,
-	.aio_write	= ext3_file_write,
+	.aio_write	= generic_file_aio_write,
 	.unlocked_ioctl	= ext3_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext3_compat_ioctl,
-- 
1.6.0.2

[PATCH 10/16] ext4: Remove syncing logic from ext4_file_write

[Jan Kara]

The syncing is now properly handled by generic_file_aio_write() so
no special ext4 code is needed.

CC: linux-ext4@vger.kernel.org
CC: tytso@mit.edu
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext4/file.c |   53 ++---------------------------------------------------
 1 files changed, 2 insertions(+), 51 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3f1873f..aafe432 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -58,10 +58,7 @@ static ssize_t
 ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_path.dentry->d_inode;
-	ssize_t ret;
-	int err;
+	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
 
 	/*
 	 * If we have encountered a bitmap-format file, the size limit
@@ -81,53 +78,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
-	/*
-	 * Skip flushing if there was an error, or if nothing was written.
-	 */
-	if (ret <= 0)
-		return ret;
-
-	/*
-	 * If the inode is IS_SYNC, or is O_SYNC and we are doing data
-	 * journalling then we need to make sure that we force the transaction
-	 * to disk to keep all metadata uptodate synchronously.
-	 */
-	if (file->f_flags & O_SYNC) {
-		/*
-		 * If we are non-data-journaled, then the dirty data has
-		 * already been flushed to backing store by generic_osync_inode,
-		 * and the inode has been flushed too if there have been any
-		 * modifications other than mere timestamp updates.
-		 *
-		 * Open question --- do we care about flushing timestamps too
-		 * if the inode is IS_SYNC?
-		 */
-		if (!ext4_should_journal_data(inode))
-			return ret;
-
-		goto force_commit;
-	}
-
-	/*
-	 * So we know that there has been no forced data flush.  If the inode
-	 * is marked IS_SYNC, we need to force one ourselves.
-	 */
-	if (!IS_SYNC(inode))
-		return ret;
-
-	/*
-	 * Open question #2 --- should we force data to disk here too?  If we
-	 * don't, the only impact is that data=writeback filesystems won't
-	 * flush data to disk automatically on IS_SYNC, only metadata (but
-	 * historically, that is what ext2 has done.)
-	 */
-
-force_commit:
-	err = ext4_force_commit(inode->i_sb);
-	if (err)
-		return err;
-	return ret;
+	return generic_file_aio_write(iocb, iov, nr_segs, pos);
 }
 
 static struct vm_operations_struct ext4_file_vm_ops = {
-- 
1.6.0.2