Merge branch 'osync_cleanup' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6

* 'osync_cleanup' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6:
  fsync: wait for data writeout completion before calling ->fsync
  vfs: Remove generic_osync_inode() and sync_page_range{_nolock}()
  fat: Opencode sync_page_range_nolock()
  pohmelfs: Use new syncing helper
  xfs: Convert sync_page_range() to simple filemap_write_and_wait_range()
  ocfs2: Update syncing after splicing to match generic version
  ntfs: Use new syncing helpers and update comments
  ext4: Remove syncing logic from ext4_file_write
  ext3: Remove syncing logic from ext3_file_write
  ext2: Update comment about generic_osync_inode
  vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode
  vfs: Rename generic_file_aio_write_nolock
  ocfs2: Use __generic_file_aio_write instead of generic_file_aio_write_nolock
  pohmelfs: Use __generic_file_aio_write instead of generic_file_aio_write_nolock
  vfs: Remove syncing from generic_file_direct_write() and generic_file_buffered_write()
  vfs: Export __generic_file_aio_write() and add some comments
  vfs: Introduce filemap_fdatawait_range

drivers/char/raw.c

@@ -246,7 +246,7 @@ static const struct file_operations raw_fops = {
 	.read	=	do_sync_read,
 	.aio_read = 	generic_file_aio_read,
 	.write	=	do_sync_write,
-	.aio_write = 	generic_file_aio_write_nolock,
+	.aio_write =	blkdev_aio_write,
 	.open	=	raw_open,
 	.release=	raw_release,
 	.ioctl	=	raw_ioctl,

drivers/staging/pohmelfs/inode.c

@@ -921,16 +921,16 @@ ssize_t pohmelfs_write(struct file *file, const char __user *buf,
 	if (ret)
 		goto err_out_unlock;
 
-	ret = generic_file_aio_write_nolock(&kiocb, &iov, 1, pos);
+	ret = __generic_file_aio_write(&kiocb, &iov, 1, &kiocb.ki_pos);
 	*ppos = kiocb.ki_pos;
 
 	mutex_unlock(&inode->i_mutex);
 	WARN_ON(ret < 0);
 
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+	if (ret > 0) {
 		ssize_t err;
 
-		err = sync_page_range(inode, mapping, pos, ret);
+		err = generic_write_sync(file, pos, ret);
 		if (err < 0)
 			ret = err;
 		WARN_ON(ret < 0);

fs/block_dev.c

@@ -1404,6 +1404,33 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
+/*
+ * Write data to the block device.  Only intended for the block device itself
+ * and the raw driver which basically is a fake block device.
+ *
+ * Does not take i_mutex for the write and thus is not for general purpose
+ * use.
+ */
+ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
+			 unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	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) {
+		ssize_t err;
+
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
+			ret = err;
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_aio_write);
+
 /*
  * Try to release a page associated with block device when the system
  * is under memory pressure.
@@ -1436,7 +1463,7 @@ const struct file_operations def_blk_fops = {
 	.read		= do_sync_read,
 	.write		= do_sync_write,
   	.aio_read	= generic_file_aio_read,
-  	.aio_write	= generic_file_aio_write_nolock,
+	.aio_write	= blkdev_aio_write,
 	.mmap		= generic_file_mmap,
 	.fsync		= block_fsync,
 	.unlocked_ioctl	= block_ioctl,

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))

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,

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 = {

fs/fat/file.c

@@ -176,8 +176,26 @@ static int fat_cont_expand(struct inode *inode, loff_t size)
 
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-	if (IS_SYNC(inode))
-		err = sync_page_range_nolock(inode, mapping, start, count);
+	if (IS_SYNC(inode)) {
+		int err2;
+
+		/*
+		 * Opencode syncing since we don't have a file open to use
+		 * standard fsync path.
+		 */
+		err = filemap_fdatawrite_range(mapping, start,
+					       start + count - 1);
+		err2 = sync_mapping_buffers(mapping);
+		if (!err)
+			err = err2;
+		err2 = write_inode_now(inode, 1);
+		if (!err)
+			err = err2;
+		if (!err) {
+			err =  filemap_fdatawait_range(mapping, start,
+						       start + count - 1);
+		}
+	}
 out:
 	return err;
 }

fs/fat/misc.c

@@ -119,8 +119,8 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster)
 		MSDOS_I(inode)->i_start = new_dclus;
 		MSDOS_I(inode)->i_logstart = new_dclus;
 		/*
-		 * Since generic_osync_inode() synchronize later if
-		 * this is not directory, we don't here.
+		 * Since generic_write_sync() synchronizes regular files later,
+		 * we sync here only directories.
 		 */
 		if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) {
 			ret = fat_sync_inode(inode);

fs/fs-writeback.c

@@ -1242,57 +1242,3 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 	return ret;
 }
 EXPORT_SYMBOL(sync_inode);
-
-/**
- * generic_osync_inode - flush all dirty data for a given inode to disk
- * @inode: inode to write
- * @mapping: the address_space that should be flushed
- * @what:  what to write and wait upon
- *
- * This can be called by file_write functions for files which have the
- * O_SYNC flag set, to flush dirty writes to disk.
- *
- * @what is a bitmask, specifying which part of the inode's data should be
- * written and waited upon.
- *
- *    OSYNC_DATA:     i_mapping's dirty data
- *    OSYNC_METADATA: the buffers at i_mapping->private_list
- *    OSYNC_INODE:    the inode itself
- */
-
-int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what)
-{
-	int err = 0;
-	int need_write_inode_now = 0;
-	int err2;
-
-	if (what & OSYNC_DATA)
-		err = filemap_fdatawrite(mapping);
-	if (what & (OSYNC_METADATA|OSYNC_DATA)) {
-		err2 = sync_mapping_buffers(mapping);
-		if (!err)
-			err = err2;
-	}
-	if (what & OSYNC_DATA) {
-		err2 = filemap_fdatawait(mapping);
-		if (!err)
-			err = err2;
-	}
-
-	spin_lock(&inode_lock);
-	if ((inode->i_state & I_DIRTY) &&
-	    ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC)))
-		need_write_inode_now = 1;
-	spin_unlock(&inode_lock);
-
-	if (need_write_inode_now) {
-		err2 = write_inode_now(inode, 1);
-		if (!err)
-			err = err2;
-	}
-	else
-		inode_sync_wait(inode);
-
-	return err;
-}
-EXPORT_SYMBOL(generic_osync_inode);

fs/ntfs/file.c

@@ -2076,14 +2076,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 	*ppos = pos;
 	if (cached_page)
 		page_cache_release(cached_page);
-	/* For now, when the user asks for O_SYNC, we actually give O_DSYNC. */
-	if (likely(!status)) {
-		if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(vi))) {
-			if (!mapping->a_ops->writepage || !is_sync_kiocb(iocb))
-				status = generic_osync_inode(vi, mapping,
-						OSYNC_METADATA|OSYNC_DATA);
-		}
-  	}
 	pagevec_lru_add_file(&lru_pvec);
 	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
 			written ? "written" : "status", (unsigned long)written,
@@ -2145,8 +2137,8 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	mutex_lock(&inode->i_mutex);
 	ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		int err = sync_page_range(inode, mapping, pos, ret);
+	if (ret > 0) {
+		int err = generic_write_sync(file, pos, ret);
 		if (err < 0)
 			ret = err;
 	}
@@ -2173,8 +2165,8 @@ static ssize_t ntfs_file_writev(struct file *file, const struct iovec *iov,
 	if (ret == -EIOCBQUEUED)
 		ret = wait_on_sync_kiocb(&kiocb);
 	mutex_unlock(&inode->i_mutex);
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		int err = sync_page_range(inode, mapping, *ppos - ret, ret);
+	if (ret > 0) {
+		int err = generic_write_sync(file, *ppos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}

fs/ntfs/mft.c

@@ -384,13 +384,12 @@ MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref,
  * it is dirty in the inode meta data rather than the data page cache of the
  * inode, and thus there are no data pages that need writing out.  Therefore, a
  * full mark_inode_dirty() is overkill.  A mark_inode_dirty_sync(), on the
- * other hand, is not sufficient, because I_DIRTY_DATASYNC needs to be set to
- * ensure ->write_inode is called from generic_osync_inode() and this needs to
- * happen or the file data would not necessarily hit the device synchronously,
- * even though the vfs inode has the O_SYNC flag set.  Also, I_DIRTY_DATASYNC
- * simply "feels" better than just I_DIRTY_SYNC, since the file data has not
- * actually hit the block device yet, which is not what I_DIRTY_SYNC on its own
- * would suggest.
+ * other hand, is not sufficient, because ->write_inode needs to be called even
+ * in case of fdatasync. This needs to happen or the file data would not
+ * necessarily hit the device synchronously, even though the vfs inode has the
+ * O_SYNC flag set.  Also, I_DIRTY_DATASYNC simply "feels" better than just
+ * I_DIRTY_SYNC, since the file data has not actually hit the block device yet,
+ * which is not what I_DIRTY_SYNC on its own would suggest.
  */
 void __mark_mft_record_dirty(ntfs_inode *ni)
 {

fs/ocfs2/file.c

@@ -1871,8 +1871,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 			goto out_dio;
 		}
 	} else {
-		written = generic_file_aio_write_nolock(iocb, iov, nr_segs,
-							*ppos);
+		written = __generic_file_aio_write(iocb, iov, nr_segs, ppos);
 	}
 
 out_dio:
@@ -1880,18 +1879,21 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
 
 	if ((file->f_flags & O_SYNC && !direct_io) || IS_SYNC(inode)) {
-		/*
-		 * The generic write paths have handled getting data
-		 * to disk, but since we don't make use of the dirty
-		 * inode list, a manual journal commit is necessary
-		 * here.
-		 */
-		if (old_size != i_size_read(inode) ||
-		    old_clusters != OCFS2_I(inode)->ip_clusters) {
+		ret = filemap_fdatawrite_range(file->f_mapping, pos,
+					       pos + count - 1);
+		if (ret < 0)
+			written = ret;
+
+		if (!ret && (old_size != i_size_read(inode) ||
+		    old_clusters != OCFS2_I(inode)->ip_clusters)) {
 			ret = jbd2_journal_force_commit(osb->journal->j_journal);
 			if (ret < 0)
 				written = ret;
 		}
+
+		if (!ret)
+			ret = filemap_fdatawait_range(file->f_mapping, pos,
+						      pos + count - 1);
 	}
 
 	/* 
@@ -1991,31 +1993,16 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 
 	if (ret > 0) {
 		unsigned long nr_pages;
-
-		*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 = ocfs2_rw_lock(inode, 1);
-			if (err < 0) {
-				mlog_errno(err);
-			} else {
-				err = generic_osync_inode(inode, mapping,
-						  OSYNC_METADATA|OSYNC_DATA);
-				ocfs2_rw_unlock(inode, 1);
-			}
-			mutex_unlock(&inode->i_mutex);
+		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
+		err = generic_write_sync(out, *ppos, ret);
 		if (err)
 			ret = err;
-		}
+		else
+			*ppos += ret;
+
 		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
 	}
 

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;
-
-		*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);
+		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
+		err = generic_write_sync(out, *ppos, ret);
 		if (err)
 			ret = err;
-		}
+		else
+			*ppos += ret;
 		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
 	}
 

fs/sync.c

@@ -178,19 +178,23 @@ 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;
@@ -214,7 +218,7 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 		goto out;
 	}
 
-	ret = filemap_fdatawrite(mapping);
+	ret = filemap_write_and_wait_range(mapping, start, end);
 
 	/*
 	 * We need to protect against concurrent writers, which could cause
@@ -225,12 +229,29 @@ 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);
-	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)
@@ -256,6 +277,23 @@ 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

fs/xfs/linux-2.6/xfs_lrw.c

@@ -817,7 +817,8 @@ xfs_write(
 		xfs_iunlock(xip, iolock);
 		if (need_i_mutex)
 			mutex_unlock(&inode->i_mutex);
-		error2 = sync_page_range(inode, mapping, pos, ret);
+		error2 = filemap_write_and_wait_range(mapping, pos,
+						      pos + ret - 1);
 		if (!error)
 			error = error2;
 		if (need_i_mutex)

include/linux/fs.h

@@ -1455,11 +1455,6 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
 #define DT_SOCK		12
 #define DT_WHT		14
 
-#define OSYNC_METADATA	(1<<0)
-#define OSYNC_DATA	(1<<1)
-#define OSYNC_INODE	(1<<2)
-int generic_osync_inode(struct inode *, struct address_space *, int);
-
 /*
  * This is the "filldir" function type, used by readdir() to let
  * the kernel specify what kind of dirent layout it wants to have.
@@ -2086,6 +2081,8 @@ extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
 extern int filemap_fdatawait(struct address_space *);
+extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
+				   loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
@@ -2096,7 +2093,10 @@ 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);
@@ -2202,9 +2202,9 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
+		loff_t *);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
-		unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, loff_t *, size_t, size_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
@@ -2214,6 +2214,10 @@ extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t l
 extern int generic_segment_checks(const struct iovec *iov,
 		unsigned long *nr_segs, size_t *count, int access_flags);
 
+/* fs/block_dev.c */
+extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
+				unsigned long nr_segs, loff_t pos);
+
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);

include/linux/writeback.h

@@ -150,10 +150,6 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-int sync_page_range(struct inode *inode, struct address_space *mapping,
-			loff_t pos, loff_t count);
-int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
-			   loff_t pos, loff_t count);
 void set_page_dirty_balance(struct page *page, int page_mkwrite);
 void writeback_set_ratelimit(void);
 

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.
@@ -307,68 +306,24 @@ int wait_on_page_writeback_range(struct address_space *mapping,
 }
 
 /**
- * sync_page_range - write and wait on all pages in the passed range
- * @inode:	target inode
- * @mapping:	target address_space
- * @pos:	beginning offset in pages to write
- * @count:	number of bytes to write
- *
- * Write and wait upon all the pages in the passed range.  This is a "data
- * integrity" operation.  It waits upon in-flight writeout before starting and
- * waiting upon new writeout.  If there was an IO error, return it.
+ * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range
+ * @mapping: address space structure to wait for
+ * @start:	offset in bytes where the range starts
+ * @end:	offset in bytes where the range ends (inclusive)
  *
- * We need to re-take i_mutex during the generic_osync_inode list walk because
- * it is otherwise livelockable.
- */
-int sync_page_range(struct inode *inode, struct address_space *mapping,
-			loff_t pos, loff_t count)
-{
-	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
-	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
-	int ret;
-
-	if (!mapping_cap_writeback_dirty(mapping) || !count)
-		return 0;
-	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
-	if (ret == 0) {
-		mutex_lock(&inode->i_mutex);
-		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
-		mutex_unlock(&inode->i_mutex);
-	}
-	if (ret == 0)
-		ret = wait_on_page_writeback_range(mapping, start, end);
-	return ret;
-}
-EXPORT_SYMBOL(sync_page_range);
-
-/**
- * sync_page_range_nolock - write & wait on all pages in the passed range without locking
- * @inode:	target inode
- * @mapping:	target address_space
- * @pos:	beginning offset in pages to write
- * @count:	number of bytes to write
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.
  *
- * Note: Holding i_mutex across sync_page_range_nolock() is not a good idea
- * as it forces O_SYNC writers to different parts of the same file
- * to be serialised right until io completion.
+ * This is just a simple wrapper so that callers don't have to convert offsets
+ * to page indexes themselves
  */
-int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
-			   loff_t pos, loff_t count)
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start,
+			    loff_t end)
 {
-	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
-	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
-	int ret;
-
-	if (!mapping_cap_writeback_dirty(mapping) || !count)
-		return 0;
-	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
-	if (ret == 0)
-		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
-	if (ret == 0)
-		ret = wait_on_page_writeback_range(mapping, start, end);
-	return ret;
+	return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT,
+					    end >> PAGE_CACHE_SHIFT);
 }
-EXPORT_SYMBOL(sync_page_range_nolock);
+EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
  * filemap_fdatawait - wait for all under-writeback pages to complete
@@ -2167,20 +2122,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 		*ppos = end;
 	}
-
-	/*
-	 * Sync the fs metadata but not the minor inode changes and
-	 * of course not the data as we did direct DMA for the IO.
-	 * i_mutex is held, which protects generic_osync_inode() from
-	 * livelocking.  AIO O_DIRECT ops attempt to sync metadata here.
-	 */
 out:
-	if ((written >= 0 || written == -EIOCBQUEUED) &&
-	    ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
-		if (err < 0)
-			written = err;
-	}
 	return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);
@@ -2312,8 +2254,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
-	const struct address_space_operations *a_ops = mapping->a_ops;
-	struct inode *inode = mapping->host;
 	ssize_t status;
 	struct iov_iter i;
 
@@ -2323,16 +2263,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 	if (likely(status >= 0)) {
 		written += status;
 		*ppos = pos + status;
-
-		/*
-		 * For now, when the user asks for O_SYNC, we'll actually give
-		 * O_DSYNC
-		 */
-		if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-			if (!a_ops->writepage || !is_sync_kiocb(iocb))
-				status = generic_osync_inode(inode, mapping,
-						OSYNC_METADATA|OSYNC_DATA);
-		}
   	}
 	
 	/*
@@ -2348,8 +2278,26 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 }
 EXPORT_SYMBOL(generic_file_buffered_write);
 
-static ssize_t
-__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
+/**
+ * __generic_file_aio_write - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @iov:	vector with data to write
+ * @nr_segs:	number of segments in the vector
+ * @ppos:	position where to write
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * object which does not need locking at all.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_mutex.
+ */
+ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				 unsigned long nr_segs, loff_t *ppos)
 {
 	struct file *file = iocb->ki_filp;
@@ -2447,51 +2395,37 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
+EXPORT_SYMBOL(__generic_file_aio_write);
 
-ssize_t generic_file_aio_write_nolock(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_nolock(iocb, iov, nr_segs,
-			&iocb->ki_pos);
-
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-		ssize_t err;
-
-		err = sync_page_range_nolock(inode, mapping, pos, ret);
-		if (err < 0)
-			ret = err;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(generic_file_aio_write_nolock);
-
+/**
+ * generic_file_aio_write - write data to a file
+ * @iocb:	IO state structure
+ * @iov:	vector with data to write
+ * @nr_segs:	number of segments in the vector
+ * @pos:	position in file where to write
+ *
+ * This is a wrapper around __generic_file_aio_write() to be used by most
+ * filesystems. It takes care of syncing the file in case of O_SYNC file
+ * and acquires i_mutex as needed.
+ */
 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);
 
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
-			&iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
-	if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+	if (ret > 0 || ret == -EIOCBQUEUED) {
 		ssize_t err;
 
-		err = sync_page_range(inode, mapping, pos, ret);
-		if (err < 0)
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
 			ret = err;
 	}
 	return ret;