[PATCH 07/17] 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 (generic_sync_file) 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@xxxxxxxxxxx>
CC: ocfs2-devel@xxxxxxxxxxxxxx
CC: Joel Becker <joel.becker@xxxxxxxxxx>
CC: Felix Blyakher <felixb@xxxxxxx>
CC: xfs@xxxxxxxxxxx
CC: Anton Altaparmakov <aia21@xxxxxxxxxx>
CC: linux-ntfs-dev@xxxxxxxxxxxxxxxxxxxxx
CC: OGAWA Hirofumi <hirofumi@xxxxxxxxxxxxxxxxxx>
CC: linux-ext4@xxxxxxxxxxxxxxx
CC: tytso@xxxxxxx
Acked-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
 fs/splice.c        |   22 ++++----------
 fs/sync.c          |   81 +++++++++++++++++++++++++++++++++++++++++++---------
 include/linux/fs.h |    7 ++++
 mm/filemap.c       |   18 ++++--------
 4 files changed, 86 insertions(+), 42 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..fc320aa 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -176,23 +176,30 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
 }
 
 /**
- * vfs_fsync - perform a fsync or fdatasync on a file
+ * generic_sync_file - helper to sync 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)
+ * @what:		what should be synced
  *
- * Write back data and metadata for @file to disk.  If @datasync is
- * set only metadata needed to access modified file data is written.
+ * What the function exactly does is controlled by the @what parameter:
  *
- * 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.
+ * If SYNC_SUBMIT_DATA is set, the function submits all pages in the given
+ * range to disk.
+ *
+ * The function always calls ->fsync() callback of the filesystem. If
+ * SYNC_INODE is not set, we pass down the fact that it is just a datasync.
+ *
+ * If SYNC_WAIT_DATA is set, the function waits for writeback to finish
+ * in the given range.
  */
-int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
+int generic_sync_file(struct file *file, struct dentry *dentry, loff_t start,
+		      loff_t end, int what)
 {
 	const struct file_operations *fop;
 	struct address_space *mapping;
-	int err, ret;
+	int err, ret = 0;
 
 	/*
 	 * Get mapping and operations from the file in case we have
@@ -212,23 +219,50 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 		goto out;
 	}
 
-	ret = filemap_fdatawrite(mapping);
+	if (what & SYNC_SUBMIT_DATA)
+		ret = filemap_fdatawrite_range(mapping, start, end);
 
 	/*
 	 * We need to protect against concurrent writers, which could cause
 	 * livelocks in fsync_buffers_list().
 	 */
 	mutex_lock(&mapping->host->i_mutex);
-	err = fop->fsync(file, dentry, datasync);
+	err = fop->fsync(file, dentry, !(what & SYNC_INODE));
 	if (!ret)
 		ret = err;
 	mutex_unlock(&mapping->host->i_mutex);
-	err = filemap_fdatawait(mapping);
-	if (!ret)
-		ret = err;
+
+	if (what & SYNC_WAIT_DATA) {
+		err = filemap_fdatawait_range(mapping, start, end);
+		if (!ret)
+			ret = err;
+	}
 out:
 	return ret;
 }
+EXPORT_SYMBOL(generic_sync_file);
+
+/**
+ * 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)
+{
+	int what = SYNC_SUBMIT_DATA | SYNC_WAIT_DATA;
+
+	if (!datasync)
+		what |= SYNC_INODE;
+	return generic_sync_file(file, dentry, 0, LLONG_MAX, what);
+}
 EXPORT_SYMBOL(vfs_fsync);
 
 static int do_fsync(unsigned int fd, int datasync)
@@ -254,6 +288,25 @@ 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.
+ * FIXME: Make it inline?
+ */
+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 generic_sync_file(file, file->f_path.dentry, pos,
+				 pos + count - 1,
+				 SYNC_SUBMIT_DATA | SYNC_WAIT_DATA);
+}
+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 29fc8da..648001c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2088,7 +2088,14 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping,
 extern int filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end);
 
+/* Flags for generic_sync_file */
+#define SYNC_INODE		1
+#define SYNC_SUBMIT_DATA	2
+#define SYNC_WAIT_DATA		4
+extern int generic_sync_file(struct file *file, struct dentry *dentry,
+			   loff_t start, loff_t end, int what);
 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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/