vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode

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>

diff --git a/fs/splice.c b/fs/splice.c
index 73766d2..8190237 100644 (file)
--- 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 103cc7f..4e15da0 100644 (file)
--- a/fs/sync.c
+++ b/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_fdatawrite_range(mapping, start, end);
 
        /*
         * We need to protect against concurrent writers, which could cause
@@ -225,12 +229,32 @@ 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)
@@ -256,6 +280,23 @@ 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 6c1be3a..e2c7f51 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2098,7 +2098,10 @@ 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 3587554..849293c 100644 (file)
--- 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.
@@ -2477,8 +2476,7 @@ 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);
@@ -2487,11 +2485,10 @@ 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;
        }