1 files changed, 39 insertions, 24 deletions

diff --git a/fs/sync.c b/fs/sync.c
index 11e3d1c44901..eb8722dc556f 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -29,16 +29,6 @@
  */
 static int __sync_filesystem(struct super_block *sb, int wait)
 {
-        /*
-         * This should be safe, as we require bdi backing to actually
-         * write out data in the first place
-         */
-        if (sb->s_bdi == &noop_backing_dev_info)
-                return 0;
-
-        if (sb->s_qcop && sb->s_qcop->quota_sync)
-                sb->s_qcop->quota_sync(sb, -1, wait);
-
         if (wait)
                 sync_inodes_sb(sb);
         else
@@ -77,29 +67,48 @@ int sync_filesystem(struct super_block *sb)
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
-static void sync_one_sb(struct super_block *sb, void *arg)
+static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
         if (!(sb->s_flags & MS_RDONLY))
-                __sync_filesystem(sb, *(int *)arg);
+                sync_inodes_sb(sb);
 }
-/*
- * Sync all the data for all the filesystems (called by sys_sync() and
- * emergency sync)
- */
-static void sync_filesystems(int wait)
+
+static void sync_fs_one_sb(struct super_block *sb, void *arg)
 {
-        iterate_supers(sync_one_sb, &wait);
+        if (!(sb->s_flags & MS_RDONLY) && sb->s_op->sync_fs)
+                sb->s_op->sync_fs(sb, *(int *)arg);
+}
+
+static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
+{
+        filemap_fdatawrite(bdev->bd_inode->i_mapping);
+}
+
+static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
+{
+        filemap_fdatawait(bdev->bd_inode->i_mapping);
 }
 
 /*
- * sync everything.  Start out by waking pdflush, because that writes back
- * all queues in parallel.
+ * Sync everything. We start by waking flusher threads so that most of
+ * writeback runs on all devices in parallel. Then we sync all inodes reliably
+ * which effectively also waits for all flusher threads to finish doing
+ * writeback. At this point all data is on disk so metadata should be stable
+ * and we tell filesystems to sync their metadata via ->sync_fs() calls.
+ * Finally, we writeout all block devices because some filesystems (e.g. ext2)
+ * just write metadata (such as inodes or bitmaps) to block device page cache
+ * and do not sync it on their own in ->sync_fs().
  */
 SYSCALL_DEFINE0(sync)
 {
+        int nowait = 0, wait = 1;
+
         wakeup_flusher_threads(0, WB_REASON_SYNC);
-        sync_filesystems(0);
-        sync_filesystems(1);
+        iterate_supers(sync_inodes_one_sb, NULL);
+        iterate_supers(sync_fs_one_sb, &nowait);
+        iterate_supers(sync_fs_one_sb, &wait);
+        iterate_bdevs(fdatawrite_one_bdev, NULL);
+        iterate_bdevs(fdatawait_one_bdev, NULL);
         if (unlikely(laptop_mode))
                 laptop_sync_completion();
         return 0;
@@ -107,12 +116,18 @@ SYSCALL_DEFINE0(sync)
 
 static void do_sync_work(struct work_struct *work)
 {
+        int nowait = 0;
+
         /*
          * Sync twice to reduce the possibility we skipped some inodes / pages
          * because they were temporarily locked
          */
-        sync_filesystems(0);
-        sync_filesystems(0);
+        iterate_supers(sync_inodes_one_sb, &nowait);
+        iterate_supers(sync_fs_one_sb, &nowait);
+        iterate_bdevs(fdatawrite_one_bdev, NULL);
+        iterate_supers(sync_inodes_one_sb, &nowait);
+        iterate_supers(sync_fs_one_sb, &nowait);
+        iterate_bdevs(fdatawrite_one_bdev, NULL);
         printk("Emergency Sync complete\n");
         kfree(work);
 }