vfs: Fix sys_sync() and fsync_super() reliability (version 4)

So far, do_sync() called:
  sync_inodes(0);
  sync_supers();
  sync_filesystems(0);
  sync_filesystems(1);
  sync_inodes(1);

This ordering makes it kind of hard for filesystems as sync_inodes(0) need not
submit all the IO (for example it skips inodes with I_SYNC set) so e.g. forcing
transaction to disk in ->sync_fs() is not really enough. Therefore sys_sync has
not been completely reliable on some filesystems (ext3, ext4, reiserfs, ocfs2
and others are hit by this) when racing e.g. with background writeback. A
similar problem hits also other filesystems (e.g. ext2) because of
write_supers() being called before the sync_inodes(1).

Change the ordering of calls in do_sync() - this requires a new function
sync_blockdevs() to preserve the property that block devices are always synced
after write_super() / sync_fs() call.

The same issue is fixed in __fsync_super() function used on umount /
remount read-only.

[AV: build fixes]

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 40 insertions, 2 deletions

diff --git a/fs/internal.h b/fs/internal.h
index 6d4ef208ef65..343a537ab809 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -71,3 +71,12 @@ extern void chroot_fs_refs(struct path *, struct path *);
  * file_table.c
  */
 extern void mark_files_ro(struct super_block *);
+
+/*
+ * super.c
+ */
+#ifdef CONFIG_BLOCK
+extern void sync_blockdevs(void);
+#else
+static inline void sync_blockdevs(void) { }
+#endif
diff --git a/fs/super.c b/fs/super.c
index 3d9f117dd2a3..18d159dc1e40 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -293,6 +293,7 @@ void __fsync_super(struct super_block *sb)
 {
         sync_inodes_sb(sb, 0);
         vfs_dq_sync(sb);
+        sync_inodes_sb(sb, 1);
         lock_super(sb);
         if (sb->s_dirt && sb->s_op->write_super)
                 sb->s_op->write_super(sb);
@@ -300,7 +301,6 @@ void __fsync_super(struct super_block *sb)
         if (sb->s_op->sync_fs)
                 sb->s_op->sync_fs(sb, 1);
         sync_blockdev(sb->s_bdev);
-        sync_inodes_sb(sb, 1);
 }
 
 /*
@@ -522,6 +522,33 @@ restart:
         mutex_unlock(&mutex);
 }
 
+#ifdef CONFIG_BLOCK
+/*
+ *  Sync all block devices underlying some superblock
+ */
+void sync_blockdevs(void)
+{
+        struct super_block *sb;
+
+        spin_lock(&sb_lock);
+restart:
+        list_for_each_entry(sb, &super_blocks, s_list) {
+                if (!sb->s_bdev)
+                        continue;
+                sb->s_count++;
+                spin_unlock(&sb_lock);
+                down_read(&sb->s_umount);
+                if (sb->s_root)
+                        sync_blockdev(sb->s_bdev);
+                up_read(&sb->s_umount);
+                spin_lock(&sb_lock);
+                if (__put_super_and_need_restart(sb))
+                        goto restart;
+        }
+        spin_unlock(&sb_lock);
+}
+#endif
+
 /**
  *      get_super - get the superblock of a device
  *      @bdev: device to get the superblock for
diff --git a/fs/sync.c b/fs/sync.c
index 7abc65fbf21d..631fd5aece78 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -13,6 +13,7 @@
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
+#include "internal.h"
 
 #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
                         SYNC_FILE_RANGE_WAIT_AFTER)
@@ -26,10 +27,11 @@ static void do_sync(unsigned long wait)
         wakeup_pdflush(0);
         sync_inodes(0);         /* All mappings, inodes and their blockdevs */
         vfs_dq_sync(NULL);
+        sync_inodes(wait);      /* Mappings, inodes and blockdevs, again. */
         sync_supers();          /* Write the superblocks */
         sync_filesystems(0);    /* Start syncing the filesystems */
         sync_filesystems(wait); /* Waitingly sync the filesystems */
-        sync_inodes(wait);      /* Mappings, inodes and blockdevs, again. */
+        sync_blockdevs();
         if (!wait)
                 printk("Emergency Sync complete\n");
         if (unlikely(laptop_mode))