writeback: split writeback_inodes_wb

The case where we have a superblock doesn't require a loop here as we scan
over all inodes in writeback_sb_inodes. Split it out into a separate helper
to make the code simpler.  This also allows to get rid of the sb member in
struct writeback_control, which was rather out of place there.

Also update the comments in writeback_sb_inodes that explain the handling
of inodes from wrong superblocks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

1 files changed, 46 insertions, 36 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 94a602e98bb..8cc06d5432b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -554,29 +554,41 @@ static bool pin_sb_for_writeback(struct super_block *sb)
 
 /*
  * Write a portion of b_io inodes which belong to @sb.
- * If @wbc->sb != NULL, then find and write all such
+ *
+ * If @only_this_sb is true, then find and write all such
  * inodes. Otherwise write only ones which go sequentially
  * in reverse order.
+ *
  * Return 1, if the caller writeback routine should be
  * interrupted. Otherwise return 0.
  */
-static int writeback_sb_inodes(struct super_block *sb,
-                               struct bdi_writeback *wb,
-                               struct writeback_control *wbc)
+static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
+                struct writeback_control *wbc, bool only_this_sb)
 {
         while (!list_empty(&wb->b_io)) {
                 long pages_skipped;
                 struct inode *inode = list_entry(wb->b_io.prev,
                                                  struct inode, i_list);
-                if (wbc->sb && sb != inode->i_sb) {
-                        /* super block given and doesn't
-                           match, skip this inode */
-                        redirty_tail(inode);
-                        continue;
-                }
-                if (sb != inode->i_sb)
-                        /* finish with this superblock */
+
+                if (inode->i_sb != sb) {
+                        if (only_this_sb) {
+                                /*
+                                 * We only want to write back data for this
+                                 * superblock, move all inodes not belonging
+                                 * to it back onto the dirty list.
+                                 */
+                                redirty_tail(inode);
+                                continue;
+                        }
+
+                        /*
+                         * The inode belongs to a different superblock.
+                         * Bounce back to the caller to unpin this and
+                         * pin the next superblock.
+                         */
                         return 0;
+                }
+
                 if (inode->i_state & (I_NEW | I_WILL_FREE)) {
                         requeue_io(inode);
                         continue;
@@ -629,29 +641,12 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
                                                  struct inode, i_list);
                 struct super_block *sb = inode->i_sb;
 
-                if (wbc->sb) {
-                        /*
-                         * We are requested to write out inodes for a specific
-                         * superblock.  This means we already have s_umount
-                         * taken by the caller which also waits for us to
-                         * complete the writeout.
-                         */
-                        if (sb != wbc->sb) {
-                                redirty_tail(inode);
-                                continue;
-                        }
-
-                        WARN_ON(!rwsem_is_locked(&sb->s_umount));
-
-                        ret = writeback_sb_inodes(sb, wb, wbc);
-                } else {
-                        if (!pin_sb_for_writeback(sb)) {
-                                requeue_io(inode);
-                                continue;
-                        }
-                        ret = writeback_sb_inodes(sb, wb, wbc);
-                        drop_super(sb);
+                if (!pin_sb_for_writeback(sb)) {
+                        requeue_io(inode);
+                        continue;
                 }
+                ret = writeback_sb_inodes(sb, wb, wbc, false);
+                drop_super(sb);
 
                 if (ret)
                         break;
@@ -660,6 +655,19 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
         /* Leave any unwritten inodes on b_io */
 }
 
+static void __writeback_inodes_sb(struct super_block *sb,
+                struct bdi_writeback *wb, struct writeback_control *wbc)
+{
+        WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+        wbc->wb_start = jiffies; /* livelock avoidance */
+        spin_lock(&inode_lock);
+        if (!wbc->for_kupdate || list_empty(&wb->b_io))
+                queue_io(wb, wbc->older_than_this);
+        writeback_sb_inodes(sb, wb, wbc, true);
+        spin_unlock(&inode_lock);
+}
+
 /*
  * The maximum number of pages to writeout in a single bdi flush/kupdate
  * operation.  We do this so we don't hold I_SYNC against an inode for
@@ -698,7 +706,6 @@ static long wb_writeback(struct bdi_writeback *wb,
                          struct wb_writeback_args *args)
 {
         struct writeback_control wbc = {
-                .sb                     = args->sb,
                 .sync_mode              = args->sync_mode,
                 .older_than_this        = NULL,
                 .for_kupdate            = args->for_kupdate,
@@ -736,7 +743,10 @@ static long wb_writeback(struct bdi_writeback *wb,
                 wbc.more_io = 0;
                 wbc.nr_to_write = MAX_WRITEBACK_PAGES;
                 wbc.pages_skipped = 0;
-                writeback_inodes_wb(wb, &wbc);
+                if (args->sb)
+                        __writeback_inodes_sb(args->sb, wb, &wbc);
+                else
+                        writeback_inodes_wb(wb, &wbc);
                 args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
                 wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;