1 files changed, 29 insertions, 6 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 5d55a896ff78..13edf7ad3ff1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -737,7 +737,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
         struct buffer_head *bh;
         struct list_head tmp;
-        struct address_space *mapping;
+        struct address_space *mapping, *prev_mapping = NULL;
         int err = 0, err2;
 
         INIT_LIST_HEAD(&tmp);
@@ -762,7 +762,18 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
                                  * contents - it is a noop if I/O is still in
                                  * flight on potentially older contents.
                                  */
-                                ll_rw_block(SWRITE_SYNC, 1, &bh);
+                                ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+
+                                /*
+                                 * Kick off IO for the previous mapping. Note
+                                 * that we will not run the very last mapping,
+                                 * wait_on_buffer() will do that for us
+                                 * through sync_buffer().
+                                 */
+                                if (prev_mapping && prev_mapping != mapping)
+                                        blk_run_address_space(prev_mapping);
+                                prev_mapping = mapping;
+
                                 brelse(bh);
                                 spin_lock(lock);
                         }
@@ -1585,6 +1596,16 @@ EXPORT_SYMBOL(unmap_underlying_metadata);
  * locked buffer.   This only can happen if someone has written the buffer
  * directly, with submit_bh().  At the address_space level PageWriteback
  * prevents this contention from occurring.
+ *
+ * If block_write_full_page() is called with wbc->sync_mode ==
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
+ * causes the writes to be flagged as synchronous writes, but the
+ * block device queue will NOT be unplugged, since usually many pages
+ * will be pushed to the out before the higher-level caller actually
+ * waits for the writes to be completed.  The various wait functions,
+ * such as wait_on_writeback_range() will ultimately call sync_page()
+ * which will ultimately call blk_run_backing_dev(), which will end up
+ * unplugging the device queue.
  */
 static int __block_write_full_page(struct inode *inode, struct page *page,
                         get_block_t *get_block, struct writeback_control *wbc)
@@ -1595,7 +1616,8 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
         struct buffer_head *bh, *head;
         const unsigned blocksize = 1 << inode->i_blkbits;
         int nr_underway = 0;
-        int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+        int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
+                        WRITE_SYNC_PLUG : WRITE);
 
         BUG_ON(!PageLocked(page));
 
@@ -2957,12 +2979,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
         for (i = 0; i < nr; i++) {
                 struct buffer_head *bh = bhs[i];
 
-                if (rw == SWRITE || rw == SWRITE_SYNC)
+                if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
                         lock_buffer(bh);
                 else if (!trylock_buffer(bh))
                         continue;
 
-                if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
+                if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
+                    rw == SWRITE_SYNC_PLUG) {
                         if (test_clear_buffer_dirty(bh)) {
                                 bh->b_end_io = end_buffer_write_sync;
                                 get_bh(bh);
@@ -2998,7 +3021,7 @@ int sync_dirty_buffer(struct buffer_head *bh)
         if (test_clear_buffer_dirty(bh)) {
                 get_bh(bh);
                 bh->b_end_io = end_buffer_write_sync;
-                ret = submit_bh(WRITE, bh);
+                ret = submit_bh(WRITE_SYNC, bh);
                 wait_on_buffer(bh);
                 if (buffer_eopnotsupp(bh)) {
                         clear_buffer_eopnotsupp(bh);