1 files changed, 9 insertions, 10 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3be57189efd5..68851ff2fd41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -45,6 +45,7 @@ struct wb_writeback_work {
         unsigned int for_kupdate:1;
         unsigned int range_cyclic:1;
         unsigned int for_background:1;
+        unsigned int for_sync:1;        /* sync(2) WB_SYNC_ALL writeback */
         enum wb_reason reason;          /* why was writeback initiated? */
 
         struct list_head list;          /* pending work list */
@@ -443,9 +444,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
         /*
          * Make sure to wait on the data before writing out the metadata.
          * This is important for filesystems that modify metadata on data
-         * I/O completion.
+         * I/O completion. We don't do it for sync(2) writeback because it has a
+         * separate, external IO completion path and ->sync_fs for guaranteeing
+         * inode metadata is written back correctly.
          */
-        if (wbc->sync_mode == WB_SYNC_ALL) {
+        if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
                 int err = filemap_fdatawait(mapping);
                 if (ret == 0)
                         ret = err;
@@ -578,6 +581,7 @@ static long writeback_sb_inodes(struct super_block *sb,
                 .tagged_writepages      = work->tagged_writepages,
                 .for_kupdate            = work->for_kupdate,
                 .for_background         = work->for_background,
+                .for_sync               = work->for_sync,
                 .range_cyclic           = work->range_cyclic,
                 .range_start            = 0,
                 .range_end              = LLONG_MAX,
@@ -959,7 +963,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 /*
  * Retrieve work items and do the writeback they describe
  */
-long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+static long wb_do_writeback(struct bdi_writeback *wb)
 {
         struct backing_dev_info *bdi = wb->bdi;
         struct wb_writeback_work *work;
@@ -967,12 +971,6 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
         set_bit(BDI_writeback_running, &wb->bdi->state);
         while ((work = get_next_work_item(bdi)) != NULL) {
-                /*
-                 * Override sync mode, in case we must wait for completion
-                 * because this thread is exiting now.
-                 */
-                if (force_wait)
-                        work->sync_mode = WB_SYNC_ALL;
 
                 trace_writeback_exec(bdi, work);
 
@@ -1021,7 +1019,7 @@ void bdi_writeback_workfn(struct work_struct *work)
                  * rescuer as work_list needs to be drained.
                  */
                 do {
-                        pages_written = wb_do_writeback(wb, 0);
+                        pages_written = wb_do_writeback(wb);
                         trace_writeback_pages_written(pages_written);
                 } while (!list_empty(&bdi->work_list));
         } else {
@@ -1362,6 +1360,7 @@ void sync_inodes_sb(struct super_block *sb)
                 .range_cyclic   = 0,
                 .done           = &done,
                 .reason         = WB_REASON_SYNC,
+                .for_sync       = 1,
         };
 
         /* Nothing to do? */