Merge branch 'for-3.18/core' of git://git.kernel.dk/linux-block

Pull core block layer changes from Jens Axboe:
 "This is the core block IO pull request for 3.18.  Apart from the new
  and improved flush machinery for blk-mq, this is all mostly bug fixes
  and cleanups.

   - blk-mq timeout updates and fixes from Christoph.

   - Removal of REQ_END, also from Christoph.  We pass it through the
     ->queue_rq() hook for blk-mq instead, freeing up one of the request
     bits.  The space was overly tight on 32-bit, so Martin also killed
     REQ_KERNEL since it's no longer used.

   - blk integrity updates and fixes from Martin and Gu Zheng.

   - Update to the flush machinery for blk-mq from Ming Lei.  Now we
     have a per hardware context flush request, which both cleans up the
     code should scale better for flush intensive workloads on blk-mq.

   - Improve the error printing, from Rob Elliott.

   - Backing device improvements and cleanups from Tejun.

   - Fixup of a misplaced rq_complete() tracepoint from Hannes.

   - Make blk_get_request() return error pointers, fixing up issues
     where we NULL deref when a device goes bad or missing.  From Joe
     Lawrence.

   - Prep work for drastically reducing the memory consumption of dm
     devices from Junichi Nomura.  This allows creating clone bio sets
     without preallocating a lot of memory.

   - Fix a blk-mq hang on certain combinations of queue depths and
     hardware queues from me.

   - Limit memory consumption for blk-mq devices for crash dump
     scenarios and drivers that use crazy high depths (certain SCSI
     shared tag setups).  We now just use a single queue and limited
     depth for that"

* 'for-3.18/core' of git://git.kernel.dk/linux-block: (58 commits)
  block: Remove REQ_KERNEL
  blk-mq: allocate cpumask on the home node
  bio-integrity: remove the needless fail handle of bip_slab creating
  block: include func name in __get_request prints
  block: make blk_update_request print prefix match ratelimited prefix
  blk-merge: don't compute bi_phys_segments from bi_vcnt for cloned bio
  block: fix alignment_offset math that assumes io_min is a power-of-2
  blk-mq: Make bt_clear_tag() easier to read
  blk-mq: fix potential hang if rolling wakeup depth is too high
  block: add bioset_create_nobvec()
  block: use bio_clone_fast() in blk_rq_prep_clone()
  block: misplaced rq_complete tracepoint
  sd: Honor block layer integrity handling flags
  block: Replace strnicmp with strncasecmp
  block: Add T10 Protection Information functions
  block: Don't merge requests if integrity flags differ
  block: Integrity checksum flag
  block: Relocate bio integrity flags
  block: Add a disk flag to block integrity profile
  block: Add prefix to block integrity profile flags
  ...

1 files changed, 16 insertions, 24 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 12a992b..0ae0df5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -40,7 +40,7 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
 	if (wb1 < wb2) {
 		spin_lock(&wb1->list_lock);
@@ -376,13 +376,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	flush_delayed_work(&bdi->wb.dwork);
 	WARN_ON(!list_empty(&bdi->work_list));
-
-	/*
-	 * This shouldn't be necessary unless @bdi for some reason has
-	 * unflushed dirty IO after work_list is drained.  Do it anyway
-	 * just in case.
-	 */
-	cancel_delayed_work_sync(&bdi->wb.dwork);
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 }
 
 /*
@@ -402,21 +396,15 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	struct device *dev = bdi->dev;
-
-	if (dev) {
+	if (bdi->dev) {
 		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 
 		bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
-
-		spin_lock_bh(&bdi->wb_lock);
+		device_unregister(bdi->dev);
 		bdi->dev = NULL;
-		spin_unlock_bh(&bdi->wb_lock);
-
-		device_unregister(dev);
 	}
 }
 EXPORT_SYMBOL(bdi_unregister);
@@ -487,8 +475,17 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	int i;
 
 	/*
-	 * Splice our entries to the default_backing_dev_info, if this
-	 * bdi disappears
+	 * Splice our entries to the default_backing_dev_info.  This
+	 * condition shouldn't happen.  @wb must be empty at this point and
+	 * dirty inodes on it might cause other issues.  This workaround is
+	 * added by ce5f8e779519 ("writeback: splice dirty inode entries to
+	 * default bdi on bdi_destroy()") without root-causing the issue.
+	 *
+	 * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com
+	 * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
+	 *
+	 * We should probably add WARN_ON() to find out whether it still
+	 * happens and track it down if so.
 	 */
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
@@ -503,12 +500,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
-	/*
-	 * If bdi_unregister() had already been called earlier, the dwork
-	 * could still be pending because bdi_prune_sb() can race with the
-	 * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
-	 */
-	cancel_delayed_work_sync(&bdi->wb.dwork);
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);