Merge branch 'for-4.3/blkcg' of git://git.kernel.dk/linux-block

Pull blk-cg updates from Jens Axboe:
 "A bit later in the cycle, but this has been in the block tree for a a
  while.  This is basically four patchsets from Tejun, that improve our
  buffered cgroup writeback.  It was dependent on the other cgroup
  changes, but they went in earlier in this cycle.

  Series 1 is set of 5 patches that has cgroup writeback updates:

   - bdi_writeback iteration fix which could lead to some wb's being
     skipped or repeated during e.g. sync under memory pressure.

   - Simplification of wb work wait mechanism.

   - Writeback tracepoints updated to report cgroup.

  Series 2 is is a set of updates for the CFQ cgroup writeback handling:

     cfq has always charged all async IOs to the root cgroup.  It didn't
     have much choice as writeback didn't know about cgroups and there
     was no way to tell who to blame for a given writeback IO.
     writeback finally grew support for cgroups and now tags each
     writeback IO with the appropriate cgroup to charge it against.

     This patchset updates cfq so that it follows the blkcg each bio is
     tagged with.  Async cfq_queues are now shared across cfq_group,
     which is per-cgroup, instead of per-request_queue cfq_data.  This
     makes all IOs follow the weight based IO resource distribution
     implemented by cfq.

     - Switched from GFP_ATOMIC to GFP_NOWAIT as suggested by Jeff.

     - Other misc review points addressed, acks added and rebased.

  Series 3 is the blkcg policy cleanup patches:

     This patchset contains assorted cleanups for blkcg_policy methods
     and blk[c]g_policy_data handling.

     - alloc/free added for blkg_policy_data.  exit dropped.

     - alloc/free added for blkcg_policy_data.

     - blk-throttle's async percpu allocation is replaced with direct
       allocation.

     - all methods now take blk[c]g_policy_data instead of blkcg_gq or
       blkcg.

  And finally, series 4 is a set of patches cleaning up the blkcg stats
  handling:

    blkcg's stats have always been somwhat of a mess.  This patchset
    tries to improve the situation a bit.

     - The following patches added to consolidate blkcg entry point and
       blkg creation.  This is in itself is an improvement and helps
       colllecting common stats on bio issue.

     - per-blkg stats now accounted on bio issue rather than request
       completion so that bio based and request based drivers can behave
       the same way.  The issue was spotted by Vivek.

     - cfq-iosched implements custom recursive stats and blk-throttle
       implements custom per-cpu stats.  This patchset make blkcg core
       support both by default.

     - cfq-iosched and blk-throttle keep track of the same stats
       multiple times.  Unify them"

* 'for-4.3/blkcg' of git://git.kernel.dk/linux-block: (45 commits)
  blkcg: use CGROUP_WEIGHT_* scale for io.weight on the unified hierarchy
  blkcg: s/CFQ_WEIGHT_*/CFQ_WEIGHT_LEGACY_*/
  blkcg: implement interface for the unified hierarchy
  blkcg: misc preparations for unified hierarchy interface
  blkcg: separate out tg_conf_updated() from tg_set_conf()
  blkcg: move body parsing from blkg_conf_prep() to its callers
  blkcg: mark existing cftypes as legacy
  blkcg: rename subsystem name from blkio to io
  blkcg: refine error codes returned during blkcg configuration
  blkcg: remove unnecessary NULL checks from __cfqg_set_weight_device()
  blkcg: reduce stack usage of blkg_rwstat_recursive_sum()
  blkcg: remove cfqg_stats->sectors
  blkcg: move io_service_bytes and io_serviced stats into blkcg_gq
  blkcg: make blkg_[rw]stat_recursive_sum() to be able to index into blkcg_gq
  blkcg: make blkcg_[rw]stat per-cpu
  blkcg: add blkg_[rw]stat->aux_cnt and replace cfq_group->dead_stats with it
  blkcg: consolidate blkg creation in blkcg_bio_issue_check()
  blk-throttle: improve queue bypass handling
  blkcg: move root blkg lookup optimization from throtl_lookup_tg() to __blkg_lookup()
  blkcg: inline [__]blkg_lookup()
  ...

diff --cc block/bio.c
Simple merge

diff --cc block/blk-core.c
Simple merge

diff --cc block/blk.h
Simple merge

diff --cc fs/fs-writeback.c
index ae0f438c2ee68f59e4f8f4ebc17aeaae9c250ff9,f4f0f228a53005f8bc7caa6b5c47e7eb4e78bf15..24489126f8ca1144441ad853ac48ac275d439e5e
--- 1/fs/fs-writeback.c
--- 2/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@@ -844,24 -783,45 +783,46 @@@ static void bdi_split_work_to_wbs(struc
        struct wb_iter iter;
  
        might_sleep();
 -
 -      if (!bdi_has_dirty_io(bdi))
 -              return;
  restart:
        rcu_read_lock();
-       bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) {
+       bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) {
+               DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done);
+               struct wb_writeback_work fallback_work;
+               struct wb_writeback_work *work;
+               long nr_pages;
+ 
 -              if (!wb_has_dirty_io(wb) ||
 -                  (skip_if_busy && writeback_in_progress(wb)))
 +              /* SYNC_ALL writes out I_DIRTY_TIME too */
 +              if (!wb_has_dirty_io(wb) &&
 +                  (base_work->sync_mode == WB_SYNC_NONE ||
 +                   list_empty(&wb->b_dirty_time)))
 +                      continue;
 +              if (skip_if_busy && writeback_in_progress(wb))
                        continue;
  
-               base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages);
-               if (!wb_clone_and_queue_work(wb, base_work)) {
-                       next_blkcg_id = wb->blkcg_css->id + 1;
-                       rcu_read_unlock();
-                       wb_wait_for_single_work(bdi, base_work);
-                       goto restart;
+               nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages);
+ 
+               work = kmalloc(sizeof(*work), GFP_ATOMIC);
+               if (work) {
+                       *work = *base_work;
+                       work->nr_pages = nr_pages;
+                       work->auto_free = 1;
+                       wb_queue_work(wb, work);
+                       continue;
                }
+ 
+               /* alloc failed, execute synchronously using on-stack fallback */
+               work = &fallback_work;
+               *work = *base_work;
+               work->nr_pages = nr_pages;
+               work->auto_free = 0;
+               work->done = &fallback_work_done;
+ 
+               wb_queue_work(wb, work);
+ 
+               next_memcg_id = wb->memcg_css->id + 1;
+               rcu_read_unlock();
+               wb_wait_for_completion(bdi, &fallback_work_done);
+               goto restart;
        }
        rcu_read_unlock();
  }
@@@ -900,10 -860,9 +861,8 @@@ static void bdi_split_work_to_wbs(struc
  {
        might_sleep();
  
 -      if (bdi_has_dirty_io(bdi) &&
 -          (!skip_if_busy || !writeback_in_progress(&bdi->wb))) {
 +      if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) {
                base_work->auto_free = 0;
-               base_work->single_wait = 0;
-               base_work->single_done = 0;
                wb_queue_work(&bdi->wb, base_work);
        }
  }

diff --cc include/linux/cgroup_subsys.h
Simple merge

diff --cc mm/backing-dev.c
Simple merge

diff --cc mm/page-writeback.c
Simple merge