Merge branch 'for-4.6/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Here are the core block changes for this merge window.  Not a lot of
  exciting stuff going on in this round, most of the changes have been
  on the driver side of things.  That pull request is coming next.  This
  pull request contains:

   - A set of fixes for chained bio handling from Christoph.

   - A tag bounds check for blk-mq from Hannes, ensuring that we don't
     do something stupid if a device reports an invalid tag value.

   - A set of fixes/updates for the CFQ IO scheduler from Jan Kara.

   - A set of blk-mq fixes from Keith, adding support for dynamic
     hardware queues, and fixing init of max_dev_sectors for stacking
     devices.

   - A fix for the dynamic hw context from Ming.

   - Enabling of cgroup writeback support on a block device, from
     Shaohua"

* 'for-4.6/core' of git://git.kernel.dk/linux-block:
  blk-mq: add bounds check on tag-to-rq conversion
  block: bio_remaining_done() isn't unlikely
  block: cleanup bio_endio
  block: factor out chained bio completion
  block: don't unecessarily clobber bi_error for chained bios
  block-dev: enable writeback cgroup support
  blk-mq: Fix NULL pointer updating nr_requests
  blk-mq: mark request queue as mq asap
  block: Initialize max_dev_sectors to 0
  blk-mq: dynamic h/w context count
  cfq-iosched: Allow parent cgroup to preempt its child
  cfq-iosched: Allow sync noidle workloads to preempt each other
  cfq-iosched: Reorder checks in cfq_should_preempt()
  cfq-iosched: Don't group_idle if cfqq has big thinktime

1 files changed, 33 insertions, 10 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1f9093e..e3c591d 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -632,6 +632,13 @@ static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
 	return pblkg ? blkg_to_cfqg(pblkg) : NULL;
 }
 
+static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
+				      struct cfq_group *ancestor)
+{
+	return cgroup_is_descendant(cfqg_to_blkg(cfqg)->blkcg->css.cgroup,
+				    cfqg_to_blkg(ancestor)->blkcg->css.cgroup);
+}
+
 static inline void cfqg_get(struct cfq_group *cfqg)
 {
 	return blkg_get(cfqg_to_blkg(cfqg));
@@ -758,6 +765,11 @@ static void cfqg_stats_xfer_dead(struct cfq_group *cfqg)
 #else	/* CONFIG_CFQ_GROUP_IOSCHED */
 
 static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg) { return NULL; }
+static inline bool cfqg_is_descendant(struct cfq_group *cfqg,
+				      struct cfq_group *ancestor)
+{
+	return true;
+}
 static inline void cfqg_get(struct cfq_group *cfqg) { }
 static inline void cfqg_put(struct cfq_group *cfqg) { }
 
@@ -2897,6 +2909,7 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
+	struct cfq_rb_root *st = cfqq->service_tree;
 	struct cfq_io_cq *cic;
 	unsigned long sl, group_idle = 0;
 
@@ -2947,8 +2960,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		return;
 	}
 
-	/* There are other queues in the group, don't do group idle */
-	if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+	/*
+	 * There are other queues in the group or this is the only group and
+	 * it has too big thinktime, don't do group idle.
+	 */
+	if (group_idle &&
+	    (cfqq->cfqg->nr_cfqq > 1 ||
+	     cfq_io_thinktime_big(cfqd, &st->ttime, true)))
 		return;
 
 	cfq_mark_cfqq_wait_request(cfqq);
@@ -3947,16 +3965,27 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
 		return true;
 
-	if (new_cfqq->cfqg != cfqq->cfqg)
+	/*
+	 * Treat ancestors of current cgroup the same way as current cgroup.
+	 * For anybody else we disallow preemption to guarantee service
+	 * fairness among cgroups.
+	 */
+	if (!cfqg_is_descendant(cfqq->cfqg, new_cfqq->cfqg))
 		return false;
 
 	if (cfq_slice_used(cfqq))
 		return true;
 
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return true;
+
+	WARN_ON_ONCE(cfqq->ioprio_class != new_cfqq->ioprio_class);
 	/* Allow preemption only if we are idling on sync-noidle tree */
 	if (cfqd->serving_wl_type == SYNC_NOIDLE_WORKLOAD &&
 	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
-	    new_cfqq->service_tree->count == 2 &&
 	    RB_EMPTY_ROOT(&cfqq->sort_list))
 		return true;
 
@@ -3967,12 +3996,6 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
 		return true;
 
-	/*
-	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
-	 */
-	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
-		return true;
-
 	/* An idle queue should not be idle now for some reason */
 	if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
 		return true;