Merge commit 'v3.0-rc1' into kbuild/kbuild

15 files changed, 879 insertions, 439 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 2bef5705ce24..bcaf16ee6ad1 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -30,10 +30,8 @@ EXPORT_SYMBOL_GPL(blkio_root_cgroup);
 
 static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
 						  struct cgroup *);
-static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
-			      struct task_struct *, bool);
-static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
-			   struct cgroup *, struct task_struct *, bool);
+static int blkiocg_can_attach_task(struct cgroup *, struct task_struct *);
+static void blkiocg_attach_task(struct cgroup *, struct task_struct *);
 static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
 static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
 
@@ -46,8 +44,8 @@ static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
 struct cgroup_subsys blkio_subsys = {
 	.name = "blkio",
 	.create = blkiocg_create,
-	.can_attach = blkiocg_can_attach,
-	.attach = blkiocg_attach,
+	.can_attach_task = blkiocg_can_attach_task,
+	.attach_task = blkiocg_attach_task,
 	.destroy = blkiocg_destroy,
 	.populate = blkiocg_populate,
 #ifdef CONFIG_BLK_CGROUP
@@ -114,6 +112,13 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
+struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, blkio_subsys_id),
+			    struct blkio_cgroup, css);
+}
+EXPORT_SYMBOL_GPL(task_blkio_cgroup);
+
 static inline void
 blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
 {
@@ -378,25 +383,40 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
 
 	spin_lock_irqsave(&blkg->stats_lock, flags);
 	blkg->stats.time += time;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	blkg->stats.unaccounted_time += unaccounted_time;
+#endif
 	spin_unlock_irqrestore(&blkg->stats_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
 
+/*
+ * should be called under rcu read lock or queue lock to make sure blkg pointer
+ * is valid.
+ */
 void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
 				uint64_t bytes, bool direction, bool sync)
 {
-	struct blkio_group_stats *stats;
+	struct blkio_group_stats_cpu *stats_cpu;
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkg->stats_lock, flags);
-	stats = &blkg->stats;
-	stats->sectors += bytes >> 9;
-	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction,
-			sync);
-	blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes,
-			direction, sync);
-	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+	/*
+	 * Disabling interrupts to provide mutual exclusion between two
+	 * writes on same cpu. It probably is not needed for 64bit. Not
+	 * optimizing that case yet.
+	 */
+	local_irq_save(flags);
+
+	stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+	u64_stats_update_begin(&stats_cpu->syncp);
+	stats_cpu->sectors += bytes >> 9;
+	blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICED],
+			1, direction, sync);
+	blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICE_BYTES],
+			bytes, direction, sync);
+	u64_stats_update_end(&stats_cpu->syncp);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
 
@@ -419,18 +439,44 @@ void blkiocg_update_completion_stats(struct blkio_group *blkg,
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
 
+/*  Merged stats are per cpu.  */
 void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
 					bool sync)
 {
+	struct blkio_group_stats_cpu *stats_cpu;
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkg->stats_lock, flags);
-	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
-			sync);
-	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+	/*
+	 * Disabling interrupts to provide mutual exclusion between two
+	 * writes on same cpu. It probably is not needed for 64bit. Not
+	 * optimizing that case yet.
+	 */
+	local_irq_save(flags);
+
+	stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+	u64_stats_update_begin(&stats_cpu->syncp);
+	blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
+				direction, sync);
+	u64_stats_update_end(&stats_cpu->syncp);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
+/*
+ * This function allocates the per cpu stats for blkio_group. Should be called
+ * from sleepable context as alloc_per_cpu() requires that.
+ */
+int blkio_alloc_blkg_stats(struct blkio_group *blkg)
+{
+	/* Allocate memory for per cpu stats */
+	blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
+	if (!blkg->stats_cpu)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
+
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, void *key, dev_t dev,
 		enum blkio_policy_id plid)
@@ -501,6 +547,30 @@ struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
 }
 EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
 
+static void blkio_reset_stats_cpu(struct blkio_group *blkg)
+{
+	struct blkio_group_stats_cpu *stats_cpu;
+	int i, j, k;
+	/*
+	 * Note: On 64 bit arch this should not be an issue. This has the
+	 * possibility of returning some inconsistent value on 32bit arch
+	 * as 64bit update on 32bit is non atomic. Taking care of this
+	 * corner case makes code very complicated, like sending IPIs to
+	 * cpus, taking care of stats of offline cpus etc.
+	 *
+	 * reset stats is anyway more of a debug feature and this sounds a
+	 * corner case. So I am not complicating the code yet until and
+	 * unless this becomes a real issue.
+	 */
+	for_each_possible_cpu(i) {
+		stats_cpu = per_cpu_ptr(blkg->stats_cpu, i);
+		stats_cpu->sectors = 0;
+		for(j = 0; j < BLKIO_STAT_CPU_NR; j++)
+			for (k = 0; k < BLKIO_STAT_TOTAL; k++)
+				stats_cpu->stat_arr_cpu[j][k] = 0;
+	}
+}
+
 static int
 blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 {
@@ -545,7 +615,11 @@ blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 		}
 #endif
 		spin_unlock(&blkg->stats_lock);
+
+		/* Reset Per cpu stats which don't take blkg->stats_lock */
+		blkio_reset_stats_cpu(blkg);
 	}
+
 	spin_unlock_irq(&blkcg->lock);
 	return 0;
 }
@@ -591,6 +665,59 @@ static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
 	return val;
 }
 
+
+static uint64_t blkio_read_stat_cpu(struct blkio_group *blkg,
+			enum stat_type_cpu type, enum stat_sub_type sub_type)
+{
+	int cpu;
+	struct blkio_group_stats_cpu *stats_cpu;
+	u64 val = 0, tval;
+
+	for_each_possible_cpu(cpu) {
+		unsigned int start;
+		stats_cpu  = per_cpu_ptr(blkg->stats_cpu, cpu);
+
+		do {
+			start = u64_stats_fetch_begin(&stats_cpu->syncp);
+			if (type == BLKIO_STAT_CPU_SECTORS)
+				tval = stats_cpu->sectors;
+			else
+				tval = stats_cpu->stat_arr_cpu[type][sub_type];
+		} while(u64_stats_fetch_retry(&stats_cpu->syncp, start));
+
+		val += tval;
+	}
+
+	return val;
+}
+
+static uint64_t blkio_get_stat_cpu(struct blkio_group *blkg,
+		struct cgroup_map_cb *cb, dev_t dev, enum stat_type_cpu type)
+{
+	uint64_t disk_total, val;
+	char key_str[MAX_KEY_LEN];
+	enum stat_sub_type sub_type;
+
+	if (type == BLKIO_STAT_CPU_SECTORS) {
+		val = blkio_read_stat_cpu(blkg, type, 0);
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, val, cb, dev);
+	}
+
+	for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
+			sub_type++) {
+		blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
+		val = blkio_read_stat_cpu(blkg, type, sub_type);
+		cb->fill(cb, key_str, val);
+	}
+
+	disk_total = blkio_read_stat_cpu(blkg, type, BLKIO_STAT_READ) +
+			blkio_read_stat_cpu(blkg, type, BLKIO_STAT_WRITE);
+
+	blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
+	cb->fill(cb, key_str, disk_total);
+	return disk_total;
+}
+
 /* This should be called with blkg->stats_lock held */
 static uint64_t blkio_get_stat(struct blkio_group *blkg,
 		struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
@@ -602,9 +729,6 @@ static uint64_t blkio_get_stat(struct blkio_group *blkg,
 	if (type == BLKIO_STAT_TIME)
 		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
 					blkg->stats.time, cb, dev);
-	if (type == BLKIO_STAT_SECTORS)
-		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
-					blkg->stats.sectors, cb, dev);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	if (type == BLKIO_STAT_UNACCOUNTED_TIME)
 		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
@@ -868,7 +992,7 @@ static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
 }
 
 /*
- * Some rules/values in blkg have changed. Propogate those to respective
+ * Some rules/values in blkg have changed. Propagate those to respective
  * policies.
  */
 static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
@@ -903,7 +1027,7 @@ static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
 }
 
 /*
- * A policy node rule has been updated. Propogate this update to all the
+ * A policy node rule has been updated. Propagate this update to all the
  * block groups which might be affected by this update.
  */
 static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
@@ -1068,8 +1192,8 @@ static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
 }
 
 static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
-		struct cftype *cft, struct cgroup_map_cb *cb, enum stat_type type,
-		bool show_total)
+		struct cftype *cft, struct cgroup_map_cb *cb,
+		enum stat_type type, bool show_total, bool pcpu)
 {
 	struct blkio_group *blkg;
 	struct hlist_node *n;
@@ -1080,10 +1204,15 @@ static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
 		if (blkg->dev) {
 			if (!cftype_blkg_same_policy(cft, blkg))
 				continue;
-			spin_lock_irq(&blkg->stats_lock);
-			cgroup_total += blkio_get_stat(blkg, cb, blkg->dev,
-						type);
-			spin_unlock_irq(&blkg->stats_lock);
+			if (pcpu)
+				cgroup_total += blkio_get_stat_cpu(blkg, cb,
+						blkg->dev, type);
+			else {
+				spin_lock_irq(&blkg->stats_lock);
+				cgroup_total += blkio_get_stat(blkg, cb,
+						blkg->dev, type);
+				spin_unlock_irq(&blkg->stats_lock);
+			}
 		}
 	}
 	if (show_total)
@@ -1107,47 +1236,47 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
 		switch(name) {
 		case BLKIO_PROP_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_TIME, 0);
+						BLKIO_STAT_TIME, 0, 0);
 		case BLKIO_PROP_sectors:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SECTORS, 0);
+						BLKIO_STAT_CPU_SECTORS, 0, 1);
 		case BLKIO_PROP_io_service_bytes:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SERVICE_BYTES, 1);
+					BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
 		case BLKIO_PROP_io_serviced:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SERVICED, 1);
+						BLKIO_STAT_CPU_SERVICED, 1, 1);
 		case BLKIO_PROP_io_service_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SERVICE_TIME, 1);
+						BLKIO_STAT_SERVICE_TIME, 1, 0);
 		case BLKIO_PROP_io_wait_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_WAIT_TIME, 1);
+						BLKIO_STAT_WAIT_TIME, 1, 0);
 		case BLKIO_PROP_io_merged:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_MERGED, 1);
+						BLKIO_STAT_CPU_MERGED, 1, 1);
 		case BLKIO_PROP_io_queued:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_QUEUED, 1);
+						BLKIO_STAT_QUEUED, 1, 0);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 		case BLKIO_PROP_unaccounted_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_UNACCOUNTED_TIME, 0);
+					BLKIO_STAT_UNACCOUNTED_TIME, 0, 0);
 		case BLKIO_PROP_dequeue:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_DEQUEUE, 0);
+						BLKIO_STAT_DEQUEUE, 0, 0);
 		case BLKIO_PROP_avg_queue_size:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+					BLKIO_STAT_AVG_QUEUE_SIZE, 0, 0);
 		case BLKIO_PROP_group_wait_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_GROUP_WAIT_TIME, 0);
+					BLKIO_STAT_GROUP_WAIT_TIME, 0, 0);
 		case BLKIO_PROP_idle_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_IDLE_TIME, 0);
+						BLKIO_STAT_IDLE_TIME, 0, 0);
 		case BLKIO_PROP_empty_time:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_EMPTY_TIME, 0);
+						BLKIO_STAT_EMPTY_TIME, 0, 0);
 #endif
 		default:
 			BUG();
@@ -1157,10 +1286,10 @@ static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
 		switch(name){
 		case BLKIO_THROTL_io_service_bytes:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SERVICE_BYTES, 1);
+						BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
 		case BLKIO_THROTL_io_serviced:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_SERVICED, 1);
+						BLKIO_STAT_CPU_SERVICED, 1, 1);
 		default:
 			BUG();
 		}
@@ -1485,9 +1614,7 @@ done:
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkiocg_can_attach(struct cgroup_subsys *subsys,
-				struct cgroup *cgroup, struct task_struct *tsk,
-				bool threadgroup)
+static int blkiocg_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	struct io_context *ioc;
 	int ret = 0;
@@ -1502,9 +1629,7 @@ static int blkiocg_can_attach(struct cgroup_subsys *subsys,
 	return ret;
 }
 
-static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
-				struct cgroup *prev, struct task_struct *tsk,
-				bool threadgroup)
+static void blkiocg_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	struct io_context *ioc;
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 10919fae2d3a..a71d2904ffb9 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/u64_stats_sync.h>
 
 enum blkio_policy_id {
 	BLKIO_POLICY_PROP = 0,		/* Proportional Bandwidth division */
@@ -36,22 +37,15 @@ enum stat_type {
 	 * request completion for IOs doen by this cgroup. This may not be
 	 * accurate when NCQ is turned on. */
 	BLKIO_STAT_SERVICE_TIME = 0,
-	/* Total bytes transferred */
-	BLKIO_STAT_SERVICE_BYTES,
-	/* Total IOs serviced, post merge */
-	BLKIO_STAT_SERVICED,
 	/* Total time spent waiting in scheduler queue in ns */
 	BLKIO_STAT_WAIT_TIME,
-	/* Number of IOs merged */
-	BLKIO_STAT_MERGED,
 	/* Number of IOs queued up */
 	BLKIO_STAT_QUEUED,
 	/* All the single valued stats go below this */
 	BLKIO_STAT_TIME,
-	BLKIO_STAT_SECTORS,
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Time not charged to this cgroup */
 	BLKIO_STAT_UNACCOUNTED_TIME,
-#ifdef CONFIG_DEBUG_BLK_CGROUP
 	BLKIO_STAT_AVG_QUEUE_SIZE,
 	BLKIO_STAT_IDLE_TIME,
 	BLKIO_STAT_EMPTY_TIME,
@@ -60,6 +54,18 @@ enum stat_type {
 #endif
 };
 
+/* Per cpu stats */
+enum stat_type_cpu {
+	BLKIO_STAT_CPU_SECTORS,
+	/* Total bytes transferred */
+	BLKIO_STAT_CPU_SERVICE_BYTES,
+	/* Total IOs serviced, post merge */
+	BLKIO_STAT_CPU_SERVICED,
+	/* Number of IOs merged */
+	BLKIO_STAT_CPU_MERGED,
+	BLKIO_STAT_CPU_NR
+};
+
 enum stat_sub_type {
 	BLKIO_STAT_READ = 0,
 	BLKIO_STAT_WRITE,
@@ -116,11 +122,11 @@ struct blkio_cgroup {
 struct blkio_group_stats {
 	/* total disk time and nr sectors dispatched by this group */
 	uint64_t time;
-	uint64_t sectors;
-	/* Time not charged to this cgroup */
-	uint64_t unaccounted_time;
 	uint64_t stat_arr[BLKIO_STAT_QUEUED + 1][BLKIO_STAT_TOTAL];
 #ifdef CONFIG_DEBUG_BLK_CGROUP
+	/* Time not charged to this cgroup */
+	uint64_t unaccounted_time;
+
 	/* Sum of number of IOs queued across all samples */
 	uint64_t avg_queue_size_sum;
 	/* Count of samples taken for average */
@@ -145,6 +151,13 @@ struct blkio_group_stats {
 #endif
 };
 
+/* Per cpu blkio group stats */
+struct blkio_group_stats_cpu {
+	uint64_t sectors;
+	uint64_t stat_arr_cpu[BLKIO_STAT_CPU_NR][BLKIO_STAT_TOTAL];
+	struct u64_stats_sync syncp;
+};
+
 struct blkio_group {
 	/* An rcu protected unique identifier for the group */
 	void *key;
@@ -160,6 +173,8 @@ struct blkio_group {
 	/* Need to serialize the stats in the case of reset/update */
 	spinlock_t stats_lock;
 	struct blkio_group_stats stats;
+	/* Per cpu stats pointer */
+	struct blkio_group_stats_cpu __percpu *stats_cpu;
 };
 
 struct blkio_policy_node {
@@ -291,9 +306,11 @@ static inline void blkiocg_set_start_empty_time(struct blkio_group *blkg) {}
 #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
 extern struct blkio_cgroup blkio_root_cgroup;
 extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
+extern struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk);
 extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 	struct blkio_group *blkg, void *key, dev_t dev,
 	enum blkio_policy_id plid);
+extern int blkio_alloc_blkg_stats(struct blkio_group *blkg);
 extern int blkiocg_del_blkio_group(struct blkio_group *blkg);
 extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg,
 						void *key);
@@ -314,11 +331,15 @@ void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
 struct cgroup;
 static inline struct blkio_cgroup *
 cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
+static inline struct blkio_cgroup *
+task_blkio_cgroup(struct task_struct *tsk) { return NULL; }
 
 static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 		struct blkio_group *blkg, void *key, dev_t dev,
 		enum blkio_policy_id plid) {}
 
+static inline int blkio_alloc_blkg_stats(struct blkio_group *blkg) { return 0; }
+
 static inline int
 blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index e0a062363937..d2f8f4049abd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -198,26 +198,13 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
-/*
- * Make sure that plugs that were pending when this function was entered,
- * are now complete and requests pushed to the queue.
-*/
-static inline void queue_sync_plugs(struct request_queue *q)
-{
-	/*
-	 * If the current process is plugged and has barriers submitted,
-	 * we will livelock if we don't unplug first.
-	 */
-	blk_flush_plug(current);
-}
-
 static void blk_delay_work(struct work_struct *work)
 {
 	struct request_queue *q;
 
 	q = container_of(work, struct request_queue, delay_work.work);
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irq(q->queue_lock);
 }
 
@@ -233,7 +220,8 @@ static void blk_delay_work(struct work_struct *work)
  */
 void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 {
-	schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs));
+	queue_delayed_work(kblockd_workqueue, &q->delay_work,
+				msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_delay_queue);
 
@@ -251,7 +239,7 @@ void blk_start_queue(struct request_queue *q)
 	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -298,38 +286,44 @@ void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
 	cancel_delayed_work_sync(&q->delay_work);
-	queue_sync_plugs(q);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
 /**
  * __blk_run_queue - run a single device queue
  * @q:	The queue to run
- * @force_kblockd: Don't run @q->request_fn directly.  Use kblockd.
  *
  * Description:
  *    See @blk_run_queue. This variant must be called with the queue lock
  *    held and interrupts disabled.
- *
  */
-void __blk_run_queue(struct request_queue *q, bool force_kblockd)
+void __blk_run_queue(struct request_queue *q)
 {
 	if (unlikely(blk_queue_stopped(q)))
 		return;
 
-	/*
-	 * Only recurse once to avoid overrunning the stack, let the unplug
-	 * handling reinvoke the handler shortly if we already got there.
-	 */
-	if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
-		q->request_fn(q);
-		queue_flag_clear(QUEUE_FLAG_REENTER, q);
-	} else
-		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+	q->request_fn(q);
 }
 EXPORT_SYMBOL(__blk_run_queue);
 
 /**
+ * blk_run_queue_async - run a single device queue in workqueue context
+ * @q:	The queue to run
+ *
+ * Description:
+ *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf
+ *    of us.
+ */
+void blk_run_queue_async(struct request_queue *q)
+{
+	if (likely(!blk_queue_stopped(q))) {
+		__cancel_delayed_work(&q->delay_work);
+		queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
+	}
+}
+EXPORT_SYMBOL(blk_run_queue_async);
+
+/**
  * blk_run_queue - run a single device queue
  * @q: The queue to run
  *
@@ -342,7 +336,7 @@ void blk_run_queue(struct request_queue *q)
 	unsigned long flags;
 
 	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -351,6 +345,7 @@ void blk_put_queue(struct request_queue *q)
 {
 	kobject_put(&q->kobj);
 }
+EXPORT_SYMBOL(blk_put_queue);
 
 /*
  * Note: If a driver supplied the queue lock, it should not zap that lock
@@ -572,11 +567,10 @@ int blk_get_queue(struct request_queue *q)
 
 	return 1;
 }
+EXPORT_SYMBOL(blk_get_queue);
 
 static inline void blk_free_request(struct request_queue *q, struct request *rq)
 {
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
 	if (rq->cmd_flags & REQ_ELVPRIV)
 		elv_put_request(q, rq);
 	mempool_free(rq, q->rq.rq_pool);
@@ -991,7 +985,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 		blk_queue_end_tag(q, rq);
 
 	add_acct_request(q, rq, where);
-	__blk_run_queue(q, false);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1116,14 +1110,6 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
-	/*
-	 * Debug stuff, kill later
-	 */
-	if (!rq_mergeable(req)) {
-		blk_dump_rq_flags(req, "back");
-		return false;
-	}
-
 	if (!ll_back_merge_fn(q, req, bio))
 		return false;
 
@@ -1138,6 +1124,7 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	drive_stat_acct(req, 0);
+	elv_bio_merged(q, req, bio);
 	return true;
 }
 
@@ -1145,15 +1132,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 				    struct request *req, struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
-	sector_t sector;
-
-	/*
-	 * Debug stuff, kill later
-	 */
-	if (!rq_mergeable(req)) {
-		blk_dump_rq_flags(req, "front");
-		return false;
-	}
 
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
@@ -1163,8 +1141,6 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
 
-	sector = bio->bi_sector;
-
 	bio->bi_next = req->bio;
 	req->bio = bio;
 
@@ -1179,12 +1155,13 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	drive_stat_acct(req, 0);
+	elv_bio_merged(q, req, bio);
 	return true;
 }
 
 /*
  * Attempts to merge with the plugged list in the current process. Returns
- * true if merge was succesful, otherwise false.
+ * true if merge was successful, otherwise false.
  */
 static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
 			       struct bio *bio)
@@ -1264,14 +1241,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	el_ret = elv_merge(q, &req, bio);
 	if (el_ret == ELEVATOR_BACK_MERGE) {
-		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
 		if (bio_attempt_back_merge(q, req, bio)) {
 			if (!attempt_back_merge(q, req))
 				elv_merged_request(q, req, el_ret);
 			goto out_unlock;
 		}
 	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-		BUG_ON(req->cmd_flags & REQ_ON_PLUG);
 		if (bio_attempt_front_merge(q, req, bio)) {
 			if (!attempt_front_merge(q, req))
 				elv_merged_request(q, req, el_ret);
@@ -1311,23 +1286,27 @@ get_rq:
 
 	plug = current->plug;
 	if (plug) {
-		if (!plug->should_sort && !list_empty(&plug->list)) {
+		/*
+		 * If this is the first request added after a plug, fire
+		 * of a plug trace. If others have been added before, check
+		 * if we have multiple devices in this plug. If so, make a
+		 * note to sort the list before dispatch.
+		 */
+		if (list_empty(&plug->list))
+			trace_block_plug(q);
+		else if (!plug->should_sort) {
 			struct request *__rq;
 
 			__rq = list_entry_rq(plug->list.prev);
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
-		/*
-		 * Debug flag, kill later
-		 */
-		req->cmd_flags |= REQ_ON_PLUG;
 		list_add_tail(&req->queuelist, &plug->list);
 		drive_stat_acct(req, 1);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 out_unlock:
 		spin_unlock_irq(q->queue_lock);
 	}
@@ -1548,7 +1527,8 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		blk_throtl_bio(q, &bio);
+		if (blk_throtl_bio(q, &bio))
+			goto end_io;
 
 		/*
 		 * If bio = NULL, bio has been throttled and will be submitted
@@ -2163,7 +2143,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	 * size, something has gone terribly wrong.
 	 */
 	if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
-		printk(KERN_ERR "blk: request botched\n");
+		blk_dump_rq_flags(req, "request botched");
 		req->__data_len = blk_rq_cur_bytes(req);
 	}
 
@@ -2644,6 +2624,7 @@ void blk_start_plug(struct blk_plug *plug)
 
 	plug->magic = PLUG_MAGIC;
 	INIT_LIST_HEAD(&plug->list);
+	INIT_LIST_HEAD(&plug->cb_list);
 	plug->should_sort = 0;
 
 	/*
@@ -2665,40 +2646,97 @@ static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
 	struct request *rqa = container_of(a, struct request, queuelist);
 	struct request *rqb = container_of(b, struct request, queuelist);
 
-	return !(rqa->q == rqb->q);
+	return !(rqa->q <= rqb->q);
 }
 
-static void flush_plug_list(struct blk_plug *plug)
+/*
+ * If 'from_schedule' is true, then postpone the dispatch of requests
+ * until a safe kblockd context. We due this to avoid accidental big
+ * additional stack usage in driver dispatch, in places where the originally
+ * plugger did not intend it.
+ */
+static void queue_unplugged(struct request_queue *q, unsigned int depth,
+			    bool from_schedule)
+	__releases(q->queue_lock)
+{
+	trace_block_unplug(q, depth, !from_schedule);
+
+	/*
+	 * If we are punting this to kblockd, then we can safely drop
+	 * the queue_lock before waking kblockd (which needs to take
+	 * this lock).
+	 */
+	if (from_schedule) {
+		spin_unlock(q->queue_lock);
+		blk_run_queue_async(q);
+	} else {
+		__blk_run_queue(q);
+		spin_unlock(q->queue_lock);
+	}
+
+}
+
+static void flush_plug_callbacks(struct blk_plug *plug)
+{
+	LIST_HEAD(callbacks);
+
+	if (list_empty(&plug->cb_list))
+		return;
+
+	list_splice_init(&plug->cb_list, &callbacks);
+
+	while (!list_empty(&callbacks)) {
+		struct blk_plug_cb *cb = list_first_entry(&callbacks,
+							  struct blk_plug_cb,
+							  list);
+		list_del(&cb->list);
+		cb->callback(cb);
+	}
+}
+
+void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
 	struct request_queue *q;
 	unsigned long flags;
 	struct request *rq;
+	LIST_HEAD(list);
+	unsigned int depth;
 
 	BUG_ON(plug->magic != PLUG_MAGIC);
 
+	flush_plug_callbacks(plug);
 	if (list_empty(&plug->list))
 		return;
 
-	if (plug->should_sort)
-		list_sort(NULL, &plug->list, plug_rq_cmp);
+	list_splice_init(&plug->list, &list);
+
+	if (plug->should_sort) {
+		list_sort(NULL, &list, plug_rq_cmp);
+		plug->should_sort = 0;
+	}
 
 	q = NULL;
+	depth = 0;
+
+	/*
+	 * Save and disable interrupts here, to avoid doing it for every
+	 * queue lock we have to take.
+	 */
 	local_irq_save(flags);
-	while (!list_empty(&plug->list)) {
-		rq = list_entry_rq(plug->list.next);
+	while (!list_empty(&list)) {
+		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
-		BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG));
 		BUG_ON(!rq->q);
 		if (rq->q != q) {
-			if (q) {
-				__blk_run_queue(q, false);
-				spin_unlock(q->queue_lock);
-			}
+			/*
+			 * This drops the queue lock
+			 */
+			if (q)
+				queue_unplugged(q, depth, from_schedule);
 			q = rq->q;
+			depth = 0;
 			spin_lock(q->queue_lock);
 		}
-		rq->cmd_flags &= ~REQ_ON_PLUG;
-
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
@@ -2706,38 +2744,27 @@ static void flush_plug_list(struct blk_plug *plug)
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
-	}
 
-	if (q) {
-		__blk_run_queue(q, false);
-		spin_unlock(q->queue_lock);
+		depth++;
 	}
 
-	BUG_ON(!list_empty(&plug->list));
-	local_irq_restore(flags);
-}
-
-static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
-	flush_plug_list(plug);
+	/*
+	 * This drops the queue lock
+	 */
+	if (q)
+		queue_unplugged(q, depth, from_schedule);
 
-	if (plug == tsk->plug)
-		tsk->plug = NULL;
+	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
 {
-	if (plug)
-		__blk_finish_plug(current, plug);
-}
-EXPORT_SYMBOL(blk_finish_plug);
+	blk_flush_plug_list(plug, false);
 
-void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug)
-{
-	__blk_finish_plug(tsk, plug);
-	tsk->plug = plug;
+	if (plug == current->plug)
+		current->plug = NULL;
 }
-EXPORT_SYMBOL(__blk_flush_plug);
+EXPORT_SYMBOL(blk_finish_plug);
 
 int __init blk_dev_init(void)
 {
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 7482b7fa863b..8a0e7ec056e7 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -55,8 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	WARN_ON(irqs_disabled());
 	spin_lock_irq(q->queue_lock);
 	__elv_add_request(q, rq, where);
-	__blk_run_queue(q, false);
-	/* the queue is stopped so it won't be plugged+unplugged */
+	__blk_run_queue(q);
+	/* the queue is stopped so it won't be run */
 	if (rq->cmd_type == REQ_TYPE_PM_RESUME)
 		q->request_fn(q);
 	spin_unlock_irq(q->queue_lock);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 93d5fd8e51eb..bb21e4c36f70 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -212,13 +212,19 @@ static void flush_end_io(struct request *flush_rq, int error)
 	}
 
 	/*
-	 * Moving a request silently to empty queue_head may stall the
-	 * queue.  Kick the queue in those cases.  This function is called
-	 * from request completion path and calling directly into
-	 * request_fn may confuse the driver.  Always use kblockd.
+	 * Kick the queue to avoid stall for two cases:
+	 * 1. Moving a request silently to empty queue_head may stall the
+	 * queue.
+	 * 2. When flush request is running in non-queueable queue, the
+	 * queue is hold. Restart the queue after flush request is finished
+	 * to avoid stall.
+	 * This function is called from request completion path and calling
+	 * directly into request_fn may confuse the driver.  Always use
+	 * kblockd.
 	 */
-	if (queued)
-		__blk_run_queue(q, true);
+	if (queued || q->flush_queue_delayed)
+		blk_run_queue_async(q);
+	q->flush_queue_delayed = 0;
 }
 
 /**
@@ -261,7 +267,7 @@ static bool blk_kick_flush(struct request_queue *q)
 	q->flush_rq.end_io = flush_end_io;
 
 	q->flush_pending_idx ^= 1;
-	elv_insert(q, &q->flush_rq, ELEVATOR_INSERT_REQUEUE);
+	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
 	return true;
 }
 
@@ -274,14 +280,14 @@ static void flush_data_end_io(struct request *rq, int error)
 	 * the comment in flush_end_io().
 	 */
 	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
-		__blk_run_queue(q, true);
+		blk_run_queue_async(q);
 }
 
 /**
  * blk_insert_flush - insert a new FLUSH/FUA request
  * @rq: request to insert
  *
- * To be called from elv_insert() for %ELEVATOR_INSERT_FLUSH insertions.
+ * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions.
  * @rq is being submitted.  Analyze what needs to be done and put it on the
  * right queue.
  *
@@ -312,7 +318,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		list_add(&rq->queuelist, &q->queue_head);
+		list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
 
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 54bcba6c02a7..129b9e209a3b 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -30,6 +30,8 @@
 
 static struct kmem_cache *integrity_cachep;
 
+static const char *bi_unsupported_name = "unsupported";
+
 /**
  * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
  * @q:		request queue
@@ -358,6 +360,14 @@ static struct kobj_type integrity_ktype = {
 	.release	= blk_integrity_release,
 };
 
+bool blk_integrity_is_initialized(struct gendisk *disk)
+{
+	struct blk_integrity *bi = blk_get_integrity(disk);
+
+	return (bi && bi->name && strcmp(bi->name, bi_unsupported_name) != 0);
+}
+EXPORT_SYMBOL(blk_integrity_is_initialized);
+
 /**
  * blk_integrity_register - Register a gendisk as being integrity-capable
  * @disk:	struct gendisk pointer to make integrity-aware
@@ -407,7 +417,7 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi->get_tag_fn = template->get_tag_fn;
 		bi->tag_size = template->tag_size;
 	} else
-		bi->name = "unsupported";
+		bi->name = bi_unsupported_name;
 
 	return 0;
 }
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index b791022beef3..c898049dafd5 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -96,6 +96,9 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 		INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
 		INIT_HLIST_HEAD(&ret->cic_list);
 		ret->ioc_data = NULL;
+#if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE)
+		ret->cgroup_changed = 0;
+#endif
 	}
 
 	return ret;
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 25de73e4759b..78e627e2581d 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,17 +9,20 @@
 
 #include "blk.h"
 
-static void blkdev_discard_end_io(struct bio *bio, int err)
-{
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
+struct bio_batch {
+	atomic_t		done;
+	unsigned long		flags;
+	struct completion	*wait;
+};
 
-	if (bio->bi_private)
-		complete(bio->bi_private);
+static void bio_batch_end_io(struct bio *bio, int err)
+{
+	struct bio_batch *bb = bio->bi_private;
 
+	if (err && (err != -EOPNOTSUPP))
+		clear_bit(BIO_UPTODATE, &bb->flags);
+	if (atomic_dec_and_test(&bb->done))
+		complete(bb->wait);
 	bio_put(bio);
 }
 
@@ -41,6 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	struct request_queue *q = bdev_get_queue(bdev);
 	int type = REQ_WRITE | REQ_DISCARD;
 	unsigned int max_discard_sectors;
+	struct bio_batch bb;
 	struct bio *bio;
 	int ret = 0;
 
@@ -67,7 +71,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		type |= REQ_SECURE;
 	}
 
-	while (nr_sects && !ret) {
+	atomic_set(&bb.done, 1);
+	bb.flags = 1 << BIO_UPTODATE;
+	bb.wait = &wait;
+
+	while (nr_sects) {
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio) {
 			ret = -ENOMEM;
@@ -75,9 +83,9 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		}
 
 		bio->bi_sector = sector;
-		bio->bi_end_io = blkdev_discard_end_io;
+		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
-		bio->bi_private = &wait;
+		bio->bi_private = &bb;
 
 		if (nr_sects > max_discard_sectors) {
 			bio->bi_size = max_discard_sectors << 9;
@@ -88,45 +96,21 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			nr_sects = 0;
 		}
 
-		bio_get(bio);
+		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+	}
 
+	/* Wait for bios in-flight */
+	if (!atomic_dec_and_test(&bb.done))
 		wait_for_completion(&wait);
 
-		if (bio_flagged(bio, BIO_EOPNOTSUPP))
-			ret = -EOPNOTSUPP;
-		else if (!bio_flagged(bio, BIO_UPTODATE))
-			ret = -EIO;
-		bio_put(bio);
-	}
+	if (!test_bit(BIO_UPTODATE, &bb.flags))
+		ret = -EIO;
 
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
-struct bio_batch
-{
-	atomic_t 		done;
-	unsigned long 		flags;
-	struct completion 	*wait;
-};
-
-static void bio_batch_end_io(struct bio *bio, int err)
-{
-	struct bio_batch *bb = bio->bi_private;
-
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bb->flags);
-		else
-			clear_bit(BIO_UPTODATE, &bb->flags);
-	}
-	if (bb)
-		if (atomic_dec_and_test(&bb->done))
-			complete(bb->wait);
-	bio_put(bio);
-}
-
 /**
  * blkdev_issue_zeroout - generate number of zero filed write bios
  * @bdev:	blockdev to issue
@@ -151,7 +135,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	bb.flags = 1 << BIO_UPTODATE;
 	bb.wait = &wait;
 
-submit:
 	ret = 0;
 	while (nr_sects != 0) {
 		bio = bio_alloc(gfp_mask,
@@ -168,9 +151,6 @@ submit:
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
-			if (sz == 0)
-				/* bio has maximum size possible */
-				break;
 			ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
 			nr_sects -= ret >> 9;
 			sector += ret >> 9;
@@ -190,16 +170,6 @@ submit:
 		/* One of bios in the batch was completed with error.*/
 		ret = -EIO;
 
-	if (ret)
-		goto out;
-
-	if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
-	if (nr_sects != 0)
-		goto submit;
-out:
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 1fa769293597..fa1eb0449a05 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -120,7 +120,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
-	lim->discard_zeroes_data = -1;
+	lim->discard_zeroes_data = 1;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -166,6 +166,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 
 	blk_set_default_limits(&q->limits);
 	blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS);
+	q->limits.discard_zeroes_data = 0;
 
 	/*
 	 * by default assume old behaviour and bounce for any highmem page
@@ -790,6 +791,12 @@ void blk_queue_flush(struct request_queue *q, unsigned int flush)
 }
 EXPORT_SYMBOL_GPL(blk_queue_flush);
 
+void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
+{
+	q->flush_not_queueable = !queueable;
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 261c75c665ae..d935bd859c87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -66,14 +66,14 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 
 	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
 		blk_set_queue_full(q, BLK_RW_SYNC);
-	} else if (rl->count[BLK_RW_SYNC]+1 <= q->nr_requests) {
+	} else {
 		blk_clear_queue_full(q, BLK_RW_SYNC);
 		wake_up(&rl->wait[BLK_RW_SYNC]);
 	}
 
 	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
 		blk_set_queue_full(q, BLK_RW_ASYNC);
-	} else if (rl->count[BLK_RW_ASYNC]+1 <= q->nr_requests) {
+	} else {
 		blk_clear_queue_full(q, BLK_RW_ASYNC);
 		wake_up(&rl->wait[BLK_RW_ASYNC]);
 	}
@@ -152,7 +152,8 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->limits.max_discard_sectors << 9, page);
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)q->limits.max_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
@@ -498,7 +499,6 @@ int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
 	struct device *dev = disk_to_dev(disk);
-
 	struct request_queue *q = disk->queue;
 
 	if (WARN_ON(!q))
@@ -509,8 +509,10 @@ int blk_register_queue(struct gendisk *disk)
 		return ret;
 
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
-	if (ret < 0)
+	if (ret < 0) {
+		blk_trace_remove_sysfs(dev);
 		return ret;
+	}
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
@@ -521,7 +523,7 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret) {
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
 		kobject_del(&q->kobj);
-		blk_trace_remove_sysfs(disk_to_dev(disk));
+		blk_trace_remove_sysfs(dev);
 		kobject_put(&dev->kobj);
 		return ret;
 	}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 5352bdafbcf0..a62be8d0dc1b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -77,7 +77,9 @@ struct throtl_grp {
 	unsigned long slice_end[2];
 
 	/* Some throttle limits got updated for the group */
-	bool limits_changed;
+	int limits_changed;
+
+	struct rcu_head rcu_head;
 };
 
 struct throtl_data
@@ -88,7 +90,7 @@ struct throtl_data
 	/* service tree for active throtl groups */
 	struct throtl_rb_root tg_service_tree;
 
-	struct throtl_grp root_tg;
+	struct throtl_grp *root_tg;
 	struct request_queue *queue;
 
 	/* Total Number of queued bios on READ and WRITE lists */
@@ -102,7 +104,7 @@ struct throtl_data
 	/* Work for dispatching throttled bios */
 	struct delayed_work throtl_work;
 
-	bool limits_changed;
+	int limits_changed;
 };
 
 enum tg_state_flags {
@@ -151,57 +153,44 @@ static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg)
 	return tg;
 }
 
-static void throtl_put_tg(struct throtl_grp *tg)
+static void throtl_free_tg(struct rcu_head *head)
 {
-	BUG_ON(atomic_read(&tg->ref) <= 0);
-	if (!atomic_dec_and_test(&tg->ref))
-		return;
+	struct throtl_grp *tg;
+
+	tg = container_of(head, struct throtl_grp, rcu_head);
+	free_percpu(tg->blkg.stats_cpu);
 	kfree(tg);
 }
 
-static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
-			struct cgroup *cgroup)
+static void throtl_put_tg(struct throtl_grp *tg)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
-	struct throtl_grp *tg = NULL;
-	void *key = td;
-	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
-	unsigned int major, minor;
+	BUG_ON(atomic_read(&tg->ref) <= 0);
+	if (!atomic_dec_and_test(&tg->ref))
+		return;
 
 	/*
-	 * TODO: Speed up blkiocg_lookup_group() by maintaining a radix
-	 * tree of blkg (instead of traversing through hash list all
-	 * the time.
+	 * A group is freed in rcu manner. But having an rcu lock does not
+	 * mean that one can access all the fields of blkg and assume these
+	 * are valid. For example, don't try to follow throtl_data and
+	 * request queue links.
+	 *
+	 * Having a reference to blkg under an rcu allows acess to only
+	 * values local to groups like group stats and group rate limits
 	 */
+	call_rcu(&tg->rcu_head, throtl_free_tg);
+}
 
-	/*
-	 * This is the common case when there are no blkio cgroups.
- 	 * Avoid lookup in this case
- 	 */
-	if (blkcg == &blkio_root_cgroup)
-		tg = &td->root_tg;
-	else
-		tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
-
-	/* Fill in device details for root group */
-	if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
-		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-		tg->blkg.dev = MKDEV(major, minor);
-		goto done;
-	}
-
-	if (tg)
-		goto done;
-
-	tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
-	if (!tg)
-		goto done;
-
+static void throtl_init_group(struct throtl_grp *tg)
+{
 	INIT_HLIST_NODE(&tg->tg_node);
 	RB_CLEAR_NODE(&tg->rb_node);
 	bio_list_init(&tg->bio_lists[0]);
 	bio_list_init(&tg->bio_lists[1]);
-	td->limits_changed = false;
+	tg->limits_changed = false;
+
+	/* Practically unlimited BW */
+	tg->bps[0] = tg->bps[1] = -1;
+	tg->iops[0] = tg->iops[1] = -1;
 
 	/*
 	 * Take the initial reference that will be released on destroy
@@ -210,33 +199,181 @@ static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td,
 	 * exit or cgroup deletion path depending on who is exiting first.
 	 */
 	atomic_set(&tg->ref, 1);
+}
+
+/* Should be called with rcu read lock held (needed for blkcg) */
+static void
+throtl_add_group_to_td_list(struct throtl_data *td, struct throtl_grp *tg)
+{
+	hlist_add_head(&tg->tg_node, &td->tg_list);
+	td->nr_undestroyed_grps++;
+}
+
+static void
+__throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
+{
+	struct backing_dev_info *bdi = &td->queue->backing_dev_info;
+	unsigned int major, minor;
+
+	if (!tg || tg->blkg.dev)
+		return;
+
+	/*
+	 * Fill in device details for a group which might not have been
+	 * filled at group creation time as queue was being instantiated
+	 * and driver had not attached a device yet
+	 */
+	if (bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		tg->blkg.dev = MKDEV(major, minor);
+	}
+}
+
+/*
+ * Should be called with without queue lock held. Here queue lock will be
+ * taken rarely. It will be taken only once during life time of a group
+ * if need be
+ */
+static void
+throtl_tg_fill_dev_details(struct throtl_data *td, struct throtl_grp *tg)
+{
+	if (!tg || tg->blkg.dev)
+		return;
+
+	spin_lock_irq(td->queue->queue_lock);
+	__throtl_tg_fill_dev_details(td, tg);
+	spin_unlock_irq(td->queue->queue_lock);
+}
+
+static void throtl_init_add_tg_lists(struct throtl_data *td,
+			struct throtl_grp *tg, struct blkio_cgroup *blkcg)
+{
+	__throtl_tg_fill_dev_details(td, tg);
 
 	/* Add group onto cgroup list */
-	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
 	blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td,
-				MKDEV(major, minor), BLKIO_POLICY_THROTL);
+				tg->blkg.dev, BLKIO_POLICY_THROTL);
 
 	tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev);
 	tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev);
 	tg->iops[READ] = blkcg_get_read_iops(blkcg, tg->blkg.dev);
 	tg->iops[WRITE] = blkcg_get_write_iops(blkcg, tg->blkg.dev);
 
-	hlist_add_head(&tg->tg_node, &td->tg_list);
-	td->nr_undestroyed_grps++;
-done:
+	throtl_add_group_to_td_list(td, tg);
+}
+
+/* Should be called without queue lock and outside of rcu period */
+static struct throtl_grp *throtl_alloc_tg(struct throtl_data *td)
+{
+	struct throtl_grp *tg = NULL;
+	int ret;
+
+	tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node);
+	if (!tg)
+		return NULL;
+
+	ret = blkio_alloc_blkg_stats(&tg->blkg);
+
+	if (ret) {
+		kfree(tg);
+		return NULL;
+	}
+
+	throtl_init_group(tg);
 	return tg;
 }
 
-static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+static struct
+throtl_grp *throtl_find_tg(struct throtl_data *td, struct blkio_cgroup *blkcg)
 {
-	struct cgroup *cgroup;
 	struct throtl_grp *tg = NULL;
+	void *key = td;
+
+	/*
+	 * This is the common case when there are no blkio cgroups.
+ 	 * Avoid lookup in this case
+ 	 */
+	if (blkcg == &blkio_root_cgroup)
+		tg = td->root_tg;
+	else
+		tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key));
+
+	__throtl_tg_fill_dev_details(td, tg);
+	return tg;
+}
+
+/*
+ * This function returns with queue lock unlocked in case of error, like
+ * request queue is no more
+ */
+static struct throtl_grp * throtl_get_tg(struct throtl_data *td)
+{
+	struct throtl_grp *tg = NULL, *__tg = NULL;
+	struct blkio_cgroup *blkcg;
+	struct request_queue *q = td->queue;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
-	tg = throtl_find_alloc_tg(td, cgroup);
-	if (!tg)
-		tg = &td->root_tg;
+	blkcg = task_blkio_cgroup(current);
+	tg = throtl_find_tg(td, blkcg);
+	if (tg) {
+		rcu_read_unlock();
+		return tg;
+	}
+
+	/*
+	 * Need to allocate a group. Allocation of group also needs allocation
+	 * of per cpu stats which in-turn takes a mutex() and can block. Hence
+	 * we need to drop rcu lock and queue_lock before we call alloc
+	 *
+	 * Take the request queue reference to make sure queue does not
+	 * go away once we return from allocation.
+	 */
+	blk_get_queue(q);
+	rcu_read_unlock();
+	spin_unlock_irq(q->queue_lock);
+
+	tg = throtl_alloc_tg(td);
+	/*
+	 * We might have slept in group allocation. Make sure queue is not
+	 * dead
+	 */
+	if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+		blk_put_queue(q);
+		if (tg)
+			kfree(tg);
+
+		return ERR_PTR(-ENODEV);
+	}
+	blk_put_queue(q);
+
+	/* Group allocated and queue is still alive. take the lock */
+	spin_lock_irq(q->queue_lock);
+
+	/*
+	 * Initialize the new group. After sleeping, read the blkcg again.
+	 */
+	rcu_read_lock();
+	blkcg = task_blkio_cgroup(current);
+
+	/*
+	 * If some other thread already allocated the group while we were
+	 * not holding queue lock, free up the group
+	 */
+	__tg = throtl_find_tg(td, blkcg);
+
+	if (__tg) {
+		kfree(tg);
+		rcu_read_unlock();
+		return __tg;
+	}
+
+	/* Group allocation failed. Account the IO to root group */
+	if (!tg) {
+		tg = td->root_tg;
+		return tg;
+	}
+
+	throtl_init_add_tg_lists(td, tg, blkcg);
 	rcu_read_unlock();
 	return tg;
 }
@@ -545,6 +682,12 @@ static bool tg_with_in_bps_limit(struct throtl_data *td, struct throtl_grp *tg,
 	return 0;
 }
 
+static bool tg_no_rule_group(struct throtl_grp *tg, bool rw) {
+	if (tg->bps[rw] == -1 && tg->iops[rw] == -1)
+		return 1;
+	return 0;
+}
+
 /*
  * Returns whether one can dispatch a bio or not. Also returns approx number
  * of jiffies to wait before this bio is with-in IO rate and can be dispatched
@@ -609,10 +752,6 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	tg->bytes_disp[rw] += bio->bi_size;
 	tg->io_disp[rw]++;
 
-	/*
-	 * TODO: This will take blkg->stats_lock. Figure out a way
-	 * to avoid this cost.
-	 */
 	blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync);
 }
 
@@ -916,7 +1055,7 @@ static void throtl_update_blkio_group_common(struct throtl_data *td,
 /*
  * For all update functions, key should be a valid pointer because these
  * update functions are called under blkcg_lock, that means, blkg is
- * valid and in turn key is valid. queue exit path can not race becuase
+ * valid and in turn key is valid. queue exit path can not race because
  * of blkcg_lock
  *
  * Can not take queue lock in update functions as queue lock under blkcg_lock
@@ -990,15 +1129,51 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 	struct throtl_grp *tg;
 	struct bio *bio = *biop;
 	bool rw = bio_data_dir(bio), update_disptime = true;
+	struct blkio_cgroup *blkcg;
 
 	if (bio->bi_rw & REQ_THROTTLED) {
 		bio->bi_rw &= ~REQ_THROTTLED;
 		return 0;
 	}
 
+	/*
+	 * A throtl_grp pointer retrieved under rcu can be used to access
+	 * basic fields like stats and io rates. If a group has no rules,
+	 * just update the dispatch stats in lockless manner and return.
+	 */
+
+	rcu_read_lock();
+	blkcg = task_blkio_cgroup(current);
+	tg = throtl_find_tg(td, blkcg);
+	if (tg) {
+		throtl_tg_fill_dev_details(td, tg);
+
+		if (tg_no_rule_group(tg, rw)) {
+			blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
+					rw, bio->bi_rw & REQ_SYNC);
+			rcu_read_unlock();
+			return 0;
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * Either group has not been allocated yet or it is not an unlimited
+	 * IO group
+	 */
+
 	spin_lock_irq(q->queue_lock);
 	tg = throtl_get_tg(td);
 
+	if (IS_ERR(tg)) {
+		if (PTR_ERR(tg)	== -ENODEV) {
+			/*
+			 * Queue is gone. No queue lock held here.
+			 */
+			return -ENODEV;
+		}
+	}
+
 	if (tg->nr_queued[rw]) {
 		/*
 		 * There is already another bio queued in same dir. No
@@ -1061,39 +1236,24 @@ int blk_throtl_init(struct request_queue *q)
 	INIT_HLIST_HEAD(&td->tg_list);
 	td->tg_service_tree = THROTL_RB_ROOT;
 	td->limits_changed = false;
+	INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
 
-	/* Init root group */
-	tg = &td->root_tg;
-	INIT_HLIST_NODE(&tg->tg_node);
-	RB_CLEAR_NODE(&tg->rb_node);
-	bio_list_init(&tg->bio_lists[0]);
-	bio_list_init(&tg->bio_lists[1]);
-
-	/* Practically unlimited BW */
-	tg->bps[0] = tg->bps[1] = -1;
-	tg->iops[0] = tg->iops[1] = -1;
-	td->limits_changed = false;
+	/* alloc and Init root group. */
+	td->queue = q;
+	tg = throtl_alloc_tg(td);
 
-	/*
-	 * Set root group reference to 2. One reference will be dropped when
-	 * all groups on tg_list are being deleted during queue exit. Other
-	 * reference will remain there as we don't want to delete this group
-	 * as it is statically allocated and gets destroyed when throtl_data
-	 * goes away.
-	 */
-	atomic_set(&tg->ref, 2);
-	hlist_add_head(&tg->tg_node, &td->tg_list);
-	td->nr_undestroyed_grps++;
+	if (!tg) {
+		kfree(td);
+		return -ENOMEM;
+	}
 
-	INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work);
+	td->root_tg = tg;
 
 	rcu_read_lock();
-	blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td,
-					0, BLKIO_POLICY_THROTL);
+	throtl_init_add_tg_lists(td, tg, &blkio_root_cgroup);
 	rcu_read_unlock();
 
 	/* Attach throtl data to request queue */
-	td->queue = q;
 	q->td = td;
 	return 0;
 }
diff --git a/block/blk.h b/block/blk.h
index c8db371a921d..d6586287adc9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -32,7 +32,7 @@ enum rq_atomic_flags {
 
 /*
  * EH timer and IO completion will both attempt to 'grab' the request, make
- * sure that only one of them suceeds
+ * sure that only one of them succeeds
  */
 static inline int blk_mark_rq_complete(struct request *rq)
 {
@@ -62,7 +62,28 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return rq;
 		}
 
-		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+		/*
+		 * Flush request is running and flush request isn't queueable
+		 * in the drive, we can hold the queue till flush request is
+		 * finished. Even we don't do this, driver can't dispatch next
+		 * requests and will requeue them. And this can improve
+		 * throughput too. For example, we have request flush1, write1,
+		 * flush 2. flush1 is dispatched, then queue is hold, write1
+		 * isn't inserted to queue. After flush1 is finished, flush2
+		 * will be dispatched. Since disk cache is already clean,
+		 * flush2 will be finished very soon, so looks like flush2 is
+		 * folded to flush1.
+		 * Since the queue is hold, a flag is set to indicate the queue
+		 * should be restarted later. Please see flush_end_io() for
+		 * details.
+		 */
+		if (q->flush_pending_idx != q->flush_running_idx &&
+				!queue_flush_queueable(q)) {
+			q->flush_queue_delayed = 1;
+			return NULL;
+		}
+		if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags) ||
+		    !q->elevator->ops->elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7785169f3c8f..7c52d6888924 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -300,7 +300,9 @@ struct cfq_data {
 
 	/* List of cfq groups being managed on this device*/
 	struct hlist_head cfqg_list;
-	struct rcu_head rcu;
+
+	/* Number of groups which are on blkcg->blkg_list */
+	unsigned int nr_blkcg_linked_grps;
 };
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
@@ -665,15 +667,11 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 	if (rq2 == NULL)
 		return rq1;
 
-	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
-		return rq1;
-	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
-		return rq2;
-	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
-		return rq1;
-	else if ((rq2->cmd_flags & REQ_META) &&
-		 !(rq1->cmd_flags & REQ_META))
-		return rq2;
+	if (rq_is_sync(rq1) != rq_is_sync(rq2))
+		return rq_is_sync(rq1) ? rq1 : rq2;
+
+	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META)
+		return rq1->cmd_flags & REQ_META ? rq1 : rq2;
 
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
@@ -888,7 +886,7 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	/*
 	 * Currently put the group at the end. Later implement something
 	 * so that groups get lesser vtime based on their weights, so that
-	 * if group does not loose all if it was not continously backlogged.
+	 * if group does not loose all if it was not continuously backlogged.
 	 */
 	n = rb_last(&st->rb);
 	if (n) {
@@ -1014,29 +1012,47 @@ void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
 	cfqg->needs_update = true;
 }
 
-static struct cfq_group *
-cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd,
+			struct cfq_group *cfqg, struct blkio_cgroup *blkcg)
 {
-	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
-	struct cfq_group *cfqg = NULL;
-	void *key = cfqd;
-	int i, j;
-	struct cfq_rb_root *st;
 	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
 	unsigned int major, minor;
 
-	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
-	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+	/*
+	 * Add group onto cgroup list. It might happen that bdi->dev is
+	 * not initialized yet. Initialize this new group without major
+	 * and minor info and this info will be filled in once a new thread
+	 * comes for IO.
+	 */
+	if (bdi->dev) {
 		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-		cfqg->blkg.dev = MKDEV(major, minor);
-		goto done;
-	}
-	if (cfqg || !create)
-		goto done;
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
+					(void *)cfqd, MKDEV(major, minor));
+	} else
+		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
+					(void *)cfqd, 0);
+
+	cfqd->nr_blkcg_linked_grps++;
+	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+
+	/* Add group on cfqd list */
+	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+}
+
+/*
+ * Should be called from sleepable context. No request queue lock as per
+ * cpu stats are allocated dynamically and alloc_percpu needs to be called
+ * from sleepable context.
+ */
+static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd)
+{
+	struct cfq_group *cfqg = NULL;
+	int i, j, ret;
+	struct cfq_rb_root *st;
 
 	cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
 	if (!cfqg)
-		goto done;
+		return NULL;
 
 	for_each_cfqg_st(cfqg, i, j, st)
 		*st = CFQ_RB_ROOT;
@@ -1050,43 +1066,94 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	 */
 	cfqg->ref = 1;
 
+	ret = blkio_alloc_blkg_stats(&cfqg->blkg);
+	if (ret) {
+		kfree(cfqg);
+		return NULL;
+	}
+
+	return cfqg;
+}
+
+static struct cfq_group *
+cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
+{
+	struct cfq_group *cfqg = NULL;
+	void *key = cfqd;
+	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+	unsigned int major, minor;
+
 	/*
-	 * Add group onto cgroup list. It might happen that bdi->dev is
-	 * not initialized yet. Initialize this new group without major
-	 * and minor info and this info will be filled in once a new thread
-	 * comes for IO. See code above.
+	 * This is the common case when there are no blkio cgroups.
+	 * Avoid lookup in this case
 	 */
-	if (bdi->dev) {
-		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
-		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
-					MKDEV(major, minor));
-	} else
-		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
-					0);
-
-	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);
+	if (blkcg == &blkio_root_cgroup)
+		cfqg = &cfqd->root_group;
+	else
+		cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
 
-	/* Add group on cfqd list */
-	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfqg->blkg.dev = MKDEV(major, minor);
+	}
 
-done:
 	return cfqg;
 }
 
 /*
- * Search for the cfq group current task belongs to. If create = 1, then also
- * create the cfq group if it does not exist. request_queue lock must be held.
+ * Search for the cfq group current task belongs to. request_queue lock must
+ * be held.
  */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {
-	struct cgroup *cgroup;
-	struct cfq_group *cfqg = NULL;
+	struct blkio_cgroup *blkcg;
+	struct cfq_group *cfqg = NULL, *__cfqg = NULL;
+	struct request_queue *q = cfqd->queue;
 
 	rcu_read_lock();
-	cgroup = task_cgroup(current, blkio_subsys_id);
-	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
-	if (!cfqg && create)
+	blkcg = task_blkio_cgroup(current);
+	cfqg = cfq_find_cfqg(cfqd, blkcg);
+	if (cfqg) {
+		rcu_read_unlock();
+		return cfqg;
+	}
+
+	/*
+	 * Need to allocate a group. Allocation of group also needs allocation
+	 * of per cpu stats which in-turn takes a mutex() and can block. Hence
+	 * we need to drop rcu lock and queue_lock before we call alloc.
+	 *
+	 * Not taking any queue reference here and assuming that queue is
+	 * around by the time we return. CFQ queue allocation code does
+	 * the same. It might be racy though.
+	 */
+
+	rcu_read_unlock();
+	spin_unlock_irq(q->queue_lock);
+
+	cfqg = cfq_alloc_cfqg(cfqd);
+
+	spin_lock_irq(q->queue_lock);
+
+	rcu_read_lock();
+	blkcg = task_blkio_cgroup(current);
+
+	/*
+	 * If some other thread already allocated the group while we were
+	 * not holding queue lock, free up the group
+	 */
+	__cfqg = cfq_find_cfqg(cfqd, blkcg);
+
+	if (__cfqg) {
+		kfree(cfqg);
+		rcu_read_unlock();
+		return __cfqg;
+	}
+
+	if (!cfqg)
 		cfqg = &cfqd->root_group;
+
+	cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg);
 	rcu_read_unlock();
 	return cfqg;
 }
@@ -1119,6 +1186,7 @@ static void cfq_put_cfqg(struct cfq_group *cfqg)
 		return;
 	for_each_cfqg_st(cfqg, i, j, st)
 		BUG_ON(!RB_EMPTY_ROOT(&st->rb));
+	free_percpu(cfqg->blkg.stats_cpu);
 	kfree(cfqg);
 }
 
@@ -1177,7 +1245,7 @@ void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
 }
 
 #else /* GROUP_IOSCHED */
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
 {
 	return &cfqd->root_group;
 }
@@ -1211,7 +1279,6 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_rb_root *service_tree;
 	int left;
 	int new_cfqq = 1;
-	int group_changed = 0;
 
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
 						cfqq_type(cfqq));
@@ -1282,7 +1349,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	rb_link_node(&cfqq->rb_node, parent, p);
 	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
 	service_tree->count++;
-	if ((add_front || !new_cfqq) && !group_changed)
+	if (add_front || !new_cfqq)
 		return;
 	cfq_group_notify_queue_add(cfqd, cfqq->cfqg);
 }
@@ -2030,7 +2097,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);
 
-	return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
+	return 2 * base_rq * (IOPRIO_BE_NR - cfqq->ioprio);
 }
 
 /*
@@ -2582,28 +2649,20 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 }
 
 /*
- * Must always be called with the rcu_read_lock() held
+ * Call func for each cic attached to this ioc.
  */
 static void
-__call_for_each_cic(struct io_context *ioc,
-		    void (*func)(struct io_context *, struct cfq_io_context *))
+call_for_each_cic(struct io_context *ioc,
+		  void (*func)(struct io_context *, struct cfq_io_context *))
 {
 	struct cfq_io_context *cic;
 	struct hlist_node *n;
 
+	rcu_read_lock();
+
 	hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list)
 		func(ioc, cic);
-}
 
-/*
- * Call func for each cic attached to this ioc.
- */
-static void
-call_for_each_cic(struct io_context *ioc,
-		  void (*func)(struct io_context *, struct cfq_io_context *))
-{
-	rcu_read_lock();
-	__call_for_each_cic(ioc, func);
 	rcu_read_unlock();
 }
 
@@ -2664,7 +2723,7 @@ static void cfq_free_io_context(struct io_context *ioc)
 	 * should be ok to iterate over the known list, we will see all cic's
 	 * since no new ones are added.
 	 */
-	__call_for_each_cic(ioc, cic_free_func);
+	call_for_each_cic(ioc, cic_free_func);
 }
 
 static void cfq_put_cooperator(struct cfq_queue *cfqq)
@@ -2920,7 +2979,7 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
 	struct cfq_group *cfqg;
 
 retry:
-	cfqg = cfq_get_cfqg(cfqd, 1);
+	cfqg = cfq_get_cfqg(cfqd);
 	cic = cfq_cic_lookup(cfqd, ioc);
 	/* cic always exists here */
 	cfqq = cic_to_cfqq(cic, is_sync);
@@ -3368,7 +3427,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			    cfqd->busy_queues > 1) {
 				cfq_del_timer(cfqd, cfqq);
 				cfq_clear_cfqq_wait_request(cfqq);
-				__blk_run_queue(cfqd->queue, false);
+				__blk_run_queue(cfqd->queue);
 			} else {
 				cfq_blkiocg_update_idle_time_stats(
 						&cfqq->cfqg->blkg);
@@ -3383,7 +3442,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		__blk_run_queue(cfqd->queue, false);
+		__blk_run_queue(cfqd->queue);
 	}
 }
 
@@ -3743,7 +3802,7 @@ static void cfq_kick_queue(struct work_struct *work)
 	struct request_queue *q = cfqd->queue;
 
 	spin_lock_irq(q->queue_lock);
-	__blk_run_queue(cfqd->queue, false);
+	__blk_run_queue(cfqd->queue);
 	spin_unlock_irq(q->queue_lock);
 }
 
@@ -3824,15 +3883,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
 		cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
-static void cfq_cfqd_free(struct rcu_head *head)
-{
-	kfree(container_of(head, struct cfq_data, rcu));
-}
-
 static void cfq_exit_queue(struct elevator_queue *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
 	struct request_queue *q = cfqd->queue;
+	bool wait = false;
 
 	cfq_shutdown_timer_wq(cfqd);
 
@@ -3851,7 +3906,13 @@ static void cfq_exit_queue(struct elevator_queue *e)
 
 	cfq_put_async_queues(cfqd);
 	cfq_release_cfq_groups(cfqd);
-	cfq_blkiocg_del_blkio_group(&cfqd->root_group.blkg);
+
+	/*
+	 * If there are groups which we could not unlink from blkcg list,
+	 * wait for a rcu period for them to be freed.
+	 */
+	if (cfqd->nr_blkcg_linked_grps)
+		wait = true;
 
 	spin_unlock_irq(q->queue_lock);
 
@@ -3861,8 +3922,25 @@ static void cfq_exit_queue(struct elevator_queue *e)
 	ida_remove(&cic_index_ida, cfqd->cic_index);
 	spin_unlock(&cic_index_lock);
 
-	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
-	call_rcu(&cfqd->rcu, cfq_cfqd_free);
+	/*
+	 * Wait for cfqg->blkg->key accessors to exit their grace periods.
+	 * Do this wait only if there are other unlinked groups out
+	 * there. This can happen if cgroup deletion path claimed the
+	 * responsibility of cleaning up a group before queue cleanup code
+	 * get to the group.
+	 *
+	 * Do not call synchronize_rcu() unconditionally as there are drivers
+	 * which create/delete request queue hundreds of times during scan/boot
+	 * and synchronize_rcu() can take significant time and slow down boot.
+	 */
+	if (wait)
+		synchronize_rcu();
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	/* Free up per cpu stats for root group */
+	free_percpu(cfqd->root_group.blkg.stats_cpu);
+#endif
+	kfree(cfqd);
 }
 
 static int cfq_alloc_cic_index(void)
@@ -3895,8 +3973,12 @@ static void *cfq_init_queue(struct request_queue *q)
 		return NULL;
 
 	cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
-	if (!cfqd)
+	if (!cfqd) {
+		spin_lock(&cic_index_lock);
+		ida_remove(&cic_index_ida, i);
+		spin_unlock(&cic_index_lock);
 		return NULL;
+	}
 
 	/*
 	 * Don't need take queue_lock in the routine, since we are
@@ -3918,14 +4000,29 @@ static void *cfq_init_queue(struct request_queue *q)
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	/*
-	 * Take a reference to root group which we never drop. This is just
-	 * to make sure that cfq_put_cfqg() does not try to kfree root group
+	 * Set root group reference to 2. One reference will be dropped when
+	 * all groups on cfqd->cfqg_list are being deleted during queue exit.
+	 * Other reference will remain there as we don't want to delete this
+	 * group as it is statically allocated and gets destroyed when
+	 * throtl_data goes away.
 	 */
-	cfqg->ref = 1;
+	cfqg->ref = 2;
+
+	if (blkio_alloc_blkg_stats(&cfqg->blkg)) {
+		kfree(cfqg);
+		kfree(cfqd);
+		return NULL;
+	}
+
 	rcu_read_lock();
+
 	cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
 					(void *)cfqd, 0);
 	rcu_read_unlock();
+	cfqd->nr_blkcg_linked_grps++;
+
+	/* Add group on cfqd->cfqg_list */
+	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 #endif
 	/*
 	 * Not strictly needed (since RB_ROOT just clears the node and we
diff --git a/block/elevator.c b/block/elevator.c
index c387d3168734..b0b38ce0dcb6 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -155,13 +155,8 @@ static struct elevator_type *elevator_get(const char *name)
 
 	e = elevator_find(name);
 	if (!e) {
-		char elv[ELV_NAME_MAX + strlen("-iosched")];
-
 		spin_unlock(&elv_list_lock);
-
-		snprintf(elv, sizeof(elv), "%s-iosched", name);
-
-		request_module("%s", elv);
+		request_module("%s-iosched", name);
 		spin_lock(&elv_list_lock);
 		e = elevator_find(name);
 	}
@@ -421,8 +416,6 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	struct list_head *entry;
 	int stop_flags;
 
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
 	if (q->last_merge == rq)
 		q->last_merge = NULL;
 
@@ -610,7 +603,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 
 	rq->cmd_flags &= ~REQ_STARTED;
 
-	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
+	__elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
 
 void elv_drain_elevator(struct request_queue *q)
@@ -642,7 +635,7 @@ void elv_quiesce_start(struct request_queue *q)
 	 */
 	elv_drain_elevator(q);
 	while (q->rq.elvpriv) {
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 		spin_unlock_irq(q->queue_lock);
 		msleep(10);
 		spin_lock_irq(q->queue_lock);
@@ -655,12 +648,24 @@ void elv_quiesce_end(struct request_queue *q)
 	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
 }
 
-void elv_insert(struct request_queue *q, struct request *rq, int where)
+void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 {
 	trace_block_rq_insert(q, rq);
 
 	rq->q = q;
 
+	if (rq->cmd_flags & REQ_SOFTBARRIER) {
+		/* barriers are scheduling boundary, update end_sector */
+		if (rq->cmd_type == REQ_TYPE_FS ||
+		    (rq->cmd_flags & REQ_DISCARD)) {
+			q->end_sector = rq_end_sector(rq);
+			q->boundary_rq = rq;
+		}
+	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
+		    (where == ELEVATOR_INSERT_SORT ||
+		     where == ELEVATOR_INSERT_SORT_MERGE))
+		where = ELEVATOR_INSERT_BACK;
+
 	switch (where) {
 	case ELEVATOR_INSERT_REQUEUE:
 	case ELEVATOR_INSERT_FRONT:
@@ -682,7 +687,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		 *   with anything.  There's no point in delaying queue
 		 *   processing.
 		 */
-		__blk_run_queue(q, false);
+		__blk_run_queue(q);
 		break;
 
 	case ELEVATOR_INSERT_SORT_MERGE:
@@ -722,24 +727,6 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		BUG();
 	}
 }
-
-void __elv_add_request(struct request_queue *q, struct request *rq, int where)
-{
-	BUG_ON(rq->cmd_flags & REQ_ON_PLUG);
-
-	if (rq->cmd_flags & REQ_SOFTBARRIER) {
-		/* barriers are scheduling boundary, update end_sector */
-		if (rq->cmd_type == REQ_TYPE_FS ||
-		    (rq->cmd_flags & REQ_DISCARD)) {
-			q->end_sector = rq_end_sector(rq);
-			q->boundary_rq = rq;
-		}
-	} else if (!(rq->cmd_flags & REQ_ELVPRIV) &&
-		    where == ELEVATOR_INSERT_SORT)
-		where = ELEVATOR_INSERT_BACK;
-
-	elv_insert(q, rq, where);
-}
 EXPORT_SYMBOL(__elv_add_request);
 
 void elv_add_request(struct request_queue *q, struct request *rq, int where)
diff --git a/block/genhd.c b/block/genhd.c
index c91a2dac6b6b..95822ae25cfe 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -739,7 +739,7 @@ void __init printk_all_partitions(void)
 
 		/*
 		 * Don't show empty devices or things that have been
-		 * surpressed
+		 * suppressed
 		 */
 		if (get_capacity(disk) == 0 ||
 		    (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO))
@@ -1588,9 +1588,13 @@ static void disk_events_workfn(struct work_struct *work)
 
 	spin_unlock_irq(&ev->lock);
 
-	/* tell userland about new events */
+	/*
+	 * Tell userland about new events.  Only the events listed in
+	 * @disk->events are reported.  Unlisted events are processed the
+	 * same internally but never get reported to userland.
+	 */
 	for (i = 0; i < ARRAY_SIZE(disk_uevents); i++)
-		if (events & (1 << i))
+		if (events & disk->events & (1 << i))
 			envp[nr_events++] = disk_uevents[i];
 
 	if (nr_events)
@@ -1724,7 +1728,7 @@ static void disk_add_events(struct gendisk *disk)
 {
 	struct disk_events *ev;
 
-	if (!disk->fops->check_events || !(disk->events | disk->async_events))
+	if (!disk->fops->check_events)
 		return;
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);