Merge branch 'master' into for-next

12 files changed, 1349 insertions, 295 deletions

diff --git a/block/Kconfig b/block/Kconfig
index f9e89f4d94b..9be0b56eaee 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,29 +77,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_CGROUP
-	tristate "Block cgroup support"
-	depends on CGROUPS
-	depends on CFQ_GROUP_IOSCHED
-	default n
-	---help---
-	Generic block IO controller cgroup interface. This is the common
-	cgroup interface which should be used by various IO controlling
-	policies.
-
-	Currently, CFQ IO scheduler uses it to recognize task groups and
-	control disk bandwidth allocation (proportional time slice allocation)
-	to such task groups.
-
-config DEBUG_BLK_CGROUP
-	bool
-	depends on BLK_CGROUP
-	default n
-	---help---
-	Enable some debugging help. Currently it stores the cgroup path
-	in the blk group which can be used by cfq for tracing various
-	group related activity.
-
 endif # BLOCK
 
 config BLOCK_COMPAT
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index fc71cf071fb..3199b76f795 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -23,7 +23,8 @@ config IOSCHED_DEADLINE
 
 config IOSCHED_CFQ
 	tristate "CFQ I/O scheduler"
-	select BLK_CGROUP if CFQ_GROUP_IOSCHED
+	# If BLK_CGROUP is a module, CFQ has to be built as module.
+	depends on (BLK_CGROUP=m && m) || !BLK_CGROUP || BLK_CGROUP=y
 	default y
 	---help---
 	  The CFQ I/O scheduler tries to distribute bandwidth equally
@@ -33,22 +34,15 @@ config IOSCHED_CFQ
 
 	  This is the default I/O scheduler.
 
+	  Note: If BLK_CGROUP=m, then CFQ can be built only as module.
+
 config CFQ_GROUP_IOSCHED
 	bool "CFQ Group Scheduling support"
-	depends on IOSCHED_CFQ && CGROUPS
+	depends on IOSCHED_CFQ && BLK_CGROUP
 	default n
 	---help---
 	  Enable group IO scheduling in CFQ.
 
-config DEBUG_CFQ_IOSCHED
-	bool "Debug CFQ Scheduling"
-	depends on CFQ_GROUP_IOSCHED
-	select DEBUG_BLK_CGROUP
-	default n
-	---help---
-	  Enable CFQ IO scheduling debugging in CFQ. Currently it makes
-	  blktrace output more verbose.
-
 choice
 	prompt "Default I/O scheduler"
 	default DEFAULT_CFQ
diff --git a/block/Makefile b/block/Makefile
index cb2d515ebd6..0bb499a739c 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			blk-iopoll.o ioctl.o genhd.o scsi_ioctl.o
+			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 6d88544b677..0d710c9d403 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -286,26 +286,31 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
 			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	}
-
-	complete(bio->bi_private);
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	bio_put(bio);
 }
 
 /**
  * blkdev_issue_flush - queue a flush
  * @bdev:	blockdev to issue flush for
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
  * @error_sector:	error sector
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
  *
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to.
+ *    wish to. If WAIT flag is not passed then caller may check only what
+ *    request was pushed in some internal queue for later handling.
  */
-int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
+int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
+		sector_t *error_sector, unsigned long flags)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	struct request_queue *q;
 	struct bio *bio;
-	int ret;
+	int ret = 0;
 
 	if (bdev->bd_disk == NULL)
 		return -ENXIO;
@@ -314,23 +319,25 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	if (!q)
 		return -ENXIO;
 
-	bio = bio_alloc(GFP_KERNEL, 0);
+	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_end_io = bio_end_empty_barrier;
-	bio->bi_private = &wait;
 	bio->bi_bdev = bdev;
-	submit_bio(WRITE_BARRIER, bio);
-
-	wait_for_completion(&wait);
+	if (test_bit(BLKDEV_WAIT, &flags))
+		bio->bi_private = &wait;
 
-	/*
-	 * The driver must store the error location in ->bi_sector, if
-	 * it supports it. For non-stacked drivers, this should be copied
-	 * from blk_rq_pos(rq).
-	 */
-	if (error_sector)
-		*error_sector = bio->bi_sector;
+	bio_get(bio);
+	submit_bio(WRITE_BARRIER, bio);
+	if (test_bit(BLKDEV_WAIT, &flags)) {
+		wait_for_completion(&wait);
+		/*
+		 * The driver must store the error location in ->bi_sector, if
+		 * it supports it. For non-stacked drivers, this should be
+		 * copied from blk_rq_pos(rq).
+		 */
+		if (error_sector)
+			*error_sector = bio->bi_sector;
+	}
 
-	ret = 0;
 	if (bio_flagged(bio, BIO_EOPNOTSUPP))
 		ret = -EOPNOTSUPP;
 	else if (!bio_flagged(bio, BIO_UPTODATE))
@@ -340,107 +347,3 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
-
-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);
-	}
-
-	if (bio->bi_private)
-		complete(bio->bi_private);
-	__free_page(bio_page(bio));
-
-	bio_put(bio);
-}
-
-/**
- * blkdev_issue_discard - queue a discard
- * @bdev:	blockdev to issue discard for
- * @sector:	start sector
- * @nr_sects:	number of sectors to discard
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	DISCARD_FL_* flags to control behaviour
- *
- * Description:
- *    Issue a discard request for the sectors in question.
- */
-int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int flags)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct request_queue *q = bdev_get_queue(bdev);
-	int type = flags & DISCARD_FL_BARRIER ?
-		DISCARD_BARRIER : DISCARD_NOBARRIER;
-	struct bio *bio;
-	struct page *page;
-	int ret = 0;
-
-	if (!q)
-		return -ENXIO;
-
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
-
-	while (nr_sects && !ret) {
-		unsigned int sector_size = q->limits.logical_block_size;
-		unsigned int max_discard_sectors =
-			min(q->limits.max_discard_sectors, UINT_MAX >> 9);
-
-		bio = bio_alloc(gfp_mask, 1);
-		if (!bio)
-			goto out;
-		bio->bi_sector = sector;
-		bio->bi_end_io = blkdev_discard_end_io;
-		bio->bi_bdev = bdev;
-		if (flags & DISCARD_FL_WAIT)
-			bio->bi_private = &wait;
-
-		/*
-		 * Add a zeroed one-sector payload as that's what
-		 * our current implementations need.  If we'll ever need
-		 * more the interface will need revisiting.
-		 */
-		page = alloc_page(gfp_mask | __GFP_ZERO);
-		if (!page)
-			goto out_free_bio;
-		if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size)
-			goto out_free_page;
-
-		/*
-		 * And override the bio size - the way discard works we
-		 * touch many more blocks on disk than the actual payload
-		 * length.
-		 */
-		if (nr_sects > max_discard_sectors) {
-			bio->bi_size = max_discard_sectors << 9;
-			nr_sects -= max_discard_sectors;
-			sector += max_discard_sectors;
-		} else {
-			bio->bi_size = nr_sects << 9;
-			nr_sects = 0;
-		}
-
-		bio_get(bio);
-		submit_bio(type, bio);
-
-		if (flags & DISCARD_FL_WAIT)
-			wait_for_completion(&wait);
-
-		if (bio_flagged(bio, BIO_EOPNOTSUPP))
-			ret = -EOPNOTSUPP;
-		else if (!bio_flagged(bio, BIO_UPTODATE))
-			ret = -EIO;
-		bio_put(bio);
-	}
-	return ret;
-out_free_page:
-	__free_page(page);
-out_free_bio:
-	bio_put(bio);
-out:
-	return -ENOMEM;
-}
-EXPORT_SYMBOL(blkdev_issue_discard);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 2cc682b860e..a6809645d21 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -15,8 +15,12 @@
 #include <linux/kdev_t.h>
 #include <linux/module.h>
 #include <linux/err.h>
+#include <linux/blkdev.h>
 #include <linux/slab.h>
 #include "blk-cgroup.h"
+#include <linux/genhd.h>
+
+#define MAX_KEY_LEN 100
 
 static DEFINE_SPINLOCK(blkio_list_lock);
 static LIST_HEAD(blkio_list);
@@ -49,6 +53,32 @@ struct cgroup_subsys blkio_subsys = {
 };
 EXPORT_SYMBOL_GPL(blkio_subsys);
 
+static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
+					    struct blkio_policy_node *pn)
+{
+	list_add(&pn->node, &blkcg->policy_list);
+}
+
+/* Must be called with blkcg->lock held */
+static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
+{
+	list_del(&pn->node);
+}
+
+/* Must be called with blkcg->lock held */
+static struct blkio_policy_node *
+blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev)
+{
+	struct blkio_policy_node *pn;
+
+	list_for_each_entry(pn, &blkcg->policy_list, node) {
+		if (pn->dev == dev)
+			return pn;
+	}
+
+	return NULL;
+}
+
 struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 {
 	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
@@ -56,13 +86,259 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
 }
 EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
 
-void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
-			unsigned long time, unsigned long sectors)
+/*
+ * Add to the appropriate stat variable depending on the request type.
+ * This should be called with the blkg->stats_lock held.
+ */
+static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
+				bool sync)
+{
+	if (direction)
+		stat[BLKIO_STAT_WRITE] += add;
+	else
+		stat[BLKIO_STAT_READ] += add;
+	if (sync)
+		stat[BLKIO_STAT_SYNC] += add;
+	else
+		stat[BLKIO_STAT_ASYNC] += add;
+}
+
+/*
+ * Decrements the appropriate stat variable if non-zero depending on the
+ * request type. Panics on value being zero.
+ * This should be called with the blkg->stats_lock held.
+ */
+static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)
+{
+	if (direction) {
+		BUG_ON(stat[BLKIO_STAT_WRITE] == 0);
+		stat[BLKIO_STAT_WRITE]--;
+	} else {
+		BUG_ON(stat[BLKIO_STAT_READ] == 0);
+		stat[BLKIO_STAT_READ]--;
+	}
+	if (sync) {
+		BUG_ON(stat[BLKIO_STAT_SYNC] == 0);
+		stat[BLKIO_STAT_SYNC]--;
+	} else {
+		BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);
+		stat[BLKIO_STAT_ASYNC]--;
+	}
+}
+
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_set_start_group_wait_time(struct blkio_group *blkg,
+						struct blkio_group *curr_blkg)
+{
+	if (blkio_blkg_waiting(&blkg->stats))
+		return;
+	if (blkg == curr_blkg)
+		return;
+	blkg->stats.start_group_wait_time = sched_clock();
+	blkio_mark_blkg_waiting(&blkg->stats);
+}
+
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_update_group_wait_time(struct blkio_group_stats *stats)
+{
+	unsigned long long now;
+
+	if (!blkio_blkg_waiting(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_group_wait_time))
+		stats->group_wait_time += now - stats->start_group_wait_time;
+	blkio_clear_blkg_waiting(stats);
+}
+
+/* This should be called with the blkg->stats_lock held. */
+static void blkio_end_empty_time(struct blkio_group_stats *stats)
+{
+	unsigned long long now;
+
+	if (!blkio_blkg_empty(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_empty_time))
+		stats->empty_time += now - stats->start_empty_time;
+	blkio_clear_blkg_empty(stats);
+}
+
+void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	BUG_ON(blkio_blkg_idling(&blkg->stats));
+	blkg->stats.start_idle_time = sched_clock();
+	blkio_mark_blkg_idling(&blkg->stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats);
+
+void blkiocg_update_idle_time_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	unsigned long long now;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	if (blkio_blkg_idling(stats)) {
+		now = sched_clock();
+		if (time_after64(now, stats->start_idle_time))
+			stats->idle_time += now - stats->start_idle_time;
+		blkio_clear_blkg_idling(stats);
+	}
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);
+
+void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	stats->avg_queue_size_sum +=
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];
+	stats->avg_queue_size_samples++;
+	blkio_update_group_wait_time(stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);
+
+void blkiocg_set_start_empty_time(struct blkio_group *blkg)
+{
+	unsigned long flags;
+	struct blkio_group_stats *stats;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+
+	if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
+			stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
+		spin_unlock_irqrestore(&blkg->stats_lock, flags);
+		return;
+	}
+
+	/*
+	 * group is already marked empty. This can happen if cfqq got new
+	 * request in parent group and moved to this group while being added
+	 * to service tree. Just ignore the event and move on.
+	 */
+	if(blkio_blkg_empty(stats)) {
+		spin_unlock_irqrestore(&blkg->stats_lock, flags);
+		return;
+	}
+
+	stats->start_empty_time = sched_clock();
+	blkio_mark_blkg_empty(stats);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
+
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+			unsigned long dequeue)
+{
+	blkg->stats.dequeue += dequeue;
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
+#else
+static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
+					struct blkio_group *curr_blkg) {}
+static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
+#endif
+
+void blkiocg_update_io_add_stats(struct blkio_group *blkg,
+			struct blkio_group *curr_blkg, bool direction,
+			bool sync)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,
+			sync);
+	blkio_end_empty_time(&blkg->stats);
+	blkio_set_start_group_wait_time(blkg, curr_blkg);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);
+
+void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
+						bool direction, bool sync)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],
+					direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
+
+void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	blkg->stats.time += time;
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
+
+void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
+				uint64_t bytes, bool direction, bool sync)
 {
-	blkg->time += time;
-	blkg->sectors += sectors;
+	struct blkio_group_stats *stats;
+	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);
 }
-EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
+
+void blkiocg_update_completion_stats(struct blkio_group *blkg,
+	uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
+{
+	struct blkio_group_stats *stats;
+	unsigned long flags;
+	unsigned long long now = sched_clock();
+
+	spin_lock_irqsave(&blkg->stats_lock, flags);
+	stats = &blkg->stats;
+	if (time_after64(now, io_start_time))
+		blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME],
+				now - io_start_time, direction, sync);
+	if (time_after64(io_start_time, start_time))
+		blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME],
+				io_start_time - start_time, direction, sync);
+	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
+
+void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
+					bool sync)
+{
+	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);
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
 void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 			struct blkio_group *blkg, void *key, dev_t dev)
@@ -70,14 +346,13 @@ void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
 	unsigned long flags;
 
 	spin_lock_irqsave(&blkcg->lock, flags);
+	spin_lock_init(&blkg->stats_lock);
 	rcu_assign_pointer(blkg->key, key);
 	blkg->blkcg_id = css_id(&blkcg->css);
 	hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
 	spin_unlock_irqrestore(&blkcg->lock, flags);
-#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* Need to take css reference ? */
 	cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
-#endif
 	blkg->dev = dev;
 }
 EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
@@ -101,17 +376,16 @@ int blkiocg_del_blkio_group(struct blkio_group *blkg)
 
 	rcu_read_lock();
 	css = css_lookup(&blkio_subsys, blkg->blkcg_id);
-	if (!css)
-		goto out;
-
-	blkcg = container_of(css, struct blkio_cgroup, css);
-	spin_lock_irqsave(&blkcg->lock, flags);
-	if (!hlist_unhashed(&blkg->blkcg_node)) {
-		__blkiocg_del_blkio_group(blkg);
-		ret = 0;
+	if (css) {
+		blkcg = container_of(css, struct blkio_cgroup, css);
+		spin_lock_irqsave(&blkcg->lock, flags);
+		if (!hlist_unhashed(&blkg->blkcg_node)) {
+			__blkiocg_del_blkio_group(blkg);
+			ret = 0;
+		}
+		spin_unlock_irqrestore(&blkcg->lock, flags);
 	}
-	spin_unlock_irqrestore(&blkcg->lock, flags);
-out:
+
 	rcu_read_unlock();
 	return ret;
 }
@@ -154,6 +428,7 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 	struct blkio_group *blkg;
 	struct hlist_node *n;
 	struct blkio_policy_type *blkiop;
+	struct blkio_policy_node *pn;
 
 	if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
 		return -EINVAL;
@@ -162,7 +437,13 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 	spin_lock(&blkio_list_lock);
 	spin_lock_irq(&blkcg->lock);
 	blkcg->weight = (unsigned int)val;
+
 	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		pn = blkio_policy_search_node(blkcg, blkg->dev);
+
+		if (pn)
+			continue;
+
 		list_for_each_entry(blkiop, &blkio_list, list)
 			blkiop->ops.blkio_update_group_weight_fn(blkg,
 					blkcg->weight);
@@ -172,13 +453,154 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
 	return 0;
 }
 
-#define SHOW_FUNCTION_PER_GROUP(__VAR)					\
+static int
+blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
+{
+	struct blkio_cgroup *blkcg;
+	struct blkio_group *blkg;
+	struct blkio_group_stats *stats;
+	struct hlist_node *n;
+	uint64_t queued[BLKIO_STAT_TOTAL];
+	int i;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	bool idling, waiting, empty;
+	unsigned long long now = sched_clock();
+#endif
+
+	blkcg = cgroup_to_blkio_cgroup(cgroup);
+	spin_lock_irq(&blkcg->lock);
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		spin_lock(&blkg->stats_lock);
+		stats = &blkg->stats;
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+		idling = blkio_blkg_idling(stats);
+		waiting = blkio_blkg_waiting(stats);
+		empty = blkio_blkg_empty(stats);
+#endif
+		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
+			queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i];
+		memset(stats, 0, sizeof(struct blkio_group_stats));
+		for (i = 0; i < BLKIO_STAT_TOTAL; i++)
+			stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+		if (idling) {
+			blkio_mark_blkg_idling(stats);
+			stats->start_idle_time = now;
+		}
+		if (waiting) {
+			blkio_mark_blkg_waiting(stats);
+			stats->start_group_wait_time = now;
+		}
+		if (empty) {
+			blkio_mark_blkg_empty(stats);
+			stats->start_empty_time = now;
+		}
+#endif
+		spin_unlock(&blkg->stats_lock);
+	}
+	spin_unlock_irq(&blkcg->lock);
+	return 0;
+}
+
+static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str,
+				int chars_left, bool diskname_only)
+{
+	snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev));
+	chars_left -= strlen(str);
+	if (chars_left <= 0) {
+		printk(KERN_WARNING
+			"Possibly incorrect cgroup stat display format");
+		return;
+	}
+	if (diskname_only)
+		return;
+	switch (type) {
+	case BLKIO_STAT_READ:
+		strlcat(str, " Read", chars_left);
+		break;
+	case BLKIO_STAT_WRITE:
+		strlcat(str, " Write", chars_left);
+		break;
+	case BLKIO_STAT_SYNC:
+		strlcat(str, " Sync", chars_left);
+		break;
+	case BLKIO_STAT_ASYNC:
+		strlcat(str, " Async", chars_left);
+		break;
+	case BLKIO_STAT_TOTAL:
+		strlcat(str, " Total", chars_left);
+		break;
+	default:
+		strlcat(str, " Invalid", chars_left);
+	}
+}
+
+static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
+				struct cgroup_map_cb *cb, dev_t dev)
+{
+	blkio_get_key_name(0, dev, str, chars_left, true);
+	cb->fill(cb, str, val);
+	return val;
+}
+
+/* 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)
+{
+	uint64_t disk_total;
+	char key_str[MAX_KEY_LEN];
+	enum stat_sub_type sub_type;
+
+	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_AVG_QUEUE_SIZE) {
+		uint64_t sum = blkg->stats.avg_queue_size_sum;
+		uint64_t samples = blkg->stats.avg_queue_size_samples;
+		if (samples)
+			do_div(sum, samples);
+		else
+			sum = 0;
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);
+	}
+	if (type == BLKIO_STAT_GROUP_WAIT_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.group_wait_time, cb, dev);
+	if (type == BLKIO_STAT_IDLE_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.idle_time, cb, dev);
+	if (type == BLKIO_STAT_EMPTY_TIME)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.empty_time, cb, dev);
+	if (type == BLKIO_STAT_DEQUEUE)
+		return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
+					blkg->stats.dequeue, cb, dev);
+#endif
+
+	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);
+		cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]);
+	}
+	disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] +
+			blkg->stats.stat_arr[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;
+}
+
+#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total)		\
 static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
-			struct cftype *cftype, struct seq_file *m)	\
+		struct cftype *cftype, struct cgroup_map_cb *cb)	\
 {									\
 	struct blkio_cgroup *blkcg;					\
 	struct blkio_group *blkg;					\
 	struct hlist_node *n;						\
+	uint64_t cgroup_total = 0;					\
 									\
 	if (!cgroup_lock_live_group(cgroup))				\
 		return -ENODEV;						\
@@ -186,50 +608,293 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup,		\
 	blkcg = cgroup_to_blkio_cgroup(cgroup);				\
 	rcu_read_lock();						\
 	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\
-		if (blkg->dev)						\
-			seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev),	\
-				 MINOR(blkg->dev), blkg->__VAR);	\
+		if (blkg->dev) {					\
+			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)							\
+		cb->fill(cb, "Total", cgroup_total);			\
 	rcu_read_unlock();						\
 	cgroup_unlock();						\
 	return 0;							\
 }
 
-SHOW_FUNCTION_PER_GROUP(time);
-SHOW_FUNCTION_PER_GROUP(sectors);
+SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0);
+SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1);
+SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1);
+SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1);
+SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1);
+SHOW_FUNCTION_PER_GROUP(io_merged, BLKIO_STAT_MERGED, 1);
+SHOW_FUNCTION_PER_GROUP(io_queued, BLKIO_STAT_QUEUED, 1);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
-SHOW_FUNCTION_PER_GROUP(dequeue);
+SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0);
+SHOW_FUNCTION_PER_GROUP(avg_queue_size, BLKIO_STAT_AVG_QUEUE_SIZE, 0);
+SHOW_FUNCTION_PER_GROUP(group_wait_time, BLKIO_STAT_GROUP_WAIT_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(idle_time, BLKIO_STAT_IDLE_TIME, 0);
+SHOW_FUNCTION_PER_GROUP(empty_time, BLKIO_STAT_EMPTY_TIME, 0);
 #endif
 #undef SHOW_FUNCTION_PER_GROUP
 
-#ifdef CONFIG_DEBUG_BLK_CGROUP
-void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
-			unsigned long dequeue)
+static int blkio_check_dev_num(dev_t dev)
 {
-	blkg->dequeue += dequeue;
+	int part = 0;
+	struct gendisk *disk;
+
+	disk = get_gendisk(dev, &part);
+	if (!disk || part)
+		return -ENODEV;
+
+	return 0;
+}
+
+static int blkio_policy_parse_and_set(char *buf,
+				      struct blkio_policy_node *newpn)
+{
+	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
+	int ret;
+	unsigned long major, minor, temp;
+	int i = 0;
+	dev_t dev;
+
+	memset(s, 0, sizeof(s));
+
+	while ((p = strsep(&buf, " ")) != NULL) {
+		if (!*p)
+			continue;
+
+		s[i++] = p;
+
+		/* Prevent from inputing too many things */
+		if (i == 3)
+			break;
+	}
+
+	if (i != 2)
+		return -EINVAL;
+
+	p = strsep(&s[0], ":");
+	if (p != NULL)
+		major_s = p;
+	else
+		return -EINVAL;
+
+	minor_s = s[0];
+	if (!minor_s)
+		return -EINVAL;
+
+	ret = strict_strtoul(major_s, 10, &major);
+	if (ret)
+		return -EINVAL;
+
+	ret = strict_strtoul(minor_s, 10, &minor);
+	if (ret)
+		return -EINVAL;
+
+	dev = MKDEV(major, minor);
+
+	ret = blkio_check_dev_num(dev);
+	if (ret)
+		return ret;
+
+	newpn->dev = dev;
+
+	if (s[1] == NULL)
+		return -EINVAL;
+
+	ret = strict_strtoul(s[1], 10, &temp);
+	if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+	    temp > BLKIO_WEIGHT_MAX)
+		return -EINVAL;
+
+	newpn->weight =  temp;
+
+	return 0;
+}
+
+unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
+			      dev_t dev)
+{
+	struct blkio_policy_node *pn;
+
+	pn = blkio_policy_search_node(blkcg, dev);
+	if (pn)
+		return pn->weight;
+	else
+		return blkcg->weight;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_weight);
+
+
+static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
+				       const char *buffer)
+{
+	int ret = 0;
+	char *buf;
+	struct blkio_policy_node *newpn, *pn;
+	struct blkio_cgroup *blkcg;
+	struct blkio_group *blkg;
+	int keep_newpn = 0;
+	struct hlist_node *n;
+	struct blkio_policy_type *blkiop;
+
+	buf = kstrdup(buffer, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
+	if (!newpn) {
+		ret = -ENOMEM;
+		goto free_buf;
+	}
+
+	ret = blkio_policy_parse_and_set(buf, newpn);
+	if (ret)
+		goto free_newpn;
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+	spin_lock_irq(&blkcg->lock);
+
+	pn = blkio_policy_search_node(blkcg, newpn->dev);
+	if (!pn) {
+		if (newpn->weight != 0) {
+			blkio_policy_insert_node(blkcg, newpn);
+			keep_newpn = 1;
+		}
+		spin_unlock_irq(&blkcg->lock);
+		goto update_io_group;
+	}
+
+	if (newpn->weight == 0) {
+		/* weight == 0 means deleteing a specific weight */
+		blkio_policy_delete_node(pn);
+		spin_unlock_irq(&blkcg->lock);
+		goto update_io_group;
+	}
+	spin_unlock_irq(&blkcg->lock);
+
+	pn->weight = newpn->weight;
+
+update_io_group:
+	/* update weight for each cfqg */
+	spin_lock(&blkio_list_lock);
+	spin_lock_irq(&blkcg->lock);
+
+	hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+		if (newpn->dev == blkg->dev) {
+			list_for_each_entry(blkiop, &blkio_list, list)
+				blkiop->ops.blkio_update_group_weight_fn(blkg,
+							 newpn->weight ?
+							 newpn->weight :
+							 blkcg->weight);
+		}
+	}
+
+	spin_unlock_irq(&blkcg->lock);
+	spin_unlock(&blkio_list_lock);
+
+free_newpn:
+	if (!keep_newpn)
+		kfree(newpn);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
+				      struct seq_file *m)
+{
+	struct blkio_cgroup *blkcg;
+	struct blkio_policy_node *pn;
+
+	seq_printf(m, "dev\tweight\n");
+
+	blkcg = cgroup_to_blkio_cgroup(cgrp);
+	if (!list_empty(&blkcg->policy_list)) {
+		spin_lock_irq(&blkcg->lock);
+		list_for_each_entry(pn, &blkcg->policy_list, node) {
+			seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+				   MINOR(pn->dev), pn->weight);
+		}
+		spin_unlock_irq(&blkcg->lock);
+	}