Merge tag 'for-5.5/block-20191121' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Due to more granular branches, this one is small and will be followed
  with other core branches that add specific features. I meant to just
  have a core and drivers branch, but external dependencies we ended up
  adding a few more that are also core.

  The changes are:

   - Fixes and improvements for the zoned device support (Ajay, Damien)

   - sed-opal table writing and datastore UID (Revanth)

   - blk-cgroup (and bfq) blk-cgroup stat fixes (Tejun)

   - Improvements to the block stats tracking (Pavel)

   - Fix for overruning sysfs buffer for large number of CPUs (Ming)

   - Optimization for small IO (Ming, Christoph)

   - Fix typo in RWH lifetime hint (Eugene)

   - Dead code removal and documentation (Bart)

   - Reduction in memory usage for queue and tag set (Bart)

   - Kerneldoc header documentation (André)

   - Device/partition revalidation fixes (Jan)

   - Stats tracking for flush requests (Konstantin)

   - Various other little fixes here and there (et al)"

* tag 'for-5.5/block-20191121' of git://git.kernel.dk/linux-block: (48 commits)
  Revert "block: split bio if the only bvec's length is > SZ_4K"
  block: add iostat counters for flush requests
  block,bfq: Skip tracing hooks if possible
  block: sed-opal: Introduce SUM_SET_LIST parameter and append it using 'add_token_u64'
  blk-cgroup: cgroup_rstat_updated() shouldn't be called on cgroup1
  block: Don't disable interrupts in trigger_softirq()
  sbitmap: Delete sbitmap_any_bit_clear()
  blk-mq: Delete blk_mq_has_free_tags() and blk_mq_can_queue()
  block: split bio if the only bvec's length is > SZ_4K
  block: still try to split bio if the bvec crosses pages
  blk-cgroup: separate out blkg_rwstat under CONFIG_BLK_CGROUP_RWSTAT
  blk-cgroup: reimplement basic IO stats using cgroup rstat
  blk-cgroup: remove now unused blkg_print_stat_{bytes|ios}_recursive()
  blk-throtl: stop using blkg->stat_bytes and ->stat_ios
  bfq-iosched: stop using blkg->stat_bytes and ->stat_ios
  bfq-iosched: relocate bfqg_*rwstat*() helpers
  block: add zone open, close and finish ioctl support
  block: add zone open, close and finish operations
  block: Simplify REQ_OP_ZONE_RESET_ALL handling
  block: Remove REQ_OP_ZONE_RESET plugging
  ...

31 files changed, 963 insertions, 516 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 41c0917ce622..c23094a14a2b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME
 config BLK_SCSI_REQUEST
 	bool
 
+config BLK_CGROUP_RWSTAT
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
@@ -86,6 +89,7 @@ config BLK_DEV_ZONED
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
+	select BLK_CGROUP_RWSTAT
 	---help---
 	Block layer bio throttling support. It can be used to limit
 	the IO rate to a device. IO rate policies are per cgroup and
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index b89310a022ad..7df14133adc8 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -31,6 +31,7 @@ config IOSCHED_BFQ
 config BFQ_GROUP_IOSCHED
        bool "BFQ hierarchical scheduling support"
        depends on IOSCHED_BFQ && BLK_CGROUP
+       select BLK_CGROUP_RWSTAT
        ---help---
 
        Enable hierarchical scheduling in BFQ, using the blkio
diff --git a/block/Makefile b/block/Makefile
index 9ef57ace90d4..205a5f2fef17 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
+obj-$(CONFIG_BLK_CGROUP_RWSTAT)	+= blk-cgroup-rwstat.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_BLK_CGROUP_IOCOST)	+= blk-iocost.o
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 86a607cf19a1..cea0ae12f937 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -347,6 +347,14 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg)
 	bfqg_put(bfqg);
 }
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq)
+{
+	struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg);
+
+	blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq));
+	blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1);
+}
+
 /* @stats = 0 */
 static void bfqg_stats_reset(struct bfqg_stats *stats)
 {
@@ -431,6 +439,8 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+	blkg_rwstat_exit(&stats->bytes);
+	blkg_rwstat_exit(&stats->ios);
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
@@ -448,6 +458,10 @@ static void bfqg_stats_exit(struct bfqg_stats *stats)
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+	if (blkg_rwstat_init(&stats->bytes, gfp) ||
+	    blkg_rwstat_init(&stats->ios, gfp))
+		return -ENOMEM;
+
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
@@ -1057,18 +1071,35 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	return bfq_io_set_device_weight(of, buf, nbytes, off);
 }
 
-#ifdef CONFIG_BFQ_CGROUP_DEBUG
-static int bfqg_print_stat(struct seq_file *sf, void *v)
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
 	return 0;
 }
 
-static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+					struct blkg_policy_data *pd, int off)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
-			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
+	struct blkg_rwstat_sample sum;
+
+	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+#ifdef CONFIG_BFQ_CGROUP_DEBUG
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
 	return 0;
 }
 
@@ -1097,15 +1128,6 @@ static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, sum);
 }
 
-static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
-					struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample sum;
-
-	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
-	return __blkg_prfill_rwstat(sf, pd, &sum);
-}
-
 static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
@@ -1114,18 +1136,11 @@ static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
-			  seq_cft(sf)->private, true);
-	return 0;
-}
-
 static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
 			       int off)
 {
-	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+	struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg);
+	u64 sum = blkg_rwstat_total(&bfqg->stats.bytes);
 
 	return __blkg_prfill_u64(sf, pd, sum >> 9);
 }
@@ -1142,8 +1157,8 @@ static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
 {
 	struct blkg_rwstat_sample tmp;
 
-	blkg_rwstat_recursive_sum(pd->blkg, NULL,
-			offsetof(struct blkcg_gq, stat_bytes), &tmp);
+	blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq,
+			offsetof(struct bfq_group, stats.bytes), &tmp);
 
 	return __blkg_prfill_u64(sf, pd,
 		(tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9);
@@ -1226,13 +1241,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* statistics, covers only the tasks in the bfqg */
 	{
 		.name = "bfq.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat,
 	},
 	{
 		.name = "bfq.io_serviced",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
@@ -1269,13 +1284,13 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	/* the same statistics which cover the bfqg and its descendants */
 	{
 		.name = "bfq.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct bfq_group, stats.bytes),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "bfq.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_bfq,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct bfq_group, stats.ios),
+		.seq_show = bfqg_print_rwstat_recursive,
 	},
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	{
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 0c6214497fcc..ad4af4aaf2ce 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5484,6 +5484,10 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	bool idle_timer_disabled = false;
 	unsigned int cmd_flags;
 
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio)
+		bfqg_stats_update_legacy_io(q, rq);
+#endif
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
 		spin_unlock_irq(&bfqd->lock);
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 5d1a519640f6..8526f20c53bc 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -10,6 +10,8 @@
 #include <linux/hrtimer.h>
 #include <linux/blk-cgroup.h>
 
+#include "blk-cgroup-rwstat.h"
+
 #define BFQ_IOPRIO_CLASSES	3
 #define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
 
@@ -809,6 +811,9 @@ struct bfq_stat {
 };
 
 struct bfqg_stats {
+	/* basic stats */
+	struct blkg_rwstat		bytes;
+	struct blkg_rwstat		ios;
 #ifdef CONFIG_BFQ_CGROUP_DEBUG
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
@@ -956,6 +961,7 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
 
 /* ---------------- cgroups-support interface ---------------- */
 
+void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq);
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
 			      unsigned int op);
 void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
@@ -1062,6 +1068,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_cgroup_trace_msg((bfqd)->queue,				\
 			bfqg_to_blkg(bfqq_group(bfqq))->blkcg,		\
@@ -1078,6 +1086,8 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do {	\
 	char pid_str[MAX_PID_STR_LENGTH];	\
+	if (likely(!blk_trace_note_message_enabled((bfqd)->queue)))	\
+		break;							\
 	bfq_pid_to_str((bfqq)->pid, pid_str, MAX_PID_STR_LENGTH);	\
 	blk_add_trace_msg((bfqd)->queue, "bfq%s%c " fmt, pid_str,	\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c
new file mode 100644
index 000000000000..85d5790ac49b
--- /dev/null
+++ b/block/blk-cgroup-rwstat.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#include "blk-cgroup-rwstat.h"
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
+{
+	int i, ret;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
+		if (ret) {
+			while (--i >= 0)
+				percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+			return ret;
+		}
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_init);
+
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		percpu_counter_destroy(&rwstat->cpu_cnt[i]);
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
+
+/**
+ * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @rwstat: rwstat to print
+ *
+ * Print @rwstat to @sf for the device assocaited with @pd.
+ */
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat)
+{
+	static const char *rwstr[] = {
+		[BLKG_RWSTAT_READ]	= "Read",
+		[BLKG_RWSTAT_WRITE]	= "Write",
+		[BLKG_RWSTAT_SYNC]	= "Sync",
+		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
+	};
+	const char *dname = blkg_dev_name(pd->blkg);
+	u64 v;
+	int i;
+
+	if (!dname)
+		return 0;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
+			   rwstat->cnt[i]);
+
+	v = rwstat->cnt[BLKG_RWSTAT_READ] +
+		rwstat->cnt[BLKG_RWSTAT_WRITE] +
+		rwstat->cnt[BLKG_RWSTAT_DISCARD];
+	seq_printf(sf, "%s Total %llu\n", dname, v);
+	return v;
+}
+EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
+
+/**
+ * blkg_prfill_rwstat - prfill callback for blkg_rwstat
+ * @sf: seq_file to print to
+ * @pd: policy private data of interest
+ * @off: offset to the blkg_rwstat in @pd
+ *
+ * prfill callback for printing a blkg_rwstat.
+ */
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off)
+{
+	struct blkg_rwstat_sample rwstat = { };
+
+	blkg_rwstat_read((void *)pd + off, &rwstat);
+	return __blkg_prfill_rwstat(sf, pd, &rwstat);
+}
+EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
+
+/**
+ * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
+ * @blkg: blkg of interest
+ * @pol: blkcg_policy which contains the blkg_rwstat
+ * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
+ * @sum: blkg_rwstat_sample structure containing the results
+ *
+ * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
+ * online descendants and their aux counts.  The caller must be holding the
+ * queue lock for online tests.
+ *
+ * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
+ * is at @off bytes into @blkg's blkg_policy_data of the policy.
+ */
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum)
+{
+	struct blkcg_gq *pos_blkg;
+	struct cgroup_subsys_state *pos_css;
+	unsigned int i;
+
+	lockdep_assert_held(&blkg->q->queue_lock);
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
+		struct blkg_rwstat *rwstat;
+
+		if (!pos_blkg->online)
+			continue;
+
+		if (pol)
+			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
+		else
+			rwstat = (void *)pos_blkg + off;
+
+		for (i = 0; i < BLKG_RWSTAT_NR; i++)
+			sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h
new file mode 100644
index 000000000000..ee746919c41f
--- /dev/null
+++ b/block/blk-cgroup-rwstat.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
+ * Do not use in new code.
+ */
+#ifndef _BLK_CGROUP_RWSTAT_H
+#define _BLK_CGROUP_RWSTAT_H
+
+#include <linux/blk-cgroup.h>
+
+enum blkg_rwstat_type {
+	BLKG_RWSTAT_READ,
+	BLKG_RWSTAT_WRITE,
+	BLKG_RWSTAT_SYNC,
+	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
+
+	BLKG_RWSTAT_NR,
+	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+};
+
+/*
+ * blkg_[rw]stat->aux_cnt is excluded for local stats but included for
+ * recursive.  Used to carry stats of dead children.
+ */
+struct blkg_rwstat {
+	struct percpu_counter		cpu_cnt[BLKG_RWSTAT_NR];
+	atomic64_t			aux_cnt[BLKG_RWSTAT_NR];
+};
+
+struct blkg_rwstat_sample {
+	u64				cnt[BLKG_RWSTAT_NR];
+};
+
+static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat,
+		unsigned int idx)
+{
+	return atomic64_read(&rwstat->aux_cnt[idx]) +
+		percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]);
+}
+
+int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp);
+void blkg_rwstat_exit(struct blkg_rwstat *rwstat);
+u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+			 const struct blkg_rwstat_sample *rwstat);
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+		       int off);
+void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
+		int off, struct blkg_rwstat_sample *sum);
+
+
+/**
+ * blkg_rwstat_add - add a value to a blkg_rwstat
+ * @rwstat: target blkg_rwstat
+ * @op: REQ_OP and flags
+ * @val: value to add
+ *
+ * Add @val to @rwstat.  The counters are chosen according to @rw.  The
+ * caller is responsible for synchronizing calls to this function.
+ */
+static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
+				   unsigned int op, uint64_t val)
+{
+	struct percpu_counter *cnt;
+
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+
+	if (op_is_sync(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
+	else
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
+
+	percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH);
+}
+
+/**
+ * blkg_rwstat_read - read the current values of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Read the current snapshot of @rwstat and return it in the aux counts.
+ */
+static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat,
+		struct blkg_rwstat_sample *result)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		result->cnt[i] =
+			percpu_counter_sum_positive(&rwstat->cpu_cnt[i]);
+}
+
+/**
+ * blkg_rwstat_total - read the total count of a blkg_rwstat
+ * @rwstat: blkg_rwstat to read
+ *
+ * Return the total count of @rwstat regardless of the IO direction.  This
+ * function can be called without synchronization and takes care of u64
+ * atomicity.
+ */
+static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat)
+{
+	struct blkg_rwstat_sample tmp = { };
+
+	blkg_rwstat_read(rwstat, &tmp);
+	return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE];
+}
+
+/**
+ * blkg_rwstat_reset - reset a blkg_rwstat
+ * @rwstat: blkg_rwstat to reset
+ */
+static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
+{
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++) {
+		percpu_counter_set(&rwstat->cpu_cnt[i], 0);
+		atomic64_set(&rwstat->aux_cnt[i], 0);
+	}
+}
+
+/**
+ * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count
+ * @to: the destination blkg_rwstat
+ * @from: the source
+ *
+ * Add @from's count including the aux one to @to's aux count.
+ */
+static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to,
+				       struct blkg_rwstat *from)
+{
+	u64 sum[BLKG_RWSTAT_NR];
+	int i;
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]);
+
+	for (i = 0; i < BLKG_RWSTAT_NR; i++)
+		atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]),
+			     &to->aux_cnt[i]);
+}
+#endif	/* _BLK_CGROUP_RWSTAT_H */
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1eb8895be4c6..708dea92dac8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg)
 		if (blkg->pd[i])
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 
-	blkg_rwstat_exit(&blkg->stat_ios);
-	blkg_rwstat_exit(&blkg->stat_bytes);
+	free_percpu(blkg->iostat_cpu);
 	percpu_ref_exit(&blkg->refcnt);
 	kfree(blkg);
 }
@@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 				   gfp_t gfp_mask)
 {
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	/* alloc and init base part */
 	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
@@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask))
 		goto err_free;
 
-	if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
-	    blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
+	blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask);
+	if (!blkg->iostat_cpu)
 		goto err_free;
 
 	blkg->q = q;
@@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
 	blkg->blkcg = blkcg;
 
+	u64_stats_init(&blkg->iostat.sync);
+	for_each_possible_cpu(cpu)
+		u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync);
+
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
@@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
 	struct blkcg *blkcg = blkg->blkcg;
-	struct blkcg_gq *parent = blkg->parent;
 	int i;
 
 	lockdep_assert_held(&blkg->q->queue_lock);
@@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 			pol->pd_offline_fn(blkg->pd[i]);
 	}
 
-	if (parent) {
-		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
-		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
-	}
-
 	blkg->online = false;
 
 	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
@@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
-	int i;
+	int i, cpu;
 
 	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
@@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	 * anyway.  If you get hit by a race, retry.
 	 */
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		blkg_rwstat_reset(&blkg->stat_bytes);
-		blkg_rwstat_reset(&blkg->stat_ios);
+		for_each_possible_cpu(cpu) {
+			struct blkg_iostat_set *bis =
+				per_cpu_ptr(blkg->iostat_cpu, cpu);
+			memset(bis, 0, sizeof(*bis));
+		}
+		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -560,186 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
 }
 EXPORT_SYMBOL_GPL(__blkg_prfill_u64);
 
-/**
- * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @rwstat: rwstat to print
- *
- * Print @rwstat to @sf for the device assocaited with @pd.
- */
-u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-			 const struct blkg_rwstat_sample *rwstat)
-{
-	static const char *rwstr[] = {
-		[BLKG_RWSTAT_READ]	= "Read",
-		[BLKG_RWSTAT_WRITE]	= "Write",
-		[BLKG_RWSTAT_SYNC]	= "Sync",
-		[BLKG_RWSTAT_ASYNC]	= "Async",
-		[BLKG_RWSTAT_DISCARD]	= "Discard",
-	};
-	const char *dname = blkg_dev_name(pd->blkg);
-	u64 v;
-	int i;
-
-	if (!dname)
-		return 0;
-
-	for (i = 0; i < BLKG_RWSTAT_NR; i++)
-		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
-			   rwstat->cnt[i]);
-
-	v = rwstat->cnt[BLKG_RWSTAT_READ] +
-		rwstat->cnt[BLKG_RWSTAT_WRITE] +
-		rwstat->cnt[BLKG_RWSTAT_DISCARD];
-	seq_printf(sf, "%s Total %llu\n", dname, v);
-	return v;
-}
-EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
-
-/**
- * blkg_prfill_rwstat - prfill callback for blkg_rwstat
- * @sf: seq_file to print to
- * @pd: policy private data of interest
- * @off: offset to the blkg_rwstat in @pd
- *
- * prfill callback for printing a blkg_rwstat.
- */
-u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
-		       int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
-
-static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
-				    struct blkg_policy_data *pd, int off)
-{
-	struct blkg_rwstat_sample rwstat = { };
-
-	blkg_rwstat_read((void *)pd->blkg + off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_bytes.
- * cftype->private must be set to the blkcg_policy.
- */
-int blkg_print_stat_bytes(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);
-
-/**
- * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
- * @sf: seq_file to print to
- * @v: unused
- *
- * To be used as cftype->seq_show to print blkg->stat_ios.  cftype->private
- * must be set to the blkcg_policy.
- */
-int blkg_print_stat_ios(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios);
-
-static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
-					      struct blkg_policy_data *pd,
-					      int off)
-{
-	struct blkg_rwstat_sample rwstat;
-
-	blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat);
-	return __blkg_prfill_rwstat(sf, pd, &rwstat);
-}
-
-/**
- * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
- * @sf: seq_file to print to
- * @v: unused
- */
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
-{
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
-			  blkg_prfill_rwstat_field_recursive,
-			  (void *)seq_cft(sf)->private,
-			  offsetof(struct blkcg_gq, stat_bytes), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);
-
-/**
- * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
- * @sf: seq_file to print to
- * @v: unused
- */