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
  ...

51 files changed, 1398 insertions, 800 deletions

diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index 2c44b4f1b060..70dcaf2481f4 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -29,4 +29,9 @@ Description:
 		17 - sectors discarded
 		18 - time spent discarding
 
+		Kernel 5.5+ appends two more fields for flush requests:
+
+		19 - flush requests completed successfully
+		20 - time spent flushing
+
 		For more details refer to Documentation/admin-guide/iostats.rst
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index f8c7c7126bb1..ed8c14f161ee 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -15,6 +15,12 @@ Description:
 		 9 - I/Os currently in progress
 		10 - time spent doing I/Os (ms)
 		11 - weighted time spent doing I/Os (ms)
+		12 - discards completed
+		13 - discards merged
+		14 - sectors discarded
+		15 - time spent discarding (ms)
+		16 - flush requests completed
+		17 - time spent flushing (ms)
 		For more details refer Documentation/admin-guide/iostats.rst
 
 
diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst
index 5d63b18bd6d1..4f0462af3ca7 100644
--- a/Documentation/admin-guide/iostats.rst
+++ b/Documentation/admin-guide/iostats.rst
@@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding
     This is the total number of milliseconds spent by all discards (as
     measured from __make_request() to end_that_request_last()).
 
+Field 16 -- # of flush requests completed
+    This is the total number of flush requests completed successfully.
+
+    Block layer combines flush requests and executes at most one at a time.
+    This counts flush requests executed by disk. Not tracked for partitions.
+
+Field 17 -- # of milliseconds spent flushing
+    This is the total number of milliseconds spent by all flush requests.
+
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
 introduced when changes collide, so (for instance) adding up all the
diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst
index 9c07bc22b0bc..77311335c08b 100644
--- a/Documentation/block/stat.rst
+++ b/Documentation/block/stat.rst
@@ -41,6 +41,8 @@ discard I/Os    requests      number of discard I/Os processed
 discard merges  requests      number of discard I/Os merged with in-queue I/O
 discard sectors sectors       number of sectors discarded
 discard ticks   milliseconds  total wait time for discard requests
+flush I/Os      requests      number of flush I/Os processed
+flush ticks     milliseconds  total wait time for flush requests
 =============== ============= =================================================
 
 read I/Os, write I/Os, discard I/0s
@@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s
 
 These values increment when an I/O request completes.
 
+flush I/Os
+==========
+
+These values increment when an flush I/O request completes.
+
+Block layer combines flush requests and executes at most one at a time.
+This counts flush requests executed by disk. Not tracked for partitions.
+
 read merges, write merges, discard merges
 =========================================
 
@@ -62,8 +72,8 @@ discarded from this block device.  The "sectors" in question are the
 standard UNIX 512-byte sectors, not any device- or filesystem-specific
 block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks, discard ticks
-======================================
+read ticks, write ticks, discard ticks, flush ticks
+===================================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
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
- */
-int blkg_print_stat_ios_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_ios), true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);
-
-/**
- * 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);
-
 /* Performs queue bypass and policy enabled checks then looks up blkg. */
 static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 					  const struct blkcg_policy *pol,
@@ -923,16 +744,18 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
 	struct blkcg_gq *blkg;
 
+	cgroup_rstat_flush(blkcg->css.cgroup);
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkg_iostat_set *bis = &blkg->iostat;
 		const char *dname;
 		char *buf;
-		struct blkg_rwstat_sample rwstat;
 		u64 rbytes, wbytes, rios, wios, dbytes, dios;
 		size_t size = seq_get_buf(sf, &buf), off = 0;
 		int i;
 		bool has_stats = false;
+		unsigned seq;
 
 		spin_lock_irq(&blkg->q->queue_lock);
 
@@ -951,17 +774,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		 */
 		off += scnprintf(buf+off, size-off, "%s ", dname);
 
-		blkg_rwstat_recursive_sum(blkg, NULL,
-				offsetof(struct blkcg_gq, stat_bytes), &rwstat);
-		rbytes = rwstat.cnt[BLKG_RWSTAT_READ];
-		wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD];
+		do {
+			seq = u64_stats_fetch_begin(&bis->sync);
 
-		blkg_rwstat_recursive_sum(blkg, NULL,
-					offsetof(struct blkcg_gq, stat_ios), &rwstat);
-		rios = rwstat.cnt[BLKG_RWSTAT_READ];
-		wios = rwstat.cnt[BLKG_RWSTAT_WRITE];
-		dios = rwstat.cnt[BLKG_RWSTAT_DISCARD];
+			rbytes = bis->cur.bytes[BLKG_IOSTAT_READ];
+			wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE];
+			dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD];
+			rios = bis->cur.ios[BLKG_IOSTAT_READ];
+			wios = bis->cur.ios[BLKG_IOSTAT_WRITE];
+			dios = bis->cur.ios[BLKG_IOSTAT_DISCARD];
+		} while (u64_stats_fetch_retry(&bis->sync, seq));
 
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
@@ -1297,6 +1119,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset)
 	return ret;
 }
 
+static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] = src->bytes[i];
+		dst->ios[i] = src->ios[i];
+	}
+}
+
+static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] += src->bytes[i];
+		dst->ios[i] += src->ios[i];
+	}
+}
+
+static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src)
+{
+	int i;
+
+	for (i = 0; i < BLKG_IOSTAT_NR; i++) {
+		dst->bytes[i] -= src->bytes[i];
+		dst->ios[i] -= src->ios[i];
+	}
+}
+
+static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct blkcg_gq *parent = blkg->parent;
+		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		struct blkg_iostat cur, delta;
+		unsigned seq;
+
+		/* fetch the current per-cpu values */
+		do {
+			seq = u64_stats_fetch_begin(&bisc->sync);
+			blkg_iostat_set(&cur, &bisc->cur);
+		} while (u64_stats_fetch_retry(&bisc->sync, seq));
+
+		/* propagate percpu delta to global */
+		u64_stats_update_begin(&blkg->iostat.sync);
+		blkg_iostat_set(&delta, &cur);
+		blkg_iostat_sub(&delta, &bisc->last);
+		blkg_iostat_add(&blkg->iostat.cur, &delta);
+		blkg_iostat_add(&bisc->last, &delta);
+		u64_stats_update_end(&blkg->iostat.sync);
+
+		/* propagate global delta to parent */
+		if (parent) {
+			u64_stats_update_begin(&parent->iostat.sync);
+			blkg_iostat_set(&delta, &blkg->iostat.cur);
+			blkg_iostat_sub(&delta, &blkg->iostat.last);
+			blkg_iostat_add(&parent->iostat.cur, &delta);
+			blkg_iostat_add(&blkg->iostat.last, &delta);
+			u64_stats_update_end(&parent->iostat.sync);
+		}
+	}
+
+	rcu_read_unlock();
+}
+
 static void blkcg_bind(struct cgroup_subsys_state *root_css)
 {
 	int i;
@@ -1329,6 +1222,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
+	.css_rstat_flush = blkcg_rstat_flush,
 	.bind = blkcg_bind,
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
diff --git a/block/blk-core.c b/block/blk-core.c
index d5e668ec751b..f0d82227a2fc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -132,6 +132,9 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(ZONE_RESET_ALL),
+	REQ_OP_NAME(ZONE_OPEN),
+	REQ_OP_NAME(ZONE_CLOSE),
+	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_registered(q));
+
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	mutex_lock(&q->sysfs_lock);
 	blk_set_queue_dying(q);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	mutex_unlock(&q->sysfs_lock);
 
 	/*
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
@@ -849,10 +852,10 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
+	 * Zone management bios do not have a sector count but they do have
+	 * a start sector filled out and need to be remapped.
 	 */
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) {
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -936,6 +939,9 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 1db44ca0f4a6..e20a852ae432 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
+	blk_account_io_start(rq, true);
+
 	/*
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 1eec9cbe5a0a..1777346baf06 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 	blk_mq_add_to_requeue_list(rq, add_front, true);
 }
 
+static void blk_account_io_flush(struct request *rq)
+{
+	struct hd_struct *part = &rq->rq_disk->part0;
+
+	part_stat_lock();
+	part_stat_inc(part, ios[STAT_FLUSH]);
+	part_stat_add(part, nsecs[STAT_FLUSH],
+		      ktime_get_ns() - rq->start_time_ns);
+	part_stat_unlock();
+}
+
 /**
  * blk_flush_complete_seq - complete flush sequence
  * @rq: PREFLUSH/FUA request being sequenced
@@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq,
 
 	case REQ_FSEQ_DONE:
 		/*
-		 * @rq was previously adjusted by blk_flush_issue() for
+		 * @rq was previously adjusted by blk_insert_flush() for
 		 * flush sequencing and may already have gone through the
 		 * flush data request completion path.  Restore @rq for
 		 * normal completion and end it.
@@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 	struct blk_mq_hw_ctx *hctx;
 
+	blk_account_io_flush(flush_rq);
+
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 48e6725b32ee..d783bdc4559b 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -293,7 +293,7 @@ split:
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
-	struct bio *split;
+	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
@@ -309,6 +309,21 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 				nr_segs);
 		break;
 	default:
+		/*
+		 * All drivers must accept single-segments bios that are <=
+		 * PAGE_SIZE.  This is a quick and dirty check that relies on
+		 * the fact that bi_io_vec[0] is always valid if a bio has data.
+		 * The check might lead to occasional false negatives when bios
+		 * are cloned, but compared to the performance impact of cloned
+		 * bios themselves the loop below doesn't matter anyway.
+		 */
+		if (!q->limits.chunk_sectors &&
+		    (*bio)->bi_vcnt == 1 &&
+		    ((*bio)->bi_io_vec[0].bv_len +
+		     (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) {
+			*nr_segs = 1;
+			break;
+		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a0d3ce30fa08..062229395a50 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(ctx, page);
+	res = entry->show(ctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(ctx, page, length);
+	res = entry->store(ctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(hctx, page);
+	res = entry->show(hctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(hctx, page, length);
+	res = entry->store(hctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 {
+	const size_t size = PAGE_SIZE - 1;
 	unsigned int i, first = 1;
-	ssize_t ret = 0;
+	int ret = 0, pos = 0;
 
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
-			ret += sprintf(ret + page, "%u", i);
+			ret = snprintf(pos + page, size - pos, "%u", i);
 		else
-			ret += sprintf(ret + page, ", %u", i);
+			ret = snprintf(pos + page, size - pos, ", %u", i);
+
+		if (ret >= size - pos)
+			break;
 
 		first = 0;
+		pos += ret;
 	}
 
-	ret += sprintf(ret + page, "\n");
-	return ret;
+	ret = snprintf(pos + page, size + 1 - pos, "\n");
+	return pos + ret;
 }
 
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 008388e82b5c..fbacde454718 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -15,14 +15,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
-{
-	if (!tags)
-		return true;
-
-	return sbitmap_any_bit_clear(&tags->bitmap_tags.sb);
-}
-
 /*
  * If a previously inactive queue goes active, bump the active user count.
  * We need to do this before try to allocate driver tag, then even if fail
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 61deab0b5a5a..15bc74acb57e 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
 			   struct blk_mq_ctx *ctx, unsigned int tag);
-extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..323c9cb28066 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 
 struct mq_inflight {
 	struct hd_struct *part;
-	unsigned int *inflight;
+	unsigned int inflight[2];
 };
 
 static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
@@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	/*
-	 * index[0] counts the specific partition that was asked for.
-	 */
 	if (rq->part == mi->part)
-		mi->inflight[0]++;
+		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
 }
 
 unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 {
-	unsigned inflight[2];
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 
-	return inflight[0];
-}
-
-static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
-				     struct request *rq, void *priv,
-				     bool reserved)
-{
-	struct mq_inflight *mi = priv;
-
-	if (rq->part == mi->part)
-		mi->inflight[rq_data_dir(rq)]++;
-
-	return true;
+	return mi.inflight[0] + mi.inflight[1];
 }
 
 void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 			 unsigned int inflight[2])
 {
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+	inflight[0] = mi.inflight[0];
+	inflight[1] = mi.inflight[1];
 }
 
 void blk_freeze_queue_start(struct request_queue *q)
@@ -276,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q)
 			blk_mq_tag_wakeup_all(hctx->tags, true);
 }
 
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
-{
-	return blk_mq_has_free_tags(hctx->tags);
-}
-EXPORT_SYMBOL(blk_mq_can_queue);
-
 /*
  * Only need start/end time stamping if we have iostat or
  * blk stats enabled, or using an IO scheduler.
@@ -663,18 +641,6 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-int blk_mq_request_started(struct request *rq)
-{
-	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_started);
-
-int blk_mq_request_completed(struct request *rq)
-{
-	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_completed);
-
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -1064,7 +1030,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	bool shared;
 
 	if (rq->tag != -1)
-		goto done;
+		return true;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
@@ -1079,7 +1045,6 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		data.hctx->tags->rqs[rq->tag] = rq;
 	}
 
-done:
 	return rq->tag != -1;
 }
 
@@ -1486,7 +1451,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	int srcu_idx;
 	bool need_run;
@@ -1504,12 +1469,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		blk_mq_hctx_has_pending(hctx);
 	hctx_unlock(hctx, srcu_idx);
 
-	if (need_run) {
+	if (need_run)
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
-		return true;
-	}
-
-	return false;
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2789,6 +2750,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	int i, j, end;
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
+	if (q->nr_hw_queues < set->nr_hw_queues) {
+		struct blk_mq_hw_ctx **new_hctxs;
+
+		new_hctxs = kcalloc_node(set->nr_hw_queues,
+				       sizeof(*new_hctxs), GFP_KERNEL,
+				       set->numa_node);
+		if (!new_hctxs)
+			return;
+		if (hctxs)
+			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+			       sizeof(*hctxs));
+		q->queue_hw_ctx = new_hctxs;
+		q->nr_hw_queues = set->nr_hw_queues;
+		kfree(hctxs);
+		hctxs = new_hctxs;
+	}
+
 	/* protect against switching io scheduler  */
 	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2844,19 +2822,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-/*
- * Maximum number of hardware queues we support. For single sets, we'll never
- * have more than the CPUs (software queues). For multiple sets, the tag_set
- * user may have set ->nr_hw_queues larger.
- */
-static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
-{
-	if (set->nr_maps == 1)
-		return nr_cpu_ids;
-
-	return max(set->nr_hw_queues, nr_cpu_ids);
-}
-
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q,
 						  bool elevator_init)
@@ -2876,12 +2841,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
 
-	q->nr_queues = nr_hw_queues(set);
-	q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
-						GFP_KERNEL, set->numa_node);
-	if (!q->queue_hw_ctx)
-		goto err_sys_init;
-
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
@@ -2929,7 +2888,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 err_hctxs:
 	kfree(q->queue_hw_ctx);
 	q->nr_hw_queues = 0;
-err_sys_init:
 	blk_mq_sysfs_deinit(q);
 err_poll:
 	blk_stat_free_callback(q->poll_cb);
@@ -3030,6 +2988,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
+static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
+				  int cur_nr_hw_queues, int new_nr_hw_queues)
+{
+	struct blk_mq_tags **new_tags;
+
+	if (cur_nr_hw_queues >= new_nr_hw_queues)
+		return 0;
+
+	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
+				GFP_KERNEL, set->numa_node);
+	if (!new_tags)
+		return -ENOMEM;
+
+	if (set->tags)
+		memcpy(new_tags, set->tags, cur_nr_hw_queues *
+		       sizeof(*set->tags));
+	kfree(set->tags);
+	set->tags = new_tags;
+	set->nr_hw_queues = new_nr_hw_queues;
+
+	return 0;
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -3083,9 +3064,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *),
-				 GFP_KERNEL, set->numa_node);
-	if (!set->tags)
+	if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
@@ -3126,7 +3105,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i, j;
 
-	for (i = 0; i < nr_hw_queues(set); i++)
+	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
 	for (j = 0; j < set->nr_maps; j++) {
@@ -3271,10 +3250,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
 	/*
-	 * Sync with blk_mq_queue_tag_busy_iter.
-	 */
-	synchronize_rcu();
-	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
 	 * updating the new sw to hw queue mappings.
@@ -3288,6 +3263,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister(q);
 	}
 
+	if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
+	    0)
+		goto reregister;
+
 	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -3304,6 +3283,7 @@ fallback:
 		blk_mq_map_swqueue(q);
 	}
 
+reregister:
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register(q);
 		blk_mq_debugfs_register_hctxs(q);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 32c62c64e6c2..eaaca8fc1c28 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_release(struct request_queue *q);
 
-/**
- * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
- * @rq: target request.
- */
-static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
-{
-	return READ_ONCE(rq->state);
-}
-
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 457d9ba3eb20..6e7ec87d49fa 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h)
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
-	unsigned long flags;
 	struct list_head *list;
 
-	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
 	list_add_tail(&rq->ipi_list, list);
 
 	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
-	local_irq_restore(flags);
 }
 
 /*
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 940f15d600f8..7da302ff88d0 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	struct request_queue *q = rq->q;
 	struct blk_stat_callback *cb;
 	struct blk_rq_stat *stat;
-	int bucket;
+	int bucket, cpu;
 	u64 value;
 
 	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
@@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	blk_throtl_stat_add(rq, value);
 
 	rcu_read_lock();
+	cpu = get_cpu();
 	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
 		if (!blk_stat_is_active(cb))
 			continue;
@@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now)
 		if (bucket < 0)
 			continue;
 
-		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
+		stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
 		blk_rq_stat_add(stat, value);
-		put_cpu_ptr(cb->cpu_stat);
 	}
+	put_cpu();
 	rcu_read_unlock();
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 46f5198be017..fca9b158f4a0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->show(q, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
@@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->store(q, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 18f773e52dfb..98233c9c65a8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -12,6 +12,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-cgroup.h>
 #include "blk.h"
+#include "blk-cgroup-rwstat.h"
 
 /* Max dispatch from a group in 1 round */
 static int throtl_grp_quantum = 8;
@@ -176,6 +177,9 @@ struct throtl_grp {
 	unsigned int bio_cnt; /* total bios */
 	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
 	unsigned long bio_cnt_reset_time;
+
+	struct blkg_rwstat stat_bytes;
+	struct blkg_rwstat stat_ios;
 };
 
 /* We measure latency for request size from <= 4k to >= 1M */
@@ -489,6 +493,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	if (!tg)
 		return NULL;
 
+	if (blkg_rwstat_init(&tg->stat_bytes, gfp))
+		goto err_free_tg;
+
+	if (blkg_rwstat_init(&tg->stat_ios, gfp))
+		goto err_exit_stat_bytes;
+
 	throtl_service_queue_init(&tg->service_queue);
 
 	for (rw = READ; rw <= WRITE; rw++) {
@@ -513,6 +523,12 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp,
 	tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD;
 
 	return &tg->pd;
+
+err_exit_stat_bytes:
+	blkg_rwstat_exit(&tg->stat_bytes);
+err_free_tg:
+	kfree(tg);
+	return NULL;
 }
 
 static void throtl_pd_init(struct blkg_policy_data *pd)
@@ -611,6 +627,8 @@ static void throtl_pd_free(struct blkg_policy_data *pd)
 	struct throtl_grp *tg = pd_to_tg(pd);
 
 	del_timer_sync(&tg->service_queue.pending_timer);
+	blkg_rwstat_exit(&tg->stat_bytes);
+	blkg_rwstat_exit(&tg->stat_ios);
 	kfree(tg);
 }
 
@@ -1464,6 +1482,32 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
+static int tg_print_rwstat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  blkg_prfill_rwstat, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 tg_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_throtl, off,
+				  &sum);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int tg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  tg_prfill_rwstat_recursive, &blkcg_policy_throtl,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
@@ -1491,23 +1535,23 @@ static struct cftype throtl_legacy_files[] = {
 	},
 	{
 		.name = "throttle.io_service_bytes",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_service_bytes_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_bytes_recursive,
+		.private = offsetof(struct throtl_grp, stat_bytes),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{
 		.name = "throttle.io_serviced",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat,
 	},
 	{
 		.name = "throttle.io_serviced_recursive",
-		.private = (unsigned long)&blkcg_policy_throtl,
-		.seq_show = blkg_print_stat_ios_recursive,
+		.private = offsetof(struct throtl_grp, stat_ios),
+		.seq_show = tg_print_rwstat_recursive,
 	},
 	{ }	/* terminate */
 };
@@ -2127,7 +2171,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* see throtl_charge_bio() */
-	if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw])
+	if (bio_flagged(bio, BIO_THROTTLED))
+		goto out;
+
+	if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) {
+		blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf,
+				bio->bi_iter.bi_size);
+		blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1);
+	}
+
+	if (!tg->has_rules[rw])
 		goto out;
 
 	spin_lock_irq(&q->queue_lock);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 4bc5f260248a..481eaf7d04d4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -202,32 +202,14 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-/*
- * Special case of zone reset operation to reset all zones in one command,
- * useful for applications like mkfs.
- */
-static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
-{
-	struct bio *bio = bio_alloc(gfp_mask, 0);
-	int ret;
-
-	/* across the zones operations, don't need any sectors */
-	bio_set_dev(bio, bdev);
-	bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
-
-	ret = submit_bio_wait(bio);
-	bio_put(bio);
-
-	return ret;
-}
-
 static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t sector,
 						sector_t nr_sectors)
 {
 	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
 		return false;
 
-	if (nr_sectors != part_nr_sects_read(bdev->bd_part))
+	if (sector || nr_sectors != part_nr_sects_read(bdev->bd_part))
 		return false;
 	/*
 	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
@@ -239,26 +221,29 @@ static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
 }
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	struct blk_plug plug;
 	int ret;
 
 	if (!blk_queue_is_zoned(q))
@@ -267,15 +252,14 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
 	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
 		/* Out of range */
 		return -EINVAL;
 
-	if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
-		return  __blkdev_reset_all_zones(bdev, gfp_mask);
-
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
@@ -283,29 +267,34 @@ int blkdev_reset_zones(struct block_device *bdev,
 	    end_sector != bdev->bd_part->nr_sects)
 		return -EINVAL;
 
-	blk_start_plug(&plug);
 	while (sector < end_sector) {
-
 		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
 
+		/*
+		 * Special case for the zone reset operation that reset all
+		 * zones, this is useful for applications like mkfs.
+		 */
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			break;
+		}
+
+		bio->bi_opf = op;
+		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
 		cond_resched();
-
 	}
 
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
-	blk_finish_plug(&plug);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
 
 /*
  * BLKREPORTZONE ioctl processing.
@@ -368,15 +357,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 }
 
 /*
- * BLKRESETZONE ioctl processing.
+ * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long arg)
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
+	enum req_opf op;
 
 	if (!argp)
 		return -EINVAL;
@@ -397,8 +387,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	switch (cmd) {
+	case BLKRESETZONE:
+		op = REQ_OP_ZONE_RESET;
+		break;
+	case BLKOPENZONE:
+		op = REQ_OP_ZONE_OPEN;
+		break;
+	case BLKCLOSEZONE:
+		op = REQ_OP_ZONE_CLOSE;
+		break;
+	case BLKFINISHZONE:
+		op = REQ_OP_ZONE_FINISH;
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+				GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,
diff --git a/block/blk.h b/block/blk.h
index 47fba9362e60..2bea40180b6f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -242,14 +242,11 @@ int blk_dev_init(void);
  * Contribute to IO statistics IFF:
  *
  *	a) it's attached to a gendisk, and
- *	b) the queue had IO stats enabled when this request was started, and
- *	c) it's a file system request
+ *	b) the queue had IO stats enabled when this request was started
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk &&
-	       (rq->rq_flags & RQF_IO_STAT) &&
-		!blk_rq_is_passthrough(rq);
+	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
 }
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)
diff --git a/block/elevator.c b/block/elevator.c
index 076ba7308e65..4eab3d70e880 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -832,3 +832,12 @@ struct request *elv_rb_latter_request(struct request_queue *q,
 	return NULL;
 }
 EXPORT_SYMBOL(elv_rb_latter_request);
+
+static int __init elevator_setup(char *str)
+{
+	pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
+		"Please use sysfs to set IO scheduler for individual devices.\n");
+	return 1;
+}
+
+__setup("elevator=", elevator_setup);
diff --git a/block/genhd.c b/block/genhd.c
index 26b31fcae217..ff6268970ddc 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
 			   "%u %u %u "
-			   "%lu %lu %lu %u\n",
+			   "%lu %lu %lu %u "
+			   "%lu %u"
+			   "\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[STAT_READ]),
@@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   part_stat_read(hd, ios[STAT_DISCARD]),
 			   part_stat_read(hd, merges[STAT_DISCARD]),
 			   part_stat_read(hd, sectors[STAT_DISCARD]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
+			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
+			   part_stat_read(hd, ios[STAT_FLUSH]),
+			   (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/ioctl.c b/block/ioctl.c
index 15a0eb80ada9..8756efb1419e 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -532,7 +532,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKREPORTZONE:
 		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
 	case BLKRESETZONE:
-		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKOPENZONE:
+	case BLKCLOSEZONE:
+	case BLKFINISHZONE:
+		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
 		return put_uint(arg, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
diff --git a/block/opal_proto.h b/block/opal_proto.h
index 5532412d567c..325cbba2465f 100644
--- a/block/opal_proto.h
+++ b/block/opal_proto.h
@@ -76,7 +76,6 @@ enum opal_response_token {
  * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Section: 6.3 Assigned UIDs
  */
-#define OPAL_UID_LENGTH 8
 #define OPAL_METHOD_LENGTH 8
 #define OPAL_MSID_KEYLEN 15
 #define OPAL_UID_LENGTH_HALF 4
@@ -108,6 +107,7 @@ enum opal_uid {
 	OPAL_C_PIN_TABLE,
 	OPAL_LOCKING_INFO_TABLE,
 	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	OPAL_DATASTORE,
 	/* C_PIN_TABLE object ID's */
 	OPAL_C_PIN_MSID,
 	OPAL_C_PIN_SID,
@@ -205,6 +205,10 @@ enum opal_lockingstate {
 	OPAL_LOCKING_LOCKED = 0x03,
 };
 
+enum opal_parameter {
+	OPAL_SUM_SET_LIST = 0x060000,
+};
+
 /* Packets derived from:
  * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Secion: 3.2.3 ComPackets, Packets & Subpackets
diff --git a/block/partition-generic.c b/block/partition-generic.c
index aee643ce13d1..3db8b73a96b1 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
 		"%8u %8u %8u "
-		"%8lu %8lu %8llu %8u"
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8u"
 		"\n",
 		part_stat_read(p, ios[STAT_READ]),
 		part_stat_read(p, merges[STAT_READ]),
@@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev,
 		part_stat_read(p, ios[STAT_DISCARD]),
 		part_stat_read(p, merges[STAT_DISCARD]),
 		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
-		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
+		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD),
+		part_stat_read(p, ios[STAT_FLUSH]),
+		(unsigned int)part_stat_read_msecs(p, STAT_FLUSH));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/block/sed-opal.c b/block/sed-opal.c
index b4c761973ac1..880cc57a5f6b 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_DATASTORE] =
+		{ 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 },
 
 	/* C_PIN_TABLE object ID's */
 	[OPAL_C_PIN_MSID] =
@@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
  *
  * the result is provided in dev->resp->tok[4]
  */
-static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
+static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid,
 				  u64 column)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	const unsigned int half = OPAL_UID_LENGTH/2;
+	const unsigned int half = OPAL_UID_LENGTH_HALF;
 
 	/* sed-opal UIDs can be split in two halves:
 	 *  first:  actual table index
@@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
 	 * first part of the target table as relative index into that table
 	 */
 	memcpy(uid, opaluid[OPAL_TABLE_TABLE], half);
-	memcpy(uid+half, opaluid[table], half);
+	memcpy(uid + half, table_uid, half);
 
 	return generic_get_column(dev, uid, column);
 }
@@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	return get_active_key_cont(dev);
 }
 
+static int generic_table_write_data(struct opal_dev *dev, const u64 data,
+				    u64 offset, u64 size, const u8 *uid)
+{
+	const u8 __user *src = (u8 __user *)(uintptr_t)data;
+	u8 *dst;
+	u64 len;
+	size_t off = 0;
+	int err;
+
+	/* do we fit in the available space? */
+	err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	len = response_get_u64(&dev->parsed, 4);
+	if (size > len || offset > len - size) {
+		pr_debug("Does not fit in the table (%llu vs. %llu)\n",
+			  offset + size, len);
+		return -ENOSPC;
+	}
+
+	/* do the actual transmission(s) */
+	while (off < size) {
+		err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_WHERE);
+		add_token_u64(&err, dev, offset + off);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+
+		/*
+		 * The bytestring header is either 1 or 2 bytes, so assume 2.
+		 * There also needs to be enough space to accommodate the
+		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
+		 * cmd_finalize.
+		 */
+		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
+			  (size_t)(size - off));
+		pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size);
+
+		dst = add_bytestring_header(&err, dev, len);
+		if (!dst)
+			break;
+
+		if (copy_from_user(dst, src + off, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		dev->pos += len;
+
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		if (err)
+			break;
+
+		err = finalize_and_send(dev, parse_and_check_status);
+		if (err)
+			break;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int generic_lr_enable_disable(struct opal_dev *dev,
 				     u8 *uid, bool rle, bool wle,
 				     bool rl, bool wl)
@@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 static int write_shadow_mbr(struct opal_dev *dev, void *data)
 {
 	struct opal_shadow_mbr *shadow = data;
-	const u8 __user *src;
-	u8 *dst;
-	size_t off = 0;
-	u64 len;
-	int err = 0;
-
-	/* do we fit in the available shadow mbr space? */
-	err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS);
-	if (err) {
-		pr_debug("MBR: could not get shadow size\n");
-		return err;
-	}
-
-	len = response_get_u64(&dev->parsed, 4);
-	if (shadow->size > len || shadow->offset > len - shadow->size) {
-		pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n",
-			 shadow->offset + shadow->size, len);
-		return -ENOSPC;
-	}
-
-	/* do the actual transmission(s) */
-	src = (u8 __user *)(uintptr_t)shadow->data;
-	while (off < shadow->size) {
-		err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]);
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_WHERE);
-		add_token_u64(&err, dev, shadow->offset + off);
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_VALUES);
-
-		/*
-		 * The bytestring header is either 1 or 2 bytes, so assume 2.
-		 * There also needs to be enough space to accommodate the
-		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
-		 * cmd_finalize.
-		 */
-		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
-			  (size_t)(shadow->size - off));
-		pr_debug("MBR: write bytes %zu+%llu/%llu\n",
-			 off, len, shadow->size);
-
-		dst = add_bytestring_header(&err, dev, len);
-		if (!dst)
-			break;
-		if (copy_from_user(dst, src + off, len))
-			err = -EFAULT;
-		dev->pos += len;
-
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-		if (err)
-			break;
-
-		err = finalize_and_send(dev, parse_and_check_status);
-		if (err)
-			break;
-
-		off += len;
-	}
 
-	return err;
+	return generic_table_write_data(dev, shadow->data, shadow->offset,
+					shadow->size, opaluid[OPAL_MBR]);
 }
 
 static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
@@ -1874,7 +1886,6 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 {
 	struct opal_lr_act *opal_act = data;
 	u8 user_lr[OPAL_UID_LENGTH];
-	u8 uint_3 = 0x83;
 	int err, i;
 
 	err = cmd_start(dev, opaluid[OPAL_LOCKINGSP_UID],
@@ -1887,10 +1898,7 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 			return err;
 
 		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, uint_3);
-		add_token_u8(&err, dev, 6);
-		add_token_u8(&err, dev, 0);
-		add_token_u8(&err, dev, 0);
+		add_token_u64(&err, dev, OPAL_SUM_SET_LIST);
 
 		add_token_u8(&err, dev, OPAL_STARTLIST);
 		add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
@@ -1957,6 +1965,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	return 0;
 }
 
+static int write_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *write_tbl = data;
+
+	return generic_table_write_data(dev, write_tbl->data, write_tbl->offset,
+					write_tbl->size, write_tbl->table_uid);
+}
+
+static int read_table_data_cont(struct opal_dev *dev)
+{
+	int err;
+	const char *data_read;
+
+	err = parse_and_check_status(dev);
+	if (err)
+		return err;
+
+	dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read);
+	dev->prev_data = (void *)data_read;
+	if (!dev->prev_data) {
+		pr_debug("%s: Couldn't read data from the table.\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	return 0;
+}
+
+/*
+ * IO_BUFFER_LENGTH = 2048
+ * sizeof(header) = 56
+ * No. of Token Bytes in the Response = 11
+ * MAX size of data that can be carried in response buffer
+ * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD.
+ */
+#define OPAL_MAX_READ_TABLE (0x7BD)
+
+static int read_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *read_tbl = data;
+	int err;
+	size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE;
+	u64 table_len, len;
+	u64 offset = read_tbl->offset, read_size = read_tbl->size - 1;
+	u8 __user *dst;
+
+	err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	table_len = response_get_u64(&dev->parsed, 4);
+
+	/* Check if the user is trying to read from the table limits */
+	if (read_size > table_len || offset > table_len - read_size) {
+		pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n",
+			  offset + read_size, table_len);
+		return -EINVAL;
+	}
+
+	while (off < read_size) {
+		err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_STARTROW);
+		add_token_u64(&err, dev, offset + off); /* start row value */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_ENDROW);
+
+		len = min(max_read_size, (size_t)(read_size - off));
+		add_token_u64(&err, dev, offset + off + len); /* end row value
+							       */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+		if (err) {
+			pr_debug("Error building read table data command.\n");
+			break;
+		}
+
+		err = finalize_and_send(dev, read_table_data_cont);
+		if (err)
+			break;
+
+		/* len+1: This includes the NULL terminator at the end*/
+		if (dev->prev_d_len > len + 1) {
+			err = -EOVERFLOW;
+			break;
+		}
+
+		dst = (u8 __user *)(uintptr_t)read_tbl->data;
+		if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) {
+			pr_debug("Error copying data to userspace\n");
+			err = -EFAULT;
+			break;
+		}
+		dev->prev_data = NULL;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int end_opal_session(struct opal_dev *dev, void *data)
 {
 	int err = 0;
@@ -2443,6 +2558,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 }
 EXPORT_SYMBOL(opal_unlock_from_suspend);
 
+static int opal_read_table(struct opal_dev *dev,
+			   struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step read_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ read_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, read_table_steps,
+			     ARRAY_SIZE(read_table_steps));
+}
+
+static int opal_write_table(struct opal_dev *dev,
+			    struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step write_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ write_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, write_table_steps,
+			     ARRAY_SIZE(write_table_steps));
+}
+
+static int opal_generic_read_write_table(struct opal_dev *dev,
+					 struct opal_read_write_table *rw_tbl)
+{
+	int ret, bit_set;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev);
+
+	bit_set = fls64(rw_tbl->flags) - 1;
+	switch (bit_set) {
+	case OPAL_READ_TABLE:
+		ret = opal_read_table(dev, rw_tbl);
+		break;
+	case OPAL_WRITE_TABLE:
+		ret = opal_write_table(dev, rw_tbl);
+		break;
+	default:
+		pr_debug("Invalid bit set in the flag (%016llx).\n",
+			 rw_tbl->flags);
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&dev->dev_lock);
+
+	return ret;
+}
+
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 {
 	void *p;
@@ -2505,6 +2682,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 	case IOC_OPAL_PSID_REVERT_TPR:
 		ret = opal_reverttper(dev, p, true);
 		break;
+	case IOC_OPAL_GENERIC_TABLE_RW:
+		ret = opal_generic_read_write_table(dev, p);
+		break;
 	default:
 		break;
 	}
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 9803c7e0376e..f4907d941f03 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_prepare(struct request *rq)
 {
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
 {
 }
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 595a73110e17..feb4718ce6a6 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1312,9 +1312,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9c073dbdc1b0..d612468ee66b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
 		       "resized disk %s\n",
 		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
 	}
-
-	if (!bdev->bd_disk)
-		return;
-	if (disk_part_scan_enabled(bdev->bd_disk))
-		bdev->bd_invalidated = 1;
+	bdev->bd_invalidated = 1;
 }
 
 /**
@@ -1512,6 +1508,19 @@ EXPORT_SYMBOL(bd_set_size);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
+static void bdev_disk_changed(struct block_device *bdev, bool invalidate)
+{
+	if (disk_part_scan_enabled(bdev->bd_disk)) {
+		if (invalidate)
+			invalidate_partitions(bdev->bd_disk, bdev);
+		else
+			rescan_partitions(bdev->bd_disk, bdev);
+	} else {
+		check_disk_size_change(bdev->bd_disk, bdev, !invalidate);
+		bdev->bd_invalidated = 0;
+	}
+}
+
 /*
  * bd_mutex locking:
  *
@@ -1594,12 +1603,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
 			if (ret)
 				goto out_clear;
@@ -1632,12 +1638,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(bdev->bd_disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(bdev->bd_disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
 				goto out_unlock_bdev;
 		}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 808709581481..2c997f94a3b2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 			return -EIO;
 		}
 		trace_f2fs_issue_reset_zone(bdev, blkstart);
-		return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
+		return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+					sector, nr_sects, GFP_NOFS);
 	}
 
 	/* For conventional zones, use regular discard if supported */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 3d40771e8e7c..41b6438bd2d9 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 static bool rw_hint_valid(enum rw_hint hint)
 {
 	switch (hint) {
-	case RWF_WRITE_LIFE_NOT_SET:
+	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
 	case RWH_WRITE_LIFE_SHORT:
 	case RWH_WRITE_LIFE_MEDIUM:
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index bed9e43f9426..19394c77ed99 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -15,7 +15,9 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/percpu.h>
 #include <linux/percpu_counter.h>
+#include <linux/u64_stats_sync.h>
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
@@ -31,15 +33,12 @@
 
 #ifdef CONFIG_BLK_CGROUP
 
-enum blkg_rwstat_type {
-	BLKG_RWSTAT_READ,
-	BLKG_RWSTAT_WRITE,
-	BLKG_RWSTAT_SYNC,
-	BLKG_RWSTAT_ASYNC,
-	BLKG_RWSTAT_DISCARD,
+enum blkg_iostat_type {
+	BLKG_IOSTAT_READ,
+	BLKG_IOSTAT_WRITE,
+	BLKG_IOSTAT_DISCARD,
 
-	BLKG_RWSTAT_NR,
-	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
+	BLKG_IOSTAT_NR,
 };
 
 struct blkcg_gq;
@@ -61,17 +60,15 @@ struct blkcg {
 #endif
 };
 
-/*
- * 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_iostat {
+	u64				bytes[BLKG_IOSTAT_NR];
+	u64				ios[BLKG_IOSTAT_NR];
 };
 
-struct blkg_rwstat_sample {
-	u64				cnt[BLKG_RWSTAT_NR];
+struct blkg_iostat_set {
+	struct u64_stats_sync		sync;
+	struct blkg_iostat		cur;
+	struct blkg_iostat		last;
 };
 
 /*
@@ -127,8 +124,8 @@ struct blkcg_gq {
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
 
-	struct blkg_rwstat		stat_bytes;
-	struct blkg_rwstat		stat_ios;
+	struct blkg_iostat_set __percpu	*iostat_cpu;
+	struct blkg_iostat_set		iostat;
 
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
@@ -202,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q,
 void blkcg_deactivate_policy(struct request_queue *q,
 			     const struct blkcg_policy *pol);
 
-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]);
-}
-
 const char *blkg_dev_name(struct blkcg_gq *blkg);
 void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 		       u64 (*prfill)(struct seq_file *,
@@ -216,17 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
 		       const struct blkcg_policy *pol, int data,
 		       bool show_total);
 u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
-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);
-int blkg_print_stat_bytes(struct seq_file *sf, void *v);
-int blkg_print_stat_ios(struct seq_file *sf, void *v);
-int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v);
-int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v);
-
-void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
-		int off, struct blkg_rwstat_sample *sum);
 
 struct blkg_conf_ctx {
 	struct gendisk			*disk;
@@ -578,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
-static inline 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;
-}
-
-static inline 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]);
-}
-
-/**
- * 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]);
-}
-
 #ifdef CONFIG_BLK_DEV_THROTTLING
 extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 			   struct bio *bio);
@@ -745,15 +602,33 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	throtl = blk_throtl_bio(q, blkg, bio);
 
 	if (!throtl) {
+		struct blkg_iostat_set *bis;
+		int rwd, cpu;
+
+		if (op_is_discard(bio->bi_opf))
+			rwd = BLKG_IOSTAT_DISCARD;
+		else if (op_is_write(bio->bi_opf))
+			rwd = BLKG_IOSTAT_WRITE;
+		else
+			rwd = BLKG_IOSTAT_READ;
+
+		cpu = get_cpu();
+		bis = per_cpu_ptr(blkg->iostat_cpu, cpu);
+		u64_stats_update_begin(&bis->sync);
+
 		/*
 		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
 		 * is a split bio and we would have already accounted for the
 		 * size of the bio.
 		 */
 		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
-			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-					bio->bi_iter.bi_size);
-		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
+			bis->cur.bytes[rwd] += bio->bi_iter.bi_size;
+		bis->cur.ios[rwd]++;
+
+		u64_stats_update_end(&bis->sync);
+		if (cgroup_subsys_on_dfl(io_cgrp_subsys))
+			cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu);
+		put_cpu();
 	}
 
 	blkcg_bio_issue_init(bio);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 0bf056de5cc3..11cfd6470b1a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -10,103 +10,239 @@ struct blk_mq_tags;
 struct blk_flush_queue;
 
 /**
- * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
+ * block device
  */
 struct blk_mq_hw_ctx {
 	struct {
+		/** @lock: Protects the dispatch list. */
 		spinlock_t		lock;
+		/**
+		 * @dispatch: Used for requests that are ready to be
+		 * dispatched to the hardware but for some reason (e.g. lack of
+		 * resources) could not be sent to the hardware. As soon as the
+		 * driver can send new requests, requests at this list will
+		 * be sent first for a fairer dispatch.
+		 */
 		struct list_head	dispatch;
-		unsigned long		state;		/* BLK_MQ_S_* flags */
+		 /**
+		  * @state: BLK_MQ_S_* flags. Defines the state of the hw
+		  * queue (active, scheduled to restart, stopped).
+		  */
+		unsigned long		state;
 	} ____cacheline_aligned_in_smp;
 
+	/**
+	 * @run_work: Used for scheduling a hardware queue run at a later time.
+	 */
 	struct delayed_work	run_work;
+	/** @cpumask: Map of available CPUs where this hctx can run. */
 	cpumask_var_t		cpumask;
+	/**
+	 * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU
+	 * selection from @cpumask.
+	 */
 	int			next_cpu;
+	/**
+	 * @next_cpu_batch: Counter of how many works left in the batch before
+	 * changing to the next CPU.
+	 */
 	int			next_cpu_batch;
 
-	unsigned long		flags;		/* BLK_MQ_F_* flags */
+	/** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */
+	unsigned long		flags;
 
+	/**
+	 * @sched_data: Pointer owned by the IO scheduler attached to a request
+	 * queue. It's up to the IO scheduler how to use this pointer.
+	 */
 	void			*sched_data;
+	/**
+	 * @queue: Pointer to the request queue that owns this hardware context.
+	 */
 	struct request_queue	*queue;
+	/** @fq: Queue of requests that need to perform a flush operation. */
 	struct blk_flush_queue	*fq;
 
+	/**
+	 * @driver_data: Pointer to data owned by the block driver that created
+	 * this hctx
+	 */
 	void			*driver_data;
 
+	/**
+	 * @ctx_map: Bitmap for each software queue. If bit is on, there is a
+	 * pending request in that software queue.
+	 */
 	struct sbitmap		ctx_map;
 
+	/**
+	 * @dispatch_from: Software queue to be used when no scheduler was
+	 * selected.
+	 */
 	struct blk_mq_ctx	*dispatch_from;
+	/**
+	 * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to
+	 * decide if the hw_queue is busy using Exponential Weighted Moving
+	 * Average algorithm.
+	 */
 	unsigned int		dispatch_busy;
 
+	/** @type: HCTX_TYPE_* flags. Type of hardware queue. */
 	unsigned short		type;
+	/** @nr_ctx: Number of software queues. */
 	unsigned short		nr_ctx;
+	/** @ctxs: Array of software queues. */
 	struct blk_mq_ctx	**ctxs;
 
+	/** @dispatch_wait_lock: Lock for dispatch_wait queue. */
 	spinlock_t		dispatch_wait_lock;
+	/**
+	 * @dispatch_wait: Waitqueue to put requests when there is no tag
+	 * available at the moment, to wait for another try in the future.
+	 */
 	wait_queue_entry_t	dispatch_wait;
+
+	/**
+	 * @wait_index: Index of next available dispatch_wait queue to insert
+	 * requests.
+	 */
 	atomic_t		wait_index;
 
+	/**
+	 * @tags: Tags owned by the block driver. A tag at this set is only
+	 * assigned when a request is dispatched from a hardware queue.
+	 */
 	struct blk_mq_tags	*tags;
+	/**
+	 * @sched_tags: Tags owned by I/O scheduler. If there is an I/O
+	 * scheduler associated with a request queue, a tag is assigned when
+	 * that request is allocated. Else, this member is not used.
+	 */
 	struct blk_mq_tags	*sched_tags;
 
+	/** @queued: Number of queued requests. */
 	unsigned long		queued;
+	/** @run: Number of dispatched requests. */
 	unsigned long		run;
 #define BLK_MQ_MAX_DISPATCH_ORDER	7
+	/** @dispatched: Number of dispatch requests by queue. */
 	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
 
+	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
+	/** @queue_num: Index of this hardware queue. */
 	unsigned int		queue_num;
 
+	/**
+	 * @nr_active: Number of active requests. Only used when a tag set is
+	 * shared across request queues.
+	 */
 	atomic_t		nr_active;
 
+	/** @cpuhp_dead: List to store request if some CPU die. */
 	struct hlist_node	cpuhp_dead;
+	/** @kobj: Kernel object for sysfs. */
 	struct kobject		kobj;
 
+	/** @poll_considered: Count times blk_poll() was called. */
 	unsigned long		poll_considered;
+	/** @poll_invoked: Count how many requests blk_poll() polled. */
 	unsigned long		poll_invoked;
+	/** @poll_success: Count how many polled requests were completed. */
 	unsigned long		poll_success;
 
 #ifdef CONFIG_BLK_DEBUG_FS
+	/**
+	 * @debugfs_dir: debugfs directory for this hardware queue. Named
+	 * as cpu<cpu_number>.
+	 */
 	struct dentry		*debugfs_dir;
+	/** @sched_debugfs_dir:	debugfs directory for the scheduler. */
 	struct dentry		*sched_debugfs_dir;
 #endif
 
+	/** @hctx_list:	List of all hardware queues. */
 	struct list_head	hctx_list;
 
-	/* Must be the last member - see also blk_mq_hw_ctx_size(). */
+	/**
+	 * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
+	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
+	 * blk_mq_hw_ctx_size().
+	 */
 	struct srcu_struct	srcu[0];
 };
 
+/**
+ * struct blk_mq_queue_map - Map software queues to hardware queues
+ * @mq_map:       CPU ID to hardware queue index map. This is an array
+ *	with nr_cpu_ids elements. Each element has a value in the range
+ *	[@queue_offset, @queue_offset + @nr_queues).
+ * @nr_queues:    Number of hardware queues to map CPU IDs onto.
+ * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe
+ *	driver to map each hardware queue type (enum hctx_type) onto a distinct
+ *	set of hardware queues.
+ */
 struct blk_mq_queue_map {
 	unsigned int *mq_map;
 	unsigned int nr_queues;
 	unsigned int queue_offset;
 };
 
+/**
+ * enum hctx_type - Type of hardware queue
+ * @HCTX_TYPE_DEFAULT:	All I/O not otherwise accounted for.
+ * @HCTX_TYPE_READ:	Just for READ I/O.
+ * @HCTX_TYPE_POLL:	Polled I/O of any kind.
+ * @HCTX_MAX_TYPES:	Number of types of hctx.
+ */
 enum hctx_type {
-	HCTX_TYPE_DEFAULT,	/* all I/O not otherwise accounted for */
-	HCTX_TYPE_READ,		/* just for READ I/O */
-	HCTX_TYPE_POLL,		/* polled I/O of any kind */
+	HCTX_TYPE_DEFAULT,
+	HCTX_TYPE_READ,
+	HCTX_TYPE_POLL,
 
 	HCTX_MAX_TYPES,
 };
 
+/**
+ * struct blk_mq_tag_set - tag set that can be shared between request queues
+ * @map:	   One or more ctx -> hctx mappings. One map exists for each
+ *		   hardware queue type (enum hctx_type) that the driver wishes
+ *		   to support. There are no restrictions on maps being of the
+ *		   same size, and it's perfectly legal to share maps between
+ *		   types.
+ * @nr_maps:	   Number of elements in the @map array. A number in the range
+ *		   [1, HCTX_MAX_TYPES].
+ * @ops:	   Pointers to functions that implement block driver behavior.
+ * @nr_hw_queues:  Number of hardware queues supported by the block driver that
+ *		   owns this data structure.
+ * @queue_depth:   Number of tags per hardware queue, reserved tags included.
+ * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag
+ *		   allocations.
+ * @cmd_size:	   Number of additional bytes to allocate per request. The block
+ *		   driver owns these additional bytes.
+ * @numa_node:	   NUMA node the storage adapter has been connected to.
+ * @timeout:	   Request processing timeout in jiffies.
+ * @flags:	   Zero or more BLK_MQ_F_* flags.
+ * @driver_data:   Pointer to data owned by the block driver that created this
+ *		   tag set.
+ * @tags:	   Tag sets. One tag set per hardware queue. Has @nr_hw_queues
+ *		   elements.
+ * @tag_list_lock: Serializes tag_list accesses.
+ * @tag_list:	   List of the request queues that use this tag set. See also
+ *		   request_queue.tag_set_list.
+ */
 struct blk_mq_tag_set {
-	/*
-	 * map[] holds ctx -> hctx mappings, one map exists for each type
-	 * that the driver wishes to support. There are no restrictions
-	 * on maps being of the same size, and it's perfectly legal to
-	 * share maps between types.
-	 */
 	struct blk_mq_queue_map	map[HCTX_MAX_TYPES];
-	unsigned int		nr_maps;	/* nr entries in map[] */
+	unsigned int		nr_maps;
 	const struct blk_mq_ops	*ops;
-	unsigned int		nr_hw_queues;	/* nr hw queues across maps */
-	unsigned int		queue_depth;	/* max hw supported */
+	unsigned int		nr_hw_queues;
+	unsigned int		queue_depth;
 	unsigned int		reserved_tags;
-	unsigned int		cmd_size;	/* per-request extra data */
+	unsigned int		cmd_size;
 	int			numa_node;
 	unsigned int		timeout;
-	unsigned int		flags;		/* BLK_MQ_F_* */
+	unsigned int		flags;
 	void			*driver_data;
 
 	struct blk_mq_tags	**tags;
@@ -115,6 +251,12 @@ struct blk_mq_tag_set {
 	struct list_head	tag_list;
 };
 
+/**
+ * struct blk_mq_queue_data - Data about a request inserted in a queue
+ *
+ * @rq:   Request pointer.
+ * @last: If it is the last request in the queue.
+ */
 struct blk_mq_queue_data {
 	struct request *rq;
 	bool last;
@@ -142,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *);
 typedef void (complete_fn)(struct request *);
 typedef void (cleanup_rq_fn)(struct request *);
 
-
+/**
+ * struct blk_mq_ops - Callback functions that implements block driver
+ * behaviour.
+ */
 struct blk_mq_ops {
-	/*
-	 * Queue request
+	/**
+	 * @queue_rq: Queue a new request from block IO.
 	 */
 	queue_rq_fn		*queue_rq;
 
-	/*
-	 * If a driver uses bd->last to judge when to submit requests to
-	 * hardware, it must define this function. In case of errors that
-	 * make us stop issuing further requests, this hook serves the
+	/**
+	 * @commit_rqs: If a driver uses bd->last to judge when to submit
+	 * requests to hardware, it must define this function. In case of errors
+	 * that make us stop issuing further requests, this hook serves the
 	 * purpose of kicking the hardware (which the last request otherwise
 	 * would have done).
 	 */
 	commit_rqs_fn		*commit_rqs;
 
-	/*
-	 * Reserve budget before queue request, once .queue_rq is
+	/**
+	 * @get_budget: Reserve budget before queue request, once .queue_rq is
 	 * run, it is driver's responsibility to release the
 	 * reserved budget. Also we have to handle failure case
 	 * of .get_budget for avoiding I/O deadlock.
 	 */
 	get_budget_fn		*get_budget;
+	/**
+	 * @put_budget: Release the reserved budget.
+	 */
 	put_budget_fn		*put_budget;
 
-	/*
-	 * Called on request timeout
+	/**
+	 * @timeout: Called on request timeout.
 	 */
 	timeout_fn		*timeout;
 
-	/*
-	 * Called to poll for completion of a specific tag.
+	/**
+	 * @poll: Called to poll for completion of a specific tag.
 	 */
 	poll_fn			*poll;
 
+	/**
+	 * @complete: Mark the request as complete.
+	 */
 	complete_fn		*complete;
 
-	/*
-	 * Called when the block layer side of a hardware queue has been
-	 * set up, allowing the driver to allocate/init matching structures.
-	 * Ditto for exit/teardown.
+	/**
+	 * @init_hctx: Called when the block layer side of a hardware queue has
+	 * been set up, allowing the driver to allocate/init matching
+	 * structures.
 	 */
 	init_hctx_fn		*init_hctx;
+	/**
+	 * @exit_hctx: Ditto for exit/teardown.
+	 */
 	exit_hctx_fn		*exit_hctx;
 
-	/*
-	 * Called for every command allocated by the block layer to allow
-	 * the driver to set up driver specific data.
+	/**
+	 * @init_request: Called for every command allocated by the block layer
+	 * to allow the driver to set up driver specific data.
 	 *
 	 * Tag greater than or equal to queue_depth is for setting up
 	 * flush request.
-	 *
-	 * Ditto for exit/teardown.
 	 */
 	init_request_fn		*init_request;
+	/**
+	 * @exit_request: Ditto for exit/teardown.
+	 */
 	exit_request_fn		*exit_request;
-	/* Called from inside blk_get_request() */
+
+	/**
+	 * @initialize_rq_fn: Called from inside blk_get_request().
+	 */
 	void (*initialize_rq_fn)(struct request *rq);
 
-	/*
-	 * Called before freeing one request which isn't completed yet,
-	 * and usually for freeing the driver private data
+	/**
+	 * @cleanup_rq: Called before freeing one request which isn't completed
+	 * yet, and usually for freeing the driver private data.
 	 */
 	cleanup_rq_fn		*cleanup_rq;
 
-	/*
-	 * If set, returns whether or not this queue currently is busy
+	/**
+	 * @busy: If set, returns whether or not this queue currently is busy.
 	 */
 	busy_fn			*busy;
 
+	/**
+	 * @map_queues: This allows drivers specify their own queue mapping by
+	 * overriding the setup-time function that builds the mq_map.
+	 */
 	map_queues_fn		*map_queues;
 
 #ifdef CONFIG_BLK_DEBUG_FS
-	/*
-	 * Used by the debugfs implementation to show driver-specific
+	/**
+	 * @show_rq: Used by the debugfs implementation to show driver-specific
 	 * information about a request.
 	 */
 	void (*show_rq)(struct seq_file *m, struct request *rq);
@@ -262,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
 void blk_mq_free_request(struct request *rq);
-bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 bool blk_mq_queue_inflight(struct request_queue *q);
 
@@ -301,9 +462,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 	return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
 }
 
+/**
+ * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
+ * @rq: target request.
+ */
+static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
+{
+	return READ_ONCE(rq->state);
+}
+
+static inline int blk_mq_request_started(struct request *rq)
+{
+	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
+}
+
+static inline int blk_mq_request_completed(struct request *rq)
+{
+	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
+}
 
-int blk_mq_request_started(struct request *rq);
-int blk_mq_request_completed(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
@@ -324,7 +501,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_quiesce_queue(struct request_queue *q);
 void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_run_hw_queues(struct request_queue *q, bool async);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
@@ -343,14 +520,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
 unsigned int blk_mq_rq_cpu(struct request *rq);
 
-/*
+/**
+ * blk_mq_rq_from_pdu - cast a PDU to a request
+ * @pdu: the PDU (Protocol Data Unit) to be casted
+ *
+ * Return: request
+ *
  * Driver command data is immediately after the request. So subtract request
- * size to get back to the original request, add request size to get the PDU.
+ * size to get back to the original request.
  */
 static inline struct request *blk_mq_rq_from_pdu(void *pdu)
 {
 	return pdu - sizeof(struct request);
 }
+
+/**
+ * blk_mq_rq_to_pdu - cast a request to a PDU
+ * @rq: the request to be casted
+ *
+ * Return: pointer to the PDU
+ *
+ * Driver command data is immediately after the request. So add request to get
+ * the PDU.
+ */
 static inline void *blk_mq_rq_to_pdu(struct request *rq)
 {
 	return rq + 1;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d688b96d1d63..70254ae11769 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -153,10 +153,10 @@ struct bio {
 	unsigned short		bi_write_hint;
 	blk_status_t		bi_status;
 	u8			bi_partno;
+	atomic_t		__bi_remaining;
 
 	struct bvec_iter	bi_iter;
 
-	atomic_t		__bi_remaining;
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;
@@ -290,6 +290,12 @@ enum req_opf {
 	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
+	/* Open a zone */
+	REQ_OP_ZONE_OPEN	= 10,
+	/* Close a zone */
+	REQ_OP_ZONE_CLOSE	= 11,
+	/* Transition a zone to full */
+	REQ_OP_ZONE_FINISH	= 12,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -371,6 +377,7 @@ enum stat_group {
 	STAT_READ,
 	STAT_WRITE,
 	STAT_DISCARD,
+	STAT_FLUSH,
 
 	NR_STAT_GROUPS
 };
@@ -417,6 +424,25 @@ static inline bool op_is_discard(unsigned int op)
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
 
+/*
+ * Check if a bio or request operation is a zone management operation, with
+ * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
+ * due to its different handling in the block layer and device response in
+ * case of command failure.
+ */
+static inline bool op_is_zone_mgmt(enum req_opf op)
+{
+	switch (op & REQ_OP_MASK) {
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline int op_stat_group(unsigned int op)
 {
 	if (op_is_discard(op))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f3ea78b0c91c..6a4f7abbdcf7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -360,14 +360,15 @@ extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
 			       unsigned int *nr_zones);
-extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
-			      sector_t nr_sectors, gfp_t gfp_mask);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+			    sector_t sectors, sector_t nr_sectors,
+			    gfp_t gfp_mask);
 extern int blk_revalidate_disk_zones(struct gendisk *disk);
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
-extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-				    unsigned int cmd, unsigned long arg);
+extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+				  unsigned int cmd, unsigned long arg);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
@@ -388,9 +389,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 	return -ENOTTY;
 }
 
-static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
-					   fmode_t mode, unsigned int cmd,
-					   unsigned long arg)
+static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
+					 fmode_t mode, unsigned int cmd,
+					 unsigned long arg)
 {
 	return -ENOTTY;
 }
@@ -411,7 +412,6 @@ struct request_queue {
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
-	unsigned int		nr_queues;
 
 	unsigned int		queue_depth;
 
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index a986ac12a848..e40d019c3d9d 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
  */
 bool sbitmap_any_bit_set(const struct sbitmap *sb);
 
-/**
- * sbitmap_any_bit_clear() - Check for an unset bit in a &struct
- * sbitmap.
- * @sb: Bitmap to check.
- *
- * Return: true if any bit in the bitmap is clear, false otherwise.
- */
-bool sbitmap_any_bit_clear(const struct sbitmap *sb);
-
 #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift)
 #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U))
 
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 53c28d750a45..1ac0d712a9c3 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	case IOC_OPAL_PSID_REVERT_TPR:
 	case IOC_OPAL_MBR_DONE:
 	case IOC_OPAL_WRITE_SHADOW_MBR:
+	case IOC_OPAL_GENERIC_TABLE_RW:
 		return true;
 	}
 	return false;
diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h
index b048694070e2..37342a13c9cb 100644
--- a/include/trace/events/wbt.h
+++ b/include/trace/events/wbt.h
@@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->rmean		= stat[0].mean;
 		__entry->rmin		= stat[0].min;
 		__entry->rmax		= stat[0].max;
@@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->lat = div_u64(lat, 1000);
 	),
 
@@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->msg	= msg;
 		__entry->step	= step;
 		__entry->window	= div_u64(window, 1000);
@@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->status		= status;
 		__entry->step		= step;
 		__entry->inflight	= inflight;
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index 498eec813494..0cdef67135f0 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -120,9 +120,11 @@ struct blk_zone_report {
 };
 
 /**
- * struct blk_zone_range - BLKRESETZONE ioctl request
- * @sector: starting sector of the first zone to issue reset write pointer
- * @nr_sectors: Total number of sectors of 1 or more zones to reset
+ * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/
+ *                         BLKCLOSEZONE/BLKFINISHZONE ioctl
+ *                         requests
+ * @sector: Starting sector of the first zone to operate on.
+ * @nr_sectors: Total number of sectors of all zones to operate on.
  */
 struct blk_zone_range {
 	__u64		sector;
@@ -139,10 +141,19 @@ struct blk_zone_range {
  *                sector range. The sector range must be zone aligned.
  * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors.
  * @BLKGETNRZONES: Get the total number of zones of the device.
+ * @BLKOPENZONE: Open the zones in the specified sector range.
+ *               The 512 B sector range must be zone aligned.
+ * @BLKCLOSEZONE: Close the zones in the specified sector range.
+ *                The 512 B sector range must be zone aligned.
+ * @BLKFINISHZONE: Mark the zones as full in the specified sector range.
+ *                 The 512 B sector range must be zone aligned.
  */
 #define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
 #define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
 #define BLKGETZONESZ	_IOR(0x12, 132, __u32)
 #define BLKGETNRZONES	_IOR(0x12, 133, __u32)
+#define BLKOPENZONE	_IOW(0x12, 134, struct blk_zone_range)
+#define BLKCLOSEZONE	_IOW(0x12, 135, struct blk_zone_range)
+#define BLKFINISHZONE	_IOW(0x12, 136, struct blk_zone_range)
 
 #endif /* _UAPI_BLKZONED_H */
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 1d338357df8a..1f97b33c840e 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -58,7 +58,7 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
@@ -66,6 +66,13 @@
 #define RWH_WRITE_LIFE_EXTREME	5
 
 /*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index c6d035fa1b6c..6f5af1a84213 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -113,6 +113,25 @@ struct opal_shadow_mbr {
 	__u64 size;
 };
 
+/* Opal table operations */
+enum opal_table_ops {
+	OPAL_READ_TABLE,
+	OPAL_WRITE_TABLE,
+};
+
+#define OPAL_UID_LENGTH 8
+struct opal_read_write_table {
+	struct opal_key key;
+	const __u64 data;
+	const __u8 table_uid[OPAL_UID_LENGTH];
+	__u64 offset;
+	__u64 size;
+#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE)
+#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE)
+	__u64 flags;
+	__u64 priv;
+};
+
 #define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
 #define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
 #define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
@@ -128,5 +147,6 @@ struct opal_shadow_mbr {
 #define IOC_OPAL_PSID_REVERT_TPR    _IOW('p', 232, struct opal_key)
 #define IOC_OPAL_MBR_DONE           _IOW('p', 233, struct opal_mbr_done)
 #define IOC_OPAL_WRITE_SHADOW_MBR   _IOW('p', 234, struct opal_shadow_mbr)
+#define IOC_OPAL_GENERIC_TABLE_RW   _IOW('p', 235, struct opal_read_write_table)
 
 #endif /* _UAPI_SED_OPAL_H */
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 969e5400a615..33feec8989f1 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -236,23 +236,6 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb)
 }
 EXPORT_SYMBOL_GPL(sbitmap_any_bit_set);
 
-bool sbitmap_any_bit_clear(const struct sbitmap *sb)
-{
-	unsigned int i;
-
-	for (i = 0; i < sb->map_nr; i++) {
-		const struct sbitmap_word *word = &sb->map[i];
-		unsigned long mask = word->word & ~word->cleared;
-		unsigned long ret;
-
-		ret = find_first_zero_bit(&mask, word->depth);
-		if (ret < word->depth)
-			return true;
-	}
-	return false;
-}
-EXPORT_SYMBOL_GPL(sbitmap_any_bit_clear);
-
 static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set)
 {
 	unsigned int i, weight = 0;
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 1d338357df8a..1f97b33c840e 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -58,7 +58,7 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
@@ -66,6 +66,13 @@
 #define RWH_WRITE_LIFE_EXTREME	5
 
 /*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */