1 files changed, 318 insertions, 492 deletions

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 9ebc2945f991..4896525b1c05 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -1,28 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
+#include <linux/build_bug.h>
 #include <linux/debugfs.h>
 
-#include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-debugfs.h"
-#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
+
+static int queue_poll_stat_show(void *data, struct seq_file *m)
+{
+	return 0;
+}
+
+static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_lock_irq(&q->requeue_lock);
+	return seq_list_start(&q->requeue_list, *pos);
+}
+
+static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct request_queue *q = m->private;
+
+	return seq_list_next(v, &q->requeue_list, pos);
+}
+
+static void queue_requeue_list_stop(struct seq_file *m, void *v)
+	__releases(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_unlock_irq(&q->requeue_lock);
+}
+
+static const struct seq_operations queue_requeue_list_seq_ops = {
+	.start	= queue_requeue_list_start,
+	.next	= queue_requeue_list_next,
+	.stop	= queue_requeue_list_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
 
 static int blk_flags_show(struct seq_file *m, const unsigned long flags,
 			  const char *const *flag_name, int flag_name_count)
@@ -44,37 +70,33 @@ static int blk_flags_show(struct seq_file *m, const unsigned long flags,
 	return 0;
 }
 
+static int queue_pm_only_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+
+	seq_printf(m, "%d\n", atomic_read(&q->pm_only));
+	return 0;
+}
+
 #define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name
 static const char *const blk_queue_flag_name[] = {
-	QUEUE_FLAG_NAME(QUEUED),
-	QUEUE_FLAG_NAME(STOPPED),
-	QUEUE_FLAG_NAME(SYNCFULL),
-	QUEUE_FLAG_NAME(ASYNCFULL),
 	QUEUE_FLAG_NAME(DYING),
-	QUEUE_FLAG_NAME(BYPASS),
-	QUEUE_FLAG_NAME(BIDI),
 	QUEUE_FLAG_NAME(NOMERGES),
 	QUEUE_FLAG_NAME(SAME_COMP),
 	QUEUE_FLAG_NAME(FAIL_IO),
-	QUEUE_FLAG_NAME(STACKABLE),
-	QUEUE_FLAG_NAME(NONROT),
-	QUEUE_FLAG_NAME(IO_STAT),
-	QUEUE_FLAG_NAME(DISCARD),
 	QUEUE_FLAG_NAME(NOXMERGES),
-	QUEUE_FLAG_NAME(ADD_RANDOM),
-	QUEUE_FLAG_NAME(SECERASE),
 	QUEUE_FLAG_NAME(SAME_FORCE),
-	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
-	QUEUE_FLAG_NAME(NO_SG_MERGE),
-	QUEUE_FLAG_NAME(POLL),
-	QUEUE_FLAG_NAME(WC),
-	QUEUE_FLAG_NAME(FUA),
-	QUEUE_FLAG_NAME(FLUSH_NQ),
-	QUEUE_FLAG_NAME(DAX),
 	QUEUE_FLAG_NAME(STATS),
-	QUEUE_FLAG_NAME(POLL_STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
+	QUEUE_FLAG_NAME(QUIESCED),
+	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
+	QUEUE_FLAG_NAME(HCTX_ACTIVE),
+	QUEUE_FLAG_NAME(SQ_SCHED),
+	QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
+	QUEUE_FLAG_NAME(NO_ELV_SWITCH),
+	QUEUE_FLAG_NAME(QOS_ENABLED),
+	QUEUE_FLAG_NAME(BIO_ISSUE_TIME),
 };
 #undef QUEUE_FLAG_NAME
 
@@ -82,6 +104,7 @@ static int queue_state_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
 
+	BUILD_BUG_ON(ARRAY_SIZE(blk_queue_flag_name) != QUEUE_FLAG_MAX);
 	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
 		       ARRAY_SIZE(blk_queue_flag_name));
 	seq_puts(m, "\n");
@@ -95,11 +118,10 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
 	char opbuf[16] = { }, *op;
 
 	/*
-	 * The "state" attribute is removed after blk_cleanup_queue() has called
-	 * blk_mq_free_queue(). Return if QUEUE_FLAG_DEAD has been set to avoid
-	 * triggering a use-after-free.
+	 * The "state" attribute is removed when the queue is removed.  Don't
+	 * allow setting the state on a dying queue to avoid a use-after-free.
 	 */
-	if (blk_queue_dead(q))
+	if (blk_queue_dying(q))
 		return -ENOENT;
 
 	if (count >= sizeof(opbuf)) {
@@ -125,63 +147,21 @@ inval:
 	return count;
 }
 
-static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
-{
-	if (stat->nr_samples) {
-		seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
-			   stat->nr_samples, stat->mean, stat->min, stat->max);
-	} else {
-		seq_puts(m, "samples=0");
-	}
-}
-
-static int queue_write_hint_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	int i;
-
-	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
-		seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
-
-	return 0;
-}
-
-static ssize_t queue_write_hint_store(void *data, const char __user *buf,
-				      size_t count, loff_t *ppos)
-{
-	struct request_queue *q = data;
-	int i;
-
-	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
-		q->write_hints[i] = 0;
-
-	return count;
-}
-
-static int queue_poll_stat_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	int bucket;
-
-	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
-		seq_printf(m, "read  (%d Bytes): ", 1 << (9+bucket));
-		print_stat(m, &q->poll_stat[2*bucket]);
-		seq_puts(m, "\n");
-
-		seq_printf(m, "write (%d Bytes): ",  1 << (9+bucket));
-		print_stat(m, &q->poll_stat[2*bucket+1]);
-		seq_puts(m, "\n");
-	}
-	return 0;
-}
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
+	{ "poll_stat", 0400, queue_poll_stat_show },
+	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
+	{ "pm_only", 0600, queue_pm_only_show, NULL },
+	{ "state", 0600, queue_state_show, queue_state_write },
+	{ "zone_wplugs", 0400, queue_zone_wplugs_show, NULL },
+	{ },
+};
 
 #define HCTX_STATE_NAME(name) [BLK_MQ_S_##name] = #name
 static const char *const hctx_state_name[] = {
 	HCTX_STATE_NAME(STOPPED),
 	HCTX_STATE_NAME(TAG_ACTIVE),
 	HCTX_STATE_NAME(SCHED_RESTART),
-	HCTX_STATE_NAME(TAG_WAITING),
-	HCTX_STATE_NAME(START_ON_RUN),
+	HCTX_STATE_NAME(INACTIVE),
 };
 #undef HCTX_STATE_NAME
 
@@ -189,66 +169,36 @@ static int hctx_state_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
 
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_state_name) != BLK_MQ_S_MAX);
 	blk_flags_show(m, hctx->state, hctx_state_name,
 		       ARRAY_SIZE(hctx_state_name));
 	seq_puts(m, "\n");
 	return 0;
 }
 
-#define BLK_TAG_ALLOC_NAME(name) [BLK_TAG_ALLOC_##name] = #name
-static const char *const alloc_policy_name[] = {
-	BLK_TAG_ALLOC_NAME(FIFO),
-	BLK_TAG_ALLOC_NAME(RR),
-};
-#undef BLK_TAG_ALLOC_NAME
-
 #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
 static const char *const hctx_flag_name[] = {
-	HCTX_FLAG_NAME(SHOULD_MERGE),
-	HCTX_FLAG_NAME(TAG_SHARED),
-	HCTX_FLAG_NAME(SG_MERGE),
+	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
+	HCTX_FLAG_NAME(STACKING),
+	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
-	HCTX_FLAG_NAME(NO_SCHED),
+	HCTX_FLAG_NAME(TAG_RR),
+	HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT),
 };
 #undef HCTX_FLAG_NAME
 
 static int hctx_flags_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
-	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
 
-	seq_puts(m, "alloc_policy=");
-	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
-	    alloc_policy_name[alloc_policy])
-		seq_puts(m, alloc_policy_name[alloc_policy]);
-	else
-		seq_printf(m, "%d", alloc_policy);
-	seq_puts(m, " ");
-	blk_flags_show(m,
-		       hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
-		       hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) != ilog2(BLK_MQ_F_MAX));
+
+	blk_flags_show(m, hctx->flags, hctx_flag_name,
+			ARRAY_SIZE(hctx_flag_name));
 	seq_puts(m, "\n");
 	return 0;
 }
 
-#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
-static const char *const op_name[] = {
-	REQ_OP_NAME(READ),
-	REQ_OP_NAME(WRITE),
-	REQ_OP_NAME(FLUSH),
-	REQ_OP_NAME(DISCARD),
-	REQ_OP_NAME(ZONE_REPORT),
-	REQ_OP_NAME(SECURE_ERASE),
-	REQ_OP_NAME(ZONE_RESET),
-	REQ_OP_NAME(WRITE_SAME),
-	REQ_OP_NAME(WRITE_ZEROES),
-	REQ_OP_NAME(SCSI_IN),
-	REQ_OP_NAME(SCSI_OUT),
-	REQ_OP_NAME(DRV_IN),
-	REQ_OP_NAME(DRV_OUT),
-};
-#undef REQ_OP_NAME
-
 #define CMD_FLAG_NAME(name) [__REQ_##name] = #name
 static const char *const cmd_flag_name[] = {
 	CMD_FLAG_NAME(FAILFAST_DEV),
@@ -264,60 +214,73 @@ static const char *const cmd_flag_name[] = {
 	CMD_FLAG_NAME(PREFLUSH),
 	CMD_FLAG_NAME(RAHEAD),
 	CMD_FLAG_NAME(BACKGROUND),
+	CMD_FLAG_NAME(NOWAIT),
+	CMD_FLAG_NAME(POLLED),
+	CMD_FLAG_NAME(ALLOC_CACHE),
+	CMD_FLAG_NAME(SWAP),
+	CMD_FLAG_NAME(DRV),
+	CMD_FLAG_NAME(FS_PRIVATE),
+	CMD_FLAG_NAME(ATOMIC),
 	CMD_FLAG_NAME(NOUNMAP),
 };
 #undef CMD_FLAG_NAME
 
-#define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name
+#define RQF_NAME(name) [__RQF_##name] = #name
 static const char *const rqf_name[] = {
-	RQF_NAME(SORTED),
 	RQF_NAME(STARTED),
-	RQF_NAME(QUEUED),
-	RQF_NAME(SOFTBARRIER),
 	RQF_NAME(FLUSH_SEQ),
 	RQF_NAME(MIXED_MERGE),
-	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
-	RQF_NAME(PREEMPT),
-	RQF_NAME(COPY_USER),
+	RQF_NAME(SCHED_TAGS),
+	RQF_NAME(USE_SCHED),
 	RQF_NAME(FAILED),
 	RQF_NAME(QUIET),
-	RQF_NAME(ELVPRIV),
 	RQF_NAME(IO_STAT),
-	RQF_NAME(ALLOCED),
 	RQF_NAME(PM),
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
+	RQF_NAME(ZONE_WRITE_PLUGGING),
+	RQF_NAME(TIMED_OUT),
+	RQF_NAME(RESV),
 };
 #undef RQF_NAME
 
-#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
-static const char *const rqaf_name[] = {
-	RQAF_NAME(COMPLETE),
-	RQAF_NAME(STARTED),
-	RQAF_NAME(POLL_SLEPT),
+static const char *const blk_mq_rq_state_name_array[] = {
+	[MQ_RQ_IDLE]		= "idle",
+	[MQ_RQ_IN_FLIGHT]	= "in_flight",
+	[MQ_RQ_COMPLETE]	= "complete",
 };
-#undef RQAF_NAME
+
+static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
+{
+	if (WARN_ON_ONCE((unsigned int)rq_state >=
+			 ARRAY_SIZE(blk_mq_rq_state_name_array)))
+		return "(?)";
+	return blk_mq_rq_state_name_array[rq_state];
+}
 
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
-	const unsigned int op = rq->cmd_flags & REQ_OP_MASK;
+	const enum req_op op = req_op(rq);
+	const char *op_str = blk_op_str(op);
+
+	BUILD_BUG_ON(ARRAY_SIZE(cmd_flag_name) != __REQ_NR_BITS);
+	BUILD_BUG_ON(ARRAY_SIZE(rqf_name) != __RQF_BITS);
 
 	seq_printf(m, "%p {.op=", rq);
-	if (op < ARRAY_SIZE(op_name) && op_name[op])
-		seq_printf(m, "%s", op_name[op]);
+	if (strcmp(op_str, "UNKNOWN") == 0)
+		seq_printf(m, "%u", op);
 	else
-		seq_printf(m, "%d", op);
+		seq_printf(m, "%s", op_str);
 	seq_puts(m, ", .cmd_flags=");
-	blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
-		       ARRAY_SIZE(cmd_flag_name));
+	blk_flags_show(m, (__force unsigned int)(rq->cmd_flags & ~REQ_OP_MASK),
+		       cmd_flag_name, ARRAY_SIZE(cmd_flag_name));
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
-	seq_puts(m, ", .atomic_flags=");
-	blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
+	seq_printf(m, ", .state=%s", blk_mq_rq_state_name(blk_mq_rq_state(rq)));
 	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
 		   rq->internal_tag);
 	if (mq_ops->show_rq)
@@ -333,37 +296,6 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 }
 EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
 
-static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
-	__acquires(&q->requeue_lock)
-{
-	struct request_queue *q = m->private;
-
-	spin_lock_irq(&q->requeue_lock);
-	return seq_list_start(&q->requeue_list, *pos);
-}
-
-static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	struct request_queue *q = m->private;
-
-	return seq_list_next(v, &q->requeue_list, pos);
-}
-
-static void queue_requeue_list_stop(struct seq_file *m, void *v)
-	__releases(&q->requeue_lock)
-{
-	struct request_queue *q = m->private;
-
-	spin_unlock_irq(&q->requeue_lock);
-}
-
-static const struct seq_operations queue_requeue_list_seq_ops = {
-	.start	= queue_requeue_list_start,
-	.next	= queue_requeue_list_next,
-	.stop	= queue_requeue_list_stop,
-	.show	= blk_mq_debugfs_rq_show,
-};
-
 static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
 	__acquires(&hctx->lock)
 {
@@ -402,26 +334,47 @@ struct show_busy_params {
 
 /*
  * Note: the state of a request may change while this function is in progress,
- * e.g. due to a concurrent blk_mq_finish_request() call.
+ * e.g. due to a concurrent blk_mq_finish_request() call. Returns true to
+ * keep iterating requests.
  */
-static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+static bool hctx_show_busy_rq(struct request *rq, void *data)
 {
 	const struct show_busy_params *params = data;
 
-	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
-	    test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
-		__blk_mq_debugfs_rq_show(params->m,
-					 list_entry_rq(&rq->queuelist));
+	if (rq->mq_hctx == params->hctx)
+		__blk_mq_debugfs_rq_show(params->m, rq);
+
+	return true;
 }
 
 static int hctx_busy_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
 	struct show_busy_params params = { .m = m, .hctx = hctx };
+	int res;
 
+	res = mutex_lock_interruptible(&hctx->queue->elevator_lock);
+	if (res)
+		return res;
 	blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
 				&params);
+	mutex_unlock(&hctx->queue->elevator_lock);
+
+	return 0;
+}
+
+static const char *const hctx_types[] = {
+	[HCTX_TYPE_DEFAULT]	= "default",
+	[HCTX_TYPE_READ]	= "read",
+	[HCTX_TYPE_POLL]	= "poll",
+};
 
+static int hctx_type_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_types) != HCTX_MAX_TYPES);
+	seq_printf(m, "%s\n", hctx_types[hctx->type]);
 	return 0;
 }
 
@@ -439,7 +392,7 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,
 	seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
 	seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
 	seq_printf(m, "active_queues=%d\n",
-		   atomic_read(&tags->active_queues));
+		   READ_ONCE(tags->active_queues));
 
 	seq_puts(m, "\nbitmap_tags:\n");
 	sbitmap_queue_show(&tags->bitmap_tags, m);
@@ -456,15 +409,14 @@ static int hctx_tags_show(void *data, struct seq_file *m)
 	struct request_queue *q = hctx->queue;
 	int res;
 
-	res = mutex_lock_interruptible(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->elevator_lock);
 	if (res)
-		goto out;
+		return res;
 	if (hctx->tags)
 		blk_mq_debugfs_tags_show(m, hctx->tags);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->elevator_lock);
 
-out:
-	return res;
+	return 0;
 }
 
 static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
@@ -473,15 +425,14 @@ static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
 	struct request_queue *q = hctx->queue;
 	int res;
 
-	res = mutex_lock_interruptible(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->elevator_lock);
 	if (res)
-		goto out;
+		return res;
 	if (hctx->tags)
 		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->elevator_lock);
 
-out:
-	return res;
+	return 0;
 }
 
 static int hctx_sched_tags_show(void *data, struct seq_file *m)
@@ -490,15 +441,14 @@ static int hctx_sched_tags_show(void *data, struct seq_file *m)
 	struct request_queue *q = hctx->queue;
 	int res;
 
-	res = mutex_lock_interruptible(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->elevator_lock);
 	if (res)
-		goto out;
+		return res;
 	if (hctx->sched_tags)
 		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->elevator_lock);
 
-out:
-	return res;
+	return 0;
 }
 
 static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
@@ -507,191 +457,73 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
 	struct request_queue *q = hctx->queue;
 	int res;
 
-	res = mutex_lock_interruptible(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->elevator_lock);
 	if (res)
-		goto out;
+		return res;
 	if (hctx->sched_tags)
 		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_unlock(&q->elevator_lock);
 
-out:
-	return res;
-}
-
-static int hctx_io_poll_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "considered=%lu\n", hctx->poll_considered);
-	seq_printf(m, "invoked=%lu\n", hctx->poll_invoked);
-	seq_printf(m, "success=%lu\n", hctx->poll_success);
 	return 0;
 }
 
-static ssize_t hctx_io_poll_write(void *data, const char __user *buf,
-				  size_t count, loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
-	return count;
-}
-
-static int hctx_dispatched_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-	int i;
-
-	seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
-
-	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
-		unsigned int d = 1U << (i - 1);
-
-		seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]);
-	}
-
-	seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]);
-	return 0;
-}
-
-static ssize_t hctx_dispatched_write(void *data, const char __user *buf,
-				     size_t count, loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-	int i;
-
-	for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
-		hctx->dispatched[i] = 0;
-	return count;
-}
-
-static int hctx_queued_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->queued);
-	return 0;
-}
-
-static ssize_t hctx_queued_write(void *data, const char __user *buf,
-				 size_t count, loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->queued = 0;
-	return count;
-}
-
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
 
-	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+	seq_printf(m, "%d\n", __blk_mq_active_requests(hctx));
 	return 0;
 }
 
-static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
-	__acquires(&ctx->lock)
+static int hctx_dispatch_busy_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_ctx *ctx = m->private;
-
-	spin_lock(&ctx->lock);
-	return seq_list_start(&ctx->rq_list, *pos);
-}
-
-static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	struct blk_mq_ctx *ctx = m->private;
-
-	return seq_list_next(v, &ctx->rq_list, pos);
-}
-
-static void ctx_rq_list_stop(struct seq_file *m, void *v)
-	__releases(&ctx->lock)
-{
-	struct blk_mq_ctx *ctx = m->private;
-
-	spin_unlock(&ctx->lock);
-}
-
-static const struct seq_operations ctx_rq_list_seq_ops = {
-	.start	= ctx_rq_list_start,
-	.next	= ctx_rq_list_next,
-	.stop	= ctx_rq_list_stop,
-	.show	= blk_mq_debugfs_rq_show,
-};
-static int ctx_dispatched_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
-	return 0;
-}
-
-static ssize_t ctx_dispatched_write(void *data, const char __user *buf,
-				    size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
-	return count;
-}
-
-static int ctx_merged_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	seq_printf(m, "%lu\n", ctx->rq_merged);
-	return 0;
-}
-
-static ssize_t ctx_merged_write(void *data, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_merged = 0;
-	return count;
-}
-
-static int ctx_completed_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
+	struct blk_mq_hw_ctx *hctx = data;
 
-	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
+	seq_printf(m, "%u\n", hctx->dispatch_busy);
 	return 0;
 }
 
-static ssize_t ctx_completed_write(void *data, const char __user *buf,
-				   size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
-	return count;
-}
+#define CTX_RQ_SEQ_OPS(name, type)					\
+static void *ctx_##name##_rq_list_start(struct seq_file *m, loff_t *pos) \
+	__acquires(&ctx->lock)						\
+{									\
+	struct blk_mq_ctx *ctx = m->private;				\
+									\
+	spin_lock(&ctx->lock);						\
+	return seq_list_start(&ctx->rq_lists[type], *pos);		\
+}									\
+									\
+static void *ctx_##name##_rq_list_next(struct seq_file *m, void *v,	\
+				     loff_t *pos)			\
+{									\
+	struct blk_mq_ctx *ctx = m->private;				\
+									\
+	return seq_list_next(v, &ctx->rq_lists[type], pos);		\
+}									\
+									\
+static void ctx_##name##_rq_list_stop(struct seq_file *m, void *v)	\
+	__releases(&ctx->lock)						\
+{									\
+	struct blk_mq_ctx *ctx = m->private;				\
+									\
+	spin_unlock(&ctx->lock);					\
+}									\
+									\
+static const struct seq_operations ctx_##name##_rq_list_seq_ops = {	\
+	.start	= ctx_##name##_rq_list_start,				\
+	.next	= ctx_##name##_rq_list_next,				\
+	.stop	= ctx_##name##_rq_list_stop,				\
+	.show	= blk_mq_debugfs_rq_show,				\
+}
+
+CTX_RQ_SEQ_OPS(default, HCTX_TYPE_DEFAULT);
+CTX_RQ_SEQ_OPS(read, HCTX_TYPE_READ);
+CTX_RQ_SEQ_OPS(poll, HCTX_TYPE_POLL);
 
 static int blk_mq_debugfs_show(struct seq_file *m, void *v)
 {
 	const struct blk_mq_debugfs_attr *attr = m->private;
-	void *data = d_inode(m->file->f_path.dentry->d_parent)->i_private;
+	void *data = debugfs_get_aux(m->file);
 
 	return attr->show(data, m);
 }
@@ -701,9 +533,13 @@ static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
 {
 	struct seq_file *m = file->private_data;
 	const struct blk_mq_debugfs_attr *attr = m->private;
-	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;
+	void *data = debugfs_get_aux(file);
 
-	if (!attr->write)
+	/*
+	 * Attributes that only implement .seq_ops are read-only and 'attr' is
+	 * the same with 'data' in this case.
+	 */
+	if (attr == data || !attr->write)
 		return -EPERM;
 
 	return attr->write(data, buf, count, ppos);
@@ -712,7 +548,7 @@ static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
 static int blk_mq_debugfs_open(struct inode *inode, struct file *file)
 {
 	const struct blk_mq_debugfs_attr *attr = inode->i_private;
-	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;
+	void *data = debugfs_get_aux(file);
 	struct seq_file *m;
 	int ret;
 
@@ -737,11 +573,11 @@ static int blk_mq_debugfs_release(struct inode *inode, struct file *file)
 
 	if (attr->show)
 		return single_release(inode, file);
-	else
-		return seq_release(inode, file);
+
+	return seq_release(inode, file);
 }
 
-const struct file_operations blk_mq_debugfs_fops = {
+static const struct file_operations blk_mq_debugfs_fops = {
 	.open		= blk_mq_debugfs_open,
 	.read		= seq_read,
 	.write		= blk_mq_debugfs_write,
@@ -749,14 +585,6 @@ const struct file_operations blk_mq_debugfs_fops = {
 	.release	= blk_mq_debugfs_release,
 };
 
-static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
-	{"poll_stat", 0400, queue_poll_stat_show},
-	{"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops},
-	{"state", 0600, queue_state_show, queue_state_write},
-	{"write_hints", 0600, queue_write_hint_show, queue_write_hint_store},
-	{},
-};
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"state", 0400, hctx_state_show},
 	{"flags", 0400, hctx_flags_show},
@@ -767,212 +595,210 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write},
-	{"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write},
-	{"queued", 0600, hctx_queued_show, hctx_queued_write},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
+	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
+	{"type", 0400, hctx_type_show},
 	{},
 };
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
-	{"rq_list", 0400, .seq_ops = &ctx_rq_list_seq_ops},
-	{"dispatched", 0600, ctx_dispatched_show, ctx_dispatched_write},
-	{"merged", 0600, ctx_merged_show, ctx_merged_write},
-	{"completed", 0600, ctx_completed_show, ctx_completed_write},
+	{"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops},
+	{"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops},
+	{"poll_rq_list", 0400, .seq_ops = &ctx_poll_rq_list_seq_ops},
 	{},
 };
 
-static bool debugfs_create_files(struct dentry *parent, void *data,
+static void debugfs_create_files(struct dentry *parent, void *data,
 				 const struct blk_mq_debugfs_attr *attr)
 {
-	d_inode(parent)->i_private = data;
+	if (IS_ERR_OR_NULL(parent))
+		return;
 
-	for (; attr->name; attr++) {
-		if (!debugfs_create_file(attr->name, attr->mode, parent,
-					 (void *)attr, &blk_mq_debugfs_fops))
-			return false;
-	}
-	return true;
+	for (; attr->name; attr++)
+		debugfs_create_file_aux(attr->name, attr->mode, parent,
+				    (void *)attr, data, &blk_mq_debugfs_fops);
 }
 
-int blk_mq_debugfs_register(struct request_queue *q)
+void blk_mq_debugfs_register(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
+	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-	if (!q->debugfs_dir)
-		return -ENOMEM;
-
-	if (!debugfs_create_files(q->debugfs_dir, q,
-				  blk_mq_debugfs_queue_attrs))
-		goto err;
-
-	/*
-	 * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir
-	 * didn't exist yet (because we don't know what to name the directory
-	 * until the queue is registered to a gendisk).
-	 */
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx))
-			goto err;
-		if (q->elevator && !hctx->sched_debugfs_dir &&
-		    blk_mq_debugfs_register_sched_hctx(q, hctx))
-			goto err;
+		if (!hctx->debugfs_dir)
+			blk_mq_debugfs_register_hctx(q, hctx);
 	}
 
-	return 0;
+	if (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
 
-err:
-	blk_mq_debugfs_unregister(q);
-	return -ENOMEM;
-}
-
-void blk_mq_debugfs_unregister(struct request_queue *q)
-{
-	debugfs_remove_recursive(q->debugfs_dir);
-	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
+		while (rqos) {
+			blk_mq_debugfs_register_rqos(rqos);
+			rqos = rqos->next;
+		}
+	}
 }
 
-static int blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
-				       struct blk_mq_ctx *ctx)
+static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
+					struct blk_mq_ctx *ctx)
 {
 	struct dentry *ctx_dir;
 	char name[20];
 
 	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
 	ctx_dir = debugfs_create_dir(name, hctx->debugfs_dir);
-	if (!ctx_dir)
-		return -ENOMEM;
-
-	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
-		return -ENOMEM;
 
-	return 0;
+	debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs);
 }
 
-int blk_mq_debugfs_register_hctx(struct request_queue *q,
-				 struct blk_mq_hw_ctx *hctx)
+void blk_mq_debugfs_register_hctx(struct request_queue *q,
+				  struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_ctx *ctx;
 	char name[20];
 	int i;
 
 	if (!q->debugfs_dir)
-		return -ENOENT;
+		return;
 
 	snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);
 	hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);
-	if (!hctx->debugfs_dir)
-		return -ENOMEM;
 
-	if (!debugfs_create_files(hctx->debugfs_dir, hctx,
-				  blk_mq_debugfs_hctx_attrs))
-		goto err;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		if (blk_mq_debugfs_register_ctx(hctx, ctx))
-			goto err;
-	}
+	debugfs_create_files(hctx->debugfs_dir, hctx, blk_mq_debugfs_hctx_attrs);
 
-	return 0;
-
-err:
-	blk_mq_debugfs_unregister_hctx(hctx);
-	return -ENOMEM;
+	hctx_for_each_ctx(hctx, ctx, i)
+		blk_mq_debugfs_register_ctx(hctx, ctx);
 }
 
 void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
 {
+	if (!hctx->queue->debugfs_dir)
+		return;
 	debugfs_remove_recursive(hctx->debugfs_dir);
 	hctx->sched_debugfs_dir = NULL;
 	hctx->debugfs_dir = NULL;
 }
 
-int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+void blk_mq_debugfs_register_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (blk_mq_debugfs_register_hctx(q, hctx))
-			return -ENOMEM;
-	}
-
-	return 0;
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_debugfs_register_hctx(q, hctx);
 }
 
 void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
-	int i;
+	unsigned long i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_debugfs_unregister_hctx(hctx);
 }
 
-int blk_mq_debugfs_register_sched(struct request_queue *q)
+void blk_mq_debugfs_register_sched(struct request_queue *q)
 {
 	struct elevator_type *e = q->elevator->type;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
+	/*
+	 * If the parent directory has not been created yet, return, we will be
+	 * called again later on and the directory/files will be created then.
+	 */
 	if (!q->debugfs_dir)
-		return -ENOENT;
+		return;
 
 	if (!e->queue_debugfs_attrs)
-		return 0;
+		return;
 
 	q->sched_debugfs_dir = debugfs_create_dir("sched", q->debugfs_dir);
-	if (!q->sched_debugfs_dir)
-		return -ENOMEM;
 
-	if (!debugfs_create_files(q->sched_debugfs_dir, q,
-				  e->queue_debugfs_attrs))
-		goto err;
-
-	return 0;
-
-err:
-	blk_mq_debugfs_unregister_sched(q);
-	return -ENOMEM;
+	debugfs_create_files(q->sched_debugfs_dir, q, e->queue_debugfs_attrs);
 }
 
 void blk_mq_debugfs_unregister_sched(struct request_queue *q)
 {
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	debugfs_remove_recursive(q->sched_debugfs_dir);
 	q->sched_debugfs_dir = NULL;
 }
 
-int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
-				       struct blk_mq_hw_ctx *hctx)
+static const char *rq_qos_id_to_name(enum rq_qos_id id)
+{
+	switch (id) {
+	case RQ_QOS_WBT:
+		return "wbt";
+	case RQ_QOS_LATENCY:
+		return "latency";
+	case RQ_QOS_COST:
+		return "cost";
+	}
+	return "unknown";
+}
+
+void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
+{
+	lockdep_assert_held(&rqos->disk->queue->debugfs_mutex);
+
+	if (!rqos->disk->queue->debugfs_dir)
+		return;
+	debugfs_remove_recursive(rqos->debugfs_dir);
+	rqos->debugfs_dir = NULL;
+}
+
+void blk_mq_debugfs_register_rqos(struct rq_qos *rqos)
+{
+	struct request_queue *q = rqos->disk->queue;
+	const char *dir_name = rq_qos_id_to_name(rqos->id);
+
+	lockdep_assert_held(&q->debugfs_mutex);
+
+	if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs)
+		return;
+
+	if (!q->rqos_debugfs_dir)
+		q->rqos_debugfs_dir = debugfs_create_dir("rqos",
+							 q->debugfs_dir);
+
+	rqos->debugfs_dir = debugfs_create_dir(dir_name, q->rqos_debugfs_dir);
+	debugfs_create_files(rqos->debugfs_dir, rqos, rqos->ops->debugfs_attrs);
+}
+
+void blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
+					struct blk_mq_hw_ctx *hctx)
 {
 	struct elevator_type *e = q->elevator->type;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
+	/*
+	 * If the parent debugfs directory has not been created yet, return;
+	 * We will be called again later on with appropriate parent debugfs
+	 * directory from blk_register_queue()
+	 */
 	if (!hctx->debugfs_dir)
-		return -ENOENT;
+		return;
 
 	if (!e->hctx_debugfs_attrs)
-		return 0;
+		return;
 
 	hctx->sched_debugfs_dir = debugfs_create_dir("sched",
 						     hctx->debugfs_dir);
-	if (!hctx->sched_debugfs_dir)
-		return -ENOMEM;
-
-	if (!debugfs_create_files(hctx->sched_debugfs_dir, hctx,
-				  e->hctx_debugfs_attrs))
-		return -ENOMEM;
-
-	return 0;
+	debugfs_create_files(hctx->sched_debugfs_dir, hctx,
+			     e->hctx_debugfs_attrs);
 }
 
 void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
 {
+	lockdep_assert_held(&hctx->queue->debugfs_mutex);
+
+	if (!hctx->queue->debugfs_dir)
+		return;
 	debugfs_remove_recursive(hctx->sched_debugfs_dir);
 	hctx->sched_debugfs_dir = NULL;
 }