Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block fixes and updates from Jens Axboe:
"Some fixes and followup features/changes that should go in, in this
merge window. This contains:

- Two fixes for lightnvm from Javier, fixing problems in the new code
merge previously in this merge window.

- A fix from Jan for the backing device changes, fixing an issue in
NFS that causes a failure to mount on certain setups.

- A change from Christoph, cleaning up the blk-mq init and exit
request paths.

- Remove elevator_change(), which is now unused. From Bart.

- A fix for queue operation invocation on a dead queue, from Bart.

- A series fixing up mtip32xx for blk-mq scheduling, removing a
bandaid we previously had in place for this. From me.

- A regression fix for this series, fixing a case where we wait on
workqueue flushing from an invalid (non-blocking) context. From me.

- A fix/optimization from Ming, ensuring that we don't both quiesce
and freeze a queue at the same time.

- A fix from Peter on lock ordering for CPU hotplug. Not a real
problem right now, but will be once the CPU hotplug rework goes in.

- A series from Omar, cleaning up out blk-mq debugfs support, and
adding support for exporting info from schedulers in debugfs as
well. This is really useful in debugging stalls or livelocks. From
Omar"

* 'for-linus' of git://git.kernel.dk/linux-block: (28 commits)
mq-deadline: add debugfs attributes
kyber: add debugfs attributes
blk-mq-debugfs: allow schedulers to register debugfs attributes
blk-mq: untangle debugfs and sysfs
blk-mq: move debugfs declarations to a separate header file
blk-mq: Do not invoke queue operations on a dead queue
blk-mq-debugfs: get rid of a bunch of boilerplate
blk-mq-debugfs: rename hw queue directories from <n> to hctx<n>
blk-mq-debugfs: don't open code strstrip()
blk-mq-debugfs: error on long write to queue "state" file
blk-mq-debugfs: clean up flag definitions
blk-mq-debugfs: separate flags with |
nfs: Fix bdi handling for cloned superblocks
block/mq: Cure cpu hotplug lock inversion
lightnvm: fix bad back free on error path
lightnvm: create cmd before allocating request
blk-mq: don't use sync workqueue flushing from drivers
mtip32xx: convert internal commands to regular block infrastructure
mtip32xx: cleanup internal tag assumptions
block: don't call blk_mq_quiesce_queue() after queue is frozen
...

block/blk-core.c

···
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
 	blk_freeze_queue(q);
-	if (!q->mq_ops) {
-		spin_lock_irq(lock);
+	spin_lock_irq(lock);
+	if (!q->mq_ops)
 		__blk_drain_queue(q, true);
-	} else {
-		blk_mq_debugfs_unregister_mq(q);
-		spin_lock_irq(lock);
-	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 

block/blk-mq-debugfs.c

···
 #include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
-
-struct blk_mq_debugfs_attr {
-	const char *name;
-	umode_t mode;
-	const struct file_operations *fops;
-};
-
-static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
-				   const struct seq_operations *ops)
-{
-	struct seq_file *m;
-	int ret;
-
-	ret = seq_open(file, ops);
-	if (!ret) {
-		m = file->private_data;
-		m->private = inode->i_private;
-	}
-	return ret;
-}
 
 static int blk_flags_show(struct seq_file *m, const unsigned long flags,
 			  const char *const *flag_name, int flag_name_count)
···
 		if (!(flags & BIT(i)))
 			continue;
 		if (sep)
-			seq_puts(m, " ");
+			seq_puts(m, "|");
 		sep = true;
 		if (i < flag_name_count && flag_name[i])
 			seq_puts(m, flag_name[i]);
···
 	return 0;
 }
 
+#define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name
 static const char *const blk_queue_flag_name[] = {
-	[QUEUE_FLAG_QUEUED]	 = "QUEUED",
-	[QUEUE_FLAG_STOPPED]	 = "STOPPED",
-	[QUEUE_FLAG_SYNCFULL]	 = "SYNCFULL",
-	[QUEUE_FLAG_ASYNCFULL]	 = "ASYNCFULL",
-	[QUEUE_FLAG_DYING]	 = "DYING",
-	[QUEUE_FLAG_BYPASS]	 = "BYPASS",
-	[QUEUE_FLAG_BIDI]	 = "BIDI",
-	[QUEUE_FLAG_NOMERGES]	 = "NOMERGES",
-	[QUEUE_FLAG_SAME_COMP]	 = "SAME_COMP",
-	[QUEUE_FLAG_FAIL_IO]	 = "FAIL_IO",
-	[QUEUE_FLAG_STACKABLE]	 = "STACKABLE",
-	[QUEUE_FLAG_NONROT]	 = "NONROT",
-	[QUEUE_FLAG_IO_STAT]	 = "IO_STAT",
-	[QUEUE_FLAG_DISCARD]	 = "DISCARD",
-	[QUEUE_FLAG_NOXMERGES]	 = "NOXMERGES",
-	[QUEUE_FLAG_ADD_RANDOM]	 = "ADD_RANDOM",
-	[QUEUE_FLAG_SECERASE]	 = "SECERASE",
-	[QUEUE_FLAG_SAME_FORCE]	 = "SAME_FORCE",
-	[QUEUE_FLAG_DEAD]	 = "DEAD",
-	[QUEUE_FLAG_INIT_DONE]	 = "INIT_DONE",
-	[QUEUE_FLAG_NO_SG_MERGE] = "NO_SG_MERGE",
-	[QUEUE_FLAG_POLL]	 = "POLL",
-	[QUEUE_FLAG_WC]		 = "WC",
-	[QUEUE_FLAG_FUA]	 = "FUA",
-	[QUEUE_FLAG_FLUSH_NQ]	 = "FLUSH_NQ",
-	[QUEUE_FLAG_DAX]	 = "DAX",
-	[QUEUE_FLAG_STATS]	 = "STATS",
-	[QUEUE_FLAG_POLL_STATS]	 = "POLL_STATS",
-	[QUEUE_FLAG_REGISTERED]	 = "REGISTERED",
+	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),
 };
+#undef QUEUE_FLAG_NAME
 
-static int blk_queue_flags_show(struct seq_file *m, void *v)
+static int queue_state_show(void *data, struct seq_file *m)
 {
-	struct request_queue *q = m->private;
+	struct request_queue *q = data;
 
 	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
 		       ARRAY_SIZE(blk_queue_flag_name));
···
 	return 0;
 }
 
-static ssize_t blk_queue_flags_store(struct file *file, const char __user *ubuf,
-				     size_t len, loff_t *offp)
+static ssize_t queue_state_write(void *data, const char __user *buf,
+				 size_t count, loff_t *ppos)
 {
-	struct request_queue *q = file_inode(file)->i_private;
-	char op[16] = { }, *s;
+	struct request_queue *q = data;
+	char opbuf[16] = { }, *op;
 
-	len = min(len, sizeof(op) - 1);
-	if (copy_from_user(op, ubuf, len))
+	/*
+	 * 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.
+	 */
+	if (blk_queue_dead(q))
+		return -ENOENT;
+
+	if (count >= sizeof(opbuf)) {
+		pr_err("%s: operation too long\n", __func__);
+		goto inval;
+	}
+
+	if (copy_from_user(opbuf, buf, count))
 		return -EFAULT;
-	s = op;
-	strsep(&s, " \t\n"); /* strip trailing whitespace */
+	op = strstrip(opbuf);
 	if (strcmp(op, "run") == 0) {
 		blk_mq_run_hw_queues(q, true);
 	} else if (strcmp(op, "start") == 0) {
 		blk_mq_start_stopped_hw_queues(q, true);
 	} else {
-		pr_err("%s: unsupported operation %s. Use either 'run' or 'start'\n",
-		       __func__, op);
+		pr_err("%s: unsupported operation '%s'\n", __func__, op);
+inval:
+		pr_err("%s: use either 'run' or 'start'\n", __func__);
 		return -EINVAL;
 	}
-	return len;
+	return count;
 }
-
-static int blk_queue_flags_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, blk_queue_flags_show, inode->i_private);
-}
-
-static const struct file_operations blk_queue_flags_fops = {
-	.open		= blk_queue_flags_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= blk_queue_flags_store,
-};
 
 static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
 {
···
 	}
 }
 
-static int queue_poll_stat_show(struct seq_file *m, void *v)
+static int queue_poll_stat_show(void *data, struct seq_file *m)
 {
-	struct request_queue *q = m->private;
+	struct request_queue *q = data;
 	int bucket;
 
 	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
···
 	return 0;
 }
 
-static int queue_poll_stat_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, queue_poll_stat_show, inode->i_private);
-}
-
-static const struct file_operations queue_poll_stat_fops = {
-	.open		= queue_poll_stat_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
+#define HCTX_STATE_NAME(name) [BLK_MQ_S_##name] = #name
 static const char *const hctx_state_name[] = {
-	[BLK_MQ_S_STOPPED]	 = "STOPPED",
-	[BLK_MQ_S_TAG_ACTIVE]	 = "TAG_ACTIVE",
-	[BLK_MQ_S_SCHED_RESTART] = "SCHED_RESTART",
-	[BLK_MQ_S_TAG_WAITING]	 = "TAG_WAITING",
-
+	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),
 };
-static int hctx_state_show(struct seq_file *m, void *v)
+#undef HCTX_STATE_NAME
+
+static int hctx_state_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	blk_flags_show(m, hctx->state, hctx_state_name,
 		       ARRAY_SIZE(hctx_state_name));
···
 	return 0;
 }
 
-static int hctx_state_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_state_show, inode->i_private);
-}
-
-static const struct file_operations hctx_state_fops = {
-	.open		= hctx_state_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
+#define BLK_TAG_ALLOC_NAME(name) [BLK_TAG_ALLOC_##name] = #name
 static const char *const alloc_policy_name[] = {
-	[BLK_TAG_ALLOC_FIFO]	= "fifo",
-	[BLK_TAG_ALLOC_RR]	= "rr",
+	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[] = {
-	[ilog2(BLK_MQ_F_SHOULD_MERGE)]	= "SHOULD_MERGE",
-	[ilog2(BLK_MQ_F_TAG_SHARED)]	= "TAG_SHARED",
-	[ilog2(BLK_MQ_F_SG_MERGE)]	= "SG_MERGE",
-	[ilog2(BLK_MQ_F_BLOCKING)]	= "BLOCKING",
-	[ilog2(BLK_MQ_F_NO_SCHED)]	= "NO_SCHED",
+	HCTX_FLAG_NAME(SHOULD_MERGE),
+	HCTX_FLAG_NAME(TAG_SHARED),
+	HCTX_FLAG_NAME(SG_MERGE),
+	HCTX_FLAG_NAME(BLOCKING),
+	HCTX_FLAG_NAME(NO_SCHED),
 };
+#undef HCTX_FLAG_NAME
 
-static int hctx_flags_show(struct seq_file *m, void *v)
+static int hctx_flags_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
 
 	seq_puts(m, "alloc_policy=");
···
 	return 0;
 }
 
-static int hctx_flags_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_flags_show, inode->i_private);
-}
-
-static const struct file_operations hctx_flags_fops = {
-	.open		= hctx_flags_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
+#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
 static const char *const op_name[] = {
-	[REQ_OP_READ]		= "READ",
-	[REQ_OP_WRITE]		= "WRITE",
-	[REQ_OP_FLUSH]		= "FLUSH",
-	[REQ_OP_DISCARD]	= "DISCARD",
-	[REQ_OP_ZONE_REPORT]	= "ZONE_REPORT",
-	[REQ_OP_SECURE_ERASE]	= "SECURE_ERASE",
-	[REQ_OP_ZONE_RESET]	= "ZONE_RESET",
-	[REQ_OP_WRITE_SAME]	= "WRITE_SAME",
-	[REQ_OP_WRITE_ZEROES]	= "WRITE_ZEROES",
-	[REQ_OP_SCSI_IN]	= "SCSI_IN",
-	[REQ_OP_SCSI_OUT]	= "SCSI_OUT",
-	[REQ_OP_DRV_IN]		= "DRV_IN",
-	[REQ_OP_DRV_OUT]	= "DRV_OUT",
+	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[] = {
-	[__REQ_FAILFAST_DEV]		= "FAILFAST_DEV",
-	[__REQ_FAILFAST_TRANSPORT]	= "FAILFAST_TRANSPORT",
-	[__REQ_FAILFAST_DRIVER]		= "FAILFAST_DRIVER",
-	[__REQ_SYNC]			= "SYNC",
-	[__REQ_META]			= "META",
-	[__REQ_PRIO]			= "PRIO",
-	[__REQ_NOMERGE]			= "NOMERGE",
-	[__REQ_IDLE]			= "IDLE",
-	[__REQ_INTEGRITY]		= "INTEGRITY",
-	[__REQ_FUA]			= "FUA",
-	[__REQ_PREFLUSH]		= "PREFLUSH",
-	[__REQ_RAHEAD]			= "RAHEAD",
-	[__REQ_BACKGROUND]		= "BACKGROUND",
-	[__REQ_NR_BITS]			= "NR_BITS",
+	CMD_FLAG_NAME(FAILFAST_DEV),
+	CMD_FLAG_NAME(FAILFAST_TRANSPORT),
+	CMD_FLAG_NAME(FAILFAST_DRIVER),
+	CMD_FLAG_NAME(SYNC),
+	CMD_FLAG_NAME(META),
+	CMD_FLAG_NAME(PRIO),
+	CMD_FLAG_NAME(NOMERGE),
+	CMD_FLAG_NAME(IDLE),
+	CMD_FLAG_NAME(INTEGRITY),
+	CMD_FLAG_NAME(FUA),
+	CMD_FLAG_NAME(PREFLUSH),
+	CMD_FLAG_NAME(RAHEAD),
+	CMD_FLAG_NAME(BACKGROUND),
+	CMD_FLAG_NAME(NOUNMAP),
 };
+#undef CMD_FLAG_NAME
 
+#define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name
 static const char *const rqf_name[] = {
-	[ilog2((__force u32)RQF_SORTED)]		= "SORTED",
-	[ilog2((__force u32)RQF_STARTED)]		= "STARTED",
-	[ilog2((__force u32)RQF_QUEUED)]		= "QUEUED",
-	[ilog2((__force u32)RQF_SOFTBARRIER)]		= "SOFTBARRIER",
-	[ilog2((__force u32)RQF_FLUSH_SEQ)]		= "FLUSH_SEQ",
-	[ilog2((__force u32)RQF_MIXED_MERGE)]		= "MIXED_MERGE",
-	[ilog2((__force u32)RQF_MQ_INFLIGHT)]		= "MQ_INFLIGHT",
-	[ilog2((__force u32)RQF_DONTPREP)]		= "DONTPREP",
-	[ilog2((__force u32)RQF_PREEMPT)]		= "PREEMPT",
-	[ilog2((__force u32)RQF_COPY_USER)]		= "COPY_USER",
-	[ilog2((__force u32)RQF_FAILED)]		= "FAILED",
-	[ilog2((__force u32)RQF_QUIET)]			= "QUIET",
-	[ilog2((__force u32)RQF_ELVPRIV)]		= "ELVPRIV",
-	[ilog2((__force u32)RQF_IO_STAT)]		= "IO_STAT",
-	[ilog2((__force u32)RQF_ALLOCED)]		= "ALLOCED",
-	[ilog2((__force u32)RQF_PM)]			= "PM",
-	[ilog2((__force u32)RQF_HASHED)]		= "HASHED",
-	[ilog2((__force u32)RQF_STATS)]			= "STATS",
-	[ilog2((__force u32)RQF_SPECIAL_PAYLOAD)]	= "SPECIAL_PAYLOAD",
+	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(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),
 };
+#undef RQF_NAME
 
-static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
+int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
-	struct request *rq = list_entry_rq(v);
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
 	const unsigned int op = rq->cmd_flags & REQ_OP_MASK;
 
···
 	seq_puts(m, "}\n");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__blk_mq_debugfs_rq_show);
+
+int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
+{
+	return __blk_mq_debugfs_rq_show(m, list_entry_rq(v));
+}
+EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
 
 static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
 	__acquires(&hctx->lock)
···
 	.show	= blk_mq_debugfs_rq_show,
 };
 
-static int hctx_dispatch_open(struct inode *inode, struct file *file)
+static int hctx_ctx_map_show(void *data, struct seq_file *m)
 {
-	return blk_mq_debugfs_seq_open(inode, file, &hctx_dispatch_seq_ops);
-}
-
-static const struct file_operations hctx_dispatch_fops = {
-	.open		= hctx_dispatch_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int hctx_ctx_map_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	sbitmap_bitmap_show(&hctx->ctx_map, m);
 	return 0;
 }
-
-static int hctx_ctx_map_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_ctx_map_show, inode->i_private);
-}
-
-static const struct file_operations hctx_ctx_map_fops = {
-	.open		= hctx_ctx_map_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 
 static void blk_mq_debugfs_tags_show(struct seq_file *m,
 				     struct blk_mq_tags *tags)
···
 	}
 }
 
-static int hctx_tags_show(struct seq_file *m, void *v)
+static int hctx_tags_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	struct request_queue *q = hctx->queue;
 	int res;
 
···
 	return res;
 }
 
-static int hctx_tags_open(struct inode *inode, struct file *file)
+static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
 {
-	return single_open(file, hctx_tags_show, inode->i_private);
-}
-
-static const struct file_operations hctx_tags_fops = {
-	.open		= hctx_tags_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_tags_bitmap_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	struct request_queue *q = hctx->queue;
 	int res;
 
···
 	return res;
 }
 
-static int hctx_tags_bitmap_open(struct inode *inode, struct file *file)
+static int hctx_sched_tags_show(void *data, struct seq_file *m)
 {
-	return single_open(file, hctx_tags_bitmap_show, inode->i_private);
-}
-
-static const struct file_operations hctx_tags_bitmap_fops = {
-	.open		= hctx_tags_bitmap_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_sched_tags_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	struct request_queue *q = hctx->queue;
 	int res;
 
···
 	return res;
 }
 
-static int hctx_sched_tags_open(struct inode *inode, struct file *file)
+static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
 {
-	return single_open(file, hctx_sched_tags_show, inode->i_private);
-}
-
-static const struct file_operations hctx_sched_tags_fops = {
-	.open		= hctx_sched_tags_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_sched_tags_bitmap_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	struct request_queue *q = hctx->queue;
 	int res;
 
···
 	return res;
 }
 
-static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file)
+static int hctx_io_poll_show(void *data, struct seq_file *m)
 {
-	return single_open(file, hctx_sched_tags_bitmap_show, inode->i_private);
-}
-
-static const struct file_operations hctx_sched_tags_bitmap_fops = {
-	.open		= hctx_sched_tags_bitmap_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_io_poll_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
+	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);
···
 	return 0;
 }
 
-static int hctx_io_poll_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_io_poll_show, inode->i_private);
-}
-
-static ssize_t hctx_io_poll_write(struct file *file, const char __user *buf,
+static ssize_t hctx_io_poll_write(void *data, const char __user *buf,
 				  size_t count, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
 	return count;
 }
 
-static const struct file_operations hctx_io_poll_fops = {
-	.open		= hctx_io_poll_open,
-	.read		= seq_read,
-	.write		= hctx_io_poll_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_dispatched_show(struct seq_file *m, void *v)
+static int hctx_dispatched_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	int i;
 
 	seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
···
 	return 0;
 }
 
-static int hctx_dispatched_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_dispatched_show, inode->i_private);
-}
-
-static ssize_t hctx_dispatched_write(struct file *file, const char __user *buf,
+static ssize_t hctx_dispatched_write(void *data, const char __user *buf,
 				     size_t count, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 	int i;
 
 	for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
···
 	return count;
 }
 
-static const struct file_operations hctx_dispatched_fops = {
-	.open		= hctx_dispatched_open,
-	.read		= seq_read,
-	.write		= hctx_dispatched_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_queued_show(struct seq_file *m, void *v)
+static int hctx_queued_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	seq_printf(m, "%lu\n", hctx->queued);
 	return 0;
 }
 
-static int hctx_queued_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_queued_show, inode->i_private);
-}
-
-static ssize_t hctx_queued_write(struct file *file, const char __user *buf,
+static ssize_t hctx_queued_write(void *data, const char __user *buf,
 				 size_t count, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	hctx->queued = 0;
 	return count;
 }
 
-static const struct file_operations hctx_queued_fops = {
-	.open		= hctx_queued_open,
-	.read		= seq_read,
-	.write		= hctx_queued_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_run_show(struct seq_file *m, void *v)
+static int hctx_run_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	seq_printf(m, "%lu\n", hctx->run);
 	return 0;
 }
 
-static int hctx_run_open(struct inode *inode, struct file *file)
+static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
+			      loff_t *ppos)
 {
-	return single_open(file, hctx_run_show, inode->i_private);
-}
-
-static ssize_t hctx_run_write(struct file *file, const char __user *buf,
-				 size_t count, loff_t *ppos)
-{
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	hctx->run = 0;
 	return count;
 }
 
-static const struct file_operations hctx_run_fops = {
-	.open		= hctx_run_open,
-	.read		= seq_read,
-	.write		= hctx_run_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int hctx_active_show(struct seq_file *m, void *v)
+static int hctx_active_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_hw_ctx *hctx = data;
 
 	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
 	return 0;
 }
-
-static int hctx_active_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_active_show, inode->i_private);
-}
-
-static const struct file_operations hctx_active_fops = {
-	.open		= hctx_active_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
 	__acquires(&ctx->lock)
···
 	.stop	= ctx_rq_list_stop,
 	.show	= blk_mq_debugfs_rq_show,
 };
-
-static int ctx_rq_list_open(struct inode *inode, struct file *file)
+static int ctx_dispatched_show(void *data, struct seq_file *m)
 {
-	return blk_mq_debugfs_seq_open(inode, file, &ctx_rq_list_seq_ops);
-}
-
-static const struct file_operations ctx_rq_list_fops = {
-	.open		= ctx_rq_list_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int ctx_dispatched_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
 	return 0;
 }
 
-static int ctx_dispatched_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ctx_dispatched_show, inode->i_private);
-}
-
-static ssize_t ctx_dispatched_write(struct file *file, const char __user *buf,
+static ssize_t ctx_dispatched_write(void *data, const char __user *buf,
 				    size_t count, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
 	return count;
 }
 
-static const struct file_operations ctx_dispatched_fops = {
-	.open		= ctx_dispatched_open,
-	.read		= seq_read,
-	.write		= ctx_dispatched_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int ctx_merged_show(struct seq_file *m, void *v)
+static int ctx_merged_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	seq_printf(m, "%lu\n", ctx->rq_merged);
 	return 0;
 }
 
-static int ctx_merged_open(struct inode *inode, struct file *file)
+static ssize_t ctx_merged_write(void *data, const char __user *buf,
+				size_t count, loff_t *ppos)
 {
-	return single_open(file, ctx_merged_show, inode->i_private);
-}
-
-static ssize_t ctx_merged_write(struct file *file, const char __user *buf,
-				    size_t count, loff_t *ppos)
-{
-	struct seq_file *m = file->private_data;
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	ctx->rq_merged = 0;
 	return count;
 }
 
-static const struct file_operations ctx_merged_fops = {
-	.open		= ctx_merged_open,
-	.read		= seq_read,
-	.write		= ctx_merged_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int ctx_completed_show(struct seq_file *m, void *v)
+static int ctx_completed_show(void *data, struct seq_file *m)
 {
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
 	return 0;
 }
 
-static int ctx_completed_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ctx_completed_show, inode->i_private);
-}
-
-static ssize_t ctx_completed_write(struct file *file, const char __user *buf,
+static ssize_t ctx_completed_write(void *data, const char __user *buf,
 				   size_t count, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
-	struct blk_mq_ctx *ctx = m->private;
+	struct blk_mq_ctx *ctx = data;
 
 	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
 	return count;
 }
 
-static const struct file_operations ctx_completed_fops = {
-	.open		= ctx_completed_open,
+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;
+
+	return attr->show(data, m);
+}
+
+static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	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;
+
+	if (!attr->write)
+		return -EPERM;
+
+	return attr->write(data, buf, count, ppos);
+}
+
+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;
+	struct seq_file *m;
+	int ret;
+
+	if (attr->seq_ops) {
+		ret = seq_open(file, attr->seq_ops);
+		if (!ret) {
+			m = file->private_data;
+			m->private = data;
+		}
+		return ret;
+	}
+
+	if (WARN_ON_ONCE(!attr->show))
+		return -EPERM;
+
+	return single_open(file, blk_mq_debugfs_show, inode->i_private);
+}
+
+static int blk_mq_debugfs_release(struct inode *inode, struct file *file)
+{
+	const struct blk_mq_debugfs_attr *attr = inode->i_private;
+
+	if (attr->show)
+		return single_release(inode, file);
+	else
+		return seq_release(inode, file);
+}
+
+const struct file_operations blk_mq_debugfs_fops = {
+	.open		= blk_mq_debugfs_open,
 	.read		= seq_read,
-	.write		= ctx_completed_write,
+	.write		= blk_mq_debugfs_write,
 	.llseek		= seq_lseek,
-	.release	= single_release,
+	.release	= blk_mq_debugfs_release,
 };
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
-	{"poll_stat", 0400, &queue_poll_stat_fops},
-	{"state", 0600, &blk_queue_flags_fops},
+	{"poll_stat", 0400, queue_poll_stat_show},
+	{"state", 0600, queue_state_show, queue_state_write},
 	{},
 };
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
-	{"state", 0400, &hctx_state_fops},
-	{"flags", 0400, &hctx_flags_fops},
-	{"dispatch", 0400, &hctx_dispatch_fops},
-	{"ctx_map", 0400, &hctx_ctx_map_fops},
-	{"tags", 0400, &hctx_tags_fops},
-	{"tags_bitmap", 0400, &hctx_tags_bitmap_fops},
-	{"sched_tags", 0400, &hctx_sched_tags_fops},
-	{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
-	{"io_poll", 0600, &hctx_io_poll_fops},
-	{"dispatched", 0600, &hctx_dispatched_fops},
-	{"queued", 0600, &hctx_queued_fops},
-	{"run", 0600, &hctx_run_fops},
-	{"active", 0400, &hctx_active_fops},
+	{"state", 0400, hctx_state_show},
+	{"flags", 0400, hctx_flags_show},
+	{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+	{"ctx_map", 0400, hctx_ctx_map_show},
+	{"tags", 0400, hctx_tags_show},
+	{"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},
 	{},
 };
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
-	{"rq_list", 0400, &ctx_rq_list_fops},
-	{"dispatched", 0600, &ctx_dispatched_fops},
-	{"merged", 0600, &ctx_merged_fops},
-	{"completed", 0600, &ctx_completed_fops},
+	{"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},
 	{},
 };
 
+static bool debugfs_create_files(struct dentry *parent, void *data,
+				 const struct blk_mq_debugfs_attr *attr)
+{
+	d_inode(parent)->i_private = data;
+
+	for (; attr->name; attr++) {
+		if (!debugfs_create_file(attr->name, attr->mode, parent,
+					 (void *)attr, &blk_mq_debugfs_fops))
+			return false;
+	}
+	return true;
+}
+
 int blk_mq_debugfs_register(struct request_queue *q)
 {
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
 	if (!blk_debugfs_root)
 		return -ENOENT;
 
 	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;
 
-	if (blk_mq_debugfs_register_mq(q))
-		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;
+	}
 
 	return 0;
 
···
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
 	debugfs_remove_recursive(q->debugfs_dir);
-	q->mq_debugfs_dir = NULL;
+	q->sched_debugfs_dir = NULL;
 	q->debugfs_dir = NULL;
 }
 
-static bool debugfs_create_files(struct dentry *parent, void *data,
-				const struct blk_mq_debugfs_attr *attr)
-{
-	for (; attr->name; attr++) {
-		if (!debugfs_create_file(attr->name, attr->mode, parent,
-					 data, attr->fops))
-			return false;
-	}
-	return true;
-}
-
-static int blk_mq_debugfs_register_ctx(struct request_queue *q,
-				       struct blk_mq_ctx *ctx,
-				       struct dentry *hctx_dir)
+static int 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_dir);
+	ctx_dir = debugfs_create_dir(name, hctx->debugfs_dir);
 	if (!ctx_dir)
 		return -ENOMEM;
 
···
 	return 0;
 }
 
-static int blk_mq_debugfs_register_hctx(struct request_queue *q,
-					struct blk_mq_hw_ctx *hctx)
+int blk_mq_debugfs_register_hctx(struct request_queue *q,
+				 struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_ctx *ctx;
-	struct dentry *hctx_dir;
 	char name[20];
-	int i;
-
-	snprintf(name, sizeof(name), "%u", hctx->queue_num);
-	hctx_dir = debugfs_create_dir(name, q->mq_debugfs_dir);
-	if (!hctx_dir)
-		return -ENOMEM;
-
-	if (!debugfs_create_files(hctx_dir, hctx, blk_mq_debugfs_hctx_attrs))
-		return -ENOMEM;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		if (blk_mq_debugfs_register_ctx(q, ctx, hctx_dir))
-			return -ENOMEM;
-	}
-
-	return 0;
-}
-
-int blk_mq_debugfs_register_mq(struct request_queue *q)
-{
-	struct blk_mq_hw_ctx *hctx;
 	int i;
 
 	if (!q->debugfs_dir)
 		return -ENOENT;
 
-	q->mq_debugfs_dir = debugfs_create_dir("mq", q->debugfs_dir);
-	if (!q->mq_debugfs_dir)
+	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;
 
-	if (!debugfs_create_files(q->mq_debugfs_dir, q, blk_mq_debugfs_queue_attrs))
-		goto err;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (blk_mq_debugfs_register_hctx(q, hctx))
+	hctx_for_each_ctx(hctx, ctx, i) {
+		if (blk_mq_debugfs_register_ctx(hctx, ctx))
 			goto err;
 	}
 
 	return 0;
 
 err:
-	blk_mq_debugfs_unregister_mq(q);
+	blk_mq_debugfs_unregister_hctx(hctx);
 	return -ENOMEM;
 }
 
-void blk_mq_debugfs_unregister_mq(struct request_queue *q)
+void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
 {
-	debugfs_remove_recursive(q->mq_debugfs_dir);
-	q->mq_debugfs_dir = NULL;
+	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)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_debugfs_register_hctx(q, hctx))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int 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)
+{
+	struct elevator_type *e = q->elevator->type;
+
+	if (!q->debugfs_dir)
+		return -ENOENT;
+
+	if (!e->queue_debugfs_attrs)
+		return 0;
+
+	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;
+}
+
+void blk_mq_debugfs_unregister_sched(struct request_queue *q)
+{
+	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)
+{
+	struct elevator_type *e = q->elevator->type;
+
+	if (!hctx->debugfs_dir)
+		return -ENOENT;
+
+	if (!e->hctx_debugfs_attrs)
+		return 0;
+
+	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;
+}
+
+void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
+{
+	debugfs_remove_recursive(hctx->sched_debugfs_dir);
+	hctx->sched_debugfs_dir = NULL;
 }

block/blk-mq-debugfs.h

···
+#ifndef INT_BLK_MQ_DEBUGFS_H
+#define INT_BLK_MQ_DEBUGFS_H
+
+#ifdef CONFIG_BLK_DEBUG_FS
+
+#include <linux/seq_file.h>
+
+struct blk_mq_debugfs_attr {
+	const char *name;
+	umode_t mode;
+	int (*show)(void *, struct seq_file *);
+	ssize_t (*write)(void *, const char __user *, size_t, loff_t *);
+	/* Set either .show or .seq_ops. */
+	const struct seq_operations *seq_ops;
+};
+
+int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq);
+int blk_mq_debugfs_rq_show(struct seq_file *m, void *v);
+
+int blk_mq_debugfs_register(struct request_queue *q);
+void blk_mq_debugfs_unregister(struct request_queue *q);
+int blk_mq_debugfs_register_hctx(struct request_queue *q,
+				 struct blk_mq_hw_ctx *hctx);
+void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx);
+int blk_mq_debugfs_register_hctxs(struct request_queue *q);
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+
+int blk_mq_debugfs_register_sched(struct request_queue *q);
+void blk_mq_debugfs_unregister_sched(struct request_queue *q);
+int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
+				       struct blk_mq_hw_ctx *hctx);
+void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx);
+#else
+static inline int blk_mq_debugfs_register(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister(struct request_queue *q)
+{
+}
+
+static inline int blk_mq_debugfs_register_hctx(struct request_queue *q,
+					       struct blk_mq_hw_ctx *hctx)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
+{
+}
+
+static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+}
+
+static inline int blk_mq_debugfs_register_sched(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_sched(struct request_queue *q)
+{
+}
+
+static inline int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
+						     struct blk_mq_hw_ctx *hctx)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
+{
+}
+#endif
+
+#endif

block/blk-mq-sched.c

···
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
 #include "blk-mq-tag.h"
 #include "blk-wbt.h"
···
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
-	/*
-	 * For a reserved tag, allocate a normal request since we might
-	 * have driver dependencies on the value of the internal tag.
-	 */
-	if (e && !(data->flags & BLK_MQ_REQ_RESERVED)) {
+	if (e) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
 
 		/*
···
 		}
 	}
 
+	blk_mq_debugfs_register_sched_hctx(q, hctx);
+
 	return 0;
 }
 
···
 
 	if (!e)
 		return;
+
+	blk_mq_debugfs_unregister_sched_hctx(hctx);
 
 	if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
 		e->type->ops.mq.exit_hctx(hctx, hctx_idx);
···
 	if (ret)
 		goto err;
 
-	if (e->ops.mq.init_hctx) {
-		queue_for_each_hw_ctx(q, hctx, i) {
+	blk_mq_debugfs_register_sched(q);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (e->ops.mq.init_hctx) {
 			ret = e->ops.mq.init_hctx(hctx, i);
 			if (ret) {
 				eq = q->elevator;
···
 				return ret;
 			}
 		}
+		blk_mq_debugfs_register_sched_hctx(q, hctx);
 	}
 
 	return 0;
···
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 
-	if (e->type->ops.mq.exit_hctx) {
-		queue_for_each_hw_ctx(q, hctx, i) {
-			if (hctx->sched_data) {
-				e->type->ops.mq.exit_hctx(hctx, i);
-				hctx->sched_data = NULL;
-			}
+	queue_for_each_hw_ctx(q, hctx, i) {
+		blk_mq_debugfs_unregister_sched_hctx(hctx);
+		if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
+			e->type->ops.mq.exit_hctx(hctx, i);
+			hctx->sched_data = NULL;
 		}
 	}
+	blk_mq_debugfs_unregister_sched(q);
 	if (e->type->ops.mq.exit_sched)
 		e->type->ops.mq.exit_sched(e);
 	blk_mq_sched_tags_teardown(q);

block/blk-mq-sysfs.c

···
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 
-	blk_mq_debugfs_unregister_mq(q);
-
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
 	kobject_put(&dev->kobj);
···
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
-	blk_mq_debugfs_register(q);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
···
 unreg:
 	while (--i >= 0)
 		blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
-
-	blk_mq_debugfs_unregister_mq(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
···
 	if (!q->mq_sysfs_init_done)
 		goto unlock;
 
-	blk_mq_debugfs_unregister_mq(q);
-
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 
···
 	mutex_lock(&q->sysfs_lock);
 	if (!q->mq_sysfs_init_done)
 		goto unlock;
-
-	blk_mq_debugfs_register_mq(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);

block/blk-mq.c

···
 #include <linux/blk-mq.h>
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
 #include "blk-wbt.h"
···
 
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
+static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
 
 static int blk_mq_poll_stats_bkt(const struct request *rq)
 {
···
 	unsigned int i;
 	bool rcu = false;
 
-	blk_mq_stop_hw_queues(q);
+	__blk_mq_stop_hw_queues(q, true);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->flags & BLK_MQ_F_BLOCKING)
···
 }
 EXPORT_SYMBOL(blk_mq_queue_stopped);
 
+static void __blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx, bool sync)
+{
+	if (sync)
+		cancel_delayed_work_sync(&hctx->run_work);
+	else
+		cancel_delayed_work(&hctx->run_work);
+
+	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
+}
+
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
-	cancel_delayed_work_sync(&hctx->run_work);
-	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	__blk_mq_stop_hw_queue(hctx, false);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
 
-void blk_mq_stop_hw_queues(struct request_queue *q)
+void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_stop_hw_queue(hctx);
+		__blk_mq_stop_hw_queue(hctx, sync);
+}
+
+void blk_mq_stop_hw_queues(struct request_queue *q)
+{
+	__blk_mq_stop_hw_queues(q, false);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queues);
 
···
 
 			if (!rq)
 				continue;
-			set->ops->exit_request(set->driver_data, rq,
-						hctx_idx, i);
+			set->ops->exit_request(set, rq, hctx_idx);
 			tags->static_rqs[i] = NULL;
 		}
 	}
···
 
 			tags->static_rqs[i] = rq;
 			if (set->ops->init_request) {
-				if (set->ops->init_request(set->driver_data,
-						rq, hctx_idx, i,
+				if (set->ops->init_request(set, rq, hctx_idx,
 						node)) {
 					tags->static_rqs[i] = NULL;
 					goto fail;
···
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
-	unsigned flush_start_tag = set->queue_depth;
+	blk_mq_debugfs_unregister_hctx(hctx);
 
 	blk_mq_tag_idle(hctx);
 
 	if (set->ops->exit_request)
-		set->ops->exit_request(set->driver_data,
-				       hctx->fq->flush_rq, hctx_idx,
-				       flush_start_tag + hctx_idx);
+		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
 
 	blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
 
···
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
 	int node;
-	unsigned flush_start_tag = set->queue_depth;
 
 	node = hctx->numa_node;
 	if (node == NUMA_NO_NODE)
···
 		goto sched_exit_hctx;
 
 	if (set->ops->init_request &&
-	    set->ops->init_request(set->driver_data,
-				   hctx->fq->flush_rq, hctx_idx,
-				   flush_start_tag + hctx_idx, node))
+	    set->ops->init_request(set, hctx->fq->flush_rq, hctx_idx,
+				   node))
 		goto free_fq;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
 		init_srcu_struct(&hctx->queue_rq_srcu);
+
+	blk_mq_debugfs_register_hctx(q, hctx);
 
 	return 0;
 
···
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
-	get_online_cpus();
 	mutex_lock(&all_q_mutex);
+	get_online_cpus();
 
 	list_add_tail(&q->all_q_node, &all_q_list);
 	blk_mq_add_queue_tag_set(set, q);
 	blk_mq_map_swqueue(q, cpu_online_mask);
 
-	mutex_unlock(&all_q_mutex);
 	put_online_cpus();
+	mutex_unlock(&all_q_mutex);
 
 	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
 		int ret;
···
 {
 	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
+	blk_mq_debugfs_unregister_hctxs(q);
 	blk_mq_sysfs_unregister(q);
 
 	/*
···
 	blk_mq_map_swqueue(q, online_mask);
 
 	blk_mq_sysfs_register(q);
+	blk_mq_debugfs_register_hctxs(q);
 }
 
 /*
···
 		return -EINVAL;
 
 	blk_mq_freeze_queue(q);
-	blk_mq_quiesce_queue(q);
 
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
···
 		q->nr_requests = nr;
 
 	blk_mq_unfreeze_queue(q);
-	blk_mq_start_stopped_hw_queues(q, true);
 
 	return ret;
 }

block/blk-mq.h

···
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
-/*
- * debugfs helpers
- */
-#ifdef CONFIG_BLK_DEBUG_FS
-int blk_mq_debugfs_register(struct request_queue *q);
-void blk_mq_debugfs_unregister(struct request_queue *q);
-int blk_mq_debugfs_register_mq(struct request_queue *q);
-void blk_mq_debugfs_unregister_mq(struct request_queue *q);
-#else
-static inline int blk_mq_debugfs_register(struct request_queue *q)
-{
-	return 0;
-}
-
-static inline void blk_mq_debugfs_unregister(struct request_queue *q)
-{
-}
-
-static inline int blk_mq_debugfs_register_mq(struct request_queue *q)
-{
-	return 0;
-}
-
-static inline void blk_mq_debugfs_unregister_mq(struct request_queue *q)
-{
-}
-#endif
-
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
 void blk_mq_release(struct request_queue *q);

block/blk-sysfs.c

···
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-wbt.h"
 
 struct queue_sysfs_entry {
···
 
 	if (q->mq_ops)
 		__blk_mq_register_dev(dev, q);
+
+	blk_mq_debugfs_register(q);
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 

block/elevator.c

···
 	int ret;
 
 	blk_mq_freeze_queue(q);
-	blk_mq_quiesce_queue(q);
 
 	if (q->elevator) {
 		if (q->elevator->registered)
···
 
 out:
 	blk_mq_unfreeze_queue(q);
-	blk_mq_start_stopped_hw_queues(q, true);
 	return ret;
-
 }
 
 /*
···
 
 	return elevator_switch(q, e);
 }
-
-int elevator_change(struct request_queue *q, const char *name)
-{
-	int ret;
-
-	/* Protect q->elevator from elevator_init() */
-	mutex_lock(&q->sysfs_lock);
-	ret = __elevator_change(q, name);
-	mutex_unlock(&q->sysfs_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL(elevator_change);
 
 static inline bool elv_support_iosched(struct request_queue *q)
 {

block/kyber-iosched.c

···
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-mq-sched.h"
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
···
 };
 #undef KYBER_LAT_ATTR
 
+#ifdef CONFIG_BLK_DEBUG_FS
+#define KYBER_DEBUGFS_DOMAIN_ATTRS(domain, name)			\
+static int kyber_##name##_tokens_show(void *data, struct seq_file *m)	\
+{									\
+	struct request_queue *q = data;					\
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;	\
+									\
+	sbitmap_queue_show(&kqd->domain_tokens[domain], m);		\
+	return 0;							\
+}									\
+									\
+static void *kyber_##name##_rqs_start(struct seq_file *m, loff_t *pos)	\
+	__acquires(&khd->lock)						\
+{									\
+	struct blk_mq_hw_ctx *hctx = m->private;			\
+	struct kyber_hctx_data *khd = hctx->sched_data;			\
+									\
+	spin_lock(&khd->lock);						\
+	return seq_list_start(&khd->rqs[domain], *pos);			\
+}									\
+									\
+static void *kyber_##name##_rqs_next(struct seq_file *m, void *v,	\
+				     loff_t *pos)			\
+{									\
+	struct blk_mq_hw_ctx *hctx = m->private;			\
+	struct kyber_hctx_data *khd = hctx->sched_data;			\
+									\
+	return seq_list_next(v, &khd->rqs[domain], pos);		\
+}									\
+									\
+static void kyber_##name##_rqs_stop(struct seq_file *m, void *v)	\
+	__releases(&khd->lock)						\
+{									\
+	struct blk_mq_hw_ctx *hctx = m->private;			\
+	struct kyber_hctx_data *khd = hctx->sched_data;			\
+									\
+	spin_unlock(&khd->lock);					\
+}									\
+									\
+static const struct seq_operations kyber_##name##_rqs_seq_ops = {	\
+	.start	= kyber_##name##_rqs_start,				\
+	.next	= kyber_##name##_rqs_next,				\
+	.stop	= kyber_##name##_rqs_stop,				\
+	.show	= blk_mq_debugfs_rq_show,				\
+};									\
+									\
+static int kyber_##name##_waiting_show(void *data, struct seq_file *m)	\
+{									\
+	struct blk_mq_hw_ctx *hctx = data;				\
+	struct kyber_hctx_data *khd = hctx->sched_data;			\
+	wait_queue_t *wait = &khd->domain_wait[domain];			\
+									\
+	seq_printf(m, "%d\n", !list_empty_careful(&wait->task_list));	\
+	return 0;							\
+}
+KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_READ, read)
+KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_SYNC_WRITE, sync_write)
+KYBER_DEBUGFS_DOMAIN_ATTRS(KYBER_OTHER, other)
+#undef KYBER_DEBUGFS_DOMAIN_ATTRS
+
+static int kyber_async_depth_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+
+	seq_printf(m, "%u\n", kqd->async_depth);
+	return 0;
+}
+
+static int kyber_cur_domain_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+	struct kyber_hctx_data *khd = hctx->sched_data;
+
+	switch (khd->cur_domain) {
+	case KYBER_READ:
+		seq_puts(m, "READ\n");
+		break;
+	case KYBER_SYNC_WRITE:
+		seq_puts(m, "SYNC_WRITE\n");
+		break;
+	case KYBER_OTHER:
+		seq_puts(m, "OTHER\n");
+		break;
+	default:
+		seq_printf(m, "%u\n", khd->cur_domain);
+		break;
+	}
+	return 0;
+}
+
+static int kyber_batching_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+	struct kyber_hctx_data *khd = hctx->sched_data;
+
+	seq_printf(m, "%u\n", khd->batching);
+	return 0;
+}
+
+#define KYBER_QUEUE_DOMAIN_ATTRS(name)	\
+	{#name "_tokens", 0400, kyber_##name##_tokens_show}
+static const struct blk_mq_debugfs_attr kyber_queue_debugfs_attrs[] = {
+	KYBER_QUEUE_DOMAIN_ATTRS(read),
+	KYBER_QUEUE_DOMAIN_ATTRS(sync_write),
+	KYBER_QUEUE_DOMAIN_ATTRS(other),
+	{"async_depth", 0400, kyber_async_depth_show},
+	{},
+};
+#undef KYBER_QUEUE_DOMAIN_ATTRS
+
+#define KYBER_HCTX_DOMAIN_ATTRS(name)					\
+	{#name "_rqs", 0400, .seq_ops = &kyber_##name##_rqs_seq_ops},	\
+	{#name "_waiting", 0400, kyber_##name##_waiting_show}
+static const struct blk_mq_debugfs_attr kyber_hctx_debugfs_attrs[] = {
+	KYBER_HCTX_DOMAIN_ATTRS(read),
+	KYBER_HCTX_DOMAIN_ATTRS(sync_write),
+	KYBER_HCTX_DOMAIN_ATTRS(other),
+	{"cur_domain", 0400, kyber_cur_domain_show},
+	{"batching", 0400, kyber_batching_show},
+	{},
+};
+#undef KYBER_HCTX_DOMAIN_ATTRS
+#endif
+
 static struct elevator_type kyber_sched = {
 	.ops.mq = {
 		.init_sched = kyber_init_sched,
···
 		.has_work = kyber_has_work,
 	},
 	.uses_mq = true,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.queue_debugfs_attrs = kyber_queue_debugfs_attrs,
+	.hctx_debugfs_attrs = kyber_hctx_debugfs_attrs,
+#endif
 	.elevator_attrs = kyber_sched_attrs,
 	.elevator_name = "kyber",
 	.elevator_owner = THIS_MODULE,

block/mq-deadline.c

···
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
 #include "blk-mq-sched.h"
 
···
 	__ATTR_NULL
 };
 
+#ifdef CONFIG_BLK_DEBUG_FS
+#define DEADLINE_DEBUGFS_DDIR_ATTRS(ddir, name)				\
+static void *deadline_##name##_fifo_start(struct seq_file *m,		\
+					  loff_t *pos)			\
+	__acquires(&dd->lock)						\
+{									\
+	struct request_queue *q = m->private;				\
+	struct deadline_data *dd = q->elevator->elevator_data;		\
+									\
+	spin_lock(&dd->lock);						\
+	return seq_list_start(&dd->fifo_list[ddir], *pos);		\
+}									\
+									\
+static void *deadline_##name##_fifo_next(struct seq_file *m, void *v,	\
+					 loff_t *pos)			\
+{									\
+	struct request_queue *q = m->private;				\
+	struct deadline_data *dd = q->elevator->elevator_data;		\
+									\
+	return seq_list_next(v, &dd->fifo_list[ddir], pos);		\
+}									\
+									\
+static void deadline_##name##_fifo_stop(struct seq_file *m, void *v)	\
+	__releases(&dd->lock)						\
+{									\
+	struct request_queue *q = m->private;				\
+	struct deadline_data *dd = q->elevator->elevator_data;		\
+									\
+	spin_unlock(&dd->lock);						\
+}									\
+									\
+static const struct seq_operations deadline_##name##_fifo_seq_ops = {	\
+	.start	= deadline_##name##_fifo_start,				\
+	.next	= deadline_##name##_fifo_next,				\
+	.stop	= deadline_##name##_fifo_stop,				\
+	.show	= blk_mq_debugfs_rq_show,				\
+};									\
+									\
+static int deadline_##name##_next_rq_show(void *data,			\
+					  struct seq_file *m)		\
+{									\
+	struct request_queue *q = data;					\
+	struct deadline_data *dd = q->elevator->elevator_data;		\
+	struct request *rq = dd->next_rq[ddir];				\
+									\
+	if (rq)								\
+		__blk_mq_debugfs_rq_show(m, rq);			\
+	return 0;							\
+}
+DEADLINE_DEBUGFS_DDIR_ATTRS(READ, read)
+DEADLINE_DEBUGFS_DDIR_ATTRS(WRITE, write)
+#undef DEADLINE_DEBUGFS_DDIR_ATTRS
+
+static int deadline_batching_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	seq_printf(m, "%u\n", dd->batching);
+	return 0;
+}
+
+static int deadline_starved_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	seq_printf(m, "%u\n", dd->starved);
+	return 0;
+}
+
+static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos)
+	__acquires(&dd->lock)
+{
+	struct request_queue *q = m->private;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	spin_lock(&dd->lock);
+	return seq_list_start(&dd->dispatch, *pos);
+}
+
+static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct request_queue *q = m->private;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	return seq_list_next(v, &dd->dispatch, pos);
+}
+
+static void deadline_dispatch_stop(struct seq_file *m, void *v)
+	__releases(&dd->lock)
+{
+	struct request_queue *q = m->private;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	spin_unlock(&dd->lock);
+}
+
+static const struct seq_operations deadline_dispatch_seq_ops = {
+	.start	= deadline_dispatch_start,
+	.next	= deadline_dispatch_next,
+	.stop	= deadline_dispatch_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
+#define DEADLINE_QUEUE_DDIR_ATTRS(name)						\
+	{#name "_fifo_list", 0400, .seq_ops = &deadline_##name##_fifo_seq_ops},	\
+	{#name "_next_rq", 0400, deadline_##name##_next_rq_show}
+static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = {
+	DEADLINE_QUEUE_DDIR_ATTRS(read),
+	DEADLINE_QUEUE_DDIR_ATTRS(write),
+	{"batching", 0400, deadline_batching_show},
+	{"starved", 0400, deadline_starved_show},
+	{"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops},
+	{},
+};
+#undef DEADLINE_QUEUE_DDIR_ATTRS
+#endif
+
 static struct elevator_type mq_deadline = {
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
···
 	},
 
 	.uses_mq	= true,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.queue_debugfs_attrs = deadline_queue_debugfs_attrs,
+#endif
 	.elevator_attrs = deadline_attrs,
 	.elevator_name = "mq-deadline",
 	.elevator_owner = THIS_MODULE,

drivers/block/loop.c

···
 	loop_handle_cmd(cmd);
 }
 
-static int loop_init_request(void *data, struct request *rq,
-		unsigned int hctx_idx, unsigned int request_idx,
-		unsigned int numa_node)
+static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 

drivers/block/mtip32xx/mtip32xx.c

···
 	if (mtip_check_surprise_removal(dd->pdev))
 		return NULL;
 
-	rq = blk_mq_alloc_request(dd->queue, 0, BLK_MQ_REQ_RESERVED);
+	rq = blk_mq_alloc_request(dd->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_RESERVED);
 	if (IS_ERR(rq))
 		return NULL;
 
···
 	return blk_mq_rq_to_pdu(rq);
 }
 
-static void mtip_put_int_command(struct driver_data *dd, struct mtip_cmd *cmd)
-{
-	blk_put_request(blk_mq_rq_from_pdu(cmd));
-}
-
-/*
- * Once we add support for one hctx per mtip group, this will change a bit
- */
-static struct request *mtip_rq_from_tag(struct driver_data *dd,
-					unsigned int tag)
-{
-	struct blk_mq_hw_ctx *hctx = dd->queue->queue_hw_ctx[0];
-
-	return blk_mq_tag_to_rq(hctx->tags, tag);
-}
-
 static struct mtip_cmd *mtip_cmd_from_tag(struct driver_data *dd,
 					  unsigned int tag)
 {
-	struct request *rq = mtip_rq_from_tag(dd, tag);
+	struct blk_mq_hw_ctx *hctx = dd->queue->queue_hw_ctx[0];
 
-	return blk_mq_rq_to_pdu(rq);
-}
-
-/*
- * IO completion function.
- *
- * This completion function is called by the driver ISR when a
- * command that was issued by the kernel completes. It first calls the
- * asynchronous completion function which normally calls back into the block
- * layer passing the asynchronous callback data, then unmaps the
- * scatter list associated with the completed command, and finally
- * clears the allocated bit associated with the completed command.
- *
- * @port   Pointer to the port data structure.
- * @tag    Tag of the command.
- * @data   Pointer to driver_data.
- * @status Completion status.
- *
- * return value
- *	None
- */
-static void mtip_async_complete(struct mtip_port *port,
-				int tag, struct mtip_cmd *cmd, int status)
-{
-	struct driver_data *dd = port->dd;
-	struct request *rq;
-
-	if (unlikely(!dd) || unlikely(!port))
-		return;
-
-	if (unlikely(status == PORT_IRQ_TF_ERR)) {
-		dev_warn(&port->dd->pdev->dev,
-			"Command tag %d failed due to TFE\n", tag);
-	}
-
-	rq = mtip_rq_from_tag(dd, tag);
-
-	cmd->status = status;
-	blk_mq_complete_request(rq);
+	return blk_mq_rq_to_pdu(blk_mq_tag_to_rq(hctx->tags, tag));
 }
 
 /*
···
 			"%d command(s) %s: tagmap [%s]", cnt, msg, tagmap);
 }
 
-/*
- * Internal command completion callback function.
- *
- * This function is normally called by the driver ISR when an internal
- * command completed. This function signals the command completion by
- * calling complete().
- *
- * @port   Pointer to the port data structure.
- * @tag    Tag of the command that has completed.
- * @data   Pointer to a completion structure.
- * @status Completion status.
- *
- * return value
- *	None
- */
-static void mtip_completion(struct mtip_port *port,
-			    int tag, struct mtip_cmd *command, int status)
-{
-	struct completion *waiting = command->comp_data;
-	if (unlikely(status == PORT_IRQ_TF_ERR))
-		dev_warn(&port->dd->pdev->dev,
-			"Internal command %d completed with TFE\n", tag);
-
-	command->comp_func = NULL;
-	command->comp_data = NULL;
-	complete(waiting);
-}
-
-static void mtip_null_completion(struct mtip_port *port,
-			    int tag, struct mtip_cmd *command, int status)
-{
-}
-
 static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer,
 				dma_addr_t buffer_dma, unsigned int sectors);
 static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id,
 						struct smart_attr *attrib);
+
+static void mtip_complete_command(struct mtip_cmd *cmd, int status)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+
+	cmd->status = status;
+	blk_mq_complete_request(req);
+}
+
 /*
  * Handle an error.
  *
···
 	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
-
-		if (cmd->comp_data && cmd->comp_func) {
-			cmd->comp_func(port, MTIP_TAG_INTERNAL,
-					cmd, PORT_IRQ_TF_ERR);
-		}
+		mtip_complete_command(cmd, -EIO);
 		return;
 	}
 
···
 				continue;
 
 			cmd = mtip_cmd_from_tag(dd, tag);
-			if (likely(cmd->comp_func)) {
-				set_bit(tag, tagaccum);
-				cmd_cnt++;
-				cmd->comp_func(port, tag, cmd, 0);
-			} else {
-				dev_err(&port->dd->pdev->dev,
-					"Missing completion func for tag %d",
-					tag);
-				if (mtip_check_surprise_removal(dd->pdev)) {
-					/* don't proceed further */
-					return;
-				}
-			}
+			mtip_complete_command(cmd, 0);
+			set_bit(tag, tagaccum);
+			cmd_cnt++;
 		}
 	}
 
···
 					tag,
 					fail_reason != NULL ?
 						fail_reason : "unknown");
-					if (cmd->comp_func) {
-						cmd->comp_func(port, tag,
-							cmd, -ENODATA);
-					}
+					mtip_complete_command(cmd, -ENODATA);
 					continue;
 				}
 			}
···
 			dev_warn(&port->dd->pdev->dev,
 				"retiring tag %d\n", tag);
 
-			if (cmd->comp_func)
-				cmd->comp_func(port, tag, cmd, PORT_IRQ_TF_ERR);
-			else
-				dev_warn(&port->dd->pdev->dev,
-					"Bad completion for tag %d\n",
-					tag);
+			mtip_complete_command(cmd, -EIO);
 		}
 	}
 	print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt);
···
 				continue;
 
 			command = mtip_cmd_from_tag(dd, tag);
-			if (likely(command->comp_func))
-				command->comp_func(port, tag, command, 0);
-			else {
-				dev_dbg(&dd->pdev->dev,
-					"Null completion for tag %d",
-					tag);
-
-				if (mtip_check_surprise_removal(
-					dd->pdev)) {
-					return;
-				}
-			}
+			mtip_complete_command(command, 0);
 		}
 		completed >>= 1;
 	}
···
 	struct mtip_port *port = dd->port;
 	struct mtip_cmd *cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 
-	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags) &&
-	    (cmd != NULL) && !(readl(port->cmd_issue[MTIP_TAG_INTERNAL])
-		& (1 << MTIP_TAG_INTERNAL))) {
-		if (cmd->comp_func) {
-			cmd->comp_func(port, MTIP_TAG_INTERNAL, cmd, 0);
-			return;
-		}
-	}
+	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags) && cmd) {
+		int group = MTIP_TAG_INDEX(MTIP_TAG_INTERNAL);
+		int status = readl(port->cmd_issue[group]);
 
-	return;
+		if (!(status & (1 << MTIP_TAG_BIT(MTIP_TAG_INTERNAL))))
+			mtip_complete_command(cmd, 0);
+	}
 }
 
 /*
···
  */
 static inline void mtip_process_errors(struct driver_data *dd, u32 port_stat)
 {
-
 	if (unlikely(port_stat & PORT_IRQ_CONNECT)) {
 		dev_warn(&dd->pdev->dev,
 			"Clearing PxSERR.DIAG.x\n");
···
 
 static void mtip_issue_non_ncq_command(struct mtip_port *port, int tag)
 {
-	writel(1 << MTIP_TAG_BIT(tag),
-		port->cmd_issue[MTIP_TAG_INDEX(tag)]);
+	writel(1 << MTIP_TAG_BIT(tag), port->cmd_issue[MTIP_TAG_INDEX(tag)]);
 }
 
 static bool mtip_pause_ncq(struct mtip_port *port,
···
 	return false;
 }
 
+static bool mtip_commands_active(struct mtip_port *port)
+{
+	unsigned int active;
+	unsigned int n;
+
+	/*
+	 * Ignore s_active bit 0 of array element 0.
+	 * This bit will always be set
+	 */
+	active = readl(port->s_active[0]) & 0xFFFFFFFE;
+	for (n = 1; n < port->dd->slot_groups; n++)
+		active |= readl(port->s_active[n]);
+
+	return active != 0;
+}
+
 /*
  * Wait for port to quiesce
  *
  * @port    Pointer to port data structure
  * @timeout Max duration to wait (ms)
- * @atomic  gfp_t flag to indicate blockable context or not
  *
  * return value
  *	0	Success
  *	-EBUSY  Commands still active
  */
-static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout,
-								gfp_t atomic)
+static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout)
 {
 	unsigned long to;
-	unsigned int n;
-	unsigned int active = 1;
+	bool active = true;
 
 	blk_mq_stop_hw_queues(port->dd->queue);
 
 	to = jiffies + msecs_to_jiffies(timeout);
 	do {
 		if (test_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags) &&
-			test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags) &&
-			atomic == GFP_KERNEL) {
+			test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) {
 			msleep(20);
 			continue; /* svc thd is actively issuing commands */
 		}
 
-		if (atomic == GFP_KERNEL)
-			msleep(100);
-		else {
-			cpu_relax();
-			udelay(100);
-		}
+		msleep(100);
 
 		if (mtip_check_surprise_removal(port->dd->pdev))
 			goto err_fault;
 
-		/*
-		 * Ignore s_active bit 0 of array element 0.
-		 * This bit will always be set
-		 */
-		active = readl(port->s_active[0]) & 0xFFFFFFFE;
-		for (n = 1; n < port->dd->slot_groups; n++)
-			active |= readl(port->s_active[n]);
-
+		active = mtip_commands_active(port);
 		if (!active)
 			break;
 	} while (time_before(jiffies, to));
···
 	blk_mq_start_stopped_hw_queues(port->dd->queue, true);
 	return -EFAULT;
 }
+
+struct mtip_int_cmd {
+	int fis_len;
+	dma_addr_t buffer;
+	int buf_len;
+	u32 opts;
+};
 
 /*
  * Execute an internal command and wait for the completion.
···
 					dma_addr_t buffer,
 					int buf_len,
 					u32 opts,
-					gfp_t atomic,
 					unsigned long timeout)
 {
-	struct mtip_cmd_sg *command_sg;
-	DECLARE_COMPLETION_ONSTACK(wait);
 	struct mtip_cmd *int_cmd;
 	struct driver_data *dd = port->dd;
+	struct request *rq;
+	struct mtip_int_cmd icmd = {
+		.fis_len = fis_len,
+		.buffer = buffer,
+		.buf_len = buf_len,
+		.opts = opts
+	};
 	int rv = 0;
 	unsigned long start;
 
···
 		dbg_printk(MTIP_DRV_NAME "Unable to allocate tag for PIO cmd\n");
 		return -EFAULT;
 	}
+	rq = blk_mq_rq_from_pdu(int_cmd);
+	rq->special = &icmd;
 
 	set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 
···
 
 	clear_bit(MTIP_PF_DM_ACTIVE_BIT, &port->flags);
 
-	if (atomic == GFP_KERNEL) {
-		if (fis->command != ATA_CMD_STANDBYNOW1) {
-			/* wait for io to complete if non atomic */
-			if (mtip_quiesce_io(port,
-				MTIP_QUIESCE_IO_TIMEOUT_MS, atomic) < 0) {
-				dev_warn(&dd->pdev->dev,
-					"Failed to quiesce IO\n");
-				mtip_put_int_command(dd, int_cmd);
-				clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
-				wake_up_interruptible(&port->svc_wait);
-				return -EBUSY;
-			}
+	if (fis->command != ATA_CMD_STANDBYNOW1) {
+		/* wait for io to complete if non atomic */
+		if (mtip_quiesce_io(port, MTIP_QUIESCE_IO_TIMEOUT_MS) < 0) {
+			dev_warn(&dd->pdev->dev, "Failed to quiesce IO\n");
+			blk_mq_free_request(rq);
+			clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
+			wake_up_interruptible(&port->svc_wait);
+			return -EBUSY;
 		}
-
-		/* Set the completion function and data for the command. */
-		int_cmd->comp_data = &wait;
-		int_cmd->comp_func = mtip_completion;
-
-	} else {
-		/* Clear completion - we're going to poll */
-		int_cmd->comp_data = NULL;
-		int_cmd->comp_func = mtip_null_completion;
 	}
 
 	/* Copy the command to the command table */
 	memcpy(int_cmd->command, fis, fis_len*4);
 
-	/* Populate the SG list */
-	int_cmd->command_header->opts =
-		 __force_bit2int cpu_to_le32(opts | fis_len);
-	if (buf_len) {
-		command_sg = int_cmd->command + AHCI_CMD_TBL_HDR_SZ;
-
-		command_sg->info =
-			__force_bit2int cpu_to_le32((buf_len-1) & 0x3FFFFF);
-		command_sg->dba	=
-			__force_bit2int cpu_to_le32(buffer & 0xFFFFFFFF);
-		command_sg->dba_upper =
-			__force_bit2int cpu_to_le32((buffer >> 16) >> 16);
-
-		int_cmd->command_header->opts |=
-			__force_bit2int cpu_to_le32((1 << 16));
-	}
-
-	/* Populate the command header */
-	int_cmd->command_header->byte_count = 0;
-
 	start = jiffies;
+	rq->timeout = timeout;
 
-	/* Issue the command to the hardware */
-	mtip_issue_non_ncq_command(port, MTIP_TAG_INTERNAL);
+	/* insert request and run queue */
+	blk_execute_rq(rq->q, NULL, rq, true);
 
-	if (atomic == GFP_KERNEL) {
-		/* Wait for the command to complete or timeout. */
-		if ((rv = wait_for_completion_interruptible_timeout(
-				&wait,
-				msecs_to_jiffies(timeout))) <= 0) {
+	rv = int_cmd->status;
+	if (rv < 0) {
+		if (rv == -ERESTARTSYS) { /* interrupted */
+			dev_err(&dd->pdev->dev,
+				"Internal command [%02X] was interrupted after %u ms\n",
+				fis->command,
+				jiffies_to_msecs(jiffies - start));
+			rv = -EINTR;
+			goto exec_ic_exit;
+		} else if (rv == 0) /* timeout */
+			dev_err(&dd->pdev->dev,
+				"Internal command did not complete [%02X] within timeout of  %lu ms\n",
+				fis->command, timeout);
+		else
+			dev_err(&dd->pdev->dev,
+				"Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n",
+				fis->command, rv, timeout);
 
-			if (rv == -ERESTARTSYS) { /* interrupted */
-				dev_err(&dd->pdev->dev,
-					"Internal command [%02X] was interrupted after %u ms\n",
-					fis->command,
-					jiffies_to_msecs(jiffies - start));
-				rv = -EINTR;
-				goto exec_ic_exit;
-			} else if (rv == 0) /* timeout */
-				dev_err(&dd->pdev->dev,
-					"Internal command did not complete [%02X] within timeout of  %lu ms\n",
-					fis->command, timeout);
-			else
-				dev_err(&dd->pdev->dev,
-					"Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n",
-					fis->command, rv, timeout);
-
-			if (mtip_check_surprise_removal(dd->pdev) ||
-				test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
-						&dd->dd_flag)) {
-				dev_err(&dd->pdev->dev,
-					"Internal command [%02X] wait returned due to SR\n",
-					fis->command);
-				rv = -ENXIO;
-				goto exec_ic_exit;
-			}
-			mtip_device_reset(dd); /* recover from timeout issue */
-			rv = -EAGAIN;
+		if (mtip_check_surprise_removal(dd->pdev) ||
+			test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
+					&dd->dd_flag)) {
+			dev_err(&dd->pdev->dev,
+				"Internal command [%02X] wait returned due to SR\n",
+				fis->command);
+			rv = -ENXIO;
 			goto exec_ic_exit;
 		}
-	} else {
-		u32 hba_stat, port_stat;
-
-		/* Spin for <timeout> checking if command still outstanding */
-		timeout = jiffies + msecs_to_jiffies(timeout);
-		while ((readl(port->cmd_issue[MTIP_TAG_INTERNAL])
-				& (1 << MTIP_TAG_INTERNAL))
-				&& time_before(jiffies, timeout)) {
-			if (mtip_check_surprise_removal(dd->pdev)) {
-				rv = -ENXIO;
-				goto exec_ic_exit;
-			}
-			if ((fis->command != ATA_CMD_STANDBYNOW1) &&
-				test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
-						&dd->dd_flag)) {
-				rv = -ENXIO;
-				goto exec_ic_exit;
-			}
-			port_stat = readl(port->mmio + PORT_IRQ_STAT);
-			if (!port_stat)
-				continue;
-
-			if (port_stat & PORT_IRQ_ERR) {
-				dev_err(&dd->pdev->dev,
-					"Internal command [%02X] failed\n",
-					fis->command);
-				mtip_device_reset(dd);
-				rv = -EIO;
-				goto exec_ic_exit;
-			} else {
-				writel(port_stat, port->mmio + PORT_IRQ_STAT);
-				hba_stat = readl(dd->mmio + HOST_IRQ_STAT);
-				if (hba_stat)
-					writel(hba_stat,
-						dd->mmio + HOST_IRQ_STAT);
-			}
-			break;
-		}
+		mtip_device_reset(dd); /* recover from timeout issue */
+		rv = -EAGAIN;
+		goto exec_ic_exit;
 	}
 
-	if (readl(port->cmd_issue[MTIP_TAG_INTERNAL])
-			& (1 << MTIP_TAG_INTERNAL)) {
+	if (readl(port->cmd_issue[MTIP_TAG_INDEX(MTIP_TAG_INTERNAL)])
+			& (1 << MTIP_TAG_BIT(MTIP_TAG_INTERNAL))) {
 		rv = -ENXIO;
 		if (!test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag)) {
 			mtip_device_reset(dd);
···
 	}
 exec_ic_exit:
 	/* Clear the allocated and active bits for the internal command. */
-	mtip_put_int_command(dd, int_cmd);
+	blk_mq_free_request(rq);
 	clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 	if (rv >= 0 && mtip_pause_ncq(port, fis)) {
 		/* NCQ paused */
···
 				port->identify_dma,
 				sizeof(u16) * ATA_ID_WORDS,
 				0,
-				GFP_KERNEL,
 				MTIP_INT_CMD_TIMEOUT_MS)
 				< 0) {
 		rv = -1;
···
 					0,
 					0,
 					0,
-					GFP_ATOMIC,
 					timeout);
 	dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
 			jiffies_to_msecs(jiffies - start));
···
 					buffer_dma,
 					sectors * ATA_SECT_SIZE,
 					0,
-					GFP_ATOMIC,
 					MTIP_INT_CMD_TIMEOUT_MS);
 }
 
···
 					buffer_dma,
 					ATA_SECT_SIZE,
 					0,
-					GFP_ATOMIC,
 					15000);
 }
 
···
 					dma_addr,
 					ATA_SECT_SIZE,
 					0,
-					GFP_KERNEL,
 					MTIP_TRIM_TIMEOUT_MS) < 0)
 		rv = -EIO;
 
···
 				 0,
 				 0,
 				 0,
-				 GFP_KERNEL,
 				 to) < 0) {
 		return -1;
 	}
···
 				 (xfer_sz ? dma_addr : 0),
 				 (xfer_sz ? ATA_SECT_SIZE * xfer_sz : 0),
 				 0,
-				 GFP_KERNEL,
 				 to)
 				 < 0) {
 		rv = -EFAULT;
···
 				 dma_buffer,
 				 transfer_size,
 				 0,
-				 GFP_KERNEL,
 				 timeout) < 0) {
 		err = -EIO;
 		goto abort;
···
 				(nents << 16) | 5 | AHCI_CMD_PREFETCH);
 	command->command_header->byte_count = 0;
 
-	/*
-	 * Set the completion function and data for the command
-	 * within this layer.
-	 */
-	command->comp_data = dd;
-	command->comp_func = mtip_async_complete;
 	command->direction = dma_dir;
 
 	/*
···
 	return false;
 }
 
+static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
+				   struct request *rq)
+{
+	struct driver_data *dd = hctx->queue->queuedata;
+	struct mtip_int_cmd *icmd = rq->special;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	struct mtip_cmd_sg *command_sg;
+
+	if (mtip_commands_active(dd->port))
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
+	/* Populate the SG list */
+	cmd->command_header->opts =
+		 __force_bit2int cpu_to_le32(icmd->opts | icmd->fis_len);
+	if (icmd->buf_len) {
+		command_sg = cmd->command + AHCI_CMD_TBL_HDR_SZ;
+
+		command_sg->info =
+			__force_bit2int cpu_to_le32((icmd->buf_len-1) & 0x3FFFFF);
+		command_sg->dba	=
+			__force_bit2int cpu_to_le32(icmd->buffer & 0xFFFFFFFF);
+		command_sg->dba_upper =
+			__force_bit2int cpu_to_le32((icmd->buffer >> 16) >> 16);
+
+		cmd->command_header->opts |=
+			__force_bit2int cpu_to_le32((1 << 16));
+	}
+
+	/* Populate the command header */
+	cmd->command_header->byte_count = 0;
+
+	blk_mq_start_request(rq);
+	mtip_issue_non_ncq_command(dd->port, rq->tag);
+	return BLK_MQ_RQ_QUEUE_OK;
+}
+
 static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
···
 	int ret;
 
 	mtip_init_cmd_header(rq);
+
+	if (blk_rq_is_passthrough(rq))
+		return mtip_issue_reserved_cmd(hctx, rq);
 
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
···
 	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
-static void mtip_free_cmd(void *data, struct request *rq,
-			  unsigned int hctx_idx, unsigned int request_idx)
+static void mtip_free_cmd(struct blk_mq_tag_set *set, struct request *rq,
+			  unsigned int hctx_idx)
 {
-	struct driver_data *dd = data;
+	struct driver_data *dd = set->driver_data;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
 	if (!cmd->command)
···
 				cmd->command, cmd->command_dma);
 }
 
-static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
-			 unsigned int request_idx, unsigned int numa_node)
+static int mtip_init_cmd(struct blk_mq_tag_set *set, struct request *rq,
+			 unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct driver_data *dd = data;
+	struct driver_data *dd = set->driver_data;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
-
-	/*
-	 * For flush requests, request_idx starts at the end of the
-	 * tag space.  Since we don't support FLUSH/FUA, simply return
-	 * 0 as there's nothing to be done.
-	 */
-	if (request_idx >= MTIP_MAX_COMMAND_SLOTS)
-		return 0;
 
 	cmd->command = dmam_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ,
 			&cmd->command_dma, GFP_KERNEL);
···
 {
 	struct driver_data *dd = req->q->queuedata;
 
-	if (reserved)
-		goto exit_handler;
+	if (reserved) {
+		struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
+
+		cmd->status = -ETIME;
+		return BLK_EH_HANDLED;
+	}
 
 	if (test_bit(req->tag, dd->port->cmds_to_issue))
 		goto exit_handler;
···
 	dd->tags.reserved_tags = 1;
 	dd->tags.cmd_size = sizeof(struct mtip_cmd);
 	dd->tags.numa_node = dd->numa_node;
-	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_SCHED;
+	dd->tags.flags = BLK_MQ_F_SHOULD_MERGE;
 	dd->tags.driver_data = dd;
 	dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS;
 
···
 
 static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
 {
-	struct driver_data *dd = (struct driver_data *)data;
-	struct mtip_cmd *cmd;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	if (likely(!reserv)) {
-		cmd = blk_mq_rq_to_pdu(rq);
-		cmd->status = -ENODEV;
-		blk_mq_complete_request(rq);
-	} else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
-
-		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
-		if (cmd->comp_func)
-			cmd->comp_func(dd->port, MTIP_TAG_INTERNAL,
-					cmd, -ENODEV);
-	}
+	cmd->status = -ENODEV;
+	blk_mq_complete_request(rq);
 }
 
 /*
···
 		 * Explicitly wait here for IOs to quiesce,
 		 * as mtip_standby_drive usually won't wait for IOs.
 		 */
-		if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS,
-								GFP_KERNEL))
+		if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS))
 			mtip_standby_drive(dd);
 	}
 	else

drivers/block/mtip32xx/mtip32xx.h

···
 
 	dma_addr_t command_dma; /* corresponding physical address */
 
-	void *comp_data; /* data passed to completion function comp_func() */
-	/*
-	 * Completion function called by the ISR upon completion of
-	 * a command.
-	 */
-	void (*comp_func)(struct mtip_port *port,
-				int tag,
-				struct mtip_cmd *cmd,
-				int status);
-
 	int scatter_ents; /* Number of scatter list entries used */
 
 	int unaligned; /* command is unaligned on 4k boundary */

drivers/block/nbd.c

···
 
 #endif
 
-static int nbd_init_request(void *data, struct request *rq,
-			    unsigned int hctx_idx, unsigned int request_idx,
-			    unsigned int numa_node)
+static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
+			    unsigned int hctx_idx, unsigned int numa_node)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq);
-	cmd->nbd = data;
+	cmd->nbd = set->driver_data;
 	return 0;
 }
 

drivers/block/rbd.c

···
 	return ret;
 }
 
-static int rbd_init_request(void *data, struct request *rq,
-		unsigned int hctx_idx, unsigned int request_idx,
-		unsigned int numa_node)
+static int rbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
 	struct work_struct *work = blk_mq_rq_to_pdu(rq);
 

drivers/block/virtio_blk.c

···
 	__ATTR(cache_type, S_IRUGO|S_IWUSR,
 	       virtblk_cache_type_show, virtblk_cache_type_store);
 
-static int virtblk_init_request(void *data, struct request *rq,
-		unsigned int hctx_idx, unsigned int request_idx,
-		unsigned int numa_node)
+static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct virtio_blk *vblk = data;
+	struct virtio_blk *vblk = set->driver_data;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
 
 #ifdef CONFIG_VIRTIO_BLK_SCSI

drivers/lightnvm/core.c

···
 
 	return 0;
 err:
-	while (--i > lun_begin)
+	while (--i >= lun_begin)
 		clear_bit(i, dev->lun_map);
 
 	return -EBUSY;
···
 
 	return tgt_dev;
 err_ch:
-	while (--i > 0)
+	while (--i >= 0)
 		kfree(dev_map->chnls[i].lun_offs);
 	kfree(luns);
 err_luns:

drivers/md/dm-rq.c

···
 	return 0;
 }
 
-static int dm_mq_init_request(void *data, struct request *rq,
-		       unsigned int hctx_idx, unsigned int request_idx,
-		       unsigned int numa_node)
+static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	return __dm_rq_init_rq(data, rq);
+	return __dm_rq_init_rq(set->driver_data, rq);
 }
 
 static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,

drivers/mtd/ubi/block.c

···
 
 }
 
-static int ubiblock_init_request(void *data, struct request *req,
-				 unsigned int hctx_idx,
-				 unsigned int request_idx,
-				 unsigned int numa_node)
+static int ubiblock_init_request(struct blk_mq_tag_set *set,
+		struct request *req, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
 	struct ubiblock_pdu *pdu = blk_mq_rq_to_pdu(req);
 

drivers/nvme/host/fc.c

···
 }
 
 static void
-nvme_fc_exit_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx)
+nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx)
 {
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 
-	return __nvme_fc_exit_request(data, op);
+	return __nvme_fc_exit_request(set->driver_data, op);
 }
 
 static int
···
 }
 
 static int
-nvme_fc_init_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct nvme_fc_ctrl *ctrl = data;
+	struct nvme_fc_ctrl *ctrl = set->driver_data;
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_queue *queue = &ctrl->queues[hctx_idx+1];
 
···
 }
 
 static int
-nvme_fc_init_admin_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+nvme_fc_init_admin_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct nvme_fc_ctrl *ctrl = data;
+	struct nvme_fc_ctrl *ctrl = set->driver_data;
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
 	struct nvme_fc_queue *queue = &ctrl->queues[0];
 

drivers/nvme/host/lightnvm.c

···
 	if (!cmd)
 		return -ENOMEM;
 
+	nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
+
 	rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0, NVME_QID_ANY);
 	if (IS_ERR(rq)) {
 		kfree(cmd);
···
 		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 		rq->__data_len = 0;
 	}
-
-	nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
 
 	rq->end_io_data = rqd;
 

drivers/nvme/host/pci.c

···
 	nvmeq->tags = NULL;
 }
 
-static int nvme_admin_init_request(void *data, struct request *req,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_admin_init_request(struct blk_mq_tag_set *set,
+		struct request *req, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
-	struct nvme_dev *dev = data;
+	struct nvme_dev *dev = set->driver_data;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = dev->queues[0];
 
···
 	return 0;
 }
 
-static int nvme_init_request(void *data, struct request *req,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct nvme_dev *dev = data;
+	struct nvme_dev *dev = set->driver_data;
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
 

drivers/nvme/host/rdma.c

···
 			DMA_TO_DEVICE);
 }
 
-static void nvme_rdma_exit_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx)
+static void nvme_rdma_exit_request(struct blk_mq_tag_set *set,
+		struct request *rq, unsigned int hctx_idx)
 {
-	return __nvme_rdma_exit_request(data, rq, hctx_idx + 1);
+	return __nvme_rdma_exit_request(set->driver_data, rq, hctx_idx + 1);
 }
 
-static void nvme_rdma_exit_admin_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx)
+static void nvme_rdma_exit_admin_request(struct blk_mq_tag_set *set,
+		struct request *rq, unsigned int hctx_idx)
 {
-	return __nvme_rdma_exit_request(data, rq, 0);
+	return __nvme_rdma_exit_request(set->driver_data, rq, 0);
 }
 
 static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
···
 	return -ENOMEM;
 }
 
-static int nvme_rdma_init_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
+		struct request *rq, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
-	return __nvme_rdma_init_request(data, rq, hctx_idx + 1);
+	return __nvme_rdma_init_request(set->driver_data, rq, hctx_idx + 1);
 }
 
-static int nvme_rdma_init_admin_request(void *data, struct request *rq,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_rdma_init_admin_request(struct blk_mq_tag_set *set,
+		struct request *rq, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
-	return __nvme_rdma_init_request(data, rq, 0);
+	return __nvme_rdma_init_request(set->driver_data, rq, 0);
 }
 
 static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,

drivers/nvme/target/loop.c

···
 	return 0;
 }
 
-static int nvme_loop_init_request(void *data, struct request *req,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_loop_init_request(struct blk_mq_tag_set *set,
+		struct request *req, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
-	return nvme_loop_init_iod(data, blk_mq_rq_to_pdu(req), hctx_idx + 1);
+	return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req),
+			hctx_idx + 1);
 }
 
-static int nvme_loop_init_admin_request(void *data, struct request *req,
-				unsigned int hctx_idx, unsigned int rq_idx,
-				unsigned int numa_node)
+static int nvme_loop_init_admin_request(struct blk_mq_tag_set *set,
+		struct request *req, unsigned int hctx_idx,
+		unsigned int numa_node)
 {
-	return nvme_loop_init_iod(data, blk_mq_rq_to_pdu(req), 0);
+	return nvme_loop_init_iod(set->driver_data, blk_mq_rq_to_pdu(req), 0);
 }
 
 static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,

drivers/scsi/scsi_lib.c

···
 	return scsi_times_out(req);
 }
 
-static int scsi_init_request(void *data, struct request *rq,
-		unsigned int hctx_idx, unsigned int request_idx,
-		unsigned int numa_node)
+static int scsi_init_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx, unsigned int numa_node)
 {
-	struct Scsi_Host *shost = data;
+	struct Scsi_Host *shost = set->driver_data;
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
 	cmd->sense_buffer =
···
 	return 0;
 }
 
-static void scsi_exit_request(void *data, struct request *rq,
-		unsigned int hctx_idx, unsigned int request_idx)
+static void scsi_exit_request(struct blk_mq_tag_set *set, struct request *rq,
+		unsigned int hctx_idx)
 {
-	struct Scsi_Host *shost = data;
+	struct Scsi_Host *shost = set->driver_data;
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
 	scsi_free_sense_buffer(shost, cmd->sense_buffer);

fs/nfs/internal.h

···
 };
 
 struct nfs_mount_info {
-	int (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
 	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
 	struct nfs_parsed_mount_data *parsed;
 	struct nfs_clone_mount *cloned;
···
 struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
 		const char *, struct nfs_mount_info *);
 void nfs_kill_super(struct super_block *);
-int nfs_fill_super(struct super_block *, struct nfs_mount_info *);
+void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
···
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 
 /* super.c */
-int nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
 void nfs_umount_begin(struct super_block *);
 int  nfs_statfs(struct dentry *, struct kstatfs *);
 int  nfs_show_options(struct seq_file *, struct dentry *);

fs/nfs/super.c

···
 /*
  * Finish setting up an NFS2/3 superblock
  */
-int nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
-	int ret;
 
 	sb->s_blocksize_bits = 0;
 	sb->s_blocksize = 0;
···
 	}
 
  	nfs_initialise_sb(sb);
-
-	ret = super_setup_bdi_name(sb, "%u:%u", MAJOR(server->s_dev),
-				   MINOR(server->s_dev));
-	if (ret)
-		return ret;
-	sb->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
-	return 0;
-
 }
 EXPORT_SYMBOL_GPL(nfs_fill_super);
 
 /*
  * Finish setting up a cloned NFS2/3/4 superblock
  */
-int nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
···
 	}
 
  	nfs_initialise_sb(sb);
-
-	sb->s_bdi = bdi_get(old_sb->s_bdi);
-
-	return 0;
 }
 
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
···
 		nfs_free_server(server);
 		server = NULL;
 	} else {
+		error = super_setup_bdi_name(s, "%u:%u", MAJOR(server->s_dev),
+					     MINOR(server->s_dev));
+		if (error) {
+			mntroot = ERR_PTR(error);
+			goto error_splat_super;
+		}
+		s->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
 		server->super = s;
 	}
 
 	if (!s->s_root) {
 		/* initial superblock/root creation */
-		error = mount_info->fill_super(s, mount_info);
-		if (error)
-			goto error_splat_super;
+		mount_info->fill_super(s, mount_info);
 		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
 	}
 

include/linux/blk-mq.h

···
 	unsigned long		poll_considered;
 	unsigned long		poll_invoked;
 	unsigned long		poll_success;
+
+#ifdef CONFIG_BLK_DEBUG_FS
+	struct dentry		*debugfs_dir;
+	struct dentry		*sched_debugfs_dir;
+#endif
 };
 
 struct blk_mq_tag_set {
···
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
-typedef int (init_request_fn)(void *, struct request *, unsigned int,
+typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *,
 		unsigned int, unsigned int);
-typedef void (exit_request_fn)(void *, struct request *, unsigned int,
+typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *,
 		unsigned int);
 typedef int (reinit_request_fn)(void *, struct request *);
 

include/linux/blkdev.h

···
 
 #ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
-	struct dentry		*mq_debugfs_dir;
+	struct dentry		*sched_debugfs_dir;
 #endif
 
 	bool			mq_sysfs_init_done;

include/linux/elevator.h

···
 
 struct io_cq;
 struct elevator_type;
+#ifdef CONFIG_BLK_DEBUG_FS
+struct blk_mq_debugfs_attr;
+#endif
 
 /*
  * Return values from elevator merger
···
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
 	bool uses_mq;
+#ifdef CONFIG_BLK_DEBUG_FS
+	const struct blk_mq_debugfs_attr *queue_debugfs_attrs;
+	const struct blk_mq_debugfs_attr *hctx_debugfs_attrs;
+#endif
 
 	/* managed by elevator core */
 	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
···
 
 extern int elevator_init(struct request_queue *, char *);
 extern void elevator_exit(struct request_queue *, struct elevator_queue *);
-extern int elevator_change(struct request_queue *, const char *);
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
 					struct elevator_type *);