blk-mq: abstract tag allocation out into sbitmap library

608 lines not on this page · raw message

index d468a79..3215c08 100644
@@ -3,31 +3,6 @@
 
 #include "blk-mq.h"
 
-enum {
-	BT_WAIT_QUEUES	= 8,
-	BT_WAIT_BATCH	= 8,
-};
-
-struct bt_wait_state {
-	atomic_t wait_cnt;
-	wait_queue_head_t wait;
-} ____cacheline_aligned_in_smp;
-
-#define TAG_TO_INDEX(bt, tag)	((tag) >> (bt)->bits_per_word)
-#define TAG_TO_BIT(bt, tag)	((tag) & ((1 << (bt)->bits_per_word) - 1))
-
-struct blk_mq_bitmap_tags {
-	unsigned int depth;
-	unsigned int wake_cnt;
-	unsigned int bits_per_word;
-
-	unsigned int map_nr;
-	struct blk_align_bitmap *map;
-
-	atomic_t wake_index;
-	struct bt_wait_state *bs;
-};
-
 /*
  * Tag address space map.
  */

@@ -37,8 +12,8 @@ struct blk_mq_tags {
 
 	atomic_t active_queues;
 
-	struct blk_mq_bitmap_tags bitmap_tags;
-	struct blk_mq_bitmap_tags breserved_tags;
+	struct sbitmap_queue bitmap_tags;
+	struct sbitmap_queue breserved_tags;
 
 	struct request **rqs;
 	struct list_head page_list;

@@ -61,6 +36,14 @@ extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
 
+static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt,
+						 struct blk_mq_hw_ctx *hctx)
+{
+	if (!hctx)
+		return &bt->ws[0];
+	return sbq_wait_ptr(bt, &hctx->wait_index);
+}
+
 enum {
 	BLK_MQ_TAG_CACHE_MIN	= 1,
 	BLK_MQ_TAG_CACHE_MAX	= 64,

180 lines not on this page · raw message

index 9087b11..71831f9 100644
@@ -63,15 +63,6 @@ extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
 void blk_mq_release(struct request_queue *q);
 
-/*
- * Basic implementation of sparser bitmap, allowing the user to spread
- * the bits over more cachelines.
- */
-struct blk_align_bitmap {
-	unsigned long word;
-	unsigned long depth;
-} ____cacheline_aligned_in_smp;
-
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {

index e43bbff..465807f 100644
@@ -2,6 +2,7 @@
 #define BLK_MQ_H
 
 #include <linux/blkdev.h>
+#include <linux/sbitmap.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;

@@ -12,12 +13,6 @@ struct blk_mq_cpu_notifier {
 	int (*notify)(void *data, unsigned long action, unsigned int cpu);
 };
 
-struct blk_mq_ctxmap {
-	unsigned int size;
-	unsigned int bits_per_word;
-	struct blk_align_bitmap *map;
-};
-
 struct blk_mq_hw_ctx {
 	struct {
 		spinlock_t		lock;

@@ -38,7 +33,7 @@ struct blk_mq_hw_ctx {
 
 	void			*driver_data;
 
-	struct blk_mq_ctxmap	ctx_map;
+	struct sbitmap		ctx_map;
 
 	unsigned int		nr_ctx;
 	struct blk_mq_ctx	**ctxs;

329 lines not on this page · raw message

300 lines not on this page · raw message

index 303d83e..213d831 100644
@@ -208,7 +208,7 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 
 	atomic_set(&sbq->wake_index, 0);
 
-	sbq->ws = kzalloc(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags);
+	sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
 	if (!sbq->ws) {
 		sbitmap_free(&sbq->sb);
 		return -ENOMEM;

index 83ee740..c9a22db 100644
@@ -94,23 +94,21 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 #define BT_ALLOC_RR(tags) (tags->alloc_policy == BLK_TAG_ALLOC_RR)
 
 static int __bt_get(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt,
-		    unsigned int *tag_cache, struct blk_mq_tags *tags)
+		    struct blk_mq_tags *tags)
 {
 	if (!hctx_may_queue(hctx, bt))
 		return -1;
-	return sbitmap_get(&bt->sb, tag_cache, BT_ALLOC_RR(tags));
+	return __sbitmap_queue_get(bt, BT_ALLOC_RR(tags));
 }
 
-static int bt_get(struct blk_mq_alloc_data *data,
-		  struct sbitmap_queue *bt,
-		  struct blk_mq_hw_ctx *hctx,
-		  unsigned int *last_tag, struct blk_mq_tags *tags)
+static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
+		  struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags)
 {
 	struct sbq_wait_state *ws;
 	DEFINE_WAIT(wait);
 	int tag;
 
-	tag = __bt_get(hctx, bt, last_tag, tags);
+	tag = __bt_get(hctx, bt, tags);
 	if (tag != -1)
 		return tag;
 

@@ -121,7 +119,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	do {
 		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt, last_tag, tags);
+		tag = __bt_get(hctx, bt, tags);
 		if (tag != -1)
 			break;
 

@@ -138,7 +136,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt, last_tag, tags);
+		tag = __bt_get(hctx, bt, tags);
 		if (tag != -1)
 			break;
 

@@ -152,7 +150,6 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		if (data->flags & BLK_MQ_REQ_RESERVED) {
 			bt = &data->hctx->tags->breserved_tags;
 		} else {
-			last_tag = &data->ctx->last_tag;
 			hctx = data->hctx;
 			bt = &hctx->tags->bitmap_tags;
 		}

@@ -169,7 +166,7 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	int tag;
 
 	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-			&data->ctx->last_tag, data->hctx->tags);
+		     data->hctx->tags);
 	if (tag >= 0)
 		return tag + data->hctx->tags->nr_reserved_tags;
 

@@ -178,15 +175,15 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
 
 static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
 {
-	int tag, zero = 0;
+	int tag;
 
 	if (unlikely(!data->hctx->tags->nr_reserved_tags)) {
 		WARN_ON_ONCE(1);
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero,
-		data->hctx->tags);
+	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL,
+		     data->hctx->tags);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 

@@ -200,8 +197,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	return __blk_mq_get_tag(data);
 }
 
-void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
-		    unsigned int *last_tag)
+void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+		    unsigned int tag)
 {
 	struct blk_mq_tags *tags = hctx->tags;
 

@@ -209,12 +206,12 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 		const int real_tag = tag - tags->nr_reserved_tags;
 
 		BUG_ON(real_tag >= tags->nr_tags);
-		sbitmap_queue_clear(&tags->bitmap_tags, real_tag);
-		if (likely(tags->alloc_policy == BLK_TAG_ALLOC_FIFO))
-			*last_tag = real_tag;
+		sbitmap_queue_clear(&tags->bitmap_tags, real_tag,
+				    BT_ALLOC_RR(tags), ctx->cpu);
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
-		sbitmap_queue_clear(&tags->breserved_tags, tag);
+		sbitmap_queue_clear(&tags->breserved_tags, tag,
+				    BT_ALLOC_RR(tags), ctx->cpu);
 	}
 }
 

index 3215c08..2b1d52e 100644
@@ -27,7 +27,8 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag, unsigned int *last_tag);
+extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			   unsigned int tag);
 extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
 extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);

index 9dbe37f..004728f 100644
@@ -302,7 +302,7 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 	rq->cmd_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
-	blk_mq_put_tag(hctx, tag, &ctx->last_tag);
+	blk_mq_put_tag(hctx, ctx, tag);
 	blk_queue_exit(q);
 }
 

index 71831f9..9b15d2e 100644
@@ -12,8 +12,6 @@ struct blk_mq_ctx {
 	unsigned int		cpu;
 	unsigned int		index_hw;
 
-	unsigned int		last_tag ____cacheline_aligned_in_smp;
-
 	/* incremented at dispatch time */
 	unsigned long		rq_dispatched[2];
 	unsigned long		rq_merged;

73 lines not on this page · raw message

index 213d831..261543c 100644
@@ -202,6 +202,12 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 	if (ret)
 		return ret;
 
+	sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags);
+	if (!sbq->alloc_hint) {
+		sbitmap_free(&sbq->sb);
+		return -ENOMEM;
+	}
+
 	sbq->wake_batch = SBQ_WAKE_BATCH;
 	if (sbq->wake_batch > depth / SBQ_WAIT_QUEUES)
 		sbq->wake_batch = max(1U, depth / SBQ_WAIT_QUEUES);

@@ -210,6 +216,7 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 
 	sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node);
 	if (!sbq->ws) {
+		free_percpu(sbq->alloc_hint);
 		sbitmap_free(&sbq->sb);
 		return -ENOMEM;
 	}

@@ -254,7 +261,8 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 	return NULL;
 }
 
-void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr)
+void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
+			 bool round_robin, unsigned int cpu)
 {
 	struct sbq_wait_state *ws;
 	int wait_cnt;

@@ -266,7 +274,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr)
 
 	ws = sbq_wake_ptr(sbq);
 	if (!ws)
-		return;
+		goto update_cache;
 
 	wait_cnt = atomic_dec_return(&ws->wait_cnt);
 	if (unlikely(wait_cnt < 0))

@@ -276,6 +284,10 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr)
 		sbq_index_atomic_inc(&sbq->wake_index);
 		wake_up(&ws->wait);
 	}
+
+update_cache:
+	if (likely(!round_robin))
+		*per_cpu_ptr(sbq->alloc_hint, cpu) = nr;
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_clear);
 

index c9a22db..e1c2bed 100644
@@ -91,14 +91,11 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-#define BT_ALLOC_RR(tags) (tags->alloc_policy == BLK_TAG_ALLOC_RR)
-
-static int __bt_get(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt,
-		    struct blk_mq_tags *tags)
+static int __bt_get(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt)
 {
 	if (!hctx_may_queue(hctx, bt))
 		return -1;
-	return __sbitmap_queue_get(bt, BT_ALLOC_RR(tags));
+	return __sbitmap_queue_get(bt);
 }
 
 static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,

@@ -108,7 +105,7 @@ static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
 	DEFINE_WAIT(wait);
 	int tag;
 
-	tag = __bt_get(hctx, bt, tags);
+	tag = __bt_get(hctx, bt);
 	if (tag != -1)
 		return tag;
 

@@ -119,7 +116,7 @@ static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
 	do {
 		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt, tags);
+		tag = __bt_get(hctx, bt);
 		if (tag != -1)
 			break;
 

@@ -136,7 +133,7 @@ static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt, tags);
+		tag = __bt_get(hctx, bt);
 		if (tag != -1)
 			break;
 

@@ -206,12 +203,10 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 		const int real_tag = tag - tags->nr_reserved_tags;
 
 		BUG_ON(real_tag >= tags->nr_tags);
-		sbitmap_queue_clear(&tags->bitmap_tags, real_tag,
-				    BT_ALLOC_RR(tags), ctx->cpu);
+		sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu);
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
-		sbitmap_queue_clear(&tags->breserved_tags, tag,
-				    BT_ALLOC_RR(tags), ctx->cpu);
+		sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu);
 	}
 }
 

@@ -363,21 +358,23 @@ static unsigned int bt_unused_tags(const struct sbitmap_queue *bt)
 	return bt->sb.depth - sbitmap_weight(&bt->sb);
 }
 
-static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, int node)
+static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
+		    bool round_robin, int node)
 {
-	return sbitmap_queue_init_node(bt, depth, -1, GFP_KERNEL, node);
+	return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL,
+				       node);
 }
 
 static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
 						   int node, int alloc_policy)
 {
 	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
+	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
 
-	tags->alloc_policy = alloc_policy;
-
-	if (bt_alloc(&tags->bitmap_tags, depth, node))
+	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
 		goto free_tags;
-	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, node))
+	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, round_robin,
+		     node))
 		goto free_bitmap_tags;
 
 	return tags;

index 2b1d52e..f90b850 100644
@@ -18,7 +18,6 @@ struct blk_mq_tags {
 	struct request **rqs;
 	struct list_head page_list;
 
-	int alloc_policy;
 	cpumask_var_t cpumask;
 };
 

index c0f0cf6..32c5596 100644
@@ -122,6 +122,11 @@ struct sbitmap_queue {
 	 * @ws: Wait queues.
 	 */
 	struct sbq_wait_state *ws;
+
+	/**
+	 * @round_robin: Allocate bits in strict round-robin order.
+	 */
+	bool round_robin;
 };
 
 /**

@@ -261,13 +266,14 @@ unsigned int sbitmap_weight(const struct sbitmap *sb);
  * @sbq: Bitmap queue to initialize.
  * @depth: See sbitmap_init_node().
  * @shift: See sbitmap_init_node().
+ * @round_robin: See sbitmap_get().
  * @flags: Allocation flags.
  * @node: Memory node to allocate on.
  *
  * Return: Zero on success or negative errno on failure.
  */
 int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
-			    int shift, gfp_t flags, int node);
+			    int shift, bool round_robin, gfp_t flags, int node);
 
 /**
  * sbitmap_queue_free() - Free memory used by a &struct sbitmap_queue.

@@ -296,34 +302,31 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
  * __sbitmap_queue_get() - Try to allocate a free bit from a &struct
  * sbitmap_queue with preemption already disabled.
  * @sbq: Bitmap queue to allocate from.
- * @round_robin: See sbitmap_get().
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-static inline int __sbitmap_queue_get(struct sbitmap_queue *sbq,
-				      bool round_robin)
+static inline int __sbitmap_queue_get(struct sbitmap_queue *sbq)
 {
 	return sbitmap_get(&sbq->sb, this_cpu_ptr(sbq->alloc_hint),
-			   round_robin);
+			   sbq->round_robin);
 }
 
 /**
  * sbitmap_queue_get() - Try to allocate a free bit from a &struct
  * sbitmap_queue.
  * @sbq: Bitmap queue to allocate from.
- * @round_robin: See sbitmap_get().
  * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
  *       sbitmap_queue_clear()).
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, bool round_robin,
+static inline int sbitmap_queue_get(struct sbitmap_queue *sbq,
 				    unsigned int *cpu)
 {
 	int nr;
 
 	*cpu = get_cpu();
-	nr = __sbitmap_queue_get(sbq, round_robin);
+	nr = __sbitmap_queue_get(sbq);
 	put_cpu();
 	return nr;
 }

@@ -333,11 +336,10 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, bool round_robin,
  * &struct sbitmap_queue.
  * @sbq: Bitmap to free from.
  * @nr: Bit number to free.
- * @round_robin: See sbitmap_get().
  * @cpu: CPU the bit was allocated on.
  */
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
-			 bool round_robin, unsigned int cpu);
+			 unsigned int cpu);
 
 static inline int sbq_index_inc(int index)
 {

index 261543c..3a91269 100644
@@ -193,7 +193,7 @@ unsigned int sbitmap_weight(const struct sbitmap *sb)
 EXPORT_SYMBOL_GPL(sbitmap_weight);
 
 int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
-			    int shift, gfp_t flags, int node)
+			    int shift, bool round_robin, gfp_t flags, int node)
 {
 	int ret;
 	int i;

@@ -225,6 +225,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 		init_waitqueue_head(&sbq->ws[i].wait);
 		atomic_set(&sbq->ws[i].wait_cnt, sbq->wake_batch);
 	}
+
+	sbq->round_robin = round_robin;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);

@@ -262,7 +264,7 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 }
 
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
-			 bool round_robin, unsigned int cpu)
+			 unsigned int cpu)
 {
 	struct sbq_wait_state *ws;
 	int wait_cnt;

@@ -286,7 +288,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 	}
 
 update_cache:
-	if (likely(!round_robin))
+	if (likely(!sbq->round_robin))
 		*per_cpu_ptr(sbq->alloc_hint, cpu) = nr;
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_clear);

index e1c2bed..cef618f 100644
@@ -7,7 +7,6 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/random.h>
 
 #include <linux/blk-mq.h>
 #include "blk.h"

@@ -419,13 +418,6 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 	kfree(tags);
 }
 
-void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *tag)
-{
-	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
-
-	*tag = prandom_u32() % depth;
-}
-
 int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
 {
 	tdepth -= tags->nr_reserved_tags;

index f90b850..09f4cc0 100644
@@ -30,7 +30,6 @@ extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			   unsigned int tag);
 extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
 extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
-extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,

index 3a91269..d873bb0a 100644
@@ -15,6 +15,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
+#include <linux/random.h>
 #include <linux/sbitmap.h>
 
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,

@@ -208,6 +209,11 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 		return -ENOMEM;
 	}
 
+	if (depth && !round_robin) {
+		for_each_possible_cpu(i)
+			*per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth;
+	}
+
 	sbq->wake_batch = SBQ_WAKE_BATCH;
 	if (sbq->wake_batch > depth / SBQ_WAIT_QUEUES)
 		sbq->wake_batch = max(1U, depth / SBQ_WAIT_QUEUES);