scsi: sbitmap: Move allocation hint into sbitmap

Allocation hint should have belonged to sbitmap. Also, when sbitmap's depth
is high and there is no need to use mulitple wakeup queues, user can
benefit from percpu allocation hint too.

Move allocation hint into sbitmap, then SCSI device queue can benefit from
allocation hint when converting to plain sbitmap.

Convert vhost/scsi.c to use sbitmap allocation with percpu alloc hint. This
is more efficient than the previous approach.

Link: https://lore.kernel.org/r/20210122023317.687987-5-ming.lei@redhat.com
Cc: Omar Sandoval <osandov@fb.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: virtualization@lists.linux-foundation.org
Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 26 insertions, 15 deletions

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 734ee6214cd6..247776fcc02c 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -65,6 +65,14 @@ struct sbitmap {
 	 * @map: Allocated bitmap.
 	 */
 	struct sbitmap_word *map;
+
+	/*
+	 * @alloc_hint: Cache of last successfully allocated or freed bit.
+	 *
+	 * This is per-cpu, which allows multiple users to stick to different
+	 * cachelines until the map is exhausted.
+	 */
+	unsigned int __percpu *alloc_hint;
 };
 
 #define SBQ_WAIT_QUEUES 8
@@ -100,14 +108,6 @@ struct sbitmap_queue {
 	 */
 	struct sbitmap sb;
 
-	/*
-	 * @alloc_hint: Cache of last successfully allocated or freed bit.
-	 *
-	 * This is per-cpu, which allows multiple users to stick to different
-	 * cachelines until the map is exhausted.
-	 */
-	unsigned int __percpu *alloc_hint;
-
 	/**
 	 * @wake_batch: Number of bits which must be freed before we wake up any
 	 * waiters.
@@ -147,11 +147,13 @@ struct sbitmap_queue {
  * @round_robin: If true, be stricter about allocation order; always allocate
  *               starting from the last allocated bit. This is less efficient
  *               than the default behavior (false).
+ * @alloc_hint: If true, apply percpu hint for where to start searching for
+ *              a free bit.
  *
  * Return: Zero on success or negative errno on failure.
  */
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
-		      gfp_t flags, int node, bool round_robin);
+		      gfp_t flags, int node, bool round_robin, bool alloc_hint);
 
 /**
  * sbitmap_free() - Free memory used by a &struct sbitmap.
@@ -159,6 +161,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
  */
 static inline void sbitmap_free(struct sbitmap *sb)
 {
+	free_percpu(sb->alloc_hint);
 	kfree(sb->map);
 	sb->map = NULL;
 }
@@ -176,19 +179,17 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
 /**
  * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap.
  * @sb: Bitmap to allocate from.
- * @alloc_hint: Hint for where to start searching for a free bit.
  *
  * This operation provides acquire barrier semantics if it succeeds.
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint);
+int sbitmap_get(struct sbitmap *sb);
 
 /**
  * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
  * limiting the depth used from each word.
  * @sb: Bitmap to allocate from.
- * @alloc_hint: Hint for where to start searching for a free bit.
  * @shallow_depth: The maximum number of bits to allocate from a single word.
  *
  * This rather specific operation allows for having multiple users with
@@ -200,8 +201,7 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint);
  *
  * Return: Non-negative allocated bit number if successful, -1 otherwise.
  */
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
-			unsigned long shallow_depth);
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth);
 
 /**
  * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
@@ -315,6 +315,18 @@ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int b
 	set_bit(SB_NR_TO_BIT(sb, bitnr), addr);
 }
 
+/*
+ * Pair of sbitmap_get, and this one applies both cleared bit and
+ * allocation hint.
+ */
+static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr)
+{
+	sbitmap_deferred_clear_bit(sb, bitnr);
+
+	if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth))
+		*this_cpu_ptr(sb->alloc_hint) = bitnr;
+}
+
 static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 {
 	return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr));
@@ -363,7 +375,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 static inline void sbitmap_queue_free(struct sbitmap_queue *sbq)
 {
 	kfree(sbq->ws);
-	free_percpu(sbq->alloc_hint);
 	sbitmap_free(&sbq->sb);
 }