sbitmap: randomize initial alloc_hint values

In order to get good cache behavior from a sbitmap, we want each CPU to
stick to its own cacheline(s) as much as possible. This might happen
naturally as the bitmap gets filled up and the alloc_hint values spread
out, but we really want this behavior from the start. blk-mq apparently
intended to do this, but the code to do this was never wired up. Get rid
of the dead code and make it part of the sbitmap library.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-mq-tag.c

@@ -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;

block/blk-mq-tag.h

@@ -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,

lib/sbitmap.c

@@ -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,
@@ -211,6 +212,11 @@ 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_calc_wake_batch(depth);
 	atomic_set(&sbq->wake_index, 0);