bfq: calculate shallow depths at init time

It doesn't change, so don't put it in the per-IO hot path.
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

block/bfq-iosched.c

@@ -486,46 +486,6 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
 	}
 }
 
-/*
- * See the comments on bfq_limit_depth for the purpose of
- * the depths set in the function.
- */
-static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
-{
-	bfqd->sb_shift = bt->sb.shift;
-
-	/*
-	 * In-word depths if no bfq_queue is being weight-raised:
-	 * leaving 25% of tags only for sync reads.
-	 *
-	 * In next formulas, right-shift the value
-	 * (1U<<bfqd->sb_shift), instead of computing directly
-	 * (1U<<(bfqd->sb_shift - something)), to be robust against
-	 * any possible value of bfqd->sb_shift, without having to
-	 * limit 'something'.
-	 */
-	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
-	/*
-	 * no more than 75% of tags for sync writes (25% extra tags
-	 * w.r.t. async I/O, to prevent async I/O from starving sync
-	 * writes)
-	 */
-	bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
-
-	/*
-	 * In-word depths in case some bfq_queue is being weight-
-	 * raised: leaving ~63% of tags for sync reads. This is the
-	 * highest percentage for which, in our tests, application
-	 * start-up times didn't suffer from any regression due to tag
-	 * shortage.
-	 */
-	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
-	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
-}
-
 /*
  * Async I/O can easily starve sync I/O (both sync reads and sync
  * writes), by consuming all tags. Similarly, storms of sync writes,
@@ -535,18 +495,11 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
  */
 static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
 {
-	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
-	struct sbitmap_queue *bt;
 
 	if (op_is_sync(op) && !op_is_write(op))
 		return;
 
-	bt = &tags->bitmap_tags;
-
-	if (unlikely(bfqd->sb_shift != bt->sb.shift))
-		bfq_update_depths(bfqd, bt);
-
 	data->shallow_depth =
 		bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
 
@@ -5126,6 +5079,55 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
 	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
 }
 
+/*
+ * See the comments on bfq_limit_depth for the purpose of
+ * the depths set in the function.
+ */
+static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
+{
+	bfqd->sb_shift = bt->sb.shift;
+
+	/*
+	 * In-word depths if no bfq_queue is being weight-raised:
+	 * leaving 25% of tags only for sync reads.
+	 *
+	 * In next formulas, right-shift the value
+	 * (1U<<bfqd->sb_shift), instead of computing directly
+	 * (1U<<(bfqd->sb_shift - something)), to be robust against
+	 * any possible value of bfqd->sb_shift, without having to
+	 * limit 'something'.
+	 */
+	/* no more than 50% of tags for async I/O */
+	bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
+	/*
+	 * no more than 75% of tags for sync writes (25% extra tags
+	 * w.r.t. async I/O, to prevent async I/O from starving sync
+	 * writes)
+	 */
+	bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
+
+	/*
+	 * In-word depths in case some bfq_queue is being weight-
+	 * raised: leaving ~63% of tags for sync reads. This is the
+	 * highest percentage for which, in our tests, application
+	 * start-up times didn't suffer from any regression due to tag
+	 * shortage.
+	 */
+	/* no more than ~18% of tags for async I/O */
+	bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
+	/* no more than ~37% of tags for sync writes (~20% extra tags) */
+	bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct blk_mq_tags *tags = hctx->sched_tags;
+
+	bfq_update_depths(bfqd, &tags->bitmap_tags);
+	return 0;
+}
+
 static void bfq_exit_queue(struct elevator_queue *e)
 {
 	struct bfq_data *bfqd = e->elevator_data;
@@ -5547,6 +5549,7 @@ static struct elevator_type iosched_bfq_mq = {
 		.requests_merged	= bfq_requests_merged,
 		.request_merged		= bfq_request_merged,
 		.has_work		= bfq_has_work,
+		.init_hctx		= bfq_init_hctx,
 		.init_sched		= bfq_init_queue,
 		.exit_sched		= bfq_exit_queue,
 	},