lib/sbitmap: convert shallow_depth from one word to the whole sbitmap

[ Upstream commit 42e6c6ce03 ]

Currently elevators will record internal 'async_depth' to throttle
asynchronous requests, and they both calculate shallow_dpeth based on
sb->shift, with the respect that sb->shift is the available tags in one
word.

However, sb->shift is not the availbale tags in the last word, see
__map_depth:

if (index == sb->map_nr - 1)
  return sb->depth - (index << sb->shift);

For consequence, if the last word is used, more tags can be get than
expected, for example, assume nr_requests=256 and there are four words,
in the worst case if user set nr_requests=32, then the first word is
the last word, and still use bits per word, which is 64, to calculate
async_depth is wrong.

One the ohter hand, due to cgroup qos, bfq can allow only one request
to be allocated, and set shallow_dpeth=1 will still allow the number
of words request to be allocated.

Fix this problems by using shallow_depth to the whole sbitmap instead
of per word, also change kyber, mq-deadline and bfq to follow this,
a new helper __map_depth_with_shallow() is introduced to calculate
available bits in each word.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250807032413.1469456-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>

block/bfq-iosched.c

@@ -701,17 +701,13 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
 	struct bfq_io_cq *bic = bfq_bic_lookup(data->q);
-	int depth;
+	unsigned int limit, act_idx;
-	unsigned limit = data->q->nr_requests;
-	unsigned int act_idx;
 
 	/* Sync reads have full depth available */
-	if (op_is_sync(opf) && !op_is_write(opf)) {
+	if (op_is_sync(opf) && !op_is_write(opf))
-		depth = 0;
+		limit = data->q->nr_requests;
-	} else {
+	else
-		depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
+		limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
-		limit = (limit * depth) >> bfqd->full_depth_shift;
-	}
 
 	for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) {
 		/* Fast path to check if bfqq is already allocated. */
@@ -725,14 +721,16 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 		 * available requests and thus starve other entities.
 		 */
 		if (bfqq_request_over_limit(bfqd, bic, opf, act_idx, limit)) {
-			depth = 1;
+			limit = 1;
 			break;
 		}
 	}
+
 	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
-		__func__, bfqd->wr_busy_queues, op_is_sync(opf), depth);
+		__func__, bfqd->wr_busy_queues, op_is_sync(opf), limit);
-	if (depth)
+
-		data->shallow_depth = depth;
+	if (limit < data->q->nr_requests)
+		data->shallow_depth = limit;
 }
 
 static struct bfq_queue *
@@ -7128,9 +7126,8 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
  */
 static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 {
-	unsigned int depth = 1U << bt->sb.shift;
+	unsigned int nr_requests = bfqd->queue->nr_requests;
 
-	bfqd->full_depth_shift = bt->sb.shift;
 	/*
 	 * In-word depths if no bfq_queue is being weight-raised:
 	 * leaving 25% of tags only for sync reads.
@@ -7142,13 +7139,13 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 	 * limit 'something'.
 	 */
 	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max(depth >> 1, 1U);
+	bfqd->async_depths[0][0] = max(nr_requests >> 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((depth * 3) >> 2, 1U);
+	bfqd->async_depths[0][1] = max((nr_requests * 3) >> 2, 1U);
 
 	/*
 	 * In-word depths in case some bfq_queue is being weight-
@@ -7158,9 +7155,9 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 	 * shortage.
 	 */
 	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max((depth * 3) >> 4, 1U);
+	bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U);
 	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max((depth * 6) >> 4, 1U);
+	bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U);
 }
 
 static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)

block/bfq-iosched.h

@@ -813,8 +813,7 @@ struct bfq_data {
 	 * Depth limits used in bfq_limit_depth (see comments on the
 	 * function)
 	 */
-	unsigned int word_depths[2][2];
+	unsigned int async_depths[2][2];
-	unsigned int full_depth_shift;
 
 	/*
 	 * Number of independent actuators. This is equal to 1 in

block/kyber-iosched.c

@@ -157,10 +157,7 @@ struct kyber_queue_data {
 	 */
 	struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS];
 
-	/*
+	/* Number of allowed async requests. */
-	 * Async request percentage, converted to per-word depth for
-	 * sbitmap_get_shallow().
-	 */
 	unsigned int async_depth;
 
 	struct kyber_cpu_latency __percpu *cpu_latency;
@@ -454,10 +451,8 @@ static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx)
 {
 	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
-	unsigned int shift = tags->bitmap_tags.sb.shift;
-
-	kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
 
+	kqd->async_depth = hctx->queue->nr_requests * KYBER_ASYNC_PERCENT / 100U;
 	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth);
 }
 

block/mq-deadline.c

@@ -487,20 +487,6 @@ unlock:
 	return rq;
 }
 
-/*
- * 'depth' is a number in the range 1..INT_MAX representing a number of
- * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
- * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
- * Values larger than q->nr_requests have the same effect as q->nr_requests.
- */
-static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
-{
-	struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
-	const unsigned int nrr = hctx->queue->nr_requests;
-
-	return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
-}
-
 /*
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
@@ -517,7 +503,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	 * Throttle asynchronous requests and writes such that these requests
 	 * do not block the allocation of synchronous requests.
 	 */
-	data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
+	data->shallow_depth = dd->async_depth;
 }
 
 /* Called by blk_mq_update_nr_requests(). */

include/linux/sbitmap.h

@@ -213,12 +213,12 @@ 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.
- * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * @shallow_depth: The maximum number of bits to allocate from the bitmap.
  *
  * This rather specific operation allows for having multiple users with
  * different allocation limits. E.g., there can be a high-priority class that
  * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
- * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
+ * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority
  * class can only allocate half of the total bits in the bitmap, preventing it
  * from starving out the high-priority class.
  *
@@ -478,7 +478,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
  * sbitmap_queue, limiting the depth used from each word, with preemption
  * already disabled.
  * @sbq: Bitmap queue to allocate from.
- * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * @shallow_depth: The maximum number of bits to allocate from the queue.
  * See sbitmap_get_shallow().
  *
  * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after

lib/sbitmap.c

@@ -208,8 +208,28 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
 	return nr;
 }
 
+static unsigned int __map_depth_with_shallow(const struct sbitmap *sb,
+					     int index,
+					     unsigned int shallow_depth)
+{
+	u64 shallow_word_depth;
+	unsigned int word_depth, reminder;
+
+	word_depth = __map_depth(sb, index);
+	if (shallow_depth >= sb->depth)
+		return word_depth;
+
+	shallow_word_depth = word_depth * shallow_depth;
+	reminder = do_div(shallow_word_depth, sb->depth);
+
+	if (reminder >= (index + 1) * word_depth)
+		shallow_word_depth++;
+
+	return (unsigned int)shallow_word_depth;
+}
+
 static int sbitmap_find_bit(struct sbitmap *sb,
-			    unsigned int depth,
+			    unsigned int shallow_depth,
 			    unsigned int index,
 			    unsigned int alloc_hint,
 			    bool wrap)
@@ -218,12 +238,12 @@ static int sbitmap_find_bit(struct sbitmap *sb,
 	int nr = -1;
 
 	for (i = 0; i < sb->map_nr; i++) {
-		nr = sbitmap_find_bit_in_word(&sb->map[index],
+		unsigned int depth = __map_depth_with_shallow(sb, index,
-					      min_t(unsigned int,
+							      shallow_depth);
-						    __map_depth(sb, index),
-						    depth),
-					      alloc_hint, wrap);
 
+		if (depth)
+			nr = sbitmap_find_bit_in_word(&sb->map[index], depth,
+						      alloc_hint, wrap);
 		if (nr != -1) {
 			nr += index << sb->shift;
 			break;
@@ -406,27 +426,9 @@ EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
 static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
 					unsigned int depth)
 {
-	unsigned int wake_batch;
+	return clamp_t(unsigned int,
-	unsigned int shallow_depth;
+		       min(depth, sbq->min_shallow_depth) / SBQ_WAIT_QUEUES,
-
+		       1, SBQ_WAKE_BATCH);
-	/*
-	 * Each full word of the bitmap has bits_per_word bits, and there might
-	 * be a partial word. There are depth / bits_per_word full words and
-	 * depth % bits_per_word bits left over. In bitwise arithmetic:
-	 *
-	 * bits_per_word = 1 << shift
-	 * depth / bits_per_word = depth >> shift
-	 * depth % bits_per_word = depth & ((1 << shift) - 1)
-	 *
-	 * Each word can be limited to sbq->min_shallow_depth bits.
-	 */
-	shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
-	depth = ((depth >> sbq->sb.shift) * shallow_depth +
-		 min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
-	wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
-			     SBQ_WAKE_BATCH);
-
-	return wake_batch;
 }
 
 int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,