sbitmap: add __sbitmap_queue_get_batch()

The block layer tag allocation batching still calls into sbitmap to get
each tag, but we can improve on that. Add __sbitmap_queue_get_batch(),
which returns a mask of tags all at once, along with an offset for
those tags.

An example return would be 0xff, where bits 0..7 are set, with
tag_offset == 128. The valid tags in this case would be 128..135.

A batch is specific to an individual sbitmap_map, hence it cannot be
larger than that. The requested number of tags is automatically reduced
to the max that can be satisfied with a single map.

On failure, 0 is returned. Caller should fall back to single tag
allocation at that point/

Signed-off-by: Jens Axboe <axboe@kernel.dk>

include/linux/sbitmap.h

@@ -426,6 +426,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth);
  */
 int __sbitmap_queue_get(struct sbitmap_queue *sbq);
 
+/**
+ * __sbitmap_queue_get_batch() - Try to allocate a batch of free bits
+ * @sbq: Bitmap queue to allocate from.
+ * @nr_tags: number of tags requested
+ * @offset: offset to add to returned bits
+ *
+ * Return: Mask of allocated tags, 0 if none are found. Each tag allocated is
+ * a bit in the mask returned, and the caller must add @offset to the value to
+ * get the absolute tag value.
+ */
+unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
+					unsigned int *offset);
+
 /**
  * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
  * sbitmap_queue, limiting the depth used from each word, with preemption

lib/sbitmap.c

@@ -489,6 +489,57 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq)
 }
 EXPORT_SYMBOL_GPL(__sbitmap_queue_get);
 
+unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
+					unsigned int *offset)
+{
+	struct sbitmap *sb = &sbq->sb;
+	unsigned int hint, depth;
+	unsigned long index, nr;
+	int i;
+
+	if (unlikely(sb->round_robin))
+		return 0;
+
+	depth = READ_ONCE(sb->depth);
+	hint = update_alloc_hint_before_get(sb, depth);
+
+	index = SB_NR_TO_INDEX(sb, hint);
+
+	for (i = 0; i < sb->map_nr; i++) {
+		struct sbitmap_word *map = &sb->map[index];
+		unsigned long get_mask;
+
+		sbitmap_deferred_clear(map);
+		if (map->word == (1UL << (map->depth - 1)) - 1)
+			continue;
+
+		nr = find_first_zero_bit(&map->word, map->depth);
+		if (nr + nr_tags <= map->depth) {
+			atomic_long_t *ptr = (atomic_long_t *) &map->word;
+			int map_tags = min_t(int, nr_tags, map->depth);
+			unsigned long val, ret;
+
+			get_mask = ((1UL << map_tags) - 1) << nr;
+			do {
+				val = READ_ONCE(map->word);
+				ret = atomic_long_cmpxchg(ptr, val, get_mask | val);
+			} while (ret != val);
+			get_mask = (get_mask & ~ret) >> nr;
+			if (get_mask) {
+				*offset = nr + (index << sb->shift);
+				update_alloc_hint_after_get(sb, depth, hint,
+							*offset + map_tags - 1);
+				return get_mask;
+			}
+		}
+		/* Jump to next index. */
+		if (++index >= sb->map_nr)
+			index = 0;
+	}
+
+	return 0;
+}
+
 int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
 				unsigned int shallow_depth)
 {