This patch aims to enable batch allocation of sufficient tags after
batch IO submission with plug mechanism, thereby avoiding the need for
frequent individual requests when the initial allocation is
insufficient.
-----------------------------------------------------------
HW:
16 CPUs/16 poll queues
Disk: Samsung PM9A3 Gen4 3.84T

CMD:
[global]
ioengine=io_uring
group_reporting=1
time_based=1
runtime=1m
refill_buffers=1
norandommap=1
randrepeat=0
fixedbufs=1
registerfiles=1
rw=randread
iodepth=128
iodepth_batch_submit=32
iodepth_batch_complete_min=32
iodepth_batch_complete_max=128
iodepth_low=32
bs=4k
numjobs=1
direct=1
hipri=1

[job1]
filename=/dev/nvme0n1
name=batch_test
------------------------------------------------------------
Perf:
base code: __blk_mq_alloc_requests() 1.47%
patch: __blk_mq_alloc_requests() 0.78%
------------------------------------------------------------

---
changes since v1:
- Modify multiple batch registrations into a single loop to achieve
  the batch quantity

changes since v2:
- Modify the call location of remainder handling
- Refactoring sbitmap cleanup time

changes since v3:
- Add handle operation in loop
- Add helper sbitmap_find_bits_in_word

changes since v4:
- Split blk-mq.c changes from sbitmap

changes since v5:
- Add workload with perf
- Modify over-counting bug

Signed-off-by: hexue <xue01.he@samsung.com>
---
 block/blk-mq.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d626d32f6e57..9e6fca1b5fb7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -467,26 +467,31 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 	unsigned long tag_mask;
 	int i, nr = 0;
 
-	tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
-	if (unlikely(!tag_mask))
-		return NULL;
+	do {
+		tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
+		if (unlikely(!tag_mask)) {
+			if (nr == 0)
+				return NULL;
+			break;
+		}
+		tags = blk_mq_tags_from_data(data);
+		for (i = 0; tag_mask; i++) {
+			if (!(tag_mask & (1UL << i)))
+				continue;
+			tag = tag_offset + i;
+			prefetch(tags->static_rqs[tag]);
+			tag_mask &= ~(1UL << i);
+			rq = blk_mq_rq_ctx_init(data, tags, tag);
+			rq_list_add_head(data->cached_rqs, rq);
+			data->nr_tags--;
+			nr++;
+		}
+	} while (data->nr_tags);
 
-	tags = blk_mq_tags_from_data(data);
-	for (i = 0; tag_mask; i++) {
-		if (!(tag_mask & (1UL << i)))
-			continue;
-		tag = tag_offset + i;
-		prefetch(tags->static_rqs[tag]);
-		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag);
-		rq_list_add_head(data->cached_rqs, rq);
-		nr++;
-	}
-	if (!(data->rq_flags & RQF_SCHED_TAGS))
-		blk_mq_add_active_requests(data->hctx, nr);
 	/* caller already holds a reference, add for remainder */
 	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
-	data->nr_tags -= nr;
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
+		blk_mq_add_active_requests(data->hctx, nr);
 
 	return rq_list_pop(data->cached_rqs);
 }
-- 
2.34.1