Merge tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - mq-deadline accounting improvements (Bart)

 - blk-wbt timer fix (Andrea)

 - Untangle the block layer includes (Christoph)

 - Rework the poll support to be bio based, which will enable adding
   support for polling for bio based drivers (Christoph)

 - Block layer core support for multi-actuator drives (Damien)

 - blk-crypto improvements (Eric)

 - Batched tag allocation support (me)

 - Request completion batching support (me)

 - Plugging improvements (me)

 - Shared tag set improvements (John)

 - Concurrent queue quiesce support (Ming)

 - Cache bdev in ->private_data for block devices (Pavel)

 - bdev dio improvements (Pavel)

 - Block device invalidation and block size improvements (Xie)

 - Various cleanups, fixes, and improvements (Christoph, Jackie,
   Masahira, Tejun, Yu, Pavel, Zheng, me)

* tag 'for-5.16/block-2021-10-29' of git://git.kernel.dk/linux-block: (174 commits)
  blk-mq-debugfs: Show active requests per queue for shared tags
  block: improve readability of blk_mq_end_request_batch()
  virtio-blk: Use blk_validate_block_size() to validate block size
  loop: Use blk_validate_block_size() to validate block size
  nbd: Use blk_validate_block_size() to validate block size
  block: Add a helper to validate the block size
  block: re-flow blk_mq_rq_ctx_init()
  block: prefetch request to be initialized
  block: pass in blk_mq_tags to blk_mq_rq_ctx_init()
  block: add rq_flags to struct blk_mq_alloc_data
  block: add async version of bio_set_polled
  block: kill DIO_MULTI_BIO
  block: kill unused polling bits in __blkdev_direct_IO()
  block: avoid extra iter advance with async iocb
  block: Add independent access ranges support
  blk-mq: don't issue request directly in case that current is to be blocked
  sbitmap: silence data race warning
  blk-cgroup: synchronize blkg creation against policy deactivation
  block: refactor bio_iov_bvec_set()
  block: add single bio async direct IO helper
  ...

2 files changed, 93 insertions, 3 deletions

diff --git a/lib/random32.c b/lib/random32.c
index 4d0e05e471d7..a57a0e18819d 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -39,6 +39,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 #include <trace/events/random.h>
 
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index b25db9be938a..2709ab825499 100644
--- a/lib/sbitmap.c
+++ b/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)
 {
@@ -577,6 +628,46 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
 
+static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag)
+{
+	if (likely(!sb->round_robin && tag < sb->depth))
+		data_race(*per_cpu_ptr(sb->alloc_hint, cpu) = tag);
+}
+
+void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
+				int *tags, int nr_tags)
+{
+	struct sbitmap *sb = &sbq->sb;
+	unsigned long *addr = NULL;
+	unsigned long mask = 0;
+	int i;
+
+	smp_mb__before_atomic();
+	for (i = 0; i < nr_tags; i++) {
+		const int tag = tags[i] - offset;
+		unsigned long *this_addr;
+
+		/* since we're clearing a batch, skip the deferred map */
+		this_addr = &sb->map[SB_NR_TO_INDEX(sb, tag)].word;
+		if (!addr) {
+			addr = this_addr;
+		} else if (addr != this_addr) {
+			atomic_long_andnot(mask, (atomic_long_t *) addr);
+			mask = 0;
+			addr = this_addr;
+		}
+		mask |= (1UL << SB_NR_TO_BIT(sb, tag));
+	}
+
+	if (mask)
+		atomic_long_andnot(mask, (atomic_long_t *) addr);
+
+	smp_mb__after_atomic();
+	sbitmap_queue_wake_up(sbq);
+	sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(),
+					tags[nr_tags - 1] - offset);
+}
+
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 			 unsigned int cpu)
 {
@@ -601,9 +692,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 	 */
 	smp_mb__after_atomic();
 	sbitmap_queue_wake_up(sbq);
-
-	if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth))
-		*per_cpu_ptr(sbq->sb.alloc_hint, cpu) = nr;
+	sbitmap_update_cpu_hint(&sbq->sb, cpu, nr);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_clear);