On 10/12/21 11:17 AM, Jens Axboe wrote:

+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)
  {

How does replacing the sbitmap_queue_clear() implementation by calling 
sbitmap_queue_clear_batch() affect performance? I'm wondering whether it 
is possible to prevent code duplication without affecting performance 
negatively.

Thanks,

Bart.