block: optimise in irq bio put caching

When enlisting a bio into ->free_list_irq we protect the list by
disabling irqs. It's likely they're already disabled and performance of
local_irq_{save,restore}() is decent, but it's not zero cost.

Let's only use the irq cache when when we're serving a hard irq, which
allows to remove local_irq_{save,restore}(), and fall back to bio_free()
in all left cases.

Profiles indicate that the bio_put() cost is reduced by ~3.5 times
(1.76% -> 0.49%), and total throughput of a CPU bound benchmark improve
by around 1% (t/io_uring with high QD and several drives).

Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/36d207540b7046c653cc16e5ff08fe7234b19f81.1707314970.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>

block/bio.c

@@ -762,30 +762,31 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 	struct bio_alloc_cache *cache;
 
 	cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
-	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) {
-		put_cpu();
-		bio_free(bio);
-		return;
-	}
-
-	bio_uninit(bio);
+	if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX)
+		goto out_free;
 
 	if (in_task()) {
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list;
 		/* Not necessary but helps not to iopoll already freed bios */
 		bio->bi_bdev = NULL;
 		cache->free_list = bio;
 		cache->nr++;
-	} else {
-		unsigned long flags;
+	} else if (in_hardirq()) {
+		lockdep_assert_irqs_disabled();
 
-		local_irq_save(flags);
+		bio_uninit(bio);
 		bio->bi_next = cache->free_list_irq;
 		cache->free_list_irq = bio;
 		cache->nr_irq++;
-		local_irq_restore(flags);
+	} else {
+		goto out_free;
 	}
 	put_cpu();
+	return;
+out_free:
+	put_cpu();
+	bio_free(bio);
 }
 
 /**