[RFC for-next 3/4] block/bio: add pcpu caching for non-polling bio_put

[Pavel Begunkov <asml.silence@gmail.com>]

This patch extends REQ_ALLOC_CACHE to IRQ completions, whenever
currently it's only limited to iopoll. Instead of guarding the list with
irq toggling on alloc, which is expensive, it keeps an additional
irq-safe list from which bios are spliced in batches to ammortise
overhead. On the put side it toggles irqs, but in many cases they're
already disabled and so cheap.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/bio.c | 62 ++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 50 insertions(+), 12 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index ac16cc154476..75107dc27304 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -25,9 +25,15 @@
 #include "blk-rq-qos.h"
 #include "blk-cgroup.h"
 
+#define ALLOC_CACHE_THRESHOLD	16
+#define ALLOC_CACHE_SLACK	64
+#define ALLOC_CACHE_MAX		512
+
 struct bio_alloc_cache {
 	struct bio		*free_list;
+	struct bio		*free_list_irq;
 	unsigned int		nr;
+	unsigned int		nr_irq;
 };
 
 static struct biovec_slab {
@@ -408,6 +414,22 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	queue_work(bs->rescue_workqueue, &bs->rescue_work);
 }
 
+static void bio_alloc_irq_cache_splice(struct bio_alloc_cache *cache)
+{
+	unsigned long flags;
+
+	/* cache->free_list must be empty */
+	if (WARN_ON_ONCE(cache->free_list))
+		return;
+
+	local_irq_save(flags);
+	cache->free_list = cache->free_list_irq;
+	cache->free_list_irq = NULL;
+	cache->nr += cache->nr_irq;
+	cache->nr_irq = 0;
+	local_irq_restore(flags);
+}
+
 static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
 		unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp,
 		struct bio_set *bs)
@@ -416,9 +438,13 @@ static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
 	struct bio *bio;
 
 	cache = per_cpu_ptr(bs->cache, get_cpu());
-	if (!cache->free_list) {
-		put_cpu();
-		return NULL;
+	if (!cache->free_list &&
+	    READ_ONCE(cache->nr_irq) >= ALLOC_CACHE_THRESHOLD) {
+		bio_alloc_irq_cache_splice(cache);
+		if (!cache->free_list) {
+			put_cpu();
+			return NULL;
+		}
 	}
 	bio = cache->free_list;
 	cache->free_list = bio->bi_next;
@@ -676,11 +702,8 @@ void guard_bio_eod(struct bio *bio)
 	bio_truncate(bio, maxsector << 9);
 }
 
-#define ALLOC_CACHE_MAX		512
-#define ALLOC_CACHE_SLACK	 64
-
-static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
-				  unsigned int nr)
+static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache,
+				   unsigned int nr)
 {
 	unsigned int i = 0;
 	struct bio *bio;
@@ -692,6 +715,17 @@ static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
 		if (++i == nr)
 			break;
 	}
+	return i;
+}
+
+static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
+				  unsigned int nr)
+{
+	nr -= __bio_alloc_cache_prune(cache, nr);
+	if (!READ_ONCE(cache->free_list)) {
+		bio_alloc_irq_cache_splice(cache);
+		__bio_alloc_cache_prune(cache, nr);
+	}
 }
 
 static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node)
@@ -728,6 +762,7 @@ static void bio_alloc_cache_destroy(struct bio_set *bs)
 static inline void bio_put_percpu_cache(struct bio *bio)
 {
 	struct bio_alloc_cache *cache;
+	unsigned long flags;
 
 	cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
 	bio_uninit(bio);
@@ -737,12 +772,15 @@ static inline void bio_put_percpu_cache(struct bio *bio)
 		cache->free_list = bio;
 		cache->nr++;
 	} else {
-		put_cpu();
-		bio_free(bio);
-		return;
+		local_irq_save(flags);
+		bio->bi_next = cache->free_list_irq;
+		cache->free_list_irq = bio;
+		cache->nr_irq++;
+		local_irq_restore(flags);
 	}
 
-	if (cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
+	if (READ_ONCE(cache->nr_irq) + cache->nr >
+	    ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
 		bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK);
 	put_cpu();
 }
-- 
2.38.0