blk-mq: move srcu from blk_mq_hw_ctx to request_queue

In case of BLK_MQ_F_BLOCKING, per-hctx srcu is used to protect dispatch
critical area. However, this srcu instance stays at the end of hctx, and
it often takes standalone cacheline, often cold.

Inside srcu_read_lock() and srcu_read_unlock(), WRITE is always done on
the indirect percpu variable which is allocated from heap instead of
being embedded, srcu->srcu_idx is read only in srcu_read_lock(). It
doesn't matter if srcu structure stays in hctx or request queue.

So switch to per-request-queue srcu for protecting dispatch, and this
way simplifies quiesce a lot, not mention quiesce is always done on the
request queue wide.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20211203131534.3668411-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 494da31..6a2c270 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -260,17 +260,9 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
  */
 void blk_mq_wait_quiesce_done(struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
-	bool rcu = false;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (hctx->flags & BLK_MQ_F_BLOCKING)
-			synchronize_srcu(hctx->srcu);
-		else
-			rcu = true;
-	}
-	if (rcu)
+	if (blk_queue_has_srcu(q))
+		synchronize_srcu(q->srcu);
+	else
 		synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done);
@@ -3400,20 +3392,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
-{
-	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
-
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
-			   __alignof__(struct blk_mq_hw_ctx)) !=
-		     sizeof(struct blk_mq_hw_ctx));
-
-	if (tag_set->flags & BLK_MQ_F_BLOCKING)
-		hw_ctx_size += sizeof(struct srcu_struct);
-
-	return hw_ctx_size;
-}
-
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -3451,7 +3429,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	struct blk_mq_hw_ctx *hctx;
 	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
 
-	hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+	hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node);
 	if (!hctx)
 		goto fail_alloc_hctx;
 
@@ -3493,8 +3471,6 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	if (!hctx->fq)
 		goto free_bitmap;
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		init_srcu_struct(hctx->srcu);
 	blk_mq_hctx_kobj_init(hctx);
 
 	return hctx;
@@ -3830,7 +3806,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node);
+	q = blk_alloc_queue(set->numa_node, set->flags & BLK_MQ_F_BLOCKING);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
 	q->queuedata = queuedata;
@@ -3979,6 +3955,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_has_srcu(q) !=
+			!!(set->flags & BLK_MQ_F_BLOCKING));
+
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;