blk-flush: count inflight flush_data requests

The flush state machine use a double list to link all inflight
flush_data requests, to avoid issuing separate post-flushes for
these flush_data requests which shared PREFLUSH.

So we can't reuse rq->queuelist, this is why we need rq->flush.list

In preparation of the next patch that reuse rq->queuelist for flush
state machine, we change the double linked list to unsigned long
counter, which count all inflight flush_data requests.

This is ok since we only need to know if there is any inflight
flush_data request, so unsigned long counter is good.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230717040058.3993930-4-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-flush.c b/block/blk-flush.c
index fdc489e0ea16257b1aa9a3d75265c3890e33f925..fedb39031647e088f94adcb668ce76117247dbee 100644 (file)
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -187,7 +187,8 @@ static void blk_flush_complete_seq(struct request *rq,
                break;
 
        case REQ_FSEQ_DATA:
-               list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
+               list_del_init(&rq->flush.list);
+               fq->flush_data_in_flight++;
                spin_lock(&q->requeue_lock);
                list_add(&rq->queuelist, &q->requeue_list);
                spin_unlock(&q->requeue_lock);
@@ -299,7 +300,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
                return;
 
        /* C2 and C3 */
-       if (!list_empty(&fq->flush_data_in_flight) &&
+       if (fq->flush_data_in_flight &&
            time_before(jiffies,
                        fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
                return;
@@ -374,6 +375,7 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq,
         * the comment in flush_end_io().
         */
        spin_lock_irqsave(&fq->mq_flush_lock, flags);
+       fq->flush_data_in_flight--;
        blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
        spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 
@@ -445,7 +447,7 @@ bool blk_insert_flush(struct request *rq)
                blk_rq_init_flush(rq);
                rq->flush.seq |= REQ_FSEQ_PREFLUSH;
                spin_lock_irq(&fq->mq_flush_lock);
-               list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
+               fq->flush_data_in_flight++;
                spin_unlock_irq(&fq->mq_flush_lock);
                return false;
        default:
@@ -496,7 +498,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
 
        INIT_LIST_HEAD(&fq->flush_queue[0]);
        INIT_LIST_HEAD(&fq->flush_queue[1]);
-       INIT_LIST_HEAD(&fq->flush_data_in_flight);
 
        return fq;
 

diff --git a/block/blk.h b/block/blk.h
index 608c5dcc516b55c992b62f0334bb5fa1abe07c62..686712e1383526f5f60cad822ac37305507240a3 100644 (file)
--- a/block/blk.h
+++ b/block/blk.h
@@ -15,15 +15,14 @@ struct elevator_type;
 extern struct dentry *blk_debugfs_root;
 
 struct blk_flush_queue {
+       spinlock_t              mq_flush_lock;
        unsigned int            flush_pending_idx:1;
        unsigned int            flush_running_idx:1;
        blk_status_t            rq_status;
        unsigned long           flush_pending_since;
        struct list_head        flush_queue[2];
-       struct list_head        flush_data_in_flight;
+       unsigned long           flush_data_in_flight;
        struct request          *flush_rq;
-
-       spinlock_t              mq_flush_lock;
 };
 
 bool is_flush_rq(struct request *req);