* Once while executing DATA and again after the whole sequence is
* complete. The first completion updates the contained bio but doesn't
* finish it so that the bio submitter is notified only after the whole
- * sequence is complete. This is implemented by testing REQ_FLUSH_SEQ in
+ * sequence is complete. This is implemented by testing RQF_FLUSH_SEQ in
* req_bio_endio().
*
* The above peculiarity requires that each FLUSH/FUA request has only one
rq->bio = rq->biotail;
/* make @rq a normal request */
- rq->cmd_flags &= ~REQ_FLUSH_SEQ;
+ rq->rq_flags &= ~RQF_FLUSH_SEQ;
rq->end_io = rq->flush.saved_end_io;
}
static bool blk_flush_queue_rq(struct request *rq, bool add_front)
{
if (rq->q->mq_ops) {
- struct request_queue *q = rq->q;
-
- blk_mq_add_to_requeue_list(rq, add_front);
- blk_mq_kick_requeue_list(q);
+ blk_mq_add_to_requeue_list(rq, add_front, true);
return false;
} else {
if (add_front)
/* release the tag's ownership to the req cloned from */
spin_lock_irqsave(&fq->mq_flush_lock, flags);
- hctx = q->mq_ops->map_queue(q, flush_rq->mq_ctx->cpu);
+ hctx = blk_mq_map_queue(q, flush_rq->mq_ctx->cpu);
blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
flush_rq->tag = -1;
}
flush_rq->tag = first_rq->tag;
fq->orig_rq = first_rq;
- hctx = q->mq_ops->map_queue(q, first_rq->mq_ctx->cpu);
+ hctx = blk_mq_map_queue(q, first_rq->mq_ctx->cpu);
blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
}
flush_rq->cmd_type = REQ_TYPE_FS;
- req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
+ flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
+ flush_rq->rq_flags |= RQF_FLUSH_SEQ;
flush_rq->rq_disk = first_rq->rq_disk;
flush_rq->end_io = flush_end_io;
struct request_queue *q = rq->q;
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
+ /*
+ * Updating q->in_flight[] here for making this tag usable
+ * early. Because in blk_queue_start_tag(),
+ * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and
+ * reserve tags for sync I/O.
+ *
+ * More importantly this way can avoid the following I/O
+ * deadlock:
+ *
+ * - suppose there are 40 fua requests comming to flush queue
+ * and queue depth is 31
+ * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc
+ * tag for async I/O any more
+ * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT
+ * and flush_data_end_io() is called
+ * - the other rqs still can't go ahead if not updating
+ * q->in_flight[BLK_RW_ASYNC] here, meantime these rqs
+ * are held in flush data queue and make no progress of
+ * handling post flush rq
+ * - only after the post flush rq is handled, all these rqs
+ * can be completed
+ */
+
+ elv_completed_request(q, rq);
+
+ /* for avoiding double accounting */
+ rq->rq_flags &= ~RQF_STARTED;
+
/*
* After populating an empty queue, kick it to avoid stall. Read
* the comment in flush_end_io().
unsigned long flags;
struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
+ hctx = blk_mq_map_queue(q, ctx->cpu);
/*
* After populating an empty queue, kick it to avoid stall. Read
if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
rq->cmd_flags &= ~REQ_FUA;
+ /*
+ * REQ_PREFLUSH|REQ_FUA implies REQ_SYNC, so if we clear any
+ * of those flags, we have to set REQ_SYNC to avoid skewing
+ * the request accounting.
+ */
+ rq->cmd_flags |= REQ_SYNC;
+
/*
* An empty flush handed down from a stacking driver may
* translate into nothing if the underlying device does not
if ((policy & REQ_FSEQ_DATA) &&
!(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
if (q->mq_ops) {
- blk_mq_insert_request(rq, false, false, true);
+ blk_mq_insert_request(rq, false, true, false);
} else
list_add_tail(&rq->queuelist, &q->queue_head);
return;
*/
memset(&rq->flush, 0, sizeof(rq->flush));
INIT_LIST_HEAD(&rq->flush.list);
- rq->cmd_flags |= REQ_FLUSH_SEQ;
+ rq->rq_flags |= RQF_FLUSH_SEQ;
rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
if (q->mq_ops) {
rq->end_io = mq_flush_data_end_io;
bio = bio_alloc(gfp_mask, 0);
bio->bi_bdev = bdev;
- bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+ bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
ret = submit_bio_wait(bio);