From: Jens Axboe axboe@kernel.dk
commit 05b79413946d8b2b58999ea1ae844b6fc3c54f61 upstream
This reverts commit 358a3a6bccb74da9d63a26b2dd5f09f1e9970e0b.
We have cases that aren't covered 100% in the drivers, so for now we have to retain the shared tag restart loops.
Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Jack Wang jinpu.wang@profitbricks.com --- block/blk-mq-sched.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 74 insertions(+), 4 deletions(-)
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 01a43fed6b8c..6f4bdb8209f7 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -68,17 +68,25 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); }
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) +static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) { if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - return; + return false;
- clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + if (hctx->flags & BLK_MQ_F_TAG_SHARED) { + struct request_queue *q = hctx->queue; + + if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) + atomic_dec(&q->shared_hctx_restart); + } else + clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
if (blk_mq_hctx_has_pending(hctx)) { blk_mq_run_hw_queue(hctx, true); - return; + return true; } + + return false; }
/* @@ -362,6 +370,68 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, return false; }
+/** + * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list + * @pos: loop cursor. + * @skip: the list element that will not be examined. Iteration starts at + * @skip->next. + * @head: head of the list to examine. This list must have at least one + * element, namely @skip. + * @member: name of the list_head structure within typeof(*pos). + */ +#define list_for_each_entry_rcu_rr(pos, skip, head, member) \ + for ((pos) = (skip); \ + (pos = (pos)->member.next != (head) ? list_entry_rcu( \ + (pos)->member.next, typeof(*pos), member) : \ + list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \ + (pos) != (skip); ) + +/* + * Called after a driver tag has been freed to check whether a hctx needs to + * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware + * queues in a round-robin fashion if the tag set of @hctx is shared with other + * hardware queues. + */ +void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx) +{ + struct blk_mq_tags *const tags = hctx->tags; + struct blk_mq_tag_set *const set = hctx->queue->tag_set; + struct request_queue *const queue = hctx->queue, *q; + struct blk_mq_hw_ctx *hctx2; + unsigned int i, j; + + if (set->flags & BLK_MQ_F_TAG_SHARED) { + /* + * If this is 0, then we know that no hardware queues + * have RESTART marked. We're done. + */ + if (!atomic_read(&queue->shared_hctx_restart)) + return; + + rcu_read_lock(); + list_for_each_entry_rcu_rr(q, queue, &set->tag_list, + tag_set_list) { + queue_for_each_hw_ctx(q, hctx2, i) + if (hctx2->tags == tags && + blk_mq_sched_restart_hctx(hctx2)) + goto done; + } + j = hctx->queue_num + 1; + for (i = 0; i < queue->nr_hw_queues; i++, j++) { + if (j == queue->nr_hw_queues) + j = 0; + hctx2 = queue->queue_hw_ctx[j]; + if (hctx2->tags == tags && + blk_mq_sched_restart_hctx(hctx2)) + break; + } +done: + rcu_read_unlock(); + } else { + blk_mq_sched_restart_hctx(hctx); + } +} + void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async, bool can_block) {