Revert "nvme: make keep-alive synchronous operation"

This reverts commit d06923670b5a5f609603d4a9fee4dec02d38de9c.

It was realized that the fix implemented to contain the race condition
among the keep alive task and the fabric shutdown code path in the commit
d06923670b5ia ("nvme: make keep-alive synchronous operation") is not
optimal. The reason being keep-alive runs under the workqueue and making
it synchronous would waste a workqueue context.
Furthermore, we later found that the above race condition is a regression
caused due to the changes implemented in commit a54a93d0e359 ("nvme: move
stopping keep-alive into nvme_uninit_ctrl()"). So we decided to revert the
commit d06923670b5a ("nvme: make keep-alive synchronous operation") and
then fix the regression.

Link: https://lore.kernel.org/all/196f4013-3bbf-43ff-98b4-9cb2a96c20c2@grimberg.me/
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7360e9c3acff014e9c24259f649084916575cf94..1221ebe399d7653baf3811d9948769fa014f3466 100644 (file)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1294,9 +1294,10 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
        queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
-static void nvme_keep_alive_finish(struct request *rq,
-               blk_status_t status, struct nvme_ctrl *ctrl)
+static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
+                                                blk_status_t status)
 {
+       struct nvme_ctrl *ctrl = rq->end_io_data;
        unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
        unsigned long delay = nvme_keep_alive_work_period(ctrl);
        enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
@@ -1313,17 +1314,20 @@ static void nvme_keep_alive_finish(struct request *rq,
                delay = 0;
        }
 
+       blk_mq_free_request(rq);
+
        if (status) {
                dev_err(ctrl->device,
                        "failed nvme_keep_alive_end_io error=%d\n",
                                status);
-               return;
+               return RQ_END_IO_NONE;
        }
 
        ctrl->ka_last_check_time = jiffies;
        ctrl->comp_seen = false;
        if (state == NVME_CTRL_LIVE || state == NVME_CTRL_CONNECTING)
                queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
+       return RQ_END_IO_NONE;
 }
 
 static void nvme_keep_alive_work(struct work_struct *work)
@@ -1332,7 +1336,6 @@ static void nvme_keep_alive_work(struct work_struct *work)
                        struct nvme_ctrl, ka_work);
        bool comp_seen = ctrl->comp_seen;
        struct request *rq;
-       blk_status_t status;
 
        ctrl->ka_last_check_time = jiffies;
 
@@ -1355,9 +1358,9 @@ static void nvme_keep_alive_work(struct work_struct *work)
        nvme_init_request(rq, &ctrl->ka_cmd);
 
        rq->timeout = ctrl->kato * HZ;
-       status = blk_execute_rq(rq, false);
-       nvme_keep_alive_finish(rq, status, ctrl);
-       blk_mq_free_request(rq);
+       rq->end_io = nvme_keep_alive_end_io;
+       rq->end_io_data = ctrl;
+       blk_execute_rq_nowait(rq, false);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)