[PATCH v4 4/5] nvme-rdma: avoid IO error for nvme native multipath

[Chao Leng]

On 2021/1/29 9:35, Sagi Grimberg wrote:
> 
>>>> @@ -2084,8 +2085,10 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
>>>>       err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
>>>>               req->mr ? &req->reg_wr.wr : NULL);
>>>> -    if (unlikely(err))
>>>> +    if (unlikely(err)) {
>>>> +        driver_error = true;
>>>>           goto err_unmap;
>>>
>>> Why not just call set the status and call nvme_rdma_complete_rq and
>>> return here?
>> If the err is ENOMEM or EAGAIN, I am not sure the err must be a
>> path-related error for all HBA drivers. So reused the error check code.
>> I think it would be more reasonable to assume any errors returned by HBA
>> driver as path-related errors.
>> If you think so, I will modify it in next patch version.
> 
> Meant to do that only for -EIO. We should absolutely not do any of this
> for stuff like EINVAL, EOPNOTSUPP, EPERM or any strange error that may
> return due to a bug or anything like that.
ok, please review again, thank you.
---
  drivers/nvme/host/rdma.c | 9 +++++++--
  1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b7ce4f221d99..66b697461bd9 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2084,8 +2084,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,

         err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
                         req->mr ? &req->reg_wr.wr : NULL);
-       if (unlikely(err))
+       if (unlikely(err)) {
+               if (err == -EIO) {
+                       nvme_complete_failed_rq(rq, NVME_SC_HOST_PATH_ERROR);
+                       err = 0;
+               }
                 goto err_unmap;
+       }

         return BLK_STS_OK;

@@ -2094,7 +2099,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
  err:
         if (err == -ENOMEM || err == -EAGAIN)
                 ret = BLK_STS_RESOURCE;
-       else
+       else if (err)
                 ret = BLK_STS_IOERR;
         nvme_cleanup_cmd(rq);
  unmap_qe:
-- 
> .