[bug report]nvme0: Admin Cmd(0x6), I/O Error (sct 0x0 / sc 0x2) MORE DNR observed during blktests

[Jonathan Derrick]

On 4/5/2022 12:14 AM, Christoph Hellwig wrote:
> On Mon, Apr 04, 2022 at 02:30:12PM -0600, Keith Busch wrote:
>>> Eg, nvme0: blah blah command set not supported
>>
>> The new print in the completion handler is pretty generic. I don't think it can
>> readily tell the difference from a harmless error. Maybe pr_err is too high?
>>
>> Or maybe since enough people have been concerned about *this* specific
>> identify, maybe it should be restricted to 2.0 devices where it's mandatory. I
>> was reluctant to do that at first since the initial device I tested was 1.4,
>> but it was a prototype and we should be fine without the non-mdts limits
>> anyway.
> 
> What SCSI does is to add RQF_QUIET to all internal passthrough commands,
> and then skips printing the SCSI specific error messages in addition
> if that flag is set.
> 
> This would be the nvme version of that:
> 
> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
> index 7e07dd69262a7..9346cd4cf5820 100644
> --- a/drivers/nvme/host/core.c
> +++ b/drivers/nvme/host/core.c
> @@ -366,7 +366,8 @@ static inline void nvme_end_req(struct request *req)
>  {
>  	blk_status_t status = nvme_error_status(nvme_req(req)->status);
>  
> -	if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS))
> +	if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS &&
> +		     !(req->rq_flags & RQF_QUIET)))
>  		nvme_log_error(req);
>  	nvme_end_req_zoned(req);
>  	nvme_trace_bio_complete(req);
> @@ -648,6 +649,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
>  	cmd->common.flags &= ~NVME_CMD_SGL_ALL;
>  
>  	req->cmd_flags |= REQ_FAILFAST_DRIVER;
> +	req->rq_flags |= RQF_QUIET;
>  	if (req->mq_hctx->type == HCTX_TYPE_POLL)
>  		req->cmd_flags |= REQ_POLLED;
>  	nvme_clear_nvme_request(req);


That's good too.
How about this so it's limited to debug loglevels:

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f204c6f78b5b..871ad2421284 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -303,9 +303,10 @@ static void nvme_log_error(struct request *req)
 {
        struct nvme_ns *ns = req->q->queuedata;
        struct nvme_request *nr = nvme_req(req);
+       int level = req->rq_flags & RQF_QUIET ? KERN_DEBUG : KERN_ERR;

        if (ns) {
-               pr_err_ratelimited("%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
+               printk_ratelimited(level "%s: %s(0x%x) @ LBA %llu, %llu blocks, %s (sct 0x%x / sc 0x%x) %s%s\n",
                       ns->disk ? ns->disk->disk_name : "?",
                       nvme_get_opcode_str(nr->cmd->common.opcode),
                       nr->cmd->common.opcode,
@@ -319,7 +320,7 @@ static void nvme_log_error(struct request *req)
                return;
        }

-       pr_err_ratelimited("%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n",
+       printk_ratelimited(level "%s: %s(0x%x), %s (sct 0x%x / sc 0x%x) %s%s\n",
                           dev_name(nr->ctrl->device),
                           nvme_get_admin_opcode_str(nr->cmd->common.opcode),
                           nr->cmd->common.opcode,
@@ -651,6 +652,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
        cmd->common.flags &= ~NVME_CMD_SGL_ALL;

        req->cmd_flags |= REQ_FAILFAST_DRIVER;
+       req->rq_flags |= RQF_QUIET;
        if (req->mq_hctx->type == HCTX_TYPE_POLL)
                req->cmd_flags |= REQ_POLLED;
        nvme_clear_nvme_request(req);