From: sagi@grimberg.me (Sagi Grimberg)
Subject: [PATCH v3 6/7] nvme-fc: Fail transport errors with NVME_SC_HOST_PATH
Date: Thu, 8 Aug 2019 13:53:24 -0700 [thread overview]
Message-ID: <20190808205325.24036-7-sagi@grimberg.me> (raw)
In-Reply-To: <20190808205325.24036-1-sagi@grimberg.me>
From: James Smart <james.smart@broadcom.com>
NVME_SC_INTERNAL should indicate an internal controller errors
and not host transport errors. These errors will propagate to
upper layers (essentially nvme core) and be interpereted as
transport errors which should not be taken into account for
namespace state or condition.
Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
---
drivers/nvme/host/fc.c | 37 ++++++++++++++++++++++++++++++-------
1 file changed, 30 insertions(+), 7 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 3f3725d1eca1..c289f46f6d13 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1608,9 +1608,13 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
sizeof(op->rsp_iu), DMA_FROM_DEVICE);
if (opstate == FCPOP_STATE_ABORTED)
- status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
- else if (freq->status)
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ else if (freq->status) {
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to lldd error %d\n",
+ ctrl->cnum, freq->status);
+ }
/*
* For the linux implementation, if we have an unsuccesful
@@ -1637,8 +1641,13 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
* no payload in the CQE by the transport.
*/
if (freq->transferred_length !=
- be32_to_cpu(op->cmd_iu.data_len)) {
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ be32_to_cpu(op->cmd_iu.data_len)) {
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to bad transfer "
+ "length: %d vs expected %d\n",
+ ctrl->cnum, freq->transferred_length,
+ be32_to_cpu(op->cmd_iu.data_len));
goto done;
}
result.u64 = 0;
@@ -1655,7 +1664,17 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
freq->transferred_length ||
op->rsp_iu.status_code ||
sqe->common.command_id != cqe->command_id)) {
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to bad NVMe_ERSP: "
+ "iu len %d, xfr len %d vs %d, status code "
+ "%d, cmdid %d vs %d\n",
+ ctrl->cnum, be16_to_cpu(op->rsp_iu.iu_len),
+ be32_to_cpu(op->rsp_iu.xfrd_len),
+ freq->transferred_length,
+ op->rsp_iu.status_code,
+ sqe->common.command_id,
+ cqe->command_id);
goto done;
}
result = cqe->result;
@@ -1663,7 +1682,11 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
break;
default:
- status = cpu_to_le16(NVME_SC_INTERNAL << 1);
+ status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: io failed due to odd NVMe_xRSP iu "
+ "len %d\n",
+ ctrl->cnum, freq->rcv_rsplen);
goto done;
}
--
2.17.1
next prev parent reply other threads:[~2019-08-08 20:53 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-08 20:53 [PATCH v3 0/7] nvme controller reset and namespace scan work race conditions Sagi Grimberg
2019-08-08 20:53 ` [PATCH v3 1/7] nvme: fail cancelled commands with NVME_SC_HOST_PATH_ERROR Sagi Grimberg
2019-08-10 11:59 ` Hannes Reinecke
2019-08-08 20:53 ` [PATCH v3 2/7] nvme: return nvme_error_status for sync commands failure Sagi Grimberg
2019-08-10 12:06 ` Hannes Reinecke
2019-08-08 20:53 ` [PATCH v3 3/7] nvme: make nvme_identify_ns propagate errors back Sagi Grimberg
2019-08-08 21:18 ` Keith Busch
2019-08-08 23:22 ` Sagi Grimberg
2019-08-10 12:09 ` Hannes Reinecke
2019-08-08 20:53 ` [PATCH v3 4/7] nvme: make nvme_report_ns_ids propagate error back Sagi Grimberg
2019-08-10 12:10 ` Hannes Reinecke
2019-08-08 20:53 ` [PATCH v3 5/7] nvme-tcp: fail command with NVME_SC_HOST_PATH_ERROR send failed Sagi Grimberg
2019-08-10 12:10 ` Hannes Reinecke
2019-08-08 20:53 ` Sagi Grimberg [this message]
2019-08-10 12:11 ` [PATCH v3 6/7] nvme-fc: Fail transport errors with NVME_SC_HOST_PATH Hannes Reinecke
2019-08-08 20:53 ` [PATCH v3 7/7] nvme: don't remove namespace if revalidate failed because of a transport error Sagi Grimberg
2019-08-10 12:14 ` Hannes Reinecke
2019-08-11 5:28 ` Sagi Grimberg
2019-08-08 23:26 ` [PATCH v3 0/7] nvme controller reset and namespace scan work race conditions Bart Van Assche
2019-08-08 23:33 ` Sagi Grimberg
2019-08-08 23:57 ` Bart Van Assche
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190808205325.24036-7-sagi@grimberg.me \
--to=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox