From: Gleb Chesnokov <gleb.chesnokov@scst.dev>
To: linux-nvme@lists.infradead.org
Cc: hch@lst.de, sagi@grimberg.me, kch@nvidia.com, kbusch@kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH] nvmet: report backend transport errors as path errors
Date: Fri, 13 Nov 2026 14:02:47 +0300 [thread overview]
Message-ID: <0099f610-a48b-4557-8515-e4df444262e8@scst.dev> (raw)
The block backend maps BLK_STS_TRANSPORT to NVME_SC_INTERNAL with DNR
set. This discards the backend's transport error classification. A Linux
native multipath host completes the request before considering path
failover, even if another controller can still access the namespace.
Map BLK_STS_TRANSPORT to NVME_SC_INTERNAL_PATH_ERROR without DNR instead.
The transport failure is behind the controller, so report an internal
path error rather than a host path error. Associate the error log entry
with the namespace, as for the existing access-denied status.
This allows otherwise retryable native multipath requests to reach path
error handling.
Signed-off-by: Gleb Chesnokov <gleb.chesnokov@scst.dev>
---
OpenAI Codex assisted with the code analysis, patch and changelog.
drivers/nvme/target/io-cmd-bdev.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index 72618dced191..da640b8e8241 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -167,6 +167,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
status = NVME_SC_ACCESS_DENIED;
req->error_loc = offsetof(struct nvme_rw_command, nsid);
break;
+ case BLK_STS_TRANSPORT:
+ status = NVME_SC_INTERNAL_PATH_ERROR;
+ req->error_loc = offsetof(struct nvme_rw_command, nsid);
+ break;
case BLK_STS_IOERR:
default:
status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
base-commit: 7e1392a42ea288d70a266f6553fe06f57f8647ea
--
2.56.0
next reply other threads:[~2026-11-13 11:02 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-13 11:02 Gleb Chesnokov [this message]
2026-11-20 17:56 ` [PATCH] nvmet: report backend transport errors as path errors Christoph Hellwig
2026-11-20 19:54 ` Keith Busch
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=0099f610-a48b-4557-8515-e4df444262e8@scst.dev \
--to=gleb.chesnokov@scst.dev \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.