Re: [PATCH v2 0/6] nvme: fix transport request and queue error handling
From: Keith Busch
Date: Mon Nov 16 2026 - 11:21:44 EST
On Sat, 14 Nov 2026 02:02:45 +0800 (CST), shao.mingyin@xxxxxxxxxx wrote:
> The six patches fix independent error paths in the NVMe transports.
>
> Patch 1 releases the target request in nvme-loop when SG setup fails.
> nvmet_req_init() has already taken the queue, namespace and reservation
> references, and blk-mq retries the same request, so each failure leaked a
> set of references.
>
> [...]
Thanks, applied to nvme-7.4.
[1/6] nvme-loop: release the target request when SG setup fails
commit: f2937481c28033e10e8a29b8742a767e73c696df
[2/6] nvmet-tcp: only wait for in-capsule data for inline SGLs
commit: 9dac3b1aa2a99e126a5504b7f5bc781c8b2771e0
[3/6] nvme-tcp: require the R2T offset to match the data sent
commit: 347d50d92e25d4b9c50c5f5c1d8b727b9c88d12c
[4/6] nvmet-fcloop: free the LS request when delivery fails
commit: 8c1f99419b6cc51892e259497c8e10a5d079621a
[5/6] nvmet-fc: reject duplicate queue IDs on Create Connection
commit: 153eac284ebf68be74993643e9b2fe2f9b2b1d88
[6/6] nvmet: roll back queue bindings on connection failure
commit: 3f82752e089283eb8204b9d2ebd8246077031173
--
Keith Busch <kbusch@xxxxxxxxxx>