Re: [PATCH v2] nvme-tcp: fix request PDU size when header digest is enabled

[Keith Busch]

On Tue, Oct 27, 2026 at 04:47:10PM -0300, Christian Aurich Zanettini Martins wrote:
> Since commit 61b0ed3be81b ("nvme-tcp: parallelize I/O queue allocation
> and startup") the I/O tag set is allocated before the I/O queues.
> nvme_tcp_init_request() sizes the PDU with nvme_tcp_hdgst_len(queue),
> but queue->hdr_digest is only set later by nvme_tcp_alloc_queue(), so
> every I/O PDU is allocated without room for the header digest.
> 
> With hdr_digest enabled, the digest is then written 4 bytes past the
> PDU, over the header of the next PDU in the page_frag cache, and the
> target drops the connection on the first I/O:
> 
>   nvmet_tcp: unexpected pdu type 159
>   nvmet: ctrl 1 fatal error occurred!
> 
> Queues that a later reconnect adds for the first time have the same
> problem.
> 
> Set queue->hdr_digest when allocating the controller, together with
> pf_cache_lock, so it is valid before any request is initialized.

Thanks, applied to nvme-7.4.

> @@ -1948,7 +1948,6 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid,
>  		}
>  	}
>  
> -	queue->hdr_digest = nctrl->opts->hdr_digest;
>  	queue->data_digest = nctrl->opts->data_digest;
>  
>  	rcv_pdu_size = sizeof(struct nvme_tcp_rsp_pdu) +
> @@ -3098,10 +3097,13 @@ static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(struct device *dev,
>  	/*
>  	 * The I/O tag set is allocated before the I/O queues, and initializing
>  	 * its requests already allocates the PDUs from the page frag caches of
> -	 * the queues, so initialize their locks here.
> +	 * the queues, sized by their header digest setting, so set up the
> +	 * locks and hdr_digest here.
>  	 */
> -	for (i = 0; i < ctrl->ctrl.queue_count; i++)
> +	for (i = 0; i < ctrl->ctrl.queue_count; i++) {
>  		mutex_init(&ctrl->queues[i].pf_cache_lock);
> +		ctrl->queues[i].hdr_digest = opts->hdr_digest;
> +	}

A follow on bonus patch can clean this up a bit by introducing a helper
function, maybe nvme_tcp_init_queue(), and initialize all the basic
fields there.