From: Sagi Grimberg <sagi@grimberg.me>
To: Keith Busch <kbusch@kernel.org>
Cc: linux-nvme@lists.infradead.org, hch@lst.de
Subject: Re: nvme tcp receive errors
Date: Tue, 27 Apr 2021 16:58:28 -0700 [thread overview]
Message-ID: <686a7cdc-a9a8-3700-3805-90d07db39707@grimberg.me> (raw)
In-Reply-To: <20210427181236.GA631001@dhcp-10-100-145-180.wdc.com>
>> What should I put on the Reported-by: and Tested-by: tags?
>
> This report and testing was done courtesy of
>
> Narayan Ayalasomayajula <Narayan.Ayalasomayajula@wdc.com>
>
> Before you submit a patch, though, we did additional testing with data
> digest enabled and observe a regression with the following error:
>
> nvme nvme0: queue 0: data digest flag is cleared
>
> From looking at the patch, the following part looks a bit suspicious:
>
>> @@ -776,19 +776,20 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
>> req->data_recvd += recv_len;
>> }
>>
>> - if (!queue->data_remaining) {
>> + if (!queue->data_remaining)
>> + nvme_tcp_init_recv_ctx(queue);
>
> The code had previously called nvme_tcp_init_recv_ctx() only if
> queue->data_digest wasn't set, but now it's called all the time. I see
> that calling this function clears ddgst_remaining, so does that explain
> the new errors?
>
>> + if (req->data_recvd == req->data_len) {
>> if (queue->data_digest) {
>> nvme_tcp_ddgst_final(queue->rcv_hash, &queue->exp_ddgst);
>> queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
>> } else {
>> - BUG_ON(req->data_recvd != req->data_len);
>> req->cmd_state = NVME_TCP_CMD_DATA_DONE;
>> if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
>> req->cmd_state = NVME_TCP_CMD_DONE;
>> nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
>> queue->nr_cqe++;
>> }
>> - nvme_tcp_init_recv_ctx(queue);
>> }
>> }
You are exactly right, I think this should do the trick:
--
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8e55d8bc0c50..eb1feaacd11a 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -55,6 +55,7 @@ struct nvme_tcp_request {
/* send state */
size_t offset;
size_t data_sent;
+ size_t data_received;
enum nvme_tcp_send_state state;
};
@@ -751,9 +752,12 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue
*queue, struct sk_buff *skb,
*len -= recv_len;
*offset += recv_len;
queue->data_remaining -= recv_len;
+ req->data_received += recv_len;
}
if (!queue->data_remaining) {
+ if (req->data_received < req->data_len)
+ return 0;
if (queue->data_digest) {
nvme_tcp_ddgst_final(queue->rcv_hash,
&queue->exp_ddgst);
queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
@@ -2274,6 +2278,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct
nvme_ns *ns,
req->state = NVME_TCP_SEND_CMD_PDU;
req->offset = 0;
req->data_sent = 0;
+ req->data_received = 0;
req->pdu_len = 0;
req->pdu_sent = 0;
req->data_len = blk_rq_nr_phys_segments(rq) ?
--
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2021-04-27 23:59 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-31 16:18 nvme tcp receive errors Keith Busch
2021-03-31 19:10 ` Sagi Grimberg
2021-03-31 20:49 ` Keith Busch
2021-03-31 22:16 ` Sagi Grimberg
2021-03-31 22:26 ` Keith Busch
2021-03-31 22:45 ` Sagi Grimberg
2021-04-02 17:11 ` Keith Busch
2021-04-02 17:27 ` Sagi Grimberg
2021-04-05 14:37 ` Keith Busch
2021-04-07 19:53 ` Keith Busch
2021-04-09 21:38 ` Sagi Grimberg
2021-04-27 23:39 ` Keith Busch
2021-04-27 23:55 ` Sagi Grimberg
2021-04-28 15:58 ` Keith Busch
2021-04-28 17:42 ` Sagi Grimberg
2021-04-28 18:01 ` Keith Busch
2021-04-28 23:06 ` Sagi Grimberg
2021-04-29 3:33 ` Keith Busch
2021-04-29 4:52 ` Sagi Grimberg
2021-05-03 18:51 ` Keith Busch
2021-05-03 19:58 ` Sagi Grimberg
2021-05-03 20:25 ` Keith Busch
2021-05-04 19:29 ` Sagi Grimberg
2021-04-09 18:04 ` Sagi Grimberg
2021-04-14 0:29 ` Keith Busch
2021-04-21 5:33 ` Sagi Grimberg
2021-04-21 14:28 ` Keith Busch
2021-04-21 16:59 ` Sagi Grimberg
2021-04-26 15:31 ` Keith Busch
2021-04-27 3:10 ` Sagi Grimberg
2021-04-27 18:12 ` Keith Busch
2021-04-27 23:58 ` Sagi Grimberg [this message]
2021-04-30 23:42 ` Sagi Grimberg
2021-05-03 14:28 ` Keith Busch
2021-05-03 19:36 ` Sagi Grimberg
2021-05-03 19:38 ` Sagi Grimberg
2021-05-03 19:44 ` Keith Busch
2021-05-03 20:00 ` Sagi Grimberg
2021-05-04 14:36 ` Keith Busch
2021-05-04 18:15 ` Sagi Grimberg
2021-05-04 19:14 ` Keith Busch
2021-05-10 18:06 ` Keith Busch
2021-05-10 18:18 ` Sagi Grimberg
2021-05-10 18:30 ` Keith Busch
2021-05-10 21:07 ` Sagi Grimberg
2021-05-11 3:00 ` Keith Busch
2021-05-11 17:17 ` Sagi Grimberg
2021-05-13 15:48 ` Keith Busch
2021-05-13 19:53 ` Sagi Grimberg
2021-05-17 20:48 ` 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=686a7cdc-a9a8-3700-3805-90d07db39707@grimberg.me \
--to=sagi@grimberg.me \
--cc=hch@lst.de \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
/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;
as well as URLs for NNTP newsgroup(s).