Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: Chengguang Xu <cgxu519@mykernel.net>
To: "linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>
Subject: Question about AETH_NAK_PSN_SEQ_ERROR
Date: Sat, 14 May 2022 21:35:03 +0800	[thread overview]
Message-ID: <2eeb36ab-0f4d-fc9a-44a6-9b6bfa2f7970@mykernel.net> (raw)

Hello Folks,


There is a logic(below code) in check_ack() in rxe_comp.c,  the case 
(AETH_NAK_PSN_SEQ_ERROR)
indicates sending side received a nak ack which means opposite side had 
an psn seq error(expected psn < received psn).
I don't fully understand the comment(/* a nak implicitly acks all 
packets with psns before */) here,
could someone give me a hint for this?

Also, set qp->comp.psn as pkt->psn will skip some psns(from qp->comp.psn 
to pkt->psn) in the retry, is it correct?

Many thanks in advance!
Chengguang

-------------------------

   case AETH_NAK:
             switch (syn) {
             case AETH_NAK_PSN_SEQ_ERROR:
                 /* a nak implicitly acks all packets with psns
                  * before
                  */
                 if (psn_compare(pkt->psn, qp->comp.psn) > 0) {
                     rxe_counter_inc(rxe,
                             RXE_CNT_RCV_SEQ_ERR);
                     qp->comp.psn = pkt->psn;
                     if (qp->req.wait_psn) {
                         qp->req.wait_psn = 0;
                         rxe_run_task(&qp->req.task, 0);
                     }
                 }
                 return COMPST_ERROR_RETRY;





             reply	other threads:[~2022-05-14 13:35 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-14 13:35 Chengguang Xu [this message]
2022-05-14 14:20 ` Question about AETH_NAK_PSN_SEQ_ERROR Chengguang Xu
2022-05-14 16:22   ` Bob Pearson
2022-05-17  5:12     ` Chengguang Xu

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=2eeb36ab-0f4d-fc9a-44a6-9b6bfa2f7970@mykernel.net \
    --to=cgxu519@mykernel.net \
    --cc=linux-rdma@vger.kernel.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