All of lore.kernel.org
 help / color / mirror / Atom feed
From: bugzilla@dpdk.org
To: dev@dpdk.org
Subject: [DPDK/ethdev Bug 1805] Outdated CQE consumer index in rxq_burst_mprq_v()
Date: Wed, 22 Oct 2025 02:57:47 +0000	[thread overview]
Message-ID: <bug-1805-3@http.bugs.dpdk.org/> (raw)

http://bugs.dpdk.org/show_bug.cgi?id=1805

            Bug ID: 1805
           Summary: Outdated CQE consumer index in rxq_burst_mprq_v()
           Product: DPDK
           Version: 22.11
          Hardware: x86
                OS: Linux
            Status: UNCONFIRMED
          Severity: normal
          Priority: Normal
         Component: ethdev
          Assignee: dev@dpdk.org
          Reporter: canary.overflow@gmail.com
  Target Milestone: ---

In function rxq_burst_mprq_v() [drivers/net/mlx5/mlx5_rxtx_vec.c line 470]:

unsigned int cq_idx = rxq->cq_ci & q_mask;
...
cq = &(*rxq->cqes)[cq_idx];
rte_prefetch0(cq);
rte_prefetch0(cq + 1);
rte_prefetch0(cq + 2);
rte_prefetch0(cq + 3);
...
if (rcvd_pkt > 0) {
    rcvd_pkt = RTE_MIN(rcvd_pkt, pkts_n);
    cp_pkt = rxq_copy_mprq_mbuf_v(rxq, pkts, rcvd_pkt); // rxq->cq_ci
incremented here
    rxq->decompressed -= rcvd_pkt;
    pkts += cp_pkt;
}
...
/* Not to overflow pkts array. */
pkts_n = RTE_ALIGN_FLOOR(pkts_n - cp_pkt, MLX5_VPMD_DESCS_PER_LOOP);
/* Not to cross queue end. */
pkts_n = RTE_MIN(pkts_n, elts_n - elts_idx);
pkts_n = RTE_MIN(pkts_n, q_n - cq_idx); // (1) 
...
/* At this point, there shouldn't be any remaining packets. */
MLX5_ASSERT(rxq->decompressed == 0);
/* Process all the CQEs */
nocmp_n = rxq_cq_process_v(rxq, cq, elts, pkts, pkts_n, err, &comp_idx); (2)

The cq pointer may be using an outdated rxq->cq_ci value if rcvd_pkt > 0 and
rxq->cq_ci gets incremented in rxq_copy_mprq_mbuf_v(). This may have the
following issues:
- pkts_n computed in (1) may be more than what it should be
- the cq pointer retrieved using the outdated cq_idx is being passed into
rxq_cq_process_v() again (2).


For the fix, I think the value of cq_idx needs to be updated again after the
processing the decompressed packets and cq pointer be retrieved after.

-- 
You are receiving this mail because:
You are the assignee for the bug.

                 reply	other threads:[~2025-10-22  2:57 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=bug-1805-3@http.bugs.dpdk.org/ \
    --to=bugzilla@dpdk.org \
    --cc=dev@dpdk.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 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.