From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id C44C345FCB; Thu, 2 Jan 2025 20:48:18 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 5C82A402E0; Thu, 2 Jan 2025 20:48:18 +0100 (CET) Received: from inbox.dpdk.org (inbox.dpdk.org [95.142.172.178]) by mails.dpdk.org (Postfix) with ESMTP id 86CA4402B4 for ; Thu, 2 Jan 2025 20:48:17 +0100 (CET) Received: by inbox.dpdk.org (Postfix, from userid 33) id 72B2B45FCC; Thu, 2 Jan 2025 20:48:17 +0100 (CET) From: bugzilla@dpdk.org To: dev@dpdk.org Subject: [DPDK/ethdev Bug 1609] memif jumbo support broken Date: Thu, 02 Jan 2025 19:48:16 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: new X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: DPDK X-Bugzilla-Component: ethdev X-Bugzilla-Version: 23.11 X-Bugzilla-Keywords: X-Bugzilla-Severity: normal X-Bugzilla-Who: bly454@gmail.com X-Bugzilla-Status: UNCONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: dev@dpdk.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: bug_id short_desc product version rep_platform op_sys bug_status bug_severity priority component assigned_to reporter target_milestone Message-ID: Content-Type: multipart/alternative; boundary=17358472970.4Cba.1195485 Content-Transfer-Encoding: 7bit X-Bugzilla-URL: http://bugs.dpdk.org/ Auto-Submitted: auto-generated X-Auto-Response-Suppress: All MIME-Version: 1.0 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org --17358472970.4Cba.1195485 Date: Thu, 2 Jan 2025 20:48:17 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.dpdk.org/ Auto-Submitted: auto-generated X-Auto-Response-Suppress: All https://bugs.dpdk.org/show_bug.cgi?id=3D1609 Bug ID: 1609 Summary: memif jumbo support broken Product: DPDK Version: 23.11 Hardware: All OS: All Status: UNCONFIRMED Severity: normal Priority: Normal Component: ethdev Assignee: dev@dpdk.org Reporter: bly454@gmail.com Target Milestone: --- We just completed our upgrade from DPDK 21.11.2 to 23.11.1. Our testing fou= nd a defect with the current 23.11 code. This can/may impact other releases. Please review the "dst_off" changes below, which restore jumbo (frames larg= er than 2KB) support relative to multiple memif buffer handling. You will also note we have disabled the new "bulk" functionality as we have not had time = to review it. For now, we have disabled it in preference to using the original "else" code with these fixes. Similar fixes/logic should be confirmed prese= nt as well in VPP's libmemif solution. We recommend a new UT be added, which tests randomly sized frames consistin= g of 1, 2 & 3 memif buffers to validate jumbo frame support. diff --git a/drivers/net/memif/rte_eth_memif.c b/drivers/net/memif/rte_eth_memif.c index 2c2fafadf9..4a3a46c34a 100644 --- a/drivers/net/memif/rte_eth_memif.c +++ b/drivers/net/memif/rte_eth_memif.c @@ -357,7 +357,7 @@ eth_memif_rx(void *queue, struct rte_mbuf **bufs, uint1= 6_t nb_pkts) goto refill; n_slots =3D (last_slot - cur_slot) & mask; - if (likely(mbuf_size >=3D pmd->cfg.pkt_buffer_size)) { + if (0 /*likely(mbuf_size >=3D pmd->cfg.pkt_buffer_size)*/) { struct rte_mbuf *mbufs[MAX_PKT_BURST]; next_bulk: ret =3D rte_pktmbuf_alloc_bulk(mq->mempool, mbufs, MAX_PKT_BURST); @@ -428,12 +428,12 @@ eth_memif_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) mbuf =3D mbuf_head; mbuf->port =3D mq->in_port; + dst_off =3D 0; next_slot2: s0 =3D cur_slot & mask; d0 =3D &ring->desc[s0]; src_len =3D d0->length; - dst_off =3D 0; src_off =3D 0; do { @@ -722,7 +722,7 @@ eth_memif_tx(void *queue, struct rte_mbuf **bufs, uint1= 6_t nb_pkts) } uint16_t mbuf_size =3D rte_pktmbuf_data_room_size(mp) - RTE_PKTMBUF_HEADROOM; - if (i =3D=3D nb_pkts && pmd->cfg.pkt_buffer_size >=3D mbuf_size) { + if ( 0 /*i =3D=3D nb_pkts && pmd->cfg.pkt_buffer_size >=3D mbuf_siz= e*/) { buf_tmp =3D bufs; while (n_tx_pkts < nb_pkts && n_free) { mbuf_head =3D *bufs++; @@ -772,6 +772,7 @@ eth_memif_tx(void *queue, struct rte_mbuf **bufs, uint1= 6_t nb_pkts) dst_off =3D 0; dst_len =3D (type =3D=3D MEMIF_RING_C2S) ? pmd->run.pkt_buffer_size : d0->length; + d0->flags =3D 0; next_in_chain2: src_off =3D 0; --=20 You are receiving this mail because: You are the assignee for the bug.= --17358472970.4Cba.1195485 Date: Thu, 2 Jan 2025 20:48:17 +0100 MIME-Version: 1.0 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.dpdk.org/ Auto-Submitted: auto-generated X-Auto-Response-Suppress: All
Bug ID 1609
Summary memif jumbo support broken
Product DPDK
Version 23.11
Hardware All
OS All
Status UNCONFIRMED
Severity normal
Priority Normal
Component ethdev
Assignee dev@dpdk.org
Reporter bly454@gmail.com
Target Milestone --- 

We just completed our upgrade from=
 DPDK 21.11.2 to 23.11.1. Our testing found a
defect with the current 23.11 code. This can/may impact other releases.

Please review the "dst_off" changes below, which restore jumbo (f=
rames larger
than 2KB) support relative to multiple memif buffer handling. You will also
note we have disabled the new "bulk" functionality as we have not=
 had time to
review it. For now, we have disabled it in preference to using the original
"else" code with these fixes. Similar fixes/logic should be confi=
rmed present
as well in VPP's libmemif solution.

We recommend a new UT be added, which tests randomly sized frames consistin=
g of
1, 2 & 3 memif buffers to validate jumbo frame support.

diff --git a/drivers/net/memif/rte_eth_memif.c
b/drivers/net/memif/rte_eth_memif.c
index 2c2fafadf9..4a3a46c34a 100644
--- a/drivers/net/memif/rte_eth_memif.c
+++ b/drivers/net/memif/rte_eth_memif.c
@@ -357,7 +357,7 @@ eth_memif_rx(void *queue, struct rte_mb=
uf **bufs, uint16_t
nb_pkts)
                goto refill;
        n_slots =3D (last_slot - cur_slot) & mask;

-       if (likely(mbuf_size >=3D pmd->cfg.pkt_buffer_size)) {
+       if (0 /*likely(mbuf_size >=3D pmd->cfg.pkt_buffer_size)*/) {
                struct rte_mbuf *mbufs[MAX_PKT_BURST];
 next_bulk:
                ret =3D rte_pktmbuf_alloc_bulk(mq->mempool, mbufs,
MAX_PKT_BURST);
@@ -428,12 +428,12 @@ eth_memif_rx(void *queue, struct rte_=
mbuf **bufs,
uint16_t nb_pkts)
                        mbuf =3D mbuf_head;
                        mbuf->port =3D mq->in_port;

+                       dst_off =3D 0;
 next_slot2:
                        s0 =3D cur_slot & mask;
                        d0 =3D &ring->desc[s0];

                        src_len =3D d0->length;
-                       dst_off =3D 0;
                        src_off =3D 0;

                        do {
@@ -722,7 +722,7 @@ eth_memif_tx(void *queue, struct rte_mb=
uf **bufs, uint16_t
nb_pkts)
        }

        uint16_t mbuf_size =3D rte_pktmbuf_data_room_size(mp) -
RTE_PKTMBUF_HEADROOM;
-       if (i =3D=3D nb_pkts && pmd->cfg.pkt_buffer_size >=3D=
 mbuf_size) {
+       if ( 0 /*i =3D=3D nb_pkts && pmd->cfg.pkt_buffer_size &g=
t;=3D mbuf_size*/) {
                buf_tmp =3D bufs;
                while (n_tx_pkts < nb_pkts && n_free) {
                        mbuf_head =3D *bufs++;
@@ -772,6 +772,7 @@ eth_memif_tx(void *queue, struct rte_mb=
uf **bufs, uint16_t
nb_pkts)
                        dst_off =3D 0;
                        dst_len =3D (type =3D=3D MEMIF_RING_C2S) ?
                                pmd->run.pkt_buffer_size : d0->length;
+                       d0->flags =3D 0;

 next_in_chain2:
                        src_off =3D 0;

You are receiving this mail because:
  • You are the assignee for the bug.
=20=20=20=20=20=20=20=20=20=20
= --17358472970.4Cba.1195485--