From: luca.boccassi@gmail.com
To: Rahul Bhansali <rbhansali@marvell.com>
Cc: dpdk stable <stable@dpdk.org>
Subject: patch 'net/cnxk: fix NIX send header L3 type' has been queued to stable release 22.11.8
Date: Mon, 17 Feb 2025 17:03:54 +0000 [thread overview]
Message-ID: <20250217170456.1068278-21-luca.boccassi@gmail.com> (raw)
In-Reply-To: <20250217170456.1068278-1-luca.boccassi@gmail.com>
Hi,
FYI, your patch has been queued to stable release 22.11.8
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/19/25. So please
shout if anyone has objections.
Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.
Queued patches are on a temporary branch at:
https://github.com/bluca/dpdk-stable
This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/bf3f2c07d4ed6953ae982869c975f508c5eece40
Thanks.
Luca Boccassi
---
From bf3f2c07d4ed6953ae982869c975f508c5eece40 Mon Sep 17 00:00:00 2001
From: Rahul Bhansali <rbhansali@marvell.com>
Date: Thu, 30 Jan 2025 17:25:26 +0530
Subject: [PATCH] net/cnxk: fix NIX send header L3 type
[ upstream commit 32c18e7364e30a8e43cc7cc6709a7ce606fa285e ]
For small packets less than 55 bytes, SQ error interrupts are
observed.
When checksum offload flag is enabled and mbuf ol_flags are not
set, then default L3 type will be set to IPv6 in vector
processing. Based on this, HW will still validate for minimum
header size and generate send header error if mismatch.
To address this, will set default L3 type to none. Mbuf ol_flags
RTE_MBUF_F_TX_IPV6 will set with offload feature TSO or L4
checksum only, so handled in corresponding routine.
Fixes: f71b7dbbf04b ("net/cnxk: add vector Tx for CN10K")
Fixes: e829e60c6917 ("net/cnxk: support Tx burst vector for CN20K")
Fixes: 862e28128707 ("net/cnxk: add vector Tx for CN9K")
Signed-off-by: Rahul Bhansali <rbhansali@marvell.com>
---
drivers/net/cnxk/cn10k_tx.h | 7 +++++--
drivers/net/cnxk/cn9k_tx.h | 7 +++++--
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/net/cnxk/cn10k_tx.h b/drivers/net/cnxk/cn10k_tx.h
index cd9b1f225e..97d06ab491 100644
--- a/drivers/net/cnxk/cn10k_tx.h
+++ b/drivers/net/cnxk/cn10k_tx.h
@@ -1340,6 +1340,9 @@ cn10k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
w0->lso_mps = m->tso_segsz;
w0->lso_format = NIX_LSO_FORMAT_IDX_TSOV4 + !!(ol_flags & RTE_MBUF_F_TX_IPV6);
w1->ol4type = NIX_SENDL4TYPE_TCP_CKSUM;
+ w1->ol3type = ((!!(ol_flags & RTE_MBUF_F_TX_IPV4)) << 1) +
+ ((!!(ol_flags & RTE_MBUF_F_TX_IPV6)) << 2) +
+ !!(ol_flags & RTE_MBUF_F_TX_IP_CKSUM);
/* Handle tunnel tso */
if ((flags & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F) &&
@@ -2031,7 +2034,7 @@ again:
*/
const uint8x16_t tbl = {
/* [0-15] = il4type:il3type */
- 0x04, /* none (IPv6 assumed) */
+ 0x00, /* none */
0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6 assumed) */
0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6 assumed) */
0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6 assumed) */
@@ -2235,7 +2238,7 @@ again:
const uint8x16x2_t tbl = {{
{
/* [0-15] = il4type:il3type */
- 0x04, /* none (IPv6) */
+ 0x00, /* none */
0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6) */
0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6) */
0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6) */
diff --git a/drivers/net/cnxk/cn9k_tx.h b/drivers/net/cnxk/cn9k_tx.h
index 33db781abe..a76c071d8a 100644
--- a/drivers/net/cnxk/cn9k_tx.h
+++ b/drivers/net/cnxk/cn9k_tx.h
@@ -659,6 +659,9 @@ cn9k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
w0->lso_mps = m->tso_segsz;
w0->lso_format = NIX_LSO_FORMAT_IDX_TSOV4 + !!(ol_flags & RTE_MBUF_F_TX_IPV6);
w1->ol4type = NIX_SENDL4TYPE_TCP_CKSUM;
+ w1->ol3type = ((!!(ol_flags & RTE_MBUF_F_TX_IPV4)) << 1) +
+ ((!!(ol_flags & RTE_MBUF_F_TX_IPV6)) << 2) +
+ !!(ol_flags & RTE_MBUF_F_TX_IP_CKSUM);
/* Handle tunnel tso */
if ((flags & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F) &&
@@ -1147,7 +1150,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
*/
const uint8x16_t tbl = {
/* [0-15] = il4type:il3type */
- 0x04, /* none (IPv6 assumed) */
+ 0x00, /* none */
0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6 assumed) */
0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6 assumed) */
0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6 assumed) */
@@ -1351,7 +1354,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
const uint8x16x2_t tbl = {{
{
/* [0-15] = il4type:il3type */
- 0x04, /* none (IPv6) */
+ 0x00, /* none */
0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6) */
0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6) */
0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6) */
--
2.47.2
---
Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- - 2025-02-17 16:13:17.617853929 +0000
+++ 0021-net-cnxk-fix-NIX-send-header-L3-type.patch 2025-02-17 16:13:16.802441593 +0000
@@ -1 +1 @@
-From 32c18e7364e30a8e43cc7cc6709a7ce606fa285e Mon Sep 17 00:00:00 2001
+From bf3f2c07d4ed6953ae982869c975f508c5eece40 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 32c18e7364e30a8e43cc7cc6709a7ce606fa285e ]
+
@@ -20 +21,0 @@
-Cc: stable@dpdk.org
@@ -25 +25,0 @@
- drivers/net/cnxk/cn20k_tx.h | 7 +++++--
@@ -27 +27 @@
- 3 files changed, 15 insertions(+), 6 deletions(-)
+ 2 files changed, 10 insertions(+), 4 deletions(-)
@@ -30 +30 @@
-index 7d9b259a5f..77f4e54cd8 100644
+index cd9b1f225e..97d06ab491 100644
@@ -33 +33 @@
-@@ -1773,6 +1773,9 @@ cn10k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
+@@ -1340,6 +1340,9 @@ cn10k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
@@ -43,33 +43 @@
-@@ -2477,7 +2480,7 @@ again:
- */
- const uint8x16_t tbl = {
- /* [0-15] = il4type:il3type */
-- 0x04, /* none (IPv6 assumed) */
-+ 0x00, /* none */
- 0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6 assumed) */
- 0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6 assumed) */
- 0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6 assumed) */
-@@ -2681,7 +2684,7 @@ again:
- const uint8x16x2_t tbl = {{
- {
- /* [0-15] = il4type:il3type */
-- 0x04, /* none (IPv6) */
-+ 0x00, /* none */
- 0x14, /* RTE_MBUF_F_TX_TCP_CKSUM (IPv6) */
- 0x24, /* RTE_MBUF_F_TX_SCTP_CKSUM (IPv6) */
- 0x34, /* RTE_MBUF_F_TX_UDP_CKSUM (IPv6) */
-diff --git a/drivers/net/cnxk/cn20k_tx.h b/drivers/net/cnxk/cn20k_tx.h
-index c731406529..8c3ba8326d 100644
---- a/drivers/net/cnxk/cn20k_tx.h
-+++ b/drivers/net/cnxk/cn20k_tx.h
-@@ -1733,6 +1733,9 @@ cn20k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1, union nix
- w0->lso_mps = m->tso_segsz;
- w0->lso_format = NIX_LSO_FORMAT_IDX_TSOV4 + !!(ol_flags & RTE_MBUF_F_TX_IPV6);
- w1->ol4type = NIX_SENDL4TYPE_TCP_CKSUM;
-+ w1->ol3type = ((!!(ol_flags & RTE_MBUF_F_TX_IPV4)) << 1) +
-+ ((!!(ol_flags & RTE_MBUF_F_TX_IPV6)) << 2) +
-+ !!(ol_flags & RTE_MBUF_F_TX_IP_CKSUM);
-
- /* Handle tunnel tso */
- if ((flags & NIX_TX_OFFLOAD_OL3_OL4_CSUM_F) && (ol_flags & RTE_MBUF_F_TX_TUNNEL_MASK)) {
-@@ -2395,7 +2398,7 @@ again:
+@@ -2031,7 +2034,7 @@ again:
@@ -84 +52 @@
-@@ -2595,7 +2598,7 @@ again:
+@@ -2235,7 +2238,7 @@ again:
@@ -94 +62 @@
-index 9370985864..902a17860c 100644
+index 33db781abe..a76c071d8a 100644
@@ -97 +65 @@
-@@ -889,6 +889,9 @@ cn9k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
+@@ -659,6 +659,9 @@ cn9k_nix_prepare_tso(struct rte_mbuf *m, union nix_send_hdr_w1_u *w1,
@@ -107 +75 @@
-@@ -1402,7 +1405,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
+@@ -1147,7 +1150,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
@@ -116 +84 @@
-@@ -1606,7 +1609,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
+@@ -1351,7 +1354,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
next prev parent reply other threads:[~2025-02-17 17:06 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-17 17:03 patch 'test/ring: fix init with custom number of lcores' " luca.boccassi
2025-02-17 17:03 ` patch 'vhost: clear ring addresses when getting vring base' " luca.boccassi
2025-02-17 17:03 ` patch 'vhost: check GSO size validity' " luca.boccassi
2025-02-17 17:03 ` patch 'crypto/cnxk: fix build with GCC 15' " luca.boccassi
2025-02-17 17:03 ` patch 'net/thunderx/base: " luca.boccassi
2025-02-17 17:03 ` patch 'eal/x86: fix some intrinsics header include for Windows' " luca.boccassi
2025-02-17 17:03 ` patch 'net/bonding: fix dedicated queue setup' " luca.boccassi
2025-02-17 17:03 ` patch 'net/hns3: fix mbuf freeing in simple Tx path' " luca.boccassi
2025-02-17 17:03 ` patch 'net/hns3: remove PVID info dump for VF' " luca.boccassi
2025-02-17 17:03 ` patch 'net/hns3: rename RAS module' " luca.boccassi
2025-02-17 17:03 ` patch 'net/sfc: remove unnecessary assignment' " luca.boccassi
2025-02-17 17:03 ` patch 'net/mlx5: fix polling CQEs' " luca.boccassi
2025-02-17 17:03 ` patch 'net/iavf: remove reset of Tx prepare function pointer' " luca.boccassi
2025-02-17 17:03 ` patch 'net/ice: fix memory leak in scalar Rx' " luca.boccassi
2025-02-17 17:03 ` patch 'common/cnxk: fix atomic load in batch ops' " luca.boccassi
2025-02-17 17:03 ` patch 'common/cnxk: fix DPI mailbox structure' " luca.boccassi
2025-02-17 17:03 ` patch 'crypto/virtio: fix redundant queue free' " luca.boccassi
2025-02-17 17:03 ` patch 'crypto/openssl: fix CMAC auth context update' " luca.boccassi
2025-02-17 17:03 ` patch 'crypto/virtio: fix data queues iteration' " luca.boccassi
2025-02-17 17:03 ` patch 'net/enetfec: remove useless assignment' " luca.boccassi
2025-02-17 17:03 ` luca.boccassi [this message]
2025-02-17 17:03 ` patch 'eal/linux: fix memseg length in legacy mem init' " luca.boccassi
2025-02-17 17:03 ` patch 'use Python raw string notation' " luca.boccassi
2025-02-17 17:03 ` patch 'net/af_packet: fix socket close on device stop' " luca.boccassi
2025-02-17 17:03 ` patch 'ethdev: fix functions available in new device event' " luca.boccassi
2025-02-17 17:03 ` patch 'vhost: add null callback checks' " luca.boccassi
2025-02-17 17:04 ` patch 'build: force GCC 15 to initialize padding bits' " luca.boccassi
2025-02-17 17:04 ` patch 'net/bnxt: fix indication of allocation' " luca.boccassi
2025-02-17 17:04 ` patch 'net/bnxt: fix crash when representor is re-attached' " luca.boccassi
2025-02-17 17:04 ` patch 'net/mlx5: fix Netlink socket leak' " luca.boccassi
2025-02-17 17:04 ` patch 'net/mlx5: adjust actions per rule limitation' " luca.boccassi
2025-02-17 17:04 ` patch 'net/mlx5: fix flush of non-template flow rules' " luca.boccassi
2025-02-17 17:04 ` patch 'net/mlx5: fix GRE flow match with SWS' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix deadlock when writing i225 register' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix infinite loop' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix bitwise operation type' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: increase PHY power up delay' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: reset loop variable' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix LTR for i225' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix typo in LTR calculation' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix unused value' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix semaphore timeout " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix iterator type' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix MAC address hash bit shift' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix data type in MAC hash' " luca.boccassi
2025-02-17 17:04 ` patch 'net/igc/base: fix NVM data type in bit shift' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix semaphore timeout value' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: correct mPHY access logic' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix iterator type' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix MAC address hash bit shift' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix data type in MAC hash' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix uninitialized variable' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix bitwise operation type' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix NVM data type in bit shift' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix reset for 82580' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: fix unchecked return' " luca.boccassi
2025-02-17 17:04 ` patch 'net/e1000/base: skip management check for 82575' " luca.boccassi
2025-02-17 17:04 ` patch 'common/idpf: fix void function returning a value' " luca.boccassi
2025-02-17 17:04 ` patch 'net/intel: fix void functions " luca.boccassi
2025-02-17 17:04 ` patch 'net/intel: fix build with icx' " luca.boccassi
2025-02-17 17:04 ` patch 'net/hns3: fix copper port initialization' " luca.boccassi
2025-02-17 17:04 ` patch 'net/hns3: fix reset timeout' " luca.boccassi
2025-02-17 17:04 ` patch 'raw/cnxk_gpio: fix file descriptor leak' " luca.boccassi
2025-02-17 17:04 ` patch 'net/i40e: remove duplicate code' " luca.boccassi
2025-02-17 17:04 ` patch 'eal: fix devargs layers parsing out of bounds' " luca.boccassi
2025-02-17 17:04 ` patch 'net/qede: fix debug messages array' " luca.boccassi
2025-02-17 17:04 ` patch 'examples/ptpclient: fix message parsing' " luca.boccassi
2025-02-17 17:04 ` patch 'net/hinic: fix flow type bitmask overflow' " luca.boccassi
2025-02-17 17:04 ` patch 'crypto/dpaa2_sec: fix bitmask truncation' " luca.boccassi
2025-02-17 17:04 ` patch 'crypto/dpaa_sec: " luca.boccassi
2025-02-17 17:04 ` patch 'event/dpaa: " luca.boccassi
2025-02-17 17:04 ` patch 'net/dpaa: " luca.boccassi
2025-02-17 17:04 ` patch 'net/dpaa2: " luca.boccassi
2025-02-17 17:04 ` patch 'net/qede: fix nested loops' " luca.boccassi
2025-02-17 17:04 ` patch 'examples/l3fwd: fix socket ID check' " luca.boccassi
2025-02-17 17:04 ` patch 'common/cnxk: fix null " luca.boccassi
2025-02-17 17:04 ` patch 'eal/linux: remove useless assignments' " luca.boccassi
2025-02-17 17:04 ` patch 'mempool: fix errno in empty create' " luca.boccassi
2025-02-17 17:04 ` patch 'ethdev: convert string initialization' " luca.boccassi
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=20250217170456.1068278-21-luca.boccassi@gmail.com \
--to=luca.boccassi@gmail.com \
--cc=rbhansali@marvell.com \
--cc=stable@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 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).