patch 'app/testpmd: fix Tx preparation in checksum engine' has been queued to stable release 22.11.2

Xueming Li xuemingl at nvidia.com
Sun Apr 9 17:23:40 CEST 2023


Hi,

FYI, your patch has been queued to stable release 22.11.2

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 04/11/23. 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://git.dpdk.org/dpdk-stable/log/?h=22.11-staging

This queued commit can be viewed at:
https://git.dpdk.org/dpdk-stable/log/?h=22.11-staging/commit/a4141026d791b6521c60a4cf9ad21e9ccf112ff7

Thanks.

Xueming Li <xuemingl at nvidia.com>

---
>From a4141026d791b6521c60a4cf9ad21e9ccf112ff7 Mon Sep 17 00:00:00 2001
From: David Marchand <david.marchand at redhat.com>
Date: Mon, 20 Feb 2023 19:34:54 +0100
Subject: [PATCH] app/testpmd: fix Tx preparation in checksum engine
Cc: Xueming Li <xuemingl at nvidia.com>

[ upstream commit 88a0b0f3858bf430616fe2bcac6f3eee05c383f5 ]

"unprepared" packets could get to the wire in the retry loop.

Split packets freeing in two stages: one for preparation failure, and
one for transmission failure.
Adjust dropped counter update accordingly.

Fixes: 6b520d54ebfe ("app/testpmd: use Tx preparation in checksum engine")

Signed-off-by: David Marchand <david.marchand at redhat.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit at amd.com>
---
 app/test-pmd/csumonly.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index 1c24598515..90a59e0aa5 100644
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -1168,10 +1168,13 @@ tunnel_update:
 
 	nb_prep = rte_eth_tx_prepare(fs->tx_port, fs->tx_queue,
 			tx_pkts_burst, nb_rx);
-	if (nb_prep != nb_rx)
+	if (nb_prep != nb_rx) {
 		fprintf(stderr,
 			"Preparing packet burst to transmit failed: %s\n",
 			rte_strerror(rte_errno));
+		fs->fwd_dropped += (nb_rx - nb_prep);
+		rte_pktmbuf_free_bulk(&tx_pkts_burst[nb_prep], nb_rx - nb_prep);
+	}
 
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, tx_pkts_burst,
 			nb_prep);
@@ -1179,12 +1182,12 @@ tunnel_update:
 	/*
 	 * Retry if necessary
 	 */
-	if (unlikely(nb_tx < nb_rx) && fs->retry_enabled) {
+	if (unlikely(nb_tx < nb_prep) && fs->retry_enabled) {
 		retry = 0;
-		while (nb_tx < nb_rx && retry++ < burst_tx_retry_num) {
+		while (nb_tx < nb_prep && retry++ < burst_tx_retry_num) {
 			rte_delay_us(burst_tx_delay_time);
 			nb_tx += rte_eth_tx_burst(fs->tx_port, fs->tx_queue,
-					&tx_pkts_burst[nb_tx], nb_rx - nb_tx);
+					&tx_pkts_burst[nb_tx], nb_prep - nb_tx);
 		}
 	}
 	fs->tx_packets += nb_tx;
@@ -1194,11 +1197,11 @@ tunnel_update:
 	fs->rx_bad_outer_ip_csum += rx_bad_outer_ip_csum;
 
 	inc_tx_burst_stats(fs, nb_tx);
-	if (unlikely(nb_tx < nb_rx)) {
-		fs->fwd_dropped += (nb_rx - nb_tx);
+	if (unlikely(nb_tx < nb_prep)) {
+		fs->fwd_dropped += (nb_prep - nb_tx);
 		do {
 			rte_pktmbuf_free(tx_pkts_burst[nb_tx]);
-		} while (++nb_tx < nb_rx);
+		} while (++nb_tx < nb_prep);
 	}
 
 	get_end_cycles(fs, start_tsc);
-- 
2.25.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2023-04-09 21:45:39.627227100 +0800
+++ 0032-app-testpmd-fix-Tx-preparation-in-checksum-engine.patch	2023-04-09 21:45:38.619042200 +0800
@@ -1 +1 @@
-From 88a0b0f3858bf430616fe2bcac6f3eee05c383f5 Mon Sep 17 00:00:00 2001
+From a4141026d791b6521c60a4cf9ad21e9ccf112ff7 Mon Sep 17 00:00:00 2001
@@ -4,0 +5,3 @@
+Cc: Xueming Li <xuemingl at nvidia.com>
+
+[ upstream commit 88a0b0f3858bf430616fe2bcac6f3eee05c383f5 ]
@@ -13 +15,0 @@
-Cc: stable at dpdk.org


More information about the stable mailing list