patch 'net/af_xdp: count mbuf allocation failures' has been queued to stable release 23.11.2

Xueming Li xuemingl at nvidia.com
Fri Jul 12 12:44:09 CEST 2024


Hi,

FYI, your patch has been queued to stable release 23.11.2

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 07/14/24. 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=23.11-staging

This queued commit can be viewed at:
https://git.dpdk.org/dpdk-stable/commit/?h=23.11-staging&id=00d025dc224497dca97616a6fbeda163da05fed8

Thanks.

Xueming Li <xuemingl at nvidia.com>

---
>From 00d025dc224497dca97616a6fbeda163da05fed8 Mon Sep 17 00:00:00 2001
From: Ciara Loftus <ciara.loftus at intel.com>
Date: Tue, 14 May 2024 08:41:53 +0000
Subject: [PATCH] net/af_xdp: count mbuf allocation failures
Cc: Xueming Li <xuemingl at nvidia.com>

[ upstream commit f294405ab98594aa41269507dde95cc89bb20a61 ]

Failures to allocate mbufs in the receive path were not being
accounted for in the ethdev statistics. Fix this.

Bugzilla ID: 1429
Fixes: f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")

Reported-by: Stephen Hemminger <stephen at networkplumber.org>
Signed-off-by: Ciara Loftus <ciara.loftus at intel.com>
Acked-by: Stephen Hemminger <stephen at networkplumber.org>
---
 drivers/net/af_xdp/rte_eth_af_xdp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index 539bfd76e1..73fc434ee3 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -316,6 +316,7 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 	unsigned long rx_bytes = 0;
 	int i;
 	struct rte_mbuf *fq_bufs[ETH_AF_XDP_RX_BATCH_SIZE];
+	struct rte_eth_dev *dev = &rte_eth_devices[rxq->port];
 
 	nb_pkts = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
 
@@ -343,6 +344,8 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		 * xsk_ring_cons__peek
 		 */
 		rx->cached_cons -= nb_pkts;
+		dev->data->rx_mbuf_alloc_failed += nb_pkts;
+
 		return 0;
 	}
 
@@ -394,6 +397,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 	int i;
 	uint32_t free_thresh = fq->size >> 1;
 	struct rte_mbuf *mbufs[ETH_AF_XDP_RX_BATCH_SIZE];
+	struct rte_eth_dev *dev = &rte_eth_devices[rxq->port];
 
 	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
 		(void)reserve_fill_queue(umem, nb_pkts, NULL, fq);
@@ -412,6 +416,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 		 * xsk_ring_cons__peek
 		 */
 		rx->cached_cons -= nb_pkts;
+		dev->data->rx_mbuf_alloc_failed += nb_pkts;
 		return 0;
 	}
 
-- 
2.34.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2024-07-12 18:40:15.324492881 +0800
+++ 0023-net-af_xdp-count-mbuf-allocation-failures.patch	2024-07-12 18:40:13.976594243 +0800
@@ -1 +1 @@
-From f294405ab98594aa41269507dde95cc89bb20a61 Mon Sep 17 00:00:00 2001
+From 00d025dc224497dca97616a6fbeda163da05fed8 Mon Sep 17 00:00:00 2001
@@ -4,0 +5,3 @@
+Cc: Xueming Li <xuemingl at nvidia.com>
+
+[ upstream commit f294405ab98594aa41269507dde95cc89bb20a61 ]
@@ -11 +13,0 @@
-Cc: stable at dpdk.org
@@ -21 +23 @@
-index 0997543ee5..0db761a204 100644
+index 539bfd76e1..73fc434ee3 100644
@@ -24 +26 @@
-@@ -320,6 +320,7 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+@@ -316,6 +316,7 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
@@ -32 +34 @@
-@@ -347,6 +348,8 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+@@ -343,6 +344,8 @@ af_xdp_rx_zc(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
@@ -41 +43 @@
-@@ -398,6 +401,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+@@ -394,6 +397,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
@@ -49 +51 @@
-@@ -416,6 +420,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+@@ -412,6 +416,7 @@ af_xdp_rx_cp(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)


More information about the stable mailing list