patch 'net/mlx5: fix error packets drop in regular Rx' has been queued to stable release 22.11.5

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 22.11.5

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 03/16/24. 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://github.com/bluca/dpdk-stable

This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/3032a40f28fa9cb423fee723e6c89a14d84fdee0

Thanks.

Luca Boccassi

---
>From 3032a40f28fa9cb423fee723e6c89a14d84fdee0 Mon Sep 17 00:00:00 2001
From: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Date: Tue, 20 Feb 2024 13:45:20 +0200
Subject: [PATCH] net/mlx5: fix error packets drop in regular Rx

[ upstream commit ef296e8f6140ea469b50c7bfe73501b1c9ef86e1 ]

When packet gets received with error it is reported in CQE
structure and PMD analyzes the error syndrome and provides
two options - either reset the entire queue for the critical
errors, or just ignore the packet.

The non-vectorized rx_burst did not ignore the non-critical
error packets, and in case of packet length exceeding the
mbuf data buffer length it took the next element in the queue
WQE ring, resulting in CQE/WQE consume indices synchronization
lost.

Fixes: aa67ed308458 ("net/mlx5: ignore non-critical syndromes for Rx queue")

Signed-off-by: Viacheslav Ovsiienko <viacheslavo at nvidia.com>
Acked-by: Dariusz Sosnowski <dsosnowski at nvidia.com>
---
 drivers/net/mlx5/mlx5_rx.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/mlx5/mlx5_rx.c b/drivers/net/mlx5/mlx5_rx.c
index b41f7a51f5..56e5568f33 100644
--- a/drivers/net/mlx5/mlx5_rx.c
+++ b/drivers/net/mlx5/mlx5_rx.c
@@ -601,7 +601,8 @@ mlx5_rx_err_handle(struct mlx5_rxq_data *rxq, uint8_t vec,
  * @param mprq
  *   Indication if it is called from MPRQ.
  * @return
- *   0 in case of empty CQE, MLX5_REGULAR_ERROR_CQE_RET in case of error CQE,
+ *   0 in case of empty CQE,
+ *   MLX5_REGULAR_ERROR_CQE_RET in case of error CQE,
  *   MLX5_CRITICAL_ERROR_CQE_RET in case of error CQE lead to Rx queue reset,
  *   otherwise the packet size in regular RxQ,
  *   and striding byte count format in mprq case.
@@ -675,6 +676,11 @@ mlx5_rx_poll_len(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe,
 					if (ret == MLX5_RECOVERY_ERROR_RET ||
 						ret == MLX5_RECOVERY_COMPLETED_RET)
 						return MLX5_CRITICAL_ERROR_CQE_RET;
+					if (!mprq && ret == MLX5_RECOVERY_IGNORE_RET) {
+						*skip_cnt = 1;
+						++rxq->cq_ci;
+						return MLX5_ERROR_CQE_MASK;
+					}
 				} else {
 					return 0;
 				}
@@ -928,19 +934,18 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
 			cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
 			len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt, &mcqe, &skip_cnt, false);
 			if (unlikely(len & MLX5_ERROR_CQE_MASK)) {
+				/* We drop packets with non-critical errors */
+				rte_mbuf_raw_free(rep);
 				if (len == MLX5_CRITICAL_ERROR_CQE_RET) {
-					rte_mbuf_raw_free(rep);
 					rq_ci = rxq->rq_ci << sges_n;
 					break;
 				}
+				/* Skip specified amount of error CQEs packets */
 				rq_ci >>= sges_n;
 				rq_ci += skip_cnt;
 				rq_ci <<= sges_n;
-				idx = rq_ci & wqe_cnt;
-				wqe = &((volatile struct mlx5_wqe_data_seg *)rxq->wqes)[idx];
-				seg = (*rxq->elts)[idx];
-				cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
-				len = len & ~MLX5_ERROR_CQE_MASK;
+				MLX5_ASSERT(!pkt);
+				continue;
 			}
 			if (len == 0) {
 				rte_mbuf_raw_free(rep);
-- 
2.39.2

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2024-03-14 00:09:22.571302258 +0000
+++ 0041-net-mlx5-fix-error-packets-drop-in-regular-Rx.patch	2024-03-14 00:09:20.633615618 +0000
@@ -1 +1 @@
-From ef296e8f6140ea469b50c7bfe73501b1c9ef86e1 Mon Sep 17 00:00:00 2001
+From 3032a40f28fa9cb423fee723e6c89a14d84fdee0 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit ef296e8f6140ea469b50c7bfe73501b1c9ef86e1 ]
+
@@ -18 +19,0 @@
-Cc: stable at dpdk.org
@@ -27 +28 @@
-index 5bf1a679b2..cc087348a4 100644
+index b41f7a51f5..56e5568f33 100644
@@ -30 +31 @@
-@@ -613,7 +613,8 @@ mlx5_rx_err_handle(struct mlx5_rxq_data *rxq, uint8_t vec,
+@@ -601,7 +601,8 @@ mlx5_rx_err_handle(struct mlx5_rxq_data *rxq, uint8_t vec,
@@ -40 +41 @@
-@@ -697,6 +698,11 @@ mlx5_rx_poll_len(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe,
+@@ -675,6 +676,11 @@ mlx5_rx_poll_len(struct mlx5_rxq_data *rxq, volatile struct mlx5_cqe *cqe,
@@ -52,3 +53,3 @@
-@@ -971,19 +977,18 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
- 			cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_mask];
- 			len = mlx5_rx_poll_len(rxq, cqe, cqe_n, cqe_mask, &mcqe, &skip_cnt, false);
+@@ -928,19 +934,18 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
+ 			cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
+ 			len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt, &mcqe, &skip_cnt, false);
@@ -67 +68 @@
--				idx = rq_ci & wqe_mask;
+-				idx = rq_ci & wqe_cnt;
@@ -70 +71 @@
--				cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_mask];
+-				cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];