Merge branch 'net-mlx5e-rx-datapath-enhancements'

Tariq Toukan says:

====================
net/mlx5e: RX datapath enhancements

This series by Dragos introduces multiple RX datapath enhancements to
the mlx5e driver.

First patch adds SW handling for oversized packets in non-linear SKB
mode.

Second patch adds a reclaim mechanism to mitigate memory allocation
failures with memory providers.
====================

Link: https://patch.msgid.link/20260203072130.1710255-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 41 insertions, 26 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 96dc6a6dc737..71e663c3b421 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4716,7 +4716,6 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_params new_params;
 	struct mlx5e_params *params;
-	bool reset = true;
 	int err = 0;
 
 	mutex_lock(&priv->state_lock);
@@ -4742,28 +4741,8 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		goto out;
 	}
 
-	if (params->packet_merge.type == MLX5E_PACKET_MERGE_LRO)
-		reset = false;
-
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
-	    params->packet_merge.type != MLX5E_PACKET_MERGE_SHAMPO) {
-		bool is_linear_old = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, params, NULL);
-		bool is_linear_new = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev,
-								  &new_params, NULL);
-		u8 sz_old = mlx5e_mpwqe_get_log_rq_size(priv->mdev, params, NULL);
-		u8 sz_new = mlx5e_mpwqe_get_log_rq_size(priv->mdev, &new_params, NULL);
-
-		/* Always reset in linear mode - hw_mtu is used in data path.
-		 * Check that the mode was non-linear and didn't change.
-		 * If XSK is active, XSK RQs are linear.
-		 * Reset if the RQ size changed, even if it's non-linear.
-		 */
-		if (!is_linear_old && !is_linear_new && !priv->xsk.refcnt &&
-		    sz_old == sz_new)
-			reset = false;
-	}
-
-	err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, reset);
+	err = mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL,
+				       true);
 
 out:
 	WRITE_ONCE(netdev->mtu, params->sw_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1fc3720d2201..849e1f16482a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1087,11 +1087,24 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 	return i;
 }
 
+static void mlx5e_reclaim_mpwqe_pages(struct mlx5e_rq *rq, int head,
+				      int reclaim)
+{
+	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+
+	for (int i = 0; i < reclaim; i++) {
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+
+		mlx5e_dealloc_rx_mpwqe(rq, head);
+	}
+}
+
 INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 {
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
 	u8  umr_completed = rq->mpwqe.umr_completed;
 	struct mlx5e_icosq *sq = rq->icosq;
+	bool reclaimed = false;
 	int alloc_err = 0;
 	u8  missing, i;
 	u16 head;
@@ -1126,11 +1139,20 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 		/* Deferred free for better page pool cache usage. */
 		mlx5e_free_rx_mpwqe(rq, wi);
 
+retry:
 		alloc_err = rq->xsk_pool ? mlx5e_xsk_alloc_rx_mpwqe(rq, head) :
 					   mlx5e_alloc_rx_mpwqe(rq, head);
+		if (unlikely(alloc_err)) {
+			int reclaim = i - 1;
 
-		if (unlikely(alloc_err))
-			break;
+			if (reclaimed || !reclaim)
+				break;
+
+			mlx5e_reclaim_mpwqe_pages(rq, head, reclaim);
+			reclaimed = true;
+
+			goto retry;
+		}
 		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
 	} while (--i);
 
@@ -1574,7 +1596,7 @@ static inline bool mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 				      struct mlx5e_rq *rq,
 				      struct sk_buff *skb)
 {
-	u8 lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
+	u8 lro_num_seg = get_cqe_lro_num_seg(cqe);
 	struct mlx5e_rq_stats *stats = rq->stats;
 	struct net_device *netdev = rq->netdev;
 
@@ -2058,6 +2080,15 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	u16 linear_hr;
 	void *va;
 
+	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
+		u8 lro_num_seg = get_cqe_lro_num_seg(cqe);
+
+		if (lro_num_seg <= 1) {
+			rq->stats->oversize_pkts_sw_drop++;
+			return NULL;
+		}
+	}
+
 	prog = rcu_dereference(rq->xdp_prog);
 
 	if (prog) {
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index d7f46a8fbfa1..b37fe39cef27 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -962,6 +962,11 @@ static inline u16 get_cqe_flow_tag(struct mlx5_cqe64 *cqe)
 	return be32_to_cpu(cqe->sop_drop_qpn) & 0xFFF;
 }
 
+static inline u8 get_cqe_lro_num_seg(struct mlx5_cqe64 *cqe)
+{
+	return be32_to_cpu(cqe->srqn) >> 24;
+}
+
 #define MLX5_MPWQE_LOG_NUM_STRIDES_EXT_BASE	3
 #define MLX5_MPWQE_LOG_NUM_STRIDES_BASE		9
 #define MLX5_MPWQE_LOG_NUM_STRIDES_MAX		16