From 7ed7a576f20a8c60bbd4335e57776f3ad5812577 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Tue, 3 Feb 2026 09:21:29 +0200 Subject: [PATCH] net/mlx5e: RX, Drop oversized packets in non-linear mode Currently the driver has an inconsistent behaviour between modes when it comes to oversized packets that are not dropped through the physical MTU check in HW. This can happen for Multi Host configurations where each port has a different MTU. Current behavior: 1) Striding RQ in linear mode drops the packet in SW and counts it with oversize_pkts_sw_drop. 2) Striding RQ in non-linear mode allows it like a normal packet. 3) Legacy RQ can't receive oversized packets by design: the RX WQE uses MTU sized packet buffers. This inconsistency is not a violation of the netdev policy [1] but it is better to be consistent across modes. This patch aligns (2) with (1) and (3). One exception is added for LRO: don't drop the oversized packet if it is an LRO packet. As now rq->hw_mtu always needs to be updated during the MTU change flow, drop the reset avoidance optimization from mlx5e_change_mtu(). Extract the CQE LRO segments reading into a helper function as it is used twice now. [1] Documentation/networking/netdevices.rst#L205 Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20260203072130.1710255-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 25 ++----------------- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 11 +++++++- include/linux/mlx5/device.h | 5 ++++ 3 files changed, 17 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 96dc6a6dc7376..71e663c3b4211 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 1fc3720d2201c..05b6823273053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1574,7 +1574,7 @@ 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 +2058,15 @@ 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 d7f46a8fbfa18..b37fe39cef273 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 -- 2.47.3