From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=100.103.45.18 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795309282; b=knGeNdxKQ9g6m00VgyB6CGynL9HivHuKr/K5mq8UTAy19GIPOYVib5XC7HpvmUvnkAdG wmAmjmQMKcGdTvuWkTovTAAnlaQPHCYjWuX7dCn0jLdO4AzeB8vRVJxN+pp5LaT14mk0a DHqdWs/pyIbI7hXDlKCoKfHCP9HiCP/xh1xGAFjBuSJ3zOCfeSvtLYb3bEbwwFprZfePp zdPAbXM+la59Or9Mj9nlhCO783P1lpq2OEogNR9SVOeX58T+Km+2xEnTfYKaO2/vCcOP1 lhGUNTX48s6VE9gnhtIGPsRQQH9QH8lI6Sy66rJ5n32gwT+ypdCsZzN+/AXAnDChOqA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795309282; h=Received:DKIM-Signature:From:To:Cc:Subject:Date:Message-ID:X-Mailer: In-Reply-To:References:MIME-Version:Content-Transfer-Encoding; bh=tXjeZU5GSs/uz0hKlC0URJrZHP/eBhjfdOTv8TzdxBI=; b=L3KW7YMP89OtJmXXZ/Gk87queKaqSLzDNZY3BEnaea5WR5Kehsr2U57qOHqeR0dJmx1J CimN8WbJ+36iKVCdL/J+7eyJeP0yZMEL8j+xbzeTNg9/Dvuuylu32z5GgVJrojy88/uOd n04CP/QpYBqD3FRdo+7O+ABV5hdHOGj+e7g11cA7oAEnzG2aPCNUs3NhYNN6wO2zM4bwb feX6SUhSaZc1F5R7S0806F8WNLXA1g08KjYNubIPJSwltis7I0rZfdwlVHvCuVSqVqLNS HApVJg12ZcatzDDoC4OwE42gH7zxNP0kYzLVGEnZrxJ6JY1p2WtiKqzO10CwoPkq+xw== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=OXyRtWqu; arc=none smtp.remote-ip=100.103.45.18 Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0177D606A33F; Sun, 22 Nov 2026 01:01:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256 header.s=k20260515 header.b=OXyRtWqu Received: by smtp.kernel.org (Postfix) with ESMTPSA id 537981F000D0; Sun, 22 Nov 2026 01:01:21 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1795309281; bh=tXjeZU5GSs/uz0hKlC0URJrZHP/eBhjfdOTv8TzdxBI=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=OXyRtWqu1BaINOKsbnlFoJ2y0Gvp7BI0djrH3TmiqcsghgQpgfSsnXBDT7seZ/TnP j2zQ5vS6aBifB92XgDGp1Mznl+y1Kg7VlmD+OZKwrTgG0bCIthcfBx53hvN7oTFcgx YVZuYCJm9IJMvynQfzrYPIENKh2y/168AGh7fhb5KelgDXWoGNYZKwssaUVugByKaR 4+f6hNvRQ02rwvLmqEeQBC29EgaEK/9Efe7LyygoBnN61eWslITZA7frjh/iCnB9Nq ksSmGnodvQVCDjnjjuZTYBk0Jnmz7filLsTrikJQQ1vWHvFDJ16dbiN1z3Nu5tNMNK Q93O7NxqUUbmw== From: Jakub Kicinski To: davem@davemloft.net Cc: netdev@vger.kernel.org, edumazet@google.com, pabeni@redhat.com, andrew+netdev@lunn.ch, horms@kernel.org, michael.chan@broadcom.com, manishc@marvell.com, joshwash@google.com, hramamurthy@google.com, tariqt@nvidia.com, saeedm@nvidia.com, daniel@iogearbox.net, hawk@kernel.org, sdf@fomichev.me, willemb@google.com, przemyslaw.kitszel@intel.com, bpf@vger.kernel.org, Jakub Kicinski Subject: [PATCH net-next v2 6/9] eth: mlx5e: drop the now-dead HW-GRO and LRO vs XDP handling Date: Sat, 21 Nov 2026 17:01:09 -0800 Message-ID: <20261122010112.1471146-7-kuba@kernel.org> X-Mailer: git-send-email 2.56.1 In-Reply-To: <20261122010112.1471146-1-kuba@kernel.org> References: <20261122010112.1471146-1-kuba@kernel.org> X-Mailing-List: netdev@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Transfer-Encoding: 8bit The core clears HW-GRO and LRO before ndo_bpf runs and keeps them off for as long as a program is attached. mlx5e_fix_features() never sees either with params->xdp_prog set, and packet merge is always off by the time mlx5e_xdp_set() gets called, packet_merge.type only follows the two feature handlers. If tcp-data-split keeps HW-GRO on, the core refuses the attach with -EBUSY before calling the driver. The netdev_update_features() call at the end of mlx5e_xdp_set() was there to apply and release the XDP clause of mlx5e_fix_features(). The core recomputes the features itself, on detach after the program is gone. XDP features were only advertised with packet merge off, matching the old refusal. Key them off tcp-data-split instead, the only setting under which the attach is still refused. The AF_XDP check stays, the core doesn't know about XSK pools. This does change user visible behavior: attaching XDP with HW-GRO or LRO on used to fail with -EINVAL and now succeeds with them turned off. Signed-off-by: Jakub Kicinski --- v2: - drop the netdev_update_features() call from mlx5e_xdp_set() (Dragos) - key XDP features off tcp-data-split rather than packet merge (Dragos) v1: https://lore.kernel.org/20261118232315.3593731-6-kuba@kernel.org --- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 8 +++- .../net/ethernet/mellanox/mlx5/core/en_main.c | 40 +++---------------- 2 files changed, 12 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8e7c748caf2d..da224ad3dea9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -488,9 +488,13 @@ static int mlx5e_set_ringparam(struct net_device *dev, if (err) return err; - /* Might need to adjust HW-GRO if it was kept on/off due to hds. */ - if (dev->cfg->hds_config != kernel_param->tcp_data_split) + /* Might need to adjust HW-GRO if it was kept on/off due to hds. + * XDP features depend on hds as well. + */ + if (dev->cfg->hds_config != kernel_param->tcp_data_split) { netdev_update_features(priv->netdev); + mlx5e_set_xdp_feature(priv); + } return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 06a8a4be4be7..08568137d044 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4487,12 +4487,14 @@ static int mlx5e_handle_feature(struct net_device *netdev, void mlx5e_set_xdp_feature(struct mlx5e_priv *priv) { + struct netdev_config *cfg = priv->netdev->cfg_pending; struct mlx5e_params *params = &priv->channels.params; struct net_device *netdev = priv->netdev; xdp_features_t val = 0; + /* XDP can't run with HW-GRO, and tcp-data-split keeps HW-GRO on */ if (netdev->netdev_ops->ndo_bpf && - params->packet_merge.type == MLX5E_PACKET_MERGE_NONE) + cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY | NETDEV_XDP_ACT_RX_SG; @@ -4604,17 +4606,6 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, } } - if (params->xdp_prog) { - if (features & NETIF_F_LRO) { - netdev_warn(netdev, "LRO is incompatible with XDP\n"); - features &= ~NETIF_F_LRO; - } - if (features & NETIF_F_GRO_HW) { - netdev_warn(netdev, "HW GRO is incompatible with XDP\n"); - features &= ~NETIF_F_GRO_HW; - } - } - if (priv->xsk.refcnt) { if (features & NETIF_F_LRO) { netdev_warn(netdev, "LRO is incompatible with AF_XDP (%u XSKs are active)\n", @@ -5203,20 +5194,6 @@ static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue) queue_work(priv->wq, &priv->tx_timeout_work); } -static int mlx5e_xdp_allowed(struct net_device *netdev, struct mlx5_core_dev *mdev, - struct mlx5e_params *params) -{ - if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE) { - netdev_warn(netdev, "can't set XDP while HW-GRO/LRO is on, disable them first\n"); - return -EINVAL; - } - - if (!mlx5e_params_validate_xdp(netdev, mdev, params)) - return -EINVAL; - - return 0; -} - static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog) { struct bpf_prog *old_prog; @@ -5241,10 +5218,9 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) new_params = priv->channels.params; new_params.xdp_prog = prog; - if (prog) { - err = mlx5e_xdp_allowed(netdev, priv->mdev, &new_params); - if (err) - goto unlock; + if (prog && !mlx5e_params_validate_xdp(netdev, priv->mdev, &new_params)) { + err = -EINVAL; + goto unlock; } /* no need for full reset when exchanging programs */ @@ -5279,10 +5255,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) unlock: mutex_unlock(&priv->state_lock); - /* Need to fix some features. */ - if (!err) - netdev_update_features(netdev); - return err; } -- 2.56.1