Merge tag 'mlx5-net-next-2021-06-22' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-net-next-2021-06-22

1) Various minor cleanups and fixes from net-next branch
2) Optimize mlx5 feature check on tx and
   a fix to allow Vxlan with Ipsec offloads
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 130 insertions, 40 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index d62f90aedade..e1a5a79e27c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -12,7 +12,6 @@ config MLX5_CORE
 	depends on MLXFW || !MLXFW
 	depends on PTP_1588_CLOCK || !PTP_1588_CLOCK
 	depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE
-	default n
 	help
 	  Core driver for low level functionality of the ConnectX-4 and
 	  Connect-IB cards by Mellanox Technologies.
@@ -36,7 +35,6 @@ config MLX5_CORE_EN
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	select PAGE_POOL
 	select DIMLIB
-	default n
 	help
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
 
@@ -141,7 +139,6 @@ config MLX5_CORE_EN_DCB
 config MLX5_CORE_IPOIB
 	bool "Mellanox 5th generation network adapters (connectX series) IPoIB offloads support"
 	depends on MLX5_CORE_EN
-	default n
 	help
 	  MLX5 IPoIB offloads & acceleration support.
 
@@ -149,7 +146,6 @@ config MLX5_FPGA_IPSEC
 	bool "Mellanox Technologies IPsec Innova support"
 	depends on MLX5_CORE
 	depends on MLX5_FPGA
-	default n
 	help
 	Build IPsec support for the Innova family of network cards by Mellanox
 	Technologies. Innova network cards are comprised of a ConnectX chip
@@ -163,7 +159,6 @@ config MLX5_IPSEC
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
 	select MLX5_ACCEL
-	default n
 	help
 	Build IPsec support for the Connect-X family of network cards by Mellanox
 	Technologies.
@@ -176,7 +171,6 @@ config MLX5_EN_IPSEC
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
 	depends on MLX5_FPGA_IPSEC || MLX5_IPSEC
-	default n
 	help
 	  Build support for IPsec cryptography-offload acceleration in the NIC.
 	  Note: Support for hardware with this capability needs to be selected
@@ -189,7 +183,6 @@ config MLX5_FPGA_TLS
 	depends on MLX5_CORE_EN
 	depends on MLX5_FPGA
 	select MLX5_EN_TLS
-	default n
 	help
 	Build TLS support for the Innova family of network cards by Mellanox
 	Technologies. Innova network cards are comprised of a ConnectX chip
@@ -204,7 +197,6 @@ config MLX5_TLS
 	depends on MLX5_CORE_EN
 	select MLX5_ACCEL
 	select MLX5_EN_TLS
-	default n
 	help
 	Build TLS support for the Connect-X family of network cards by Mellanox
 	Technologies.
@@ -227,7 +219,6 @@ config MLX5_SW_STEERING
 config MLX5_SF
 	bool "Mellanox Technologies subfunction device support using auxiliary device"
 	depends on MLX5_CORE && MLX5_CORE_EN
-	default n
 	help
 	Build support for subfuction device in the NIC. A Mellanox subfunction
 	device can support RDMA, netdevice and vdpa device.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index a97e8d205094..33de8f0092a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -136,8 +136,6 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 				struct mlx5_wqe_eth_seg *eseg, u8 mode,
 				struct xfrm_offload *xo)
 {
-	struct mlx5e_swp_spec swp_spec = {};
-
 	/* Tunnel Mode:
 	 * SWP:      OutL3       InL3  InL4
 	 * Pkt: MAC  IP     ESP  IP    L4
@@ -146,23 +144,58 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 	 * SWP:      OutL3       InL4
 	 *           InL3
 	 * Pkt: MAC  IP     ESP  L4
+	 *
+	 * Tunnel(VXLAN TCP/UDP) over Transport Mode
+	 * SWP:      OutL3                   InL3  InL4
+	 * Pkt: MAC  IP     ESP  UDP  VXLAN  IP    L4
 	 */
-	swp_spec.l3_proto = skb->protocol;
-	swp_spec.is_tun = mode == XFRM_MODE_TUNNEL;
-	if (swp_spec.is_tun) {
-		if (xo->proto == IPPROTO_IPV6) {
-			swp_spec.tun_l3_proto = htons(ETH_P_IPV6);
-			swp_spec.tun_l4_proto = inner_ipv6_hdr(skb)->nexthdr;
-		} else {
-			swp_spec.tun_l3_proto = htons(ETH_P_IP);
-			swp_spec.tun_l4_proto = inner_ip_hdr(skb)->protocol;
-		}
-	} else {
-		swp_spec.tun_l3_proto = skb->protocol;
-		swp_spec.tun_l4_proto = xo->proto;
+
+	/* Shared settings */
+	eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2;
+	if (skb->protocol == htons(ETH_P_IPV6))
+		eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6;
+
+	/* Tunnel mode */
+	if (mode == XFRM_MODE_TUNNEL) {
+		eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+		if (xo->proto == IPPROTO_IPV6)
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+		if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP)
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+		return;
+	}
+
+	/* Transport mode */
+	if (mode != XFRM_MODE_TRANSPORT)
+		return;
+
+	if (!xo->inner_ipproto) {
+		eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2;
+		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+		if (skb->protocol == htons(ETH_P_IPV6))
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+		if (xo->proto == IPPROTO_UDP)
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+		return;
+	}
+
+	/* Tunnel(VXLAN TCP/UDP) over Transport Mode */
+	switch (xo->inner_ipproto) {
+	case IPPROTO_UDP:
+		eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+		fallthrough;
+	case IPPROTO_TCP:
+		eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+		eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2;
+		if (skb->protocol == htons(ETH_P_IPV6))
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+		break;
+	default:
+		break;
 	}
 
-	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+	return;
 }
 
 void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 3e80742a3caf..5120a59361e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -93,18 +93,38 @@ static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg)
 void mlx5e_ipsec_tx_build_eseg(struct mlx5e_priv *priv, struct sk_buff *skb,
 			       struct mlx5_wqe_eth_seg *eseg);
 
-static inline bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev,
-					     netdev_features_t features)
+static inline netdev_features_t
+mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features)
 {
+	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct sec_path *sp = skb_sec_path(skb);
 
-	if (sp && sp->len) {
+	if (sp && sp->len && xo) {
 		struct xfrm_state *x = sp->xvec[0];
 
-		if (x && x->xso.offload_handle)
-			return true;
+		if (!x || !x->xso.offload_handle)
+			goto out_disable;
+
+		if (xo->inner_ipproto) {
+			/* Cannot support tunnel packet over IPsec tunnel mode
+			 * because we cannot offload three IP header csum
+			 */
+			if (x->props.mode == XFRM_MODE_TUNNEL)
+				goto out_disable;
+
+			/* Only support UDP or TCP L4 checksum */
+			if (xo->inner_ipproto != IPPROTO_UDP &&
+			    xo->inner_ipproto != IPPROTO_TCP)
+				goto out_disable;
+		}
+
+		return features;
+
 	}
-	return false;
+
+	/* Disable CSUM and GSO for software IPsec */
+out_disable:
+	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
 #else
@@ -120,8 +140,9 @@ static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg)
 }
 
 static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { return false; }
-static inline bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev,
-					     netdev_features_t features) { return false; }
+static inline netdev_features_t
+mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features)
+{ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); }
 #endif /* CONFIG_MLX5_EN_IPSEC */
 
 #endif /* __MLX5E_IPSEC_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7d732fac09f0..414a73d16619 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4331,6 +4331,11 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		if (port == GENEVE_UDP_PORT && mlx5_geneve_tx_allowed(priv->mdev))
 			return features;
 #endif
+		break;
+#ifdef CONFIG_MLX5_EN_IPSEC
+	case IPPROTO_ESP:
+		return mlx5e_ipsec_feature_check(skb, features);
+#endif
 	}
 
 out:
@@ -4347,9 +4352,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	features = vlan_features_check(skb, features);
 	features = vxlan_features_check(skb, features);
 
-	if (mlx5e_ipsec_feature_check(skb, netdev, features))
-		return features;
-
 	/* Validate if the tunneled packet is being offloaded by HW */
 	if (skb->encapsulation &&
 	    (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c7efd177da1f..6e074cc457de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -712,7 +712,7 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev,
 	struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
 	int err;
 
-	if (!param->affinity)
+	if (!cpumask_available(param->affinity))
 		return ERR_PTR(-EINVAL);
 
 	if (!eq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2cd7aea5d329..b8617458a3fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2969,8 +2969,11 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 		return err;
 
 	steering = kzalloc(sizeof(*steering), GFP_KERNEL);
-	if (!steering)
+	if (!steering) {
+		err = -ENOMEM;
 		goto err;
+	}
+
 	steering->dev = dev;
 	dev->priv.steering = steering;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 27de8da8edf7..b25f764daa08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -479,7 +479,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec)
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_err(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_err(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c58a6d4eb610..1d803e890c76 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1024,6 +1024,7 @@ struct xfrm_offload {
 #define CRYPTO_INVALID_PROTOCOL			128
 
 	__u8			proto;
+	__u8			inner_ipproto;
 };
 
 struct sec_path {
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index e4cb0ff4dcf4..e321fc63a2e9 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -565,6 +565,42 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
 	return 0;
 }
 
+/* For partial checksum offload, the outer header checksum is calculated
+ * by software and the inner header checksum is calculated by hardware.
+ * This requires hardware to know the inner packet type to calculate
+ * the inner header checksum. Save inner ip protocol here to avoid
+ * traversing the packet in the vendor's xmit code.
+ * If the encap type is IPIP, just save skb->inner_ipproto. Otherwise,
+ * get the ip protocol from the IP header.
+ */
+static void xfrm_get_inner_ipproto(struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	const struct ethhdr *eth;
+
+	if (!xo)
+		return;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) {
+		xo->inner_ipproto = skb->inner_ipproto;
+		return;
+	}
+
+	if (skb->inner_protocol_type != ENCAP_TYPE_ETHER)
+		return;
+
+	eth = (struct ethhdr *)skb_inner_mac_header(skb);
+
+	switch (ntohs(eth->h_proto)) {
+	case ETH_P_IPV6:
+		xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr;
+		break;
+	case ETH_P_IP:
+		xo->inner_ipproto = inner_ip_hdr(skb)->protocol;
+		break;
+	}
+}
+
 int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
@@ -594,12 +630,15 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 			kfree_skb(skb);
 			return -ENOMEM;
 		}
-		skb->encapsulation = 1;
 
 		sp->olen++;
 		sp->xvec[sp->len++] = x;
 		xfrm_state_hold(x);
 
+		if (skb->encapsulation)
+			xfrm_get_inner_ipproto(skb);
+		skb->encapsulation = 1;
+
 		if (skb_is_gso(skb)) {
 			if (skb->inner_protocol)
 				return xfrm_output_gso(net, sk, skb);