Merge tag 'v5.15' into rdma.git for-next

Pull in the accepted for-rc patches as the next merge needs a newer base.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

12 files changed, 97 insertions, 67 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 41684a6c44e9..a88a1a48229f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -199,6 +199,9 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 
+int mlx5e_fs_init(struct mlx5e_priv *priv);
+void mlx5e_fs_cleanup(struct mlx5e_priv *priv);
+
 int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int  trap_id, int tir_num);
 void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv);
 int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int  trap_id, int tir_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index b4e986818794..4a13ef561587 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -10,6 +10,8 @@
 #include "en_tc.h"
 #include "rep/tc.h"
 #include "rep/neigh.h"
+#include "lag.h"
+#include "lag_mp.h"
 
 struct mlx5e_tc_tun_route_attr {
 	struct net_device *out_dev;
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 33de8f0092a6..fb5397324aa4 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
@@ -141,8 +141,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 	 * Pkt: MAC  IP     ESP  IP    L4
 	 *
 	 * Transport Mode:
-	 * SWP:      OutL3       InL4
-	 *           InL3
+	 * SWP:      OutL3       OutL4
 	 * Pkt: MAC  IP     ESP  L4
 	 *
 	 * Tunnel(VXLAN TCP/UDP) over Transport Mode
@@ -171,31 +170,35 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 		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)
+		switch (xo->proto) {
+		case IPPROTO_UDP:
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP;
+			fallthrough;
+		case IPPROTO_TCP:
+			/* IP | ESP | TCP */
+			eseg->swp_outer_l4_offset = skb_inner_transport_offset(skb) / 2;
+			break;
+		default:
+			break;
+		}
+	} else {
+		/* Tunnel(VXLAN TCP/UDP) over Transport Mode */
+		switch (xo->inner_ipproto) {
+		case 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;
+			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;
+		}
 	}
 
-	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_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index c06b4b938ae7..d226cc5ab1d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1186,10 +1186,6 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
 	struct mlx5e_flow_table *ft;
 	int err;
 
-	priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL);
-	if (!priv->fs.vlan)
-		return -ENOMEM;
-
 	ft = &priv->fs.vlan->ft;
 	ft->num_groups = 0;
 
@@ -1198,10 +1194,8 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
 	ft_attr.prio = MLX5E_NIC_PRIO;
 
 	ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
-	if (IS_ERR(ft->t)) {
-		err = PTR_ERR(ft->t);
-		goto err_free_t;
-	}
+	if (IS_ERR(ft->t))
+		return PTR_ERR(ft->t);
 
 	ft->g = kcalloc(MLX5E_NUM_VLAN_GROUPS, sizeof(*ft->g), GFP_KERNEL);
 	if (!ft->g) {
@@ -1221,9 +1215,6 @@ err_free_g:
 	kfree(ft->g);
 err_destroy_vlan_table:
 	mlx5_destroy_flow_table(ft->t);
-err_free_t:
-	kvfree(priv->fs.vlan);
-	priv->fs.vlan = NULL;
 
 	return err;
 }
@@ -1232,7 +1223,6 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv)
 {
 	mlx5e_del_vlan_rules(priv);
 	mlx5e_destroy_flow_table(&priv->fs.vlan->ft);
-	kvfree(priv->fs.vlan);
 }
 
 static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
@@ -1351,3 +1341,17 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
 	mlx5e_arfs_destroy_tables(priv);
 	mlx5e_ethtool_cleanup_steering(priv);
 }
+
+int mlx5e_fs_init(struct mlx5e_priv *priv)
+{
+	priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL);
+	if (!priv->fs.vlan)
+		return -ENOMEM;
+	return 0;
+}
+
+void mlx5e_fs_cleanup(struct mlx5e_priv *priv)
+{
+	kvfree(priv->fs.vlan);
+	priv->fs.vlan = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 63076d0e8b63..5fce9401ac74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4577,6 +4577,12 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 
 	mlx5e_timestamp_init(priv);
 
+	err = mlx5e_fs_init(priv);
+	if (err) {
+		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+		return err;
+	}
+
 	err = mlx5e_ipsec_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err);
@@ -4594,6 +4600,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 	mlx5e_health_destroy_reporters(priv);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
+	mlx5e_fs_cleanup(priv);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ba8164792016..129ff7e0d65c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -67,6 +67,8 @@
 #include "lib/fs_chains.h"
 #include "diag/en_tc_tracepoint.h"
 #include <asm/div64.h>
+#include "lag.h"
+#include "lag_mp.h"
 
 #define nic_chains(priv) ((priv)->fs.tc.chains)
 #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c63d78eda606..188994d091c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -213,19 +213,18 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
 	memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
 }
 
-/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet),
- * need to set L3 checksum flag for IPsec
- */
 static void
 ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			    struct mlx5_wqe_eth_seg *eseg)
 {
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
 	eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
-	if (skb->encapsulation) {
-		eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
+	if (xo->inner_ipproto) {
+		eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM;
+	} else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
+		eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 		sq->stats->csum_partial_inner++;
-	} else {
-		sq->stats->csum_partial++;
 	}
 }
 
@@ -234,6 +233,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			    struct mlx5e_accel_tx_state *accel,
 			    struct mlx5_wqe_eth_seg *eseg)
 {
+	if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) {
+		ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
+		return;
+	}
+
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
 		if (skb->encapsulation) {
@@ -249,8 +253,6 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
 		sq->stats->csum_partial++;
 #endif
-	} else if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) {
-		ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
 	} else
 		sq->stats->csum_none++;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 985e305179d1..c6cc67cb4f6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -473,10 +473,9 @@ esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 
 err_min_rate:
 	list_del(&group->list);
-	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
-						  SCHEDULING_HIERARCHY_E_SWITCH,
-						  group->tsar_ix);
-	if (err)
+	if (mlx5_destroy_scheduling_element_cmd(esw->dev,
+						SCHEDULING_HIERARCHY_E_SWITCH,
+						group->tsar_ix))
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed");
 err_sched_elem:
 	kfree(group);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index ca5690b0a7ab..d2105c1635c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -442,6 +442,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	if (!mlx5_lag_is_ready(ldev)) {
 		do_bond = false;
 	} else {
+		/* VF LAG is in multipath mode, ignore bond change requests */
+		if (mlx5_lag_is_multipath(dev0))
+			return;
+
 		tracker = ldev->tracker;
 
 		do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index f239b352a58a..21fdaf708f1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -9,20 +9,23 @@
 #include "eswitch.h"
 #include "lib/mlx5.h"
 
+static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
+}
+
 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
 {
 	if (!mlx5_lag_is_ready(ldev))
 		return false;
 
+	if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev))
+		return false;
+
 	return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev,
 					 ldev->pf[MLX5_LAG_P2].dev);
 }
 
-static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
-{
-	return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
-}
-
 bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
index 729c839397a8..dea199e79bed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -24,12 +24,14 @@ struct lag_mp {
 void mlx5_lag_mp_reset(struct mlx5_lag *ldev);
 int mlx5_lag_mp_init(struct mlx5_lag *ldev);
 void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 
 static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {};
 static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
 static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { return false; }
 
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_LAG_MP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 13b0259f7ea6..fcace73eae40 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci,
 	struct sk_buff *skb;
 	int err;
 
-	elem_info->u.rdq.skb = NULL;
 	skb = netdev_alloc_skb_ip_align(NULL, buf_len);
 	if (!skb)
 		return -ENOMEM;
 
-	/* Assume that wqe was previously zeroed. */
-
 	err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data,
 				     buf_len, DMA_FROM_DEVICE);
 	if (err)
@@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_elem_info *elem_info;
 	struct mlxsw_rx_info rx_info = {};
-	char *wqe;
+	char wqe[MLXSW_PCI_WQE_SIZE];
 	struct sk_buff *skb;
 	u16 byte_count;
 	int err;
 
 	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
-	skb = elem_info->u.sdq.skb;
-	if (!skb)
-		return;
-	wqe = elem_info->elem;
-	mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+	skb = elem_info->u.rdq.skb;
+	memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE);
 
 	if (q->consumer_counter++ != consumer_counter_limit)
 		dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
 
+	err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
+	if (err) {
+		dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+		goto out;
+	}
+
+	mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+
 	if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
 		rx_info.is_lag = true;
 		rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
@@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	skb_put(skb, byte_count);
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
 
-	memset(wqe, 0, q->elem_size);
-	err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
-	if (err)
-		dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+out:
 	/* Everything is set up, ring doorbell to pass elem to HW */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);