Merge tag 'mlx5-fixes-2020-11-17' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2020-11-17

This series introduces some fixes to mlx5 driver.

* tag 'mlx5-fixes-2020-11-17' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5: fix error return code in mlx5e_tc_nic_init()
  net/mlx5: E-Switch, Fail mlx5_esw_modify_vport_rate if qos disabled
  net/mlx5: Disable QoS when min_rates on all VFs are zero
  net/mlx5: Clear bw_share upon VF disable
  net/mlx5: Add handling of port type in rule deletion
  net/mlx5e: Fix check if netdev is bond slave
  net/mlx5e: Fix IPsec packet drop by mlx5e_tc_update_skb
  net/mlx5e: Set IPsec WAs only in IP's non checksum partial case.
  net/mlx5e: Fix refcount leak on kTLS RX resync
====================

Link: https://lore.kernel.org/r/20201117195702.386113-1-saeedm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c

@@ -187,7 +187,7 @@ static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev)
 	struct mlx5e_priv *priv;
 
 	/* A given netdev is not a representor or not a slave of LAG configuration */
-	if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev))
+	if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev))
 		return false;
 
 	priv = netdev_priv(netdev);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c

@@ -64,13 +64,13 @@ static int rx_err_add_rule(struct mlx5e_priv *priv,
 	if (!spec)
 		return -ENOMEM;
 
-	/* Action to copy 7 bit ipsec_syndrome to regB[0:6] */
+	/* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
 	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
 	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
 	MLX5_SET(copy_action_in, action, src_offset, 0);
 	MLX5_SET(copy_action_in, action, length, 7);
 	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(copy_action_in, action, dst_offset, 0);
+	MLX5_SET(copy_action_in, action, dst_offset, 24);
 
 	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
 					      1, action);
@@ -488,13 +488,13 @@ static int rx_add_rule(struct mlx5e_priv *priv,
 
 	setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act);
 
-	/* Set 1  bit ipsec marker */
-	/* Set 24 bit ipsec_obj_id */
+	/* Set bit[31] ipsec marker */
+	/* Set bit[23-0] ipsec_obj_id */
 	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
 	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1);
-	MLX5_SET(set_action_in, action, offset, 7);
-	MLX5_SET(set_action_in, action, length, 25);
+	MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31)));
+	MLX5_SET(set_action_in, action, offset, 0);
+	MLX5_SET(set_action_in, action, length, 32);
 
 	modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL,
 					      1, action);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c

@@ -453,7 +453,6 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct mlx5_cqe64 *cqe)
 {
 	u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata);
-	u8 ipsec_syndrome = ipsec_meta_data & 0xFF;
 	struct mlx5e_priv *priv;
 	struct xfrm_offload *xo;
 	struct xfrm_state *xs;
@@ -481,7 +480,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
 
-	switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) {
+	switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) {
 	case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED:
 		xo->status = CRYPTO_SUCCESS;
 		if (WARN_ON_ONCE(priv->ipsec->no_trailer))

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h

@@ -39,9 +39,10 @@
 #include "en.h"
 #include "en/txrx.h"
 
-#define MLX5_IPSEC_METADATA_MARKER_MASK      (0x80)
-#define MLX5_IPSEC_METADATA_SYNDROM_MASK     (0x7F)
-#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF)
+/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */
+#define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
+#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0))
+#define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
 
 struct mlx5e_accel_tx_ipsec_state {
 	struct xfrm_offload *xo;
@@ -78,7 +79,7 @@ static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_st
 
 static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe)
 {
-	return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata));
+	return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata));
 }
 
 static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st)

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c

@@ -476,19 +476,22 @@ static void resync_update_sn(struct mlx5e_rq *rq, struct sk_buff *skb)
 
 	depth += sizeof(struct tcphdr);
 
-	if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT))
+	if (unlikely(!sk))
 		return;
 
-	if (unlikely(!resync_queue_get_psv(sk)))
-		return;
+	if (unlikely(sk->sk_state == TCP_TIME_WAIT))
+		goto unref;
 
-	skb->sk = sk;
-	skb->destructor = sock_edemux;
+	if (unlikely(!resync_queue_get_psv(sk)))
+		goto unref;
 
 	seq = th->seq;
 	datalen = skb->len - depth;
 	tls_offload_rx_resync_async_request_start(sk, seq, datalen);
 	rq->stats->tls_resync_req_start++;
+
+unref:
+	sock_gen_put(sk);
 }
 
 void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk,

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -5229,8 +5229,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 	tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
 				 MLX5_FLOW_NAMESPACE_KERNEL);
-	if (IS_ERR(tc->ct))
+	if (IS_ERR(tc->ct)) {
+		err = PTR_ERR(tc->ct);
 		goto err_ct;
+	}
 
 	tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
 	err = register_netdevice_notifier_dev_net(priv->netdev,

drivers/net/ethernet/mellanox/mlx5/core/en_tc.h

@@ -283,6 +283,9 @@ static inline bool mlx5e_cqe_regb_chain(struct mlx5_cqe64 *cqe)
 
 	reg_b = be32_to_cpu(cqe->ft_metadata);
 
+	if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS))
+		return false;
+
 	chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
 	if (chain)
 		return true;

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -144,7 +144,9 @@ 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);
 }
 
-/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */
+/* 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)
@@ -154,19 +156,13 @@ ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
 		sq->stats->csum_partial_inner++;
 	} else {
-		eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 		sq->stats->csum_partial++;
 	}
 }
 
 static inline void
 mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
 {
-	if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
-		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) {
@@ -177,6 +173,9 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct
 			eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
 			sq->stats->csum_partial++;
 		}
+	} else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
+		ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
+
 	} else
 		sq->stats->csum_none++;
 }

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1142,6 +1142,10 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+	if (!vport->qos.enabled)
+		return -EOPNOTSUPP;
+
 	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
 
 	return mlx5_modify_scheduling_element_cmd(esw->dev,
@@ -1408,6 +1412,7 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
 	int i;
 
 	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+		memset(&vport->qos, 0, sizeof(vport->qos));
 		memset(&vport->info, 0, sizeof(vport->info));
 		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 	}
@@ -2221,12 +2226,15 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
 		max_guarantee = evport->info.min_rate;
 	}
 
-	return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+	if (max_guarantee)
+		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+	return 0;
 }
 
-static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
+static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
 {
 	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	u32 divider = calculate_vports_min_rate_divider(esw);
 	struct mlx5_vport *evport;
 	u32 vport_max_rate;
 	u32 vport_min_rate;
@@ -2239,9 +2247,9 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 			continue;
 		vport_min_rate = evport->info.min_rate;
 		vport_max_rate = evport->info.max_rate;
-		bw_share = MLX5_MIN_BW_SHARE;
+		bw_share = 0;
 
-		if (vport_min_rate)
+		if (divider)
 			bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate,
 							 divider,
 							 fw_max_bw_share);
@@ -2266,7 +2274,6 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	u32 fw_max_bw_share;
 	u32 previous_min_rate;
-	u32 divider;
 	bool min_rate_supported;
 	bool max_rate_supported;
 	int err = 0;
@@ -2291,8 +2298,7 @@ int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 
 	previous_min_rate = evport->info.min_rate;
 	evport->info.min_rate = min_rate;
-	divider = calculate_vports_min_rate_divider(esw);
-	err = normalize_vports_min_rate(esw, divider);
+	err = normalize_vports_min_rate(esw);
 	if (err) {
 		evport->info.min_rate = previous_min_rate;
 		goto unlock;

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

@@ -534,6 +534,13 @@ static void del_sw_hw_rule(struct fs_node *node)
 		goto out;
 	}
 
+	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT &&
+	    --fte->dests_size) {
+		fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+		goto out;
+	}
+
 	if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
 	    --fte->dests_size) {
 		fte->modify_mask |=