Merge tag 'mlx5-fixes-2020-11-03' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2020-11-03

v1->v2:
 - Fix fixes line tag in patch #1
 - Toss ktls refcount leak fix, Maxim will look further into the root
   cause.
 - Toss eswitch chain 0 prio patch, until we determine if it is needed
   for -rc and net.

* tag 'mlx5-fixes-2020-11-03' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Fix incorrect access of RCU-protected xdp_prog
  net/mlx5e: Fix VXLAN synchronization after function reload
  net/mlx5: E-switch, Avoid extack error log for disabled vport
  net/mlx5: Fix deletion of duplicate rules
  net/mlx5e: Use spin_lock_bh for async_icosq_lock
  net/mlx5e: Protect encap route dev from concurrent release
  net/mlx5e: Fix modify header actions memory leak
====================

Link: https://lore.kernel.org/r/20201105202129.23644-1-saeedm@nvidia.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -107,12 +107,16 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 		mlx5e_tc_encap_flows_del(priv, e, &flow_list);
 
 	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+		struct net_device *route_dev;
+
 		ether_addr_copy(e->h_dest, ha);
 		ether_addr_copy(eth->h_dest, ha);
 		/* Update the encap source mac, in case that we delete
 		 * the flows when encap source mac changed.
 		 */
-		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
+		route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex);
+		if (route_dev)
+			ether_addr_copy(eth->h_source, route_dev->dev_addr);
 
 		mlx5e_tc_encap_flows_add(priv, e, &flow_list);
 	}

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c

@@ -77,13 +77,13 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct net_device **route_dev,
-				   struct flowi4 *fl4,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
+static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv,
+				       struct net_device *mirred_dev,
+				       struct net_device **out_dev,
+				       struct net_device **route_dev,
+				       struct flowi4 *fl4,
+				       struct neighbour **out_n,
+				       u8 *out_ttl)
 {
 	struct neighbour *n;
 	struct rtable *rt;
@@ -117,18 +117,28 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 		ip_rt_put(rt);
 		return ret;
 	}
+	dev_hold(*route_dev);
 
 	if (!(*out_ttl))
 		*out_ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
 	ip_rt_put(rt);
-	if (!n)
+	if (!n) {
+		dev_put(*route_dev);
 		return -ENOMEM;
+	}
 
 	*out_n = n;
 	return 0;
 }
 
+static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev,
+					struct neighbour *n)
+{
+	neigh_release(n);
+	dev_put(route_dev);
+}
+
 static const char *mlx5e_netdev_kind(struct net_device *dev)
 {
 	if (dev->rtnl_link_ops)
@@ -193,8 +203,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	fl4.saddr = tun_key->u.ipv4.src;
 	ttl = tun_key->ttl;
 
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
-				      &fl4, &n, &ttl);
+	err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev,
+					  &fl4, &n, &ttl);
 	if (err)
 		return err;
 
@@ -223,7 +233,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
-	e->route_dev = route_dev;
+	e->route_dev_ifindex = route_dev->ifindex;
 
 	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -278,7 +288,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
+	mlx5e_route_lookup_ipv4_put(route_dev, n);
 	return err;
 
 destroy_neigh_entry:
@@ -286,18 +296,18 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 free_encap:
 	kfree(encap_header);
 release_neigh:
-	neigh_release(n);
+	mlx5e_route_lookup_ipv4_put(route_dev, n);
 	return err;
 }
 
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct net_device **route_dev,
-				   struct flowi6 *fl6,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
+static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv,
+				       struct net_device *mirred_dev,
+				       struct net_device **out_dev,
+				       struct net_device **route_dev,
+				       struct flowi6 *fl6,
+				       struct neighbour **out_n,
+				       u8 *out_ttl)
 {
 	struct dst_entry *dst;
 	struct neighbour *n;
@@ -318,15 +328,25 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 		return ret;
 	}
 
+	dev_hold(*route_dev);
 	n = dst_neigh_lookup(dst, &fl6->daddr);
 	dst_release(dst);
-	if (!n)
+	if (!n) {
+		dev_put(*route_dev);
 		return -ENOMEM;
+	}
 
 	*out_n = n;
 	return 0;
 }
 
+static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev,
+					struct neighbour *n)
+{
+	neigh_release(n);
+	dev_put(route_dev);
+}
+
 int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e)
@@ -348,8 +368,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
 
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
-				      &fl6, &n, &ttl);
+	err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev,
+					  &fl6, &n, &ttl);
 	if (err)
 		return err;
 
@@ -378,7 +398,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
-	e->route_dev = route_dev;
+	e->route_dev_ifindex = route_dev->ifindex;
 
 	/* It's importent to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -433,7 +453,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
+	mlx5e_route_lookup_ipv6_put(route_dev, n);
 	return err;
 
 destroy_neigh_entry:
@@ -441,7 +461,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 free_encap:
 	kfree(encap_header);
 release_neigh:
-	neigh_release(n);
+	mlx5e_route_lookup_ipv6_put(route_dev, n);
 	return err;
 }
 #endif

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -122,9 +122,9 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c)
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
 	/* TX queue is created active. */
 
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 	mlx5e_trigger_irq(&c->async_icosq);
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 }
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c

@@ -36,9 +36,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 		if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state))
 			return 0;
 
-		spin_lock(&c->async_icosq_lock);
+		spin_lock_bh(&c->async_icosq_lock);
 		mlx5e_trigger_irq(&c->async_icosq);
-		spin_unlock(&c->async_icosq_lock);
+		spin_unlock_bh(&c->async_icosq_lock);
 	}
 
 	return 0;

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

@@ -188,7 +188,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c,
 
 	err = 0;
 	sq = &c->async_icosq;
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 
 	cseg = post_static_params(sq, priv_rx);
 	if (IS_ERR(cseg))
@@ -199,7 +199,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c,
 
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
 unlock:
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 
 	return err;
 
@@ -265,10 +265,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
 
-	spin_lock(&sq->channel->async_icosq_lock);
+	spin_lock_bh(&sq->channel->async_icosq_lock);
 
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
-		spin_unlock(&sq->channel->async_icosq_lock);
+		spin_unlock_bh(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
 		goto err_dma_unmap;
 	}
@@ -299,7 +299,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	icosq_fill_wi(sq, pi, &wi);
 	sq->pc++;
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
-	spin_unlock(&sq->channel->async_icosq_lock);
+	spin_unlock_bh(&sq->channel->async_icosq_lock);
 
 	return 0;
 
@@ -360,7 +360,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx
 	err = 0;
 
 	sq = &c->async_icosq;
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 
 	cseg = post_static_params(sq, priv_rx);
 	if (IS_ERR(cseg)) {
@@ -372,7 +372,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
 	priv_rx->stats->tls_resync_res_ok++;
 unlock:
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 
 	return err;
 }

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

@@ -5253,6 +5253,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
+	mlx5_vxlan_reset_to_default(mdev->vxlan);
 }
 
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv)

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

@@ -186,7 +186,7 @@ struct mlx5e_encap_entry {
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 
 	struct net_device *out_dev;
-	struct net_device *route_dev;
+	int route_dev_ifindex;
 	struct mlx5e_tc_tunnel *tunnel;
 	int reformat_type;
 	u8 flags;

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

@@ -1584,7 +1584,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 out:
-	if (rq->xdp_prog)
+	if (rcu_access_pointer(rq->xdp_prog))
 		mlx5e_xdp_rx_poll_complete(rq);
 
 	mlx5_cqwq_update_db_record(cqwq);

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

@@ -4658,6 +4658,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	return flow;
 
 err_free:
+	dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 	mlx5e_flow_put(priv, flow);
 out:
 	return ERR_PTR(err);
@@ -4802,6 +4803,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	return 0;
 
 err_free:
+	dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 	mlx5e_flow_put(priv, flow);
 out:
 	return err;

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

@@ -1902,8 +1902,6 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
 		ether_addr_copy(hw_addr, vport->info.mac);
 		*hw_addr_len = ETH_ALEN;
 		err = 0;
-	} else {
-		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
 	}
 	mutex_unlock(&esw->state_lock);
 	return err;

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

@@ -2010,10 +2010,11 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 	down_write_ref_node(&fte->node, false);
 	for (i = handle->num_rules - 1; i >= 0; i--)
 		tree_remove_node(&handle->rule[i]->node, true);
-	if (fte->modify_mask && fte->dests_size) {
-		modify_fte(fte);
+	if (fte->dests_size) {
+		if (fte->modify_mask)
+			modify_fte(fte);
 		up_write_ref_node(&fte->node, false);
-	} else {
+	} else if (list_empty(&fte->node.children)) {
 		del_hw_fte(&fte->node);
 		/* Avoid double call to del_hw_fte */
 		fte->node.del_hw_func = NULL;

drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c

@@ -167,6 +167,17 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
 }
 
 void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
+{
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT);
+	WARN_ON(!hash_empty(vxlan->htable));
+
+	kfree(vxlan);
+}
+
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan)
 {
 	struct mlx5_vxlan_port *vxlanp;
 	struct hlist_node *tmp;
@@ -175,12 +186,12 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
 	if (!mlx5_vxlan_allowed(vxlan))
 		return;
 
-	/* Lockless since we are the only hash table consumers*/
 	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
-		hash_del(&vxlanp->hlist);
-		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
-		kfree(vxlanp);
+		/* Don't delete default UDP port added by the HW.
+		 * Remove only user configured ports
+		 */
+		if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT)
+			continue;
+		mlx5_vxlan_del_port(vxlan, vxlanp->udp_port);
 	}
-
-	kfree(vxlan);
 }

drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h

@@ -56,6 +56,7 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
 int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
 int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
 bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan);
 #else
 static inline struct mlx5_vxlan*
 mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
@@ -63,6 +64,7 @@ static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
 static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
 static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
 static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; }
+static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; }
 #endif
 
 #endif /* __MLX5_VXLAN_H__ */