Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix state pruning in bpf verifier wrt. alignment, from Daniel
    Borkmann.

 2) Handle non-linear SKBs properly in SCTP ICMP parsing, from Davide
    Caratti.

 3) Fix bit field definitions for rss_hash_type of descriptors in mlx5
    driver, from Jesper Brouer.

 4) Defer slave->link updates until bonding is ready to do a full commit
    to the new settings, from Nithin Sujir.

 5) Properly reference count ipv4 FIB metrics to avoid use after free
    situations, from Eric Dumazet and several others including Cong Wang
    and Julian Anastasov.

 6) Fix races in llc_ui_bind(), from Lin Zhang.

 7) Fix regression of ESP UDP encapsulation for TCP packets, from
    Steffen Klassert.

 8) Fix mdio-octeon driver Kconfig deps, from Randy Dunlap.

 9) Fix regression in setting DSCP on ipv6/GRE encapsulation, from Peter
    Dawson.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (43 commits)
  ipv4: add reference counting to metrics
  net: ethernet: ax88796: don't call free_irq without request_irq first
  ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets
  sctp: fix ICMP processing if skb is non-linear
  net: llc: add lock_sock in llc_ui_bind to avoid a race condition
  bonding: Don't update slave->link until ready to commit
  test_bpf: Add a couple of tests for BPF_JSGE.
  bpf: add various verifier test cases
  bpf: fix wrong exposure of map_flags into fdinfo for lpm
  bpf: add bpf_clone_redirect to bpf_helper_changes_pkt_data
  bpf: properly reset caller saved regs after helper call and ld_abs/ind
  bpf: fix incorrect pruning decision when alignment must be tracked
  arp: fixed -Wuninitialized compiler warning
  tcp: avoid fastopen API to be used on AF_UNSPEC
  net: move somaxconn init from sysctl code
  net: fix potential null pointer dereference
  geneve: fix fill_info when using collect_metadata
  virtio-net: enable TSO/checksum offloads for Q-in-Q vlans
  be2net: Fix offload features for Q-in-Q packets
  vlan: Fix tcp checksum offloads in Q-in-Q vlans
  ...

Documentation/devicetree/bindings/net/fsl-fec.txt

@@ -15,6 +15,10 @@ Optional properties:
 - phy-reset-active-high : If present then the reset sequence using the GPIO
   specified in the "phy-reset-gpios" property is reversed (H=reset state,
   L=operation state).
+- phy-reset-post-delay : Post reset delay in milliseconds. If present then
+  a delay of phy-reset-post-delay milliseconds will be observed after the
+  phy-reset-gpios has been toggled. Can be omitted thus no delay is
+  observed. Delay is in range of 1ms to 1000ms. Other delays are invalid.
 - phy-supply : regulator that powers the Ethernet PHY.
 - phy-handle : phandle to the PHY device connected to this device.
 - fixed-link : Assume a fixed link. See fixed-link.txt in the same directory.

drivers/net/bonding/bond_main.c

@@ -2612,11 +2612,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
+		slave->new_link = BOND_LINK_NOCHANGE;
+
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->link  = BOND_LINK_UP;
+				slave->new_link = BOND_LINK_UP;
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2643,7 +2645,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->link  = BOND_LINK_DOWN;
+				slave->new_link = BOND_LINK_DOWN;
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2674,6 +2676,11 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 		if (!rtnl_trylock())
 			goto re_arm;
 
+		bond_for_each_slave(bond, slave, iter) {
+			if (slave->new_link != BOND_LINK_NOCHANGE)
+				slave->link = slave->new_link;
+		}
+
 		if (slave_state_changed) {
 			bond_slave_state_change(bond);
 			if (BOND_MODE(bond) == BOND_MODE_XOR)

drivers/net/ethernet/8390/ax88796.c

@@ -748,23 +748,20 @@ static int ax_init_dev(struct net_device *dev)
 
 	ret = ax_mii_init(dev);
 	if (ret)
-		goto out_irq;
+		goto err_out;
 
 	ax_NS8390_init(dev, 0);
 
 	ret = register_netdev(dev);
 	if (ret)
-		goto out_irq;
+		goto err_out;
 
 	netdev_info(dev, "%dbit, irq %d, %lx, MAC: %pM\n",
 		    ei_local->word16 ? 16 : 8, dev->irq, dev->base_addr,
 		    dev->dev_addr);
 
 	return 0;
 
- out_irq:
-	/* cleanup irq */
-	free_irq(dev->irq, dev);
  err_out:
 	return ret;
 }

drivers/net/ethernet/emulex/benet/be_main.c

@@ -5078,9 +5078,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;

drivers/net/ethernet/freescale/fec_main.c

@@ -3192,7 +3192,7 @@ static int fec_reset_phy(struct platform_device *pdev)
 {
 	int err, phy_reset;
 	bool active_high = false;
-	int msec = 1;
+	int msec = 1, phy_post_delay = 0;
 	struct device_node *np = pdev->dev.of_node;
 
 	if (!np)
@@ -3209,6 +3209,11 @@ static int fec_reset_phy(struct platform_device *pdev)
 	else if (!gpio_is_valid(phy_reset))
 		return 0;
 
+	err = of_property_read_u32(np, "phy-reset-post-delay", &phy_post_delay);
+	/* valid reset duration should be less than 1s */
+	if (!err && phy_post_delay > 1000)
+		return -EINVAL;
+
 	active_high = of_property_read_bool(np, "phy-reset-active-high");
 
 	err = devm_gpio_request_one(&pdev->dev, phy_reset,
@@ -3226,6 +3231,15 @@ static int fec_reset_phy(struct platform_device *pdev)
 
 	gpio_set_value_cansleep(phy_reset, !active_high);
 
+	if (!phy_post_delay)
+		return 0;
+
+	if (phy_post_delay > 20)
+		msleep(phy_post_delay);
+	else
+		usleep_range(phy_post_delay * 1000,
+			     phy_post_delay * 1000 + 1000);
+
 	return 0;
 }
 #else /* CONFIG_OF */

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

@@ -774,7 +774,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 		       mlx5_command_str(msg_to_opcode(ent->in)),
 		       msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
 static void cmd_work_handler(struct work_struct *work)
@@ -804,6 +804,7 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -825,6 +826,20 @@ static void cmd_work_handler(struct work_struct *work)
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
 
+	/* Skip sending command to fw if internal error */
+	if (pci_channel_offline(dev->pdev) ||
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		u8 status = 0;
+		u32 drv_synd;
+
+		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+		MLX5_SET(mbox_out, ent->out, status, status);
+		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		return;
+	}
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -835,7 +850,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -879,7 +894,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
 		ent->ret = -ETIMEDOUT;
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
 	err = ent->ret;
@@ -1375,7 +1390,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1395,6 +1410,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+
+			/* if we already completed the command, ignore it */
+			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+						&ent->state)) {
+				/* only real completion can free the cmd slot */
+				if (!forced) {
+					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+						      ent->idx);
+					free_ent(cmd, ent->idx);
+				}
+				continue;
+			}
+
 			if (ent->callback)
 				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
@@ -1417,7 +1445,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
 			}
-			free_ent(cmd, ent->idx);
+
+			/* only real completion will free the entry slot */
+			if (!forced)
+				free_ent(cmd, ent->idx);
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;

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

@@ -1041,13 +1041,16 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 #define MLX5_IB_GRH_BYTES       40
 #define MLX5_IPOIB_ENCAP_LEN    4
 #define MLX5_GID_SIZE           16
+#define MLX5_IPOIB_PSEUDO_LEN   20
+#define MLX5_IPOIB_HARD_LEN     (MLX5_IPOIB_PSEUDO_LEN + MLX5_IPOIB_ENCAP_LEN)
 
 static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
 {
 	struct net_device *netdev = rq->netdev;
+	char *pseudo_header;
 	u8 *dgid;
 	u8 g;
 
@@ -1076,8 +1079,11 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	if (likely(netdev->features & NETIF_F_RXHASH))
 		mlx5e_skb_set_hash(cqe, skb);
 
+	/* 20 bytes of ipoib header and 4 for encap existing */
+	pseudo_header = skb_push(skb, MLX5_IPOIB_PSEUDO_LEN);
+	memset(pseudo_header, 0, MLX5_IPOIB_PSEUDO_LEN);
 	skb_reset_mac_header(skb);
-	skb_pull(skb, MLX5_IPOIB_ENCAP_LEN);
+	skb_pull(skb, MLX5_IPOIB_HARD_LEN);
 
 	skb->dev = netdev;
 

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

@@ -43,6 +43,7 @@
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
+#include <net/tc_act/tc_csum.h>
 #include <net/vxlan.h>
 #include <net/arp.h>
 #include "en.h"
@@ -384,7 +385,7 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 		if (e->flags & MLX5_ENCAP_ENTRY_VALID)
 			mlx5_encap_dealloc(priv->mdev, e->encap_id);
 
-		hlist_del_rcu(&e->encap_hlist);
+		hash_del_rcu(&e->encap_hlist);
 		kfree(e->encap_header);
 		kfree(e);
 	}
@@ -925,11 +926,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 				struct mlx5e_tc_flow_parse_attr *parse_attr)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
-	int i, action_size, nactions, max_actions, first, last;
+	int i, action_size, nactions, max_actions, first, last, first_z;
 	void *s_masks_p, *a_masks_p, *vals_p;
-	u32 s_mask, a_mask, val;
 	struct mlx5_fields *f;
 	u8 cmd, field_bsize;
+	u32 s_mask, a_mask;
 	unsigned long mask;
 	void *action;
 
@@ -946,7 +947,8 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
 		/* avoid seeing bits set from previous iterations */
-		s_mask = a_mask = mask = val = 0;
+		s_mask = 0;
+		a_mask = 0;
 
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
@@ -981,12 +983,12 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 			memset(a_masks_p, 0, f->size);
 		}
 
-		memcpy(&val, vals_p, f->size);
-
 		field_bsize = f->size * BITS_PER_BYTE;
+
+		first_z = find_first_zero_bit(&mask, field_bsize);
 		first = find_first_bit(&mask, field_bsize);
 		last  = find_last_bit(&mask, field_bsize);
-		if (first > 0 || last != (field_bsize - 1)) {
+		if (first > 0 || last != (field_bsize - 1) || first_z < last) {
 			printk(KERN_WARNING "mlx5: partial rewrite (mask %lx) is currently not offloaded\n",
 			       mask);
 			return -EOPNOTSUPP;
@@ -1002,11 +1004,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 		}
 
 		if (field_bsize == 32)
-			MLX5_SET(set_action_in, action, data, ntohl(val));
+			MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p));
 		else if (field_bsize == 16)
-			MLX5_SET(set_action_in, action, data, ntohs(val));
+			MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p));
 		else if (field_bsize == 8)
-			MLX5_SET(set_action_in, action, data, val);
+			MLX5_SET(set_action_in, action, data, *(u8 *)vals_p);
 
 		action += action_size;
 		nactions++;
@@ -1109,6 +1111,28 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
 	return err;
 }
 
+static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 update_flags)
+{
+	u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP |
+			 TCA_CSUM_UPDATE_FLAG_UDP;
+
+	/*  The HW recalcs checksums only if re-writing headers */
+	if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) {
+		netdev_warn(priv->netdev,
+			    "TC csum action is only offloaded with pedit\n");
+		return false;
+	}
+
+	if (update_flags & ~prot_flags) {
+		netdev_warn(priv->netdev,
+			    "can't offload TC csum action for some header/s - flags %#x\n",
+			    update_flags);
+		return false;
+	}
+
+	return true;
+}
+
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -1149,6 +1173,14 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_csum(a)) {
+			if (csum_offload_supported(priv, attr->action,
+						   tcf_csum_update_flags(a)))
+				continue;
+
+			return -EOPNOTSUPP;
+		}
+
 		if (is_tcf_skbedit_mark(a)) {
 			u32 mark = tcf_skbedit_mark(a);
 
@@ -1651,6 +1683,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			continue;
 		}
 
+		if (is_tcf_csum(a)) {
+			if (csum_offload_supported(priv, attr->action,
+						   tcf_csum_update_flags(a)))
+				continue;
+
+			return -EOPNOTSUPP;
+		}
+
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
 			struct net_device *out_dev, *encap_dev = NULL;

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

@@ -422,7 +422,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 			break;
 
 		case MLX5_EVENT_TYPE_PORT_CHANGE:

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

@@ -90,7 +90,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
 	return;
 
 no_trig: