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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 115 insertions, 74 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 34481c9be1d1..2be78807fd6e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -201,12 +201,6 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
-static __be32 arp_target[BOND_MAX_ARP_TARGETS];
-static int arp_ip_count;
-static int bond_mode	= BOND_MODE_ROUNDROBIN;
-static int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
-static int lacp_fast;
-
 /*-------------------------- Forward declarations ---------------------------*/
 
 static int bond_init(struct net_device *bond_dev);
@@ -371,9 +365,10 @@ down:
 /* Get link speed and duplex from the slave's base driver
  * using ethtool. If for some reason the call fails or the
  * values are invalid, set speed and duplex to -1,
- * and return.
+ * and return. Return 1 if speed or duplex settings are
+ * UNKNOWN; 0 otherwise.
  */
-static void bond_update_speed_duplex(struct slave *slave)
+static int bond_update_speed_duplex(struct slave *slave)
 {
 	struct net_device *slave_dev = slave->dev;
 	struct ethtool_link_ksettings ecmd;
@@ -384,23 +379,21 @@ static void bond_update_speed_duplex(struct slave *slave)
 
 	res = __ethtool_get_link_ksettings(slave_dev, &ecmd);
 	if (res < 0)
-		return;
-
+		return 1;
 	if (ecmd.base.speed == 0 || ecmd.base.speed == ((__u32)-1))
-		return;
-
+		return 1;
 	switch (ecmd.base.duplex) {
 	case DUPLEX_FULL:
 	case DUPLEX_HALF:
 		break;
 	default:
-		return;
+		return 1;
 	}
 
 	slave->speed = ecmd.base.speed;
 	slave->duplex = ecmd.base.duplex;
 
-	return;
+	return 0;
 }
 
 const char *bond_slave_link_status(s8 link)
@@ -652,8 +645,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 				  struct slave *new_active,
 				  struct slave *old_active)
 {
-	u8 tmp_mac[ETH_ALEN];
-	struct sockaddr saddr;
+	u8 tmp_mac[MAX_ADDR_LEN];
+	struct sockaddr_storage ss;
 	int rv;
 
 	switch (bond->params.fail_over_mac) {
@@ -673,16 +666,20 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			old_active = bond_get_old_active(bond, new_active);
 
 		if (old_active) {
-			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
-			ether_addr_copy(saddr.sa_data,
-					old_active->dev->dev_addr);
-			saddr.sa_family = new_active->dev->type;
+			bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+					  new_active->dev->addr_len);
+			bond_hw_addr_copy(ss.__data,
+					  old_active->dev->dev_addr,
+					  old_active->dev->addr_len);
+			ss.ss_family = new_active->dev->type;
 		} else {
-			ether_addr_copy(saddr.sa_data, bond->dev->dev_addr);
-			saddr.sa_family = bond->dev->type;
+			bond_hw_addr_copy(ss.__data, bond->dev->dev_addr,
+					  bond->dev->addr_len);
+			ss.ss_family = bond->dev->type;
 		}
 
-		rv = dev_set_mac_address(new_active->dev, &saddr);
+		rv = dev_set_mac_address(new_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv) {
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -692,10 +689,12 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!old_active)
 			goto out;
 
-		ether_addr_copy(saddr.sa_data, tmp_mac);
-		saddr.sa_family = old_active->dev->type;
+		bond_hw_addr_copy(ss.__data, tmp_mac,
+				  new_active->dev->addr_len);
+		ss.ss_family = old_active->dev->type;
 
-		rv = dev_set_mac_address(old_active->dev, &saddr);
+		rv = dev_set_mac_address(old_active->dev,
+					 (struct sockaddr *)&ss);
 		if (rv)
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
@@ -1177,6 +1176,9 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
+	/* don't change skb->dev for link-local packets */
+	if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+		return RX_HANDLER_PASS;
 	if (bond_should_deliver_exact_match(skb, slave, bond))
 		return RX_HANDLER_EXACT;
 
@@ -1191,7 +1193,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 			kfree_skb(skb);
 			return RX_HANDLER_CONSUMED;
 		}
-		ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr);
+		bond_hw_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr,
+				  bond->dev->addr_len);
 	}
 
 	return ret;
@@ -1330,7 +1333,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct slave *new_slave = NULL, *prev_slave;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int link_reporting;
 	int res = 0, i;
 
@@ -1481,16 +1484,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * that need it, and for restoring it upon release, and then
 	 * set it to the master's address
 	 */
-	ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
+	bond_hw_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr,
+			  slave_dev->addr_len);
 
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
 		 */
-		memcpy(addr.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-		addr.sa_family = slave_dev->type;
-		res = dev_set_mac_address(slave_dev, &addr);
+		memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 		if (res) {
 			netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res);
 			goto err_restore_mtu;
@@ -1565,7 +1569,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	new_slave->delay = 0;
 	new_slave->link_failure_count = 0;
 
-	bond_update_speed_duplex(new_slave);
+	if (bond_update_speed_duplex(new_slave))
+		new_slave->link = BOND_LINK_DOWN;
 
 	new_slave->last_rx = jiffies -
 		(msecs_to_jiffies(bond->params.arp_interval) + 1);
@@ -1773,9 +1778,10 @@ err_restore_mac:
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
 		 */
-		ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, new_slave->perm_hwaddr,
+				  new_slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 err_restore_mtu:
@@ -1818,7 +1824,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
-	struct sockaddr addr;
+	struct sockaddr_storage ss;
 	int old_flags = bond_dev->flags;
 	netdev_features_t old_features = bond_dev->features;
 
@@ -1953,9 +1959,10 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
-		ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
-		addr.sa_family = slave_dev->type;
-		dev_set_mac_address(slave_dev, &addr);
+		bond_hw_addr_copy(ss.__data, slave->perm_hwaddr,
+				  slave->dev->addr_len);
+		ss.ss_family = slave_dev->type;
+		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss);
 	}
 
 	dev_set_mtu(slave_dev, slave->original_mtu);
@@ -2039,8 +2046,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_FAIL);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2055,13 +2061,13 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				bond_set_slave_link_state(slave, BOND_LINK_UP,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
 					    bond->params.miimon,
 					    slave->dev->name);
+				commit++;
 				continue;
 			}
 
@@ -2078,8 +2084,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_BACK,
-						  BOND_SLAVE_NOTIFY_LATER);
+			bond_propose_link_state(slave, BOND_LINK_BACK);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -2092,14 +2097,12 @@ static int bond_miimon_inspect(struct bonding *bond)
 			/*FALLTHRU*/
 		case BOND_LINK_BACK:
 			if (!link_state) {
-				bond_set_slave_link_state(slave,
-							  BOND_LINK_DOWN,
-							  BOND_SLAVE_NOTIFY_LATER);
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
 					    slave->dev->name);
-
+				commit++;
 				continue;
 			}
 
@@ -2132,7 +2135,13 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			bond_update_speed_duplex(slave);
+			if (bond_update_speed_duplex(slave)) {
+				slave->link = BOND_LINK_DOWN;
+				netdev_warn(bond->dev,
+					    "failed to get link speed/duplex for %s\n",
+					    slave->dev->name);
+				continue;
+			}
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
 						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
@@ -2231,6 +2240,8 @@ static void bond_mii_monitor(struct work_struct *work)
 					    mii_work.work);
 	bool should_notify_peers = false;
 	unsigned long delay;
+	struct slave *slave;
+	struct list_head *iter;
 
 	delay = msecs_to_jiffies(bond->params.miimon);
 
@@ -2251,6 +2262,9 @@ static void bond_mii_monitor(struct work_struct *work)
 			goto re_arm;
 		}
 
+		bond_for_each_slave(bond, slave, iter) {
+			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		}
 		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
@@ -2575,10 +2589,8 @@ static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
  * arp is transmitted to generate traffic. see activebackup_arp_monitor for
  * arp monitoring in active backup mode.
  */
-static void bond_loadbalance_arp_mon(struct work_struct *work)
+static void bond_loadbalance_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	struct slave *slave, *oldcurrent;
 	struct list_head *iter;
 	int do_failover = 0, slave_state_changed = 0;
@@ -2916,10 +2928,8 @@ check_state:
 	return should_notify_rtnl;
 }
 
-static void bond_activebackup_arp_mon(struct work_struct *work)
+static void bond_activebackup_arp_mon(struct bonding *bond)
 {
-	struct bonding *bond = container_of(work, struct bonding,
-					    arp_work.work);
 	bool should_notify_peers = false;
 	bool should_notify_rtnl = false;
 	int delta_in_ticks;
@@ -2972,6 +2982,17 @@ re_arm:
 	}
 }
 
+static void bond_arp_monitor(struct work_struct *work)
+{
+	struct bonding *bond = container_of(work, struct bonding,
+					    arp_work.work);
+
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
+		bond_activebackup_arp_mon(bond);
+	else
+		bond_loadbalance_arp_mon(bond);
+}
+
 /*-------------------------- netdev event handling --------------------------*/
 
 /* Change device name */
@@ -3222,16 +3243,13 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 
 /*-------------------------- Device entry points ----------------------------*/
 
-static void bond_work_init_all(struct bonding *bond)
+void bond_work_init_all(struct bonding *bond)
 {
 	INIT_DELAYED_WORK(&bond->mcast_work,
 			  bond_resend_igmp_join_requests_delayed);
 	INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
 	INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
-	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
-		INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
-	else
-		INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
+	INIT_DELAYED_WORK(&bond->arp_work, bond_arp_monitor);
 	INIT_DELAYED_WORK(&bond->ad_work, bond_3ad_state_machine_handler);
 	INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler);
 }
@@ -3266,8 +3284,6 @@ static int bond_open(struct net_device *bond_dev)
 		}
 	}
 
-	bond_work_init_all(bond);
-
 	if (bond_is_lb(bond)) {
 		/* bond_alb_initialize must be called before the timer
 		 * is started.
@@ -3327,12 +3343,17 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
 		u64 nv = new[i];
 		u64 ov = old[i];
+		s64 delta = nv - ov;
 
 		/* detects if this particular field is 32bit only */
 		if (((nv | ov) >> 32) == 0)
-			res[i] += (u32)nv - (u32)ov;
-		else
-			res[i] += nv - ov;
+			delta = (s64)(s32)((u32)nv - (u32)ov);
+
+		/* filter anomalies, some drivers reset their stats
+		 * at down/up events.
+		 */
+		if (delta > 0)
+			res[i] += delta;
 	}
 }
 
@@ -3619,7 +3640,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *rollback_slave;
-	struct sockaddr *sa = addr, tmp_sa;
+	struct sockaddr_storage *ss = addr, tmp_ss;
 	struct list_head *iter;
 	int res = 0;
 
@@ -3636,7 +3657,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	    BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
-	if (!is_valid_ether_addr(sa->sa_data))
+	if (!is_valid_ether_addr(ss->__data))
 		return -EADDRNOTAVAIL;
 
 	bond_for_each_slave(bond, slave, iter) {
@@ -3655,12 +3676,12 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	}
 
 	/* success */
-	memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len);
+	memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len);
 	return 0;
 
 unwind:
-	memcpy(tmp_sa.sa_data, bond_dev->dev_addr, bond_dev->addr_len);
-	tmp_sa.sa_family = bond_dev->type;
+	memcpy(tmp_ss.__data, bond_dev->dev_addr, bond_dev->addr_len);
+	tmp_ss.ss_family = bond_dev->type;
 
 	/* unwind from head to the slave that failed */
 	bond_for_each_slave(bond, rollback_slave, iter) {
@@ -3669,7 +3690,8 @@ unwind:
 		if (rollback_slave == slave)
 			break;
 
-		tmp_res = dev_set_mac_address(rollback_slave->dev, &tmp_sa);
+		tmp_res = dev_set_mac_address(rollback_slave->dev,
+					      (struct sockaddr *)&tmp_ss);
 		if (tmp_res) {
 			netdev_dbg(bond_dev, "unwind err %d dev %s\n",
 				   tmp_res, rollback_slave->dev->name);
@@ -4252,6 +4274,12 @@ static int bond_check_params(struct bond_params *params)
 	int arp_all_targets_value;
 	u16 ad_actor_sys_prio = 0;
 	u16 ad_user_port_key = 0;
+	__be32 arp_target[BOND_MAX_ARP_TARGETS];
+	int arp_ip_count;
+	int bond_mode	= BOND_MODE_ROUNDROBIN;
+	int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
+	int lacp_fast = 0;
+	int tlb_dynamic_lb = 0;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4564,6 +4592,17 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
+	if (bond_mode == BOND_MODE_TLB) {
+		bond_opt_initstr(&newval, "default");
+		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
+					&newval);
+		if (!valptr) {
+			pr_err("Error: No tlb_dynamic_lb default value");
+			return -EINVAL;
+		}
+		tlb_dynamic_lb = valptr->value;
+	}
+
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
 			INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
@@ -4591,7 +4630,7 @@ static int bond_check_params(struct bond_params *params)
 	params->min_links = min_links;
 	params->lp_interval = lp_interval;
 	params->packets_per_slave = packets_per_slave;
-	params->tlb_dynamic_lb = 1; /* Default value */
+	params->tlb_dynamic_lb = tlb_dynamic_lb;
 	params->ad_actor_sys_prio = ad_actor_sys_prio;
 	eth_zero_addr(params->ad_actor_system);
 	params->ad_user_port_key = ad_user_port_key;
@@ -4687,6 +4726,8 @@ int bond_create(struct net *net, const char *name)
 
 	netif_carrier_off(bond_dev);
 
+	bond_work_init_all(bond);
+
 	rtnl_unlock();
 	if (res < 0)
 		bond_destructor(bond_dev);