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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 144 insertions, 105 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9201e3621351..a78fd61da0ec 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -62,7 +62,7 @@
 struct rtnl_link {
 	rtnl_doit_func		doit;
 	rtnl_dumpit_func	dumpit;
-	rtnl_calcit_func 	calcit;
+	unsigned int		flags;
 };
 
 static DEFINE_MUTEX(rtnl_mutex);
@@ -127,7 +127,8 @@ bool lockdep_rtnl_is_held(void)
 EXPORT_SYMBOL(lockdep_rtnl_is_held);
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 
-static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
+static struct rtnl_link __rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
+static refcount_t rtnl_msg_handlers_ref[RTNL_FAMILY_MAX + 1];
 
 static inline int rtm_msgindex(int msgtype)
 {
@@ -143,58 +144,13 @@ static inline int rtm_msgindex(int msgtype)
 	return msgindex;
 }
 
-static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
-{
-	struct rtnl_link *tab;
-
-	if (protocol <= RTNL_FAMILY_MAX)
-		tab = rtnl_msg_handlers[protocol];
-	else
-		tab = NULL;
-
-	if (tab == NULL || tab[msgindex].doit == NULL)
-		tab = rtnl_msg_handlers[PF_UNSPEC];
-
-	return tab[msgindex].doit;
-}
-
-static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
-{
-	struct rtnl_link *tab;
-
-	if (protocol <= RTNL_FAMILY_MAX)
-		tab = rtnl_msg_handlers[protocol];
-	else
-		tab = NULL;
-
-	if (tab == NULL || tab[msgindex].dumpit == NULL)
-		tab = rtnl_msg_handlers[PF_UNSPEC];
-
-	return tab[msgindex].dumpit;
-}
-
-static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
-{
-	struct rtnl_link *tab;
-
-	if (protocol <= RTNL_FAMILY_MAX)
-		tab = rtnl_msg_handlers[protocol];
-	else
-		tab = NULL;
-
-	if (tab == NULL || tab[msgindex].calcit == NULL)
-		tab = rtnl_msg_handlers[PF_UNSPEC];
-
-	return tab[msgindex].calcit;
-}
-
 /**
  * __rtnl_register - Register a rtnetlink message type
  * @protocol: Protocol family or PF_UNSPEC
  * @msgtype: rtnetlink message type
  * @doit: Function pointer called for each request message
  * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message
- * @calcit: Function pointer to calc size of dump message
+ * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions
  *
  * Registers the specified function pointers (at least one of them has
  * to be non-NULL) to be called whenever a request message for the
@@ -208,7 +164,7 @@ static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex)
  */
 int __rtnl_register(int protocol, int msgtype,
 		    rtnl_doit_func doit, rtnl_dumpit_func dumpit,
-		    rtnl_calcit_func calcit)
+		    unsigned int flags)
 {
 	struct rtnl_link *tab;
 	int msgindex;
@@ -216,23 +172,20 @@ int __rtnl_register(int protocol, int msgtype,
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 	msgindex = rtm_msgindex(msgtype);
 
-	tab = rtnl_msg_handlers[protocol];
+	tab = rcu_dereference_raw(rtnl_msg_handlers[protocol]);
 	if (tab == NULL) {
 		tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL);
 		if (tab == NULL)
 			return -ENOBUFS;
 
-		rtnl_msg_handlers[protocol] = tab;
+		rcu_assign_pointer(rtnl_msg_handlers[protocol], tab);
 	}
 
 	if (doit)
 		tab[msgindex].doit = doit;
-
 	if (dumpit)
 		tab[msgindex].dumpit = dumpit;
-
-	if (calcit)
-		tab[msgindex].calcit = calcit;
+	tab[msgindex].flags |= flags;
 
 	return 0;
 }
@@ -249,9 +202,9 @@ EXPORT_SYMBOL_GPL(__rtnl_register);
  */
 void rtnl_register(int protocol, int msgtype,
 		   rtnl_doit_func doit, rtnl_dumpit_func dumpit,
-		   rtnl_calcit_func calcit)
+		   unsigned int flags)
 {
-	if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0)
+	if (__rtnl_register(protocol, msgtype, doit, dumpit, flags) < 0)
 		panic("Unable to register rtnetlink message handler, "
 		      "protocol = %d, message type = %d\n",
 		      protocol, msgtype);
@@ -267,17 +220,23 @@ EXPORT_SYMBOL_GPL(rtnl_register);
  */
 int rtnl_unregister(int protocol, int msgtype)
 {
+	struct rtnl_link *handlers;
 	int msgindex;
 
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 	msgindex = rtm_msgindex(msgtype);
 
-	if (rtnl_msg_handlers[protocol] == NULL)
+	rtnl_lock();
+	handlers = rtnl_dereference(rtnl_msg_handlers[protocol]);
+	if (!handlers) {
+		rtnl_unlock();
 		return -ENOENT;
+	}
 
-	rtnl_msg_handlers[protocol][msgindex].doit = NULL;
-	rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;
-	rtnl_msg_handlers[protocol][msgindex].calcit = NULL;
+	handlers[msgindex].doit = NULL;
+	handlers[msgindex].dumpit = NULL;
+	handlers[msgindex].flags = 0;
+	rtnl_unlock();
 
 	return 0;
 }
@@ -292,10 +251,20 @@ EXPORT_SYMBOL_GPL(rtnl_unregister);
  */
 void rtnl_unregister_all(int protocol)
 {
+	struct rtnl_link *handlers;
+
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 
-	kfree(rtnl_msg_handlers[protocol]);
-	rtnl_msg_handlers[protocol] = NULL;
+	rtnl_lock();
+	handlers = rtnl_dereference(rtnl_msg_handlers[protocol]);
+	RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
+	rtnl_unlock();
+
+	synchronize_net();
+
+	while (refcount_read(&rtnl_msg_handlers_ref[protocol]) > 1)
+		schedule();
+	kfree(handlers);
 }
 EXPORT_SYMBOL_GPL(rtnl_unregister_all);
 
@@ -433,16 +402,24 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
 {
 	struct net_device *master_dev;
 	const struct rtnl_link_ops *ops;
+	size_t size = 0;
 
-	master_dev = netdev_master_upper_dev_get((struct net_device *) dev);
+	rcu_read_lock();
+
+	master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev);
 	if (!master_dev)
-		return 0;
+		goto out;
+
 	ops = master_dev->rtnl_link_ops;
 	if (!ops || !ops->get_slave_size)
-		return 0;
+		goto out;
 	/* IFLA_INFO_SLAVE_DATA + nested data */
-	return nla_total_size(sizeof(struct nlattr)) +
+	size = nla_total_size(sizeof(struct nlattr)) +
 	       ops->get_slave_size(master_dev, dev);
+
+out:
+	rcu_read_unlock();
+	return size;
 }
 
 static size_t rtnl_link_get_size(const struct net_device *dev)
@@ -1644,8 +1621,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
 
-	cb->seq = net->dev_base_seq;
-
 	/* A hack to preserve kernel<->userspace interface.
 	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
 	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
@@ -1691,8 +1666,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 
 				goto out_err;
 			}
-
-			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
@@ -1702,6 +1675,8 @@ out:
 out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
+	cb->seq = net->dev_base_seq;
+	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 
 	return err;
 }
@@ -2831,11 +2806,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	 * traverse the list of net devices and compute the minimum
 	 * buffer size based upon the filter mask.
 	 */
-	list_for_each_entry(dev, &net->dev_base_head, dev_list) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
 					     if_nlmsg_size(dev,
 						           ext_filter_mask));
 	}
+	rcu_read_unlock();
 
 	return nlmsg_total_size(min_ifinfo_dump_size);
 }
@@ -2847,19 +2824,29 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 
 	if (s_idx == 0)
 		s_idx = 1;
+
 	for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
 		int type = cb->nlh->nlmsg_type-RTM_BASE;
+		struct rtnl_link *handlers;
+		rtnl_dumpit_func dumpit;
+
 		if (idx < s_idx || idx == PF_PACKET)
 			continue;
-		if (rtnl_msg_handlers[idx] == NULL ||
-		    rtnl_msg_handlers[idx][type].dumpit == NULL)
+
+		handlers = rtnl_dereference(rtnl_msg_handlers[idx]);
+		if (!handlers)
 			continue;
+
+		dumpit = READ_ONCE(handlers[type].dumpit);
+		if (!dumpit)
+			continue;
+
 		if (idx > s_idx) {
 			memset(&cb->args[0], 0, sizeof(cb->args));
 			cb->prev_seq = 0;
 			cb->seq = 0;
 		}
-		if (rtnl_msg_handlers[idx][type].dumpit(skb, cb))
+		if (dumpit(skb, cb))
 			break;
 	}
 	cb->family = idx;
@@ -4162,11 +4149,13 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
+	struct rtnl_link *handlers;
+	int err = -EOPNOTSUPP;
 	rtnl_doit_func doit;
+	unsigned int flags;
 	int kind;
 	int family;
 	int type;
-	int err;
 
 	type = nlh->nlmsg_type;
 	if (type > RTM_MAX)
@@ -4184,20 +4173,40 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
+	if (family >= ARRAY_SIZE(rtnl_msg_handlers))
+		family = PF_UNSPEC;
+
+	rcu_read_lock();
+	handlers = rcu_dereference(rtnl_msg_handlers[family]);
+	if (!handlers) {
+		family = PF_UNSPEC;
+		handlers = rcu_dereference(rtnl_msg_handlers[family]);
+	}
+
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
-		rtnl_calcit_func calcit;
 		u16 min_dump_alloc = 0;
 
-		dumpit = rtnl_get_dumpit(family, type);
-		if (dumpit == NULL)
-			return -EOPNOTSUPP;
-		calcit = rtnl_get_calcit(family, type);
-		if (calcit)
-			min_dump_alloc = calcit(skb, nlh);
+		dumpit = READ_ONCE(handlers[type].dumpit);
+		if (!dumpit) {
+			family = PF_UNSPEC;
+			handlers = rcu_dereference(rtnl_msg_handlers[PF_UNSPEC]);
+			if (!handlers)
+				goto err_unlock;
+
+			dumpit = READ_ONCE(handlers[type].dumpit);
+			if (!dumpit)
+				goto err_unlock;
+		}
+
+		refcount_inc(&rtnl_msg_handlers_ref[family]);
+
+		if (type == RTM_GETLINK - RTM_BASE)
+			min_dump_alloc = rtnl_calcit(skb, nlh);
+
+		rcu_read_unlock();
 
-		__rtnl_unlock();
 		rtnl = net->rtnl;
 		{
 			struct netlink_dump_control c = {
@@ -4206,22 +4215,47 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			};
 			err = netlink_dump_start(rtnl, skb, nlh, &c);
 		}
-		rtnl_lock();
+		refcount_dec(&rtnl_msg_handlers_ref[family]);
 		return err;
 	}
 
-	doit = rtnl_get_doit(family, type);
-	if (doit == NULL)
-		return -EOPNOTSUPP;
+	doit = READ_ONCE(handlers[type].doit);
+	if (!doit) {
+		family = PF_UNSPEC;
+		handlers = rcu_dereference(rtnl_msg_handlers[family]);
+	}
+
+	flags = READ_ONCE(handlers[type].flags);
+	if (flags & RTNL_FLAG_DOIT_UNLOCKED) {
+		refcount_inc(&rtnl_msg_handlers_ref[family]);
+		doit = READ_ONCE(handlers[type].doit);
+		rcu_read_unlock();
+		if (doit)
+			err = doit(skb, nlh, extack);
+		refcount_dec(&rtnl_msg_handlers_ref[family]);
+		return err;
+	}
 
-	return doit(skb, nlh, extack);
+	rcu_read_unlock();
+
+	rtnl_lock();
+	handlers = rtnl_dereference(rtnl_msg_handlers[family]);
+	if (handlers) {
+		doit = READ_ONCE(handlers[type].doit);
+		if (doit)
+			err = doit(skb, nlh, extack);
+	}
+	rtnl_unlock();
+	return err;
+
+err_unlock:
+	rcu_read_unlock();
+	return -EOPNOTSUPP;
 }
 
 static void rtnetlink_rcv(struct sk_buff *skb)
 {
-	rtnl_lock();
 	netlink_rcv_skb(skb, &rtnetlink_rcv_msg);
-	rtnl_unlock();
 }
 
 static int rtnetlink_bind(struct net *net, int group)
@@ -4294,29 +4328,34 @@ static struct pernet_operations rtnetlink_net_ops = {
 
 void __init rtnetlink_init(void)
 {
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rtnl_msg_handlers_ref); i++)
+		refcount_set(&rtnl_msg_handlers_ref[i], 1);
+
 	if (register_pernet_subsys(&rtnetlink_net_ops))
 		panic("rtnetlink_init: cannot initialize rtnetlink\n");
 
 	register_netdevice_notifier(&rtnetlink_dev_notifier);
 
 	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
-		      rtnl_dump_ifinfo, rtnl_calcit);
-	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL);
-	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL);
+		      rtnl_dump_ifinfo, 0);
+	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0);
 
-	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, 0);
+	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0);
+	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0);
 
-	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
-	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
-	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
+	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, 0);
 
-	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL);
-	rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL);
-	rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL);
+	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, 0);
 
 	rtnl_register(PF_UNSPEC, RTM_GETSTATS, rtnl_stats_get, rtnl_stats_dump,
-		      NULL);
+		      0);
 }