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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 105 insertions, 27 deletions

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 467a2f4510a7..d1ba90980be1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -16,6 +16,7 @@
  *	Vitaly E. Lavrov		RTA_OK arithmetics was wrong.
  */
 
+#include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -39,6 +40,7 @@
 #include <linux/if_vlan.h>
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
+#include <linux/bpf.h>
 
 #include <linux/uaccess.h>
 
@@ -647,7 +649,7 @@ int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int g
 
 	NETLINK_CB(skb).dst_group = group;
 	if (echo)
-		atomic_inc(&skb->users);
+		refcount_inc(&skb->users);
 	netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL);
 	if (echo)
 		err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT);
@@ -899,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev,
 static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
-			  nla_total_size(1);	/* XDP_ATTACHED */
+			  nla_total_size(1) +	/* XDP_ATTACHED */
+			  nla_total_size(4);	/* XDP_PROG_ID */
 
 	return xdp_size;
 }
@@ -942,6 +945,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
 	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + rtnl_xdp_size() /* IFLA_XDP */
+	       + nla_total_size(4)  /* IFLA_EVENT */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
@@ -1248,23 +1252,29 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static u8 rtnl_xdp_attached_mode(struct net_device *dev)
+static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	const struct bpf_prog *generic_xdp_prog;
 
 	ASSERT_RTNL();
 
-	if (rcu_access_pointer(dev->xdp_prog))
+	*prog_id = 0;
+	generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
+	if (generic_xdp_prog) {
+		*prog_id = generic_xdp_prog->aux->id;
 		return XDP_ATTACHED_SKB;
-	if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp))
-		return XDP_ATTACHED_DRV;
+	}
+	if (!ops->ndo_xdp)
+		return XDP_ATTACHED_NONE;
 
-	return XDP_ATTACHED_NONE;
+	return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id);
 }
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 {
 	struct nlattr *xdp;
+	u32 prog_id;
 	int err;
 
 	xdp = nla_nest_start(skb, IFLA_XDP);
@@ -1272,10 +1282,16 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 		return -EMSGSIZE;
 
 	err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
-			 rtnl_xdp_attached_mode(dev));
+			 rtnl_xdp_attached_mode(dev, &prog_id));
 	if (err)
 		goto err_cancel;
 
+	if (prog_id) {
+		err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
+		if (err)
+			goto err_cancel;
+	}
+
 	nla_nest_end(skb, xdp);
 	return 0;
 
@@ -1284,9 +1300,40 @@ err_cancel:
 	return err;
 }
 
+static u32 rtnl_get_event(unsigned long event)
+{
+	u32 rtnl_event_type = IFLA_EVENT_NONE;
+
+	switch (event) {
+	case NETDEV_REBOOT:
+		rtnl_event_type = IFLA_EVENT_REBOOT;
+		break;
+	case NETDEV_FEAT_CHANGE:
+		rtnl_event_type = IFLA_EVENT_FEATURES;
+		break;
+	case NETDEV_BONDING_FAILOVER:
+		rtnl_event_type = IFLA_EVENT_BONDING_FAILOVER;
+		break;
+	case NETDEV_NOTIFY_PEERS:
+		rtnl_event_type = IFLA_EVENT_NOTIFY_PEERS;
+		break;
+	case NETDEV_RESEND_IGMP:
+		rtnl_event_type = IFLA_EVENT_IGMP_RESEND;
+		break;
+	case NETDEV_CHANGEINFODATA:
+		rtnl_event_type = IFLA_EVENT_BONDING_OPTIONS;
+		break;
+	default:
+		break;
+	}
+
+	return rtnl_event_type;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
-			    unsigned int flags, u32 ext_filter_mask)
+			    unsigned int flags, u32 ext_filter_mask,
+			    u32 event)
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
@@ -1335,6 +1382,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
 		goto nla_put_failure;
 
+	if (event != IFLA_EVENT_NONE) {
+		if (nla_put_u32(skb, IFLA_EVENT, event))
+			goto nla_put_failure;
+	}
+
 	if (rtnl_fill_link_ifmap(skb, dev))
 		goto nla_put_failure;
 
@@ -1469,6 +1521,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
 	[IFLA_XDP]		= { .type = NLA_NESTED },
+	[IFLA_EVENT]		= { .type = NLA_U32 },
 	[IFLA_GROUP]		= { .type = NLA_U32 },
 };
 
@@ -1517,6 +1570,7 @@ static const struct nla_policy ifla_xdp_policy[IFLA_XDP_MAX + 1] = {
 	[IFLA_XDP_FD]		= { .type = NLA_S32 },
 	[IFLA_XDP_ATTACHED]	= { .type = NLA_U8 },
 	[IFLA_XDP_FLAGS]	= { .type = NLA_U32 },
+	[IFLA_XDP_PROG_ID]	= { .type = NLA_U32 },
 };
 
 static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla)
@@ -1629,7 +1683,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
-					       ext_filter_mask);
+					       ext_filter_mask, 0);
 
 			if (err < 0) {
 				if (likely(skb->len))
@@ -2051,8 +2105,8 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_TXQLEN]) {
-		unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
-		unsigned long orig_len = dev->tx_queue_len;
+		unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
+		unsigned int orig_len = dev->tx_queue_len;
 
 		if (dev->tx_queue_len ^ value) {
 			dev->tx_queue_len = value;
@@ -2189,7 +2243,7 @@ static int do_setlink(const struct sk_buff *skb,
 		if (err < 0)
 			goto errout;
 
-		if (xdp[IFLA_XDP_ATTACHED]) {
+		if (xdp[IFLA_XDP_ATTACHED] || xdp[IFLA_XDP_PROG_ID]) {
 			err = -EINVAL;
 			goto errout;
 		}
@@ -2200,8 +2254,7 @@ static int do_setlink(const struct sk_buff *skb,
 				err = -EINVAL;
 				goto errout;
 			}
-			if ((xdp_flags & XDP_FLAGS_SKB_MODE) &&
-			    (xdp_flags & XDP_FLAGS_DRV_MODE)) {
+			if (hweight32(xdp_flags & XDP_FLAGS_MODES) > 1) {
 				err = -EINVAL;
 				goto errout;
 			}
@@ -2529,7 +2582,7 @@ replay:
 				data = attr;
 			}
 			if (ops->validate) {
-				err = ops->validate(tb, data);
+				err = ops->validate(tb, data, extack);
 				if (err < 0)
 					return err;
 			}
@@ -2548,7 +2601,8 @@ replay:
 				slave_data = slave_attr;
 			}
 			if (m_ops->slave_validate) {
-				err = m_ops->slave_validate(tb, slave_data);
+				err = m_ops->slave_validate(tb, slave_data,
+							    extack);
 				if (err < 0)
 					return err;
 			}
@@ -2567,7 +2621,7 @@ replay:
 				    !ops->changelink)
 					return -EOPNOTSUPP;
 
-				err = ops->changelink(dev, tb, data);
+				err = ops->changelink(dev, tb, data, extack);
 				if (err < 0)
 					return err;
 				status |= DO_SETLINK_NOTIFY;
@@ -2578,7 +2632,8 @@ replay:
 					return -EOPNOTSUPP;
 
 				err = m_ops->slave_changelink(master_dev, dev,
-							      tb, slave_data);
+							      tb, slave_data,
+							      extack);
 				if (err < 0)
 					return err;
 				status |= DO_SETLINK_NOTIFY;
@@ -2652,7 +2707,8 @@ replay:
 		dev->ifindex = ifm->ifi_index;
 
 		if (ops->newlink) {
-			err = ops->newlink(link_net ? : net, dev, tb, data);
+			err = ops->newlink(link_net ? : net, dev, tb, data,
+					   extack);
 			/* Drivers should call free_netdev() in ->destructor
 			 * and unregister it on failure after registration
 			 * so that device could be finally freed in rtnl_unlock.
@@ -2739,7 +2795,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -ENOBUFS;
 
 	err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
-			       nlh->nlmsg_seq, 0, 0, ext_filter_mask);
+			       nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
 		WARN_ON(err == -EMSGSIZE);
@@ -2811,7 +2867,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
-				       unsigned int change, gfp_t flags)
+				       unsigned int change,
+				       u32 event, gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
@@ -2822,7 +2879,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 	if (skb == NULL)
 		goto errout;
 
-	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0);
+	err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -2843,18 +2900,25 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
-		  gfp_t flags)
+static void rtmsg_ifinfo_event(int type, struct net_device *dev,
+			       unsigned int change, u32 event,
+			       gfp_t flags)
 {
 	struct sk_buff *skb;
 
 	if (dev->reg_state != NETREG_REGISTERED)
 		return;
 
-	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+	skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags);
 	if (skb)
 		rtmsg_ifinfo_send(skb, dev, flags);
 }
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
+{
+	rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags);
+}
 EXPORT_SYMBOL(rtmsg_ifinfo);
 
 static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
@@ -4159,6 +4223,18 @@ static void rtnetlink_rcv(struct sk_buff *skb)
 	rtnl_unlock();
 }
 
+static int rtnetlink_bind(struct net *net, int group)
+{
+	switch (group) {
+	case RTNLGRP_IPV4_MROUTE_R:
+	case RTNLGRP_IPV6_MROUTE_R:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		break;
+	}
+	return 0;
+}
+
 static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -4171,7 +4247,8 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_NOTIFY_PEERS:
 	case NETDEV_RESEND_IGMP:
 	case NETDEV_CHANGEINFODATA:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
+		rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event),
+				   GFP_KERNEL);
 		break;
 	default:
 		break;
@@ -4192,6 +4269,7 @@ static int __net_init rtnetlink_net_init(struct net *net)
 		.input		= rtnetlink_rcv,
 		.cb_mutex	= &rtnl_mutex,
 		.flags		= NL_CFG_F_NONROOT_RECV,
+		.bind		= rtnetlink_bind,
 	};
 
 	sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg);