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

Pull networking fixes from David Miller:

 1) Handle notifier registry failures properly in tun/tap driver, from
    Tonghao Zhang.

 2) Fix bpf verifier handling of subtraction bounds and add a testcase
    for this, from Edward Cree.

 3) Increase reset timeout in ftgmac100 driver, from Ben Herrenschmidt.

 4) Fix use after free in prd_retire_rx_blk_timer_exired() in AF_PACKET,
    from Cong Wang.

 5) Fix SElinux regression due to recent UDP optimizations, from Paolo
    Abeni.

 6) We accidently increment IPSTATS_MIB_FRAGFAILS in the ipv6 code
    paths, fix from Stefano Brivio.

 7) Fix some mem leaks in dccp, from Xin Long.

 8) Adjust MDIO_BUS kconfig deps to avoid build errors, from Arnd
    Bergmann.

 9) Mac address length check and buffer size fixes from Cong Wang.

10) Don't leak sockets in ipv6 udp early demux, from Paolo Abeni.

11) Fix return value when copy_from_user() fails in
    bpf_prog_get_info_by_fd(), from Daniel Borkmann.

12) Handle PHY_HALTED properly in phy library state machine, from
    Florian Fainelli.

13) Fix OOPS in fib_sync_down_dev(), from Ido Schimmel.

14) Fix truesize calculation in virtio_net which led to performance
    regressions, from Michael S Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (76 commits)
  samples/bpf: fix bpf tunnel cleanup
  udp6: fix jumbogram reception
  ppp: Fix a scheduling-while-atomic bug in del_chan
  Revert "net: bcmgenet: Remove init parameter from bcmgenet_mii_config"
  virtio_net: fix truesize for mergeable buffers
  mv643xx_eth: fix of_irq_to_resource() error check
  MAINTAINERS: Add more files to the PHY LIBRARY section
  ipv4: fib: Fix NULL pointer deref during fib_sync_down_dev()
  net: phy: Correctly process PHY_HALTED in phy_stop_machine()
  sunhme: fix up GREG_STAT and GREG_IMASK register offsets
  bpf: fix bpf_prog_get_info_by_fd to dump correct xlated_prog_len
  tcp: avoid bogus gcc-7 array-bounds warning
  net: tc35815: fix spelling mistake: "Intterrupt" -> "Interrupt"
  bpf: don't indicate success when copy_from_user fails
  udp6: fix socket leak on early demux
  net: thunderx: Fix BGX transmit stall due to underflow
  Revert "vhost: cache used event for better performance"
  team: use a larger struct for mac address
  net: check dev->addr_len for dev_set_mac_address()
  phy: bcm-ns-usb3: fix MDIO_BUS dependency
  ...

15 files changed, 79 insertions, 52 deletions

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 06b147d7d9e2..709a4e6fb447 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -263,6 +263,8 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		return dev_set_mtu(dev, ifr->ifr_mtu);
 
 	case SIOCSIFHWADDR:
+		if (dev->addr_len > sizeof(struct sockaddr))
+			return -EINVAL;
 		return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
 
 	case SIOCSIFHWBROADCAST:
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 8357f164c660..912731bed7b7 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -666,7 +666,7 @@ int netpoll_setup(struct netpoll *np)
 	int err;
 
 	rtnl_lock();
-	if (np->dev_name) {
+	if (np->dev_name[0]) {
 		struct net *net = current->nsproxy->net_ns;
 		ndev = __dev_get_by_name(net, np->dev_name);
 	}
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 1704948e6a12..f227f002c73d 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk)
 	 * singleton values (which always leads to failure).
 	 * These settings can still (later) be overridden via sockopts.
 	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
-	    ccid_get_builtin_ccids(&rx.val, &rx.len))
+	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
 		return -ENOBUFS;
+	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
+		kfree(tx.val);
+		return -ENOBUFS;
+	}
 
 	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
 	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index f85d901f4e3f..1b202f16531f 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -631,6 +631,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index c376af5bfdfb..1b58eac8aad3 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -380,6 +380,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 56e46090526b..c442051d5a55 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -509,21 +509,22 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index,
 		dst->cpu_dp->netdev = ethernet_dev;
 	}
 
+	/* Initialize cpu_port_mask now for drv->setup()
+	 * to have access to a correct value, just like what
+	 * net/dsa/dsa.c::dsa_switch_setup_one does.
+	 */
+	ds->cpu_port_mask |= BIT(index);
+
 	tag_protocol = ds->ops->get_tag_protocol(ds);
 	dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol);
 	if (IS_ERR(dst->tag_ops)) {
 		dev_warn(ds->dev, "No tagger for this switch\n");
+		ds->cpu_port_mask &= ~BIT(index);
 		return PTR_ERR(dst->tag_ops);
 	}
 
 	dst->rcv = dst->tag_ops->rcv;
 
-	/* Initialize cpu_port_mask now for drv->setup()
-	 * to have access to a correct value, just like what
-	 * net/dsa/dsa.c::dsa_switch_setup_one does.
-	 */
-	ds->cpu_port_mask |= BIT(index);
-
 	return 0;
 }
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 222100103808..b8d18171cca3 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1452,7 +1452,7 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 		return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type,
 					  &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
 		    (fib_nh->nh_flags & RTNH_F_DEAD))
 			return call_fib_notifiers(dev_net(fib_nh->nh_dev),
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4e985dea1dd2..2f1588bf73da 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2202,9 +2202,10 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
 static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new)
 {
 	const u32 now = tcp_jiffies32;
+	enum tcp_chrono old = tp->chrono_type;
 
-	if (tp->chrono_type > TCP_CHRONO_UNSPEC)
-		tp->chrono_stat[tp->chrono_type - 1] += now - tp->chrono_start;
+	if (old > TCP_CHRONO_UNSPEC)
+		tp->chrono_stat[old - 1] += now - tp->chrono_start;
 	tp->chrono_start = now;
 	tp->chrono_type = new;
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b057653ceca9..e6276fa3750b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1163,34 +1163,32 @@ out:
 	return ret;
 }
 
-#if BITS_PER_LONG == 64
+#define UDP_SKB_IS_STATELESS 0x80000000
+
 static void udp_set_dev_scratch(struct sk_buff *skb)
 {
-	struct udp_dev_scratch *scratch;
+	struct udp_dev_scratch *scratch = udp_skb_scratch(skb);
 
 	BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long));
-	scratch = (struct udp_dev_scratch *)&skb->dev_scratch;
-	scratch->truesize = skb->truesize;
+	scratch->_tsize_state = skb->truesize;
+#if BITS_PER_LONG == 64
 	scratch->len = skb->len;
 	scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
 	scratch->is_linear = !skb_is_nonlinear(skb);
+#endif
+	if (likely(!skb->_skb_refdst))
+		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
 static int udp_skb_truesize(struct sk_buff *skb)
 {
-	return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize;
-}
-#else
-static void udp_set_dev_scratch(struct sk_buff *skb)
-{
-	skb->dev_scratch = skb->truesize;
+	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
 }
 
-static int udp_skb_truesize(struct sk_buff *skb)
+static bool udp_skb_has_head_state(struct sk_buff *skb)
 {
-	return skb->dev_scratch;
+	return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS);
 }
-#endif
 
 /* fully reclaim rmem/fwd memory allocated for skb */
 static void udp_rmem_release(struct sock *sk, int size, int partial,
@@ -1388,10 +1386,10 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		unlock_sock_fast(sk, slow);
 	}
 
-	/* we cleared the head states previously only if the skb lacks any IP
-	 * options, see __udp_queue_rcv_skb().
+	/* In the more common cases we cleared the head states previously,
+	 * see __udp_queue_rcv_skb().
 	 */
-	if (unlikely(IPCB(skb)->opt.optlen > 0))
+	if (unlikely(udp_skb_has_head_state(skb)))
 		skb_release_head_state(skb);
 	consume_stateless_skb(skb);
 }
@@ -1784,11 +1782,11 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id_once(sk, skb);
 	}
 
-	/* At recvmsg() time we need skb->dst to process IP options-related
-	 * cmsg, elsewhere can we clear all pending head states while they are
-	 * hot in the cache
+	/* At recvmsg() time we may access skb->dst or skb->sp depending on
+	 * the IP options and the cmsg flags, elsewhere can we clear all
+	 * pending head states while they are hot in the cache
 	 */
-	if (likely(IPCB(skb)->opt.optlen == 0))
+	if (likely(IPCB(skb)->opt.optlen == 0 && !skb_sec_path(skb)))
 		skb_release_head_state(skb);
 
 	rc = __udp_enqueue_schedule_skb(sk, skb);
@@ -1930,7 +1928,7 @@ drop:
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
@@ -1939,6 +1937,7 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 		dst_release(old);
 	}
 }
+EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
 /*
  *	Multicasts and broadcasts go to each listener.
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 4996d734f1d2..3cec529c6113 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -756,6 +756,7 @@ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
 	if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr)))
 		goto drop;
 
+	IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM;
 	return true;
 
 drop:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1422d6c08377..162efba0d0cd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -673,8 +673,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -789,8 +787,6 @@ slow_path:
 		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
 				 hroom + troom, GFP_ATOMIC);
 		if (!frag) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4a3e65626e8b..578142b7ca3e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  struct udp_table *udptable)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk;
 
-	sk = skb_steal_sock(skb);
-	if (unlikely(sk))
-		return sk;
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
 				 udptable, skb);
@@ -332,6 +328,15 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
 EXPORT_SYMBOL_GPL(udp6_lib_lookup);
 #endif
 
+/* do not use the scratch area len for jumbogram: their length execeeds the
+ * scratch area space; note that the IP6CB flags is still in the first
+ * cacheline, so checking for jumbograms is cheap
+ */
+static int udp6_skb_len(struct sk_buff *skb)
+{
+	return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb);
+}
+
 /*
  *	This should be easy, if there is something there we
  *	return it, otherwise we block.
@@ -362,7 +367,7 @@ try_again:
 	if (!skb)
 		return err;
 
-	ulen = udp_skb_len(skb);
+	ulen = udp6_skb_len(skb);
 	copied = len;
 	if (copied > ulen - off)
 		copied = ulen - off;
@@ -804,6 +809,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp6_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	/* Check if the socket is already available, e.g. due to early demux */
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
+		int ret;
+
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp_sk_rx_dst_set(sk, dst);
+
+		ret = udpv6_queue_rcv_skb(sk, skb);
+		sock_put(sk);
+
+		/* a return value > 0 means to resubmit the input */
+		if (ret > 0)
+			return ret;
+		return 0;
+	}
+
 	/*
 	 *	Multicast receive code
 	 */
@@ -812,11 +835,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 				saddr, daddr, udptable, proto);
 
 	/* Unicast */
-
-	/*
-	 * check socket cache ... must talk to Alan about his plans
-	 * for sock caches... i'll skip this for now.
-	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
 		int ret;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e3c4c6c3fef7..03859e386b47 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1310,8 +1310,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		int maxlen = ovs_ct_attr_lens[type].maxlen;
-		int minlen = ovs_ct_attr_lens[type].minlen;
+		int maxlen;
+		int minlen;
 
 		if (type > OVS_CT_ATTR_MAX) {
 			OVS_NLERR(log,
@@ -1319,6 +1319,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				  type, OVS_CT_ATTR_MAX);
 			return -EINVAL;
 		}
+
+		maxlen = ovs_ct_attr_lens[type].maxlen;
+		minlen = ovs_ct_attr_lens[type].minlen;
 		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
 			OVS_NLERR(log,
 				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 008bb34ee324..0615c2a950fa 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4329,7 +4329,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		register_prot_hook(sk);
 	}
 	spin_unlock(&po->bind_lock);
-	if (closing && (po->tp_version > TPACKET_V2)) {
+	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
diff --git a/net/socket.c b/net/socket.c
index bf2122691fba..ad22df1ffbd1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1916,7 +1916,7 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 	if (copy_from_user(&msg, umsg, sizeof(*umsg)))
 		return -EFAULT;
 
-	kmsg->msg_control = msg.msg_control;
+	kmsg->msg_control = (void __force *)msg.msg_control;
 	kmsg->msg_controllen = msg.msg_controllen;
 	kmsg->msg_flags = msg.msg_flags;
 
@@ -1935,7 +1935,8 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 
 	if (msg.msg_name && kmsg->msg_namelen) {
 		if (!save_addr) {
-			err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen,
+			err = move_addr_to_kernel(msg.msg_name,
+						  kmsg->msg_namelen,
 						  kmsg->msg_name);
 			if (err < 0)
 				return err;