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

Pull networking fixes from David Miller:
 "Lots of bug fixes here:

   1) Out of bounds access in __bpf_skc_lookup, from Lorenz Bauer.

   2) Fix rate reporting in cfg80211_calculate_bitrate_he(), from John
      Crispin.

   3) Use after free in psock backlog workqueue, from John Fastabend.

   4) Fix source port matching in fdb peer flow rule of mlx5, from Raed
      Salem.

   5) Use atomic_inc_not_zero() in fl6_sock_lookup(), from Eric Dumazet.

   6) Network header needs to be set for packet redirect in nfp, from
      John Hurley.

   7) Fix udp zerocopy refcnt, from Willem de Bruijn.

   8) Don't assume linear buffers in vxlan and geneve error handlers,
      from Stefano Brivio.

   9) Fix TOS matching in mlxsw, from Jiri Pirko.

  10) More SCTP cookie memory leak fixes, from Neil Horman.

  11) Fix VLAN filtering in rtl8366, from Linus Walluij.

  12) Various TCP SACK payload size and fragmentation memory limit fixes
      from Eric Dumazet.

  13) Use after free in pneigh_get_next(), also from Eric Dumazet.

  14) LAPB control block leak fix from Jeremy Sowden"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (145 commits)
  lapb: fixed leak of control-blocks.
  tipc: purge deferredq list for each grp member in tipc_group_delete
  ax25: fix inconsistent lock state in ax25_destroy_timer
  neigh: fix use-after-free read in pneigh_get_next
  tcp: fix compile error if !CONFIG_SYSCTL
  hv_sock: Suppress bogus "may be used uninitialized" warnings
  be2net: Fix number of Rx queues used for flow hashing
  net: handle 802.1P vlan 0 packets properly
  tcp: enforce tcp_min_snd_mss in tcp_mtu_probing()
  tcp: add tcp_min_snd_mss sysctl
  tcp: tcp_fragment() should apply sane memory limits
  tcp: limit payload size of sacked skbs
  Revert "net: phylink: set the autoneg state in phylink_phy_change"
  bpf: fix nested bpf tracepoints with per-cpu data
  bpf: Fix out of bounds memory access in bpf_sk_storage
  vsock/virtio: set SOCK_DONE on peer shutdown
  net: dsa: rtl8366: Fix up VLAN filtering
  net: phylink: set the autoneg state in phylink_phy_change
  net: add high_order_alloc_disable sysctl/static key
  tcp: add tcp_tx_skb_cache sysctl
  ...

10 files changed, 71 insertions, 13 deletions

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b80410673915..bfa49a88d03a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -964,7 +964,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
 {
 	struct net_device *dev;
 	struct fib_result res;
-	int err;
+	int err = 0;
 
 	if (nh->fib_nh_flags & RTNH_F_ONLINK) {
 		unsigned int addr_type;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8c9189a41b13..16f9159234a2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -918,7 +918,7 @@ static int __ip_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
-		extra_uref = !skb;	/* only extra ref if !MSG_MORE */
+		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 4370f4246e86..073273b751f8 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -287,6 +287,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
 	SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
 	SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
+	SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 875867b64d6a..b6f14af926fa 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -39,6 +39,8 @@ static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
 static int tcp_adv_win_scale_min = -31;
 static int tcp_adv_win_scale_max = 31;
+static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS;
+static int tcp_min_snd_mss_max = 65535;
 static int ip_privileged_port_min;
 static int ip_privileged_port_max = 65535;
 static int ip_ttl_min = 1;
@@ -559,6 +561,18 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &sysctl_fib_sync_mem_min,
 		.extra2		= &sysctl_fib_sync_mem_max,
 	},
+	{
+		.procname	= "tcp_rx_skb_cache",
+		.data		= &tcp_rx_skb_cache_key.key,
+		.mode		= 0644,
+		.proc_handler	= proc_do_static_key,
+	},
+	{
+		.procname	= "tcp_tx_skb_cache",
+		.data		= &tcp_tx_skb_cache_key.key,
+		.mode		= 0644,
+		.proc_handler	= proc_do_static_key,
+	},
 	{ }
 };
 
@@ -758,6 +772,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "tcp_min_snd_mss",
+		.data		= &init_net.ipv4.sysctl_tcp_min_snd_mss,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &tcp_min_snd_mss_min,
+		.extra2		= &tcp_min_snd_mss_max,
+	},
+	{
 		.procname	= "tcp_probe_threshold",
 		.data		= &init_net.ipv4.sysctl_tcp_probe_threshold,
 		.maxlen		= sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f12d500ec85c..7dc9ab84bb69 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -317,6 +317,11 @@ struct tcp_splice_state {
 unsigned long tcp_memory_pressure __read_mostly;
 EXPORT_SYMBOL_GPL(tcp_memory_pressure);
 
+DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key);
+EXPORT_SYMBOL(tcp_rx_skb_cache_key);
+
+DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
+
 void tcp_enter_memory_pressure(struct sock *sk)
 {
 	unsigned long val;
@@ -3868,6 +3873,7 @@ void __init tcp_init(void)
 	unsigned long limit;
 	unsigned int i;
 
+	BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
 		     FIELD_SIZEOF(struct sk_buff, cb));
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 08a477e74cf3..d95ee40df6c2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1302,7 +1302,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 	TCP_SKB_CB(skb)->seq += shifted;
 
 	tcp_skb_pcount_add(prev, pcount);
-	BUG_ON(tcp_skb_pcount(skb) < pcount);
+	WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount);
 	tcp_skb_pcount_add(skb, -pcount);
 
 	/* When we're adding to gso_segs == 1, gso_size will be zero,
@@ -1368,6 +1368,21 @@ static int skb_can_shift(const struct sk_buff *skb)
 	return !skb_headlen(skb) && skb_is_nonlinear(skb);
 }
 
+int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from,
+		  int pcount, int shiftlen)
+{
+	/* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE)
+	 * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need
+	 * to make sure not storing more than 65535 * 8 bytes per skb,
+	 * even if current MSS is bigger.
+	 */
+	if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE))
+		return 0;
+	if (unlikely(tcp_skb_pcount(to) + pcount > 65535))
+		return 0;
+	return skb_shift(to, from, shiftlen);
+}
+
 /* Try collapsing SACK blocks spanning across multiple skbs to a single
  * skb.
  */
@@ -1473,7 +1488,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una))
 		goto fallback;
 
-	if (!skb_shift(prev, skb, len))
+	if (!tcp_skb_shift(prev, skb, pcount, len))
 		goto fallback;
 	if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
 		goto out;
@@ -1491,11 +1506,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 		goto out;
 
 	len = skb->len;
-	if (skb_shift(prev, skb, len)) {
-		pcount += tcp_skb_pcount(skb);
-		tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+	pcount = tcp_skb_pcount(skb);
+	if (tcp_skb_shift(prev, skb, pcount, len))
+		tcp_shifted_skb(sk, prev, skb, state, pcount,
 				len, mss, 0);
-	}
 
 out:
 	return prev;
@@ -2648,7 +2662,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
-	if ((flag & FLAG_SND_UNA_ADVANCED) &&
+	if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
 	    tcp_try_undo_loss(sk, false))
 		return;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bc86f9735f45..cfa81190a1b1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2628,6 +2628,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_ecn_fallback = 1;
 
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
+	net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
 	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f429e856e263..00c01a01b547 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1296,6 +1296,11 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	if (nsize < 0)
 		nsize = 0;
 
+	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf)) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+		return -ENOMEM;
+	}
+
 	if (skb_unclone(skb, gfp))
 		return -ENOMEM;
 
@@ -1454,8 +1459,7 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	mss_now -= icsk->icsk_ext_hdr_len;
 
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
-	if (mss_now < 48)
-		mss_now = 48;
+	mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
 	return mss_now;
 }
 
@@ -2747,7 +2751,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 		if (next_skb_size <= skb_availroom(skb))
 			skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
 				      next_skb_size);
-		else if (!skb_shift(skb, next_skb, next_skb_size))
+		else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size))
 			return false;
 	}
 	tcp_highest_sack_replace(sk, next_skb, skb);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5bad937ce779..c801cd37cc2a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -155,6 +155,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 		mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
 		mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
 		mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len);
+		mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss);
 		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 	}
 	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7c6228fbf5dd..eed59c847722 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -498,7 +498,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
-	return __udp4_lib_lookup_skb(skb, sport, dport, &udp_table);
+	const struct iphdr *iph = ip_hdr(skb);
+
+	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 inet_sdif(skb), &udp_table, NULL);
 }
 EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
 
@@ -1773,6 +1777,10 @@ try_again:
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 		*addr_len = sizeof(*sin);
+
+		if (cgroup_bpf_enabled)
+			BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk,
+							(struct sockaddr *)sin);
 	}
 
 	if (udp_sk(sk)->gro_enabled)