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

Pull networking fixes from David Miller:

 1) Fix free/alloc races in batmanadv, from Sven Eckelmann.

 2) Several leaks and other fixes in kTLS support of mlx5 driver, from
    Tariq Toukan.

 3) BPF devmap_hash cost calculation can overflow on 32-bit, from Toke
    Høiland-Jørgensen.

 4) Add an r8152 device ID, from Kazutoshi Noguchi.

 5) Missing include in ipv6's addrconf.c, from Ben Dooks.

 6) Use siphash in flow dissector, from Eric Dumazet. Attackers can
    easily infer the 32-bit secret otherwise etc.

 7) Several netdevice nesting depth fixes from Taehee Yoo.

 8) Fix several KCSAN reported errors, from Eric Dumazet. For example,
    when doing lockless skb_queue_empty() checks, and accessing
    sk_napi_id/sk_incoming_cpu lockless as well.

 9) Fix jumbo packet handling in RXRPC, from David Howells.

10) Bump SOMAXCONN and tcp_max_syn_backlog values, from Eric Dumazet.

11) Fix DMA synchronization in gve driver, from Yangchun Fu.

12) Several bpf offload fixes, from Jakub Kicinski.

13) Fix sk_page_frag() recursion during memory reclaim, from Tejun Heo.

14) Fix ping latency during high traffic rates in hisilicon driver, from
    Jiangfent Xiao.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (146 commits)
  net: fix installing orphaned programs
  net: cls_bpf: fix NULL deref on offload filter removal
  selftests: bpf: Skip write only files in debugfs
  selftests: net: reuseport_dualstack: fix uninitalized parameter
  r8169: fix wrong PHY ID issue with RTL8168dp
  net: dsa: bcm_sf2: Fix IMP setup for port different than 8
  net: phylink: Fix phylink_dbg() macro
  gve: Fixes DMA synchronization.
  inet: stop leaking jiffies on the wire
  ixgbe: Remove duplicate clear_bit() call
  Documentation: networking: device drivers: Remove stray asterisks
  e1000: fix memory leaks
  i40e: Fix receive buffer starvation for AF_XDP
  igb: Fix constant media auto sense switching when no cable is connected
  net: ethernet: arc: add the missed clk_disable_unprepare
  igb: Enable media autosense for the i350.
  igb/igc: Don't warn on fatal read failures when the device is removed
  tcp: increase tcp_max_syn_backlog max value
  net: increase SOMAXCONN to 4096
  netdevsim: Fix use-after-free during device dismantle
  ...

8 files changed, 36 insertions, 24 deletions

diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 9a0fe0c2fa02..4a8550c49202 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
-	inet->inet_id = jiffies;
+	inet->inet_id = prandom_u32();
 
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index dde77f72e03e..71c78d223dfd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1148,7 +1148,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric)
 	if (!(dev->flags & IFF_UP) ||
 	    ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) ||
 	    ipv4_is_zeronet(prefix) ||
-	    prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32)
+	    (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32))
 		return;
 
 	/* add the new */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 97824864e40d..83fb00153018 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			return -1;
 
 		score = sk->sk_family == PF_INET ? 2 : 1;
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 52690bb3e40f..10636fb6093e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -509,9 +509,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 	key = &tun_info->key;
 	if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
 		goto err_free_skb;
-	md = ip_tunnel_info_opts(tun_info);
-	if (!md)
+	if (tun_info->options_len < sizeof(*md))
 		goto err_free_skb;
+	md = ip_tunnel_info_opts(tun_info);
 
 	/* ERSPAN has fixed 8 byte GRE header */
 	version = md->version;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 814b9b8882a0..3d8baaaf7086 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -645,11 +645,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
 EXPORT_SYMBOL(ip_fraglist_prepare);
 
 void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
-		  unsigned int ll_rs, unsigned int mtu,
+		  unsigned int ll_rs, unsigned int mtu, bool DF,
 		  struct ip_frag_state *state)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
+	state->DF = DF;
 	state->hlen = hlen;
 	state->ll_rs = ll_rs;
 	state->mtu = mtu;
@@ -668,9 +669,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
-	if (IPCB(from)->flags & IPSKB_FRAG_PMTU)
-		state->iph->frag_off |= htons(IP_DF);
-
 	/* ANK: dirty, but effective trick. Upgrade options only if
 	 * the segment to be fragmented was THE FIRST (otherwise,
 	 * options are already fixed) and make it ONCE
@@ -738,6 +736,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
 	 */
 	iph = ip_hdr(skb2);
 	iph->frag_off = htons((state->offset >> 3));
+	if (state->DF)
+		iph->frag_off |= htons(IP_DF);
 
 	/*
 	 *	Added AC : If we are fragmenting a fragment that's not the
@@ -883,7 +883,8 @@ slow_path:
 	 *	Fragment the datagram.
 	 */
 
-	ip_frag_init(skb, hlen, ll_rs, mtu, &state);
+	ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
+		     &state);
 
 	/*
 	 *	Keep copying data until we run out.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 42187a3b82f4..d8876f0e9672 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR;
 
 	return mask;
@@ -1964,7 +1964,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
 		sk_busy_loop(sk, nonblock);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6be568334848..67b2dc7a1727 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -303,7 +303,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						 inet->inet_daddr);
 	}
 
-	inet->inet_id = tp->write_seq ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
@@ -1450,7 +1450,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	newinet->inet_id = newtp->write_seq ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
@@ -2681,7 +2681,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
-	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 14bc654b6842..1d58ce829dca 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net,
 		return -1;
 	score += 4;
 
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
+	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 		score++;
 	return score;
 }
@@ -1316,6 +1316,20 @@ static void udp_set_dev_scratch(struct sk_buff *skb)
 		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
+static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
+{
+	/* We come here after udp_lib_checksum_complete() returned 0.
+	 * This means that __skb_checksum_complete() might have
+	 * set skb->csum_valid to 1.
+	 * On 64bit platforms, we can set csum_unnecessary
+	 * to true, but only if the skb is not shared.
+	 */
+#if BITS_PER_LONG == 64
+	if (!skb_shared(skb))
+		udp_skb_scratch(skb)->csum_unnecessary = true;
+#endif
+}
+
 static int udp_skb_truesize(struct sk_buff *skb)
 {
 	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
@@ -1550,10 +1564,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk,
 			*total += skb->truesize;
 			kfree_skb(skb);
 		} else {
-			/* the csum related bits could be changed, refresh
-			 * the scratch area
-			 */
-			udp_set_dev_scratch(skb);
+			udp_skb_csum_unnecessary_set(skb);
 			break;
 		}
 	}
@@ -1577,7 +1588,7 @@ static int first_packet_length(struct sock *sk)
 
 	spin_lock_bh(&rcvq->lock);
 	skb = __first_packet_length(sk, rcvq, &total);
-	if (!skb && !skb_queue_empty(sk_queue)) {
+	if (!skb && !skb_queue_empty_lockless(sk_queue)) {
 		spin_lock(&sk_queue->lock);
 		skb_queue_splice_tail_init(sk_queue, rcvq);
 		spin_unlock(&sk_queue->lock);
@@ -1650,7 +1661,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 				return skb;
 			}
 
-			if (skb_queue_empty(sk_queue)) {
+			if (skb_queue_empty_lockless(sk_queue)) {
 				spin_unlock_bh(&queue->lock);
 				goto busy_check;
 			}
@@ -1676,7 +1687,7 @@ busy_check:
 				break;
 
 			sk_busy_loop(sk, flags & MSG_DONTWAIT);
-		} while (!skb_queue_empty(sk_queue));
+		} while (!skb_queue_empty_lockless(sk_queue));
 
 		/* sk_queue is empty, reader_queue may contain peeked packets */
 	} while (timeo &&
@@ -2712,7 +2723,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	__poll_t mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
-	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
+	if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Check for false positives due to checksum errors */