Merge tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netstable

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, IPSec and Netfilter.

  Current release - fix to a fix:

   - netfilter: ipset: remove need to allocate memory on delete operations

  Current release - regressions:

   - macb: drop CONFIG_OF #if block, fix build

  Previous releases - always broken:

   - stream of fixes for SCTP continues

   - inet: frags: strip GSO state from fragments before reassembly

   - virtio-net: ensure that TCP packets don't overflow gso_segs

   - tcp-ao: fix use-after-free of current_key on reconnect to another
     peer

   - page_pool: remove zone/policy GFP flags when allocating XArray
     entries

   - Bluetooth: L2CAP: reject accept queue add unless BT_LISTEN

   - tls: device: fix out-of-bounds write in tls_append_frag()

   - eth: bnxt:
      - ring the doorbell when SW USO exits early, avoid packets stuck
        in Tx
      - gate TPH enablement behind BNXT_SUPPORTS_QUEUE_API check, avoid
        users of older NICs seeing non-actionable warning messages

   - eth: qede: fix NULL pointer dereference in TPA fragment processing"

* tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (216 commits)
  inet: frags: strip GSO state from fragments before reassembly
  net/sched: sch_htb: limit htb_classify inner-class filter hops
  selftests/net: packetdrill: add tcp_urg_ptr_retransmit
  tcp: fix corruption of urgent data on multi-segment retransmit
  usb: atm: usbatm: fix invalid ci_range initialization
  net: fec: only stop PTP if it was initialized
  slip: remove slip_hangup() to fix use-after-free in slip_receive_buf()
  net: bridge: mcast: fix use-after-free of a master VLAN's multicast context
  net/sched: bound qdisc_pkt_len to prevent qdisc soft lockup
  net: dsa: mxl862xx: enable assisted learning on CPU port
  net: stmmac: restore NET_IP_ALIGN in the RX DMA offset
  net: stmmac: drop gso_enabled_types and rely on netdev features
  net: stmmac: selftests: Don't test flow control for small rx fifos
  net: stmmac: selftests: Account for the UC filter list for filtering tests
  net: stmmac: dwxgmac: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac4: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac1000: Account for the primary MAC address for UC filtering
  net: stmmac: selftests: Check multiple MMC counters
  selftests: net: Fix slow configurations in big_tcp_tunnels.sh
  selftests: net: Lower threshold with csum offload off in big_tcp_tunnels.sh
  ...

11 files changed, 69 insertions, 28 deletions

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index fc0cb993959f..c17e57ec7d5c 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -435,6 +435,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
 {
 	struct sk_buff *last = q->fragments_tail;
 
+	/* An IP fragment is never a GSO packet, but an untrusted source
+	 * (virtio_net_hdr) may have attached GSO metadata to it. Do not let
+	 * that reach the reassembled skb, whose head keeps the first
+	 * fragment's shinfo and whose frag_list is not GRO-shaped.
+	 */
+	skb_gso_reset(skb);
+
 	/* RFC5722, Section 4, amended by Errata ID : 3089
 	 *                          When reassembling an IPv6 datagram, if
 	 *   one or more its constituent fragments is determined to be an
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 5b957a831e7c..adf6dc8a95b4 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -21,6 +21,7 @@
 #include <net/ip.h>
 #include <net/inetpeer.h>
 #include <net/secure_seq.h>
+#include <linux/siphash.h>
 
 /*
  *  Theory of operations.
@@ -52,6 +53,34 @@
  */
 
 static struct kmem_cache *peer_cachep __ro_after_init;
+static siphash_aligned_key_t inetpeer_hash_key __read_mostly;
+
+static u64 inetpeer_addr_hash(const struct inetpeer_addr *a)
+{
+	net_get_random_once(&inetpeer_hash_key, sizeof(inetpeer_hash_key));
+
+	if (a->family == AF_INET)
+		return siphash_2u32((__force u32)a->a4.addr, a->a4.vif,
+				    &inetpeer_hash_key);
+
+	return siphash_4u32((__force u32)a->a6.s6_addr32[0],
+			    (__force u32)a->a6.s6_addr32[1],
+			    (__force u32)a->a6.s6_addr32[2],
+			    (__force u32)a->a6.s6_addr32[3],
+			    &inetpeer_hash_key);
+}
+
+static int inetpeer_entry_cmp(u64 dhash,
+			      const struct inetpeer_addr *daddr,
+			      const struct inet_peer *p)
+{
+	if (dhash < p->hash)
+		return -1;
+	if (dhash > p->hash)
+		return 1;
+
+	return inetpeer_addr_cmp(daddr, &p->daddr);
+}
 
 void inet_peer_base_init(struct inet_peer_base *bp)
 {
@@ -84,6 +113,7 @@ void __init inet_initpeers(void)
 
 /* Called with rcu_read_lock() or base->lock held */
 static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
+				u64 dhash,
 				struct inet_peer_base *base,
 				unsigned int seq,
 				struct inet_peer *gc_stack[],
@@ -105,7 +135,7 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
 			break;
 		parent = next;
 		p = rb_entry(parent, struct inet_peer, rb_node);
-		cmp = inetpeer_addr_cmp(daddr, &p->daddr);
+		cmp = inetpeer_entry_cmp(dhash, daddr, p);
 		if (cmp == 0) {
 			now = jiffies;
 			if (READ_ONCE(p->dtime) != now)
@@ -170,6 +200,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			       const struct inetpeer_addr *daddr)
 {
 	struct inet_peer *p, *gc_stack[PEER_MAX_GC];
+	u64 dhash = inetpeer_addr_hash(daddr);
 	struct rb_node **pp, *parent;
 	unsigned int gc_cnt, seq;
 
@@ -177,7 +208,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	 * Because of a concurrent writer, we might not find an existing entry.
 	 */
 	seq = read_seqbegin(&base->lock);
-	p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
+	p = lookup(daddr, dhash, base, seq, NULL, &gc_cnt, &parent, &pp);
 
 	/* Make sure tree was not modified during our lookup. */
 	if (p && !read_seqretry(&base->lock, seq))
@@ -190,11 +221,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	write_seqlock_bh(&base->lock);
 
 	gc_cnt = 0;
-	p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
+	p = lookup(daddr, dhash, base, seq, gc_stack, &gc_cnt, &parent, &pp);
 	if (!p) {
 		p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
 		if (p) {
 			p->daddr = *daddr;
+			p->hash = dhash;
 			p->dtime = (__u32)jiffies;
 			refcount_set(&p->refcnt, 1);
 			atomic_set(&p->rid, 0);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 1630325c77d3..f684baf8e58f 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -248,7 +248,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 
 			tun_dst = ip_tun_rx_dst(skb, flags, 0, 0);
 			if (!tun_dst)
-				return 0;
+				goto drop;
 			ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info);
 		}
 		skb_reset_mac_header(skb);
diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c
index 161ba412cb08..7131f297ada2 100644
--- a/net/ipv4/netfilter/ipt_ah.c
+++ b/net/ipv4/netfilter/ipt_ah.c
@@ -19,12 +19,7 @@ MODULE_DESCRIPTION("Xtables: IPv4 IPsec-AH SPI match");
 static inline bool
 spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
 {
-	bool r;
-	pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
-		 invert ? '!' : ' ', min, spi, max);
-	r = (spi >= min && spi <= max) ^ invert;
-	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
-	return r;
+	return (spi >= min && spi <= max) ^ invert;
 }
 
 static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -42,7 +37,6 @@ static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		/* We've been asked to examine this packet, and we
 		 * can't.  Hence, no choice but to drop.
 		 */
-		pr_debug("Dropping evil AH tinygram.\n");
 		par->hotdrop = true;
 		return false;
 	}
@@ -58,7 +52,7 @@ static int ah_mt_check(const struct xt_mtchk_param *par)
 
 	/* Must specify no unknown invflags */
 	if (ahinfo->invflags & ~IPT_AH_INV_MASK) {
-		pr_debug("unknown flags %X\n", ahinfo->invflags);
+		pr_info_ratelimited("unknown flags %X\n", ahinfo->invflags);
 		return -EINVAL;
 	}
 	return 0;
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 041c3f37f237..5eab7a2dc8ef 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -137,7 +137,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		}
 		break;
 	default:
-		WARN_ON(1);
+		DEBUG_NET_WARN_ON_ONCE(1);
 		sk = NULL;
 	}
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 604cc51dfd9b..37674d76f90f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1363,8 +1363,8 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 
 	rcu_read_lock();
 	net = dst_dev_net_rcu(dst);
-	advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
-				   net->ipv4.ip_rt_min_advmss);
+	advmss = max_t(unsigned int, ip_dst_mtu_configured(dst) - header_size,
+		       net->ipv4.ip_rt_min_advmss);
 	rcu_read_unlock();
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 455441f1b694..b4237d0e994d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1240,7 +1240,8 @@ restart:
 
 		trace_tcp_sendmsg_locked(sk, msg, skb, size_goal);
 
-		if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
+		if (copy <= 0 || !tcp_skb_can_collapse_to(skb) ||
+		    unlikely(skb_frags_readable(skb) != !binding)) {
 			bool first_skb;
 
 new_segment:
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index e4ec60a33496..bb7bbc20ba3f 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1160,6 +1160,15 @@ void tcp_ao_connect_init(struct sock *sk)
 	l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
 						 sk->sk_bound_dev_if);
 
+	hlist_for_each_entry(key, &ao_info->head, node) {
+		if (tcp_ao_key_cmp(key, l3index, addr, key->prefixlen,
+				   family, -1, -1)) {
+			/* pairs with tcp_inbound_ao_hash() */
+			synchronize_rcu();
+			break;
+		}
+	}
+
 	hlist_for_each_entry_safe(key, next, &ao_info->head, node) {
 		if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1))
 			continue;
@@ -1187,12 +1196,7 @@ void tcp_ao_connect_init(struct sock *sk)
 		ao_info->lisn = htonl(tp->write_seq);
 		ao_info->snd_sne = 0;
 	} else {
-		/* Can't happen: tcp_connect() verifies that there's
-		 * at least one tcp-ao key that matches the remote peer.
-		 */
-		WARN_ON_ONCE(1);
-		rcu_assign_pointer(tp->ao_info, NULL);
-		kfree(ao_info);
+		tcp_ao_destroy_sock(sk, false);
 	}
 }
 
@@ -1825,6 +1829,9 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family,
 	if (cmd.ifindex && !(cmd.keyflags & TCP_AO_KEYF_IFINDEX))
 		return -EINVAL;
 
+	if (cmd.keyflags & TCP_AO_KEYF_IFINDEX)
+		l3index = cmd.ifindex;
+
 	ao_info = setsockopt_ao_info(sk);
 	if (IS_ERR(ao_info))
 		return PTR_ERR(ao_info);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 190c7af4cf92..9f053eb8b46e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1736,7 +1736,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
-	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst));
+	newtp->advmss = tcp_mss_clamp(tcp_sk(sk), tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(newsk);
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 12254e6eb2f3..f3fa0b18eda0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -440,7 +440,7 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 	u32 rcv_wnd;
 	int mss;
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 	window_clamp = READ_ONCE(tp->window_clamp);
 	/* Set this up on the first call only */
 	req->rsk_window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fcaa04e65189..6f4dca4a4de9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -143,7 +143,7 @@ static __u16 tcp_advertise_mss(struct sock *sk)
 	int mss = tp->advmss;
 
 	if (dst) {
-		unsigned int metric = dst_metric_advmss(dst);
+		unsigned int metric = tcp_dst_advmss(dst);
 
 		if (metric < mss) {
 			mss = metric;
@@ -3603,7 +3603,7 @@ start:
 		avail_wnd = cur_mss;
 	}
 
-	len = cur_mss * segs;
+	len = cur_mss * (tcp_urg_mode(tp) ? 1 : segs);
 	if (len > avail_wnd) {
 		len = rounddown(avail_wnd, cur_mss);
 		if (!len)
@@ -3972,7 +3972,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	}
 	skb_dst_set(skb, dst);
 
-	mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	mss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	memset(&opts, 0, sizeof(opts));
 	now = tcp_clock_ns();
@@ -4128,7 +4128,7 @@ static void tcp_connect_init(struct sock *sk)
 
 	if (!tp->window_clamp)
 		WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW));
-	tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
+	tp->advmss = tcp_mss_clamp(tp, tcp_dst_advmss(dst));
 
 	tcp_initialize_rcv_mss(sk);