Merge tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf and netfilter.

  A lot of networking people were at a conference last week, busy
  catching COVID, so relatively short PR.

  Current release - regressions:

   - tcp: process the 3rd ACK with sk_socket for TFO and MPTCP

  Current release - new code bugs:

   - l2tp: protect session IDR and tunnel session list with one lock,
     make sure the state is coherent to avoid a warning

   - eth: bnxt_en: update xdp_rxq_info in queue restart logic

   - eth: airoha: fix location of the MBI_RX_AGE_SEL_MASK field

  Previous releases - regressions:

   - xsk: require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len,
     the field reuses previously un-validated pad

  Previous releases - always broken:

   - tap/tun: drop short frames to prevent crashes later in the stack

   - eth: ice: add a per-VF limit on number of FDIR filters

   - af_unix: disable MSG_OOB handling for sockets in sockmap/sockhash"

* tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (34 commits)
  tun: add missing verification for short frame
  tap: add missing verification for short frame
  mISDN: Fix a use after free in hfcmulti_tx()
  gve: Fix an edge case for TSO skb validity check
  bnxt_en: update xdp_rxq_info in queue restart logic
  tcp: process the 3rd ACK with sk_socket for TFO/MPTCP
  selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test
  xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len
  bpf: Fix a segment issue when downgrading gso_size
  net: mediatek: Fix potential NULL pointer dereference in dummy net_device handling
  MAINTAINERS: make Breno the netconsole maintainer
  MAINTAINERS: Update bonding entry
  net: nexthop: Initialize all fields in dumped nexthops
  net: stmmac: Correct byte order of perfect_match
  selftests: forwarding: skip if kernel not support setting bridge fdb learning limit
  tipc: Return non-zero value from tipc_udp_addr2str() on error
  netfilter: nft_set_pipapo_avx2: disable softinterrupts
  ice: Fix recipe read procedure
  ice: Add a per-VF limit on number of FDIR filters
  net: bonding: correctly annotate RCU in bond_should_notify_peers()
  ...

10 files changed, 93 insertions, 36 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 4cf1d34f7617..f3c72cf86099 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3548,13 +3548,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		/* Due to header grow, MSS needs to be downgraded. */
-		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
-			skb_decrease_gso_size(shinfo, len_diff);
-
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= gso_type;
 		shinfo->gso_segs = 0;
+
+		/* Due to header growth, MSS needs to be downgraded.
+		 * There is a BUG_ON() when segmenting the frag_list with
+		 * head_frag true, so linearize the skb after downgrading
+		 * the MSS.
+		 */
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) {
+			skb_decrease_gso_size(shinfo, len_diff);
+			if (shinfo->frag_list)
+				return skb_linearize(skb);
+		}
 	}
 
 	return 0;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 535856b0f0ed..6b9787ee8601 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -888,9 +888,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 
 	p = nla_data(nla);
 	for (i = 0; i < nhg->num_nh; ++i) {
-		p->id = nhg->nh_entries[i].nh->id;
-		p->weight = nhg->nh_entries[i].weight - 1;
-		p += 1;
+		*p++ = (struct nexthop_grp) {
+			.id = nhg->nh_entries[i].nh->id,
+			.weight = nhg->nh_entries[i].weight - 1,
+		};
 	}
 
 	if (nhg->resilient && nla_put_nh_group_res(skb, nhg))
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5cc476ee8ced..13c0f1d455f3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		struct flowi4 fl4 = {
 			.daddr = iph->daddr,
 			.saddr = iph->saddr,
-			.flowi4_tos = RT_TOS(iph->tos),
+			.flowi4_tos = iph->tos & IPTOS_RT_MASK,
 			.flowi4_oif = rt->dst.dev->ifindex,
 			.flowi4_iif = skb->dev->ifindex,
 			.flowi4_mark = skb->mark,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ff9ab3d01ced..454362e359da 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6819,9 +6819,6 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		tcp_fast_path_on(tp);
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			tcp_shutdown(sk, SEND_SHUTDOWN);
-
-		if (sk->sk_socket)
-			goto consume;
 		break;
 
 	case TCP_FIN_WAIT1: {
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1c1decce7f06..c80ab3f26084 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -441,14 +441,15 @@ int l2tp_session_register(struct l2tp_session *session,
 	int err;
 
 	spin_lock_bh(&tunnel->list_lock);
+	spin_lock_bh(&pn->l2tp_session_idr_lock);
+
 	if (!tunnel->acpt_newsess) {
 		err = -ENODEV;
-		goto err_tlock;
+		goto out;
 	}
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		session_key = session->session_id;
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL,
 				    &session_key, session_key, GFP_ATOMIC);
 		/* IP encap expects session IDs to be globally unique, while
@@ -462,43 +463,36 @@ int l2tp_session_register(struct l2tp_session *session,
 			err = l2tp_session_collision_add(pn, session,
 							 other_session);
 		}
-		spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	} else {
 		session_key = l2tp_v2_session_key(tunnel->tunnel_id,
 						  session->session_id);
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL,
 				    &session_key, session_key, GFP_ATOMIC);
-		spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	}
 
 	if (err) {
 		if (err == -ENOSPC)
 			err = -EEXIST;
-		goto err_tlock;
+		goto out;
 	}
 
 	l2tp_tunnel_inc_refcount(tunnel);
-
 	list_add(&session->list, &tunnel->session_list);
-	spin_unlock_bh(&tunnel->list_lock);
 
-	spin_lock_bh(&pn->l2tp_session_idr_lock);
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		if (!other_session)
 			idr_replace(&pn->l2tp_v3_session_idr, session, session_key);
 	} else {
 		idr_replace(&pn->l2tp_v2_session_idr, session, session_key);
 	}
-	spin_unlock_bh(&pn->l2tp_session_idr_lock);
-
-	trace_register_session(session);
 
-	return 0;
-
-err_tlock:
+out:
+	spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	spin_unlock_bh(&tunnel->list_lock);
 
+	if (!err)
+		trace_register_session(session);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
@@ -1260,13 +1254,13 @@ static void l2tp_session_unhash(struct l2tp_session *session)
 		struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
 		struct l2tp_session *removed = session;
 
-		/* Remove from the per-tunnel list */
 		spin_lock_bh(&tunnel->list_lock);
+		spin_lock_bh(&pn->l2tp_session_idr_lock);
+
+		/* Remove from the per-tunnel list */
 		list_del_init(&session->list);
-		spin_unlock_bh(&tunnel->list_lock);
 
 		/* Remove from per-net IDR */
-		spin_lock_bh(&pn->l2tp_session_idr_lock);
 		if (tunnel->version == L2TP_HDR_VER_3) {
 			if (hash_hashed(&session->hlist))
 				l2tp_session_collision_del(pn, session);
@@ -1280,7 +1274,9 @@ static void l2tp_session_unhash(struct l2tp_session *session)
 					     session_key);
 		}
 		WARN_ON_ONCE(removed && removed != session);
+
 		spin_unlock_bh(&pn->l2tp_session_idr_lock);
+		spin_unlock_bh(&tunnel->list_lock);
 
 		synchronize_rcu();
 	}
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 8910a5ac7ed1..b8d3c3213efe 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1139,8 +1139,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	bool map_index;
 	int i, ret = 0;
 
-	if (unlikely(!irq_fpu_usable()))
-		return nft_pipapo_lookup(net, set, key, ext);
+	local_bh_disable();
+
+	if (unlikely(!irq_fpu_usable())) {
+		bool fallback_res = nft_pipapo_lookup(net, set, key, ext);
+
+		local_bh_enable();
+		return fallback_res;
+	}
 
 	m = rcu_dereference(priv->match);
 
@@ -1155,6 +1161,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	scratch = *raw_cpu_ptr(m->scratch);
 	if (unlikely(!scratch)) {
 		kernel_fpu_end();
+		local_bh_enable();
 		return false;
 	}
 
@@ -1235,6 +1242,7 @@ out:
 	if (i % 2)
 		scratch->map_index = !map_index;
 	kernel_fpu_end();
+	local_bh_enable();
 
 	return ret >= 0;
 }
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index b849a3d133a0..439f75539977 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -135,8 +135,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
 		snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
 	else if (ntohs(ua->proto) == ETH_P_IPV6)
 		snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
-	else
+	else {
 		pr_err("Invalid UDP media address\n");
+		return 1;
+	}
+
 	return 0;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b0a4c6d08e0a..0be0dcb07f7b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2721,10 +2721,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
+	struct unix_sock *u = unix_sk(sk);
+	struct sk_buff *skb;
+	int err;
+
 	if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
 		return -ENOTCONN;
 
-	return unix_read_skb(sk, recv_actor);
+	mutex_lock(&u->iolock);
+	skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
+	mutex_unlock(&u->iolock);
+	if (!skb)
+		return err;
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (unlikely(skb == READ_ONCE(u->oob_skb))) {
+		bool drop = false;
+
+		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD)) {
+			unix_state_unlock(sk);
+			kfree_skb(skb);
+			return -ECONNRESET;
+		}
+
+		spin_lock(&sk->sk_receive_queue.lock);
+		if (likely(skb == u->oob_skb)) {
+			WRITE_ONCE(u->oob_skb, NULL);
+			drop = true;
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		unix_state_unlock(sk);
+
+		if (drop) {
+			WARN_ON_ONCE(skb_unref(skb));
+			kfree_skb(skb);
+			return -EAGAIN;
+		}
+	}
+#endif
+
+	return recv_actor(sk, skb);
 }
 
 static int unix_stream_read_generic(struct unix_stream_read_state *state,
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index bd84785bf8d6..bca2d86ba97d 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 	struct sk_psock *psock;
 	int copied;
 
+	if (flags & MSG_OOB)
+		return -EOPNOTSUPP;
+
 	if (!len)
 		return 0;
 
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index caa340134b0e..9f76ca591d54 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 #define XDP_UMEM_FLAGS_VALID ( \
 		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
 		XDP_UMEM_TX_SW_CSUM | \
+		XDP_UMEM_TX_METADATA_LEN | \
 	0)
 
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
@@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
-	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
-		return -EINVAL;
+	if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
+		if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+			return -EINVAL;
+		umem->tx_metadata_len = mr->tx_metadata_len;
+	}
 
 	umem->size = size;
 	umem->headroom = headroom;
@@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);