Merge tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Quite smaller than usual. Notably it includes the fix for the unix
  regression from the past weeks. The TCP window fix will require some
  follow-up, already queued.

  Current release - regressions:

   - af_unix: fix garbage collection of embryos

  Previous releases - regressions:

   - af_unix: fix race between GC and receive path

   - ipv6: sr: fix missing sk_buff release in seg6_input_core

   - tcp: remove 64 KByte limit for initial tp->rcv_wnd value

   - eth: r8169: fix rx hangup

   - eth: lan966x: remove ptp traps in case the ptp is not enabled

   - eth: ixgbe: fix link breakage vs cisco switches

   - eth: ice: prevent ethtool from corrupting the channels

  Previous releases - always broken:

   - openvswitch: set the skbuff pkt_type for proper pmtud support

   - tcp: Fix shift-out-of-bounds in dctcp_update_alpha()

  Misc:

   - a bunch of selftests stabilization patches"

* tag 'net-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (25 commits)
  r8169: Fix possible ring buffer corruption on fragmented Tx packets.
  idpf: Interpret .set_channels() input differently
  ice: Interpret .set_channels() input differently
  nfc: nci: Fix handling of zero-length payload packets in nci_rx_work()
  net: relax socket state check at accept time.
  tcp: remove 64 KByte limit for initial tp->rcv_wnd value
  net: ti: icssg_prueth: Fix NULL pointer dereference in prueth_probe()
  tls: fix missing memory barrier in tls_init
  net: fec: avoid lock evasion when reading pps_enable
  Revert "ixgbe: Manual AN-37 for troublesome link partners for X550 SFI"
  testing: net-drv: use stats64 for testing
  net: mana: Fix the extra HZ in mana_hwc_send_request
  net: lan966x: Remove ptp traps in case the ptp is not enabled.
  openvswitch: Set the skbuff pkt_type for proper pmtud support.
  selftest: af_unix: Make SCM_RIGHTS into OOB data.
  af_unix: Fix garbage collection of embryos carrying OOB with SCM_RIGHTS
  tcp: Fix shift-out-of-bounds in dctcp_update_alpha().
  selftests/net: use tc rule to filter the na packet
  ipv6: sr: fix memleak in seg6_hmac_init_algo
  af_unix: Update unix_sk(sk)->oob_skb under sk_receive_queue lock.
  ...

10 files changed, 116 insertions, 41 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ce50d7187a3f..e03ba4a21c39 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -758,7 +758,9 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new
 	sock_rps_record_flow(newsk);
 	WARN_ON(!((1 << newsk->sk_state) &
 		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
-		  TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+		   TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 |
+		   TCPF_CLOSING | TCPF_CLOSE_WAIT |
+		   TCPF_CLOSE)));
 
 	if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
 		set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 6b712a33d49f..8a45a4aea933 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -58,7 +58,18 @@ struct dctcp {
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
-module_param(dctcp_shift_g, uint, 0644);
+
+static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp, 0, 10);
+}
+
+static const struct kernel_param_ops dctcp_shift_g_ops = {
+	.set = dctcp_shift_g_set,
+	.get = param_get_uint,
+};
+
+module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644);
 MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
 
 static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 95caf8aaa8be..95618d0e78e4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -232,7 +232,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
 		(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
 	else
-		(*rcv_wnd) = min_t(u32, space, U16_MAX);
+		(*rcv_wnd) = space;
 
 	if (init_rcv_wnd)
 		*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 861e0366f549..bbf5b84a70fc 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -356,6 +356,7 @@ static int seg6_hmac_init_algo(void)
 	struct crypto_shash *tfm;
 	struct shash_desc *shash;
 	int i, alg_count, cpu;
+	int ret = -ENOMEM;
 
 	alg_count = ARRAY_SIZE(hmac_algos);
 
@@ -366,12 +367,14 @@ static int seg6_hmac_init_algo(void)
 		algo = &hmac_algos[i];
 		algo->tfms = alloc_percpu(struct crypto_shash *);
 		if (!algo->tfms)
-			return -ENOMEM;
+			goto error_out;
 
 		for_each_possible_cpu(cpu) {
 			tfm = crypto_alloc_shash(algo->name, 0, 0);
-			if (IS_ERR(tfm))
-				return PTR_ERR(tfm);
+			if (IS_ERR(tfm)) {
+				ret = PTR_ERR(tfm);
+				goto error_out;
+			}
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
 			*p_tfm = tfm;
 		}
@@ -383,18 +386,22 @@ static int seg6_hmac_init_algo(void)
 
 		algo->shashs = alloc_percpu(struct shash_desc *);
 		if (!algo->shashs)
-			return -ENOMEM;
+			goto error_out;
 
 		for_each_possible_cpu(cpu) {
 			shash = kzalloc_node(shsize, GFP_KERNEL,
 					     cpu_to_node(cpu));
 			if (!shash)
-				return -ENOMEM;
+				goto error_out;
 			*per_cpu_ptr(algo->shashs, cpu) = shash;
 		}
 	}
 
 	return 0;
+
+error_out:
+	seg6_hmac_exit();
+	return ret;
 }
 
 int __init seg6_hmac_init(void)
@@ -412,22 +419,29 @@ int __net_init seg6_hmac_net_init(struct net *net)
 void seg6_hmac_exit(void)
 {
 	struct seg6_hmac_algo *algo = NULL;
+	struct crypto_shash *tfm;
+	struct shash_desc *shash;
 	int i, alg_count, cpu;
 
 	alg_count = ARRAY_SIZE(hmac_algos);
 	for (i = 0; i < alg_count; i++) {
 		algo = &hmac_algos[i];
-		for_each_possible_cpu(cpu) {
-			struct crypto_shash *tfm;
-			struct shash_desc *shash;
 
-			shash = *per_cpu_ptr(algo->shashs, cpu);
-			kfree(shash);
-			tfm = *per_cpu_ptr(algo->tfms, cpu);
-			crypto_free_shash(tfm);
+		if (algo->shashs) {
+			for_each_possible_cpu(cpu) {
+				shash = *per_cpu_ptr(algo->shashs, cpu);
+				kfree(shash);
+			}
+			free_percpu(algo->shashs);
+		}
+
+		if (algo->tfms) {
+			for_each_possible_cpu(cpu) {
+				tfm = *per_cpu_ptr(algo->tfms, cpu);
+				crypto_free_shash(tfm);
+			}
+			free_percpu(algo->tfms);
 		}
-		free_percpu(algo->tfms);
-		free_percpu(algo->shashs);
 	}
 }
 EXPORT_SYMBOL(seg6_hmac_exit);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 03b877ff4558..a75df2ec8db0 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -459,10 +459,8 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	int err;
 
 	err = seg6_do_srh(skb);
-	if (unlikely(err)) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (unlikely(err))
+		goto drop;
 
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
@@ -486,7 +484,7 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 
 	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 	if (unlikely(err))
-		return err;
+		goto drop;
 
 	if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
 		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
@@ -494,6 +492,9 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 			       skb_dst(skb)->dev, seg6_input_finish);
 
 	return seg6_input_finish(dev_net(skb->dev), NULL, skb);
+drop:
+	kfree_skb(skb);
+	return err;
 }
 
 static int seg6_input_nf(struct sk_buff *skb)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index b133dc55304c..f456a5911e7d 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1463,6 +1463,19 @@ int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode,
 				 ndev->ops->n_core_ops);
 }
 
+static bool nci_valid_size(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(NCI_CTRL_HDR_SIZE != NCI_DATA_HDR_SIZE);
+	unsigned int hdr_size = NCI_CTRL_HDR_SIZE;
+
+	if (skb->len < hdr_size ||
+	    !nci_plen(skb->data) ||
+	    skb->len < hdr_size + nci_plen(skb->data)) {
+		return false;
+	}
+	return true;
+}
+
 /* ---- NCI TX Data worker thread ---- */
 
 static void nci_tx_work(struct work_struct *work)
@@ -1516,10 +1529,9 @@ static void nci_rx_work(struct work_struct *work)
 		nfc_send_to_raw_sock(ndev->nfc_dev, skb,
 				     RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
 
-		if (!nci_plen(skb->data)) {
+		if (!nci_valid_size(skb)) {
 			kfree_skb(skb);
-			kcov_remote_stop();
-			break;
+			continue;
 		}
 
 		/* Process frame */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 6fcd7e2ca81f..964225580824 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -936,6 +936,12 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 				pskb_trim(skb, ovs_mac_header_len(key));
 		}
 
+		/* Need to set the pkt_type to involve the routing layer.  The
+		 * packet movement through the OVS datapath doesn't generally
+		 * use routing, but this is needed for tunnel cases.
+		 */
+		skb->pkt_type = PACKET_OUTGOING;
+
 		if (likely(!mru ||
 		           (skb->len <= mru + vport->dev->hard_header_len))) {
 			ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index b4674f03d71a..90b7f253d363 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -816,9 +816,17 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 		return NULL;
 
 	mutex_init(&ctx->tx_lock);
-	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	ctx->sk_proto = READ_ONCE(sk->sk_prot);
 	ctx->sk = sk;
+	/* Release semantic of rcu_assign_pointer() ensures that
+	 * ctx->sk_proto is visible before changing sk->sk_prot in
+	 * update_sk_prot(), and prevents reading uninitialized value in
+	 * tls_{getsockopt, setsockopt}. Note that we do not need a
+	 * read barrier in tls_{getsockopt,setsockopt} as there is an
+	 * address dependency between sk->sk_proto->{getsockopt,setsockopt}
+	 * and ctx->sk_proto.
+	 */
+	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	return ctx;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d5f10783c251..e4af6616e1df 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2170,13 +2170,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	maybe_add_creds(skb, sock, other);
 	skb_get(skb);
 
+	scm_stat_add(other, skb);
+
+	spin_lock(&other->sk_receive_queue.lock);
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
-
 	WRITE_ONCE(ousk->oob_skb, skb);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	spin_unlock(&other->sk_receive_queue.lock);
 
-	scm_stat_add(other, skb);
-	skb_queue_tail(&other->sk_receive_queue, skb);
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
@@ -2567,8 +2569,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
+	spin_lock(&sk->sk_receive_queue.lock);
 
 	if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) {
+		spin_unlock(&sk->sk_receive_queue.lock);
 		unix_state_unlock(sk);
 		mutex_unlock(&u->iolock);
 		return -EINVAL;
@@ -2580,6 +2584,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 		WRITE_ONCE(u->oob_skb, NULL);
 	else
 		skb_get(oob_skb);
+
+	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
@@ -2608,6 +2614,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		consume_skb(skb);
 		skb = NULL;
 	} else {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
@@ -2619,13 +2629,19 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			} else if (flags & MSG_PEEK) {
 				skb = NULL;
 			} else {
-				skb_unlink(skb, &sk->sk_receive_queue);
+				__skb_unlink(skb, &sk->sk_receive_queue);
 				WRITE_ONCE(u->oob_skb, NULL);
-				if (!WARN_ON_ONCE(skb_unref(skb)))
-					kfree_skb(skb);
+				unlinked_skb = skb;
 				skb = skb_peek(&sk->sk_receive_queue);
 			}
 		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		if (unlinked_skb) {
+			WARN_ON_ONCE(skb_unref(unlinked_skb));
+			kfree_skb(unlinked_skb);
+		}
 	}
 	return skb;
 }
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 1f8b8cdfcdc8..dfe94a90ece4 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -342,6 +342,18 @@ enum unix_recv_queue_lock_class {
 	U_RECVQ_LOCK_EMBRYO,
 };
 
+static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist)
+{
+	skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+	if (u->oob_skb) {
+		WARN_ON_ONCE(skb_unref(u->oob_skb));
+		u->oob_skb = NULL;
+	}
+#endif
+}
+
 static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist)
 {
 	struct unix_vertex *vertex;
@@ -365,18 +377,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist
 
 				/* listener -> embryo order, the inversion never happens. */
 				spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO);
-				skb_queue_splice_init(embryo_queue, hitlist);
+				unix_collect_queue(unix_sk(skb->sk), hitlist);
 				spin_unlock(&embryo_queue->lock);
 			}
 		} else {
-			skb_queue_splice_init(queue, hitlist);
-
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-			if (u->oob_skb) {
-				kfree_skb(u->oob_skb);
-				u->oob_skb = NULL;
-			}
-#endif
+			unix_collect_queue(u, hitlist);
 		}
 
 		spin_unlock(&queue->lock);