Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 89 insertions, 75 deletions

diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c
index a2325e70dd..670da7822e 100644
--- a/net/mptcp/mptcp_pm_gen.c
+++ b/net/mptcp/mptcp_pm_gen.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel source */
 
 #include <net/netlink.h>
diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h
index 10579d1845..ac9fc7225b 100644
--- a/net/mptcp/mptcp_pm_gen.h
+++ b/net/mptcp/mptcp_pm_gen.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel header */
 
 #ifndef _LINUX_MPTCP_PM_GEN_H
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index cccb720c1c..58d17d9604 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1109,7 +1109,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
 	[MPTCP_PM_CMD_GRP_OFFSET]	= { .name = MPTCP_PM_CMD_GRP_NAME, },
 	[MPTCP_PM_EV_GRP_OFFSET]        = { .name = MPTCP_PM_EV_GRP_NAME,
-					    .flags = GENL_UNS_ADMIN_PERM,
+					    .flags = GENL_MCAST_CAP_NET_ADMIN,
 					  },
 };
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 6eabd1d79f..bc97cc30f0 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -288,12 +288,12 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 	if (!mptcp_pm_is_userspace(msk)) {
 		GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected");
-		goto remove_err;
+		goto out;
 	}
 
 	if (id_val == 0) {
 		err = mptcp_userspace_pm_remove_id_zero_address(msk, info);
-		goto remove_err;
+		goto out;
 	}
 
 	lock_sock(sk);
@@ -308,7 +308,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	if (!match) {
 		GENL_SET_ERR_MSG(info, "address with specified id not found");
 		release_sock(sk);
-		goto remove_err;
+		goto out;
 	}
 
 	list_move(&match->list, &free_list);
@@ -322,7 +322,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	err = 0;
- remove_err:
+out:
 	sock_put(sk);
 	return err;
 }
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 046ab95bc0..2b921af271 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -55,28 +55,14 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
 	return READ_ONCE(msk->wnd_end);
 }
 
-static bool mptcp_is_tcpsk(struct sock *sk)
+static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk)
 {
-	struct socket *sock = sk->sk_socket;
-
-	if (unlikely(sk->sk_prot == &tcp_prot)) {
-		/* we are being invoked after mptcp_accept() has
-		 * accepted a non-mp-capable flow: sk is a tcp_sk,
-		 * not an mptcp one.
-		 *
-		 * Hand the socket over to tcp so all further socket ops
-		 * bypass mptcp.
-		 */
-		WRITE_ONCE(sock->ops, &inet_stream_ops);
-		return true;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	} else if (unlikely(sk->sk_prot == &tcpv6_prot)) {
-		WRITE_ONCE(sock->ops, &inet6_stream_ops);
-		return true;
+	if (sk->sk_prot == &tcpv6_prot)
+		return &inet6_stream_ops;
 #endif
-	}
-
-	return false;
+	WARN_ON_ONCE(sk->sk_prot != &tcp_prot);
+	return &inet_stream_ops;
 }
 
 static int __mptcp_socket_create(struct mptcp_sock *msk)
@@ -3333,44 +3319,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
 }
 
-static struct sock *mptcp_accept(struct sock *ssk, int flags, int *err,
-				 bool kern)
-{
-	struct sock *newsk;
-
-	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
-	newsk = inet_csk_accept(ssk, flags, err, kern);
-	if (!newsk)
-		return NULL;
-
-	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
-	if (sk_is_mptcp(newsk)) {
-		struct mptcp_subflow_context *subflow;
-		struct sock *new_mptcp_sock;
-
-		subflow = mptcp_subflow_ctx(newsk);
-		new_mptcp_sock = subflow->conn;
-
-		/* is_mptcp should be false if subflow->conn is missing, see
-		 * subflow_syn_recv_sock()
-		 */
-		if (WARN_ON_ONCE(!new_mptcp_sock)) {
-			tcp_sk(newsk)->is_mptcp = 0;
-			goto out;
-		}
-
-		newsk = new_mptcp_sock;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-	} else {
-		MPTCP_INC_STATS(sock_net(ssk),
-				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
-	}
-
-out:
-	newsk->sk_kern_sock = kern;
-	return newsk;
-}
-
 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
@@ -3807,7 +3755,6 @@ static struct proto mptcp_prot = {
 	.connect	= mptcp_connect,
 	.disconnect	= mptcp_disconnect,
 	.close		= mptcp_close,
-	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
 	.shutdown	= mptcp_shutdown,
@@ -3917,18 +3864,36 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (!ssk)
 		return -EINVAL;
 
-	newsk = mptcp_accept(ssk, flags, &err, kern);
+	pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
+	newsk = inet_csk_accept(ssk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
-	lock_sock(newsk);
-
-	__inet_accept(sock, newsock, newsk);
-	if (!mptcp_is_tcpsk(newsock->sk)) {
-		struct mptcp_sock *msk = mptcp_sk(newsk);
+	pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
+	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
+		struct sock *new_mptcp_sock;
+
+		subflow = mptcp_subflow_ctx(newsk);
+		new_mptcp_sock = subflow->conn;
+
+		/* is_mptcp should be false if subflow->conn is missing, see
+		 * subflow_syn_recv_sock()
+		 */
+		if (WARN_ON_ONCE(!new_mptcp_sock)) {
+			tcp_sk(newsk)->is_mptcp = 0;
+			goto tcpfallback;
+		}
+
+		newsk = new_mptcp_sock;
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
+
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
 
 		set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
+		msk = mptcp_sk(newsk);
 		msk->in_accept_queue = 0;
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
@@ -3950,6 +3915,19 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (unlikely(list_is_singular(&msk->conn_list)))
 				mptcp_set_state(newsk, TCP_CLOSE);
 		}
+	} else {
+tcpfallback:
+		newsk->sk_kern_sock = kern;
+		lock_sock(newsk);
+		__inet_accept(sock, newsock, newsk);
+		/* we are being invoked after accepting a non-mp-capable
+		 * flow: sk is a tcp_sk, not an mptcp one.
+		 *
+		 * Hand the socket over to tcp so all further socket ops
+		 * bypass mptcp.
+		 */
+		WRITE_ONCE(newsock->sk->sk_socket->ops,
+			   mptcp_fallback_tcp_ops(newsock->sk));
 	}
 	release_sock(newsk);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7384613ea2..07f6242afc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1087,6 +1087,15 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
+static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk)
+{
+	struct sock *ssk = READ_ONCE(msk->first);
+
+	return ssk && ((1 << inet_sk_state_load(ssk)) &
+		       (TCPF_ESTABLISHED | TCPF_SYN_SENT |
+			TCPF_SYN_RECV | TCPF_LISTEN));
+}
+
 static inline void mptcp_do_fallback(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 3536807337..ef3edba754 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -440,6 +440,8 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		/* should work fine */
 		case IP_FREEBIND:
 		case IP_TRANSPARENT:
+		case IP_BIND_ADDRESS_NO_PORT:
+		case IP_LOCAL_PORT_RANGE:
 
 		/* the following are control cmsg related */
 		case IP_PKTINFO:
@@ -455,7 +457,6 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		/* common stuff that need some love */
 		case IP_TOS:
 		case IP_TTL:
-		case IP_BIND_ADDRESS_NO_PORT:
 		case IP_MTU_DISCOVER:
 		case IP_RECVERR:
 
@@ -683,8 +684,8 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
 	return 0;
 }
 
-static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int optname,
-						   sockptr_t optval, unsigned int optlen)
+static int mptcp_setsockopt_sol_ip_set(struct mptcp_sock *msk, int optname,
+				       sockptr_t optval, unsigned int optlen)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct sock *ssk;
@@ -710,6 +711,14 @@ static int mptcp_setsockopt_sol_ip_set_transparent(struct mptcp_sock *msk, int o
 		inet_assign_bit(TRANSPARENT, ssk,
 				inet_test_bit(TRANSPARENT, sk));
 		break;
+	case IP_BIND_ADDRESS_NO_PORT:
+		inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk,
+				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+		break;
+	case IP_LOCAL_PORT_RANGE:
+		WRITE_ONCE(inet_sk(ssk)->local_port_range,
+			   READ_ONCE(inet_sk(sk)->local_port_range));
+		break;
 	default:
 		release_sock(sk);
 		WARN_ON_ONCE(1);
@@ -755,7 +764,9 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 	switch (optname) {
 	case IP_FREEBIND:
 	case IP_TRANSPARENT:
-		return mptcp_setsockopt_sol_ip_set_transparent(msk, optname, optval, optlen);
+	case IP_BIND_ADDRESS_NO_PORT:
+	case IP_LOCAL_PORT_RANGE:
+		return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen);
 	case IP_TOS:
 		return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen);
 	}
@@ -938,6 +949,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	info->mptcpi_bytes_sent = msk->bytes_sent;
 	info->mptcpi_bytes_received = msk->bytes_received;
 	info->mptcpi_bytes_retrans = msk->bytes_retrans;
+	info->mptcpi_subflows_total = info->mptcpi_subflows +
+		__mptcp_has_initial_subflow(msk);
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
@@ -1348,6 +1361,12 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 	switch (optname) {
 	case IP_TOS:
 		return mptcp_put_int_option(msk, optval, optlen, READ_ONCE(inet_sk(sk)->tos));
+	case IP_BIND_ADDRESS_NO_PORT:
+		return mptcp_put_int_option(msk, optval, optlen,
+				inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+	case IP_LOCAL_PORT_RANGE:
+		return mptcp_put_int_option(msk, optval, optlen,
+				READ_ONCE(inet_sk(sk)->local_port_range));
 	}
 
 	return -EOPNOTSUPP;
@@ -1448,6 +1467,8 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 
 	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
+	inet_assign_bit(BIND_ADDRESS_NO_PORT, ssk, inet_test_bit(BIND_ADDRESS_NO_PORT, sk));
+	WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range));
 }
 
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk)
@@ -1479,6 +1500,10 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 	struct mptcp_subflow_context *subflow;
 	int space, cap;
 
+	/* bpf can land here with a wrong sk type */
+	if (sk->sk_protocol == IPPROTO_TCP)
+		return -EINVAL;
+
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 71ba86246f..13f66d11b7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -905,6 +905,8 @@ dispose_child:
 	return child;
 
 fallback:
+	if (fallback)
+		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
 	mptcp_subflow_drop_ctx(child);
 	return child;
 }