1 files changed, 116 insertions, 51 deletions

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index c40f1428e602..505445a9598f 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -181,8 +181,6 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case SO_KEEPALIVE:
-		mptcp_sol_socket_sync_intval(msk, optname, val);
-		return 0;
 	case SO_DEBUG:
 	case SO_MARK:
 	case SO_PRIORITY:
@@ -618,26 +616,42 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	}
 
 	if (ret == 0)
-		strcpy(msk->ca_name, name);
+		strscpy(msk->ca_name, name, sizeof(msk->ca_name));
 
 	release_sock(sk);
 	return ret;
 }
 
-static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval,
-					 unsigned int optlen)
+static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max,
+				      int (*set_val)(struct sock *, int),
+				      int *msk_val, int val)
 {
 	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	int val;
+	int err = 0;
 
-	if (optlen < sizeof(int))
-		return -EINVAL;
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int ret;
 
-	if (copy_from_sockptr(&val, optval, sizeof(val)))
-		return -EFAULT;
+		lock_sock(ssk);
+		ret = set_val(ssk, val);
+		err = err ? : ret;
+		release_sock(ssk);
+	}
+
+	if (!err) {
+		*msk_val = val;
+		sockopt_seq_inc(msk);
+	}
+
+	return err;
+}
+
+static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
 
-	lock_sock(sk);
 	sockopt_seq_inc(msk);
 	msk->cork = !!val;
 	mptcp_for_each_subflow(msk, subflow) {
@@ -649,25 +663,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva
 	}
 	if (!val)
 		mptcp_check_and_set_pending(sk);
-	release_sock(sk);
 
 	return 0;
 }
 
-static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval,
-					    unsigned int optlen)
+static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val)
 {
 	struct mptcp_subflow_context *subflow;
 	struct sock *sk = (struct sock *)msk;
-	int val;
 
-	if (optlen < sizeof(int))
-		return -EINVAL;
-
-	if (copy_from_sockptr(&val, optval, sizeof(val)))
-		return -EFAULT;
-
-	lock_sock(sk);
 	sockopt_seq_inc(msk);
 	msk->nodelay = !!val;
 	mptcp_for_each_subflow(msk, subflow) {
@@ -679,8 +683,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op
 	}
 	if (val)
 		mptcp_check_and_set_pending(sk);
-	release_sock(sk);
-
 	return 0;
 }
 
@@ -803,25 +805,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	int ret, val;
 
 	switch (optname) {
-	case TCP_INQ:
-		ret = mptcp_get_int_option(msk, optval, optlen, &val);
-		if (ret)
-			return ret;
-		if (val < 0 || val > 1)
-			return -EINVAL;
-
-		lock_sock(sk);
-		msk->recvmsg_inq = !!val;
-		release_sock(sk);
-		return 0;
 	case TCP_ULP:
 		return -EOPNOTSUPP;
 	case TCP_CONGESTION:
 		return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen);
-	case TCP_CORK:
-		return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen);
-	case TCP_NODELAY:
-		return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen);
 	case TCP_DEFER_ACCEPT:
 		/* See tcp.c: TCP_DEFER_ACCEPT does not fail */
 		mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen);
@@ -834,7 +821,50 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 						      optval, optlen);
 	}
 
-	return -EOPNOTSUPP;
+	ret = mptcp_get_int_option(msk, optval, optlen, &val);
+	if (ret)
+		return ret;
+
+	lock_sock(sk);
+	switch (optname) {
+	case TCP_INQ:
+		if (val < 0 || val > 1)
+			ret = -EINVAL;
+		else
+			msk->recvmsg_inq = !!val;
+		break;
+	case TCP_NOTSENT_LOWAT:
+		WRITE_ONCE(msk->notsent_lowat, val);
+		mptcp_write_space(sk);
+		break;
+	case TCP_CORK:
+		ret = __mptcp_setsockopt_sol_tcp_cork(msk, val);
+		break;
+	case TCP_NODELAY:
+		ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
+		break;
+	case TCP_KEEPIDLE:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE,
+						 &tcp_sock_set_keepidle_locked,
+						 &msk->keepalive_idle, val);
+		break;
+	case TCP_KEEPINTVL:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL,
+						 &tcp_sock_set_keepintvl,
+						 &msk->keepalive_intvl, val);
+		break;
+	case TCP_KEEPCNT:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT,
+						 &tcp_sock_set_keepcnt,
+						 &msk->keepalive_cnt,
+						 val);
+		break;
+	default:
+		ret = -ENOPROTOOPT;
+	}
+
+	release_sock(sk);
+	return ret;
 }
 
 int mptcp_setsockopt(struct sock *sk, int level, int optname,
@@ -843,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sock *ssk;
 
-	pr_debug("msk=%p", msk);
+	pr_debug("msk=%p\n", msk);
 
 	if (level == SOL_SOCKET)
 		return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
@@ -907,6 +937,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	struct sock *sk = (struct sock *)msk;
 	u32 flags = 0;
 	bool slow;
+	u32 now;
 
 	memset(info, 0, sizeof(*info));
 
@@ -935,14 +966,9 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	if (READ_ONCE(msk->can_ack))
 		flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
 	info->mptcpi_flags = flags;
-	mptcp_data_lock(sk);
-	info->mptcpi_snd_una = msk->snd_una;
-	info->mptcpi_rcv_nxt = msk->ack_seq;
-	info->mptcpi_bytes_acked = msk->bytes_acked;
-	mptcp_data_unlock(sk);
 
 	slow = lock_sock_fast(sk);
-	info->mptcpi_csum_enabled = msk->csum_enabled;
+	info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
 	info->mptcpi_token = msk->token;
 	info->mptcpi_write_seq = msk->write_seq;
 	info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits;
@@ -951,7 +977,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	info->mptcpi_bytes_retrans = msk->bytes_retrans;
 	info->mptcpi_subflows_total = info->mptcpi_subflows +
 		__mptcp_has_initial_subflow(msk);
+	now = tcp_jiffies32;
+	info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent);
+	info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv);
 	unlock_sock_fast(sk, slow);
+
+	mptcp_data_lock(sk);
+	info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv);
+	info->mptcpi_snd_una = msk->snd_una;
+	info->mptcpi_rcv_nxt = msk->ack_seq;
+	info->mptcpi_bytes_acked = msk->bytes_acked;
+	mptcp_data_unlock(sk);
 }
 EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
 
@@ -963,6 +999,10 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	/* When used only to check if a fallback to TCP happened. */
+	if (len == 0)
+		return 0;
+
 	len = min_t(unsigned int, len, sizeof(struct mptcp_info));
 
 	mptcp_diag_fill_info(msk, &m_info);
@@ -1331,6 +1371,8 @@ static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
 static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    char __user *optval, int __user *optlen)
 {
+	struct sock *sk = (void *)msk;
+
 	switch (optname) {
 	case TCP_ULP:
 	case TCP_CONGESTION:
@@ -1349,6 +1391,22 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 		return mptcp_put_int_option(msk, optval, optlen, msk->cork);
 	case TCP_NODELAY:
 		return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
+	case TCP_KEEPIDLE:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_idle ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ);
+	case TCP_KEEPINTVL:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_intvl ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ);
+	case TCP_KEEPCNT:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_cnt ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes));
+	case TCP_NOTSENT_LOWAT:
+		return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat);
+	case TCP_IS_MPTCP:
+		return mptcp_put_int_option(msk, optval, optlen, 1);
 	}
 	return -EOPNOTSUPP;
 }
@@ -1395,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sock *ssk;
 
-	pr_debug("msk=%p", msk);
+	pr_debug("msk=%p\n", msk);
 
 	/* @@ the meaning of setsockopt() when the socket is connected and
 	 * there are multiple subflows is not yet defined. It is up to the
@@ -1464,6 +1522,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
 	__tcp_sock_set_cork(ssk, !!msk->cork);
 	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
+	tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle);
+	tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl);
+	tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt);
 
 	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));
@@ -1500,6 +1561,10 @@ 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
@@ -1514,7 +1579,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		return 0;
 
-	space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val);
+	space = mptcp_space_from_win(sk, val);
 	if (space <= sk->sk_rcvbuf)
 		return 0;
 
@@ -1526,7 +1591,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val)
 
 		slow = lock_sock_fast(ssk);
 		WRITE_ONCE(ssk->sk_rcvbuf, space);
-		tcp_sk(ssk)->window_clamp = val;
+		WRITE_ONCE(tcp_sk(ssk)->window_clamp, val);
 		unlock_sock_fast(ssk, slow);
 	}
 	return 0;