mptcp: MSG_ERRQUEUE support on the parent socket

index 87b5796d0135..b9cac04a749a 100644
@@ -16,6 +16,10 @@
 
 #define MIN_INFO_OPTLEN_SIZE		16
 #define MIN_FULL_INFO_OPTLEN_SIZE	40
+#define MPTCP_INET_FLAGS_MASK \
+	(BIT(INET_FLAGS_TRANSPARENT) | \
+	 BIT(INET_FLAGS_FREEBIND) | \
+	 BIT(INET_FLAGS_BIND_ADDRESS_NO_PORT))
 
 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
 {

@@ -1546,6 +1550,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 {
 	static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
 	struct sock *sk = (struct sock *)msk;
+	unsigned long mask = MPTCP_INET_FLAGS_MASK;
+	unsigned long src;
+	int b;
 	bool keep_open;
 
 	keep_open = sock_flag(sk, SOCK_KEEPOPEN);

@@ -1592,9 +1599,11 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 	tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt);
 	tcp_sock_set_maxseg(ssk, msk->maxseg);
 
-	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));
+	src = READ_ONCE(inet_sk(sk)->inet_flags);
+
+	for_each_set_bit(b, &mask, BITS_PER_LONG)
+		assign_bit(b, &inet_sk(ssk)->inet_flags, src & BIT(b));
+
 	WRITE_ONCE(inet_sk(ssk)->local_port_range, READ_ONCE(inet_sk(sk)->local_port_range));
 }
 

index b9cac04a749a..28229fe3eeca 100644
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <net/ipv6.h>
 #include <net/sock.h>
 #include <net/protocol.h>
 #include <net/tcp.h>

@@ -19,7 +20,11 @@
 #define MPTCP_INET_FLAGS_MASK \
 	(BIT(INET_FLAGS_TRANSPARENT) | \
 	 BIT(INET_FLAGS_FREEBIND) | \
-	 BIT(INET_FLAGS_BIND_ADDRESS_NO_PORT))
+	 BIT(INET_FLAGS_BIND_ADDRESS_NO_PORT) | \
+	 BIT(INET_FLAGS_RECVERR) | \
+	 BIT(INET_FLAGS_RECVERR_RFC4884) | \
+	 BIT(INET_FLAGS_RECVERR6) | \
+	 BIT(INET_FLAGS_RECVERR6_RFC4884))
 
 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
 {

@@ -394,6 +399,82 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
 	return -EOPNOTSUPP;
 }
 
+static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level,
+				   int optname, sockptr_t optval,
+				   unsigned int optlen)
+{
+	struct mptcp_subflow_context *subflow;
+	int ret = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		/* SOL_IPV6 options on a v4 subflow (v4 MP_JOIN, or userspace PM
+		 * grafting a v4 subflow onto an AF_INET6 msk) would otherwise
+		 * abort the loop with -EAFNOSUPPORT from ipv6_setsockopt().
+		 */
+		if (level == SOL_IPV6 && ssk->sk_family != AF_INET6)
+			continue;
+
+		ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
+		if (ret)
+			break;
+	}
+
+	if (!ret)
+		sockopt_seq_inc(msk);
+
+	return ret;
+}
+
+static int mptcp_setsockopt_recverr(struct mptcp_sock *msk, int level,
+				    int optname, sockptr_t optval,
+				    unsigned int optlen)
+{
+	struct sock *sk = (struct sock *)msk;
+	int val, ret;
+
+	/* Let ip_setsockopt() / ipv6_setsockopt() validate optval and optlen
+	 * (so 1-byte boolean writes keep the same ABI as plain TCP) and update
+	 * the parent's RECVERR bit. Re-read that bit under lock_sock() and
+	 * push it to the subflows: concurrent setsockopt callers cannot leave
+	 * parent and subflows desynchronized this way.
+	 */
+	if (level == SOL_IP)
+		ret = ip_setsockopt(sk, level, optname, optval, optlen);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (level == SOL_IPV6)
+		ret = ipv6_setsockopt(sk, level, optname, optval, optlen);
+#endif
+	else
+		return -EOPNOTSUPP;
+	if (ret)
+		return ret;
+
+	lock_sock(sk);
+	switch (optname) {
+	case IP_RECVERR:
+		val = inet_test_bit(RECVERR, sk);
+		break;
+	case IP_RECVERR_RFC4884:
+		val = inet_test_bit(RECVERR_RFC4884, sk);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPV6_RECVERR:
+		val = inet6_test_bit(RECVERR6, sk);
+		break;
+	case IPV6_RECVERR_RFC4884:
+		val = inet6_test_bit(RECVERR6_RFC4884, sk);
+		break;
+#endif
+	}
+
+	ret = mptcp_setsockopt_all_sf(msk, level, optname,
+				      KERNEL_SOCKPTR(&val), sizeof(val));
+	release_sock(sk);
+	return ret;
+}
+
 static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 			       sockptr_t optval, unsigned int optlen)
 {

@@ -436,6 +517,10 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname,
 
 		release_sock(sk);
 		break;
+	case IPV6_RECVERR:
+	case IPV6_RECVERR_RFC4884:
+		ret = mptcp_setsockopt_recverr(msk, SOL_IPV6, optname, optval, optlen);
+		break;
 	}
 
 	return ret;

@@ -781,6 +866,9 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname,
 		return mptcp_setsockopt_sol_ip_set(msk, optname, optval, optlen);
 	case IP_TOS:
 		return mptcp_setsockopt_v4_set_tos(msk, optname, optval, optlen);
+	case IP_RECVERR:
+	case IP_RECVERR_RFC4884:
+		return mptcp_setsockopt_recverr(msk, SOL_IP, optname, optval, optlen);
 	}
 
 	return -EOPNOTSUPP;

@@ -808,27 +896,6 @@ static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int
 	return ret;
 }
 
-static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level,
-				   int optname, sockptr_t optval,
-				   unsigned int optlen)
-{
-	struct mptcp_subflow_context *subflow;
-	int ret = 0;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
-		if (ret)
-			break;
-	}
-
-	if (!ret)
-		sockopt_seq_inc(msk);
-
-	return ret;
-}
-
 static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    sockptr_t optval, unsigned int optlen)
 {

@@ -1473,6 +1540,12 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname,
 	case IP_LOCAL_PORT_RANGE:
 		return mptcp_put_int_option(msk, optval, optlen,
 				READ_ONCE(inet_sk(sk)->local_port_range));
+	case IP_RECVERR:
+		return mptcp_put_int_option(msk, optval, optlen,
+				inet_test_bit(RECVERR, sk));
+	case IP_RECVERR_RFC4884:
+		return mptcp_put_int_option(msk, optval, optlen,
+				inet_test_bit(RECVERR_RFC4884, sk));
 	}
 
 	return -EOPNOTSUPP;

@@ -1493,6 +1566,12 @@ static int mptcp_getsockopt_v6(struct mptcp_sock *msk, int optname,
 	case IPV6_FREEBIND:
 		return mptcp_put_int_option(msk, optval, optlen,
 					    inet_test_bit(FREEBIND, sk));
+	case IPV6_RECVERR:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    inet6_test_bit(RECVERR6, sk));
+	case IPV6_RECVERR_RFC4884:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    inet6_test_bit(RECVERR6_RFC4884, sk));
 	}
 
 	return -EOPNOTSUPP;

index 1d67728d4233..28403fbdc994 100644
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/sched/signal.h>
 #include <linux/atomic.h>
+#include <linux/errqueue.h>
 #include <net/aligned_data.h>
 #include <net/rps.h>
 #include <net/sock.h>

@@ -829,21 +830,52 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 	return moved;
 }
 
+static bool mptcp_errqueue_skb_forwardable(const struct sk_buff *skb)
+{
+	u8 origin = SKB_EXT_ERR(skb)->ee.ee_origin;
+
+	return origin == SO_EE_ORIGIN_TIMESTAMPING ||
+		origin == SO_EE_ORIGIN_ZEROCOPY ||
+		origin == SO_EE_ORIGIN_LOCAL;
+}
+
+static bool __mptcp_subflow_splice_errqueue(struct sock *sk, struct sock *ssk)
+{
+	struct sk_buff *skb;
+	bool moved = false;
+
+	while ((skb = skb_dequeue(&ssk->sk_error_queue))) {
+		if (!mptcp_errqueue_skb_forwardable(skb)) {
+			kfree_skb(skb);  /* path-specific (ICMP) — belongs in MPTCP_RECERR */
+			continue;
+		}
+		if (sock_queue_err_skb(sk, skb)) {
+			kfree_skb(skb);
+			continue;
+		}
+		moved = true;
+	}
+
+	return moved;
+}
+
 static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
 {
 	int ssk_state;
+	bool report;
 	int err;
 
+	report = __mptcp_subflow_splice_errqueue(sk, ssk);
+
 	/* only propagate errors on fallen-back sockets or
 	 * on MPC connect
 	 */
 	if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk)))
-		return false;
+		goto out;
 
 	err = sock_error(ssk);
 	if (!err)
-		return false;
-
+		goto out;
 	/* We need to propagate only transition to CLOSE state.
 	 * Orphaned socket will see such state change via
 	 * subflow_sched_work_if_closed() and that path will properly

@@ -853,6 +885,11 @@ static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk)
 	if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
 		mptcp_set_state(sk, ssk_state);
 	WRITE_ONCE(sk->sk_err, -err);
+	report = true;
+
+out:
+	if (!report)
+		return false;
 
 	/* This barrier is coupled with smp_rmb() in mptcp_poll() */
 	smp_wmb();

@@ -2313,7 +2350,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	int target;
 	long timeo;
 
-	/* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len);
 

@@ -4363,7 +4399,8 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 
 	/* This barrier is coupled with smp_wmb() in __mptcp_error_report() */
 	smp_rmb();
-	if (READ_ONCE(sk->sk_err))
+	if (READ_ONCE(sk->sk_err) ||
+	    !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR;
 
 	return mask;

index b6e58d936ebe..95bb2cc8e2ff 100644
@@ -769,6 +769,60 @@ static void test_ip_tos_sockopt(int fd)
 		xerror("expect socklen_t == -1");
 }
 
+static void test_ip_recverr_sockopt(int fd)
+{
+	struct iovec iov = {
+		.iov_base = &(char){ 0 },
+		.iov_len = 1,
+	};
+	struct msghdr msg = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	int one = 1, zero = 0, val = -1;
+	socklen_t s = sizeof(val);
+	int level, optname, r;
+
+	switch (pf) {
+	case AF_INET:
+		level = SOL_IP;
+		optname = IP_RECVERR;
+		break;
+	case AF_INET6:
+		level = SOL_IPV6;
+		optname = IPV6_RECVERR;
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	r = setsockopt(fd, level, optname, &one, sizeof(one));
+	if (r)
+		die_perror("setsockopt recverr on");
+
+	r = getsockopt(fd, level, optname, &val, &s);
+	if (r)
+		die_perror("getsockopt recverr on");
+	if (s != sizeof(val) || val != one)
+		xerror("recverr on mismatch val=%d len=%u", val, s);
+
+	r = recvmsg(fd, &msg, MSG_ERRQUEUE | MSG_DONTWAIT);
+	if (r != -1 || errno != EAGAIN)
+		xerror("expected empty errqueue to return EAGAIN, ret=%d errno=%d", r, errno);
+
+	r = setsockopt(fd, level, optname, &zero, sizeof(zero));
+	if (r)
+		die_perror("setsockopt recverr off");
+
+	val = -1;
+	s = sizeof(val);
+	r = getsockopt(fd, level, optname, &val, &s);
+	if (r)
+		die_perror("getsockopt recverr off");
+	if (s != sizeof(val) || val != zero)
+		xerror("recverr off mismatch val=%d len=%u", val, s);
+}
+
 static int client(int pipefd)
 {
 	int fd = -1;

@@ -787,6 +841,7 @@ static int client(int pipefd)
 	}
 
 	test_ip_tos_sockopt(fd);
+	test_ip_recverr_sockopt(fd);
 
 	connect_one_server(fd, pipefd);