From: David Carlier <devnexen@gmail.com>
To: mptcp@lists.linux.dev
Cc: Matthieu Baerts <matttbe@kernel.org>,
Paolo Abeni <pabeni@redhat.com>,
Mat Martineau <martineau@kernel.org>,
Geliang Tang <geliang@kernel.org>,
netdev@vger.kernel.org, David Carlier <devnexen@gmail.com>
Subject: [PATCH mptcp-next v6 2/4] mptcp: propagate RECVERR sockopts to subflows
Date: Wed, 6 May 2026 17:55:54 +0100 [thread overview]
Message-ID: <6a28b1d7069ddeab82f22c42ddb28bbc90589492.1778086500.git.devnexen@gmail.com> (raw)
In-Reply-To: <cover.1778086500.git.devnexen@gmail.com>
Propagate IP_RECVERR/IP_RECVERR_RFC4884 and
IPV6_RECVERR/IPV6_RECVERR_RFC4884 from the MPTCP socket to existing
and future subflows.
mptcp_setsockopt_recverr() snapshots optval into a local int, applies
it to the parent socket via ip_setsockopt() / ipv6_setsockopt(), bumps
msk->setsockopt_seq, and forwards to every subflow via
mptcp_setsockopt_all_sf(). Newly-joining subflows pick up the four
RECVERR bits through sync_socket_options() now that
MPTCP_INET_FLAGS_MASK covers them.
mptcp_setsockopt_all_sf() skips IPv4 subflows when called with
SOL_IPV6 to avoid the -ENOPROTOOPT that ip_setsockopt() returns on
level mismatch in AF_INET6 msks carrying IPv4 subflows.
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Assisted-by: Codex:gpt-5
Signed-off-by: David Carlier <devnexen@gmail.com>
---
net/mptcp/sockopt.c | 123 ++++++++++++++++++++++++++++++++++++--------
1 file changed, 101 insertions(+), 22 deletions(-)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 20c737b2e704..3046e9eb2c33 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -8,6 +8,8 @@
#include <linux/kernel.h>
#include <linux/module.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
#include <net/sock.h>
#include <net/protocol.h>
#include <net/tcp.h>
@@ -19,7 +21,11 @@
#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)
{
@@ -388,6 +394,81 @@ 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);
+
+ 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
+ default:
+ release_sock(sk);
+ return -EOPNOTSUPP;
+ }
+
+ 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)
{
@@ -430,6 +511,10 @@ 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;
@@ -775,6 +860,9 @@ 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;
@@ -802,27 +890,6 @@ 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)
{
@@ -1467,6 +1534,12 @@ 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;
@@ -1487,6 +1560,12 @@ 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;
--
2.53.0
next prev parent reply other threads:[~2026-05-06 16:56 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-06 16:55 [PATCH mptcp-next v6 0/4] mptcp: MSG_ERRQUEUE support on the parent socket David Carlier
2026-05-06 16:55 ` [PATCH mptcp-next v6 1/4] mptcp: sockopt: factor inet_flags propagation into a mask David Carlier
2026-05-06 16:55 ` David Carlier [this message]
2026-05-06 16:55 ` [PATCH mptcp-next v6 3/4] mptcp: support MSG_ERRQUEUE on the parent socket David Carlier
2026-05-06 16:55 ` [PATCH mptcp-next v6 4/4] selftests: mptcp: cover IP_RECVERR sockopt propagation David Carlier
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6a28b1d7069ddeab82f22c42ddb28bbc90589492.1778086500.git.devnexen@gmail.com \
--to=devnexen@gmail.com \
--cc=geliang@kernel.org \
--cc=martineau@kernel.org \
--cc=matttbe@kernel.org \
--cc=mptcp@lists.linux.dev \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox