From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-wm1-f51.google.com (mail-wm1-f51.google.com [209.85.128.51]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9A3924968E1 for ; Wed, 6 May 2026 16:56:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.51 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778086571; cv=none; b=YRATQwZ8wl9lFi27EJM5lGrCk13E4cSn74XwucQZupbv5Ahdl4YiBIsLitmuONsAaBN0OyeeQ3hE38jcK9My8FC5caIe5ELMhEN60BitKIGBA1cAx0OOfLG21zCsmbFIDw8vKaywM0LS4eTeXy0hGzfueQkQkFchwX/D1Loj81o= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778086571; c=relaxed/simple; bh=EqNU8Yrd0TXiupxHPwzxKotS3UioELwzqEx0ic4rLgM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=G2ChT1/6r+g2QvLAko93mc4fyiohgW9Ge0SYVQFdMPFmCcd83uNgNTAF4sUvU7Fb+90aW2JhWjppUxnDoIfF4P3XK0fOZp1AXSlFRQO+mlUdH5A6i9DSxH3q0Yqzg6kDk77Gej+hijQ74OG0FjYiY+bPRwOsmaSBZFtpHrjBnc0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=QTiSChjf; arc=none smtp.client-ip=209.85.128.51 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="QTiSChjf" Received: by mail-wm1-f51.google.com with SMTP id 5b1f17b1804b1-488a88aeec9so75165305e9.2 for ; Wed, 06 May 2026 09:56:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1778086568; x=1778691368; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=xzDki06gKQpjz5uZEWAJE/Td9F8aqZ6hehFHrs+9QQs=; b=QTiSChjfJlQI3Gu3Pwhcbf3tuq5lHhIUUifylDss2l8Ih78C9BtBgKe56zf+ps+UgD pjJ2aZusfdXDU67WuyVQ6pG9Bt3266tF0JWDbHLMGHO4iUEZJtCXl24rfNO0dHyeT1vD gLQ6AaiEhdQcC/iB50f44ufb5TVttzDVI9jOLlrtKuYsTnHNRhRp3kY9utmFIWoD46sK xaxkh1UwAmiwunXpNh68CkTnRP2RGaN8Naixi/tDulLeY9QNo8p74quCoXlIc95w4EVa NgeewQGyOHsY9Ah/N8+v7EAcaTpht6lsc0eliY115gJWkQaHsqKsjsPyCs/wzPasvKwo v94A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1778086568; x=1778691368; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=xzDki06gKQpjz5uZEWAJE/Td9F8aqZ6hehFHrs+9QQs=; b=g2U+DaJbjfyOnbZvi2VYUPwrlYGPx7t9cRHoz7WqirgQXU6KLpXSCusSNe4fZx5gvJ g2/ml9rzq9NtgsbIvQ8ZIlUel4UcZEhfknFJTDGMlfok5Pm3zrIR+YB9CAoiGYFwMwOL ve/X/U50B/IV+rOqNJU6iQ7ZPzznymP6w8Y5+ulF3/5BewN+DiD/nPueBqBPGqdkVbY+ Fx3xSDyyaXnhcPBIGL5jKhfkcQyeORsIxNe0nUWqGLylOvmur8ZfXYoQBtBPfbTOolq1 EdzlFwqRszSqcejYcauwk8HzStpw/7S8HTmhuZ3sk30rmb0m31zt19xGRzIshA8b/vtI bx3Q== X-Forwarded-Encrypted: i=1; AFNElJ/l4KbkNbw/gnw//lsGPMNtjiwThsJ5hDNLgeMMoNG2muB1UfmbWTyLl9uGHeqfsTkPns7JosI=@vger.kernel.org X-Gm-Message-State: AOJu0YxU+a+Vob85liXu4GtgfC5+Zw15eOXPrx0/tsUSqbD8arXcSZ9y DxhPE46A7aXIfJH/bSG0jC5AvKAoVqaa9rnU1LvkqIQF9DUMRz3By+RSUAZlOTxx7HA= X-Gm-Gg: AeBDietGDabc4if211Cd8lpsTnZFfW+RsoEGtM1ZCUGLqB4kS4Kac6s5oStLo94cZbL OvHZAZoOV3v2wE5lR+vl0rHEg8gLuOynHmG24xEpRQpLarBFNltC61IfSjt77BMI+/R77pSM09T uwu4b9awOZmdUPSXAb8oQAPzJvazX7U58BTcd+qzVL7YYlCJyBLkYPOSANn0qBA8CUuB3W03kJz ybGfU9I1vPgFvOtadSXXT6tLSC0JLpmo41yukpdUSmm4jq7pj/kutIx0Y+P+dtelDEln7utghTc 0MfCVIa0duKXwtY3xiTbWBFRrhbsiTd2X9Hiu+bpe5RFRvrSlY3f4aCGdi0AVxBSUKMFymtzVR+ uPcJTm7Tf9XBZlZkK/ygZcF9BpZkC4tmKHgy/xUg8ZMVIHBq4ttreQXpmmuCLiPvfLXoT4EKdG+ VdNYBleTEG0mtPu/uZJXoiG553R9cDI07U0GWGn3+IlXGMf2cLuS4WSJb3+almZBGbaxGs7lpud 59LOdRfZGxQkj6cETMG6w== X-Received: by 2002:a05:600c:3e8d:b0:488:bc6a:528d with SMTP id 5b1f17b1804b1-48e51f40b12mr79389955e9.22.1778086567804; Wed, 06 May 2026 09:56:07 -0700 (PDT) Received: from dohko.chello.ie (188-141-5-72.dynamic.upc.ie. [188.141.5.72]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-48e538d2878sm94586715e9.15.2026.05.06.09.56.07 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 06 May 2026 09:56:07 -0700 (PDT) From: David Carlier To: mptcp@lists.linux.dev Cc: Matthieu Baerts , Paolo Abeni , Mat Martineau , Geliang Tang , netdev@vger.kernel.org, David Carlier Subject: [PATCH mptcp-next v6 3/4] mptcp: support MSG_ERRQUEUE on the parent socket Date: Wed, 6 May 2026 17:55:55 +0100 Message-ID: <2b6d945e90f64cb8b18cf866faf8f1a66683152b.1778086500.git.devnexen@gmail.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: References: Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Splice pending err skbs from each subflow's error queue onto the parent msk's error queue at error-report time, so poll() and recvmsg(MSG_ERRQUEUE) on the parent socket observe TX timestamps and MSG_ZEROCOPY completion notifications through the standard inet ABI. The splice filters by SO_EE_ORIGIN: TIMESTAMPING / ZEROCOPY / LOCAL events forward to the parent because they are tied to user-handed data, not to a specific path; subflow-level ICMP errors are dropped because the legacy RECVERR ABI cannot meaningfully convey their per-subflow peer identity to single-path-aware userspace. Such events will be carried by a future MPTCP_RECERR channel. mptcp_recv_error() retries the splice on the pull side: if sock_queue_err_skb() previously failed under rmem pressure, the skb stays on the subflow queue, and the next recvmsg(MSG_ERRQUEUE) splices it once the parent's queue has been drained. Suggested-by: Paolo Abeni Signed-off-by: David Carlier --- net/mptcp/protocol.c | 74 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 68 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0db50e3715c3..203ee37f57e0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -815,21 +816,52 @@ 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)) { + skb_queue_head(&ssk->sk_error_queue, skb); + break; + } + 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 @@ -839,6 +871,11 @@ 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(); @@ -2286,6 +2323,31 @@ static unsigned int mptcp_inq_hint(const struct sock *sk) return 0; } +static int mptcp_recv_error(struct sock *sk, struct msghdr *msg, int len) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_subflow_context *subflow; + int ret; + + /* Drain the parent first: a previous splice may have failed under + * rmem pressure and the skb stayed on a subflow. Freeing space here + * lets the splice below succeed; sock_queue_err_skb() then re-asserts + * EPOLLERR so userspace knows to drain again on the next poll. + */ + ret = inet_recv_error(sk, msg, len); + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + if (!skb_queue_empty_lockless(&ssk->sk_error_queue)) + __mptcp_subflow_splice_errqueue(sk, ssk); + } + release_sock(sk); + + return ret; +} + static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { @@ -2295,9 +2357,8 @@ 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); + return mptcp_recv_error(sk, msg, len); lock_sock(sk); if (unlikely(sk->sk_state == TCP_LISTEN)) { @@ -4340,7 +4401,8 @@ 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; -- 2.53.0