From nobody Thu Jun 25 07:14:28 2026 Received: from mail-wr1-f54.google.com (mail-wr1-f54.google.com [209.85.221.54]) (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 28BDF1A6825 for ; Sat, 2 May 2026 21:20:19 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.221.54 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777756820; cv=none; b=C6rIHN4ZfqOSaHyKkI+m/OYkmmY1HGRwPXrAldj6j8V5lvl9MLBTroz9w/gx+xItAYROzRjp2ibA472SVjvgDepj5e/ZedLiYqNq0HhYKr8ZhO6JAM6SIajXZyB82ErQn+K+hDCcbuwcpbPoR8eMIuxJ8oPds3ZZ2YNRmejMHMU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777756820; c=relaxed/simple; bh=VMBMfvrQfme4v1F3IF2CnljZz9JLs9rmam8hQwxkoUI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=GcHhWyZuh0CX109ZNNAGGIXU6/Lndx/LvL23n3wdrWuPWNCnNP/uc0hfpVpz2PtGkpFv1q9C+rTbrD+DG269zvdpPhF+SweSe0ktHPLj4ZqjIC+cXhvpP5eqjb+IONGwGcfenJYoecv7t60eY9JST5XCYPJ4J6p4CD8d/87KC9c= 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=W0WZOicj; arc=none smtp.client-ip=209.85.221.54 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="W0WZOicj" Received: by mail-wr1-f54.google.com with SMTP id ffacd0b85a97d-441209fb77eso1631825f8f.1 for ; Sat, 02 May 2026 14:20:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1777756817; x=1778361617; darn=lists.linux.dev; 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=mZs56aPqR5NiVcGf7GGB49cZUg0adWLDOUMtOX8cPak=; b=W0WZOicjqjkz2g0q1m4IuSNR6lTDarLmYi+m0ftiyf3chH8qBqQdVZUGFRZZZ1J0D5 KSVY9L6zqD6dfa5xfXbmnbwtANhROQNl3GaMM5xqV3c6TSMLNJQtFNTXHKsHcuSzHSq2 /GmMliQ5GoIx2qGPO3VZQiE+xSvp4hHMrZcAxGCSQbxHt+E0qFxUrVziDIfc8uE3hbjA HLbekTdpMH1UHObPS44KaWCaMB8KxyczvCvPxzJUt2grl797XTJukoPlnM0eNYNESqab uwwgS3SvcD0nQW0FP8DgwJEMUuT5hX9gg+OvotOtBotkZU3iLbwSNd8mV595x/0CFsgk rZQg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1777756817; x=1778361617; 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=mZs56aPqR5NiVcGf7GGB49cZUg0adWLDOUMtOX8cPak=; b=FksmAxq34oN5eTVSKLY7IpjZSf7Qa5psR2qMmDwQ7NA6fz/gdAM+1QwWykg3KA/wrO wq/korKtMNx/LDwv9q+s11tptEN5Fr0IGEjDOncSyHLGtWcHjgVQ0fyiIAe6A+jhJTJ3 zMNBq2zfJG47Rm1cV7j8QE+YCW3aDAOZDieMFCL+RnTxN4geh5NeZ/xFaCYi1QVOwJ2z obZwqLYExeoZkbh4AaxV9Bt/tN6+/dgDh4FOY+0Gd3gUqTP9D6A4hE4h96xdx2HecTYN G4X7cFwkUiRs/Jhe+moiHvBsBcnydWnS+Zy7BzAeOkjwRjfOpBkFb2Hc3Y7p46olWKr4 XRaQ== X-Gm-Message-State: AOJu0YxgBV+LVObvsfzCxlpvx6qjO1s+O8DZa+bwt61gUEn3xZ5mjm2j 16Gu+t7BLFcyd9Y8bEtdp09CgCGb594V1Gh8JzV0pX/UOkp86OL+DinzVurjm6NJ X-Gm-Gg: AeBDies4/tRxWiBEdLmE6pd36AFR6yWx+jUnH3cvOVsB7CcRwlKofx01nIewZjQGpK+ 5wVIu6rmsU988IjncnW4tN4Q+G8wpaz5x6kP351LO2qJCn+Gn1JeFxJ1yuqfImnI+kEv/H+e8zt p1/vQl/POZAvzB8FbvgpEyQECjgwlkx9/7/rijYobZI5nWSnwrIlaHkCI1P/BdVsnNRo6jlwkF4 /ZeYjuNJ02xKG1wQ4ETTU7hS2Lq+sz3h9jzdWoaM/ILNsJKTMYfpnLGDhlaibrVFh8Jc2i1ABz+ LPWVzj3Tg9s52wEfLtbWLkbbhZoLpkXU+y+yJ+IaA08Q5qNKikjjJnewCq2RK3fjejsnXFBec0r ytVS6K6GltXvZbrkz6uriVYrNGxbBO1Ow6lpWWKuqK/XwVIGBIyVj3brRE+epGM3iSBbYGF3brU yEj37tDOYuZ/hyHnHDP81t3qGGxgWQbhwBpLDW2UL4c1MHlkKuDEBsQAoLbSt6t98qvlO6zjIKJ 2B0PxoKXg9hHsmhwgEcIg== X-Received: by 2002:a05:6000:1614:b0:446:708e:1e8d with SMTP id ffacd0b85a97d-44951bd849emr13336594f8f.30.1777756817229; Sat, 02 May 2026 14:20:17 -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 ffacd0b85a97d-44a981defb3sm19490140f8f.20.2026.05.02.14.20.15 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 02 May 2026 14:20:16 -0700 (PDT) From: David Carlier To: mptcp@lists.linux.dev Cc: matttbe@kernel.org, martineau@kernel.org, geliang@kernel.org, pabeni@redhat.com, David Carlier Subject: [PATCH mptcp-next v5 3/4] mptcp: support MSG_ERRQUEUE on the parent socket Date: Sat, 2 May 2026 22:19:59 +0100 Message-ID: <690b4b87e71514a4fc0a0400db62edc63b4bf5eb.1777756707.git.devnexen@gmail.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: References: Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable 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 | 66 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 60 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0db50e3715c3..ed7b086f109a 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; } =20 +static bool mptcp_errqueue_skb_forwardable(const struct sk_buff *skb) +{ + u8 origin =3D SKB_EXT_ERR(skb)->ee.ee_origin; + + return origin =3D=3D SO_EE_ORIGIN_TIMESTAMPING || + origin =3D=3D SO_EE_ORIGIN_ZEROCOPY || + origin =3D=3D SO_EE_ORIGIN_LOCAL; +} + +static bool __mptcp_subflow_splice_errqueue(struct sock *sk, struct sock *= ssk) +{ + struct sk_buff *skb; + bool moved =3D false; + + while ((skb =3D skb_dequeue(&ssk->sk_error_queue))) { + if (!mptcp_errqueue_skb_forwardable(skb)) { + kfree_skb(skb); /* path-specific (ICMP) =E2=80=94 belongs in MPTCP_REC= ERR */ + continue; + } + if (sock_queue_err_skb(sk, skb)) { + skb_queue_head(&ssk->sk_error_queue, skb); + break; + } + moved =3D true; + } + + return moved; +} + static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { int ssk_state; + bool report; int err; =20 + report =3D __mptcp_subflow_splice_errqueue(sk, ssk); + /* only propagate errors on fallen-back sockets or * on MPC connect */ if (sk->sk_state !=3D TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk= ))) - return false; + goto out; =20 err =3D 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 =3D=3D TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) mptcp_set_state(sk, ssk_state); WRITE_ONCE(sk->sk_err, -err); + report =3D true; + +out: + if (!report) + return false; =20 /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); @@ -2286,6 +2323,23 @@ static unsigned int mptcp_inq_hint(const struct sock= *sk) return 0; } =20 +static int mptcp_recv_error(struct sock *sk, struct msghdr *msg, int len) +{ + struct mptcp_sock *msk =3D mptcp_sk(sk); + struct mptcp_subflow_context *subflow; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk =3D mptcp_subflow_tcp_sock(subflow); + + if (!skb_queue_empty(&ssk->sk_error_queue)) + __mptcp_subflow_splice_errqueue(sk, ssk); + } + release_sock(sk); + + return inet_recv_error(sk, msg, len); +} + static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { @@ -2295,9 +2349,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msgh= dr *msg, size_t len, int target; long timeo; =20 - /* 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); =20 lock_sock(sk); if (unlikely(sk->sk_state =3D=3D TCP_LISTEN)) { @@ -4340,7 +4393,8 @@ static __poll_t mptcp_poll(struct file *file, struct = socket *sock, =20 /* 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 |=3D EPOLLERR; =20 return mask; --=20 2.53.0