From nobody Mon Aug 24 01:42:19 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D1AC818B0A; Tue, 18 Aug 2026 06:03:38 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033020; cv=none; b=VC0HUu+XNzs7zOIBk3G3B6v2GAOzhcbygSCaUKoIjRRvyN3/rSJcxC6J4WYYEM9Vwx4VsYLXgdUXVH20Jtnvx5xjCkiCR7BOay6LZ3kRlKJNde3DZzrpZm1rW3kpyDQJZt9i/yr2EWyHZxR/coCw6qYV/R00yu7CUME34UVyLE0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033020; c=relaxed/simple; bh=k1q0/EBlrqimZXrQ/x9R+8ZMrJyj5Xntgj49rB5L33c=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=La8zArBEzy6a4kdeJ1d6MVrG4iEBtPv9ojr5KGF2Xm9lRNRa6/Yphl4iZDtrL6soxaKq0AEdOco4fi7OULdDhPdt7DzTEK3z1pRpqxfD44QLBDN4XSaSUR6M0YgZGUE9AlB32ftwSW6uUtbaqYPIvwBbt3vb04XS6yBOAzb++yU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=YQvaLOa5; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="YQvaLOa5" Received: by smtp.kernel.org (Postfix) with ESMTPSA id CB9A91F00A3D; Tue, 18 Aug 2026 06:03:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787033018; bh=7e86Qnm6H9Lggduhxe1ZAqQOUAeMCD6ncoq8Z1k+VhA=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=YQvaLOa5c6oxVX8Pxnmnc1HtrWESrl48NVxshGoB0SIcZRdBB9I4jTfDm12HPRFrI zD5SgOpN0Sm0+1uH16MG9WTcXlJIJkIFUuMWaVBdMOTDF8W5SgVlpV8+kJp9e6kHhG TLffkfBScnLSk3gBjUSdFRQpuQbQ9n+HaHJ9T14HkVCSUg+2enysOsved6Agbb87IF PVLqrgDciWnfsPPS1eYKKKkSMcx2VJP8C0m1+BbLGrReqr2bwbSqcPOcVE0xoRYw9S b1UFQ8+iaMqAmXrd0rtnhnEX+xzEMksHEdGasugGoM+T1cnuhCF5SKvmGMflI36j1A 6rTS4wCfkLHww== From: Geliang Tang To: Keith Busch , Jens Axboe , Christoph Hellwig , Sagi Grimberg , Chaitanya Kulkarni , David Ahern , Ido Schimmel , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Hannes Reinecke , Stanislav Fomichev Cc: Geliang Tang , linux-nvme@lists.infradead.org, netdev@vger.kernel.org, mptcp@lists.linux.dev Subject: [PATCH v4 1/4] nvmet-tcp: unify sockopt with do_sock_setsockopt Date: Tue, 18 Aug 2026 14:03:00 +0800 Message-ID: <010e6810cc4c10b30237c964b2bb9dfa7a3c740c.1786947923.git.tanggeliang@kylinos.cn> 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-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Geliang Tang This patch consolidates socket option settings in nvmet-tcp by utilizing the generic do_sock_setsockopt() helper for options including SO_LINGER, SO_PRIORITY, SO_REUSEADDR, TCP_NODELAY, and IP_TOS. This change eliminates the need to export and use specialized helpers for each individual socket option. A key benefit of this refactoring is that it decouples the socket option configuration from the underlying transport protocol. This makes it easier to extend nvmet-tcp to support other protocols, such as MPTCP, in the future, as do_sock_setsockopt() abstracts away protocol-specific differences without requiring per-option protocol-specific wrappers. Signed-off-by: Geliang Tang Reviewed-by: Hannes Reinecke --- drivers/nvme/target/tcp.c | 82 ++++++++++++++++++++++++++++++++++----- 1 file changed, 72 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 75a276d73be3..38b0c446ae89 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1696,10 +1696,50 @@ static void nvmet_tcp_state_change(struct sock *sk) read_unlock_bh(&sk->sk_callback_lock); } =20 +static int nvmet_tcp_sock_no_linger(struct sock *sk) +{ + struct linger ling =3D { .l_onoff =3D 1, .l_linger =3D 0 }; + + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, SO_LINGER, + KERNEL_SOCKPTR(&ling), sizeof(ling)); +} + +static int nvmet_tcp_sock_set_priority(struct sock *sk, u32 priority) +{ + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, SO_PRIORITY, + KERNEL_SOCKPTR(&priority), sizeof(priority)); +} + +static int nvmet_tcp_sock_set_reuseaddr(struct sock *sk) +{ + int val =3D SK_CAN_REUSE; + + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, + SO_REUSEADDR, KERNEL_SOCKPTR(&val), + sizeof(val)); +} + +static int nvmet_tcp_sock_set_nodelay(struct sock *sk) +{ + int val =3D 1; + + return do_sock_setsockopt(sk->sk_socket, false, SOL_TCP, TCP_NODELAY, + KERNEL_SOCKPTR(&val), sizeof(val)); +} + +static int nvmet_tcp_sock_set_tos(struct sock *sk) +{ + int tos =3D inet_sk(sk)->rcv_tos; + + if (tos > 0) + return do_sock_setsockopt(sk->sk_socket, false, SOL_IP, IP_TOS, + KERNEL_SOCKPTR(&tos), sizeof(tos)); + return 0; +} + static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) { struct socket *sock =3D queue->sock; - struct inet_sock *inet =3D inet_sk(sock->sk); int ret; =20 ret =3D kernel_getsockname(sock, @@ -1717,14 +1757,20 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tc= p_queue *queue) * close. This is done to prevent stale data from being sent should * the network connection be restored before TCP times out. */ - sock_no_linger(sock->sk); + ret =3D nvmet_tcp_sock_no_linger(sock->sk); + if (ret) + return ret; =20 - if (so_priority > 0) - sock_set_priority(sock->sk, so_priority); + if (so_priority > 0) { + ret =3D nvmet_tcp_sock_set_priority(sock->sk, so_priority); + if (ret) + return ret; + } =20 /* Set socket type of service */ - if (inet->rcv_tos > 0) - ip_sock_set_tos(sock->sk, inet->rcv_tos); + ret =3D nvmet_tcp_sock_set_tos(sock->sk); + if (ret) + return ret; =20 ret =3D 0; write_lock_bh(&sock->sk->sk_callback_lock); @@ -2098,10 +2144,26 @@ static int nvmet_tcp_add_port(struct nvmet_port *np= ort) port->sock->sk->sk_user_data =3D port; port->data_ready =3D port->sock->sk->sk_data_ready; port->sock->sk->sk_data_ready =3D nvmet_tcp_listen_data_ready; - sock_set_reuseaddr(port->sock->sk); - tcp_sock_set_nodelay(port->sock->sk); - if (so_priority > 0) - sock_set_priority(port->sock->sk, so_priority); + ret =3D nvmet_tcp_sock_set_reuseaddr(port->sock->sk); + if (ret) { + pr_err("failed to set SO_REUSEADDR on port socket %d\n", ret); + goto err_sock; + } + + ret =3D nvmet_tcp_sock_set_nodelay(port->sock->sk); + if (ret) { + pr_err("failed to set TCP_NODELAY on port socket %d\n", ret); + goto err_sock; + } + + if (so_priority > 0) { + ret =3D nvmet_tcp_sock_set_priority(port->sock->sk, so_priority); + if (ret) { + pr_err("failed to set SO_PRIORITY on port socket %d\n", + ret); + goto err_sock; + } + } =20 ret =3D kernel_bind(port->sock, (struct sockaddr_unsized *)&port->addr, sizeof(port->addr)); --=20 2.53.0 From nobody Mon Aug 24 01:42:19 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DB75218B0A; Tue, 18 Aug 2026 06:03:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033026; cv=none; b=MrIUldFAk4aKNS7fsskd8BxJmas5nB2LBErUfZSUBKGhcQm9n8TM06skI+2TYroDcrv2nyyZ5MGFAtrVSsJrLLRBuDprJYCJb8T3tUXxJiRHrYO7AhmvvPqBRAL1TQJxwRgDDfxafpkW9S/E7T1IoPB2DI44HHn5X5aP26XtiXU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033026; c=relaxed/simple; bh=Qq64n4tLRPSTw6ELD6YkUu6/mLx0g+C2oHXtJpaqH/s=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SEUw6g/QBZI9u2khiFbE7UX4MNLvnAg5I/KZLyso4hiXHVl7dOwYe3Wmf4kuHV9YVlXhy/a581C3B0gxyKlMWeeXl0ldSMn1tm7mOnSdlEhSofTsfxetNVkFxV5cSM9ymjSkfgu0d822iqz0fDrb4aRBy4Pk7x10q/NWgaH8Ib0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=a5xYytDT; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="a5xYytDT" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 191A01F00A3E; Tue, 18 Aug 2026 06:03:38 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787033024; bh=bVkuvMHFLexS/2qWy9M58HdBBKwviyPo8XyjkbRCihA=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=a5xYytDTVyISZUZxjM7M60SlySDlqJoHK1wUwvYsbsWMK/COfvRZ1ttlp+V9lutq7 Aijd9f7eNt/QWOUR27Y3VdTj3L9ivz2O9umGUipBouRt6qGlmcVbKU48G0PHGbEryu uHIltNQySmPYbCugrygpF6UhyZQAmb622M1mTrTUYvYR33zOa0dvdHVm+OmdwB0roN 5legOzmGFKhJYZlNjvn2uhsEsvSq0uBZEculz9GvYASUVOoehe9pQFq/pmrOtIcmuy mF9xaF44zNRLR/0U6H1FNuVQcuS846xSg5FW4sLxo4VOA/5ovqDYTlXvV0kWJM/Hkh aL24FIA84z+pQ== From: Geliang Tang To: Keith Busch , Jens Axboe , Christoph Hellwig , Sagi Grimberg , Chaitanya Kulkarni , David Ahern , Ido Schimmel , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Hannes Reinecke , Stanislav Fomichev Cc: Geliang Tang , linux-nvme@lists.infradead.org, netdev@vger.kernel.org, mptcp@lists.linux.dev Subject: [PATCH v4 2/4] nvme-tcp: unify sockopt with do_sock_setsockopt Date: Tue, 18 Aug 2026 14:03:01 +0800 Message-ID: <5d77334ae43750d8c12923148d71077301242c89.1786947923.git.tanggeliang@kylinos.cn> 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-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Geliang Tang This patch consolidates socket option settings in nvme-tcp by utilizing the generic do_sock_setsockopt() helper for options including SO_LINGER, SO_PRIORITY, TCP_NODELAY, IP_TOS, SO_BINDTODEVICE, and TCP_SYNCNT. Compared to the target-side implementation, this patch additionally converts SO_BINDTODEVICE and TCP_SYNCNT to use the same unified mechanism. This change eliminates the need to export and use specialized helpers for each individual socket option. Signed-off-by: Geliang Tang --- drivers/nvme/host/tcp.c | 91 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 81 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index ba5c7b3e2a7c..025cade370b2 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1774,6 +1774,47 @@ static int nvme_tcp_start_tls(struct nvme_ctrl *nctr= l, return ret; } =20 +static int nvme_tcp_sock_no_linger(struct sock *sk) +{ + struct linger ling =3D { .l_onoff =3D 1, .l_linger =3D 0 }; + + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, SO_LINGER, + KERNEL_SOCKPTR(&ling), sizeof(ling)); +} + +static int nvme_tcp_sock_set_priority(struct sock *sk, u32 priority) +{ + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, SO_PRIORITY, + KERNEL_SOCKPTR(&priority), sizeof(priority)); +} + +static int nvme_tcp_sock_set_bindtodevice(struct sock *sk, char *iface) +{ + return do_sock_setsockopt(sk->sk_socket, false, SOL_SOCKET, + SO_BINDTODEVICE, KERNEL_SOCKPTR(iface), + strlen(iface)); +} + +static int nvme_tcp_sock_set_nodelay(struct sock *sk) +{ + int val =3D 1; + + return do_sock_setsockopt(sk->sk_socket, false, SOL_TCP, TCP_NODELAY, + KERNEL_SOCKPTR(&val), sizeof(val)); +} + +static int nvme_tcp_sock_set_syncnt(struct sock *sk, int val) +{ + return do_sock_setsockopt(sk->sk_socket, false, SOL_TCP, TCP_SYNCNT, + KERNEL_SOCKPTR(&val), sizeof(val)); +} + +static int nvme_tcp_sock_set_tos(struct sock *sk, int tos) +{ + return do_sock_setsockopt(sk->sk_socket, false, SOL_IP, IP_TOS, + KERNEL_SOCKPTR(&tos), sizeof(tos)); +} + static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, key_serial_t pskid) { @@ -1819,24 +1860,56 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *n= ctrl, int qid, #endif =20 /* Single syn retry */ - tcp_sock_set_syncnt(queue->sock->sk, 1); + ret =3D nvme_tcp_sock_set_syncnt(queue->sock->sk, 1); + if (ret) { + dev_err(nctrl->device, + "failed to set TCP_SYNCNT on queue %d err %d\n", + qid, ret); + goto err_sock; + } =20 /* Set TCP no delay */ - tcp_sock_set_nodelay(queue->sock->sk); + ret =3D nvme_tcp_sock_set_nodelay(queue->sock->sk); + if (ret) { + dev_err(nctrl->device, + "failed to set TCP_NODELAY on queue %d err %d\n", + qid, ret); + goto err_sock; + } =20 /* * Cleanup whatever is sitting in the TCP transmit queue on socket * close. This is done to prevent stale data from being sent should * the network connection be restored before TCP times out. */ - sock_no_linger(queue->sock->sk); + ret =3D nvme_tcp_sock_no_linger(queue->sock->sk); + if (ret) { + dev_err(nctrl->device, + "failed to set SO_LINGER on queue %d err %d\n", + qid, ret); + goto err_sock; + } =20 - if (so_priority > 0) - sock_set_priority(queue->sock->sk, so_priority); + if (so_priority > 0) { + ret =3D nvme_tcp_sock_set_priority(queue->sock->sk, so_priority); + if (ret) { + dev_err(nctrl->device, + "failed to set SO_PRIORITY on queue %d err %d\n", + qid, ret); + goto err_sock; + } + } =20 /* Set socket type of service */ - if (nctrl->opts->tos >=3D 0) - ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + if (nctrl->opts->tos >=3D 0) { + ret =3D nvme_tcp_sock_set_tos(queue->sock->sk, nctrl->opts->tos); + if (ret) { + dev_err(nctrl->device, + "failed to set IP_TOS on queue %d err %d\n", + qid, ret); + goto err_sock; + } + } =20 /* Set 10 seconds timeout for icresp recvmsg */ queue->sock->sk->sk_rcvtimeo =3D 10 * HZ; @@ -1864,10 +1937,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nc= trl, int qid, =20 if (nctrl->opts->mask & NVMF_OPT_HOST_IFACE) { char *iface =3D nctrl->opts->host_iface; - sockptr_t optval =3D KERNEL_SOCKPTR(iface); =20 - ret =3D sock_setsockopt(queue->sock, SOL_SOCKET, SO_BINDTODEVICE, - optval, strlen(iface)); + ret =3D nvme_tcp_sock_set_bindtodevice(queue->sock->sk, iface); if (ret) { dev_err(nctrl->device, "failed to bind to interface %s queue %d err %d\n", --=20 2.53.0 From nobody Mon Aug 24 01:42:19 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2FFE03890EE; Tue, 18 Aug 2026 06:03:53 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033035; cv=none; b=kTbrTS+LDSGD8jhYJeHyBfBUUxVRNLTf4mIZ6Poc/Cceix5FqjWzANmcVO5UyAQkfkLgQqcz2h67brocZB9yiEzg8WCc0LLMqdeBprfrlKgPHpOA4CWyxQysaylvzbmzlLOM0n0B9o3PkFsOlrfOLwqaho8KtFpCXxh8wYsGxjw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033035; c=relaxed/simple; bh=kKPJGW/oiaUn0VowSlJHbCgeZO9HPFHZc7oXkGBj39w=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=uNKG9ilZ1jEsOB68xrJDW3Kp/xe2jey9jB+1w0HQKoHHkbfiN/jrZF4qgFxCsQY9SdC1rcbCT0M+weMmIgc8N5oqnlM2z/Zds+8ZZdYcw6TsCfO83Sz3Cw5mO7IwSXG3N2/jm3hpcmeGgPh1qmnuu+auH4rUozP2Ohtlb4frsMU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=A2UdzNx5; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="A2UdzNx5" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 56A441F000E9; Tue, 18 Aug 2026 06:03:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787033033; bh=Nis9dfnj0IQkbN06JcjcoUd3EWxyn7iXPcVuP3vmsVY=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=A2UdzNx5HptTFp1gQu4gHG08W2f7E9uDmm+H84rYpZ/MMKbb035eG6R2U3tweQxiz bYwDEhkzx7I6kqFz+0t3tH2Xs74YWxY+uz00woRJt4BQTEtcfhzEfrncajoy6IN4/E 1YxfoCTxEQVL0CDJeDaX/GRBHZL/xcpZK3RHLhkFuALkNJchkNObRyl6Ld0qj/Ip/A 9tKkD2jh+sLGuWieQCxKqoZW2mbsOXDHEhvAFMPbD9zf4Y3m7efbMH1Bhma2GmlmI2 4IH618bfievO8blR167r2NuPqm9yfl30vTAb7nA/F3YUjnARjMGOhjsURM7/ysvvB8 IfiT8d1iQc6lg== From: Geliang Tang To: Keith Busch , Jens Axboe , Christoph Hellwig , Sagi Grimberg , Chaitanya Kulkarni , David Ahern , Ido Schimmel , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Hannes Reinecke , Stanislav Fomichev Cc: Geliang Tang , linux-nvme@lists.infradead.org, netdev@vger.kernel.org, mptcp@lists.linux.dev Subject: [PATCH v4 3/4] nvmet-tcp: support IPv6 traffic class Date: Tue, 18 Aug 2026 14:03:02 +0800 Message-ID: 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-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Geliang Tang Currently, nvmet-tcp only applies the received IPv4 TOS value when setting up a queue socket, but does not handle the IPv6 traffic class. Extend the queue socket setup to handle AF_INET6 sockets. Obtain the traffic class from the IPv6 socket's rcv_flowinfo and apply it through IPV6_TCLASS using do_sock_setsockopt(). Signed-off-by: Geliang Tang --- drivers/nvme/target/tcp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 38b0c446ae89..ed413aa5601c 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1737,6 +1737,22 @@ static int nvmet_tcp_sock_set_tos(struct sock *sk) return 0; } =20 +static int nvmet_tcp_sock_set_tclass(struct sock *sk) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family =3D=3D AF_INET6) { + int tclass =3D ip6_tclass(inet6_sk(sk)->rcv_flowinfo); + + if (tclass > 0) + return do_sock_setsockopt(sk->sk_socket, false, + SOL_IPV6, IPV6_TCLASS, + KERNEL_SOCKPTR(&tclass), + sizeof(tclass)); + } +#endif + return 0; +} + static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) { struct socket *sock =3D queue->sock; @@ -1772,6 +1788,10 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp= _queue *queue) if (ret) return ret; =20 + ret =3D nvmet_tcp_sock_set_tclass(sock->sk); + if (ret) + return ret; + ret =3D 0; write_lock_bh(&sock->sk->sk_callback_lock); if (sock->sk->sk_state !=3D TCP_ESTABLISHED) { --=20 2.53.0 From nobody Mon Aug 24 01:42:19 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 352B53659FB; Tue, 18 Aug 2026 06:04:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033043; cv=none; b=dlNUy+RqYq8BwSUJoLXsqeAdbYv8ddcadx8gPjsf4AGwiwn6dJdnQke1qLMFw8qlL0uvD+I2YtXZ09HO+21NBz46nAQBJDTkQ9lUkXTtgpgO7khKgGnwLshQ0LvjVD/yD/gCh49Zdj9k7Halx8l4dUzvzxN1k1X1fBcERjThyPo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1787033043; c=relaxed/simple; bh=Z/IR77niDGTQI2i+rwwTaipv6ufjef5SM5qVq8VLSmc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=MLPVt/RBICLsEqfmc8WONib1bwX13A+jnNsP3mHGBqZW7ZP121ek39RZuoDcC56ypvc9oP4T7w9oHJKjmRMLVYzSPrigMHXl7wno/XRGFRqV1yfq7UKxIzQrmIX0+suchLnEiMQHO+FSF4I9jHdPfSBgTsfbtDqYnxM3CrcXySg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=LWHxdTg9; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="LWHxdTg9" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 711821F00A3A; Tue, 18 Aug 2026 06:03:54 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1787033041; bh=B2O7HteIhiLtqRyn/DIyOgikrgWD4I8OBbeQRR73W8A=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=LWHxdTg90cikKZA64HRhmzVNAddjUJL6WZIMNJ22gDFgJucfSnFcBwSM9x8B/fvWT Q8CnzzRUthtyG67xBv+GsZjfvUwd4U54mjVqrlux1aJmTV2m2OtlKaKF9m0SCxMhYf PIHFoWxBqG6lfRnQixUnyZGoz9WpkUM5bDqO3AU2L/+e+IxZYRhbRhYCabQC7yMah2 7DZq+pqCvPCZXKNDyFMBqTCNOeanYn5wSInTcNwzkgmPgQuxR8yy2yzkPj3gUJCZkO 0mPMe7zTe7Yb9e+zJQvSdiiaaC/FVLkjAY6+GVNxubrtVH3eGPbunFuKXlv4zcXXZs ApvJwpWoEMi3g== From: Geliang Tang To: Keith Busch , Jens Axboe , Christoph Hellwig , Sagi Grimberg , Chaitanya Kulkarni , David Ahern , Ido Schimmel , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Hannes Reinecke , Stanislav Fomichev Cc: Geliang Tang , linux-nvme@lists.infradead.org, netdev@vger.kernel.org, mptcp@lists.linux.dev Subject: [PATCH v4 4/4] nvme-tcp: support IPv6 traffic class Date: Tue, 18 Aug 2026 14:03:03 +0800 Message-ID: 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-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Geliang Tang Currently, nvme-tcp host only supports setting the IPv4 TOS value when a TOS is specified, but does not handle the IPv6 traffic class. Extend the queue socket setup to handle AF_INET6 sockets by applying the TOS value to both IPv4 and IPv6 sockets. For IPv6, the TOS value is set as the IPv6 traffic class via IPV6_TCLASS using do_sock_setsockopt(). Signed-off-by: Geliang Tang --- drivers/nvme/host/tcp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 025cade370b2..5f30be04a9dd 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1815,6 +1815,17 @@ static int nvme_tcp_sock_set_tos(struct sock *sk, in= t tos) KERNEL_SOCKPTR(&tos), sizeof(tos)); } =20 +static int nvme_tcp_sock_set_tclass(struct sock *sk, int tclass) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family =3D=3D AF_INET6) + return do_sock_setsockopt(sk->sk_socket, false, SOL_IPV6, + IPV6_TCLASS, KERNEL_SOCKPTR(&tclass), + sizeof(tclass)); +#endif + return 0; +} + static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, key_serial_t pskid) { @@ -1909,6 +1920,15 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nc= trl, int qid, qid, ret); goto err_sock; } + + ret =3D nvme_tcp_sock_set_tclass(queue->sock->sk, + nctrl->opts->tos); + if (ret) { + dev_err(nctrl->device, + "failed to set IPV6_TCLASS on queue %d err %d\n", + qid, ret); + goto err_sock; + } } =20 /* Set 10 seconds timeout for icresp recvmsg */ --=20 2.53.0