From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 27D3F279780 for ; Sat, 27 Sep 2025 12:31:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976297; cv=none; b=sZcY5AQ54GgKZYLkDmUtwe9+1VWROFfFuNVRV6phmX9mkbuhBx6K1O3TeuPGov1CY3T5bJZ/52yTrfJdckPnMlcLgrpZ+9bKLu4Voq8ENFA+/GvqdIYRBoU1nYKA11r3dQ7wz7yeW136gdTfy114QxlZglJPhSkxty8MLkOZyLo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976297; c=relaxed/simple; bh=u6uL/2JO+e+PImVQJitwPk7c7+HFp3BT5LJ36sbowYE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=qq909LGnKcYJjiXD440uTQgqNVKw/rb/FKpyFt/r+H0zumilDzCXpMy7UXRSy8yYeD+cOsdapVKaFbKB9oT1CwVik9SjJCzBv0dJhVgyoaAcMMLu9XTnp1w3oVSGx6nJdSOpuFzapLJZ57RqceGZbTIIeM4PKqG/f6+Rwbr1RoY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=XkwQlOYs; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="XkwQlOYs" Received: by smtp.kernel.org (Postfix) with ESMTPSA id DCCB5C4CEF5; Sat, 27 Sep 2025 12:31:35 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976296; bh=u6uL/2JO+e+PImVQJitwPk7c7+HFp3BT5LJ36sbowYE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=XkwQlOYsARgXf01oASoyMNgzrXykGXIJ+KOMfxwe8r8LiJw1ytRsVFubqe+0FXxyC INgozC8/WYo89NgLGaePwq8ulOxo892f6iA5T+ofn/vDV1aBQksO75zVXsK3Wl1h3J IMdIhph4OKe+oGbh29mQVVjUr70zPg5zJg0h7JKbE7TCvz7pus6uc9eBbwVSHAVEhM sjJpEluWuam5hbZWDSGPRDoCQIIe7PX4OZzDh/VirAFe+AVxbzeQ6Vo1zdLFoQTm2m LiVYd8mROoay1sDpw2kwvK6skAJMs2GxWl5HpQWs5KR+HF/IjpBoTKfEmyMexlGN+Q dk//H6GSopUvg== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang Subject: [PATCH mptcp-next v12 1/8] mptcp: add eat_recv_skb helper Date: Sat, 27 Sep 2025 20:30:18 +0800 Message-ID: X-Mailer: git-send-email 2.43.0 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 extracts the free skb related code in __mptcp_recvmsg_mskq() into a new helper mptcp_eat_recv_skb(). Signed-off-by: Geliang Tang --- net/mptcp/protocol.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 574a1e222d9c..e12dad700a58 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1936,6 +1936,17 @@ static int mptcp_sendmsg(struct sock *sk, struct msg= hdr *msg, size_t len) =20 static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); =20 +static void mptcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) +{ + /* avoid the indirect call, we know the destructor is sock_rfree */ + skb->destructor =3D NULL; + skb->sk =3D NULL; + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, skb->truesize); + __skb_unlink(skb, &sk->sk_receive_queue); + skb_attempt_defer_free(skb); +} + static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, size_t len, int flags, @@ -1978,13 +1989,7 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, } =20 if (!(flags & MSG_PEEK)) { - /* avoid the indirect call, we know the destructor is sock_rfree */ - skb->destructor =3D NULL; - skb->sk =3D NULL; - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - sk_mem_uncharge(sk, skb->truesize); - __skb_unlink(skb, &sk->sk_receive_queue); - skb_attempt_defer_free(skb); + mptcp_eat_recv_skb(sk, skb); msk->bytes_consumed +=3D count; } =20 --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 15B2927A900 for ; Sat, 27 Sep 2025 12:31:38 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976300; cv=none; b=FXwaB1Z+a4cMZFlC6g00lzp+zV0LXsMzD238g71J2CFr22Zpjf7P7qGTtJc52JNE/DHF8J1YrSK98ILcq1uFp1S6LpgSx4AK+nOzYthwUzA+QZVCC04RLNy3z58jO4atkzm+teOKle6eD33lqt0Wt7X4lfEHl+ZqQWlT1X8lkg4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976300; c=relaxed/simple; bh=kAO0rb/tHrkcMFGp2LhqpXQkx7OXrBt5JdXbJn8olhE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=PvO44uMp7Y8UkS/wEVHNz1Qqr2EqmfM+hUI4+ivL03OLW19/nTw/PSbV75Mana90J3dYVGYzDlQy5T/V//YcqEyKXrbxm97qZzSdW3AiQSeb3TPUQ8eaZ66TJkavf7H/dzRArn95S6tyfm42DJubrvWIsGoCjh/PKXBrs5X14C0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=QXkqMGVY; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="QXkqMGVY" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 4A729C4CEE7; Sat, 27 Sep 2025 12:31:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976298; bh=kAO0rb/tHrkcMFGp2LhqpXQkx7OXrBt5JdXbJn8olhE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=QXkqMGVYvlm09i9tQ18MvUgaNVgi6gfl+pNPDaDhcVV6QDx9+/crGvqxCld6sSy45 hCTxkyrSoNpPJCS/aBIZTHLztPQ+nLqLzdyCRN0jtCam/XF0aRWiqPzKkwUqhGMvx6 cgcj82XaITE5h7x4r8RWl9h0iBnssrqmYxrrW+UNmdFkpDIQdB8Dv4EbDYTsV/GQ9W 56lDgaZlXa7ijfgtVT8cEe7DfRfHNrZQku9XnA+HuPjPQ1RrpceScdJemPk1L1rvMQ ZqZkqVPALjI1ap3TD+h3tl2EI5L7oqGmnBjS3QF9W2Ji7ndvp62OJLA/u4qouFMLa2 itbooh/WFHkyQ== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang , Hannes Reinecke Subject: [PATCH mptcp-next v12 2/8] mptcp: implement .read_sock Date: Sat, 27 Sep 2025 20:30:19 +0800 Message-ID: <2f159972f4aac7002a46ebc03b9d3898ece4c081.1758975929.git.tanggeliang@kylinos.cn> X-Mailer: git-send-email 2.43.0 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 nvme_tcp_try_recv() needs to call .read_sock interface of struct proto_ops, but it's not implemented in MPTCP. This patch implements it with reference to __tcp_read_sock() and __mptcp_recvmsg_mskq(). Corresponding to tcp_recv_skb(), a new helper for MPTCP named mptcp_recv_skb() is added to peek a skb from sk->sk_receive_queue. Compared with __mptcp_recvmsg_mskq(), mptcp_read_sock() uses sk->sk_rcvbuf as the max read length. The LISTEN status is checked before the while loop, and mptcp_recv_skb() and mptcp_cleanup_rbuf() are invoked after the loop. In the loop, all flags checks for __mptcp_recvmsg_mskq() are removed. Reviewed-by: Hannes Reinecke Signed-off-by: Geliang Tang --- net/mptcp/protocol.c | 74 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e12dad700a58..dda16dbae9fd 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -4055,6 +4055,78 @@ static __poll_t mptcp_poll(struct file *file, struct= socket *sock, return mask; } =20 +static struct sk_buff *mptcp_recv_skb(struct sock *sk, u32 *off) +{ + struct sk_buff *skb; + u32 offset; + + if (skb_queue_empty(&sk->sk_receive_queue)) + __mptcp_move_skbs(sk); + + while ((skb =3D skb_peek(&sk->sk_receive_queue)) !=3D NULL) { + offset =3D MPTCP_SKB_CB(skb)->offset; + if (offset < skb->len) { + *off =3D offset; + return skb; + } + mptcp_eat_recv_skb(sk, skb); + } + return NULL; +} + +/* + * Note: + * - It is assumed that the socket was locked by the caller. + */ +static int mptcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct mptcp_sock *msk =3D mptcp_sk(sk); + size_t len =3D sk->sk_rcvbuf; + struct sk_buff *skb; + int copied =3D 0; + u32 offset; + + if (sk->sk_state =3D=3D TCP_LISTEN) + return -ENOTCONN; + while ((skb =3D mptcp_recv_skb(sk, &offset)) !=3D NULL) { + u32 data_len =3D skb->len - offset; + u32 size =3D min_t(size_t, len - copied, data_len); + int count; + + count =3D recv_actor(desc, skb, offset, size); + if (count <=3D 0) { + if (!copied) + copied =3D count; + break; + } + + copied +=3D count; + + if (count < data_len) { + MPTCP_SKB_CB(skb)->offset +=3D count; + MPTCP_SKB_CB(skb)->map_seq +=3D count; + msk->bytes_consumed +=3D count; + break; + } + + mptcp_eat_recv_skb(sk, skb); + msk->bytes_consumed +=3D count; + + if (copied >=3D len) + break; + } + + mptcp_rcv_space_adjust(msk, copied); + + if (copied > 0) { + mptcp_recv_skb(sk, &offset); + mptcp_cleanup_rbuf(msk, copied); + } + + return copied; +} + static const struct proto_ops mptcp_stream_ops =3D { .family =3D PF_INET, .owner =3D THIS_MODULE, @@ -4075,6 +4147,7 @@ static const struct proto_ops mptcp_stream_ops =3D { .recvmsg =3D inet_recvmsg, .mmap =3D sock_no_mmap, .set_rcvlowat =3D mptcp_set_rcvlowat, + .read_sock =3D mptcp_read_sock, }; =20 static struct inet_protosw mptcp_protosw =3D { @@ -4179,6 +4252,7 @@ static const struct proto_ops mptcp_v6_stream_ops =3D= { .compat_ioctl =3D inet6_compat_ioctl, #endif .set_rcvlowat =3D mptcp_set_rcvlowat, + .read_sock =3D mptcp_read_sock, }; =20 static struct proto mptcp_v6_prot; --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 35F8B27A900 for ; Sat, 27 Sep 2025 12:31:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976302; cv=none; b=JBNnbu5Q5JkU11oHlf9rk4Nx6zhX2VjInJTTZ/jnwH/Jn1zAZQcOxyrK/96AwjJvCBt5yKbqd8oPy6IuL3zBqpZIvgMgBAszxzoEYnuI7jBp5m+VqYhrZb/zglCBub2GreBQAf/e/UcHbAJ3d+6GFejL/3mztl3SBpfSJtzMrQ4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976302; c=relaxed/simple; bh=Gf/1GGWFVT75sh9k240f+4uEhi0FRKi36OKzPuA+VC8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=TxwYCvzoKvUvfpJiqdlb8Fkm5ELeLyDWWb9RntHmvJeizuXkxjkbkx7wInuCxCQu4iDEmwugxX5lNMLlT+tUtxdg9FedvHNfX0TZe7VdKoVXQl3NhntK4dsW69RQInJYI3qwjbRq0wnXtJYf417/OWO5a/R13WPiGb56T6l0D1M= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=ZqmftGnI; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="ZqmftGnI" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 566EFC113CF; Sat, 27 Sep 2025 12:31:39 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976300; bh=Gf/1GGWFVT75sh9k240f+4uEhi0FRKi36OKzPuA+VC8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ZqmftGnIjnz95BhVDiRAaFXC2H9Gmvo5Dn3wc4Kl3DRiLLFim96aYT/fiSlrIeMXW nc1DWkV3TUXZvNvj8u6lxVsiQgsjSJhaty1vzdRudvjldhNUdTxNpMgWuNz4pf9B5/ UX4EZdkkXPJEljIaLn5IWFNQm3Cu05oBC6dvOe9+JPQjMqTPTfyKzKxK6GJiJ1NzEd cow5r+75osNvmlkieJaHZYDPRovcdt9HYfuBqhJkttSUUnxjIpdeB4wlUZvN3m5HTD 38UFN9BlEO4H06pI3ezOcwSfdGAdE9j32KhjX7h3C6tiDmgiRhPSjKPp8UgmtCvunT 39L+x8dFRECEg== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang , Paolo Abeni Subject: [PATCH mptcp-next v12 3/8] tcp: export splice_state and splice_data_recv Date: Sat, 27 Sep 2025 20:30:20 +0800 Message-ID: <41ca62e786b275e637c19ff260d71a1ec2f43d8c.1758975929.git.tanggeliang@kylinos.cn> X-Mailer: git-send-email 2.43.0 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 Export struct tcp_splice_state and tcp_splice_data_recv() in net/tcp.h so that they can be used by MPTCP. Suggested-by: Paolo Abeni Signed-off-by: Geliang Tang --- include/net/tcp.h | 12 ++++++++++++ net/ipv4/tcp.c | 13 ++----------- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 5ca230ed526a..402017e8367e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -282,6 +282,18 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); */ #define TFO_SERVER_WO_SOCKOPT1 0x400 =20 +/* + * TCP splice context + */ +struct tcp_splice_state { + struct pipe_inode_info *pipe; + size_t len; + unsigned int flags; +}; + +int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, + unsigned int offset, size_t len); + =20 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 15602793e4a9..bfad7ccf6bad 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -319,15 +319,6 @@ EXPORT_SYMBOL(tcp_have_smc); struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_IPV6_MOD(tcp_sockets_allocated); =20 -/* - * TCP splice context - */ -struct tcp_splice_state { - struct pipe_inode_info *pipe; - size_t len; - unsigned int flags; -}; - /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. @@ -777,8 +768,8 @@ void tcp_push(struct sock *sk, int flags, int mss_now, __tcp_push_pending_frames(sk, mss_now, nonagle); } =20 -static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff= *skb, - unsigned int offset, size_t len) +int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, + unsigned int offset, size_t len) { struct tcp_splice_state *tss =3D rd_desc->arg.data; int ret; --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 E213E27A900 for ; Sat, 27 Sep 2025 12:31:42 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976303; cv=none; b=kaIVUYawuaTNQMBIbsvP1w8It1NsZ+HZvbEuzhDp3xL/n9iTx0PVM2QkSIkRCNfSqgh88+Fh0U40tmsdT9FkormuE4KJ2pvtDK9hQ88YaE3GekXQq/Ld2OhXgvD2KtS3G/t2sIgq7wIEw+OZB18SpyBeZjKUkr0+W+nhsBHBycc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976303; c=relaxed/simple; bh=Cq5wvVk0/9Ya5fhm3TV00/i0wjTJZX4g1uY68NMvft8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=a4VfIm1TSofjBZcR//BMFwm6G9IL5DrVqDlfnzoR1ua5iEHq6UHspm0GpoOzGyA73G9qkernVJ2ErFNw5aaSfyZNCazAtyPwIAt98z0vJH/Zi4TPmR/kDpR58K4eXjtA9LeDCFjmxmWM1uC0jFXChHl3BxtylFBIGULNngg2tbc= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=draM5z4J; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="draM5z4J" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 49E56C4CEE7; Sat, 27 Sep 2025 12:31:41 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976302; bh=Cq5wvVk0/9Ya5fhm3TV00/i0wjTJZX4g1uY68NMvft8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=draM5z4JTXBmHupLq2aVP1jHOoc+I48VbzbPQVWxVLgek92taKQYFxlxoc31hKIGA 5CD4AL/5Y70XSIb48Oi5NoKXpdVm3LBkHU2ciWqqc67exPQkstB+uGzVKPIY9x2m50 /TQRzD3qc6i6vfKMTTw8ejpxEFDWpYVRLxPcgrXvgEQqS01bEShMxjFGG9OEKg7t9a lEQubnBe4RwVRhCjgy+rdm4Vtqm5aufbCQeP28pxDmIkDN5GBVlCcYGi16AM9C1Es/ UVkXo20u3o1zEcmVE0wzDOgkAB7cvRv0jBbM8U28zGl2qIXNEQAwBxbPn/fQGG0JUL YMfdkMtNJ72vA== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang , Paolo Abeni Subject: [PATCH mptcp-next v12 4/8] tcp: add recv_should_stop helper Date: Sat, 27 Sep 2025 20:30:21 +0800 Message-ID: <9696fa685c7c2f6455eed9c62664e0affe3b3bfc.1758975929.git.tanggeliang@kylinos.cn> X-Mailer: git-send-email 2.43.0 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 Factor out a new helper tcp_recv_should_stop() from tcp_recvmsg_locked() and tcp_splice_read() to check whether to stop receiving. It will be used for MPTCP too. Suggested-by: Paolo Abeni Signed-off-by: Geliang Tang --- include/net/tcp.h | 23 +++++++++++++++ net/ipv4/tcp.c | 73 ++++++++--------------------------------------- 2 files changed, 35 insertions(+), 61 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 402017e8367e..746ad7561eb6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -294,6 +294,29 @@ struct tcp_splice_state { int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len); =20 +static inline int tcp_recv_should_stop(struct sock *sk, long timeo) +{ + if (sock_flag(sk, SOCK_DONE)) + return -ENETDOWN; + + if (sk->sk_err) + return sock_error(sk); + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return -ESHUTDOWN; + + if (sk->sk_state =3D=3D TCP_CLOSE) + return -ENOTCONN; + + if (!timeo) + return -EAGAIN; + + if (signal_pending(current)) + return sock_intr_errno(timeo); + + return 0; +} + =20 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bfad7ccf6bad..39c86c338378 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -835,26 +835,14 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *= ppos, if (ret < 0) break; else if (!ret) { + int err; + if (spliced) break; - if (sock_flag(sk, SOCK_DONE)) - break; - if (sk->sk_err) { - ret =3D sock_error(sk); - break; - } - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - if (sk->sk_state =3D=3D TCP_CLOSE) { - /* - * This occurs when user tries to read - * from never connected socket. - */ - ret =3D -ENOTCONN; - break; - } - if (!timeo) { - ret =3D -EAGAIN; + err =3D tcp_recv_should_stop(sk, timeo); + if (err < 0) { + if (err !=3D -ENETDOWN && err !=3D -ESHUTDOWN) + ret =3D err; break; } /* if __tcp_splice_read() got nothing while we have @@ -866,10 +854,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *p= pos, ret =3D sk_wait_data(sk, &timeo, NULL); if (ret < 0) break; - if (signal_pending(current)) { - ret =3D sock_intr_errno(timeo); - break; - } continue; } tss.len -=3D ret; @@ -880,9 +864,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *pp= os, release_sock(sk); lock_sock(sk); =20 - if (sk->sk_err || sk->sk_state =3D=3D TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current)) + if (tcp_recv_should_stop(sk, timeo)) break; } =20 @@ -2719,42 +2701,11 @@ static int tcp_recvmsg_locked(struct sock *sk, stru= ct msghdr *msg, size_t len, if (copied >=3D target && !READ_ONCE(sk->sk_backlog.tail)) break; =20 - if (copied) { - if (!timeo || - sk->sk_err || - sk->sk_state =3D=3D TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || - signal_pending(current)) - break; - } else { - if (sock_flag(sk, SOCK_DONE)) - break; - - if (sk->sk_err) { - copied =3D sock_error(sk); - break; - } - - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - - if (sk->sk_state =3D=3D TCP_CLOSE) { - /* This occurs when user tries to read - * from never connected socket. - */ - copied =3D -ENOTCONN; - break; - } - - if (!timeo) { - copied =3D -EAGAIN; - break; - } - - if (signal_pending(current)) { - copied =3D sock_intr_errno(timeo); - break; - } + err =3D tcp_recv_should_stop(sk, timeo); + if (err < 0) { + if (!copied && err !=3D -ENETDOWN && err !=3D -ESHUTDOWN) + copied =3D err; + break; } =20 if (copied >=3D target) { --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 B71FC27A900 for ; Sat, 27 Sep 2025 12:31:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976304; cv=none; b=rYG+ayxM7Gscpz77Gfpz1q3AN1h3VkzJ2iZdNOND/uuBdW6ugalnxBwvrCUDN5e8NM7HOGehCREkUvFE45wmT80pZ5Qp6wc2ULnjzARr3BPpXnqbdFPnRnhx2ctoKz6/tXQU6FKoGOsESobGYE3SGv0/mARH7nNeXaOdWHxH2UI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976304; c=relaxed/simple; bh=Iki+1dnb+B/uAJcXECqXdbHo2g86Fup0XTV0nSZlnzE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SnkLdZ2YQF/eb+SPXHGhBP0lZVxcM6PuNfuuix9KpvvHxMiHONajgTSWOzslDFQBrwW6fHU4sZD/abws3hBijJ/bs48ZA9m/pb9f4ujJ4ReaMq86zzseIA+wBt6l0oXhQ+T5qWOeJDfC3KYqYWW768tdjsODRHQkKuESZ5PyGj4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=eCuduuQ8; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="eCuduuQ8" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 728FBC4CEE7; Sat, 27 Sep 2025 12:31:43 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976304; bh=Iki+1dnb+B/uAJcXECqXdbHo2g86Fup0XTV0nSZlnzE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=eCuduuQ8cngqf0DXG8ustO/4Re7P8eLUSXFRAeUyIFujXklMKb3RmgmvlgtyByTA+ ls4bE2eHIpdkmd+FwtEdxpuxOnt7HODC3D0fnefY78PC4ZM3P1JkMrOQUu7vH3YpWf IS/m42qypRGQNhXFp8fi9f2K6Aemzs3RbrQJoQdtE6VMt48qKjiMTaY7cKv1ISxPgG yahFYxz854d7fVdxGnS0CESOEBnRG60coMgC3Y7tFRcHH5bAtUsoYDFmCXZefmd7U4 VaZJyRjSX/gQO8Be29rlUmkk66owb+HDsGdX1Jfydm/3C5aTY5wNBFZMboyt3Ji/vb e9SUQh+vnLIGA== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang Subject: [PATCH mptcp-next v12 5/8] mptcp: use recv_should_stop helper Date: Sat, 27 Sep 2025 20:30:22 +0800 Message-ID: X-Mailer: git-send-email 2.43.0 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 Use the newly added tcp_recv_should_stop() helper in mptcp_recvmsg() to check whether to stop receiving. Signed-off-by: Geliang Tang --- net/mptcp/protocol.c | 35 +++++------------------------------ 1 file changed, 5 insertions(+), 30 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dda16dbae9fd..5cbe652b6ea0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2206,36 +2206,11 @@ static int mptcp_recvmsg(struct sock *sk, struct ms= ghdr *msg, size_t len, if (copied >=3D target) break; =20 - if (copied) { - if (sk->sk_err || - sk->sk_state =3D=3D TCP_CLOSE || - (sk->sk_shutdown & RCV_SHUTDOWN) || - !timeo || - signal_pending(current)) - break; - } else { - if (sk->sk_err) { - copied =3D sock_error(sk); - break; - } - - if (sk->sk_shutdown & RCV_SHUTDOWN) - break; - - if (sk->sk_state =3D=3D TCP_CLOSE) { - copied =3D -ENOTCONN; - break; - } - - if (!timeo) { - copied =3D -EAGAIN; - break; - } - - if (signal_pending(current)) { - copied =3D sock_intr_errno(timeo); - break; - } + err =3D tcp_recv_should_stop(sk, timeo); + if (err < 0) { + if (!copied && err !=3D -ESHUTDOWN) + copied =3D err; + break; } =20 pr_debug("block timeout %ld\n", timeo); --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 9068827A900 for ; Sat, 27 Sep 2025 12:31:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976306; cv=none; b=QHTw0cUwUJUItuYhahaEwsNq6NWzhk/nsaNn6Xl66vE+CnTZObFr8SeYgGapJVtVPhD3BJjBwGIrGTqx/lAVJeiQ+cpTIbidRLMv8LUfIOdSgdt3UFVx507InXNP1T9z9xQthFK+ukCko34nifAFM8Rduv1alUXcoa7pLckX7xk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976306; c=relaxed/simple; bh=pxt1pf4TBCUyzUS2syS0aYk17cBKb0JLhvV1XbP8PWI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SIBig2AgakB/KXCPyHCTesP9RvHEoztT+8OnPstBNeQceABWvN54c7MtVZmznmehTn/bMTf3Dkk/7my6QHWdd9cXDdbAjlXXMb2q6TMt2dPU7Un/exGFYLxV3OTWwTI20cidh629npbbifClLFaKF6A9aGv7CWhLkcoHAKO8kiw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=kBeOF7fT; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="kBeOF7fT" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 6EFD7C4CEE7; Sat, 27 Sep 2025 12:31:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976306; bh=pxt1pf4TBCUyzUS2syS0aYk17cBKb0JLhvV1XbP8PWI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=kBeOF7fTrHFQ6tq/O6lobSwK5C0kg7ZrSxDngfQf9loyPWR/EGIerlNebgt84um4j BeziqLvcpRU8q+3eG6kwJALyQWJnIIQmY9HZlV/EkBh9GDs3i6DzJ2uKCwKm/MuSLO F76ikn6REj6v9tH5qn1/0mlhGdm31VaLcNEIKRgYt09PFXJywfoSPvLEMCU8wqZv/D ts5P5lrDAGYocOsUefsgjySGL9bV8gtQ091aynRo54EJwO3e44f0r9QDBt8HZ6OPFm RfzjVdL+p8eCi5E4XT+uW1CTZGCEFrFiZ+6Z60sEVdx1MzIDcrTIUuzrZE6VpIap7U UJCyg59jUSTTw== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang Subject: [PATCH mptcp-next v12 6/8] mptcp: implement .splice_read Date: Sat, 27 Sep 2025 20:30:23 +0800 Message-ID: X-Mailer: git-send-email 2.43.0 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 implements .splice_read interface of mptcp struct proto_ops as mptcp_splice_read() with reference to tcp_splice_read(). Corresponding to __tcp_splice_read(), __mptcp_splice_read() is defined, invoking mptcp_read_sock() instead of tcp_read_sock(). mptcp_splice_read() is almost the same as tcp_splice_read(), except for sock_rps_record_flow(). Signed-off-by: Geliang Tang --- net/mptcp/protocol.c | 96 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5cbe652b6ea0..05c6ab0b9848 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -4102,6 +4102,100 @@ static int mptcp_read_sock(struct sock *sk, read_de= scriptor_t *desc, return copied; } =20 +static int __mptcp_splice_read(struct sock *sk, struct tcp_splice_state *t= ss) +{ + /* Store TCP splice context information in read_descriptor_t. */ + read_descriptor_t rd_desc =3D { + .arg.data =3D tss, + .count =3D tss->len, + }; + + return mptcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); +} + +/** + * mptcp_splice_read - splice data from MPTCP socket to a pipe + * @sock: socket to splice from + * @ppos: position (not valid) + * @pipe: pipe to splice to + * @len: number of bytes to splice + * @flags: splice modifier flags + * + * Description: + * Will read pages from given socket and fill them into a pipe. + * + **/ +static ssize_t mptcp_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + struct tcp_splice_state tss =3D { + .pipe =3D pipe, + .len =3D len, + .flags =3D flags, + }; + struct sock *sk =3D sock->sk; + ssize_t spliced =3D 0; + int ret =3D 0; + long timeo; + + /* + * We can't seek on a socket input + */ + if (unlikely(*ppos)) + return -ESPIPE; + + lock_sock(sk); + + mptcp_rps_record_subflows(mptcp_sk(sk)); + + timeo =3D sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); + while (tss.len) { + ret =3D __mptcp_splice_read(sk, &tss); + if (ret < 0) { + break; + } else if (!ret) { + int err; + + if (spliced) + break; + err =3D tcp_recv_should_stop(sk, timeo); + if (err < 0) { + if (err !=3D -ESHUTDOWN) + ret =3D err; + break; + } + /* if __mptcp_splice_read() got nothing while we have + * an skb in receive queue, we do not want to loop. + * This might happen with URG data. + */ + if (!skb_queue_empty(&sk->sk_receive_queue)) + break; + ret =3D sk_wait_data(sk, &timeo, NULL); + if (ret < 0) + break; + continue; + } + tss.len -=3D ret; + spliced +=3D ret; + + if (!tss.len || !timeo) + break; + release_sock(sk); + lock_sock(sk); + + if (tcp_recv_should_stop(sk, timeo)) + break; + } + + release_sock(sk); + + if (spliced) + return spliced; + + return ret; +} + static const struct proto_ops mptcp_stream_ops =3D { .family =3D PF_INET, .owner =3D THIS_MODULE, @@ -4123,6 +4217,7 @@ static const struct proto_ops mptcp_stream_ops =3D { .mmap =3D sock_no_mmap, .set_rcvlowat =3D mptcp_set_rcvlowat, .read_sock =3D mptcp_read_sock, + .splice_read =3D mptcp_splice_read, }; =20 static struct inet_protosw mptcp_protosw =3D { @@ -4228,6 +4323,7 @@ static const struct proto_ops mptcp_v6_stream_ops =3D= { #endif .set_rcvlowat =3D mptcp_set_rcvlowat, .read_sock =3D mptcp_read_sock, + .splice_read =3D mptcp_splice_read, }; =20 static struct proto mptcp_v6_prot; --=20 2.43.0 From nobody Sat Oct 11 05:56:22 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (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 0344D27A900 for ; Sat, 27 Sep 2025 12:31:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976308; cv=none; b=Kz+yc7lf1+fQf3TA6lpMyeR42xTMmEv9KE6/mmSeCWjE4946Smvx8VL2E/EurNDIhsK5kBZ7zGdfg7tDGC2PMDmZNcqQ6ftmXVrrNQPrnITvMubEYr5l5LgdWzE2r6NYr1DJbu1+ZP+nrCFjI8Hdq4By7moITCKlDJzEBPTpx4k= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1758976308; c=relaxed/simple; bh=2yQXe35CBtR4uoYT5CbBOnaes42b897+rj8e59xHPGg=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=om9SlUnuXKdNMQd65HkF9MvPFw+RB9G54qyg0GKqHhhPb42ejw8F5bjeMRAzkCJbC5snZCy5ABs7vwZDxth93rIP9NPyxfof9qrKwex4W+dqwI1w+OjIRizWwMTdxBu1LIQAZL4viTLEXdL2Uc/ebfWMv1BlMiBZtvnrLI6fMy4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=DkyOK7eW; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="DkyOK7eW" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9FD78C4CEF5; Sat, 27 Sep 2025 12:31:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1758976307; bh=2yQXe35CBtR4uoYT5CbBOnaes42b897+rj8e59xHPGg=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=DkyOK7eWStj82UMNztMFluLjGk9ANf36qPuz9WKpOeJPDBrPsPRj0bOingV1S3+t/ eB305JagVlFpQFFrakX5f0/6pHPNNKnu+5UyUdtEp6VBRLpc4yduwA+YZ9tPf4LsS9 OWEqwkmUkrwXaFp4dnwikPOysAUIjH7TptKGL2nPg6gHBrt4d0MJYTsYPCli11iwwy vPjjfjXvpNABn2p3Y77VBCRBONDHXhbYJ3LTqYUNpikGLseVL+6DVb62RXLD+rMhB8 10/PZEF3Ev1/0v0Cn/dFIBYVzEgPZ2Dcjz4lmuiBXHqfakNn1u9T0uf0eHJC2NiIr2 2f3kSAZfyA7Vw== From: Geliang Tang To: mptcp@lists.linux.dev Cc: Geliang Tang Subject: [PATCH mptcp-next v12 7/8] selftests: mptcp: add splice io mode Date: Sat, 27 Sep 2025 20:30:24 +0800 Message-ID: X-Mailer: git-send-email 2.43.0 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 adds a new 'splice' io mode for mptcp_connect to test the newly added read_sock() and splice_read() functions of MPTCP. do_splice() efficiently transfers data directly between two file descriptors (infd and outfd) without copying to userspace, using Linux's splice() system call. Usage: ./mptcp_connect.sh -m splice Signed-off-by: Geliang Tang --- .../selftests/net/mptcp/mptcp_connect.c | 63 ++++++++++++++++++- 1 file changed, 62 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/test= ing/selftests/net/mptcp/mptcp_connect.c index b148cadb96d0..52c6696a13a5 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -51,6 +51,7 @@ enum cfg_mode { CFG_MODE_POLL, CFG_MODE_MMAP, CFG_MODE_SENDFILE, + CFG_MODE_SPLICE, }; =20 enum cfg_peek { @@ -123,7 +124,7 @@ static void die_usage(void) fprintf(stderr, "\t-j -- add additional sleep at connection start and= tear down " "-- for MPJ tests\n"); fprintf(stderr, "\t-l -- listens mode, accepts incoming connection\n"= ); - fprintf(stderr, "\t-m [poll|mmap|sendfile] -- use poll(default)/mmap+writ= e/sendfile\n"); + fprintf(stderr, "\t-m [poll|mmap|sendfile|splice] -- use poll(default)/mm= ap+write/sendfile/splice\n"); fprintf(stderr, "\t-M mark -- set socket packet mark\n"); fprintf(stderr, "\t-o option -- test sockopt