From: Mat Martineau <mathew.j.martineau@linux.intel.com>
To: netdev@vger.kernel.org, edumazet@google.com
Cc: Mat Martineau <mathew.j.martineau@linux.intel.com>,
cpaasch@apple.com, fw@strlen.de, pabeni@redhat.com,
peter.krystad@linux.intel.com, dcaratti@redhat.com,
matthieu.baerts@tessares.net
Subject: [RFC PATCH v2 05/45] mptcp: Add MPTCP socket stubs
Date: Wed, 2 Oct 2019 16:36:15 -0700 [thread overview]
Message-ID: <20191002233655.24323-6-mathew.j.martineau@linux.intel.com> (raw)
In-Reply-To: <20191002233655.24323-1-mathew.j.martineau@linux.intel.com>
Implements the infrastructure for MPTCP sockets.
MPTCP sockets open one in-kernel TCP socket per subflow. These subflow
sockets are only managed by the MPTCP socket that owns them and are not
visible from userspace. This commit allows a userspace program to open
an MPTCP socket with:
sock = socket(AF_INET, SOCK_STREAM, IPPROTO_MPTCP);
The resulting socket is simply a wrapper around a single regular TCP
socket, without any of the MPTCP protocol implemented over the wire.
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Peter Krystad <peter.krystad@linux.intel.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
---
include/net/mptcp.h | 22 +++++++++
net/Kconfig | 1 +
net/Makefile | 1 +
net/ipv4/tcp.c | 2 +
net/mptcp/Kconfig | 10 ++++
net/mptcp/Makefile | 4 ++
net/mptcp/protocol.c | 114 +++++++++++++++++++++++++++++++++++++++++++
net/mptcp/protocol.h | 22 +++++++++
8 files changed, 176 insertions(+)
create mode 100644 include/net/mptcp.h
create mode 100644 net/mptcp/Kconfig
create mode 100644 net/mptcp/Makefile
create mode 100644 net/mptcp/protocol.c
create mode 100644 net/mptcp/protocol.h
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
new file mode 100644
index 000000000000..0fe78fddc638
--- /dev/null
+++ b/include/net/mptcp.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __NET_MPTCP_H
+#define __NET_MPTCP_H
+
+#ifdef CONFIG_MPTCP
+
+void mptcp_init(void);
+
+#else
+
+static inline void mptcp_init(void)
+{
+}
+
+#endif /* CONFIG_MPTCP */
+#endif /* __NET_MPTCP_H */
diff --git a/net/Kconfig b/net/Kconfig
index 3101bfcbdd7a..4f7e7f3618d0 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -91,6 +91,7 @@ if INET
source "net/ipv4/Kconfig"
source "net/ipv6/Kconfig"
source "net/netlabel/Kconfig"
+source "net/mptcp/Kconfig"
endif # if INET
diff --git a/net/Makefile b/net/Makefile
index 449fc0b221f8..306d2e8c12c0 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -87,3 +87,4 @@ endif
obj-$(CONFIG_QRTR) += qrtr/
obj-$(CONFIG_NET_NCSI) += ncsi/
obj-$(CONFIG_XDP_SOCKETS) += xdp/
+obj-$(CONFIG_MPTCP) += mptcp/
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 79c325a07ba5..5893d08cb204 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -271,6 +271,7 @@
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/sock.h>
@@ -4006,4 +4007,5 @@ void __init tcp_init(void)
tcp_metrics_init();
BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
tcp_tasklet_init();
+ mptcp_init();
}
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
new file mode 100644
index 000000000000..d87dfdc210cc
--- /dev/null
+++ b/net/mptcp/Kconfig
@@ -0,0 +1,10 @@
+
+config MPTCP
+ bool "Multipath TCP"
+ depends on INET
+ help
+ Multipath TCP (MPTCP) connections send and receive data over multiple
+ subflows in order to utilize multiple network paths. Each subflow
+ uses the TCP protocol, and TCP options carry header information for
+ MPTCP.
+
diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
new file mode 100644
index 000000000000..659129d1fcbf
--- /dev/null
+++ b/net/mptcp/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_MPTCP) += mptcp.o
+
+mptcp-y := protocol.o
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
new file mode 100644
index 000000000000..e5c87cb08f97
--- /dev/null
+++ b/net/mptcp/protocol.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <net/sock.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/protocol.h>
+#include <net/tcp.h>
+#include <net/mptcp.h>
+#include "protocol.h"
+
+static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *subflow = msk->subflow;
+
+ return sock_sendmsg(subflow, msg);
+}
+
+static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *subflow = msk->subflow;
+
+ return sock_recvmsg(subflow, msg, flags);
+}
+
+static int mptcp_init_sock(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct net *net = sock_net(sk);
+ struct socket *sf;
+ int err;
+
+ err = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sf);
+ if (!err) {
+ pr_debug("subflow=%p", sf->sk);
+ msk->subflow = sf;
+ }
+
+ return err;
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ inet_sk_state_store(sk, TCP_CLOSE);
+
+ if (msk->subflow) {
+ pr_debug("subflow=%p", msk->subflow->sk);
+ sock_release(msk->subflow);
+ }
+
+ sock_orphan(sk);
+ sock_put(sk);
+}
+
+static int mptcp_connect(struct sock *sk, struct sockaddr *saddr, int len)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ int err;
+
+ saddr->sa_family = AF_INET;
+
+ pr_debug("msk=%p, subflow=%p", msk, msk->subflow->sk);
+
+ err = kernel_connect(msk->subflow, saddr, len, 0);
+
+ sk->sk_state = TCP_ESTABLISHED;
+
+ return err;
+}
+
+static struct proto mptcp_prot = {
+ .name = "MPTCP",
+ .owner = THIS_MODULE,
+ .init = mptcp_init_sock,
+ .close = mptcp_close,
+ .accept = inet_csk_accept,
+ .connect = mptcp_connect,
+ .shutdown = tcp_shutdown,
+ .sendmsg = mptcp_sendmsg,
+ .recvmsg = mptcp_recvmsg,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .get_port = inet_csk_get_port,
+ .obj_size = sizeof(struct mptcp_sock),
+ .no_autobind = 1,
+};
+
+static struct inet_protosw mptcp_protosw = {
+ .type = SOCK_STREAM,
+ .protocol = IPPROTO_MPTCP,
+ .prot = &mptcp_prot,
+ .ops = &inet_stream_ops,
+};
+
+void __init mptcp_init(void)
+{
+ if (proto_register(&mptcp_prot, 1) != 0)
+ panic("Failed to register MPTCP proto.\n");
+
+ inet_register_protosw(&mptcp_protosw);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
new file mode 100644
index 000000000000..ee04a01bffd3
--- /dev/null
+++ b/net/mptcp/protocol.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#ifndef __MPTCP_PROTOCOL_H
+#define __MPTCP_PROTOCOL_H
+
+/* MPTCP connection sock */
+struct mptcp_sock {
+ /* inet_connection_sock must be the first member */
+ struct inet_connection_sock sk;
+ struct socket *subflow; /* outgoing connect/listener/!mp_capable */
+};
+
+static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
+{
+ return (struct mptcp_sock *)sk;
+}
+
+#endif /* __MPTCP_PROTOCOL_H */
--
2.23.0
next prev parent reply other threads:[~2019-10-02 23:37 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-02 23:36 [RFC PATCH v2 00/45] Multipath TCP Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 01/45] tcp: Add MPTCP option number Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 02/45] net: Make sock protocol value checks more specific Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 03/45] sock: Make sk_protocol a 16-bit value Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 04/45] tcp: Define IPPROTO_MPTCP Mat Martineau
2019-10-02 23:36 ` Mat Martineau [this message]
2019-10-02 23:36 ` [RFC PATCH v2 06/45] mptcp: Handle MPTCP TCP options Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 07/45] mptcp: Associate MPTCP context with TCP socket Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 08/45] tcp: Expose tcp struct and routine for MPTCP Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 09/45] mptcp: Handle MP_CAPABLE options for outgoing connections Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 10/45] mptcp: add mptcp_poll Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 11/45] tcp, ulp: Add clone operation to tcp_ulp_ops Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 12/45] mptcp: Create SUBFLOW socket for incoming connections Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 13/45] mptcp: Add key generation and token tree Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 14/45] mptcp: Add shutdown() socket operation Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 15/45] mptcp: Add setsockopt()/getsockopt() socket operations Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 16/45] tcp: clean ext on tx recycle Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 17/45] mptcp: Add MPTCP to skb extensions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 18/45] tcp: Prevent coalesce/collapse when skb has MPTCP extensions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 19/45] tcp: Export low-level TCP functions Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 20/45] mptcp: Write MPTCP DSS headers to outgoing data packets Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 21/45] mptcp: Implement MPTCP receive path Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 22/45] mptcp: use sk_page_frag() in sendmsg Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 23/45] mptcp: sendmsg() do spool all the provided data Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 24/45] mptcp: allow collapsing consecutive sendpages on the same substream Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 25/45] tcp: Check for filled TCP option space before SACK Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 26/45] mptcp: Add path manager interface Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 27/45] mptcp: Add ADD_ADDR handling Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 28/45] mptcp: Add handling of incoming MP_JOIN requests Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 29/45] mptcp: harmonize locking on all socket operations Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 30/45] mptcp: new sysctl to control the activation per NS Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 31/45] mptcp: add basic kselftest for mptcp Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 32/45] mptcp: Add handling of outgoing MP_JOIN requests Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 33/45] mptcp: Implement path manager interface commands Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 34/45] mptcp: Make MPTCP socket block/wakeup ignore sk_receive_queue Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 35/45] mptcp: update per unacked sequence on pkt reception Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 36/45] mptcp: queue data for mptcp level retransmission Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 37/45] mptcp: introduce MPTCP retransmission timer Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 38/45] mptcp: implement memory accounting for mptcp rtx queue Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 39/45] mptcp: rework mptcp_sendmsg_frag to accept optional dfrag Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 40/45] mptcp: implement and use MPTCP-level retransmission Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 41/45] selftests: mptcp: make tc delays random Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 42/45] selftests: mptcp: extend mptcp_connect tool for ipv6 family Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 43/45] selftests: mptcp: add accept/getpeer checks Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 44/45] selftests: mptcp: add ipv6 connectivity Mat Martineau
2019-10-02 23:36 ` [RFC PATCH v2 45/45] selftests: mptcp: random ethtool tweaking Mat Martineau
2019-10-02 23:53 ` [RFC PATCH v2 00/45] Multipath TCP Mat Martineau
2019-10-03 0:12 ` David Miller
2019-10-03 0:27 ` Mat Martineau
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=20191002233655.24323-6-mathew.j.martineau@linux.intel.com \
--to=mathew.j.martineau@linux.intel.com \
--cc=cpaasch@apple.com \
--cc=dcaratti@redhat.com \
--cc=edumazet@google.com \
--cc=fw@strlen.de \
--cc=matthieu.baerts@tessares.net \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=peter.krystad@linux.intel.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;
as well as URLs for NNTP newsgroup(s).