[v3,bpf-next,01/11] net: Introduce net.ipv4.tcp_migrate_req.
diff mbox series

Message ID 20210420154140.80034-2-kuniyu@amazon.co.jp
State New
Headers show
Series
  • Socket migration for SO_REUSEPORT.
Related show

Commit Message

Kuniyuki Iwashima April 20, 2021, 3:41 p.m. UTC
This commit adds a new sysctl option: net.ipv4.tcp_migrate_req. If this
option is enabled or eBPF program is attached, we will be able to migrate
child sockets from a listener to another in the same reuseport group after
close() or shutdown() syscalls.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
---
 Documentation/networking/ip-sysctl.rst | 20 ++++++++++++++++++++
 include/net/netns/ipv4.h               |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  9 +++++++++
 3 files changed, 30 insertions(+)

Patch
diff mbox series

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index c2ecc9894fd0..8e92f9b28aad 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -732,6 +732,26 @@  tcp_syncookies - INTEGER
 	network connections you can set this knob to 2 to enable
 	unconditionally generation of syncookies.
 
+tcp_migrate_req - INTEGER
+	The incoming connection is tied to a specific listening socket when
+	the initial SYN packet is received during the three-way handshake.
+	When a listener is closed, in-flight request sockets during the
+	handshake and established sockets in the accept queue are aborted.
+
+	If the listener has SO_REUSEPORT enabled, other listeners on the
+	same port should have been able to accept such connections. This
+	option makes it possible to migrate such child sockets to another
+	listener after close() or shutdown().
+
+	Default: 0
+
+	Note that the source and destination listeners MUST have the same
+	settings at the socket API level. If different applications listen
+	on the same port, disable this option or attach the
+	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program to select
+	the correct socket by bpf_sk_select_reuseport() or to cancel
+	migration by returning SK_DROP.
+
 tcp_fastopen - INTEGER
 	Enable TCP Fast Open (RFC7413) to send and accept data in the opening
 	SYN packet.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 87e1612497ea..6402d489419d 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -136,6 +136,7 @@  struct netns_ipv4 {
 	u8 sysctl_tcp_syn_retries;
 	u8 sysctl_tcp_synack_retries;
 	u8 sysctl_tcp_syncookies;
+	u8 sysctl_tcp_migrate_req;
 	int sysctl_tcp_reordering;
 	u8 sysctl_tcp_retries1;
 	u8 sysctl_tcp_retries2;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a62934b9f15a..7bb013fcbf5f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -940,6 +940,15 @@  static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dou8vec_minmax,
 	},
 #endif
+	{
+		.procname	= "tcp_migrate_req",
+		.data		= &init_net.ipv4.sysctl_tcp_migrate_req,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
+	},
 	{
 		.procname	= "tcp_reordering",
 		.data		= &init_net.ipv4.sysctl_tcp_reordering,