This commit adds a new sysctl option: net.ipv4.tcp_migrate_req. If this
option is enabled, and then we call listen() for SO_REUSEPORT enabled
sockets and close one, we will be able to migrate its child sockets to
another listener.
Reviewed-by: Benjamin Herrenschmidt <b...@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kun...@amazon.co.jp>
---
Documentation/networking/ip-sysctl.rst | 15 +++++++++++++++
include/net/netns/ipv4.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 9 +++++++++
3 files changed, 25 insertions(+)
diff --git a/Documentation/networking/ip-sysctl.rst
b/Documentation/networking/ip-sysctl.rst
index dd2b12a32b73..4116771bf5ef 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -712,6 +712,21 @@ tcp_syncookies - INTEGER
network connections you can set this knob to 2 to enable
unconditionally generation of syncookies.
+tcp_migrate_req - INTEGER
+ By default, when a listening socket is closed, child sockets are also
+ closed. If it has SO_REUSEPORT enabled, the dropped connections should
+ have been accepted by other listeners on the same port. This option
+ makes it possible to migrate child sockets to another listener when
+ calling close() or shutdown().
+
+ Default: 0
+
+ Note that the source and destination listeners _must_ have the same
+ settings at the socket API level. If there are different kinds of
+ sockets on the port, disable this option or use
+ BPF_PROG_TYPE_SK_REUSEPORT 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 8e4fcac4df72..a3edc30d6a63 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -132,6 +132,7 @@ struct netns_ipv4 {
int sysctl_tcp_syn_retries;
int sysctl_tcp_synack_retries;
int sysctl_tcp_syncookies;
+ int sysctl_tcp_migrate_req;
int sysctl_tcp_reordering;
int sysctl_tcp_retries1;
int sysctl_tcp_retries2;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3e5f4f2e705e..6b76298fa271 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -933,6 +933,15 @@ static struct ctl_table ipv4_net_table[] = {
.proc_handler = proc_dointvec
},
#endif
+ {
+ .procname = "tcp_migrate_req",
+ .data = &init_net.ipv4.sysctl_tcp_migrate_req,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
+ },
{
.procname = "tcp_reordering",
.data = &init_net.ipv4.sysctl_tcp_reordering,
--
2.17.2 (Apple Git-113)
