net: Introduce net.ipv4.tcp_migrate_req.

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>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210612123224.12525-2-kuniyu@amazon.co.jp

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index a5c2500..b0436d3 100644 (file)
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -761,6 +761,31 @@ tcp_syncookies - INTEGER
        network connections you can set this knob to 2 to enable
        unconditionally generation of syncookies.
 
+tcp_migrate_req - BOOLEAN
+       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().
+
+       The BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program should
+       usually be used to define the policy to pick an alive listener.
+       Otherwise, the kernel will randomly pick an alive listener only if
+       this option is enabled.
+
+       Note that migration between listeners with different settings may
+       crash applications. Let's say migration happens from listener A to
+       B, and only B has TCP_SAVE_SYN enabled. B cannot read SYN data from
+       the requests migrated from A. To avoid such a situation, cancel
+       migration by returning SK_DROP in the type of eBPF program, or
+       disable this option.
+
+       Default: 0
+
 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 746c80c..b862051 100644 (file)
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -126,6 +126,7 @@ 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 4fa77f1..6f1e64d 100644 (file)
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -961,6 +961,15 @@ static struct ctl_table ipv4_net_table[] = {
        },
 #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,
                .maxlen         = sizeof(int),