bpf: Sample bpf program to set sndcwnd clamp

Sample BPF program, tcp_clamp_kern.c, to demostrate the use
of setting the sndcwnd clamp. This program assumes that if the
first 5.5 bytes of the host's IPv6 addresses are the same, then
the hosts are in the same datacenter and sets sndcwnd clamp to
100 packets, SYN and SYN-ACK RTOs to 10ms and send/receive buffer
sizes to 150KB.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 103 insertions, 0 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 242d76e84a4b..9c650589e80f 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -118,6 +118,7 @@ always += tcp_rwnd_kern.o
 always += tcp_bufs_kern.o
 always += tcp_cong_kern.o
 always += tcp_iw_kern.o
+always += tcp_clamp_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
diff --git a/samples/bpf/tcp_clamp_kern.c b/samples/bpf/tcp_clamp_kern.c
new file mode 100644
index 000000000000..d68eadd9ca2d
--- /dev/null
+++ b/samples/bpf/tcp_clamp_kern.c
@@ -0,0 +1,102 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * Sample BPF program to set send and receive buffers to 150KB, sndcwnd clamp
+ * to 100 packets and SYN and SYN_ACK RTOs to 10ms when both hosts are within
+ * the same datacenter. For his example, we assume they are within the same
+ * datacenter when the first 5.5 bytes of their IPv6 addresses are the same.
+ *
+ * Use load_sock_ops to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define DEBUG 1
+
+#define bpf_printk(fmt, ...)                                    \
+({                                                              \
+               char ____fmt[] = fmt;                            \
+               bpf_trace_printk(____fmt, sizeof(____fmt),       \
+                                ##__VA_ARGS__);                 \
+})
+
+SEC("sockops")
+int bpf_clamp(struct bpf_sock_ops *skops)
+{
+        int bufsize = 150000;
+        int to_init = 10;
+        int clamp = 100;
+        int rv = 0;
+        int op;
+
+        /* For testing purposes, only execute rest of BPF program
+         * if neither port numberis 55601
+         */
+        if (bpf_ntohl(skops->remote_port) != 55601 && skops->local_port != 55601)
+                return -1;
+
+        op = (int) skops->op;
+
+#ifdef DEBUG
+        bpf_printk("BPF command: %d\n", op);
+#endif
+
+        /* Check that both hosts are within same datacenter. For this example
+         * it is the case when the first 5.5 bytes of their IPv6 addresses are
+         * the same.
+         */
+        if (skops->family == AF_INET6 &&
+            skops->local_ip6[0] == skops->remote_ip6[0] &&
+            (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+            (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+                switch (op) {
+                case BPF_SOCK_OPS_TIMEOUT_INIT:
+                        rv = to_init;
+                        break;
+                case BPF_SOCK_OPS_TCP_CONNECT_CB:
+                        /* Set sndbuf and rcvbuf of active connections */
+                        rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF,
+                                            &bufsize, sizeof(bufsize));
+                        rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+                                                      SO_RCVBUF, &bufsize,
+                                                      sizeof(bufsize));
+                        break;
+                case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+                        rv = bpf_setsockopt(skops, SOL_TCP,
+                                            TCP_BPF_SNDCWND_CLAMP,
+                                            &clamp, sizeof(clamp));
+                        break;
+                case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+                        /* Set sndbuf and rcvbuf of passive connections */
+                        rv = bpf_setsockopt(skops, SOL_TCP,
+                                            TCP_BPF_SNDCWND_CLAMP,
+                                            &clamp, sizeof(clamp));
+                        rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+                                                      SO_SNDBUF, &bufsize,
+                                                      sizeof(bufsize));
+                        rv = rv*100 + bpf_setsockopt(skops, SOL_SOCKET,
+                                                      SO_RCVBUF, &bufsize,
+                                                      sizeof(bufsize));
+                        break;
+                default:
+                        rv = -1;
+                }
+        } else {
+                rv = -1;
+        }
+#ifdef DEBUG
+        bpf_printk("Returning %d\n", rv);
+#endif
+        skops->reply = rv;
+        return 1;
+}
+char _license[] SEC("license") = "GPL";