bpf: Sample BPF program to set initial cwnd

Sample BPF program that assumes hosts are far away (i.e. large RTTs)
and sets initial cwnd and initial receive window to 40 packets,
send and receive buffers to 1.5MB.

In practice there would be a test to insure the hosts are actually
far enough away.

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

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 6fdf32dffa927cc885fe4f06741ce777f4858ca9..242d76e84a4b98a70c051e1f4d08fb7975cee6a8 100644 (file)
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -117,6 +117,7 @@ always += tcp_synrto_kern.o
 always += tcp_rwnd_kern.o
 always += tcp_bufs_kern.o
 always += tcp_cong_kern.o
+always += tcp_iw_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/

diff --git a/samples/bpf/tcp_iw_kern.c b/samples/bpf/tcp_iw_kern.c
new file mode 100644 (file)
index 0000000..23c5122
--- /dev/null
+++ b/samples/bpf/tcp_iw_kern.c
@@ -0,0 +1,88 @@
+/* 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.
+ *
+ * BPF program to set initial congestion window and initial receive
+ * window to 40 packets and send and receive buffers to 1.5MB. This
+ * would usually be done after doing appropriate checks that indicate
+ * the hosts are far enough away (i.e. large RTT).
+ *
+ * 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_iw(struct bpf_sock_ops *skops)
+{
+       int bufsize = 1500000;
+       int rwnd_init = 40;
+       int iw = 40;
+       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
+
+       /* Usually there would be a check to insure the hosts are far
+        * from each other so it makes sense to increase buffer sizes
+        */
+       switch (op) {
+       case BPF_SOCK_OPS_RWND_INIT:
+               rv = rwnd_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_IW, &iw,
+                                   sizeof(iw));
+               break;
+       case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+               /* Set sndbuf and rcvbuf of passive 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;
+       default:
+               rv = -1;
+       }
+#ifdef DEBUG
+       bpf_printk("Returning %d\n", rv);
+#endif
+       skops->reply = rv;
+       return 1;
+}
+char _license[] SEC("license") = "GPL";