diff mbox

[RFC,net-next,v2,13/15] bpf: Sample BPF program to set initial cwnd

Message ID 20170615200844.2752485-14-brakmo@fb.com
State RFC, archived
Delegated to: David Miller
Headers show

Commit Message

Lawrence Brakmo June 15, 2017, 8:08 p.m. UTC 
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>
---
 samples/bpf/Makefile      |  1 +
 samples/bpf/tcp_iw_kern.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)
 create mode 100644 samples/bpf/tcp_iw_kern.c
diff mbox

Patch

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index eb324e0..3ec96a0 100644
--- 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
index 0000000..07962c8
--- /dev/null
+++ b/samples/bpf/tcp_iw_kern.c
@@ -0,0 +1,73 @@ 
+/*
+ * 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).
+ */
+
+#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"
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_iw(struct bpf_socket_ops *skops)
+{
+	char fmt1[] = "BPF command: %d\n";
+	char fmt2[] = "  Returning %d\n";
+	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 (skops->remote_port != 55601 && skops->local_port != 55601)
+		return -1;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_trace_printk(fmt1, sizeof(fmt1), 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_SOCKET_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCKET_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_SOCKET_OPS_ACTIVE_ESTABLISHED_CB:
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_BPF_IW, &iw,
+				    sizeof(iw));
+		break;
+	case BPF_SOCKET_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_trace_printk(fmt2, sizeof(fmt2), rv);
+#endif
+	return rv;
+}
+char _license[] SEC("license") = "GPL";