All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lawrence Brakmo <brakmo@fb.com>
To: netdev <netdev@vger.kernel.org>
Cc: Kernel Team <kernel-team@fb.com>, Blake Matheny <bmatheny@fb.com>,
	Alexei Starovoitov <ast@fb.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	David Ahern <dsa@cumulusnetworks.com>
Subject: [PATCH net-next v3 09/15] bpf: Sample BPF program to set buffer sizes
Date: Mon, 19 Jun 2017 20:00:42 -0700	[thread overview]
Message-ID: <20170620030048.3275347-10-brakmo@fb.com> (raw)
In-Reply-To: <20170620030048.3275347-1-brakmo@fb.com>

This patch contains a BPF program to set 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).

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 samples/bpf/Makefile        |  1 +
 samples/bpf/tcp_bufs_kern.c | 76 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)
 create mode 100644 samples/bpf/tcp_bufs_kern.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 9aca209..942c7c7 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -115,6 +115,7 @@ always += test_map_in_map_kern.o
 always += cookie_uid_helper_example.o
 always += tcp_synrto_kern.o
 always += tcp_rwnd_kern.o
+always += tcp_bufs_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
diff --git a/samples/bpf/tcp_bufs_kern.c b/samples/bpf/tcp_bufs_kern.c
new file mode 100644
index 0000000..6cc096c
--- /dev/null
+++ b/samples/bpf/tcp_bufs_kern.c
@@ -0,0 +1,76 @@
+/* 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 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_bufs(struct bpf_sock_ops *skops)
+{
+	char fmt1[] = "BPF command: %d\n";
+	char fmt2[] = "  Returning %d\n";
+	int bufsize = 1500000;
+	int rwnd_init = 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_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:
+		/* Nothing to do */
+		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_trace_printk(fmt2, sizeof(fmt2), rv);
+#endif
+	return rv;
+}
+char _license[] SEC("license") = "GPL";
-- 
2.9.3

  parent reply	other threads:[~2017-06-20  3:00 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-20  3:00 PATCH net-next v3 00/15 Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 01/15] bpf: BPF support for sock_ops Lawrence Brakmo
2017-06-22 22:41   ` Daniel Borkmann
2017-06-22 22:58     ` Lawrence Brakmo
2017-06-22 23:19       ` Daniel Borkmann
2017-06-22 23:57         ` Lawrence Brakmo
2017-06-23 21:15           ` Daniel Borkmann
2017-06-28 17:45             ` Lawrence Brakmo
2017-06-29  9:47               ` Daniel Borkmann
2017-06-20  3:00 ` [PATCH net-next v3 02/15] bpf: program to load sock_ops BPF programs Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 03/15] bpf: Support for per connection SYN/SYN-ACK RTOs Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 04/15] bpf: Sample bpf program to set " Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 05/15] bpf: Support for setting initial receive window Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 06/15] bpf: Sample bpf program to set initial window Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 07/15] bpf: Add setsockopt helper function to bpf Lawrence Brakmo
2017-06-20 21:25   ` Craig Gallek
2017-06-21 16:51     ` Lawrence Brakmo
2017-06-21 17:13       ` Craig Gallek
2017-06-21 23:55         ` Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 08/15] bpf: Add TCP connection BPF callbacks Lawrence Brakmo
2017-06-20  3:00 ` Lawrence Brakmo [this message]
2017-06-20  3:00 ` [PATCH net-next v3 10/15] bpf: Add support for changing congestion control Lawrence Brakmo
2017-06-20  8:40   ` kbuild test robot
2017-06-20  3:00 ` [PATCH net-next v3 11/15] bpf: Sample BPF program to set " Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 12/15] bpf: Adds support for setting initial cwnd Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 13/15] bpf: Sample BPF program to set " Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 14/15] bpf: Adds support for setting sndcwnd clamp Lawrence Brakmo
2017-06-20  3:00 ` [PATCH net-next v3 15/15] bpf: Sample bpf program to set " Lawrence Brakmo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170620030048.3275347-10-brakmo@fb.com \
    --to=brakmo@fb.com \
    --cc=ast@fb.com \
    --cc=bmatheny@fb.com \
    --cc=daniel@iogearbox.net \
    --cc=dsa@cumulusnetworks.com \
    --cc=kernel-team@fb.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.