bpf: Add tests and samples for LWT-BPF

Adds a series of tests to verify the functionality of attaching
BPF programs at LWT hooks.

Also adds a sample which collects a histogram of packet sizes which
pass through an LWT hook.

$ ./lwt_len_hist.sh
Starting netserver with host 'IN(6)ADDR_ANY' port '12865' and family AF_UNSPEC
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.253.2 () port 0 AF_INET : demo
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

 87380  16384  16384    10.00    39857.69
       1 -> 1        : 0        |                                      |
       2 -> 3        : 0        |                                      |
       4 -> 7        : 0        |                                      |
       8 -> 15       : 0        |                                      |
      16 -> 31       : 0        |                                      |
      32 -> 63       : 22       |                                      |
      64 -> 127      : 98       |                                      |
     128 -> 255      : 213      |                                      |
     256 -> 511      : 1444251  |********                              |
     512 -> 1023     : 660610   |***                                   |
    1024 -> 2047     : 535241   |**                                    |
    2048 -> 4095     : 19       |                                      |
    4096 -> 8191     : 180      |                                      |
    8192 -> 16383    : 5578023  |************************************* |
   16384 -> 32767    : 632099   |***                                   |
   32768 -> 65535    : 6575     |                                      |

Signed-off-by: Thomas Graf <[email protected]>
Acked-by: Alexei Starovoitov <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

samples/bpf/Makefile

@@ -29,6 +29,7 @@ hostprogs-y += test_current_task_under_cgroup
 hostprogs-y += trace_event
 hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
+hostprogs-y += lwt_len_hist
 
 test_lru_dist-objs := test_lru_dist.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
@@ -59,6 +60,7 @@ test_current_task_under_cgroup-objs := bpf_load.o libbpf.o \
 trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
 sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
+lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -89,6 +91,7 @@ always += xdp2_kern.o
 always += test_current_task_under_cgroup_kern.o
 always += trace_event_kern.o
 always += sampleip_kern.o
+always += lwt_len_hist_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
@@ -117,6 +120,7 @@ HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
 HOSTLOADLIBES_trace_event += -lelf
 HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
+HOSTLOADLIBES_lwt_len_hist += -l elf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang

samples/bpf/bpf_helpers.h

@@ -80,6 +80,8 @@ struct bpf_map_def {
 	unsigned int map_flags;
 };
 
+static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
+	(void *) BPF_FUNC_skb_load_bytes;
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
 	(void *) BPF_FUNC_skb_store_bytes;
 static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
@@ -88,6 +90,8 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag
 	(void *) BPF_FUNC_l4_csum_replace;
 static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
 	(void *) BPF_FUNC_skb_under_cgroup;
+static int (*bpf_skb_change_head)(void *, int len, int flags) =
+	(void *) BPF_FUNC_skb_change_head;
 
 #if defined(__x86_64__)
 

samples/bpf/lwt_len_hist.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+NS1=lwt_ns1
+VETH0=tst_lwt1a
+VETH1=tst_lwt1b
+
+TRACE_ROOT=/sys/kernel/debug/tracing
+
+function cleanup {
+	ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null
+	ip link del $VETH0 2> /dev/null
+	ip link del $VETH1 2> /dev/null
+	ip netns exec $NS1 killall netserver
+	ip netns delete $NS1 2> /dev/null
+}
+
+cleanup
+
+ip netns add $NS1
+ip link add $VETH0 type veth peer name $VETH1
+ip link set dev $VETH0 up
+ip addr add 192.168.253.1/24 dev $VETH0
+ip link set $VETH1 netns $NS1
+ip netns exec $NS1 ip link set dev $VETH1 up
+ip netns exec $NS1 ip addr add 192.168.253.2/24 dev $VETH1
+ip netns exec $NS1 netserver
+
+echo 1 > ${TRACE_ROOT}/tracing_on
+cp /dev/null ${TRACE_ROOT}/trace
+ip route add 192.168.253.2/32 encap bpf out obj lwt_len_hist_kern.o section len_hist dev $VETH0
+netperf -H 192.168.253.2 -t TCP_STREAM
+cat ${TRACE_ROOT}/trace | grep -v '^#'
+./lwt_len_hist
+cleanup
+echo 0 > ${TRACE_ROOT}/tracing_on
+
+exit 0

samples/bpf/lwt_len_hist_kern.c

@@ -0,0 +1,82 @@
+/* Copyright (c) 2016 Thomas Graf <[email protected]>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/in.h>
+#include "bpf_helpers.h"
+
+# define printk(fmt, ...)						\
+		({							\
+			char ____fmt[] = fmt;				\
+			bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				     ##__VA_ARGS__);			\
+		})
+
+struct bpf_elf_map {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+	__u32 id;
+	__u32 pinning;
+};
+
+struct bpf_elf_map SEC("maps") lwt_len_hist_map = {
+	.type = BPF_MAP_TYPE_PERCPU_HASH,
+	.size_key = sizeof(__u64),
+	.size_value = sizeof(__u64),
+	.pinning = 2,
+	.max_elem = 1024,
+};
+
+static unsigned int log2(unsigned int v)
+{
+	unsigned int r;
+	unsigned int shift;
+
+	r = (v > 0xFFFF) << 4; v >>= r;
+	shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+	shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+	shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+	r |= (v >> 1);
+	return r;
+}
+
+static unsigned int log2l(unsigned long v)
+{
+	unsigned int hi = v >> 32;
+	if (hi)
+		return log2(hi) + 32;
+	else
+		return log2(v);
+}
+
+SEC("len_hist")
+int do_len_hist(struct __sk_buff *skb)
+{
+	__u64 *value, key, init_val = 1;
+
+	key = log2l(skb->len);
+
+	value = bpf_map_lookup_elem(&lwt_len_hist_map, &key);
+	if (value)
+		__sync_fetch_and_add(value, 1);
+	else
+		bpf_map_update_elem(&lwt_len_hist_map, &key, &init_val, BPF_ANY);
+
+	return BPF_OK;
+}
+
+char _license[] SEC("license") = "GPL";

samples/bpf/lwt_len_hist_user.c

@@ -0,0 +1,76 @@
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <arpa/inet.h>
+
+#include "libbpf.h"
+#include "bpf_util.h"
+
+#define MAX_INDEX 64
+#define MAX_STARS 38
+
+static void stars(char *str, long val, long max, int width)
+{
+	int i;
+
+	for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++)
+		str[i] = '*';
+	if (val > max)
+		str[i - 1] = '+';
+	str[i] = '\0';
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	const char *map_filename = "/sys/fs/bpf/tc/globals/lwt_len_hist_map";
+	uint64_t values[nr_cpus], sum, max_value = 0, data[MAX_INDEX] = {};
+	uint64_t key = 0, next_key, max_key = 0;
+	char starstr[MAX_STARS];
+	int i, map_fd;
+
+	map_fd = bpf_obj_get(map_filename);
+	if (map_fd < 0) {
+		fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+			map_filename, strerror(errno), errno);
+		return -1;
+	}
+
+	while (bpf_get_next_key(map_fd, &key, &next_key) == 0) {
+		if (next_key >= MAX_INDEX) {
+			fprintf(stderr, "Key %lu out of bounds\n", next_key);
+			continue;
+		}
+
+		bpf_lookup_elem(map_fd, &next_key, values);
+
+		sum = 0;
+		for (i = 0; i < nr_cpus; i++)
+			sum += values[i];
+
+		data[next_key] = sum;
+		if (sum && next_key > max_key)
+			max_key = next_key;
+
+		if (sum > max_value)
+			max_value = sum;
+
+		key = next_key;
+	}
+
+	for (i = 1; i <= max_key + 1; i++) {
+		stars(starstr, data[i - 1], max_value, MAX_STARS);
+		printf("%8ld -> %-8ld : %-8ld |%-*s|\n",
+		       (1l << i) >> 1, (1l << i) - 1, data[i - 1],
+		       MAX_STARS, starstr);
+	}
+
+	close(map_fd);
+
+	return 0;
+}