bpf: BPF based latency tracing

BPF offers another way to generate latency histograms. We attach
kprobes at trace_preempt_off and trace_preempt_on and calculate the
time it takes to from seeing the off/on transition.

The first array is used to store the start time stamp. The key is the
CPU id. The second array stores the log2(time diff). We need to use
static allocation here (array and not hash tables). The kprobes
hooking into trace_preempt_on|off should not calling any dynamic
memory allocation or free path. We need to avoid recursivly
getting called. Besides that, it reduces jitter in the measurement.

CPU 0
      latency        : count     distribution
       1 -> 1        : 0        |                                        |
       2 -> 3        : 0        |                                        |
       4 -> 7        : 0        |                                        |
       8 -> 15       : 0        |                                        |
      16 -> 31       : 0        |                                        |
      32 -> 63       : 0        |                                        |
      64 -> 127      : 0        |                                        |
     128 -> 255      : 0        |                                        |
     256 -> 511      : 0        |                                        |
     512 -> 1023     : 0        |                                        |
    1024 -> 2047     : 0        |                                        |
    2048 -> 4095     : 166723   |*************************************** |
    4096 -> 8191     : 19870    |***                                     |
    8192 -> 16383    : 6324     |                                        |
   16384 -> 32767    : 1098     |                                        |
   32768 -> 65535    : 190      |                                        |
   65536 -> 131071   : 179      |                                        |
  131072 -> 262143   : 18       |                                        |
  262144 -> 524287   : 4        |                                        |
  524288 -> 1048575  : 1363     |                                        |
CPU 1
      latency        : count     distribution
       1 -> 1        : 0        |                                        |
       2 -> 3        : 0        |                                        |
       4 -> 7        : 0        |                                        |
       8 -> 15       : 0        |                                        |
      16 -> 31       : 0        |                                        |
      32 -> 63       : 0        |                                        |
      64 -> 127      : 0        |                                        |
     128 -> 255      : 0        |                                        |
     256 -> 511      : 0        |                                        |
     512 -> 1023     : 0        |                                        |
    1024 -> 2047     : 0        |                                        |
    2048 -> 4095     : 114042   |*************************************** |
    4096 -> 8191     : 9587     |**                                      |
    8192 -> 16383    : 4140     |                                        |
   16384 -> 32767    : 673      |                                        |
   32768 -> 65535    : 179      |                                        |
   65536 -> 131071   : 29       |                                        |
  131072 -> 262143   : 4        |                                        |
  262144 -> 524287   : 1        |                                        |
  524288 -> 1048575  : 364      |                                        |
CPU 2
      latency        : count     distribution
       1 -> 1        : 0        |                                        |
       2 -> 3        : 0        |                                        |
       4 -> 7        : 0        |                                        |
       8 -> 15       : 0        |                                        |
      16 -> 31       : 0        |                                        |
      32 -> 63       : 0        |                                        |
      64 -> 127      : 0        |                                        |
     128 -> 255      : 0        |                                        |
     256 -> 511      : 0        |                                        |
     512 -> 1023     : 0        |                                        |
    1024 -> 2047     : 0        |                                        |
    2048 -> 4095     : 40147    |*************************************** |
    4096 -> 8191     : 2300     |*                                       |
    8192 -> 16383    : 828      |                                        |
   16384 -> 32767    : 178      |                                        |
   32768 -> 65535    : 59       |                                        |
   65536 -> 131071   : 2        |                                        |
  131072 -> 262143   : 0        |                                        |
  262144 -> 524287   : 1        |                                        |
  524288 -> 1048575  : 174      |                                        |
CPU 3
      latency        : count     distribution
       1 -> 1        : 0        |                                        |
       2 -> 3        : 0        |                                        |
       4 -> 7        : 0        |                                        |
       8 -> 15       : 0        |                                        |
      16 -> 31       : 0        |                                        |
      32 -> 63       : 0        |                                        |
      64 -> 127      : 0        |                                        |
     128 -> 255      : 0        |                                        |
     256 -> 511      : 0        |                                        |
     512 -> 1023     : 0        |                                        |
    1024 -> 2047     : 0        |                                        |
    2048 -> 4095     : 29626    |*************************************** |
    4096 -> 8191     : 2704     |**                                      |
    8192 -> 16383    : 1090     |                                        |
   16384 -> 32767    : 160      |                                        |
   32768 -> 65535    : 72       |                                        |
   65536 -> 131071   : 32       |                                        |
  131072 -> 262143   : 26       |                                        |
  262144 -> 524287   : 12       |                                        |
  524288 -> 1048575  : 298      |                                        |

All this is based on the trace3 examples written by
Alexei Starovoitov <ast@plumgrid.com>.

Signed-off-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 99 insertions, 0 deletions

diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c
new file mode 100644
index 000000000000..18fa088473cd
--- /dev/null
+++ b/samples/bpf/lathist_kern.c
@@ -0,0 +1,99 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2015 BMW Car IT GmbH
+ *
+ * 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.
+ */
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define MAX_ENTRIES	20
+#define MAX_CPU		4
+
+/* We need to stick to static allocated memory (an array instead of
+ * hash table) because managing dynamic memory from the
+ * trace_preempt_[on|off] tracepoints hooks is not supported.
+ */
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u64),
+	.max_entries = MAX_CPU,
+};
+
+SEC("kprobe/trace_preempt_off")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	int cpu = bpf_get_smp_processor_id();
+	u64 *ts = bpf_map_lookup_elem(&my_map, &cpu);
+
+	if (ts)
+		*ts = bpf_ktime_get_ns();
+
+	return 0;
+}
+
+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);
+}
+
+struct bpf_map_def SEC("maps") my_lat = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(long),
+	.max_entries = MAX_CPU * MAX_ENTRIES,
+};
+
+SEC("kprobe/trace_preempt_on")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	u64 *ts, cur_ts, delta;
+	int key, cpu;
+	long *val;
+
+	cpu = bpf_get_smp_processor_id();
+	ts = bpf_map_lookup_elem(&my_map, &cpu);
+	if (!ts)
+		return 0;
+
+	cur_ts = bpf_ktime_get_ns();
+	delta = log2l(cur_ts - *ts);
+
+	if (delta > MAX_ENTRIES - 1)
+		delta = MAX_ENTRIES - 1;
+
+	key = cpu * MAX_ENTRIES + delta;
+	val = bpf_map_lookup_elem(&my_lat, &key);
+	if (val)
+		__sync_fetch_and_add((long *)val, 1);
+
+	return 0;
+
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;