This example samples the instruction pointer at a timed interval, and
frequency counts it in a BPF map. It is an example of summarizing sampled
data in-kernel for passing to user space. It uses the perf:perf_hrtimer
tracepoint with perf_events sampling.

Example output:

Sampling at 99 Hertz for 5 seconds. Ctrl-C also ends.
ADDR                KSYM                             COUNT
0xffffffff81257088  __fsnotify_parent                1
0x7f20b792d9b0      (user)                           1
0xffffffff8121469e  __vfs_read                       1
0xffffffff81214afd  rw_verify_area                   1
0xffffffff8123327e  __fget_light                     1
0x7fc0965a6e2c      (user)                           1
0xffffffff81233c04  __fdget_pos                      1
0xffffffff81378528  common_file_perm                 1
0x404d90            (user)                           1
0xffffffff81214c13  vfs_read                         1
[...]
0xffffffff813d9e97  copy_user_enhanced_fast_string   3
0xffffffff817e310c  _raw_spin_lock_irqsave           4
0xffffffff817e31a0  entry_SYSCALL_64_fastpath        4
0xffffffff814fb96c  extract_crng                     6
0xffffffff813d9e95  copy_user_enhanced_fast_string   7
0xffffffff814fb8a3  _extract_crng                    7
0xffffffff817e2d55  _raw_spin_unlock_irqrestore      1399
0xffffffff8105fb46  native_safe_halt                 2190

It also has basic options:

USAGE: sampleip [-F freq] [duration]
       -F freq    # sample frequency (Hertz), default 99
       duration   # sampling duration (seconds), default 5

Signed-off-by: Brendan Gregg <bgr...@netflix.com>
Cc: Alexei Starovoitov <a...@kernel.org>
Cc: Wang Nan <wangn...@huawei.com>
---
 samples/bpf/Makefile        |   4 +
 samples/bpf/sampleip_kern.c |  48 +++++++++++
 samples/bpf/sampleip_user.c | 189 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 241 insertions(+)
 create mode 100644 samples/bpf/sampleip_kern.c
 create mode 100644 samples/bpf/sampleip_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 90ebf7d..dc88a1e 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -24,6 +24,7 @@ hostprogs-y += test_overhead
 hostprogs-y += test_cgrp2_array_pin
 hostprogs-y += xdp1
 hostprogs-y += xdp2
+hostprogs-y += sampleip
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -49,6 +50,7 @@ test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
 xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
 # reuse xdp1 source intentionally
 xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
+sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -74,6 +76,7 @@ always += parse_varlen.o parse_simple.o parse_ldabs.o
 always += test_cgrp2_tc_kern.o
 always += xdp1_kern.o
 always += xdp2_kern.o
+always += sampleip_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
@@ -97,6 +100,7 @@ HOSTLOADLIBES_map_perf_test += -lelf -lrt
 HOSTLOADLIBES_test_overhead += -lelf -lrt
 HOSTLOADLIBES_xdp1 += -lelf
 HOSTLOADLIBES_xdp2 += -lelf
+HOSTLOADLIBES_sampleip += -lelf
 
 # 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
diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c
new file mode 100644
index 0000000..afec3fe
--- /dev/null
+++ b/samples/bpf/sampleip_kern.c
@@ -0,0 +1,48 @@
+/* Copyright 2016 Netflix, Inc.
+ *
+ * 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 <uapi/linux/bpf.h>
+#include <linux/ptrace.h>
+#include "bpf_helpers.h"
+
+#define MAX_IPS                8192
+
+#define _(P) ({typeof(P) val; bpf_probe_read(&val, sizeof(val), &P); val;})
+
+struct bpf_map_def SEC("maps") ip_map = {
+       .type = BPF_MAP_TYPE_HASH,
+       .key_size = sizeof(u64),
+       .value_size = sizeof(u32),
+       .max_entries = MAX_IPS,
+};
+
+/* from /sys/kernel/debug/tracing/events/perf/perf_hrtimer/format */
+struct perf_hrtimer_args {
+       unsigned long long pad;
+       struct pt_regs *regs;
+       struct perf_event *event;
+};
+SEC("tracepoint/perf/perf_hrtimer")
+int do_sample(struct perf_hrtimer_args *args)
+{
+       struct pt_regs *regs;
+       u64 ip;
+       u32 *value, init_val = 1;
+
+       regs = _(args->regs);
+       ip = _(regs->ip);
+       value = bpf_map_lookup_elem(&ip_map, &ip);
+       if (value)
+               *value += 1;
+       else
+               /* E2BIG not tested for this example only */
+               bpf_map_update_elem(&ip_map, &ip, &init_val, BPF_ANY);
+
+       return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
new file mode 100644
index 0000000..da0727d
--- /dev/null
+++ b/samples/bpf/sampleip_user.c
@@ -0,0 +1,189 @@
+/*
+ * sampleip: sample instruction pointer and frequency count in a BPF map.
+ *
+ * Copyright 2016 Netflix, Inc.
+ *
+ * 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 <stdio.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define DEFAULT_FREQ   99
+#define DEFAULT_SECS   5
+#define MAX_IPS                8192
+#define PAGE_OFFSET    0xffff880000000000
+
+static int nr_cpus;
+
+static void usage(void)
+{
+       printf("USAGE: sampleip [-F freq] [duration]\n");
+       printf("       -F freq    # sample frequency (Hertz), default 99\n");
+       printf("       duration   # sampling duration (seconds), default 5\n");
+}
+
+static int sampling_start(int *pmu_fd, int freq)
+{
+       int i;
+
+       struct perf_event_attr pe_sample_attr = {
+               .type = PERF_TYPE_SOFTWARE,
+               .freq = 1,
+               .sample_period = freq,
+       };
+
+       for (i = 0; i < nr_cpus; i++) {
+               pmu_fd[i] = perf_event_open(&pe_sample_attr, -1 /* pid */, i,
+                                           -1 /* group_fd */, 0 /* flags */);
+               if (pmu_fd[i] < 0) {
+                       fprintf(stderr, "ERROR: Initializing perf sampling\n");
+                       return 1;
+               }
+       }
+
+       return 0;
+}
+
+static void sampling_end(int *pmu_fd)
+{
+       int i;
+
+       for (i = 0; i < nr_cpus; i++)
+               close(pmu_fd[i]);
+}
+
+struct ipcount {
+       __u64 ip;
+       __u32 count;
+};
+
+/* used for sorting */
+struct ipcount counts[MAX_IPS];
+
+static int count_cmp(const void *p1, const void *p2)
+{
+       return ((struct ipcount *)p1)->count - ((struct ipcount *)p2)->count;
+}
+
+static void print_ip_map(int fd)
+{
+       struct ksym *sym;
+       __u64 key, next_key;
+       __u32 value;
+       int i, max;
+
+       printf("%-19s %-32s %s\n", "ADDR", "KSYM", "COUNT");
+
+       /* fetch IPs and counts */
+       key = 0, i = 0;
+       while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+               bpf_lookup_elem(fd, &next_key, &value);
+               counts[i].ip = next_key;
+               counts[i++].count = value;
+               key = next_key;
+       }
+       max = i;
+
+       /* sort and print */
+       qsort(counts, max, sizeof(struct ipcount), count_cmp);
+       for (i = 0; i < max; i++) {
+               if (counts[i].ip > PAGE_OFFSET) {
+                       sym = ksym_search(counts[i].ip);
+                       printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name,
+                              counts[i].count);
+               } else {
+                       printf("0x%-17llx %-32s %u\n", counts[i].ip, "(user)",
+                              counts[i].count);
+               }
+       }
+
+       if (max == MAX_IPS) {
+               printf("WARNING: IP hash was full (max %d entries); ", max);
+               printf("may have dropped samples\n");
+       }
+}
+
+static void int_exit(int sig)
+{
+       printf("\n");
+       print_ip_map(map_fd[0]);
+       exit(0);
+}
+
+int main(int argc, char **argv)
+{
+       char filename[256];
+       int *pmu_fd, opt, freq = DEFAULT_FREQ, secs = DEFAULT_SECS;
+
+       /* process arguments */
+       while ((opt = getopt(argc, argv, "F:h")) != -1) {
+               switch (opt) {
+               case 'F':
+                       freq = atoi(optarg);
+                       break;
+               case 'h':
+               default:
+                       usage();
+                       return 0;
+               }
+       }
+       if (argc - optind == 1)
+               secs = atoi(argv[optind]);
+       if (freq == 0 || secs == 0) {
+               usage();
+               return 1;
+       }
+
+       /* initialize kernel symbol translation */
+       if (load_kallsyms()) {
+               fprintf(stderr, "ERROR: loading /proc/kallsyms\n");
+               return 2;
+       }
+
+       /* create perf FDs for each CPU */
+       nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+       pmu_fd = malloc(nr_cpus * sizeof(int));
+       if (pmu_fd == NULL) {
+               fprintf(stderr, "ERROR: malloc of pmu_fd\n");
+               return 1;
+       }
+
+       /* load BPF program */
+       snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+       if (load_bpf_file(filename)) {
+               fprintf(stderr, "ERROR: loading BPF program (errno %d):\n",
+                       errno);
+               if (strcmp(bpf_log_buf, "") == 0)
+                       fprintf(stderr, "Try: ulimit -l unlimited\n");
+               else
+                       fprintf(stderr, "%s", bpf_log_buf);
+               return 1;
+       }
+       signal(SIGINT, int_exit);
+
+       /* do sampling */
+       printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n",
+              freq, secs);
+       if (sampling_start(pmu_fd, freq) != 0)
+               return 1;
+       sleep(secs);
+       sampling_end(pmu_fd);
+       free(pmu_fd);
+
+       /* output sample counts */
+       print_ip_map(map_fd[0]);
+
+       return 0;
+}
-- 
2.7.4

Reply via email to