Merge branch 'bpf-perf-hw-sw-events'

Alexei Starovoitov says:

====================
perf, bpf: add support for bpf in sw/hw perf_events

this patch set is a follow up to the discussion:
https://lkml.kernel.org/r/20160804142853.GO6862%20()%20twins%20!%20programming%20!%20kicks-ass%20!%20net
It turned out to be simpler than what we discussed.

Patches 1-3 is bpf-side prep for the main patch 4
that adds bpf program as an overflow_handler to sw and hw perf_events.

Patches 5 and 6 are examples from myself and Brendan.

Peter,
to implement your suggestion to add ifdef CONFIG_BPF_SYSCALL
inside struct perf_event, I had to shuffle ifdefs in events/core.c
Please double check whether that is what you wanted to see.

v2->v3: fixed few more minor issues
v1->v2: fixed issues spotted by Peter and Daniel.
====================

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf.h

@@ -297,6 +297,10 @@ static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
 static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
+static inline struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 /* verifier prototypes for helper functions called from eBPF programs */

include/linux/perf_event.h

@@ -679,6 +679,10 @@ struct perf_event {
 	u64				(*clock)(void);
 	perf_overflow_handler_t		overflow_handler;
 	void				*overflow_handler_context;
+#ifdef CONFIG_BPF_SYSCALL
+	perf_overflow_handler_t		orig_overflow_handler;
+	struct bpf_prog			*prog;
+#endif
 
 #ifdef CONFIG_EVENT_TRACING
 	struct trace_event_call		*tp_event;
@@ -788,6 +792,11 @@ struct perf_output_handle {
 	int				page;
 };
 
+struct bpf_perf_event_data_kern {
+	struct pt_regs *regs;
+	struct perf_sample_data *data;
+};
+
 #ifdef CONFIG_CGROUP_PERF
 
 /*

include/uapi/linux/Kbuild

@@ -71,6 +71,7 @@ header-y += binfmts.h
 header-y += blkpg.h
 header-y += blktrace_api.h
 header-y += bpf_common.h
+header-y += bpf_perf_event.h
 header-y += bpf.h
 header-y += bpqether.h
 header-y += bsg.h

include/uapi/linux/bpf.h

@@ -95,6 +95,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SCHED_ACT,
 	BPF_PROG_TYPE_TRACEPOINT,
 	BPF_PROG_TYPE_XDP,
+	BPF_PROG_TYPE_PERF_EVENT,
 };
 
 #define BPF_PSEUDO_MAP_FD	1

include/uapi/linux/bpf_perf_event.h

@@ -0,0 +1,18 @@
+/* Copyright (c) 2016 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.
+ */
+#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
+#define _UAPI__LINUX_BPF_PERF_EVENT_H__
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+struct bpf_perf_event_data {
+	struct pt_regs regs;
+	__u64 sample_period;
+};
+
+#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */

kernel/bpf/verifier.c

@@ -2333,7 +2333,8 @@ static int do_check(struct verifier_env *env)
 			if (err)
 				return err;
 
-			if (BPF_SIZE(insn->code) != BPF_W) {
+			if (BPF_SIZE(insn->code) != BPF_W &&
+			    BPF_SIZE(insn->code) != BPF_DW) {
 				insn_idx++;
 				continue;
 			}
@@ -2510,6 +2511,20 @@ process_bpf_exit:
 	return 0;
 }
 
+static int check_map_prog_compatibility(struct bpf_map *map,
+					struct bpf_prog *prog)
+
+{
+	if (prog->type == BPF_PROG_TYPE_PERF_EVENT &&
+	    (map->map_type == BPF_MAP_TYPE_HASH ||
+	     map->map_type == BPF_MAP_TYPE_PERCPU_HASH) &&
+	    (map->map_flags & BPF_F_NO_PREALLOC)) {
+		verbose("perf_event programs can only use preallocated hash map\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* look for pseudo eBPF instructions that access map FDs and
  * replace them with actual map pointers
  */
@@ -2517,7 +2532,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 {
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
-	int i, j;
+	int i, j, err;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		if (BPF_CLASS(insn->code) == BPF_LDX &&
@@ -2561,6 +2576,12 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return PTR_ERR(map);
 			}
 
+			err = check_map_prog_compatibility(map, env->prog);
+			if (err) {
+				fdput(f);
+				return err;
+			}
+
 			/* store map pointer inside BPF_LD_IMM64 instruction */
 			insn[0].imm = (u32) (unsigned long) map;
 			insn[1].imm = ((u64) (unsigned long) map) >> 32;
@@ -2642,9 +2663,11 @@ static int convert_ctx_accesses(struct verifier_env *env)
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		u32 insn_delta, cnt;
 
-		if (insn->code == (BPF_LDX | BPF_MEM | BPF_W))
+		if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
+		    insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
 			type = BPF_READ;
-		else if (insn->code == (BPF_STX | BPF_MEM | BPF_W))
+		else if (insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+			 insn->code == (BPF_STX | BPF_MEM | BPF_DW))
 			type = BPF_WRITE;
 		else
 			continue;

kernel/events/core.c

@@ -7022,7 +7022,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		irq_work_queue(&event->pending);
 	}
 
-	event->overflow_handler(event, data, regs);
+	READ_ONCE(event->overflow_handler)(event, data, regs);
 
 	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
@@ -7637,11 +7637,83 @@ static void perf_event_free_filter(struct perf_event *event)
 	ftrace_profile_free_filter(event);
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+static void bpf_overflow_handler(struct perf_event *event,
+				 struct perf_sample_data *data,
+				 struct pt_regs *regs)
+{
+	struct bpf_perf_event_data_kern ctx = {
+		.data = data,
+		.regs = regs,
+	};
+	int ret = 0;
+
+	preempt_disable();
+	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
+		goto out;
+	rcu_read_lock();
+	ret = BPF_PROG_RUN(event->prog, (void *)&ctx);
+	rcu_read_unlock();
+out:
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
+	if (!ret)
+		return;
+
+	event->orig_overflow_handler(event, data, regs);
+}
+
+static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
+{
+	struct bpf_prog *prog;
+
+	if (event->overflow_handler_context)
+		/* hw breakpoint or kernel counter */
+		return -EINVAL;
+
+	if (event->prog)
+		return -EEXIST;
+
+	prog = bpf_prog_get_type(prog_fd, BPF_PROG_TYPE_PERF_EVENT);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	event->prog = prog;
+	event->orig_overflow_handler = READ_ONCE(event->overflow_handler);
+	WRITE_ONCE(event->overflow_handler, bpf_overflow_handler);
+	return 0;
+}
+
+static void perf_event_free_bpf_handler(struct perf_event *event)
+{
+	struct bpf_prog *prog = event->prog;
+
+	if (!prog)
+		return;
+
+	WRITE_ONCE(event->overflow_handler, event->orig_overflow_handler);
+	event->prog = NULL;
+	bpf_prog_put(prog);
+}
+#else
+static int perf_event_set_bpf_handler(struct perf_event *event, u32 prog_fd)
+{
+	return -EOPNOTSUPP;
+}
+static void perf_event_free_bpf_handler(struct perf_event *event)
+{
+}
+#endif
+
 static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 {
 	bool is_kprobe, is_tracepoint;
 	struct bpf_prog *prog;
 
+	if (event->attr.type == PERF_TYPE_HARDWARE ||
+	    event->attr.type == PERF_TYPE_SOFTWARE)
+		return perf_event_set_bpf_handler(event, prog_fd);
+
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -EINVAL;
 
@@ -7682,6 +7754,8 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 {
 	struct bpf_prog *prog;
 
+	perf_event_free_bpf_handler(event);
+
 	if (!event->tp_event)
 		return;
 
@@ -8998,6 +9072,19 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (!overflow_handler && parent_event) {
 		overflow_handler = parent_event->overflow_handler;
 		context = parent_event->overflow_handler_context;
+#ifdef CONFIG_BPF_SYSCALL
+		if (overflow_handler == bpf_overflow_handler) {
+			struct bpf_prog *prog = bpf_prog_inc(parent_event->prog);
+
+			if (IS_ERR(prog)) {
+				err = PTR_ERR(prog);
+				goto err_ns;
+			}
+			event->prog = prog;
+			event->orig_overflow_handler =
+				parent_event->orig_overflow_handler;
+		}
+#endif
 	}
 
 	if (overflow_handler) {

kernel/trace/bpf_trace.c

@@ -1,4 +1,5 @@
 /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 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
@@ -8,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/bpf.h>
+#include <linux/bpf_perf_event.h>
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
@@ -552,10 +554,69 @@ static struct bpf_prog_type_list tracepoint_tl = {
 	.type	= BPF_PROG_TYPE_TRACEPOINT,
 };
 
+static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+				    enum bpf_reg_type *reg_type)
+{
+	if (off < 0 || off >= sizeof(struct bpf_perf_event_data))
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+	if (off == offsetof(struct bpf_perf_event_data, sample_period)) {
+		if (size != sizeof(u64))
+			return false;
+	} else {
+		if (size != sizeof(long))
+			return false;
+	}
+	return true;
+}
+
+static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, int dst_reg,
+				      int src_reg, int ctx_off,
+				      struct bpf_insn *insn_buf,
+				      struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (ctx_off) {
+	case offsetof(struct bpf_perf_event_data, sample_period):
+		BUILD_BUG_ON(FIELD_SIZEOF(struct perf_sample_data, period) != sizeof(u64));
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, data)),
+				      dst_reg, src_reg,
+				      offsetof(struct bpf_perf_event_data_kern, data));
+		*insn++ = BPF_LDX_MEM(BPF_DW, dst_reg, dst_reg,
+				      offsetof(struct perf_sample_data, period));
+		break;
+	default:
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs)),
+				      dst_reg, src_reg,
+				      offsetof(struct bpf_perf_event_data_kern, regs));
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(long)),
+				      dst_reg, dst_reg, ctx_off);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+static const struct bpf_verifier_ops perf_event_prog_ops = {
+	.get_func_proto		= tp_prog_func_proto,
+	.is_valid_access	= pe_prog_is_valid_access,
+	.convert_ctx_access	= pe_prog_convert_ctx_access,
+};
+
+static struct bpf_prog_type_list perf_event_tl = {
+	.ops	= &perf_event_prog_ops,
+	.type	= BPF_PROG_TYPE_PERF_EVENT,
+};
+
 static int __init register_kprobe_prog_ops(void)
 {
 	bpf_register_prog_type(&kprobe_tl);
 	bpf_register_prog_type(&tracepoint_tl);
+	bpf_register_prog_type(&perf_event_tl);
 	return 0;
 }
 late_initcall(register_kprobe_prog_ops);

samples/bpf/Makefile

@@ -25,6 +25,8 @@ hostprogs-y += test_cgrp2_array_pin
 hostprogs-y += xdp1
 hostprogs-y += xdp2
 hostprogs-y += test_current_task_under_cgroup
+hostprogs-y += trace_event
+hostprogs-y += sampleip
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -52,6 +54,8 @@ xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
 xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
 test_current_task_under_cgroup-objs := bpf_load.o libbpf.o \
 				       test_current_task_under_cgroup_user.o
+trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
+sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -79,6 +83,8 @@ always += test_cgrp2_tc_kern.o
 always += xdp1_kern.o
 always += xdp2_kern.o
 always += test_current_task_under_cgroup_kern.o
+always += trace_event_kern.o
+always += sampleip_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
@@ -103,6 +109,8 @@ HOSTLOADLIBES_test_overhead += -lelf -lrt
 HOSTLOADLIBES_xdp1 += -lelf
 HOSTLOADLIBES_xdp2 += -lelf
 HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
+HOSTLOADLIBES_trace_event += -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

samples/bpf/bpf_helpers.h

@@ -55,6 +55,8 @@ static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) =
 	(void *) BPF_FUNC_skb_get_tunnel_opt;
 static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
 	(void *) BPF_FUNC_skb_set_tunnel_opt;
+static unsigned long long (*bpf_get_prandom_u32)(void) =
+	(void *) BPF_FUNC_get_prandom_u32;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

samples/bpf/bpf_load.c

@@ -51,6 +51,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
 	bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
 	bool is_xdp = strncmp(event, "xdp", 3) == 0;
+	bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
 	enum bpf_prog_type prog_type;
 	char buf[256];
 	int fd, efd, err, id;
@@ -69,6 +70,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		prog_type = BPF_PROG_TYPE_TRACEPOINT;
 	} else if (is_xdp) {
 		prog_type = BPF_PROG_TYPE_XDP;
+	} else if (is_perf_event) {
+		prog_type = BPF_PROG_TYPE_PERF_EVENT;
 	} else {
 		printf("Unknown event '%s'\n", event);
 		return -1;
@@ -82,7 +85,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 
 	prog_fd[prog_cnt++] = fd;
 
-	if (is_xdp)
+	if (is_xdp || is_perf_event)
 		return 0;
 
 	if (is_socket) {
@@ -326,6 +329,7 @@ int load_bpf_file(char *path)
 			    memcmp(shname_prog, "kretprobe/", 10) == 0 ||
 			    memcmp(shname_prog, "tracepoint/", 11) == 0 ||
 			    memcmp(shname_prog, "xdp", 3) == 0 ||
+			    memcmp(shname_prog, "perf_event", 10) == 0 ||
 			    memcmp(shname_prog, "socket", 6) == 0)
 				load_and_attach(shname_prog, insns, data_prog->d_size);
 		}
@@ -344,6 +348,7 @@ int load_bpf_file(char *path)
 		    memcmp(shname, "kretprobe/", 10) == 0 ||
 		    memcmp(shname, "tracepoint/", 11) == 0 ||
 		    memcmp(shname, "xdp", 3) == 0 ||
+		    memcmp(shname, "perf_event", 10) == 0 ||
 		    memcmp(shname, "socket", 6) == 0)
 			load_and_attach(shname, data->d_buf, data->d_size);
 	}

samples/bpf/sampleip_kern.c

@@ -0,0 +1,38 @@
+/* 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 <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/bpf_perf_event.h>
+#include "bpf_helpers.h"
+
+#define MAX_IPS		8192
+
+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,
+};
+
+SEC("perf_event")
+int do_sample(struct bpf_perf_event_data *ctx)
+{
+	u64 ip;
+	u32 *value, init_val = 1;
+
+	ip = ctx->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_NOEXIST);
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

samples/bpf/sampleip_user.c

@@ -0,0 +1,196 @@
+/*
+ * 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 <assert.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.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,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.inherit = 1,
+	};
+
+	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;
+		}
+		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF,
+			     prog_fd[0]) == 0);
+		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0) == 0);
+	}
+
+	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;
+}

samples/bpf/trace_event_kern.c

@@ -0,0 +1,65 @@
+/* Copyright (c) 2016 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.
+ */
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/bpf_perf_event.h>
+#include <uapi/linux/perf_event.h>
+#include "bpf_helpers.h"
+
+struct key_t {
+	char comm[TASK_COMM_LEN];
+	u32 kernstack;
+	u32 userstack;
+};
+
+struct bpf_map_def SEC("maps") counts = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(struct key_t),
+	.value_size = sizeof(u64),
+	.max_entries = 10000,
+};
+
+struct bpf_map_def SEC("maps") stackmap = {
+	.type = BPF_MAP_TYPE_STACK_TRACE,
+	.key_size = sizeof(u32),
+	.value_size = PERF_MAX_STACK_DEPTH * sizeof(u64),
+	.max_entries = 10000,
+};
+
+#define KERN_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)
+#define USER_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP | BPF_F_USER_STACK)
+
+SEC("perf_event")
+int bpf_prog1(struct bpf_perf_event_data *ctx)
+{
+	char fmt[] = "CPU-%d period %lld ip %llx";
+	u32 cpu = bpf_get_smp_processor_id();
+	struct key_t key;
+	u64 *val, one = 1;
+
+	if (ctx->sample_period < 10000)
+		/* ignore warmup */
+		return 0;
+	bpf_get_current_comm(&key.comm, sizeof(key.comm));
+	key.kernstack = bpf_get_stackid(ctx, &stackmap, KERN_STACKID_FLAGS);
+	key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS);
+	if ((int)key.kernstack < 0 && (int)key.userstack < 0) {
+		bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period,
+				 ctx->regs.ip);
+		return 0;
+	}
+
+	val = bpf_map_lookup_elem(&counts, &key);
+	if (val)
+		(*val)++;
+	else
+		bpf_map_update_elem(&counts, &key, &one, BPF_NOEXIST);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

samples/bpf/trace_event_user.c

@@ -0,0 +1,213 @@
+/* Copyright (c) 2016 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.
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sys/ioctl.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include <signal.h>
+#include <assert.h>
+#include <errno.h>
+#include <sys/resource.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define SAMPLE_FREQ 50
+
+static bool sys_read_seen, sys_write_seen;
+
+static void print_ksym(__u64 addr)
+{
+	struct ksym *sym;
+
+	if (!addr)
+		return;
+	sym = ksym_search(addr);
+	printf("%s;", sym->name);
+	if (!strcmp(sym->name, "sys_read"))
+		sys_read_seen = true;
+	else if (!strcmp(sym->name, "sys_write"))
+		sys_write_seen = true;
+}
+
+static void print_addr(__u64 addr)
+{
+	if (!addr)
+		return;
+	printf("%llx;", addr);
+}
+
+#define TASK_COMM_LEN 16
+
+struct key_t {
+	char comm[TASK_COMM_LEN];
+	__u32 kernstack;
+	__u32 userstack;
+};
+
+static void print_stack(struct key_t *key, __u64 count)
+{
+	__u64 ip[PERF_MAX_STACK_DEPTH] = {};
+	static bool warned;
+	int i;
+
+	printf("%3lld %s;", count, key->comm);
+	if (bpf_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_ksym(ip[i]);
+	}
+	printf("-;");
+	if (bpf_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_addr(ip[i]);
+	}
+	printf("\n");
+
+	if (key->kernstack == -EEXIST && !warned) {
+		printf("stackmap collisions seen. Consider increasing size\n");
+		warned = true;
+	} else if ((int)key->kernstack < 0 && (int)key->userstack < 0) {
+		printf("err stackid %d %d\n", key->kernstack, key->userstack);
+	}
+}
+
+static void int_exit(int sig)
+{
+	kill(0, SIGKILL);
+	exit(0);
+}
+
+static void print_stacks(void)
+{
+	struct key_t key = {}, next_key;
+	__u64 value;
+	__u32 stackid = 0, next_id;
+	int fd = map_fd[0], stack_map = map_fd[1];
+
+	sys_read_seen = sys_write_seen = false;
+	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_lookup_elem(fd, &next_key, &value);
+		print_stack(&next_key, value);
+		bpf_delete_elem(fd, &next_key);
+		key = next_key;
+	}
+
+	if (!sys_read_seen || !sys_write_seen) {
+		printf("BUG kernel stack doesn't contain sys_read() and sys_write()\n");
+		int_exit(0);
+	}
+
+	/* clear stack map */
+	while (bpf_get_next_key(stack_map, &stackid, &next_id) == 0) {
+		bpf_delete_elem(stack_map, &next_id);
+		stackid = next_id;
+	}
+}
+
+static void test_perf_event_all_cpu(struct perf_event_attr *attr)
+{
+	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	int *pmu_fd = malloc(nr_cpus * sizeof(int));
+	int i;
+
+	/* open perf_event on all cpus */
+	for (i = 0; i < nr_cpus; i++) {
+		pmu_fd[i] = perf_event_open(attr, -1, i, -1, 0);
+		if (pmu_fd[i] < 0) {
+			printf("perf_event_open failed\n");
+			goto all_cpu_err;
+		}
+		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
+		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0) == 0);
+	}
+	system("dd if=/dev/zero of=/dev/null count=5000k");
+	print_stacks();
+all_cpu_err:
+	for (i--; i >= 0; i--)
+		close(pmu_fd[i]);
+	free(pmu_fd);
+}
+
+static void test_perf_event_task(struct perf_event_attr *attr)
+{
+	int pmu_fd;
+
+	/* open task bound event */
+	pmu_fd = perf_event_open(attr, 0, -1, -1, 0);
+	if (pmu_fd < 0) {
+		printf("perf_event_open failed\n");
+		return;
+	}
+	assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
+	assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0) == 0);
+	system("dd if=/dev/zero of=/dev/null count=5000k");
+	print_stacks();
+	close(pmu_fd);
+}
+
+static void test_bpf_perf_event(void)
+{
+	struct perf_event_attr attr_type_hw = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.inherit = 1,
+	};
+	struct perf_event_attr attr_type_sw = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.inherit = 1,
+	};
+
+	test_perf_event_all_cpu(&attr_type_hw);
+	test_perf_event_task(&attr_type_hw);
+	test_perf_event_all_cpu(&attr_type_sw);
+	test_perf_event_task(&attr_type_sw);
+}
+
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	setrlimit(RLIMIT_MEMLOCK, &r);
+
+	signal(SIGINT, int_exit);
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		return 1;
+	}
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 2;
+	}
+
+	if (fork() == 0) {
+		read_trace_pipe();
+		return 0;
+	}
+	test_bpf_perf_event();
+
+	int_exit(0);
+	return 0;
+}