samples/bpf: Add kmem_alloc()/free() tracker tool

One BPF program attaches to kmem_cache_alloc_node() and
remembers all allocated objects in the map.
Another program attaches to kmem_cache_free() and deletes
corresponding object from the map.

User space walks the map every second and prints any objects
which are older than 1 second.

Usage:

	$ sudo tracex4

Then start few long living processes. The 'tracex4' will print
something like this:

	obj 0xffff880465928000 is 13sec old was allocated at ip ffffffff8105dc32
	obj 0xffff88043181c280 is 13sec old was allocated at ip ffffffff8105dc32
	obj 0xffff880465848000 is  8sec old was allocated at ip ffffffff8105dc32
	obj 0xffff8804338bc280 is 15sec old was allocated at ip ffffffff8105dc32

	$ addr2line -fispe vmlinux ffffffff8105dc32
	do_fork at fork.c:1665

As soon as processes exit the memory is reclaimed and 'tracex4'
prints nothing.

Similar experiment can be done with the __kmalloc()/kfree() pair.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1427312966-8434-10-git-send-email-ast@plumgrid.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

samples/bpf/Makefile

@@ -9,6 +9,7 @@ hostprogs-y += sockex2
 hostprogs-y += tracex1
 hostprogs-y += tracex2
 hostprogs-y += tracex3
+hostprogs-y += tracex4
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -18,6 +19,7 @@ sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
 tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
 tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
 tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
+tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -26,6 +28,7 @@ always += sockex2_kern.o
 always += tracex1_kern.o
 always += tracex2_kern.o
 always += tracex3_kern.o
+always += tracex4_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
@@ -35,6 +38,7 @@ HOSTLOADLIBES_sockex2 += -lelf
 HOSTLOADLIBES_tracex1 += -lelf
 HOSTLOADLIBES_tracex2 += -lelf
 HOSTLOADLIBES_tracex3 += -lelf
+HOSTLOADLIBES_tracex4 += -lelf -lrt
 
 # point this to your LLVM backend with bpf support
 LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc

samples/bpf/tracex4_kern.c

@@ -0,0 +1,54 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 "bpf_helpers.h"
+
+struct pair {
+	u64 val;
+	u64 ip;
+};
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(long),
+	.value_size = sizeof(struct pair),
+	.max_entries = 1000000,
+};
+
+/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
+ * example will no longer be meaningful
+ */
+SEC("kprobe/kmem_cache_free")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	long ptr = ctx->si;
+
+	bpf_map_delete_elem(&my_map, &ptr);
+	return 0;
+}
+
+SEC("kretprobe/kmem_cache_alloc_node")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	long ptr = ctx->ax;
+	long ip = 0;
+
+	/* get ip address of kmem_cache_alloc_node() caller */
+	bpf_probe_read(&ip, sizeof(ip), (void *)(ctx->bp + sizeof(ip)));
+
+	struct pair v = {
+		.val = bpf_ktime_get_ns(),
+		.ip = ip,
+	};
+
+	bpf_map_update_elem(&my_map, &ptr, &v, BPF_ANY);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

samples/bpf/tracex4_user.c

@@ -0,0 +1,69 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <time.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+struct pair {
+	long long val;
+	__u64 ip;
+};
+
+static __u64 time_get_ns(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
+}
+
+static void print_old_objects(int fd)
+{
+	long long val = time_get_ns();
+	__u64 key, next_key;
+	struct pair v;
+
+	key = write(1, "\e[1;1H\e[2J", 12); /* clear screen */
+
+	key = -1;
+	while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
+		bpf_lookup_elem(map_fd[0], &next_key, &v);
+		key = next_key;
+		if (val - v.val < 1000000000ll)
+			/* object was allocated more then 1 sec ago */
+			continue;
+		printf("obj 0x%llx is %2lldsec old was allocated at ip %llx\n",
+		       next_key, (val - v.val) / 1000000000ll, v.ip);
+	}
+}
+
+int main(int ac, char **argv)
+{
+	char filename[256];
+	int i;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	for (i = 0; ; i++) {
+		print_old_objects(map_fd[1]);
+		sleep(1);
+	}
+
+	return 0;
+}