Merge tag 'perf-ebpf-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull basic perf/ebpf integration:

 "Please see the changeset comments, but this is the very basic integration of
  perf with libbpf that, given a .o file built for the 'bpf' target with clang,
  will get it validated and loaded into the kernel via the sys_bpf syscall, which
  can be seen using 'perf trace' to trace the whole thing looking just for the
  bpf and perf_event_open syscalls:

    # perf trace -e bpf,perf_event_open perf record -g --event /tmp/foo.o -a
     362.779 ( 0.129 ms): perf/22408 bpf(cmd: 5, uattr: 0x7ffd4edb6db0, size: 48                           ) = 3
     384.192 ( 0.016 ms): perf/22408 perf_event_open(attr_uptr: 0x7ffd4edbace0, pid: -1, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 5
     384.247 ( 0.038 ms): perf/22408 perf_event_open(attr_uptr: 0x37aedd8, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
     384.261 ( 0.007 ms): perf/22408 perf_event_open(attr_uptr: 0x37aedd8, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
     387.680 ( 3.413 ms): perf/22408 perf_event_open(attr_uptr: 0x3222f08, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 5
     387.688 ( 0.005 ms): perf/22408 perf_event_open(attr_uptr: 0x3222f08, pid: -1, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 6
     387.693 ( 0.004 ms): perf/22408 perf_event_open(attr_uptr: 0x3222f08, pid: -1, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 7
     387.698 ( 0.003 ms): perf/22408 perf_event_open(attr_uptr: 0x3222f08, pid: -1, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8
    ^C[ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 0.221 MB perf.data (2 samples) ]
    # perf script
    bash 18389 [002] 83446.412607: perf_bpf_probe:fork: (ffffffff8109be30)
                    29be31 _do_fork (/lib/modules/4.3.0-rc6+/build/vmlinux)
                    96d662 tracesys_phase2 (/lib/modules/4.3.0-rc6+/build/vmlinux)
                     bd56c __libc_fork (/usr/lib64/libc-2.17.so)
                     413b2 make_child (/usr/bin/bash)

    bash 18389 [002] 83447.227255: perf_bpf_probe:fork: (ffffffff8109be30)
                    29be31 _do_fork (/lib/modules/4.3.0-rc6+/build/vmlinux)
                    96d662 tracesys_phase2 (/lib/modules/4.3.0-rc6+/build/vmlinux)
                     bd56c __libc_fork (/usr/lib64/libc-2.17.so)
                     413b2 make_child (/usr/bin/bash)

    # perf evlist -v
    perf_bpf_probe:fork: type: 2, size: 112, config: 0x6cf, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
    #

  More work is about to be reviewed, tested and merged that will allow the whole
  process of going from a .c file to an .o file via clang, etc to be done
  automagically. (Wang Nan)"

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 339 insertions, 0 deletions

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
new file mode 100644
index 000000000000..aa784a498c48
--- /dev/null
+++ b/tools/perf/util/bpf-loader.c
@@ -0,0 +1,339 @@
+/*
+ * bpf-loader.c
+ *
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ */
+
+#include <bpf/libbpf.h>
+#include <linux/err.h>
+#include "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "probe-event.h"
+#include "probe-finder.h" // for MAX_PROBES
+
+#define DEFINE_PRINT_FN(name, level) \
+static int libbpf_##name(const char *fmt, ...)	\
+{						\
+	va_list args;				\
+	int ret;				\
+						\
+	va_start(args, fmt);			\
+	ret = veprintf(level, verbose, pr_fmt(fmt), args);\
+	va_end(args);				\
+	return ret;				\
+}
+
+DEFINE_PRINT_FN(warning, 0)
+DEFINE_PRINT_FN(info, 0)
+DEFINE_PRINT_FN(debug, 1)
+
+struct bpf_prog_priv {
+	struct perf_probe_event pev;
+};
+
+struct bpf_object *bpf__prepare_load(const char *filename)
+{
+	struct bpf_object *obj;
+	static bool libbpf_initialized;
+
+	if (!libbpf_initialized) {
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+		libbpf_initialized = true;
+	}
+
+	obj = bpf_object__open(filename);
+	if (!obj) {
+		pr_debug("bpf: failed to load %s\n", filename);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return obj;
+}
+
+void bpf__clear(void)
+{
+	struct bpf_object *obj, *tmp;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		bpf__unprobe(obj);
+		bpf_object__close(obj);
+	}
+}
+
+static void
+bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
+		     void *_priv)
+{
+	struct bpf_prog_priv *priv = _priv;
+
+	cleanup_perf_probe_events(&priv->pev, 1);
+	free(priv);
+}
+
+static int
+config_bpf_program(struct bpf_program *prog)
+{
+	struct perf_probe_event *pev = NULL;
+	struct bpf_prog_priv *priv = NULL;
+	const char *config_str;
+	int err;
+
+	config_str = bpf_program__title(prog, false);
+	if (!config_str) {
+		pr_debug("bpf: unable to get title for program\n");
+		return -EINVAL;
+	}
+
+	priv = calloc(sizeof(*priv), 1);
+	if (!priv) {
+		pr_debug("bpf: failed to alloc priv\n");
+		return -ENOMEM;
+	}
+	pev = &priv->pev;
+
+	pr_debug("bpf: config program '%s'\n", config_str);
+	err = parse_perf_probe_command(config_str, pev);
+	if (err < 0) {
+		pr_debug("bpf: '%s' is not a valid config string\n",
+			 config_str);
+		err = -EINVAL;
+		goto errout;
+	}
+
+	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
+		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
+			 config_str, PERF_BPF_PROBE_GROUP);
+		err = -EINVAL;
+		goto errout;
+	} else if (!pev->group)
+		pev->group = strdup(PERF_BPF_PROBE_GROUP);
+
+	if (!pev->group) {
+		pr_debug("bpf: strdup failed\n");
+		err = -ENOMEM;
+		goto errout;
+	}
+
+	if (!pev->event) {
+		pr_debug("bpf: '%s': event name is missing\n",
+			 config_str);
+		err = -EINVAL;
+		goto errout;
+	}
+	pr_debug("bpf: config '%s' is ok\n", config_str);
+
+	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	if (err) {
+		pr_debug("Failed to set priv for program '%s'\n", config_str);
+		goto errout;
+	}
+
+	return 0;
+
+errout:
+	if (pev)
+		clear_perf_probe_event(pev);
+	free(priv);
+	return err;
+}
+
+static int bpf__prepare_probe(void)
+{
+	static int err = 0;
+	static bool initialized = false;
+
+	/*
+	 * Make err static, so if init failed the first, bpf__prepare_probe()
+	 * fails each time without calling init_probe_symbol_maps multiple
+	 * times.
+	 */
+	if (initialized)
+		return err;
+
+	initialized = true;
+	err = init_probe_symbol_maps(false);
+	if (err < 0)
+		pr_debug("Failed to init_probe_symbol_maps\n");
+	probe_conf.max_probes = MAX_PROBES;
+	return err;
+}
+
+int bpf__probe(struct bpf_object *obj)
+{
+	int err = 0;
+	struct bpf_program *prog;
+	struct bpf_prog_priv *priv;
+	struct perf_probe_event *pev;
+
+	err = bpf__prepare_probe();
+	if (err) {
+		pr_debug("bpf__prepare_probe failed\n");
+		return err;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		err = config_bpf_program(prog);
+		if (err)
+			goto out;
+
+		err = bpf_program__get_private(prog, (void **)&priv);
+		if (err || !priv)
+			goto out;
+		pev = &priv->pev;
+
+		err = convert_perf_probe_events(pev, 1);
+		if (err < 0) {
+			pr_debug("bpf_probe: failed to convert perf probe events");
+			goto out;
+		}
+
+		err = apply_perf_probe_events(pev, 1);
+		if (err < 0) {
+			pr_debug("bpf_probe: failed to apply perf probe events");
+			goto out;
+		}
+	}
+out:
+	return err < 0 ? err : 0;
+}
+
+#define EVENTS_WRITE_BUFSIZE  4096
+int bpf__unprobe(struct bpf_object *obj)
+{
+	int err, ret = 0;
+	struct bpf_program *prog;
+	struct bpf_prog_priv *priv;
+
+	bpf_object__for_each_program(prog, obj) {
+		int i;
+
+		err = bpf_program__get_private(prog, (void **)&priv);
+		if (err || !priv)
+			continue;
+
+		for (i = 0; i < priv->pev.ntevs; i++) {
+			struct probe_trace_event *tev = &priv->pev.tevs[i];
+			char name_buf[EVENTS_WRITE_BUFSIZE];
+			struct strfilter *delfilter;
+
+			snprintf(name_buf, EVENTS_WRITE_BUFSIZE,
+				 "%s:%s", tev->group, tev->event);
+			name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0';
+
+			delfilter = strfilter__new(name_buf, NULL);
+			if (!delfilter) {
+				pr_debug("Failed to create filter for unprobing\n");
+				ret = -ENOMEM;
+				continue;
+			}
+
+			err = del_perf_probe_events(delfilter);
+			strfilter__delete(delfilter);
+			if (err) {
+				pr_debug("Failed to delete %s\n", name_buf);
+				ret = err;
+				continue;
+			}
+		}
+	}
+	return ret;
+}
+
+int bpf__load(struct bpf_object *obj)
+{
+	int err;
+
+	err = bpf_object__load(obj);
+	if (err) {
+		pr_debug("bpf: load objects failed\n");
+		return err;
+	}
+	return 0;
+}
+
+int bpf__foreach_tev(struct bpf_object *obj,
+		     bpf_prog_iter_callback_t func,
+		     void *arg)
+{
+	struct bpf_program *prog;
+	int err;
+
+	bpf_object__for_each_program(prog, obj) {
+		struct probe_trace_event *tev;
+		struct perf_probe_event *pev;
+		struct bpf_prog_priv *priv;
+		int i, fd;
+
+		err = bpf_program__get_private(prog,
+				(void **)&priv);
+		if (err || !priv) {
+			pr_debug("bpf: failed to get private field\n");
+			return -EINVAL;
+		}
+
+		pev = &priv->pev;
+		for (i = 0; i < pev->ntevs; i++) {
+			tev = &pev->tevs[i];
+
+			fd = bpf_program__fd(prog);
+			if (fd < 0) {
+				pr_debug("bpf: failed to get file descriptor\n");
+				return fd;
+			}
+
+			err = (*func)(tev, fd, arg);
+			if (err) {
+				pr_debug("bpf: call back failed, stop iterate\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+#define bpf__strerror_head(err, buf, size) \
+	char sbuf[STRERR_BUFSIZE], *emsg;\
+	if (!size)\
+		return 0;\
+	if (err < 0)\
+		err = -err;\
+	emsg = strerror_r(err, sbuf, sizeof(sbuf));\
+	switch (err) {\
+	default:\
+		scnprintf(buf, size, "%s", emsg);\
+		break;
+
+#define bpf__strerror_entry(val, fmt...)\
+	case val: {\
+		scnprintf(buf, size, fmt);\
+		break;\
+	}
+
+#define bpf__strerror_end(buf, size)\
+	}\
+	buf[size - 1] = '\0';
+
+int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
+			int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0\n");
+	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file\n");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
+		       int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(EINVAL, "%s: Are you root and runing a CONFIG_BPF_SYSCALL kernel?",
+			    emsg)
+	bpf__strerror_end(buf, size);
+	return 0;
+}