perf ftrace: Introduce new 'ftrace' tool

The 'perf ftrace' command is a simple wrapper of kernel's ftrace
functionality.  It only supports single thread tracing currently and
just reads trace_pipe in text and then write it to stdout.

Committer notes:

Testing it:

  # perf ftrace -f function_graph usleep 123456
  <SNIP>
  2)               |  SyS_nanosleep() {
  2)               |    _copy_from_user() {
  <SNIP>
  2)   0.900 us    |      }
  2)   1.354 us    |    }
  2)               |    hrtimer_nanosleep() {
  2)   0.062 us    |      __hrtimer_init();
  2)               |      do_nanosleep() {
  2)               |        hrtimer_start_range_ns() {
  <SNIP>
  2)   5.025 us    |        }
  2)               |        schedule() {
  2)   0.125 us    |          rcu_note_context_switch();
  2)   0.057 us    |          _raw_spin_lock();
  2)               |          deactivate_task() {
  2)   0.369 us    |            update_rq_clock.part.77();
  2)               |            dequeue_task_fair() {
  <SNIP>
  2) + 22.453 us   |            }
  2) + 23.736 us   |          }
  2)               |          pick_next_task_fair() {
  <SNIP>
  2) + 47.167 us   |          }
  2)               |          pick_next_task_idle() {
  <SNIP>
  2)   4.462 us    |          }
  ------------------------------------------
  2)  usleep-20387  =>    <idle>-0
  ------------------------------------------

  2)   0.806 us    |  switch_mm_irqs_off();
  ------------------------------------------
  2)    <idle>-0    =>  usleep-20387
  ------------------------------------------

  2)   0.151 us    |          finish_task_switch();
  2) @ 123597.2 us |        }
  2)   0.037 us    |        _cond_resched();
  2)               |        hrtimer_try_to_cancel() {
  2)   0.064 us    |          hrtimer_active();
  2)   0.353 us    |        }
  2) @ 123605.3 us |      }
  2) @ 123606.2 us |    }
  2) @ 123608.3 us |  } /* SyS_nanosleep */
  2)               |  __do_page_fault() {
 <SNIP>

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jeremy Eder <jeder@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>,
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/n/tip-r1hgmsj4dxny8arn3o9mw512@git.kernel.org
[ Various foward port fixes, add man page ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 242 insertions, 0 deletions

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 0000000..c320ae2
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,242 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+
+
+#define DEFAULT_TRACER  "function_graph"
+
+struct perf_ftrace {
+	struct perf_evlist *evlist;
+	struct target target;
+	const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+						siginfo_t *info __maybe_unused,
+						void *ucontext __maybe_unused)
+{
+	/* workload_exec_errno = info->si_value.sival_int; */
+	done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+	char *file;
+	int fd, ret = -1;
+	ssize_t size = strlen(val);
+
+	file = get_tracing_file(name);
+	if (!file) {
+		pr_debug("cannot get tracing file: %s\n", name);
+		return -1;
+	}
+
+	fd = open(file, O_WRONLY);
+	if (fd < 0) {
+		pr_debug("cannot open tracing file: %s\n", name);
+		goto out;
+	}
+
+	if (write(fd, val, size) == size)
+		ret = 0;
+	else
+		pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+	close(fd);
+out:
+	put_tracing_file(file);
+	return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+	if (write_tracing_file("tracing_on", "0") < 0)
+		return -1;
+
+	if (write_tracing_file("current_tracer", "nop") < 0)
+		return -1;
+
+	if (write_tracing_file("set_ftrace_pid", " ") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+	char *trace_file;
+	int trace_fd;
+	char *trace_pid;
+	char buf[4096];
+	struct pollfd pollfd = {
+		.events = POLLIN,
+	};
+
+	if (geteuid() != 0) {
+		pr_err("ftrace only works for root!\n");
+		return -1;
+	}
+
+	if (argc < 1)
+		return -1;
+
+	signal(SIGINT, sig_handler);
+	signal(SIGUSR1, sig_handler);
+	signal(SIGCHLD, sig_handler);
+
+	reset_tracing_files(ftrace);
+
+	/* reset ftrace buffer */
+	if (write_tracing_file("trace", "0") < 0)
+		goto out;
+
+	if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+					  argv, false, ftrace__workload_exec_failed_signal) < 0)
+		goto out;
+
+	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+		goto out;
+	}
+
+	if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+		pr_err("failed to allocate pid string\n");
+		goto out;
+	}
+
+	if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+		pr_err("failed to set pid: %s\n", trace_pid);
+		goto out_free_pid;
+	}
+
+	trace_file = get_tracing_file("trace_pipe");
+	if (!trace_file) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	trace_fd = open(trace_file, O_RDONLY);
+
+	put_tracing_file(trace_file);
+
+	if (trace_fd < 0) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+	pollfd.fd = trace_fd;
+
+	if (write_tracing_file("tracing_on", "1") < 0) {
+		pr_err("can't enable tracing\n");
+		goto out_close_fd;
+	}
+
+	perf_evlist__start_workload(ftrace->evlist);
+
+	while (!done) {
+		if (poll(&pollfd, 1, -1) < 0)
+			break;
+
+		if (pollfd.revents & POLLIN) {
+			int n = read(trace_fd, buf, sizeof(buf));
+			if (n < 0)
+				break;
+			if (fwrite(buf, n, 1, stdout) != 1)
+				break;
+		}
+	}
+
+	write_tracing_file("tracing_on", "0");
+
+	/* read remaining buffer contents */
+	while (true) {
+		int n = read(trace_fd, buf, sizeof(buf));
+		if (n <= 0)
+			break;
+		if (fwrite(buf, n, 1, stdout) != 1)
+			break;
+	}
+
+out_close_fd:
+	close(trace_fd);
+out_free_pid:
+	free(trace_pid);
+out:
+	reset_tracing_files(ftrace);
+
+	return done ? 0 : -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	int ret;
+	struct perf_ftrace ftrace = {
+		.target = { .uid = UINT_MAX, },
+	};
+	const char * const ftrace_usage[] = {
+		"perf ftrace [<options>] <command>",
+		"perf ftrace [<options>] -- <command> [<options>]",
+		NULL
+	};
+	const struct option ftrace_options[] = {
+	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+		   "tracer to use: function_graph or function"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+			    PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(ftrace_usage, ftrace_options);
+
+	ftrace.evlist = perf_evlist__new();
+	if (ftrace.evlist == NULL)
+		return -ENOMEM;
+
+	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+	if (ret < 0)
+		goto out_delete_evlist;
+
+	if (ftrace.tracer == NULL)
+		ftrace.tracer = DEFAULT_TRACER;
+
+	ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+	perf_evlist__delete(ftrace.evlist);
+
+	return ret;
+}