perf sched: Fix for getting task's execution time

In current code, task's execute time is got by reading
'/proc/<pid>/sched' file, it's wrong if the task is created
by pthread_create(), because every thread task has same pid.

This way also has two demerits:

 1: 'perf sched replay' can't work if the kernel is not
    compiled with the 'CONFIG_SCHED_DEBUG' option

 2: perf tool should depend on proc file system

So, this patch uses PERF_COUNT_SW_TASK_CLOCK to get task's
execution time instead of reading /proc file.

Changelog v2 -> v3:
use PERF_COUNT_SW_TASK_CLOCK instead of rusage() as Ingo's
suggestion

Reported-by: Torok Edwin <edwintorok@gmail.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Xiao Guangrong <ericxiao.gr@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <4B1F7322.80103@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 19f43faa9f810cd4786ca3e8e64fb9a2a9484735..b12b23ac06f3812531d6425c076caa030527d5dc 100644 (file)
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -13,7 +13,6 @@
 #include "util/debug.h"
 #include "util/data_map.h"
 
-#include <sys/types.h>
 #include <sys/prctl.h>
 
 #include <semaphore.h>
@@ -414,34 +413,33 @@ static u64 get_cpu_usage_nsec_parent(void)
        return sum;
 }
 
-static u64 get_cpu_usage_nsec_self(void)
+static int self_open_counters(void)
 {
-       char filename [] = "/proc/1234567890/sched";
-       unsigned long msecs, nsecs;
-       char *line = NULL;
-       u64 total = 0;
-       size_t len = 0;
-       ssize_t chars;
-       FILE *file;
-       int ret;
+       struct perf_event_attr attr;
+       int fd;
 
-       sprintf(filename, "/proc/%d/sched", getpid());
-       file = fopen(filename, "r");
-       BUG_ON(!file);
+       memset(&attr, 0, sizeof(attr));
 
-       while ((chars = getline(&line, &len, file)) != -1) {
-               ret = sscanf(line, "se.sum_exec_runtime : %ld.%06ld\n",
-                       &msecs, &nsecs);
-               if (ret == 2) {
-                       total = msecs*1e6 + nsecs;
-                       break;
-               }
-       }
-       if (line)
-               free(line);
-       fclose(file);
+       attr.type = PERF_TYPE_SOFTWARE;
+       attr.config = PERF_COUNT_SW_TASK_CLOCK;
 
-       return total;
+       fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+
+       if (fd < 0)
+               die("Error: sys_perf_event_open() syscall returned"
+                   "with %d (%s)\n", fd, strerror(errno));
+       return fd;
+}
+
+static u64 get_cpu_usage_nsec_self(int fd)
+{
+       u64 runtime;
+       int ret;
+
+       ret = read(fd, &runtime, sizeof(runtime));
+       BUG_ON(ret != sizeof(runtime));
+
+       return runtime;
 }
 
 static void *thread_func(void *ctx)
@@ -450,9 +448,11 @@ static void *thread_func(void *ctx)
        u64 cpu_usage_0, cpu_usage_1;
        unsigned long i, ret;
        char comm2[22];
+       int fd;
 
        sprintf(comm2, ":%s", this_task->comm);
        prctl(PR_SET_NAME, comm2);
+       fd = self_open_counters();
 
 again:
        ret = sem_post(&this_task->ready_for_work);
@@ -462,16 +462,15 @@ again:
        ret = pthread_mutex_unlock(&start_work_mutex);
        BUG_ON(ret);
 
-       cpu_usage_0 = get_cpu_usage_nsec_self();
+       cpu_usage_0 = get_cpu_usage_nsec_self(fd);
 
        for (i = 0; i < this_task->nr_events; i++) {
                this_task->curr_event = i;
                process_sched_event(this_task, this_task->atoms[i]);
        }
 
-       cpu_usage_1 = get_cpu_usage_nsec_self();
+       cpu_usage_1 = get_cpu_usage_nsec_self(fd);
        this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
-
        ret = sem_post(&this_task->work_done_sem);
        BUG_ON(ret);