1 files changed, 90 insertions, 58 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3db31e7bf173..95db31cff6fd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -44,21 +44,25 @@
 #include "util/parse-events.h"
 #include "util/event.h"
 #include "util/debug.h"
+#include "util/header.h"
+#include "util/cpumap.h"
 
 #include <sys/prctl.h>
 #include <math.h>
 
 static struct perf_event_attr default_attrs[] = {
 
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK      },
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES},
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS  },
-  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS     },
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK              },
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES        },
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS          },
+  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS             },
 
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES      },
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS    },
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES},
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES    },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES              },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS            },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS     },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES           },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES        },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES            },
 
 };
 
@@ -77,6 +81,8 @@ static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int                      event_scaled[MAX_COUNTERS];
 
+static volatile int done = 0;
+
 struct stats
 {
         double n, mean, M2;
@@ -125,6 +131,7 @@ struct stats			event_res_stats[MAX_COUNTERS][3];
 struct stats                    runtime_nsecs_stats;
 struct stats                    walltime_nsecs_stats;
 struct stats                    runtime_cycles_stats;
+struct stats                    runtime_branches_stats;
 
 #define MATCH_EVENT(t, c, counter)                      \
         (attrs[counter].type == PERF_TYPE_##t &&        \
@@ -145,7 +152,7 @@ static void create_perf_stat_counter(int counter, int pid)
                 unsigned int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
-                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpu, -1, 0);
+                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
                         if (fd[cpu][counter] < 0 && verbose)
                                 fprintf(stderr, ERR_PERF_OPEN, counter,
                                         fd[cpu][counter], strerror(errno));
@@ -235,6 +242,8 @@ static void read_counter(int counter)
                 update_stats(&runtime_nsecs_stats, count[0]);
         if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
                 update_stats(&runtime_cycles_stats, count[0]);
+        if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
+                update_stats(&runtime_branches_stats, count[0]);
 }
 
 static int run_perf_stat(int argc __used, const char **argv)
@@ -242,61 +251,64 @@ static int run_perf_stat(int argc __used, const char **argv)
         unsigned long long t0, t1;
         int status = 0;
         int counter;
-        int pid;
+        int pid = target_pid;
         int child_ready_pipe[2], go_pipe[2];
+        const bool forks = (target_pid == -1 && argc > 0);
         char buf;
 
         if (!system_wide)
                 nr_cpus = 1;
 
-        if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+        if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
                 perror("failed to create pipes");
                 exit(1);
         }
 
-        if ((pid = fork()) < 0)
-                perror("failed to fork");
-
-        if (!pid) {
-                close(child_ready_pipe[0]);
-                close(go_pipe[1]);
-                fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+        if (forks) {
+                if ((pid = fork()) < 0)
+                        perror("failed to fork");
+
+                if (!pid) {
+                        close(child_ready_pipe[0]);
+                        close(go_pipe[1]);
+                        fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+
+                        /*
+                         * Do a dummy execvp to get the PLT entry resolved,
+                         * so we avoid the resolver overhead on the real
+                         * execvp call.
+                         */
+                        execvp("", (char **)argv);
+
+                        /*
+                         * Tell the parent we're ready to go
+                         */
+                        close(child_ready_pipe[1]);
+
+                        /*
+                         * Wait until the parent tells us to go.
+                         */
+                        if (read(go_pipe[0], &buf, 1) == -1)
+                                perror("unable to read pipe");
+
+                        execvp(argv[0], (char **)argv);
+
+                        perror(argv[0]);
+                        exit(-1);
+                }
 
-                /*
-                 * Do a dummy execvp to get the PLT entry resolved,
-                 * so we avoid the resolver overhead on the real
-                 * execvp call.
-                 */
-                execvp("", (char **)argv);
+                child_pid = pid;
 
                 /*
-                 * Tell the parent we're ready to go
+                 * Wait for the child to be ready to exec.
                  */
                 close(child_ready_pipe[1]);
-
-                /*
-                 * Wait until the parent tells us to go.
-                 */
-                if (read(go_pipe[0], &buf, 1) == -1)
+                close(go_pipe[0]);
+                if (read(child_ready_pipe[0], &buf, 1) == -1)
                         perror("unable to read pipe");
-
-                execvp(argv[0], (char **)argv);
-
-                perror(argv[0]);
-                exit(-1);
+                close(child_ready_pipe[0]);
         }
 
-        child_pid = pid;
-
-        /*
-         * Wait for the child to be ready to exec.
-         */
-        close(child_ready_pipe[1]);
-        close(go_pipe[0]);
-        if (read(child_ready_pipe[0], &buf, 1) == -1)
-                perror("unable to read pipe");
-        close(child_ready_pipe[0]);
-
         for (counter = 0; counter < nr_counters; counter++)
                 create_perf_stat_counter(counter, pid);
 
@@ -305,8 +317,12 @@ static int run_perf_stat(int argc __used, const char **argv)
          */
         t0 = rdclock();
 
-        close(go_pipe[1]);
-        wait(&status);
+        if (forks) {
+                close(go_pipe[1]);
+                wait(&status);
+        } else {
+                while(!done);
+        }
 
         t1 = rdclock();
 
@@ -352,7 +368,16 @@ static void abs_printout(int counter, double avg)
                         ratio = avg / total;
 
                 fprintf(stderr, " # %10.3f IPC  ", ratio);
-        } else {
+        } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) &&
+                        runtime_branches_stats.n != 0) {
+                total = avg_stats(&runtime_branches_stats);
+
+                if (total)
+                        ratio = avg * 100 / total;
+
+                fprintf(stderr, " # %10.3f %%    ", ratio);
+
+        } else if (runtime_nsecs_stats.n != 0) {
                 total = avg_stats(&runtime_nsecs_stats);
 
                 if (total)
@@ -403,10 +428,13 @@ static void print_stat(int argc, const char **argv)
         fflush(stdout);
 
         fprintf(stderr, "\n");
-        fprintf(stderr, " Performance counter stats for \'%s", argv[0]);
-
-        for (i = 1; i < argc; i++)
-                fprintf(stderr, " %s", argv[i]);
+        fprintf(stderr, " Performance counter stats for ");
+        if(target_pid == -1) {
+                fprintf(stderr, "\'%s", argv[0]);
+                for (i = 1; i < argc; i++)
+                        fprintf(stderr, " %s", argv[i]);
+        }else
+                fprintf(stderr, "task pid \'%d", target_pid);
 
         fprintf(stderr, "\'");
         if (run_count > 1)
@@ -431,6 +459,9 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
+        if(target_pid != -1)
+                done = 1;
+
         signr = signo;
 }
 
@@ -447,7 +478,7 @@ static void sig_atexit(void)
 }
 
 static const char * const stat_usage[] = {
-        "perf stat [<options>] <command>",
+        "perf stat [<options>] [<command>]",
         NULL
 };
 
@@ -478,7 +509,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 
         argc = parse_options(argc, argv, options, stat_usage,
                 PARSE_OPT_STOP_AT_NON_OPTION);
-        if (!argc)
+        if (!argc && target_pid == -1)
                 usage_with_options(stat_usage, options);
         if (run_count <= 0)
                 usage_with_options(stat_usage, options);
@@ -489,9 +520,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
                 nr_counters = ARRAY_SIZE(default_attrs);
         }
 
-        nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert((int)nr_cpus >= 0);
+        if (system_wide)
+                nr_cpus = read_cpu_map();
+        else
+                nr_cpus = 1;
 
         /*
          * We dont want to block the signals - that would cause