perf stat: Refactor aggregation code

Refactor aggregation code by introducing a single aggr_mode variable and an
enum for aggregation.

Also refactor cpumap code having to do with cpu to socket mappings. All in
preparation for extended modes, such as cpu -> core.

Also fix socket aggregation and ensure that sockets are printed in increasing
order.

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1360846649-6411-2-git-send-email-eranian@google.com
[ committer note: Fixup conflicts with a7e191c "--repeat forever" and
  acf2892 "Use perf_evlist__prepare/start_workload()" ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 147 insertions, 100 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ba0bdd87c279..ded34fc4df4f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -68,7 +68,7 @@
 static void print_stat(int argc, const char **argv);
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
 static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr_socket(char *prefix);
+static void print_aggr(char *prefix);
 
 static struct perf_evlist       *evsel_list;
 
@@ -76,11 +76,16 @@ static struct perf_target	target = {
         .uid    = UINT_MAX,
 };
 
+enum aggr_mode {
+        AGGR_NONE,
+        AGGR_GLOBAL,
+        AGGR_SOCKET,
+};
+
 static int                      run_count                       =  1;
 static bool                     no_inherit                      = false;
 static bool                     scale                           =  true;
-static bool                     no_aggr                         = false;
-static bool                     aggr_socket                     = false;
+static enum aggr_mode           aggr_mode                       = AGGR_GLOBAL;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
 static int                      detailed_run                    =  0;
@@ -96,7 +101,8 @@ static bool			sync_run			= false;
 static unsigned int             interval                        = 0;
 static bool                     forever                         = false;
 static struct timespec          ref_time;
-static struct cpu_map           *sock_map;
+static struct cpu_map           *aggr_map;
+static int                      (*aggr_get_id)(struct cpu_map *m, int cpu);
 
 static volatile int done = 0;
 
@@ -355,41 +361,51 @@ static void print_interval(void)
         struct timespec ts, rs;
         char prefix[64];
 
-        if (no_aggr) {
+        if (aggr_mode == AGGR_GLOBAL) {
                 list_for_each_entry(counter, &evsel_list->entries, node) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
-                        read_counter(counter);
+                        read_counter_aggr(counter);
                 }
-        } else {
+        } else  {
                 list_for_each_entry(counter, &evsel_list->entries, node) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
-                        read_counter_aggr(counter);
+                        read_counter(counter);
                 }
         }
+
         clock_gettime(CLOCK_MONOTONIC, &ts);
         diff_timespec(&rs, &ts, &ref_time);
         sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
 
         if (num_print_interval == 0 && !csv_output) {
-                if (aggr_socket)
+                switch (aggr_mode) {
+                case AGGR_SOCKET:
                         fprintf(output, "#           time socket cpus             counts events\n");
-                else if (no_aggr)
+                        break;
+                case AGGR_NONE:
                         fprintf(output, "#           time CPU                 counts events\n");
-                else
+                        break;
+                case AGGR_GLOBAL:
+                default:
                         fprintf(output, "#           time             counts events\n");
+                }
         }
 
         if (++num_print_interval == 25)
                 num_print_interval = 0;
 
-        if (aggr_socket)
-                print_aggr_socket(prefix);
-        else if (no_aggr) {
+        switch (aggr_mode) {
+        case AGGR_SOCKET:
+                print_aggr(prefix);
+                break;
+        case AGGR_NONE:
                 list_for_each_entry(counter, &evsel_list->entries, node)
                         print_counter(counter, prefix);
-        } else {
+                break;
+        case AGGR_GLOBAL:
+        default:
                 list_for_each_entry(counter, &evsel_list->entries, node)
                         print_counter_aggr(counter, prefix);
         }
@@ -412,12 +428,6 @@ static int __run_perf_stat(int argc, const char **argv)
                 ts.tv_nsec = 0;
         }
 
-        if (aggr_socket
-            && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) {
-                perror("cannot build socket map");
-                return -1;
-        }
-
         if (forks) {
                 if (perf_evlist__prepare_workload(evsel_list, &target, argv,
                                                   false, false) < 0) {
@@ -493,17 +503,17 @@ static int __run_perf_stat(int argc, const char **argv)
 
         update_stats(&walltime_nsecs_stats, t1 - t0);
 
-        if (no_aggr) {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
-                        read_counter(counter);
-                        perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-                }
-        } else {
+        if (aggr_mode == AGGR_GLOBAL) {
                 list_for_each_entry(counter, &evsel_list->entries, node) {
                         read_counter_aggr(counter);
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
                                              thread_map__nr(evsel_list->threads));
                 }
+        } else {
+                list_for_each_entry(counter, &evsel_list->entries, node) {
+                        read_counter(counter);
+                        perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
+                }
         }
 
         return WEXITSTATUS(status);
@@ -556,26 +566,37 @@ static void print_noise(struct perf_evsel *evsel, double avg)
         print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void aggr_printout(struct perf_evsel *evsel, int cpu, int nr)
 {
-        double msecs = avg / 1e6;
-        char cpustr[16] = { '\0', };
-        const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
-
-        if (aggr_socket)
-                sprintf(cpustr, "S%*d%s%*d%s",
+        switch (aggr_mode) {
+        case AGGR_SOCKET:
+                fprintf(output, "S%*d%s%*d%s",
                         csv_output ? 0 : -5,
                         cpu,