perf env: Introduce read_cpu_topology_map() method

Out of the code to write the cpu topology map in the perf.data file
header.

Now if one needs the CPU topology map for the running machine, one needs
to call perf_env__read_cpu_topology_map(perf_env) and the info will be
stored in perf_env.cpu.

For now we're using a global perf_env variable, that will have its
contents freed after we run a builtin.

v2: Check perf_env__read_cpu_topology_map() return in
    write_cpu_topology() (Kan Liang)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1441828225-667-5-git-send-email-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/perf.c

@@ -8,6 +8,7 @@
  */
 #include "builtin.h"
 
+#include "util/env.h"
 #include "util/exec_cmd.h"
 #include "util/cache.h"
 #include "util/quote.h"
@@ -369,6 +370,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 
 	status = p->fn(argc, argv, prefix);
 	exit_browser(status);
+	perf_env__exit(&perf_env);
 
 	if (status)
 		return status & 0xff;

tools/perf/util/env.c

@@ -1,3 +1,4 @@
+#include "cpumap.h"
 #include "env.h"
 #include "util.h"
 
@@ -56,3 +57,30 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 out_enomem:
 	return -ENOMEM;
 }
+
+int perf_env__read_cpu_topology_map(struct perf_env *env)
+{
+	int cpu, nr_cpus;
+
+	if (env->cpu != NULL)
+		return 0;
+
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+
+	nr_cpus = env->nr_cpus_avail;
+	if (nr_cpus == -1)
+		return -EINVAL;
+
+	env->cpu = calloc(nr_cpus, sizeof(env->cpu[0]));
+	if (env->cpu == NULL)
+		return -ENOMEM;
+
+	for (cpu = 0; cpu < nr_cpus; ++cpu) {
+		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);
+		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);
+	}
+
+	env->nr_cpus_avail = nr_cpus;
+	return 0;
+}

tools/perf/util/env.h

@@ -39,4 +39,6 @@ void perf_env__exit(struct perf_env *env);
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
+int perf_env__read_cpu_topology_map(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */

tools/perf/util/header.c

@@ -415,8 +415,6 @@ struct cpu_topo {
 	u32 thread_sib;
 	char **core_siblings;
 	char **thread_siblings;
-	int *core_id;
-	int *phy_pkg_id;
 };
 
 static int build_cpu_topo(struct cpu_topo *tp, int cpu)
@@ -479,9 +477,6 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu)
 	}
 	ret = 0;
 done:
-	tp->core_id[cpu] = cpu_map__get_core_id(cpu);
-	tp->phy_pkg_id[cpu] = cpu_map__get_socket_id(cpu);
-
 	if(fp)
 		fclose(fp);
 	free(buf);
@@ -509,7 +504,7 @@ static struct cpu_topo *build_cpu_topology(void)
 	struct cpu_topo *tp;
 	void *addr;
 	u32 nr, i;
-	size_t sz, sz_id;
+	size_t sz;
 	long ncpus;
 	int ret = -1;
 
@@ -520,9 +515,8 @@ static struct cpu_topo *build_cpu_topology(void)
 	nr = (u32)(ncpus & UINT_MAX);
 
 	sz = nr * sizeof(char *);
-	sz_id = nr * sizeof(int);
 
-	addr = calloc(1, sizeof(*tp) + 2 * sz + 2 * sz_id);
+	addr = calloc(1, sizeof(*tp) + 2 * sz);
 	if (!addr)
 		return NULL;
 
@@ -532,10 +526,6 @@ static struct cpu_topo *build_cpu_topology(void)
 	tp->core_siblings = addr;
 	addr += sz;
 	tp->thread_siblings = addr;
-	addr += sz;
-	tp->core_id = addr;
-	addr += sz_id;
-	tp->phy_pkg_id = addr;
 
 	for (i = 0; i < nr; i++) {
 		ret = build_cpu_topo(tp, i);
@@ -554,7 +544,7 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
 {
 	struct cpu_topo *tp;
 	u32 i;
-	int ret;
+	int ret, j;
 
 	tp = build_cpu_topology();
 	if (!tp)
@@ -579,11 +569,17 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
 			break;
 	}
 
-	for (i = 0; i < tp->cpu_nr; i++) {
-		ret = do_write(fd, &tp->core_id[i], sizeof(int));
+	ret = perf_env__read_cpu_topology_map(&perf_env);
+	if (ret < 0)
+		goto done;
+
+	for (j = 0; j < perf_env.nr_cpus_avail; j++) {
+		ret = do_write(fd, &perf_env.cpu[j].core_id,
+			       sizeof(perf_env.cpu[j].core_id));
 		if (ret < 0)
 			return ret;
-		ret = do_write(fd, &tp->phy_pkg_id[i], sizeof(int));
+		ret = do_write(fd, &perf_env.cpu[j].socket_id,
+			       sizeof(perf_env.cpu[j].socket_id));
 		if (ret < 0)
 			return ret;
 	}