1 files changed, 196 insertions, 43 deletions

diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 1b52402a8923..8bbeb2dc76fd 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -12,15 +12,19 @@
 #include "cpumap.h"
 #include "debug.h"
 #include "env.h"
+#include "pmu.h"
+#include "pmus.h"
 
-#define CORE_SIB_FMT \
+#define PACKAGE_CPUS_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/package_cpus_list"
+#define PACKAGE_CPUS_FMT_OLD \
 	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
-#define DIE_SIB_FMT \
+#define DIE_CPUS_FMT \
 	"%s/devices/system/cpu/cpu%d/topology/die_cpus_list"
-#define THRD_SIB_FMT \
-	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
-#define THRD_SIB_FMT_NEW \
+#define CORE_CPUS_FMT \
 	"%s/devices/system/cpu/cpu%d/topology/core_cpus_list"
+#define CORE_CPUS_FMT_OLD \
+	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 #define NODE_ONLINE_FMT \
 	"%s/devices/system/node/online"
 #define NODE_MEMINFO_FMT \
@@ -38,8 +42,12 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu)
 	u32 i = 0;
 	int ret = -1;
 
-	scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
+	if (access(filename, F_OK) == -1) {
+		scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT_OLD,
+			sysfs__mountpoint(), cpu);
+	}
 	fp = fopen(filename, "r");
 	if (!fp)
 		goto try_dies;
@@ -53,23 +61,23 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu)
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->core_sib; i++) {
-		if (!strcmp(buf, tp->core_siblings[i]))
+	for (i = 0; i < tp->package_cpus_lists; i++) {
+		if (!strcmp(buf, tp->package_cpus_list[i]))
 			break;
 	}
-	if (i == tp->core_sib) {
-		tp->core_siblings[i] = buf;
-		tp->core_sib++;
+	if (i == tp->package_cpus_lists) {
+		tp->package_cpus_list[i] = buf;
+		tp->package_cpus_lists++;
 		buf = NULL;
 		len = 0;
 	}
 	ret = 0;
 
 try_dies:
-	if (!tp->die_siblings)
+	if (!tp->die_cpus_list)
 		goto try_threads;
 
-	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
 	fp = fopen(filename, "r");
 	if (!fp)
@@ -84,23 +92,23 @@ try_dies:
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->die_sib; i++) {
-		if (!strcmp(buf, tp->die_siblings[i]))
+	for (i = 0; i < tp->die_cpus_lists; i++) {
+		if (!strcmp(buf, tp->die_cpus_list[i]))
 			break;
 	}
-	if (i == tp->die_sib) {
-		tp->die_siblings[i] = buf;
-		tp->die_sib++;
+	if (i == tp->die_cpus_lists) {
+		tp->die_cpus_list[i] = buf;
+		tp->die_cpus_lists++;
 		buf = NULL;
 		len = 0;
 	}
 	ret = 0;
 
 try_threads:
-	scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW,
+	scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
 	if (access(filename, F_OK) == -1) {
-		scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+		scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT_OLD,
 			  sysfs__mountpoint(), cpu);
 	}
 	fp = fopen(filename, "r");
@@ -114,13 +122,13 @@ try_threads:
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->thread_sib; i++) {
-		if (!strcmp(buf, tp->thread_siblings[i]))
+	for (i = 0; i < tp->core_cpus_lists; i++) {
+		if (!strcmp(buf, tp->core_cpus_list[i]))
 			break;
 	}
-	if (i == tp->thread_sib) {
-		tp->thread_siblings[i] = buf;
-		tp->thread_sib++;
+	if (i == tp->core_cpus_lists) {
+		tp->core_cpus_list[i] = buf;
+		tp->core_cpus_lists++;
 		buf = NULL;
 	}
 	ret = 0;
@@ -138,20 +146,79 @@ void cpu_topology__delete(struct cpu_topology *tp)
 	if (!tp)
 		return;
 
-	for (i = 0 ; i < tp->core_sib; i++)
-		zfree(&tp->core_siblings[i]);
+	for (i = 0 ; i < tp->package_cpus_lists; i++)
+		zfree(&tp->package_cpus_list[i]);
 
-	if (tp->die_sib) {
-		for (i = 0 ; i < tp->die_sib; i++)
-			zfree(&tp->die_siblings[i]);
-	}
+	for (i = 0 ; i < tp->die_cpus_lists; i++)
+		zfree(&tp->die_cpus_list[i]);
 
-	for (i = 0 ; i < tp->thread_sib; i++)
-		zfree(&tp->thread_siblings[i]);
+	for (i = 0 ; i < tp->core_cpus_lists; i++)
+		zfree(&tp->core_cpus_list[i]);
 
 	free(tp);
 }
 
+bool cpu_topology__smt_on(const struct cpu_topology *topology)
+{
+	for (u32 i = 0; i < topology->core_cpus_lists; i++) {
+		const char *cpu_list = topology->core_cpus_list[i];
+
+		/*
+		 * If there is a need to separate siblings in a core then SMT is
+		 * enabled.
+		 */
+		if (strchr(cpu_list, ',') || strchr(cpu_list, '-'))
+			return true;
+	}
+	return false;
+}
+
+bool cpu_topology__core_wide(const struct cpu_topology *topology,
+			     const char *user_requested_cpu_list)
+{
+	struct perf_cpu_map *user_requested_cpus;
+
+	/*
+	 * If user_requested_cpu_list is empty then all CPUs are recorded and so
+	 * core_wide is true.
+	 */
+	if (!user_requested_cpu_list)
+		return true;
+
+	user_requested_cpus = perf_cpu_map__new(user_requested_cpu_list);
+	/* Check that every user requested CPU is the complete set of SMT threads on a core. */
+	for (u32 i = 0; i < topology->core_cpus_lists; i++) {
+		const char *core_cpu_list = topology->core_cpus_list[i];
+		struct perf_cpu_map *core_cpus = perf_cpu_map__new(core_cpu_list);
+		struct perf_cpu cpu;
+		int idx;
+		bool has_first, first = true;
+
+		perf_cpu_map__for_each_cpu(cpu, idx, core_cpus) {
+			if (first) {
+				has_first = perf_cpu_map__has(user_requested_cpus, cpu);
+				first = false;
+			} else {
+				/*
+				 * If the first core CPU is user requested then
+				 * all subsequent CPUs in the core must be user
+				 * requested too. If the first CPU isn't user
+				 * requested then none of the others must be
+				 * too.
+				 */
+				if (perf_cpu_map__has(user_requested_cpus, cpu) != has_first) {
+					perf_cpu_map__put(core_cpus);
+					perf_cpu_map__put(user_requested_cpus);
+					return false;
+				}
+			}
+		}
+		perf_cpu_map__put(core_cpus);
+	}
+	perf_cpu_map__put(user_requested_cpus);
+	return true;
+}
+
 static bool has_die_topology(void)
 {
 	char filename[MAXPATHLEN];
@@ -160,10 +227,11 @@ static bool has_die_topology(void)
 	if (uname(&uts) < 0)
 		return false;
 
-	if (strncmp(uts.machine, "x86_64", 6))
+	if (strncmp(uts.machine, "x86_64", 6) &&
+	    strncmp(uts.machine, "s390x", 5))
 		return false;
 
-	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
 		  sysfs__mountpoint(), 0);
 	if (access(filename, F_OK) == -1)
 		return false;
@@ -171,6 +239,20 @@ static bool has_die_topology(void)
 	return true;
 }
 
+const struct cpu_topology *online_topology(void)
+{
+	static const struct cpu_topology *topology;
+
+	if (!topology) {
+		topology = cpu_topology__new();
+		if (!topology) {
+			pr_err("Error creating CPU topology");
+			abort();
+		}
+	}
+	return topology;
+}
+
 struct cpu_topology *cpu_topology__new(void)
 {
 	struct cpu_topology *tp = NULL;
@@ -182,10 +264,10 @@ struct cpu_topology *cpu_topology__new(void)
 	struct perf_cpu_map *map;
 	bool has_die = has_die_topology();
 
-	ncpus = cpu__max_present_cpu();
+	ncpus = cpu__max_present_cpu().cpu;
 
 	/* build online CPU map */
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		return NULL;
@@ -204,16 +286,16 @@ struct cpu_topology *cpu_topology__new(void)
 
 	tp = addr;
 	addr += sizeof(*tp);
-	tp->core_siblings = addr;
+	tp->package_cpus_list = addr;
 	addr += sz;
 	if (has_die) {
-		tp->die_siblings = addr;
+		tp->die_cpus_list = addr;
 		addr += sz;
 	}
-	tp->thread_siblings = addr;
+	tp->core_cpus_list = addr;
 
 	for (i = 0; i < nr; i++) {
-		if (!cpu_map__has(map, i))
+		if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i }))
 			continue;
 
 		ret = build_cpu_topology(tp, i);
@@ -319,7 +401,7 @@ struct numa_topology *numa_topology__new(void)
 	if (!node_map)
 		goto out;
 
-	nr = (u32) node_map->nr;
+	nr = (u32) perf_cpu_map__nr(node_map);
 
 	tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0])*nr);
 	if (!tp)
@@ -328,7 +410,7 @@ struct numa_topology *numa_topology__new(void)
 	tp->nr = nr;
 
 	for (i = 0; i < nr; i++) {
-		if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+		if (load_numa_node(&tp->nodes[i], perf_cpu_map__cpu(node_map, i).cpu)) {
 			numa_topology__delete(tp);
 			tp = NULL;
 			break;
@@ -351,3 +433,74 @@ void numa_topology__delete(struct numa_topology *tp)
 
 	free(tp);
 }
+
+static int load_hybrid_node(struct hybrid_topology_node *node,
+			    struct perf_pmu *pmu)
+{
+	char *buf = NULL, *p;
+	FILE *fp;
+	size_t len = 0;
+
+	node->pmu_name = strdup(pmu->name);
+	if (!node->pmu_name)
+		return -1;
+
+	fp = perf_pmu__open_file(pmu, "cpus");
+	if (!fp)
+		goto err;
+
+	if (getline(&buf, &len, fp) <= 0) {
+		fclose(fp);
+		goto err;
+	}
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	fclose(fp);
+	node->cpus = buf;
+	return 0;
+
+err:
+	zfree(&node->pmu_name);
+	free(buf);
+	return -1;
+}
+
+struct hybrid_topology *hybrid_topology__new(void)
+{
+	struct perf_pmu *pmu = NULL;
+	struct hybrid_topology *tp = NULL;
+	int nr = perf_pmus__num_core_pmus(), i = 0;
+
+	if (nr <= 1)
+		return NULL;
+
+	tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0]) * nr);
+	if (!tp)
+		return NULL;
+
+	tp->nr = nr;
+	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+		if (load_hybrid_node(&tp->nodes[i], pmu)) {
+			hybrid_topology__delete(tp);
+			return NULL;
+		}
+		i++;
+	}
+
+	return tp;
+}
+
+void hybrid_topology__delete(struct hybrid_topology *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->nr; i++) {
+		zfree(&tp->nodes[i].pmu_name);
+		zfree(&tp->nodes[i].cpus);
+	}
+
+	free(tp);
+}