perf header: Support HYBRID_TOPOLOGY feature

It is useful to let the user know about the hybrid topology.

Add the HYBRID_TOPOLOGY feature in header to indicate the core CPUs
and the atom CPUs.

With this patch a perf.data generated on a hybrid platform reports
the hybrid CPU list:

  root@otcpl-adl-s-2:~# perf report --header-only -I
  ...
  # hybrid cpu system:
  # cpu_core cpu list : 0-15
  # cpu_atom cpu list : 16-23

For a perf.data generated on a non-hybrid platform, reports a message
that HYBRID_TOPOLOGY is missing:

  root@kbl-ppc:~# perf report --header-only -I
  ...
  # missing features: TRACING_DATA BRANCH_STACK GROUP_DESC AUXTRACE STAT CLOCKID DIR_FORMAT COMPRESSED CLOCK_DATA HYBRID_TOPOLOGY

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210514122948.9472-2-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf.data-file-format.txt

@@ -402,6 +402,23 @@ struct {
 	u64 clockid_time_ns;
 };
 
+	HEADER_HYBRID_TOPOLOGY = 30,
+
+Indicate the hybrid CPUs. The format of data is as below.
+
+struct {
+	u32 nr;
+	struct {
+		char pmu_name[];
+		char cpus[];
+	} [nr]; /* Variable length records */
+};
+
+Example:
+  hybrid cpu system:
+  cpu_core cpu list : 0-15
+  cpu_atom cpu list : 16-23
+
 	other bits are reserved and should ignored for now
 	HEADER_FEAT_BITS	= 256,
 

tools/perf/util/cputopo.c

@@ -12,6 +12,7 @@
 #include "cpumap.h"
 #include "debug.h"
 #include "env.h"
+#include "pmu-hybrid.h"
 
 #define CORE_SIB_FMT \
 	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
@@ -351,3 +352,82 @@ void numa_topology__delete(struct numa_topology *tp)
 
 	free(tp);
 }
+
+static int load_hybrid_node(struct hybrid_topology_node *node,
+			    struct perf_pmu *pmu)
+{
+	const char *sysfs;
+	char path[PATH_MAX];
+	char *buf = NULL, *p;
+	FILE *fp;
+	size_t len = 0;
+
+	node->pmu_name = strdup(pmu->name);
+	if (!node->pmu_name)
+		return -1;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		goto err;
+
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_CPU, sysfs, pmu->name);
+	fp = fopen(path, "r");
+	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;
+	struct hybrid_topology *tp = NULL;
+	u32 nr, i = 0;
+
+	nr = perf_pmu__hybrid_pmu_num();
+	if (nr == 0)
+		return NULL;
+
+	tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0]) * nr);
+	if (!tp)
+		return NULL;
+
+	tp->nr = nr;
+	perf_pmu__for_each_hybrid_pmu(pmu) {
+		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);
+}

tools/perf/util/cputopo.h

@@ -25,10 +25,23 @@ struct numa_topology {
 	struct numa_topology_node	nodes[];
 };
 
+struct hybrid_topology_node {
+	char		*pmu_name;
+	char		*cpus;
+};
+
+struct hybrid_topology {
+	u32				nr;
+	struct hybrid_topology_node	nodes[];
+};
+
 struct cpu_topology *cpu_topology__new(void);
 void cpu_topology__delete(struct cpu_topology *tp);
 
 struct numa_topology *numa_topology__new(void);
 void numa_topology__delete(struct numa_topology *tp);
 
+struct hybrid_topology *hybrid_topology__new(void);
+void hybrid_topology__delete(struct hybrid_topology *tp);
+
 #endif /* __PERF_CPUTOPO_H */

tools/perf/util/env.c

@@ -202,6 +202,12 @@ void perf_env__exit(struct perf_env *env)
 	for (i = 0; i < env->nr_memory_nodes; i++)
 		zfree(&env->memory_nodes[i].set);
 	zfree(&env->memory_nodes);
+
+	for (i = 0; i < env->nr_hybrid_nodes; i++) {
+		zfree(&env->hybrid_nodes[i].pmu_name);
+		zfree(&env->hybrid_nodes[i].cpus);
+	}
+	zfree(&env->hybrid_nodes);
 }
 
 void perf_env__init(struct perf_env *env __maybe_unused)

tools/perf/util/env.h

@@ -37,6 +37,11 @@ struct memory_node {
 	unsigned long	*set;
 };
 
+struct hybrid_node {
+	char	*pmu_name;
+	char	*cpus;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -59,6 +64,7 @@ struct perf_env {
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	int			nr_cpu_pmu_caps;
+	int			nr_hybrid_nodes;
 	char			*cmdline;
 	const char		**cmdline_argv;
 	char			*sibling_cores;
@@ -77,6 +83,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	struct hybrid_node	*hybrid_nodes;
 #ifdef HAVE_LIBBPF_SUPPORT
 	/*
 	 * bpf_info_lock protects bpf rbtrees. This is needed because the

tools/perf/util/header.c

@@ -932,6 +932,40 @@ static int write_clock_data(struct feat_fd *ff,
 	return do_write(ff, data64, sizeof(*data64));
 }
 
+static int write_hybrid_topology(struct feat_fd *ff,
+				 struct evlist *evlist __maybe_unused)
+{
+	struct hybrid_topology *tp;
+	int ret;
+	u32 i;
+
+	tp = hybrid_topology__new();
+	if (!tp)
+		return -ENOENT;
+
+	ret = do_write(ff, &tp->nr, sizeof(u32));
+	if (ret < 0)
+		goto err;
+
+	for (i = 0; i < tp->nr; i++) {
+		struct hybrid_topology_node *n = &tp->nodes[i];
+
+		ret = do_write_string(ff, n->pmu_name);
+		if (ret < 0)
+			goto err;
+
+		ret = do_write_string(ff, n->cpus);
+		if (ret < 0)
+			goto err;
+	}
+
+	ret = 0;
+
+err:
+	hybrid_topology__delete(tp);
+	return ret;
+}
+
 static int write_dir_format(struct feat_fd *ff,
 			    struct evlist *evlist __maybe_unused)
 {
@@ -1623,6 +1657,18 @@ static void print_clock_data(struct feat_fd *ff, FILE *fp)
 		    clockid_name(clockid));
 }
 
+static void print_hybrid_topology(struct feat_fd *ff, FILE *fp)
+{
+	int i;
+	struct hybrid_node *n;
+
+	fprintf(fp, "# hybrid cpu system:\n");
+	for (i = 0; i < ff->ph->env.nr_hybrid_nodes; i++) {
+		n = &ff->ph->env.hybrid_nodes[i];
+		fprintf(fp, "# %s cpu list : %s\n", n->pmu_name, n->cpus);
+	}
+}
+
 static void print_dir_format(struct feat_fd *ff, FILE *fp)
 {
 	struct perf_session *session;
@@ -2849,6 +2895,46 @@ static int process_clock_data(struct feat_fd *ff,
 	return 0;
 }
 
+static int process_hybrid_topology(struct feat_fd *ff,
+				   void *data __maybe_unused)
+{
+	struct hybrid_node *nodes, *n;
+	u32 nr, i;
+
+	/* nr nodes */
+	if (do_read_u32(ff, &nr))
+		return -1;
+
+	nodes = zalloc(sizeof(*nodes) * nr);
+	if (!nodes)
+		return -ENOMEM;
+
+	for (i = 0; i < nr; i++) {
+		n = &nodes[i];
+
+		n->pmu_name = do_read_string(ff);
+		if (!n->pmu_name)
+			goto error;
+
+		n->cpus = do_read_string(ff);
+		if (!n->cpus)
+			goto error;
+	}
+
+	ff->ph->env.nr_hybrid_nodes = nr;
+	ff->ph->env.hybrid_nodes = nodes;
+	return 0;
+
+error:
+	for (i = 0; i < nr; i++) {
+		free(nodes[i].pmu_name);
+		free(nodes[i].cpus);
+	}
+
+	free(nodes);
+	return -1;
+}
+
 static int process_dir_format(struct feat_fd *ff,
 			      void *_data __maybe_unused)
 {
@@ -3117,6 +3203,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(COMPRESSED,	compressed,	false),
 	FEAT_OPR(CPU_PMU_CAPS,	cpu_pmu_caps,	false),
 	FEAT_OPR(CLOCK_DATA,	clock_data,	false),
+	FEAT_OPN(HYBRID_TOPOLOGY,	hybrid_topology,	true),
 };
 
 struct header_print_data {

tools/perf/util/header.h

@@ -45,6 +45,7 @@ enum {
 	HEADER_COMPRESSED,
 	HEADER_CPU_PMU_CAPS,
 	HEADER_CLOCK_DATA,
+	HEADER_HYBRID_TOPOLOGY,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };

tools/perf/util/pmu-hybrid.h

@@ -19,4 +19,15 @@ struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name);
 bool perf_pmu__is_hybrid(const char *name);
 char *perf_pmu__hybrid_type_to_pmu(const char *type);
 
+static inline int perf_pmu__hybrid_pmu_num(void)
+{
+	struct perf_pmu *pmu;
+	int num = 0;
+
+	perf_pmu__for_each_hybrid_pmu(pmu)
+		num++;
+
+	return num;
+}
+
 #endif /* __PMU_HYBRID_H */