perf cpumap: Use perf_cpu_map__for_each_cpu when possible

Rather than manually iterating the CPU map, use
perf_cpu_map__for_each_cpu(). When possible tidy local variables.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: André Almeida <andrealmeid@igalia.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Atish Patra <atishp@rivosinc.com>
Cc: Changbin Du <changbin.du@huawei.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paran Lee <p4ranlee@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Jihong <yangjihong1@huawei.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Link: https://lore.kernel.org/r/20240202234057.2085863-9-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/arm64/util/header.c

@@ -4,8 +4,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
-#include <util/cpumap.h>
-#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include <errno.h>
 #include "debug.h"
@@ -19,18 +17,18 @@
 static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
-	int ret = EINVAL;
+	struct perf_cpu cpu;
+	int idx, ret = EINVAL;
 
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
 
-	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		char path[PATH_MAX];
 		FILE *file;
 
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
-			  sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu);
+			  sysfs, cpu.cpu);
 
 		file = fopen(path, "r");
 		if (!file) {

tools/perf/tests/bitmap.c

@@ -11,18 +11,19 @@
 static unsigned long *get_bitmap(const char *str, int nbits)
 {
 	struct perf_cpu_map *map = perf_cpu_map__new(str);
-	unsigned long *bm = NULL;
-	int i;
+	unsigned long *bm;
 
 	bm = bitmap_zalloc(nbits);
 
 	if (map && bm) {
-		for (i = 0; i < perf_cpu_map__nr(map); i++)
-			__set_bit(perf_cpu_map__cpu(map, i).cpu, bm);
+		int i;
+		struct perf_cpu cpu;
+
+		perf_cpu_map__for_each_cpu(cpu, i, map)
+			__set_bit(cpu.cpu, bm);
 	}
 
-	if (map)
-		perf_cpu_map__put(map);
+	perf_cpu_map__put(map);
 	return bm;
 }
 

tools/perf/tests/topology.c

@@ -68,6 +68,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	};
 	int i;
 	struct aggr_cpu_id id;
+	struct perf_cpu cpu;
 
 	session = perf_session__new(&data, NULL);
 	TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
@@ -113,8 +114,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
 
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
-		struct perf_cpu cpu = { .cpu = i };
-
+		cpu.cpu = i;
 		if (!perf_cpu_map__has(map, cpu))
 			continue;
 		pr_debug("CPU %d, core %d, socket %d\n", i,
@@ -123,48 +123,48 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that CPU ID contains socket, die, core and CPU
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__cpu(cpu, NULL);
 		TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match",
-				perf_cpu_map__cpu(map, i).cpu == id.cpu.cpu);
+				cpu.cpu == id.cpu.cpu);
 
 		TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
+			session->header.env.cpu[cpu.cpu].core_id == id.core);
 		TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.cpu].die_id == id.die);
 		TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Cpu map - Thread IDX is set", id.thread_idx == -1);
 	}
 
 	// Test that core ID contains socket, die and core
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__core(cpu, NULL);
 		TEST_ASSERT_VAL("Core map - Core ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
+			session->header.env.cpu[cpu.cpu].core_id == id.core);
 
 		TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Core map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.cpu].die_id == id.die);
 		TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Core map - Thread IDX is set", id.thread_idx == -1);
 	}
 
 	// Test that die ID contains socket and die
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__die(cpu, NULL);
 		TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Die map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.cpu].die_id == id.die);
 
 		TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
@@ -173,10 +173,10 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that socket ID contains only socket
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__socket(cpu, NULL);
 		TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
@@ -187,10 +187,10 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that node ID contains only node
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__node(cpu, NULL);
 		TEST_ASSERT_VAL("Node map - Node ID doesn't match",
-				cpu__get_node(perf_cpu_map__cpu(map, i)) == id.node);
+				cpu__get_node(cpu) == id.node);
 		TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
 		TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
 		TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);

tools/perf/util/bpf_kwork.c

@@ -147,12 +147,12 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, key, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list != NULL) {
-		fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+		int idx, nr_cpus;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+		int fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
 			return -1;
@@ -165,8 +165,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);
@@ -181,6 +181,8 @@ static int setup_filters(struct perf_kwork *kwork)
 	}
 
 	if (kwork->profile_name != NULL) {
+		int key, fd;
+
 		if (strlen(kwork->profile_name) >= MAX_KWORKNAME) {
 			pr_err("Requested name filter %s too large, limit to %d\n",
 			       kwork->profile_name, MAX_KWORKNAME - 1);

tools/perf/util/bpf_kwork_top.c

@@ -122,11 +122,11 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list) {
+		int idx, nr_cpus, fd;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+
 		fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter);
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
@@ -140,8 +140,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);

tools/perf/util/cpumap.c

@@ -655,10 +655,10 @@ static char hex_char(unsigned char val)
 
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 {
-	int i, cpu;
+	int idx;
 	char *ptr = buf;
 	unsigned char *bitmap;
-	struct perf_cpu last_cpu = perf_cpu_map__cpu(map, perf_cpu_map__nr(map) - 1);
+	struct perf_cpu c, last_cpu = perf_cpu_map__max(map);
 
 	if (buf == NULL)
 		return 0;
@@ -669,12 +669,10 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 		return 0;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		cpu = perf_cpu_map__cpu(map, i).cpu;
-		bitmap[cpu / 8] |= 1 << (cpu % 8);
-	}
+	perf_cpu_map__for_each_cpu(c, idx, map)
+		bitmap[c.cpu / 8] |= 1 << (c.cpu % 8);
 
-	for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+	for (int cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
 		unsigned char bits = bitmap[cpu / 8];
 
 		if (cpu % 8)

tools/perf/util/scripting-engines/trace-event-python.c

@@ -1699,13 +1699,15 @@ static void python_process_stat(struct perf_stat_config *config,
 {
 	struct perf_thread_map *threads = counter->core.threads;
 	struct perf_cpu_map *cpus = counter->core.cpus;
-	int cpu, thread;
 
-	for (thread = 0; thread < perf_thread_map__nr(threads); thread++) {
-		for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
-			process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
+	for (int thread = 0; thread < perf_thread_map__nr(threads); thread++) {
+		int idx;
+		struct perf_cpu cpu;
+
+		perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+			process_stat(counter, cpu,
 				     perf_thread_map__pid(threads, thread), tstamp,
-				     perf_counts(counter->counts, cpu, thread));
+				     perf_counts(counter->counts, idx, thread));
 		}
 	}
 }

tools/perf/util/session.c

@@ -2749,6 +2749,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	int i, err = -1;
 	struct perf_cpu_map *map;
 	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
+	struct perf_cpu cpu;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2770,9 +2771,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		return -1;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
-
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
 		if (cpu.cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu.cpu);

tools/perf/util/svghelper.c

@@ -725,26 +725,24 @@ static void scan_core_topology(int *map, struct topology *t, int nr_cpus)
 
 static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 {
-	int i;
-	int ret = 0;
-	struct perf_cpu_map *m;
-	struct perf_cpu c;
+	int idx, ret = 0;
+	struct perf_cpu_map *map;
+	struct perf_cpu cpu;
 
-	m = perf_cpu_map__new(s);
-	if (!m)
+	map = perf_cpu_map__new(s);
+	if (!map)
 		return -1;
 
-	for (i = 0; i < perf_cpu_map__nr(m); i++) {
-		c = perf_cpu_map__cpu(m, i);
-		if (c.cpu >= nr_cpus) {
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		if (cpu.cpu >= nr_cpus) {
 			ret = -1;
 			break;
 		}
 
-		__set_bit(c.cpu, cpumask_bits(b));
+		__set_bit(cpu.cpu, cpumask_bits(b));
 	}
 
-	perf_cpu_map__put(m);
+	perf_cpu_map__put(map);
 
 	return ret;
 }