perf cpumap: Reduce cpu size from int to int16_t

Fewer than 32k logical CPUs are currently supported by perf. A cpumap
is indexed by an integer (see perf_cpu_map__cpu) yielding a perf_cpu
that wraps a 4-byte int for the logical CPU - the wrapping is done
deliberately to avoid confusing a logical CPU with an index into a
cpumap. Using a 4-byte int within the perf_cpu is larger than required
so this patch reduces it to the 2-byte int16_t. For a cpumap
containing 16 entries this will reduce the array size from 64 to 32
bytes. For very large servers with lots of logical CPUs the size
savings will be greater.

Signed-off-by: Ian Rogers <[email protected]>
Reviewed-by: James Clark <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

Author: captain5050

tools/lib/perf/cpumap.c

@@ -185,7 +185,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	while (isdigit(*cpu_list)) {
 		p = NULL;
 		start_cpu = strtoul(cpu_list, &p, 0);
-		if (start_cpu >= INT_MAX
+		if (start_cpu >= INT16_MAX
 		    || (*p != '\0' && *p != ',' && *p != '-' && *p != '\n'))
 			goto invalid;
 
@@ -194,7 +194,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 			p = NULL;
 			end_cpu = strtoul(cpu_list, &p, 0);
 
-			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
+			if (end_cpu >= INT16_MAX || (*p != '\0' && *p != ',' && *p != '\n'))
 				goto invalid;
 
 			if (end_cpu < start_cpu)
@@ -209,7 +209,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i].cpu == (int)start_cpu)
+				if (tmp_cpus[i].cpu == (int16_t)start_cpu)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
@@ -219,7 +219,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 					goto invalid;
 				tmp_cpus = tmp;
 			}
-			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
+			tmp_cpus[nr_cpus++].cpu = (int16_t)start_cpu;
 		}
 		if (*p)
 			++p;

tools/lib/perf/include/perf/cpumap.h

@@ -4,10 +4,11 @@
 
 #include <perf/core.h>
 #include <stdbool.h>
+#include <stdint.h>
 
 /** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
 struct perf_cpu {
-	int cpu;
+	int16_t cpu;
 };
 
 struct perf_cache {

tools/perf/util/cpumap.c

@@ -67,19 +67,23 @@ static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_m
 	struct perf_cpu_map *map;
 
 	map = perf_cpu_map__empty_new(data->cpus_data.nr);
-	if (map) {
-		unsigned i;
-
-		for (i = 0; i < data->cpus_data.nr; i++) {
-			/*
-			 * Special treatment for -1, which is not real cpu number,
-			 * and we need to use (int) -1 to initialize map[i],
-			 * otherwise it would become 65535.
-			 */
-			if (data->cpus_data.cpu[i] == (u16) -1)
-				RC_CHK_ACCESS(map)->map[i].cpu = -1;
-			else
-				RC_CHK_ACCESS(map)->map[i].cpu = (int) data->cpus_data.cpu[i];
+	if (!map)
+		return NULL;
+
+	for (unsigned int i = 0; i < data->cpus_data.nr; i++) {
+		/*
+		 * Special treatment for -1, which is not real cpu number,
+		 * and we need to use (int) -1 to initialize map[i],
+		 * otherwise it would become 65535.
+		 */
+		if (data->cpus_data.cpu[i] == (u16) -1) {
+			RC_CHK_ACCESS(map)->map[i].cpu = -1;
+		} else if (data->cpus_data.cpu[i] < INT16_MAX) {
+			RC_CHK_ACCESS(map)->map[i].cpu = (int16_t) data->cpus_data.cpu[i];
+		} else {
+			pr_err("Invalid cpumap entry %u\n", data->cpus_data.cpu[i]);
+			perf_cpu_map__put(map);
+			return NULL;
 		}
 	}
 
@@ -106,8 +110,15 @@ static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_
 		int cpu;
 
 		perf_record_cpu_map_data__read_one_mask(data, i, local_copy);
-		for_each_set_bit(cpu, local_copy, 64)
-			RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i;
+		for_each_set_bit(cpu, local_copy, 64) {
+			if (cpu + cpus_per_i < INT16_MAX) {
+				RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i;
+			} else {
+				pr_err("Invalid cpumap entry %d\n", cpu + cpus_per_i);
+				perf_cpu_map__put(map);
+				return NULL;
+			}
+		}
 	}
 	return map;
 
@@ -127,8 +138,15 @@ static struct perf_cpu_map *cpu_map__from_range(const struct perf_record_cpu_map
 		RC_CHK_ACCESS(map)->map[i++].cpu = -1;
 
 	for (int cpu = data->range_cpu_data.start_cpu; cpu <= data->range_cpu_data.end_cpu;
-	     i++, cpu++)
-		RC_CHK_ACCESS(map)->map[i].cpu = cpu;
+	     i++, cpu++) {
+		if (cpu < INT16_MAX) {
+			RC_CHK_ACCESS(map)->map[i].cpu = cpu;
+		} else {
+			pr_err("Invalid cpumap entry %d\n", cpu);
+			perf_cpu_map__put(map);
+			return NULL;
+		}
+	}
 
 	return map;
 }
@@ -427,7 +445,7 @@ static void set_max_cpu_num(void)
 {
 	const char *mnt;
 	char path[PATH_MAX];
-	int ret = -1;
+	int max, ret = -1;
 
 	/* set up default */
 	max_cpu_num.cpu = 4096;
@@ -444,19 +462,27 @@ static void set_max_cpu_num(void)
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_cpu_num.cpu);
+	ret = get_max_num(path, &max);
 	if (ret)
 		goto out;
 
+	max_cpu_num.cpu = max;
+
 	/* get the highest present cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
 	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_present_cpu_num.cpu);
+	ret = get_max_num(path, &max);
 
+	if (!ret && max > INT16_MAX) {
+		pr_err("Read out of bounds max cpus of %d\n", max);
+		ret = -1;
+	}
+	if (!ret)
+		max_present_cpu_num.cpu = (int16_t)max;
 out:
 	if (ret)
 		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
@@ -606,7 +632,7 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
 #define COMMA first ? "" : ","
 
 	for (i = 0; i < perf_cpu_map__nr(map) + 1; i++) {
-		struct perf_cpu cpu = { .cpu = INT_MAX };
+		struct perf_cpu cpu = { .cpu = INT16_MAX };
 		bool last = i == perf_cpu_map__nr(map);
 
 		if (!last)

tools/perf/util/env.c

@@ -543,7 +543,7 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 
 		for (i = 0; i < env->nr_numa_nodes; i++) {
 			nn = &env->numa_nodes[i];
-			nr = max(nr, perf_cpu_map__max(nn->map).cpu);
+			nr = max(nr, (int)perf_cpu_map__max(nn->map).cpu);
 		}
 
 		nr++;