[PATCH 1/5] rtla: Replace get_nprocs_conf() with sysfs possible cpus

rtla uses get_nprocs_conf(), a standard libc routine, to retrieve the
total number of CPUs for the purpose of processing per-CPU data.

In some configurations, libc might return a different value than what is
seen by the kernel. To cover for this situation, replace the call to
get_nprocs_conf() with a newly added helper, get_possible_cpus().

get_possible_cpus() reads /sys/devices/system/cpu/possible and parses
the CPU list, identically to what libbpf_num_possible_cpus() does.
Additionally, it checks that the possible cpu list is zero-based and has
no holes by computing both the cpu count and the maximum cpu number.
Systems where /sys/.../cpu/possible is unreadable, is not zero-based,
or has holes, now report an error instead of crashing later due to unmet
assumptions.

Note that parse_cpu_set() cannot be used to parse
/sys/devices/system/cpu/possible, because it only supports CPU count of
1024 and lower. Higher CPU counts are not fully supported by rtla;
nr_cpus > 1024 is, though, so it has to be covered by the new
implementation in order to avoid a regression.

A new function, cpu_list_iterate(), is added to utils.c to contain the
cpu list parsing logic, which is now shared between the new function
get_possible_cpus() and the pre-existing parse_cpu_set().

Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Tomas Glozar <[email protected]>
---
 tools/tracing/rtla/src/common.c |  16 +++-
 tools/tracing/rtla/src/utils.c  | 165 +++++++++++++++++++++++++++-----
 tools/tracing/rtla/src/utils.h  |   3 +
 3 files changed, 156 insertions(+), 28 deletions(-)

diff --git a/tools/tracing/rtla/src/common.c b/tools/tracing/rtla/src/common.c
index 8c7f5e75b2ec8..20fae1f19cacf 100644
--- a/tools/tracing/rtla/src/common.c
+++ b/tools/tracing/rtla/src/common.c
@@ -6,7 +6,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <sys/sysinfo.h>
 
 #include "common.h"
 
@@ -155,7 +154,20 @@ int run_tool(struct tool_ops *ops, int argc, char *argv[])
 	bool stopped;
 	int retval;
 
-	nr_cpus = get_nprocs_conf();
+	nr_cpus = get_possible_cpus();
+	if (nr_cpus == -1) {
+		err_msg("Could not read number of possible cpus\n");
+		goto out_exit;
+	}
+	if (nr_cpus == -2) {
+		err_msg("Could not parse number of possible cpus\n");
+		goto out_exit;
+	}
+	if (nr_cpus == -3) {
+		err_msg("Unsupported non-contiguous or non-zero-based CPU topology\n");
+		goto out_exit;
+	}
+
 	params = ops->parse_args(argc, argv);
 	if (!params)
 		exit(1);
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index cb187e7d48d1c..d65de511be9e1 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -108,57 +108,170 @@ void get_duration(time_t start_time, char *output, int output_size)
 }
 
 /*
- * parse_cpu_set - parse a cpu_list filling cpu_set_t argument
+ * cpu_list_iterate - parse a cpu list and call a function on each element
  *
- * Receives a cpu list, like 1-3,5 (cpus 1, 2, 3, 5), and then set
- * filling cpu_set_t argument.
+ * If callback returns a non-zero value, the iteration is stopped.
  *
- * Returns 0 on success, 1 otherwise.
+ * Returns the number of cpus in the list (including duplicates) on success,
+ * callback return value on break, and -1 on error.
  */
-int parse_cpu_set(char *cpu_list, cpu_set_t *set)
+int cpu_list_iterate(const char *cpu_list, int (*callback)(int, void *), void *data)
 {
 	const char *p;
-	int end_cpu;
-	int cpu;
-	int i;
-
-	CPU_ZERO(set);
+	int i, cpu, end_cpu, count = 0, retval;
 
-	for (p = cpu_list; *p; ) {
+	for (p = cpu_list; *p && *p != '\n'; ) {
 		cpu = atoi(p);
-		if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus)
-			goto err;
+		if (cpu < 0 || (!cpu && *p != '0'))
+			return -1;
 
 		while (isdigit(*p))
 			p++;
 		if (*p == '-') {
 			p++;
 			end_cpu = atoi(p);
-			if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus)
-				goto err;
+			if (end_cpu < cpu || (!end_cpu && *p != '0'))
+				return -1;
 			while (isdigit(*p))
 				p++;
 		} else
 			end_cpu = cpu;
 
-		if (cpu == end_cpu) {
-			debug_msg("cpu_set: adding cpu %d\n", cpu);
-			CPU_SET(cpu, set);
-		} else {
-			for (i = cpu; i <= end_cpu; i++) {
-				debug_msg("cpu_set: adding cpu %d\n", i);
-				CPU_SET(i, set);
-			}
+		for (i = cpu; i <= end_cpu; i++) {
+			retval = callback(i, data);
+			if (retval)
+				return retval;
+			++count;
 		}
 
 		if (*p == ',')
 			p++;
 	}
 
+	return count;
+}
+
+static int max_cpu_callback(int i, void *data)
+{
+	int *max_cpu = data;
+
+	if (i > *max_cpu)
+		*max_cpu = i;
+
+	return 0;
+}
+
+static int tmp_cpu_set_callback(int i, void *data)
+{
+	bool *cpu_set = data;
+
+	cpu_set[i] = true;
+
+	return 0;
+}
+
+/*
+ * get_possible_cpus - get the number of possible CPUs from sysfs
+ *
+ * Parse /sys/devices/system/cpu/possible to determine the number of
+ * possible CPUs. Only contiguous zero-based CPUs lists are accepted.
+ *
+ * Returns the number of possible CPUs, or a negative value on error:
+ * - -1 if the file is unreadable,
+ * - -2 if parsing failed,
+ * - -3 if the cpu list is non-zero-based or non-contiguous.
+ */
+int get_possible_cpus(void)
+{
+	char *str = NULL;
+	size_t len = 0;
+	int nr_cpus = 0, max_cpu = -1, i;
+	FILE *fp;
+	bool *cpu_set;
+
+	fp = fopen("/sys/devices/system/cpu/possible", "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&str, &len, fp) < 1) {
+		/* cpu string should be at least 1 character */
+		if (str)
+			free(str);
+		fclose(fp);
+		return -1;
+	}
+
+	fclose(fp);
+
+	/* get maximum cpu number */
+	if (cpu_list_iterate(str, max_cpu_callback, &max_cpu) < 0) {
+		free(str);
+		return -2;
+	}
+
+	if (max_cpu < 0 || max_cpu == INT_MAX) {
+		/* empty or bogus cpu list */
+		free(str);
+		return -2;
+	}
+
+	/* get max cpu using dynamic array, as nr_cpus might be > 1024 */
+	cpu_set = calloc(max_cpu + 1, sizeof(bool));
+	if (!cpu_set) {
+		free(str);
+		return -2;
+	}
+	if (cpu_list_iterate(str, tmp_cpu_set_callback, cpu_set) < 0) {
+		free(str);
+		free(cpu_set);
+		return -2;
+	}
+	for (i = 0; i <= max_cpu; i++) {
+		if (cpu_set[i])
+			++nr_cpus;
+	}
+	free(cpu_set);
+
+	free(str);
+
+	if (max_cpu >= nr_cpus)
+		/* rtla assumes cpu < nr_cpus for all cpus */
+		return -3;
+
+	return nr_cpus;
+}
+
+static int cpu_set_callback(int i, void *data)
+{
+	cpu_set_t *set = data;
+
+	if (i >= nr_cpus || i >= CPU_SETSIZE)
+		return -1;
+
+	debug_msg("cpu_set: adding cpu %d\n", i);
+	CPU_SET(i, set);
+
+	return 0;
+}
+
+/*
+ * parse_cpu_set - parse a cpu_list filling cpu_set_t argument
+ *
+ * Receives a cpu list, like 1-3,5 (cpus 1, 2, 3, 5), and then set
+ * filling cpu_set_t argument.
+ *
+ * Returns 0 on success, 1 otherwise.
+ */
+int parse_cpu_set(char *cpu_list, cpu_set_t *set)
+{
+	CPU_ZERO(set);
+
+	if (cpu_list_iterate(cpu_list, cpu_set_callback, set) < 0) {
+		debug_msg("Error parsing the cpu set %s\n", cpu_list);
+		return 1;
+	}
+
 	return 0;
-err:
-	debug_msg("Error parsing the cpu set %s\n", cpu_list);
-	return 1;
 }
 
 /*
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 2ba3333669bb4..c26ba8827947a 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -47,6 +47,9 @@ void fatal(const char *fmt, ...);
 long parse_seconds_duration(char *val);
 void get_duration(time_t start_time, char *output, int output_size);
 
+int cpu_list_iterate(const char *cpu_list, int (*callback)(int, void *), void *data);
+int get_possible_cpus(void);
+
 long long get_llong_from_str(char *start);
 
 static inline void
-- 
2.55.0