1 files changed, 161 insertions, 48 deletions

diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 1cade75176eb..195f04c4d158 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -13,6 +13,8 @@
 
 #include "resctrl.h"
 
+int snc_unreliable;
+
 static int find_resctrl_mount(char *buffer)
 {
 	FILE *mounts;
@@ -157,6 +159,98 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id)
 }
 
 /*
+ * Count number of CPUs in a /sys bitmap
+ */
+static unsigned int count_sys_bitmap_bits(char *name)
+{
+	FILE *fp = fopen(name, "r");
+	int count = 0, c;
+
+	if (!fp)
+		return 0;
+
+	while ((c = fgetc(fp)) != EOF) {
+		if (!isxdigit(c))
+			continue;
+		switch (c) {
+		case 'f':
+			count++;
+			fallthrough;
+		case '7': case 'b': case 'd': case 'e':
+			count++;
+			fallthrough;
+		case '3': case '5': case '6': case '9': case 'a': case 'c':
+			count++;
+			fallthrough;
+		case '1': case '2': case '4': case '8':
+			count++;
+			break;
+		}
+	}
+	fclose(fp);
+
+	return count;
+}
+
+static bool cpus_offline_empty(void)
+{
+	char offline_cpus_str[64];
+	FILE *fp;
+
+	fp = fopen("/sys/devices/system/cpu/offline", "r");
+	if (!fp) {
+		ksft_perror("Could not open /sys/devices/system/cpu/offline");
+		return 0;
+	}
+
+	if (fscanf(fp, "%63s", offline_cpus_str) < 0) {
+		if (!errno) {
+			fclose(fp);
+			return 1;
+		}
+		ksft_perror("Could not read /sys/devices/system/cpu/offline");
+	}
+
+	fclose(fp);
+
+	return 0;
+}
+
+/*
+ * Detect SNC by comparing #CPUs in node0 with #CPUs sharing LLC with CPU0.
+ * If any CPUs are offline declare the detection as unreliable.
+ */
+int snc_nodes_per_l3_cache(void)
+{
+	int node_cpus, cache_cpus;
+	static int snc_mode;
+
+	if (!snc_mode) {
+		snc_mode = 1;
+		if (!cpus_offline_empty()) {
+			ksft_print_msg("Runtime SNC detection unreliable due to offline CPUs.\n");
+			ksft_print_msg("Setting SNC mode to disabled.\n");
+			snc_unreliable = 1;
+			return snc_mode;
+		}
+		node_cpus = count_sys_bitmap_bits("/sys/devices/system/node/node0/cpumap");
+		cache_cpus = count_sys_bitmap_bits("/sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_map");
+
+		if (!node_cpus || !cache_cpus) {
+			ksft_print_msg("Could not determine Sub-NUMA Cluster mode.\n");
+			snc_unreliable = 1;
+			return snc_mode;
+		}
+		snc_mode = cache_cpus / node_cpus;
+
+		if (snc_mode > 1)
+			ksft_print_msg("SNC-%d mode discovered.\n", snc_mode);
+	}
+
+	return snc_mode;
+}
+
+/*
  * get_cache_size - Get cache size for a specified CPU
  * @cpu_no:	CPU number
  * @cache_type:	Cache level L2/L3
@@ -182,7 +276,7 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size
 
 		return -1;
 	}
-	if (fscanf(fp, "%s", cache_str) <= 0) {
+	if (fscanf(fp, "%63s", cache_str) <= 0) {
 		ksft_perror("Could not get cache_size");
 		fclose(fp);
 
@@ -211,6 +305,17 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size
 			break;
 	}
 
+	/*
+	 * The amount of cache represented by each bit in the masks
+	 * in the schemata file is reduced by a factor equal to SNC
+	 * nodes per L3 cache.
+	 * E.g. on a SNC-2 system with a 100MB L3 cache a test that
+	 * allocates memory from its local SNC node (default behavior
+	 * without using libnuma) will only see 50 MB llc_occupancy
+	 * with a fully populated L3 mask in the schemata file.
+	 */
+	if (cache_num == 3)
+		*cache_size /= snc_nodes_per_l3_cache();
 	return 0;
 }
 
@@ -456,6 +561,9 @@ int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity)
  * @grp:	Full path and name of the group
  * @parent_grp:	Full path and name of the parent group
  *
+ * Creates a group @grp_name if it does not exist yet. If @grp_name is NULL,
+ * it is interpreted as the root group which always results in success.
+ *
  * Return: 0 on success, < 0 on error.
  */
 static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
@@ -464,12 +572,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 	struct dirent *ep;
 	DIR *dp;
 
-	/*
-	 * At this point, we are guaranteed to have resctrl FS mounted and if
-	 * length of grp_name == 0, it means, user wants to use root con_mon
-	 * grp, so do nothing
-	 */
-	if (strlen(grp_name) == 0)
+	if (!grp_name)
 		return 0;
 
 	/* Check if requested grp exists or not */
@@ -508,7 +611,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
 
 		return -1;
 	}
-	if (fprintf(fp, "%d\n", pid) < 0) {
+	if (fprintf(fp, "%d\n", (int)pid) < 0) {
 		ksft_print_msg("Failed to write pid to tasks file\n");
 		fclose(fp);
 
@@ -524,7 +627,6 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  * @bm_pid:		PID that should be written
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  *
  * If a con_mon grp is requested, create it and write pid to it, otherwise
  * write pid to root con_mon grp.
@@ -534,14 +636,13 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
-			    char *resctrl_val)
+int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp)
 {
 	char controlgroup[128], monitorgroup[512], monitorgroup_p[256];
 	char tasks[1024];
 	int ret = 0;
 
-	if (strlen(ctrlgrp))
+	if (ctrlgrp)
 		sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp);
 	else
 		sprintf(controlgroup, "%s", RESCTRL_PATH);
@@ -555,22 +656,19 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 	if (ret)
 		goto out;
 
-	/* Create mon grp and write pid into it for "mbm" and "cmt" test */
-	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
-		if (strlen(mongrp)) {
-			sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
-			sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
-			ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
-			if (ret)
-				goto out;
-
-			sprintf(tasks, "%s/mon_groups/%s/tasks",
-				controlgroup, mongrp);
-			ret = write_pid_to_tasks(tasks, bm_pid);
-			if (ret)
-				goto out;
-		}
+	/* Create monitor group and write pid into if it is used */
+	if (mongrp) {
+		sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
+		sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
+		ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
+		if (ret)
+			goto out;
+
+		sprintf(tasks, "%s/mon_groups/%s/tasks",
+			controlgroup, mongrp);
+		ret = write_pid_to_tasks(tasks, bm_pid);
+		if (ret)
+			goto out;
 	}
 
 out:
@@ -593,7 +691,8 @@ out:
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
+int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
+		   const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
 	int domain_id, fd, schema_len, ret = 0;
@@ -611,7 +710,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour
 		goto out;
 	}
 
-	if (strlen(ctrlgrp) != 0)
+	if (ctrlgrp)
 		sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp);
 	else
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
@@ -837,24 +936,6 @@ int filter_dmesg(void)
 	return 0;
 }
 
-int validate_bw_report_request(char *bw_report)
-{
-	if (strcmp(bw_report, "reads") == 0)
-		return 0;
-	if (strcmp(bw_report, "writes") == 0)
-		return 0;
-	if (strcmp(bw_report, "nt-writes") == 0) {
-		strcpy(bw_report, "writes");
-		return 0;
-	}
-	if (strcmp(bw_report, "total") == 0)
-		return 0;
-
-	fprintf(stderr, "Requested iMC B/W report type unavailable\n");
-
-	return -1;
-}
-
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags)
 {
@@ -876,3 +957,35 @@ unsigned int count_bits(unsigned long n)
 
 	return count;
 }
+
+/**
+ * snc_kernel_support - Check for existence of mon_sub_L3_00 file that indicates
+ * SNC resctrl support on the kernel side.
+ *
+ * Return: 0 if not supported, 1 if SNC is disabled or SNC discovery is
+ * unreliable or SNC is both enabled and supported.
+ */
+int snc_kernel_support(void)
+{
+	char node_path[PATH_MAX];
+	struct stat statbuf;
+	int ret;
+
+	ret = snc_nodes_per_l3_cache();
+	/*
+	 * If SNC is disabled then its kernel support isn't important. If SNC
+	 * got disabled because the discovery process was unreliable the
+	 * snc_unreliable variable was set. It can be used to verify the SNC
+	 * discovery reliability elsewhere in the selftest.
+	 */
+	if (ret == 1)
+		return ret;
+
+	snprintf(node_path, sizeof(node_path), "%s/%s", RESCTRL_PATH,
+		 "mon_data/mon_L3_00/mon_sub_L3_00");
+
+	if (!stat(node_path, &statbuf))
+		return 1;
+
+	return 0;
+}