Merge: KVM: Fix for access_tracking_perf_test random failures

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1109

Backport a patch that skips part of the test,
when the test machine has NUMA balancing enabled.

Now in case of the failure only a warning will be printed like this:

WARNING: vCPU0: Too many pages still idle (36738 out of 262144), this will affect performance results.

JIRA: https://issues.redhat.com/browse/RHEL-92771

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>

Approved-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Approved-by: Bandan Das <bsd@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Jan Stancek <jstancek@redhat.com>

Author: jstancek

tools/testing/selftests/kvm/access_tracking_perf_test.c

@@ -65,6 +65,16 @@ static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 /* Whether to overlap the regions of memory vCPUs access. */
 static bool overlap_memory_access;
 
+/*
+ * If the test should only warn if there are too many idle pages (i.e., it is
+ * expected).
+ * -1: Not yet set.
+ *  0: We do not expect too many idle pages, so FAIL if too many idle pages.
+ *  1: Having too many idle pages is expected, so merely print a warning if
+ *     too many idle pages are found.
+ */
+static int idle_pages_warn_only = -1;
+
 struct test_params {
 	/* The backing source for the region of memory. */
 	enum vm_mem_backing_src_type backing_src;
@@ -177,18 +187,12 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
 	 * arbitrary; high enough that we ensure most memory access went through
 	 * access tracking but low enough as to not make the test too brittle
 	 * over time and across architectures.
-	 *
-	 * When running the guest as a nested VM, "warn" instead of asserting
-	 * as the TLB size is effectively unlimited and the KVM doesn't
-	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
-	 * are cached and the guest won't see the "idle" bit cleared.
 	 */
 	if (still_idle >= pages / 10) {
-#ifdef __x86_64__
-		TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR),
+		TEST_ASSERT(idle_pages_warn_only,
 			    "vCPU%d: Too many pages still idle (%lu out of %lu)",
 			    vcpu_idx, still_idle, pages);
-#endif
+
 		printf("WARNING: vCPU%d: Too many pages still idle (%lu out of %lu), "
 		       "this will affect performance results.\n",
 		       vcpu_idx, still_idle, pages);
@@ -328,6 +332,32 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	memstress_destroy_vm(vm);
 }
 
+static int access_tracking_unreliable(void)
+{
+#ifdef __x86_64__
+	/*
+	 * When running nested, the TLB size may be effectively unlimited (for
+	 * example, this is the case when running on KVM L0), and KVM doesn't
+	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
+	 * are cached and the guest won't see the "idle" bit cleared.
+	 */
+	if (this_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		puts("Skipping idle page count sanity check, because the test is run nested");
+		return 1;
+	}
+#endif
+	/*
+	 * When NUMA balancing is enabled, guest memory will be unmapped to get
+	 * NUMA faults, dropping the Accessed bits.
+	 */
+	if (is_numa_balancing_enabled()) {
+		puts("Skipping idle page count sanity check, because NUMA balancing is enabled");
+		return 1;
+	}
+
+	return 0;
+}
+
 static void help(char *name)
 {
 	puts("");
@@ -342,6 +372,12 @@ static void help(char *name)
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
+	printf(" -w: Control whether the test warns or fails if more than 10%%\n"
+	       "     of pages are still seen as idle/old after accessing guest\n"
+	       "     memory.  >0 == warn only, 0 == fail, <0 == auto.  For auto\n"
+	       "     mode, the test fails by default, but switches to warn only\n"
+	       "     if NUMA balancing is enabled or the test detects it's running\n"
+	       "     in a VM.\n");
 	backing_src_help("-s");
 	puts("");
 	exit(0);
@@ -359,7 +395,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:b:v:os:w:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -376,6 +412,11 @@ int main(int argc, char *argv[])
 		case 's':
 			params.backing_src = parse_backing_src_type(optarg);
 			break;
+		case 'w':
+			idle_pages_warn_only =
+				atoi_non_negative("Idle pages warning",
+						  optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -388,6 +429,9 @@ int main(int argc, char *argv[])
 		       "CONFIG_IDLE_PAGE_TRACKING is not enabled");
 	close(page_idle_fd);
 
+	if (idle_pages_warn_only == -1)
+		idle_pages_warn_only = access_tracking_unreliable();
+
 	for_each_guest_mode(run_test, &params);
 
 	return 0;

tools/testing/selftests/kvm/include/test_util.h

@@ -153,6 +153,7 @@ bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
+bool is_numa_balancing_enabled(void);
 
 /*
  * Whether or not the given source type is shared memory (as opposed to

tools/testing/selftests/kvm/lib/test_util.c

@@ -132,37 +132,57 @@ void print_skip(const char *fmt, ...)
 	puts(", skipping test");
 }
 
-bool thp_configured(void)
+static bool test_sysfs_path(const char *path)
 {
-	int ret;
 	struct stat statbuf;
+	int ret;
 
-	ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+	ret = stat(path, &statbuf);
 	TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
-		    "Error in stating /sys/kernel/mm/transparent_hugepage");
+		    "Error in stat()ing '%s'", path);
 
 	return ret == 0;
 }
 
-size_t get_trans_hugepagesz(void)
+bool thp_configured(void)
+{
+	return test_sysfs_path("/sys/kernel/mm/transparent_hugepage");
+}
+
+static size_t get_sysfs_val(const char *path)
 {
 	size_t size;
 	FILE *f;
 	int ret;
 
-	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
-
-	f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r");
-	TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size");
+	f = fopen(path, "r");
+	TEST_ASSERT(f, "Error opening '%s'", path);
 
 	ret = fscanf(f, "%ld", &size);
+	TEST_ASSERT(ret > 0, "Error reading '%s'", path);
+
+	/* Re-scan the input stream to verify the entire file was read. */
 	ret = fscanf(f, "%ld", &size);
-	TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size");
-	fclose(f);
+	TEST_ASSERT(ret < 1, "Error reading '%s'", path);
 
+	fclose(f);
 	return size;
 }
 
+size_t get_trans_hugepagesz(void)
+{
+	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
+
+	return get_sysfs_val("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size");
+}
+
+bool is_numa_balancing_enabled(void)
+{
+	if (!test_sysfs_path("/proc/sys/kernel/numa_balancing"))
+		return false;
+	return get_sysfs_val("/proc/sys/kernel/numa_balancing") == 1;
+}
+
 size_t get_def_hugetlb_pagesz(void)
 {
 	char buf[64];