selftests/mm/khugepaged: enlighten for multi-size THP

The `collapse_max_ptes_none` test was previously failing when a THP size
less than PMD-size had enabled="always".  The root cause is because the
test faults in 1 page less than the threshold it set for collapsing.  But
when THP is enabled always, we "over allocate" and therefore the threshold
is passed, and collapse unexpectedly succeeds.

Solve this by enlightening khugepaged selftest.  Add a command line option
to pass in the desired THP size that should be used for all anonymous
allocations.  The harness will then explicitly configure a THP size as
requested and modify the `collapse_max_ptes_none` test so that it faults
in the threshold minus the number of pages in the configured THP size.  If
no command line option is provided, default to order 0, as per previous
behaviour.

I chose to use an order in the command line interface, since this makes
the interface agnostic of base page size, making it easier to invoke from
run_vmtests.sh.

Link: https://lkml.kernel.org/r/20231207161211.2374093-9-ryan.roberts@arm.comSigned-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

tools/testing/selftests/mm/khugepaged.c

@@ -28,6 +28,7 @@
 static unsigned long hpage_pmd_size;
 static unsigned long page_size;
 static int hpage_pmd_nr;
+static int anon_order;
 
 #define PID_SMAPS "/proc/self/smaps"
 #define TEST_FILE "collapse_test_file"
@@ -607,6 +608,11 @@ static bool is_tmpfs(struct mem_ops *ops)
 	return ops == &__file_ops && finfo.type == VMA_SHMEM;
 }
 
+static bool is_anon(struct mem_ops *ops)
+{
+	return ops == &__anon_ops;
+}
+
 static void alloc_at_fault(void)
 {
 	struct thp_settings settings = *thp_current_settings();
@@ -673,6 +679,7 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o
 	int max_ptes_none = hpage_pmd_nr / 2;
 	struct thp_settings settings = *thp_current_settings();
 	void *p;
+	int fault_nr_pages = is_anon(ops) ? 1 << anon_order : 1;
 
 	settings.khugepaged.max_ptes_none = max_ptes_none;
 	thp_push_settings(&settings);
@@ -686,10 +693,10 @@ static void collapse_max_ptes_none(struct collapse_context *c, struct mem_ops *o
 		goto skip;
 	}
 
-	ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+	ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);
 	c->collapse("Maybe collapse with max_ptes_none exceeded", p, 1,
 		    ops, !c->enforce_pte_scan_limits);
-	validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - 1) * page_size);
+	validate_memory(p, 0, (hpage_pmd_nr - max_ptes_none - fault_nr_pages) * page_size);
 
 	if (c->enforce_pte_scan_limits) {
 		ops->fault(p, 0, (hpage_pmd_nr - max_ptes_none) * page_size);
@@ -1076,7 +1083,7 @@ static void madvise_retracted_page_tables(struct collapse_context *c,
 
 static void usage(void)
 {
-	fprintf(stderr, "\nUsage: ./khugepaged <test type> [dir]\n\n");
+	fprintf(stderr, "\nUsage: ./khugepaged [OPTIONS] <test type> [dir]\n\n");
 	fprintf(stderr, "\t<test type>\t: <context>:<mem_type>\n");
 	fprintf(stderr, "\t<context>\t: [all|khugepaged|madvise]\n");
 	fprintf(stderr, "\t<mem_type>\t: [all|anon|file|shmem]\n");
@@ -1085,15 +1092,34 @@ static void usage(void)
 	fprintf(stderr,	"\tCONFIG_READ_ONLY_THP_FOR_FS=y\n");
 	fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n");
 	fprintf(stderr,	"\tmounted with huge=madvise option for khugepaged tests to work\n");
+	fprintf(stderr,	"\n\tSupported Options:\n");
+	fprintf(stderr,	"\t\t-h: This help message.\n");
+	fprintf(stderr,	"\t\t-s: mTHP size, expressed as page order.\n");
+	fprintf(stderr,	"\t\t    Defaults to 0. Use this size for anon allocations.\n");
 	exit(1);
 }
 
-static void parse_test_type(int argc, const char **argv)
+static void parse_test_type(int argc, char **argv)
 {
+	int opt;
 	char *buf;
 	const char *token;
 
-	if (argc == 1) {
+	while ((opt = getopt(argc, argv, "s:h")) != -1) {
+		switch (opt) {
+		case 's':
+			anon_order = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			usage();
+		}
+	}
+
+	argv += optind;
+	argc -= optind;
+
+	if (argc == 0) {
 		/* Backwards compatibility */
 		khugepaged_context =  &__khugepaged_context;
 		madvise_context =  &__madvise_context;
@@ -1101,7 +1127,7 @@ static void parse_test_type(int argc, const char **argv)
 		return;
 	}
 
-	buf = strdup(argv[1]);
+	buf = strdup(argv[0]);
 	token = strsep(&buf, ":");
 
 	if (!strcmp(token, "all")) {
@@ -1135,11 +1161,13 @@ static void parse_test_type(int argc, const char **argv)
 	if (!file_ops)
 		return;
 
-	if (argc != 3)
+	if (argc != 2)
 		usage();
+
+	get_finfo(argv[1]);
 }
 
-int main(int argc, const char **argv)
+int main(int argc, char **argv)
 {
 	int hpage_pmd_order;
 	struct thp_settings default_settings = {
@@ -1164,9 +1192,6 @@ int main(int argc, const char **argv)
 
 	parse_test_type(argc, argv);
 
-	if (file_ops)
-		get_finfo(argv[2]);
-
 	setbuf(stdout, NULL);
 
 	page_size = getpagesize();
@@ -1183,6 +1208,7 @@ int main(int argc, const char **argv)
 	default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2;
 	default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8;
 	default_settings.hugepages[hpage_pmd_order].enabled = THP_INHERIT;
+	default_settings.hugepages[anon_order].enabled = THP_ALWAYS;
 
 	save_settings();
 	thp_push_settings(&default_settings);

tools/testing/selftests/mm/run_vmtests.sh

@@ -357,6 +357,8 @@ CATEGORY="cow" run_test ./cow
 
 CATEGORY="thp" run_test ./khugepaged
 
+CATEGORY="thp" run_test ./khugepaged -s 2
+
 CATEGORY="thp" run_test ./transhuge-stress -d 20
 
 CATEGORY="thp" run_test ./split_huge_page_test