[PATCH 5/6] mm: add selftests to split_huge_page() to verify unmap/zap of zero pages

[Usama Arif]

From: Alexander Zhu <alexlzhu@xxxxxx>

Self tests to verify the RssAnon value to make sure zero
pages are not remapped except in the case of userfaultfd.
Also includes a self test for the userfaultfd use case.

Signed-off-by: Alexander Zhu <alexlzhu@xxxxxx>
Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
---
 .../selftests/mm/split_huge_page_test.c       | 113 ++++++++++++++++++
 tools/testing/selftests/mm/vm_util.c          |  22 ++++
 tools/testing/selftests/mm/vm_util.h          |   1 +
 3 files changed, 136 insertions(+)

diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index e5e8dafc9d94..da271ad6ff11 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -17,6 +17,8 @@
 #include <malloc.h>
 #include <stdbool.h>
 #include <time.h>
+#include <sys/syscall.h>
+#include <linux/userfaultfd.h>
 #include "vm_util.h"
 #include "../kselftest.h"
 
@@ -84,6 +86,115 @@ static void write_debugfs(const char *fmt, ...)
 	write_file(SPLIT_DEBUGFS, input, ret + 1);
 }
 
+static char *allocate_zero_filled_hugepage(size_t len)
+{
+	char *result;
+	size_t i;
+
+	result = memalign(pmd_pagesize, len);
+	if (!result) {
+		printf("Fail to allocate memory\n");
+		exit(EXIT_FAILURE);
+	}
+
+	madvise(result, len, MADV_HUGEPAGE);
+
+	for (i = 0; i < len; i++)
+		result[i] = (char)0;
+
+	return result;
+}
+
+static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hpages, size_t len)
+{
+	uint64_t rss_anon_before, rss_anon_after;
+	size_t i;
+
+	if (!check_huge_anon(one_page, 4, pmd_pagesize)) {
+		printf("No THP is allocated\n");
+		exit(EXIT_FAILURE);
+	}
+
+	rss_anon_before = rss_anon();
+	if (!rss_anon_before) {
+		printf("No RssAnon is allocated before split\n");
+		exit(EXIT_FAILURE);
+	}
+
+	/* split all THPs */
+	write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
+		      (uint64_t)one_page + len, 0);
+
+	for (i = 0; i < len; i++)
+		if (one_page[i] != (char)0) {
+			printf("%ld byte corrupted\n", i);
+			exit(EXIT_FAILURE);
+		}
+
+	if (!check_huge_anon(one_page, 0, pmd_pagesize)) {
+		printf("Still AnonHugePages not split\n");
+		exit(EXIT_FAILURE);
+	}
+
+	rss_anon_after = rss_anon();
+	if (rss_anon_after >= rss_anon_before) {
+		printf("Incorrect RssAnon value. Before: %ld After: %ld\n",
+		       rss_anon_before, rss_anon_after);
+		exit(EXIT_FAILURE);
+	}
+}
+
+void split_pmd_zero_pages(void)
+{
+	char *one_page;
+	int nr_hpages = 4;
+	size_t len = nr_hpages * pmd_pagesize;
+
+	one_page = allocate_zero_filled_hugepage(len);
+	verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len);
+	printf("Split zero filled huge pages successful\n");
+	free(one_page);
+}
+
+void split_pmd_zero_pages_uffd(void)
+{
+	char *one_page;
+	int nr_hpages = 4;
+	size_t len = nr_hpages * pmd_pagesize;
+	long uffd; /* userfaultfd file descriptor */
+	struct uffdio_api uffdio_api;
+	struct uffdio_register uffdio_register;
+
+	/* Create and enable userfaultfd object. */
+
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	if (uffd == -1) {
+		perror("userfaultfd");
+		exit(1);
+	}
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = 0;
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+		perror("ioctl-UFFDIO_API");
+		exit(1);
+	}
+
+	one_page = allocate_zero_filled_hugepage(len);
+
+	uffdio_register.range.start = (unsigned long)one_page;
+	uffdio_register.range.len = len;
+	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+		perror("ioctl-UFFDIO_REGISTER");
+		exit(1);
+	}
+
+	verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len);
+	printf("Split zero filled huge pages with uffd successful\n");
+	free(one_page);
+}
+
 void split_pmd_thp(void)
 {
 	char *one_page;
@@ -431,6 +542,8 @@ int main(int argc, char **argv)
 
 	fd_size = 2 * pmd_pagesize;
 
+	split_pmd_zero_pages();
+	split_pmd_zero_pages_uffd();
 	split_pmd_thp();
 	split_pte_mapped_thp();
 	split_file_backed_thp();
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 5a62530da3b5..7b7e763ba8e3 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -12,6 +12,7 @@
 
 #define PMD_SIZE_FILE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size"
 #define SMAP_FILE_PATH "/proc/self/smaps"
+#define STATUS_FILE_PATH "/proc/self/status"
 #define MAX_LINE_LENGTH 500
 
 unsigned int __page_size;
@@ -171,6 +172,27 @@ uint64_t read_pmd_pagesize(void)
 	return strtoul(buf, NULL, 10);
 }
 
+uint64_t rss_anon(void)
+{
+	uint64_t rss_anon = 0;
+	FILE *fp;
+	char buffer[MAX_LINE_LENGTH];
+
+	fp = fopen(STATUS_FILE_PATH, "r");
+	if (!fp)
+		ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, STATUS_FILE_PATH);
+
+	if (!check_for_pattern(fp, "RssAnon:", buffer, sizeof(buffer)))
+		goto err_out;
+
+	if (sscanf(buffer, "RssAnon:%10ld kB", &rss_anon) != 1)
+		ksft_exit_fail_msg("Reading status error\n");
+
+err_out:
+	fclose(fp);
+	return rss_anon;
+}
+
 bool __check_huge(void *addr, char *pattern, int nr_hpages,
 		  uint64_t hpage_size)
 {
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 9007c420d52c..71b75429f4a5 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -39,6 +39,7 @@ unsigned long pagemap_get_pfn(int fd, char *start);
 void clear_softdirty(void);
 bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t len);
 uint64_t read_pmd_pagesize(void);
+uint64_t rss_anon(void);
 bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size);
 bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size);
 bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size);
-- 
2.43.0