From: Alexander Zhu <alexlzhu@fb.com>

When a THP is split, any subpage that is zero-filled will be mapped
to the shared zeropage, hence saving memory. Add selftest to verify
this by allocating zero-filled THP and comparing RssAnon before and
after split.

Signed-off-by: Alexander Zhu <alexlzhu@fb.com>
Acked-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
---
 .../selftests/mm/split_huge_page_test.c       | 71 +++++++++++++++++++
 tools/testing/selftests/mm/vm_util.c          | 22 ++++++
 tools/testing/selftests/mm/vm_util.h          |  1 +
 3 files changed, 94 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..eb6d1b9fc362 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -84,6 +84,76 @@ 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)
+{
+	unsigned long 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_thp(void)
 {
 	char *one_page;
@@ -431,6 +501,7 @@ int main(int argc, char **argv)
 
 	fd_size = 2 * pmd_pagesize;
 
+	split_pmd_zero_pages();
 	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..d8d0cf04bb57 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);
 }
 
+unsigned long rss_anon(void)
+{
+	unsigned long 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:%10lu 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);
-- 
2.43.5

On 18/08/2024 22:30, Usama Arif wrote:
> From: Alexander Zhu <alexlzhu@fb.com>
> 
> When a THP is split, any subpage that is zero-filled will be mapped
> to the shared zeropage, hence saving memory. Add selftest to verify
> this by allocating zero-filled THP and comparing RssAnon before and
> after split.
> 
> Signed-off-by: Alexander Zhu <alexlzhu@fb.com>
> Acked-by: Rik van Riel <riel@surriel.com>
> Signed-off-by: Usama Arif <usamaarif642@gmail.com>
> ---
>  .../selftests/mm/split_huge_page_test.c       | 71 +++++++++++++++++++
>  tools/testing/selftests/mm/vm_util.c          | 22 ++++++
>  tools/testing/selftests/mm/vm_util.h          |  1 +
>  3 files changed, 94 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..eb6d1b9fc362 100644
> --- a/tools/testing/selftests/mm/split_huge_page_test.c
> +++ b/tools/testing/selftests/mm/split_huge_page_test.c
> @@ -84,6 +84,76 @@ 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)
> +{
> +	unsigned long 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_thp(void)
>  {
>  	char *one_page;
> @@ -431,6 +501,7 @@ int main(int argc, char **argv)
>  
>  	fd_size = 2 * pmd_pagesize;
>  
> +	split_pmd_zero_pages();
>  	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..d8d0cf04bb57 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);
>  }
>  
> +unsigned long rss_anon(void)
> +{
> +	unsigned long 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:%10lu 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);


Need below fixlet as well

From 2476b7a46908c801ab446f41566f4af52b939ac7 Mon Sep 17 00:00:00 2001
From: Usama Arif <usamaarif642@gmail.com>
Date: Wed, 21 Aug 2024 20:06:53 +0100
Subject: [PATCH] mm: selftest to verify zero-filled pages are mapped to
 zeropage fix

change uint64_t to unsigned long for rss_anon

Signed-off-by: Usama Arif <usamaarif642@gmail.com>
---
 tools/testing/selftests/mm/vm_util.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 71b75429f4a5..2eaed8209925 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -39,7 +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);
+unsigned long 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);
-- 
2.43.5