[Patch v3 0/2] assert rmap behaves as expected

[Patch v3 0/2] assert rmap behaves as expected

[Wei Yang]

As David suggested, currently we don't have a high level test case to
verify the behavior of rmap. This patch set introduce the verification
on rmap by migration.

Patch 1 is a preparation to move ksm related operations into vm_util.
Patch 2 is the new test case for rmap.

Currently it covers following four scenarios:

  * anonymous page
  * shmem page
  * pagecache page
  * ksm page

v2->v3:
  * handle ksm error return in worker
  * rebase on current mm-unstable
v1->v2:
  * do check on file opening in init_global_file_handlers()
  * factor out ksm_merge() and ksm_unmerge() instead of partial of it
  * align the return value of helpers: 0 on success, -errno on error
  * skip instead of assert if numa not available
  * check ksm sys file before continue
  * use private anonymous map instead of shared map
  * check pfn instead of content
  * retry migrate
  * fault in region for each process by FORCE_READ()

RFC->v1:
  * open file in function itself instead of pass fd as parameter
  * fault in the region by accessing it instead of print content

Wei Yang (2):
  selftests/mm: put general ksm operation into vm_util
  selftests/mm: assert rmap behave as expected

 MAINTAINERS                                   |   1 +
 tools/testing/selftests/mm/.gitignore         |   1 +
 tools/testing/selftests/mm/Makefile           |   3 +
 .../selftests/mm/ksm_functional_tests.c       | 134 +-----
 tools/testing/selftests/mm/rmap.c             | 433 ++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh     |   4 +
 tools/testing/selftests/mm/vm_util.c          | 123 +++++
 tools/testing/selftests/mm/vm_util.h          |   7 +
 8 files changed, 595 insertions(+), 111 deletions(-)
 create mode 100644 tools/testing/selftests/mm/rmap.c

-- 
2.34.1

[Patch v3 1/2] selftests/mm: put general ksm operation into vm_util

[Wei Yang]

There are some general ksm operations could be used by other related
test cases. Put them into vm_util for common use.

This is a preparation patch for later use.

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Harry Yoo <harry.yoo@oracle.com>

---
v3:
  * rebase on latest mm-unstable
v2:
  * do check on file opening in init_global_file_handlers()
  * factor out ksm_merge() and ksm_unmerge() instead of partial of it
  * align the return value of helpers: 0 on success, -errno on error
v1: open/close fd in function itself instead of pass as parameter
---
 .../selftests/mm/ksm_functional_tests.c       | 134 +++---------------
 tools/testing/selftests/mm/vm_util.c          | 123 ++++++++++++++++
 tools/testing/selftests/mm/vm_util.h          |   7 +
 3 files changed, 153 insertions(+), 111 deletions(-)

diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index d8bd1911dfc0..c9d72daa3138 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -38,11 +38,6 @@ enum ksm_merge_mode {
 };
 
 static int mem_fd;
-static int ksm_fd;
-static int ksm_full_scans_fd;
-static int proc_self_ksm_stat_fd;
-static int proc_self_ksm_merging_pages_fd;
-static int ksm_use_zero_pages_fd;
 static int pagemap_fd;
 static size_t pagesize;
 
@@ -73,88 +68,6 @@ static bool range_maps_duplicates(char *addr, unsigned long size)
 	return false;
 }
 
-static long get_my_ksm_zero_pages(void)
-{
-	char buf[200];
-	char *substr_ksm_zero;
-	size_t value_pos;
-	ssize_t read_size;
-	unsigned long my_ksm_zero_pages;
-
-	if (!proc_self_ksm_stat_fd)
-		return 0;
-
-	read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0);
-	if (read_size < 0)
-		return -errno;
-
-	buf[read_size] = 0;
-
-	substr_ksm_zero = strstr(buf, "ksm_zero_pages");
-	if (!substr_ksm_zero)
-		return 0;
-
-	value_pos = strcspn(substr_ksm_zero, "0123456789");
-	my_ksm_zero_pages = strtol(substr_ksm_zero + value_pos, NULL, 10);
-
-	return my_ksm_zero_pages;
-}
-
-static long get_my_merging_pages(void)
-{
-	char buf[10];
-	ssize_t ret;
-
-	if (proc_self_ksm_merging_pages_fd < 0)
-		return proc_self_ksm_merging_pages_fd;
-
-	ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0);
-	if (ret <= 0)
-		return -errno;
-	buf[ret] = 0;
-
-	return strtol(buf, NULL, 10);
-}
-
-static long ksm_get_full_scans(void)
-{
-	char buf[10];
-	ssize_t ret;
-
-	ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0);
-	if (ret <= 0)
-		return -errno;
-	buf[ret] = 0;
-
-	return strtol(buf, NULL, 10);
-}
-
-static int ksm_merge(void)
-{
-	long start_scans, end_scans;
-
-	/* Wait for two full scans such that any possible merging happened. */
-	start_scans = ksm_get_full_scans();
-	if (start_scans < 0)
-		return start_scans;
-	if (write(ksm_fd, "1", 1) != 1)
-		return -errno;
-	do {
-		end_scans = ksm_get_full_scans();
-		if (end_scans < 0)
-			return end_scans;
-	} while (end_scans < start_scans + 2);
-
-	return 0;
-}
-
-static int ksm_unmerge(void)
-{
-	if (write(ksm_fd, "2", 1) != 1)
-		return -errno;
-	return 0;
-}
-
 static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
 				  enum ksm_merge_mode mode)
 {
@@ -163,12 +76,12 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
 	int ret;
 
 	/* Stabilize accounting by disabling KSM completely. */
-	if (ksm_unmerge()) {
+	if (ksm_stop() < 0) {
 		ksft_print_msg("Disabling (unmerging) KSM failed\n");
 		return err_map;
 	}
 
-	if (get_my_merging_pages() > 0) {
+	if (ksm_get_self_merging_pages() > 0) {
 		ksft_print_msg("Still pages merged\n");
 		return err_map;
 	}
@@ -218,7 +131,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
 	}
 
 	/* Run KSM to trigger merging and wait. */
-	if (ksm_merge()) {
+	if (ksm_start() < 0) {
 		ksft_print_msg("Running KSM failed\n");
 		goto unmap;
 	}
@@ -227,7 +140,7 @@ static char *__mmap_and_merge_range(char val, unsigned long size, int prot,
 	 * Check if anything was merged at all. Ignore the zero page that is
 	 * accounted differently (depending on kernel support).
 	 */
-	if (val && !get_my_merging_pages()) {
+	if (val && !ksm_get_self_merging_pages()) {
 		ksft_print_msg("No pages got merged\n");
 		goto unmap;
 	}
@@ -274,6 +187,7 @@ static void test_unmerge(void)
 	ksft_test_result(!range_maps_duplicates(map, size),
 			 "Pages were unmerged\n");
 unmap:
+	ksm_stop();
 	munmap(map, size);
 }
 
@@ -286,15 +200,12 @@ static void test_unmerge_zero_pages(void)
 
 	ksft_print_msg("[RUN] %s\n", __func__);
 
-	if (proc_self_ksm_stat_fd < 0) {
-		ksft_test_result_skip("open(\"/proc/self/ksm_stat\") failed\n");
-		return;
-	}
-	if (ksm_use_zero_pages_fd < 0) {
-		ksft_test_result_skip("open \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n");
+	if (ksm_get_self_zero_pages() < 0) {
+		ksft_test_result_skip("accessing \"/proc/self/ksm_stat\" failed\n");
 		return;
 	}
-	if (write(ksm_use_zero_pages_fd, "1", 1) != 1) {
+
+	if (ksm_use_zero_pages() < 0) {
 		ksft_test_result_skip("write \"/sys/kernel/mm/ksm/use_zero_pages\" failed\n");
 		return;
 	}
@@ -306,7 +217,7 @@ static void test_unmerge_zero_pages(void)
 
 	/* Check if ksm_zero_pages is updated correctly after KSM merging */
 	pages_expected = size / pagesize;
-	if (pages_expected != get_my_ksm_zero_pages()) {
+	if (pages_expected != ksm_get_self_zero_pages()) {
 		ksft_test_result_fail("'ksm_zero_pages' updated after merging\n");
 		goto unmap;
 	}
@@ -319,7 +230,7 @@ static void test_unmerge_zero_pages(void)
 
 	/* Check if ksm_zero_pages is updated correctly after unmerging */
 	pages_expected /= 2;
-	if (pages_expected != get_my_ksm_zero_pages()) {
+	if (pages_expected != ksm_get_self_zero_pages()) {
 		ksft_test_result_fail("'ksm_zero_pages' updated after unmerging\n");
 		goto unmap;
 	}
@@ -329,7 +240,7 @@ static void test_unmerge_zero_pages(void)
 		*((unsigned int *)&map[offs]) = offs;
 
 	/* Now we should have no zeropages remaining. */
-	if (get_my_ksm_zero_pages()) {
+	if (ksm_get_self_zero_pages()) {
 		ksft_test_result_fail("'ksm_zero_pages' updated after write fault\n");
 		goto unmap;
 	}
@@ -338,6 +249,7 @@ static void test_unmerge_zero_pages(void)
 	ksft_test_result(!range_maps_duplicates(map, size),
 			"KSM zero pages were unmerged\n");
 unmap:
+	ksm_stop();
 	munmap(map, size);
 }
 
@@ -366,6 +278,7 @@ static void test_unmerge_discarded(void)
 	ksft_test_result(!range_maps_duplicates(map, size),
 			 "Pages were unmerged\n");
 unmap:
+	ksm_stop();
 	munmap(map, size);
 }
 
@@ -452,6 +365,7 @@ static void test_unmerge_uffd_wp(void)
 close_uffd:
 	close(uffd);
 unmap:
+	ksm_stop();
 	munmap(map, size);
 }
 #endif
@@ -515,6 +429,7 @@ static int test_child_ksm(void)
 	else if (map == MAP_MERGE_SKIP)
 		return -3;
 
+	ksm_stop();
 	munmap(map, size);
 	return 0;
 }
@@ -644,6 +559,7 @@ static void test_prctl_unmerge(void)
 	ksft_test_result(!range_maps_duplicates(map, size),
 			 "Pages were unmerged\n");
 unmap:
+	ksm_stop();
 	munmap(map, size);
 }
 
@@ -685,19 +601,15 @@ static void init_global_file_handles(void)
 	mem_fd = open("/proc/self/mem", O_RDWR);
 	if (mem_fd < 0)
 		ksft_exit_fail_msg("opening /proc/self/mem failed\n");
-	ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
-	if (ksm_fd < 0)
-		ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n");
-	ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY);
-	if (ksm_full_scans_fd < 0)
-		ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n");
+	if (ksm_stop() < 0)
+		ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/run\") failed\n");
+	if (ksm_get_full_scans() < 0)
+		ksft_exit_skip("accessing \"/sys/kernel/mm/ksm/full_scans\") failed\n");
 	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
 	if (pagemap_fd < 0)
 		ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n");
-	proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY);
-	proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages",
-						O_RDONLY);
-	ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR);
+	if (ksm_get_self_merging_pages() < 0)
+		ksft_exit_skip("accessing \"/proc/self/ksm_merging_pages\") failed\n");
 }
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 6a239aa413e2..ab7271ed5ff3 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -565,3 +565,126 @@ bool detect_huge_zeropage(void)
 	close(fd);
 	return enabled;
 }
+
+long ksm_get_self_zero_pages(void)
+{
+	int proc_self_ksm_stat_fd;
+	char buf[200];
+	char *substr_ksm_zero;
+	size_t value_pos;
+	ssize_t read_size;
+
+	proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY);
+	if (proc_self_ksm_stat_fd < 0)
+		return -errno;
+
+	read_size = pread(proc_self_ksm_stat_fd, buf, sizeof(buf) - 1, 0);
+	close(proc_self_ksm_stat_fd);
+	if (read_size < 0)
+		return -errno;
+
+	buf[read_size] = 0;
+
+	substr_ksm_zero = strstr(buf, "ksm_zero_pages");
+	if (!substr_ksm_zero)
+		return 0;
+
+	value_pos = strcspn(substr_ksm_zero, "0123456789");
+	return strtol(substr_ksm_zero + value_pos, NULL, 10);
+}
+
+long ksm_get_self_merging_pages(void)
+{
+	int proc_self_ksm_merging_pages_fd;
+	char buf[10];
+	ssize_t ret;
+
+	proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages",
+						O_RDONLY);
+	if (proc_self_ksm_merging_pages_fd < 0)
+		return -errno;
+
+	ret = pread(proc_self_ksm_merging_pages_fd, buf, sizeof(buf) - 1, 0);
+	close(proc_self_ksm_merging_pages_fd);
+	if (ret <= 0)
+		return -errno;
+	buf[ret] = 0;
+
+	return strtol(buf, NULL, 10);
+}
+
+long ksm_get_full_scans(void)
+{
+	int ksm_full_scans_fd;
+	char buf[10];
+	ssize_t ret;
+
+	ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY);
+	if (ksm_full_scans_fd < 0)
+		return -errno;
+
+	ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0);
+	close(ksm_full_scans_fd);
+	if (ret <= 0)
+		return -errno;
+	buf[ret] = 0;
+
+	return strtol(buf, NULL, 10);
+}
+
+int ksm_use_zero_pages(void)
+{
+	int ksm_use_zero_pages_fd;
+	ssize_t ret;
+
+	ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR);
+	if (ksm_use_zero_pages_fd < 0)
+		return -errno;
+
+	ret = write(ksm_use_zero_pages_fd, "1", 1);
+	close(ksm_use_zero_pages_fd);
+	return ret == 1 ? 0 : -errno;
+}
+
+int ksm_start(void)
+{
+	int ksm_fd;
+	ssize_t ret;
+	long start_scans, end_scans;
+
+	ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
+	if (ksm_fd < 0)
+		return -errno;
+
+	/* Wait for two full scans such that any possible merging happened. */
+	start_scans = ksm_get_full_scans();
+	if (start_scans < 0) {
+		close(ksm_fd);
+		return start_scans;
+	}
+	ret = write(ksm_fd, "1", 1);
+	close(ksm_fd);
+	if (ret != 1)
+		return -errno;
+	do {
+		end_scans = ksm_get_full_scans();
+		if (end_scans < 0)
+			return end_scans;
+	} while (end_scans < start_scans + 2);
+
+	return 0;
+}
+
+int ksm_stop(void)
+{
+	int ksm_fd;
+	ssize_t ret;
+
+	ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
+	if (ksm_fd < 0)
+		return -errno;
+
+	ret = write(ksm_fd, "2", 1);
+	close(ksm_fd);
+	return ret == 1 ? 0 : -errno;
+}
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 1843ad48d32b..ba4d9fa44a7d 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -130,6 +130,13 @@ static inline void log_test_result(int result)
 void *sys_mremap(void *old_address, unsigned long old_size,
 		 unsigned long new_size, int flags, void *new_address);
 
+long ksm_get_self_zero_pages(void);
+long ksm_get_self_merging_pages(void);
+long ksm_get_full_scans(void);
+int ksm_use_zero_pages(void);
+int ksm_start(void);
+int ksm_stop(void);
+
 /*
  * On ppc64 this will only work with radix 2M hugepage size
  */
-- 
2.34.1

[Patch v3 2/2] selftests/mm: assert rmap behave as expected

[Wei Yang]

As David suggested, currently we don't have a high level test case to
verify the behavior of rmap. This patch introduce the verification on
rmap by migration.

The general idea is if migrate one shared page between processes, this
would be reflected in all related processes. Otherwise, we have problem
in rmap.

Currently it covers following four scenarios:

  * anonymous page
  * shmem page
  * pagecache page
  * ksm page

Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Harry Yoo <harry.yoo@oracle.com>

---
v3:
  * handle ksm failure in worker
v2:
  * skip instead of assert if numa not available
  * check ksm sys file before continue
  * use private anonymous map instead of shared map
  * check pfn instead of content
  * retry migrate
  * fault in region for each process by FORCE_READ()
  * behave -> behaves
v1: fault in region by just accessing it instead of print it
---
 MAINTAINERS                               |   1 +
 tools/testing/selftests/mm/.gitignore     |   1 +
 tools/testing/selftests/mm/Makefile       |   3 +
 tools/testing/selftests/mm/rmap.c         | 433 ++++++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh |   4 +
 5 files changed, 442 insertions(+)
 create mode 100644 tools/testing/selftests/mm/rmap.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 390829ae9803..c0a4bda39f8e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16192,6 +16192,7 @@ S:	Maintained
 F:	include/linux/rmap.h
 F:	mm/page_vma_mapped.c
 F:	mm/rmap.c
+F:	tools/testing/selftests/mm/rmap.c
 
 MEMORY MANAGEMENT - SECRETMEM
 M:	Andrew Morton <akpm@linux-foundation.org>
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index e7b23a8a05fe..92af0ae0fa7f 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -58,3 +58,4 @@ pkey_sighandler_tests_32
 pkey_sighandler_tests_64
 guard-regions
 merge
+rmap
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index d75f1effcb79..1a156637207f 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -102,6 +102,7 @@ TEST_GEN_FILES += hugetlb_dio
 TEST_GEN_FILES += droppable
 TEST_GEN_FILES += guard-regions
 TEST_GEN_FILES += merge
+TEST_GEN_FILES += rmap
 
 ifneq ($(ARCH),arm64)
 TEST_GEN_FILES += soft-dirty
@@ -229,6 +230,8 @@ $(OUTPUT)/ksm_tests: LDLIBS += -lnuma
 
 $(OUTPUT)/migration: LDLIBS += -lnuma
 
+$(OUTPUT)/rmap: LDLIBS += -lnuma
+
 local_config.mk local_config.h: check_config.sh
 	/bin/sh ./check_config.sh $(CC)
 
diff --git a/tools/testing/selftests/mm/rmap.c b/tools/testing/selftests/mm/rmap.c
new file mode 100644
index 000000000000..13f7bccfd0a9
--- /dev/null
+++ b/tools/testing/selftests/mm/rmap.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RMAP functional tests
+ *
+ * Author(s): Wei Yang <richard.weiyang@gmail.com>
+ */
+
+#include "../kselftest_harness.h"
+#include <strings.h>
+#include <pthread.h>
+#include <numa.h>
+#include <numaif.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <time.h>
+#include <sys/sem.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#include "vm_util.h"
+
+#define TOTAL_LEVEL 5
+#define MAX_CHILDREN 3
+
+#define FAIL_ON_CHECK	(1 << 0)
+#define FAIL_ON_WORK	(1 << 1)
+
+struct sembuf sem_wait = {0, -1, 0};
+struct sembuf sem_signal = {0, 1, 0};
+
+enum backend_type {
+	ANON,
+	SHM,
+	NORM_FILE,
+};
+
+#define PREFIX "kst_rmap"
+#define MAX_FILENAME_LEN 256
+const char *suffixes[] = {
+	"",
+	"_shm",
+	"_file",
+};
+
+struct global_data;
+typedef int (*work_fn)(struct global_data *data);
+typedef int (*check_fn)(struct global_data *data);
+typedef void (*prepare_fn)(struct global_data *data);
+
+struct global_data {
+	int worker_level;
+
+	int semid;
+	int pipefd[2];
+
+	unsigned int mapsize;
+	unsigned int rand_seed;
+	char *region;
+
+	prepare_fn do_prepare;
+	work_fn do_work;
+	check_fn do_check;
+
+	enum backend_type backend;
+	char filename[MAX_FILENAME_LEN];
+
+	unsigned long *expected_pfn;
+};
+
+/*
+ * Create a process tree with TOTAL_LEVEL height and at most MAX_CHILDREN
+ * children for each.
+ *
+ * It will randomly select one process as 'worker' process which will
+ * 'do_work' until all processes are created. And all other processes will
+ * wait until 'worker' finish its work.
+ */
+void propagate_children(struct __test_metadata *_metadata, struct global_data *data)
+{
+	pid_t root_pid, pid;
+	unsigned int num_child;
+	int status;
+	int ret = 0;
+	int curr_child, worker_child;
+	int curr_level = 1;
+	bool is_worker = true;
+
+	root_pid = getpid();
+repeat:
+	num_child = rand_r(&data->rand_seed) % MAX_CHILDREN + 1;
+	worker_child = is_worker ? rand_r(&data->rand_seed) % num_child : -1;
+
+	for (curr_child = 0; curr_child < num_child; curr_child++) {
+		pid = fork();
+
+		if (pid < 0) {
+			perror("Error: fork\n");
+		} else if (pid == 0) {
+			curr_level++;
+
+			if (curr_child != worker_child)
+				is_worker = false;
+
+			if (curr_level == TOTAL_LEVEL)
+				break;
+
+			data->rand_seed += curr_child;
+			goto repeat;
+		}
+	}
+
+	if (data->do_prepare)
+		data->do_prepare(data);
+
+	close(data->pipefd[1]);
+
+	if (is_worker && curr_level == data->worker_level) {
+		/* This is the worker process, first wait last process created */
+		char buf;
+
+		while (read(data->pipefd[0], &buf, 1) > 0)
+			;
+
+		if (data->do_work)
+			ret = data->do_work(data);
+
+		/* Kick others */
+		semctl(data->semid, 0, IPC_RMID);
+	} else {
+		/* Wait worker finish */
+		semop(data->semid, &sem_wait, 1);
+		if (data->do_check)
+			ret = data->do_check(data);
+	}
+
+	/* Wait all child to quit */
+	while (wait(&status) > 0) {
+		if (WIFEXITED(status))
+			ret |= WEXITSTATUS(status);
+	}
+
+	if (getpid() == root_pid) {
+		if (ret & FAIL_ON_WORK)
+			SKIP(return, "Failed in worker");
+
+		ASSERT_EQ(ret, 0);
+	} else {
+		exit(ret);
+	}
+}
+
+FIXTURE(migrate)
+{
+	struct global_data data;
+};
+
+FIXTURE_SETUP(migrate)
+{
+	struct global_data *data = &self->data;
+
+	if (numa_available() < 0)
+		SKIP(return, "NUMA not available");
+	if (numa_bitmask_weight(numa_all_nodes_ptr) <= 1)
+		SKIP(return, "Not enough NUMA nodes available");
+
+	data->mapsize = getpagesize();
+
+	data->expected_pfn = mmap(0, sizeof(unsigned long),
+				PROT_READ | PROT_WRITE,
+				MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(data->expected_pfn, MAP_FAILED);
+
+	/* Prepare semaphore */
+	data->semid = semget(IPC_PRIVATE, 1, 0666 | IPC_CREAT);
+	ASSERT_NE(data->semid, -1);
+	ASSERT_NE(semctl(data->semid, 0, SETVAL, 0), -1);
+
+	/* Prepare pipe */
+	ASSERT_NE(pipe(data->pipefd), -1);
+
+	data->rand_seed = time(NULL);
+	srand(data->rand_seed);
+
+	data->worker_level = rand() % TOTAL_LEVEL + 1;
+
+	data->do_prepare = NULL;
+	data->do_work = NULL;
+	data->do_check = NULL;
+
+	data->backend = ANON;
+};
+
+FIXTURE_TEARDOWN(migrate)
+{
+	struct global_data *data = &self->data;
+
+	if (data->region != MAP_FAILED)
+		munmap(data->region, data->mapsize);
+	data->region = MAP_FAILED;
+	if (data->expected_pfn != MAP_FAILED)
+		munmap(data->expected_pfn, sizeof(unsigned long));
+	data->expected_pfn = MAP_FAILED;
+	semctl(data->semid, 0, IPC_RMID);
+	data->semid = -1;
+
+	close(data->pipefd[0]);
+
+	switch (data->backend) {
+	case ANON:
+		break;
+	case SHM:
+		shm_unlink(data->filename);
+		break;
+	case NORM_FILE:
+		unlink(data->filename);
+		break;
+	}
+}
+
+void access_region(struct global_data *data)
+{
+	/*
+	 * Force read "region" to make sure page fault in.
+	 */
+	FORCE_READ(*data->region);
+}
+
+int try_to_move_page(char *region)
+{
+	int ret;
+	int node;
+	int status = 0;
+	int failures = 0;
+
+	ret = move_pages(0, 1, (void **)&region, NULL, &status, MPOL_MF_MOVE_ALL);
+	if (ret != 0) {
+		perror("Failed to get original numa");
+		return FAIL_ON_WORK;
+	}
+
+	/* Pick up a different target node */
+	for (node = 0; node <= numa_max_node(); node++) {
+		if (numa_bitmask_isbitset(numa_all_nodes_ptr, node) && node != status)
+			break;
+	}
+
+	if (node > numa_max_node()) {
+		ksft_print_msg("Couldn't find available numa node for testing\n");
+		return FAIL_ON_WORK;
+	}
+
+	while (1) {
+		ret = move_pages(0, 1, (void **)&region, &node, &status, MPOL_MF_MOVE_ALL);
+
+		/* migrate successfully */
+		if (!ret)
+			break;
+
+		/* error happened */
+		if (ret < 0) {
+			ksft_perror("Failed to move pages");
+			return FAIL_ON_WORK;
+		}
+
+		/* migration is best effort; try again */
+		if (++failures >= 100)
+			return FAIL_ON_WORK;
+	}
+
+	return 0;
+}
+
+int move_region(struct global_data *data)
+{
+	int ret;
+	int pagemap_fd;
+
+	ret = try_to_move_page(data->region);
+	if (ret != 0)
+		return ret;
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd == -1)
+		return FAIL_ON_WORK;
+	*data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region);
+
+	return 0;
+}
+
+int has_same_pfn(struct global_data *data)
+{
+	unsigned long pfn;
+	int pagemap_fd;
+
+	if (data->region == MAP_FAILED)
+		return 0;
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd == -1)
+		return FAIL_ON_CHECK;
+
+	pfn = pagemap_get_pfn(pagemap_fd, data->region);
+	if (pfn != *data->expected_pfn)
+		return FAIL_ON_CHECK;
+
+	return 0;
+}
+
+TEST_F(migrate, anon)
+{
+	struct global_data *data = &self->data;
+
+	/* Map an area and fault in */
+	data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(data->region, MAP_FAILED);
+	memset(data->region, 0xcf, data->mapsize);
+
+	data->do_prepare = access_region;
+	data->do_work = move_region;
+	data->do_check = has_same_pfn;
+
+	propagate_children(_metadata, data);
+}
+
+TEST_F(migrate, shm)
+{
+	int shm_fd;
+	struct global_data *data = &self->data;
+
+	snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[SHM]);
+	shm_fd = shm_open(data->filename, O_CREAT | O_RDWR, 0666);
+	ASSERT_NE(shm_fd, -1);
+	ftruncate(shm_fd, data->mapsize);
+	data->backend = SHM;
+
+	/* Map a shared area and fault in */
+	data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+				MAP_SHARED, shm_fd, 0);
+	ASSERT_NE(data->region, MAP_FAILED);
+	memset(data->region, 0xcf, data->mapsize);
+	close(shm_fd);
+
+	data->do_prepare = access_region;
+	data->do_work = move_region;
+	data->do_check = has_same_pfn;
+
+	propagate_children(_metadata, data);
+}
+
+TEST_F(migrate, file)
+{
+	int fd;
+	struct global_data *data = &self->data;
+
+	snprintf(data->filename, MAX_FILENAME_LEN, "%s%s", PREFIX, suffixes[NORM_FILE]);
+	fd = open(data->filename, O_CREAT | O_RDWR | O_EXCL, 0666);
+	ASSERT_NE(fd, -1);
+	ftruncate(fd, data->mapsize);
+	data->backend = NORM_FILE;
+
+	/* Map a shared area and fault in */
+	data->region = mmap(0, data->mapsize, PROT_READ | PROT_WRITE,
+				MAP_SHARED, fd, 0);
+	ASSERT_NE(data->region, MAP_FAILED);
+	memset(data->region, 0xcf, data->mapsize);
+	close(fd);
+
+	data->do_prepare = access_region;
+	data->do_work = move_region;
+	data->do_check = has_same_pfn;
+
+	propagate_children(_metadata, data);
+}
+
+void prepare_local_region(struct global_data *data)
+{
+	/* Allocate range and set the same data */
+	data->region = mmap(NULL, data->mapsize, PROT_READ|PROT_WRITE,
+			   MAP_PRIVATE|MAP_ANON, -1, 0);
+	if (data->region == MAP_FAILED)
+		return;
+
+	memset(data->region, 0xcf, data->mapsize);
+}
+
+int merge_and_migrate(struct global_data *data)
+{
+	int pagemap_fd;
+	int ret = 0;
+
+	if (data->region == MAP_FAILED)
+		return FAIL_ON_WORK;
+
+	if (ksm_start() < 0)
+		return FAIL_ON_WORK;
+
+	ret = try_to_move_page(data->region);
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd == -1)
+		return FAIL_ON_WORK;
+	*data->expected_pfn = pagemap_get_pfn(pagemap_fd, data->region);
+
+	return ret;
+}
+
+TEST_F(migrate, ksm)
+{
+	int ret;
+	struct global_data *data = &self->data;
+
+	if (ksm_stop() < 0)
+		SKIP(return, "accessing \"/sys/kernel/mm/ksm/run\") failed");
+	if (ksm_get_full_scans() < 0)
+		SKIP(return, "accessing \"/sys/kernel/mm/ksm/full_scan\") failed");
+
+	ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+	if (ret < 0 && errno == EINVAL)
+		SKIP(return, "PR_SET_MEMORY_MERGE not supported");
+	else if (ret)
+		ksft_exit_fail_perror("PR_SET_MEMORY_MERGE=1 failed");
+
+	data->do_prepare = prepare_local_region;
+	data->do_work = merge_and_migrate;
+	data->do_check = has_same_pfn;
+
+	propagate_children(_metadata, data);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 471e539d82b8..75b94fdc915f 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -85,6 +85,8 @@ separated by spaces:
 	test handling of page fragment allocation and freeing
 - vma_merge
 	test VMA merge cases behave as expected
+- rmap
+	test rmap behaves as expected
 
 example: ./run_vmtests.sh -t "hmm mmap ksm"
 EOF
@@ -532,6 +534,8 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
 
 CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
 
+CATEGORY="rmap" run_test ./rmap
+
 echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
 echo "1..${count_total}" | tap_output
 
-- 
2.34.1

Re: [Patch v3 0/2] assert rmap behaves as expected

[Andrew Morton]

On Mon, 18 Aug 2025 02:29:03 +0000 Wei Yang <richard.weiyang@gmail.com> wrote:

> As David suggested, currently we don't have a high level test case to
> verify the behavior of rmap. This patch set introduce the verification
> on rmap by migration.

I'm seeing many rejects here, so please redo against tomorrow's mm-new?

Also, seeing "assert" in the changelogs was a little surprising.  The
term "assert" made me expect to see assertions, such as VM_BUG_ON(). 
Perhaps "test that" would be clearer.

Re: [Patch v3 0/2] assert rmap behaves as expected

[Wei Yang]

On Sun, Aug 17, 2025 at 08:06:42PM -0700, Andrew Morton wrote:
>On Mon, 18 Aug 2025 02:29:03 +0000 Wei Yang <richard.weiyang@gmail.com> wrote:
>
>> As David suggested, currently we don't have a high level test case to
>> verify the behavior of rmap. This patch set introduce the verification
>> on rmap by migration.
>
>I'm seeing many rejects here, so please redo against tomorrow's mm-new?
>

Sure.

>Also, seeing "assert" in the changelogs was a little surprising.  The
>term "assert" made me expect to see assertions, such as VM_BUG_ON(). 
>Perhaps "test that" would be clearer.

Will update it.

-- 
Wei Yang
Help you, Help me