Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

12 files changed, 522 insertions, 124 deletions

diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index bfabb19dc0d3..196b6640bf37 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -57,6 +57,19 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
 test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
 echo "$orig_content" > "$file"
 
+# Test schemes file
+# =================
+
+file="$DBGFS/schemes"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
+	"$orig_content" "valid input"
+test_write_fail "$file" "1 2
+3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
+test_write_succ "$file" "" "$orig_content" "disabling"
+echo "$orig_content" > "$file"
+
 # Test target_ids file
 # ====================
 
diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config
index a7e8cd5bb265..1eef042a31e1 100644
--- a/tools/testing/selftests/memory-hotplug/config
+++ b/tools/testing/selftests/memory-hotplug/config
@@ -1,5 +1,4 @@
 CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTPLUG_SPARSE=y
 CONFIG_NOTIFIER_ERROR_INJECTION=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_MEMORY_HOTREMOVE=y
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index b02eac613fdd..2e7e86e85282 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 hugepage-mmap
+hugepage-mremap
 hugepage-shm
 khugepaged
 map_hugetlb
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d9605bd10f2d..1607322a112c 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -29,6 +29,7 @@ TEST_GEN_FILES = compaction_test
 TEST_GEN_FILES += gup_test
 TEST_GEN_FILES += hmm-tests
 TEST_GEN_FILES += hugepage-mmap
+TEST_GEN_FILES += hugepage-mremap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += khugepaged
 TEST_GEN_FILES += madv_populate
diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c
new file mode 100644
index 000000000000..257df94697a5
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-mremap.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * hugepage-mremap:
+ *
+ * Example of remapping huge page memory in a user application using the
+ * mremap system call.  Code assumes a hugetlbfs filesystem is mounted
+ * at './huge'.  The code will use 10MB worth of huge pages.
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <errno.h>
+#include <fcntl.h> /* Definition of O_* constants */
+#include <sys/syscall.h> /* Definition of SYS_* constants */
+#include <linux/userfaultfd.h>
+#include <sys/ioctl.h>
+
+#define LENGTH (1UL * 1024 * 1024 * 1024)
+
+#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
+#define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
+
+static void check_bytes(char *addr)
+{
+	printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int read_bytes(char *addr)
+{
+	unsigned long i;
+
+	check_bytes(addr);
+	for (i = 0; i < LENGTH; i++)
+		if (*(addr + i) != (char)i) {
+			printf("Mismatch at %lu\n", i);
+			return 1;
+		}
+	return 0;
+}
+
+static void register_region_with_uffd(char *addr, size_t len)
+{
+	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);
+	}
+
+	/* Create a private anonymous mapping. The memory will be
+	 * demand-zero paged--that is, not yet allocated. When we
+	 * actually touch the memory, it will be allocated via
+	 * the userfaultfd.
+	 */
+
+	addr = mmap(NULL, len, PROT_READ | PROT_WRITE,
+		    MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	printf("Address returned by mmap() = %p\n", addr);
+
+	/* Register the memory range of the mapping we just created for
+	 * handling by the userfaultfd object. In mode, we request to track
+	 * missing pages (i.e., pages that have not yet been faulted in).
+	 */
+
+	uffdio_register.range.start = (unsigned long)addr;
+	uffdio_register.range.len = len;
+	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+		perror("ioctl-UFFDIO_REGISTER");
+		exit(1);
+	}
+}
+
+int main(void)
+{
+	int ret = 0;
+
+	int fd = open("/huge/test", O_CREAT | O_RDWR, 0755);
+
+	if (fd < 0) {
+		perror("Open failed");
+		exit(1);
+	}
+
+	/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
+	unsigned long suggested_addr = 0x7eaa40000000;
+	void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+			   MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
+	printf("Map haddr: Returned address is %p\n", haddr);
+	if (haddr == MAP_FAILED) {
+		perror("mmap1");
+		exit(1);
+	}
+
+	/* mmap again to a dummy address to hopefully trigger pmd sharing. */
+	suggested_addr = 0x7daa40000000;
+	void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+			   MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
+	printf("Map daddr: Returned address is %p\n", daddr);
+	if (daddr == MAP_FAILED) {
+		perror("mmap3");
+		exit(1);
+	}
+
+	suggested_addr = 0x7faa40000000;
+	void *vaddr =
+		mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0);
+	printf("Map vaddr: Returned address is %p\n", vaddr);
+	if (vaddr == MAP_FAILED) {
+		perror("mmap2");
+		exit(1);
+	}
+
+	register_region_with_uffd(haddr, LENGTH);
+
+	void *addr = mremap(haddr, LENGTH, LENGTH,
+			    MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
+	if (addr == MAP_FAILED) {
+		perror("mremap");
+		exit(1);
+	}
+
+	printf("Mremap: Returned address is %p\n", addr);
+	check_bytes(addr);
+	write_bytes(addr);
+	ret = read_bytes(addr);
+
+	munmap(addr, LENGTH);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c
index b61dcdb44c5b..1436e1a9a3d3 100644
--- a/tools/testing/selftests/vm/ksm_tests.c
+++ b/tools/testing/selftests/vm/ksm_tests.c
@@ -5,6 +5,10 @@
 #include <time.h>
 #include <string.h>
 #include <numa.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <err.h>
 
 #include "../kselftest.h"
 #include "../../../../include/vdso/time64.h"
@@ -18,6 +22,15 @@
 #define KSM_MERGE_ACROSS_NODES_DEFAULT true
 #define MB (1ul << 20)
 
+#define PAGE_SHIFT 12
+#define HPAGE_SHIFT 21
+
+#define PAGE_SIZE (1 << PAGE_SHIFT)
+#define HPAGE_SIZE (1 << HPAGE_SHIFT)
+
+#define PAGEMAP_PRESENT(ent)	(((ent) & (1ull << 63)) != 0)
+#define PAGEMAP_PFN(ent)	((ent) & ((1ull << 55) - 1))
+
 struct ksm_sysfs {
 	unsigned long max_page_sharing;
 	unsigned long merge_across_nodes;
@@ -34,6 +47,7 @@ enum ksm_test_name {
 	CHECK_KSM_ZERO_PAGE_MERGE,
 	CHECK_KSM_NUMA_MERGE,
 	KSM_MERGE_TIME,
+	KSM_MERGE_TIME_HUGE_PAGES,
 	KSM_COW_TIME
 };
 
@@ -100,6 +114,9 @@ static void print_help(void)
 	       " -P evaluate merging time and speed.\n"
 	       "    For this test, the size of duplicated memory area (in MiB)\n"
 	       "    must be provided using -s option\n"
+				 " -H evaluate merging time and speed of area allocated mostly with huge pages\n"
+	       "    For this test, the size of duplicated memory area (in MiB)\n"
+	       "    must be provided using -s option\n"
 	       " -C evaluate the time required to break COW of merged pages.\n\n");
 
 	printf(" -a: specify the access protections of pages.\n"
@@ -354,12 +371,34 @@ err_out:
 	return KSFT_FAIL;
 }
 
+static int get_next_mem_node(int node)
+{
+
+	long node_size;
+	int mem_node = 0;
+	int i, max_node = numa_max_node();
+
+	for (i = node + 1; i <= max_node + node; i++) {
+		mem_node = i % (max_node + 1);
+		node_size = numa_node_size(mem_node, NULL);
+		if (node_size > 0)
+			break;
+	}
+	return mem_node;
+}
+
+static int get_first_mem_node(void)
+{
+	return get_next_mem_node(numa_max_node());
+}
+
 static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_across_nodes,
 				size_t page_size)
 {
 	void *numa1_map_ptr, *numa2_map_ptr;
 	struct timespec start_time;
 	int page_count = 2;
+	int first_node;
 
 	if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
 		perror("clock_gettime");
@@ -370,7 +409,7 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a
 		perror("NUMA support not enabled");
 		return KSFT_SKIP;
 	}
-	if (numa_max_node() < 1) {
+	if (numa_num_configured_nodes() <= 1) {
 		printf("At least 2 NUMA nodes must be available\n");
 		return KSFT_SKIP;
 	}
@@ -378,8 +417,9 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a
 		return KSFT_FAIL;
 
 	/* allocate 2 pages in 2 different NUMA nodes and fill them with the same data */
-	numa1_map_ptr = numa_alloc_onnode(page_size, 0);
-	numa2_map_ptr = numa_alloc_onnode(page_size, 1);
+	first_node = get_first_mem_node();
+	numa1_map_ptr = numa_alloc_onnode(page_size, first_node);
+	numa2_map_ptr = numa_alloc_onnode(page_size, get_next_mem_node(first_node));
 	if (!numa1_map_ptr || !numa2_map_ptr) {
 		perror("numa_alloc_onnode");
 		return KSFT_FAIL;
@@ -416,6 +456,101 @@ err_out:
 	return KSFT_FAIL;
 }
 
+int64_t allocate_transhuge(void *ptr, int pagemap_fd)
+{
+	uint64_t ent[2];
+
+	/* drop pmd */
+	if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_ANONYMOUS |
+				MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+		errx(2, "mmap transhuge");
+
+	if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
+		err(2, "MADV_HUGEPAGE");
+
+	/* allocate transparent huge page */
+	*(volatile void **)ptr = ptr;
+
+	if (pread(pagemap_fd, ent, sizeof(ent),
+			(uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
+		err(2, "read pagemap");
+
+	if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
+	    PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
+	    !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
+		return PAGEMAP_PFN(ent[0]);
+
+	return -1;
+}
+
+static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size)
+{
+	void *map_ptr, *map_ptr_orig;
+	struct timespec start_time, end_time;
+	unsigned long scan_time_ns;
+	int pagemap_fd, n_normal_pages, n_huge_pages;
+
+	map_size *= MB;
+	size_t len = map_size;
+
+	len -= len % HPAGE_SIZE;
+	map_ptr_orig = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0);
+	map_ptr = map_ptr_orig + HPAGE_SIZE - (uintptr_t)map_ptr_orig % HPAGE_SIZE;
+
+	if (map_ptr_orig == MAP_FAILED)
+		err(2, "initial mmap");
+
+	if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE))
+		err(2, "MADV_HUGEPAGE");
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd < 0)
+		err(2, "open pagemap");
+
+	n_normal_pages = 0;
+	n_huge_pages = 0;
+	for (void *p = map_ptr; p < map_ptr + len; p += HPAGE_SIZE) {
+		if (allocate_transhuge(p, pagemap_fd) < 0)
+			n_normal_pages++;
+		else
+			n_huge_pages++;
+	}
+	printf("Number of normal pages:    %d\n", n_normal_pages);
+	printf("Number of huge pages:    %d\n", n_huge_pages);
+
+	memset(map_ptr, '*', len);
+
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
+		perror("clock_gettime");
+		goto err_out;
+	}
+	if (ksm_merge_pages(map_ptr, map_size, start_time, timeout))
+		goto err_out;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) {
+		perror("clock_gettime");
+		goto err_out;
+	}
+
+	scan_time_ns = (end_time.tv_sec - start_time.tv_sec) * NSEC_PER_SEC +
+		       (end_time.tv_nsec - start_time.tv_nsec);
+
+	printf("Total size:    %lu MiB\n", map_size / MB);
+	printf("Total time:    %ld.%09ld s\n", scan_time_ns / NSEC_PER_SEC,
+	       scan_time_ns % NSEC_PER_SEC);
+	printf("Average speed:  %.3f MiB/s\n", (map_size / MB) /
+					       ((double)scan_time_ns / NSEC_PER_SEC));
+
+	munmap(map_ptr_orig, len + HPAGE_SIZE);
+	return KSFT_PASS;
+
+err_out:
+	printf("Not OK\n");
+	munmap(map_ptr_orig, len + HPAGE_SIZE);
+	return KSFT_FAIL;
+}
+
 static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size)
 {
 	void *map_ptr;
@@ -541,7 +676,7 @@ int main(int argc, char *argv[])
 	bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT;
 	long size_MB = 0;
 
-	while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPC")) != -1) {
+	while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCH")) != -1) {
 		switch (opt) {
 		case 'a':
 			prot = str_to_prot(optarg);
@@ -595,6 +730,9 @@ int main(int argc, char *argv[])
 		case 'P':
 			test_name = KSM_MERGE_TIME;
 			break;
+		case 'H':
+			test_name = KSM_MERGE_TIME_HUGE_PAGES;
+			break;
 		case 'C':
 			test_name = KSM_COW_TIME;
 			break;
@@ -647,6 +785,14 @@ int main(int argc, char *argv[])
 		ret = ksm_merge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
 				     size_MB);
 		break;
+	case KSM_MERGE_TIME_HUGE_PAGES:
+		if (size_MB == 0) {
+			printf("Option '-s' is required.\n");
+			return KSFT_FAIL;
+		}
+		ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot,
+				ksm_scan_limit_sec, size_MB);
+		break;
 	case KSM_COW_TIME:
 		ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
 				   page_size);
diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c
index b959e4ebdad4..3ee0e8275600 100644
--- a/tools/testing/selftests/vm/madv_populate.c
+++ b/tools/testing/selftests/vm/madv_populate.c
@@ -14,12 +14,11 @@
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/mman.h>
 #include <sys/mman.h>
 
 #include "../kselftest.h"
 
-#if defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE)
-
 /*
  * For now, we're using 2 MiB of private anonymous memory for all tests.
  */
@@ -328,15 +327,3 @@ int main(int argc, char **argv)
 				   err, ksft_test_num());
 	return ksft_exit_pass();
 }
-
-#else /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */
-
-#warning "missing MADV_POPULATE_READ or MADV_POPULATE_WRITE definition"
-
-int main(int argc, char **argv)
-{
-	ksft_print_header();
-	ksft_exit_skip("MADV_POPULATE_READ or MADV_POPULATE_WRITE not defined\n");
-}
-
-#endif /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 45e803af7c77..a24d30af3094 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -108,6 +108,17 @@ else
 	echo "[PASS]"
 fi
 
+echo "-----------------------"
+echo "running hugepage-mremap"
+echo "-----------------------"
+./hugepage-mremap
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 echo "NOTE: The above hugetlb tests provide minimal coverage.  Use"
 echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
 echo "      hugetlb regression testing."
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
index fd7f1b4a96f9..5e4c036f6ad3 100644
--- a/tools/testing/selftests/vm/transhuge-stress.c
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -79,7 +79,7 @@ int main(int argc, char **argv)
 
 	warnx("allocate %zd transhuge pages, using %zd MiB virtual memory"
 	      " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20,
-	      len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1));
+	      ram >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1));
 
 	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
 	if (pagemap_fd < 0)
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 60aa1a4fc69b..8a09057d2f22 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -57,6 +57,7 @@
 #include <assert.h>
 #include <inttypes.h>
 #include <stdint.h>
+#include <sys/random.h>
 
 #include "../kselftest.h"
 
@@ -307,37 +308,24 @@ static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset)
 }
 
 struct uffd_test_ops {
-	unsigned long expected_ioctls;
 	void (*allocate_area)(void **alloc_area);
 	void (*release_pages)(char *rel_area);
 	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
-#define SHMEM_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
-					 (1 << _UFFDIO_COPY) | \
-					 (1 << _UFFDIO_ZEROPAGE))
-
-#define ANON_EXPECTED_IOCTLS		((1 << _UFFDIO_WAKE) | \
-					 (1 << _UFFDIO_COPY) | \
-					 (1 << _UFFDIO_ZEROPAGE) | \
-					 (1 << _UFFDIO_WRITEPROTECT))
-
 static struct uffd_test_ops anon_uffd_test_ops = {
-	.expected_ioctls = ANON_EXPECTED_IOCTLS,
 	.allocate_area	= anon_allocate_area,
 	.release_pages	= anon_release_pages,
 	.alias_mapping = noop_alias_mapping,
 };
 
 static struct uffd_test_ops shmem_uffd_test_ops = {
-	.expected_ioctls = SHMEM_EXPECTED_IOCTLS,
 	.allocate_area	= shmem_allocate_area,
 	.release_pages	= shmem_release_pages,
 	.alias_mapping = shmem_alias_mapping,
 };
 
 static struct uffd_test_ops hugetlb_uffd_test_ops = {
-	.expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC & ~(1 << _UFFDIO_CONTINUE),
 	.allocate_area	= hugetlb_allocate_area,
 	.release_pages	= hugetlb_release_pages,
 	.alias_mapping = hugetlb_alias_mapping,
@@ -345,6 +333,43 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = {
 
 static struct uffd_test_ops *uffd_test_ops;
 
+static inline uint64_t uffd_minor_feature(void)
+{
+	if (test_type == TEST_HUGETLB && map_shared)
+		return UFFD_FEATURE_MINOR_HUGETLBFS;
+	else if (test_type == TEST_SHMEM)
+		return UFFD_FEATURE_MINOR_SHMEM;
+	else
+		return 0;
+}
+
+static uint64_t get_expected_ioctls(uint64_t mode)
+{
+	uint64_t ioctls = UFFD_API_RANGE_IOCTLS;
+
+	if (test_type == TEST_HUGETLB)
+		ioctls &= ~(1 << _UFFDIO_ZEROPAGE);
+
+	if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp))
+		ioctls &= ~(1 << _UFFDIO_WRITEPROTECT);
+
+	if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor))
+		ioctls &= ~(1 << _UFFDIO_CONTINUE);
+
+	return ioctls;
+}
+
+static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls)
+{
+	uint64_t expected = get_expected_ioctls(mode);
+	uint64_t actual = ioctls & expected;
+
+	if (actual != expected) {
+		err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64,
+		    expected, actual);
+	}
+}
+
 static void userfaultfd_open(uint64_t *features)
 {
 	struct uffdio_api uffdio_api;
@@ -405,7 +430,7 @@ static void uffd_test_ctx_clear(void)
 	munmap_area((void **)&area_dst_alias);
 }
 
-static void uffd_test_ctx_init_ext(uint64_t *features)
+static void uffd_test_ctx_init(uint64_t features)
 {
 	unsigned long nr, cpu;
 
@@ -414,7 +439,7 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 	uffd_test_ops->allocate_area((void **)&area_src);
 	uffd_test_ops->allocate_area((void **)&area_dst);
 
-	userfaultfd_open(features);
+	userfaultfd_open(&features);
 
 	count_verify = malloc(nr_pages * sizeof(unsigned long long));
 	if (!count_verify)
@@ -462,11 +487,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
 			err("pipe");
 }
 
-static inline void uffd_test_ctx_init(uint64_t features)
-{
-	uffd_test_ctx_init_ext(&features);
-}
-
 static int my_bcmp(char *str1, char *str2, size_t n)
 {
 	unsigned long i;
@@ -518,22 +538,10 @@ static void continue_range(int ufd, __u64 start, __u64 len)
 static void *locking_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
-	struct random_data rand;
 	unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
-	int32_t rand_nr;
 	unsigned long long count;
-	char randstate[64];
-	unsigned int seed;
 
-	if (bounces & BOUNCE_RANDOM) {
-		seed = (unsigned int) time(NULL) - bounces;
-		if (!(bounces & BOUNCE_RACINGFAULTS))
-			seed += cpu;
-		bzero(&rand, sizeof(rand));
-		bzero(&randstate, sizeof(randstate));
-		if (initstate_r(seed, randstate, sizeof(randstate), &rand))
-			err("initstate_r failed");
-	} else {
+	if (!(bounces & BOUNCE_RANDOM)) {
 		page_nr = -bounces;
 		if (!(bounces & BOUNCE_RACINGFAULTS))
 			page_nr += cpu * nr_pages_per_cpu;
@@ -541,15 +549,8 @@ static void *locking_thread(void *arg)
 
 	while (!finished) {
 		if (bounces & BOUNCE_RANDOM) {
-			if (random_r(&rand, &rand_nr))
-				err("random_r failed");
-			page_nr = rand_nr;
-			if (sizeof(page_nr) > sizeof(rand_nr)) {
-				if (random_r(&rand, &rand_nr))
-					err("random_r failed");
-				page_nr |= (((unsigned long) rand_nr) << 16) <<
-					   16;
-			}
+			if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr))
+				err("getrandom failed");
 		} else
 			page_nr += 1;
 		page_nr %= nr_pages;
@@ -1030,11 +1031,9 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
-	unsigned long has_zeropage;
+	bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE);
 	__s64 res;
 
-	has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE);
-
 	if (offset >= nr_pages * page_size)
 		err("unexpected offset %lu", offset);
 	uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
@@ -1074,7 +1073,6 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 static int userfaultfd_zeropage_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 
 	printf("testing UFFDIO_ZEROPAGE: ");
 	fflush(stdout);
@@ -1089,9 +1087,8 @@ static int userfaultfd_zeropage_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (uffdio_zeropage(uffd, 0))
 		if (my_bcmp(area_dst, zeropage, page_size))
@@ -1104,7 +1101,6 @@ static int userfaultfd_zeropage_test(void)
 static int userfaultfd_events_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	pthread_t uffd_mon;
 	int err, features;
 	pid_t pid;
@@ -1128,9 +1124,8 @@ static int userfaultfd_events_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
 		err("uffd_poll_thread create");
@@ -1158,7 +1153,6 @@ static int userfaultfd_events_test(void)
 static int userfaultfd_sig_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	unsigned long userfaults;
 	pthread_t uffd_mon;
 	int err, features;
@@ -1182,9 +1176,8 @@ static int userfaultfd_sig_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl for anon memory");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	if (faulting_process(1))
 		err("faulting process failed");
@@ -1219,14 +1212,12 @@ static int userfaultfd_sig_test(void)
 static int userfaultfd_minor_test(void)
 {
 	struct uffdio_register uffdio_register;
-	unsigned long expected_ioctls;
 	unsigned long p;
 	pthread_t uffd_mon;
 	uint8_t expected_byte;
 	void *expected_page;
 	char c;
 	struct uffd_stats stats = { 0 };
-	uint64_t req_features, features_out;
 
 	if (!test_uffdio_minor)
 		return 0;
@@ -1234,21 +1225,7 @@ static int userfaultfd_minor_test(void)
 	printf("testing minor faults: ");
 	fflush(stdout);
 
-	if (test_type == TEST_HUGETLB)
-		req_features = UFFD_FEATURE_MINOR_HUGETLBFS;
-	else if (test_type == TEST_SHMEM)
-		req_features = UFFD_FEATURE_MINOR_SHMEM;
-	else
-		return 1;
-
-	features_out = req_features;
-	uffd_test_ctx_init_ext(&features_out);
-	/* If kernel reports required features aren't supported, skip test. */
-	if ((features_out & req_features) != req_features) {
-		printf("skipping test due to lack of feature support\n");
-		fflush(stdout);
-		return 0;
-	}
+	uffd_test_ctx_init(uffd_minor_feature());
 
 	uffdio_register.range.start = (unsigned long)area_dst_alias;
 	uffdio_register.range.len = nr_pages * page_size;
@@ -1256,10 +1233,8 @@ static int userfaultfd_minor_test(void)
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 		err("register failure");
 
-	expected_ioctls = uffd_test_ops->expected_ioctls;
-	expected_ioctls |= 1 << _UFFDIO_CONTINUE;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
-		err("unexpected missing ioctl(s)");
+	assert_expected_ioctls_present(
+		uffdio_register.mode, uffdio_register.ioctls);
 
 	/*
 	 * After registering with UFFD, populate the non-UFFD-registered side of
@@ -1456,8 +1431,6 @@ static int userfaultfd_stress(void)
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
 	while (bounces--) {
-		unsigned long expected_ioctls;
-
 		printf("bounces: %d, mode:", bounces);
 		if (bounces & BOUNCE_RANDOM)
 			printf(" rnd");
@@ -1485,10 +1458,8 @@ static int userfaultfd_stress(void)
 			uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
 		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
 			err("register failure");
-		expected_ioctls = uffd_test_ops->expected_ioctls;
-		if ((uffdio_register.ioctls & expected_ioctls) !=
-		    expected_ioctls)
-			err("unexpected missing ioctl for anon memory");
+		assert_expected_ioctls_present(
+			uffdio_register.mode, uffdio_register.ioctls);
 
 		if (area_dst_alias) {
 			uffdio_register.range.start = (unsigned long)
@@ -1609,6 +1580,8 @@ unsigned long default_huge_page_size(void)
 
 static void set_test_type(const char *type)
 {
+	uint64_t features = UFFD_API_FEATURES;
+
 	if (!strcmp(type, "anon")) {
 		test_type = TEST_ANON;
 		uffd_test_ops = &anon_uffd_test_ops;
@@ -1642,6 +1615,22 @@ static void set_test_type(const char *type)
 	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
 	    > page_size)
 		err("Impossible to run this test");
+
+	/*
+	 * Whether we can test certain features depends not just on test type,
+	 * but also on whether or not this particular kernel supports the
+	 * feature.
+	 */
+
+	userfaultfd_open(&features);
+
+	test_uffdio_wp = test_uffdio_wp &&
+		(features & UFFD_FEATURE_PAGEFAULT_FLAG_WP);
+	test_uffdio_minor = test_uffdio_minor &&
+		(features & uffd_minor_feature());
+
+	close(uffd);
+	uffd = -1;
 }
 
 static void sigalrm(int sig)
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index f62f10c988db..b1ed76d9a979 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -390,7 +390,7 @@ static void show_page_range(unsigned long voffset, unsigned long offset,
 		if (opt_pid)
 			printf("%lx\t", voff);
 		if (opt_file)
-			printf("%lu\t", voff);
+			printf("%lx\t", voff);
 		if (opt_list_cgroup)
 			printf("@%llu\t", (unsigned long long)cgroup0);
 		if (opt_list_mapcnt)
@@ -418,7 +418,7 @@ static void show_page(unsigned long voffset, unsigned long offset,
 	if (opt_pid)
 		printf("%lx\t", voffset);
 	if (opt_file)
-		printf("%lu\t", voffset);
+		printf("%lx\t", voffset);
 	if (opt_list_cgroup)
 		printf("@%llu\t", (unsigned long long)cgroup);
 	if (opt_list_mapcnt)
@@ -967,22 +967,19 @@ static struct sigaction sigbus_action = {
 	.sa_flags = SA_SIGINFO,
 };
 
-static void walk_file(const char *name, const struct stat *st)
+static void walk_file_range(const char *name, int fd,
+			    unsigned long off, unsigned long end)
 {
 	uint8_t vec[PAGEMAP_BATCH];
 	uint64_t buf[PAGEMAP_BATCH], flags;
 	uint64_t cgroup = 0;
 	uint64_t mapcnt = 0;
 	unsigned long nr_pages, pfn, i;
-	off_t off, end = st->st_size;
-	int fd;
 	ssize_t len;
 	void *ptr;
 	int first = 1;
 
-	fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW);
-
-	for (off = 0; off < end; off += len) {
+	for (; off < end; off += len) {
 		nr_pages = (end - off + page_size - 1) / page_size;
 		if (nr_pages > PAGEMAP_BATCH)
 			nr_pages = PAGEMAP_BATCH;
@@ -1037,12 +1034,26 @@ got_sigbus:
 			if (first && opt_list) {
 				first = 0;
 				flush_page_range();
-				show_file(name, st);
 			}
 			add_page(off / page_size + i, pfn,
 				 flags, cgroup, mapcnt, buf[i]);
 		}
 	}
+}
+
+static void walk_file(const char *name, const struct stat *st)
+{
+	int i;
+	int fd;
+
+	fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW);
+
+	if (!nr_addr_ranges)
+		add_addr_range(0, st->st_size / page_size);
+
+	for (i = 0; i < nr_addr_ranges; i++)
+		walk_file_range(name, fd, opt_offset[i] * page_size,
+				(opt_offset[i] + opt_size[i]) * page_size);
 
 	close(fd);
 }
@@ -1062,10 +1073,10 @@ int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f)
 	return 0;
 }
 
+struct stat st;
+
 static void walk_page_cache(void)
 {
-	struct stat st;
-
 	kpageflags_fd = checked_open(opt_kpageflags, O_RDONLY);
 	pagemap_fd = checked_open("/proc/self/pagemap", O_RDONLY);
 	sigaction(SIGBUS, &sigbus_action, NULL);
@@ -1362,6 +1373,11 @@ int main(int argc, char *argv[])
 	if (opt_list)
 		printf("\n\n");
 
+	if (opt_file) {
+		show_file(opt_file, &st);
+		printf("\n");
+	}
+
 	show_summary();
 
 	if (opt_list_mapcnt)
diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c
index 0e75f22c9475..9ebb84a9c731 100644
--- a/tools/vm/page_owner_sort.c
+++ b/tools/vm/page_owner_sort.c
@@ -5,6 +5,8 @@
  * Example use:
  * cat /sys/kernel/debug/page_owner > page_owner_full.txt
  * ./page_owner_sort page_owner_full.txt sorted_page_owner.txt
+ * Or sort by total memory:
+ * ./page_owner_sort -m page_owner_full.txt sorted_page_owner.txt
  *
  * See Documentation/vm/page_owner.rst
 */
@@ -16,14 +18,18 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
+#include <regex.h>
+#include <errno.h>
 
 struct block_list {
 	char *txt;
 	int len;
 	int num;
+	int page_num;
 };
 
-
+static int sort_by_memory;
+static regex_t order_pattern;
 static struct block_list *list;
 static int list_size;
 static int max_size;
@@ -59,12 +65,50 @@ static int compare_num(const void *p1, const void *p2)
 	return l2->num - l1->num;
 }
 
+static int compare_page_num(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l2->page_num - l1->page_num;
+}
+
+static int get_page_num(char *buf)
+{
+	int err, val_len, order_val;
+	char order_str[4] = {0};
+	char *endptr;
+	regmatch_t pmatch[2];
+
+	err = regexec(&order_pattern, buf, 2, pmatch, REG_NOTBOL);
+	if (err != 0 || pmatch[1].rm_so == -1) {
+		printf("no order pattern in %s\n", buf);
+		return 0;
+	}
+	val_len = pmatch[1].rm_eo - pmatch[1].rm_so;
+	if (val_len > 2) /* max_order should not exceed 2 digits */
+		goto wrong_order;
+
+	memcpy(order_str, buf + pmatch[1].rm_so, val_len);
+
+	errno = 0;
+	order_val = strtol(order_str, &endptr, 10);
+	if (errno != 0 || endptr == order_str || *endptr != '\0')
+		goto wrong_order;
+
+	return 1 << order_val;
+
+wrong_order:
+	printf("wrong order in follow buf:\n%s\n", buf);
+	return 0;
+}
+
 static void add_list(char *buf, int len)
 {
 	if (list_size != 0 &&
 	    len == list[list_size-1].len &&
 	    memcmp(buf, list[list_size-1].txt, len) == 0) {
 		list[list_size-1].num++;
+		list[list_size-1].page_num += get_page_num(buf);
 		return;
 	}
 	if (list_size == max_size) {
@@ -74,6 +118,7 @@ static void add_list(char *buf, int len)
 	list[list_size].txt = malloc(len+1);
 	list[list_size].len = len;
 	list[list_size].num = 1;
+	list[list_size].page_num = get_page_num(buf);
 	memcpy(list[list_size].txt, buf, len);
 	list[list_size].txt[len] = 0;
 	list_size++;
@@ -85,6 +130,13 @@ static void add_list(char *buf, int len)
 
 #define BUF_SIZE	(128 * 1024)
 
+static void usage(void)
+{
+	printf("Usage: ./page_owner_sort [-m] <input> <output>\n"
+		"-m	Sort by total memory. If this option is unset, sort by times\n"
+	);
+}
+
 int main(int argc, char **argv)
 {
 	FILE *fin, *fout;
@@ -92,21 +144,39 @@ int main(int argc, char **argv)
 	int ret, i, count;
 	struct block_list *list2;
 	struct stat st;
+	int err;
+	int opt;
 
-	if (argc < 3) {
-		printf("Usage: ./program <input> <output>\n");
-		perror("open: ");
+	while ((opt = getopt(argc, argv, "m")) != -1)
+		switch (opt) {
+		case 'm':
+			sort_by_memory = 1;
+			break;
+		default:
+			usage();
+			exit(1);
+		}
+
+	if (optind >= (argc - 1)) {
+		usage();
 		exit(1);
 	}
 
-	fin = fopen(argv[1], "r");
-	fout = fopen(argv[2], "w");
+	fin = fopen(argv[optind], "r");
+	fout = fopen(argv[optind + 1], "w");
 	if (!fin || !fout) {
-		printf("Usage: ./program <input> <output>\n");
+		usage();
 		perror("open: ");
 		exit(1);
 	}
 
+	err = regcomp(&order_pattern, "order\\s*([0-9]*),", REG_EXTENDED|REG_NEWLINE);
+	if (err != 0 || order_pattern.re_nsub != 1) {
+		printf("%s: Invalid pattern 'order\\s*([0-9]*),' code %d\n",
+			argv[0], err);
+		exit(1);
+	}
+
 	fstat(fileno(fin), &st);
 	max_size = st.st_size / 100; /* hack ... */
 
@@ -145,13 +215,19 @@ int main(int argc, char **argv)
 			list2[count++] = list[i];
 		} else {
 			list2[count-1].num += list[i].num;
+			list2[count-1].page_num += list[i].page_num;
 		}
 	}
 
-	qsort(list2, count, sizeof(list[0]), compare_num);
+	if (sort_by_memory)
+		qsort(list2, count, sizeof(list[0]), compare_page_num);
+	else
+		qsort(list2, count, sizeof(list[0]), compare_num);
 
 	for (i = 0; i < count; i++)
-		fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt);
+		fprintf(fout, "%d times, %d pages:\n%s\n",
+				list2[i].num, list2[i].page_num, list2[i].txt);
 
+	regfree(&order_pattern);
 	return 0;
 }