Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "146 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, vfs, and mm (slab-generic, slab, kmemleak,
  dax, kasan, debug, pagecache, gup, shmem, frontswap, memremap,
  memcg, selftests, pagemap, dma, vmalloc, memory-failure, hugetlb,
  userfaultfd, vmscan, mempolicy, oom-kill, hugetlbfs, migration, thp,
  ksm, page-poison, percpu, rmap, zswap, zram, cleanups, hmm, and
  damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (146 commits)
  mm/damon: hide kernel pointer from tracepoint event
  mm/damon/vaddr: hide kernel pointer from damon_va_three_regions() failure log
  mm/damon/vaddr: use pr_debug() for damon_va_three_regions() failure logging
  mm/damon/dbgfs: remove an unnecessary variable
  mm/damon: move the implementation of damon_insert_region to damon.h
  mm/damon: add access checking for hugetlb pages
  Docs/admin-guide/mm/damon/usage: update for schemes statistics
  mm/damon/dbgfs: support all DAMOS stats
  Docs/admin-guide/mm/damon/reclaim: document statistics parameters
  mm/damon/reclaim: provide reclamation statistics
  mm/damon/schemes: account how many times quota limit has exceeded
  mm/damon/schemes: account scheme actions that successfully applied
  mm/damon: remove a mistakenly added comment for a future feature
  Docs/admin-guide/mm/damon/usage: update for kdamond_pid and (mk|rm)_contexts
  Docs/admin-guide/mm/damon/usage: mention tracepoint at the beginning
  Docs/admin-guide/mm/damon/usage: remove redundant information
  Docs/admin-guide/mm/damon/usage: update for scheme quotas and watermarks
  mm/damon: convert macro functions to static inline functions
  mm/damon: modify damon_rand() macro to static inline function
  mm/damon: move damon_rand() definition into damon.h
  ...

tools/testing/selftests/vm/charge_reserved_hugetlb.sh

@@ -24,19 +24,23 @@ if [[ "$1" == "-cgroup-v2" ]]; then
   reservation_usage_file=rsvd.current
 fi
 
-cgroup_path=/dev/cgroup/memory
-if [[ ! -e $cgroup_path ]]; then
-  mkdir -p $cgroup_path
-  if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+  cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+  if [[ -z "$cgroup_path" ]]; then
+    cgroup_path=/dev/cgroup/memory
     mount -t cgroup2 none $cgroup_path
-  else
+    do_umount=1
+  fi
+  echo "+hugetlb" >$cgroup_path/cgroup.subtree_control
+else
+  cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+  if [[ -z "$cgroup_path" ]]; then
+    cgroup_path=/dev/cgroup/memory
     mount -t cgroup memory,hugetlb $cgroup_path
+    do_umount=1
   fi
 fi
-
-if [[ $cgroup2 ]]; then
-  echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control
-fi
+export cgroup_path
 
 function cleanup() {
   if [[ $cgroup2 ]]; then
@@ -108,7 +112,7 @@ function setup_cgroup() {
 
 function wait_for_hugetlb_memory_to_get_depleted() {
   local cgroup="$1"
-  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+  local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
   # Wait for hugetlbfs memory to get depleted.
   while [ $(cat $path) != 0 ]; do
     echo Waiting for hugetlb memory to get depleted.
@@ -121,7 +125,7 @@ function wait_for_hugetlb_memory_to_get_reserved() {
   local cgroup="$1"
   local size="$2"
 
-  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+  local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
   # Wait for hugetlbfs memory to get written.
   while [ $(cat $path) != $size ]; do
     echo Waiting for hugetlb memory reservation to reach size $size.
@@ -134,7 +138,7 @@ function wait_for_hugetlb_memory_to_get_written() {
   local cgroup="$1"
   local size="$2"
 
-  local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
+  local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
   # Wait for hugetlbfs memory to get written.
   while [ $(cat $path) != $size ]; do
     echo Waiting for hugetlb memory to reach size $size.
@@ -574,5 +578,7 @@ for populate in "" "-o"; do
   done     # populate
 done       # method
 
-umount $cgroup_path
-rmdir $cgroup_path
+if [[ $do_umount ]]; then
+  umount $cgroup_path
+  rmdir $cgroup_path
+fi

tools/testing/selftests/vm/hmm-tests.c

@@ -1248,6 +1248,48 @@ TEST_F(hmm, anon_teardown)
 	}
 }
 
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
+TEST_F(hmm, mixedmap)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned char *m;
+	int ret;
+
+	npages = 1;
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(npages);
+	ASSERT_NE(buffer->mirror, NULL);
+
+
+	/* Reserve a range of addresses. */
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE,
+			   self->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Simulate a device snapshotting CPU pagetables. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device saw. */
+	m = buffer->mirror;
+	ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ);
+
+	hmm_buffer_free(buffer);
+}
+
 /*
  * Test memory snapshot without faulting in pages accessed by the device.
  */

tools/testing/selftests/vm/hugepage-mremap.c

@@ -4,7 +4,11 @@
  *
  * 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.
+ * at './huge'.  The amount of memory used by this test is decided by a command
+ * line argument in MBs. If missing, the default amount is 10MB.
+ *
+ * To make sure the test triggers pmd sharing and goes through the 'unshare'
+ * path in the mremap code use 1GB (1024) or more.
  */
 
 #define _GNU_SOURCE
@@ -18,8 +22,10 @@
 #include <linux/userfaultfd.h>
 #include <sys/ioctl.h>
 
-#define LENGTH (1UL * 1024 * 1024 * 1024)
+#define DEFAULT_LENGTH_MB 10UL
+#define MB_TO_BYTES(x) (x * 1024 * 1024)
 
+#define FILE_NAME "huge/hugepagefile"
 #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
 #define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
 
@@ -28,20 +34,20 @@ static void check_bytes(char *addr)
 	printf("First hex is %x\n", *((unsigned int *)addr));
 }
 
-static void write_bytes(char *addr)
+static void write_bytes(char *addr, size_t len)
 {
 	unsigned long i;
 
-	for (i = 0; i < LENGTH; i++)
+	for (i = 0; i < len; i++)
 		*(addr + i) = (char)i;
 }
 
-static int read_bytes(char *addr)
+static int read_bytes(char *addr, size_t len)
 {
 	unsigned long i;
 
 	check_bytes(addr);
-	for (i = 0; i < LENGTH; i++)
+	for (i = 0; i < len; i++)
 		if (*(addr + i) != (char)i) {
 			printf("Mismatch at %lu\n", i);
 			return 1;
@@ -99,11 +105,19 @@ static void register_region_with_uffd(char *addr, size_t len)
 	}
 }
 
-int main(void)
+int main(int argc, char *argv[])
 {
+	/* Read memory length as the first arg if valid, otherwise fallback to
+	 * the default length. Any additional args are ignored.
+	 */
+	size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL;
+
+	length = length > 0 ? length : DEFAULT_LENGTH_MB;
+	length = MB_TO_BYTES(length);
+
 	int ret = 0;
 
-	int fd = open("/huge/test", O_CREAT | O_RDWR, 0755);
+	int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
 
 	if (fd < 0) {
 		perror("Open failed");
@@ -112,7 +126,7 @@ int main(void)
 
 	/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
 	unsigned long suggested_addr = 0x7eaa40000000;
-	void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+	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) {
@@ -122,7 +136,7 @@ int main(void)
 
 	/* mmap again to a dummy address to hopefully trigger pmd sharing. */
 	suggested_addr = 0x7daa40000000;
-	void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+	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) {
@@ -132,16 +146,16 @@ int main(void)
 
 	suggested_addr = 0x7faa40000000;
 	void *vaddr =
-		mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0);
+		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);
+	register_region_with_uffd(haddr, length);
 
-	void *addr = mremap(haddr, LENGTH, LENGTH,
+	void *addr = mremap(haddr, length, length,
 			    MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
 	if (addr == MAP_FAILED) {
 		perror("mremap");
@@ -150,10 +164,10 @@ int main(void)
 
 	printf("Mremap: Returned address is %p\n", addr);
 	check_bytes(addr);
-	write_bytes(addr);
-	ret = read_bytes(addr);
+	write_bytes(addr, length);
+	ret = read_bytes(addr, length);
 
-	munmap(addr, LENGTH);
+	munmap(addr, length);
 
 	return ret;
 }

tools/testing/selftests/vm/hugetlb_reparenting_test.sh

@@ -18,19 +18,24 @@ if [[ "$1" == "-cgroup-v2" ]]; then
   usage_file=current
 fi
 
-CGROUP_ROOT='/dev/cgroup/memory'
-MNT='/mnt/huge/'
 
-if [[ ! -e $CGROUP_ROOT ]]; then
-  mkdir -p $CGROUP_ROOT
-  if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+  CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+  if [[ -z "$CGROUP_ROOT" ]]; then
+    CGROUP_ROOT=/dev/cgroup/memory
     mount -t cgroup2 none $CGROUP_ROOT
-    sleep 1
-    echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
-  else
+    do_umount=1
+  fi
+  echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
+else
+  CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+  if [[ -z "$CGROUP_ROOT" ]]; then
+    CGROUP_ROOT=/dev/cgroup/memory
     mount -t cgroup memory,hugetlb $CGROUP_ROOT
+    do_umount=1
   fi
 fi
+MNT='/mnt/huge/'
 
 function get_machine_hugepage_size() {
   hpz=$(grep -i hugepagesize /proc/meminfo)

tools/testing/selftests/vm/run_vmtests.sh

@@ -111,7 +111,7 @@ fi
 echo "-----------------------"
 echo "running hugepage-mremap"
 echo "-----------------------"
-./hugepage-mremap
+./hugepage-mremap 256
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1

tools/testing/selftests/vm/userfaultfd.c

@@ -87,7 +87,7 @@ static bool test_uffdio_minor = false;
 
 static bool map_shared;
 static int shm_fd;
-static int huge_fd = -1;	/* only used for hugetlb_shared test */
+static int huge_fd;
 static char *huge_fd_off0;
 static unsigned long long *count_verify;
 static int uffd = -1;
@@ -223,9 +223,6 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
 
 static void hugetlb_release_pages(char *rel_area)
 {
-	if (huge_fd == -1)
-		return;
-
 	if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 		      rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
 		      nr_pages * page_size))
@@ -238,17 +235,17 @@ static void hugetlb_allocate_area(void **alloc_area)
 	char **alloc_area_alias;
 
 	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-			   map_shared ? MAP_SHARED :
-			   MAP_PRIVATE | MAP_HUGETLB |
+			   (map_shared ? MAP_SHARED : MAP_PRIVATE) |
+			   MAP_HUGETLB |
 			   (*alloc_area == area_src ? 0 : MAP_NORESERVE),
-			   huge_fd,
-			   *alloc_area == area_src ? 0 : nr_pages * page_size);
+			   huge_fd, *alloc_area == area_src ? 0 :
+			   nr_pages * page_size);
 	if (*alloc_area == MAP_FAILED)
 		err("mmap of hugetlbfs file failed");
 
 	if (map_shared) {
 		area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-				  MAP_SHARED,
+				  MAP_SHARED | MAP_HUGETLB,
 				  huge_fd, *alloc_area == area_src ? 0 :
 				  nr_pages * page_size);
 		if (area_alias == MAP_FAILED)
@@ -648,7 +645,7 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
 
 	if (ret != sizeof(*msg)) {
 		if (ret < 0) {
-			if (errno == EAGAIN)
+			if (errno == EAGAIN || errno == EINTR)
 				return 1;
 			err("blocking read error");
 		} else {
@@ -724,8 +721,11 @@ static void *uffd_poll_thread(void *arg)
 
 	for (;;) {
 		ret = poll(pollfd, 2, -1);
-		if (ret <= 0)
+		if (ret <= 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
 			err("poll error: %d", ret);
+		}
 		if (pollfd[1].revents & POLLIN) {
 			if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
 				err("read pipefd error");
@@ -1417,7 +1417,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize)
 static int userfaultfd_stress(void)
 {
 	void *area;
-	char *tmp_area;
 	unsigned long nr;
 	struct uffdio_register uffdio_register;
 	struct uffd_stats uffd_stats[nr_cpus];
@@ -1528,13 +1527,9 @@ static int userfaultfd_stress(void)
 					    count_verify[nr], nr);
 
 		/* prepare next bounce */
-		tmp_area = area_src;
-		area_src = area_dst;
-		area_dst = tmp_area;
+		swap(area_src, area_dst);
 
-		tmp_area = area_src_alias;
-		area_src_alias = area_dst_alias;
-		area_dst_alias = tmp_area;
+		swap(area_src_alias, area_dst_alias);
 
 		uffd_stats_report(uffd_stats, nr_cpus);
 	}

tools/testing/selftests/vm/write_hugetlb_memory.sh

@@ -14,7 +14,7 @@ want_sleep=$8
 reserve=$9
 
 echo "Putting task in cgroup '$cgroup'"
-echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs
+echo $$ > ${cgroup_path:-/dev/cgroup/memory}/"$cgroup"/cgroup.procs
 
 echo "Method is $method"