Merge tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Many singleton patches against the MM code. The patch series which are
  included in this merge do the following:

   - Peng Zhang has done some mapletree maintainance work in the series

	'maple_tree: add mt_free_one() and mt_attr() helpers'
	'Some cleanups of maple tree'

   - In the series 'mm: use memmap_on_memory semantics for dax/kmem'
     Vishal Verma has altered the interworking between memory-hotplug
     and dax/kmem so that newly added 'device memory' can more easily
     have its memmap placed within that newly added memory.

   - Matthew Wilcox continues folio-related work (including a few fixes)
     in the patch series

	'Add folio_zero_tail() and folio_fill_tail()'
	'Make folio_start_writeback return void'
	'Fix fault handler's handling of poisoned tail pages'
	'Convert aops->error_remove_page to ->error_remove_folio'
	'Finish two folio conversions'
	'More swap folio conversions'

   - Kefeng Wang has also contributed folio-related work in the series

	'mm: cleanup and use more folio in page fault'

   - Jim Cromie has improved the kmemleak reporting output in the series
     'tweak kmemleak report format'.

   - In the series 'stackdepot: allow evicting stack traces' Andrey
     Konovalov to permits clients (in this case KASAN) to cause eviction
     of no longer needed stack traces.

   - Charan Teja Kalla has fixed some accounting issues in the page
     allocator's atomic reserve calculations in the series 'mm:
     page_alloc: fixes for high atomic reserve caluculations'.

   - Dmitry Rokosov has added to the samples/ dorectory some sample code
     for a userspace memcg event listener application. See the series
     'samples: introduce cgroup events listeners'.

   - Some mapletree maintanance work from Liam Howlett in the series
     'maple_tree: iterator state changes'.

   - Nhat Pham has improved zswap's approach to writeback in the series
     'workload-specific and memory pressure-driven zswap writeback'.

   - DAMON/DAMOS feature and maintenance work from SeongJae Park in the
     series

	'mm/damon: let users feed and tame/auto-tune DAMOS'
	'selftests/damon: add Python-written DAMON functionality tests'
	'mm/damon: misc updates for 6.8'

   - Yosry Ahmed has improved memcg's stats flushing in the series 'mm:
     memcg: subtree stats flushing and thresholds'.

   - In the series 'Multi-size THP for anonymous memory' Ryan Roberts
     has added a runtime opt-in feature to transparent hugepages which
     improves performance by allocating larger chunks of memory during
     anonymous page faults.

   - Matthew Wilcox has also contributed some cleanup and maintenance
     work against eh buffer_head code int he series 'More buffer_head
     cleanups'.

   - Suren Baghdasaryan has done work on Andrea Arcangeli's series
     'userfaultfd move option'. UFFDIO_MOVE permits userspace heap
     compaction algorithms to move userspace's pages around rather than
     UFFDIO_COPY'a alloc/copy/free.

   - Stefan Roesch has developed a 'KSM Advisor', in the series 'mm/ksm:
     Add ksm advisor'. This is a governor which tunes KSM's scanning
     aggressiveness in response to userspace's current needs.

   - Chengming Zhou has optimized zswap's temporary working memory use
     in the series 'mm/zswap: dstmem reuse optimizations and cleanups'.

   - Matthew Wilcox has performed some maintenance work on the writeback
     code, both code and within filesystems. The series is 'Clean up the
     writeback paths'.

   - Andrey Konovalov has optimized KASAN's handling of alloc and free
     stack traces for secondary-level allocators, in the series 'kasan:
     save mempool stack traces'.

   - Andrey also performed some KASAN maintenance work in the series
     'kasan: assorted clean-ups'.

   - David Hildenbrand has gone to town on the rmap code. Cleanups, more
     pte batching, folio conversions and more. See the series 'mm/rmap:
     interface overhaul'.

   - Kinsey Ho has contributed some maintenance work on the MGLRU code
     in the series 'mm/mglru: Kconfig cleanup'.

   - Matthew Wilcox has contributed lruvec page accounting code cleanups
     in the series 'Remove some lruvec page accounting functions'"

* tag 'mm-stable-2024-01-08-15-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (361 commits)
  mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER
  mm, treewide: introduce NR_PAGE_ORDERS
  selftests/mm: add separate UFFDIO_MOVE test for PMD splitting
  selftests/mm: skip test if application doesn't has root privileges
  selftests/mm: conform test to TAP format output
  selftests: mm: hugepage-mmap: conform to TAP format output
  selftests/mm: gup_test: conform test to TAP format output
  mm/selftests: hugepage-mremap: conform test to TAP format output
  mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING
  mm: zsmalloc: return -ENOSPC rather than -EINVAL in zs_malloc while size is too large
  mm/memcontrol: remove __mod_lruvec_page_state()
  mm/khugepaged: use a folio more in collapse_file()
  slub: use a folio in __kmalloc_large_node
  slub: use folio APIs in free_large_kmalloc()
  slub: use alloc_pages_node() in alloc_slab_page()
  mm: remove inc/dec lruvec page state functions
  mm: ratelimit stat flush from workingset shrinker
  kasan: stop leaking stack trace handles
  mm/mglru: remove CONFIG_TRANSPARENT_HUGEPAGE
  mm/mglru: add dummy pmd_dirty()
  ...

5 files changed, 425 insertions, 0 deletions

diff --git a/samples/Kconfig b/samples/Kconfig
index b0ddf5f36738..b288d9991d27 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -285,6 +285,12 @@ config SAMPLE_KMEMLEAK
           Build a sample program which have explicitly leaks memory to test
           kmemleak
 
+config SAMPLE_CGROUP
+	bool "Build cgroup sample code"
+	depends on CGROUPS && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build samples that demonstrate the usage of the cgroup API.
+
 source "samples/rust/Kconfig"
 
 endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index 0a551c2b33f4..b85fa64390c5 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -3,6 +3,7 @@
 
 subdir-$(CONFIG_SAMPLE_AUXDISPLAY)	+= auxdisplay
 subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs
+subdir-$(CONFIG_SAMPLE_CGROUP) += cgroup
 obj-$(CONFIG_SAMPLE_CONFIGFS)		+= configfs/
 obj-$(CONFIG_SAMPLE_CONNECTOR)		+= connector/
 obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR)	+= fanotify/
diff --git a/samples/cgroup/Makefile b/samples/cgroup/Makefile
new file mode 100644
index 000000000000..526c8569707c
--- /dev/null
+++ b/samples/cgroup/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+userprogs-always-y += cgroup_event_listener memcg_event_listener
+
+userccflags += -I usr/include
diff --git a/samples/cgroup/cgroup_event_listener.c b/samples/cgroup/cgroup_event_listener.c
new file mode 100644
index 000000000000..3d70dc831a76
--- /dev/null
+++ b/samples/cgroup/cgroup_event_listener.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <err.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>"
+
+int main(int argc, char **argv)
+{
+	int efd = -1;
+	int cfd = -1;
+	int event_control = -1;
+	char event_control_path[PATH_MAX];
+	char line[LINE_MAX];
+	int ret;
+
+	if (argc != 3)
+		errx(1, "%s", USAGE_STR);
+
+	cfd = open(argv[1], O_RDONLY);
+	if (cfd == -1)
+		err(1, "Cannot open %s", argv[1]);
+
+	ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+			dirname(argv[1]));
+	if (ret >= PATH_MAX)
+		errx(1, "Path to cgroup.event_control is too long");
+
+	event_control = open(event_control_path, O_WRONLY);
+	if (event_control == -1)
+		err(1, "Cannot open %s", event_control_path);
+
+	efd = eventfd(0, 0);
+	if (efd == -1)
+		err(1, "eventfd() failed");
+
+	ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+	if (ret >= LINE_MAX)
+		errx(1, "Arguments string is too long");
+
+	ret = write(event_control, line, strlen(line) + 1);
+	if (ret == -1)
+		err(1, "Cannot write to cgroup.event_control");
+
+	while (1) {
+		uint64_t result;
+
+		ret = read(efd, &result, sizeof(result));
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+			err(1, "Cannot read from eventfd");
+		}
+		assert(ret == sizeof(result));
+
+		ret = access(event_control_path, W_OK);
+		if ((ret == -1) && (errno == ENOENT)) {
+			puts("The cgroup seems to have removed.");
+			break;
+		}
+
+		if (ret == -1)
+			err(1, "cgroup.event_control is not accessible any more");
+
+		printf("%s %s: crossed\n", argv[1], argv[2]);
+	}
+
+	return 0;
+}
diff --git a/samples/cgroup/memcg_event_listener.c b/samples/cgroup/memcg_event_listener.c
new file mode 100644
index 000000000000..a1667fe2489a
--- /dev/null
+++ b/samples/cgroup/memcg_event_listener.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * memcg_event_listener.c - Simple listener of memcg memory.events
+ *
+ * Copyright (c) 2023, SaluteDevices. All Rights Reserved.
+ *
+ * Author: Dmitry Rokosov <ddrokosov@salutedevices.com>
+ */
+
+#include <err.h>
+#include <errno.h>
+#include <limits.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/inotify.h>
+#include <unistd.h>
+
+#define MEMCG_EVENTS "memory.events"
+
+/* Size of buffer to use when reading inotify events */
+#define INOTIFY_BUFFER_SIZE 8192
+
+#define INOTIFY_EVENT_NEXT(event, length) ({         \
+	(length) -= sizeof(*(event)) + (event)->len; \
+	(event)++;                                   \
+})
+
+#define INOTIFY_EVENT_OK(event, length) ((length) >= (ssize_t)sizeof(*(event)))
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+
+struct memcg_counters {
+	long low;
+	long high;
+	long max;
+	long oom;
+	long oom_kill;
+	long oom_group_kill;
+};
+
+struct memcg_events {
+	struct memcg_counters counters;
+	char path[PATH_MAX];
+	int inotify_fd;
+	int inotify_wd;
+};
+
+static void print_memcg_counters(const struct memcg_counters *counters)
+{
+	printf("MEMCG events:\n");
+	printf("\tlow: %ld\n", counters->low);
+	printf("\thigh: %ld\n", counters->high);
+	printf("\tmax: %ld\n", counters->max);
+	printf("\toom: %ld\n", counters->oom);
+	printf("\toom_kill: %ld\n", counters->oom_kill);
+	printf("\toom_group_kill: %ld\n", counters->oom_group_kill);
+}
+
+static int get_memcg_counter(char *line, const char *name, long *counter)
+{
+	size_t len = strlen(name);
+	char *endptr;
+	long tmp;
+
+	if (memcmp(line, name, len)) {
+		warnx("Counter line %s has wrong name, %s is expected",
+		      line, name);
+		return -EINVAL;
+	}
+
+	/* skip the whitespace delimiter */
+	len += 1;
+
+	errno = 0;
+	tmp = strtol(&line[len], &endptr, 10);
+	if (((tmp == LONG_MAX || tmp == LONG_MIN) && errno == ERANGE) ||
+	    (errno && !tmp)) {
+		warnx("Failed to parse: %s", &line[len]);
+		return -ERANGE;
+	}
+
+	if (endptr == &line[len]) {
+		warnx("Not digits were found in line %s", &line[len]);
+		return -EINVAL;
+	}
+
+	if (!(*endptr == '\0' || (*endptr == '\n' && *++endptr == '\0'))) {
+		warnx("Further characters after number: %s", endptr);
+		return -EINVAL;
+	}
+
+	*counter = tmp;
+
+	return 0;
+}
+
+static int read_memcg_events(struct memcg_events *events, bool show_diff)
+{
+	FILE *fp = fopen(events->path, "re");
+	size_t i;
+	int ret = 0;
+	bool any_new_events = false;
+	char *line = NULL;
+	size_t len = 0;
+	struct memcg_counters new_counters;
+	struct memcg_counters *counters = &events->counters;
+	struct {
+		const char *name;
+		long *new;
+		long *old;
+	} map[] = {
+		{
+			.name = "low",
+			.new = &new_counters.low,
+			.old = &counters->low,
+		},
+		{
+			.name = "high",
+			.new = &new_counters.high,
+			.old = &counters->high,
+		},
+		{
+			.name = "max",
+			.new = &new_counters.max,
+			.old = &counters->max,
+		},
+		{
+			.name = "oom",
+			.new = &new_counters.oom,
+			.old = &counters->oom,
+		},
+		{
+			.name = "oom_kill",
+			.new = &new_counters.oom_kill,
+			.old = &counters->oom_kill,
+		},
+		{
+			.name = "oom_group_kill",
+			.new = &new_counters.oom_group_kill,
+			.old = &counters->oom_group_kill,
+		},
+	};
+
+	if (!fp) {
+		warn("Failed to open memcg events file %s", events->path);
+		return -EBADF;
+	}
+
+	/* Read new values for memcg counters */
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		ssize_t nread;
+
+		errno = 0;
+		nread = getline(&line, &len, fp);
+		if (nread == -1) {
+			if (errno) {
+				warn("Failed to read line for counter %s",
+				     map[i].name);
+				ret = -EIO;
+				goto exit;
+			}
+
+			break;
+		}
+
+		ret = get_memcg_counter(line, map[i].name, map[i].new);
+		if (ret) {
+			warnx("Failed to get counter value from line %s", line);
+			goto exit;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(map); ++i) {
+		long diff;
+
+		if (*map[i].new > *map[i].old) {
+			diff = *map[i].new - *map[i].old;
+
+			if (show_diff)
+				printf("*** %ld MEMCG %s event%s, "
+				       "change counter %ld => %ld\n",
+				       diff, map[i].name,
+				       (diff == 1) ? "" : "s",
+				       *map[i].old, *map[i].new);
+
+			*map[i].old += diff;
+			any_new_events = true;
+		}
+	}
+
+	if (show_diff && !any_new_events)
+		printf("*** No new untracked memcg events available\n");
+
+exit:
+	free(line);
+	fclose(fp);
+
+	return ret;
+}
+
+static void process_memcg_events(struct memcg_events *events,
+				 struct inotify_event *event)
+{
+	int ret;
+
+	if (events->inotify_wd != event->wd) {
+		warnx("Unknown inotify event %d, should be %d", event->wd,
+		      events->inotify_wd);
+		return;
+	}
+
+	printf("Received event in %s:\n", events->path);
+
+	if (!(event->mask & IN_MODIFY)) {
+		warnx("No IN_MODIFY event, skip it");
+		return;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */true);
+	if (ret)
+		warnx("Can't read memcg events");
+}
+
+static void monitor_events(struct memcg_events *events)
+{
+	struct pollfd fds[1];
+	int ret;
+
+	printf("Started monitoring memory events from '%s'...\n", events->path);
+
+	fds[0].fd = events->inotify_fd;
+	fds[0].events = POLLIN;
+
+	for (;;) {
+		ret = poll(fds, ARRAY_SIZE(fds), -1);
+		if (ret < 0 && errno != EAGAIN)
+			err(EXIT_FAILURE, "Can't poll memcg events (%d)", ret);
+
+		if (fds[0].revents & POLLERR)
+			err(EXIT_FAILURE, "Got POLLERR during monitor events");
+
+		if (fds[0].revents & POLLIN) {
+			struct inotify_event *event;
+			char buffer[INOTIFY_BUFFER_SIZE];
+			ssize_t length;
+
+			length = read(fds[0].fd, buffer, INOTIFY_BUFFER_SIZE);
+			if (length <= 0)
+				continue;
+
+			event = (struct inotify_event *)buffer;
+			while (INOTIFY_EVENT_OK(event, length)) {
+				process_memcg_events(events, event);
+				event = INOTIFY_EVENT_NEXT(event, length);
+			}
+		}
+	}
+}
+
+static int initialize_memcg_events(struct memcg_events *events,
+				   const char *cgroup)
+{
+	int ret;
+
+	memset(events, 0, sizeof(struct memcg_events));
+
+	ret = snprintf(events->path, PATH_MAX,
+		       "/sys/fs/cgroup/%s/memory.events", cgroup);
+	if (ret >= PATH_MAX) {
+		warnx("Path to cgroup memory.events is too long");
+		return -EMSGSIZE;
+	} else if (ret < 0) {
+		warn("Can't generate cgroup event full name");
+		return ret;
+	}
+
+	ret = read_memcg_events(events, /* show_diff = */false);
+	if (ret) {
+		warnx("Failed to read initial memcg events state (%d)", ret);
+		return ret;
+	}
+
+	events->inotify_fd = inotify_init();
+	if (events->inotify_fd < 0) {
+		warn("Failed to setup new inotify device");
+		return -EMFILE;
+	}
+
+	events->inotify_wd = inotify_add_watch(events->inotify_fd,
+					       events->path, IN_MODIFY);
+	if (events->inotify_wd < 0) {
+		warn("Couldn't add monitor in dir %s", events->path);
+		return -EIO;
+	}
+
+	printf("Initialized MEMCG events with counters:\n");
+	print_memcg_counters(&events->counters);
+
+	return 0;
+}
+
+static void cleanup_memcg_events(struct memcg_events *events)
+{
+	inotify_rm_watch(events->inotify_fd, events->inotify_wd);
+	close(events->inotify_fd);
+}
+
+int main(int argc, const char **argv)
+{
+	struct memcg_events events;
+	ssize_t ret;
+
+	if (argc != 2)
+		errx(EXIT_FAILURE, "Usage: %s <cgroup>", argv[0]);
+
+	ret = initialize_memcg_events(&events, argv[1]);
+	if (ret)
+		errx(EXIT_FAILURE, "Can't initialize memcg events (%zd)", ret);
+
+	monitor_events(&events);
+
+	cleanup_memcg_events(&events);
+
+	printf("Exiting memcg event listener...\n");
+
+	return EXIT_SUCCESS;
+}