Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

76 files changed, 4636 insertions, 3545 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 623d95659ff9..34d36958b8ac 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -801,7 +801,7 @@ endchoice
 
 config THP_SWAP
 	def_bool y
-	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP
+	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
 	help
 	  Swap transparent huge pages in one piece, without splitting.
 	  XXX: For now, swap cluster backing transparent huge page
@@ -1100,7 +1100,13 @@ config IO_MAPPING
 	bool
 
 config SECRETMEM
-	def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+	default y
+	bool "Enable memfd_secret() system call" if EXPERT
+	depends on ARCH_HAS_SET_DIRECT_MAP
+	help
+	  Enable the memfd_secret() system call with the ability to create
+	  memory areas visible only in the context of the owning process and
+	  not mapped to other processes and other kernel page tables.
 
 config ANON_VMA_NAME
 	bool "Anonymous VMA name support"
@@ -1133,17 +1139,10 @@ config HAVE_ARCH_USERFAULTFD_MINOR
 	help
 	  Arch has userfaultfd minor fault support
 
-config PTE_MARKER
-	bool
-
-	help
-	  Allows to create marker PTEs for file-backed memory.
-
 config PTE_MARKER_UFFD_WP
 	bool "Userfaultfd write protection support for shmem/hugetlbfs"
 	default y
 	depends on HAVE_ARCH_USERFAULTFD_WP
-	select PTE_MARKER
 
 	help
 	  Allows to create marker PTEs for userfaultfd write protection
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c30419a5e119..a53b9360b72e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -178,7 +178,26 @@ static ssize_t min_ratio_store(struct device *dev,
 
 	return ret;
 }
-BDI_SHOW(min_ratio, bdi->min_ratio)
+BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE)
+
+static ssize_t min_ratio_fine_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_ratio_no_scale(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(min_ratio_fine, bdi->min_ratio)
 
 static ssize_t max_ratio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
@@ -197,7 +216,82 @@ static ssize_t max_ratio_store(struct device *dev,
 
 	return ret;
 }
-BDI_SHOW(max_ratio, bdi->max_ratio)
+BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE)
+
+static ssize_t max_ratio_fine_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_ratio_no_scale(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(max_ratio_fine, bdi->max_ratio)
+
+static ssize_t min_bytes_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi));
+}
+
+static ssize_t min_bytes_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	u64 bytes;
+	ssize_t ret;
+
+	ret = kstrtoull(buf, 10, &bytes);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_bytes(bdi, bytes);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+DEVICE_ATTR_RW(min_bytes);
+
+static ssize_t max_bytes_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi));
+}
+
+static ssize_t max_bytes_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	u64 bytes;
+	ssize_t ret;
+
+	ret = kstrtoull(buf, 10, &bytes);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_bytes(bdi, bytes);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+DEVICE_ATTR_RW(max_bytes);
 
 static ssize_t stable_pages_required_show(struct device *dev,
 					  struct device_attribute *attr,
@@ -209,11 +303,44 @@ static ssize_t stable_pages_required_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
+static ssize_t strict_limit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int strict_limit;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &strict_limit);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_strict_limit(bdi, strict_limit);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+
+static ssize_t strict_limit_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n",
+			!!(bdi->capabilities & BDI_CAP_STRICTLIMIT));
+}
+static DEVICE_ATTR_RW(strict_limit);
+
 static struct attribute *bdi_dev_attrs[] = {
 	&dev_attr_read_ahead_kb.attr,
 	&dev_attr_min_ratio.attr,
+	&dev_attr_min_ratio_fine.attr,
 	&dev_attr_max_ratio.attr,
+	&dev_attr_max_ratio_fine.attr,
+	&dev_attr_min_bytes.attr,
+	&dev_attr_max_bytes.attr,
 	&dev_attr_stable_pages_required.attr,
+	&dev_attr_strict_limit.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(bdi_dev);
@@ -780,7 +907,7 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	kref_init(&bdi->refcnt);
 	bdi->min_ratio = 0;
-	bdi->max_ratio = 100;
+	bdi->max_ratio = 100 * BDI_RATIO_SCALE;
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
diff --git a/mm/compaction.c b/mm/compaction.c
index 1f6da31dd9a5..ca1603524bbe 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1344,7 +1344,7 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage)
 }
 
 static void
-fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long nr_isolated)
+fast_isolate_around(struct compact_control *cc, unsigned long pfn)
 {
 	unsigned long start_pfn, end_pfn;
 	struct page *page;
@@ -1365,21 +1365,13 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long
 	if (!page)
 		return;
 
-	/* Scan before */
-	if (start_pfn != pfn) {
-		isolate_freepages_block(cc, &start_pfn, pfn, &cc->freepages, 1, false);
-		if (cc->nr_freepages >= cc->nr_migratepages)
-			return;
-	}
-
-	/* Scan after */
-	start_pfn = pfn + nr_isolated;
-	if (start_pfn < end_pfn)
-		isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
+	isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
 
 	/* Skip this pageblock in the future as it's full or nearly full */
 	if (cc->nr_freepages < cc->nr_migratepages)
 		set_pageblock_skip(page);
+
+	return;
 }
 
 /* Search orders in round-robin fashion */
@@ -1556,7 +1548,7 @@ fast_isolate_freepages(struct compact_control *cc)
 		return cc->free_pfn;
 
 	low_pfn = page_to_pfn(page);
-	fast_isolate_around(cc, low_pfn, nr_isolated);
+	fast_isolate_around(cc, low_pfn);
 	return low_pfn;
 }
 
diff --git a/mm/damon/Makefile b/mm/damon/Makefile
index 3e6b8ad73858..f7add3f4aa79 100644
--- a/mm/damon/Makefile
+++ b/mm/damon/Makefile
@@ -3,7 +3,7 @@
 obj-y				:= core.o
 obj-$(CONFIG_DAMON_VADDR)	+= ops-common.o vaddr.o
 obj-$(CONFIG_DAMON_PADDR)	+= ops-common.o paddr.o
-obj-$(CONFIG_DAMON_SYSFS)	+= sysfs.o
+obj-$(CONFIG_DAMON_SYSFS)	+= sysfs-common.o sysfs-schemes.o sysfs.o
 obj-$(CONFIG_DAMON_DBGFS)	+= dbgfs.o
-obj-$(CONFIG_DAMON_RECLAIM)	+= reclaim.o
-obj-$(CONFIG_DAMON_LRU_SORT)	+= lru_sort.o
+obj-$(CONFIG_DAMON_RECLAIM)	+= modules-common.o reclaim.o
+obj-$(CONFIG_DAMON_LRU_SORT)	+= modules-common.o lru_sort.o
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 36d098d06c55..ceec75b88ef9 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -694,6 +694,115 @@ static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t,
 	return c->ops.get_scheme_score(c, t, r, s) >= s->quota.min_score;
 }
 
+/*
+ * damos_skip_charged_region() - Check if the given region or starting part of
+ * it is already charged for the DAMOS quota.
+ * @t:	The target of the region.
+ * @rp:	The pointer to the region.
+ * @s:	The scheme to be applied.
+ *
+ * If a quota of a scheme has exceeded in a quota charge window, the scheme's
+ * action would applied to only a part of the target access pattern fulfilling
+ * regions.  To avoid applying the scheme action to only already applied
+ * regions, DAMON skips applying the scheme action to the regions that charged
+ * in the previous charge window.
+ *
+ * This function checks if a given region should be skipped or not for the
+ * reason.  If only the starting part of the region has previously charged,
+ * this function splits the region into two so that the second one covers the
+ * area that not charged in the previous charge widnow and saves the second
+ * region in *rp and returns false, so that the caller can apply DAMON action
+ * to the second one.
+ *
+ * Return: true if the region should be entirely skipped, false otherwise.
+ */
+static bool damos_skip_charged_region(struct damon_target *t,
+		struct damon_region **rp, struct damos *s)
+{
+	struct damon_region *r = *rp;
+	struct damos_quota *quota = &s->quota;
+	unsigned long sz_to_skip;
+
+	/* Skip previously charged regions */
+	if (quota->charge_target_from) {
+		if (t != quota->charge_target_from)
+			return true;
+		if (r == damon_last_region(t)) {
+			quota->charge_target_from = NULL;
+			quota->charge_addr_from = 0;
+			return true;
+		}
+		if (quota->charge_addr_from &&
+				r->ar.end <= quota->charge_addr_from)
+			return true;
+
+		if (quota->charge_addr_from && r->ar.start <
+				quota->charge_addr_from) {
+			sz_to_skip = ALIGN_DOWN(quota->charge_addr_from -
+					r->ar.start, DAMON_MIN_REGION);
+			if (!sz_to_skip) {
+				if (damon_sz_region(r) <= DAMON_MIN_REGION)
+					return true;
+				sz_to_skip = DAMON_MIN_REGION;
+			}
+			damon_split_region_at(t, r, sz_to_skip);
+			r = damon_next_region(r);
+			*rp = r;
+		}
+		quota->charge_target_from = NULL;
+		quota->charge_addr_from = 0;
+	}
+	return false;
+}
+
+static void damos_update_stat(struct damos *s,
+		unsigned long sz_tried, unsigned long sz_applied)
+{
+	s->stat.nr_tried++;
+	s->stat.sz_tried += sz_tried;
+	if (sz_applied)
+		s->stat.nr_applied++;
+	s->stat.sz_applied += sz_applied;
+}
+
+static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
+		struct damon_region *r, struct damos *s)
+{
+	struct damos_quota *quota = &s->quota;
+	unsigned long sz = damon_sz_region(r);
+	struct timespec64 begin, end;
+	unsigned long sz_applied = 0;
+	int err = 0;
+
+	if (c->ops.apply_scheme) {
+		if (quota->esz && quota->charged_sz + sz > quota->esz) {
+			sz = ALIGN_DOWN(quota->esz - quota->charged_sz,
+					DAMON_MIN_REGION);
+			if (!sz)
+				goto update_stat;
+			damon_split_region_at(t, r, sz);
+		}
+		ktime_get_coarse_ts64(&begin);
+		if (c->callback.before_damos_apply)
+			err = c->callback.before_damos_apply(c, t, r, s);
+		if (!err)
+			sz_applied = c->ops.apply_scheme(c, t, r, s);
+		ktime_get_coarse_ts64(&end);
+		quota->total_charged_ns += timespec64_to_ns(&end) -
+			timespec64_to_ns(&begin);
+		quota->charged_sz += sz;
+		if (quota->esz && quota->charged_sz >= quota->esz) {
+			quota->charge_target_from = t;
+			quota->charge_addr_from = r->ar.end + 1;
+		}
+	}
+	if (s->action != DAMOS_STAT)
+		r->age = 0;
+
+update_stat:
+	damos_update_stat(s, sz, sz_applied);
+}
+
 static void damon_do_apply_schemes(struct damon_ctx *c,
 				   struct damon_target *t,
 				   struct damon_region *r)
@@ -702,9 +811,6 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 
 	damon_for_each_scheme(s, c) {
 		struct damos_quota *quota = &s->quota;
-		unsigned long sz = damon_sz_region(r);
-		struct timespec64 begin, end;
-		unsigned long sz_applied = 0;
 
 		if (!s->wmarks.activated)
 			continue;
@@ -713,70 +819,13 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 		if (quota->esz && quota->charged_sz >= quota->esz)
 			continue;
 
-		/* Skip previously charged regions */
-		if (quota->charge_target_from) {
-			if (t != quota->charge_target_from)
-				continue;
-			if (r == damon_last_region(t)) {
-				quota->charge_target_from = NULL;
-				quota->charge_addr_from = 0;
-				continue;
-			}
-			if (quota->charge_addr_from &&
-					r->ar.end <= quota->charge_addr_from)
-				continue;
-
-			if (quota->charge_addr_from && r->ar.start <
-					quota->charge_addr_from) {
-				sz = ALIGN_DOWN(quota->charge_addr_from -
-						r->ar.start, DAMON_MIN_REGION);
-				if (!sz) {
-					if (damon_sz_region(r) <=
-					    DAMON_MIN_REGION)
-						continue;
-					sz = DAMON_MIN_REGION;
-				}
-				damon_split_region_at(t, r, sz);
-				r = damon_next_region(r);
-				sz = damon_sz_region(r);
-			}
-			quota->charge_target_from = NULL;
-			quota->charge_addr_from = 0;
-		}
+		if (damos_skip_charged_region(t, &r, s))