Merge tag 'mm-stable-2025-01-26-14-59' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "The various patchsets are summarized below. Plus of course many
  indivudual patches which are described in their changelogs.

   - "Allocate and free frozen pages" from Matthew Wilcox reorganizes
     the page allocator so we end up with the ability to allocate and
     free zero-refcount pages. So that callers (ie, slab) can avoid a
     refcount inc & dec

   - "Support large folios for tmpfs" from Baolin Wang teaches tmpfs to
     use large folios other than PMD-sized ones

   - "Fix mm/rodata_test" from Petr Tesarik performs some maintenance
     and fixes for this small built-in kernel selftest

   - "mas_anode_descend() related cleanup" from Wei Yang tidies up part
     of the mapletree code

   - "mm: fix format issues and param types" from Keren Sun implements a
     few minor code cleanups

   - "simplify split calculation" from Wei Yang provides a few fixes and
     a test for the mapletree code

   - "mm/vma: make more mmap logic userland testable" from Lorenzo
     Stoakes continues the work of moving vma-related code into the
     (relatively) new mm/vma.c

   - "mm/page_alloc: gfp flags cleanups for alloc_contig_*()" from David
     Hildenbrand cleans up and rationalizes handling of gfp flags in the
     page allocator

   - "readahead: Reintroduce fix for improper RA window sizing" from Jan
     Kara is a second attempt at fixing a readahead window sizing issue.
     It should reduce the amount of unnecessary reading

   - "synchronously scan and reclaim empty user PTE pages" from Qi Zheng
     addresses an issue where "huge" amounts of pte pagetables are
     accumulated:

       https://lore.kernel.org/lkml/cover.1718267194.git.zhengqi.arch@bytedance.com/

     Qi's series addresses this windup by synchronously freeing PTE
     memory within the context of madvise(MADV_DONTNEED)

   - "selftest/mm: Remove warnings found by adding compiler flags" from
     Muhammad Usama Anjum fixes some build warnings in the selftests
     code when optional compiler warnings are enabled

   - "mm: don't use __GFP_HARDWALL when migrating remote pages" from
     David Hildenbrand tightens the allocator's observance of
     __GFP_HARDWALL

   - "pkeys kselftests improvements" from Kevin Brodsky implements
     various fixes and cleanups in the MM selftests code, mainly
     pertaining to the pkeys tests

   - "mm/damon: add sample modules" from SeongJae Park enhances DAMON to
     estimate application working set size

   - "memcg/hugetlb: Rework memcg hugetlb charging" from Joshua Hahn
     provides some cleanups to memcg's hugetlb charging logic

   - "mm/swap_cgroup: remove global swap cgroup lock" from Kairui Song
     removes the global swap cgroup lock. A speedup of 10% for a
     tmpfs-based kernel build was demonstrated

   - "zram: split page type read/write handling" from Sergey Senozhatsky
     has several fixes and cleaups for zram in the area of
     zram_write_page(). A watchdog softlockup warning was eliminated

   - "move pagetable_*_dtor() to __tlb_remove_table()" from Kevin
     Brodsky cleans up the pagetable destructor implementations. A rare
     use-after-free race is fixed

   - "mm/debug: introduce and use VM_WARN_ON_VMG()" from Lorenzo Stoakes
     simplifies and cleans up the debugging code in the VMA merging
     logic

   - "Account page tables at all levels" from Kevin Brodsky cleans up
     and regularizes the pagetable ctor/dtor handling. This results in
     improvements in accounting accuracy

   - "mm/damon: replace most damon_callback usages in sysfs with new
     core functions" from SeongJae Park cleans up and generalizes
     DAMON's sysfs file interface logic

   - "mm/damon: enable page level properties based monitoring" from
     SeongJae Park increases the amount of information which is
     presented in response to DAMOS actions

   - "mm/damon: remove DAMON debugfs interface" from SeongJae Park
     removes DAMON's long-deprecated debugfs interfaces. Thus the
     migration to sysfs is completed

   - "mm/hugetlb: Refactor hugetlb allocation resv accounting" from
     Peter Xu cleans up and generalizes the hugetlb reservation
     accounting

   - "mm: alloc_pages_bulk: small API refactor" from Luiz Capitulino
     removes a never-used feature of the alloc_pages_bulk() interface

   - "mm/damon: extend DAMOS filters for inclusion" from SeongJae Park
     extends DAMOS filters to support not only exclusion (rejecting),
     but also inclusion (allowing) behavior

   - "Add zpdesc memory descriptor for zswap.zpool" from Alex Shi
     introduces a new memory descriptor for zswap.zpool that currently
     overlaps with struct page for now. This is part of the effort to
     reduce the size of struct page and to enable dynamic allocation of
     memory descriptors

   - "mm, swap: rework of swap allocator locks" from Kairui Song redoes
     and simplifies the swap allocator locking. A speedup of 400% was
     demonstrated for one workload. As was a 35% reduction for kernel
     build time with swap-on-zram

   - "mm: update mips to use do_mmap(), make mmap_region() internal"
     from Lorenzo Stoakes reworks MIPS's use of mmap_region() so that
     mmap_region() can be made MM-internal

   - "mm/mglru: performance optimizations" from Yu Zhao fixes a few
     MGLRU regressions and otherwise improves MGLRU performance

   - "Docs/mm/damon: add tuning guide and misc updates" from SeongJae
     Park updates DAMON documentation

   - "Cleanup for memfd_create()" from Isaac Manjarres does that thing

   - "mm: hugetlb+THP folio and migration cleanups" from David
     Hildenbrand provides various cleanups in the areas of hugetlb
     folios, THP folios and migration

   - "Uncached buffered IO" from Jens Axboe implements the new
     RWF_DONTCACHE flag which provides synchronous dropbehind for
     pagecache reading and writing. To permite userspace to address
     issues with massive buildup of useless pagecache when
     reading/writing fast devices

   - "selftests/mm: virtual_address_range: Reduce memory" from Thomas
     Weißschuh fixes and optimizes some of the MM selftests"

* tag 'mm-stable-2025-01-26-14-59' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  mm/compaction: fix UBSAN shift-out-of-bounds warning
  s390/mm: add missing ctor/dtor on page table upgrade
  kasan: sw_tags: use str_on_off() helper in kasan_init_sw_tags()
  tools: add VM_WARN_ON_VMG definition
  mm/damon/core: use str_high_low() helper in damos_wmark_wait_us()
  seqlock: add missing parameter documentation for raw_seqcount_try_begin()
  mm/page-writeback: consolidate wb_thresh bumping logic into __wb_calc_thresh
  mm/page_alloc: remove the incorrect and misleading comment
  zram: remove zcomp_stream_put() from write_incompressible_page()
  mm: separate move/undo parts from migrate_pages_batch()
  mm/kfence: use str_write_read() helper in get_access_type()
  selftests/mm/mkdirty: fix memory leak in test_uffdio_copy()
  kasan: hw_tags: Use str_on_off() helper in kasan_init_hw_tags()
  selftests/mm: virtual_address_range: avoid reading from VM_IO mappings
  selftests/mm: vm_util: split up /proc/self/smaps parsing
  selftests/mm: virtual_address_range: unmap chunks after validation
  selftests/mm: virtual_address_range: mmap() without PROT_WRITE
  selftests/memfd/memfd_test: fix possible NULL pointer dereference
  mm: add FGP_DONTCACHE folio creation flag
  mm: call filemap_fdatawrite_range_kick() after IOCB_DONTCACHE issue
  ...

6 files changed, 290 insertions, 0 deletions

diff --git a/samples/Kconfig b/samples/Kconfig
index 84a9d4e8d947..820e00b2ed68 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -302,6 +302,8 @@ config SAMPLE_CHECK_EXEC
 
 source "samples/rust/Kconfig"
 
+source "samples/damon/Kconfig"
+
 endif # SAMPLES
 
 config HAVE_SAMPLE_FTRACE_DIRECT
diff --git a/samples/Makefile b/samples/Makefile
index f988202f3a30..f24cd0d72dd0 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -40,3 +40,5 @@ obj-$(CONFIG_SAMPLE_KMEMLEAK)		+= kmemleak/
 obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG)	+= coresight/
 obj-$(CONFIG_SAMPLE_FPROBE)		+= fprobe/
 obj-$(CONFIG_SAMPLES_RUST)		+= rust/
+obj-$(CONFIG_SAMPLE_DAMON_WSSE)		+= damon/
+obj-$(CONFIG_SAMPLE_DAMON_PRCL)		+= damon/
diff --git a/samples/damon/Kconfig b/samples/damon/Kconfig
new file mode 100644
index 000000000000..63f6dcd71daa
--- /dev/null
+++ b/samples/damon/Kconfig
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menu "DAMON Samples"
+
+config SAMPLE_DAMON_WSSE
+	bool "DAMON sameple module for working set size estimation"
+	depends on DAMON && DAMON_VADDR
+	help
+	  This builds DAMON sample module for working set size estimation.
+
+	  The module receives a pid, monitor access to the virtual address
+	  space of the process, estimate working set size of the process, and
+	  repeatedly prints the size on the kernel log.
+
+	  If unsure, say N.
+
+config SAMPLE_DAMON_PRCL
+	bool "DAMON sameple module for access-aware proactive reclamation"
+	depends on DAMON && DAMON_VADDR
+	help
+	  This builds DAMON sample module for access-aware proactive
+	  reclamation.
+
+	  The module receives a pid, monitor access to the virtual address
+	  space of the process, find memory regions that not accessed, and
+	  proactively reclaim the regions.
+
+	  If unsure, say N.
+
+endmenu
diff --git a/samples/damon/Makefile b/samples/damon/Makefile
new file mode 100644
index 000000000000..7f155143f237
--- /dev/null
+++ b/samples/damon/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_SAMPLE_DAMON_WSSE) += wsse.o
+obj-$(CONFIG_SAMPLE_DAMON_PRCL) += prcl.o
diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c
new file mode 100644
index 000000000000..c3acbdab7a62
--- /dev/null
+++ b/samples/damon/prcl.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proactive reclamation: monitor access pattern of a given process, find
+ * regiosn that seems not accessed, and proactively page out the regions.
+ */
+
+#define pr_fmt(fmt) "damon_sample_prcl: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static int target_pid __read_mostly;
+module_param(target_pid, int, 0600);
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops enable_param_ops = {
+	.set = damon_sample_prcl_enable_store,
+	.get = param_get_bool,
+};
+
+static bool enable __read_mostly;
+module_param_cb(enable, &enable_param_ops, &enable, 0600);
+MODULE_PARM_DESC(enable, "Enable of disable DAMON_SAMPLE_WSSE");
+
+static struct damon_ctx *ctx;
+static struct pid *target_pidp;
+
+static int damon_sample_prcl_after_aggregate(struct damon_ctx *c)
+{
+	struct damon_target *t;
+
+	damon_for_each_target(t, c) {
+		struct damon_region *r;
+		unsigned long wss = 0;
+
+		damon_for_each_region(r, t) {
+			if (r->nr_accesses > 0)
+				wss += r->ar.end - r->ar.start;
+		}
+		pr_info("wss: %lu\n", wss);
+	}
+	return 0;
+}
+
+static int damon_sample_prcl_start(void)
+{
+	struct damon_target *target;
+	struct damos *scheme;
+
+	pr_info("start\n");
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+	if (damon_select_ops(ctx, DAMON_OPS_VADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+	target_pidp = find_get_pid(target_pid);
+	if (!target_pidp) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+	target->pid = target_pidp;
+
+	ctx->callback.after_aggregation = damon_sample_prcl_after_aggregate;
+
+	scheme = damon_new_scheme(
+			&(struct damos_access_pattern) {
+			.min_sz_region = PAGE_SIZE,
+			.max_sz_region = ULONG_MAX,
+			.min_nr_accesses = 0,
+			.max_nr_accesses = 0,
+			.min_age_region = 50,
+			.max_age_region = UINT_MAX},
+			DAMOS_PAGEOUT,
+			0,
+			&(struct damos_quota){},
+			&(struct damos_watermarks){},
+			NUMA_NO_NODE);
+	if (!scheme) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_set_schemes(ctx, &scheme, 1);
+
+	return damon_start(&ctx, 1, true);
+}
+
+static void damon_sample_prcl_stop(void)
+{
+	pr_info("stop\n");
+	if (ctx) {
+		damon_stop(&ctx, 1);
+		damon_destroy_ctx(ctx);
+	}
+	if (target_pidp)
+		put_pid(target_pidp);
+}
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp)
+{
+	bool enabled = enable;
+	int err;
+
+	err = kstrtobool(val, &enable);
+	if (err)
+		return err;
+
+	if (enable == enabled)
+		return 0;
+
+	if (enable)
+		return damon_sample_prcl_start();
+	damon_sample_prcl_stop();
+	return 0;
+}
+
+static int __init damon_sample_prcl_init(void)
+{
+	return 0;
+}
+
+module_init(damon_sample_prcl_init);
diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c
new file mode 100644
index 000000000000..11be25803274
--- /dev/null
+++ b/samples/damon/wsse.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * working set size estimation: monitor access pattern of given process and
+ * print estimated working set size (total size of regions that showing some
+ * access).
+ */
+
+#define pr_fmt(fmt) "damon_sample_wsse: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static int target_pid __read_mostly;
+module_param(target_pid, int, 0600);
+
+static int damon_sample_wsse_enable_store(
+		const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops enable_param_ops = {
+	.set = damon_sample_wsse_enable_store,
+	.get = param_get_bool,
+};
+
+static bool enable __read_mostly;
+module_param_cb(enable, &enable_param_ops, &enable, 0600);
+MODULE_PARM_DESC(enable, "Enable or disable DAMON_SAMPLE_WSSE");
+
+static struct damon_ctx *ctx;
+static struct pid *target_pidp;
+
+static int damon_sample_wsse_after_aggregate(struct damon_ctx *c)
+{
+	struct damon_target *t;
+
+	damon_for_each_target(t, c) {
+		struct damon_region *r;
+		unsigned long wss = 0;
+
+		damon_for_each_region(r, t) {
+			if (r->nr_accesses > 0)
+				wss += r->ar.end - r->ar.start;
+		}
+		pr_info("wss: %lu\n", wss);
+	}
+	return 0;
+}
+
+static int damon_sample_wsse_start(void)
+{
+	struct damon_target *target;
+
+	pr_info("start\n");
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+	if (damon_select_ops(ctx, DAMON_OPS_VADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+	target_pidp = find_get_pid(target_pid);
+	if (!target_pidp) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+	target->pid = target_pidp;
+
+	ctx->callback.after_aggregation = damon_sample_wsse_after_aggregate;
+	return damon_start(&ctx, 1, true);
+}
+
+static void damon_sample_wsse_stop(void)
+{
+	pr_info("stop\n");
+	if (ctx) {
+		damon_stop(&ctx, 1);
+		damon_destroy_ctx(ctx);
+	}
+	if (target_pidp)
+		put_pid(target_pidp);
+}
+
+static int damon_sample_wsse_enable_store(
+		const char *val, const struct kernel_param *kp)
+{
+	bool enabled = enable;
+	int err;
+
+	err = kstrtobool(val, &enable);
+	if (err)
+		return err;
+
+	if (enable == enabled)
+		return 0;
+
+	if (enable)
+		return damon_sample_wsse_start();
+	damon_sample_wsse_stop();
+	return 0;
+}
+
+static int __init damon_sample_wsse_init(void)
+{
+	return 0;
+}
+
+module_init(damon_sample_wsse_init);