Merge tag 'mm-stable-2025-10-01-19-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - "mm, swap: improve cluster scan strategy" from Kairui Song improves
   performance and reduces the failure rate of swap cluster allocation

 - "support large align and nid in Rust allocators" from Vitaly Wool
   permits Rust allocators to set NUMA node and large alignment when
   perforning slub and vmalloc reallocs

 - "mm/damon/vaddr: support stat-purpose DAMOS" from Yueyang Pan extend
   DAMOS_STAT's handling of the DAMON operations sets for virtual
   address spaces for ops-level DAMOS filters

 - "execute PROCMAP_QUERY ioctl under per-vma lock" from Suren
   Baghdasaryan reduces mmap_lock contention during reads of
   /proc/pid/maps

 - "mm/mincore: minor clean up for swap cache checking" from Kairui Song
   performs some cleanup in the swap code

 - "mm: vm_normal_page*() improvements" from David Hildenbrand provides
   code cleanup in the pagemap code

 - "add persistent huge zero folio support" from Pankaj Raghav provides
   a block layer speedup by optionalls making the
   huge_zero_pagepersistent, instead of releasing it when its refcount
   falls to zero

 - "kho: fixes and cleanups" from Mike Rapoport adds a few touchups to
   the recently added Kexec Handover feature

 - "mm: make mm->flags a bitmap and 64-bit on all arches" from Lorenzo
   Stoakes turns mm_struct.flags into a bitmap. To end the constant
   struggle with space shortage on 32-bit conflicting with 64-bit's
   needs

 - "mm/swapfile.c and swap.h cleanup" from Chris Li cleans up some swap
   code

 - "selftests/mm: Fix false positives and skip unsupported tests" from
   Donet Tom fixes a few things in our selftests code

 - "prctl: extend PR_SET_THP_DISABLE to only provide THPs when advised"
   from David Hildenbrand "allows individual processes to opt-out of
   THP=always into THP=madvise, without affecting other workloads on the
   system".

   It's a long story - the [1/N] changelog spells out the considerations

 - "Add and use memdesc_flags_t" from Matthew Wilcox gets us started on
   the memdesc project. Please see

      https://kernelnewbies.org/MatthewWilcox/Memdescs and
      https://blogs.oracle.com/linux/post/introducing-memdesc

 - "Tiny optimization for large read operations" from Chi Zhiling
   improves the efficiency of the pagecache read path

 - "Better split_huge_page_test result check" from Zi Yan improves our
   folio splitting selftest code

 - "test that rmap behaves as expected" from Wei Yang adds some rmap
   selftests

 - "remove write_cache_pages()" from Christoph Hellwig removes that
   function and converts its two remaining callers

 - "selftests/mm: uffd-stress fixes" from Dev Jain fixes some UFFD
   selftests issues

 - "introduce kernel file mapped folios" from Boris Burkov introduces
   the concept of "kernel file pages". Using these permits btrfs to
   account its metadata pages to the root cgroup, rather than to the
   cgroups of random inappropriate tasks

 - "mm/pageblock: improve readability of some pageblock handling" from
   Wei Yang provides some readability improvements to the page allocator
   code

 - "mm/damon: support ARM32 with LPAE" from SeongJae Park teaches DAMON
   to understand arm32 highmem

 - "tools: testing: Use existing atomic.h for vma/maple tests" from
   Brendan Jackman performs some code cleanups and deduplication under
   tools/testing/

 - "maple_tree: Fix testing for 32bit compiles" from Liam Howlett fixes
   a couple of 32-bit issues in tools/testing/radix-tree.c

 - "kasan: unify kasan_enabled() and remove arch-specific
   implementations" from Sabyrzhan Tasbolatov moves KASAN arch-specific
   initialization code into a common arch-neutral implementation

 - "mm: remove zpool" from Johannes Weiner removes zspool - an
   indirection layer which now only redirects to a single thing
   (zsmalloc)

 - "mm: task_stack: Stack handling cleanups" from Pasha Tatashin makes a
   couple of cleanups in the fork code

 - "mm: remove nth_page()" from David Hildenbrand makes rather a lot of
   adjustments at various nth_page() callsites, eventually permitting
   the removal of that undesirable helper function

 - "introduce kasan.write_only option in hw-tags" from Yeoreum Yun
   creates a KASAN read-only mode for ARM, using that architecture's
   memory tagging feature. It is felt that a read-only mode KASAN is
   suitable for use in production systems rather than debug-only

 - "mm: hugetlb: cleanup hugetlb folio allocation" from Kefeng Wang does
   some tidying in the hugetlb folio allocation code

 - "mm: establish const-correctness for pointer parameters" from Max
   Kellermann makes quite a number of the MM API functions more accurate
   about the constness of their arguments. This was getting in the way
   of subsystems (in this case CEPH) when they attempt to improving
   their own const/non-const accuracy

 - "Cleanup free_pages() misuse" from Vishal Moola fixes a number of
   code sites which were confused over when to use free_pages() vs
   __free_pages()

 - "Add Rust abstraction for Maple Trees" from Alice Ryhl makes the
   mapletree code accessible to Rust. Required by nouveau and by its
   forthcoming successor: the new Rust Nova driver

 - "selftests/mm: split_huge_page_test: split_pte_mapped_thp
   improvements" from David Hildenbrand adds a fix and some cleanups to
   the thp selftesting code

 - "mm, swap: introduce swap table as swap cache (phase I)" from Chris
   Li and Kairui Song is the first step along the path to implementing
   "swap tables" - a new approach to swap allocation and state tracking
   which is expected to yield speed and space improvements. This
   patchset itself yields a 5-20% performance benefit in some situations

 - "Some ptdesc cleanups" from Matthew Wilcox utilizes the new memdesc
   layer to clean up the ptdesc code a little

 - "Fix va_high_addr_switch.sh test failure" from Chunyu Hu fixes some
   issues in our 5-level pagetable selftesting code

 - "Minor fixes for memory allocation profiling" from Suren Baghdasaryan
   addresses a couple of minor issues in relatively new memory
   allocation profiling feature

 - "Small cleanups" from Matthew Wilcox has a few cleanups in
   preparation for more memdesc work

 - "mm/damon: add addr_unit for DAMON_LRU_SORT and DAMON_RECLAIM" from
   Quanmin Yan makes some changes to DAMON in furtherance of supporting
   arm highmem

 - "selftests/mm: Add -Wunreachable-code and fix warnings" from Muhammad
   Anjum adds that compiler check to selftests code and fixes the
   fallout, by removing dead code

 - "Improvements to Victim Process Thawing and OOM Reaper Traversal
   Order" from zhongjinji makes a number of improvements in the OOM
   killer: mainly thawing a more appropriate group of victim threads so
   they can release resources

 - "mm/damon: misc fixups and improvements for 6.18" from SeongJae Park
   is a bunch of small and unrelated fixups for DAMON

 - "mm/damon: define and use DAMON initialization check function" from
   SeongJae Park implement reliability and maintainability improvements
   to a recently-added bug fix

 - "mm/damon/stat: expose auto-tuned intervals and non-idle ages" from
   SeongJae Park provides additional transparency to userspace clients
   of the DAMON_STAT information

 - "Expand scope of khugepaged anonymous collapse" from Dev Jain removes
   some constraints on khubepaged's collapsing of anon VMAs. It also
   increases the success rate of MADV_COLLAPSE against an anon vma

 - "mm: do not assume file == vma->vm_file in compat_vma_mmap_prepare()"
   from Lorenzo Stoakes moves us further towards removal of
   file_operations.mmap(). This patchset concentrates upon clearing up
   the treatment of stacked filesystems

 - "mm: Improve mlock tracking for large folios" from Kiryl Shutsemau
   provides some fixes and improvements to mlock's tracking of large
   folios. /proc/meminfo's "Mlocked" field became more accurate

 - "mm/ksm: Fix incorrect accounting of KSM counters during fork" from
   Donet Tom fixes several user-visible KSM stats inaccuracies across
   forks and adds selftest code to verify these counters

 - "mm_slot: fix the usage of mm_slot_entry" from Wei Yang addresses
   some potential but presently benign issues in KSM's mm_slot handling

* tag 'mm-stable-2025-10-01-19-00' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (372 commits)
  mm: swap: check for stable address space before operating on the VMA
  mm: convert folio_page() back to a macro
  mm/khugepaged: use start_addr/addr for improved readability
  hugetlbfs: skip VMAs without shareable locks in hugetlb_vmdelete_list
  alloc_tag: fix boot failure due to NULL pointer dereference
  mm: silence data-race in update_hiwater_rss
  mm/memory-failure: don't select MEMORY_ISOLATION
  mm/khugepaged: remove definition of struct khugepaged_mm_slot
  mm/ksm: get mm_slot by mm_slot_entry() when slot is !NULL
  hugetlb: increase number of reserving hugepages via cmdline
  selftests/mm: add fork inheritance test for ksm_merging_pages counter
  mm/ksm: fix incorrect KSM counter handling in mm_struct during fork
  drivers/base/node: fix double free in register_one_node()
  mm: remove PMD alignment constraint in execmem_vmalloc()
  mm/memory_hotplug: fix typo 'esecially' -> 'especially'
  mm/rmap: improve mlock tracking for large folios
  mm/filemap: map entire large folio faultaround
  mm/fault: try to map the entire file folio in finish_fault()
  mm/rmap: mlock large folios in try_to_unmap_one()
  mm/rmap: fix a mlock race condition in folio_referenced_one()
  ...

46 files changed, 792 insertions, 653 deletions

diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 9ef2633e2c08..d40ac39bfbe8 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -221,6 +221,16 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
 	ref->ct = NULL;
 }
 
+static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag)
+{
+	tag->ct.flags |= CODETAG_FLAG_INACCURATE;
+}
+
+static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag)
+{
+	return !!(tag->ct.flags & CODETAG_FLAG_INACCURATE);
+}
+
 #define alloc_tag_record(p)	((p) = current->alloc_tag)
 
 #else /* CONFIG_MEM_ALLOC_PROFILING */
@@ -230,6 +240,8 @@ static inline bool mem_alloc_profiling_enabled(void) { return false; }
 static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag,
 				 size_t bytes) {}
 static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {}
+static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag) {}
+static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) { return false; }
 #define alloc_tag_record(p)	do {} while (0)
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 066e5309bd45..dad5cb5b3812 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -199,7 +199,7 @@ struct gendisk {
 	unsigned int		zone_wplugs_hash_bits;
 	atomic_t		nr_zone_wplugs;
 	spinlock_t		zone_wplugs_lock;
-	struct mempool_s	*zone_wplugs_pool;
+	struct mempool		*zone_wplugs_pool;
 	struct hlist_head	*zone_wplugs_hash;
 	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h
index 1af241525a17..f6e0795db484 100644
--- a/include/linux/bpfptr.h
+++ b/include/linux/bpfptr.h
@@ -67,7 +67,7 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset,
 
 static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len)
 {
-	void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN);
+	void *p = kvmalloc_node_align_noprof(len, 1, GFP_USER | __GFP_NOWARN, NUMA_NO_NODE);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 0a80e1f9aa20..3fc0efa0825b 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -22,11 +22,8 @@ struct page;
  * @bv_len:    Number of bytes in the address range.
  * @bv_offset: Start of the address range relative to the start of @bv_page.
  *
- * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len:
- *
- *   nth_page(@bv_page, n) == @bv_page + n
- *
- * This holds because page_is_mergeable() checks the above property.
+ * All pages within a bio_vec starting from @bv_page are contiguous and
+ * can simply be iterated (see bvec_advance()).
  */
 struct bio_vec {
 	struct page	*bv_page;
diff --git a/include/linux/codetag.h b/include/linux/codetag.h
index 457ed8fd3214..8ea2a5f7c98a 100644
--- a/include/linux/codetag.h
+++ b/include/linux/codetag.h
@@ -16,13 +16,16 @@ struct module;
 #define CODETAG_SECTION_START_PREFIX	"__start_"
 #define CODETAG_SECTION_STOP_PREFIX	"__stop_"
 
+/* codetag flags */
+#define CODETAG_FLAG_INACCURATE	(1 << 0)
+
 /*
  * An instance of this structure is created in a special ELF section at every
  * code location being tagged.  At runtime, the special section is treated as
  * an array of these.
  */
 struct codetag {
-	unsigned int flags; /* used in later patches */
+	unsigned int flags;
 	unsigned int lineno;
 	const char *modname;
 	const char *function;
diff --git a/include/linux/damon.h b/include/linux/damon.h
index 9e62b2a85538..cae8c613c5fc 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -110,7 +110,7 @@ struct damon_target {
  *
  * @DAMOS_WILLNEED:	Call ``madvise()`` for the region with MADV_WILLNEED.
  * @DAMOS_COLD:		Call ``madvise()`` for the region with MADV_COLD.
- * @DAMOS_PAGEOUT:	Call ``madvise()`` for the region with MADV_PAGEOUT.
+ * @DAMOS_PAGEOUT:	Reclaim the region.
  * @DAMOS_HUGEPAGE:	Call ``madvise()`` for the region with MADV_HUGEPAGE.
  * @DAMOS_NOHUGEPAGE:	Call ``madvise()`` for the region with MADV_NOHUGEPAGE.
  * @DAMOS_LRU_PRIO:	Prioritize the region on its LRU lists.
@@ -121,10 +121,10 @@ struct damon_target {
  * @NR_DAMOS_ACTIONS:	Total number of DAMOS actions
  *
  * The support of each action is up to running &struct damon_operations.
- * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR supports all actions except
- * &enum DAMOS_LRU_PRIO and &enum DAMOS_LRU_DEPRIO.  &enum DAMON_OPS_PADDR
- * supports only &enum DAMOS_PAGEOUT, &enum DAMOS_LRU_PRIO, &enum
- * DAMOS_LRU_DEPRIO, and &DAMOS_STAT.
+ * Refer to 'Operation Action' section of Documentation/mm/damon/design.rst for
+ * status of the supports.
+ *
+ * Note that DAMOS_PAGEOUT doesn't trigger demotions.
  */
 enum damos_action {
 	DAMOS_WILLNEED,
@@ -748,7 +748,8 @@ struct damon_attrs {
  * Accesses to other fields must be protected by themselves.
  *
  * @ops:	Set of monitoring operations for given use cases.
- *
+ * @addr_unit:	Scale factor for core to ops address conversion.
+ * @min_sz_region:		Minimum region size.
  * @adaptive_targets:	Head of monitoring targets (&damon_target) list.
  * @schemes:		Head of schemes (&damos) list.
  */
@@ -790,6 +791,8 @@ struct damon_ctx {
 	struct mutex kdamond_lock;
 
 	struct damon_operations ops;
+	unsigned long addr_unit;
+	unsigned long min_sz_region;
 
 	struct list_head adaptive_targets;
 	struct list_head schemes;
@@ -878,7 +881,7 @@ static inline void damon_insert_region(struct damon_region *r,
 void damon_add_region(struct damon_region *r, struct damon_target *t);
 void damon_destroy_region(struct damon_region *r, struct damon_target *t);
 int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
-		unsigned int nr_ranges);
+		unsigned int nr_ranges, unsigned long min_sz_region);
 void damon_update_region_access_rate(struct damon_region *r, bool accessed,
 		struct damon_attrs *attrs);
 
@@ -935,6 +938,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 }
 
 
+bool damon_initialized(void);
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
 bool damon_is_running(struct damon_ctx *ctx);
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index b303472255be..32884c9721e5 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -47,6 +47,7 @@ extern int freeze_processes(void);
 extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 extern void thaw_kernel_threads(void);
+extern void thaw_process(struct task_struct *p);
 
 static inline bool try_to_freeze(void)
 {
@@ -80,6 +81,7 @@ static inline int freeze_processes(void) { return -ENOSYS; }
 static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 static inline void thaw_kernel_threads(void) {}
+static inline void thaw_process(struct task_struct *p) {}
 
 static inline bool try_to_freeze(void) { return false; }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9e9d7c757efe..75fb216b0f7a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -537,7 +537,7 @@ struct address_space {
 /*
  * Returns true if any of the pages in the mapping are marked with the tag.
  */
-static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
+static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag)
 {
 	return xa_marked(&mapping->i_pages, tag);
 }
@@ -585,7 +585,7 @@ static inline void i_mmap_assert_write_locked(struct address_space *mapping)
 /*
  * Might pages of this file be mapped into userspace?
  */
-static inline int mapping_mapped(struct address_space *mapping)
+static inline int mapping_mapped(const struct address_space *mapping)
 {
 	return	!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
 }
@@ -599,7 +599,7 @@ static inline int mapping_mapped(struct address_space *mapping)
  * If i_mmap_writable is negative, no new writable mappings are allowed. You
  * can only deny writable mappings, if none exists right now.
  */
-static inline int mapping_writably_mapped(struct address_space *mapping)
+static inline int mapping_writably_mapped(const struct address_space *mapping)
 {
 	return atomic_read(&mapping->i_mmap_writable) > 0;
 }
@@ -2385,6 +2385,8 @@ static inline bool can_mmap_file(struct file *file)
 	return true;
 }
 
+int __compat_vma_mmap_prepare(const struct file_operations *f_op,
+		struct file *file, struct vm_area_struct *vma);
 int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma);
 
 static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 36053c3d6d64..0574c21ca45d 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -7,7 +7,7 @@
  */
 #ifdef CONFIG_KMAP_LOCAL
 void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
-void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
+void *__kmap_local_page_prot(const struct page *page, pgprot_t prot);
 void kunmap_local_indexed(const void *vaddr);
 void kmap_local_fork(struct task_struct *tsk);
 void __kmap_local_sched_out(void);
@@ -33,7 +33,7 @@ static inline void kmap_flush_tlb(unsigned long addr) { }
 #endif
 
 void *kmap_high(struct page *page);
-void kunmap_high(struct page *page);
+void kunmap_high(const struct page *page);
 void __kmap_flush_unused(void);
 struct page *__kmap_to_page(void *addr);
 
@@ -50,7 +50,7 @@ static inline void *kmap(struct page *page)
 	return addr;
 }
 
-static inline void kunmap(struct page *page)
+static inline void kunmap(const struct page *page)
 {
 	might_sleep();
 	if (!PageHighMem(page))
@@ -68,12 +68,12 @@ static inline void kmap_flush_unused(void)
 	__kmap_flush_unused();
 }
 
-static inline void *kmap_local_page(struct page *page)
+static inline void *kmap_local_page(const struct page *page)
 {
 	return __kmap_local_page_prot(page, kmap_prot);
 }
 
-static inline void *kmap_local_page_try_from_panic(struct page *page)
+static inline void *kmap_local_page_try_from_panic(const struct page *page)
 {
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -81,13 +81,13 @@ static inline void *kmap_local_page_try_from_panic(struct page *page)
 	return NULL;
 }
 
-static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset)
 {
-	struct page *page = folio_page(folio, offset / PAGE_SIZE);
+	const struct page *page = folio_page(folio, offset / PAGE_SIZE);
 	return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE;
 }
 
-static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot)
 {
 	return __kmap_local_page_prot(page, prot);
 }
@@ -102,7 +102,7 @@ static inline void __kunmap_local(const void *vaddr)
 	kunmap_local_indexed(vaddr);
 }
 
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot)
 {
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		migrate_disable();
@@ -113,7 +113,7 @@ static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	return __kmap_local_page_prot(page, prot);
 }
 
-static inline void *kmap_atomic(struct page *page)
+static inline void *kmap_atomic(const struct page *page)
 {
 	return kmap_atomic_prot(page, kmap_prot);
 }
@@ -173,32 +173,32 @@ static inline void *kmap(struct page *page)
 	return page_address(page);
 }
 
-static inline void kunmap_high(struct page *page) { }
+static inline void kunmap_high(const struct page *page) { }
 static inline void kmap_flush_unused(void) { }
 
-static inline void kunmap(struct page *page)
+static inline void kunmap(const struct page *page)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
 	kunmap_flush_on_unmap(page_address(page));
 #endif
 }
 
-static inline void *kmap_local_page(struct page *page)
+static inline void *kmap_local_page(const struct page *page)
 {
 	return page_address(page);
 }
 
-static inline void *kmap_local_page_try_from_panic(struct page *page)
+static inline void *kmap_local_page_try_from_panic(const struct page *page)
 {
 	return page_address(page);
 }
 
-static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset)
 {
 	return folio_address(folio) + offset;
 }
 
-static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot)
 {
 	return kmap_local_page(page);
 }
@@ -215,7 +215,7 @@ static inline void __kunmap_local(const void *addr)
 #endif
 }
 
-static inline void *kmap_atomic(struct page *page)
+static inline void *kmap_atomic(const struct page *page)
 {
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		migrate_disable();
@@ -225,7 +225,7 @@ static inline void *kmap_atomic(struct page *page)
 	return page_address(page);
 }
 
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot)
 {
 	return kmap_atomic(page);
 }
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 6234f316468c..105cc4c00cc3 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -43,7 +43,7 @@ static inline void *kmap(struct page *page);
  * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
  * pages in the low memory area.
  */
-static inline void kunmap(struct page *page);
+static inline void kunmap(const struct page *page);
 
 /**
  * kmap_to_page - Get the page for a kmap'ed address
@@ -93,7 +93,7 @@ static inline void kmap_flush_unused(void);
  * disabling migration in order to keep the virtual address stable across
  * preemption. No caller of kmap_local_page() can rely on this side effect.
  */
-static inline void *kmap_local_page(struct page *page);
+static inline void *kmap_local_page(const struct page *page);
 
 /**
  * kmap_local_folio - Map a page in this folio for temporary usage
@@ -129,7 +129,7 @@ static inline void *kmap_local_page(struct page *page);
  * Context: Can be invoked from any context.
  * Return: The virtual address of @offset.
  */
-static inline void *kmap_local_folio(struct folio *folio, size_t offset);
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset);
 
 /**
  * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
@@ -176,7 +176,7 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
  * kunmap_atomic(vaddr2);
  * kunmap_atomic(vaddr1);
  */
-static inline void *kmap_atomic(struct page *page);
+static inline void *kmap_atomic(const struct page *page);
 
 /* Highmem related interfaces for management code */
 static inline unsigned long nr_free_highpages(void);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7748489fde1b..f327d62fc985 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -94,12 +94,15 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define THP_ORDERS_ALL	\
 	(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT)
 
-#define TVA_SMAPS		(1 << 0)	/* Will be used for procfs */
-#define TVA_IN_PF		(1 << 1)	/* Page fault handler */
-#define TVA_ENFORCE_SYSFS	(1 << 2)	/* Obey sysfs configuration */
+enum tva_type {
+	TVA_SMAPS,		/* Exposing "THPeligible:" in smaps. */
+	TVA_PAGEFAULT,		/* Serving a page fault. */
+	TVA_KHUGEPAGED,		/* Khugepaged collapse. */
+	TVA_FORCED_COLLAPSE,	/* Forced collapse (e.g. MADV_COLLAPSE). */
+};
 
-#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \
-	(!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order)))
+#define thp_vma_allowable_order(vma, vm_flags, type, order) \
+	(!!thp_vma_allowable_orders(vma, vm_flags, type, BIT(order)))
 
 #define split_folio(f) split_folio_to_list(f, NULL)
 
@@ -264,14 +267,14 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
 
 unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 					 vm_flags_t vm_flags,
-					 unsigned long tva_flags,
+					 enum tva_type type,
 					 unsigned long orders);
 
 /**
  * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma
  * @vma:  the vm area to check
  * @vm_flags: use these vm_flags instead of vma->vm_flags
- * @tva_flags: Which TVA flags to honour
+ * @type: TVA type
  * @orders: bitfield of all orders to consider
  *
  * Calculates the intersection of the requested hugepage orders and the allowed
@@ -285,11 +288,14 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 static inline
 unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
 				       vm_flags_t vm_flags,
-				       unsigned long tva_flags,
+				       enum tva_type type,
 				       unsigned long orders)
 {
-	/* Optimization to check if required orders are enabled early. */
-	if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) {
+	/*
+	 * Optimization to check if required orders are enabled early. Only
+	 * forced collapse ignores sysfs configs.
+	 */
+	if (type != TVA_FORCED_COLLAPSE && vma_is_anonymous(vma)) {
 		unsigned long mask = READ_ONCE(huge_anon_orders_always);
 
 		if (vm_flags & VM_HUGEPAGE)
@@ -303,7 +309,7 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
 			return 0;
 	}