Merge tag 'mm-hotfixes-stable-2025-04-19-21-24' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc hotfixes from Andrew Morton:
 "16 hotfixes. 2 are cc:stable and the remainder address post-6.14
  issues or aren't considered necessary for -stable kernels.

  All patches are basically for MM although five are alterations to
  MAINTAINERS"

[ Basic counting skills are clearly not a strictly necessary requirement
  for kernel maintainers.     - Linus ]

* tag 'mm-hotfixes-stable-2025-04-19-21-24' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  MAINTAINERS: add section for locking of mm's and VMAs
  mm: vmscan: fix kswapd exit condition in defrag_mode
  mm: vmscan: restore high-cpu watermark safety in kswapd
  MAINTAINERS: add Pedro as reviewer to the MEMORY MAPPING section
  mm/memory: move sanity checks in do_wp_page() after mapcount vs. refcount stabilization
  mm, hugetlb: increment the number of pages to be reset on HVO
  writeback: fix false warning in inode_to_wb()
  docs: ABI: replace [email protected] with new Meta address
  mm/gup: fix wrongly calculated returned value in fault_in_safe_writeable()
  MAINTAINERS: add memory advice section
  MAINTAINERS: add mmap trace events to MEMORY MAPPING
  mm: memcontrol: fix swap counter leak from offline cgroup
  MAINTAINERS: add MM subsection for the page allocator
  MAINTAINERS: update SLAB ALLOCATOR maintainers
  fs/dax: fix folio splitting issue by resetting old folio order + _nr_pages
  mm/page_alloc: fix deadlock on cpu_hotplug_lock in __accept_page()

Author: torvalds

CREDITS

@@ -2071,6 +2071,10 @@ S: 660 Harvard Ave. #7
 S: Santa Clara, CA 95051
 S: USA
 
+N: Joonsoo Kim
+E: [email protected]
+D: Slab allocators
+
 N: Kukjin Kim
 E: [email protected]
 D: Samsung S3C, S5P and Exynos ARM architectures

Documentation/ABI/stable/sysfs-block

@@ -77,7 +77,7 @@ Description:
 
 What:		/sys/block/<disk>/diskseq
 Date:		February 2021
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:
 		The /sys/block/<disk>/diskseq files reports the disk
 		sequence number, which is a monotonically increasing

Documentation/ABI/testing/sysfs-kernel-reboot

@@ -1,33 +1,33 @@
 What:		/sys/kernel/reboot
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Interface to set the kernel reboot behavior, similarly to
 		what can be done via the reboot= cmdline option.
 		(see Documentation/admin-guide/kernel-parameters.txt)
 
 What:		/sys/kernel/reboot/mode
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Reboot mode. Valid values are: cold warm hard soft gpio
 
 What:		/sys/kernel/reboot/type
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Reboot type. Valid values are: bios acpi kbd triple efi pci
 
 What:		/sys/kernel/reboot/cpu
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	CPU number to use to reboot.
 
 What:		/sys/kernel/reboot/force
 Date:		November 2020
 KernelVersion:	5.11
-Contact:	Matteo Croce <mcroce@microsoft.com>
+Contact:	Matteo Croce <teknoraver@meta.com>
 Description:	Don't wait for any other CPUs on reboot and
 		avoid anything that could hang.
 

MAINTAINERS

@@ -15517,6 +15517,21 @@ F:	mm/numa.c
 F:	mm/numa_emulation.c
 F:	mm/numa_memblks.c
 
+MEMORY MANAGEMENT - PAGE ALLOCATOR
+M:	Andrew Morton <[email protected]>
+R:	Vlastimil Babka <[email protected]>
+R:	Suren Baghdasaryan <[email protected]>
+R:	Michal Hocko <[email protected]>
+R:	Brendan Jackman <[email protected]>
+R:	Johannes Weiner <[email protected]>
+R:	Zi Yan <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	mm/compaction.c
+F:	mm/page_alloc.c
+F:	include/linux/gfp.h
+F:	include/linux/compaction.h
+
 MEMORY MANAGEMENT - SECRETMEM
 M:	Andrew Morton <[email protected]>
 M:	Mike Rapoport <[email protected]>
@@ -15544,10 +15559,12 @@ M:	Liam R. Howlett <[email protected]>
 M:	Lorenzo Stoakes <[email protected]>
 R:	Vlastimil Babka <[email protected]>
 R:	Jann Horn <[email protected]>
+R:	Pedro Falcato <[email protected]>
 L:	[email protected]
 S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/trace/events/mmap.h
 F:	mm/mlock.c
 F:	mm/mmap.c
 F:	mm/mprotect.c
@@ -15558,6 +15575,36 @@ F:	mm/vma.h
 F:	mm/vma_internal.h
 F:	tools/testing/vma/
 
+MEMORY MAPPING - LOCKING
+M:	Andrew Morton <[email protected]>
+M:	Suren Baghdasaryan <[email protected]>
+M:	Liam R. Howlett <[email protected]>
+M:	Lorenzo Stoakes <[email protected]>
+R:	Vlastimil Babka <[email protected]>
+R:	Shakeel Butt <[email protected]>
+L:	[email protected]
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	Documentation/mm/process_addrs.rst
+F:	include/linux/mmap_lock.h
+F:	include/trace/events/mmap_lock.h
+F:	mm/mmap_lock.c
+
+MEMORY MAPPING - MADVISE (MEMORY ADVICE)
+M:	Andrew Morton <[email protected]>
+M:	Liam R. Howlett <[email protected]>
+M:	Lorenzo Stoakes <[email protected]>
+M:	David Hildenbrand <[email protected]>
+R:	Vlastimil Babka <[email protected]>
+R:	Jann Horn <[email protected]>
+L:	[email protected]
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	include/uapi/asm-generic/mman-common.h
+F:	mm/madvise.c
+
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	Miquel Raynal <[email protected]>
 M:	Richard Weinberger <[email protected]>
@@ -22250,9 +22297,7 @@ F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
 M:	Christoph Lameter <[email protected]>
-M:	Pekka Enberg <[email protected]>
 M:	David Rientjes <[email protected]>
-M:	Joonsoo Kim <[email protected]>
 M:	Andrew Morton <[email protected]>
 M:	Vlastimil Babka <[email protected]>
 R:	Roman Gushchin <[email protected]>

fs/dax.c

@@ -396,6 +396,7 @@ static inline unsigned long dax_folio_put(struct folio *folio)
 	order = folio_order(folio);
 	if (!order)
 		return 0;
+	folio_reset_order(folio);
 
 	for (i = 0; i < (1UL << order); i++) {
 		struct dev_pagemap *pgmap = page_pgmap(&folio->page);

include/linux/backing-dev.h

@@ -249,6 +249,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 {
 #ifdef CONFIG_LOCKDEP
 	WARN_ON_ONCE(debug_locks &&
+		     (inode->i_sb->s_iflags & SB_I_CGROUPWB) &&
 		     (!lockdep_is_held(&inode->i_lock) &&
 		      !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) &&
 		      !lockdep_is_held(&inode->i_wb->list_lock)));

include/linux/mm.h

@@ -1218,6 +1218,23 @@ static inline unsigned int folio_order(const struct folio *folio)
 	return folio_large_order(folio);
 }
 
+/**
+ * folio_reset_order - Reset the folio order and derived _nr_pages
+ * @folio: The folio.
+ *
+ * Reset the order and derived _nr_pages to 0. Must only be used in the
+ * process of splitting large folios.
+ */
+static inline void folio_reset_order(struct folio *folio)
+{
+	if (WARN_ON_ONCE(!folio_test_large(folio)))
+		return;
+	folio->_flags_1 &= ~0xffUL;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+	folio->_nr_pages = 0;
+#endif
+}
+
 #include <linux/huge_mm.h>
 
 /*

include/linux/mmzone.h

@@ -967,6 +967,9 @@ struct zone {
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
 	struct list_head	unaccepted_pages;
+
+	/* To be called once the last page in the zone is accepted */
+	struct work_struct	unaccepted_cleanup;
 #endif
 
 	/* zone flags, see below */
@@ -1499,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int highest_zoneidx);
 /*
  * Memory initialization context, use to differentiate memory added by
  * the platform statically or via memory hotplug interface.

mm/gup.c

@@ -2207,8 +2207,8 @@ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
 	} while (start != end);
 	mmap_read_unlock(mm);
 
-	if (size > (unsigned long)uaddr - start)
-		return size - ((unsigned long)uaddr - start);
+	if (size > start - (unsigned long)uaddr)
+		return size - (start - (unsigned long)uaddr);
 	return 0;
 }
 EXPORT_SYMBOL(fault_in_safe_writeable);

mm/hugetlb_vmemmap.c

@@ -238,11 +238,11 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
  * struct page, the special metadata (e.g. page->flags or page->mapping)
  * cannot copy to the tail struct page structs. The invalid value will be
  * checked in the free_tail_page_prepare(). In order to avoid the message
- * of "corrupted mapping in tail page". We need to reset at least 3 (one
- * head struct page struct and two tail struct page structs) struct page
+ * of "corrupted mapping in tail page". We need to reset at least 4 (one
+ * head struct page struct and three tail struct page structs) struct page
  * structs.
  */
-#define NR_RESET_STRUCT_PAGE		3
+#define NR_RESET_STRUCT_PAGE		4
 
 static inline void reset_struct_pages(struct page *start)
 {

mm/internal.h

@@ -1595,6 +1595,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc);
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 void accept_page(struct page *page);
+void unaccepted_cleanup_work(struct work_struct *work);
 #else /* CONFIG_UNACCEPTED_MEMORY */
 static inline void accept_page(struct page *page)
 {

mm/memcontrol-v1.c

@@ -620,7 +620,7 @@ void memcg1_swapout(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
+	swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
 
 	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;

mm/memory.c

@@ -3734,8 +3734,6 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 		return false;
 
 	VM_WARN_ON_ONCE(folio_test_ksm(folio));
-	VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio));
-	VM_WARN_ON_ONCE(folio_entire_mapcount(folio));
 
 	if (unlikely(folio_test_swapcache(folio))) {
 		/*
@@ -3760,6 +3758,8 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
 	if (folio_large_mapcount(folio) != folio_ref_count(folio))
 		goto unlock;
 
+	VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio);
 	VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
 			folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
 

mm/mm_init.c

@@ -1441,6 +1441,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	INIT_LIST_HEAD(&zone->unaccepted_pages);
+	INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work);
 #endif
 }
 

mm/page_alloc.c

@@ -3470,18 +3470,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	return false;
 }
 
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-			unsigned long mark, int highest_zoneidx)
-{
-	long free_pages = zone_page_state(z, NR_FREE_PAGES);
-
-	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
-		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
-
-	return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
-								free_pages);
-}
-
 #ifdef CONFIG_NUMA
 int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
 
@@ -7191,6 +7179,11 @@ static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
 
 static bool lazy_accept = true;
 
+void unaccepted_cleanup_work(struct work_struct *work)
+{
+	static_branch_dec(&zones_with_unaccepted_pages);
+}
+
 static int __init accept_memory_parse(char *p)
 {
 	if (!strcmp(p, "lazy")) {
@@ -7229,8 +7222,27 @@ static void __accept_page(struct zone *zone, unsigned long *flags,
 
 	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
 
-	if (last)
-		static_branch_dec(&zones_with_unaccepted_pages);
+	if (last) {
+		/*
+		 * There are two corner cases:
+		 *
+		 * - If allocation occurs during the CPU bring up,
+		 *   static_branch_dec() cannot be used directly as
+		 *   it causes a deadlock on cpu_hotplug_lock.
+		 *
+		 *   Instead, use schedule_work() to prevent deadlock.
+		 *
+		 * - If allocation occurs before workqueues are initialized,
+		 *   static_branch_dec() should be called directly.
+		 *
+		 *   Workqueues are initialized before CPU bring up, so this
+		 *   will not conflict with the first scenario.
+		 */
+		if (system_wq)
+			schedule_work(&zone->unaccepted_cleanup);
+		else
+			unaccepted_cleanup_work(&zone->unaccepted_cleanup);
+	}
 }
 
 void accept_page(struct page *page)

mm/vmscan.c

@@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 	 * meet watermarks.
 	 */
 	for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) {
+		enum zone_stat_item item;
 		unsigned long free_pages;
 
 		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
@@ -6746,11 +6747,33 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 		/*
 		 * In defrag_mode, watermarks must be met in whole
 		 * blocks to avoid polluting allocator fallbacks.
+		 *
+		 * However, kswapd usually cannot accomplish this on
+		 * its own and needs kcompactd support. Once it's
+		 * reclaimed a compaction gap, and kswapd_shrink_node
+		 * has dropped order, simply ensure there are enough
+		 * base pages for compaction, wake kcompactd & sleep.
 		 */
-		if (defrag_mode)
-			free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS);
+		if (defrag_mode && order)
+			item = NR_FREE_PAGES_BLOCKS;
 		else
-			free_pages = zone_page_state(zone, NR_FREE_PAGES);
+			item = NR_FREE_PAGES;
+
+		/*
+		 * When there is a high number of CPUs in the system,
+		 * the cumulative error from the vmstat per-cpu cache
+		 * can blur the line between the watermarks. In that
+		 * case, be safe and get an accurate snapshot.
+		 *
+		 * TODO: NR_FREE_PAGES_BLOCKS moves in steps of
+		 * pageblock_nr_pages, while the vmstat pcp threshold
+		 * is limited to 125. On many configurations that
+		 * counter won't actually be per-cpu cached. But keep
+		 * things simple for now; revisit when somebody cares.
+		 */
+		free_pages = zone_page_state(zone, item);
+		if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark)
+			free_pages = zone_page_state_snapshot(zone, item);
 
 		if (__zone_watermark_ok(zone, order, mark, highest_zoneidx,
 					0, free_pages))