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
  ...

26 files changed, 589 insertions, 396 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 439815cc1ab9..fbad4fcd408e 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -102,8 +102,18 @@ static inline unsigned long wb_stat_error(void)
 #endif
 }
 
+/* BDI ratio is expressed as part per 1000000 for finer granularity. */
+#define BDI_RATIO_SCALE 10000
+
+u64 bdi_get_min_bytes(struct backing_dev_info *bdi);
+u64 bdi_get_max_bytes(struct backing_dev_info *bdi);
 int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
 int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
+int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio);
+int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio);
+int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes);
+int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes);
+int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit);
 
 /*
  * Flags in backing_dev_info::capability
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index f55a37efdb97..7af9e34ec261 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -82,26 +82,21 @@
 #define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
-#if __has_attribute(__no_sanitize_address__)
-#define __no_sanitize_address __attribute__((no_sanitize_address))
-#else
-#define __no_sanitize_address
-#endif
+#define __no_sanitize_address __attribute__((__no_sanitize_address__))
 
-#if defined(__SANITIZE_THREAD__) && __has_attribute(__no_sanitize_thread__)
-#define __no_sanitize_thread __attribute__((no_sanitize_thread))
+#if defined(__SANITIZE_THREAD__)
+#define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
 #else
 #define __no_sanitize_thread
 #endif
 
-#if __has_attribute(__no_sanitize_undefined__)
-#define __no_sanitize_undefined __attribute__((no_sanitize_undefined))
-#else
-#define __no_sanitize_undefined
-#endif
+#define __no_sanitize_undefined __attribute__((__no_sanitize_undefined__))
 
+/*
+ * Only supported since gcc >= 12
+ */
 #if defined(CONFIG_KCOV) && __has_attribute(__no_sanitize_coverage__)
-#define __no_sanitize_coverage __attribute__((no_sanitize_coverage))
+#define __no_sanitize_coverage __attribute__((__no_sanitize_coverage__))
 #else
 #define __no_sanitize_coverage
 #endif
diff --git a/include/linux/damon.h b/include/linux/damon.h
index 84525b9cdf6e..ad15a5b88e3a 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -357,6 +357,7 @@ struct damon_operations {
  * @after_wmarks_check:	Called after each schemes' watermarks check.
  * @after_sampling:	Called after each sampling.
  * @after_aggregation:	Called after each aggregation.
+ * @before_damos_apply:	Called before applying DAMOS action.
  * @before_terminate:	Called before terminating the monitoring.
  * @private:		User private data.
  *
@@ -385,6 +386,10 @@ struct damon_callback {
 	int (*after_wmarks_check)(struct damon_ctx *context);
 	int (*after_sampling)(struct damon_ctx *context);
 	int (*after_aggregation)(struct damon_ctx *context);
+	int (*before_damos_apply)(struct damon_ctx *context,
+			struct damon_target *target,
+			struct damon_region *region,
+			struct damos *scheme);
 	void (*before_terminate)(struct damon_ctx *context);
 };
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index ba985333e26b..2b5ecb591059 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -205,6 +205,8 @@ static inline void dax_unlock_mapping_entry(struct address_space *mapping,
 }
 #endif
 
+int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
+		const struct iomap_ops *ops);
 int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 		const struct iomap_ops *ops);
 int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index e9912da5441b..44242268f53b 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -319,6 +319,32 @@ static inline void copy_user_highpage(struct page *to, struct page *from,
 
 #endif
 
+#ifdef copy_mc_to_kernel
+static inline int copy_mc_user_highpage(struct page *to, struct page *from,
+					unsigned long vaddr, struct vm_area_struct *vma)
+{
+	unsigned long ret;
+	char *vfrom, *vto;
+
+	vfrom = kmap_local_page(from);
+	vto = kmap_local_page(to);
+	ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE);
+	if (!ret)
+		kmsan_unpoison_memory(page_address(to), PAGE_SIZE);
+	kunmap_local(vto);
+	kunmap_local(vfrom);
+
+	return ret;
+}
+#else
+static inline int copy_mc_user_highpage(struct page *to, struct page *from,
+					unsigned long vaddr, struct vm_area_struct *vma)
+{
+	copy_user_highpage(to, from, vaddr, vma);
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_COPY_HIGHPAGE
 
 static inline void copy_highpage(struct page *to, struct page *from)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8b4f93e84868..551834cd5299 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -33,22 +33,9 @@ typedef struct { unsigned long pd; } hugepd_t;
 /*
  * For HugeTLB page, there are more metadata to save in the struct page. But
  * the head struct page cannot meet our needs, so we have to abuse other tail
- * struct page to store the metadata. In order to avoid conflicts caused by
- * subsequent use of more tail struct pages, we gather these discrete indexes
- * of tail struct page here.
+ * struct page to store the metadata.
  */
-enum {
-	SUBPAGE_INDEX_SUBPOOL = 1,	/* reuse page->private */
-#ifdef CONFIG_CGROUP_HUGETLB
-	SUBPAGE_INDEX_CGROUP,		/* reuse page->private */
-	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
-	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
-	SUBPAGE_INDEX_HWPOISON,
-#endif
-	__NR_USED_SUBPAGE,
-};
+#define __NR_USED_SUBPAGE 3
 
 struct hugepage_subpool {
 	spinlock_t lock;
@@ -149,6 +136,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     unsigned long len);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
 			    struct vm_area_struct *, struct vm_area_struct *);
+struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
@@ -181,10 +170,11 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 int isolate_hugetlb(struct page *page, struct list_head *list);
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+				bool *migratable_cleared);
 void putback_active_hugepage(struct page *page);
-void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
+void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
@@ -209,17 +199,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write);
-struct page *follow_huge_pd(struct vm_area_struct *vma,
-			    unsigned long address, hugepd_t hpd,
-			    int flags, int pdshift);
-struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
-				 int flags);
-struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-				pud_t *pud, int flags);
-struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
-			     pgd_t *pgd, int flags);
 
 void hugetlb_vma_lock_read(struct vm_area_struct *vma);
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
@@ -272,6 +251,12 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags)
+{
+	BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/
+}
+
 static inline long follow_hugetlb_page(struct mm_struct *mm,
 			struct vm_area_struct *vma, struct page **pages,
 			struct vm_area_struct **vmas, unsigned long *position,
@@ -282,12 +267,6 @@ static inline long follow_hugetlb_page(struct mm_struct *mm,
 	return 0;
 }
 
-static inline struct page *follow_huge_addr(struct mm_struct *mm,
-					unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
 					  struct mm_struct *src,
 					  struct vm_area_struct *dst_vma,
@@ -320,31 +299,6 @@ static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
-static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
-				unsigned long address, hugepd_t hpd, int flags,
-				int pdshift)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
-				unsigned long address, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pud(struct mm_struct *mm,
-				unsigned long address, pud_t *pud, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pgd(struct mm_struct *mm,
-				unsigned long address, pgd_t *pgd, int flags)
-{
-	return NULL;
-}
-
 static inline int prepare_hugepage_range(struct file *file,
 				unsigned long addr, unsigned long len)
 {
@@ -425,12 +379,13 @@ static inline int isolate_hugetlb(struct page *page, struct list_head *list)
 	return -EBUSY;
 }
 
-static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
 {
 	return 0;
 }
 
-static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+					bool *migratable_cleared)
 {
 	return 0;
 }
@@ -439,8 +394,8 @@ static inline void putback_active_hugepage(struct page *page)
 {
 }
 
-static inline void move_hugetlb_state(struct page *oldpage,
-					struct page *newpage, int reason)
+static inline void move_hugetlb_state(struct folio *old_folio,
+					struct folio *new_folio, int reason)
 {
 }
 
@@ -623,26 +578,50 @@ enum hugetlb_page_flags {
  */
 #ifdef CONFIG_HUGETLB_PAGE
 #define TESTHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+bool folio_test_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		return test_bit(HPG_##flname, private);		\
+	}							\
 static inline int HPage##uname(struct page *page)		\
 	{ return test_bit(HPG_##flname, &(page->private)); }
 
 #define SETHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+void folio_set_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		set_bit(HPG_##flname, private);			\
+	}							\
 static inline void SetHPage##uname(struct page *page)		\
 	{ set_bit(HPG_##flname, &(page->private)); }
 
 #define CLEARHPAGEFLAG(uname, flname)				\
+static __always_inline						\
+void folio_clear_hugetlb_##flname(struct folio *folio)		\
+	{	void *private = &folio->private;		\
+		clear_bit(HPG_##flname, private);		\
+	}							\
 static inline void ClearHPage##uname(struct page *page)		\
 	{ clear_bit(HPG_##flname, &(page->private)); }
 #else
 #define TESTHPAGEFLAG(uname, flname)				\
+static inline bool						\
+folio_test_hugetlb_##flname(struct folio *folio)		\
+	{ return 0; }						\
 static inline int HPage##uname(struct page *page)		\
 	{ return 0; }
 
 #define SETHPAGEFLAG(uname, flname)				\
+static inline void						\
+folio_set_hugetlb_##flname(struct folio *folio) 		\
+	{ }							\
 static inline void SetHPage##uname(struct page *page)		\
 	{ }
 
 #define CLEARHPAGEFLAG(uname, flname)				\
+static inline void						\
+folio_clear_hugetlb_##flname(struct folio *folio)		\
+	{ }							\
 static inline void ClearHPage##uname(struct page *page)		\
 	{ }
 #endif
@@ -728,18 +707,29 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
+static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
+{
+	return folio->_hugetlb_subpool;
+}
+
 /*
- * hugetlb page subpool pointer located in hpage[1].private
+ * hugetlb page subpool pointer located in hpage[2].hugetlb_subpool
  */
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
-	return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
+	return hugetlb_folio_subpool(page_folio(hpage));
+}
+
+static inline void hugetlb_set_folio_subpool(struct folio *folio,
+					struct hugepage_subpool *subpool)
+{
+	folio->_hugetlb_subpool = subpool;
 }
 
 static inline void hugetlb_set_page_subpool(struct page *hpage,
 					struct hugepage_subpool *subpool)
 {
-	set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
+	hugetlb_set_folio_subpool(page_folio(hpage), subpool);
 }
 
 static inline struct hstate *hstate_file(struct file *f)
@@ -823,10 +813,15 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
 }
 #endif
 
+static inline struct hstate *folio_hstate(struct folio *folio)
+{
+	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	return size_to_hstate(folio_size(folio));
+}
+
 static inline struct hstate *page_hstate(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return size_to_hstate(page_size(page));
+	return folio_hstate(page_folio(page));
 }
 
 static inline unsigned hstate_index_to_shift(unsigned index)
@@ -983,6 +978,11 @@ void hugetlb_unregister_node(struct node *node);
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
 	return NULL;
@@ -1035,6 +1035,11 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 	return NULL;
 }
 
+static inline struct hstate *folio_hstate(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline struct hstate *page_hstate(struct page *page)
 {
 	return NULL;
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 630cd255d0cf..f706626a8063 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -24,12 +24,10 @@ struct file_region;
 #ifdef CONFIG_CGROUP_HUGETLB
 /*
  * Minimum page order trackable by hugetlb cgroup.
- * At least 4 pages are necessary for all the tracking information.
- * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
- * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
- * is the reservation usage cgroup.
+ * At least 3 pages are necessary for all the tracking information.
+ * The second tail page contains all of the hugetlb-specific fields.
  */
-#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1)
+#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__NR_USED_SUBPAGE)
 
 enum hugetlb_memory_event {
 	HUGETLB_MAX,
@@ -67,54 +65,50 @@ struct hugetlb_cgroup {
 };
 
 static inline struct hugetlb_cgroup *
-__hugetlb_cgroup_from_page(struct page *page, bool rsvd)
+__hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-
-	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
 	if (rsvd)
-		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
+		return folio->_hugetlb_cgroup_rsvd;
 	else
-		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
+		return folio->_hugetlb_cgroup;
 }
 
-static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio)
 {
-	return __hugetlb_cgroup_from_page(page, false);
+	return __hugetlb_cgroup_from_folio(folio, false);
 }
 
 static inline struct hugetlb_cgroup *
-hugetlb_cgroup_from_page_rsvd(struct page *page)
+hugetlb_cgroup_from_folio_rsvd(struct folio *folio)
 {
-	return __hugetlb_cgroup_from_page(page, true);
+	return __hugetlb_cgroup_from_folio(folio, true);
 }
 
-static inline void __set_hugetlb_cgroup(struct page *page,
+static inline void __set_hugetlb_cgroup(struct folio *folio,
 				       struct hugetlb_cgroup *h_cg, bool rsvd)
 {
-	VM_BUG_ON_PAGE(!PageHuge(page), page);
-
-	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER)
 		return;
 	if (rsvd)
-		set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
-				 (unsigned long)h_cg);
+		folio->_hugetlb_cgroup_rsvd = h_cg;
 	else
-		set_page_private(page + SUBPAGE_INDEX_CGROUP,
-				 (unsigned long)h_cg);
+		folio->_hugetlb_cgroup = h_cg;
 }
 
-static inline void set_hugetlb_cgroup(struct page *page,
+static inline void set_hugetlb_cgroup(struct folio *folio,
 				     struct hugetlb_cgroup *h_cg)
 {
-	__set_hugetlb_cgroup(page, h_cg, false);
+	__set_hugetlb_cgroup(folio, h_cg, false);
 }
 
-static inline void set_hugetlb_cgroup_rsvd(struct page *page,
+static inline void set_hugetlb_cgroup_rsvd(struct folio *folio,
 					  struct hugetlb_cgroup *h_cg)
 {
-	__set_hugetlb_cgroup(page, h_cg, true);
+	__set_hugetlb_cgroup(folio, h_cg, true);
 }
 
 static inline bool hugetlb_cgroup_disabled(void)
@@ -151,10 +145,10 @@ extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
 extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages,
 					      struct hugetlb_cgroup *h_cg,
 					      struct page *page);
-extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
-					 struct page *page);
-extern void hugetlb_cgroup_uncharge_page_rsvd(int idx, unsigned long nr_pages,
-					      struct page *page);
+extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages,
+					 struct folio *folio);
+extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages,
+					      struct folio *folio);
 
 extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 					   struct hugetlb_cgroup *h_cg);
@@ -170,8 +164,8 @@ extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 						bool region_del);
 
 extern void hugetlb_cgroup_file_init(void) __init;
-extern void hugetlb_cgroup_migrate(struct page *oldhpage,
-				   struct page *newhpage);
+extern void hugetlb_cgroup_migrate(struct folio *old_folio,
+				   struct folio *new_folio);
 
 #else
 static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
@@ -181,29 +175,23 @@ static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 {
 }
 
-static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
-{
-	return NULL;
-}
-
-static inline struct hugetlb_cgroup *
-hugetlb_cgroup_from_page_resv(struct page *page)
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio)
 {
 	return NULL;
 }
 
 static inline struct hugetlb_cgroup *
-hugetlb_cgroup_from_page_rsvd(struct page *page)
+hugetlb_cgroup_from_folio_rsvd(struct folio *folio)
 {
 	return NULL;
 }
 
-static inline void set_hugetlb_cgroup(struct page *page,
+static inline void set_hugetlb_cgroup(struct folio *folio,
 				     struct hugetlb_cgroup *h_cg)
 {
 }
 
-static inline void set_hugetlb_cgroup_rsvd(struct page *page,
+static inline void set_hugetlb_cgroup_rsvd(struct folio *folio,
 					  struct hugetlb_cgroup *h_cg)
 {
 }
@@ -253,14 +241,14 @@ hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages,
 {
 }
 
-static inline void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
-						struct page *page)
+static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages,
+						struct folio *folio)
 {
 }
 
-static inline void hugetlb_cgroup_uncharge_page_rsvd(int idx,
+static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx,
 						     unsigned long nr_pages,
-						     struct page *page)
+						     struct folio *folio)
 {
 }
 static inline void hugetlb_cgroup_uncharge_cgroup(int idx,
@@ -285,8 +273,8 @@ static inline void hugetlb_cgroup_file_init(void)
 {
 }
 
-static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
-					  struct page *newhpage)
+static inline void hugetlb_cgroup_migrate(struct folio *old_folio,
+					  struct folio *new_folio)
 {
 }
 
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 70162d707caf..f68865e19b0b 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,7 @@ extern void __khugepaged_exit(struct mm_struct *mm);
 extern void khugepaged_enter_vma(struct vm_area_struct *vma,
 				 unsigned long vm_flags);
 extern void khugepaged_min_free_kbytes_update(void);
+extern bool current_is_khugepaged(void);
 #ifdef CONFIG_SHMEM
 extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 				   bool install_pmd);
@@ -57,6 +58,11 @@ static inline int collapse_pte_mapped_thp(struct mm_struct *mm,
 static inline void khugepaged_min_free_kbytes_update(void)
 {
 }
+
+static inline bool current_is_khugepaged(void)
+{
+	return false;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_KHUGEPAGED_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e1644a24009c..d3c8203cab6c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -615,28 +615,32 @@ static inline void mem_cgroup_protection(struct mem_cgroup *root,
 void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 				     struct mem_cgroup *memcg);
 
-static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_unprotected(struct mem_cgroup *target,
+					  struct mem_cgroup *memcg)
 {
 	/*
 	 * The root memcg doesn't account charges, and doesn't support
-	 * protection.
+	 * protection. The target memcg's protection is ignored, see
+	 * mem_cgroup_calculate_protection() and mem_cgroup_protection()
 	 */
-	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
-
+	return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) ||
+		memcg == target;
 }
 
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
-	if (!mem_cgroup_supports_protection(memcg))
+	if (mem_cgroup_unprotected(target, memcg))
 		return false;
 
 	return READ_ONCE(memcg->memory.elow) >=
 		page_counter_read(&memcg->memory);
 }
 
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
-	if (!mem_cgroup_supports_protection(memcg))
+	if (mem_cgroup_unprotected(target, memcg))
 		return false;
 
 	return READ_ONCE(memcg->memory.emin) >=
@@ -1209,12 +1213,19 @@ static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 {
 }
 
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_unprotected(struct mem_cgroup *target,
+					  struct mem_cgroup *memcg)
+{
+	return true;
+}
+static inline bool mem_cgroup_below_low(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
 	return false;
 }
 
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
+					struct mem_cgroup *memcg)
 {
 	return false;
 }
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 965009aa01d7..fc9647b1b4f9 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -18,7 +18,6 @@
  * the same memory tier.
  */
 #define MEMTIER_ADISTANCE_DRAM	((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
-#define MEMTIER_HOTPLUG_PRIO	100
 
 struct memory_tier;
 struct memory_dev_type {
diff --git a/include/linux/memory.h b/include/linux/memory.h
index aa619464a1df..31343566c221 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -19,7 +19,6 @@
 #include <linux/node.h>
 #include <linux/compiler.h>
 #include <linux/mutex.h>
-#include <linux/notifier.h>
 
 #define MIN_MEMORY_BLOCK_SIZE     (1UL << SECTION_SIZE_BITS)
 
@@ -85,6 +84,9 @@ struct memory_block {
 	unsigned long nr_vmemmap_pages;
 	struct memory_group *group;	/* group (if any) for this block */
 	struct list_head group_next;	/* next block inside memory group */
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+	atomic_long_t nr_hwpoison;
+#endif
 };
 
 int arch_get_memory_phys_device(uns