23 files changed, 319 insertions, 152 deletions

diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index c75d4a753849..879e5f8aa5e9 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -169,6 +169,8 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 	ptdesc = pagetable_alloc(gfp, 0);
 	if (!ptdesc)
 		return NULL;
+
+	pagetable_pud_ctor(ptdesc);
 	return ptdesc_address(ptdesc);
 }
 
@@ -190,8 +192,11 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 
 static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
 {
+	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
 	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	pagetable_free(virt_to_ptdesc(pud));
+	pagetable_pud_dtor(ptdesc);
+	pagetable_free(ptdesc);
 }
 
 #ifndef __HAVE_ARCH_PUD_FREE
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 44e9de51eedf..3dc4720e4773 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -198,7 +198,7 @@ void touch_buffer(struct buffer_head *bh);
 void folio_set_bh(struct buffer_head *bh, struct folio *folio,
 		  unsigned long offset);
 struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
-					bool retry);
+					gfp_t gfp);
 struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		bool retry);
 void create_empty_buffers(struct page *, unsigned long,
@@ -227,8 +227,8 @@ void __wait_on_buffer(struct buffer_head *);
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
-struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
-				  unsigned size, gfp_t gfp);
+struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
+		unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
@@ -338,17 +338,38 @@ sb_breadahead(struct super_block *sb, sector_t block)
 	__breadahead(sb->s_bdev, block, sb->s_blocksize);
 }
 
-static inline struct buffer_head *
-sb_getblk(struct super_block *sb, sector_t block)
+static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
+		sector_t block, unsigned size)
 {
-	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
+	gfp_t gfp;
+
+	gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
+	gfp |= __GFP_NOFAIL;
+
+	return bdev_getblk(bdev, block, size, gfp);
 }
 
+static inline struct buffer_head *__getblk(struct block_device *bdev,
+		sector_t block, unsigned size)
+{
+	gfp_t gfp;
 
-static inline struct buffer_head *
-sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+	gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
+	gfp |= __GFP_MOVABLE | __GFP_NOFAIL;
+
+	return bdev_getblk(bdev, block, size, gfp);
+}
+
+static inline struct buffer_head *sb_getblk(struct super_block *sb,
+		sector_t block)
 {
-	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+	return __getblk(sb->s_bdev, block, sb->s_blocksize);
+}
+
+static inline struct buffer_head *sb_getblk_gfp(struct super_block *sb,
+		sector_t block, gfp_t gfp)
+{
+	return bdev_getblk(sb->s_bdev, block, sb->s_blocksize, gfp);
 }
 
 static inline struct buffer_head *
@@ -385,20 +406,6 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
-static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
-						   sector_t block,
-						   unsigned size)
-{
-	return __getblk_gfp(bdev, block, size, 0);
-}
-
-static inline struct buffer_head *__getblk(struct block_device *bdev,
-					   sector_t block,
-					   unsigned size)
-{
-	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
-}
-
 static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags)
 {
 	if (!buffer_uptodate(bh) && trylock_buffer(bh)) {
diff --git a/include/linux/damon.h b/include/linux/damon.h
index ae2664d1d5f1..27b995c22497 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -40,9 +40,24 @@ struct damon_addr_range {
  * @ar:			The address range of the region.
  * @sampling_addr:	Address of the sample for the next access check.
  * @nr_accesses:	Access frequency of this region.
+ * @nr_accesses_bp:	@nr_accesses in basis point (0.01%) that updated for
+ *			each sampling interval.
  * @list:		List head for siblings.
  * @age:		Age of this region.
  *
+ * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be
+ * increased for every &damon_attrs->sample_interval if an access to the region
+ * during the last sampling interval is found.  The update of this field should
+ * not be done with direct access but with the helper function,
+ * damon_update_region_access_rate().
+ *
+ * @nr_accesses_bp is another representation of @nr_accesses in basis point
+ * (1 in 10,000) that updated for every &damon_attrs->sample_interval in a
+ * manner similar to moving sum.  By the algorithm, this value becomes
+ * @nr_accesses * 10000 for every &struct damon_attrs->aggr_interval.  This can
+ * be used when the aggregation interval is too huge and therefore cannot wait
+ * for it before getting the access monitoring results.
+ *
  * @age is initially zero, increased for each aggregation interval, and reset
  * to zero again if the access frequency is significantly changed.  If two
  * regions are merged into a new region, both @nr_accesses and @age of the new
@@ -52,6 +67,7 @@ struct damon_region {
 	struct damon_addr_range ar;
 	unsigned long sampling_addr;
 	unsigned int nr_accesses;
+	unsigned int nr_accesses_bp;
 	struct list_head list;
 
 	unsigned int age;
@@ -298,24 +314,24 @@ struct damos_access_pattern {
  * struct damos - Represents a Data Access Monitoring-based Operation Scheme.
  * @pattern:		Access pattern of target regions.
  * @action:		&damo_action to be applied to the target regions.
+ * @apply_interval_us:	The time between applying the @action.
  * @quota:		Control the aggressiveness of this scheme.
  * @wmarks:		Watermarks for automated (in)activation of this scheme.
  * @filters:		Additional set of &struct damos_filter for &action.
  * @stat:		Statistics of this scheme.
  * @list:		List head for siblings.
  *
- * For each aggregation interval, DAMON finds regions which fit in the
+ * For each @apply_interval_us, DAMON finds regions which fit in the
  * &pattern and applies &action to those. To avoid consuming too much
  * CPU time or IO resources for the &action, &quota is used.
  *
+ * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead.
+ *
  * To do the work only when needed, schemes can be activated for specific
  * system situations using &wmarks.  If all schemes that registered to the
  * monitoring context are inactive, DAMON stops monitoring either, and just
  * repeatedly checks the watermarks.
  *
- * If all schemes that registered to a &struct damon_ctx are inactive, DAMON
- * stops monitoring and just repeatedly checks the watermarks.
- *
  * Before applying the &action to a memory region, &struct damon_operations
  * implementation could check pages of the region and skip &action to respect
  * &filters
@@ -327,6 +343,14 @@ struct damos_access_pattern {
 struct damos {
 	struct damos_access_pattern pattern;
 	enum damos_action action;
+	unsigned long apply_interval_us;
+/* private: internal use only */
+	/*
+	 * number of sample intervals that should be passed before applying
+	 * @action
+	 */
+	unsigned long next_apply_sis;
+/* public: */
 	struct damos_quota quota;
 	struct damos_watermarks wmarks;
 	struct list_head filters;
@@ -472,13 +496,14 @@ struct damon_callback {
  *				regions.
  *
  * For each @sample_interval, DAMON checks whether each region is accessed or
- * not.  It aggregates and keeps the access information (number of accesses to
- * each region) for @aggr_interval time.  DAMON also checks whether the target
- * memory regions need update (e.g., by ``mmap()`` calls from the application,
- * in case of virtual memory monitoring) and applies the changes for each
- * @ops_update_interval.  All time intervals are in micro-seconds.
- * Please refer to &struct damon_operations and &struct damon_callback for more
- * detail.
+ * not during the last @sample_interval.  If such access is found, DAMON
+ * aggregates the information by increasing &damon_region->nr_accesses for
+ * @aggr_interval time.  For each @aggr_interval, the count is reset.  DAMON
+ * also checks whether the target memory regions need update (e.g., by
+ * ``mmap()`` calls from the application, in case of virtual memory monitoring)
+ * and applies the changes for each @ops_update_interval.  All time intervals
+ * are in micro-seconds.  Please refer to &struct damon_operations and &struct
+ * damon_callback for more detail.
  */
 struct damon_attrs {
 	unsigned long sample_interval;
@@ -522,8 +547,18 @@ struct damon_ctx {
 	struct damon_attrs attrs;
 
 /* private: internal use only */
-	struct timespec64 last_aggregation;
-	struct timespec64 last_ops_update;
+	/* number of sample intervals that passed since this context started */
+	unsigned long passed_sample_intervals;
+	/*
+	 * number of sample intervals that should be passed before next
+	 * aggregation
+	 */
+	unsigned long next_aggregation_sis;
+	/*
+	 * number of sample intervals that should be passed before next ops
+	 * update
+	 */
+	unsigned long next_ops_update_sis;
 
 /* public: */
 	struct task_struct *kdamond;
@@ -608,6 +643,8 @@ 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);
+void damon_update_region_access_rate(struct damon_region *r, bool accessed,
+		struct damon_attrs *attrs);
 
 struct damos_filter *damos_new_filter(enum damos_filter_type type,
 		bool matching);
@@ -615,7 +652,9 @@ void damos_add_filter(struct damos *s, struct damos_filter *f);
 void damos_destroy_filter(struct damos_filter *f);
 
 struct damos *damon_new_scheme(struct damos_access_pattern *pattern,
-			enum damos_action action, struct damos_quota *quota,
+			enum damos_action action,
+			unsigned long apply_interval_us,
+			struct damos_quota *quota,
 			struct damos_watermarks *wmarks);
 void damon_add_scheme(struct damon_ctx *ctx, struct damos *s);
 void damon_destroy_scheme(struct damos *s);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 22cd9902345d..b463502b16e1 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -159,8 +159,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
-dax_entry_t dax_lock_page(struct page *page);
-void dax_unlock_page(struct page *page, dax_entry_t cookie);
+dax_entry_t dax_lock_folio(struct folio *folio);
+void dax_unlock_folio(struct folio *folio, dax_entry_t cookie);
 dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
 		unsigned long index, struct page **page);
 void dax_unlock_mapping_entry(struct address_space *mapping,
@@ -182,14 +182,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 	return -EOPNOTSUPP;
 }
 
-static inline dax_entry_t dax_lock_page(struct page *page)
+static inline dax_entry_t dax_lock_folio(struct folio *folio)
 {
-	if (IS_DAX(page->mapping->host))
+	if (IS_DAX(folio->mapping->host))
 		return ~0UL;
 	return 0;
 }
 
-static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
+static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie)
 {
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b528f063e8ff..fd539c9fef8e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1265,7 +1265,7 @@ struct super_block {
 
 	const struct dentry_operations *s_d_op; /* default d_op for dentries */
 
-	struct shrinker s_shrink;	/* per-sb shrinker handle */
+	struct shrinker *s_shrink;	/* per-sb shrinker handle */
 
 	/* Number of inodes with nlink == 0 but still referenced */
 	atomic_long_t s_remove_count;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 47d25a5e1933..e5b9f7e62eeb 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -844,6 +844,12 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h)
 	return huge_page_size(h) / 512;
 }
 
+static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
+				struct address_space *mapping, pgoff_t idx)
+{
+	return filemap_lock_folio(mapping, idx << huge_page_order(h));
+}
+
 #include <asm/hugetlb.h>
 
 #ifndef is_hugepage_only_range
@@ -1040,6 +1046,12 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio
 	return NULL;
 }
 
+static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
+				struct address_space *mapping, pgoff_t idx)
+{
+	return NULL;
+}
+
 static inline int isolate_or_dissolve_huge_page(struct page *page,
 						struct list_head *list)
 {
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 52772c826c86..6dcbb4eb80fb 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -886,7 +886,7 @@ struct journal_s
 	 * Journal head shrinker, reclaim buffer's journal head which
 	 * has been written back.
 	 */
-	struct shrinker		j_shrinker;
+	struct shrinker		*j_shrinker;
 
 	/**
 	 * @j_checkpoint_jh_count:
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 1c1072e3ca06..ae3bde302f70 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -40,6 +40,8 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
+ * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
+ * not initialized (only for reserved regions).
  */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
@@ -47,6 +49,7 @@ enum memblock_flags {
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
 	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 	MEMBLOCK_DRIVER_MANAGED = 0x8,	/* always detected via a driver */
+	MEMBLOCK_RSRV_NOINIT	= 0x10,	/* don't initialize struct pages */
 };
 
 /**
@@ -125,6 +128,7 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
 int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
+int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
 void memblock_free(void *ptr, size_t size);
@@ -259,6 +263,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
 	return m->flags & MEMBLOCK_NOMAP;
 }
 
+static inline bool memblock_is_reserved_noinit(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_RSRV_NOINIT;
+}
+
 static inline bool memblock_is_driver_managed(struct memblock_region *m)
 {
 	return m->flags & MEMBLOCK_DRIVER_MANAGED;
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e4e24da16d2c..031102ac9311 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -21,6 +21,7 @@
 #include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
+#include <linux/shrinker.h>
 
 struct mem_cgroup;
 struct obj_cgroup;
@@ -88,17 +89,6 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
-/*
- * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
- * shrinkers, which have elements charged to this memcg.
- */
-struct shrinker_info {
-	struct rcu_head rcu;
-	atomic_long_t *nr_deferred;
-	unsigned long *map;
-	int map_nr_max;
-};
-
 struct lruvec_stats_percpu {
 	/* Local (CPU and cgroup) state */
 	long state[NR_VM_NODE_STAT_ITEMS];
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 437441cdf78f..1e39d27bee41 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -6,6 +6,7 @@
 #include <linux/nodemask.h>
 #include <linux/kref.h>
 #include <linux/mmzone.h>
+#include <linux/notifier.h>
 /*
  * Each tier cover a abstrace distance chunk size of 128
  */
@@ -22,7 +23,9 @@
 struct memory_tier;
 struct memory_dev_type {
 	/* list of memory types that are part of same tier as this type */
-	struct list_head tier_sibiling;
+	struct list_head tier_sibling;
+	/* list of memory types that are managed by one driver */
+	struct list_head list;
 	/* abstract distance for this specific memory type */
 	int adistance;
 	/* Nodes of same abstract distance */
@@ -30,12 +33,21 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
+struct node_hmem_attrs;
+
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
+extern struct memory_dev_type *default_dram_type;
 struct memory_dev_type *alloc_memory_type(int adistance);
 void put_memory_type(struct memory_dev_type *memtype);
 void init_node_memory_type(int node, struct memory_dev_type *default_type);
 void clear_node_memory_type(int node, struct memory_dev_type *memtype);
+int register_mt_adistance_algorithm(struct notifier_block *nb);
+int unregister_mt_adistance_algorithm(struct notifier_block *nb);
+int mt_calc_adistance(int node, int *adist);
+int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+			     const char *source);
+int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -60,6 +72,7 @@ static inline bool node_is_toptier(int node)
 #else
 
 #define numa_demotion_enabled	false
+#define default_dram_type	NULL
 /*
  * CONFIG_NUMA implementation returns non NULL error.
  */
@@ -97,5 +110,31 @@ static inline bool node_is_toptier(int node)
 {
 	return true;
 }
+
+static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int mt_calc_adistance(int node, int *adist)
+{
+	return NOTIFY_DONE;
+}
+
+static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+					   const char *source)
+{
+	return -EIO;
+}
+
+static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+{
+	return -EIO;
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index d232de7cdc56..6c2754d7bfed 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -174,7 +174,7 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 /* Check if a vma is migratable */
 extern bool vma_migratable(struct vm_area_struct *vma);
 
-extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long);
 extern void mpol_put_task_policy(struct task_struct *);
 
 static inline bool mpol_is_preferred_many(struct mempolicy *pol)
@@ -278,7 +278,8 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 }
 #endif
 
-static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
+static inline int mpol_misplaced(struct folio *folio,
+				 struct vm_area_struct *vma,
 				 unsigned long address)
 {
 	return -1; /* no node preference */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 711dd9412561..2ce13e8a309b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -142,10 +142,10 @@ const struct movable_operations *page_movable_ops(struct page *page)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
+int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
 			   int node);
 #else
-static inline int migrate_misplaced_page(struct page *page,
+static inline int migrate_misplaced_folio(struct folio *folio,
 					 struct vm_area_struct *vma, int node)
 {
 	return -EAGAIN; /* can't migrate now */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf5d0b1b16f4..52c40b3d0813 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2327,6 +2327,8 @@ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
+struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
+				  unsigned long addr, pmd_t pmd);
 struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t pmd);
 
@@ -2480,7 +2482,7 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
-		bool need_rmap_locks);
+		bool need_rmap_locks, bool for_stack);
 
 /*
  * Flags used by change_protection().  For now we make it a bitmap so
@@ -2628,14 +2630,6 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 		*maxrss = hiwater_rss;
 }
 
-#if defined(SPLIT_RSS_COUNTING)
-void sync_mm_rss(struct mm_struct *mm);
-#else
-static inline void sync_mm_rss(struct mm_struct *mm)
-{
-}
-#endif
-
 #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL
 static inline int pte_special(pte_t pte)
 {
@@ -3057,6 +3051,22 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 	return ptl;
 }
 
+static inline void pagetable_pud_ctor(struct ptdesc *ptdesc)
+{
+	struct folio *folio = ptdesc_folio(ptdesc);
+
+	__folio_set_pgtable(folio);
+	lruvec_stat_add_folio(folio, NR_PAGETABLE);
+}
+
+static inline void pagetable_pud_dtor(struct ptdesc *ptdesc)
+{
+	struct folio *folio = ptdesc_folio(ptdesc);
+
+	__folio_clear_pgtable(folio);
+	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
+}
+
 extern void __init pagecache_init(void);
 extern void free_initmem(void);
 
@@ -4062,4 +4072,11 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end)
 
 #endif
 
+static inline bool pfn_is_unaccepted_memory(unsigned long pfn)
+{
+	phys_addr_t paddr = pfn << PAGE_SHIFT;
+
+	return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE);
+}
+
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 6e3c857606f1..f349e08a9dfe 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -459,7 +459,14 @@ mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 }
 
-static inline int
+/*
+ * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it
+ * can return an error if a notifier can't proceed without blocking, in which
+ * case you're not allowed to modify PTEs in the specified range.
+ *
+ * This is mainly intended for OOM handling.
+ */
+static inline int __must_check
 mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range)
 {
 	int ret = 0;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4106fbc5b4b3..486587fcd27f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -639,8 +639,6 @@ struct lruvec {
 #endif
 };
 
-/* Isolate unmapped pages */
-#define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
 /* Isolate for asynchronous migration */
 #define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
 /* Isolate unevictable pages */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 351c3b7f93a1..759b29d9a69a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -789,9 +789,6 @@ static inline pgoff_t folio_next_index(struct folio *folio)
  */
 static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
 {
-	/* HugeTLBfs indexes the page cache in units of hpage_size */
-	if (folio_test_hugetlb(folio))
-		return &folio->page;
 	return folio_page(folio, index & (folio_nr_pages(folio) - 1));
 }
 
@@ -807,9 +804,6 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
  */
 static inline bool folio_contains(struct folio *folio, pgoff_t index)
 {
-	/* HugeTLBfs indexes the page cache in units of hpage_size */
-	if (folio_test_hugetlb(folio))
-		return folio->index == index;
 	return index - folio_index(folio) < folio_nr_pages(folio);
 }
 
@@ -867,10 +861,9 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping,
 }
 
 /*
- * Get index of the page within radix-tree (but not for hugetlb pages).
- * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
+ * Get the offset in PAGE_SIZE (even for hugetlb pages).
  */
-static inline pgoff_t page_to_index(struct page *page)
+static inline pgoff_t page_to_pgoff(struct page *page)
 {
 	struct page *head;
 
@@ -885,19 +878,6 @@ static inline pgoff_t page_to_index(struct page *page)
 	return head->index + page - head;
 }
 
-extern pgoff_t hugetlb_basepage_index(struct page *page);
-
-/*
- * Get the offset in PAGE_SIZE (even for hugetlb pages).
- * (TODO: hugetlb pages should have ->index in PAGE_SIZE)
- */
-static inline pgoff_t page_to_pgoff(struct page *page)
-{
-	if (unlikely(PageHuge(page)))
-		return hugetlb_basepage_index(page);
-	return page_to_index(page);
-}
-
 /*
  * Return byte-offset into filesystem object for page.
  */
@@ -934,24 +914,16 @@ static inline loff_t folio_file_pos(struct folio *folio)
 
 /*
  * Get the offset in PAGE_SIZE (even for hugetlb folios).
- * (TODO: hugetlb folios should have ->index in PAGE_SIZE)
  */
 static inline pgoff_t folio_pgoff(struct folio *folio)
 {
-	if (unlikely(folio_test_hugetlb(folio)))
-		return hugetlb_basepage_index(&folio->page);
 	return folio->index;
 }
 
-extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
-				     unsigned long address);
-
 static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 					unsigned long address)
 {
 	pgoff_t pgoff;
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		return linear_hugepage_index(vma, address);
 	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
 	pgoff += vma->vm_pgoff;
 	return pgoff;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 51cc21ebb568..d22f4d21a11c 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -203,7 +203,7 @@ void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr,
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
 
-void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
+void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 0ee96ea7a0e9..02f5090ffea2 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
+#define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 #define MMF_OOM_REAP_QUEUED	25	/* mm was queued for oom_reaper */
 #define MMF_MULTIPROCESS	26	/* mm is shared between processes */
 /*
@@ -85,10 +86,22 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HAS_MDWE		28
 #define MMF_HAS_MDWE_MASK	(1 << MMF_HAS_MDWE)
 
-#define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
+
+#define MMF_HAS_MDWE_NO_INHERIT	29
+
+#define MMF_VM_MERGE_ANY	30
+#define MMF_VM_MERGE_ANY_MASK	(1 << MMF_VM_MERGE_ANY)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
-				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
+				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
+				 MMF_VM_MERGE_ANY_MASK)
+
+static inline unsigned long mmf_init_flags(unsigned long flags)
+{
+	if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT))
+		flags &= ~((1UL << MMF_HAS_MDWE) |
+			   (1UL << MMF_HAS_MDWE_NO_INHERIT));
+	return flags & MMF_INIT_MASK;
+}
 
-#define MMF_VM_MERGE_ANY	29
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index 3988762efe15..06a9d35650f0 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -20,8 +20,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p, bool final);
-extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
-					int src_nid, int dst_cpu);
+bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio,
+				int src_nid, int dst_cpu);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
@@ -38,7 +38,7 @@ static inline void task_numa_free(struct task_struct *p, bool final)
 {
 }
 static inline bool should_numa_migrate_memory(struct task_struct *p,
-				struct page *page, int src_nid, int dst_cpu)
+				struct folio *folio, int src_nid, int dst_cpu)
 {
 	return true;
 }
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 224293b2dd06..e4f93120e0ab 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -4,6 +4,25 @@
 
 #include <linux/atomic.h>
 #include <linux/types.h>
+#include <linux/refcount.h>
+#include <linux/completion.h>
+
+#define SHRINKER_UNIT_BITS	BITS_PER_LONG
+
+/*
+ * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
+ * shrinkers, which have elements charged to the memcg.
+ */
+struct shrinker_info_unit {
+	atomic_long_t nr_deferred[SHRINKER_UNIT_BITS];
+	DECLARE_BITMAP(map, SHRINKER_UNIT_BITS);
+};
+
+struct shrinker_info {
+	struct rcu_head rcu;
+	int map_nr_max;
+	struct shrinker_info_unit *unit[];
+};
 
 /*
  * This struct is used to pass information from page reclaim to the shrinkers.
@@ -70,6 +89,19 @@ struct shrinker {
 	int seeks;	/* seeks to recreate an obj */
 	unsigned flags;
 
+	/*
+	 * The reference count of this shrinker. Registered shrinker have an
+	 * initial refcount of 1, then the lookup operations are now allowed
+	 * to use it via shrinker_try_get(). Later in the unregistration step,
+	 * the initial refcount will be discarded, and will free the shrinker
+	 * asynchronously via RCU after its refcount reaches 0.
+	 */
+	refcount_t refcount;
+	struct completion done;	/* use to wait for refcount to reach 0 */
+	struct rcu_head rcu;
+
+	void *private_data;
+
 	/* These are for internal use */
 	struct list_head list;
 #ifdef CONFIG_MEMCG
@@ -86,48 +118,38 @@ struct shrinker {
 };
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
 
-/* Flags */
-#define SHRINKER_REGISTERED	(1 << 0)
-#define SHRINKER_NUMA_AWARE	(1 << 1)
-#define SHRINKER_MEMCG_AWARE	(1 << 2)
+/* Internal flags */
+#define SHRINKER_REGISTERED	BIT(0)
+#define SHRINKER_ALLOCATED	BIT(1)
+
+/* Flags for users to use */
+#define SHRINKER_NUMA_AWARE	BIT(2)
+#define SHRINKER_MEMCG_AWARE	BIT(3)
 /*
  * It just makes sense when the shrinker is also MEMCG_AWARE for now,
  * non-MEMCG_AWARE shrinker should not have this flag set.
  */
-#define SHRINKER_NONSLAB	(1 << 3)
+#define SHRINKER_NONSLAB	BIT(4)
 
-extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker,
-					    const char *fmt, ...);
-extern void register_shrinker_prepared(struct shrinker *shrinker);
-extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker,
-					    const char *fmt, ...);
-extern void unregister_shrinker(struct shrinker *shrinker);
-extern void free_prealloced_shrinker(struct shrinker *shrinker);
-extern void synchronize_shrinkers(void);
+struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...);
+void shrinker_register(struct shrinker *shrinker);
+void shrinker_free(struct shrinker *shrinker);
 
-#ifdef CONFIG_SHRINKER_DEBUG
-extern int shrinker_debugfs_add(struct shrinker *shrinker);
-extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
-					      int *debugfs_id);
-extern void shrinker_debugfs_remove(struct dentry *debugfs_entry,
-				    int debugfs_id);
-extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker,
-						  const char *fmt, ...);
-#else /* CONFIG_SHRINKER_DEBUG */
-static inline int shrinker_debugfs_add(struct shrinker *shrinker)
-{
-	return 0;
-}
-static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
-						     int *debugfs_id)
+static inline bool shrinker_try_get(struct shrinker *shrinker)
 {
-	*debugfs_id = -1;
-	return NULL;
+	return refcount_inc_not_zero(&shrinker->refcount);
 }
-static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
-					   int debugfs_id)
+
+static inline void shrinker_put(struct shrinker *shrinker)
 {
+	if (refcount_dec_and_test(&shrinker->refcount))
+		complete(&shrinker->done);
 }
+
+#ifdef CONFIG_SHRINKER_DEBUG
+extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker,
+						  const char *fmt, ...);
+#else /* CONFIG_SHRINKER_DEBUG */
 static inline __printf(2, 3)
 int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 {
diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h
index c79f1d4c39af..23200aabccac 100644
--- a/include/trace/events/damon.h
+++ b/include/trace/events/damon.h
@@ -9,12 +9,51 @@
 #include <linux/types.h>
 #include <linux/tracepoint.h>
 
+TRACE_EVENT_CONDITION(damos_before_apply,
+
+	TP_PROTO(unsigned int context_idx, unsigned int scheme_idx,
+		unsigned int target_idx, struct damon_region *r,
+		unsigned int nr_regions, bool do_trace),
+
+	TP_ARGS(context_idx, target_idx, scheme_idx, r, nr_regions, do_trace),
+
+	TP_CONDITION(do_trace),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, context_idx)
+		__field(unsigned int, scheme_idx)
+		__field(unsigned long, target_idx)
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+		__field(unsigned int, nr_accesses)
+		__field(unsigned int, age)
+		__field(unsigned int, nr_regions)
+	),
+
+	TP_fast_assign(
+		__entry->context_idx = context_idx;
+		__entry->scheme_idx = scheme_idx;
+		__entry->target_idx = target_idx;
+		__entry->start = r->ar.start;
+		__entry->end = r->ar.end;
+		__entry->nr_accesses = r->nr_accesses_bp / 10000;
+		__entry->age = r->age;
+		__entry->nr_regions = nr_regions;
+	),
+
+	TP_printk("ctx_idx=%u scheme_idx=%u target_idx=%lu nr_regions=%u %lu-%lu: %u %u",
+			__entry->context_idx, __entry->scheme_idx,
+			__entry->target_idx, __entry->nr_regions,
+			__entry->start, __entry->end,
+			__entry->nr_accesses, __entry->age)
+);
+
 TRACE_EVENT(damon_aggregated,
 
-	TP_PROTO(struct damon_target *t, unsigned int target_id,
-		struct damon_region *r, unsigned int nr_regions),
+	TP_PROTO(unsigned int target_id, struct damon_region *r,
+		unsigned int nr_regions),
 
-	TP_ARGS(t, target_id, r, nr_regions),
+	TP_ARGS(target_id, r, nr_regions),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, target_id)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index d2123dd960d5..1a488c30afa5 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -285,10 +285,9 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		unsigned long nr_scanned,
 		unsigned long nr_skipped,
 		unsigned long nr_taken,
-		isolate_mode_t isolate_mode,
 		int lru),
 
-	TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru),
+	TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru),
 
 	TP_STRUCT__entry(
 		__field(int, highest_zoneidx)
@@ -297,7 +296,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_skipped)
 		__field(unsigned long, nr_taken)
-		__field(unsigned int, isolate_mode)
 		__field(int, lru)
 	),
 
@@ -308,7 +306,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_skipped = nr_skipped;
 		__entry->nr_taken = nr_taken;
-		__entry->isolate_mode = (__force unsigned int)isolate_mode;
 		__entry->lru = lru;
 	),
 
@@ -316,8 +313,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 	 * classzone is previous name of the highest_zoneidx.
 	 * Reason not to change it is the ABI requirement of the tracepoint.
 	 */
-	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s",
-		__entry->isolate_mode,
+	TP_printk("classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s",
 		__entry->highest_zoneidx,
 		__entry->order,
 		__entry->nr_requested,
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 3c36aeade991..370ed14b1ae0 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -283,7 +283,8 @@ struct prctl_mm_map {
 
 /* Memory deny write / execute */
 #define PR_SET_MDWE			65
-# define PR_MDWE_REFUSE_EXEC_GAIN	1
+# define PR_MDWE_REFUSE_EXEC_GAIN	(1UL << 0)
+# define PR_MDWE_NO_INHERIT		(1UL << 1)
 
 #define PR_GET_MDWE			66