Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - A few misc subsystems: kthread, scripts, ntfs, ocfs2, block, and vfs

 - Most the MM patches which precede the patches in Willy's tree: kasan,
   pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
   sparsemem, vmalloc, pagealloc, memory-failure, mlock, hugetlb,
   userfaultfd, vmscan, compaction, mempolicy, oom-kill, migration, thp,
   cma, autonuma, psi, ksm, page-poison, madvise, memory-hotplug, rmap,
   zswap, uaccess, ioremap, highmem, cleanups, kfence, hmm, and damon.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (227 commits)
  mm/damon/sysfs: remove repeat container_of() in damon_sysfs_kdamond_release()
  Docs/ABI/testing: add DAMON sysfs interface ABI document
  Docs/admin-guide/mm/damon/usage: document DAMON sysfs interface
  selftests/damon: add a test for DAMON sysfs interface
  mm/damon/sysfs: support DAMOS stats
  mm/damon/sysfs: support DAMOS watermarks
  mm/damon/sysfs: support schemes prioritization
  mm/damon/sysfs: support DAMOS quotas
  mm/damon/sysfs: support DAMON-based Operation Schemes
  mm/damon/sysfs: support the physical address space monitoring
  mm/damon/sysfs: link DAMON for virtual address spaces monitoring
  mm/damon: implement a minimal stub for sysfs-based DAMON interface
  mm/damon/core: add number of each enum type values
  mm/damon/core: allow non-exclusive DAMON start/stop
  Docs/damon: update outdated term 'regions update interval'
  Docs/vm/damon/design: update DAMON-Idle Page Tracking interference handling
  Docs/vm/damon: call low level monitoring primitives the operations
  mm/damon: remove unnecessary CONFIG_DAMON option
  mm/damon/paddr,vaddr: remove damon_{p,v}a_{target_valid,set_operations}()
  mm/damon/dbgfs-test: fix is_target_id() change
  ...

32 files changed, 365 insertions, 279 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 993c5628a726..e863c88df95f 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -207,14 +207,6 @@ struct backing_dev_info {
 #endif
 };
 
-enum {
-	BLK_RW_ASYNC	= 0,
-	BLK_RW_SYNC	= 1,
-};
-
-void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
-void set_bdi_congested(struct backing_dev_info *bdi, int sync);
-
 struct wb_lock_cookie {
 	bool locked;
 	unsigned long flags;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 483979c1b9f4..87ce24d238f3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -135,13 +135,6 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb)
 
 struct backing_dev_info *inode_to_bdi(struct inode *inode);
 
-static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
-{
-	return wb->congested & cong_bits;
-}
-
-long congestion_wait(int sync, long timeout);
-
 static inline bool mapping_can_writeback(struct address_space *mapping)
 {
 	return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK;
@@ -162,7 +155,6 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
 				    gfp_t gfp);
 void wb_memcg_offline(struct mem_cgroup *memcg);
 void wb_blkcg_offline(struct blkcg *blkcg);
-int inode_congested(struct inode *inode, int cong_bits);
 
 /**
  * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
@@ -390,50 +382,8 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg)
 {
 }
 
-static inline int inode_congested(struct inode *inode, int cong_bits)
-{
-	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
-}
-
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
-static inline int inode_read_congested(struct inode *inode)
-{
-	return inode_congested(inode, 1 << WB_sync_congested);
-}
-
-static inline int inode_write_congested(struct inode *inode)
-{
-	return inode_congested(inode, 1 << WB_async_congested);
-}
-
-static inline int inode_rw_congested(struct inode *inode)
-{
-	return inode_congested(inode, (1 << WB_sync_congested) |
-				      (1 << WB_async_congested));
-}
-
-static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits)
-{
-	return wb_congested(&bdi->wb, cong_bits);
-}
-
-static inline int bdi_read_congested(struct backing_dev_info *bdi)
-{
-	return bdi_congested(bdi, 1 << WB_sync_congested);
-}
-
-static inline int bdi_write_congested(struct backing_dev_info *bdi)
-{
-	return bdi_congested(bdi, 1 << WB_async_congested);
-}
-
-static inline int bdi_rw_congested(struct backing_dev_info *bdi)
-{
-	return bdi_congested(bdi, (1 << WB_sync_congested) |
-				  (1 << WB_async_congested));
-}
-
 const char *bdi_dev_name(struct backing_dev_info *bdi);
 
 #endif	/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/cma.h b/include/linux/cma.h
index bd801023504b..90fd742fd1ef 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -20,6 +20,14 @@
 
 #define CMA_MAX_NAME 64
 
+/*
+ * TODO: once the buddy -- especially pageblock merging and alloc_contig_range()
+ * -- can deal with only some pageblocks of a higher-order page being
+ *  MIGRATE_CMA, we can use pageblock_nr_pages.
+ */
+#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES
+#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES)
+
 struct cma;
 
 extern unsigned long totalcma_pages;
@@ -50,4 +58,6 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned
 extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count);
 
 extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data);
+
+extern void cma_reserve_pages_on_error(struct cma *cma);
 #endif
diff --git a/include/linux/damon.h b/include/linux/damon.h
index 5e1e3a128b77..f23cbfa4248d 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -60,19 +60,18 @@ struct damon_region {
 
 /**
  * struct damon_target - Represents a monitoring target.
- * @id:			Unique identifier for this target.
+ * @pid:		The PID of the virtual address space to monitor.
  * @nr_regions:		Number of monitoring target regions of this target.
  * @regions_list:	Head of the monitoring target regions of this target.
  * @list:		List head for siblings.
  *
  * Each monitoring context could have multiple targets.  For example, a context
  * for virtual memory address spaces could have multiple target processes.  The
- * @id of each target should be unique among the targets of the context.  For
- * example, in the virtual address monitoring context, it could be a pidfd or
- * an address of an mm_struct.
+ * @pid should be set for appropriate &struct damon_operations including the
+ * virtual address spaces monitoring operations.
  */
 struct damon_target {
-	unsigned long id;
+	struct pid *pid;
 	unsigned int nr_regions;
 	struct list_head regions_list;
 	struct list_head list;
@@ -88,6 +87,7 @@ struct damon_target {
  * @DAMOS_HUGEPAGE:	Call ``madvise()`` for the region with MADV_HUGEPAGE.
  * @DAMOS_NOHUGEPAGE:	Call ``madvise()`` for the region with MADV_NOHUGEPAGE.
  * @DAMOS_STAT:		Do nothing but count the stat.
+ * @NR_DAMOS_ACTIONS:	Total number of DAMOS actions
  */
 enum damos_action {
 	DAMOS_WILLNEED,
@@ -96,6 +96,7 @@ enum damos_action {
 	DAMOS_HUGEPAGE,
 	DAMOS_NOHUGEPAGE,
 	DAMOS_STAT,		/* Do nothing but only record the stat */
+	NR_DAMOS_ACTIONS,
 };
 
 /**
@@ -121,9 +122,9 @@ enum damos_action {
  * uses smaller one as the effective quota.
  *
  * For selecting regions within the quota, DAMON prioritizes current scheme's
- * target memory regions using the &struct damon_primitive->get_scheme_score.
+ * target memory regions using the &struct damon_operations->get_scheme_score.
  * You could customize the prioritization logic by setting &weight_sz,
- * &weight_nr_accesses, and &weight_age, because monitoring primitives are
+ * &weight_nr_accesses, and &weight_age, because monitoring operations are
  * encouraged to respect those.
  */
 struct damos_quota {
@@ -158,10 +159,12 @@ struct damos_quota {
  *
  * @DAMOS_WMARK_NONE:		Ignore the watermarks of the given scheme.
  * @DAMOS_WMARK_FREE_MEM_RATE:	Free memory rate of the system in [0,1000].
+ * @NR_DAMOS_WMARK_METRICS:	Total number of DAMOS watermark metrics
  */
 enum damos_wmark_metric {
 	DAMOS_WMARK_NONE,
 	DAMOS_WMARK_FREE_MEM_RATE,
+	NR_DAMOS_WMARK_METRICS,
 };
 
 /**
@@ -254,13 +257,26 @@ struct damos {
 	struct list_head list;
 };
 
+/**
+ * enum damon_ops_id - Identifier for each monitoring operations implementation
+ *
+ * @DAMON_OPS_VADDR:	Monitoring operations for virtual address spaces
+ * @DAMON_OPS_PADDR:	Monitoring operations for the physical address space
+ */
+enum damon_ops_id {
+	DAMON_OPS_VADDR,
+	DAMON_OPS_PADDR,
+	NR_DAMON_OPS,
+};
+
 struct damon_ctx;
 
 /**
- * struct damon_primitive - Monitoring primitives for given use cases.
+ * struct damon_operations - Monitoring operations for given use cases.
  *
- * @init:			Initialize primitive-internal data structures.
- * @update:			Update primitive-internal data structures.
+ * @id:				Identifier of this operations set.
+ * @init:			Initialize operations-related data structures.
+ * @update:			Update operations-related data structures.
  * @prepare_access_checks:	Prepare next access check of target regions.
  * @check_accesses:		Check the accesses to target regions.
  * @reset_aggregated:		Reset aggregated accesses monitoring results.
@@ -270,18 +286,20 @@ struct damon_ctx;
  * @cleanup:			Clean up the context.
  *
  * DAMON can be extended for various address spaces and usages.  For this,
- * users should register the low level primitives for their target address
- * space and usecase via the &damon_ctx.primitive.  Then, the monitoring thread
+ * users should register the low level operations for their target address
+ * space and usecase via the &damon_ctx.ops.  Then, the monitoring thread
  * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting
- * the monitoring, @update after each &damon_ctx.primitive_update_interval, and
+ * the monitoring, @update after each &damon_ctx.ops_update_interval, and
  * @check_accesses, @target_valid and @prepare_access_checks after each
  * &damon_ctx.sample_interval.  Finally, @reset_aggregated is called after each
  * &damon_ctx.aggr_interval.
  *
- * @init should initialize primitive-internal data structures.  For example,
+ * Each &struct damon_operations instance having valid @id can be registered
+ * via damon_register_ops() and selected by damon_select_ops() later.
+ * @init should initialize operations-related data structures.  For example,
  * this could be used to construct proper monitoring target regions and link
  * those to @damon_ctx.adaptive_targets.
- * @update should update the primitive-internal data structures.  For example,
+ * @update should update the operations-related data structures.  For example,
  * this could be used to update monitoring target regions for current status.
  * @prepare_access_checks should manipulate the monitoring regions to be
  * prepared for the next access check.
@@ -301,7 +319,8 @@ struct damon_ctx;
  * monitoring.
  * @cleanup is called from @kdamond just before its termination.
  */
-struct damon_primitive {
+struct damon_operations {
+	enum damon_ops_id id;
 	void (*init)(struct damon_ctx *context);
 	void (*update)(struct damon_ctx *context);
 	void (*prepare_access_checks)(struct damon_ctx *context);
@@ -355,15 +374,15 @@ struct damon_callback {
  *
  * @sample_interval:		The time between access samplings.
  * @aggr_interval:		The time between monitor results aggregations.
- * @primitive_update_interval:	The time between monitoring primitive updates.
+ * @ops_update_interval:	The time between monitoring operations updates.
  *
  * 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
- * @primitive_update_interval.  All time intervals are in micro-seconds.
- * Please refer to &struct damon_primitive and &struct damon_callback for more
+ * @ops_update_interval.  All time intervals are in micro-seconds.
+ * Please refer to &struct damon_operations and &struct damon_callback for more
  * detail.
  *
  * @kdamond:		Kernel thread who does the monitoring.
@@ -375,7 +394,7 @@ struct damon_callback {
  *
  * Once started, the monitoring thread runs until explicitly required to be
  * terminated or every monitoring target is invalid.  The validity of the
- * targets is checked via the &damon_primitive.target_valid of @primitive.  The
+ * targets is checked via the &damon_operations.target_valid of @ops.  The
  * termination can also be explicitly requested by writing non-zero to
  * @kdamond_stop.  The thread sets @kdamond to NULL when it terminates.
  * Therefore, users can know whether the monitoring is ongoing or terminated by
@@ -385,7 +404,7 @@ struct damon_callback {
  * Note that the monitoring thread protects only @kdamond and @kdamond_stop via
  * @kdamond_lock.  Accesses to other fields must be protected by themselves.
  *
- * @primitive:	Set of monitoring primitives for given use cases.
+ * @ops:	Set of monitoring operations for given use cases.
  * @callback:	Set of callbacks for monitoring events notifications.
  *
  * @min_nr_regions:	The minimum number of adaptive monitoring regions.
@@ -396,17 +415,17 @@ struct damon_callback {
 struct damon_ctx {
 	unsigned long sample_interval;
 	unsigned long aggr_interval;
-	unsigned long primitive_update_interval;
+	unsigned long ops_update_interval;
 
 /* private: internal use only */
 	struct timespec64 last_aggregation;
-	struct timespec64 last_primitive_update;
+	struct timespec64 last_ops_update;
 
 /* public: */
 	struct task_struct *kdamond;
 	struct mutex kdamond_lock;
 
-	struct damon_primitive primitive;
+	struct damon_operations ops;
 	struct damon_callback callback;
 
 	unsigned long min_nr_regions;
@@ -475,7 +494,7 @@ struct damos *damon_new_scheme(
 void damon_add_scheme(struct damon_ctx *ctx, struct damos *s);
 void damon_destroy_scheme(struct damos *s);
 
-struct damon_target *damon_new_target(unsigned long id);
+struct damon_target *damon_new_target(void);
 void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
 bool damon_targets_empty(struct damon_ctx *ctx);
 void damon_free_target(struct damon_target *t);
@@ -484,28 +503,18 @@ unsigned int damon_nr_regions(struct damon_target *t);
 
 struct damon_ctx *damon_new_ctx(void);
 void damon_destroy_ctx(struct damon_ctx *ctx);
-int damon_set_targets(struct damon_ctx *ctx,
-		unsigned long *ids, ssize_t nr_ids);
 int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
-		unsigned long aggr_int, unsigned long primitive_upd_int,
+		unsigned long aggr_int, unsigned long ops_upd_int,
 		unsigned long min_nr_reg, unsigned long max_nr_reg);
 int damon_set_schemes(struct damon_ctx *ctx,
 			struct damos **schemes, ssize_t nr_schemes);
 int damon_nr_running_ctxs(void);
+int damon_register_ops(struct damon_operations *ops);
+int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id);
 
-int damon_start(struct damon_ctx **ctxs, int nr_ctxs);
+int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
 
 #endif	/* CONFIG_DAMON */
 
-#ifdef CONFIG_DAMON_VADDR
-bool damon_va_target_valid(void *t);
-void damon_va_set_primitives(struct damon_ctx *ctx);
-#endif	/* CONFIG_DAMON_VADDR */
-
-#ifdef CONFIG_DAMON_PADDR
-bool damon_pa_target_valid(void *t);
-void damon_pa_set_primitives(struct damon_ctx *ctx);
-#endif	/* CONFIG_DAMON_PADDR */
-
 #endif	/* _DAMON_H */
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index e525f6957c49..2d04f6448cde 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -64,6 +64,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name,
 
 struct kmem_cache;
 
+bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
+
 int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #ifdef CONFIG_FAILSLAB
 extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 27746a3da8fd..4fb6d5a50be7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -42,6 +42,7 @@
 #include <linux/mount.h>
 #include <linux/cred.h>
 #include <linux/mnt_idmapping.h>
+#include <linux/slab.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -930,10 +931,15 @@ struct fown_struct {
  * struct file_ra_state - Track a file's readahead state.
  * @start: Where the most recent readahead started.
  * @size: Number of pages read in the most recent readahead.
- * @async_size: Start next readahead when this many pages are left.
- * @ra_pages: Maximum size of a readahead request.
+ * @async_size: Numer of pages that were/are not needed immediately
+ *      and so were/are genuinely "ahead".  Start next readahead when
+ *      the first of these pages is accessed.
+ * @ra_pages: Maximum size of a readahead request, copied from the bdi.
  * @mmap_miss: How many mmap accesses missed in the page cache.
  * @prev_pos: The last byte in the most recent read request.
+ *
+ * When this structure is passed to ->readahead(), the "most recent"
+ * readahead means the current readahead.
  */
 struct file_ra_state {
 	pgoff_t start;
@@ -1435,6 +1441,7 @@ extern int send_sigurg(struct fown_struct *fown);
 
 #define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
 #define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
+#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
 
 /* Possible states of 'frozen' field */
 enum {
@@ -3108,6 +3115,16 @@ extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_privs(struct file *);
 
+/*
+ * This must be used for allocating filesystems specific inodes to set
+ * up the inode reclaim context correctly.
+ */
+static inline void *
+alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp)
+{
+	return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp);
+}
+
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 static inline void insert_inode_hash(struct inode *inode)
 {
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 80f63c862be5..20f6fbe12993 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -79,7 +79,7 @@ struct vm_area_struct;
  * DOC: Page mobility and placement hints
  *
  * Page mobility and placement hints
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * ---------------------------------
  *
  * These flags provide hints about how mobile the page is. Pages with similar
  * mobility are placed within the same pageblocks to minimise problems due
@@ -112,7 +112,7 @@ struct vm_area_struct;
  * DOC: Watermark modifiers
  *
  * Watermark modifiers -- controls access to emergency reserves
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * ------------------------------------------------------------
  *
  * %__GFP_HIGH indicates that the caller is high-priority and that granting
  * the request is necessary before the system can make forward progress.
@@ -144,7 +144,7 @@ struct vm_area_struct;
  * DOC: Reclaim modifiers
  *
  * Reclaim modifiers
- * ~~~~~~~~~~~~~~~~~
+ * -----------------
  * Please note that all the following flags are only applicable to sleepable
  * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
  *
@@ -224,7 +224,7 @@ struct vm_area_struct;
  * DOC: Action modifiers
  *
  * Action modifiers
- * ~~~~~~~~~~~~~~~~
+ * ----------------
  *
  * %__GFP_NOWARN suppresses allocation failure reports.
  *
@@ -256,7 +256,7 @@ struct vm_area_struct;
  * DOC: Useful GFP flag combinations
  *
  * Useful GFP flag combinations
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * ----------------------------
  *
  * Useful GFP flag combinations that are commonly used. It is recommended
  * that subsystems start with one of these combinations and then set/clear
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 0a0b2b09b1b8..a77be5630209 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -246,6 +246,16 @@ do {								\
 	__kunmap_atomic(__addr);				\
 } while (0)
 
+/**
+ * kunmap_local - Unmap a page mapped via kmap_local_page().
+ * @__addr: An address within the page mapped
+ *
+ * @__addr can be any address within the mapped page.  Commonly it is the
+ * address return from kmap_local_page(), but it can also include offsets.
+ *
+ * Unmapping should be done in the reverse order of the mapping.  See
+ * kmap_local_page() for details.
+ */
 #define kunmap_local(__addr)					\
 do {								\
 	BUILD_BUG_ON(__same_type((__addr), struct page *));	\
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d1897a69c540..08357b4c7be7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -754,7 +754,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { }
 static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
 				       vm_flags_t flags)
 {
-	return entry;
+	return pte_mkhuge(entry);
 }
 #endif
 
@@ -1075,12 +1075,6 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 }
 #endif	/* CONFIG_HUGETLB_PAGE */
 
-#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
-extern bool hugetlb_free_vmemmap_enabled;
-#else
-#define hugetlb_free_vmemmap_enabled	false
-#endif
-
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
 					struct mm_struct *mm, pte_t *pte)
 {
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 3df4ea04716f..de5d75bafd66 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -141,12 +141,6 @@ struct kthread_delayed_work {
 	struct timer_list timer;
 };
 
-#define KTHREAD_WORKER_INIT(worker)	{				\
-	.lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock),		\
-	.work_list = LIST_HEAD_INIT((worker).work_list),		\
-	.delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\
-	}
-
 #define KTHREAD_WORK_INIT(work, fn)	{				\
 	.node = LIST_HEAD_INIT((work).node),				\
 	.func = (fn),							\
@@ -158,9 +152,6 @@ struct kthread_delayed_work {
 				     TIMER_IRQSAFE),			\
 	}
 
-#define DEFINE_KTHREAD_WORKER(worker)					\
-	struct kthread_worker worker = KTHREAD_WORKER_INIT(worker)
-
 #define DEFINE_KTHREAD_WORK(work, fn)					\
 	struct kthread_work work = KTHREAD_WORK_INIT(work, fn)
 
@@ -168,19 +159,6 @@ struct kthread_delayed_work {
 	struct kthread_delayed_work dwork =				\
 		KTHREAD_DELAYED_WORK_INIT(dwork, fn)
 
-/*
- * kthread_worker.lock needs its own lockdep class key when defined on
- * stack with lockdep enabled.  Use the following macros in such cases.
- */
-#ifdef CONFIG_LOCKDEP
-# define KTHREAD_WORKER_INIT_ONSTACK(worker)				\
-	({ kthread_init_worker(&worker); worker; })
-# define DEFINE_KTHREAD_WORKER_ONSTACK(worker)				\
-	struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker)
-#else
-# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker)
-#endif
-
 extern void __kthread_init_worker(struct kthread_worker *worker,
 			const char *name, struct lock_class_key *key);
 
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 1b5fceb565df..b35968ee9fb5 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/nodemask.h>
 #include <linux/shrinker.h>
+#include <linux/xarray.h>
 
 struct mem_cgroup;
 
@@ -33,8 +34,8 @@ struct list_lru_one {
 
 struct list_lru_memcg {
 	struct rcu_head		rcu;
-	/* array of per cgroup lists, indexed by memcg_cache_id */
-	struct list_lru_one	*lru[];
+	/* array of per cgroup per node lists, indexed by node id */
+	struct list_lru_one	node[];
 };
 
 struct list_lru_node {
@@ -42,11 +43,7 @@ struct list_lru_node {
 	spinlock_t		lock;
 	/* global list, used for the root cgroup in cgroup aware lrus */
 	struct list_lru_one	lru;
-#ifdef CONFIG_MEMCG_KMEM
-	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
-	struct list_lru_memcg	__rcu *memcg_lrus;
-#endif
-	long nr_items;
+	long			nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
@@ -55,6 +52,7 @@ struct list_lru {
 	struct list_head	list;
 	int			shrinker_id;
 	bool			memcg_aware;
+	struct xarray		xa;
 #endif
 };
 
@@ -69,8 +67,9 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 #define list_lru_init_memcg(lru, shrinker)		\
 	__list_lru_init((lru), true, NULL, shrinker)
 
-int memcg_update_all_list_lrus(int num_memcgs);
-void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg);
+int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
+			 gfp_t gfp);
+void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent);
 
 /**
  * list_lru_add: add an element to the lru list's tail
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0abbd685703b..a68dce3873fc 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -34,6 +34,7 @@ enum memcg_stat_item {
 	MEMCG_SOCK,
 	MEMCG_PERCPU_B,
 	MEMCG_VMALLOC,
+	MEMCG_KMEM,
 	MEMCG_NR_STAT,
 };
 
@@ -523,6 +524,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+retry:
+	memcg = obj_cgroup_memcg(objcg);
+	if (unlikely(!css_tryget(&memcg->css)))
+		goto retry;
+	rcu_read_unlock();
+
+	return memcg;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
@@ -841,9 +856,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
  */
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
-	if (!memcg->memory.parent)
-		return NULL;
-	return mem_cgroup_from_counter(memcg->memory.parent, memory);
+	return mem_cgroup_from_css(memcg->css.parent);
 }
 
 static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
@@ -1672,18 +1685,6 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
 
 extern struct static_key_false memcg_kmem_enabled_key;
 
-extern int memcg_nr_cache_ids;
-void memcg_get_cache_ids(void);
-void memcg_put_cache_ids(void);
-
-/*
- * Helper macro to loop through all memcg-specific caches. Callers must still
- * check if the cache is valid (it is either valid or NULL).
- * the slab_mutex must be held when looping through those caches
- */
-#define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
-
 static inline bool memcg_kmem_enabled(void)
 {
 	return static_branch_likely(&memcg_kmem_enabled_key);
@@ -1707,7 +1708,7 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order)
  * A helper for accessing memcg's kmem_id, used for getting
  * corresponding LRU lists.
  */
-static inline int memcg_cache_id(struct mem_cgroup *memcg)
+static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 {
 	return memcg ? memcg->kmemcg_id : -1;
 }
@@ -1740,27 +1741,16 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
 }
 
-#define for_each_memcg_cache_index(_idx)	\
-	for (; NULL; )
-
 static inline bool memcg_kmem_enabled(void)
 {
 	return false;
 }
 
-static inline int memcg_cache_id(struct mem_cgroup *memcg)
+static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 {
 	return -1;
 }
 
-static inline void memcg_get_cache_ids(void)
-{
-}
-
-static inline void memcg_put_cache_ids(void)
-{
-}
-
 static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
 {
        return NULL;
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 88eb587b5143..aa619464a1df 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -70,6 +70,13 @@ struct memory_block {
 	unsigned long state;		/* serialized by the dev->lock */
 	int online_type;		/* for passing data to online routine */
 	int nid;			/* NID for this memory block */
+	/*
+	 * The single zone of this memory block if all PFNs of this memory block
+	 * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are
+	 * managed by a single zone. NULL if multiple zones (including nodes)
+	 * apply.
+	 */
+	struct zone *zone;
 	struct device dev;
 	/*
 	 * Number of vmemmap pages. These pages
@@ -161,6 +168,11 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 })
 #define register_hotmemory_notifier(nb)		register_memory_notifier(nb)
 #define unregister_hotmemory_notifier(nb) 	unregister_memory_notifier(nb)
+
+#ifdef CONFIG_NUMA
+void memory_block_add_nid(struct memory_block *mem, int nid,
+			  enum meminit_context context);
+#endif /* CONFIG_NUMA */
 #endif	/* CONFIG_MEMORY_HOTPLUG */
 
 /*
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index be48e003a518..1ce6f8044f1e 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -16,6 +16,62 @@ struct memory_group;
 struct resource;
 struct vmem_altmap;
 
+#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
+/*
+ * For supporting node-hotadd, we have to allocate a new pgdat.
+ *
+ * If an arch has generic style NODE_DATA(),
+ * node_data[nid] = kzalloc() works well. But it depends on the architecture.
+ *
+ * In general, generic_alloc_nodedata() is used.
+ *
+ */
+extern pg_data_t *arch_alloc_nodedata(int nid);
+extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
+
+#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
+
+#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)
+
+#ifdef CONFIG_NUMA
+/*
+ * XXX: node aware allocation can't work well to get new node's memory at this time.
+ *	Because, pgdat for the new node is not allocated/initialized yet itself.
+ *	To use new node's memory, more consideration will be necessary.
+ */
+#define generic_alloc_nodedata(nid)				\
+({								\
+	memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES);	\
+})
+/*
+ * This definition is just for error path in node hotadd.
+ * For node hotremove, we have to replace this.
+ */
+#define generic_free_nodedata(pgdat)	kfree(pgdat)
+
+extern pg_data_t *node_data[];
+static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
+{
+	node_data[nid] = pgdat;
+}
+
+#else /* !CONFIG_NUMA */
+
+/* never called */
+static inline pg_data_t *generic_alloc_nodedata(int nid)
+{
+	BUG();
+	return NULL;
+}
+static inline void generic_free_nodedata(pg_data_t *pgdat)
+{
+}
+static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
+{
+}
+#endif /* CONFIG_NUMA */
+#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 struct page *pfn_to_online_page(unsigned long pfn);
 
@@ -107,8 +163,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
 extern int online_pages(unsigned long pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group);
-extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
-					 unsigned long end_pfn);
 extern void __offline_isolated_pages(unsigned long start_pfn,
 				     unsigned long end_pfn);
 
@@ -154,66 +208,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params);
 #endif /* ARCH_HAS_ADD_PAGES */
 
-#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
-/*
- * For supporting node-hotadd, we have to allocate a new pgdat.
- *
- * If an arch has generic style NODE_DATA(),
- * node_data[nid] = kzalloc() works well. But it depends on the architecture.
- *
- * In general, generic_alloc_nodedata() is used.
- * Now, arch_free_nodedata() is just defined for error path of node_hot_add.
- *
- */
-extern pg_data_t *arch_alloc_nodedata(int nid);
-extern void arch_free_nodedata(pg_data_t *pgdat);
-extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
-
-#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
-
-#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)
-#define arch_free_nodedata(pgdat)	generic_free_nodedata(pgdat)
-
-#ifdef CONFIG_NUMA
-/*
- * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
- * XXX: kmalloc_node() can't work well to get new node's memory at this time.
- *	Because, pgdat for the new node is not allocated/initialized yet itself.
- *	To use new node's memory, more consideration will be necessary.
- */
-#define generic_alloc_nodedata(nid)				\
-({								\
-	kzalloc(sizeof(pg_data_t), GFP_KERNEL);			\
-})
-/*
- * This definition is just for error path in node hotadd.
- * For node hotremove, we have to replace this.
- */
-#define generic_free_nodedata(pgdat)	kfree(pgdat)
-
-extern pg_data_t *node_data[];
-static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
-{
-	node_data[nid] = pgdat;
-}
-
-#else /* !CONFIG_NUMA */
-
-/* never called */
-static inline pg_data_t *generic_alloc_nodedata(int nid)
-{
-	BUG();
-	return NULL;
-}
-static inline void generic_free_nodedata(pg_data_t *pgdat)
-{
-}
-static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
-{
-}
-#endif /* CONFIG_NUMA */
-#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
-
 void get_online_mems(void);
 void put_online_mems(void);
 
@@ -297,7 +291,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 
 extern void try_offline_node(int nid);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-			 struct memory_group *group);
+			 struct zone *zone, struct memory_group *group);
 extern int remove_memory(u64 start, u64 size);
 extern void __remove_memory(u64 start, u64 size);
 extern int offline_and_remove_memory(u64 start, u64 size);
@@ -306,7 +300,7 @@ extern int offline_and_remove_memory(u64 start, u64 size);
 static inline void try_offline_node(int nid) {}
 
 static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-				struct memory_group *group)
+				struct zone *zone, struct memory_group *group)
 {
 	return -EINVAL;
 }
@@ -323,7 +317,7 @@ extern void set_zone_contiguous(struct zone *zone);
 extern void clear_zone_contiguous(struct zone *zone);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern void __ref free_area_init_core_hotplug(int nid);
+extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat);
 extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory_resource(int nid, struct resource *resource,
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index db96e10eb8da..90e75d5a54d6 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -48,7 +48,15 @@ int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
 
 extern bool numa_demotion_enabled;
+extern void migrate_on_reclaim_init(void);
+#ifdef CONFIG_HOTPLUG_CPU
+extern void set_migration_target_nodes(void);
 #else
+static inline void set_migration_target_nodes(void) {}
+#endif
+#else
+
+static inline void set_migration_target_nodes(void) {}
 
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t new,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5744a3fc4716..0e4fd101616e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -478,7 +478,8 @@ struct vm_fault {
 		struct vm_area_struct *vma;	/* Target VMA */
 		gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 		pgoff_t pgoff;			/* Logical page offset based on vma */
-		unsigned long address;		/* Faulting virtual address */
+		unsigned long address;		/* Faulting virtual address - masked */
+		unsigned long real_address;	/* Faulting virtual address - unmasked */
 	};
 	enum fault_flag flags;		/* FAULT_FLAG_xxx flags
 					 * XXX: should really be 'const' */
@@ -1916,10 +1917,6 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages,
 		    struct vm_area_struct **vmas);
-long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
-		    unsigned int gup_flags, struct page **pages, int *locked);
-long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
-		    unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
@@ -2453,7 +2450,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 }
 
 extern void __init pagecache_init(void);
-extern void __init free_area_init_memoryless_node(int nid);
 extern void free_initmem(void);
 
 /*
@@ -3151,10 +3147,12 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 }
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 int vmemmap_remap_free(unsigned long start, unsigned long end,
 		       unsigned long reuse);
 int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 			unsigned long reuse, gfp_t gfp_mask);
+#endif
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
@@ -3244,6 +3242,7 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
+	MF_MSG_DIFFERENT_PAGE_SIZE,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aed44e9b5d89..962b14d403e8 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -83,6 +83,17 @@ static inline bool is_migrate_movable(int mt)
 	return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE;
 }
 
+/*
+ * Check whether a migratetype can be merged with another migratetype.
+ *
+ * It is only mergeable when it can fall back to other migratetypes for
+ * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c.
+ */
+static inline bool migratetype_is_mergeable(int mt)
+{
+	return mt < MIGRATE_PCPTYPES;
+}
+
 #define for_each_migratetype_order(order, type) \
 	for (order = 0; order < MAX_ORDER; order++) \
 		for (type = 0; type < MIGRATE_TYPES; type++)
@@ -211,6 +222,9 @@ enum node_stat_item {
 #ifdef CONFIG_SWAP
 	NR_SWAPCACHE,
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	PGPROMOTE_SUCCESS,	/* promote successfully */
+#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
@@ -339,6 +353,7 @@ enum zone_watermarks {
 	WMARK_MIN,
 	WMARK_LOW,
 	WMARK_HIGH,
+	WMARK_PROMO,
 	NR_WMARK
 };
 
@@ -920,12 +935,6 @@ typedef struct pglist_data {
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
 #define node_spanned_pages(nid)	(NODE_DATA(nid)->node_spanned_pages)
-#ifdef CONFIG_FLATMEM
-#define pgdat_page_nr(pgdat, pagenr)	((pgdat)->node_mem_map + (pagenr))
-#else
-#define pgdat_page_nr(pgdat, pagenr)	pfn_to_page((pgdat)->node_start_pfn + (pagenr))
-#endif
-#define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
@@ -1101,7 +1110,6 @@ static inline struct pglist_data *NODE_DATA(int nid)
 {
 	return &contig_page_data;
 }
-#define NODE_MEM_MAP(nid)	mem_map
 
 #else /* CONFIG_NUMA */
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index ca0959e51e81..6aa2a200676a 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -138,6 +138,7 @@ struct nfs_server {
 	struct nlm_host		*nlm_host;	/* NLM client handle */
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
 	atomic_long_t		writeback;	/* number of writeback pages */
+	unsigned int		write_congested;/* flag set when writeback gets too high */
 	unsigned int		flags;		/* various flags */
 
 /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */
diff --git a/include/linux/node.h b/include/linux/node.h
index bb21fd631b16..40d641a8bfb0 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,19 +99,20 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
-void link_mem_sections(int nid, unsigned long start_pfn,
-		       unsigned long end_pfn,
-		       enum meminit_context context);
+void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+				       unsigned long end_pfn,
+				       enum meminit_context context);
 #else
-static inline void link_mem_sections(int nid, unsigned long start_pfn,
-				     unsigned long end_pfn,
-				     enum meminit_context context)
+static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+						     unsigned long end_pfn,
+						     enum meminit_context context)
 {
 }
 #endif
 
 extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
+extern void node_dev_init(void);
 /* Core of the node registration - only memory hotplug should use this */
 extern int __register_one_node(int nid);
 
@@ -128,8 +129,8 @@ static inline int register_one_node(int nid)
 		error = __register_one_node(nid);
 		if (error)
 			return error;
-		/* link memory sections under this node */
-		link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
+		register_memory_blocks_under_node(nid, start_pfn, end_pfn,
+						  MEMINIT_EARLY);
 	}
 
 	return error;
@@ -149,6 +150,9 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
 					 node_registration_func_t unregister);
 #endif
 #else
+static inline void node_dev_init(void)
+{
+}
 static inline int __register_one_node(int nid)
 {
 	return 0;
@@ -181,4 +185,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
 
 #define to_node(device) container_of(device, struct node, dev)
 
+static inline bool node_is_toptier(int node)
+{
+	return node_state(node, N_CPU);
+}
+
 #endif /* _LINUX_NODE_H_ */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1c3b6e5c8bfd..88fe1d759cdd 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -190,13 +190,81 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+			 hugetlb_free_vmemmap_enabled_key);
+
+static __always_inline bool hugetlb_free_vmemmap_enabled(void)
+{
+	return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
+				   &hugetlb_free_vmemmap_enabled_key);
+}
+
+/*
+ * If the feature of freeing some vmemmap pages associated with each HugeTLB
+ * page is enabled, the head vmemmap page frame is reused and all of the tail
+ * vmemmap addresses map to the head vmemmap page frame (furture details can
+ * refer to the figure at the head of the mm/hugetlb_vmemmap.c).  In other
+ * words, there are more than one page struct with PG_head associated with each
+ * HugeTLB page.  We __know__ that there is only one head page struct, the tail
+ * page structs with PG_head are fake head page structs.  We need an approach
+ * to distinguish between those two different types of page structs so that
+ * compound_head() can return the real head page struct when the parameter is
+ * the tail page struct but with PG_head.
+ *
+ * The page_fixed_fake_head() returns the real head page struct if the @page is
+ * fake page head, otherwise, returns @page which can either be a true page
+ * head or tail.
+ */
+static __always_inline const struct page *page_fixed_fake_head(const struct page *page)
+{
+	if (!hugetlb_free_vmemmap_enabled())
+		return page;
+
+	/*
+	 * Only addresses aligned with PAGE_SIZE of struct page may be fake head
+	 * struct page. The alignment check aims to avoid access the fields (
+	 * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly)
+	 * cold cacheline in some cases.
+	 */
+	if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) &&
+	    test_bit(PG_head, &page->flags)) {
+		/*
+		 * We can safely access the field of the @page[1] with PG_head
+		 * because the @page is a compound page composed with at least
+		 * two contiguous pages.
+		 */
+		unsigned long head = READ_ONCE(page[1].compound_head);
+
+		if (likely(head & 1))
+			return (const struct page *)(head - 1);
+	}
+	return page;
+}
+#else
+static inline const struct page *page_fixed_fake_head(const struct page *page)
+{
+	return page;
+}
+
+static inline bool hugetlb_free_vmemmap_enabled(void)
+{
+	return false;
+}
+#endif
+
+static __always_inline int page_is_fake_head(struct page *page)
+{
+	return page_fixed_fake_head(page) != page;
+}
+
 static inline unsigned long _compound_head(const struct page *page)
 {
 	unsigned long head = READ_ONCE(page->compound_head);
 
 	if (unlikely(head & 1))
 		return head - 1;
-	return (unsigned long)page;
+	return (unsigned long)page_fixed_fake_head(page);
 }
 
 #define compound_head(page)	((typeof(page))_compound_head(page))
@@ -231,12 +299,13 @@ static inline unsigned long _compound_head(const struct page *page)
 
 static __always_inline int PageTail(struct page *page)
 {
-	return READ_ONCE(page->compound_head) & 1;
+	return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page);
 }
 
 static __always_inline int PageCompound(struct page *page)
 {
-	return test_bit(PG_head, &page->flags) || PageTail(page);
+	return test_bit(PG_head, &page->flags) ||
+	       READ_ONCE(page->compound_head) & 1;
 }
 
 #define	PAGE_POISON_PATTERN	-1l
@@ -695,7 +764,20 @@ static inline bool test_set_page_writeback(struct page *page)
 	return set_page_writeback(page);
 }
 
-__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
+static __always_inline bool folio_test_head(struct folio *folio)
+{
+	return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY));
+}
+
+static __always_inline int PageHead(struct page *page)
+{
+	PF_POISONED_CHECK(page);
+	return test_bit(PG_head, &page->flags) && !page_is_fake_head(page);
+}
+
+__SETPAGEFLAG(Head, head, PF_ANY)
+__CLEARPAGEFLAG(Head, head, PF_ANY)
+CLEARPAGEFLAG(Head, head, PF_ANY)
 
 /**
  * folio_test_large() - Does this folio contain more than one page?
@@ -918,7 +1000,7 @@ PAGE_TYPE_OPS(Guard, guard)
 
 extern bool is_free_buddy_page(struct page *page);
 
-__PAGEFLAG(Isolated, isolated, PF_ANY);
+PAGEFLAG(Isolated, isolated, PF_ANY);
 
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1UL << PG_mlocked)
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 973fd731a520..83c7248053a1 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -37,8 +37,11 @@ extern unsigned int pageblock_order;
 
 #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-/* Huge pages are a constant size */
-#define pageblock_order		HUGETLB_PAGE_ORDER
+/*
+ * Huge pages are a constant size, but don't exceed the maximum allocation
+ * granularity.
+ */
+#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 270bf5136c34..dc31eb981ea2 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -594,13 +594,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 			pgoff_t end, unsigned int nr_pages,
 			struct page **pages);
-static inline unsigned find_get_pages(struct address_space *mapping,
-			pgoff_t *start, unsigned int nr_pages,
-			struct page **pages)
-{
-	return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages,
-				    pages);
-}
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
 			       unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index fee34a8a8fe8..ff6901dcb06d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1708,7 +1708,6 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 3f2b70f8d32c..c1076b5e17fb 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -23,6 +23,16 @@ enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_END,
 };
 
+#define NUMA_BALANCING_DISABLED		0x0
+#define NUMA_BALANCING_NORMAL		0x1
+#define NUMA_BALANCING_MEMORY_TIERING	0x2
+
+#ifdef CONFIG_NUMA_BALANCING
+extern int sysctl_numa_balancing_mode;
+#else
+#define sysctl_numa_balancing_mode	0
+#endif
+
 /*
  *  control realtime throttling:
  *
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index e65b80ed09e7..ab51d3cd39bd 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -24,6 +24,7 @@ struct shmem_inode_info {
 	struct shared_policy	policy;		/* NUMA memory alloc policy */
 	struct simple_xattrs	xattrs;		/* list of xattrs */
 	atomic_t		stop_eviction;	/* hold when working on inode */
+	struct timespec64	i_crtime;	/* file creation time */
 	struct inode		vfs_inode;
 };
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 5b6193fd8bd9..e6addaf91afd 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -135,6 +135,7 @@
 
 #include <linux/kasan.h>
 
+struct list_lru;
 struct mem_cgroup;
 /*
  * struct kmem_cache related prototypes
@@ -416,6 +417,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size,
 
 void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1);
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc;
+void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
+			   gfp_t gfpflags) __assume_slab_alignment __malloc;
 void kmem_cache_free(struct kmem_cache *s, void *objp);
 
 /*
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 1d38d9475c4d..a246c137678e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -334,9 +334,12 @@ void workingset_activation(struct folio *folio);
 
 /* Only track the nodes of mappings with shadow entries */
 void workingset_update_node(struct xa_node *node);
+extern struct list_lru shadow_nodes;
 #define mapping_set_update(xas, mapping) do {				\
-	if (!dax_mapping(mapping) && !shmem_mapping(mapping))		\
+	if (!dax_mapping(mapping) && !shmem_mapping(mapping)) {		\
 		xas_set_update(xas, workingset_update_node);		\
+		xas_set_lru(xas, &shadow_nodes);			\
+	}								\
 } while (0)
 
 /* linux/mm/page_alloc.c */
@@ -384,7 +387,6 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
-extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 73a6f34b3847..9f392ec76f2b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -209,9 +209,12 @@ __bad_copy_from(void);
 extern void __compiletime_error("copy destination size is too small")
 __bad_copy_to(void);
 
+void __copy_overflow(int size, unsigned long count);
+
 static inline void copy_overflow(int size, unsigned long count)
 {
-	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+	if (IS_ENABLED(CONFIG_BUG))
+		__copy_overflow(size, count);
 }
 
 static __always_inline __must_check bool
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ac0394087f7d..bca27b4e5eb2 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -401,8 +401,6 @@ static inline void user_access_restore(unsigned long flags) { }
 #endif
 
 #ifdef CONFIG_HARDENED_USERCOPY
-void usercopy_warn(const char *name, const char *detail, bool to_user,
-		   unsigned long offset, unsigned long len);
 void __noreturn usercopy_abort(const char *name, const char *detail,
 			       bool to_user, unsigned long offset,
 			       unsigned long len);
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 7b2363388bfa..16a0a4fd000b 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -129,6 +129,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_SWAP
 		SWAP_RA,
 		SWAP_RA_HIT,
+#ifdef CONFIG_KSM
+		KSM_SWPIN_COPY,
+#endif
 #endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 880227b9f044..05065915edd7 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -80,8 +80,8 @@ struct vmap_area {
 	/*
 	 * The following two variables can be packed, because
 	 * a vmap_area object can be either:
-	 *    1) in "free" tree (root is vmap_area_root)
-	 *    2) or "busy" tree (root is free_vmap_area_root)
+	 *    1) in "free" tree (root is free_vmap_area_root)
+	 *    2) or "busy" tree (root is vmap_area_root)
 	 */
 	union {
 		unsigned long subtree_max_size; /* in "free" tree */
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index d6d5da6ed735..bb52b786be1b 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1317,6 +1317,7 @@ struct xa_state {
 	struct xa_node *xa_node;
 	struct xa_node *xa_alloc;
 	xa_update_node_t xa_update;
+	struct list_lru *xa_lru;
 };
 
 /*
@@ -1336,7 +1337,8 @@ struct xa_state {
 	.xa_pad = 0,					\
 	.xa_node = XAS_RESTART,				\
 	.xa_alloc = NULL,				\
-	.xa_update = NULL				\
+	.xa_update = NULL,				\
+	.xa_lru = NULL,					\
 }
 
 /**
@@ -1631,6 +1633,11 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update)
 	xas->xa_update = update;
 }
 
+static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru)
+{
+	xas->xa_lru = lru;
+}
+
 /**
  * xas_next_entry() - Advance iterator to next present entry.
  * @xas: XArray operation state.