14 files changed, 396 insertions, 50 deletions

diff --git a/include/linux/damon.h b/include/linux/damon.h
new file mode 100644
index 000000000000..d68b67b8d458
--- /dev/null
+++ b/include/linux/damon.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DAMON api
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifndef _DAMON_H_
+#define _DAMON_H_
+
+#include <linux/mutex.h>
+#include <linux/time64.h>
+#include <linux/types.h>
+
+/* Minimal region size.  Every damon_region is aligned by this. */
+#define DAMON_MIN_REGION	PAGE_SIZE
+
+/**
+ * struct damon_addr_range - Represents an address region of [@start, @end).
+ * @start:	Start address of the region (inclusive).
+ * @end:	End address of the region (exclusive).
+ */
+struct damon_addr_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+/**
+ * struct damon_region - Represents a monitoring target region.
+ * @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.
+ * @list:		List head for siblings.
+ */
+struct damon_region {
+	struct damon_addr_range ar;
+	unsigned long sampling_addr;
+	unsigned int nr_accesses;
+	struct list_head list;
+};
+
+/**
+ * struct damon_target - Represents a monitoring target.
+ * @id:			Unique identifier for this target.
+ * @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.
+ */
+struct damon_target {
+	unsigned long id;
+	unsigned int nr_regions;
+	struct list_head regions_list;
+	struct list_head list;
+};
+
+struct damon_ctx;
+
+/**
+ * struct damon_primitive	Monitoring primitives for given use cases.
+ *
+ * @init:			Initialize primitive-internal data structures.
+ * @update:			Update primitive-internal 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.
+ * @target_valid:		Determine if the target is valid.
+ * @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
+ * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting
+ * the monitoring, @update after each &damon_ctx.primitive_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,
+ * 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,
+ * 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.
+ * @check_accesses should check the accesses to each region that made after the
+ * last preparation and update the number of observed accesses of each region.
+ * It should also return max number of observed accesses that made as a result
+ * of its update.  The value will be used for regions adjustment threshold.
+ * @reset_aggregated should reset the access monitoring results that aggregated
+ * by @check_accesses.
+ * @target_valid should check whether the target is still valid for the
+ * monitoring.
+ * @cleanup is called from @kdamond just before its termination.
+ */
+struct damon_primitive {
+	void (*init)(struct damon_ctx *context);
+	void (*update)(struct damon_ctx *context);
+	void (*prepare_access_checks)(struct damon_ctx *context);
+	unsigned int (*check_accesses)(struct damon_ctx *context);
+	void (*reset_aggregated)(struct damon_ctx *context);
+	bool (*target_valid)(void *target);
+	void (*cleanup)(struct damon_ctx *context);
+};
+
+/*
+ * struct damon_callback	Monitoring events notification callbacks.
+ *
+ * @before_start:	Called before starting the monitoring.
+ * @after_sampling:	Called after each sampling.
+ * @after_aggregation:	Called after each aggregation.
+ * @before_terminate:	Called before terminating the monitoring.
+ * @private:		User private data.
+ *
+ * The monitoring thread (&damon_ctx.kdamond) calls @before_start and
+ * @before_terminate just before starting and finishing the monitoring,
+ * respectively.  Therefore, those are good places for installing and cleaning
+ * @private.
+ *
+ * The monitoring thread calls @after_sampling and @after_aggregation for each
+ * of the sampling intervals and aggregation intervals, respectively.
+ * Therefore, users can safely access the monitoring results without additional
+ * protection.  For the reason, users are recommended to use these callback for
+ * the accesses to the results.
+ *
+ * If any callback returns non-zero, monitoring stops.
+ */
+struct damon_callback {
+	void *private;
+
+	int (*before_start)(struct damon_ctx *context);
+	int (*after_sampling)(struct damon_ctx *context);
+	int (*after_aggregation)(struct damon_ctx *context);
+	int (*before_terminate)(struct damon_ctx *context);
+};
+
+/**
+ * struct damon_ctx - Represents a context for each monitoring.  This is the
+ * main interface that allows users to set the attributes and get the results
+ * of the monitoring.
+ *
+ * @sample_interval:		The time between access samplings.
+ * @aggr_interval:		The time between monitor results aggregations.
+ * @primitive_update_interval:	The time between monitoring primitive 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
+ * detail.
+ *
+ * @kdamond:		Kernel thread who does the monitoring.
+ * @kdamond_stop:	Notifies whether kdamond should stop.
+ * @kdamond_lock:	Mutex for the synchronizations with @kdamond.
+ *
+ * For each monitoring context, one kernel thread for the monitoring is
+ * created.  The pointer to the thread is stored in @kdamond.
+ *
+ * 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
+ * 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
+ * reading @kdamond.  Reads and writes to @kdamond and @kdamond_stop from
+ * outside of the monitoring thread must be protected by @kdamond_lock.
+ *
+ * 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.
+ * @callback:	Set of callbacks for monitoring events notifications.
+ *
+ * @min_nr_regions:	The minimum number of adaptive monitoring regions.
+ * @max_nr_regions:	The maximum number of adaptive monitoring regions.
+ * @adaptive_targets:	Head of monitoring targets (&damon_target) list.
+ */
+struct damon_ctx {
+	unsigned long sample_interval;
+	unsigned long aggr_interval;
+	unsigned long primitive_update_interval;
+
+/* private: internal use only */
+	struct timespec64 last_aggregation;
+	struct timespec64 last_primitive_update;
+
+/* public: */
+	struct task_struct *kdamond;
+	bool kdamond_stop;
+	struct mutex kdamond_lock;
+
+	struct damon_primitive primitive;
+	struct damon_callback callback;
+
+	unsigned long min_nr_regions;
+	unsigned long max_nr_regions;
+	struct list_head adaptive_targets;
+};
+
+#define damon_next_region(r) \
+	(container_of(r->list.next, struct damon_region, list))
+
+#define damon_prev_region(r) \
+	(container_of(r->list.prev, struct damon_region, list))
+
+#define damon_for_each_region(r, t) \
+	list_for_each_entry(r, &t->regions_list, list)
+
+#define damon_for_each_region_safe(r, next, t) \
+	list_for_each_entry_safe(r, next, &t->regions_list, list)
+
+#define damon_for_each_target(t, ctx) \
+	list_for_each_entry(t, &(ctx)->adaptive_targets, list)
+
+#define damon_for_each_target_safe(t, next, ctx)	\
+	list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list)
+
+#ifdef CONFIG_DAMON
+
+struct damon_region *damon_new_region(unsigned long start, unsigned long end);
+inline void damon_insert_region(struct damon_region *r,
+		struct damon_region *prev, struct damon_region *next,
+		struct damon_target *t);
+void damon_add_region(struct damon_region *r, struct damon_target *t);
+void damon_destroy_region(struct damon_region *r, struct damon_target *t);
+
+struct damon_target *damon_new_target(unsigned long id);
+void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
+void damon_free_target(struct damon_target *t);
+void damon_destroy_target(struct damon_target *t);
+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 min_nr_reg, unsigned long max_nr_reg);
+int damon_nr_running_ctxs(void);
+
+int damon_start(struct damon_ctx **ctxs, int nr_ctxs);
+int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+
+#endif	/* CONFIG_DAMON */
+
+#ifdef CONFIG_DAMON_VADDR
+
+/* Monitoring primitives for virtual memory address spaces */
+void damon_va_init(struct damon_ctx *ctx);
+void damon_va_update(struct damon_ctx *ctx);
+void damon_va_prepare_access_checks(struct damon_ctx *ctx);
+unsigned int damon_va_check_accesses(struct damon_ctx *ctx);
+bool damon_va_target_valid(void *t);
+void damon_va_cleanup(struct damon_ctx *ctx);
+void damon_va_set_primitives(struct damon_ctx *ctx);
+
+#endif	/* CONFIG_DAMON_VADDR */
+
+#endif	/* _DAMON_H */
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 7902c7d8b55f..4aa1031d3e4c 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -90,7 +90,11 @@ static inline void __kunmap_local(void *vaddr)
 
 static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
+
 	pagefault_disable();
 	return __kmap_local_page_prot(page, prot);
 }
@@ -102,7 +106,11 @@ static inline void *kmap_atomic(struct page *page)
 
 static inline void *kmap_atomic_pfn(unsigned long pfn)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
+
 	pagefault_disable();
 	return __kmap_local_pfn_prot(pfn, kmap_prot);
 }
@@ -111,7 +119,10 @@ static inline void __kunmap_atomic(void *addr)
 {
 	kunmap_local_indexed(addr);
 	pagefault_enable();
-	preempt_enable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_enable();
+	else
+		preempt_enable();
 }
 
 unsigned int __nr_free_highpages(void);
@@ -179,7 +190,10 @@ static inline void __kunmap_local(void *addr)
 
 static inline void *kmap_atomic(struct page *page)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -200,7 +214,10 @@ static inline void __kunmap_atomic(void *addr)
 	kunmap_flush_on_unmap(addr);
 #endif
 	pagefault_enable();
-	preempt_enable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_enable();
+	else
+		preempt_enable();
 }
 
 static inline unsigned int nr_free_highpages(void) { return 0; }
diff --git a/include/linux/memory.h b/include/linux/memory.h
index d9a0b61cd432..7efc0a7c14c9 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -23,6 +23,48 @@
 
 #define MIN_MEMORY_BLOCK_SIZE     (1UL << SECTION_SIZE_BITS)
 
+/**
+ * struct memory_group - a logical group of memory blocks
+ * @nid: The node id for all memory blocks inside the memory group.
+ * @blocks: List of all memory blocks belonging to this memory group.
+ * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this
+ *			  memory group.
+ * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this
+ *			   memory group.
+ * @is_dynamic: The memory group type: static vs. dynamic
+ * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum
+ *		 number of pages we'll have in this static memory group.
+ * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages
+ *		  in which memory is added/removed in this dynamic memory group.
+ *		  This granularity defines the alignment of a unit in physical
+ *		  address space; it has to be at least as big as a single
+ *		  memory block.
+ *
+ * A memory group logically groups memory blocks; each memory block
+ * belongs to at most one memory group. A memory group corresponds to
+ * a memory device, such as a DIMM or a NUMA node, which spans multiple
+ * memory blocks and might even span multiple non-contiguous physical memory
+ * ranges.
+ *
+ * Modification of members after registration is serialized by memory
+ * hot(un)plug code.
+ */
+struct memory_group {
+	int nid;
+	struct list_head memory_blocks;
+	unsigned long present_kernel_pages;
+	unsigned long present_movable_pages;
+	bool is_dynamic;
+	union {
+		struct {
+			unsigned long max_pages;
+		} s;
+		struct {
+			unsigned long unit_pages;
+		} d;
+	};
+};
+
 struct memory_block {
 	unsigned long start_section_nr;
 	unsigned long state;		/* serialized by the dev->lock */
@@ -34,6 +76,8 @@ struct memory_block {
 	 * lay at the beginning of the memory block.
 	 */
 	unsigned long nr_vmemmap_pages;
+	struct memory_group *group;	/* group (if any) for this block */
+	struct list_head group_next;	/* next block inside memory group */
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -86,7 +130,8 @@ static inline int memory_notify(unsigned long val, void *v)
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages);
+				unsigned long vmemmap_pages,
+				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
@@ -96,6 +141,14 @@ extern int walk_memory_blocks(unsigned long start, unsigned long size,
 			      void *arg, walk_memory_blocks_func_t func);
 extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
 #define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
+
+extern int memory_group_register_static(int nid, unsigned long max_pages);
+extern int memory_group_register_dynamic(int nid, unsigned long unit_pages);
+extern int memory_group_unregister(int mgid);
+struct memory_group *memory_group_find_by_id(int mgid);
+typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+			       struct memory_group *excluded, void *arg);
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index a7fd2c3ccb77..e5a867c950b2 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -12,6 +12,7 @@ struct zone;
 struct pglist_data;
 struct mem_section;
 struct memory_block;
+struct memory_group;
 struct resource;
 struct vmem_altmap;
 
@@ -50,6 +51,11 @@ typedef int __bitwise mhp_t;
  * Only selected architectures support it with SPARSE_VMEMMAP.
  */
 #define MHP_MEMMAP_ON_MEMORY   ((__force mhp_t)BIT(1))
+/*
+ * The nid field specifies a memory group id (mgid) instead. The memory group
+ * implies the node id (nid).
+ */
+#define MHP_NID_IS_MGID		((__force mhp_t)BIT(2))
 
 /*
  * Extended parameters for memory hotplug:
@@ -95,13 +101,15 @@ static inline void zone_seqlock_init(struct zone *zone)
 extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
-extern void adjust_present_page_count(struct zone *zone, long nr_pages);
+extern void adjust_present_page_count(struct page *page,
+				      struct memory_group *group,
+				      long nr_pages);
 /* VM interface that may be used by firmware interface */
 extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 				     struct zone *zone);
 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 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,
@@ -130,8 +138,7 @@ static inline bool movable_node_is_enabled(void)
 	return movable_node_enabled;
 }
 
-extern void arch_remove_memory(int nid, u64 start, u64 size,
-			       struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
 extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
 			   struct vmem_altmap *altmap);
 
@@ -292,25 +299,27 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern void try_offline_node(int nid);
-extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern int remove_memory(int nid, u64 start, u64 size);
-extern void __remove_memory(int nid, u64 start, u64 size);
-extern int offline_and_remove_memory(int nid, u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+			 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);
 
 #else
 static inline void try_offline_node(int nid) {}
 
-static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+				struct memory_group *group)
 {
 	return -EINVAL;
 }
 
-static inline int remove_memory(int nid, u64 start, u64 size)
+static inline int remove_memory(u64 start, u64 size)
 {
 	return -EBUSY;
 }
 
-static inline void __remove_memory(int nid, u64 start, u64 size) {}
+static inline void __remove_memory(u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 extern void set_zone_contiguous(struct zone *zone);
@@ -339,7 +348,8 @@ extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long map_offset, struct vmem_altmap *altmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
+extern struct zone *zone_for_pfn_range(int online_type, int nid,
+		struct memory_group *group, unsigned long start_pfn,
 		unsigned long nr_pages);
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1bd5f5955f9a..6a1d79d84675 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -540,6 +540,10 @@ struct zone {
 	 * is calculated as:
 	 *	present_pages = spanned_pages - absent_pages(pages in holes);
 	 *
+	 * present_early_pages is present pages existing within the zone
+	 * located on memory available since early boot, excluding hotplugged
+	 * memory.
+	 *
 	 * managed_pages is present pages managed by the buddy system, which
 	 * is calculated as (reserved_pages includes pages allocated by the
 	 * bootmem allocator):
@@ -572,6 +576,9 @@ struct zone {
 	atomic_long_t		managed_pages;
 	unsigned long		spanned_pages;
 	unsigned long		present_pages;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+	unsigned long		present_early_pages;
+#endif
 #ifdef CONFIG_CMA
 	unsigned long		cma_pages;
 #endif
@@ -1525,18 +1532,6 @@ void sparse_init(void);
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
-/*
- * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
- * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
- * pfn_valid_within() should be used in this case; we optimise this away
- * when we have no holes within a MAX_ORDER_NR_PAGES block.
- */
-#ifdef CONFIG_HOLES_IN_ZONE
-#define pfn_valid_within(pfn) pfn_valid(pfn)
-#else
-#define pfn_valid_within(pfn) (1)
-#endif
-
 #endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* _LINUX_MMZONE_H */
diff --git a/include/linux/once.h b/include/linux/once.h
index ae6f4eb41cbe..d361fb14ac3a 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -16,7 +16,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key,
  * out the condition into a nop. DO_ONCE() guarantees type safety of
  * arguments!
  *
- * Not that the following is not equivalent ...
+ * Note that the following is not equivalent ...
  *
  *   DO_ONCE(func, arg);
  *   DO_ONCE(func, arg);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4ca160053b1f..a558d67ee86f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -131,7 +131,7 @@ enum pageflags {
 #ifdef CONFIG_MEMORY_FAILURE
 	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
 	PG_young,
 	PG_idle,
 #endif
@@ -178,6 +178,8 @@ enum pageflags {
 	PG_reported = PG_uptodate,
 };
 
+#define PAGEFLAGS_MASK		((1UL << NR_PAGEFLAGS) - 1)
+
 #ifndef __GENERATING_BOUNDS_H
 
 static inline unsigned long _compound_head(const struct page *page)
@@ -439,7 +441,7 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
 TESTPAGEFLAG(Young, young, PF_ANY)
 SETPAGEFLAG(Young, young, PF_ANY)
 TESTCLEARFLAG(Young, young, PF_ANY)
@@ -831,7 +833,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
  * alloc-free cycle to prevent from reusing the page.
  */
 #define PAGE_FLAGS_CHECK_AT_PREP	\
-	(((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
+	(PAGEFLAGS_MASK & ~__PG_HWPOISON)
 
 #define PAGE_FLAGS_PRIVATE				\
 	(1UL << PG_private | 1UL << PG_private_2)
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index aff81ba31bd8..fabb2e1e087f 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -19,7 +19,7 @@ struct page_ext_operations {
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
 	PAGE_EXT_OWNER_ALLOCATED,
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
 #endif
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index 1e894d34bdce..d8a6aecf99cb 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -6,7 +6,7 @@
 #include <linux/page-flags.h>
 #include <linux/page_ext.h>
 
-#ifdef CONFIG_IDLE_PAGE_TRACKING
+#ifdef CONFIG_PAGE_IDLE_FLAG
 
 #ifdef CONFIG_64BIT
 static inline bool page_is_young(struct page *page)
@@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page)
 }
 #endif /* CONFIG_64BIT */
 
-#else /* !CONFIG_IDLE_PAGE_TRACKING */
+#else /* !CONFIG_PAGE_IDLE_FLAG */
 
 static inline bool page_is_young(struct page *page)
 {
@@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page)
 {
 }
 
-#endif /* CONFIG_IDLE_PAGE_TRACKING */
+#endif /* CONFIG_PAGE_IDLE_FLAG */
 
 #endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5dcf446f42e5..62db6b0176b9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -521,18 +521,17 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
  */
 static inline pgoff_t page_to_index(struct page *page)
 {
-	pgoff_t pgoff;
+	struct page *head;
 
 	if (likely(!PageTransTail(page)))
 		return page->index;
 
+	head = compound_head(page);
 	/*
 	 *  We don't initialize ->index for tail pages: calculate based on
 	 *  head page
 	 */
-	pgoff = compound_head(page)->index;
-	pgoff += page - compound_head(page);
-	return pgoff;
+	return head->index + page - head;
 }
 
 extern pgoff_t hugetlb_basepage_index(struct page *page);
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 2462f7d07695..00ed419dd464 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -4,6 +4,7 @@
 
 #include <linux/uidgid.h>
 #include <linux/atomic.h>
+#include <linux/percpu_counter.h>
 #include <linux/refcount.h>
 #include <linux/ratelimit.h>
 
@@ -13,7 +14,7 @@
 struct user_struct {
 	refcount_t __count;	/* reference count */
 #ifdef CONFIG_EPOLL
-	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
+	struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */
 #endif
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
diff --git a/include/linux/threads.h b/include/linux/threads.h
index 18d5a74bcc3d..c34173e6c5f1 100644
--- a/include/linux/threads.h
+++ b/include/linux/threads.h
@@ -38,7 +38,7 @@
  * Define a minimum number of pids per cpu.  Heuristically based
  * on original pid max of 32k for 32 cpus.  Also, increase the
  * minimum settable value for pid_max on the running system based
- * on similar defaults.  See kernel/pid.c:pidmap_init() for details.
+ * on similar defaults.  See kernel/pid.c:pid_idr_init() for details.
  */
 #define PIDS_PER_CPU_DEFAULT	1024
 #define PIDS_PER_CPU_MIN	8
diff --git a/include/linux/units.h b/include/linux/units.h
index 4a25e0cc8fb3..681fc652e3d7 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -20,9 +20,13 @@
 #define PICO	1000000000000ULL
 #define FEMTO	1000000000000000ULL
 
-#define MILLIWATT_PER_WATT	1000L
-#define MICROWATT_PER_MILLIWATT	1000L
-#define MICROWATT_PER_WATT	1000000L
+#define HZ_PER_KHZ		1000UL
+#define KHZ_PER_MHZ		1000UL
+#define HZ_PER_MHZ		1000000UL
+
+#define MILLIWATT_PER_WATT	1000UL
+#define MICROWATT_PER_MILLIWATT	1000UL
+#define MICROWATT_PER_WATT	1000000UL
 
 #define ABSOLUTE_ZERO_MILLICELSIUS -273150
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 2644425b6dce..671d402c3778 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -225,9 +225,6 @@ static inline bool is_vm_area_hugepages(const void *addr)
 }
 
 #ifdef CONFIG_MMU
-int vmap_range(unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift);
 void vunmap_range(unsigned long addr, unsigned long end);
 static inline void set_vm_flush_reset_perms(void *addr)
 {