Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a90aba3..c142a15 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -88,53 +88,16 @@
 
 extern int page_group_by_mobility_disabled;
 
-#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
-#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
+#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
 
 #define get_pageblock_migratetype(page)					\
-	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
-			PB_migrate_end, MIGRATETYPE_MASK)
+	get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
 
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
 	unsigned long		nr_free;
 };
 
-/* Used for pages not on another list */
-static inline void add_to_free_area(struct page *page, struct free_area *area,
-			     int migratetype)
-{
-	list_add(&page->lru, &area->free_list[migratetype]);
-	area->nr_free++;
-}
-
-/* Used for pages not on another list */
-static inline void add_to_free_area_tail(struct page *page, struct free_area *area,
-				  int migratetype)
-{
-	list_add_tail(&page->lru, &area->free_list[migratetype]);
-	area->nr_free++;
-}
-
-#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
-/* Used to preserve page allocation order entropy */
-void add_to_free_area_random(struct page *page, struct free_area *area,
-		int migratetype);
-#else
-static inline void add_to_free_area_random(struct page *page,
-		struct free_area *area, int migratetype)
-{
-	add_to_free_area(page, area, migratetype);
-}
-#endif
-
-/* Used for pages which are on another list */
-static inline void move_to_free_area(struct page *page, struct free_area *area,
-			     int migratetype)
-{
-	list_move(&page->lru, &area->free_list[migratetype]);
-}
-
 static inline struct page *get_page_from_free_area(struct free_area *area,
 					    int migratetype)
 {
@@ -142,15 +105,6 @@
 					struct page, lru);
 }
 
-static inline void del_page_from_free_area(struct page *page,
-		struct free_area *area)
-{
-	list_del(&page->lru);
-	__ClearPageBuddy(page);
-	set_page_private(page, 0);
-	area->nr_free--;
-}
-
 static inline bool free_area_empty(struct free_area *area, int migratetype)
 {
 	return list_empty(&area->free_list[migratetype]);
@@ -199,7 +153,6 @@
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
 	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
@@ -215,14 +168,20 @@
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
+	NR_SLAB_RECLAIMABLE_B,
+	NR_SLAB_UNRECLAIMABLE_B,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,
-	WORKINGSET_REFAULT,
-	WORKINGSET_ACTIVATE,
-	WORKINGSET_RESTORE,
+	WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE,
+	WORKINGSET_REFAULT_FILE,
+	WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE,
+	WORKINGSET_ACTIVATE_FILE,
+	WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE,
+	WORKINGSET_RESTORE_FILE,
 	WORKINGSET_NODERECLAIM,
 	NR_ANON_MAPPED,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
@@ -237,16 +196,41 @@
 	NR_FILE_THPS,
 	NR_FILE_PMDMAPPED,
 	NR_ANON_THPS,
-	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_VMSCAN_WRITE,
 	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
 	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
+	NR_FOLL_PIN_ACQUIRED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
+	NR_FOLL_PIN_RELEASED,	/* pages returned via unpin_user_page() */
+	NR_KERNEL_STACK_KB,	/* measured in KiB */
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	NR_KERNEL_SCS_KB,	/* measured in KiB */
+#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
 /*
+ * Returns true if the value is measured in bytes (most vmstat values are
+ * measured in pages). This defines the API part, the internal representation
+ * might be different.
+ */
+static __always_inline bool vmstat_item_in_bytes(int idx)
+{
+	/*
+	 * Global and per-node slab counters track slab pages.
+	 * It's expected that changes are multiples of PAGE_SIZE.
+	 * Internally values are stored in pages.
+	 *
+	 * Per-memcg and per-lruvec counters track memory, consumed
+	 * by individual slab objects. These counters are actually
+	 * byte-precise.
+	 */
+	return (idx == NR_SLAB_RECLAIMABLE_B ||
+		idx == NR_SLAB_UNRECLAIMABLE_B);
+}
+
+/*
  * We do arithmetic on the LRU lists in various places in the code,
  * so it is important to keep the active lists LRU_ACTIVE higher in
  * the array than the corresponding inactive lists, and to keep
@@ -272,42 +256,45 @@
 
 #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
 
-static inline int is_file_lru(enum lru_list lru)
+static inline bool is_file_lru(enum lru_list lru)
 {
 	return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE);
 }
 
-static inline int is_active_lru(enum lru_list lru)
+static inline bool is_active_lru(enum lru_list lru)
 {
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
 
-struct zone_reclaim_stat {
-	/*
-	 * The pageout code in vmscan.c keeps track of how many of the
-	 * mem/swap backed and file backed pages are referenced.
-	 * The higher the rotated/scanned ratio, the more valuable
-	 * that cache is.
-	 *
-	 * The anon LRU stats live in [0], file LRU stats in [1]
-	 */
-	unsigned long		recent_rotated[2];
-	unsigned long		recent_scanned[2];
+#define ANON_AND_FILE 2
+
+enum lruvec_flags {
+	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
+					 * backed by a congested BDI
+					 */
 };
 
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
-	struct zone_reclaim_stat	reclaim_stat;
-	/* Evictions & activations on the inactive file list */
-	atomic_long_t			inactive_age;
+	/*
+	 * These track the cost of reclaiming one LRU - file or anon -
+	 * over the other. As the observed cost of reclaiming one LRU
+	 * increases, the reclaim scan balance tips toward the other.
+	 */
+	unsigned long			anon_cost;
+	unsigned long			file_cost;
+	/* Non-resident age, driven by LRU movement */
+	atomic_long_t			nonresident_age;
 	/* Refaults at the time of last reclaim cycle */
-	unsigned long			refaults;
+	unsigned long			refaults[ANON_AND_FILE];
+	/* Various lruvec state flags (enum lruvec_flags) */
+	unsigned long			flags;
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
 };
 
-/* Isolate unmapped file */
+/* Isolate unmapped pages */
 #define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
 /* Isolate for asynchronous migration */
 #define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
@@ -358,33 +345,20 @@
 #endif /* !__GENERATING_BOUNDS.H */
 
 enum zone_type {
-#ifdef CONFIG_ZONE_DMA
 	/*
-	 * ZONE_DMA is used when there are devices that are not able
-	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
-	 * carve out the portion of memory that is needed for these devices.
-	 * The range is arch specific.
-	 *
-	 * Some examples
-	 *
-	 * Architecture		Limit
-	 * ---------------------------
-	 * parisc, ia64, sparc	<4G
-	 * s390, powerpc	<2G
-	 * arm			Various
-	 * alpha		Unlimited or 0-16MB.
-	 *
-	 * i386, x86_64 and multiple other arches
-	 * 			<16M.
+	 * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able
+	 * to DMA to all of the addressable memory (ZONE_NORMAL).
+	 * On architectures where this area covers the whole 32 bit address
+	 * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller
+	 * DMA addressing constraints. This distinction is important as a 32bit
+	 * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit
+	 * platforms may need both zones as they support peripherals with
+	 * different DMA addressing limitations.
 	 */
+#ifdef CONFIG_ZONE_DMA
 	ZONE_DMA,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	/*
-	 * x86_64 needs two ZONE_DMAs because it supports devices that are
-	 * only able to do DMA to the lower 16M but also 32 bit devices that
-	 * can only do DMA areas below 4G.
-	 */
 	ZONE_DMA32,
 #endif
 	/*
@@ -404,6 +378,41 @@
 	 */
 	ZONE_HIGHMEM,
 #endif
+	/*
+	 * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains
+	 * movable pages with few exceptional cases described below. Main use
+	 * cases for ZONE_MOVABLE are to make memory offlining/unplug more
+	 * likely to succeed, and to locally limit unmovable allocations - e.g.,
+	 * to increase the number of THP/huge pages. Notable special cases are:
+	 *
+	 * 1. Pinned pages: (long-term) pinning of movable pages might
+	 *    essentially turn such pages unmovable. Memory offlining might
+	 *    retry a long time.
+	 * 2. memblock allocations: kernelcore/movablecore setups might create
+	 *    situations where ZONE_MOVABLE contains unmovable allocations
+	 *    after boot. Memory offlining and allocations fail early.
+	 * 3. Memory holes: kernelcore/movablecore setups might create very rare
+	 *    situations where ZONE_MOVABLE contains memory holes after boot,
+	 *    for example, if we have sections that are only partially
+	 *    populated. Memory offlining and allocations fail early.
+	 * 4. PG_hwpoison pages: while poisoned pages can be skipped during
+	 *    memory offlining, such pages cannot be allocated.
+	 * 5. Unmovable PG_offline pages: in paravirtualized environments,
+	 *    hotplugged memory blocks might only partially be managed by the
+	 *    buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The
+	 *    parts not manged by the buddy are unmovable PG_offline pages. In
+	 *    some cases (virtio-mem), such pages can be skipped during
+	 *    memory offlining, however, cannot be moved/allocated. These
+	 *    techniques might use alloc_contig_range() to hide previously
+	 *    exposed pages from the buddy again (e.g., to implement some sort
+	 *    of memory unplug in virtio-mem).
+	 *
+	 * In general, no unmovable allocations that degrade memory offlining
+	 * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range())
+	 * have to expect that migrating pages in ZONE_MOVABLE can fail (even
+	 * if has_unmovable_pages() states that there are no unmovable pages,
+	 * there can be false negatives).
+	 */
 	ZONE_MOVABLE,
 #ifdef CONFIG_ZONE_DEVICE
 	ZONE_DEVICE,
@@ -414,6 +423,8 @@
 
 #ifndef __GENERATING_BOUNDS_H
 
+#define ASYNC_AND_SYNC 2
+
 struct zone {
 	/* Read-mostly fields */
 
@@ -434,7 +445,7 @@
 	 */
 	long lowmem_reserve[MAX_NR_ZONES];
 
-#ifdef CONFIG_NUMA
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	int node;
 #endif
 	struct pglist_data	*zone_pgdat;
@@ -533,8 +544,8 @@
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 	/* pfn where compaction free scanner should start */
 	unsigned long		compact_cached_free_pfn;
-	/* pfn where async and sync compaction migration scanner should start */
-	unsigned long		compact_cached_migrate_pfn[2];
+	/* pfn where compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[ASYNC_AND_SYNC];
 	unsigned long		compact_init_migrate_pfn;
 	unsigned long		compact_init_free_pfn;
 #endif
@@ -544,6 +555,7 @@
 	 * On compaction failure, 1<<compact_defer_shift compactions
 	 * are skipped before trying again. The number attempted since
 	 * last failure is tracked with compact_considered.
+	 * compact_order_failed is the minimum compaction failed order.
 	 */
 	unsigned int		compact_considered;
 	unsigned int		compact_defer_shift;
@@ -564,9 +576,6 @@
 } ____cacheline_internodealigned_in_smp;
 
 enum pgdat_flags {
-	PGDAT_CONGESTED,		/* pgdat has many dirty pages backed by
-					 * a congested BDI
-					 */
 	PGDAT_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
@@ -694,11 +703,22 @@
  * Memory statistics and page replacement data structures are maintained on a
  * per-zone basis.
  */
-struct bootmem_data;
 typedef struct pglist_data {
+	/*
+	 * node_zones contains just the zones for THIS node. Not all of the
+	 * zones may be populated, but it is the full list. It is referenced by
+	 * this node's node_zonelists as well as other node's node_zonelists.
+	 */
 	struct zone node_zones[MAX_NR_ZONES];
+
+	/*
+	 * node_zonelists contains references to all zones in all nodes.
+	 * Generally the first zones will be references to this node's
+	 * node_zones.
+	 */
 	struct zonelist node_zonelists[MAX_ZONELISTS];
-	int nr_zones;
+
+	int nr_zones; /* number of populated zones in this node */
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
 #ifdef CONFIG_PAGE_EXTENSION
@@ -730,13 +750,13 @@
 	struct task_struct *kswapd;	/* Protected by
 					   mem_hotplug_begin/end() */
 	int kswapd_order;
-	enum zone_type kswapd_classzone_idx;
+	enum zone_type kswapd_highest_zoneidx;
 
 	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */
 
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
-	enum zone_type kcompactd_classzone_idx;
+	enum zone_type kcompactd_highest_zoneidx;
 	wait_queue_head_t kcompactd_wait;
 	struct task_struct *kcompactd;
 #endif
@@ -748,7 +768,7 @@
 
 #ifdef CONFIG_NUMA
 	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
+	 * node reclaim becomes active if more unmapped pages exist.
 	 */
 	unsigned long		min_unmapped_pages;
 	unsigned long		min_slab_pages;
@@ -771,7 +791,13 @@
 #endif
 
 	/* Fields commonly accessed by the page reclaim scanner */
-	struct lruvec		lruvec;
+
+	/*
+	 * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED.
+	 *
+	 * Use mem_cgroup_lruvec() to look up lruvecs.
+	 */
+	struct lruvec		__lruvec;
 
 	unsigned long		flags;
 
@@ -794,11 +820,6 @@
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
 
-static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
-{
-	return &pgdat->lruvec;
-}
-
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {
 	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
@@ -813,15 +834,15 @@
 
 void build_all_zonelists(pg_data_t *pgdat);
 void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
-		   enum zone_type classzone_idx);
+		   enum zone_type highest_zoneidx);
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
-			 int classzone_idx, unsigned int alloc_flags,
+			 int highest_zoneidx, unsigned int alloc_flags,
 			 long free_pages);
 bool zone_watermark_ok(struct zone *z, unsigned int order,
-		unsigned long mark, int classzone_idx,
+		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
 bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int classzone_idx);
+		unsigned long mark, int highest_zoneidx);
 /*
  * Memory initialization context, use to differentiate memory added by
  * the platform statically or via memory hotplug interface.
@@ -841,24 +862,12 @@
 #ifdef CONFIG_MEMCG
 	return lruvec->pgdat;
 #else
-	return container_of(lruvec, struct pglist_data, lruvec);
+	return container_of(lruvec, struct pglist_data, __lruvec);
 #endif
 }
 
 extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
 
-#ifdef CONFIG_HAVE_MEMORY_PRESENT
-void memory_present(int nid, unsigned long start, unsigned long end);
-#else
-static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
-#endif
-
-#if defined(CONFIG_SPARSEMEM)
-void memblocks_present(void);
-#else
-static inline void memblocks_present(void) {}
-#endif
-
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 int local_memory_node(int node_id);
 #else
@@ -887,7 +896,7 @@
 	return zone->present_pages;
 }
 
-#ifdef CONFIG_NUMA
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 static inline int zone_to_nid(struct zone *zone)
 {
 	return zone->node;
@@ -911,7 +920,7 @@
 #ifdef CONFIG_HIGHMEM
 static inline int zone_movable_is_highmem(void)
 {
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	return movable_zone == ZONE_HIGHMEM;
 #else
 	return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
@@ -929,6 +938,15 @@
 #endif
 }
 
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void);
+#else
+static inline bool has_managed_dma(void)
+{
+	return false;
+}
+#endif
+
 /**
  * is_highmem - helper function to quickly check if a struct zone is a
  *              highmem zone or not.  This is an attempt to keep references
@@ -946,24 +964,23 @@
 
 /* These two functions are used to setup the per zone pages min values */
 struct ctl_table;
-int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int watermark_boost_factor_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
-int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
-int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
 
-extern int numa_zonelist_order_handler(struct ctl_table *, int,
-			void __user *, size_t *, loff_t *);
+int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *,
+		loff_t *);
+int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *,
+		size_t *, loff_t *);
+extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
+int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *,
+		size_t *, loff_t *);
+int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
+		void *, size_t *, loff_t *);
+int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
+		void *, size_t *, loff_t *);
+int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
+		void *, size_t *, loff_t *);
+int numa_zonelist_order_handler(struct ctl_table *, int,
+		void *, size_t *, loff_t *);
+extern int percpu_pagelist_fraction;
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN	16
 
@@ -1078,7 +1095,7 @@
 /**
  * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
  * @zone - The current zone in the iterator
- * @z - The current pointer within zonelist->zones being iterated
+ * @z - The current pointer within zonelist->_zonerefs being iterated
  * @zlist - The zonelist being iterated
  * @highidx - The zone index of the highest zone to return
  * @nodemask - Nodemask allowed by the allocator
@@ -1092,7 +1109,7 @@
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
 			zone = zonelist_zone(z))
 
-#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \
 	for (zone = z->zone;	\
 		zone;							\
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
@@ -1115,15 +1132,6 @@
 #include <asm/sparsemem.h>
 #endif
 
-#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
-	!defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-static inline unsigned long early_pfn_to_nid(unsigned long pfn)
-{
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA));
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_FLATMEM
 #define pfn_to_nid(pfn)		(0)
 #endif
@@ -1164,6 +1172,7 @@
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 #define SUBSECTION_SHIFT 21
+#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT)
 
 #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
 #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)
@@ -1179,7 +1188,9 @@
 #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
 
 struct mem_section_usage {
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
+#endif
 	/* See declaration of similar field in struct zone */
 	unsigned long pageblock_flags[0];
 };
@@ -1366,13 +1377,23 @@
 }
 #endif
 
-static inline int pfn_present(unsigned long pfn)
+static inline int pfn_in_present_section(unsigned long pfn)
 {
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
 }
 
+static inline unsigned long next_present_section_nr(unsigned long section_nr)
+{
+	while (++section_nr <= __highest_present_section_nr) {
+		if (present_section_nr(section_nr))
+			return section_nr;
+	}
+
+	return -1;
+}
+
 /*
  * These are _only_ used during initialisation, therefore they
  * can use __initdata ...  They could have names to indicate
@@ -1388,12 +1409,11 @@
 #define pfn_to_nid(pfn)		(0)
 #endif
 
-#define early_pfn_valid(pfn)	pfn_valid(pfn)
 void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
-#define pfn_present pfn_valid
+#define pfn_in_present_section pfn_valid
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
@@ -1408,12 +1428,6 @@
 	int last_nid;
 };
 
-#ifndef early_pfn_valid
-#define early_pfn_valid(pfn)	(1)
-#endif
-
-void memory_present(int nid, unsigned long start, unsigned long end);
-
 /*
  * 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.