1 files changed, 146 insertions, 170 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 07da5c6c5ba0..f2f16cdd73ee 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -11,46 +11,70 @@ struct page;
 struct zone;
 struct pglist_data;
 struct mem_section;
-struct memory_block;
+struct memory_group;
 struct resource;
 struct vmem_altmap;
+struct dev_pagemap;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+struct page *pfn_to_online_page(unsigned long pfn);
+
+/* Types for control the zone type of onlined and offlined memory */
+enum {
+	/* Offline the memory. */
+	MMOP_OFFLINE = 0,
+	/* Online the memory. Zone depends, see default_zone_for_pfn(). */
+	MMOP_ONLINE,
+	/* Online the memory to ZONE_NORMAL. */
+	MMOP_ONLINE_KERNEL,
+	/* Online the memory to ZONE_MOVABLE. */
+	MMOP_ONLINE_MOVABLE,
+};
+
+/* Flags for add_memory() and friends to specify memory hotplug details. */
+typedef int __bitwise mhp_t;
+
+/* No special request */
+#define MHP_NONE		((__force mhp_t)0)
 /*
- * Return page for the valid pfn only if the page is online. All pfn
- * walkers which rely on the fully initialized page->flags and others
- * should use this rather than pfn_valid && pfn_to_page
+ * Allow merging of the added System RAM resource with adjacent,
+ * mergeable resources. After a successful call to add_memory_resource()
+ * with this flag set, the resource pointer must no longer be used as it
+ * might be stale, or the resource might have changed.
  */
-#define pfn_to_online_page(pfn)				\
-({							\
-	struct page *___page = NULL;			\
-	unsigned long ___nr = pfn_to_section_nr(pfn);	\
-							\
-	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
-		___page = pfn_to_page(pfn);		\
-	___page;					\
-})
+#define MHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
 
 /*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
+ * We want memmap (struct page array) to be self contained.
+ * To do so, we will use the beginning of the hot-added range to build
+ * the page tables for the memmap array that describes the entire range.
+ * Only selected architectures support it with SPARSE_VMEMMAP.
+ * This is only a hint, the core kernel can decide to not do this based on
+ * different alignment checks.
  */
-enum {
-	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
-	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
-	MIX_SECTION_INFO,
-	NODE_INFO,
-	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
-};
+#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))
 
-/* Types for control the zone type of onlined and offlined memory */
-enum {
-	MMOP_OFFLINE = -1,
-	MMOP_ONLINE_KEEP,
-	MMOP_ONLINE_KERNEL,
-	MMOP_ONLINE_MOVABLE,
+/*
+ * Extended parameters for memory hotplug:
+ * altmap: alternative allocator for memmap array (optional)
+ * pgprot: page protection flags to apply to newly created page tables
+ *	(required)
+ */
+struct mhp_params {
+	struct vmem_altmap *altmap;
+	pgprot_t pgprot;
+	struct dev_pagemap *pgmap;
 };
 
+bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
+struct range mhp_get_pluggable_range(bool need_mapping);
+bool mhp_supports_memmap_on_memory(void);
+
 /*
  * Zone resizing functions
  *
@@ -78,27 +102,32 @@ static inline void zone_seqlock_init(struct zone *zone)
 {
 	seqlock_init(&zone->span_seqlock);
 }
-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 page *page,
+				      struct memory_group *group,
+				      long nr_pages);
 /* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
-	unsigned long *valid_start, unsigned long *valid_end);
-extern void __offline_isolated_pages(unsigned long, unsigned long);
+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 memory_group *group);
+extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
+		unsigned long end_pfn);
 
-typedef void (*online_page_callback_t)(struct page *page);
+typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
+extern void generic_online_page(struct page *page, unsigned int order);
 extern int set_online_page_callback(online_page_callback_t callback);
 extern int restore_online_page_callback(online_page_callback_t callback);
 
-extern void __online_page_set_limits(struct page *page);
-extern void __online_page_increment_counters(struct page *page);
-extern void __online_page_free(struct page *page);
-
 extern int try_online_node(int nid);
 
-extern bool memhp_auto_online;
+extern int arch_add_memory(int nid, u64 start, u64 size,
+			   struct mhp_params *params);
+extern u64 max_mem_size;
+
+extern int mhp_online_type_from_str(const char *str);
+
 /* If movable_node boot option specified */
 extern bool movable_node_enabled;
 static inline bool movable_node_is_enabled(void)
@@ -106,117 +135,46 @@ static inline bool movable_node_is_enabled(void)
 	return movable_node_enabled;
 }
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
-extern int arch_remove_memory(int nid, u64 start, u64 size,
-				struct vmem_altmap *altmap);
-extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
-	unsigned long nr_pages, struct vmem_altmap *altmap);
-#endif /* CONFIG_MEMORY_HOTREMOVE */
+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);
 
 /* reasonably generic interface to expand the physical pages */
 extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock);
+		       struct mhp_params *params);
 
 #ifndef CONFIG_ARCH_HAS_ADD_PAGES
 static inline int add_pages(int nid, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap,
-		bool want_memblock)
+		unsigned long nr_pages, struct mhp_params *params)
 {
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, params);
 }
 #else /* ARCH_HAS_ADD_PAGES */
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock);
+	      struct mhp_params *params);
 #endif /* ARCH_HAS_ADD_PAGES */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-#endif
-
-#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)
+void get_online_mems(void);
+void put_online_mems(void);
 
-#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)
+void mem_hotplug_begin(void);
+void mem_hotplug_done(void);
 
-extern pg_data_t *node_data[];
-static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
+/* See kswapd_is_running() */
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat)
 {
-	node_data[nid] = pgdat;
+	mutex_lock(&pgdat->kswapd_lock);
 }
 
-#else /* !CONFIG_NUMA */
-
-/* never called */
-static inline pg_data_t *generic_alloc_nodedata(int nid)
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat)
 {
-	BUG();
-	return NULL;
+	mutex_unlock(&pgdat->kswapd_lock);
 }
-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_HAVE_BOOTMEM_INFO_NODE
-extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
-#else
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat)
 {
+	mutex_init(&pgdat->kswapd_lock);
 }
-#endif
-extern void put_page_bootmem(struct page *page);
-extern void get_page_bootmem(unsigned long ingo, struct page *page,
-			     unsigned long type);
-
-void get_online_mems(void);
-void put_online_mems(void);
-
-void mem_hotplug_begin(void);
-void mem_hotplug_done(void);
-
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
 
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
@@ -239,17 +197,6 @@ static inline void zone_span_writelock(struct zone *zone) {}
 static inline void zone_span_writeunlock(struct zone *zone) {}
 static inline void zone_seqlock_init(struct zone *zone) {}
 
-static inline int mhp_notimplemented(const char *func)
-{
-	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
-	dump_stack();
-	return -ENOSYS;
-}
-
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-
 static inline int try_online_node(int nid)
 {
 	return 0;
@@ -265,8 +212,24 @@ static inline bool movable_node_is_enabled(void)
 {
 	return false;
 }
+
+static inline bool mhp_supports_memmap_on_memory(void)
+{
+	return false;
+}
+
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {}
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+/*
+ * Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some
+ * platforms might override and use arch_get_mappable_range()
+ * for internal non memory hotplug purposes.
+ */
+struct range arch_get_mappable_range(void);
+
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions
@@ -297,49 +260,62 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
-extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
 extern void try_offline_node(int nid);
-extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern void remove_memory(int nid, u64 start, u64 size);
-extern void __remove_memory(int nid, u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+			 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);
 
 #else
-static inline bool is_mem_section_removable(unsigned long pfn,
-					unsigned long nr_pages)
-{
-	return false;
-}
-
 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 zone *zone, struct memory_group *group)
 {
 	return -EINVAL;
 }
 
-static inline void remove_memory(int nid, u64 start, u64 size) {}
-static inline void __remove_memory(int nid, u64 start, u64 size) {}
+static inline int remove_memory(u64 start, u64 size)
+{
+	return -EBUSY;
+}
+
+static inline void __remove_memory(u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-extern void __ref free_area_init_core_hotplug(int nid);
-extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
-		void *arg, int (*func)(struct memory_block *, void *));
-extern int __add_memory(int nid, u64 start, u64 size);
-extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
-extern int arch_add_memory(int nid, u64 start, u64 size,
-		struct vmem_altmap *altmap, bool want_memblock);
+#ifdef CONFIG_MEMORY_HOTPLUG
+/* Default online_type (MMOP_*) when new memory blocks are added. */
+extern int mhp_get_default_online_type(void);
+extern void mhp_set_default_online_type(int online_type);
+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,
+			       mhp_t mhp_flags);
+extern int add_memory_driver_managed(int nid, u64 start, u64 size,
+				     const char *resource_name,
+				     mhp_t mhp_flags);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
-extern bool is_memblock_offlined(struct memory_block *mem);
-extern int sparse_add_one_section(int nid, unsigned long start_pfn,
+				   unsigned long nr_pages,
+				   struct vmem_altmap *altmap, int migratetype,
+				   bool isolate_pageblock);
+extern void remove_pfn_range_from_zone(struct zone *zone,
+				       unsigned long start_pfn,
+				       unsigned long nr_pages);
+extern int sparse_add_section(int nid, unsigned long pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
+extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
 				  struct vmem_altmap *altmap);
-extern void sparse_remove_one_section(struct zone *zone, 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 bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
-		int online_type);
-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);
+void arch_remove_linear_mapping(u64 start, u64 size);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */