1 files changed, 98 insertions, 142 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d65c6fdc5cfc..eaac5ae8c05c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -11,39 +11,13 @@ 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
-/*
- * 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
- */
-#define pfn_to_online_page(pfn)					   \
-({								   \
-	struct page *___page = NULL;				   \
-	unsigned long ___pfn = pfn;				   \
-	unsigned long ___nr = pfn_to_section_nr(___pfn);	   \
-								   \
-	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
-	    pfn_valid_within(___pfn))				   \
-		___page = pfn_to_page(___pfn);			   \
-	___page;						   \
-})
-
-/*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
- */
-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,
-};
+struct page *pfn_to_online_page(unsigned long pfn);
 
 /* Types for control the zone type of onlined and offlined memory */
 enum {
@@ -68,7 +42,38 @@ typedef int __bitwise mhp_t;
  * with this flag set, the resource pointer must no longer be used as it
  * might be stale, or the resource might have changed.
  */
-#define MEMHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
+#define MHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
+
+/*
+ * 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.
+ */
+#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))
+/*
+ * The hotplugged memory is completely inaccessible while the memory is
+ * offline. The memory provider will handle MEM_PREPARE_ONLINE /
+ * MEM_FINISH_OFFLINE notifications and make the memory accessible.
+ *
+ * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY,
+ * because the altmap cannot be written (e.g., poisoned) when adding
+ * memory -- before it is set online.
+ *
+ * This allows for adding memory with an altmap that is not currently
+ * made available by a hypervisor. When onlining that memory, the
+ * hypervisor can be instructed to make that memory available, and
+ * the onlining phase will not require any memory allocations, which is
+ * helpful in low-memory situations.
+ */
+#define MHP_OFFLINE_INACCESSIBLE	((__force mhp_t)BIT(3))
 
 /*
  * Extended parameters for memory hotplug:
@@ -79,8 +84,13 @@ typedef int __bitwise mhp_t;
 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
  *
@@ -108,16 +118,17 @@ 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 mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
+				     struct zone *zone, bool mhp_off_inaccessible);
+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,
-			int online_type, int nid);
-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);
+			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, unsigned int order);
 
@@ -131,10 +142,8 @@ extern int arch_add_memory(int nid, u64 start, u64 size,
 			   struct mhp_params *params);
 extern u64 max_mem_size;
 
-extern int memhp_online_type_from_str(const char *str);
+extern int mhp_online_type_from_str(const char *str);
 
-/* Default online_type (MMOP_*) when new memory blocks are added. */
-extern int memhp_default_online_type;
 /* If movable_node boot option specified */
 extern bool movable_node_enabled;
 static inline bool movable_node_is_enabled(void)
@@ -142,8 +151,7 @@ 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);
 
@@ -162,82 +170,27 @@ 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)
+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)
-{
-	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)
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat)
 {
+	mutex_unlock(&pgdat->kswapd_lock);
 }
-#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);
 
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
@@ -260,10 +213,6 @@ 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 void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-
 static inline int try_online_node(int nid)
 {
 	return 0;
@@ -279,21 +228,23 @@ static inline bool movable_node_is_enabled(void)
 {
 	return false;
 }
-#endif /* ! CONFIG_MEMORY_HOTPLUG */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-extern int phys_to_target_node(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-static inline int phys_to_target_node(u64 start)
+static inline bool mhp_supports_memmap_on_memory(void)
 {
-	return 0;
+	return false;
 }
-#endif
+
+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)
 /*
@@ -326,32 +277,34 @@ 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 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 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 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);
-extern void clear_zone_contiguous(struct zone *zone);
-
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern void __ref free_area_init_core_hotplug(int nid);
+/* 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,
@@ -365,16 +318,19 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
-extern bool is_memblock_offlined(struct memory_block *mem);
 extern int sparse_add_section(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
-extern void sparse_remove_section(struct mem_section *ms,
-		unsigned long pfn, unsigned long nr_pages,
-		unsigned long map_offset, struct vmem_altmap *altmap);
+		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 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);
+void arch_remove_linear_mapping(u64 start, u64 size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */