mm/memory_hotplug: track present pages in memory groups

Let's track all present pages in each memory group. Especially, track
memory present in ZONE_MOVABLE and memory present in one of the kernel
zones (which really only is ZONE_NORMAL right now as memory groups only
apply to hotplugged memory) separately within a memory group, to prepare
for making smart auto-online decision for individual memory blocks within
a memory group based on group statistics.

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: David Hildenbrand <[e-mail]>
Cc: Anshuman Khandual <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Greg Kroah-Hartman <[e-mail]>
Cc: Hui Zhu <[e-mail]>
Cc: Jason Wang <[e-mail]>
Cc: Len Brown <[e-mail]>
Cc: Marek Kedzierski <[e-mail]>
Cc: "Michael S. Tsirkin" <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Mike Rapoport <[e-mail]>
Cc: Oscar Salvador <[e-mail]>
Cc: Pankaj Gupta <[e-mail]>
Cc: Pavel Tatashin <[e-mail]>
Cc: Rafael J. Wysocki <[e-mail]>
Cc: "Rafael J. Wysocki" <[e-mail]>
Cc: Vitaly Kuznetsov <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Cc: Wei Yang <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

drivers/base/memory.c

···
 	}
 
 	ret = online_pages(start_pfn + nr_vmemmap_pages,
-			   nr_pages - nr_vmemmap_pages, zone);
+			   nr_pages - nr_vmemmap_pages, zone, mem->group);
 	if (ret) {
 		if (nr_vmemmap_pages)
 			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
···
 	 * now already properly populated.
 	 */
 	if (nr_vmemmap_pages)
-		adjust_present_page_count(pfn_to_page(start_pfn),
+		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  nr_vmemmap_pages);
 
 	return ret;
···
 	 * can properly be torn down in offline_pages().
 	 */
 	if (nr_vmemmap_pages)
-		adjust_present_page_count(pfn_to_page(start_pfn),
+		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
 
 	ret = offline_pages(start_pfn + nr_vmemmap_pages,
-			    nr_pages - nr_vmemmap_pages);
+			    nr_pages - nr_vmemmap_pages, mem->group);
 	if (ret) {
 		/* offline_pages() failed. Account back. */
 		if (nr_vmemmap_pages)
 			adjust_present_page_count(pfn_to_page(start_pfn),
-						  nr_vmemmap_pages);
+						  mem->group, nr_vmemmap_pages);
 		return ret;
 	}
 

include/linux/memory.h

···
  * 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.
···
 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 {

include/linux/memory_hotplug.h

···
 struct pglist_data;
 struct mem_section;
 struct memory_block;
+struct memory_group;
 struct resource;
 struct vmem_altmap;
 
···
 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, 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,
···
 #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 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;
 }

mm/memory_hotplug.c

···
  * This function should only be called by memory_block_{online,offline},
  * and {online,offline}_pages.
  */
-void adjust_present_page_count(struct page *page, long nr_pages)
+void adjust_present_page_count(struct page *page, struct memory_group *group,
+			       long nr_pages)
 {
 	struct zone *zone = page_zone(page);
+	const bool movable = zone_idx(zone) == ZONE_MOVABLE;
 
 	/*
 	 * We only support onlining/offlining/adding/removing of complete
···
 		zone->present_early_pages += nr_pages;
 	zone->present_pages += nr_pages;
 	zone->zone_pgdat->node_present_pages += nr_pages;
+
+	if (group && movable)
+		group->present_movable_pages += nr_pages;
+	else if (group && !movable)
+		group->present_kernel_pages += nr_pages;
 }
 
 int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
···
 	kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
 }
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
+		       struct zone *zone, struct memory_group *group)
 {
 	unsigned long flags;
 	int need_zonelists_rebuild = 0;
···
 	}
 
 	online_pages_range(pfn, nr_pages);
-	adjust_present_page_count(pfn_to_page(pfn), nr_pages);
+	adjust_present_page_count(pfn_to_page(pfn), group, nr_pages);
 
 	node_states_set_node(nid, &arg);
 	if (need_zonelists_rebuild)
···
 	return 0;
 }
 
-int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+			struct memory_group *group)
 {
 	const unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn, system_ram_pages = 0;
···
 
 	/* removal success */
 	adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
-	adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages);
+	adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages);
 
 	/* reinitialise watermarks and update pcp limits */
 	init_per_zone_wmark_min();