drivers/base/memory: determine and store zone for single-zone memory blocks

index a133981a12fc..5d75341413ce 100644
@@ -892,8 +892,9 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
-void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
-		       enum meminit_context context)
+void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+				       unsigned long end_pfn,
+				       enum meminit_context context)
 {
 	walk_memory_blocks_func_t func;
 

index f3be6ccfebed..9ec680dd607f 100644
@@ -99,13 +99,13 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
-void link_mem_sections(int nid, unsigned long start_pfn,
-		       unsigned long end_pfn,
-		       enum meminit_context context);
+void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+				       unsigned long end_pfn,
+				       enum meminit_context context);
 #else
-static inline void link_mem_sections(int nid, unsigned long start_pfn,
-				     unsigned long end_pfn,
-				     enum meminit_context context)
+static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
+						     unsigned long end_pfn,
+						     enum meminit_context context)
 {
 }
 #endif

@@ -129,8 +129,8 @@ static inline int register_one_node(int nid)
 		error = __register_one_node(nid);
 		if (error)
 			return error;
-		/* link memory sections under this node */
-		link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
+		register_memory_blocks_under_node(nid, start_pfn, end_pfn,
+						  MEMINIT_EARLY);
 	}
 
 	return error;

index 2a9627dc784c..69af90e9f507 100644
@@ -1421,9 +1421,9 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		BUG_ON(ret);
 	}
 
-	/* link memory sections under this node.*/
-	link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
-			  MEMINIT_HOTPLUG);
+	register_memory_blocks_under_node(nid, PFN_DOWN(start),
+					  PFN_UP(start + size - 1),
+					  MEMINIT_HOTPLUG);
 
 	/* create new memmap entry */
 	if (!strcmp(res->name, "System RAM"))

index 60c38f9cf1a7..8652368d179d 100644
@@ -215,6 +215,7 @@ static int memory_block_online(struct memory_block *mem)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  nr_vmemmap_pages);
 
+	mem->zone = zone;
 	return ret;
 }
 

@@ -225,6 +226,9 @@ static int memory_block_offline(struct memory_block *mem)
 	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
 	int ret;
 
+	if (!mem->zone)
+		return -EBUSY;
+
 	/*
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().

@@ -234,7 +238,7 @@ static int memory_block_offline(struct memory_block *mem)
 					  -nr_vmemmap_pages);
 
 	ret = offline_pages(start_pfn + nr_vmemmap_pages,
-			    nr_pages - nr_vmemmap_pages, mem->group);
+			    nr_pages - nr_vmemmap_pages, mem->zone, mem->group);
 	if (ret) {
 		/* offline_pages() failed. Account back. */
 		if (nr_vmemmap_pages)

@@ -246,6 +250,7 @@ static int memory_block_offline(struct memory_block *mem)
 	if (nr_vmemmap_pages)
 		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
 
+	mem->zone = NULL;
 	return ret;
 }
 

@@ -411,11 +416,10 @@ static ssize_t valid_zones_show(struct device *dev,
 	 */
 	if (mem->state == MEM_ONLINE) {
 		/*
-		 * The block contains more than one zone can not be offlined.
-		 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
+		 * If !mem->zone, the memory block spans multiple zones and
+		 * cannot get offlined.
 		 */
-		default_zone = test_pages_in_a_zone(start_pfn,
-						    start_pfn + nr_pages);
+		default_zone = mem->zone;
 		if (!default_zone)
 			return sysfs_emit(buf, "%s\n", "none");
 		len += sysfs_emit_at(buf, len, "%s", default_zone->name);

@@ -641,6 +645,73 @@ int register_memory(struct memory_block *memory)
 	return ret;
 }
 
+static struct zone *early_node_zone_for_memory_block(struct memory_block *mem,
+						     int nid)
+{
+	const unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	const unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	struct zone *zone, *matching_zone = NULL;
+	pg_data_t *pgdat = NODE_DATA(nid);
+	int i;
+
+	/*
+	 * This logic only works for early memory, when the applicable zones
+	 * already span the memory block. We don't expect overlapping zones on
+	 * a single node for early memory. So if we're told that some pfns
+	 * of a node fall into this memory block, we can assume that all node
+	 * zones that intersect with the memory block are actually applicable.
+	 * No need to look at the memmap.
+	 *
+	 * Memory hot(un)plug updates the zone manually after memory
+	 * onlinig/offlining succeeded.
+	 */
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		zone = pgdat->node_zones + i;
+		if (!populated_zone(zone))
+			continue;
+		if (!zone_intersects(zone, start_pfn, nr_pages))
+			continue;
+		if (!matching_zone) {
+			matching_zone = zone;
+			continue;
+		}
+		/* Spans multiple zones ... */
+		matching_zone = NULL;
+		break;
+	}
+	return matching_zone;
+}
+
+#ifdef CONFIG_NUMA
+void memory_block_set_nid(struct memory_block *mem, int nid,
+			  enum meminit_context context)
+{
+	if (context == MEMINIT_EARLY && mem->nid != nid) {
+		/*
+		 * For early memory we have to determine the zone when setting
+		 * the node id and handle multiple nodes spanning a single
+		 * memory block by indicate via zone == NULL that we're not
+		 * dealing with a single zone. So if we're setting the node id
+		 * the first time, determine if there is a single zone. If we're
+		 * setting the node id a second time to a differen node,
+		 * invalidate the single detected zone.
+		 */
+		if (mem->nid == NUMA_NO_NODE)
+			mem->zone = early_node_zone_for_memory_block(mem, nid);
+		else
+			mem->zone = NULL;
+	}
+
+	/*
+	 * If this memory block spans multiple nodes, we only indicate
+	 * the last processed node. If we span multiple nodes (not applicable
+	 * to hotplugged memory), zone == NULL will prohibit memory offlining
+	 * and consequently unplug.
+	 */
+	mem->nid = nid;
+}
+#endif
+
 static int init_memory_block(unsigned long block_id, unsigned long state,
 			     unsigned long nr_vmemmap_pages,
 			     struct memory_group *group)

@@ -663,6 +734,17 @@ static int init_memory_block(unsigned long block_id, unsigned long state,
 	mem->nr_vmemmap_pages = nr_vmemmap_pages;
 	INIT_LIST_HEAD(&mem->group_next);
 
+#ifndef CONFIG_NUMA
+	if (state == MEM_ONLINE)
+		/*
+		 * MEM_ONLINE at this point imples early memory. With NUMA,
+		 * we'll determine the zone when setting the node id via
+		 * memory_block_set_nid(). Memory hotplug updated the zone
+		 * manually when memory onlining/offlining succeeds.
+		 */
+		mem->zone = early_node_zone_for_memory_block(mem, NUMA_NO_NODE);
+#endif /* CONFIG_NUMA */
+
 	ret = register_memory(mem);
 	if (ret)
 		return ret;

index 5d75341413ce..4ba3990d8f7f 100644
@@ -796,15 +796,12 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 }
 
 static void do_register_memory_block_under_node(int nid,
-						struct memory_block *mem_blk)
+						struct memory_block *mem_blk,
+						enum meminit_context context)
 {
 	int ret;
 
-	/*
-	 * If this memory block spans multiple nodes, we only indicate
-	 * the last processed node.
-	 */
-	mem_blk->nid = nid;
+	memory_block_set_nid(mem_blk, nid, context);
 
 	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 				       &mem_blk->dev.kobj,

@@ -857,7 +854,7 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk,
 		if (page_nid != nid)
 			continue;
 
-		do_register_memory_block_under_node(nid, mem_blk);
+		do_register_memory_block_under_node(nid, mem_blk, MEMINIT_EARLY);
 		return 0;
 	}
 	/* mem section does not span the specified node */

@@ -873,7 +870,7 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
 {
 	int nid = *(int *)arg;
 
-	do_register_memory_block_under_node(nid, mem_blk);
+	do_register_memory_block_under_node(nid, mem_blk, MEMINIT_HOTPLUG);
 	return 0;
 }
 

index 88eb587b5143..13b7d2582af0 100644
@@ -70,6 +70,13 @@ struct memory_block {
 	unsigned long state;		/* serialized by the dev->lock */
 	int online_type;		/* for passing data to online routine */
 	int nid;			/* NID for this memory block */
+	/*
+	 * The single zone of this memory block if all PFNs of this memory block
+	 * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are
+	 * managed by a single zone. NULL if multiple zones (including nodes)
+	 * apply.
+	 */
+	struct zone *zone;
 	struct device dev;
 	/*
 	 * Number of vmemmap pages. These pages

@@ -161,6 +168,12 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 })
 #define register_hotmemory_notifier(nb)		register_memory_notifier(nb)
 #define unregister_hotmemory_notifier(nb) 	unregister_memory_notifier(nb)
+
+#ifdef CONFIG_NUMA
+/* Only to be used by node initialization code. */
+void memory_block_set_nid(struct memory_block *mem, int nid,
+			  enum meminit_context context);
+#endif /* CONFIG_NUMA */
 #endif	/* CONFIG_MEMORY_HOTPLUG */
 
 /*

index be48e003a518..05b2cdf6c935 100644
@@ -107,8 +107,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 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 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);
 

@@ -297,7 +295,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 
 extern void try_offline_node(int nid);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-			 struct memory_group *group);
+			 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);

@@ -306,7 +304,7 @@ extern int offline_and_remove_memory(u64 start, u64 size);
 static inline void try_offline_node(int nid) {}
 
 static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
-				struct memory_group *group)
+				struct zone *zone, struct memory_group *group)
 {
 	return -EINVAL;
 }

82 lines not on this page · raw message