mm/memory_hotplug: embed vmem_altmap details in memory block

With memmap on memory, some architecture needs more details w.r.t altmap
such as base_pfn, end_pfn, etc to unmap vmemmap memory. Instead of
computing them again when we remove a memory block, embed vmem_altmap
details in struct memory_block if we are using memmap on memory block
feature.

[[e-mail]: fix error return code in add_memory_resource()]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Aneesh Kumar K.V <[e-mail]>
Signed-off-by: Yang Yingliang <[e-mail]>
Acked-by: Michal Hocko <[e-mail]>
Acked-by: David Hildenbrand <[e-mail]>
Cc: Christophe Leroy <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Oscar Salvador <[e-mail]>
Cc: Vishal Verma <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

drivers/base/memory.c

···
 static void memory_block_release(struct device *dev)
 {
 	struct memory_block *mem = to_memory_block(dev);
-
+	/* Verify that the altmap is freed */
+	WARN_ON(mem->altmap);
 	kfree(mem);
 }
 
···
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	unsigned long nr_vmemmap_pages = 0;
 	struct zone *zone;
 	int ret;
 
···
 	 * stage helps to keep accounting easier to follow - e.g vmemmaps
 	 * belong to the same zone as the memory they backed.
 	 */
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
···
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
+	unsigned long nr_vmemmap_pages = 0;
 	int ret;
 
 	if (!mem->zone)
···
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().
 	 */
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
 	if (nr_vmemmap_pages)
 		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
 					  -nr_vmemmap_pages);
···
 #endif
 
 static int add_memory_block(unsigned long block_id, unsigned long state,
-			    unsigned long nr_vmemmap_pages,
+			    struct vmem_altmap *altmap,
 			    struct memory_group *group)
 {
 	struct memory_block *mem;
···
 	mem->start_section_nr = block_id * sections_per_block;
 	mem->state = state;
 	mem->nid = NUMA_NO_NODE;
-	mem->nr_vmemmap_pages = nr_vmemmap_pages;
+	mem->altmap = altmap;
 	INIT_LIST_HEAD(&mem->group_next);
 
 #ifndef CONFIG_NUMA
···
 	if (section_count == 0)
 		return 0;
 	return add_memory_block(memory_block_id(base_section_nr),
-				MEM_ONLINE, 0,  NULL);
+				MEM_ONLINE, NULL,  NULL);
 }
 
 static int add_hotplug_memory_block(unsigned long block_id,
-				    unsigned long nr_vmemmap_pages,
+				    struct vmem_altmap *altmap,
 				    struct memory_group *group)
 {
-	return add_memory_block(block_id, MEM_OFFLINE, nr_vmemmap_pages, group);
+	return add_memory_block(block_id, MEM_OFFLINE, altmap, group);
 }
 
 static void remove_memory_block(struct memory_block *memory)
···
  * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group)
 {
 	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
···
 		return -EINVAL;
 
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
-		ret = add_hotplug_memory_block(block_id, vmemmap_pages, group);
+		ret = add_hotplug_memory_block(block_id, altmap, group);
 		if (ret)
 			break;
 	}

include/linux/memory.h

···
 	 */
 	struct zone *zone;
 	struct device dev;
-	/*
-	 * Number of vmemmap pages. These pages
-	 * lay at the beginning of the memory block.
-	 */
-	unsigned long nr_vmemmap_pages;
+	struct vmem_altmap *altmap;
 	struct memory_group *group;	/* group (if any) for this block */
 	struct list_head group_next;	/* next block inside memory group */
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
···
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				struct vmem_altmap *altmap,
 				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);

mm/memory_hotplug.c

···
 	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
 		if (mhp_supports_memmap_on_memory(size)) {
 			mhp_altmap.free = memory_block_memmap_on_memory_pages();
-			params.altmap = &mhp_altmap;
+			params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
+			if (!params.altmap) {
+				ret = -ENOMEM;
+				goto error;
+			}
+
+			memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
 		}
 		/* fallback to not using altmap  */
 	}
···
 	/* call arch's memory hotadd */
 	ret = arch_add_memory(nid, start, size, &params);
 	if (ret < 0)
-		goto error;
+		goto error_free;
 
 	/* create memory block devices after memory was added */
-	ret = create_memory_block_devices(start, size, mhp_altmap.free, group);
+	ret = create_memory_block_devices(start, size, params.altmap, group);
 	if (ret) {
 		arch_remove_memory(start, size, NULL);
-		goto error;
+		goto error_free;
 	}
 
 	if (new_node) {
···
 		walk_memory_blocks(start, size, NULL, online_memory_block);
 
 	return ret;
+error_free:
+	kfree(params.altmap);
 error:
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		memblock_remove(start, size);
···
 	return 0;
 }
 
-static int get_nr_vmemmap_pages_cb(struct memory_block *mem, void *arg)
+static int test_has_altmap_cb(struct memory_block *mem, void *arg)
 {
+	struct memory_block **mem_ptr = (struct memory_block **)arg;
 	/*
-	 * If not set, continue with the next block.
+	 * return the memblock if we have altmap
+	 * and break callback.
 	 */
-	return mem->nr_vmemmap_pages;
+	if (mem->altmap) {
+		*mem_ptr = mem;
+		return 1;
+	}
+	return 0;
 }
 
 static int check_cpu_on_node(int nid)
···
 
 static int __ref try_remove_memory(u64 start, u64 size)
 {
-	struct vmem_altmap mhp_altmap = {};
-	struct vmem_altmap *altmap = NULL;
-	unsigned long nr_vmemmap_pages;
+	struct memory_block *mem;
 	int rc = 0, nid = NUMA_NO_NODE;
+	struct vmem_altmap *altmap = NULL;
 
 	BUG_ON(check_hotplug_memory_range(start, size));
 
···
 	 * the same granularity it was added - a single memory block.
 	 */
 	if (mhp_memmap_on_memory()) {
-		nr_vmemmap_pages = walk_memory_blocks(start, size, NULL,
-						      get_nr_vmemmap_pages_cb);
-		if (nr_vmemmap_pages) {
+		rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
+		if (rc) {
 			if (size != memory_block_size_bytes()) {
 				pr_warn("Refuse to remove %#llx - %#llx,"
 					"wrong granularity\n",
 					start, start + size);
 				return -EINVAL;
 			}
-
+			altmap = mem->altmap;
 			/*
-			 * Let remove_pmd_table->free_hugepage_table do the
-			 * right thing if we used vmem_altmap when hot-adding
-			 * the range.
+			 * Mark altmap NULL so that we can add a debug
+			 * check on memblock free.
 			 */
-			mhp_altmap.base_pfn = PHYS_PFN(start);
-			mhp_altmap.free = nr_vmemmap_pages;
-			mhp_altmap.alloc = nr_vmemmap_pages;
-			altmap = &mhp_altmap;
+			mem->altmap = NULL;
 		}
 	}
 
···
 	mem_hotplug_begin();
 
 	arch_remove_memory(start, size, altmap);
+
+	/* Verify that all vmemmap pages have actually been freed. */
+	if (altmap) {
+		WARN(altmap->alloc, "Altmap not fully unmapped");
+		kfree(altmap);
+	}
 
 	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
 		memblock_phys_free(start, size);