1 files changed, 472 insertions, 115 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index aa31a21f33d7..751f248ca4a8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -22,6 +22,7 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/xarray.h>
+#include <linux/export.h>
 
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
@@ -48,27 +49,13 @@ int mhp_online_type_from_str(const char *str)
 
 #define to_memory_block(dev) container_of(dev, struct memory_block, dev)
 
-static int sections_per_block;
-
-static inline unsigned long memory_block_id(unsigned long section_nr)
-{
-	return section_nr / sections_per_block;
-}
-
-static inline unsigned long pfn_to_block_id(unsigned long pfn)
-{
-	return memory_block_id(pfn_to_section_nr(pfn));
-}
-
-static inline unsigned long phys_to_block_id(unsigned long phys)
-{
-	return pfn_to_block_id(PFN_DOWN(phys));
-}
+int sections_per_block;
+EXPORT_SYMBOL(sections_per_block);
 
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
 
-static struct bus_type memory_subsys = {
+static const struct bus_type memory_subsys = {
 	.name = MEMORY_CLASS_NAME,
 	.dev_name = MEMORY_CLASS_NAME,
 	.online = memory_subsys_online,
@@ -82,6 +69,12 @@ static struct bus_type memory_subsys = {
  */
 static DEFINE_XARRAY(memory_blocks);
 
+/*
+ * Memory groups, indexed by memory group id (mgid).
+ */
+static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC);
+#define MEMORY_GROUP_MARK_DYNAMIC	XA_MARK_1
+
 static BLOCKING_NOTIFIER_HEAD(memory_chain);
 
 int register_memory_notifier(struct notifier_block *nb)
@@ -99,28 +92,75 @@ EXPORT_SYMBOL(unregister_memory_notifier);
 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);
 }
 
+
+/* Max block size to be set by memory_block_advise_max_size */
+static unsigned long memory_block_advised_size;
+static bool memory_block_advised_size_queried;
+
+/**
+ * memory_block_advise_max_size() - advise memory hotplug on the max suggested
+ *				    block size, usually for alignment.
+ * @size: suggestion for maximum block size. must be aligned on power of 2.
+ *
+ * Early boot software (pre-allocator init) may advise archs on the max block
+ * size. This value can only decrease after initialization, as the intent is
+ * to identify the largest supported alignment for all sources.
+ *
+ * Use of this value is arch-defined, as is min/max block size.
+ *
+ * Return: 0 on success
+ *	   -EINVAL if size is 0 or not pow2 aligned
+ *	   -EBUSY if value has already been probed
+ */
+int __init memory_block_advise_max_size(unsigned long size)
+{
+	if (!size || !is_power_of_2(size))
+		return -EINVAL;
+
+	if (memory_block_advised_size_queried)
+		return -EBUSY;
+
+	if (memory_block_advised_size)
+		memory_block_advised_size = min(memory_block_advised_size, size);
+	else
+		memory_block_advised_size = size;
+
+	return 0;
+}
+
+/**
+ * memory_block_advised_max_size() - query advised max hotplug block size.
+ *
+ * After the first call, the value can never change. Callers looking for the
+ * actual block size should use memory_block_size_bytes. This interface is
+ * intended for use by arch-init when initializing the hotplug block size.
+ *
+ * Return: advised size in bytes, or 0 if never set.
+ */
+unsigned long memory_block_advised_max_size(void)
+{
+	memory_block_advised_size_queried = true;
+	return memory_block_advised_size;
+}
+
 unsigned long __weak memory_block_size_bytes(void)
 {
 	return MIN_MEMORY_BLOCK_SIZE;
 }
 EXPORT_SYMBOL_GPL(memory_block_size_bytes);
 
-/*
- * Show the first physical section index (number) of this memory block.
- */
+/* Show the memory block ID, relative to the memory block size */
 static ssize_t phys_index_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct memory_block *mem = to_memory_block(dev);
-	unsigned long phys_index;
-
-	phys_index = mem->start_section_nr / sections_per_block;
 
-	return sysfs_emit(buf, "%08lx\n", phys_index);
+	return sysfs_emit(buf, "%08lx\n", memory_block_id(mem->start_section_nr));
 }
 
 /*
@@ -158,26 +198,42 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr,
 		break;
 	default:
 		WARN_ON(1);
-		return sysfs_emit(buf, "ERROR-UNKNOWN-%ld\n", mem->state);
+		return sysfs_emit(buf, "ERROR-UNKNOWN-%d\n", mem->state);
 	}
 
 	return sysfs_emit(buf, "%s\n", output);
 }
 
-int memory_notify(unsigned long val, void *v)
+int memory_notify(enum memory_block_state state, void *v)
 {
-	return blocking_notifier_call_chain(&memory_chain, val, v);
+	return blocking_notifier_call_chain(&memory_chain, state, v);
 }
 
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+static unsigned long memblk_nr_poison(struct memory_block *mem);
+#else
+static inline unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_online(struct memory_block *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;
 
-	zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages);
+	if (memblk_nr_poison(mem))
+		return -EHWPOISON;
+
+	zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
+				  start_pfn, nr_pages);
 
 	/*
 	 * Although vmemmap pages have a different lifecycle than the pages
@@ -186,18 +242,22 @@ static int memory_block_online(struct memory_block *mem)
 	 * 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;
+
+	mem_hotplug_begin();
 	if (nr_vmemmap_pages) {
 		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	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);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -205,40 +265,56 @@ static int memory_block_online(struct memory_block *mem)
 	 * now already properly populated.
 	 */
 	if (nr_vmemmap_pages)
-		adjust_present_page_count(zone, nr_vmemmap_pages);
+		adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
+					  nr_vmemmap_pages);
 
+	mem->zone = zone;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
+/*
+ * Must acquire mem_hotplug_lock in write mode.
+ */
 static int memory_block_offline(struct memory_block *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;
-	struct zone *zone;
+	unsigned long nr_vmemmap_pages = 0;
 	int ret;
 
+	if (!mem->zone)
+		return -EINVAL;
+
 	/*
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().
 	 */
-	if (nr_vmemmap_pages) {
-		zone = page_zone(pfn_to_page(start_pfn));
-		adjust_present_page_count(zone, -nr_vmemmap_pages);
-	}
+	if (mem->altmap)
+		nr_vmemmap_pages = mem->altmap->free;
+
+	mem_hotplug_begin();
+	if (nr_vmemmap_pages)
+		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->zone, mem->group);
 	if (ret) {
 		/* offline_pages() failed. Account back. */
 		if (nr_vmemmap_pages)
-			adjust_present_page_count(zone, nr_vmemmap_pages);
-		return ret;
+			adjust_present_page_count(pfn_to_page(start_pfn),
+						  mem->group, nr_vmemmap_pages);
+		goto out;
 	}
 
 	if (nr_vmemmap_pages)
 		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
 
+	mem->zone = NULL;
+out:
+	mem_hotplug_done();
 	return ret;
 }
 
@@ -374,12 +450,13 @@ static ssize_t phys_device_show(struct device *dev,
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static int print_allowed_zone(char *buf, int len, int nid,
+			      struct memory_group *group,
 			      unsigned long start_pfn, unsigned long nr_pages,
 			      int online_type, struct zone *default_zone)
 {
 	struct zone *zone;
 
-	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
+	zone = zone_for_pfn_range(online_type, nid, group, start_pfn, nr_pages);
 	if (zone == default_zone)
 		return 0;
 
@@ -392,9 +469,10 @@ static ssize_t valid_zones_show(struct device *dev,
 	struct memory_block *mem = to_memory_block(dev);
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	struct memory_group *group = mem->group;
 	struct zone *default_zone;
-	int len = 0;
-	int nid;
+	int nid = mem->nid;
+	int len;
 
 	/*
 	 * Check the existing zone. Make sure that we do that only on the
@@ -402,27 +480,21 @@ 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);
-		if (!default_zone)
-			return sysfs_emit(buf, "%s\n", "none");
-		len += sysfs_emit_at(buf, len, "%s", default_zone->name);
-		goto out;
+		return sysfs_emit(buf, "%s\n",
+				  mem->zone ? mem->zone->name : "none");
 	}
 
-	nid = mem->nid;
-	default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn,
-					  nr_pages);
+	default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, group,
+					  start_pfn, nr_pages);
 
-	len += sysfs_emit_at(buf, len, "%s", default_zone->name);
-	len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
+	len = sysfs_emit(buf, "%s", default_zone->name);
+	len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages,
 				  MMOP_ONLINE_KERNEL, default_zone);
-	len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
+	len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages,
 				  MMOP_ONLINE_MOVABLE, default_zone);
-out:
 	len += sysfs_emit_at(buf, len, "\n");
 	return len;
 }
@@ -453,7 +525,7 @@ static ssize_t auto_online_blocks_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
 {
 	return sysfs_emit(buf, "%s\n",
-			  online_type_to_str[mhp_default_online_type]);
+			  online_type_to_str[mhp_get_default_online_type()]);
 }
 
 static ssize_t auto_online_blocks_store(struct device *dev,
@@ -465,12 +537,22 @@ static ssize_t auto_online_blocks_store(struct device *dev,
 	if (online_type < 0)
 		return -EINVAL;
 
-	mhp_default_online_type = online_type;
+	mhp_set_default_online_type(online_type);
 	return count;
 }
 
 static DEVICE_ATTR_RW(auto_online_blocks);
 
+#ifdef CONFIG_CRASH_HOTPLUG
+#include <linux/kexec.h>
+static ssize_t crash_hotplug_show(struct device *dev,
+				       struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", crash_check_hotplug_support());
+}
+static DEVICE_ATTR_RO(crash_hotplug);
+#endif
+
 /*
  * Some architectures will have custom drivers to do this, and
  * will not need to do it from userspace.  The fake hot-add code
@@ -546,7 +628,9 @@ static ssize_t hard_offline_page_store(struct device *dev,
 	if (kstrtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
-	ret = memory_failure(pfn, 0);
+	ret = memory_failure(pfn, MF_SW_SIMULATED);
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
 	return ret ? ret : count;
 }
 
@@ -565,7 +649,7 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
  *
  * Called under device_hotplug_lock.
  */
-static struct memory_block *find_memory_block_by_id(unsigned long block_id)
+struct memory_block *find_memory_block_by_id(unsigned long block_id)
 {
 	struct memory_block *mem;
 
@@ -578,9 +662,9 @@ static struct memory_block *find_memory_block_by_id(unsigned long block_id)
 /*
  * Called under device_hotplug_lock.
  */
-struct memory_block *find_memory_block(struct mem_section *section)
+struct memory_block *find_memory_block(unsigned long section_nr)
 {
-	unsigned long block_id = memory_block_id(__section_nr(section));
+	unsigned long block_id = memory_block_id(section_nr);
 
 	return find_memory_block_by_id(block_id);
 }
@@ -605,11 +689,7 @@ static const struct attribute_group *memory_memblk_attr_groups[] = {
 	NULL,
 };
 
-/*
- * register_memory - Setup a sysfs device for a memory block
- */
-static
-int register_memory(struct memory_block *memory)
+static int __add_memory_block(struct memory_block *memory)
 {
 	int ret;
 
@@ -626,15 +706,91 @@ int register_memory(struct memory_block *memory)
 	}
 	ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory,
 			      GFP_KERNEL));
-	if (ret) {
-		put_device(&memory->dev);
+	if (ret)
 		device_unregister(&memory->dev);
-	}
+
 	return ret;
 }
 
-static int init_memory_block(unsigned long block_id, unsigned long state,
-			     unsigned long nr_vmemmap_pages)
+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.
+	 */
+	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
+/**
+ * memory_block_add_nid_early() - Indicate that early system RAM falling into
+ *				  this memory block device (partially) belongs
+ *				  to the given node.
+ * @mem: The memory block device.
+ * @nid: The node id.
+ *
+ * Indicate that early system RAM falling into this memory block (partially)
+ * belongs to the given node. This will also properly set/adjust mem->zone based
+ * on the zone ranges of the given node.
+ *
+ * Memory hotplug handles this on memory block creation, where we can only have
+ * a single nid span a memory block.
+ */
+void memory_block_add_nid_early(struct memory_block *mem, int nid)
+{
+	if (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 different 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 add_memory_block(unsigned long block_id, int nid, unsigned long state,
+			    struct vmem_altmap *altmap,
+			    struct memory_group *group)
 {
 	struct memory_block *mem;
 	int ret = 0;
@@ -650,37 +806,45 @@ static int init_memory_block(unsigned long block_id, unsigned long state,
 
 	mem->start_section_nr = block_id * sections_per_block;
 	mem->state = state;
-	mem->nid = NUMA_NO_NODE;
-	mem->nr_vmemmap_pages = nr_vmemmap_pages;
-
-	ret = register_memory(mem);
+	mem->nid = nid;
+	mem->altmap = altmap;
+	INIT_LIST_HEAD(&mem->group_next);
 
-	return ret;
-}
+#ifndef CONFIG_NUMA
+	if (state == MEM_ONLINE)
+		/*
+		 * MEM_ONLINE at this point implies early memory. With NUMA,
+		 * we'll determine the zone when setting the node id via
+		 * memory_block_add_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 */
 
-static int add_memory_block(unsigned long base_section_nr)
-{
-	int section_count = 0;
-	unsigned long nr;
+	ret = __add_memory_block(mem);
+	if (ret)
+		return ret;
 
-	for (nr = base_section_nr; nr < base_section_nr + sections_per_block;
-	     nr++)
-		if (present_section_nr(nr))
-			section_count++;
+	if (group) {
+		mem->group = group;
+		list_add(&mem->group_next, &group->memory_blocks);
+	}
 
-	if (section_count == 0)
-		return 0;
-	return init_memory_block(memory_block_id(base_section_nr),
-				 MEM_ONLINE, 0);
+	return 0;
 }
 
-static void unregister_memory(struct memory_block *memory)
+static void remove_memory_block(struct memory_block *memory)
 {
 	if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
 		return;
 
 	WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL);
 
+	if (memory->group) {
+		list_del(&memory->group_next);
+		memory->group = NULL;
+	}
+
 	/* drop the ref. we got via find_memory_block() */
 	put_device(&memory->dev);
 	device_unregister(&memory->dev);
@@ -694,7 +858,8 @@ static void unregister_memory(struct memory_block *memory)
  * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages)
+				int nid, struct vmem_altmap *altmap,
+				struct memory_group *group)
 {
 	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
 	unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
@@ -707,7 +872,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
 		return -EINVAL;
 
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
-		ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages);
+		ret = add_memory_block(block_id, nid, MEM_OFFLINE, altmap, group);
 		if (ret)
 			break;
 	}
@@ -718,7 +883,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
 			mem = find_memory_block_by_id(block_id);
 			if (WARN_ON_ONCE(!mem))
 				continue;
-			unregister_memory(mem);
+			remove_memory_block(mem);
 		}
 	}
 	return ret;
@@ -746,17 +911,12 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 		mem = find_memory_block_by_id(block_id);
 		if (WARN_ON_ONCE(!mem))
 			continue;
+		num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem));
 		unregister_memory_block_under_nodes(mem);
-		unregister_memory(mem);
+		remove_memory_block(mem);
 	}
 }
 
-/* return true if the memory block is offlined, otherwise, return false */
-bool is_memblock_offlined(struct memory_block *mem)
-{
-	return mem->state == MEM_OFFLINE;
-}
-
 static struct attribute *memory_root_attrs[] = {
 #ifdef CONFIG_ARCH_MEMORY_PROBE
 	&dev_attr_probe.attr,
@@ -769,6 +929,9 @@ static struct attribute *memory_root_attrs[] = {
 
 	&dev_attr_block_size_bytes.attr,
 	&dev_attr_auto_online_blocks.attr,
+#ifdef CONFIG_CRASH_HOTPLUG
+	&dev_attr_crash_hotplug.attr,
+#endif
 	NULL
 };
 
@@ -789,7 +952,7 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 void __init memory_dev_init(void)
 {
 	int ret;
-	unsigned long block_sz, nr;
+	unsigned long block_sz, block_id, nr;
 
 	/* Validate the configured memory block size */
 	block_sz = memory_block_size_bytes();
@@ -802,15 +965,23 @@ void __init memory_dev_init(void)
 		panic("%s() failed to register subsystem: %d\n", __func__, ret);
 
 	/*
-	 * Create entries for memory sections that were found
-	 * during boot and have been initialized
+	 * Create entries for memory sections that were found during boot
+	 * and have been initialized. Use @block_id to track the last
+	 * handled block and initialize it to an invalid value (ULONG_MAX)
+	 * to bypass the block ID matching check for the first present
+	 * block so that it can be covered.
 	 */
-	for (nr = 0; nr <= __highest_present_section_nr;
-	     nr += sections_per_block) {
-		ret = add_memory_block(nr);
-		if (ret)
-			panic("%s() failed to add memory block: %d\n", __func__,
-			      ret);
+	block_id = ULONG_MAX;
+	for_each_present_section_nr(0, nr) {
+		if (block_id != ULONG_MAX && memory_block_id(nr) == block_id)
+			continue;
+
+		block_id = memory_block_id(nr);
+		ret = add_memory_block(block_id, NUMA_NO_NODE, MEM_ONLINE, NULL, NULL);
+		if (ret) {
+			panic("%s() failed to add memory block: %d\n",
+			      __func__, ret);
+		}
 	}
 }
 
@@ -891,3 +1062,189 @@ int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
 	return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
 				for_each_memory_block_cb);
 }
+
+/*
+ * This is an internal helper to unify allocation and initialization of
+ * memory groups. Note that the passed memory group will be copied to a
+ * dynamically allocated memory group. After this call, the passed
+ * memory group should no longer be used.
+ */
+static int memory_group_register(struct memory_group group)
+{
+	struct memory_group *new_group;
+	uint32_t mgid;
+	int ret;
+
+	if (!node_possible(group.nid))
+		return -EINVAL;
+
+	new_group = kzalloc(sizeof(group), GFP_KERNEL);
+	if (!new_group)
+		return -ENOMEM;
+	*new_group = group;
+	INIT_LIST_HEAD(&new_group->memory_blocks);
+
+	ret = xa_alloc(&memory_groups, &mgid, new_group, xa_limit_31b,
+		       GFP_KERNEL);
+	if (ret) {
+		kfree(new_group);
+		return ret;
+	} else if (group.is_dynamic) {
+		xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC);
+	}
+	return mgid;
+}
+
+/**
+ * memory_group_register_static() - Register a static memory group.
+ * @nid: The node id.
+ * @max_pages: The maximum number of pages we'll have in this static memory
+ *	       group.
+ *
+ * Register a new static memory group and return the memory group id.
+ * All memory in the group belongs to a single unit, such as a DIMM. All
+ * memory belonging to a static memory group is added in one go to be removed
+ * in one go -- it's static.
+ *
+ * Returns an error if out of memory, if the node id is invalid, if no new
+ * memory groups can be registered, or if max_pages is invalid (0). Otherwise,
+ * returns the new memory group id.
+ */
+int memory_group_register_static(int nid, unsigned long max_pages)
+{
+	struct memory_group group = {
+		.nid = nid,
+		.s = {
+			.max_pages = max_pages,
+		},
+	};
+
+	if (!max_pages)
+		return -EINVAL;
+	return memory_group_register(group);
+}
+EXPORT_SYMBOL_GPL(memory_group_register_static);
+
+/**
+ * memory_group_register_dynamic() - Register a dynamic memory group.
+ * @nid: The node id.
+ * @unit_pages: Unit in pages in which is memory added/removed in this dynamic
+ *		memory group.
+ *
+ * Register a new dynamic memory group and return the memory group id.
+ * Memory within a dynamic memory group is added/removed dynamically
+ * in unit_pages.
+ *
+ * Returns an error if out of memory, if the node id is invalid, if no new
+ * memory groups can be registered, or if unit_pages is invalid (0, not a
+ * power of two, smaller than a single memory block). Otherwise, returns the
+ * new memory group id.
+ */
+int memory_group_register_dynamic(int nid, unsigned long unit_pages)
+{
+	struct memory_group group = {
+		.nid = nid,
+		.is_dynamic = true,
+		.d = {
+			.unit_pages = unit_pages,
+		},
+	};
+
+	if (!unit_pages || !is_power_of_2(unit_pages) ||
+	    unit_pages < PHYS_PFN(memory_block_size_bytes()))
+		return -EINVAL;
+	return memory_group_register(group);
+}
+EXPORT_SYMBOL_GPL(memory_group_register_dynamic);
+
+/**
+ * memory_group_unregister() - Unregister a memory group.
+ * @mgid: the memory group id
+ *
+ * Unregister a memory group. If any memory block still belongs to this
+ * memory group, unregistering will fail.
+ *
+ * Returns -EINVAL if the memory group id is invalid, returns -EBUSY if some
+ * memory blocks still belong to this memory group and returns 0 if
+ * unregistering succeeded.
+ */
+int memory_group_unregister(int mgid)
+{
+	struct memory_group *group;
+
+	if (mgid < 0)
+		return -EINVAL;
+
+	group = xa_load(&memory_groups, mgid);
+	if (!group)
+		return -EINVAL;
+	if (!list_empty(&group->memory_blocks))
+		return -EBUSY;
+	xa_erase(&memory_groups, mgid);
+	kfree(group);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(memory_group_unregister);
+
+/*
+ * This is an internal helper only to be used in core memory hotplug code to
+ * lookup a memory group. We don't care about locking, as we don't expect a
+ * memory group to get unregistered while adding memory to it -- because
+ * the group and the memory is managed by the same driver.
+ */
+struct memory_group *memory_group_find_by_id(int mgid)
+{
+	return xa_load(&memory_groups, mgid);
+}
+
+/*
+ * This is an internal helper only to be used in core memory hotplug code to
+ * walk all dynamic memory groups excluding a given memory group, either
+ * belonging to a specific node, or belonging to any node.
+ */
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+			       struct memory_group *excluded, void *arg)
+{
+	struct memory_group *group;
+	unsigned long index;
+	int ret = 0;
+
+	xa_for_each_marked(&memory_groups, index, group,
+			   MEMORY_GROUP_MARK_DYNAMIC) {
+		if (group == excluded)
+			continue;
+#ifdef CONFIG_NUMA
+		if (nid != NUMA_NO_NODE && group->nid != nid)
+			continue;
+#endif /* CONFIG_NUMA */
+		ret = func(group, arg);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+	const unsigned long block_id = pfn_to_block_id(pfn);
+	struct memory_block *mem = find_memory_block_by_id(block_id);
+
+	if (mem)
+		atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+	const unsigned long block_id = pfn_to_block_id(pfn);
+	struct memory_block *mem = find_memory_block_by_id(block_id);
+
+	if (mem)
+		atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+static unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+	return atomic_long_read(&mem->nr_hwpoison);
+}
+#endif