Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The remainder of the main mm/ queue.

  143 patches.

  Subsystems affected by this patch series (all mm): pagecache, hugetlb,
  userfaultfd, vmscan, compaction, migration, cma, ksm, vmstat, mmap,
  kconfig, util, memory-hotplug, zswap, zsmalloc, highmem, cleanups, and
  kfence"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (143 commits)
  kfence: use power-efficient work queue to run delayed work
  kfence: maximize allocation wait timeout duration
  kfence: await for allocation using wait_event
  kfence: zero guard page after out-of-bounds access
  mm/process_vm_access.c: remove duplicate include
  mm/mempool: minor coding style tweaks
  mm/highmem.c: fix coding style issue
  btrfs: use memzero_page() instead of open coded kmap pattern
  iov_iter: lift memzero_page() to highmem.h
  mm/zsmalloc: use BUG_ON instead of if condition followed by BUG.
  mm/zswap.c: switch from strlcpy to strscpy
  arm64/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  x86/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  mm,memory_hotplug: add kernel boot option to enable memmap_on_memory
  acpi,memhotplug: enable MHP_MEMMAP_ON_MEMORY when supported
  mm,memory_hotplug: allocate memmap from the added memory range
  mm,memory_hotplug: factor out adjusting present pages into adjust_present_page_count()
  mm,memory_hotplug: relax fully spanned sections check
  drivers/base/memory: introduce memory_block_{online,offline}
  mm/memory_hotplug: remove broken locking of zone PCP structures during hot remove
  ...

2 files changed, 89 insertions, 17 deletions

diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index b02fd51e5589..8cc195c4c861 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -171,6 +171,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 	acpi_handle handle = mem_device->device->handle;
 	int result, num_enabled = 0;
 	struct acpi_memory_info *info;
+	mhp_t mhp_flags = MHP_NONE;
 	int node;
 
 	node = acpi_get_node(handle);
@@ -194,8 +195,10 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (node < 0)
 			node = memory_add_physaddr_to_nid(info->start_addr);
 
+		if (mhp_supports_memmap_on_memory(info->length))
+			mhp_flags |= MHP_MEMMAP_ON_MEMORY;
 		result = __add_memory(node, info->start_addr, info->length,
-				      MHP_NONE);
+				      mhp_flags);
 
 		/*
 		 * If the memory block has been used by the kernel, add_memory()
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f35298425575..b31b3af5c490 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -169,30 +169,98 @@ int memory_notify(unsigned long val, void *v)
 	return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
+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;
+	struct zone *zone;
+	int ret;
+
+	zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages);
+
+	/*
+	 * Although vmemmap pages have a different lifecycle than the pages
+	 * they describe (they remain until the memory is unplugged), doing
+	 * their initialization and accounting at memory onlining/offlining
+	 * stage helps to keep accounting easier to follow - e.g vmemmaps
+	 * belong to the same zone as the memory they backed.
+	 */
+	if (nr_vmemmap_pages) {
+		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
+		if (ret)
+			return ret;
+	}
+
+	ret = online_pages(start_pfn + nr_vmemmap_pages,
+			   nr_pages - nr_vmemmap_pages, zone);
+	if (ret) {
+		if (nr_vmemmap_pages)
+			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+		return ret;
+	}
+
+	/*
+	 * Account once onlining succeeded. If the zone was unpopulated, it is
+	 * now already properly populated.
+	 */
+	if (nr_vmemmap_pages)
+		adjust_present_page_count(zone, nr_vmemmap_pages);
+
+	return ret;
+}
+
+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;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+
+	/*
+	 * Unaccount before offlining, such that unpopulated zone and kthreads
+	 * can properly be torn down in offline_pages().
+	 */
+	if (nr_vmemmap_pages)
+		adjust_present_page_count(zone, -nr_vmemmap_pages);
+
+	ret = offline_pages(start_pfn + nr_vmemmap_pages,
+			    nr_pages - nr_vmemmap_pages);
+	if (ret) {
+		/* offline_pages() failed. Account back. */
+		if (nr_vmemmap_pages)
+			adjust_present_page_count(zone, nr_vmemmap_pages);
+		return ret;
+	}
+
+	if (nr_vmemmap_pages)
+		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
+
+	return ret;
+}
+
 /*
  * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(unsigned long start_section_nr, unsigned long action,
-		    int online_type, int nid)
+memory_block_action(struct memory_block *mem, unsigned long action)
 {
-	unsigned long start_pfn;
-	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	int ret;
 
-	start_pfn = section_nr_to_pfn(start_section_nr);
-
 	switch (action) {
 	case MEM_ONLINE:
-		ret = online_pages(start_pfn, nr_pages, online_type, nid);
+		ret = memory_block_online(mem);
 		break;
 	case MEM_OFFLINE:
-		ret = offline_pages(start_pfn, nr_pages);
+		ret = memory_block_offline(mem);
 		break;
 	default:
 		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
-		     "%ld\n", __func__, start_section_nr, action, action);
+		     "%ld\n", __func__, mem->start_section_nr, action, action);
 		ret = -EINVAL;
 	}
 
@@ -210,9 +278,7 @@ static int memory_block_change_state(struct memory_block *mem,
 	if (to_state == MEM_OFFLINE)
 		mem->state = MEM_GOING_OFFLINE;
 
-	ret = memory_block_action(mem->start_section_nr, to_state,
-				  mem->online_type, mem->nid);
-
+	ret = memory_block_action(mem, to_state);
 	mem->state = ret ? from_state_req : to_state;
 
 	return ret;
@@ -567,7 +633,8 @@ int register_memory(struct memory_block *memory)
 	return ret;
 }
 
-static int init_memory_block(unsigned long block_id, unsigned long state)
+static int init_memory_block(unsigned long block_id, unsigned long state,
+			     unsigned long nr_vmemmap_pages)
 {
 	struct memory_block *mem;
 	int ret = 0;
@@ -584,6 +651,7 @@ 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);
 
@@ -603,7 +671,7 @@ static int add_memory_block(unsigned long base_section_nr)
 	if (section_count == 0)
 		return 0;
 	return init_memory_block(memory_block_id(base_section_nr),
-				 MEM_ONLINE);
+				 MEM_ONLINE, 0);
 }
 
 static void unregister_memory(struct memory_block *memory)
@@ -625,7 +693,8 @@ static void unregister_memory(struct memory_block *memory)
  *
  * Called under device_hotplug_lock.
  */
-int create_memory_block_devices(unsigned long start, unsigned long size)
+int create_memory_block_devices(unsigned long start, unsigned long size,
+				unsigned long vmemmap_pages)
 {
 	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));
@@ -638,7 +707,7 @@ 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);
+		ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages);
 		if (ret)
 			break;
 	}