1 files changed, 145 insertions, 189 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 96d34ebb20a9..9983017ecbe0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -90,6 +90,12 @@ DEFINE_ENTRY(pud, pud, init)
 DEFINE_ENTRY(pmd, pmd, init)
 DEFINE_ENTRY(pte, pte, init)
 
+static inline pgprot_t prot_sethuge(pgprot_t prot)
+{
+	WARN_ON_ONCE(pgprot_val(prot) & _PAGE_PAT);
+
+	return __pgprot(pgprot_val(prot) | _PAGE_PSE);
+}
 
 /*
  * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
@@ -110,7 +116,6 @@ int force_personality32;
 /*
  * noexec32=on|off
  * Control non executable heap for 32bit processes.
- * To control the stack too use noexec=off
  *
  * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
  * off	PROT_READ implies PROT_EXEC
@@ -219,6 +224,24 @@ static void sync_global_pgds(unsigned long start, unsigned long end)
 }
 
 /*
+ * Make kernel mappings visible in all page tables in the system.
+ * This is necessary except when the init task populates kernel mappings
+ * during the boot process. In that case, all processes originating from
+ * the init task copies the kernel mappings, so there is no issue.
+ * Otherwise, missing synchronization could lead to kernel crashes due
+ * to missing page table entries for certain kernel mappings.
+ *
+ * Synchronization is performed at the top level, which is the PGD in
+ * 5-level paging systems. But in 4-level paging systems, however,
+ * pgd_populate() is a no-op, so synchronization is done at the P4D level.
+ * sync_global_pgds() handles this difference between paging levels.
+ */
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	sync_global_pgds(start, end);
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -464,7 +487,7 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_ACPI))
 				set_pte_init(pte, __pte(0), init);
 			continue;
 		}
@@ -481,9 +504,6 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 			continue;
 		}
 
-		if (0)
-			pr_info("   pte=%p addr=%lx pte=%016lx\n", pte, paddr,
-				pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte);
 		pages++;
 		set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init);
 		paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE;
@@ -519,13 +539,13 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_ACPI))
 				set_pmd_init(pmd, __pmd(0), init);
 			continue;
 		}
 
 		if (!pmd_none(*pmd)) {
-			if (!pmd_large(*pmd)) {
+			if (!pmd_leaf(*pmd)) {
 				spin_lock(&init_mm.page_table_lock);
 				pte = (pte_t *)pmd_page_vaddr(*pmd);
 				paddr_last = phys_pte_init(pte, paddr,
@@ -558,9 +578,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 		if (page_size_mask & (1<<PG_LEVEL_2M)) {
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
-			set_pte_init((pte_t *)pmd,
-				     pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT,
-					     __pgprot(pgprot_val(prot) | _PAGE_PSE)),
+			set_pmd_init(pmd,
+				     pfn_pmd(paddr >> PAGE_SHIFT, prot_sethuge(prot)),
 				     init);
 			spin_unlock(&init_mm.page_table_lock);
 			paddr_last = paddr_next;
@@ -607,13 +626,13 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_ACPI))
 				set_pud_init(pud, __pud(0), init);
 			continue;
 		}
 
 		if (!pud_none(*pud)) {
-			if (!pud_large(*pud)) {
+			if (!pud_leaf(*pud)) {
 				pmd = pmd_offset(pud, 0);
 				paddr_last = phys_pmd_init(pmd, paddr,
 							   paddr_end,
@@ -645,12 +664,8 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
 		if (page_size_mask & (1<<PG_LEVEL_1G)) {
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
-
-			prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE);
-
-			set_pte_init((pte_t *)pud,
-				     pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
-					     prot),
+			set_pud_init(pud,
+				     pfn_pud(paddr >> PAGE_SHIFT, prot_sethuge(prot)),
 				     init);
 			spin_unlock(&init_mm.page_table_lock);
 			paddr_last = paddr_next;
@@ -698,7 +713,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
-					     E820_TYPE_RESERVED_KERN))
+					     E820_TYPE_ACPI))
 				set_p4d_init(p4d, __p4d(0), init);
 			continue;
 		}
@@ -805,12 +820,17 @@ kernel_physical_mapping_change(unsigned long paddr_start,
 }
 
 #ifndef CONFIG_NUMA
-void __init initmem_init(void)
+static __always_inline void x86_numa_init(void)
 {
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
 }
 #endif
 
+void __init initmem_init(void)
+{
+	x86_numa_init();
+}
+
 void __init paging_init(void)
 {
 	sparse_init();
@@ -827,7 +847,6 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define PAGE_UNUSED 0xFD
 
 /*
@@ -902,6 +921,8 @@ static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end
 
 static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
 {
+	const unsigned long page = ALIGN_DOWN(start, PMD_SIZE);
+
 	vmemmap_flush_unused_pmd();
 
 	/*
@@ -914,8 +935,7 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long
 	 * Mark with PAGE_UNUSED the unused parts of the new memmap range
 	 */
 	if (!IS_ALIGNED(start, PMD_SIZE))
-		memset((void *)start, PAGE_UNUSED,
-			start - ALIGN_DOWN(start, PMD_SIZE));
+		memset((void *)page, PAGE_UNUSED, start - page);
 
 	/*
 	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
@@ -925,7 +945,6 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long
 	if (!IS_ALIGNED(end, PMD_SIZE))
 		unused_pmd_start = end;
 }
-#endif
 
 /*
  * Memory hotplug specific functions
@@ -949,14 +968,27 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params)
 {
+	unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	int ret;
 
+	if (WARN_ON_ONCE(end > DIRECT_MAP_PHYSMEM_END))
+		return -ERANGE;
+
 	ret = __add_pages(nid, start_pfn, nr_pages, params);
 	WARN_ON_ONCE(ret);
 
-	/* update max_pfn, max_low_pfn and high_memory */
-	update_end_of_memory_vars(start_pfn << PAGE_SHIFT,
-				  nr_pages << PAGE_SHIFT);
+	/*
+	 * Special case: add_pages() is called by memremap_pages() for adding device
+	 * private pages. Do not bump up max_pfn in the device private path,
+	 * because max_pfn changes affect dma_addressing_limited().
+	 *
+	 * dma_addressing_limited() returning true when max_pfn is the device's
+	 * addressable memory can force device drivers to use bounce buffers
+	 * and impact their performance negatively:
+	 */
+	if (!params->pgmap)
+		/* update max_pfn, max_low_pfn and high_memory */
+		update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
 
 	return ret;
 }
@@ -972,24 +1004,32 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return add_pages(nid, start_pfn, nr_pages, params);
 }
 
-static void __meminit free_pagetable(struct page *page, int order)
+static void free_reserved_pages(struct page *page, unsigned long nr_pages)
 {
-	unsigned long magic;
-	unsigned int nr_pages = 1 << order;
+	while (nr_pages--)
+		free_reserved_page(page++);
+}
 
+static void __meminit free_pagetable(struct page *page, int order)
+{
 	/* bootmem page has reserved flag */
 	if (PageReserved(page)) {
-		__ClearPageReserved(page);
+		unsigned long nr_pages = 1 << order;
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+		enum bootmem_type type = bootmem_type(page);
 
-		magic = page->index;
-		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
+		if (type == SECTION_INFO || type == MIX_SECTION_INFO) {
 			while (nr_pages--)
 				put_page_bootmem(page++);
-		} else
-			while (nr_pages--)
-				free_reserved_page(page++);
-	} else
-		free_pages((unsigned long)page_address(page), order);
+		} else {
+			free_reserved_pages(page, nr_pages);
+		}
+#else
+		free_reserved_pages(page, nr_pages);
+#endif
+	} else {
+		pagetable_free(page_ptdesc(page));
+	}
 }
 
 static void __meminit free_hugepage_table(struct page *page,
@@ -1012,7 +1052,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 			return;
 	}
 
-	/* free a pte talbe */
+	/* free a pte table */
 	free_pagetable(pmd_page(*pmd), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pmd_clear(pmd);
@@ -1030,7 +1070,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 			return;
 	}
 
-	/* free a pmd talbe */
+	/* free a pmd table */
 	free_pagetable(pud_page(*pud), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pud_clear(pud);
@@ -1048,7 +1088,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
 			return;
 	}
 
-	/* free a pud talbe */
+	/* free a pud table */
 	free_pagetable(p4d_page(*p4d), 0);
 	spin_lock(&init_mm.page_table_lock);
 	p4d_clear(p4d);
@@ -1113,7 +1153,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 		if (!pmd_present(*pmd))
 			continue;
 
-		if (pmd_large(*pmd)) {
+		if (pmd_leaf(*pmd)) {
 			if (IS_ALIGNED(addr, PMD_SIZE) &&
 			    IS_ALIGNED(next, PMD_SIZE)) {
 				if (!direct)
@@ -1124,16 +1164,13 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				pmd_clear(pmd);
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
-			}
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-			else if (vmemmap_pmd_is_unused(addr, next)) {
+			} else if (vmemmap_pmd_is_unused(addr, next)) {
 					free_hugepage_table(pmd_page(*pmd),
 							    altmap);
 					spin_lock(&init_mm.page_table_lock);
 					pmd_clear(pmd);
 					spin_unlock(&init_mm.page_table_lock);
 			}
-#endif
 			continue;
 		}
 
@@ -1162,7 +1199,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 		if (!pud_present(*pud))
 			continue;
 
-		if (pud_large(*pud) &&
+		if (pud_leaf(*pud) &&
 		    IS_ALIGNED(addr, PUD_SIZE) &&
 		    IS_ALIGNED(next, PUD_SIZE)) {
 			spin_lock(&init_mm.page_table_lock);
@@ -1196,7 +1233,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
 		if (!p4d_present(*p4d))
 			continue;
 
-		BUILD_BUG_ON(p4d_large(*p4d));
+		BUILD_BUG_ON(p4d_leaf(*p4d));
 
 		pud_base = pud_offset(p4d, 0);
 		remove_pud_table(pud_base, addr, next, altmap, direct);
@@ -1240,8 +1277,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct,
 void __ref vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
-	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
-	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
 
 	remove_pagetable(start, end, false, altmap);
 }
@@ -1269,7 +1306,7 @@ static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
@@ -1287,7 +1324,7 @@ static void __init preallocate_vmalloc_pages(void)
 	unsigned long addr;
 	const char *lvl;
 
-	for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+	for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
 		pgd_t *pgd = pgd_offset_k(addr);
 		p4d_t *p4d;
 		pud_t *pud;
@@ -1327,14 +1364,15 @@ failed:
 	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
 }
 
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	pci_iommu_alloc();
+}
 
+void __init mem_init(void)
+{
 	/* clear_bss() already clear the empty_zero_page */
 
-	/* this will put all memory onto the freelists */
-	memblock_free_all();
 	after_bootmem = 1;
 	x86_init.hyper.init_after_bootmem();
 
@@ -1353,18 +1391,6 @@ void __init mem_init(void)
 	preallocate_vmalloc_pages();
 }
 
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask)
-{
-	/*
-	 * More CPUs always led to greater speedups on tested systems, up to
-	 * all the nodes' CPUs.  Use all since the system is otherwise idle
-	 * now.
-	 */
-	return max_t(int, cpumask_weight(node_cpumask), 1);
-}
-#endif
-
 int kernel_set_to_readonly;
 
 void mark_rodata_ro(void)
@@ -1411,49 +1437,6 @@ void mark_rodata_ro(void)
 				(void *)text_end, (void *)rodata_start);
 	free_kernel_image_pages("unused kernel image (rodata/data gap)",
 				(void *)rodata_end, (void *)_sdata);
-
-	debug_checkwx();
-}
-
-int kern_addr_valid(unsigned long addr)
-{
-	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	if (above != 0 && above != -1UL)
-		return 0;
-
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
-		return 0;
-
-	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
-		return 0;
-
-	pud = pud_offset(p4d, addr);
-	if (!pud_present(*pud))
-		return 0;
-
-	if (pud_large(*pud))
-		return pfn_valid(pud_pfn(*pud));
-
-	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
-		return 0;
-
-	if (pmd_large(*pmd))
-		return pfn_valid(pmd_pfn(*pmd));
-
-	pte = pte_offset_kernel(pmd, addr);
-	if (pte_none(*pte))
-		return 0;
-
-	return pfn_valid(pte_pfn(*pte));
 }
 
 /*
@@ -1496,16 +1479,21 @@ static unsigned long probe_memory_block_size(void)
 	}
 
 	/*
-	 * Use max block size to minimize overhead on bare metal, where
-	 * alignment for memory hotplug isn't a concern.
+	 * When hotplug alignment is not a concern, maximize blocksize
+	 * to minimize overhead. Otherwise, align to the lesser of advice
+	 * alignment and end of memory alignment.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+	bz = memory_block_advised_max_size();
+	if (!bz) {
 		bz = MAX_BLOCK_SIZE;
-		goto done;
+		if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+			goto done;
+	} else {
+		bz = max(min(bz, MAX_BLOCK_SIZE), MIN_MEMORY_BLOCK_SIZE);
 	}
 
 	/* Find the largest allowed block size that aligns to memory end */
-	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+	for (; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
 		if (IS_ALIGNED(boot_mem_end, bz))
 			break;
 	}
@@ -1524,7 +1512,6 @@ unsigned long memory_block_size_bytes(void)
 	return memory_block_size_probed;
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
  */
@@ -1532,72 +1519,44 @@ static long __meminitdata addr_start, addr_end;
 static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
-static int __meminit vmemmap_populate_hugepages(unsigned long start,
-		unsigned long end, int node, struct vmem_altmap *altmap)
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
 {
-	unsigned long addr;
-	unsigned long next;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-
-	for (addr = start; addr < end; addr = next) {
-		next = pmd_addr_end(addr, end);
-
-		pgd = vmemmap_pgd_populate(addr, node);
-		if (!pgd)
-			return -ENOMEM;
-
-		p4d = vmemmap_p4d_populate(pgd, addr, node);
-		if (!p4d)
-			return -ENOMEM;
-
-		pud = vmemmap_pud_populate(p4d, addr, node);
-		if (!pud)
-			return -ENOMEM;
-
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			void *p;
-
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
-			if (p) {
-				pte_t entry;
-
-				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-						PAGE_KERNEL_LARGE);
-				set_pmd(pmd, __pmd(pte_val(entry)));
+	pte_t entry;
+
+	entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
+			PAGE_KERNEL_LARGE);
+	set_pmd(pmd, __pmd(pte_val(entry)));
+
+	/* check to see if we have contiguous blocks */
+	if (p_end != p || node_start != node) {
+		if (p_start)
+			pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+				addr_start, addr_end-1, p_start, p_end-1, node_start);
+		addr_start = addr;
+		node_start = node;
+		p_start = p;
+	}
 
-				/* check to see if we have contiguous blocks */
-				if (p_end != p || node_start != node) {
-					if (p_start)
-						pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-						       addr_start, addr_end-1, p_start, p_end-1, node_start);
-					addr_start = addr;
-					node_start = node;
-					p_start = p;
-				}
+	addr_end = addr + PMD_SIZE;
+	p_end = p + PMD_SIZE;
 
-				addr_end = addr + PMD_SIZE;
-				p_end = p + PMD_SIZE;
+	if (!IS_ALIGNED(addr, PMD_SIZE) ||
+		!IS_ALIGNED(next, PMD_SIZE))
+		vmemmap_use_new_sub_pmd(addr, next);
+}
 
-				if (!IS_ALIGNED(addr, PMD_SIZE) ||
-				    !IS_ALIGNED(next, PMD_SIZE))
-					vmemmap_use_new_sub_pmd(addr, next);
+int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+				unsigned long addr, unsigned long next)
+{
+	int large = pmd_leaf(*pmd);
 
-				continue;
-			} else if (altmap)
-				return -ENOMEM; /* no fallback */
-		} else if (pmd_large(*pmd)) {
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
-			vmemmap_use_sub_pmd(addr, next);
-			continue;
-		}
-		if (vmemmap_populate_basepages(addr, next, node, NULL))
-			return -ENOMEM;
+	if (pmd_leaf(*pmd)) {
+		vmemmap_verify((pte_t *)pmd, node, addr, next);
+		vmemmap_use_sub_pmd(addr, next);
 	}
-	return 0;
+
+	return large;
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -1605,8 +1564,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
-	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
 
 	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
@@ -1661,11 +1620,14 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!boot_cpu_has(X86_FEATURE_PSE)) {
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd)) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			continue;
+		}
+
+		if (!boot_cpu_has(X86_FEATURE_PSE) || !pmd_leaf(*pmd)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
-			pmd = pmd_offset(pud, addr);
-			if (pmd_none(*pmd))
-				continue;
 			get_page_bootmem(section_nr, pmd_page(*pmd),
 					 MIX_SECTION_INFO);
 
@@ -1676,12 +1638,7 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 					 SECTION_INFO);
 		} else {
 			next = pmd_addr_end(addr, end);
-
-			pmd = pmd_offset(pud, addr);
-			if (pmd_none(*pmd))
-				continue;
-
-			nr_pmd_pages = 1 << get_order(PMD_SIZE);
+			nr_pmd_pages = (next - addr) >> PAGE_SHIFT;
 			page = pmd_page(*pmd);
 			while (nr_pmd_pages--)
 				get_page_bootmem(section_nr, page++,
@@ -1701,4 +1658,3 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
-#endif