1 files changed, 67 insertions, 56 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7e177856ee4f..fdb6cab524f0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -469,7 +469,7 @@ 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;
 		}
@@ -524,7 +524,7 @@ 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;
 		}
@@ -611,7 +611,7 @@ 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;
 		}
@@ -698,7 +698,7 @@ 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 +805,17 @@ kernel_physical_mapping_change(unsigned long paddr_start,
 }
 
 #ifndef CONFIG_NUMA
-void __init initmem_init(void)
+static 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 +832,6 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define PAGE_UNUSED 0xFD
 
 /*
@@ -926,7 +930,6 @@ 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
@@ -950,14 +953,27 @@ 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;
 }
@@ -973,24 +989,32 @@ 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
+		} else {
+			free_reserved_pages(page, nr_pages);
+		}
+#else
+		free_reserved_pages(page, nr_pages);
+#endif
+	} else {
 		free_pages((unsigned long)page_address(page), order);
+	}
 }
 
 static void __meminit free_hugepage_table(struct page *page,
@@ -1125,16 +1149,13 @@ 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;
 		}
 
@@ -1328,14 +1349,15 @@ 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();
 
@@ -1354,18 +1376,6 @@ 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)
@@ -1454,16 +1464,21 @@ 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;
 	}
@@ -1482,7 +1497,6 @@ 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.
  */
@@ -1591,11 +1605,14 @@ 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);
 
@@ -1606,12 +1623,7 @@ 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++,
@@ -1631,4 +1643,3 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
-#endif