Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Peter Anvin:
 "This is a huge set of several partly interrelated (and concurrently
  developed) changes, which is why the branch history is messier than
  one would like.

  The *really* big items are two humonguous patchsets mostly developed
  by Yinghai Lu at my request, which completely revamps the way we
  create initial page tables.  In particular, rather than estimating how
  much memory we will need for page tables and then build them into that
  memory -- a calculation that has shown to be incredibly fragile -- we
  now build them (on 64 bits) with the aid of a "pseudo-linear mode" --
  a #PF handler which creates temporary page tables on demand.

  This has several advantages:

  1. It makes it much easier to support things that need access to data
     very early (a followon patchset uses this to load microcode way
     early in the kernel startup).

  2. It allows the kernel and all the kernel data objects to be invoked
     from above the 4 GB limit.  This allows kdump to work on very large
     systems.

  3. It greatly reduces the difference between Xen and native (Xen's
     equivalent of the #PF handler are the temporary page tables created
     by the domain builder), eliminating a bunch of fragile hooks.

  The patch series also gets us a bit closer to W^X.

  Additional work in this pull is the 64-bit get_user() work which you
  were also involved with, and a bunch of cleanups/speedups to
  __phys_addr()/__pa()."

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (105 commits)
  x86, mm: Move reserving low memory later in initialization
  x86, doc: Clarify the use of asm("%edx") in uaccess.h
  x86, mm: Redesign get_user with a __builtin_choose_expr hack
  x86: Be consistent with data size in getuser.S
  x86, mm: Use a bitfield to mask nuisance get_user() warnings
  x86/kvm: Fix compile warning in kvm_register_steal_time()
  x86-32: Add support for 64bit get_user()
  x86-32, mm: Remove reference to alloc_remap()
  x86-32, mm: Remove reference to resume_map_numa_kva()
  x86-32, mm: Rip out x86_32 NUMA remapping code
  x86/numa: Use __pa_nodebug() instead
  x86: Don't panic if can not alloc buffer for swiotlb
  mm: Add alloc_bootmem_low_pages_nopanic()
  x86, 64bit, mm: hibernate use generic mapping_init
  x86, 64bit, mm: Mark data/bss/brk to nx
  x86: Merge early kernel reserve for 32bit and 64bit
  x86: Add Crash kernel low reservation
  x86, kdump: Remove crashkernel range find limit for 64bit
  memblock: Add memblock_mem_size()
  x86, boot: Not need to check setup_header version for setup_data
  ...

1 files changed, 143 insertions, 112 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index d6eeead43758..3eba7f429880 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -54,6 +54,82 @@
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
 
+#include "mm_internal.h"
+
+static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+			   unsigned long addr, unsigned long end)
+{
+	addr &= PMD_MASK;
+	for (; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+
+		if (!pmd_present(*pmd))
+			set_pmd(pmd, __pmd(addr | pmd_flag));
+	}
+}
+static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		next = (addr & PUD_MASK) + PUD_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, 0);
+			ident_pmd_init(info->pmd_flag, pmd, addr, next);
+			continue;
+		}
+		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
+		if (!pmd)
+			return -ENOMEM;
+		ident_pmd_init(info->pmd_flag, pmd, addr, next);
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+			      unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+	int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+		pud_t *pud;
+
+		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pgd_present(*pgd)) {
+			pud = pud_offset(pgd, 0);
+			result = ident_pud_init(info, pud, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+		result = ident_pud_init(info, pud, addr, next);
+		if (result)
+			return result;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	return 0;
+}
+
 static int __init parse_direct_gbpages_off(char *arg)
 {
 	direct_gbpages = 0;
@@ -302,10 +378,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
 void __init cleanup_highmap(void)
 {
 	unsigned long vaddr = __START_KERNEL_map;
-	unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+	unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE;
 	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
 	pmd_t *pmd = level2_kernel_pgt;
 
+	/*
+	 * Native path, max_pfn_mapped is not set yet.
+	 * Xen has valid max_pfn_mapped set in
+	 *	arch/x86/xen/mmu.c:xen_setup_kernel_pagetable().
+	 */
+	if (max_pfn_mapped)
+		vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+
 	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -314,69 +398,24 @@ void __init cleanup_highmap(void)
 	}
 }
 
-static __ref void *alloc_low_page(unsigned long *phys)
-{
-	unsigned long pfn = pgt_buf_end++;
-	void *adr;
-
-	if (after_bootmem) {
-		adr = (void *)get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
-		*phys = __pa(adr);
-
-		return adr;
-	}
-
-	if (pfn >= pgt_buf_top)
-		panic("alloc_low_page: ran out of memory");
-
-	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	clear_page(adr);
-	*phys  = pfn * PAGE_SIZE;
-	return adr;
-}
-
-static __ref void *map_low_page(void *virt)
-{
-	void *adr;
-	unsigned long phys, left;
-
-	if (after_bootmem)
-		return virt;
-
-	phys = __pa(virt);
-	left = phys & (PAGE_SIZE - 1);
-	adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
-	adr = (void *)(((unsigned long)adr) | left);
-
-	return adr;
-}
-
-static __ref void unmap_low_page(void *adr)
-{
-	if (after_bootmem)
-		return;
-
-	early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
-}
-
 static unsigned long __meminit
 phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 	      pgprot_t prot)
 {
-	unsigned pages = 0;
+	unsigned long pages = 0, next;
 	unsigned long last_map_addr = end;
 	int i;
 
 	pte_t *pte = pte_page + pte_index(addr);
 
-	for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {
-
+	for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) {
+		next = (addr & PAGE_MASK) + PAGE_SIZE;
 		if (addr >= end) {
-			if (!after_bootmem) {
-				for(; i < PTRS_PER_PTE; i++, pte++)
-					set_pte(pte, __pte(0));
-			}
-			break;
+			if (!after_bootmem &&
+			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
+			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
+				set_pte(pte, __pte(0));
+			continue;
 		}
 
 		/*
@@ -414,28 +453,25 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 	int i = pmd_index(address);
 
 	for (; i < PTRS_PER_PMD; i++, address = next) {
-		unsigned long pte_phys;
 		pmd_t *pmd = pmd_page + pmd_index(address);
 		pte_t *pte;
 		pgprot_t new_prot = prot;
 
+		next = (address & PMD_MASK) + PMD_SIZE;
 		if (address >= end) {
-			if (!after_bootmem) {
-				for (; i < PTRS_PER_PMD; i++, pmd++)
-					set_pmd(pmd, __pmd(0));
-			}
-			break;
+			if (!after_bootmem &&
+			    !e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
+			    !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
+				set_pmd(pmd, __pmd(0));
+			continue;
 		}
 
-		next = (address & PMD_MASK) + PMD_SIZE;
-
 		if (pmd_val(*pmd)) {
 			if (!pmd_large(*pmd)) {
 				spin_lock(&init_mm.page_table_lock);
-				pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
+				pte = (pte_t *)pmd_page_vaddr(*pmd);
 				last_map_addr = phys_pte_init(pte, address,
 								end, prot);
-				unmap_low_page(pte);
 				spin_unlock(&init_mm.page_table_lock);
 				continue;
 			}
@@ -464,19 +500,18 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
 			set_pte((pte_t *)pmd,
-				pfn_pte(address >> PAGE_SHIFT,
+				pfn_pte((address & PMD_MASK) >> PAGE_SHIFT,
 					__pgprot(pgprot_val(prot) | _PAGE_PSE)));
 			spin_unlock(&init_mm.page_table_lock);
 			last_map_addr = next;
 			continue;
 		}
 
-		pte = alloc_low_page(&pte_phys);
+		pte = alloc_low_page();
 		last_map_addr = phys_pte_init(pte, address, end, new_prot);
-		unmap_low_page(pte);
 
 		spin_lock(&init_mm.page_table_lock);
-		pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
+		pmd_populate_kernel(&init_mm, pmd, pte);
 		spin_unlock(&init_mm.page_table_lock);
 	}
 	update_page_count(PG_LEVEL_2M, pages);
@@ -492,27 +527,24 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 	int i = pud_index(addr);
 
 	for (; i < PTRS_PER_PUD; i++, addr = next) {
-		unsigned long pmd_phys;
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
 		pgprot_t prot = PAGE_KERNEL;
 
-		if (addr >= end)
-			break;
-
 		next = (addr & PUD_MASK) + PUD_SIZE;
-
-		if (!after_bootmem && !e820_any_mapped(addr, next, 0)) {
-			set_pud(pud, __pud(0));
+		if (addr >= end) {
+			if (!after_bootmem &&
+			    !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) &&
+			    !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN))
+				set_pud(pud, __pud(0));
 			continue;
 		}
 
 		if (pud_val(*pud)) {
 			if (!pud_large(*pud)) {
-				pmd = map_low_page(pmd_offset(pud, 0));
+				pmd = pmd_offset(pud, 0);
 				last_map_addr = phys_pmd_init(pmd, addr, end,
 							 page_size_mask, prot);
-				unmap_low_page(pmd);
 				__flush_tlb_all();
 				continue;
 			}
@@ -541,19 +573,19 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			pages++;
 			spin_lock(&init_mm.page_table_lock);
 			set_pte((pte_t *)pud,
-				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+				pfn_pte((addr & PUD_MASK) >> PAGE_SHIFT,
+					PAGE_KERNEL_LARGE));
 			spin_unlock(&init_mm.page_table_lock);
 			last_map_addr = next;
 			continue;
 		}
 
-		pmd = alloc_low_page(&pmd_phys);
+		pmd = alloc_low_page();
 		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
 					      prot);
-		unmap_low_page(pmd);
 
 		spin_lock(&init_mm.page_table_lock);
-		pud_populate(&init_mm, pud, __va(pmd_phys));
+		pud_populate(&init_mm, pud, pmd);
 		spin_unlock(&init_mm.page_table_lock);
 	}
 	__flush_tlb_all();
@@ -578,28 +610,23 @@ kernel_physical_mapping_init(unsigned long start,
 
 	for (; start < end; start = next) {
 		pgd_t *pgd = pgd_offset_k(start);
-		unsigned long pud_phys;
 		pud_t *pud;
 
-		next = (start + PGDIR_SIZE) & PGDIR_MASK;
-		if (next > end)
-			next = end;
+		next = (start & PGDIR_MASK) + PGDIR_SIZE;
 
 		if (pgd_val(*pgd)) {
-			pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
+			pud = (pud_t *)pgd_page_vaddr(*pgd);
 			last_map_addr = phys_pud_init(pud, __pa(start),
 						 __pa(end), page_size_mask);
-			unmap_low_page(pud);
 			continue;
 		}
 
-		pud = alloc_low_page(&pud_phys);
-		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
+		pud = alloc_low_page();
+		last_map_addr = phys_pud_init(pud, __pa(start), __pa(end),
 						 page_size_mask);
-		unmap_low_page(pud);
 
 		spin_lock(&init_mm.page_table_lock);
-		pgd_populate(&init_mm, pgd, __va(pud_phys));
+		pgd_populate(&init_mm, pgd, pud);
 		spin_unlock(&init_mm.page_table_lock);
 		pgd_changed = true;
 	}
@@ -664,13 +691,11 @@ int arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
-	unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
+	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	last_mapped_pfn = init_memory_mapping(start, start + size);
-	if (last_mapped_pfn > max_pfn_mapped)
-		max_pfn_mapped = last_mapped_pfn;
+	init_memory_mapping(start, start + size);
 
 	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
@@ -686,6 +711,16 @@ EXPORT_SYMBOL_GPL(arch_add_memory);
 
 static struct kcore_list kcore_vsyscall;
 
+static void __init register_page_bootmem_info(void)
+{
+#ifdef CONFIG_NUMA
+	int i;
+
+	for_each_online_node(i)
+		register_page_bootmem_info_node(NODE_DATA(i));
+#endif
+}
+
 void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
@@ -698,11 +733,8 @@ void __init mem_init(void)
 	reservedpages = 0;
 
 	/* this will put all low memory onto the freelists */
-#ifdef CONFIG_NUMA
-	totalram_pages = numa_free_all_bootmem();
-#else
+	register_page_bootmem_info();
 	totalram_pages = free_all_bootmem();
-#endif
 
 	absent_pages = absent_pages_in_range(0, max_pfn);
 	reservedpages = max_pfn - totalram_pages - absent_pages;
@@ -772,12 +804,11 @@ void set_kernel_text_ro(void)
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long rodata_start =
-		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
-	unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
-	unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
-	unsigned long data_start = (unsigned long) &_sdata;
+	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
+	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
+	unsigned long all_end = PFN_ALIGN(&_end);
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -786,10 +817,10 @@ void mark_rodata_ro(void)
 	kernel_set_to_readonly = 1;
 
 	/*
-	 * The rodata section (but not the kernel text!) should also be
-	 * not-executable.
+	 * The rodata/data/bss/brk section (but not the kernel text!)
+	 * should also be not-executable.
 	 */
-	set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
 
@@ -802,12 +833,12 @@ void mark_rodata_ro(void)
 #endif
 
 	free_init_pages("unused kernel memory",
-			(unsigned long) page_address(virt_to_page(text_end)),
-			(unsigned long)
-				 page_address(virt_to_page(rodata_start)));
+			(unsigned long) __va(__pa_symbol(text_end)),
+			(unsigned long) __va(__pa_symbol(rodata_start)));
+
 	free_init_pages("unused kernel memory",
-			(unsigned long) page_address(virt_to_page(rodata_end)),
-			(unsigned long) page_address(virt_to_page(data_start)));
+			(unsigned long) __va(__pa_symbol(rodata_end)),
+			(unsigned long) __va(__pa_symbol(_sdata)));
 }
 
 #endif