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

Pull x86 boot updates from Ingo Molnar:
 "The main changes:

   - add initial commits to randomize kernel memory section virtual
     addresses, enabled via a new kernel option: RANDOMIZE_MEMORY
     (Thomas Garnier, Kees Cook, Baoquan He, Yinghai Lu)

   - enhance KASLR (RANDOMIZE_BASE) physical memory randomization (Kees
     Cook)

   - EBDA/BIOS region boot quirk cleanups (Andy Lutomirski, Ingo Molnar)

   - misc cleanups/fixes"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Simplify EBDA-vs-BIOS reservation logic
  x86/boot: Clarify what x86_legacy_features.reserve_bios_regions does
  x86/boot: Reorganize and clean up the BIOS area reservation code
  x86/mm: Do not reference phys addr beyond kernel
  x86/mm: Add memory hotplug support for KASLR memory randomization
  x86/mm: Enable KASLR for vmalloc memory regions
  x86/mm: Enable KASLR for physical mapping memory regions
  x86/mm: Implement ASLR for kernel memory regions
  x86/mm: Separate variable for trampoline PGD
  x86/mm: Add PUD VA support for physical mapping
  x86/mm: Update physical mapping variable names
  x86/mm: Refactor KASLR entropy functions
  x86/KASLR: Fix boot crash with certain memory configurations
  x86/boot/64: Add forgotten end of function marker
  x86/KASLR: Allow randomization below the load address
  x86/KASLR: Extend kernel image physical address randomization to addresses larger than 4G
  x86/KASLR: Randomize virtual address separately
  x86/KASLR: Clarify identity map interface
  x86/boot: Refuse to build with data relocations
  x86/KASLR, x86/power: Remove x86 hibernation restrictions

1 files changed, 101 insertions, 66 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e14f87057c3f..53cc2256cf23 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -328,22 +328,30 @@ void __init cleanup_highmap(void)
 	}
 }
 
+/*
+ * Create PTE level page table mapping for physical addresses.
+ * It returns the last physical address mapped.
+ */
 static unsigned long __meminit
-phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
+phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
 	      pgprot_t prot)
 {
-	unsigned long pages = 0, next;
-	unsigned long last_map_addr = end;
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
+	pte_t *pte;
 	int i;
 
-	pte_t *pte = pte_page + pte_index(addr);
+	pte = pte_page + pte_index(paddr);
+	i = pte_index(paddr);
 
-	for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) {
-		next = (addr & PAGE_MASK) + PAGE_SIZE;
-		if (addr >= end) {
+	for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) {
+		paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE;
+		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
+			    !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
+					     E820_RAM) &&
+			    !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
+					     E820_RESERVED_KERN))
 				set_pte(pte, __pte(0));
 			continue;
 		}
@@ -361,37 +369,44 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		}
 
 		if (0)
-			printk("   pte=%p addr=%lx pte=%016lx\n",
-			       pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
+			pr_info("   pte=%p addr=%lx pte=%016lx\n", pte, paddr,
+				pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte);
 		pages++;
-		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
-		last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
+		set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
+		paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE;
 	}
 
 	update_page_count(PG_LEVEL_4K, pages);
 
-	return last_map_addr;
+	return paddr_last;
 }
 
+/*
+ * Create PMD level page table mapping for physical addresses. The virtual
+ * and physical address have to be aligned at this level.
+ * It returns the last physical address mapped.
+ */
 static unsigned long __meminit
-phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
+phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
 	      unsigned long page_size_mask, pgprot_t prot)
 {
-	unsigned long pages = 0, next;
-	unsigned long last_map_addr = end;
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
 
-	int i = pmd_index(address);
+	int i = pmd_index(paddr);
 
-	for (; i < PTRS_PER_PMD; i++, address = next) {
-		pmd_t *pmd = pmd_page + pmd_index(address);
+	for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) {
+		pmd_t *pmd = pmd_page + pmd_index(paddr);
 		pte_t *pte;
 		pgprot_t new_prot = prot;
 
-		next = (address & PMD_MASK) + PMD_SIZE;
-		if (address >= end) {
+		paddr_next = (paddr & PMD_MASK) + PMD_SIZE;
+		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
+			    !e820_any_mapped(paddr & PMD_MASK, paddr_next,
+					     E820_RAM) &&
+			    !e820_any_mapped(paddr & PMD_MASK, paddr_next,
+					     E820_RESERVED_KERN))
 				set_pmd(pmd, __pmd(0));
 			continue;
 		}
@@ -400,8 +415,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			if (!pmd_large(*pmd)) {
 				spin_lock(&init_mm.page_table_lock);
 				pte = (pte_t *)pmd_page_vaddr(*pmd);
-				last_map_addr = phys_pte_init(pte, address,
-								end, prot);
+				paddr_last = phys_pte_init(pte, paddr,
+							   paddr_end, prot);
 				spin_unlock(&init_mm.page_table_lock);
 				continue;
 			}
@@ -420,7 +435,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			if (page_size_mask & (1 << PG_LEVEL_2M)) {
 				if (!after_bootmem)
 					pages++;
-				last_map_addr = next;
+				paddr_last = paddr_next;
 				continue;
 			}
 			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
@@ -430,42 +445,54 @@ 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 & PMD_MASK) >> PAGE_SHIFT,
+				pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT,
 					__pgprot(pgprot_val(prot) | _PAGE_PSE)));
 			spin_unlock(&init_mm.page_table_lock);
-			last_map_addr = next;
+			paddr_last = paddr_next;
 			continue;
 		}
 
 		pte = alloc_low_page();
-		last_map_addr = phys_pte_init(pte, address, end, new_prot);
+		paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot);
 
 		spin_lock(&init_mm.page_table_lock);
 		pmd_populate_kernel(&init_mm, pmd, pte);
 		spin_unlock(&init_mm.page_table_lock);
 	}
 	update_page_count(PG_LEVEL_2M, pages);
-	return last_map_addr;
+	return paddr_last;
 }
 
+/*
+ * Create PUD level page table mapping for physical addresses. The virtual
+ * and physical address do not have to be aligned at this level. KASLR can
+ * randomize virtual addresses up to this level.
+ * It returns the last physical address mapped.
+ */
 static unsigned long __meminit
-phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
-			 unsigned long page_size_mask)
+phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
+	      unsigned long page_size_mask)
 {
-	unsigned long pages = 0, next;
-	unsigned long last_map_addr = end;
-	int i = pud_index(addr);
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
+	unsigned long vaddr = (unsigned long)__va(paddr);
+	int i = pud_index(vaddr);
 
-	for (; i < PTRS_PER_PUD; i++, addr = next) {
-		pud_t *pud = pud_page + pud_index(addr);
+	for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) {
+		pud_t *pud;
 		pmd_t *pmd;
 		pgprot_t prot = PAGE_KERNEL;
 
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (addr >= end) {
+		vaddr = (unsigned long)__va(paddr);
+		pud = pud_page + pud_index(vaddr);
+		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
+
+		if (paddr >= paddr_end) {
 			if (!after_bootmem &&
-			    !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) &&
-			    !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN))
+			    !e820_any_mapped(paddr & PUD_MASK, paddr_next,
+					     E820_RAM) &&
+			    !e820_any_mapped(paddr & PUD_MASK, paddr_next,
+					     E820_RESERVED_KERN))
 				set_pud(pud, __pud(0));
 			continue;
 		}
@@ -473,8 +500,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 		if (!pud_none(*pud)) {
 			if (!pud_large(*pud)) {
 				pmd = pmd_offset(pud, 0);
-				last_map_addr = phys_pmd_init(pmd, addr, end,
-							 page_size_mask, prot);
+				paddr_last = phys_pmd_init(pmd, paddr,
+							   paddr_end,
+							   page_size_mask,
+							   prot);
 				__flush_tlb_all();
 				continue;
 			}
@@ -493,7 +522,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			if (page_size_mask & (1 << PG_LEVEL_1G)) {
 				if (!after_bootmem)
 					pages++;
-				last_map_addr = next;
+				paddr_last = paddr_next;
 				continue;
 			}
 			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
@@ -503,16 +532,16 @@ 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 & PUD_MASK) >> PAGE_SHIFT,
+				pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT,
 					PAGE_KERNEL_LARGE));
 			spin_unlock(&init_mm.page_table_lock);
-			last_map_addr = next;
+			paddr_last = paddr_next;
 			continue;
 		}
 
 		pmd = alloc_low_page();
-		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
-					      prot);
+		paddr_last = phys_pmd_init(pmd, paddr, paddr_end,
+					   page_size_mask, prot);
 
 		spin_lock(&init_mm.page_table_lock);
 		pud_populate(&init_mm, pud, pmd);
@@ -522,38 +551,44 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 
 	update_page_count(PG_LEVEL_1G, pages);
 
-	return last_map_addr;
+	return paddr_last;
 }
 
+/*
+ * Create page table mapping for the physical memory for specific physical
+ * addresses. The virtual and physical addresses have to be aligned on PMD level
+ * down. It returns the last physical address mapped.
+ */
 unsigned long __meminit
-kernel_physical_mapping_init(unsigned long start,
-			     unsigned long end,
+kernel_physical_mapping_init(unsigned long paddr_start,
+			     unsigned long paddr_end,
 			     unsigned long page_size_mask)
 {
 	bool pgd_changed = false;
-	unsigned long next, last_map_addr = end;
-	unsigned long addr;
+	unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last;
 
-	start = (unsigned long)__va(start);
-	end = (unsigned long)__va(end);
-	addr = start;
+	paddr_last = paddr_end;
+	vaddr = (unsigned long)__va(paddr_start);
+	vaddr_end = (unsigned long)__va(paddr_end);
+	vaddr_start = vaddr;
 
-	for (; start < end; start = next) {
-		pgd_t *pgd = pgd_offset_k(start);
+	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+		pgd_t *pgd = pgd_offset_k(vaddr);
 		pud_t *pud;
 
-		next = (start & PGDIR_MASK) + PGDIR_SIZE;
+		vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE;
 
 		if (pgd_val(*pgd)) {
 			pud = (pud_t *)pgd_page_vaddr(*pgd);
-			last_map_addr = phys_pud_init(pud, __pa(start),
-						 __pa(end), page_size_mask);
+			paddr_last = phys_pud_init(pud, __pa(vaddr),
+						   __pa(vaddr_end),
+						   page_size_mask);
 			continue;
 		}
 
 		pud = alloc_low_page();
-		last_map_addr = phys_pud_init(pud, __pa(start), __pa(end),
-						 page_size_mask);
+		paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end),
+					   page_size_mask);
 
 		spin_lock(&init_mm.page_table_lock);
 		pgd_populate(&init_mm, pgd, pud);
@@ -562,11 +597,11 @@ kernel_physical_mapping_init(unsigned long start,
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(addr, end - 1, 0);
+		sync_global_pgds(vaddr_start, vaddr_end - 1, 0);
 
 	__flush_tlb_all();
 
-	return last_map_addr;
+	return paddr_last;
 }
 
 #ifndef CONFIG_NUMA