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
2016-07-25 17:32:28 -07:00
parent 0f657262d5 6a79296cb1
commit 77cd3d0c43
30 changed files with 778 additions and 336 deletions
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -85,7 +85,25 @@ vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
 	$(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o

+# The compressed kernel is built with -fPIC/-fPIE so that a boot loader
+# can place it anywhere in memory and it will still run. However, since
+# it is executed as-is without any ELF relocation processing performed
+# (and has already had all relocation sections stripped from the binary),
+# none of the code can use data relocations (e.g. static assignments of
+# pointer values), since they will be meaningless at runtime. This check
+# will refuse to link the vmlinux if any of these relocations are found.
+quiet_cmd_check_data_rel = DATAREL $@
+define cmd_check_data_rel
+	for obj in $(filter %.o,$^); do \
+		readelf -S $$obj | grep -qF .rel.local && { \
+			echo "error: $$obj has data relocations!" >&2; \
+			exit 1; \
+		} || true; \
+	done
+endef
+
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+	$(call if_changed,check_data_rel)
 	$(call if_changed,ld)

 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -12,10 +12,6 @@
 #include "misc.h"
 #include "error.h"

-#include <asm/msr.h>
-#include <asm/archrandom.h>
-#include <asm/e820.h>
-
 #include <generated/compile.h>
 #include <linux/module.h>
 #include <linux/uts.h>
@@ -26,26 +22,6 @@
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;

-#define I8254_PORT_CONTROL	0x43
-#define I8254_PORT_COUNTER0	0x40
-#define I8254_CMD_READBACK	0xC0
-#define I8254_SELECT_COUNTER0	0x02
-#define I8254_STATUS_NOTREADY	0x40
-static inline u16 i8254(void)
-{
-	u16 status, timer;
-
-	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
-		status = inb(I8254_PORT_COUNTER0);
-		timer  = inb(I8254_PORT_COUNTER0);
-		timer |= inb(I8254_PORT_COUNTER0) << 8;
-	} while (status & I8254_STATUS_NOTREADY);
-
-	return timer;
-}
-
 static unsigned long rotate_xor(unsigned long hash, const void *area,
 				size_t size)
 {
@@ -62,7 +38,7 @@ static unsigned long rotate_xor(unsigned long hash, const void *area,
 }

 /* Attempt to create a simple but unpredictable starting entropy. */
-static unsigned long get_random_boot(void)
+static unsigned long get_boot_seed(void)
 {
 	unsigned long hash = 0;

@@ -72,50 +48,8 @@ static unsigned long get_random_boot(void)
 	return hash;
 }

-static unsigned long get_random_long(const char *purpose)
-{
-#ifdef CONFIG_X86_64
-	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
-#else
-	const unsigned long mix_const = 0x3f39e593UL;
-#endif
-	unsigned long raw, random = get_random_boot();
-	bool use_i8254 = true;
-
-	debug_putstr(purpose);
-	debug_putstr(" KASLR using");
-
-	if (has_cpuflag(X86_FEATURE_RDRAND)) {
-		debug_putstr(" RDRAND");
-		if (rdrand_long(&raw)) {
-			random ^= raw;
-			use_i8254 = false;
-		}
-	}
-
-	if (has_cpuflag(X86_FEATURE_TSC)) {
-		debug_putstr(" RDTSC");
-		raw = rdtsc();
-
-		random ^= raw;
-		use_i8254 = false;
-	}
-
-	if (use_i8254) {
-		debug_putstr(" i8254");
-		random ^= i8254();
-	}
-
-	/* Circular multiply for better bit diffusion */
-	asm("mul %3"
-	    : "=a" (random), "=d" (raw)
-	    : "a" (random), "rm" (mix_const));
-	random += raw;
-
-	debug_putstr("...\n");
-
-	return random;
-}
+#define KASLR_COMPRESSED_BOOT
+#include "../../lib/kaslr.c"

 struct mem_vector {
 	unsigned long start;
@@ -132,17 +66,6 @@ enum mem_avoid_index {

 static struct mem_vector mem_avoid[MEM_AVOID_MAX];

-static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
-{
-	/* Item at least partially before region. */
-	if (item->start < region->start)
-		return false;
-	/* Item at least partially after region. */
-	if (item->start + item->size > region->start + region->size)
-		return false;
-	return true;
-}
-
 static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
 {
 	/* Item one is entirely before item two. */
@@ -296,6 +219,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 		if (mem_overlaps(img, &mem_avoid[i]) &&
 		    mem_avoid[i].start < earliest) {
 			*overlap = mem_avoid[i];
+			earliest = overlap->start;
 			is_overlapping = true;
 		}
 	}
@@ -310,6 +234,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,

 		if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
 			*overlap = avoid;
+			earliest = overlap->start;
 			is_overlapping = true;
 		}

@@ -319,8 +244,6 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 	return is_overlapping;
 }

-static unsigned long slots[KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN];
-
 struct slot_area {
 	unsigned long addr;
 	int num;
@@ -351,36 +274,44 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 	}
 }

-static void slots_append(unsigned long addr)
-{
-	/* Overflowing the slots list should be impossible. */
-	if (slot_max >= KERNEL_IMAGE_SIZE / CONFIG_PHYSICAL_ALIGN)
-		return;
-
-	slots[slot_max++] = addr;
-}
-
 static unsigned long slots_fetch_random(void)
 {
+	unsigned long slot;
+	int i;
+
 	/* Handle case of no slots stored. */
 	if (slot_max == 0)
 		return 0;

-	return slots[get_random_long("Physical") % slot_max];
+	slot = kaslr_get_random_long("Physical") % slot_max;
+
+	for (i = 0; i < slot_area_index; i++) {
+		if (slot >= slot_areas[i].num) {
+			slot -= slot_areas[i].num;
+			continue;
+		}
+		return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN;
+	}
+
+	if (i == slot_area_index)
+		debug_putstr("slots_fetch_random() failed!?\n");
+	return 0;
 }

 static void process_e820_entry(struct e820entry *entry,
 			       unsigned long minimum,
 			       unsigned long image_size)
 {
-	struct mem_vector region, img, overlap;
+	struct mem_vector region, overlap;
+	struct slot_area slot_area;
+	unsigned long start_orig;

 	/* Skip non-RAM entries. */
 	if (entry->type != E820_RAM)
 		return;

-	/* Ignore entries entirely above our maximum. */
-	if (entry->addr >= KERNEL_IMAGE_SIZE)
+	/* On 32-bit, ignore entries entirely above our maximum. */
+	if (IS_ENABLED(CONFIG_X86_32) && entry->addr >= KERNEL_IMAGE_SIZE)
 		return;

 	/* Ignore entries entirely below our minimum. */
@@ -390,31 +321,55 @@ static void process_e820_entry(struct e820entry *entry,
 	region.start = entry->addr;
 	region.size = entry->size;

-	/* Potentially raise address to minimum location. */
-	if (region.start < minimum)
-		region.start = minimum;
+	/* Give up if slot area array is full. */
+	while (slot_area_index < MAX_SLOT_AREA) {
+		start_orig = region.start;

-	/* Potentially raise address to meet alignment requirements. */
-	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+		/* Potentially raise address to minimum location. */
+		if (region.start < minimum)
+			region.start = minimum;

-	/* Did we raise the address above the bounds of this e820 region? */
-	if (region.start > entry->addr + entry->size)
-		return;
+		/* Potentially raise address to meet alignment needs. */
+		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);

-	/* Reduce size by any delta from the original address. */
-	region.size -= region.start - entry->addr;
+		/* Did we raise the address above this e820 region? */
+		if (region.start > entry->addr + entry->size)
+			return;

-	/* Reduce maximum size to fit end of image within maximum limit. */
-	if (region.start + region.size > KERNEL_IMAGE_SIZE)
-		region.size = KERNEL_IMAGE_SIZE - region.start;
+		/* Reduce size by any delta from the original address. */
+		region.size -= region.start - start_orig;

-	/* Walk each aligned slot and check for avoided areas. */
-	for (img.start = region.start, img.size = image_size ;
-	     mem_contains(&region, &img) ;
-	     img.start += CONFIG_PHYSICAL_ALIGN) {
-		if (mem_avoid_overlap(&img, &overlap))
-			continue;
-		slots_append(img.start);
+		/* On 32-bit, reduce region size to fit within max size. */
+		if (IS_ENABLED(CONFIG_X86_32) &&
+		    region.start + region.size > KERNEL_IMAGE_SIZE)
+			region.size = KERNEL_IMAGE_SIZE - region.start;
+
+		/* Return if region can't contain decompressed kernel */
+		if (region.size < image_size)
+			return;
+
+		/* If nothing overlaps, store the region and return. */
+		if (!mem_avoid_overlap(&region, &overlap)) {
+			store_slot_info(&region, image_size);
+			return;
+		}
+
+		/* Store beginning of region if holds at least image_size. */
+		if (overlap.start > region.start + image_size) {
+			struct mem_vector beginning;
+
+			beginning.start = region.start;
+			beginning.size = overlap.start - region.start;
+			store_slot_info(&beginning, image_size);
+		}
+
+		/* Return if overlap extends to or past end of region. */
+		if (overlap.start + overlap.size >= region.start + region.size)
+			return;
+
+		/* Clip off the overlapping region and start over. */
+		region.size -= overlap.start - region.start + overlap.size;
+		region.start = overlap.start + overlap.size;
 	}
 }

@@ -431,6 +386,10 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
 	for (i = 0; i < boot_params->e820_entries; i++) {
 		process_e820_entry(&boot_params->e820_map[i], minimum,
 				   image_size);
+		if (slot_area_index == MAX_SLOT_AREA) {
+			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
+			break;
+		}
 	}

 	return slots_fetch_random();
@@ -454,7 +413,7 @@ static unsigned long find_random_virt_addr(unsigned long minimum,
 	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
 		 CONFIG_PHYSICAL_ALIGN + 1;

-	random_addr = get_random_long("Virtual") % slots;
+	random_addr = kaslr_get_random_long("Virtual") % slots;

 	return random_addr * CONFIG_PHYSICAL_ALIGN + minimum;
 }
@@ -463,48 +422,54 @@ static unsigned long find_random_virt_addr(unsigned long minimum,
 * Since this function examines addresses much more numerically,
 * it takes the input and output pointers as 'unsigned long'.
 */
-unsigned char *choose_random_location(unsigned long input,
-				      unsigned long input_size,
-				      unsigned long output,
-				      unsigned long output_size)
+void choose_random_location(unsigned long input,
+			    unsigned long input_size,
+			    unsigned long *output,
+			    unsigned long output_size,
+			    unsigned long *virt_addr)
 {
-	unsigned long choice = output;
-	unsigned long random_addr;
+	unsigned long random_addr, min_addr;
+
+	/* By default, keep output position unchanged. */
+	*virt_addr = *output;

-#ifdef CONFIG_HIBERNATION
-	if (!cmdline_find_option_bool("kaslr")) {
-		warn("KASLR disabled: 'kaslr' not on cmdline (hibernation selected).");
-		goto out;
-	}
-#else
 	if (cmdline_find_option_bool("nokaslr")) {
 		warn("KASLR disabled: 'nokaslr' on cmdline.");
-		goto out;
+		return;
 	}
-#endif

 	boot_params->hdr.loadflags |= KASLR_FLAG;

+	/* Prepare to add new identity pagetables on demand. */
+	initialize_identity_maps();
+
 	/* Record the various known unsafe memory ranges. */
-	mem_avoid_init(input, input_size, output);
+	mem_avoid_init(input, input_size, *output);
+
+	/*
+	 * Low end of the randomization range should be the
+	 * smaller of 512M or the initial kernel image
+	 * location:
+	 */
+	min_addr = min(*output, 512UL << 20);

 	/* Walk e820 and find a random address. */
-	random_addr = find_random_phys_addr(output, output_size);
+	random_addr = find_random_phys_addr(min_addr, output_size);
 	if (!random_addr) {
 		warn("KASLR disabled: could not find suitable E820 region!");
-		goto out;
+	} else {
+		/* Update the new physical address location. */
+		if (*output != random_addr) {
+			add_identity_map(random_addr, output_size);
+			*output = random_addr;
+		}
 	}

-	/* Always enforce the minimum. */
-	if (random_addr < choice)
-		goto out;
-
-	choice = random_addr;
-
-	add_identity_map(choice, output_size);
-
 	/* This actually loads the identity pagetable on x86_64. */
 	finalize_identity_maps();
-out:
-	return (unsigned char *)choice;
+
+	/* Pick random virtual address starting from LOAD_PHYSICAL_ADDR. */
+	if (IS_ENABLED(CONFIG_X86_64))
+		random_addr = find_random_virt_addr(LOAD_PHYSICAL_ADDR, output_size);
+	*virt_addr = random_addr;
 }
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -170,7 +170,8 @@ void __puthex(unsigned long value)
 }

 #if CONFIG_X86_NEED_RELOCS
-static void handle_relocations(void *output, unsigned long output_len)
+static void handle_relocations(void *output, unsigned long output_len,
+			       unsigned long virt_addr)
 {
 	int *reloc;
 	unsigned long delta, map, ptr;
@@ -182,11 +183,6 @@ static void handle_relocations(void *output, unsigned long output_len)
 	 * and where it was actually loaded.
 	 */
 	delta = min_addr - LOAD_PHYSICAL_ADDR;
-	if (!delta) {
-		debug_putstr("No relocation needed... ");
-		return;
-	}
-	debug_putstr("Performing relocations... ");

 	/*
 	 * The kernel contains a table of relocation addresses. Those
@@ -197,6 +193,20 @@ static void handle_relocations(void *output, unsigned long output_len)
 	 */
 	map = delta - __START_KERNEL_map;

+	/*
+	 * 32-bit always performs relocations. 64-bit relocations are only
+	 * needed if KASLR has chosen a different starting address offset
+	 * from __START_KERNEL_map.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64))
+		delta = virt_addr - LOAD_PHYSICAL_ADDR;
+
+	if (!delta) {
+		debug_putstr("No relocation needed... ");
+		return;
+	}
+	debug_putstr("Performing relocations... ");
+
 	/*
 	 * Process relocations: 32 bit relocations first then 64 bit after.
 	 * Three sets of binary relocations are added to the end of the kernel
@@ -250,7 +260,8 @@ static void handle_relocations(void *output, unsigned long output_len)
 #endif
 }
 #else
-static inline void handle_relocations(void *output, unsigned long output_len)
+static inline void handle_relocations(void *output, unsigned long output_len,
+				      unsigned long virt_addr)
 { }
 #endif

@@ -327,7 +338,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 				  unsigned long output_len)
 {
 	const unsigned long kernel_total_size = VO__end - VO__text;
-	unsigned char *output_orig = output;
+	unsigned long virt_addr = (unsigned long)output;

 	/* Retain x86 boot parameters pointer passed from startup_32/64. */
 	boot_params = rmode;
@@ -366,13 +377,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_random_location((unsigned long)input_data, input_len,
-					(unsigned long)output,
-					max(output_len, kernel_total_size));
+	choose_random_location((unsigned long)input_data, input_len,
+				(unsigned long *)&output,
+				max(output_len, kernel_total_size),
+				&virt_addr);

 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
-		error("Destination address inappropriately aligned");
+		error("Destination physical address inappropriately aligned");
+	if (virt_addr & (MIN_KERNEL_ALIGN - 1))
+		error("Destination virtual address inappropriately aligned");
 #ifdef CONFIG_X86_64
 	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
@@ -382,19 +396,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 #endif
 #ifndef CONFIG_RELOCATABLE
 	if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
-		error("Wrong destination address");
+		error("Destination address does not match LOAD_PHYSICAL_ADDR");
+	if ((unsigned long)output != virt_addr)
+		error("Destination virtual address changed when not relocatable");
 #endif

 	debug_putstr("\nDecompressing Linux... ");
 	__decompress(input_data, input_len, NULL, NULL, output, output_len,
 			NULL, error);
 	parse_elf(output);
-	/*
-	 * 32-bit always performs relocations. 64-bit relocations are only
-	 * needed if kASLR has chosen a different load address.
-	 */
-	if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
-		handle_relocations(output, output_len);
+	handle_relocations(output, output_len, virt_addr);
 	debug_putstr("done.\nBooting the kernel.\n");
 	return output;
 }
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -67,28 +67,33 @@ int cmdline_find_option_bool(const char *option);

 #if CONFIG_RANDOMIZE_BASE
 /* kaslr.c */
-unsigned char *choose_random_location(unsigned long input_ptr,
-				      unsigned long input_size,
-				      unsigned long output_ptr,
-				      unsigned long output_size);
+void choose_random_location(unsigned long input,
+			    unsigned long input_size,
+			    unsigned long *output,
+			    unsigned long output_size,
+			    unsigned long *virt_addr);
 /* cpuflags.c */
 bool has_cpuflag(int flag);
 #else
-static inline
-unsigned char *choose_random_location(unsigned long input_ptr,
-				      unsigned long input_size,
-				      unsigned long output_ptr,
-				      unsigned long output_size)
+static inline void choose_random_location(unsigned long input,
+					  unsigned long input_size,
+					  unsigned long *output,
+					  unsigned long output_size,
+					  unsigned long *virt_addr)
 {
-	return (unsigned char *)output_ptr;
+	/* No change from existing output location. */
+	*virt_addr = *output;
 }
 #endif

 #ifdef CONFIG_X86_64
+void initialize_identity_maps(void);
 void add_identity_map(unsigned long start, unsigned long size);
 void finalize_identity_maps(void);
 extern unsigned char _pgtable[];
 #else
+static inline void initialize_identity_maps(void)
+{ }
 static inline void add_identity_map(unsigned long start, unsigned long size)
 { }
 static inline void finalize_identity_maps(void)
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -2,6 +2,9 @@
 * This code is used on x86_64 to create page table identity mappings on
 * demand by building up a new set of page tables (or appending to the
 * existing ones), and then switching over to them when ready.
+ *
+ * Copyright (C) 2015-2016  Yinghai Lu
+ * Copyright (C)      2016  Kees Cook
 */

 /*
@@ -17,6 +20,9 @@
 /* These actually do the work of building the kernel identity maps. */
 #include <asm/init.h>
 #include <asm/pgtable.h>
+/* Use the static base for this part of the boot process */
+#undef __PAGE_OFFSET
+#define __PAGE_OFFSET __PAGE_OFFSET_BASE
 #include "../../mm/ident_map.c"

 /* Used by pgtable.h asm code to force instruction serialization. */
@@ -59,9 +65,21 @@ static struct alloc_pgt_data pgt_data;
 /* The top level page table entry pointer. */
 static unsigned long level4p;

+/*
+ * Mapping information structure passed to kernel_ident_mapping_init().
+ * Due to relocation, pointers must be assigned at run time not build time.
+ */
+static struct x86_mapping_info mapping_info = {
+	.pmd_flag       = __PAGE_KERNEL_LARGE_EXEC,
+};
+
 /* Locates and clears a region for a new top level page table. */
-static void prepare_level4(void)
+void initialize_identity_maps(void)
 {
+	/* Init mapping_info with run-time function/buffer pointers. */
+	mapping_info.alloc_pgt_page = alloc_pgt_page;
+	mapping_info.context = &pgt_data;
+
 	/*
 	 * It should be impossible for this not to already be true,
 	 * but since calling this a second time would rewind the other
@@ -96,17 +114,8 @@ static void prepare_level4(void)
 */
 void add_identity_map(unsigned long start, unsigned long size)
 {
-	struct x86_mapping_info mapping_info = {
-		.alloc_pgt_page	= alloc_pgt_page,
-		.context	= &pgt_data,
-		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
-	};
 	unsigned long end = start + size;

-	/* Make sure we have a top level page table ready to use. */
-	if (!level4p)
-		prepare_level4();
-
 	/* Align boundary to 2M. */
 	start = round_down(start, PMD_SIZE);
 	end = round_up(end, PMD_SIZE);