summaryrefslogtreecommitdiffstats
path: root/arch/x86/boot/compressed/kaslr.c
blob: 8b7c9e75edcbf5a397c968d441a34369553f7870 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
/*
 * kaslr.c
 *
 * This contains the routines needed to generate a reasonable level of
 * entropy to choose a randomized kernel base address offset in support
 * of Kernel Address Space Layout Randomization (KASLR). Additionally
 * handles walking the physical memory maps (and tracking memory regions
 * to avoid) in order to select a physical memory location that can
 * contain the entire properly aligned running kernel image.
 *
 */
#include "misc.h"
#include "error.h"
#include "../boot.h"

#include <generated/compile.h>
#include <linux/module.h>
#include <linux/uts.h>
#include <linux/utsname.h>
#include <generated/utsrelease.h>

/* Simplified build-specific string for starting entropy. */
static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;

static unsigned long rotate_xor(unsigned long hash, const void *area,
				size_t size)
{
	size_t i;
	unsigned long *ptr = (unsigned long *)area;

	for (i = 0; i < size / sizeof(hash); i++) {
		/* Rotate by odd number of bits and XOR. */
		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
		hash ^= ptr[i];
	}

	return hash;
}

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

	hash = rotate_xor(hash, build_str, sizeof(build_str));
	hash = rotate_xor(hash, boot_params, sizeof(*boot_params));

	return hash;
}

#define KASLR_COMPRESSED_BOOT
#include "../../lib/kaslr.c"

struct mem_vector {
	unsigned long long start;
	unsigned long long size;
};

/* Only supporting at most 4 unusable memmap regions with kaslr */
#define MAX_MEMMAP_REGIONS	4

static bool memmap_too_large;

enum mem_avoid_index {
	MEM_AVOID_ZO_RANGE = 0,
	MEM_AVOID_INITRD,
	MEM_AVOID_CMDLINE,
	MEM_AVOID_BOOTPARAMS,
	MEM_AVOID_MEMMAP_BEGIN,
	MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1,
	MEM_AVOID_MAX,
};

static struct mem_vector mem_avoid[MEM_AVOID_MAX];

static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
{
	/* Item one is entirely before item two. */
	if (one->start + one->size <= two->start)
		return false;
	/* Item one is entirely after item two. */
	if (one->start >= two->start + two->size)
		return false;
	return true;
}

/**
 *	_memparse - Parse a string with mem suffixes into a number
 *	@ptr: Where parse begins
 *	@retptr: (output) Optional pointer to next char after parse completes
 *
 *	Parses a string into a number.  The number stored at @ptr is
 *	potentially suffixed with K, M, G, T, P, E.
 */
static unsigned long long _memparse(const char *ptr, char **retptr)
{
	char *endptr;	/* Local pointer to end of parsed string */

	unsigned long long ret = simple_strtoull(ptr, &endptr, 0);

	switch (*endptr) {
	case 'E':
	case 'e':
		ret <<= 10;
	case 'P':
	case 'p':
		ret <<= 10;
	case 'T':
	case 't':
		ret <<= 10;
	case 'G':
	case 'g':
		ret <<= 10;
	case 'M':
	case 'm':
		ret <<= 10;
	case 'K':
	case 'k':
		ret <<= 10;
		endptr++;
	default:
		break;
	}

	if (retptr)
		*retptr = endptr;

	return ret;
}

static int
parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
{
	char *oldp;

	if (!p)
		return -EINVAL;

	/* We don't care about this option here */
	if (!strncmp(p, "exactmap", 8))
		return -EINVAL;

	oldp = p;
	*size = _memparse(p, &p);
	if (p == oldp)
		return -EINVAL;

	switch (*p) {
	case '@':
		/* Skip this region, usable */
		*start = 0;
		*size = 0;
		return 0;
	case '#':
	case '$':
	case '!':
		*start = _memparse(p + 1, &p);
		return 0;
	}

	return -EINVAL;
}

static void mem_avoid_memmap(void)
{
	char arg[128];
	int rc;
	int i;
	char *str;

	/* See if we have any memmap areas */
	rc = cmdline_find_option("memmap", arg, sizeof(arg));
	if (rc <= 0)
		return;

	i = 0;
	str = arg;
	while (str && (i < MAX_MEMMAP_REGIONS)) {
		int rc;
		unsigned long long start, size;
		char *k = strchr(str, ',');

		if (k)
			*k++ = 0;

		rc = parse_memmap(str, &start, &size);
		if (rc < 0)
			break;
		str = k;
		/* A usable region that should not be skipped */
		if (size == 0)
			continue;

		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start;
		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size;
		i++;
	}

	/* More than 4 memmaps, fail kaslr */
	if ((i >= MAX_MEMMAP_REGIONS) && str)
		memmap_too_large = true;
}

/*
 * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
 * The mem_avoid array is used to store the ranges that need to be avoided
 * when KASLR searches for an appropriate random address. We must avoid any
 * regions that are unsafe to overlap with during decompression, and other
 * things like the initrd, cmdline and boot_params. This comment seeks to
 * explain mem_avoid as clearly as possible since incorrect mem_avoid
 * memory ranges lead to really hard to debug boot failures.
 *
 * The initrd, cmdline, and boot_params are trivial to identify for
 * avoiding. They are MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, and
 * MEM_AVOID_BOOTPARAMS respectively below.
 *
 * What is not obvious how to avoid is the range of memory that is used
 * during decompression (MEM_AVOID_ZO_RANGE below). This range must cover
 * the compressed kernel (ZO) and its run space, which is used to extract
 * the uncompressed kernel (VO) and relocs.
 *
 * ZO's full run size sits against the end of the decompression buffer, so
 * we can calculate where text, data, bss, etc of ZO are positioned more
 * easily.
 *
 * For additional background, the decompression calculations can be found
 * in header.S, and the memory diagram is based on the one found in misc.c.
 *
 * The following conditions are already enforced by the image layouts and
 * associated code:
 *  - input + input_size >= output + output_size
 *  - kernel_total_size <= init_size
 *  - kernel_total_size <= output_size (see Note below)
 *  - output + init_size >= output + output_size
 *
 * (Note that kernel_total_size and output_size have no fundamental
 * relationship, but output_size is passed to choose_random_location
 * as a maximum of the two. The diagram is showing a case where
 * kernel_total_size is larger than output_size, but this case is
 * handled by bumping output_size.)
 *
 * The above conditions can be illustrated by a diagram:
 *
 * 0   output            input            input+input_size    output+init_size
 * |     |                 |                             |             |
 * |     |                 |                             |             |
 * |-----|--------|--------|--------------|-----------|--|-------------|
 *                |                       |           |
 *                |                       |           |
 * output+init_size-ZO_INIT_SIZE  output+output_size  output+kernel_total_size
 *
 * [output, output+init_size) is the entire memory range used for
 * extracting the compressed image.
 *
 * [output, output+kernel_total_size) is the range needed for the
 * uncompressed kernel (VO) and its run size (bss, brk, etc).
 *
 * [output, output+output_size) is VO plus relocs (i.e. the entire
 * uncompressed payload contained by ZO). This is the area of the buffer
 * written to during decompression.
 *
 * [output+init_size-ZO_INIT_SIZE, output+init_size) is the worst-case
 * range of the copied ZO and decompression code. (i.e. the range
 * covered backwards of size ZO_INIT_SIZE, starting from output+init_size.)
 *
 * [input, input+input_size) is the original copied compressed image (ZO)
 * (i.e. it does not include its run size). This range must be avoided
 * because it contains the data used for decompression.
 *
 * [input+input_size, output+init_size) is [_text, _end) for ZO. This
 * range includes ZO's heap and stack, and must be avoided since it
 * performs the decompression.
 *
 * Since the above two ranges need to be avoided and they are adjacent,
 * they can be merged, resulting in: [input, output+init_size) which
 * becomes the MEM_AVOID_ZO_RANGE below.
 */
static void mem_avoid_init(unsigned long input, unsigned long input_size,
			   unsigned long output)
{
	unsigned long init_size = boot_params->hdr.init_size;
	u64 initrd_start, initrd_size;
	u64 cmd_line, cmd_line_size;
	char *ptr;

	/*
	 * Avoid the region that is unsafe to overlap during
	 * decompression.
	 */
	mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
	mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
	add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
			 mem_avoid[MEM_AVOID_ZO_RANGE].size);

	/* Avoid initrd. */
	initrd_start  = (u64)boot_params->ext_ramdisk_image << 32;
	initrd_start |= boot_params->hdr.ramdisk_image;
	initrd_size  = (u64)boot_params->ext_ramdisk_size << 32;
	initrd_size |= boot_params->hdr.ramdisk_size;
	mem_avoid[MEM_AVOID_INITRD].start = initrd_start;
	mem_avoid[MEM_AVOID_INITRD].size = initrd_size;
	/* No need to set mapping for initrd, it will be handled in VO. */

	/* Avoid kernel command line. */
	cmd_line  = (u64)boot_params->ext_cmd_line_ptr << 32;
	cmd_line |= boot_params->hdr.cmd_line_ptr;
	/* Calculate size of cmd_line. */
	ptr = (char *)(unsigned long)cmd_line;
	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
		;
	mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
	add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
			 mem_avoid[MEM_AVOID_CMDLINE].size);

	/* Avoid boot parameters. */
	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
	add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
			 mem_avoid[MEM_AVOID_BOOTPARAMS].size);

	/* We don't need to set a mapping for setup_data. */

	/* Mark the memmap regions we need to avoid */
	mem_avoid_memmap();

#ifdef CONFIG_X86_VERBOSE_BOOTUP
	/* Make sure video RAM can be used. */
	add_identity_map(0, PMD_SIZE);
#endif
}

/*
 * Does this memory vector overlap a known avoided area? If so, record the
 * overlap region with the lowest address.
 */
static bool mem_avoid_overlap(struct mem_vector *img,
			      struct mem_vector *overlap)
{
	int i;
	struct setup_data *ptr;
	unsigned long earliest = img->start + img->size;
	bool is_overlapping = false;

	for (i = 0; i < MEM_AVOID_MAX; i++) {
		if (mem_overlaps(img, &mem_avoid[i]) &&
		    mem_avoid[i].start < earliest) {
			*overlap = mem_avoid[i];
			earliest = overlap->start;
			is_overlapping = true;
		}
	}

	/* Avoid all entries in the setup_data linked list. */
	ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
	while (ptr) {
		struct mem_vector avoid;

		avoid.start = (unsigned long)ptr;
		avoid.size = sizeof(*ptr) + ptr->len;

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

		ptr = (struct setup_data *)(unsigned long)ptr->next;
	}

	return is_overlapping;
}

struct slot_area {
	unsigned long addr;
	int num;
};

#define MAX_SLOT_AREA 100

static struct slot_area slot_areas[MAX_SLOT_AREA];

static unsigned long slot_max;

static unsigned long slot_area_index;

static void store_slot_info(struct mem_vector *region, unsigned long image_size)
{
	struct slot_area slot_area;

	if (slot_area_index == MAX_SLOT_AREA)
		return;

	slot_area.addr = region->start;
	slot_area.num = (region->size - image_size) /
			CONFIG_PHYSICAL_ALIGN + 1;

	if (slot_area.num > 0) {
		slot_areas[slot_area_index++] = slot_area;
		slot_max += slot_area.num;
	}
}

static unsigned long slots_fetch_random(void)
{
	unsigned long slot;
	int i;

	/* Handle case of no slots stored. */
	if (slot_max == 0)
		return 0;

	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, overlap;
	struct slot_area slot_area;
	unsigned long start_orig;

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

	/* 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. */
	if (entry->addr + entry->size < minimum)
		return;

	region.start = entry->addr;
	region.size = entry->size;

	/* Give up if slot area array is full. */
	while (slot_area_index < MAX_SLOT_AREA) {
		start_orig = region.start;

		/* Potentially raise address to minimum location. */
		if (region.start < minimum)
			region.start = minimum;

		/* Potentially raise address to meet alignment needs. */
		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);

		/* Did we raise the address above this e820 region? */
		if (region.start > entry->addr + entry->size)
			return;

		/* Reduce size by any delta from the original address. */
		region.size -= region.start - start_orig;

		/* 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;
	}
}

static unsigned long find_random_phys_addr(unsigned long minimum,
					   unsigned long image_size)
{
	int i;
	unsigned long addr;

	/* Check if we had too many memmaps. */
	if (memmap_too_large) {
		debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
		return 0;
	}

	/* Make sure minimum is aligned. */
	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);

	/* Verify potential e820 positions, appending to slots list. */
	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();
}

static unsigned long find_random_virt_addr(unsigned long minimum,
					   unsigned long image_size)
{
	unsigned long slots, random_addr;

	/* Make sure minimum is aligned. */
	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
	/* Align image_size for easy slot calculations. */
	image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);

	/*
	 * There are how many CONFIG_PHYSICAL_ALIGN-sized slots
	 * that can hold image_size within the range of minimum to
	 * KERNEL_IMAGE_SIZE?
	 */
	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
		 CONFIG_PHYSICAL_ALIGN + 1;

	random_addr = kaslr_get_random_long("Virtual") % slots;

	return random_addr * CONFIG_PHYSICAL_ALIGN + minimum;
}

/*
 * Since this function examines addresses much more numerically,
 * it takes the input and output pointers as 'unsigned long'.
 */
void choose_random_location(unsigned long input,
			    unsigned long input_size,
			    unsigned long *output,
			    unsigned long output_size,
			    unsigned long *virt_addr)
{
	unsigned long random_addr, min_addr;

	/* By default, keep output position unchanged. */
	*virt_addr = *output;

	if (cmdline_find_option_bool("nokaslr")) {
		warn("KASLR disabled: 'nokaslr' on cmdline.");
		return;
	}

	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);

	/*
	 * 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(min_addr, output_size);
	if (!random_addr) {
		warn("Physical KASLR disabled: no suitable memory region!");
	} else {
		/* Update the new physical address location. */
		if (*output != random_addr) {
			add_identity_map(random_addr, output_size);
			*output = random_addr;
		}
	}

	/* This actually loads the identity pagetable on x86_64. */
	finalize_identity_maps();

	/* 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;
}