summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/module.c
blob: f2d4bb14bfabe28e7fa79333c6c290bc9a3043c4 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * AArch64 loadable module support.
 *
 * Copyright (C) 2012 ARM Limited
 *
 * Author: Will Deacon <will.deacon@arm.com>
 */

#include <linux/bitops.h>
#include <linux/elf.h>
#include <linux/ftrace.h>
#include <linux/gfp.h>
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/moduleloader.h>
#include <linux/vmalloc.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/sections.h>

void *module_alloc(unsigned long size)
{
	u64 module_alloc_end = module_alloc_base + MODULES_VSIZE;
	gfp_t gfp_mask = GFP_KERNEL;
	void *p;

	/* Silence the initial allocation */
	if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
		gfp_mask |= __GFP_NOWARN;

	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
		/* don't exceed the static module region - see below */
		module_alloc_end = MODULES_END;

	p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
				module_alloc_end, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK,
				NUMA_NO_NODE, __builtin_return_address(0));

	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
	    (IS_ENABLED(CONFIG_KASAN_VMALLOC) ||
	     (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
	      !IS_ENABLED(CONFIG_KASAN_SW_TAGS))))
		/*
		 * KASAN without KASAN_VMALLOC can only deal with module
		 * allocations being served from the reserved module region,
		 * since the remainder of the vmalloc region is already
		 * backed by zero shadow pages, and punching holes into it
		 * is non-trivial. Since the module region is not randomized
		 * when KASAN is enabled without KASAN_VMALLOC, it is even
		 * less likely that the module region gets exhausted, so we
		 * can simply omit this fallback in that case.
		 */
		p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
				module_alloc_base + SZ_2G, GFP_KERNEL,
				PAGE_KERNEL, 0, NUMA_NO_NODE,
				__builtin_return_address(0));

	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
		vfree(p);
		return NULL;
	}

	/* Memory is intended to be executable, reset the pointer tag. */
	return kasan_reset_tag(p);
}

enum aarch64_reloc_op {
	RELOC_OP_NONE,
	RELOC_OP_ABS,
	RELOC_OP_PREL,
	RELOC_OP_PAGE,
};

static u64 do_reloc(enum aarch64_reloc_op reloc_op, __le32 *place, u64 val)
{
	switch (reloc_op) {
	case RELOC_OP_ABS:
		return val;
	case RELOC_OP_PREL:
		return val - (u64)place;
	case RELOC_OP_PAGE:
		return (val & ~0xfff) - ((u64)place & ~0xfff);
	case RELOC_OP_NONE:
		return 0;
	}

	pr_err("do_reloc: unknown relocation operation %d\n", reloc_op);
	return 0;
}

static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len)
{
	s64 sval = do_reloc(op, place, val);

	/*
	 * The ELF psABI for AArch64 documents the 16-bit and 32-bit place
	 * relative and absolute relocations as having a range of [-2^15, 2^16)
	 * or [-2^31, 2^32), respectively. However, in order to be able to
	 * detect overflows reliably, we have to choose whether we interpret
	 * such quantities as signed or as unsigned, and stick with it.
	 * The way we organize our address space requires a signed
	 * interpretation of 32-bit relative references, so let's use that
	 * for all R_AARCH64_PRELxx relocations. This means our upper
	 * bound for overflow detection should be Sxx_MAX rather than Uxx_MAX.
	 */

	switch (len) {
	case 16:
		*(s16 *)place = sval;
		switch (op) {
		case RELOC_OP_ABS:
			if (sval < 0 || sval > U16_MAX)
				return -ERANGE;
			break;
		case RELOC_OP_PREL:
			if (sval < S16_MIN || sval > S16_MAX)
				return -ERANGE;
			break;
		default:
			pr_err("Invalid 16-bit data relocation (%d)\n", op);
			return 0;
		}
		break;
	case 32:
		*(s32 *)place = sval;
		switch (op) {
		case RELOC_OP_ABS:
			if (sval < 0 || sval > U32_MAX)
				return -ERANGE;
			break;
		case RELOC_OP_PREL:
			if (sval < S32_MIN || sval > S32_MAX)
				return -ERANGE;
			break;
		default:
			pr_err("Invalid 32-bit data relocation (%d)\n", op);
			return 0;
		}
		break;
	case 64:
		*(s64 *)place = sval;
		break;
	default:
		pr_err("Invalid length (%d) for data relocation\n", len);
		return 0;
	}
	return 0;
}

enum aarch64_insn_movw_imm_type {
	AARCH64_INSN_IMM_MOVNZ,
	AARCH64_INSN_IMM_MOVKZ,
};

static int reloc_insn_movw(enum aarch64_reloc_op op, __le32 *place, u64 val,
			   int lsb, enum aarch64_insn_movw_imm_type imm_type)
{
	u64 imm;
	s64 sval;
	u32 insn = le32_to_cpu(*place);

	sval = do_reloc(op, place, val);
	imm = sval >> lsb;

	if (imm_type == AARCH64_INSN_IMM_MOVNZ) {
		/*
		 * For signed MOVW relocations, we have to manipulate the
		 * instruction encoding depending on whether or not the
		 * immediate is less than zero.
		 */
		insn &= ~(3 << 29);
		if (sval >= 0) {
			/* >=0: Set the instruction to MOVZ (opcode 10b). */
			insn |= 2 << 29;
		} else {
			/*
			 * <0: Set the instruction to MOVN (opcode 00b).
			 *     Since we've masked the opcode already, we
			 *     don't need to do anything other than
			 *     inverting the new immediate field.
			 */
			imm = ~imm;
		}
	}

	/* Update the instruction with the new encoding. */
	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
	*place = cpu_to_le32(insn);

	if (imm > U16_MAX)
		return -ERANGE;

	return 0;
}

static int reloc_insn_imm(enum aarch64_reloc_op op, __le32 *place, u64 val,
			  int lsb, int len, enum aarch64_insn_imm_type imm_type)
{
	u64 imm, imm_mask;
	s64 sval;
	u32 insn = le32_to_cpu(*place);

	/* Calculate the relocation value. */
	sval = do_reloc(op, place, val);
	sval >>= lsb;

	/* Extract the value bits and shift them to bit 0. */
	imm_mask = (BIT(lsb + len) - 1) >> lsb;
	imm = sval & imm_mask;

	/* Update the instruction's immediate field. */
	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
	*place = cpu_to_le32(insn);

	/*
	 * Extract the upper value bits (including the sign bit) and
	 * shift them to bit 0.
	 */
	sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1);

	/*
	 * Overflow has occurred if the upper bits are not all equal to
	 * the sign bit of the value.
	 */
	if ((u64)(sval + 1) >= 2)
		return -ERANGE;

	return 0;
}

static int reloc_insn_adrp(struct module *mod, Elf64_Shdr *sechdrs,
			   __le32 *place, u64 val)
{
	u32 insn;

	if (!is_forbidden_offset_for_adrp(place))
		return reloc_insn_imm(RELOC_OP_PAGE, place, val, 12, 21,
				      AARCH64_INSN_IMM_ADR);

	/* patch ADRP to ADR if it is in range */
	if (!reloc_insn_imm(RELOC_OP_PREL, place, val & ~0xfff, 0, 21,
			    AARCH64_INSN_IMM_ADR)) {
		insn = le32_to_cpu(*place);
		insn &= ~BIT(31);
	} else {
		/* out of range for ADR -> emit a veneer */
		val = module_emit_veneer_for_adrp(mod, sechdrs, place, val & ~0xfff);
		if (!val)
			return -ENOEXEC;
		insn = aarch64_insn_gen_branch_imm((u64)place, val,
						   AARCH64_INSN_BRANCH_NOLINK);
	}

	*place = cpu_to_le32(insn);
	return 0;
}

int apply_relocate_add(Elf64_Shdr *sechdrs,
		       const char *strtab,
		       unsigned int symindex,
		       unsigned int relsec,
		       struct module *me)
{
	unsigned int i;
	int ovf;
	bool overflow_check;
	Elf64_Sym *sym;
	void *loc;
	u64 val;
	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;

	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
		/* loc corresponds to P in the AArch64 ELF document. */
		loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
			+ rel[i].r_offset;

		/* sym is the ELF symbol we're referring to. */
		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
			+ ELF64_R_SYM(rel[i].r_info);

		/* val corresponds to (S + A) in the AArch64 ELF document. */
		val = sym->st_value + rel[i].r_addend;

		/* Check for overflow by default. */
		overflow_check = true;

		/* Perform the static relocation. */
		switch (ELF64_R_TYPE(rel[i].r_info)) {
		/* Null relocations. */
		case R_ARM_NONE:
		case R_AARCH64_NONE:
			ovf = 0;
			break;

		/* Data relocations. */
		case R_AARCH64_ABS64:
			overflow_check = false;
			ovf = reloc_data(RELOC_OP_ABS, loc, val, 64);
			break;
		case R_AARCH64_ABS32:
			ovf = reloc_data(RELOC_OP_ABS, loc, val, 32);
			break;
		case R_AARCH64_ABS16:
			ovf = reloc_data(RELOC_OP_ABS, loc, val, 16);
			break;
		case R_AARCH64_PREL64:
			overflow_check = false;
			ovf = reloc_data(RELOC_OP_PREL, loc, val, 64);
			break;
		case R_AARCH64_PREL32:
			ovf = reloc_data(RELOC_OP_PREL, loc, val, 32);
			break;
		case R_AARCH64_PREL16:
			ovf = reloc_data(RELOC_OP_PREL, loc, val, 16);
			break;

		/* MOVW instruction relocations. */
		case R_AARCH64_MOVW_UABS_G0_NC:
			overflow_check = false;
			fallthrough;
		case R_AARCH64_MOVW_UABS_G0:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_UABS_G1_NC:
			overflow_check = false;
			fallthrough;
		case R_AARCH64_MOVW_UABS_G1:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_UABS_G2_NC:
			overflow_check = false;
			fallthrough;
		case R_AARCH64_MOVW_UABS_G2:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_UABS_G3:
			/* We're using the top bits so we can't overflow. */
			overflow_check = false;
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_SABS_G0:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_SABS_G1:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_SABS_G2:
			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_PREL_G0_NC:
			overflow_check = false;
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_PREL_G0:
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_PREL_G1_NC:
			overflow_check = false;
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_PREL_G1:
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_PREL_G2_NC:
			overflow_check = false;
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
					      AARCH64_INSN_IMM_MOVKZ);
			break;
		case R_AARCH64_MOVW_PREL_G2:
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
					      AARCH64_INSN_IMM_MOVNZ);
			break;
		case R_AARCH64_MOVW_PREL_G3:
			/* We're using the top bits so we can't overflow. */
			overflow_check = false;
			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 48,
					      AARCH64_INSN_IMM_MOVNZ);
			break;

		/* Immediate instruction relocations. */
		case R_AARCH64_LD_PREL_LO19:
			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
					     AARCH64_INSN_IMM_19);
			break;
		case R_AARCH64_ADR_PREL_LO21:
			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
					     AARCH64_INSN_IMM_ADR);
			break;
		case R_AARCH64_ADR_PREL_PG_HI21_NC:
			overflow_check = false;
			fallthrough;
		case R_AARCH64_ADR_PREL_PG_HI21:
			ovf = reloc_insn_adrp(me, sechdrs, loc, val);
			if (ovf && ovf != -ERANGE)
				return ovf;
			break;
		case R_AARCH64_ADD_ABS_LO12_NC:
		case R_AARCH64_LDST8_ABS_LO12_NC:
			overflow_check = false;
			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 0, 12,
					     AARCH64_INSN_IMM_12);
			break;
		case R_AARCH64_LDST16_ABS_LO12_NC:
			overflow_check = false;
			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 1, 11,
					     AARCH64_INSN_IMM_12);
			break;
		case R_AARCH64_LDST32_ABS_LO12_NC:
			overflow_check = false;
			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 2, 10,
					     AARCH64_INSN_IMM_12);
			break;
		case R_AARCH64_LDST64_ABS_LO12_NC:
			overflow_check = false;
			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 3, 9,
					     AARCH64_INSN_IMM_12);
			break;
		case R_AARCH64_LDST128_ABS_LO12_NC:
			overflow_check = false;
			ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 4, 8,
					     AARCH64_INSN_IMM_12);
			break;
		case R_AARCH64_TSTBR14:
			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 14,
					     AARCH64_INSN_IMM_14);
			break;
		case R_AARCH64_CONDBR19:
			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
					     AARCH64_INSN_IMM_19);
			break;
		case R_AARCH64_JUMP26:
		case R_AARCH64_CALL26:
			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
					     AARCH64_INSN_IMM_26);

			if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
			    ovf == -ERANGE) {
				val = module_emit_plt_entry(me, sechdrs, loc, &rel[i], sym);
				if (!val)
					return -ENOEXEC;
				ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2,
						     26, AARCH64_INSN_IMM_26);
			}
			break;

		default:
			pr_err("module %s: unsupported RELA relocation: %llu\n",
			       me->name, ELF64_R_TYPE(rel[i].r_info));
			return -ENOEXEC;
		}

		if (overflow_check && ovf == -ERANGE)
			goto overflow;

	}

	return 0;

overflow:
	pr_err("module %s: overflow in relocation type %d val %Lx\n",
	       me->name, (int)ELF64_R_TYPE(rel[i].r_info), val);
	return -ENOEXEC;
}

static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
				    const Elf_Shdr *sechdrs,
				    const char *name)
{
	const Elf_Shdr *s, *se;
	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;

	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
		if (strcmp(name, secstrs + s->sh_name) == 0)
			return s;
	}

	return NULL;
}

static inline void __init_plt(struct plt_entry *plt, unsigned long addr)
{
	*plt = get_plt_entry(addr, plt);
}

static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
				  const Elf_Shdr *sechdrs,
				  struct module *mod)
{
#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
	const Elf_Shdr *s;
	struct plt_entry *plts;

	s = find_section(hdr, sechdrs, ".text.ftrace_trampoline");
	if (!s)
		return -ENOEXEC;

	plts = (void *)s->sh_addr;

	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);

	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
		__init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR);

	mod->arch.ftrace_trampolines = plts;
#endif
	return 0;
}

int module_finalize(const Elf_Ehdr *hdr,
		    const Elf_Shdr *sechdrs,
		    struct module *me)
{
	const Elf_Shdr *s;
	s = find_section(hdr, sechdrs, ".altinstructions");
	if (s)
		apply_alternatives_module((void *)s->sh_addr, s->sh_size);

	return module_init_ftrace_plt(hdr, sechdrs, me);
}