core.c 55.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-or-later
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Linux Socket Filter - Kernel level socket filtering
 *
 * Based on the design of the Berkeley Packet Filter. The new
 * internal format has been designed by PLUMgrid:
 *
 *	Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
 *
 * Authors:
 *
 *	Jay Schulist <jschlst@samba.org>
 *	Alexei Starovoitov <ast@plumgrid.com>
 *	Daniel Borkmann <dborkman@redhat.com>
 *
 * Andi Kleen - Fix a few bad bugs and races.
17
 * Kris Katterjohn - Added many additional checks in bpf_check_classic()
18
 */
19

20
#include <uapi/linux/btf.h>
21 22
#include <linux/filter.h>
#include <linux/skbuff.h>
23
#include <linux/vmalloc.h>
24 25
#include <linux/random.h>
#include <linux/moduleloader.h>
26
#include <linux/bpf.h>
27
#include <linux/btf.h>
28
#include <linux/frame.h>
29 30 31
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
32
#include <linux/perf_event.h>
33
#include <linux/extable.h>
Daniel Borkmann's avatar
Daniel Borkmann committed
34 35
#include <asm/unaligned.h>

36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52
/* Registers */
#define BPF_R0	regs[BPF_REG_0]
#define BPF_R1	regs[BPF_REG_1]
#define BPF_R2	regs[BPF_REG_2]
#define BPF_R3	regs[BPF_REG_3]
#define BPF_R4	regs[BPF_REG_4]
#define BPF_R5	regs[BPF_REG_5]
#define BPF_R6	regs[BPF_REG_6]
#define BPF_R7	regs[BPF_REG_7]
#define BPF_R8	regs[BPF_REG_8]
#define BPF_R9	regs[BPF_REG_9]
#define BPF_R10	regs[BPF_REG_10]

/* Named registers */
#define DST	regs[insn->dst_reg]
#define SRC	regs[insn->src_reg]
#define FP	regs[BPF_REG_FP]
53
#define AX	regs[BPF_REG_AX]
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69
#define ARG1	regs[BPF_REG_ARG1]
#define CTX	regs[BPF_REG_CTX]
#define IMM	insn->imm

/* No hurry in this branch
 *
 * Exported for the bpf jit load helper.
 */
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
	u8 *ptr = NULL;

	if (k >= SKF_NET_OFF)
		ptr = skb_network_header(skb) + k - SKF_NET_OFF;
	else if (k >= SKF_LL_OFF)
		ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
Daniel Borkmann's avatar
Daniel Borkmann committed
70

71 72 73 74 75 76
	if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
		return ptr;

	return NULL;
}

77
struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags)
78
{
79
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
80
	struct bpf_prog_aux *aux;
81 82 83 84 85 86 87
	struct bpf_prog *fp;

	size = round_up(size, PAGE_SIZE);
	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
	if (fp == NULL)
		return NULL;

88 89
	aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
	if (aux == NULL) {
90 91 92 93 94
		vfree(fp);
		return NULL;
	}

	fp->pages = size / PAGE_SIZE;
95
	fp->aux = aux;
96
	fp->aux->prog = fp;
97
	fp->jit_requested = ebpf_jit_enabled();
98

99 100
	INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);

101 102
	return fp;
}
103 104 105 106 107

struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
{
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
	struct bpf_prog *prog;
108
	int cpu;
109 110 111 112 113 114 115 116 117 118 119 120

	prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags);
	if (!prog)
		return NULL;

	prog->aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
	if (!prog->aux->stats) {
		kfree(prog->aux);
		vfree(prog);
		return NULL;
	}

121 122 123 124 125 126
	for_each_possible_cpu(cpu) {
		struct bpf_prog_stats *pstats;

		pstats = per_cpu_ptr(prog->aux->stats, cpu);
		u64_stats_init(&pstats->syncp);
	}
127 128
	return prog;
}
129 130
EXPORT_SYMBOL_GPL(bpf_prog_alloc);

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
int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog)
{
	if (!prog->aux->nr_linfo || !prog->jit_requested)
		return 0;

	prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo,
					 sizeof(*prog->aux->jited_linfo),
					 GFP_KERNEL | __GFP_NOWARN);
	if (!prog->aux->jited_linfo)
		return -ENOMEM;

	return 0;
}

void bpf_prog_free_jited_linfo(struct bpf_prog *prog)
{
	kfree(prog->aux->jited_linfo);
	prog->aux->jited_linfo = NULL;
}

void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog)
{
	if (prog->aux->jited_linfo && !prog->aux->jited_linfo[0])
		bpf_prog_free_jited_linfo(prog);
}

/* The jit engine is responsible to provide an array
 * for insn_off to the jited_off mapping (insn_to_jit_off).
 *
 * The idx to this array is the insn_off.  Hence, the insn_off
 * here is relative to the prog itself instead of the main prog.
 * This array has one entry for each xlated bpf insn.
 *
 * jited_off is the byte off to the last byte of the jited insn.
 *
 * Hence, with
 * insn_start:
 *      The first bpf insn off of the prog.  The insn off
 *      here is relative to the main prog.
 *      e.g. if prog is a subprog, insn_start > 0
 * linfo_idx:
 *      The prog's idx to prog->aux->linfo and jited_linfo
 *
 * jited_linfo[linfo_idx] = prog->bpf_func
 *
 * For i > linfo_idx,
 *
 * jited_linfo[i] = prog->bpf_func +
 *	insn_to_jit_off[linfo[i].insn_off - insn_start - 1]
 */
void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
			       const u32 *insn_to_jit_off)
{
	u32 linfo_idx, insn_start, insn_end, nr_linfo, i;
	const struct bpf_line_info *linfo;
	void **jited_linfo;

	if (!prog->aux->jited_linfo)
		/* Userspace did not provide linfo */
		return;

	linfo_idx = prog->aux->linfo_idx;
	linfo = &prog->aux->linfo[linfo_idx];
	insn_start = linfo[0].insn_off;
	insn_end = insn_start + prog->len;

	jited_linfo = &prog->aux->jited_linfo[linfo_idx];
	jited_linfo[0] = prog->bpf_func;

	nr_linfo = prog->aux->nr_linfo - linfo_idx;

	for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++)
		/* The verifier ensures that linfo[i].insn_off is
		 * strictly increasing
		 */
		jited_linfo[i] = prog->bpf_func +
			insn_to_jit_off[linfo[i].insn_off - insn_start - 1];
}

void bpf_prog_free_linfo(struct bpf_prog *prog)
{
	bpf_prog_free_jited_linfo(prog);
	kvfree(prog->aux->linfo);
}

216 217 218
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
				  gfp_t gfp_extra_flags)
{
219
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
220
	struct bpf_prog *fp;
221 222
	u32 pages, delta;
	int ret;
223 224 225 226

	BUG_ON(fp_old == NULL);

	size = round_up(size, PAGE_SIZE);
227 228
	pages = size / PAGE_SIZE;
	if (pages <= fp_old->pages)
229 230
		return fp_old;

231 232 233 234 235
	delta = pages - fp_old->pages;
	ret = __bpf_prog_charge(fp_old->aux->user, delta);
	if (ret)
		return NULL;

236
	fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
237 238 239
	if (fp == NULL) {
		__bpf_prog_uncharge(fp_old->aux->user, delta);
	} else {
240
		memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
241
		fp->pages = pages;
242
		fp->aux->prog = fp;
243

244
		/* We keep fp->aux from fp_old around in the new
245 246
		 * reallocated structure.
		 */
247
		fp_old->aux = NULL;
248 249 250 251 252 253 254 255
		__bpf_prog_free(fp_old);
	}

	return fp;
}

void __bpf_prog_free(struct bpf_prog *fp)
{
256 257 258 259
	if (fp->aux) {
		free_percpu(fp->aux->stats);
		kfree(fp->aux);
	}
260 261 262
	vfree(fp);
}

263
int bpf_prog_calc_tag(struct bpf_prog *fp)
264 265
{
	const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
266 267
	u32 raw_size = bpf_prog_tag_scratch_size(fp);
	u32 digest[SHA_DIGEST_WORDS];
268
	u32 ws[SHA_WORKSPACE_WORDS];
269
	u32 i, bsize, psize, blocks;
270
	struct bpf_insn *dst;
271
	bool was_ld_map;
272
	u8 *raw, *todo;
273 274 275
	__be32 *result;
	__be64 *bits;

276 277 278 279
	raw = vmalloc(raw_size);
	if (!raw)
		return -ENOMEM;

280
	sha_init(digest);
281 282 283 284 285
	memset(ws, 0, sizeof(ws));

	/* We need to take out the map fd for the digest calculation
	 * since they are unstable from user space side.
	 */
286
	dst = (void *)raw;
287 288 289 290
	for (i = 0, was_ld_map = false; i < fp->len; i++) {
		dst[i] = fp->insnsi[i];
		if (!was_ld_map &&
		    dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
291 292
		    (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
		     dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
293 294 295 296 297 298 299 300 301 302 303 304 305 306
			was_ld_map = true;
			dst[i].imm = 0;
		} else if (was_ld_map &&
			   dst[i].code == 0 &&
			   dst[i].dst_reg == 0 &&
			   dst[i].src_reg == 0 &&
			   dst[i].off == 0) {
			was_ld_map = false;
			dst[i].imm = 0;
		} else {
			was_ld_map = false;
		}
	}

307 308
	psize = bpf_prog_insn_size(fp);
	memset(&raw[psize], 0, raw_size - psize);
309 310 311 312
	raw[psize++] = 0x80;

	bsize  = round_up(psize, SHA_MESSAGE_BYTES);
	blocks = bsize / SHA_MESSAGE_BYTES;
313
	todo   = raw;
314 315 316 317 318 319 320 321 322
	if (bsize - psize >= sizeof(__be64)) {
		bits = (__be64 *)(todo + bsize - sizeof(__be64));
	} else {
		bits = (__be64 *)(todo + bsize + bits_offset);
		blocks++;
	}
	*bits = cpu_to_be64((psize - 1) << 3);

	while (blocks--) {
323
		sha_transform(digest, todo, ws);
324 325 326
		todo += SHA_MESSAGE_BYTES;
	}

327
	result = (__force __be32 *)digest;
328
	for (i = 0; i < SHA_DIGEST_WORDS; i++)
329 330
		result[i] = cpu_to_be32(digest[i]);
	memcpy(fp->tag, result, sizeof(fp->tag));
331 332 333

	vfree(raw);
	return 0;
334 335
}

336
static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old,
337
				s32 end_new, s32 curr, const bool probe_pass)
338
{
339
	const s64 imm_min = S32_MIN, imm_max = S32_MAX;
340
	s32 delta = end_new - end_old;
341 342
	s64 imm = insn->imm;

343
	if (curr < pos && curr + imm + 1 >= end_old)
344
		imm += delta;
345
	else if (curr >= end_new && curr + imm + 1 < end_new)
346 347 348 349 350 351 352 353
		imm -= delta;
	if (imm < imm_min || imm > imm_max)
		return -ERANGE;
	if (!probe_pass)
		insn->imm = imm;
	return 0;
}

354
static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old,
355
				s32 end_new, s32 curr, const bool probe_pass)
356 357
{
	const s32 off_min = S16_MIN, off_max = S16_MAX;
358
	s32 delta = end_new - end_old;
359 360
	s32 off = insn->off;

361
	if (curr < pos && curr + off + 1 >= end_old)
362
		off += delta;
363
	else if (curr >= end_new && curr + off + 1 < end_new)
364 365 366 367 368 369 370 371
		off -= delta;
	if (off < off_min || off > off_max)
		return -ERANGE;
	if (!probe_pass)
		insn->off = off;
	return 0;
}

372 373
static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old,
			    s32 end_new, const bool probe_pass)
374
{
375
	u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0);
376
	struct bpf_insn *insn = prog->insnsi;
377
	int ret = 0;
378 379

	for (i = 0; i < insn_cnt; i++, insn++) {
380 381 382 383 384 385 386
		u8 code;

		/* In the probing pass we still operate on the original,
		 * unpatched image in order to check overflows before we
		 * do any other adjustments. Therefore skip the patchlet.
		 */
		if (probe_pass && i == pos) {
387 388
			i = end_new;
			insn = prog->insnsi + end_old;
389
		}
390
		code = insn->code;
Jiong Wang's avatar
Jiong Wang committed
391 392
		if ((BPF_CLASS(code) != BPF_JMP &&
		     BPF_CLASS(code) != BPF_JMP32) ||
393
		    BPF_OP(code) == BPF_EXIT)
394
			continue;
395
		/* Adjust offset of jmps if we cross patch boundaries. */
396
		if (BPF_OP(code) == BPF_CALL) {
397
			if (insn->src_reg != BPF_PSEUDO_CALL)
398
				continue;
399 400
			ret = bpf_adj_delta_to_imm(insn, pos, end_old,
						   end_new, i, probe_pass);
401
		} else {
402 403
			ret = bpf_adj_delta_to_off(insn, pos, end_old,
						   end_new, i, probe_pass);
404
		}
405 406
		if (ret)
			break;
407
	}
408 409

	return ret;
410 411
}

412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta)
{
	struct bpf_line_info *linfo;
	u32 i, nr_linfo;

	nr_linfo = prog->aux->nr_linfo;
	if (!nr_linfo || !delta)
		return;

	linfo = prog->aux->linfo;

	for (i = 0; i < nr_linfo; i++)
		if (off < linfo[i].insn_off)
			break;

	/* Push all off < linfo[i].insn_off by delta */
	for (; i < nr_linfo; i++)
		linfo[i].insn_off += delta;
}

432 433 434 435
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
				       const struct bpf_insn *patch, u32 len)
{
	u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
436
	const u32 cnt_max = S16_MAX;
437
	struct bpf_prog *prog_adj;
438
	int err;
439 440 441 442 443 444 445 446 447

	/* Since our patchlet doesn't expand the image, we're done. */
	if (insn_delta == 0) {
		memcpy(prog->insnsi + off, patch, sizeof(*patch));
		return prog;
	}

	insn_adj_cnt = prog->len + insn_delta;

448 449 450 451 452 453
	/* Reject anything that would potentially let the insn->off
	 * target overflow when we have excessive program expansions.
	 * We need to probe here before we do any reallocation where
	 * we afterwards may not fail anymore.
	 */
	if (insn_adj_cnt > cnt_max &&
454 455
	    (err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
		return ERR_PTR(err);
456

457 458 459 460 461 462 463
	/* Several new instructions need to be inserted. Make room
	 * for them. Likely, there's no need for a new allocation as
	 * last page could have large enough tailroom.
	 */
	prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
				    GFP_USER);
	if (!prog_adj)
464
		return ERR_PTR(-ENOMEM);
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481

	prog_adj->len = insn_adj_cnt;

	/* Patching happens in 3 steps:
	 *
	 * 1) Move over tail of insnsi from next instruction onwards,
	 *    so we can patch the single target insn with one or more
	 *    new ones (patching is always from 1 to n insns, n > 0).
	 * 2) Inject new instructions at the target location.
	 * 3) Adjust branch offsets if necessary.
	 */
	insn_rest = insn_adj_cnt - off - len;

	memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
		sizeof(*patch) * insn_rest);
	memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);

482 483 484 485
	/* We are guaranteed to not fail at this point, otherwise
	 * the ship has sailed to reverse to the original state. An
	 * overflow cannot happen at this point.
	 */
486
	BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false));
487

488 489
	bpf_adj_linfo(prog_adj, off, insn_delta);

490 491 492
	return prog_adj;
}

493 494 495 496 497 498 499 500 501 502 503 504
int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
{
	/* Branch offsets can't overflow when program is shrinking, no need
	 * to call bpf_adj_branches(..., true) here
	 */
	memmove(prog->insnsi + off, prog->insnsi + off + cnt,
		sizeof(struct bpf_insn) * (prog->len - off - cnt));
	prog->len -= cnt;

	return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
}

505 506 507 508 509 510 511 512 513 514 515 516 517 518
void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
	int i;

	for (i = 0; i < fp->aux->func_cnt; i++)
		bpf_prog_kallsyms_del(fp->aux->func[i]);
}

void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
{
	bpf_prog_kallsyms_del_subprogs(fp);
	bpf_prog_kallsyms_del(fp);
}

519
#ifdef CONFIG_BPF_JIT
520 521 522 523
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable   __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
int bpf_jit_harden   __read_mostly;
int bpf_jit_kallsyms __read_mostly;
524
long bpf_jit_limit   __read_mostly;
525

526 527 528 529 530 531 532 533 534 535 536 537 538 539
static __always_inline void
bpf_get_prog_addr_region(const struct bpf_prog *prog,
			 unsigned long *symbol_start,
			 unsigned long *symbol_end)
{
	const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
	unsigned long addr = (unsigned long)hdr;

	WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));

	*symbol_start = addr;
	*symbol_end   = addr + hdr->pages * PAGE_SIZE;
}

540
void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
541
{
542
	const char *end = sym + KSYM_NAME_LEN;
543 544
	const struct btf_type *type;
	const char *func_name;
545

546
	BUILD_BUG_ON(sizeof("bpf_prog_") +
547 548 549 550 551 552 553 554 555
		     sizeof(prog->tag) * 2 +
		     /* name has been null terminated.
		      * We should need +1 for the '_' preceding
		      * the name.  However, the null character
		      * is double counted between the name and the
		      * sizeof("bpf_prog_") above, so we omit
		      * the +1 here.
		      */
		     sizeof(prog->aux->name) > KSYM_NAME_LEN);
556 557 558

	sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
	sym  = bin2hex(sym, prog->tag, sizeof(prog->tag));
559 560

	/* prog->aux->name will be ignored if full btf name is available */
561
	if (prog->aux->func_info_cnt) {
562 563
		type = btf_type_by_id(prog->aux->btf,
				      prog->aux->func_info[prog->aux->func_idx].type_id);
564 565 566 567 568
		func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
		snprintf(sym, (size_t)(end - sym), "_%s", func_name);
		return;
	}

569 570 571 572
	if (prog->aux->name[0])
		snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
	else
		*sym = 0;
573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651
}

static __always_inline unsigned long
bpf_get_prog_addr_start(struct latch_tree_node *n)
{
	unsigned long symbol_start, symbol_end;
	const struct bpf_prog_aux *aux;

	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);

	return symbol_start;
}

static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
					  struct latch_tree_node *b)
{
	return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
}

static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
{
	unsigned long val = (unsigned long)key;
	unsigned long symbol_start, symbol_end;
	const struct bpf_prog_aux *aux;

	aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
	bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);

	if (val < symbol_start)
		return -1;
	if (val >= symbol_end)
		return  1;

	return 0;
}

static const struct latch_tree_ops bpf_tree_ops = {
	.less	= bpf_tree_less,
	.comp	= bpf_tree_comp,
};

static DEFINE_SPINLOCK(bpf_lock);
static LIST_HEAD(bpf_kallsyms);
static struct latch_tree_root bpf_tree __cacheline_aligned;

static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
{
	WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
	list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
	latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
}

static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
{
	if (list_empty(&aux->ksym_lnode))
		return;

	latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
	list_del_rcu(&aux->ksym_lnode);
}

static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
{
	return fp->jited && !bpf_prog_was_classic(fp);
}

static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
{
	return list_empty(&fp->aux->ksym_lnode) ||
	       fp->aux->ksym_lnode.prev == LIST_POISON2;
}

void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
	if (!bpf_prog_kallsyms_candidate(fp) ||
	    !capable(CAP_SYS_ADMIN))
		return;

652
	spin_lock_bh(&bpf_lock);
653
	bpf_prog_ksym_node_add(fp->aux);
654
	spin_unlock_bh(&bpf_lock);
655 656 657 658 659 660 661
}

void bpf_prog_kallsyms_del(struct bpf_prog *fp)
{
	if (!bpf_prog_kallsyms_candidate(fp))
		return;

662
	spin_lock_bh(&bpf_lock);
663
	bpf_prog_ksym_node_del(fp->aux);
664
	spin_unlock_bh(&bpf_lock);
665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714
}

static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
{
	struct latch_tree_node *n;

	if (!bpf_jit_kallsyms_enabled())
		return NULL;

	n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
	return n ?
	       container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
	       NULL;
}

const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
				 unsigned long *off, char *sym)
{
	unsigned long symbol_start, symbol_end;
	struct bpf_prog *prog;
	char *ret = NULL;

	rcu_read_lock();
	prog = bpf_prog_kallsyms_find(addr);
	if (prog) {
		bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
		bpf_get_prog_name(prog, sym);

		ret = sym;
		if (size)
			*size = symbol_end - symbol_start;
		if (off)
			*off  = addr - symbol_start;
	}
	rcu_read_unlock();

	return ret;
}

bool is_bpf_text_address(unsigned long addr)
{
	bool ret;

	rcu_read_lock();
	ret = bpf_prog_kallsyms_find(addr) != NULL;
	rcu_read_unlock();

	return ret;
}

715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
const struct exception_table_entry *search_bpf_extables(unsigned long addr)
{
	const struct exception_table_entry *e = NULL;
	struct bpf_prog *prog;

	rcu_read_lock();
	prog = bpf_prog_kallsyms_find(addr);
	if (!prog)
		goto out;
	if (!prog->aux->num_exentries)
		goto out;

	e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr);
out:
	rcu_read_unlock();
	return e;
}

733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
		    char *sym)
{
	struct bpf_prog_aux *aux;
	unsigned int it = 0;
	int ret = -ERANGE;

	if (!bpf_jit_kallsyms_enabled())
		return ret;

	rcu_read_lock();
	list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
		if (it++ != symnum)
			continue;

		bpf_get_prog_name(aux->prog, sym);

750
		*value = (unsigned long)aux->prog->bpf_func;
751 752 753 754 755 756 757 758 759 760
		*type  = BPF_SYM_ELF_TYPE;

		ret = 0;
		break;
	}
	rcu_read_unlock();

	return ret;
}

761 762
static atomic_long_t bpf_jit_current;

763 764 765 766 767 768
/* Can be overridden by an arch's JIT compiler if it has a custom,
 * dedicated BPF backend memory area, or if neither of the two
 * below apply.
 */
u64 __weak bpf_jit_alloc_exec_limit(void)
{
769
#if defined(MODULES_VADDR)
770 771 772 773 774 775
	return MODULES_END - MODULES_VADDR;
#else
	return VMALLOC_END - VMALLOC_START;
#endif
}

776 777 778
static int __init bpf_jit_charge_init(void)
{
	/* Only used as heuristic here to derive limit. */
779 780
	bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
					    PAGE_SIZE), LONG_MAX);
781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802
	return 0;
}
pure_initcall(bpf_jit_charge_init);

static int bpf_jit_charge_modmem(u32 pages)
{
	if (atomic_long_add_return(pages, &bpf_jit_current) >
	    (bpf_jit_limit >> PAGE_SHIFT)) {
		if (!capable(CAP_SYS_ADMIN)) {
			atomic_long_sub(pages, &bpf_jit_current);
			return -EPERM;
		}
	}

	return 0;
}

static void bpf_jit_uncharge_modmem(u32 pages)
{
	atomic_long_sub(pages, &bpf_jit_current);
}

803 804 805 806 807 808 809 810 811 812
void *__weak bpf_jit_alloc_exec(unsigned long size)
{
	return module_alloc(size);
}

void __weak bpf_jit_free_exec(void *addr)
{
	module_memfree(addr);
}

813 814 815 816 817 818
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
		     unsigned int alignment,
		     bpf_jit_fill_hole_t bpf_fill_ill_insns)
{
	struct bpf_binary_header *hdr;
819
	u32 size, hole, start, pages;
820 821 822 823 824 825

	/* Most of BPF filters are really small, but if some of them
	 * fill a page, allow at least 128 extra bytes to insert a
	 * random section of illegal instructions.
	 */
	size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
826 827 828 829
	pages = size / PAGE_SIZE;

	if (bpf_jit_charge_modmem(pages))
		return NULL;
830
	hdr = bpf_jit_alloc_exec(size);
831 832
	if (!hdr) {
		bpf_jit_uncharge_modmem(pages);
833
		return NULL;
834
	}
835 836 837 838

	/* Fill space with illegal/arch-dep instructions. */
	bpf_fill_ill_insns(hdr, size);

839
	hdr->pages = pages;
840 841
	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
		     PAGE_SIZE - sizeof(*hdr));
842
	start = (get_random_int() % hole) & ~(alignment - 1);
843 844 845 846 847 848 849 850 851

	/* Leave a random number of instructions before BPF code. */
	*image_ptr = &hdr->image[start];

	return hdr;
}

void bpf_jit_binary_free(struct bpf_binary_header *hdr)
{
852 853
	u32 pages = hdr->pages;

854
	bpf_jit_free_exec(hdr);
855
	bpf_jit_uncharge_modmem(pages);
856
}
857

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874
/* This symbol is only overridden by archs that have different
 * requirements than the usual eBPF JITs, f.e. when they only
 * implement cBPF JIT, do not set images read-only, etc.
 */
void __weak bpf_jit_free(struct bpf_prog *fp)
{
	if (fp->jited) {
		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);

		bpf_jit_binary_free(hdr);

		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
	}

	bpf_prog_unlock_free(fp);
}

875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908
int bpf_jit_get_func_addr(const struct bpf_prog *prog,
			  const struct bpf_insn *insn, bool extra_pass,
			  u64 *func_addr, bool *func_addr_fixed)
{
	s16 off = insn->off;
	s32 imm = insn->imm;
	u8 *addr;

	*func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
	if (!*func_addr_fixed) {
		/* Place-holder address till the last pass has collected
		 * all addresses for JITed subprograms in which case we
		 * can pick them up from prog->aux.
		 */
		if (!extra_pass)
			addr = NULL;
		else if (prog->aux->func &&
			 off >= 0 && off < prog->aux->func_cnt)
			addr = (u8 *)prog->aux->func[off]->bpf_func;
		else
			return -EINVAL;
	} else {
		/* Address of a BPF helper call. Since part of the core
		 * kernel, it's always at a fixed location. __bpf_call_base
		 * and the helper with imm relative to it are both in core
		 * kernel.
		 */
		addr = (u8 *)__bpf_call_base + imm;
	}

	*func_addr = (unsigned long)addr;
	return 0;
}

909 910
static int bpf_jit_blind_insn(const struct bpf_insn *from,
			      const struct bpf_insn *aux,
911 912
			      struct bpf_insn *to_buff,
			      bool emit_zext)
913 914
{
	struct bpf_insn *to = to_buff;
915
	u32 imm_rnd = get_random_int();
916 917 918 919 920
	s16 off;

	BUILD_BUG_ON(BPF_REG_AX  + 1 != MAX_BPF_JIT_REG);
	BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
	/* Constraints on AX register:
	 *
	 * AX register is inaccessible from user space. It is mapped in
	 * all JITs, and used here for constant blinding rewrites. It is
	 * typically "stateless" meaning its contents are only valid within
	 * the executed instruction, but not across several instructions.
	 * There are a few exceptions however which are further detailed
	 * below.
	 *
	 * Constant blinding is only used by JITs, not in the interpreter.
	 * The interpreter uses AX in some occasions as a local temporary
	 * register e.g. in DIV or MOD instructions.
	 *
	 * In restricted circumstances, the verifier can also use the AX
	 * register for rewrites as long as they do not interfere with
	 * the above cases!
	 */
	if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX)
		goto out;

941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979
	if (from->imm == 0 &&
	    (from->code == (BPF_ALU   | BPF_MOV | BPF_K) ||
	     from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
		*to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg);
		goto out;
	}

	switch (from->code) {
	case BPF_ALU | BPF_ADD | BPF_K:
	case BPF_ALU | BPF_SUB | BPF_K:
	case BPF_ALU | BPF_AND | BPF_K:
	case BPF_ALU | BPF_OR  | BPF_K:
	case BPF_ALU | BPF_XOR | BPF_K:
	case BPF_ALU | BPF_MUL | BPF_K:
	case BPF_ALU | BPF_MOV | BPF_K:
	case BPF_ALU | BPF_DIV | BPF_K:
	case BPF_ALU | BPF_MOD | BPF_K:
		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
		break;

	case BPF_ALU64 | BPF_ADD | BPF_K:
	case BPF_ALU64 | BPF_SUB | BPF_K:
	case BPF_ALU64 | BPF_AND | BPF_K:
	case BPF_ALU64 | BPF_OR  | BPF_K:
	case BPF_ALU64 | BPF_XOR | BPF_K:
	case BPF_ALU64 | BPF_MUL | BPF_K:
	case BPF_ALU64 | BPF_MOV | BPF_K:
	case BPF_ALU64 | BPF_DIV | BPF_K:
	case BPF_ALU64 | BPF_MOD | BPF_K:
		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
		break;

	case BPF_JMP | BPF_JEQ  | BPF_K:
	case BPF_JMP | BPF_JNE  | BPF_K:
	case BPF_JMP | BPF_JGT  | BPF_K:
980
	case BPF_JMP | BPF_JLT  | BPF_K:
981
	case BPF_JMP | BPF_JGE  | BPF_K:
982
	case BPF_JMP | BPF_JLE  | BPF_K:
983
	case BPF_JMP | BPF_JSGT | BPF_K:
984
	case BPF_JMP | BPF_JSLT | BPF_K:
985
	case BPF_JMP | BPF_JSGE | BPF_K:
986
	case BPF_JMP | BPF_JSLE | BPF_K:
987 988 989 990 991 992 993 994 995 996
	case BPF_JMP | BPF_JSET | BPF_K:
		/* Accommodate for extra offset in case of a backjump. */
		off = from->off;
		if (off < 0)
			off -= 2;
		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
		break;

Jiong Wang's avatar
Jiong Wang committed
997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017
	case BPF_JMP32 | BPF_JEQ  | BPF_K:
	case BPF_JMP32 | BPF_JNE  | BPF_K:
	case BPF_JMP32 | BPF_JGT  | BPF_K:
	case BPF_JMP32 | BPF_JLT  | BPF_K:
	case BPF_JMP32 | BPF_JGE  | BPF_K:
	case BPF_JMP32 | BPF_JLE  | BPF_K:
	case BPF_JMP32 | BPF_JSGT | BPF_K:
	case BPF_JMP32 | BPF_JSLT | BPF_K:
	case BPF_JMP32 | BPF_JSGE | BPF_K:
	case BPF_JMP32 | BPF_JSLE | BPF_K:
	case BPF_JMP32 | BPF_JSET | BPF_K:
		/* Accommodate for extra offset in case of a backjump. */
		off = from->off;
		if (off < 0)
			off -= 2;
		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX,
				      off);
		break;

1018 1019 1020 1021 1022 1023 1024 1025 1026
	case BPF_LD | BPF_IMM | BPF_DW:
		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
		*to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX);
		break;
	case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
		*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
		*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
1027 1028
		if (emit_zext)
			*to++ = BPF_ZEXT_REG(BPF_REG_AX);
1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
		*to++ = BPF_ALU64_REG(BPF_OR,  aux[0].dst_reg, BPF_REG_AX);
		break;

	case BPF_ST | BPF_MEM | BPF_DW:
	case BPF_ST | BPF_MEM | BPF_W:
	case BPF_ST | BPF_MEM | BPF_H:
	case BPF_ST | BPF_MEM | BPF_B:
		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
		*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
		break;
	}
out:
	return to - to_buff;
}

static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
					      gfp_t gfp_extra_flags)
{
1048
	gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
	struct bpf_prog *fp;

	fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
	if (fp != NULL) {
		/* aux->prog still points to the fp_other one, so
		 * when promoting the clone to the real program,
		 * this still needs to be adapted.
		 */
		memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE);
	}

	return fp;
}

static void bpf_prog_clone_free(struct bpf_prog *fp)
{
	/* aux was stolen by the other clone, so we cannot free
	 * it from this path! It will be freed eventually by the
	 * other program on release.
	 *
	 * At this point, we don't need a deferred release since
	 * clone is guaranteed to not be locked.
	 */
	fp->aux = NULL;
	__bpf_prog_free(fp);
}

void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
{
	/* We have to repoint aux->prog to self, as we don't
	 * know whether fp here is the clone or the original.
	 */
	fp->aux->prog = fp;
	bpf_prog_clone_free(fp_other);
}

struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
{
	struct bpf_insn insn_buff[16], aux[2];
	struct bpf_prog *clone, *tmp;
	int insn_delta, insn_cnt;
	struct bpf_insn *insn;
	int i, rewritten;

1093
	if (!bpf_jit_blinding_enabled(prog) || prog->blinded)
1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111
		return prog;

	clone = bpf_prog_clone_create(prog, GFP_USER);
	if (!clone)
		return ERR_PTR(-ENOMEM);

	insn_cnt = clone->len;
	insn = clone->insnsi;

	for (i = 0; i < insn_cnt; i++, insn++) {
		/* We temporarily need to hold the original ld64 insn
		 * so that we can still access the first part in the
		 * second blinding run.
		 */
		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) &&
		    insn[1].code == 0)
			memcpy(aux, insn, sizeof(aux));

1112 1113
		rewritten = bpf_jit_blind_insn(insn, aux, insn_buff,
						clone->aux->verifier_zext);
1114 1115 1116 1117
		if (!rewritten)
			continue;

		tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
1118
		if (IS_ERR(tmp)) {
1119 1120 1121 1122 1123
			/* Patching may have repointed aux->prog during
			 * realloc from the original one, so we need to
			 * fix it up here on error.
			 */
			bpf_jit_prog_release_other(prog, clone);
1124
			return tmp;
1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
		}

		clone = tmp;
		insn_delta = rewritten - 1;

		/* Walk new program and skip insns we just inserted. */
		insn = clone->insnsi + i + insn_delta;
		insn_cnt += insn_delta;
		i        += insn_delta;
	}

1136
	clone->blinded = 1;
1137 1138
	return clone;
}
1139
#endif /* CONFIG_BPF_JIT */
1140

1141 1142
/* Base function for offset calculation. Needs to go into .text section,
 * therefore keeping it non-static as well; will also be used by JITs
1143 1144 1145
 * anyway later on, so do not let the compiler omit it. This also needs
 * to go into kallsyms for correlation from e.g. bpftool, so naming
 * must not change.
1146 1147 1148 1149 1150
 */
noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
	return 0;
}
1151
EXPORT_SYMBOL_GPL(__bpf_call_base);
1152

1153 1154 1155 1156
/* All UAPI available opcodes. */
#define BPF_INSN_MAP(INSN_2, INSN_3)		\
	/* 32 bit ALU operations. */		\
	/*   Register based. */			\
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168
	INSN_3(ALU, ADD,  X),			\
	INSN_3(ALU, SUB,  X),			\
	INSN_3(ALU, AND,  X),			\
	INSN_3(ALU, OR,   X),			\
	INSN_3(ALU, LSH,  X),			\
	INSN_3(ALU, RSH,  X),			\
	INSN_3(ALU, XOR,  X),			\
	INSN_3(ALU, MUL,  X),			\
	INSN_3(ALU, MOV,  X),			\
	INSN_3(ALU, ARSH, X),			\
	INSN_3(ALU, DIV,  X),			\
	INSN_3(ALU, MOD,  X),			\
1169 1170 1171 1172
	INSN_2(ALU, NEG),			\
	INSN_3(ALU, END, TO_BE),		\
	INSN_3(ALU, END, TO_LE),		\
	/*   Immediate based. */		\
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184
	INSN_3(ALU, ADD,  K),			\
	INSN_3(ALU, SUB,  K),			\
	INSN_3(ALU, AND,  K),			\
	INSN_3(ALU, OR,   K),			\
	INSN_3(ALU, LSH,  K),			\
	INSN_3(ALU, RSH,  K),			\
	INSN_3(ALU, XOR,  K),			\
	INSN_3(ALU, MUL,  K),			\
	INSN_3(ALU, MOV,  K),			\
	INSN_3(ALU, ARSH, K),			\
	INSN_3(ALU, DIV,  K),			\
	INSN_3(ALU, MOD,  K),			\
1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216
	/* 64 bit ALU operations. */		\
	/*   Register based. */			\
	INSN_3(ALU64, ADD,  X),			\
	INSN_3(ALU64, SUB,  X),			\
	INSN_3(ALU64, AND,  X),			\
	INSN_3(ALU64, OR,   X),			\
	INSN_3(ALU64, LSH,  X),			\
	INSN_3(ALU64, RSH,  X),			\
	INSN_3(ALU64, XOR,  X),			\
	INSN_3(ALU64, MUL,  X),			\
	INSN_3(ALU64, MOV,  X),			\
	INSN_3(ALU64, ARSH, X),			\
	INSN_3(ALU64, DIV,  X),			\
	INSN_3(ALU64, MOD,  X),			\
	INSN_2(ALU64, NEG),			\
	/*   Immediate based. */		\
	INSN_3(ALU64, ADD,  K),			\
	INSN_3(ALU64, SUB,  K),			\
	INSN_3(ALU64, AND,  K),			\
	INSN_3(ALU64, OR,   K),			\
	INSN_3(ALU64, LSH,  K),			\
	INSN_3(ALU64, RSH,  K),			\
	INSN_3(ALU64, XOR,  K),			\
	INSN_3(ALU64, MUL,  K),			\
	INSN_3(ALU64, MOV,  K),			\
	INSN_3(ALU64, ARSH, K),			\
	INSN_3(ALU64, DIV,  K),			\
	INSN_3(ALU64, MOD,  K),			\
	/* Call instruction. */			\
	INSN_2(JMP, CALL),			\
	/* Exit instruction. */			\
	INSN_2(JMP, EXIT),			\
1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
	/* 32-bit Jump instructions. */		\
	/*   Register based. */			\
	INSN_3(JMP32, JEQ,  X),			\
	INSN_3(JMP32, JNE,  X),			\
	INSN_3(JMP32, JGT,  X),			\
	INSN_3(JMP32, JLT,  X),			\
	INSN_3(JMP32, JGE,  X),			\
	INSN_3(JMP32, JLE,  X),			\
	INSN_3(JMP32, JSGT, X),			\
	INSN_3(JMP32, JSLT, X),			\
	INSN_3(JMP32, JSGE, X),			\
	INSN_3(JMP32, JSLE, X),			\
	INSN_3(JMP32, JSET, X),			\
	/*   Immediate based. */		\
	INSN_3(JMP32, JEQ,  K),			\
	INSN_3(JMP32, JNE,  K),			\
	INSN_3(JMP32, JGT,  K),			\
	INSN_3(JMP32, JLT,  K),			\
	INSN_3(JMP32, JGE,  K),			\
	INSN_3(JMP32, JLE,  K),			\
	INSN_3(JMP32, JSGT, K),			\
	INSN_3(JMP32, JSLT, K),			\
	INSN_3(JMP32, JSGE, K),			\
	INSN_3(JMP32, JSLE, K),			\
	INSN_3(JMP32, JSET, K),			\
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287
	/* Jump instructions. */		\
	/*   Register based. */			\
	INSN_3(JMP, JEQ,  X),			\
	INSN_3(JMP, JNE,  X),			\
	INSN_3(JMP, JGT,  X),			\
	INSN_3(JMP, JLT,  X),			\
	INSN_3(JMP, JGE,  X),			\
	INSN_3(JMP, JLE,  X),			\
	INSN_3(JMP, JSGT, X),			\
	INSN_3(JMP, JSLT, X),			\
	INSN_3(JMP, JSGE, X),			\
	INSN_3(JMP, JSLE, X),			\
	INSN_3(JMP, JSET, X),			\
	/*   Immediate based. */		\
	INSN_3(JMP, JEQ,  K),			\
	INSN_3(JMP, JNE,  K),			\
	INSN_3(JMP, JGT,  K),			\
	INSN_3(JMP, JLT,  K),			\
	INSN_3(JMP, JGE,  K),			\
	INSN_3(JMP, JLE,  K),			\
	INSN_3(JMP, JSGT, K),			\
	INSN_3(JMP, JSLT, K),			\
	INSN_3(JMP, JSGE, K),			\
	INSN_3(JMP, JSLE, K),			\
	INSN_3(JMP, JSET, K),			\
	INSN_2(JMP, JA),			\
	/* Store instructions. */		\
	/*   Register based. */			\
	INSN_3(STX, MEM,  B),			\
	INSN_3(STX, MEM,  H),			\
	INSN_3(STX, MEM,  W),			\
	INSN_3(STX, MEM,  DW),			\
	INSN_3(STX, XADD, W),			\
	INSN_3(STX, XADD, DW),			\
	/*   Immediate based. */		\
	INSN_3(ST, MEM, B),			\
	INSN_3(ST, MEM, H),			\
	INSN_3(ST, MEM, W),			\
	INSN_3(ST, MEM, DW),			\
	/* Load instructions. */		\
	/*   Register based. */			\
	INSN_3(LDX, MEM, B),			\
	INSN_3(LDX, MEM, H),			\
	INSN_3(LDX, MEM, W),			\
	INSN_3(LDX, MEM, DW),			\
	/*   Immediate based. */		\
1288
	INSN_3(LD, IMM, DW)
1289 1290 1291 1292 1293 1294 1295 1296 1297

bool bpf_opcode_in_insntable(u8 code)
{
#define BPF_INSN_2_TBL(x, y)    [BPF_##x | BPF_##y] = true
#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
	static const bool public_insntable[256] = {
		[0 ... 255] = false,
		/* Now overwrite non-defaults ... */
		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
1298 1299 1300 1301 1302 1303 1304
		/* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
		[BPF_LD | BPF_ABS | BPF_B] = true,
		[BPF_LD | BPF_ABS | BPF_H] = true,
		[BPF_LD | BPF_ABS | BPF_W] = true,
		[BPF_LD | BPF_IND | BPF_B] = true,
		[BPF_LD | BPF_IND | BPF_H] = true,
		[BPF_LD | BPF_IND | BPF_W] = true,
1305 1306 1307 1308 1309 1310
	};
#undef BPF_INSN_3_TBL
#undef BPF_INSN_2_TBL
	return public_insntable[code];
}

1311
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
1312 1313 1314 1315 1316
u64 __weak bpf_probe_read(void * dst, u32 size, const void * unsafe_ptr)
{
	memset(dst, 0, size);
	return -EFAULT;
}
1317
/**
1318
 *	__bpf_prog_run - run eBPF program on a given context
1319
 *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
1320
 *	@insn: is the array of eBPF instructions
1321
 *	@stack: is the eBPF storage stack
1322
 *
1323
 * Decode and execute eBPF instructions.
1324
 */
1325
static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
1326
{
1327 1328
#define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
1329
	static const void * const jumptable[256] __annotate_jump_table = {
1330 1331
		[0 ... 255] = &&default_label,
		/* Now overwrite non-defaults ... */
1332 1333
		BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
		/* Non-UAPI available opcodes. */
1334
		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
1335
		[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
1336 1337 1338 1339
		[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
		[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
		[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
		[BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW,
1340
	};
1341 1342
#undef BPF_INSN_3_LBL
#undef BPF_INSN_2_LBL
1343
	u32 tail_call_cnt = 0;
1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392

#define CONT	 ({ insn++; goto select_insn; })
#define CONT_JMP ({ insn++; goto select_insn; })

select_insn:
	goto *jumptable[insn->code];

	/* ALU */
#define ALU(OPCODE, OP)			\
	ALU64_##OPCODE##_X:		\
		DST = DST OP SRC;	\
		CONT;			\
	ALU_##OPCODE##_X:		\
		DST = (u32) DST OP (u32) SRC;	\
		CONT;			\
	ALU64_##OPCODE##_K:		\
		DST = DST OP IMM;		\
		CONT;			\
	ALU_##OPCODE##_K:		\
		DST = (u32) DST OP (u32) IMM;	\
		CONT;

	ALU(ADD,  +)
	ALU(SUB,  -)
	ALU(AND,  &)
	ALU(OR,   |)
	ALU(LSH, <<)
	ALU(RSH, >>)
	ALU(XOR,  ^)
	ALU(MUL,  *)
#undef ALU
	ALU_NEG:
		DST = (u32) -DST;
		CONT;
	ALU64_NEG:
		DST = -DST;
		CONT;
	ALU_MOV_X:
		DST = (u32) SRC;
		CONT;
	ALU_MOV_K:
		DST = (u32) IMM;
		CONT;
	ALU64_MOV_X:
		DST = SRC;
		CONT;
	ALU64_MOV_K:
		DST = IMM;
		CONT;
1393 1394 1395 1396
	LD_IMM_DW:
		DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
		insn++;
		CONT;
1397
	ALU_ARSH_X:
1398
		DST = (u64) (u32) (((s32) DST) >> SRC);
1399 1400
		CONT;
	ALU_ARSH_K:
1401
		DST = (u64) (u32) (((s32) DST) >> IMM);
1402
		CONT;
1403 1404 1405 1406 1407 1408 1409
	ALU64_ARSH_X:
		(*(s64 *) &DST) >>= SRC;
		CONT;
	ALU64_ARSH_K:
		(*(s64 *) &DST) >>= IMM;
		CONT;
	ALU64_MOD_X:
1410 1411
		div64_u64_rem(DST, SRC, &AX);
		DST = AX;
1412 1413
		CONT;
	ALU_MOD_X:
1414 1415
		AX = (u32) DST;
		DST = do_div(AX, (u32) SRC);
1416 1417
		CONT;
	ALU64_MOD_K:
1418 1419
		div64_u64_rem(DST, IMM, &AX);
		DST = AX;
1420 1421
		CONT;
	ALU_MOD_K:
1422 1423
		AX = (u32) DST;
		DST = do_div(AX, (u32) IMM);
1424 1425
		CONT;
	ALU64_DIV_X:
1426
		DST = div64_u64(DST, SRC);
1427 1428
		CONT;
	ALU_DIV_X:
1429 1430 1431
		AX = (u32) DST;
		do_div(AX, (u32) SRC);
		DST = (u32) AX;
1432 1433
		CONT;
	ALU64_DIV_K:
1434
		DST = div64_u64(DST, IMM);
1435 1436
		CONT;
	ALU_DIV_K:
1437 1438 1439
		AX = (u32) DST;
		do_div(AX, (u32) IMM);
		DST = (u32) AX;
1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
		CONT;
	ALU_END_TO_BE:
		switch (IMM) {
		case 16:
			DST = (__force u16) cpu_to_be16(DST);
			break;
		case 32:
			DST = (__force u32) cpu_to_be32(DST);
			break;
		case 64:
			DST = (__force u64) cpu_to_be64(DST);
			break;
		}
		CONT;
	ALU_END_TO_LE:
		switch (IMM) {
		case 16:
			DST = (__force u16) cpu_to_le16(DST);
			break;
		case 32:
			DST = (__force u32) cpu_to_le32(DST);
			break;
		case 64:
			DST = (__force u64) cpu_to_le64(DST);
			break;
		}
		CONT;

	/* CALL */
	JMP_CALL:
		/* Function call scratches BPF_R1-BPF_R5 registers,
		 * preserves BPF_R6-BPF_R9, and stores return value
		 * into BPF_R0.
		 */
		BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
						       BPF_R4, BPF_R5);
		CONT;

1478 1479 1480 1481 1482 1483 1484
	JMP_CALL_ARGS:
		BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
							    BPF_R3, BPF_R4,
							    BPF_R5,
							    insn + insn->off + 1);
		CONT;

1485 1486 1487 1488
	JMP_TAIL_CALL: {
		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
		struct bpf_array *array = container_of(map, struct bpf_array, map);
		struct bpf_prog *prog;
1489
		u32 index = BPF_R3;
1490 1491 1492 1493 1494 1495 1496 1497

		if (unlikely(index >= array->map.max_entries))
			goto out;
		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
			goto out;

		tail_call_cnt++;

1498
		prog = READ_ONCE(array->ptrs[index]);
1499
		if (!prog)
1500 1501
			goto out;

1502 1503 1504 1505 1506
		/* ARG1 at this point is guaranteed to point to CTX from
		 * the verifier side due to the fact that the tail call is
		 * handeled like a helper, that is, bpf_tail_call_proto,
		 * where arg1_type is ARG_PTR_TO_CTX.
		 */
1507 1508 1509 1510 1511
		insn = prog->insnsi;
		goto select_insn;
out:
		CONT;
	}
1512 1513 1514 1515 1516
	JMP_JA:
		insn += insn->off;
		CONT;
	JMP_EXIT:
		return BPF_R0;
1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554
	/* JMP */
#define COND_JMP(SIGN, OPCODE, CMP_OP)				\
	JMP_##OPCODE##_X:					\
		if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) {	\
			insn += insn->off;			\
			CONT_JMP;				\
		}						\
		CONT;						\
	JMP32_##OPCODE##_X:					\
		if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) {	\
			insn += insn->off;			\
			CONT_JMP;				\
		}						\
		CONT;						\
	JMP_##OPCODE##_K:					\
		if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) {	\
			insn += insn->off;			\
			CONT_JMP;				\
		}						\
		CONT;						\
	JMP32_##OPCODE##_K:					\
		if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) {	\
			insn += insn->off;			\
			CONT_JMP;				\
		}						\
		CONT;
	COND_JMP(u, JEQ, ==)
	COND_JMP(u, JNE, !=)
	COND_JMP(u, JGT, >)
	COND_JMP(u, JLT, <)
	COND_JMP(u, JGE, >=)
	COND_JMP(u, JLE, <=)
	COND_JMP(u, JSET, &)
	COND_JMP(s, JSGT, >)
	COND_JMP(s, JSLT, <)
	COND_JMP(s, JSGE, >=)
	COND_JMP(s, JSLE, <=)
#undef COND_JMP
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571
	/* STX and ST and LDX*/
#define LDST(SIZEOP, SIZE)						\
	STX_MEM_##SIZEOP:						\
		*(SIZE *)(unsigned long) (DST + insn->off) = SRC;	\
		CONT;							\
	ST_MEM_##SIZEOP:						\
		*(SIZE *)(unsigned long) (DST + insn->off) = IMM;	\
		CONT;							\
	LDX_MEM_##SIZEOP:						\
		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
		CONT;

	LDST(B,   u8)
	LDST(H,  u16)
	LDST(W,  u32)
	LDST(DW, u64)
#undef LDST
1572 1573 1574 1575 1576 1577 1578 1579 1580 1581
#define LDX_PROBE(SIZEOP, SIZE)						\
	LDX_PROBE_MEM_##SIZEOP:						\
		bpf_probe_read(&DST, SIZE, (const void *)(long) SRC);	\
		CONT;
	LDX_PROBE(B,  1)
	LDX_PROBE(H,  2)
	LDX_PROBE(W,  4)
	LDX_PROBE(DW, 8)
#undef LDX_PROBE

1582 1583 1584 1585 1586 1587 1588 1589 1590 1591
	STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
		atomic_add((u32) SRC, (atomic_t *)(unsigned long)
			   (DST + insn->off));
		CONT;
	STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
		atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
			     (DST + insn->off));
		CONT;

	default_label:
1592 1593 1594 1595 1596 1597 1598 1599
		/* If we ever reach this, we have a bug somewhere. Die hard here
		 * instead of just returning 0; we could be somewhere in a subprog,
		 * so execution could continue otherwise which we do /not/ want.
		 *
		 * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
		 */
		pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code);
		BUG_ON(1);
1600 1601
		return 0;
}
1602

1603 1604 1605 1606 1607
#define PROG_NAME(stack_size) __bpf_prog_run##stack_size
#define DEFINE_BPF_PROG_RUN(stack_size) \
static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
{ \
	u64 stack[stack_size / sizeof(u64)]; \
1608
	u64 regs[MAX_BPF_EXT_REG]; \
1609 1610 1611 1612
\
	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
	ARG1 = (u64) (unsigned long) ctx; \
	return ___bpf_prog_run(regs, insn, stack); \
1613
}
1614

1615 1616 1617 1618 1619 1620
#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
#define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \
static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
				      const struct bpf_insn *insn) \
{ \
	u64 stack[stack_size / sizeof(u64)]; \
1621
	u64 regs[MAX_BPF_EXT_REG]; \
1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
\
	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
	BPF_R1 = r1; \
	BPF_R2 = r2; \
	BPF_R3 = r3; \
	BPF_R4 = r4; \
	BPF_R5 = r5; \
	return ___bpf_prog_run(regs, insn, stack); \
}

1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642
#define EVAL1(FN, X) FN(X)
#define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y)
#define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y)
#define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y)
#define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y)
#define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y)

EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192);
EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384);
EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512);

1643 1644 1645 1646
EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192);
EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384);
EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);

1647 1648 1649 1650 1651 1652 1653 1654
#define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),

static unsigned int (*interpreters[])(const void *ctx,
				      const struct bpf_insn *insn) = {
EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
};
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672
#undef PROG_NAME_LIST
#define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size),
static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
				  const struct bpf_insn *insn) = {
EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
};
#undef PROG_NAME_LIST

void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
{
	stack_depth = max_t(u32, stack_depth, 1);
	insn->off = (s16) insn->imm;
	insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
		__bpf_call_base_args;
	insn->code = BPF_JMP | BPF_CALL_ARGS;
}
1673

1674
#else
1675 1676
static unsigned int __bpf_prog_ret0_warn(const void *ctx,
					 const struct bpf_insn *insn)
1677
{
1678 1679 1680 1681
	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
	 * is not working properly, so warn about it!
	 */
	WARN_ON_ONCE(1);
1682 1683 1684 1685
	return 0;
}
#endif

Daniel Borkmann's avatar
Daniel Borkmann committed
1686 1687
bool bpf_prog_array_compatible(struct bpf_array *array,
			       const struct bpf_prog *fp)
1688
{
1689 1690 1691
	if (fp->kprobe_override)
		return false;

Daniel Borkmann's avatar
Daniel Borkmann committed
1692 1693 1694 1695
	if (!array->owner_prog_type) {
		/* There's no owner yet where we could check for
		 * compatibility.
		 */
1696 1697
		array->owner_prog_type = fp->type;
		array->owner_jited = fp->jited;
Daniel Borkmann's avatar
Daniel Borkmann committed
1698 1699

		return true;
1700
	}
Daniel Borkmann's avatar
Daniel Borkmann committed
1701 1702 1703

	return array->owner_prog_type == fp->type &&
	       array->owner_jited == fp->jited;
1704 1705
}

Daniel Borkmann's avatar
Daniel Borkmann committed
1706
static int bpf_check_tail_call(const struct bpf_prog *fp)
1707 1708 1709 1710 1711
{
	struct bpf_prog_aux *aux = fp->aux;
	int i;

	for (i = 0; i < aux->used_map_cnt; i++) {
Daniel Borkmann's avatar
Daniel Borkmann committed
1712
		struct bpf_map *map = aux->used_maps[i];
1713 1714 1715 1716
		struct bpf_array *array;

		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
			continue;
Daniel Borkmann's avatar
Daniel Borkmann committed
1717

1718 1719 1720 1721 1722 1723 1724 1725
		array = container_of(map, struct bpf_array, map);
		if (!bpf_prog_array_compatible(array, fp))
			return -EINVAL;
	}

	return 0;
}

1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736
static void bpf_prog_select_func(struct bpf_prog *fp)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);

	fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
#else
	fp->bpf_func = __bpf_prog_ret0_warn;
#endif
}

1737
/**
Daniel Borkmann's avatar
Daniel Borkmann committed
1738
 *	bpf_prog_select_runtime - select exec runtime for BPF program
1739
 *	@fp: bpf_prog populated with internal BPF program
1740
 *	@err: pointer to error variable
1741
 *
Daniel Borkmann's avatar
Daniel Borkmann committed
1742 1743
 * Try to JIT eBPF program, if JIT is not available, use interpreter.
 * The BPF program will be executed via BPF_PROG_RUN() macro.
1744
 */
1745
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
1746
{
1747 1748 1749 1750 1751
	/* In case of BPF to BPF calls, verifier did all the prep
	 * work with regards to JITing, etc.
	 */
	if (fp->bpf_func)
		goto finalize;
1752

1753
	bpf_prog_select_func(fp);
1754

1755 1756 1757 1758 1759 1760
	/* eBPF JITs can rewrite the program in case constant
	 * blinding is active. However, in case of error during
	 * blinding, bpf_int_jit_compile() must always return a
	 * valid program, which in this case would simply not
	 * be JITed, but falls back to the interpreter.
	 */
1761
	if (!bpf_prog_is_dev_bound(fp->aux)) {
1762 1763 1764 1765
		*err = bpf_prog_alloc_jited_linfo(fp);
		if (*err)
			return fp;

1766
		fp = bpf_int_jit_compile(fp);
1767
		if (!fp->jited) {
1768 1769
			bpf_prog_free_jited_linfo(fp);
#ifdef CONFIG_BPF_JIT_ALWAYS_ON
1770 1771 1772
			*err = -ENOTSUPP;
			return fp;
#endif
1773 1774 1775
		} else {
			bpf_prog_free_unused_jited_linfo(fp);
		}
1776 1777 1778 1779 1780
	} else {
		*err = bpf_prog_offload_compile(fp);
		if (*err)
			return fp;
	}
1781 1782

finalize:
1783
	bpf_prog_lock_ro(fp);
1784

Daniel Borkmann's avatar
Daniel Borkmann committed
1785 1786 1787 1788 1789
	/* The tail call compatibility check can only be done at
	 * this late stage as we need to determine, if we deal
	 * with JITed or non JITed program concatenations and not
	 * all eBPF JITs might immediately support all features.
	 */
1790
	*err = bpf_check_tail_call(fp);
1791

1792
	return fp;
1793
}
1794
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
1795

1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809
static unsigned int __bpf_prog_ret1(const void *ctx,
				    const struct bpf_insn *insn)
{
	return 1;
}

static struct bpf_prog_dummy {
	struct bpf_prog prog;
} dummy_bpf_prog = {
	.prog = {
		.bpf_func = __bpf_prog_ret1,
	},
};

1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822
/* to avoid allocating empty bpf_prog_array for cgroups that
 * don't have bpf program attached use one global 'empty_prog_array'
 * It will not be modified the caller of bpf_prog_array_alloc()
 * (since caller requested prog_cnt == 0)
 * that pointer should be 'freed' by bpf_prog_array_free()
 */
static struct {
	struct bpf_prog_array hdr;
	struct bpf_prog *null_prog;
} empty_prog_array = {
	.null_prog = NULL,
};

1823
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
1824 1825 1826
{
	if (prog_cnt)
		return kzalloc(sizeof(struct bpf_prog_array) +
1827 1828
			       sizeof(struct bpf_prog_array_item) *
			       (prog_cnt + 1),
1829 1830 1831 1832 1833
			       flags);

	return &empty_prog_array.hdr;
}

1834
void bpf_prog_array_free(struct bpf_prog_array *progs)
1835
{
1836
	if (!progs || progs == &empty_prog_array.hdr)
1837 1838 1839 1840
		return;
	kfree_rcu(progs, rcu);
}

1841
int bpf_prog_array_length(struct bpf_prog_array *array)
1842
{
1843
	struct bpf_prog_array_item *item;
1844 1845
	u32 cnt = 0;

1846
	for (item = array->items; item->prog; item++)
1847
		if (item->prog != &dummy_bpf_prog.prog)
1848
			cnt++;
1849 1850 1851
	return cnt;
}

1852 1853 1854 1855 1856 1857 1858 1859 1860
bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
{
	struct bpf_prog_array_item *item;

	for (item = array->items; item->prog; item++)
		if (item->prog != &dummy_bpf_prog.prog)
			return false;
	return true;
}
1861

1862
static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
1863 1864 1865
				     u32 *prog_ids,
				     u32 request_cnt)
{
1866
	struct bpf_prog_array_item *item;
1867 1868
	int i = 0;

1869
	for (item = array->items; item->prog; item++) {
1870
		if (item->prog == &dummy_bpf_prog.prog)
1871
			continue;
1872
		prog_ids[i] = item->prog->aux->id;
1873
		if (++i == request_cnt) {
1874
			item++;
1875 1876 1877 1878
			break;
		}
	}

1879
	return !!(item->prog);
1880 1881
}

1882
int bpf_prog_array_copy_to_user(struct bpf_prog_array *array,
1883 1884
				__u32 __user *prog_ids, u32 cnt)
{
1885 1886
	unsigned long err = 0;
	bool nospc;
1887
	u32 *ids;
1888 1889 1890 1891 1892

	/* users of this function are doing:
	 * cnt = bpf_prog_array_length();
	 * if (cnt > 0)
	 *     bpf_prog_array_copy_to_user(..., cnt);
1893
	 * so below kcalloc doesn't need extra cnt > 0 check.
1894
	 */
1895
	ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
1896 1897
	if (!ids)
		return -ENOMEM;
1898
	nospc = bpf_prog_array_copy_core(array, ids, cnt);
1899 1900 1901 1902 1903
	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
	kfree(ids);
	if (err)
		return -EFAULT;
	if (nospc)
1904 1905 1906 1907
		return -ENOSPC;
	return 0;
}

1908
void bpf_prog_array_delete_safe(struct bpf_prog_array *array,
1909 1910
				struct bpf_prog *old_prog)
{
1911
	struct bpf_prog_array_item *item;
1912

1913
	for (item = array->items; item->prog; item++)
1914 1915
		if (item->prog == old_prog) {
			WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
1916 1917 1918 1919
			break;
		}
}

1920
int bpf_prog_array_copy(struct bpf_prog_array *old_array,
1921 1922 1923 1924 1925
			struct bpf_prog *exclude_prog,
			struct bpf_prog *include_prog,
			struct bpf_prog_array **new_array)
{
	int new_prog_cnt, carry_prog_cnt = 0;
1926
	struct bpf_prog_array_item *existing;
1927
	struct bpf_prog_array *array;
1928
	bool found_exclude = false;
1929 1930 1931 1932 1933 1934
	int new_prog_idx = 0;

	/* Figure out how many existing progs we need to carry over to
	 * the new array.
	 */
	if (old_array) {
1935 1936 1937
		existing = old_array->items;
		for (; existing->prog; existing++) {
			if (existing->prog == exclude_prog) {
1938 1939 1940
				found_exclude = true;
				continue;
			}
1941
			if (existing->prog != &dummy_bpf_prog.prog)
1942
				carry_prog_cnt++;
1943
			if (existing->prog == include_prog)
1944 1945 1946 1947
				return -EEXIST;
		}
	}

1948 1949 1950
	if (exclude_prog && !found_exclude)
		return -ENOENT;

1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
	/* How many progs (not NULL) will be in the new array? */
	new_prog_cnt = carry_prog_cnt;
	if (include_prog)
		new_prog_cnt += 1;

	/* Do we have any prog (not NULL) in the new array? */
	if (!new_prog_cnt) {
		*new_array = NULL;
		return 0;
	}

	/* +1 as the end of prog_array is marked with NULL */
	array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
	if (!array)
		return -ENOMEM;

	/* Fill in the new prog array */
	if (carry_prog_cnt) {
1969 1970 1971 1972 1973 1974 1975
		existing = old_array->items;
		for (; existing->prog; existing++)
			if (existing->prog != exclude_prog &&
			    existing->prog != &dummy_bpf_prog.prog) {
				array->items[new_prog_idx++].prog =
					existing->prog;
			}
1976 1977
	}
	if (include_prog)
1978 1979
		array->items[new_prog_idx++].prog = include_prog;
	array->items[new_prog_idx].prog = NULL;
1980 1981 1982 1983
	*new_array = array;
	return 0;
}

1984
int bpf_prog_array_copy_info(struct bpf_prog_array *array,
1985 1986
			     u32 *prog_ids, u32 request_cnt,
			     u32 *prog_cnt)
1987 1988 1989 1990 1991 1992
{
	u32 cnt = 0;

	if (array)
		cnt = bpf_prog_array_length(array);

1993
	*prog_cnt = cnt;
1994 1995 1996 1997 1998

	/* return early if user requested only program count or nothing to copy */
	if (!request_cnt || !cnt)
		return 0;

1999
	/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
2000
	return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
2001
								     : 0;
2002 2003
}

2004 2005
static void bpf_prog_free_deferred(struct work_struct *work)
{
2006
	struct bpf_prog_aux *aux;
2007
	int i;
2008

2009
	aux = container_of(work, struct bpf_prog_aux, work);
2010 2011
	if (bpf_prog_is_dev_bound(aux))
		bpf_prog_offload_destroy(aux->prog);
2012 2013 2014 2015
#ifdef CONFIG_PERF_EVENTS
	if (aux->prog->has_callchain_buf)
		put_callchain_buffers();
#endif
2016 2017 2018 2019 2020 2021 2022 2023
	for (i = 0; i < aux->func_cnt; i++)
		bpf_jit_free(aux->func[i]);
	if (aux->func_cnt) {
		kfree(aux->func);
		bpf_prog_unlock_free(aux->prog);
	} else {
		bpf_jit_free(aux->prog);
	}
2024 2025 2026
}

/* Free internal BPF program */
2027
void bpf_prog_free(struct bpf_prog *fp)
2028
{
2029
	struct bpf_prog_aux *aux = fp->aux;
2030

2031 2032
	INIT_WORK(&aux->work, bpf_prog_free_deferred);
	schedule_work(&aux->work);
2033
}
2034
EXPORT_SYMBOL_GPL(bpf_prog_free);
2035

2036 2037 2038 2039 2040 2041 2042 2043
/* RNG for unpriviledged user space with separated state from prandom_u32(). */
static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state);

void bpf_user_rnd_init_once(void)
{
	prandom_init_once(&bpf_user_rnd_state);
}

2044
BPF_CALL_0(bpf_user_rnd_u32)
2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056
{
	/* Should someone ever have the rather unwise idea to use some
	 * of the registers passed into this function, then note that
	 * this function is called from native eBPF and classic-to-eBPF
	 * transformations. Register assignments from both sides are
	 * different, f.e. classic always sets fn(ctx, A, X) here.
	 */
	struct rnd_state *state;
	u32 res;

	state = &get_cpu_var(bpf_user_rnd_state);
	res = prandom_u32_state(state);
2057
	put_cpu_var(bpf_user_rnd_state);
2058 2059 2060 2061

	return res;
}

2062 2063 2064 2065
/* Weak definitions of helper functions in case we don't have bpf syscall. */
const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
const struct bpf_func_proto bpf_map_update_elem_proto __weak;
const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
2066 2067 2068
const struct bpf_func_proto bpf_map_push_elem_proto __weak;
const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
2069 2070
const struct bpf_func_proto bpf_spin_lock_proto __weak;
const struct bpf_func_proto bpf_spin_unlock_proto __weak;
2071

2072
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
2073
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
2074
const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
2075
const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
2076

2077 2078 2079
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
const struct bpf_func_proto bpf_get_current_comm_proto __weak;
2080
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
2081
const struct bpf_func_proto bpf_get_local_storage_proto __weak;
2082

2083 2084 2085 2086
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
	return NULL;
}
2087

2088 2089 2090
u64 __weak
bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
		 void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
2091
{
2092
	return -ENOTSUPP;
2093
}
2094
EXPORT_SYMBOL_GPL(bpf_event_output);
2095

Daniel Borkmann's avatar
Daniel Borkmann committed
2096 2097 2098 2099 2100 2101 2102 2103 2104 2105
/* Always built-in helper functions. */
const struct bpf_func_proto bpf_tail_call_proto = {
	.func		= NULL,
	.gpl_only	= false,
	.ret_type	= RET_VOID,
	.arg1_type	= ARG_PTR_TO_CTX,
	.arg2_type	= ARG_CONST_MAP_PTR,
	.arg3_type	= ARG_ANYTHING,
};

2106 2107 2108 2109
/* Stub for JITs that only support cBPF. eBPF programs are interpreted.
 * It is encouraged to implement bpf_int_jit_compile() instead, so that
 * eBPF and implicitly also cBPF can get JITed!
 */
2110
struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
Daniel Borkmann's avatar
Daniel Borkmann committed
2111
{
2112
	return prog;
Daniel Borkmann's avatar
Daniel Borkmann committed
2113 2114
}

2115 2116 2117 2118 2119 2120 2121
/* Stub for JITs that support eBPF. All cBPF code gets transformed into
 * eBPF by the kernel and is later compiled by bpf_int_jit_compile().
 */
void __weak bpf_jit_compile(struct bpf_prog *prog)
{
}

2122
bool __weak bpf_helper_changes_pkt_data(void *func)
2123 2124 2125 2126
{
	return false;
}

2127 2128 2129 2130 2131 2132 2133 2134 2135
/* Return TRUE if the JIT backend wants verifier to enable sub-register usage
 * analysis code and wants explicit zero extension inserted by verifier.
 * Otherwise, return FALSE.
 */
bool __weak bpf_jit_needs_zext(void)
{
	return false;
}

2136 2137 2138 2139 2140 2141 2142 2143
/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
 * skb_copy_bits(), so provide a weak definition of it for NET-less config.
 */
int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
			 int len)
{
	return -EFAULT;
}
2144

2145 2146 2147
DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
EXPORT_SYMBOL(bpf_stats_enabled_key);

2148 2149 2150 2151 2152
/* All definitions of tracepoints related to BPF. */
#define CREATE_TRACE_POINTS
#include <linux/bpf_trace.h>

EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
2153
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);