iov_iter.c 40.9 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2
#include <linux/export.h>
3
#include <linux/bvec.h>
4 5
#include <linux/uio.h>
#include <linux/pagemap.h>
6 7
#include <linux/slab.h>
#include <linux/vmalloc.h>
8
#include <linux/splice.h>
A
Al Viro 已提交
9
#include <net/checksum.h>
10
#include <linux/scatterlist.h>
11

12 13
#define PIPE_PARANOIA /* for now */

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
#define iterate_iovec(i, n, __v, __p, skip, STEP) {	\
	size_t left;					\
	size_t wanted = n;				\
	__p = i->iov;					\
	__v.iov_len = min(n, __p->iov_len - skip);	\
	if (likely(__v.iov_len)) {			\
		__v.iov_base = __p->iov_base + skip;	\
		left = (STEP);				\
		__v.iov_len -= left;			\
		skip += __v.iov_len;			\
		n -= __v.iov_len;			\
	} else {					\
		left = 0;				\
	}						\
	while (unlikely(!left && n)) {			\
		__p++;					\
		__v.iov_len = min(n, __p->iov_len);	\
		if (unlikely(!__v.iov_len))		\
			continue;			\
		__v.iov_base = __p->iov_base;		\
		left = (STEP);				\
		__v.iov_len -= left;			\
		skip = __v.iov_len;			\
		n -= __v.iov_len;			\
	}						\
	n = wanted - n;					\
}

42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64
#define iterate_kvec(i, n, __v, __p, skip, STEP) {	\
	size_t wanted = n;				\
	__p = i->kvec;					\
	__v.iov_len = min(n, __p->iov_len - skip);	\
	if (likely(__v.iov_len)) {			\
		__v.iov_base = __p->iov_base + skip;	\
		(void)(STEP);				\
		skip += __v.iov_len;			\
		n -= __v.iov_len;			\
	}						\
	while (unlikely(n)) {				\
		__p++;					\
		__v.iov_len = min(n, __p->iov_len);	\
		if (unlikely(!__v.iov_len))		\
			continue;			\
		__v.iov_base = __p->iov_base;		\
		(void)(STEP);				\
		skip = __v.iov_len;			\
		n -= __v.iov_len;			\
	}						\
	n = wanted;					\
}

65 66 67 68 69 70 71
#define iterate_bvec(i, n, __v, __bi, skip, STEP) {	\
	struct bvec_iter __start;			\
	__start.bi_size = n;				\
	__start.bi_bvec_done = skip;			\
	__start.bi_idx = 0;				\
	for_each_bvec(__v, i->bvec, __bi, __start) {	\
		if (!__v.bv_len)			\
72 73 74 75 76
			continue;			\
		(void)(STEP);				\
	}						\
}

77
#define iterate_all_kinds(i, n, v, I, B, K) {			\
78 79 80 81 82 83 84 85 86 87
	if (likely(n)) {					\
		size_t skip = i->iov_offset;			\
		if (unlikely(i->type & ITER_BVEC)) {		\
			struct bio_vec v;			\
			struct bvec_iter __bi;			\
			iterate_bvec(i, n, v, __bi, skip, (B))	\
		} else if (unlikely(i->type & ITER_KVEC)) {	\
			const struct kvec *kvec;		\
			struct kvec v;				\
			iterate_kvec(i, n, v, kvec, skip, (K))	\
88
		} else if (unlikely(i->type & ITER_DISCARD)) {	\
89 90 91 92 93
		} else {					\
			const struct iovec *iov;		\
			struct iovec v;				\
			iterate_iovec(i, n, v, iov, skip, (I))	\
		}						\
94 95 96
	}							\
}

97
#define iterate_and_advance(i, n, v, I, B, K) {			\
98 99
	if (unlikely(i->count < n))				\
		n = i->count;					\
100
	if (i->count) {						\
101 102
		size_t skip = i->iov_offset;			\
		if (unlikely(i->type & ITER_BVEC)) {		\
103
			const struct bio_vec *bvec = i->bvec;	\
104
			struct bio_vec v;			\
105 106 107 108 109
			struct bvec_iter __bi;			\
			iterate_bvec(i, n, v, __bi, skip, (B))	\
			i->bvec = __bvec_iter_bvec(i->bvec, __bi);	\
			i->nr_segs -= i->bvec - bvec;		\
			skip = __bi.bi_bvec_done;		\
110 111 112 113 114 115 116 117 118 119
		} else if (unlikely(i->type & ITER_KVEC)) {	\
			const struct kvec *kvec;		\
			struct kvec v;				\
			iterate_kvec(i, n, v, kvec, skip, (K))	\
			if (skip == kvec->iov_len) {		\
				kvec++;				\
				skip = 0;			\
			}					\
			i->nr_segs -= kvec - i->kvec;		\
			i->kvec = kvec;				\
120 121
		} else if (unlikely(i->type & ITER_DISCARD)) {	\
			skip += n;				\
122 123 124 125 126 127 128 129 130 131
		} else {					\
			const struct iovec *iov;		\
			struct iovec v;				\
			iterate_iovec(i, n, v, iov, skip, (I))	\
			if (skip == iov->iov_len) {		\
				iov++;				\
				skip = 0;			\
			}					\
			i->nr_segs -= iov - i->iov;		\
			i->iov = iov;				\
A
Al Viro 已提交
132
		}						\
133 134
		i->count -= n;					\
		i->iov_offset = skip;				\
A
Al Viro 已提交
135 136 137
	}							\
}

138 139
static int copyout(void __user *to, const void *from, size_t n)
{
140
	if (access_ok(to, n)) {
141 142 143 144 145 146 147 148
		kasan_check_read(from, n);
		n = raw_copy_to_user(to, from, n);
	}
	return n;
}

static int copyin(void *to, const void __user *from, size_t n)
{
149
	if (access_ok(from, n)) {
150 151 152 153 154 155
		kasan_check_write(to, n);
		n = raw_copy_from_user(to, from, n);
	}
	return n;
}

A
Al Viro 已提交
156
static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
157 158 159 160 161 162 163 164 165 166 167 168 169
			 struct iov_iter *i)
{
	size_t skip, copy, left, wanted;
	const struct iovec *iov;
	char __user *buf;
	void *kaddr, *from;

	if (unlikely(bytes > i->count))
		bytes = i->count;

	if (unlikely(!bytes))
		return 0;

170
	might_fault();
171 172 173 174 175 176
	wanted = bytes;
	iov = i->iov;
	skip = i->iov_offset;
	buf = iov->iov_base + skip;
	copy = min(bytes, iov->iov_len - skip);

177
	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) {
178 179 180 181
		kaddr = kmap_atomic(page);
		from = kaddr + offset;

		/* first chunk, usually the only one */
182
		left = copyout(buf, from, copy);
183 184 185 186 187 188 189 190 191
		copy -= left;
		skip += copy;
		from += copy;
		bytes -= copy;

		while (unlikely(!left && bytes)) {
			iov++;
			buf = iov->iov_base;
			copy = min(bytes, iov->iov_len);
192
			left = copyout(buf, from, copy);
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
			copy -= left;
			skip = copy;
			from += copy;
			bytes -= copy;
		}
		if (likely(!bytes)) {
			kunmap_atomic(kaddr);
			goto done;
		}
		offset = from - kaddr;
		buf += copy;
		kunmap_atomic(kaddr);
		copy = min(bytes, iov->iov_len - skip);
	}
	/* Too bad - revert to non-atomic kmap */
208

209 210
	kaddr = kmap(page);
	from = kaddr + offset;
211
	left = copyout(buf, from, copy);
212 213 214 215 216 217 218 219
	copy -= left;
	skip += copy;
	from += copy;
	bytes -= copy;
	while (unlikely(!left && bytes)) {
		iov++;
		buf = iov->iov_base;
		copy = min(bytes, iov->iov_len);
220
		left = copyout(buf, from, copy);
221 222 223 224 225 226
		copy -= left;
		skip = copy;
		from += copy;
		bytes -= copy;
	}
	kunmap(page);
227

228
done:
229 230 231 232
	if (skip == iov->iov_len) {
		iov++;
		skip = 0;
	}
233 234 235 236 237 238 239
	i->count -= wanted - bytes;
	i->nr_segs -= iov - i->iov;
	i->iov = iov;
	i->iov_offset = skip;
	return wanted - bytes;
}

A
Al Viro 已提交
240
static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes,
241 242 243 244 245 246 247 248 249 250 251 252 253
			 struct iov_iter *i)
{
	size_t skip, copy, left, wanted;
	const struct iovec *iov;
	char __user *buf;
	void *kaddr, *to;

	if (unlikely(bytes > i->count))
		bytes = i->count;

	if (unlikely(!bytes))
		return 0;

254
	might_fault();
255 256 257 258 259 260
	wanted = bytes;
	iov = i->iov;
	skip = i->iov_offset;
	buf = iov->iov_base + skip;
	copy = min(bytes, iov->iov_len - skip);

261
	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) {
262 263 264 265
		kaddr = kmap_atomic(page);
		to = kaddr + offset;

		/* first chunk, usually the only one */
266
		left = copyin(to, buf, copy);
267 268 269 270 271 272 273 274 275
		copy -= left;
		skip += copy;
		to += copy;
		bytes -= copy;

		while (unlikely(!left && bytes)) {
			iov++;
			buf = iov->iov_base;
			copy = min(bytes, iov->iov_len);
276
			left = copyin(to, buf, copy);
277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
			copy -= left;
			skip = copy;
			to += copy;
			bytes -= copy;
		}
		if (likely(!bytes)) {
			kunmap_atomic(kaddr);
			goto done;
		}
		offset = to - kaddr;
		buf += copy;
		kunmap_atomic(kaddr);
		copy = min(bytes, iov->iov_len - skip);
	}
	/* Too bad - revert to non-atomic kmap */
292

293 294
	kaddr = kmap(page);
	to = kaddr + offset;
295
	left = copyin(to, buf, copy);
296 297 298 299 300 301 302 303
	copy -= left;
	skip += copy;
	to += copy;
	bytes -= copy;
	while (unlikely(!left && bytes)) {
		iov++;
		buf = iov->iov_base;
		copy = min(bytes, iov->iov_len);
304
		left = copyin(to, buf, copy);
305 306 307 308 309 310
		copy -= left;
		skip = copy;
		to += copy;
		bytes -= copy;
	}
	kunmap(page);
311

312
done:
313 314 315 316
	if (skip == iov->iov_len) {
		iov++;
		skip = 0;
	}
317 318 319 320 321 322 323
	i->count -= wanted - bytes;
	i->nr_segs -= iov - i->iov;
	i->iov = iov;
	i->iov_offset = skip;
	return wanted - bytes;
}

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
#ifdef PIPE_PARANOIA
static bool sanity(const struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	int idx = i->idx;
	int next = pipe->curbuf + pipe->nrbufs;
	if (i->iov_offset) {
		struct pipe_buffer *p;
		if (unlikely(!pipe->nrbufs))
			goto Bad;	// pipe must be non-empty
		if (unlikely(idx != ((next - 1) & (pipe->buffers - 1))))
			goto Bad;	// must be at the last buffer...

		p = &pipe->bufs[idx];
		if (unlikely(p->offset + p->len != i->iov_offset))
			goto Bad;	// ... at the end of segment
	} else {
		if (idx != (next & (pipe->buffers - 1)))
			goto Bad;	// must be right after the last buffer
	}
	return true;
Bad:
	printk(KERN_ERR "idx = %d, offset = %zd\n", i->idx, i->iov_offset);
	printk(KERN_ERR "curbuf = %d, nrbufs = %d, buffers = %d\n",
			pipe->curbuf, pipe->nrbufs, pipe->buffers);
	for (idx = 0; idx < pipe->buffers; idx++)
		printk(KERN_ERR "[%p %p %d %d]\n",
			pipe->bufs[idx].ops,
			pipe->bufs[idx].page,
			pipe->bufs[idx].offset,
			pipe->bufs[idx].len);
	WARN_ON(1);
	return false;
}
#else
#define sanity(i) true
#endif

static inline int next_idx(int idx, struct pipe_inode_info *pipe)
{
	return (idx + 1) & (pipe->buffers - 1);
}

static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
			 struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	struct pipe_buffer *buf;
	size_t off;
	int idx;

	if (unlikely(bytes > i->count))
		bytes = i->count;

	if (unlikely(!bytes))
		return 0;

	if (!sanity(i))
		return 0;

	off = i->iov_offset;
	idx = i->idx;
	buf = &pipe->bufs[idx];
	if (off) {
		if (offset == off && buf->page == page) {
			/* merge with the last one */
			buf->len += bytes;
			i->iov_offset += bytes;
			goto out;
		}
		idx = next_idx(idx, pipe);
		buf = &pipe->bufs[idx];
	}
	if (idx == pipe->curbuf && pipe->nrbufs)
		return 0;
	pipe->nrbufs++;
	buf->ops = &page_cache_pipe_buf_ops;
	get_page(buf->page = page);
	buf->offset = offset;
	buf->len = bytes;
	i->iov_offset = offset + bytes;
	i->idx = idx;
out:
	i->count -= bytes;
	return bytes;
}

411 412 413 414 415 416 417
/*
 * Fault in one or more iovecs of the given iov_iter, to a maximum length of
 * bytes.  For each iovec, fault in each page that constitutes the iovec.
 *
 * Return 0 on success, or non-zero if the memory could not be accessed (i.e.
 * because it is an invalid address).
 */
418
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
419 420 421 422 423 424 425 426
{
	size_t skip = i->iov_offset;
	const struct iovec *iov;
	int err;
	struct iovec v;

	if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
		iterate_iovec(i, bytes, v, iov, skip, ({
427
			err = fault_in_pages_readable(v.iov_base, v.iov_len);
428 429 430 431 432 433
			if (unlikely(err))
			return err;
		0;}))
	}
	return 0;
}
434
EXPORT_SYMBOL(iov_iter_fault_in_readable);
435

436
void iov_iter_init(struct iov_iter *i, unsigned int direction,
437 438 439
			const struct iovec *iov, unsigned long nr_segs,
			size_t count)
{
440 441 442
	WARN_ON(direction & ~(READ | WRITE));
	direction &= READ | WRITE;

443
	/* It will get better.  Eventually... */
A
Al Viro 已提交
444
	if (uaccess_kernel()) {
445
		i->type = ITER_KVEC | direction;
446 447
		i->kvec = (struct kvec *)iov;
	} else {
448
		i->type = ITER_IOVEC | direction;
449 450
		i->iov = iov;
	}
451 452 453 454 455
	i->nr_segs = nr_segs;
	i->iov_offset = 0;
	i->count = count;
}
EXPORT_SYMBOL(iov_iter_init);
456

A
Al Viro 已提交
457 458 459 460 461 462 463
static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len)
{
	char *from = kmap_atomic(page);
	memcpy(to, from + offset, len);
	kunmap_atomic(from);
}

464
static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
A
Al Viro 已提交
465 466 467 468 469 470
{
	char *to = kmap_atomic(page);
	memcpy(to + offset, from, len);
	kunmap_atomic(to);
}

471 472 473 474 475 476 477
static void memzero_page(struct page *page, size_t offset, size_t len)
{
	char *addr = kmap_atomic(page);
	memset(addr + offset, 0, len);
	kunmap_atomic(addr);
}

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
static inline bool allocated(struct pipe_buffer *buf)
{
	return buf->ops == &default_pipe_buf_ops;
}

static inline void data_start(const struct iov_iter *i, int *idxp, size_t *offp)
{
	size_t off = i->iov_offset;
	int idx = i->idx;
	if (off && (!allocated(&i->pipe->bufs[idx]) || off == PAGE_SIZE)) {
		idx = next_idx(idx, i->pipe);
		off = 0;
	}
	*idxp = idx;
	*offp = off;
}

static size_t push_pipe(struct iov_iter *i, size_t size,
			int *idxp, size_t *offp)
{
	struct pipe_inode_info *pipe = i->pipe;
	size_t off;
	int idx;
	ssize_t left;

	if (unlikely(size > i->count))
		size = i->count;
	if (unlikely(!size))
		return 0;

	left = size;
	data_start(i, &idx, &off);
	*idxp = idx;
	*offp = off;
	if (off) {
		left -= PAGE_SIZE - off;
		if (left <= 0) {
			pipe->bufs[idx].len += size;
			return size;
		}
		pipe->bufs[idx].len = PAGE_SIZE;
		idx = next_idx(idx, pipe);
	}
	while (idx != pipe->curbuf || !pipe->nrbufs) {
		struct page *page = alloc_page(GFP_USER);
		if (!page)
			break;
		pipe->nrbufs++;
		pipe->bufs[idx].ops = &default_pipe_buf_ops;
		pipe->bufs[idx].page = page;
		pipe->bufs[idx].offset = 0;
		if (left <= PAGE_SIZE) {
			pipe->bufs[idx].len = left;
			return size;
		}
		pipe->bufs[idx].len = PAGE_SIZE;
		left -= PAGE_SIZE;
		idx = next_idx(idx, pipe);
	}
	return size - left;
}

static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
				struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	size_t n, off;
	int idx;

	if (!sanity(i))
		return 0;

	bytes = n = push_pipe(i, bytes, &idx, &off);
	if (unlikely(!n))
		return 0;
	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
		memcpy_to_page(pipe->bufs[idx].page, off, addr, chunk);
		i->idx = idx;
		i->iov_offset = off + chunk;
		n -= chunk;
		addr += chunk;
	}
	i->count -= bytes;
	return bytes;
}

565 566 567 568 569 570 571
static __wsum csum_and_memcpy(void *to, const void *from, size_t len,
			      __wsum sum, size_t off)
{
	__wsum next = csum_partial_copy_nocheck(from, to, len, 0);
	return csum_block_add(sum, next, off);
}

572 573 574 575 576 577
static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
				__wsum *csum, struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	size_t n, r;
	size_t off = 0;
578
	__wsum sum = *csum;
579 580 581 582 583 584 585 586 587 588 589
	int idx;

	if (!sanity(i))
		return 0;

	bytes = n = push_pipe(i, bytes, &idx, &r);
	if (unlikely(!n))
		return 0;
	for ( ; n; idx = next_idx(idx, pipe), r = 0) {
		size_t chunk = min_t(size_t, n, PAGE_SIZE - r);
		char *p = kmap_atomic(pipe->bufs[idx].page);
590
		sum = csum_and_memcpy(p + r, addr, chunk, sum, off);
591 592 593 594 595 596 597 598 599 600 601 602
		kunmap_atomic(p);
		i->idx = idx;
		i->iov_offset = r + chunk;
		n -= chunk;
		off += chunk;
		addr += chunk;
	}
	i->count -= bytes;
	*csum = sum;
	return bytes;
}

603
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
A
Al Viro 已提交
604
{
605
	const char *from = addr;
606
	if (unlikely(iov_iter_is_pipe(i)))
607
		return copy_pipe_to_iter(addr, bytes, i);
608 609
	if (iter_is_iovec(i))
		might_fault();
610
	iterate_and_advance(i, bytes, v,
611
		copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
612
		memcpy_to_page(v.bv_page, v.bv_offset,
613 614
			       (from += v.bv_len) - v.bv_len, v.bv_len),
		memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len)
615
	)
A
Al Viro 已提交
616

617
	return bytes;
618
}
619
EXPORT_SYMBOL(_copy_to_iter);
620

621 622 623
#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
static int copyout_mcsafe(void __user *to, const void *from, size_t n)
{
624
	if (access_ok(to, n)) {
625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643
		kasan_check_read(from, n);
		n = copy_to_user_mcsafe((__force void *) to, from, n);
	}
	return n;
}

static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
		const char *from, size_t len)
{
	unsigned long ret;
	char *to;

	to = kmap_atomic(page);
	ret = memcpy_mcsafe(to + offset, from, len);
	kunmap_atomic(to);

	return ret;
}

644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
				struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	size_t n, off, xfer = 0;
	int idx;

	if (!sanity(i))
		return 0;

	bytes = n = push_pipe(i, bytes, &idx, &off);
	if (unlikely(!n))
		return 0;
	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
		unsigned long rem;

		rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
				chunk);
		i->idx = idx;
		i->iov_offset = off + chunk - rem;
		xfer += chunk - rem;
		if (rem)
			break;
		n -= chunk;
		addr += chunk;
	}
	i->count -= xfer;
	return xfer;
}

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
/**
 * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
 * @addr: source kernel address
 * @bytes: total transfer length
 * @iter: destination iterator
 *
 * The pmem driver arranges for filesystem-dax to use this facility via
 * dax_copy_to_iter() for protecting read/write to persistent memory.
 * Unless / until an architecture can guarantee identical performance
 * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
 * performance regression to switch more users to the mcsafe version.
 *
 * Otherwise, the main differences between this and typical _copy_to_iter().
 *
 * * Typical tail/residue handling after a fault retries the copy
 *   byte-by-byte until the fault happens again. Re-triggering machine
 *   checks is potentially fatal so the implementation uses source
 *   alignment and poison alignment assumptions to avoid re-triggering
 *   hardware exceptions.
 *
 * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
 *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
 *   a short copy.
 *
 * See MCSAFE_TEST for self-test.
 */
701 702 703 704 705
size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
{
	const char *from = addr;
	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;

706
	if (unlikely(iov_iter_is_pipe(i)))
707
		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736
	if (iter_is_iovec(i))
		might_fault();
	iterate_and_advance(i, bytes, v,
		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
		({
		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
                               (from += v.bv_len) - v.bv_len, v.bv_len);
		if (rem) {
			curr_addr = (unsigned long) from;
			bytes = curr_addr - s_addr - rem;
			return bytes;
		}
		}),
		({
		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
				v.iov_len);
		if (rem) {
			curr_addr = (unsigned long) from;
			bytes = curr_addr - s_addr - rem;
			return bytes;
		}
		})
	)

	return bytes;
}
EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */

737
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
738
{
739
	char *to = addr;
740
	if (unlikely(iov_iter_is_pipe(i))) {
741 742 743
		WARN_ON(1);
		return 0;
	}
744 745
	if (iter_is_iovec(i))
		might_fault();
746
	iterate_and_advance(i, bytes, v,
747
		copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len),
748
		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
749 750
				 v.bv_offset, v.bv_len),
		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
751 752 753
	)

	return bytes;
754
}
755
EXPORT_SYMBOL(_copy_from_iter);
756

757
bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
758 759
{
	char *to = addr;
760
	if (unlikely(iov_iter_is_pipe(i))) {
761 762 763
		WARN_ON(1);
		return false;
	}
764
	if (unlikely(i->count < bytes))
765 766
		return false;

767 768
	if (iter_is_iovec(i))
		might_fault();
769
	iterate_all_kinds(i, bytes, v, ({
770
		if (copyin((to += v.iov_len) - v.iov_len,
771 772 773 774 775 776 777 778 779 780 781
				      v.iov_base, v.iov_len))
			return false;
		0;}),
		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
				 v.bv_offset, v.bv_len),
		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
	)

	iov_iter_advance(i, bytes);
	return true;
}
782
EXPORT_SYMBOL(_copy_from_iter_full);
783

784
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
A
Al Viro 已提交
785 786
{
	char *to = addr;
787
	if (unlikely(iov_iter_is_pipe(i))) {
788 789 790
		WARN_ON(1);
		return 0;
	}
A
Al Viro 已提交
791
	iterate_and_advance(i, bytes, v,
792
		__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
A
Al Viro 已提交
793 794 795 796 797 798 799 800
					 v.iov_base, v.iov_len),
		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
				 v.bv_offset, v.bv_len),
		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
	)

	return bytes;
}
801
EXPORT_SYMBOL(_copy_from_iter_nocache);
A
Al Viro 已提交
802

803
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
804 805 806 807 808 809 810 811 812 813 814 815 816 817
/**
 * _copy_from_iter_flushcache - write destination through cpu cache
 * @addr: destination kernel address
 * @bytes: total transfer length
 * @iter: source iterator
 *
 * The pmem driver arranges for filesystem-dax to use this facility via
 * dax_copy_from_iter() for ensuring that writes to persistent memory
 * are flushed through the CPU cache. It is differentiated from
 * _copy_from_iter_nocache() in that guarantees all data is flushed for
 * all iterator types. The _copy_from_iter_nocache() only attempts to
 * bypass the cache for the ITER_IOVEC case, and on some archs may use
 * instructions that strand dirty-data in the cache.
 */
818
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
819 820
{
	char *to = addr;
821
	if (unlikely(iov_iter_is_pipe(i))) {
822 823 824 825 826 827 828 829 830 831 832 833 834 835
		WARN_ON(1);
		return 0;
	}
	iterate_and_advance(i, bytes, v,
		__copy_from_user_flushcache((to += v.iov_len) - v.iov_len,
					 v.iov_base, v.iov_len),
		memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page,
				 v.bv_offset, v.bv_len),
		memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base,
			v.iov_len)
	)

	return bytes;
}
836
EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache);
837 838
#endif

839
bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
840 841
{
	char *to = addr;
842
	if (unlikely(iov_iter_is_pipe(i))) {
843 844 845
		WARN_ON(1);
		return false;
	}
846
	if (unlikely(i->count < bytes))
847 848
		return false;
	iterate_all_kinds(i, bytes, v, ({
849
		if (__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
850 851 852 853 854 855 856 857 858 859 860
					     v.iov_base, v.iov_len))
			return false;
		0;}),
		memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
				 v.bv_offset, v.bv_len),
		memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
	)

	iov_iter_advance(i, bytes);
	return true;
}
861
EXPORT_SYMBOL(_copy_from_iter_full_nocache);
862

863 864
static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
{
865 866 867 868 869 870 871 872 873 874 875 876 877 878 879
	struct page *head;
	size_t v = n + offset;

	/*
	 * The general case needs to access the page order in order
	 * to compute the page size.
	 * However, we mostly deal with order-0 pages and thus can
	 * avoid a possible cache line miss for requests that fit all
	 * page orders.
	 */
	if (n <= v && v <= PAGE_SIZE)
		return true;

	head = compound_head(page);
	v += (page - head) << PAGE_SHIFT;
880 881

	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
882 883 884 885
		return true;
	WARN_ON(1);
	return false;
}
886

A
Al Viro 已提交
887 888 889
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
			 struct iov_iter *i)
{
890 891
	if (unlikely(!page_copy_sane(page, offset, bytes)))
		return 0;
892 893 894 895 896
	if (i->type & (ITER_BVEC|ITER_KVEC)) {
		void *kaddr = kmap_atomic(page);
		size_t wanted = copy_to_iter(kaddr + offset, bytes, i);
		kunmap_atomic(kaddr);
		return wanted;
897 898 899
	} else if (unlikely(iov_iter_is_discard(i)))
		return bytes;
	else if (likely(!iov_iter_is_pipe(i)))
A
Al Viro 已提交
900
		return copy_page_to_iter_iovec(page, offset, bytes, i);
901 902
	else
		return copy_page_to_iter_pipe(page, offset, bytes, i);
A
Al Viro 已提交
903 904 905 906 907 908
}
EXPORT_SYMBOL(copy_page_to_iter);

size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
			 struct iov_iter *i)
{
909 910
	if (unlikely(!page_copy_sane(page, offset, bytes)))
		return 0;
911
	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
912 913 914
		WARN_ON(1);
		return 0;
	}
915
	if (i->type & (ITER_BVEC|ITER_KVEC)) {
916
		void *kaddr = kmap_atomic(page);
917
		size_t wanted = _copy_from_iter(kaddr + offset, bytes, i);
918 919 920
		kunmap_atomic(kaddr);
		return wanted;
	} else
A
Al Viro 已提交
921 922 923 924
		return copy_page_from_iter_iovec(page, offset, bytes, i);
}
EXPORT_SYMBOL(copy_page_from_iter);

925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
static size_t pipe_zero(size_t bytes, struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	size_t n, off;
	int idx;

	if (!sanity(i))
		return 0;

	bytes = n = push_pipe(i, bytes, &idx, &off);
	if (unlikely(!n))
		return 0;

	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
		memzero_page(pipe->bufs[idx].page, off, chunk);
		i->idx = idx;
		i->iov_offset = off + chunk;
		n -= chunk;
	}
	i->count -= bytes;
	return bytes;
}

949 950
size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
{
951
	if (unlikely(iov_iter_is_pipe(i)))
952
		return pipe_zero(bytes, i);
953
	iterate_and_advance(i, bytes, v,
954
		clear_user(v.iov_base, v.iov_len),
955 956
		memzero_page(v.bv_page, v.bv_offset, v.bv_len),
		memset(v.iov_base, 0, v.iov_len)
957 958 959
	)

	return bytes;
960 961 962
}
EXPORT_SYMBOL(iov_iter_zero);

A
Al Viro 已提交
963 964 965
size_t iov_iter_copy_from_user_atomic(struct page *page,
		struct iov_iter *i, unsigned long offset, size_t bytes)
{
966
	char *kaddr = kmap_atomic(page), *p = kaddr + offset;
967 968 969 970
	if (unlikely(!page_copy_sane(page, offset, bytes))) {
		kunmap_atomic(kaddr);
		return 0;
	}
971
	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
972 973 974 975
		kunmap_atomic(kaddr);
		WARN_ON(1);
		return 0;
	}
976
	iterate_all_kinds(i, bytes, v,
977
		copyin((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len),
978
		memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page,
979 980
				 v.bv_offset, v.bv_len),
		memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)
981 982 983
	)
	kunmap_atomic(kaddr);
	return bytes;
A
Al Viro 已提交
984 985 986
}
EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);

987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006
static inline void pipe_truncate(struct iov_iter *i)
{
	struct pipe_inode_info *pipe = i->pipe;
	if (pipe->nrbufs) {
		size_t off = i->iov_offset;
		int idx = i->idx;
		int nrbufs = (idx - pipe->curbuf) & (pipe->buffers - 1);
		if (off) {
			pipe->bufs[idx].len = off - pipe->bufs[idx].offset;
			idx = next_idx(idx, pipe);
			nrbufs++;
		}
		while (pipe->nrbufs > nrbufs) {
			pipe_buf_release(pipe, &pipe->bufs[idx]);
			idx = next_idx(idx, pipe);
			pipe->nrbufs--;
		}
	}
}

1007 1008 1009 1010 1011 1012
static void pipe_advance(struct iov_iter *i, size_t size)
{
	struct pipe_inode_info *pipe = i->pipe;
	if (unlikely(i->count < size))
		size = i->count;
	if (size) {
1013 1014 1015
		struct pipe_buffer *buf;
		size_t off = i->iov_offset, left = size;
		int idx = i->idx;
1016
		if (off) /* make it relative to the beginning of buffer */
1017
			left += off - pipe->bufs[idx].offset;
1018 1019
		while (1) {
			buf = &pipe->bufs[idx];
1020
			if (left <= buf->len)
1021
				break;
1022
			left -= buf->len;
1023 1024 1025
			idx = next_idx(idx, pipe);
		}
		i->idx = idx;
1026
		i->iov_offset = buf->offset + left;
1027
	}
1028 1029 1030
	i->count -= size;
	/* ... and discard everything past that point */
	pipe_truncate(i);
1031 1032
}

A
Al Viro 已提交
1033 1034
void iov_iter_advance(struct iov_iter *i, size_t size)
{
1035
	if (unlikely(iov_iter_is_pipe(i))) {
1036 1037 1038
		pipe_advance(i, size);
		return;
	}
1039 1040 1041 1042
	if (unlikely(iov_iter_is_discard(i))) {
		i->count -= size;
		return;
	}
1043
	iterate_and_advance(i, size, v, 0, 0, 0)
A
Al Viro 已提交
1044 1045 1046
}
EXPORT_SYMBOL(iov_iter_advance);

1047 1048 1049 1050
void iov_iter_revert(struct iov_iter *i, size_t unroll)
{
	if (!unroll)
		return;
1051 1052
	if (WARN_ON(unroll > MAX_RW_COUNT))
		return;
1053
	i->count += unroll;
1054
	if (unlikely(iov_iter_is_pipe(i))) {
1055 1056 1057 1058 1059 1060
		struct pipe_inode_info *pipe = i->pipe;
		int idx = i->idx;
		size_t off = i->iov_offset;
		while (1) {
			size_t n = off - pipe->bufs[idx].offset;
			if (unroll < n) {
1061
				off -= unroll;
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077
				break;
			}
			unroll -= n;
			if (!unroll && idx == i->start_idx) {
				off = 0;
				break;
			}
			if (!idx--)
				idx = pipe->buffers - 1;
			off = pipe->bufs[idx].offset + pipe->bufs[idx].len;
		}
		i->iov_offset = off;
		i->idx = idx;
		pipe_truncate(i);
		return;
	}
1078 1079
	if (unlikely(iov_iter_is_discard(i)))
		return;
1080 1081 1082 1083 1084
	if (unroll <= i->iov_offset) {
		i->iov_offset -= unroll;
		return;
	}
	unroll -= i->iov_offset;
1085
	if (iov_iter_is_bvec(i)) {
1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112
		const struct bio_vec *bvec = i->bvec;
		while (1) {
			size_t n = (--bvec)->bv_len;
			i->nr_segs++;
			if (unroll <= n) {
				i->bvec = bvec;
				i->iov_offset = n - unroll;
				return;
			}
			unroll -= n;
		}
	} else { /* same logics for iovec and kvec */
		const struct iovec *iov = i->iov;
		while (1) {
			size_t n = (--iov)->iov_len;
			i->nr_segs++;
			if (unroll <= n) {
				i->iov = iov;
				i->iov_offset = n - unroll;
				return;
			}
			unroll -= n;
		}
	}
}
EXPORT_SYMBOL(iov_iter_revert);

A
Al Viro 已提交
1113 1114 1115 1116 1117
/*
 * Return the count of just the current iov_iter segment.
 */
size_t iov_iter_single_seg_count(const struct iov_iter *i)
{
1118
	if (unlikely(iov_iter_is_pipe(i)))
1119
		return i->count;	// it is a silly place, anyway
A
Al Viro 已提交
1120 1121
	if (i->nr_segs == 1)
		return i->count;
1122 1123
	if (unlikely(iov_iter_is_discard(i)))
		return i->count;
1124
	else if (iov_iter_is_bvec(i))
A
Al Viro 已提交
1125
		return min(i->count, i->bvec->bv_len - i->iov_offset);
1126 1127
	else
		return min(i->count, i->iov->iov_len - i->iov_offset);
A
Al Viro 已提交
1128 1129 1130
}
EXPORT_SYMBOL(iov_iter_single_seg_count);

1131
void iov_iter_kvec(struct iov_iter *i, unsigned int direction,
A
Al Viro 已提交
1132
			const struct kvec *kvec, unsigned long nr_segs,
A
Al Viro 已提交
1133 1134
			size_t count)
{
1135 1136
	WARN_ON(direction & ~(READ | WRITE));
	i->type = ITER_KVEC | (direction & (READ | WRITE));
A
Al Viro 已提交
1137
	i->kvec = kvec;
A
Al Viro 已提交
1138 1139 1140 1141 1142 1143
	i->nr_segs = nr_segs;
	i->iov_offset = 0;
	i->count = count;
}
EXPORT_SYMBOL(iov_iter_kvec);

1144
void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
A
Al Viro 已提交
1145 1146 1147
			const struct bio_vec *bvec, unsigned long nr_segs,
			size_t count)
{
1148 1149
	WARN_ON(direction & ~(READ | WRITE));
	i->type = ITER_BVEC | (direction & (READ | WRITE));
A
Al Viro 已提交
1150 1151 1152 1153 1154 1155 1156
	i->bvec = bvec;
	i->nr_segs = nr_segs;
	i->iov_offset = 0;
	i->count = count;
}
EXPORT_SYMBOL(iov_iter_bvec);

1157
void iov_iter_pipe(struct iov_iter *i, unsigned int direction,
1158 1159 1160
			struct pipe_inode_info *pipe,
			size_t count)
{
1161
	BUG_ON(direction != READ);
1162
	WARN_ON(pipe->nrbufs == pipe->buffers);
1163
	i->type = ITER_PIPE | READ;
1164 1165 1166 1167
	i->pipe = pipe;
	i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
	i->iov_offset = 0;
	i->count = count;
1168
	i->start_idx = i->idx;
1169 1170 1171
}
EXPORT_SYMBOL(iov_iter_pipe);

1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
/**
 * iov_iter_discard - Initialise an I/O iterator that discards data
 * @i: The iterator to initialise.
 * @direction: The direction of the transfer.
 * @count: The size of the I/O buffer in bytes.
 *
 * Set up an I/O iterator that just discards everything that's written to it.
 * It's only available as a READ iterator.
 */
void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count)
{
	BUG_ON(direction != READ);
	i->type = ITER_DISCARD | READ;
	i->count = count;
	i->iov_offset = 0;
}
EXPORT_SYMBOL(iov_iter_discard);

A
Al Viro 已提交
1190 1191
unsigned long iov_iter_alignment(const struct iov_iter *i)
{
1192 1193 1194
	unsigned long res = 0;
	size_t size = i->count;

1195
	if (unlikely(iov_iter_is_pipe(i))) {
1196
		if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx]))
1197 1198 1199
			return size | i->iov_offset;
		return size;
	}
1200 1201
	iterate_all_kinds(i, size, v,
		(res |= (unsigned long)v.iov_base | v.iov_len, 0),
1202 1203
		res |= v.bv_offset | v.bv_len,
		res |= (unsigned long)v.iov_base | v.iov_len
1204 1205
	)
	return res;
A
Al Viro 已提交
1206 1207 1208
}
EXPORT_SYMBOL(iov_iter_alignment);

1209 1210
unsigned long iov_iter_gap_alignment(const struct iov_iter *i)
{
1211
	unsigned long res = 0;
1212 1213
	size_t size = i->count;

1214
	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
1215 1216 1217 1218
		WARN_ON(1);
		return ~0U;
	}

1219 1220 1221 1222 1223 1224 1225 1226
	iterate_all_kinds(i, size, v,
		(res |= (!res ? 0 : (unsigned long)v.iov_base) |
			(size != v.iov_len ? size : 0), 0),
		(res |= (!res ? 0 : (unsigned long)v.bv_offset) |
			(size != v.bv_len ? size : 0)),
		(res |= (!res ? 0 : (unsigned long)v.iov_base) |
			(size != v.iov_len ? size : 0))
		);
1227
	return res;
1228 1229 1230
}
EXPORT_SYMBOL(iov_iter_gap_alignment);

1231
static inline ssize_t __pipe_get_pages(struct iov_iter *i,
1232 1233 1234 1235 1236 1237
				size_t maxsize,
				struct page **pages,
				int idx,
				size_t *start)
{
	struct pipe_inode_info *pipe = i->pipe;
1238
	ssize_t n = push_pipe(i, maxsize, &idx, start);
1239 1240 1241 1242 1243
	if (!n)
		return -EFAULT;

	maxsize = n;
	n += *start;
1244
	while (n > 0) {
1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
		get_page(*pages++ = pipe->bufs[idx].page);
		idx = next_idx(idx, pipe);
		n -= PAGE_SIZE;
	}

	return maxsize;
}

static ssize_t pipe_get_pages(struct iov_iter *i,
		   struct page **pages, size_t maxsize, unsigned maxpages,
		   size_t *start)
{
	unsigned npages;
	size_t capacity;
	int idx;

1261 1262 1263
	if (!maxsize)
		return 0;

1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
	if (!sanity(i))
		return -EFAULT;

	data_start(i, &idx, start);
	/* some of this one + all after this one */
	npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1;
	capacity = min(npages,maxpages) * PAGE_SIZE - *start;

	return __pipe_get_pages(i, min(maxsize, capacity), pages, idx, start);
}

A
Al Viro 已提交
1275
ssize_t iov_iter_get_pages(struct iov_iter *i,
1276
		   struct page **pages, size_t maxsize, unsigned maxpages,
A
Al Viro 已提交
1277 1278
		   size_t *start)
{
1279 1280 1281
	if (maxsize > i->count)
		maxsize = i->count;

1282
	if (unlikely(iov_iter_is_pipe(i)))
1283
		return pipe_get_pages(i, pages, maxsize, maxpages, start);
1284 1285 1286
	if (unlikely(iov_iter_is_discard(i)))
		return -EFAULT;

1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
	iterate_all_kinds(i, maxsize, v, ({
		unsigned long addr = (unsigned long)v.iov_base;
		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
		int n;
		int res;

		if (len > maxpages * PAGE_SIZE)
			len = maxpages * PAGE_SIZE;
		addr &= ~(PAGE_SIZE - 1);
		n = DIV_ROUND_UP(len, PAGE_SIZE);
1297 1298 1299
		res = get_user_pages_fast(addr, n,
				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0,
				pages);
1300 1301 1302 1303 1304 1305 1306 1307
		if (unlikely(res < 0))
			return res;
		return (res == n ? len : res * PAGE_SIZE) - *start;
	0;}),({
		/* can't be more than PAGE_SIZE */
		*start = v.bv_offset;
		get_page(*pages = v.bv_page);
		return v.bv_len;
1308 1309
	}),({
		return -EFAULT;
1310 1311 1312
	})
	)
	return 0;
A
Al Viro 已提交
1313 1314 1315
}
EXPORT_SYMBOL(iov_iter_get_pages);

1316 1317
static struct page **get_pages_array(size_t n)
{
1318
	return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL);
1319 1320
}

1321 1322 1323 1324 1325
static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
		   struct page ***pages, size_t maxsize,
		   size_t *start)
{
	struct page **p;
1326
	ssize_t n;
1327 1328 1329
	int idx;
	int npages;

1330 1331 1332
	if (!maxsize)
		return 0;

1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354
	if (!sanity(i))
		return -EFAULT;

	data_start(i, &idx, start);
	/* some of this one + all after this one */
	npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1;
	n = npages * PAGE_SIZE - *start;
	if (maxsize > n)
		maxsize = n;
	else
		npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
	p = get_pages_array(npages);
	if (!p)
		return -ENOMEM;
	n = __pipe_get_pages(i, maxsize, p, idx, start);
	if (n > 0)
		*pages = p;
	else
		kvfree(p);
	return n;
}

A
Al Viro 已提交
1355 1356 1357 1358
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
		   struct page ***pages, size_t maxsize,
		   size_t *start)
{
1359 1360 1361 1362 1363
	struct page **p;

	if (maxsize > i->count)
		maxsize = i->count;

1364
	if (unlikely(iov_iter_is_pipe(i)))
1365
		return pipe_get_pages_alloc(i, pages, maxsize, start);
1366 1367 1368
	if (unlikely(iov_iter_is_discard(i)))
		return -EFAULT;

1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379
	iterate_all_kinds(i, maxsize, v, ({
		unsigned long addr = (unsigned long)v.iov_base;
		size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
		int n;
		int res;

		addr &= ~(PAGE_SIZE - 1);
		n = DIV_ROUND_UP(len, PAGE_SIZE);
		p = get_pages_array(n);
		if (!p)
			return -ENOMEM;
1380 1381
		res = get_user_pages_fast(addr, n,
				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0, p);
1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395
		if (unlikely(res < 0)) {
			kvfree(p);
			return res;
		}
		*pages = p;
		return (res == n ? len : res * PAGE_SIZE) - *start;
	0;}),({
		/* can't be more than PAGE_SIZE */
		*start = v.bv_offset;
		*pages = p = get_pages_array(1);
		if (!p)
			return -ENOMEM;
		get_page(*p = v.bv_page);
		return v.bv_len;
1396 1397
	}),({
		return -EFAULT;
1398 1399 1400
	})
	)
	return 0;
A
Al Viro 已提交
1401 1402 1403
}
EXPORT_SYMBOL(iov_iter_get_pages_alloc);

A
Al Viro 已提交
1404 1405 1406 1407 1408 1409 1410
size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
			       struct iov_iter *i)
{
	char *to = addr;
	__wsum sum, next;
	size_t off = 0;
	sum = *csum;
1411
	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
1412 1413 1414
		WARN_ON(1);
		return 0;
	}
A
Al Viro 已提交
1415 1416
	iterate_and_advance(i, bytes, v, ({
		int err = 0;
1417
		next = csum_and_copy_from_user(v.iov_base,
A
Al Viro 已提交
1418 1419 1420 1421 1422 1423 1424 1425 1426
					       (to += v.iov_len) - v.iov_len,
					       v.iov_len, 0, &err);
		if (!err) {
			sum = csum_block_add(sum, next, off);
			off += v.iov_len;
		}
		err ? v.iov_len : 0;
	}), ({
		char *p = kmap_atomic(v.bv_page);
1427 1428 1429
		sum = csum_and_memcpy((to += v.bv_len) - v.bv_len,
				      p + v.bv_offset, v.bv_len,
				      sum, off);
A
Al Viro 已提交
1430 1431 1432
		kunmap_atomic(p);
		off += v.bv_len;
	}),({
1433 1434 1435
		sum = csum_and_memcpy((to += v.iov_len) - v.iov_len,
				      v.iov_base, v.iov_len,
				      sum, off);
A
Al Viro 已提交
1436 1437 1438 1439 1440 1441 1442 1443
		off += v.iov_len;
	})
	)
	*csum = sum;
	return bytes;
}
EXPORT_SYMBOL(csum_and_copy_from_iter);

1444 1445 1446 1447 1448 1449 1450
bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum,
			       struct iov_iter *i)
{
	char *to = addr;
	__wsum sum, next;
	size_t off = 0;
	sum = *csum;
1451
	if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) {
1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
		WARN_ON(1);
		return false;
	}
	if (unlikely(i->count < bytes))
		return false;
	iterate_all_kinds(i, bytes, v, ({
		int err = 0;
		next = csum_and_copy_from_user(v.iov_base,
					       (to += v.iov_len) - v.iov_len,
					       v.iov_len, 0, &err);
		if (err)
			return false;
		sum = csum_block_add(sum, next, off);
		off += v.iov_len;
		0;
	}), ({
		char *p = kmap_atomic(v.bv_page);
1469 1470 1471
		sum = csum_and_memcpy((to += v.bv_len) - v.bv_len,
				      p + v.bv_offset, v.bv_len,
				      sum, off);
1472 1473 1474
		kunmap_atomic(p);
		off += v.bv_len;
	}),({
1475 1476 1477
		sum = csum_and_memcpy((to += v.iov_len) - v.iov_len,
				      v.iov_base, v.iov_len,
				      sum, off);
1478 1479 1480 1481 1482 1483 1484 1485 1486
		off += v.iov_len;
	})
	)
	*csum = sum;
	iov_iter_advance(i, bytes);
	return true;
}
EXPORT_SYMBOL(csum_and_copy_from_iter_full);

1487
size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
A
Al Viro 已提交
1488 1489
			     struct iov_iter *i)
{
1490
	const char *from = addr;
1491
	__wsum *csum = csump;
A
Al Viro 已提交
1492 1493
	__wsum sum, next;
	size_t off = 0;
1494 1495 1496 1497

	if (unlikely(iov_iter_is_pipe(i)))
		return csum_and_copy_to_pipe_iter(addr, bytes, csum, i);

A
Al Viro 已提交
1498
	sum = *csum;
1499
	if (unlikely(iov_iter_is_discard(i))) {
1500 1501 1502
		WARN_ON(1);	/* for now */
		return 0;
	}
A
Al Viro 已提交
1503 1504 1505
	iterate_and_advance(i, bytes, v, ({
		int err = 0;
		next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len,
1506
					     v.iov_base,
A
Al Viro 已提交
1507 1508 1509 1510 1511 1512 1513 1514
					     v.iov_len, 0, &err);
		if (!err) {
			sum = csum_block_add(sum, next, off);
			off += v.iov_len;
		}
		err ? v.iov_len : 0;
	}), ({
		char *p = kmap_atomic(v.bv_page);
1515 1516 1517
		sum = csum_and_memcpy(p + v.bv_offset,
				      (from += v.bv_len) - v.bv_len,
				      v.bv_len, sum, off);
A
Al Viro 已提交
1518 1519 1520
		kunmap_atomic(p);
		off += v.bv_len;
	}),({
1521 1522 1523
		sum = csum_and_memcpy(v.iov_base,
				     (from += v.iov_len) - v.iov_len,
				     v.iov_len, sum, off);
A
Al Viro 已提交
1524 1525 1526 1527 1528 1529 1530 1531
		off += v.iov_len;
	})
	)
	*csum = sum;
	return bytes;
}
EXPORT_SYMBOL(csum_and_copy_to_iter);

1532 1533 1534
size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
		struct iov_iter *i)
{
1535
#ifdef CONFIG_CRYPTO
1536 1537 1538 1539 1540 1541 1542 1543 1544
	struct ahash_request *hash = hashp;
	struct scatterlist sg;
	size_t copied;

	copied = copy_to_iter(addr, bytes, i);
	sg_init_one(&sg, addr, copied);
	ahash_request_set_crypt(hash, &sg, NULL, copied);
	crypto_ahash_update(hash);
	return copied;
1545 1546 1547
#else
	return 0;
#endif
1548 1549 1550
}
EXPORT_SYMBOL(hash_and_copy_to_iter);

A
Al Viro 已提交
1551 1552
int iov_iter_npages(const struct iov_iter *i, int maxpages)
{
1553 1554 1555 1556 1557
	size_t size = i->count;
	int npages = 0;

	if (!size)
		return 0;
1558 1559
	if (unlikely(iov_iter_is_discard(i)))
		return 0;
1560

1561
	if (unlikely(iov_iter_is_pipe(i))) {
1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574
		struct pipe_inode_info *pipe = i->pipe;
		size_t off;
		int idx;

		if (!sanity(i))
			return 0;

		data_start(i, &idx, &off);
		/* some of this one + all after this one */
		npages = ((pipe->curbuf - idx - 1) & (pipe->buffers - 1)) + 1;
		if (npages >= maxpages)
			return maxpages;
	} else iterate_all_kinds(i, size, v, ({
1575 1576 1577 1578 1579 1580 1581 1582 1583
		unsigned long p = (unsigned long)v.iov_base;
		npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE)
			- p / PAGE_SIZE;
		if (npages >= maxpages)
			return maxpages;
	0;}),({
		npages++;
		if (npages >= maxpages)
			return maxpages;
1584 1585 1586 1587 1588 1589
	}),({
		unsigned long p = (unsigned long)v.iov_base;
		npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE)
			- p / PAGE_SIZE;
		if (npages >= maxpages)
			return maxpages;
1590 1591 1592
	})
	)
	return npages;
A
Al Viro 已提交
1593
}
A
Al Viro 已提交
1594
EXPORT_SYMBOL(iov_iter_npages);
A
Al Viro 已提交
1595 1596 1597 1598

const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
{
	*new = *old;
1599
	if (unlikely(iov_iter_is_pipe(new))) {
1600 1601 1602
		WARN_ON(1);
		return NULL;
	}
1603 1604
	if (unlikely(iov_iter_is_discard(new)))
		return NULL;
1605
	if (iov_iter_is_bvec(new))
A
Al Viro 已提交
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615
		return new->bvec = kmemdup(new->bvec,
				    new->nr_segs * sizeof(struct bio_vec),
				    flags);
	else
		/* iovec and kvec have identical layout */
		return new->iov = kmemdup(new->iov,
				   new->nr_segs * sizeof(struct iovec),
				   flags);
}
EXPORT_SYMBOL(dup_iter);
1616

1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638
/**
 * import_iovec() - Copy an array of &struct iovec from userspace
 *     into the kernel, check that it is valid, and initialize a new
 *     &struct iov_iter iterator to access it.
 *
 * @type: One of %READ or %WRITE.
 * @uvector: Pointer to the userspace array.
 * @nr_segs: Number of elements in userspace array.
 * @fast_segs: Number of elements in @iov.
 * @iov: (input and output parameter) Pointer to pointer to (usually small
 *     on-stack) kernel array.
 * @i: Pointer to iterator that will be initialized on success.
 *
 * If the array pointed to by *@iov is large enough to hold all @nr_segs,
 * then this function places %NULL in *@iov on return. Otherwise, a new
 * array will be allocated and the result placed in *@iov. This means that
 * the caller may call kfree() on *@iov regardless of whether the small
 * on-stack array was used or not (and regardless of whether this function
 * returns an error or not).
 *
 * Return: 0 on success or negative error code on error.
 */
1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686
int import_iovec(int type, const struct iovec __user * uvector,
		 unsigned nr_segs, unsigned fast_segs,
		 struct iovec **iov, struct iov_iter *i)
{
	ssize_t n;
	struct iovec *p;
	n = rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
				  *iov, &p);
	if (n < 0) {
		if (p != *iov)
			kfree(p);
		*iov = NULL;
		return n;
	}
	iov_iter_init(i, type, p, nr_segs, n);
	*iov = p == *iov ? NULL : p;
	return 0;
}
EXPORT_SYMBOL(import_iovec);

#ifdef CONFIG_COMPAT
#include <linux/compat.h>

int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
		 unsigned nr_segs, unsigned fast_segs,
		 struct iovec **iov, struct iov_iter *i)
{
	ssize_t n;
	struct iovec *p;
	n = compat_rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
				  *iov, &p);
	if (n < 0) {
		if (p != *iov)
			kfree(p);
		*iov = NULL;
		return n;
	}
	iov_iter_init(i, type, p, nr_segs, n);
	*iov = p == *iov ? NULL : p;
	return 0;
}
#endif

int import_single_range(int rw, void __user *buf, size_t len,
		 struct iovec *iov, struct iov_iter *i)
{
	if (len > MAX_RW_COUNT)
		len = MAX_RW_COUNT;
1687
	if (unlikely(!access_ok(buf, len)))
1688 1689 1690 1691 1692 1693 1694
		return -EFAULT;

	iov->iov_base = buf;
	iov->iov_len = len;
	iov_iter_init(i, rw, iov, 1, len);
	return 0;
}
1695
EXPORT_SYMBOL(import_single_range);
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717

int iov_iter_for_each_range(struct iov_iter *i, size_t bytes,
			    int (*f)(struct kvec *vec, void *context),
			    void *context)
{
	struct kvec w;
	int err = -EINVAL;
	if (!bytes)
		return 0;

	iterate_all_kinds(i, bytes, v, -EINVAL, ({
		w.iov_base = kmap(v.bv_page) + v.bv_offset;
		w.iov_len = v.bv_len;
		err = f(&w, context);
		kunmap(v.bv_page);
		err;}), ({
		w = v;
		err = f(&w, context);})
	)
	return err;
}
EXPORT_SYMBOL(iov_iter_for_each_range);
新手
引导
客服 返回
顶部