gup.c 65.7 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2 3 4 5 6 7
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>

#include <linux/mm.h>
8
#include <linux/memremap.h>
9 10 11 12 13
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

14
#include <linux/sched/signal.h>
15
#include <linux/rwsem.h>
16
#include <linux/hugetlb.h>
17 18 19
#include <linux/migrate.h>
#include <linux/mm_inline.h>
#include <linux/sched/mm.h>
20

21
#include <asm/mmu_context.h>
22
#include <asm/pgtable.h>
23
#include <asm/tlbflush.h>
24

25 26
#include "internal.h"

27 28 29 30 31
struct follow_page_context {
	struct dev_pagemap *pgmap;
	unsigned int page_mask;
};

32
/**
33 34
 * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
 * @pages:  array of pages to be maybe marked dirty, and definitely released.
35
 * @npages: number of pages in the @pages array.
36
 * @make_dirty: whether to mark the pages dirty
37 38 39 40 41
 *
 * "gup-pinned page" refers to a page that has had one of the get_user_pages()
 * variants called on that page.
 *
 * For each page in the @pages array, make that page (or its head page, if a
42 43 44
 * compound page) dirty, if @make_dirty is true, and if the page was previously
 * listed as clean. In any case, releases all pages using put_user_page(),
 * possibly via put_user_pages(), for the non-dirty case.
45 46 47
 *
 * Please see the put_user_page() documentation for details.
 *
48 49 50 51
 * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
 * required, then the caller should a) verify that this is really correct,
 * because _lock() is usually required, and b) hand code it:
 * set_page_dirty_lock(), put_user_page().
52 53
 *
 */
54 55
void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
			       bool make_dirty)
56
{
57
	unsigned long index;
58

59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
	/*
	 * TODO: this can be optimized for huge pages: if a series of pages is
	 * physically contiguous and part of the same compound page, then a
	 * single operation to the head page should suffice.
	 */

	if (!make_dirty) {
		put_user_pages(pages, npages);
		return;
	}

	for (index = 0; index < npages; index++) {
		struct page *page = compound_head(pages[index]);
		/*
		 * Checking PageDirty at this point may race with
		 * clear_page_dirty_for_io(), but that's OK. Two key
		 * cases:
		 *
		 * 1) This code sees the page as already dirty, so it
		 * skips the call to set_page_dirty(). That could happen
		 * because clear_page_dirty_for_io() called
		 * page_mkclean(), followed by set_page_dirty().
		 * However, now the page is going to get written back,
		 * which meets the original intention of setting it
		 * dirty, so all is well: clear_page_dirty_for_io() goes
		 * on to call TestClearPageDirty(), and write the page
		 * back.
		 *
		 * 2) This code sees the page as clean, so it calls
		 * set_page_dirty(). The page stays dirty, despite being
		 * written back, so it gets written back again in the
		 * next writeback cycle. This is harmless.
		 */
		if (!PageDirty(page))
			set_page_dirty_lock(page);
		put_user_page(page);
	}
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121
}
EXPORT_SYMBOL(put_user_pages_dirty_lock);

/**
 * put_user_pages() - release an array of gup-pinned pages.
 * @pages:  array of pages to be marked dirty and released.
 * @npages: number of pages in the @pages array.
 *
 * For each page in the @pages array, release the page using put_user_page().
 *
 * Please see the put_user_page() documentation for details.
 */
void put_user_pages(struct page **pages, unsigned long npages)
{
	unsigned long index;

	/*
	 * TODO: this can be optimized for huge pages: if a series of pages is
	 * physically contiguous and part of the same compound page, then a
	 * single operation to the head page should suffice.
	 */
	for (index = 0; index < npages; index++)
		put_user_page(pages[index]);
}
EXPORT_SYMBOL(put_user_pages);

122
#ifdef CONFIG_MMU
123 124
static struct page *no_page_table(struct vm_area_struct *vma,
		unsigned int flags)
125
{
126 127 128 129 130 131 132 133 134 135 136 137
	/*
	 * When core dumping an enormous anonymous area that nobody
	 * has touched so far, we don't want to allocate unnecessary pages or
	 * page tables.  Return error instead of NULL to skip handle_mm_fault,
	 * then get_dump_page() will return NULL to leave a hole in the dump.
	 * But we can only make this optimization where a hole would surely
	 * be zero-filled if handle_mm_fault() actually did handle it.
	 */
	if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
		return ERR_PTR(-EFAULT);
	return NULL;
}
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
static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
		pte_t *pte, unsigned int flags)
{
	/* No page to get reference */
	if (flags & FOLL_GET)
		return -EFAULT;

	if (flags & FOLL_TOUCH) {
		pte_t entry = *pte;

		if (flags & FOLL_WRITE)
			entry = pte_mkdirty(entry);
		entry = pte_mkyoung(entry);

		if (!pte_same(*pte, entry)) {
			set_pte_at(vma->vm_mm, address, pte, entry);
			update_mmu_cache(vma, address, pte);
		}
	}

	/* Proper page table entry exists, but no corresponding struct page */
	return -EEXIST;
}

163 164 165 166 167 168
/*
 * FOLL_FORCE can write to even unwritable pte's, but only
 * after we've gone through a COW cycle and they are dirty.
 */
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
169
	return pte_write(pte) ||
170 171 172
		((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}

173
static struct page *follow_page_pte(struct vm_area_struct *vma,
174 175
		unsigned long address, pmd_t *pmd, unsigned int flags,
		struct dev_pagemap **pgmap)
176 177 178 179 180
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	spinlock_t *ptl;
	pte_t *ptep, pte;
181

182
retry:
183
	if (unlikely(pmd_bad(*pmd)))
184
		return no_page_table(vma, flags);
185 186 187 188 189 190 191 192 193 194 195 196

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!pte_present(pte)) {
		swp_entry_t entry;
		/*
		 * KSM's break_ksm() relies upon recognizing a ksm page
		 * even while it is being migrated, so for that case we
		 * need migration_entry_wait().
		 */
		if (likely(!(flags & FOLL_MIGRATION)))
			goto no_page;
197
		if (pte_none(pte))
198 199 200 201 202 203
			goto no_page;
		entry = pte_to_swp_entry(pte);
		if (!is_migration_entry(entry))
			goto no_page;
		pte_unmap_unlock(ptep, ptl);
		migration_entry_wait(mm, pmd, address);
204
		goto retry;
205
	}
206
	if ((flags & FOLL_NUMA) && pte_protnone(pte))
207
		goto no_page;
208
	if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
209 210 211
		pte_unmap_unlock(ptep, ptl);
		return NULL;
	}
212 213

	page = vm_normal_page(vma, address, pte);
214 215 216 217 218
	if (!page && pte_devmap(pte) && (flags & FOLL_GET)) {
		/*
		 * Only return device mapping pages in the FOLL_GET case since
		 * they are only valid while holding the pgmap reference.
		 */
219 220
		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
		if (*pgmap)
221 222 223 224
			page = pte_page(pte);
		else
			goto no_page;
	} else if (unlikely(!page)) {
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
		if (flags & FOLL_DUMP) {
			/* Avoid special (like zero) pages in core dumps */
			page = ERR_PTR(-EFAULT);
			goto out;
		}

		if (is_zero_pfn(pte_pfn(pte))) {
			page = pte_page(pte);
		} else {
			int ret;

			ret = follow_pfn_pte(vma, address, ptep, flags);
			page = ERR_PTR(ret);
			goto out;
		}
240 241
	}

242 243 244 245 246 247 248 249 250 251 252 253 254
	if (flags & FOLL_SPLIT && PageTransCompound(page)) {
		int ret;
		get_page(page);
		pte_unmap_unlock(ptep, ptl);
		lock_page(page);
		ret = split_huge_page(page);
		unlock_page(page);
		put_page(page);
		if (ret)
			return ERR_PTR(ret);
		goto retry;
	}

255 256 257 258 259 260
	if (flags & FOLL_GET) {
		if (unlikely(!try_get_page(page))) {
			page = ERR_PTR(-ENOMEM);
			goto out;
		}
	}
261 262 263 264 265 266 267 268 269 270 271
	if (flags & FOLL_TOUCH) {
		if ((flags & FOLL_WRITE) &&
		    !pte_dirty(pte) && !PageDirty(page))
			set_page_dirty(page);
		/*
		 * pte_mkyoung() would be more correct here, but atomic care
		 * is needed to avoid losing the dirty bit: it is easier to use
		 * mark_page_accessed().
		 */
		mark_page_accessed(page);
	}
E
Eric B Munson 已提交
272
	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
273 274 275 276
		/* Do not mlock pte-mapped THP */
		if (PageTransCompound(page))
			goto out;

277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
		/*
		 * The preliminary mapping check is mainly to avoid the
		 * pointless overhead of lock_page on the ZERO_PAGE
		 * which might bounce very badly if there is contention.
		 *
		 * If the page is already locked, we don't need to
		 * handle it now - vmscan will handle it later if and
		 * when it attempts to reclaim the page.
		 */
		if (page->mapping && trylock_page(page)) {
			lru_add_drain();  /* push cached pages to LRU */
			/*
			 * Because we lock page here, and migration is
			 * blocked by the pte's page reference, and we
			 * know the page is still mapped, we don't even
			 * need to check for file-cache page truncation.
			 */
			mlock_vma_page(page);
			unlock_page(page);
		}
	}
298
out:
299 300 301 302 303
	pte_unmap_unlock(ptep, ptl);
	return page;
no_page:
	pte_unmap_unlock(ptep, ptl);
	if (!pte_none(pte))
304 305 306 307
		return NULL;
	return no_page_table(vma, flags);
}

308 309
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
				    unsigned long address, pud_t *pudp,
310 311
				    unsigned int flags,
				    struct follow_page_context *ctx)
312
{
313
	pmd_t *pmd, pmdval;
314 315 316 317
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

318
	pmd = pmd_offset(pudp, address);
319 320 321 322 323 324
	/*
	 * The READ_ONCE() will stabilize the pmdval in a register or
	 * on the stack so that it will stop changing under the code.
	 */
	pmdval = READ_ONCE(*pmd);
	if (pmd_none(pmdval))
325
		return no_page_table(vma, flags);
326
	if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
327 328 329 330
		page = follow_huge_pmd(mm, address, pmd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
331
	}
332
	if (is_hugepd(__hugepd(pmd_val(pmdval)))) {
333
		page = follow_huge_pd(vma, address,
334
				      __hugepd(pmd_val(pmdval)), flags,
335 336 337 338 339
				      PMD_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
340
retry:
341
	if (!pmd_present(pmdval)) {
342 343 344
		if (likely(!(flags & FOLL_MIGRATION)))
			return no_page_table(vma, flags);
		VM_BUG_ON(thp_migration_supported() &&
345 346
				  !is_pmd_migration_entry(pmdval));
		if (is_pmd_migration_entry(pmdval))
347
			pmd_migration_entry_wait(mm, pmd);
348 349 350 351 352 353 354
		pmdval = READ_ONCE(*pmd);
		/*
		 * MADV_DONTNEED may convert the pmd to null because
		 * mmap_sem is held in read mode
		 */
		if (pmd_none(pmdval))
			return no_page_table(vma, flags);
355 356
		goto retry;
	}
357
	if (pmd_devmap(pmdval)) {
358
		ptl = pmd_lock(mm, pmd);
359
		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
360 361 362 363
		spin_unlock(ptl);
		if (page)
			return page;
	}
364
	if (likely(!pmd_trans_huge(pmdval)))
365
		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
366

367
	if ((flags & FOLL_NUMA) && pmd_protnone(pmdval))
368 369
		return no_page_table(vma, flags);

370
retry_locked:
371
	ptl = pmd_lock(mm, pmd);
372 373 374 375
	if (unlikely(pmd_none(*pmd))) {
		spin_unlock(ptl);
		return no_page_table(vma, flags);
	}
376 377 378 379 380 381 382
	if (unlikely(!pmd_present(*pmd))) {
		spin_unlock(ptl);
		if (likely(!(flags & FOLL_MIGRATION)))
			return no_page_table(vma, flags);
		pmd_migration_entry_wait(mm, pmd);
		goto retry_locked;
	}
383 384
	if (unlikely(!pmd_trans_huge(*pmd))) {
		spin_unlock(ptl);
385
		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
386
	}
S
Song Liu 已提交
387
	if (flags & (FOLL_SPLIT | FOLL_SPLIT_PMD)) {
388 389 390 391 392
		int ret;
		page = pmd_page(*pmd);
		if (is_huge_zero_page(page)) {
			spin_unlock(ptl);
			ret = 0;
393
			split_huge_pmd(vma, pmd, address);
394 395
			if (pmd_trans_unstable(pmd))
				ret = -EBUSY;
S
Song Liu 已提交
396
		} else if (flags & FOLL_SPLIT) {
397 398 399 400
			if (unlikely(!try_get_page(page))) {
				spin_unlock(ptl);
				return ERR_PTR(-ENOMEM);
			}
401
			spin_unlock(ptl);
402 403 404 405
			lock_page(page);
			ret = split_huge_page(page);
			unlock_page(page);
			put_page(page);
406 407
			if (pmd_none(*pmd))
				return no_page_table(vma, flags);
S
Song Liu 已提交
408 409 410 411
		} else {  /* flags & FOLL_SPLIT_PMD */
			spin_unlock(ptl);
			split_huge_pmd(vma, pmd, address);
			ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
412 413 414
		}

		return ret ? ERR_PTR(ret) :
415
			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
416
	}
417 418
	page = follow_trans_huge_pmd(vma, address, pmd, flags);
	spin_unlock(ptl);
419
	ctx->page_mask = HPAGE_PMD_NR - 1;
420
	return page;
421 422
}

423 424
static struct page *follow_pud_mask(struct vm_area_struct *vma,
				    unsigned long address, p4d_t *p4dp,
425 426
				    unsigned int flags,
				    struct follow_page_context *ctx)
427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
{
	pud_t *pud;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	pud = pud_offset(p4dp, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pud(mm, address, pud, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
442 443 444 445 446 447 448 449
	if (is_hugepd(__hugepd(pud_val(*pud)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(pud_val(*pud)), flags,
				      PUD_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
450 451
	if (pud_devmap(*pud)) {
		ptl = pud_lock(mm, pud);
452
		page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
453 454 455 456 457 458 459
		spin_unlock(ptl);
		if (page)
			return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

460
	return follow_pmd_mask(vma, address, pud, flags, ctx);
461 462 463 464
}

static struct page *follow_p4d_mask(struct vm_area_struct *vma,
				    unsigned long address, pgd_t *pgdp,
465 466
				    unsigned int flags,
				    struct follow_page_context *ctx)
467 468
{
	p4d_t *p4d;
469
	struct page *page;
470 471 472 473 474 475 476 477

	p4d = p4d_offset(pgdp, address);
	if (p4d_none(*p4d))
		return no_page_table(vma, flags);
	BUILD_BUG_ON(p4d_huge(*p4d));
	if (unlikely(p4d_bad(*p4d)))
		return no_page_table(vma, flags);

478 479 480 481 482 483 484 485
	if (is_hugepd(__hugepd(p4d_val(*p4d)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(p4d_val(*p4d)), flags,
				      P4D_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
486
	return follow_pud_mask(vma, address, p4d, flags, ctx);
487 488 489 490 491 492 493
}

/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
494 495
 * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
 *       pointer to output page_mask
496 497 498
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
499 500 501 502 503 504
 * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
 * the device's dev_pagemap metadata to avoid repeating expensive lookups.
 *
 * On output, the @ctx->page_mask is set according to the size of the page.
 *
 * Return: the mapped (struct page *), %NULL if no mapping exists, or
505 506 507
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
508
static struct page *follow_page_mask(struct vm_area_struct *vma,
509
			      unsigned long address, unsigned int flags,
510
			      struct follow_page_context *ctx)
511 512 513 514 515
{
	pgd_t *pgd;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

516
	ctx->page_mask = 0;
517 518 519 520 521 522 523 524 525 526 527 528 529

	/* make this handle hugepd */
	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
		return page;
	}

	pgd = pgd_offset(mm, address);

	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);

530 531 532 533 534 535
	if (pgd_huge(*pgd)) {
		page = follow_huge_pgd(mm, address, pgd, flags);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
536 537 538 539 540 541 542 543
	if (is_hugepd(__hugepd(pgd_val(*pgd)))) {
		page = follow_huge_pd(vma, address,
				      __hugepd(pgd_val(*pgd)), flags,
				      PGDIR_SHIFT);
		if (page)
			return page;
		return no_page_table(vma, flags);
	}
544

545 546 547 548 549 550 551 552 553 554 555 556 557
	return follow_p4d_mask(vma, address, pgd, flags, ctx);
}

struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
			 unsigned int foll_flags)
{
	struct follow_page_context ctx = { NULL };
	struct page *page;

	page = follow_page_mask(vma, address, foll_flags, &ctx);
	if (ctx.pgmap)
		put_dev_pagemap(ctx.pgmap);
	return page;
558 559
}

560 561 562 563 564
static int get_gate_page(struct mm_struct *mm, unsigned long address,
		unsigned int gup_flags, struct vm_area_struct **vma,
		struct page **page)
{
	pgd_t *pgd;
565
	p4d_t *p4d;
566 567 568 569 570 571 572 573 574 575 576 577
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int ret = -EFAULT;

	/* user gate pages are read-only */
	if (gup_flags & FOLL_WRITE)
		return -EFAULT;
	if (address > TASK_SIZE)
		pgd = pgd_offset_k(address);
	else
		pgd = pgd_offset_gate(mm, address);
578 579
	if (pgd_none(*pgd))
		return -EFAULT;
580
	p4d = p4d_offset(pgd, address);
581 582
	if (p4d_none(*p4d))
		return -EFAULT;
583
	pud = pud_offset(p4d, address);
584 585
	if (pud_none(*pud))
		return -EFAULT;
586
	pmd = pmd_offset(pud, address);
587
	if (!pmd_present(*pmd))
588 589 590 591 592 593 594 595 596 597 598 599 600 601
		return -EFAULT;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	pte = pte_offset_map(pmd, address);
	if (pte_none(*pte))
		goto unmap;
	*vma = get_gate_vma(mm);
	if (!page)
		goto out;
	*page = vm_normal_page(*vma, address, *pte);
	if (!*page) {
		if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
			goto unmap;
		*page = pte_page(*pte);
	}
602 603 604 605
	if (unlikely(!try_get_page(*page))) {
		ret = -ENOMEM;
		goto unmap;
	}
606 607 608 609 610 611 612
out:
	ret = 0;
unmap:
	pte_unmap(pte);
	return ret;
}

613 614 615 616 617
/*
 * mmap_sem must be held on entry.  If @nonblocking != NULL and
 * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
 * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
 */
618 619 620 621
static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
		unsigned long address, unsigned int *flags, int *nonblocking)
{
	unsigned int fault_flags = 0;
622
	vm_fault_t ret;
623

E
Eric B Munson 已提交
624 625 626
	/* mlock all present pages, but do not fault in new pages */
	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
		return -ENOENT;
627 628
	if (*flags & FOLL_WRITE)
		fault_flags |= FAULT_FLAG_WRITE;
629 630
	if (*flags & FOLL_REMOTE)
		fault_flags |= FAULT_FLAG_REMOTE;
631 632 633 634
	if (nonblocking)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
	if (*flags & FOLL_NOWAIT)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
635 636 637 638
	if (*flags & FOLL_TRIED) {
		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
		fault_flags |= FAULT_FLAG_TRIED;
	}
639

640
	ret = handle_mm_fault(vma, address, fault_flags);
641
	if (ret & VM_FAULT_ERROR) {
642 643 644 645
		int err = vm_fault_to_errno(ret, *flags);

		if (err)
			return err;
646 647 648 649 650 651 652 653 654 655 656
		BUG();
	}

	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}

	if (ret & VM_FAULT_RETRY) {
657
		if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
658 659 660 661 662 663 664 665 666 667 668 669 670 671
			*nonblocking = 0;
		return -EBUSY;
	}

	/*
	 * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
	 * necessary, even if maybe_mkwrite decided not to set pte_write. We
	 * can thus safely do subsequent page lookups as if they were reads.
	 * But only do so when looping for pte_write is futile: in some cases
	 * userspace may also be wanting to write to the gotten user page,
	 * which a read fault here might prevent (a readonly page might get
	 * reCOWed by userspace write).
	 */
	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
672
		*flags |= FOLL_COW;
673 674 675
	return 0;
}

676 677 678
static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
	vm_flags_t vm_flags = vma->vm_flags;
679 680
	int write = (gup_flags & FOLL_WRITE);
	int foreign = (gup_flags & FOLL_REMOTE);
681 682 683 684

	if (vm_flags & (VM_IO | VM_PFNMAP))
		return -EFAULT;

685 686 687
	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
		return -EFAULT;

688
	if (write) {
689 690 691 692 693 694 695 696 697 698 699 700
		if (!(vm_flags & VM_WRITE)) {
			if (!(gup_flags & FOLL_FORCE))
				return -EFAULT;
			/*
			 * We used to let the write,force case do COW in a
			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
			 * set a breakpoint in a read-only mapping of an
			 * executable, without corrupting the file (yet only
			 * when that file had been opened for writing!).
			 * Anon pages in shared mappings are surprising: now
			 * just reject it.
			 */
701
			if (!is_cow_mapping(vm_flags))
702 703 704 705 706 707 708 709 710 711 712 713
				return -EFAULT;
		}
	} else if (!(vm_flags & VM_READ)) {
		if (!(gup_flags & FOLL_FORCE))
			return -EFAULT;
		/*
		 * Is there actually any vma we can reach here which does not
		 * have VM_MAYREAD set?
		 */
		if (!(vm_flags & VM_MAYREAD))
			return -EFAULT;
	}
714 715 716 717 718
	/*
	 * gups are always data accesses, not instruction
	 * fetches, so execute=false here
	 */
	if (!arch_vma_access_permitted(vma, write, false, foreign))
719
		return -EFAULT;
720 721 722
	return 0;
}

723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
/**
 * __get_user_pages() - pin user pages in memory
 * @tsk:	task_struct of target task
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @gup_flags:	flags modifying pin behaviour
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 * @nonblocking: whether waiting for disk IO or mmap_sem contention
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
743
 * Must be called with mmap_sem held.  It may be released.  See below.
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765
 *
 * __get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * __get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
 * the page is written to, set_page_dirty (or set_page_dirty_lock, as
 * appropriate) must be called after the page is finished with, and
 * before put_page is called.
 *
 * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
 * or mmap_sem contention, and if waiting is needed to pin all pages,
766 767 768 769 770 771 772 773
 * *@nonblocking will be set to 0.  Further, if @gup_flags does not
 * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
 * this case.
 *
 * A caller using such a combination of @nonblocking and @gup_flags
 * must therefore hold the mmap_sem for reading only, and recognize
 * when it's been released.  Otherwise, it must be held for either
 * reading or writing and will not be released.
774 775 776 777 778
 *
 * In most cases, get_user_pages or get_user_pages_fast should be used
 * instead of __get_user_pages. __get_user_pages should be used only if
 * you need some special @gup_flags.
 */
L
Lorenzo Stoakes 已提交
779
static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
780 781 782 783
		unsigned long start, unsigned long nr_pages,
		unsigned int gup_flags, struct page **pages,
		struct vm_area_struct **vmas, int *nonblocking)
{
784
	long ret = 0, i = 0;
785
	struct vm_area_struct *vma = NULL;
786
	struct follow_page_context ctx = { NULL };
787 788 789 790

	if (!nr_pages)
		return 0;

791 792
	start = untagged_addr(start);

793 794 795 796 797 798 799 800 801 802 803
	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

	/*
	 * If FOLL_FORCE is set then do not force a full fault as the hinting
	 * fault information is unrelated to the reference behaviour of a task
	 * using the address space
	 */
	if (!(gup_flags & FOLL_FORCE))
		gup_flags |= FOLL_NUMA;

	do {
804 805 806 807 808 809 810 811 812 813 814 815
		struct page *page;
		unsigned int foll_flags = gup_flags;
		unsigned int page_increm;

		/* first iteration or cross vma bound */
		if (!vma || start >= vma->vm_end) {
			vma = find_extend_vma(mm, start);
			if (!vma && in_gate_area(mm, start)) {
				ret = get_gate_page(mm, start & PAGE_MASK,
						gup_flags, &vma,
						pages ? &pages[i] : NULL);
				if (ret)
816
					goto out;
817
				ctx.page_mask = 0;
818 819
				goto next_page;
			}
820

821 822 823 824
			if (!vma || check_vma_flags(vma, gup_flags)) {
				ret = -EFAULT;
				goto out;
			}
825 826 827
			if (is_vm_hugetlb_page(vma)) {
				i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &nr_pages, i,
828
						gup_flags, nonblocking);
829
				continue;
830
			}
831 832 833 834 835 836
		}
retry:
		/*
		 * If we have a pending SIGKILL, don't keep faulting pages and
		 * potentially allocating memory.
		 */
837
		if (fatal_signal_pending(current)) {
838 839 840
			ret = -ERESTARTSYS;
			goto out;
		}
841
		cond_resched();
842 843

		page = follow_page_mask(vma, start, foll_flags, &ctx);
844 845 846 847 848 849
		if (!page) {
			ret = faultin_page(tsk, vma, start, &foll_flags,
					nonblocking);
			switch (ret) {
			case 0:
				goto retry;
850 851 852
			case -EBUSY:
				ret = 0;
				/* FALLTHRU */
853 854 855
			case -EFAULT:
			case -ENOMEM:
			case -EHWPOISON:
856
				goto out;
857 858
			case -ENOENT:
				goto next_page;
859
			}
860
			BUG();
861 862 863 864 865 866 867
		} else if (PTR_ERR(page) == -EEXIST) {
			/*
			 * Proper page table entry exists, but no corresponding
			 * struct page.
			 */
			goto next_page;
		} else if (IS_ERR(page)) {
868 869
			ret = PTR_ERR(page);
			goto out;
870
		}
871 872 873 874
		if (pages) {
			pages[i] = page;
			flush_anon_page(vma, page, start);
			flush_dcache_page(page);
875
			ctx.page_mask = 0;
876 877
		}
next_page:
878 879
		if (vmas) {
			vmas[i] = vma;
880
			ctx.page_mask = 0;
881
		}
882
		page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
883 884 885 886 887
		if (page_increm > nr_pages)
			page_increm = nr_pages;
		i += page_increm;
		start += page_increm * PAGE_SIZE;
		nr_pages -= page_increm;
888
	} while (nr_pages);
889 890 891 892
out:
	if (ctx.pgmap)
		put_dev_pagemap(ctx.pgmap);
	return i ? i : ret;
893 894
}

895 896
static bool vma_permits_fault(struct vm_area_struct *vma,
			      unsigned int fault_flags)
897
{
898 899
	bool write   = !!(fault_flags & FAULT_FLAG_WRITE);
	bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE);
900
	vm_flags_t vm_flags = write ? VM_WRITE : VM_READ;
901 902 903 904

	if (!(vm_flags & vma->vm_flags))
		return false;

905 906
	/*
	 * The architecture might have a hardware protection
907
	 * mechanism other than read/write that can deny access.
908 909 910
	 *
	 * gup always represents data access, not instruction
	 * fetches, so execute=false here:
911
	 */
912
	if (!arch_vma_access_permitted(vma, write, false, foreign))
913 914
		return false;

915 916 917
	return true;
}

918 919 920 921 922 923 924
/*
 * fixup_user_fault() - manually resolve a user page fault
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @address:	user address
 * @fault_flags:flags to pass down to handle_mm_fault()
925 926
 * @unlocked:	did we unlock the mmap_sem while retrying, maybe NULL if caller
 *		does not allow retry
927 928 929 930 931 932 933 934 935 936 937
 *
 * This is meant to be called in the specific scenario where for locking reasons
 * we try to access user memory in atomic context (within a pagefault_disable()
 * section), this returns -EFAULT, and we want to resolve the user fault before
 * trying again.
 *
 * Typically this is meant to be used by the futex code.
 *
 * The main difference with get_user_pages() is that this function will
 * unconditionally call handle_mm_fault() which will in turn perform all the
 * necessary SW fixup of the dirty and young bits in the PTE, while
938
 * get_user_pages() only guarantees to update these in the struct page.
939 940 941 942 943 944
 *
 * This is important for some architectures where those bits also gate the
 * access permission to the page because they are maintained in software.  On
 * such architectures, gup() will not be enough to make a subsequent access
 * succeed.
 *
945 946
 * This function will not return with an unlocked mmap_sem. So it has not the
 * same semantics wrt the @mm->mmap_sem as does filemap_fault().
947 948
 */
int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
949 950
		     unsigned long address, unsigned int fault_flags,
		     bool *unlocked)
951 952
{
	struct vm_area_struct *vma;
953
	vm_fault_t ret, major = 0;
954

955 956
	address = untagged_addr(address);

957 958
	if (unlocked)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
959

960
retry:
961 962 963 964
	vma = find_extend_vma(mm, address);
	if (!vma || address < vma->vm_start)
		return -EFAULT;

965
	if (!vma_permits_fault(vma, fault_flags))
966 967
		return -EFAULT;

968
	ret = handle_mm_fault(vma, address, fault_flags);
969
	major |= ret & VM_FAULT_MAJOR;
970
	if (ret & VM_FAULT_ERROR) {
971 972 973 974
		int err = vm_fault_to_errno(ret, 0);

		if (err)
			return err;
975 976
		BUG();
	}
977 978 979 980 981 982 983 984 985 986 987

	if (ret & VM_FAULT_RETRY) {
		down_read(&mm->mmap_sem);
		if (!(fault_flags & FAULT_FLAG_TRIED)) {
			*unlocked = true;
			fault_flags &= ~FAULT_FLAG_ALLOW_RETRY;
			fault_flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}

988
	if (tsk) {
989
		if (major)
990 991 992 993 994 995
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}
	return 0;
}
996
EXPORT_SYMBOL_GPL(fixup_user_fault);
997

998 999 1000 1001 1002 1003
static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
						struct mm_struct *mm,
						unsigned long start,
						unsigned long nr_pages,
						struct page **pages,
						struct vm_area_struct **vmas,
1004
						int *locked,
1005
						unsigned int flags)
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
{
	long ret, pages_done;
	bool lock_dropped;

	if (locked) {
		/* if VM_FAULT_RETRY can be returned, vmas become invalid */
		BUG_ON(vmas);
		/* check caller initialized locked */
		BUG_ON(*locked != 1);
	}

	if (pages)
		flags |= FOLL_GET;

	pages_done = 0;
	lock_dropped = false;
	for (;;) {
		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
				       vmas, locked);
		if (!locked)
			/* VM_FAULT_RETRY couldn't trigger, bypass */
			return ret;

		/* VM_FAULT_RETRY cannot return errors */
		if (!*locked) {
			BUG_ON(ret < 0);
			BUG_ON(ret >= nr_pages);
		}

		if (ret > 0) {
			nr_pages -= ret;
			pages_done += ret;
			if (!nr_pages)
				break;
		}
		if (*locked) {
1042 1043 1044 1045
			/*
			 * VM_FAULT_RETRY didn't trigger or it was a
			 * FOLL_NOWAIT.
			 */
1046 1047 1048 1049
			if (!pages_done)
				pages_done = ret;
			break;
		}
1050 1051 1052 1053 1054 1055
		/*
		 * VM_FAULT_RETRY triggered, so seek to the faulting offset.
		 * For the prefault case (!pages) we only update counts.
		 */
		if (likely(pages))
			pages += ret;
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077
		start += ret << PAGE_SHIFT;

		/*
		 * Repeat on the address that fired VM_FAULT_RETRY
		 * without FAULT_FLAG_ALLOW_RETRY but with
		 * FAULT_FLAG_TRIED.
		 */
		*locked = 1;
		lock_dropped = true;
		down_read(&mm->mmap_sem);
		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
				       pages, NULL, NULL);
		if (ret != 1) {
			BUG_ON(ret > 1);
			if (!pages_done)
				pages_done = ret;
			break;
		}
		nr_pages--;
		pages_done++;
		if (!nr_pages)
			break;
1078 1079
		if (likely(pages))
			pages++;
1080 1081
		start += PAGE_SIZE;
	}
1082
	if (lock_dropped && *locked) {
1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
		/*
		 * We must let the caller know we temporarily dropped the lock
		 * and so the critical section protected by it was lost.
		 */
		up_read(&mm->mmap_sem);
		*locked = 0;
	}
	return pages_done;
}

1093
/*
1094
 * get_user_pages_remote() - pin user pages in memory
1095 1096 1097 1098 1099
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
1100
 * @gup_flags:	flags modifying lookup behaviour
1101 1102 1103 1104 1105
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
1106 1107 1108
 * @locked:	pointer to lock flag indicating whether lock is held and
 *		subsequently whether VM_FAULT_RETRY functionality can be
 *		utilised. Lock must initially be held.
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
 * Must be called with mmap_sem held for read or write.
 *
 * get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
1132 1133 1134
 * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
 * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
 * be called after the page is finished with, and before put_page is called.
1135 1136 1137 1138 1139 1140 1141 1142
 *
 * get_user_pages is typically used for fewer-copy IO operations, to get a
 * handle on the memory by some means other than accesses via the user virtual
 * addresses. The pages may be submitted for DMA to devices or accessed via
 * their kernel linear mapping (via the kmap APIs). Care should be taken to
 * use the correct cache flushing APIs.
 *
 * See also get_user_pages_fast, for performance critical applications.
1143 1144 1145 1146 1147
 *
 * get_user_pages should be phased out in favor of
 * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
 * should use get_user_pages because it cannot pass
 * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
1148
 */
1149 1150
long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages,
1151
		unsigned int gup_flags, struct page **pages,
1152
		struct vm_area_struct **vmas, int *locked)
1153
{
1154 1155 1156 1157 1158 1159 1160 1161 1162
	/*
	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
	 * vmas.  As there are no users of this flag in this call we simply
	 * disallow this option for now.
	 */
	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
		return -EINVAL;

1163
	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
1164
				       locked,
1165
				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
1166 1167 1168
}
EXPORT_SYMBOL(get_user_pages_remote);

1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 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 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 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 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314
/**
 * populate_vma_page_range() -  populate a range of pages in the vma.
 * @vma:   target vma
 * @start: start address
 * @end:   end address
 * @nonblocking:
 *
 * This takes care of mlocking the pages too if VM_LOCKED is set.
 *
 * return 0 on success, negative error code on error.
 *
 * vma->vm_mm->mmap_sem must be held.
 *
 * If @nonblocking is NULL, it may be held for read or write and will
 * be unperturbed.
 *
 * If @nonblocking is non-NULL, it must held for read only and may be
 * released.  If it's released, *@nonblocking will be set to 0.
 */
long populate_vma_page_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end, int *nonblocking)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long nr_pages = (end - start) / PAGE_SIZE;
	int gup_flags;

	VM_BUG_ON(start & ~PAGE_MASK);
	VM_BUG_ON(end   & ~PAGE_MASK);
	VM_BUG_ON_VMA(start < vma->vm_start, vma);
	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);

	gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
	if (vma->vm_flags & VM_LOCKONFAULT)
		gup_flags &= ~FOLL_POPULATE;
	/*
	 * We want to touch writable mappings with a write fault in order
	 * to break COW, except for shared mappings because these don't COW
	 * and we would not want to dirty them for nothing.
	 */
	if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
		gup_flags |= FOLL_WRITE;

	/*
	 * We want mlock to succeed for regions that have any permissions
	 * other than PROT_NONE.
	 */
	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
		gup_flags |= FOLL_FORCE;

	/*
	 * We made sure addr is within a VMA, so the following will
	 * not result in a stack expansion that recurses back here.
	 */
	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
				NULL, NULL, nonblocking);
}

/*
 * __mm_populate - populate and/or mlock pages within a range of address space.
 *
 * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
 * flags. VMAs must be already marked with the desired vm_flags, and
 * mmap_sem must not be held.
 */
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
	struct mm_struct *mm = current->mm;
	unsigned long end, nstart, nend;
	struct vm_area_struct *vma = NULL;
	int locked = 0;
	long ret = 0;

	end = start + len;

	for (nstart = start; nstart < end; nstart = nend) {
		/*
		 * We want to fault in pages for [nstart; end) address range.
		 * Find first corresponding VMA.
		 */
		if (!locked) {
			locked = 1;
			down_read(&mm->mmap_sem);
			vma = find_vma(mm, nstart);
		} else if (nstart >= vma->vm_end)
			vma = vma->vm_next;
		if (!vma || vma->vm_start >= end)
			break;
		/*
		 * Set [nstart; nend) to intersection of desired address
		 * range with the first VMA. Also, skip undesirable VMA types.
		 */
		nend = min(end, vma->vm_end);
		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
			continue;
		if (nstart < vma->vm_start)
			nstart = vma->vm_start;
		/*
		 * Now fault in a range of pages. populate_vma_page_range()
		 * double checks the vma flags, so that it won't mlock pages
		 * if the vma was already munlocked.
		 */
		ret = populate_vma_page_range(vma, nstart, nend, &locked);
		if (ret < 0) {
			if (ignore_errors) {
				ret = 0;
				continue;	/* continue at next VMA */
			}
			break;
		}
		nend = nstart + ret * PAGE_SIZE;
		ret = 0;
	}
	if (locked)
		up_read(&mm->mmap_sem);
	return ret;	/* 0 or negative error code */
}

/**
 * get_dump_page() - pin user page in memory while writing it to core dump
 * @addr: user address
 *
 * Returns struct page pointer of user page pinned for dump,
 * to be freed afterwards by put_page().
 *
 * Returns NULL on any kind of failure - a hole must then be inserted into
 * the corefile, to preserve alignment with its headers; and also returns
 * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
 * allowing a hole to be left in the corefile to save diskspace.
 *
 * Called without mmap_sem, but after all other threads have been killed.
 */
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
	struct vm_area_struct *vma;
	struct page *page;

	if (__get_user_pages(current, current->mm, addr, 1,
			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
			     NULL) < 1)
		return NULL;
	flush_cache_page(vma, addr, page_to_pfn(page));
	return page;
}
#endif /* CONFIG_ELF_CORE */
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
#else /* CONFIG_MMU */
static long __get_user_pages_locked(struct task_struct *tsk,
		struct mm_struct *mm, unsigned long start,
		unsigned long nr_pages, struct page **pages,
		struct vm_area_struct **vmas, int *locked,
		unsigned int foll_flags)
{
	struct vm_area_struct *vma;
	unsigned long vm_flags;
	int i;

	/* calculate required read or write permissions.
	 * If FOLL_FORCE is set, we only require the "MAY" flags.
	 */
	vm_flags  = (foll_flags & FOLL_WRITE) ?
			(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	vm_flags &= (foll_flags & FOLL_FORCE) ?
			(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);

	for (i = 0; i < nr_pages; i++) {
		vma = find_vma(mm, start);
		if (!vma)
			goto finish_or_fault;

		/* protect what we can, including chardevs */
		if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
		    !(vm_flags & vma->vm_flags))
			goto finish_or_fault;

		if (pages) {
			pages[i] = virt_to_page(start);
			if (pages[i])
				get_page(pages[i]);
		}
		if (vmas)
			vmas[i] = vma;
		start = (start + PAGE_SIZE) & PAGE_MASK;
	}

	return i;

finish_or_fault:
	return i ? : -EFAULT;
}
#endif /* !CONFIG_MMU */
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 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432
#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
{
	long i;
	struct vm_area_struct *vma_prev = NULL;

	for (i = 0; i < nr_pages; i++) {
		struct vm_area_struct *vma = vmas[i];

		if (vma == vma_prev)
			continue;

		vma_prev = vma;

		if (vma_is_fsdax(vma))
			return true;
	}
	return false;
}

#ifdef CONFIG_CMA
static struct page *new_non_cma_page(struct page *page, unsigned long private)
{
	/*
	 * We want to make sure we allocate the new page from the same node
	 * as the source page.
	 */
	int nid = page_to_nid(page);
	/*
	 * Trying to allocate a page for migration. Ignore allocation
	 * failure warnings. We don't force __GFP_THISNODE here because
	 * this node here is the node where we have CMA reservation and
	 * in some case these nodes will have really less non movable
	 * allocation memory.
	 */
	gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;

	if (PageHighMem(page))
		gfp_mask |= __GFP_HIGHMEM;

#ifdef CONFIG_HUGETLB_PAGE
	if (PageHuge(page)) {
		struct hstate *h = page_hstate(page);
		/*
		 * We don't want to dequeue from the pool because pool pages will
		 * mostly be from the CMA region.
		 */
		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
	}
#endif
	if (PageTransHuge(page)) {
		struct page *thp;
		/*
		 * ignore allocation failure warnings
		 */
		gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;

		/*
		 * Remove the movable mask so that we don't allocate from
		 * CMA area again.
		 */
		thp_gfpmask &= ~__GFP_MOVABLE;
		thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
		if (!thp)
			return NULL;
		prep_transhuge_page(thp);
		return thp;
	}

	return __alloc_pages_node(nid, gfp_mask, 0);
}

1433 1434 1435 1436
static long check_and_migrate_cma_pages(struct task_struct *tsk,
					struct mm_struct *mm,
					unsigned long start,
					unsigned long nr_pages,
1437
					struct page **pages,
1438 1439
					struct vm_area_struct **vmas,
					unsigned int gup_flags)
1440
{
1441 1442
	unsigned long i;
	unsigned long step;
1443 1444 1445 1446 1447
	bool drain_allow = true;
	bool migrate_allow = true;
	LIST_HEAD(cma_page_list);

check_again:
1448 1449 1450 1451 1452 1453 1454 1455
	for (i = 0; i < nr_pages;) {

		struct page *head = compound_head(pages[i]);

		/*
		 * gup may start from a tail page. Advance step by the left
		 * part.
		 */
1456
		step = compound_nr(head) - (pages[i] - head);
1457 1458 1459 1460 1461
		/*
		 * If we get a page from the CMA zone, since we are going to
		 * be pinning these entries, we might as well move them out
		 * of the CMA zone if possible.
		 */
1462 1463
		if (is_migrate_cma_page(head)) {
			if (PageHuge(head))
1464
				isolate_huge_page(head, &cma_page_list);
1465
			else {
1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479
				if (!PageLRU(head) && drain_allow) {
					lru_add_drain_all();
					drain_allow = false;
				}

				if (!isolate_lru_page(head)) {
					list_add_tail(&head->lru, &cma_page_list);
					mod_node_page_state(page_pgdat(head),
							    NR_ISOLATED_ANON +
							    page_is_file_cache(head),
							    hpage_nr_pages(head));
				}
			}
		}
1480 1481

		i += step;
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502
	}

	if (!list_empty(&cma_page_list)) {
		/*
		 * drop the above get_user_pages reference.
		 */
		for (i = 0; i < nr_pages; i++)
			put_page(pages[i]);

		if (migrate_pages(&cma_page_list, new_non_cma_page,
				  NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
			/*
			 * some of the pages failed migration. Do get_user_pages
			 * without migration.
			 */
			migrate_allow = false;

			if (!list_empty(&cma_page_list))
				putback_movable_pages(&cma_page_list);
		}
		/*
1503 1504 1505
		 * We did migrate all the pages, Try to get the page references
		 * again migrating any new CMA pages which we failed to isolate
		 * earlier.
1506
		 */
1507 1508 1509 1510
		nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages,
						   pages, vmas, NULL,
						   gup_flags);

1511 1512 1513 1514 1515 1516 1517 1518 1519
		if ((nr_pages > 0) && migrate_allow) {
			drain_allow = true;
			goto check_again;
		}
	}

	return nr_pages;
}
#else
1520 1521 1522 1523 1524 1525 1526
static long check_and_migrate_cma_pages(struct task_struct *tsk,
					struct mm_struct *mm,
					unsigned long start,
					unsigned long nr_pages,
					struct page **pages,
					struct vm_area_struct **vmas,
					unsigned int gup_flags)
1527 1528 1529
{
	return nr_pages;
}
1530
#endif /* CONFIG_CMA */
1531

1532
/*
1533 1534
 * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
 * allows us to process the FOLL_LONGTERM flag.
1535
 */
1536 1537 1538 1539 1540 1541 1542
static long __gup_longterm_locked(struct task_struct *tsk,
				  struct mm_struct *mm,
				  unsigned long start,
				  unsigned long nr_pages,
				  struct page **pages,
				  struct vm_area_struct **vmas,
				  unsigned int gup_flags)
1543
{
1544 1545
	struct vm_area_struct **vmas_tmp = vmas;
	unsigned long flags = 0;
1546 1547
	long rc, i;

1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559
	if (gup_flags & FOLL_LONGTERM) {
		if (!pages)
			return -EINVAL;

		if (!vmas_tmp) {
			vmas_tmp = kcalloc(nr_pages,
					   sizeof(struct vm_area_struct *),
					   GFP_KERNEL);
			if (!vmas_tmp)
				return -ENOMEM;
		}
		flags = memalloc_nocma_save();
1560 1561
	}

1562 1563
	rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
				     vmas_tmp, NULL, gup_flags);
1564

1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578
	if (gup_flags & FOLL_LONGTERM) {
		memalloc_nocma_restore(flags);
		if (rc < 0)
			goto out;

		if (check_dax_vmas(vmas_tmp, rc)) {
			for (i = 0; i < rc; i++)
				put_page(pages[i]);
			rc = -EOPNOTSUPP;
			goto out;
		}

		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
						 vmas_tmp, gup_flags);
1579
	}
1580 1581

out:
1582 1583
	if (vmas_tmp != vmas)
		kfree(vmas_tmp);
1584 1585
	return rc;
}
1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614
#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
						  struct mm_struct *mm,
						  unsigned long start,
						  unsigned long nr_pages,
						  struct page **pages,
						  struct vm_area_struct **vmas,
						  unsigned int flags)
{
	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
				       NULL, flags);
}
#endif /* CONFIG_FS_DAX || CONFIG_CMA */

/*
 * This is the same as get_user_pages_remote(), just with a
 * less-flexible calling convention where we assume that the task
 * and mm being operated on are the current task's and don't allow
 * passing of a locked parameter.  We also obviously don't pass
 * FOLL_REMOTE in here.
 */
long get_user_pages(unsigned long start, unsigned long nr_pages,
		unsigned int gup_flags, struct page **pages,
		struct vm_area_struct **vmas)
{
	return __gup_longterm_locked(current, current->mm, start, nr_pages,
				     pages, vmas, gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages);
1615

1616 1617 1618 1619
/*
 * We can leverage the VM_FAULT_RETRY functionality in the page fault
 * paths better by using either get_user_pages_locked() or
 * get_user_pages_unlocked().
1620
 *
1621
 * get_user_pages_locked() is suitable to replace the form:
1622
 *
1623 1624 1625 1626
 *      down_read(&mm->mmap_sem);
 *      do_something()
 *      get_user_pages(tsk, mm, ..., pages, NULL);
 *      up_read(&mm->mmap_sem);
1627
 *
1628
 *  to:
1629
 *
1630 1631 1632 1633 1634 1635
 *      int locked = 1;
 *      down_read(&mm->mmap_sem);
 *      do_something()
 *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
 *      if (locked)
 *          up_read(&mm->mmap_sem);
1636
 */
1637 1638 1639
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
			   unsigned int gup_flags, struct page **pages,
			   int *locked)
1640 1641
{
	/*
1642 1643 1644 1645
	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
	 * vmas.  As there are no users of this flag in this call we simply
	 * disallow this option for now.
1646
	 */
1647 1648
	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
		return -EINVAL;
1649

1650 1651 1652
	return __get_user_pages_locked(current, current->mm, start, nr_pages,
				       pages, NULL, locked,
				       gup_flags | FOLL_TOUCH);
1653
}
1654
EXPORT_SYMBOL(get_user_pages_locked);
1655 1656

/*
1657
 * get_user_pages_unlocked() is suitable to replace the form:
1658
 *
1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
 *      down_read(&mm->mmap_sem);
 *      get_user_pages(tsk, mm, ..., pages, NULL);
 *      up_read(&mm->mmap_sem);
 *
 *  with:
 *
 *      get_user_pages_unlocked(tsk, mm, ..., pages);
 *
 * It is functionally equivalent to get_user_pages_fast so
 * get_user_pages_fast should be used instead if specific gup_flags
 * (e.g. FOLL_FORCE) are not required.
1670
 */
1671 1672
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
			     struct page **pages, unsigned int gup_flags)
1673 1674
{
	struct mm_struct *mm = current->mm;
1675 1676
	int locked = 1;
	long ret;
1677

1678 1679 1680 1681 1682 1683 1684 1685
	/*
	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
	 * vmas.  As there are no users of this flag in this call we simply
	 * disallow this option for now.
	 */
	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
		return -EINVAL;
1686

1687 1688 1689
	down_read(&mm->mmap_sem);
	ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
				      &locked, gup_flags | FOLL_TOUCH);
1690 1691
	if (locked)
		up_read(&mm->mmap_sem);
1692
	return ret;
1693
}
1694
EXPORT_SYMBOL(get_user_pages_unlocked);
1695 1696

/*
1697
 * Fast GUP
1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717
 *
 * get_user_pages_fast attempts to pin user pages by walking the page
 * tables directly and avoids taking locks. Thus the walker needs to be
 * protected from page table pages being freed from under it, and should
 * block any THP splits.
 *
 * One way to achieve this is to have the walker disable interrupts, and
 * rely on IPIs from the TLB flushing code blocking before the page table
 * pages are freed. This is unsuitable for architectures that do not need
 * to broadcast an IPI when invalidating TLBs.
 *
 * Another way to achieve this is to batch up page table containing pages
 * belonging to more than one mm_user, then rcu_sched a callback to free those
 * pages. Disabling interrupts will allow the fast_gup walker to both block
 * the rcu_sched callback, and an IPI that we broadcast for splitting THPs
 * (which is a relatively rare event). The code below adopts this strategy.
 *
 * Before activating this code, please be aware that the following assumptions
 * are currently made:
 *
1718 1719
 *  *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
 *  free pages containing page tables or TLB flushing requires IPI broadcast.
1720 1721 1722 1723 1724 1725 1726 1727 1728
 *
 *  *) ptes can be read atomically by the architecture.
 *
 *  *) access_ok is sufficient to validate userspace address ranges.
 *
 * The last two assumptions can be relaxed by the addition of helper functions.
 *
 * This code is based heavily on the PowerPC implementation by Nick Piggin.
 */
1729
#ifdef CONFIG_HAVE_FAST_GUP
1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
/*
 * WARNING: only to be used in the get_user_pages_fast() implementation.
 *
 * With get_user_pages_fast(), we walk down the pagetables without taking any
 * locks.  For this we would like to load the pointers atomically, but sometimes
 * that is not possible (e.g. without expensive cmpxchg8b on x86_32 PAE).  What
 * we do have is the guarantee that a PTE will only either go from not present
 * to present, or present to not present or both -- it will not switch to a
 * completely different present page without a TLB flush in between; something
 * that we are blocking by holding interrupts off.
 *
 * Setting ptes from not present to present goes:
 *
 *   ptep->pte_high = h;
 *   smp_wmb();
 *   ptep->pte_low = l;
 *
 * And present to not present goes:
 *
 *   ptep->pte_low = 0;
 *   smp_wmb();
 *   ptep->pte_high = 0;
 *
 * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'.
 * We load pte_high *after* loading pte_low, which ensures we don't see an older
 * value of pte_high.  *Then* we recheck pte_low, which ensures that we haven't
 * picked up a changed pte high. We might have gotten rubbish values from
 * pte_low and pte_high, but we are guaranteed that pte_low will not have the
 * present bit set *unless* it is 'l'. Because get_user_pages_fast() only
 * operates on present ptes we're safe.
 */
static inline pte_t gup_get_pte(pte_t *ptep)
{
	pte_t pte;
1765

1766 1767 1768 1769 1770 1771 1772 1773 1774 1775
	do {
		pte.pte_low = ptep->pte_low;
		smp_rmb();
		pte.pte_high = ptep->pte_high;
		smp_rmb();
	} while (unlikely(pte.pte_low != ptep->pte_low));

	return pte;
}
#else /* CONFIG_GUP_GET_PTE_LOW_HIGH */
1776
/*
1777
 * We require that the PTE can be read atomically.
1778 1779 1780 1781 1782
 */
static inline pte_t gup_get_pte(pte_t *ptep)
{
	return READ_ONCE(*ptep);
}
1783
#endif /* CONFIG_GUP_GET_PTE_LOW_HIGH */
1784

1785 1786
static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
					    struct page **pages)
1787 1788 1789 1790 1791 1792 1793 1794 1795
{
	while ((*nr) - nr_start) {
		struct page *page = pages[--(*nr)];

		ClearPageReferenced(page);
		put_page(page);
	}
}

1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809
/*
 * Return the compund head page with ref appropriately incremented,
 * or NULL if that failed.
 */
static inline struct page *try_get_compound_head(struct page *page, int refs)
{
	struct page *head = compound_head(page);
	if (WARN_ON_ONCE(page_ref_count(head) < 0))
		return NULL;
	if (unlikely(!page_cache_add_speculative(head, refs)))
		return NULL;
	return head;
}

1810
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
1811
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
1812
			 unsigned int flags, struct page **pages, int *nr)
1813
{
1814 1815
	struct dev_pagemap *pgmap = NULL;
	int nr_start = *nr, ret = 0;
1816 1817 1818 1819
	pte_t *ptep, *ptem;

	ptem = ptep = pte_offset_map(&pmd, addr);
	do {
1820
		pte_t pte = gup_get_pte(ptep);
1821
		struct page *head, *page;
1822 1823 1824

		/*
		 * Similar to the PMD case below, NUMA hinting must take slow
1825
		 * path using the pte_protnone check.
1826
		 */
1827 1828 1829
		if (pte_protnone(pte))
			goto pte_unmap;

1830
		if (!pte_access_permitted(pte, flags & FOLL_WRITE))
1831 1832
			goto pte_unmap;

1833
		if (pte_devmap(pte)) {
1834 1835 1836
			if (unlikely(flags & FOLL_LONGTERM))
				goto pte_unmap;

1837 1838 1839 1840 1841 1842
			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
			if (unlikely(!pgmap)) {
				undo_dev_pagemap(nr, nr_start, pages);
				goto pte_unmap;
			}
		} else if (pte_special(pte))
1843 1844 1845 1846 1847
			goto pte_unmap;

		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
		page = pte_page(pte);

1848 1849
		head = try_get_compound_head(page, 1);
		if (!head)
1850 1851 1852
			goto pte_unmap;

		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
1853
			put_page(head);
1854 1855 1856
			goto pte_unmap;
		}

1857
		VM_BUG_ON_PAGE(compound_head(page) != head, page);
1858 1859

		SetPageReferenced(page);
1860 1861 1862 1863 1864 1865 1866 1867
		pages[*nr] = page;
		(*nr)++;

	} while (ptep++, addr += PAGE_SIZE, addr != end);

	ret = 1;

pte_unmap:
1868 1869
	if (pgmap)
		put_dev_pagemap(pgmap);
1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884
	pte_unmap(ptem);
	return ret;
}
#else

/*
 * If we can't determine whether or not a pte is special, then fail immediately
 * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
 * to be special.
 *
 * For a futex to be placed on a THP tail page, get_futex_key requires a
 * __get_user_pages_fast implementation that can pin pages. Thus it's still
 * useful to have gup_huge_pmd even if we can't operate on ptes.
 */
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
1885
			 unsigned int flags, struct page **pages, int *nr)
1886 1887 1888
{
	return 0;
}
1889
#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
1890

R
Robin Murphy 已提交
1891
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911
static int __gup_device_huge(unsigned long pfn, unsigned long addr,
		unsigned long end, struct page **pages, int *nr)
{
	int nr_start = *nr;
	struct dev_pagemap *pgmap = NULL;

	do {
		struct page *page = pfn_to_page(pfn);

		pgmap = get_dev_pagemap(pfn, pgmap);
		if (unlikely(!pgmap)) {
			undo_dev_pagemap(nr, nr_start, pages);
			return 0;
		}
		SetPageReferenced(page);
		pages[*nr] = page;
		get_page(page);
		(*nr)++;
		pfn++;
	} while (addr += PAGE_SIZE, addr != end);
1912 1913 1914

	if (pgmap)
		put_dev_pagemap(pgmap);
1915 1916 1917
	return 1;
}

1918
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
1919 1920 1921
		unsigned long end, struct page **pages, int *nr)
{
	unsigned long fault_pfn;
1922 1923 1924 1925 1926
	int nr_start = *nr;

	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
		return 0;
1927

1928 1929 1930 1931 1932
	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
		undo_dev_pagemap(nr, nr_start, pages);
		return 0;
	}
	return 1;
1933 1934
}

1935
static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
1936 1937 1938
		unsigned long end, struct page **pages, int *nr)
{
	unsigned long fault_pfn;
1939 1940 1941 1942 1943
	int nr_start = *nr;

	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
		return 0;
1944

1945 1946 1947 1948 1949
	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
		undo_dev_pagemap(nr, nr_start, pages);
		return 0;
	}
	return 1;
1950 1951
}
#else
1952
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
1953 1954 1955 1956 1957 1958
		unsigned long end, struct page **pages, int *nr)
{
	BUILD_BUG();
	return 0;
}

1959
static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
1960 1961 1962 1963 1964 1965 1966
		unsigned long end, struct page **pages, int *nr)
{
	BUILD_BUG();
	return 0;
}
#endif

1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006
#ifdef CONFIG_ARCH_HAS_HUGEPD
static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
				      unsigned long sz)
{
	unsigned long __boundary = (addr + sz) & ~(sz-1);
	return (__boundary - 1 < end - 1) ? __boundary : end;
}

static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
		       unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long pte_end;
	struct page *head, *page;
	pte_t pte;
	int refs;

	pte_end = (addr + sz) & ~(sz-1);
	if (pte_end < end)
		end = pte_end;

	pte = READ_ONCE(*ptep);

	if (!pte_access_permitted(pte, write))
		return 0;

	/* hugepages are never "special" */
	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

	refs = 0;
	head = pte_page(pte);

	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
	do {
		VM_BUG_ON(compound_head(page) != head);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

2007 2008
	head = try_get_compound_head(head, refs);
	if (!head) {
2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
		*nr -= refs;
		return 0;
	}

	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
		/* Could be optimized better */
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

2021
	SetPageReferenced(head);
2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050
	return 1;
}

static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
		unsigned int pdshift, unsigned long end, int write,
		struct page **pages, int *nr)
{
	pte_t *ptep;
	unsigned long sz = 1UL << hugepd_shift(hugepd);
	unsigned long next;

	ptep = hugepte_offset(hugepd, addr, pdshift);
	do {
		next = hugepte_addr_end(addr, end, sz);
		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
			return 0;
	} while (ptep++, addr = next, addr != end);

	return 1;
}
#else
static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
		unsigned pdshift, unsigned long end, int write,
		struct page **pages, int *nr)
{
	return 0;
}
#endif /* CONFIG_ARCH_HAS_HUGEPD */

2051
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
2052
		unsigned long end, unsigned int flags, struct page **pages, int *nr)
2053
{
2054
	struct page *head, *page;
2055 2056
	int refs;

2057
	if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
2058 2059
		return 0;

2060 2061 2062
	if (pmd_devmap(orig)) {
		if (unlikely(flags & FOLL_LONGTERM))
			return 0;
2063
		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
2064
	}
2065

2066
	refs = 0;
2067
	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
2068 2069 2070 2071 2072 2073 2074
	do {
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

2075 2076
	head = try_get_compound_head(pmd_page(orig), refs);
	if (!head) {
2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087
		*nr -= refs;
		return 0;
	}

	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

2088
	SetPageReferenced(head);
2089 2090 2091 2092
	return 1;
}

static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
2093
		unsigned long end, unsigned int flags, struct page **pages, int *nr)
2094
{
2095
	struct page *head, *page;
2096 2097
	int refs;

2098
	if (!pud_access_permitted(orig, flags & FOLL_WRITE))
2099 2100
		return 0;

2101 2102 2103
	if (pud_devmap(orig)) {
		if (unlikely(flags & FOLL_LONGTERM))
			return 0;
2104
		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
2105
	}
2106

2107
	refs = 0;
2108
	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
2109 2110 2111 2112 2113 2114 2115
	do {
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

2116 2117
	head = try_get_compound_head(pud_page(orig), refs);
	if (!head) {
2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128
		*nr -= refs;
		return 0;
	}

	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

2129
	SetPageReferenced(head);
2130 2131 2132
	return 1;
}

2133
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
2134
			unsigned long end, unsigned int flags,
2135 2136 2137
			struct page **pages, int *nr)
{
	int refs;
2138
	struct page *head, *page;
2139

2140
	if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
2141 2142
		return 0;

2143
	BUILD_BUG_ON(pgd_devmap(orig));
2144
	refs = 0;
2145
	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
2146 2147 2148 2149 2150 2151 2152
	do {
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

2153 2154
	head = try_get_compound_head(pgd_page(orig), refs);
	if (!head) {
2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165
		*nr -= refs;
		return 0;
	}

	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

2166
	SetPageReferenced(head);
2167 2168 2169
	return 1;
}

2170
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
2171
		unsigned int flags, struct page **pages, int *nr)
2172 2173 2174 2175 2176 2177
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
2178
		pmd_t pmd = READ_ONCE(*pmdp);
2179 2180

		next = pmd_addr_end(addr, end);
2181
		if (!pmd_present(pmd))
2182 2183
			return 0;

Y
Yu Zhao 已提交
2184 2185
		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) ||
			     pmd_devmap(pmd))) {
2186 2187 2188 2189 2190
			/*
			 * NUMA hinting faults need to be handled in the GUP
			 * slowpath for accounting purposes and so that they
			 * can be serialised against THP migration.
			 */
2191
			if (pmd_protnone(pmd))
2192 2193
				return 0;

2194
			if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
2195 2196 2197
				pages, nr))
				return 0;

2198 2199 2200 2201 2202 2203
		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
			/*
			 * architecture have different format for hugetlbfs
			 * pmd format and THP pmd format
			 */
			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
2204
					 PMD_SHIFT, next, flags, pages, nr))
2205
				return 0;
2206
		} else if (!gup_pte_range(pmd, addr, next, flags, pages, nr))
2207
			return 0;
2208 2209 2210 2211 2212
	} while (pmdp++, addr = next, addr != end);

	return 1;
}

2213
static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
2214
			 unsigned int flags, struct page **pages, int *nr)
2215 2216 2217 2218
{
	unsigned long next;
	pud_t *pudp;

2219
	pudp = pud_offset(&p4d, addr);
2220
	do {
2221
		pud_t pud = READ_ONCE(*pudp);
2222 2223 2224 2225

		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
2226
		if (unlikely(pud_huge(pud))) {
2227
			if (!gup_huge_pud(pud, pudp, addr, next, flags,
2228 2229 2230 2231
					  pages, nr))
				return 0;
		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
2232
					 PUD_SHIFT, next, flags, pages, nr))
2233
				return 0;
2234
		} else if (!gup_pmd_range(pud, addr, next, flags, pages, nr))
2235 2236 2237 2238 2239 2240
			return 0;
	} while (pudp++, addr = next, addr != end);

	return 1;
}

2241
static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
2242
			 unsigned int flags, struct page **pages, int *nr)
2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256
{
	unsigned long next;
	p4d_t *p4dp;

	p4dp = p4d_offset(&pgd, addr);
	do {
		p4d_t p4d = READ_ONCE(*p4dp);

		next = p4d_addr_end(addr, end);
		if (p4d_none(p4d))
			return 0;
		BUILD_BUG_ON(p4d_huge(p4d));
		if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
			if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
2257
					 P4D_SHIFT, next, flags, pages, nr))
2258
				return 0;
2259
		} else if (!gup_pud_range(p4d, addr, next, flags, pages, nr))
2260 2261 2262 2263 2264 2265
			return 0;
	} while (p4dp++, addr = next, addr != end);

	return 1;
}

2266
static void gup_pgd_range(unsigned long addr, unsigned long end,
2267
		unsigned int flags, struct page **pages, int *nr)
2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279
{
	unsigned long next;
	pgd_t *pgdp;

	pgdp = pgd_offset(current->mm, addr);
	do {
		pgd_t pgd = READ_ONCE(*pgdp);

		next = pgd_addr_end(addr, end);
		if (pgd_none(pgd))
			return;
		if (unlikely(pgd_huge(pgd))) {
2280
			if (!gup_huge_pgd(pgd, pgdp, addr, next, flags,
2281 2282 2283 2284
					  pages, nr))
				return;
		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
2285
					 PGDIR_SHIFT, next, flags, pages, nr))
2286
				return;
2287
		} else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr))
2288 2289 2290
			return;
	} while (pgdp++, addr = next, addr != end);
}
2291 2292 2293 2294 2295 2296
#else
static inline void gup_pgd_range(unsigned long addr, unsigned long end,
		unsigned int flags, struct page **pages, int *nr)
{
}
#endif /* CONFIG_HAVE_FAST_GUP */
2297 2298 2299 2300 2301 2302

#ifndef gup_fast_permitted
/*
 * Check if it's allowed to use __get_user_pages_fast() for the range, or
 * we need to fall back to the slow version:
 */
2303
static bool gup_fast_permitted(unsigned long start, unsigned long end)
2304
{
2305
	return true;
2306 2307 2308
}
#endif

2309 2310
/*
 * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
2311 2312 2313
 * the regular GUP.
 * Note a difference with get_user_pages_fast: this always returns the
 * number of pages pinned, 0 if no pages were pinned.
2314 2315 2316
 *
 * If the architecture does not support this function, simply return with no
 * pages pinned.
2317 2318 2319 2320
 */
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages)
{
2321
	unsigned long len, end;
2322
	unsigned long flags;
2323 2324
	int nr = 0;

2325
	start = untagged_addr(start) & PAGE_MASK;
2326 2327 2328
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

2329 2330
	if (end <= start)
		return 0;
2331
	if (unlikely(!access_ok((void __user *)start, len)))
2332 2333 2334 2335 2336 2337 2338
		return 0;

	/*
	 * Disable interrupts.  We use the nested form as we can already have
	 * interrupts disabled by get_futex_key.
	 *
	 * With interrupts disabled, we block page table pages from being
2339 2340
	 * freed from under us. See struct mmu_table_batch comments in
	 * include/asm-generic/tlb.h for more details.
2341 2342 2343 2344 2345
	 *
	 * We do not adopt an rcu_read_lock(.) here as we also want to
	 * block IPIs that come from THPs splitting.
	 */

2346 2347
	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
	    gup_fast_permitted(start, end)) {
2348
		local_irq_save(flags);
2349
		gup_pgd_range(start, end, write ? FOLL_WRITE : 0, pages, &nr);
2350 2351
		local_irq_restore(flags);
	}
2352 2353 2354

	return nr;
}
2355
EXPORT_SYMBOL_GPL(__get_user_pages_fast);
2356

2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379
static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
				   unsigned int gup_flags, struct page **pages)
{
	int ret;

	/*
	 * FIXME: FOLL_LONGTERM does not work with
	 * get_user_pages_unlocked() (see comments in that function)
	 */
	if (gup_flags & FOLL_LONGTERM) {
		down_read(&current->mm->mmap_sem);
		ret = __gup_longterm_locked(current, current->mm,
					    start, nr_pages,
					    pages, NULL, gup_flags);
		up_read(&current->mm->mmap_sem);
	} else {
		ret = get_user_pages_unlocked(start, nr_pages,
					      pages, gup_flags);
	}

	return ret;
}

2380 2381 2382 2383
/**
 * get_user_pages_fast() - pin user pages in memory
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
2384
 * @gup_flags:	flags modifying pin behaviour
2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long.
 *
 * Attempt to pin user pages in memory without taking mm->mmap_sem.
 * If not successful, it will fall back to taking the lock and
 * calling get_user_pages().
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno.
 */
2396 2397
int get_user_pages_fast(unsigned long start, int nr_pages,
			unsigned int gup_flags, struct page **pages)
2398
{
2399
	unsigned long addr, len, end;
2400
	int nr = 0, ret = 0;
2401

2402 2403 2404
	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
		return -EINVAL;

2405
	start = untagged_addr(start) & PAGE_MASK;
2406 2407 2408 2409
	addr = start;
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

2410
	if (end <= start)
2411
		return 0;
2412
	if (unlikely(!access_ok((void __user *)start, len)))
2413
		return -EFAULT;
2414

2415 2416
	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP) &&
	    gup_fast_permitted(start, end)) {
2417
		local_irq_disable();
2418
		gup_pgd_range(addr, end, gup_flags, pages, &nr);
2419
		local_irq_enable();
2420 2421
		ret = nr;
	}
2422 2423 2424 2425 2426 2427

	if (nr < nr_pages) {
		/* Try to get the remaining pages with get_user_pages */
		start += nr << PAGE_SHIFT;
		pages += nr;

2428 2429
		ret = __gup_longterm_unlocked(start, nr_pages - nr,
					      gup_flags, pages);
2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441

		/* Have to be a bit careful with return values */
		if (nr > 0) {
			if (ret < 0)
				ret = nr;
			else
				ret += nr;
		}
	}

	return ret;
}
2442
EXPORT_SYMBOL_GPL(get_user_pages_fast);