mlock.c 15.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7
/*
 *	linux/mm/mlock.c
 *
 *  (C) Copyright 1995 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 */

8
#include <linux/capability.h>
L
Linus Torvalds 已提交
9 10
#include <linux/mman.h>
#include <linux/mm.h>
N
Nick Piggin 已提交
11 12 13
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
L
Linus Torvalds 已提交
14 15
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
A
Alexey Dobriyan 已提交
16 17
#include <linux/sched.h>
#include <linux/module.h>
N
Nick Piggin 已提交
18 19 20 21 22
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>

#include "internal.h"
L
Linus Torvalds 已提交
23

A
Alexey Dobriyan 已提交
24 25 26 27 28 29 30 31 32
int can_do_mlock(void)
{
	if (capable(CAP_IPC_LOCK))
		return 1;
	if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
		return 1;
	return 0;
}
EXPORT_SYMBOL(can_do_mlock);
L
Linus Torvalds 已提交
33

N
Nick Piggin 已提交
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
#ifdef CONFIG_UNEVICTABLE_LRU
/*
 * Mlocked pages are marked with PageMlocked() flag for efficient testing
 * in vmscan and, possibly, the fault path; and to support semi-accurate
 * statistics.
 *
 * An mlocked page [PageMlocked(page)] is unevictable.  As such, it will
 * be placed on the LRU "unevictable" list, rather than the [in]active lists.
 * The unevictable list is an LRU sibling list to the [in]active lists.
 * PageUnevictable is set to indicate the unevictable state.
 *
 * When lazy mlocking via vmscan, it is important to ensure that the
 * vma's VM_LOCKED status is not concurrently being modified, otherwise we
 * may have mlocked a page that is being munlocked. So lazy mlock must take
 * the mmap_sem for read, and verify that the vma really is locked
 * (see mm/rmap.c).
 */

/*
 *  LRU accounting for clear_page_mlock()
 */
void __clear_page_mlock(struct page *page)
{
	VM_BUG_ON(!PageLocked(page));

	if (!page->mapping) {	/* truncated ? */
		return;
	}

	if (!isolate_lru_page(page)) {
		putback_lru_page(page);
	} else {
		/*
		 * Page not on the LRU yet.  Flush all pagevecs and retry.
		 */
		lru_add_drain_all();
		if (!isolate_lru_page(page))
			putback_lru_page(page);
	}
}

/*
 * Mark page as mlocked if not already.
 * If page on LRU, isolate and putback to move to unevictable list.
 */
void mlock_vma_page(struct page *page)
{
	BUG_ON(!PageLocked(page));

	if (!TestSetPageMlocked(page) && !isolate_lru_page(page))
		putback_lru_page(page);
}

/*
 * called from munlock()/munmap() path with page supposedly on the LRU.
 *
 * Note:  unlike mlock_vma_page(), we can't just clear the PageMlocked
 * [in try_to_munlock()] and then attempt to isolate the page.  We must
 * isolate the page to keep others from messing with its unevictable
 * and mlocked state while trying to munlock.  However, we pre-clear the
 * mlocked state anyway as we might lose the isolation race and we might
 * not get another chance to clear PageMlocked.  If we successfully
 * isolate the page and try_to_munlock() detects other VM_LOCKED vmas
 * mapping the page, it will restore the PageMlocked state, unless the page
 * is mapped in a non-linear vma.  So, we go ahead and SetPageMlocked(),
 * perhaps redundantly.
 * If we lose the isolation race, and the page is mapped by other VM_LOCKED
 * vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
 * either of which will restore the PageMlocked state by calling
 * mlock_vma_page() above, if it can grab the vma's mmap sem.
 */
static void munlock_vma_page(struct page *page)
{
	BUG_ON(!PageLocked(page));

	if (TestClearPageMlocked(page) && !isolate_lru_page(page)) {
		try_to_munlock(page);
		putback_lru_page(page);
	}
}

115 116 117 118 119 120 121 122 123 124
/**
 * __mlock_vma_pages_range() -  mlock/munlock a range of pages in the vma.
 * @vma:   target vma
 * @start: start address
 * @end:   end address
 * @mlock: 0 indicate munlock, otherwise mlock.
 *
 * If @mlock == 0, unlock an mlocked range;
 * else mlock the range of pages.  This takes care of making the pages present ,
 * too.
N
Nick Piggin 已提交
125
 *
126
 * return 0 on success, negative error code on error.
N
Nick Piggin 已提交
127
 *
128
 * vma->vm_mm->mmap_sem must be held for at least read.
N
Nick Piggin 已提交
129
 */
130 131 132
static long __mlock_vma_pages_range(struct vm_area_struct *vma,
				   unsigned long start, unsigned long end,
				   int mlock)
N
Nick Piggin 已提交
133 134 135 136 137 138
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long addr = start;
	struct page *pages[16]; /* 16 gives a reasonable batch */
	int nr_pages = (end - start) / PAGE_SIZE;
	int ret;
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
	int gup_flags = 0;

	VM_BUG_ON(start & ~PAGE_MASK);
	VM_BUG_ON(end   & ~PAGE_MASK);
	VM_BUG_ON(start < vma->vm_start);
	VM_BUG_ON(end   > vma->vm_end);
	VM_BUG_ON((!rwsem_is_locked(&mm->mmap_sem)) &&
		  (atomic_read(&mm->mm_users) != 0));

	/*
	 * mlock:   don't page populate if page has PROT_NONE permission.
	 * munlock: the pages always do munlock althrough
	 *          its has PROT_NONE permission.
	 */
	if (!mlock)
		gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS;
N
Nick Piggin 已提交
155

156 157
	if (vma->vm_flags & VM_WRITE)
		gup_flags |= GUP_FLAGS_WRITE;
N
Nick Piggin 已提交
158 159 160 161 162 163 164 165 166 167 168 169 170 171

	lru_add_drain_all();	/* push cached pages to LRU */

	while (nr_pages > 0) {
		int i;

		cond_resched();

		/*
		 * get_user_pages makes pages present if we are
		 * setting mlock. and this extra reference count will
		 * disable migration of this page.  However, page may
		 * still be truncated out from under us.
		 */
172
		ret = __get_user_pages(current, mm, addr,
N
Nick Piggin 已提交
173
				min_t(int, nr_pages, ARRAY_SIZE(pages)),
174
				gup_flags, pages, NULL);
N
Nick Piggin 已提交
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
		/*
		 * This can happen for, e.g., VM_NONLINEAR regions before
		 * a page has been allocated and mapped at a given offset,
		 * or for addresses that map beyond end of a file.
		 * We'll mlock the the pages if/when they get faulted in.
		 */
		if (ret < 0)
			break;
		if (ret == 0) {
			/*
			 * We know the vma is there, so the only time
			 * we cannot get a single page should be an
			 * error (ret < 0) case.
			 */
			WARN_ON(1);
			break;
		}

		lru_add_drain();	/* push cached pages to LRU */

		for (i = 0; i < ret; i++) {
			struct page *page = pages[i];

			lock_page(page);
			/*
			 * Because we lock page here and migration is blocked
			 * by the elevated reference, we need only check for
			 * page truncation (file-cache only).
			 */
204 205 206 207 208 209
			if (page->mapping) {
				if (mlock)
					mlock_vma_page(page);
				else
					munlock_vma_page(page);
			}
N
Nick Piggin 已提交
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
			unlock_page(page);
			put_page(page);		/* ref from get_user_pages() */

			/*
			 * here we assume that get_user_pages() has given us
			 * a list of virtually contiguous pages.
			 */
			addr += PAGE_SIZE;	/* for next get_user_pages() */
			nr_pages--;
		}
	}

	lru_add_drain_all();	/* to update stats */

	return 0;	/* count entire vma as locked_vm */
}

#else /* CONFIG_UNEVICTABLE_LRU */

/*
 * Just make pages present if VM_LOCKED.  No-op if unlocking.
 */
232 233 234
static long __mlock_vma_pages_range(struct vm_area_struct *vma,
				   unsigned long start, unsigned long end,
				   int mlock)
N
Nick Piggin 已提交
235
{
236
	if (mlock && (vma->vm_flags & VM_LOCKED))
N
Nick Piggin 已提交
237 238 239 240 241
		make_pages_present(start, end);
	return 0;
}
#endif /* CONFIG_UNEVICTABLE_LRU */

242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
/**
 * mlock_vma_pages_range() - mlock pages in specified vma range.
 * @vma - the vma containing the specfied address range
 * @start - starting address in @vma to mlock
 * @end   - end address [+1] in @vma to mlock
 *
 * For mmap()/mremap()/expansion of mlocked vma.
 *
 * return 0 on success for "normal" vmas.
 *
 * return number of pages [> 0] to be removed from locked_vm on success
 * of "special" vmas.
 *
 * return negative error if vma spanning @start-@range disappears while
 * mmap semaphore is dropped.  Unlikely?
N
Nick Piggin 已提交
257
 */
258
long mlock_vma_pages_range(struct vm_area_struct *vma,
N
Nick Piggin 已提交
259 260
			unsigned long start, unsigned long end)
{
261
	struct mm_struct *mm = vma->vm_mm;
N
Nick Piggin 已提交
262 263 264 265 266 267 268 269 270 271 272
	int nr_pages = (end - start) / PAGE_SIZE;
	BUG_ON(!(vma->vm_flags & VM_LOCKED));

	/*
	 * filter unlockable vmas
	 */
	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
		goto no_mlock;

	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
			is_vm_hugetlb_page(vma) ||
273
			vma == get_gate_vma(current))) {
274
		long error;
275
		downgrade_write(&mm->mmap_sem);
276 277

		error = __mlock_vma_pages_range(vma, start, end, 1);
278 279 280 281 282 283 284

		up_read(&mm->mmap_sem);
		/* vma can change or disappear */
		down_write(&mm->mmap_sem);
		vma = find_vma(mm, start);
		/* non-NULL vma must contain @start, but need to check @end */
		if (!vma ||  end > vma->vm_end)
285 286 287
			return -ENOMEM;

		return 0;	/* hide other errors from mmap(), et al */
288
	}
N
Nick Piggin 已提交
289 290 291 292 293 294 295 296 297 298 299 300 301

	/*
	 * User mapped kernel pages or huge pages:
	 * make these pages present to populate the ptes, but
	 * fall thru' to reset VM_LOCKED--no need to unlock, and
	 * return nr_pages so these don't get counted against task's
	 * locked limit.  huge pages are already counted against
	 * locked vm limit.
	 */
	make_pages_present(start, end);

no_mlock:
	vma->vm_flags &= ~VM_LOCKED;	/* and don't come back! */
302
	return nr_pages;		/* error or pages NOT mlocked */
N
Nick Piggin 已提交
303 304 305 306
}


/*
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
 * munlock_vma_pages_range() - munlock all pages in the vma range.'
 * @vma - vma containing range to be munlock()ed.
 * @start - start address in @vma of the range
 * @end - end of range in @vma.
 *
 *  For mremap(), munmap() and exit().
 *
 * Called with @vma VM_LOCKED.
 *
 * Returns with VM_LOCKED cleared.  Callers must be prepared to
 * deal with this.
 *
 * We don't save and restore VM_LOCKED here because pages are
 * still on lru.  In unmap path, pages might be scanned by reclaim
 * and re-mlocked by try_to_{munlock|unmap} before we unmap and
 * free them.  This will result in freeing mlocked pages.
N
Nick Piggin 已提交
323
 */
324 325
void munlock_vma_pages_range(struct vm_area_struct *vma,
			   unsigned long start, unsigned long end)
N
Nick Piggin 已提交
326 327
{
	vma->vm_flags &= ~VM_LOCKED;
328
	__mlock_vma_pages_range(vma, start, end, 0);
N
Nick Piggin 已提交
329 330 331 332 333 334 335 336 337 338 339
}

/*
 * mlock_fixup  - handle mlock[all]/munlock[all] requests.
 *
 * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
 * munlock is a no-op.  However, for some special vmas, we go ahead and
 * populate the ptes via make_pages_present().
 *
 * For vmas that pass the filters, merge/split as appropriate.
 */
L
Linus Torvalds 已提交
340 341 342
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
	unsigned long start, unsigned long end, unsigned int newflags)
{
N
Nick Piggin 已提交
343
	struct mm_struct *mm = vma->vm_mm;
L
Linus Torvalds 已提交
344
	pgoff_t pgoff;
N
Nick Piggin 已提交
345
	int nr_pages;
L
Linus Torvalds 已提交
346
	int ret = 0;
N
Nick Piggin 已提交
347
	int lock = newflags & VM_LOCKED;
L
Linus Torvalds 已提交
348

N
Nick Piggin 已提交
349 350 351 352 353 354 355 356 357 358
	if (newflags == vma->vm_flags ||
			(vma->vm_flags & (VM_IO | VM_PFNMAP)))
		goto out;	/* don't set VM_LOCKED,  don't count */

	if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
			is_vm_hugetlb_page(vma) ||
			vma == get_gate_vma(current)) {
		if (lock)
			make_pages_present(start, end);
		goto out;	/* don't set VM_LOCKED,  don't count */
L
Linus Torvalds 已提交
359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381
	}

	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
			  vma->vm_file, pgoff, vma_policy(vma));
	if (*prev) {
		vma = *prev;
		goto success;
	}

	if (start != vma->vm_start) {
		ret = split_vma(mm, vma, start, 1);
		if (ret)
			goto out;
	}

	if (end != vma->vm_end) {
		ret = split_vma(mm, vma, end, 0);
		if (ret)
			goto out;
	}

success:
N
Nick Piggin 已提交
382 383 384 385 386 387 388 389
	/*
	 * Keep track of amount of locked VM.
	 */
	nr_pages = (end - start) >> PAGE_SHIFT;
	if (!lock)
		nr_pages = -nr_pages;
	mm->locked_vm += nr_pages;

L
Linus Torvalds 已提交
390 391 392
	/*
	 * vm_flags is protected by the mmap_sem held in write mode.
	 * It's okay if try_to_unmap_one unmaps a page just after we
N
Nick Piggin 已提交
393
	 * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
L
Linus Torvalds 已提交
394 395 396
	 */
	vma->vm_flags = newflags;

N
Nick Piggin 已提交
397
	if (lock) {
398 399 400 401 402 403 404
		/*
		 * mmap_sem is currently held for write.  Downgrade the write
		 * lock to a read lock so that other faults, mmap scans, ...
		 * while we fault in all pages.
		 */
		downgrade_write(&mm->mmap_sem);

405
		ret = __mlock_vma_pages_range(vma, start, end, 1);
N
Nick Piggin 已提交
406 407 408 409
		if (ret > 0) {
			mm->locked_vm -= ret;
			ret = 0;
		}
410 411 412 413 414 415 416 417 418 419 420 421
		/*
		 * Need to reacquire mmap sem in write mode, as our callers
		 * expect this.  We have no support for atomically upgrading
		 * a sem to write, so we need to check for ranges while sem
		 * is unlocked.
		 */
		up_read(&mm->mmap_sem);
		/* vma can change or disappear */
		down_write(&mm->mmap_sem);
		*prev = find_vma(mm, start);
		/* non-NULL *prev must contain @start, but need to check @end */
		if (!(*prev) || end > (*prev)->vm_end)
422
			ret = -ENOMEM;
423 424 425 426 427 428 429 430
	} else {
		/*
		 * TODO:  for unlocking, pages will already be resident, so
		 * we don't need to wait for allocations/reclaim/pagein, ...
		 * However, unlocking a very large region can still take a
		 * while.  Should we downgrade the semaphore for both lock
		 * AND unlock ?
		 */
431
		__mlock_vma_pages_range(vma, start, end, 0);
432
	}
L
Linus Torvalds 已提交
433 434

out:
N
Nick Piggin 已提交
435
	*prev = vma;
L
Linus Torvalds 已提交
436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599
	return ret;
}

static int do_mlock(unsigned long start, size_t len, int on)
{
	unsigned long nstart, end, tmp;
	struct vm_area_struct * vma, * prev;
	int error;

	len = PAGE_ALIGN(len);
	end = start + len;
	if (end < start)
		return -EINVAL;
	if (end == start)
		return 0;
	vma = find_vma_prev(current->mm, start, &prev);
	if (!vma || vma->vm_start > start)
		return -ENOMEM;

	if (start > vma->vm_start)
		prev = vma;

	for (nstart = start ; ; ) {
		unsigned int newflags;

		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */

		newflags = vma->vm_flags | VM_LOCKED;
		if (!on)
			newflags &= ~VM_LOCKED;

		tmp = vma->vm_end;
		if (tmp > end)
			tmp = end;
		error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
		if (error)
			break;
		nstart = tmp;
		if (nstart < prev->vm_end)
			nstart = prev->vm_end;
		if (nstart >= end)
			break;

		vma = prev->vm_next;
		if (!vma || vma->vm_start != nstart) {
			error = -ENOMEM;
			break;
		}
	}
	return error;
}

asmlinkage long sys_mlock(unsigned long start, size_t len)
{
	unsigned long locked;
	unsigned long lock_limit;
	int error = -ENOMEM;

	if (!can_do_mlock())
		return -EPERM;

	down_write(&current->mm->mmap_sem);
	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
	start &= PAGE_MASK;

	locked = len >> PAGE_SHIFT;
	locked += current->mm->locked_vm;

	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
	lock_limit >>= PAGE_SHIFT;

	/* check against resource limits */
	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
		error = do_mlock(start, len, 1);
	up_write(&current->mm->mmap_sem);
	return error;
}

asmlinkage long sys_munlock(unsigned long start, size_t len)
{
	int ret;

	down_write(&current->mm->mmap_sem);
	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
	start &= PAGE_MASK;
	ret = do_mlock(start, len, 0);
	up_write(&current->mm->mmap_sem);
	return ret;
}

static int do_mlockall(int flags)
{
	struct vm_area_struct * vma, * prev = NULL;
	unsigned int def_flags = 0;

	if (flags & MCL_FUTURE)
		def_flags = VM_LOCKED;
	current->mm->def_flags = def_flags;
	if (flags == MCL_FUTURE)
		goto out;

	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
		unsigned int newflags;

		newflags = vma->vm_flags | VM_LOCKED;
		if (!(flags & MCL_CURRENT))
			newflags &= ~VM_LOCKED;

		/* Ignore errors */
		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
	}
out:
	return 0;
}

asmlinkage long sys_mlockall(int flags)
{
	unsigned long lock_limit;
	int ret = -EINVAL;

	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
		goto out;

	ret = -EPERM;
	if (!can_do_mlock())
		goto out;

	down_write(&current->mm->mmap_sem);

	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
	lock_limit >>= PAGE_SHIFT;

	ret = -ENOMEM;
	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
	    capable(CAP_IPC_LOCK))
		ret = do_mlockall(flags);
	up_write(&current->mm->mmap_sem);
out:
	return ret;
}

asmlinkage long sys_munlockall(void)
{
	int ret;

	down_write(&current->mm->mmap_sem);
	ret = do_mlockall(0);
	up_write(&current->mm->mmap_sem);
	return ret;
}

/*
 * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
 * shm segments) get accounted against the user_struct instead.
 */
static DEFINE_SPINLOCK(shmlock_user_lock);

int user_shm_lock(size_t size, struct user_struct *user)
{
	unsigned long lock_limit, locked;
	int allowed = 0;

	locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
600 601
	if (lock_limit == RLIM_INFINITY)
		allowed = 1;
L
Linus Torvalds 已提交
602 603
	lock_limit >>= PAGE_SHIFT;
	spin_lock(&shmlock_user_lock);
604 605
	if (!allowed &&
	    locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
L
Linus Torvalds 已提交
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621
		goto out;
	get_uid(user);
	user->locked_shm += locked;
	allowed = 1;
out:
	spin_unlock(&shmlock_user_lock);
	return allowed;
}

void user_shm_unlock(size_t size, struct user_struct *user)
{
	spin_lock(&shmlock_user_lock);
	user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
	spin_unlock(&shmlock_user_lock);
	free_uid(user);
}