nommu.c 35.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12
/*
 *  linux/mm/nommu.c
 *
 *  Replacement code for mm functions to support CPU's that don't
 *  have any form of memory management unit (thus no virtual memory).
 *
 *  See Documentation/nommu-mmap.txt
 *
 *  Copyright (c) 2004-2005 David Howells <dhowells@redhat.com>
 *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
 *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
 *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
13
 *  Copyright (c) 2007      Paul Mundt <lethal@linux-sh.org>
L
Linus Torvalds 已提交
14 15
 */

16
#include <linux/module.h>
L
Linus Torvalds 已提交
17 18 19 20 21 22 23 24
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
25
#include <linux/tracehook.h>
L
Linus Torvalds 已提交
26 27 28 29 30 31 32 33 34 35 36
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>

#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>

N
Nick Piggin 已提交
37 38
#include "internal.h"

L
Linus Torvalds 已提交
39 40 41 42 43
void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
unsigned long askedalloc, realalloc;
A
Alan Cox 已提交
44
atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
L
Linus Torvalds 已提交
45 46 47 48 49 50
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
int heap_stack_gap = 0;

EXPORT_SYMBOL(mem_map);
51
EXPORT_SYMBOL(num_physpages);
L
Linus Torvalds 已提交
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

/* list of shareable VMAs */
struct rb_root nommu_vma_tree = RB_ROOT;
DECLARE_RWSEM(nommu_vma_sem);

struct vm_operations_struct generic_file_vm_ops = {
};

/*
 * Handle all mappings that got truncated by a "truncate()"
 * system call.
 *
 * NOTE! We have to be ready to update the memory sharing
 * between the file and the memory map for a potential last
 * incomplete page.  Ugly, but necessary.
 */
int vmtruncate(struct inode *inode, loff_t offset)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned long limit;

	if (inode->i_size < offset)
		goto do_expand;
	i_size_write(inode, offset);

	truncate_inode_pages(mapping, offset);
	goto out_truncate;

do_expand:
	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && offset > limit)
		goto out_sig;
	if (offset > inode->i_sb->s_maxbytes)
		goto out;
	i_size_write(inode, offset);

out_truncate:
	if (inode->i_op && inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out:
	return -EFBIG;
}

EXPORT_SYMBOL(vmtruncate);

/*
 * Return the total memory allocated for this pointer, not
 * just what the caller asked for.
 *
 * Doesn't have to be accurate, i.e. may have races.
 */
unsigned int kobjsize(const void *objp)
{
	struct page *page;

110 111 112 113
	/*
	 * If the object we have should not have ksize performed on it,
	 * return size of 0
	 */
114
	if (!objp || !virt_addr_valid(objp))
115 116 117 118 119 120 121 122
		return 0;

	page = virt_to_head_page(objp);

	/*
	 * If the allocator sets PageSlab, we know the pointer came from
	 * kmalloc().
	 */
L
Linus Torvalds 已提交
123 124 125
	if (PageSlab(page))
		return ksize(objp);

126 127
	/*
	 * The ksize() function is only guaranteed to work for pointers
128
	 * returned by kmalloc(). So handle arbitrary pointers here.
129
	 */
130
	return PAGE_SIZE << compound_order(page);
L
Linus Torvalds 已提交
131 132
}

N
Nick Piggin 已提交
133 134 135
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long start, int len, int flags,
		struct page **pages, struct vm_area_struct **vmas)
L
Linus Torvalds 已提交
136
{
137
	struct vm_area_struct *vma;
138 139
	unsigned long vm_flags;
	int i;
N
Nick Piggin 已提交
140 141 142
	int write = !!(flags & GUP_FLAGS_WRITE);
	int force = !!(flags & GUP_FLAGS_FORCE);
	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
143 144 145 146 147 148

	/* calculate required read or write permissions.
	 * - if 'force' is set, we only require the "MAY" flags.
	 */
	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
L
Linus Torvalds 已提交
149 150

	for (i = 0; i < len; i++) {
151
		vma = find_vma(mm, start);
152 153 154 155 156
		if (!vma)
			goto finish_or_fault;

		/* protect what we can, including chardevs */
		if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
N
Nick Piggin 已提交
157
		    (!ignore && !(vm_flags & vma->vm_flags)))
158
			goto finish_or_fault;
159

L
Linus Torvalds 已提交
160 161 162 163 164 165
		if (pages) {
			pages[i] = virt_to_page(start);
			if (pages[i])
				page_cache_get(pages[i]);
		}
		if (vmas)
166
			vmas[i] = vma;
L
Linus Torvalds 已提交
167 168
		start += PAGE_SIZE;
	}
169 170 171 172 173

	return i;

finish_or_fault:
	return i ? : -EFAULT;
L
Linus Torvalds 已提交
174
}
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


/*
 * get a list of pages in an address range belonging to the specified process
 * and indicate the VMA that covers each page
 * - this is potentially dodgy as we may end incrementing the page count of a
 *   slab page or a secondary page from a compound page
 * - don't permit access to VMAs that don't support it, such as I/O mappings
 */
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
	unsigned long start, int len, int write, int force,
	struct page **pages, struct vm_area_struct **vmas)
{
	int flags = 0;

	if (write)
		flags |= GUP_FLAGS_WRITE;
	if (force)
		flags |= GUP_FLAGS_FORCE;

	return __get_user_pages(tsk, mm,
				start, len, flags,
				pages, vmas);
}
199 200
EXPORT_SYMBOL(get_user_pages);

L
Linus Torvalds 已提交
201 202 203
DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;

204
void vfree(const void *addr)
L
Linus Torvalds 已提交
205 206 207
{
	kfree(addr);
}
208
EXPORT_SYMBOL(vfree);
L
Linus Torvalds 已提交
209

A
Al Viro 已提交
210
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
L
Linus Torvalds 已提交
211 212
{
	/*
213 214
	 *  You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
	 * returns only a logical address.
L
Linus Torvalds 已提交
215
	 */
216
	return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
L
Linus Torvalds 已提交
217
}
218
EXPORT_SYMBOL(__vmalloc);
L
Linus Torvalds 已提交
219

220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
void *vmalloc_user(unsigned long size)
{
	void *ret;

	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
			PAGE_KERNEL);
	if (ret) {
		struct vm_area_struct *vma;

		down_write(&current->mm->mmap_sem);
		vma = find_vma(current->mm, (unsigned long)ret);
		if (vma)
			vma->vm_flags |= VM_USERMAP;
		up_write(&current->mm->mmap_sem);
	}

	return ret;
}
EXPORT_SYMBOL(vmalloc_user);

240
struct page *vmalloc_to_page(const void *addr)
L
Linus Torvalds 已提交
241 242 243
{
	return virt_to_page(addr);
}
244
EXPORT_SYMBOL(vmalloc_to_page);
L
Linus Torvalds 已提交
245

246
unsigned long vmalloc_to_pfn(const void *addr)
L
Linus Torvalds 已提交
247 248 249
{
	return page_to_pfn(virt_to_page(addr));
}
250
EXPORT_SYMBOL(vmalloc_to_pfn);
L
Linus Torvalds 已提交
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275

long vread(char *buf, char *addr, unsigned long count)
{
	memcpy(buf, addr, count);
	return count;
}

long vwrite(char *buf, char *addr, unsigned long count)
{
	/* Don't allow overflow */
	if ((unsigned long) addr + count < count)
		count = -(unsigned long) addr;

	memcpy(addr, buf, count);
	return(count);
}

/*
 *	vmalloc  -  allocate virtually continguos memory
 *
 *	@size:		allocation size
 *
 *	Allocate enough pages to cover @size from the page level
 *	allocator and map them into continguos kernel virtual space.
 *
276
 *	For tight control over page level allocator and protection flags
L
Linus Torvalds 已提交
277 278 279 280 281 282
 *	use __vmalloc() instead.
 */
void *vmalloc(unsigned long size)
{
       return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}
283 284 285 286 287 288 289
EXPORT_SYMBOL(vmalloc);

void *vmalloc_node(unsigned long size, int node)
{
	return vmalloc(size);
}
EXPORT_SYMBOL(vmalloc_node);
L
Linus Torvalds 已提交
290

P
Paul Mundt 已提交
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif

/**
 *	vmalloc_exec  -  allocate virtually contiguous, executable memory
 *	@size:		allocation size
 *
 *	Kernel-internal function to allocate enough pages to cover @size
 *	the page level allocator and map them into contiguous and
 *	executable kernel virtual space.
 *
 *	For tight control over page level allocator and protection flags
 *	use __vmalloc() instead.
 */

void *vmalloc_exec(unsigned long size)
{
	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
}

312 313
/**
 * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
L
Linus Torvalds 已提交
314 315 316 317 318 319 320 321 322
 *	@size:		allocation size
 *
 *	Allocate enough 32bit PA addressable pages to cover @size from the
 *	page level allocator and map them into continguos kernel virtual space.
 */
void *vmalloc_32(unsigned long size)
{
	return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
}
323 324 325 326 327 328 329 330
EXPORT_SYMBOL(vmalloc_32);

/**
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
 *	@size:		allocation size
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
331 332 333
 *
 * VM_USERMAP is set on the corresponding VMA so that subsequent calls to
 * remap_vmalloc_range() are permissible.
334 335 336
 */
void *vmalloc_32_user(unsigned long size)
{
337 338 339 340 341
	/*
	 * We'll have to sort out the ZONE_DMA bits for 64-bit,
	 * but for now this can simply use vmalloc_user() directly.
	 */
	return vmalloc_user(size);
342 343
}
EXPORT_SYMBOL(vmalloc_32_user);
L
Linus Torvalds 已提交
344 345 346 347 348 349

void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot)
{
	BUG();
	return NULL;
}
350
EXPORT_SYMBOL(vmap);
L
Linus Torvalds 已提交
351

352
void vunmap(const void *addr)
L
Linus Torvalds 已提交
353 354 355
{
	BUG();
}
356
EXPORT_SYMBOL(vunmap);
L
Linus Torvalds 已提交
357

358 359 360 361 362 363 364 365
/*
 * Implement a stub for vmalloc_sync_all() if the architecture chose not to
 * have one.
 */
void  __attribute__((weak)) vmalloc_sync_all(void)
{
}

366 367 368 369 370 371 372
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
		   struct page *page)
{
	return -EINVAL;
}
EXPORT_SYMBOL(vm_insert_page);

L
Linus Torvalds 已提交
373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
/*
 *  sys_brk() for the most part doesn't need the global kernel
 *  lock, except when an application is doing something nasty
 *  like trying to un-brk an area that has already been mapped
 *  to a regular file.  in this case, the unmapping will need
 *  to invoke file system routines that need the global lock.
 */
asmlinkage unsigned long sys_brk(unsigned long brk)
{
	struct mm_struct *mm = current->mm;

	if (brk < mm->start_brk || brk > mm->context.end_brk)
		return mm->brk;

	if (mm->brk == brk)
		return mm->brk;

	/*
	 * Always allow shrinking brk
	 */
	if (brk <= mm->brk) {
		mm->brk = brk;
		return brk;
	}

	/*
	 * Ok, looks good - let it rip.
	 */
	return mm->brk = brk;
}

#ifdef DEBUG
static void show_process_blocks(void)
{
	struct vm_list_struct *vml;

	printk("Process blocks %d:", current->pid);

	for (vml = &current->mm->context.vmlist; vml; vml = vml->next) {
		printk(" %p: %p", vml, vml->vma);
		if (vml->vma)
			printk(" (%d @%lx #%d)",
			       kobjsize((void *) vml->vma->vm_start),
			       vml->vma->vm_start,
			       atomic_read(&vml->vma->vm_usage));
		printk(vml->next ? " ->" : ".\n");
	}
}
#endif /* DEBUG */

423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
/*
 * add a VMA into a process's mm_struct in the appropriate place in the list
 * - should be called with mm->mmap_sem held writelocked
 */
static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml)
{
	struct vm_list_struct **ppv;

	for (ppv = &current->mm->context.vmlist; *ppv; ppv = &(*ppv)->next)
		if ((*ppv)->vma->vm_start > vml->vma->vm_start)
			break;

	vml->next = *ppv;
	*ppv = vml;
}

/*
 * look up the first VMA in which addr resides, NULL if none
 * - should be called with mm->mmap_sem at least held readlocked
 */
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
	struct vm_list_struct *loop, *vml;

	/* search the vm_start ordered list */
	vml = NULL;
	for (loop = mm->context.vmlist; loop; loop = loop->next) {
		if (loop->vma->vm_start > addr)
			break;
		vml = loop;
	}

	if (vml && vml->vma->vm_end > addr)
		return vml->vma;

	return NULL;
}
EXPORT_SYMBOL(find_vma);

462 463 464 465 466 467 468 469 470
/*
 * find a VMA
 * - we don't extend stack VMAs under NOMMU conditions
 */
struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
{
	return find_vma(mm, addr);
}

471 472 473 474 475
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
	return -ENOMEM;
}

476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
/*
 * look up the first VMA exactly that exactly matches addr
 * - should be called with mm->mmap_sem at least held readlocked
 */
static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
						    unsigned long addr)
{
	struct vm_list_struct *vml;

	/* search the vm_start ordered list */
	for (vml = mm->context.vmlist; vml; vml = vml->next) {
		if (vml->vma->vm_start == addr)
			return vml->vma;
		if (vml->vma->vm_start > addr)
			break;
	}

	return NULL;
}

496 497 498
/*
 * find a VMA in the global tree
 */
L
Linus Torvalds 已提交
499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517
static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
{
	struct vm_area_struct *vma;
	struct rb_node *n = nommu_vma_tree.rb_node;

	while (n) {
		vma = rb_entry(n, struct vm_area_struct, vm_rb);

		if (start < vma->vm_start)
			n = n->rb_left;
		else if (start > vma->vm_start)
			n = n->rb_right;
		else
			return vma;
	}

	return NULL;
}

518 519 520
/*
 * add a VMA in the global tree
 */
L
Linus Torvalds 已提交
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
static void add_nommu_vma(struct vm_area_struct *vma)
{
	struct vm_area_struct *pvma;
	struct address_space *mapping;
	struct rb_node **p = &nommu_vma_tree.rb_node;
	struct rb_node *parent = NULL;

	/* add the VMA to the mapping */
	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;

		flush_dcache_mmap_lock(mapping);
		vma_prio_tree_insert(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}

	/* add the VMA to the master list */
	while (*p) {
		parent = *p;
		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);

		if (vma->vm_start < pvma->vm_start) {
			p = &(*p)->rb_left;
		}
		else if (vma->vm_start > pvma->vm_start) {
			p = &(*p)->rb_right;
		}
		else {
			/* mappings are at the same address - this can only
			 * happen for shared-mem chardevs and shared file
			 * mappings backed by ramfs/tmpfs */
			BUG_ON(!(pvma->vm_flags & VM_SHARED));

			if (vma < pvma)
				p = &(*p)->rb_left;
			else if (vma > pvma)
				p = &(*p)->rb_right;
			else
				BUG();
		}
	}

	rb_link_node(&vma->vm_rb, parent, p);
	rb_insert_color(&vma->vm_rb, &nommu_vma_tree);
}

567 568 569
/*
 * delete a VMA from the global list
 */
L
Linus Torvalds 已提交
570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614
static void delete_nommu_vma(struct vm_area_struct *vma)
{
	struct address_space *mapping;

	/* remove the VMA from the mapping */
	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;

		flush_dcache_mmap_lock(mapping);
		vma_prio_tree_remove(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}

	/* remove from the master list */
	rb_erase(&vma->vm_rb, &nommu_vma_tree);
}

/*
 * determine whether a mapping should be permitted and, if so, what sort of
 * mapping we're capable of supporting
 */
static int validate_mmap_request(struct file *file,
				 unsigned long addr,
				 unsigned long len,
				 unsigned long prot,
				 unsigned long flags,
				 unsigned long pgoff,
				 unsigned long *_capabilities)
{
	unsigned long capabilities;
	unsigned long reqprot = prot;
	int ret;

	/* do the simple checks first */
	if (flags & MAP_FIXED || addr) {
		printk(KERN_DEBUG
		       "%d: Can't do fixed-address/overlay mmap of RAM\n",
		       current->pid);
		return -EINVAL;
	}

	if ((flags & MAP_TYPE) != MAP_PRIVATE &&
	    (flags & MAP_TYPE) != MAP_SHARED)
		return -EINVAL;

615
	if (!len)
L
Linus Torvalds 已提交
616 617
		return -EINVAL;

618 619 620 621 622
	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
	if (!len || len > TASK_SIZE)
		return -ENOMEM;

L
Linus Torvalds 已提交
623 624
	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
625
		return -EOVERFLOW;
L
Linus Torvalds 已提交
626 627 628 629 630 631 632 633 634 635 636 637 638 639 640

	if (file) {
		/* validate file mapping requests */
		struct address_space *mapping;

		/* files must support mmap */
		if (!file->f_op || !file->f_op->mmap)
			return -ENODEV;

		/* work out if what we've got could possibly be shared
		 * - we support chardevs that provide their own "memory"
		 * - we support files/blockdevs that are memory backed
		 */
		mapping = file->f_mapping;
		if (!mapping)
J
Josef Sipek 已提交
641
			mapping = file->f_path.dentry->d_inode->i_mapping;
L
Linus Torvalds 已提交
642 643 644 645 646 647 648 649

		capabilities = 0;
		if (mapping && mapping->backing_dev_info)
			capabilities = mapping->backing_dev_info->capabilities;

		if (!capabilities) {
			/* no explicit capabilities set, so assume some
			 * defaults */
J
Josef Sipek 已提交
650
			switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) {
L
Linus Torvalds 已提交
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
			case S_IFREG:
			case S_IFBLK:
				capabilities = BDI_CAP_MAP_COPY;
				break;

			case S_IFCHR:
				capabilities =
					BDI_CAP_MAP_DIRECT |
					BDI_CAP_READ_MAP |
					BDI_CAP_WRITE_MAP;
				break;

			default:
				return -EINVAL;
			}
		}

		/* eliminate any capabilities that we can't support on this
		 * device */
		if (!file->f_op->get_unmapped_area)
			capabilities &= ~BDI_CAP_MAP_DIRECT;
		if (!file->f_op->read)
			capabilities &= ~BDI_CAP_MAP_COPY;

		if (flags & MAP_SHARED) {
			/* do checks for writing, appending and locking */
			if ((prot & PROT_WRITE) &&
			    !(file->f_mode & FMODE_WRITE))
				return -EACCES;

J
Josef Sipek 已提交
681
			if (IS_APPEND(file->f_path.dentry->d_inode) &&
L
Linus Torvalds 已提交
682 683 684
			    (file->f_mode & FMODE_WRITE))
				return -EACCES;

J
Josef Sipek 已提交
685
			if (locks_verify_locked(file->f_path.dentry->d_inode))
L
Linus Torvalds 已提交
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
				return -EAGAIN;

			if (!(capabilities & BDI_CAP_MAP_DIRECT))
				return -ENODEV;

			if (((prot & PROT_READ)  && !(capabilities & BDI_CAP_READ_MAP))  ||
			    ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
			    ((prot & PROT_EXEC)  && !(capabilities & BDI_CAP_EXEC_MAP))
			    ) {
				printk("MAP_SHARED not completely supported on !MMU\n");
				return -EINVAL;
			}

			/* we mustn't privatise shared mappings */
			capabilities &= ~BDI_CAP_MAP_COPY;
		}
		else {
			/* we're going to read the file into private memory we
			 * allocate */
			if (!(capabilities & BDI_CAP_MAP_COPY))
				return -ENODEV;

			/* we don't permit a private writable mapping to be
			 * shared with the backing device */
			if (prot & PROT_WRITE)
				capabilities &= ~BDI_CAP_MAP_DIRECT;
		}

		/* handle executable mappings and implied executable
		 * mappings */
J
Josef Sipek 已提交
716
		if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
L
Linus Torvalds 已提交
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747
			if (prot & PROT_EXEC)
				return -EPERM;
		}
		else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
			/* handle implication of PROT_EXEC by PROT_READ */
			if (current->personality & READ_IMPLIES_EXEC) {
				if (capabilities & BDI_CAP_EXEC_MAP)
					prot |= PROT_EXEC;
			}
		}
		else if ((prot & PROT_READ) &&
			 (prot & PROT_EXEC) &&
			 !(capabilities & BDI_CAP_EXEC_MAP)
			 ) {
			/* backing file is not executable, try to copy */
			capabilities &= ~BDI_CAP_MAP_DIRECT;
		}
	}
	else {
		/* anonymous mappings are always memory backed and can be
		 * privately mapped
		 */
		capabilities = BDI_CAP_MAP_COPY;

		/* handle PROT_EXEC implication by PROT_READ */
		if ((prot & PROT_READ) &&
		    (current->personality & READ_IMPLIES_EXEC))
			prot |= PROT_EXEC;
	}

	/* allow the security API to have its say */
748
	ret = security_file_mmap(file, reqprot, prot, flags, addr, 0);
L
Linus Torvalds 已提交
749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790
	if (ret < 0)
		return ret;

	/* looks okay */
	*_capabilities = capabilities;
	return 0;
}

/*
 * we've determined that we can make the mapping, now translate what we
 * now know into VMA flags
 */
static unsigned long determine_vm_flags(struct file *file,
					unsigned long prot,
					unsigned long flags,
					unsigned long capabilities)
{
	unsigned long vm_flags;

	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
	vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
	/* vm_flags |= mm->def_flags; */

	if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
		/* attempt to share read-only copies of mapped file chunks */
		if (file && !(prot & PROT_WRITE))
			vm_flags |= VM_MAYSHARE;
	}
	else {
		/* overlay a shareable mapping on the backing device or inode
		 * if possible - used for chardevs, ramfs/tmpfs/shmfs and
		 * romfs/cramfs */
		if (flags & MAP_SHARED)
			vm_flags |= VM_MAYSHARE | VM_SHARED;
		else if ((((vm_flags & capabilities) ^ vm_flags) & BDI_CAP_VMFLAGS) == 0)
			vm_flags |= VM_MAYSHARE;
	}

	/* refuse to let anyone share private mappings with this process if
	 * it's being traced - otherwise breakpoints set in it may interfere
	 * with another untraced process
	 */
791
	if ((flags & MAP_PRIVATE) && tracehook_expect_breakpoints(current))
L
Linus Torvalds 已提交
792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843
		vm_flags &= ~VM_MAYSHARE;

	return vm_flags;
}

/*
 * set up a shared mapping on a file
 */
static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
{
	int ret;

	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
	if (ret != -ENOSYS)
		return ret;

	/* getting an ENOSYS error indicates that direct mmap isn't
	 * possible (as opposed to tried but failed) so we'll fall
	 * through to making a private copy of the data and mapping
	 * that if we can */
	return -ENODEV;
}

/*
 * set up a private mapping or an anonymous shared mapping
 */
static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
{
	void *base;
	int ret;

	/* invoke the file's mapping function so that it can keep track of
	 * shared mappings on devices or memory
	 * - VM_MAYSHARE will be set if it may attempt to share
	 */
	if (vma->vm_file) {
		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
		if (ret != -ENOSYS) {
			/* shouldn't return success if we're not sharing */
			BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE));
			return ret; /* success or a real error */
		}

		/* getting an ENOSYS error indicates that direct mmap isn't
		 * possible (as opposed to tried but failed) so we'll try to
		 * make a private copy of the data and map that instead */
	}

	/* allocate some memory to hold the mapping
	 * - note that this may not return a page-aligned address if the object
	 *   we're allocating is smaller than a page
	 */
844
	base = kmalloc(len, GFP_KERNEL|__GFP_COMP);
L
Linus Torvalds 已提交
845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913
	if (!base)
		goto enomem;

	vma->vm_start = (unsigned long) base;
	vma->vm_end = vma->vm_start + len;
	vma->vm_flags |= VM_MAPPED_COPY;

#ifdef WARN_ON_SLACK
	if (len + WARN_ON_SLACK <= kobjsize(result))
		printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n",
		       len, current->pid, kobjsize(result) - len);
#endif

	if (vma->vm_file) {
		/* read the contents of a file into the copy */
		mm_segment_t old_fs;
		loff_t fpos;

		fpos = vma->vm_pgoff;
		fpos <<= PAGE_SHIFT;

		old_fs = get_fs();
		set_fs(KERNEL_DS);
		ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
		set_fs(old_fs);

		if (ret < 0)
			goto error_free;

		/* clear the last little bit */
		if (ret < len)
			memset(base + ret, 0, len - ret);

	} else {
		/* if it's an anonymous mapping, then just clear it */
		memset(base, 0, len);
	}

	return 0;

error_free:
	kfree(base);
	vma->vm_start = 0;
	return ret;

enomem:
	printk("Allocation of length %lu from process %d failed\n",
	       len, current->pid);
	show_free_areas();
	return -ENOMEM;
}

/*
 * handle mapping creation for uClinux
 */
unsigned long do_mmap_pgoff(struct file *file,
			    unsigned long addr,
			    unsigned long len,
			    unsigned long prot,
			    unsigned long flags,
			    unsigned long pgoff)
{
	struct vm_list_struct *vml = NULL;
	struct vm_area_struct *vma = NULL;
	struct rb_node *rb;
	unsigned long capabilities, vm_flags;
	void *result;
	int ret;

914 915 916
	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

L
Linus Torvalds 已提交
917 918 919 920 921 922 923 924 925 926 927 928
	/* decide whether we should attempt the mapping, and if so what sort of
	 * mapping */
	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
				    &capabilities);
	if (ret < 0)
		return ret;

	/* we've determined that we can make the mapping, now translate what we
	 * now know into VMA flags */
	vm_flags = determine_vm_flags(file, prot, flags, capabilities);

	/* we're going to need to record the mapping if it works */
929
	vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
L
Linus Torvalds 已提交
930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946
	if (!vml)
		goto error_getting_vml;

	down_write(&nommu_vma_sem);

	/* if we want to share, we need to check for VMAs created by other
	 * mmap() calls that overlap with our proposed mapping
	 * - we can only share with an exact match on most regular files
	 * - shared mappings on character devices and memory backed files are
	 *   permitted to overlap inexactly as far as we are concerned for in
	 *   these cases, sharing is handled in the driver or filesystem rather
	 *   than here
	 */
	if (vm_flags & VM_MAYSHARE) {
		unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		unsigned long vmpglen;

947 948 949 950 951
		/* suppress VMA sharing for shared regions */
		if (vm_flags & VM_SHARED &&
		    capabilities & BDI_CAP_MAP_DIRECT)
			goto dont_share_VMAs;

L
Linus Torvalds 已提交
952 953 954 955 956 957 958
		for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) {
			vma = rb_entry(rb, struct vm_area_struct, vm_rb);

			if (!(vma->vm_flags & VM_MAYSHARE))
				continue;

			/* search for overlapping mappings on the same file */
J
Josef Sipek 已提交
959
			if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode)
L
Linus Torvalds 已提交
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984
				continue;

			if (vma->vm_pgoff >= pgoff + pglen)
				continue;

			vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1;
			vmpglen >>= PAGE_SHIFT;
			if (pgoff >= vma->vm_pgoff + vmpglen)
				continue;

			/* handle inexactly overlapping matches between mappings */
			if (vma->vm_pgoff != pgoff || vmpglen != pglen) {
				if (!(capabilities & BDI_CAP_MAP_DIRECT))
					goto sharing_violation;
				continue;
			}

			/* we've found a VMA we can share */
			atomic_inc(&vma->vm_usage);

			vml->vma = vma;
			result = (void *) vma->vm_start;
			goto shared;
		}

985
	dont_share_VMAs:
L
Linus Torvalds 已提交
986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
		vma = NULL;

		/* obtain the address at which to make a shared mapping
		 * - this is the hook for quasi-memory character devices to
		 *   tell us the location of a shared mapping
		 */
		if (file && file->f_op->get_unmapped_area) {
			addr = file->f_op->get_unmapped_area(file, addr, len,
							     pgoff, flags);
			if (IS_ERR((void *) addr)) {
				ret = addr;
				if (ret != (unsigned long) -ENOSYS)
					goto error;

				/* the driver refused to tell us where to site
				 * the mapping so we'll have to attempt to copy
				 * it */
				ret = (unsigned long) -ENODEV;
				if (!(capabilities & BDI_CAP_MAP_COPY))
					goto error;

				capabilities &= ~BDI_CAP_MAP_DIRECT;
			}
		}
	}

	/* we're going to need a VMA struct as well */
1013
	vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
L
Linus Torvalds 已提交
1014 1015 1016 1017 1018
	if (!vma)
		goto error_getting_vma;

	INIT_LIST_HEAD(&vma->anon_vma_node);
	atomic_set(&vma->vm_usage, 1);
M
Matt Helsley 已提交
1019
	if (file) {
L
Linus Torvalds 已提交
1020
		get_file(file);
M
Matt Helsley 已提交
1021 1022 1023 1024 1025
		if (vm_flags & VM_EXECUTABLE) {
			added_exe_file_vma(current->mm);
			vma->vm_mm = current->mm;
		}
	}
L
Linus Torvalds 已提交
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
	vma->vm_file	= file;
	vma->vm_flags	= vm_flags;
	vma->vm_start	= addr;
	vma->vm_end	= addr + len;
	vma->vm_pgoff	= pgoff;

	vml->vma = vma;

	/* set up the mapping */
	if (file && vma->vm_flags & VM_SHARED)
		ret = do_mmap_shared_file(vma, len);
	else
		ret = do_mmap_private(vma, len);
	if (ret < 0)
		goto error;

	/* okay... we have a mapping; now we have to register it */
	result = (void *) vma->vm_start;

	if (vma->vm_flags & VM_MAPPED_COPY) {
		realalloc += kobjsize(result);
		askedalloc += len;
	}

	realalloc += kobjsize(vma);
	askedalloc += sizeof(*vma);

	current->mm->total_vm += len >> PAGE_SHIFT;

	add_nommu_vma(vma);

 shared:
	realalloc += kobjsize(vml);
	askedalloc += sizeof(*vml);

1061
	add_vma_to_mm(current->mm, vml);
L
Linus Torvalds 已提交
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079

	up_write(&nommu_vma_sem);

	if (prot & PROT_EXEC)
		flush_icache_range((unsigned long) result,
				   (unsigned long) result + len);

#ifdef DEBUG
	printk("do_mmap:\n");
	show_process_blocks();
#endif

	return (unsigned long) result;

 error:
	up_write(&nommu_vma_sem);
	kfree(vml);
	if (vma) {
M
Matt Helsley 已提交
1080
		if (vma->vm_file) {
1081
			fput(vma->vm_file);
M
Matt Helsley 已提交
1082 1083 1084
			if (vma->vm_flags & VM_EXECUTABLE)
				removed_exe_file_vma(vma->vm_mm);
		}
L
Linus Torvalds 已提交
1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
		kfree(vma);
	}
	return ret;

 sharing_violation:
	up_write(&nommu_vma_sem);
	printk("Attempt to share mismatched mappings\n");
	kfree(vml);
	return -EINVAL;

 error_getting_vma:
	up_write(&nommu_vma_sem);
	kfree(vml);
1098
	printk("Allocation of vma for %lu byte allocation from process %d failed\n",
L
Linus Torvalds 已提交
1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
	       len, current->pid);
	show_free_areas();
	return -ENOMEM;

 error_getting_vml:
	printk("Allocation of vml for %lu byte allocation from process %d failed\n",
	       len, current->pid);
	show_free_areas();
	return -ENOMEM;
}
1109
EXPORT_SYMBOL(do_mmap_pgoff);
L
Linus Torvalds 已提交
1110 1111 1112 1113

/*
 * handle mapping disposal for uClinux
 */
M
Matt Helsley 已提交
1114
static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
L
Linus Torvalds 已提交
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
{
	if (vma) {
		down_write(&nommu_vma_sem);

		if (atomic_dec_and_test(&vma->vm_usage)) {
			delete_nommu_vma(vma);

			if (vma->vm_ops && vma->vm_ops->close)
				vma->vm_ops->close(vma);

			/* IO memory and memory shared directly out of the pagecache from
			 * ramfs/tmpfs mustn't be released here */
			if (vma->vm_flags & VM_MAPPED_COPY) {
				realalloc -= kobjsize((void *) vma->vm_start);
				askedalloc -= vma->vm_end - vma->vm_start;
				kfree((void *) vma->vm_start);
			}

			realalloc -= kobjsize(vma);
			askedalloc -= sizeof(*vma);

M
Matt Helsley 已提交
1136
			if (vma->vm_file) {
L
Linus Torvalds 已提交
1137
				fput(vma->vm_file);
M
Matt Helsley 已提交
1138 1139 1140
				if (vma->vm_flags & VM_EXECUTABLE)
					removed_exe_file_vma(mm);
			}
L
Linus Torvalds 已提交
1141 1142 1143 1144 1145 1146 1147
			kfree(vma);
		}

		up_write(&nommu_vma_sem);
	}
}

1148 1149 1150 1151 1152
/*
 * release a mapping
 * - under NOMMU conditions the parameters must match exactly to the mapping to
 *   be removed
 */
L
Linus Torvalds 已提交
1153 1154 1155 1156 1157 1158 1159 1160 1161
int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
{
	struct vm_list_struct *vml, **parent;
	unsigned long end = addr + len;

#ifdef DEBUG
	printk("do_munmap:\n");
#endif

1162 1163 1164
	for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) {
		if ((*parent)->vma->vm_start > addr)
			break;
L
Linus Torvalds 已提交
1165
		if ((*parent)->vma->vm_start == addr &&
1166
		    ((len == 0) || ((*parent)->vma->vm_end == end)))
L
Linus Torvalds 已提交
1167
			goto found;
1168
	}
L
Linus Torvalds 已提交
1169 1170 1171 1172 1173 1174 1175 1176

	printk("munmap of non-mmaped memory by process %d (%s): %p\n",
	       current->pid, current->comm, (void *) addr);
	return -EINVAL;

 found:
	vml = *parent;

M
Matt Helsley 已提交
1177
	put_vma(mm, vml->vma);
L
Linus Torvalds 已提交
1178 1179 1180 1181 1182

	*parent = vml->next;
	realalloc -= kobjsize(vml);
	askedalloc -= sizeof(*vml);
	kfree(vml);
1183 1184

	update_hiwater_vm(mm);
L
Linus Torvalds 已提交
1185 1186 1187 1188 1189 1190 1191 1192
	mm->total_vm -= len >> PAGE_SHIFT;

#ifdef DEBUG
	show_process_blocks();
#endif

	return 0;
}
1193
EXPORT_SYMBOL(do_munmap);
L
Linus Torvalds 已提交
1194

1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208
asmlinkage long sys_munmap(unsigned long addr, size_t len)
{
	int ret;
	struct mm_struct *mm = current->mm;

	down_write(&mm->mmap_sem);
	ret = do_munmap(mm, addr, len);
	up_write(&mm->mmap_sem);
	return ret;
}

/*
 * Release all mappings
 */
L
Linus Torvalds 已提交
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221
void exit_mmap(struct mm_struct * mm)
{
	struct vm_list_struct *tmp;

	if (mm) {
#ifdef DEBUG
		printk("Exit_mmap:\n");
#endif

		mm->total_vm = 0;

		while ((tmp = mm->context.vmlist)) {
			mm->context.vmlist = tmp->next;
M
Matt Helsley 已提交
1222
			put_vma(mm, tmp->vma);
L
Linus Torvalds 已提交
1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240

			realalloc -= kobjsize(tmp);
			askedalloc -= sizeof(*tmp);
			kfree(tmp);
		}

#ifdef DEBUG
		show_process_blocks();
#endif
	}
}

unsigned long do_brk(unsigned long addr, unsigned long len)
{
	return -ENOMEM;
}

/*
1241 1242
 * expand (or shrink) an existing mapping, potentially moving it at the same
 * time (controlled by the MREMAP_MAYMOVE flag and available VM space)
L
Linus Torvalds 已提交
1243
 *
1244 1245 1246
 * under NOMMU conditions, we only permit changing a mapping's size, and only
 * as long as it stays within the hole allocated by the kmalloc() call in
 * do_mmap_pgoff() and the block is not shareable
L
Linus Torvalds 已提交
1247
 *
1248
 * MREMAP_FIXED is not supported under NOMMU conditions
L
Linus Torvalds 已提交
1249 1250 1251 1252 1253
 */
unsigned long do_mremap(unsigned long addr,
			unsigned long old_len, unsigned long new_len,
			unsigned long flags, unsigned long new_addr)
{
1254
	struct vm_area_struct *vma;
L
Linus Torvalds 已提交
1255 1256 1257 1258 1259 1260 1261 1262

	/* insanity checks first */
	if (new_len == 0)
		return (unsigned long) -EINVAL;

	if (flags & MREMAP_FIXED && new_addr != addr)
		return (unsigned long) -EINVAL;

1263 1264 1265
	vma = find_vma_exact(current->mm, addr);
	if (!vma)
		return (unsigned long) -EINVAL;
L
Linus Torvalds 已提交
1266

1267
	if (vma->vm_end != vma->vm_start + old_len)
L
Linus Torvalds 已提交
1268 1269
		return (unsigned long) -EFAULT;

1270
	if (vma->vm_flags & VM_MAYSHARE)
L
Linus Torvalds 已提交
1271 1272 1273 1274 1275 1276
		return (unsigned long) -EPERM;

	if (new_len > kobjsize((void *) addr))
		return (unsigned long) -ENOMEM;

	/* all checks complete - do it */
1277
	vma->vm_end = vma->vm_start + new_len;
L
Linus Torvalds 已提交
1278 1279 1280 1281

	askedalloc -= old_len;
	askedalloc += new_len;

1282 1283
	return vma->vm_start;
}
1284
EXPORT_SYMBOL(do_mremap);
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295

asmlinkage unsigned long sys_mremap(unsigned long addr,
	unsigned long old_len, unsigned long new_len,
	unsigned long flags, unsigned long new_addr)
{
	unsigned long ret;

	down_write(&current->mm->mmap_sem);
	ret = do_mremap(addr, old_len, new_len, flags, new_addr);
	up_write(&current->mm->mmap_sem);
	return ret;
L
Linus Torvalds 已提交
1296 1297
}

1298
struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
1299
			unsigned int foll_flags)
L
Linus Torvalds 已提交
1300 1301 1302 1303 1304 1305 1306
{
	return NULL;
}

int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
		unsigned long to, unsigned long size, pgprot_t prot)
{
1307 1308
	vma->vm_start = vma->vm_pgoff << PAGE_SHIFT;
	return 0;
L
Linus Torvalds 已提交
1309
}
1310
EXPORT_SYMBOL(remap_pfn_range);
L
Linus Torvalds 已提交
1311

1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
			unsigned long pgoff)
{
	unsigned int size = vma->vm_end - vma->vm_start;

	if (!(vma->vm_flags & VM_USERMAP))
		return -EINVAL;

	vma->vm_start = (unsigned long)(addr + (pgoff << PAGE_SHIFT));
	vma->vm_end = vma->vm_start + size;

	return 0;
}
EXPORT_SYMBOL(remap_vmalloc_range);

L
Linus Torvalds 已提交
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
{
}

unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
	unsigned long len, unsigned long pgoff, unsigned long flags)
{
	return -ENOMEM;
}

1337
void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
L
Linus Torvalds 已提交
1338 1339 1340 1341 1342 1343 1344 1345
{
}

void unmap_mapping_range(struct address_space *mapping,
			 loff_t const holebegin, loff_t const holelen,
			 int even_cows)
{
}
1346
EXPORT_SYMBOL(unmap_mapping_range);
L
Linus Torvalds 已提交
1347

1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
/*
 * ask for an unmapped area at which to create a mapping on a file
 */
unsigned long get_unmapped_area(struct file *file, unsigned long addr,
				unsigned long len, unsigned long pgoff,
				unsigned long flags)
{
	unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
				  unsigned long, unsigned long);

	get_area = current->mm->get_unmapped_area;
	if (file && file->f_op && file->f_op->get_unmapped_area)
		get_area = file->f_op->get_unmapped_area;

	if (!get_area)
		return -ENOSYS;

	return get_area(file, addr, len, pgoff, flags);
}
EXPORT_SYMBOL(get_unmapped_area);

L
Linus Torvalds 已提交
1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
/*
 * Check that a process has enough memory to allocate a new virtual
 * mapping. 0 means there is enough memory for the allocation to
 * succeed and -ENOMEM implies there is not.
 *
 * We currently support three overcommit policies, which are set via the
 * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting
 *
 * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
 * Additional code 2002 Jul 20 by Robert Love.
 *
 * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
 *
 * Note this is a helper function intended to be used by LSMs which
 * wish to use this logic.
 */
1385
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
L
Linus Torvalds 已提交
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
{
	unsigned long free, allowed;

	vm_acct_memory(pages);

	/*
	 * Sometimes we want to use more memory than we have
	 */
	if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
		return 0;

	if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
		unsigned long n;

1400
		free = global_page_state(NR_FILE_PAGES);
L
Linus Torvalds 已提交
1401 1402 1403 1404 1405 1406 1407 1408
		free += nr_swap_pages;

		/*
		 * Any slabs which are created with the
		 * SLAB_RECLAIM_ACCOUNT flag claim to have contents
		 * which are reclaimable, under pressure.  The dentry
		 * cache and most inode caches should fall into this
		 */
1409
		free += global_page_state(NR_SLAB_RECLAIMABLE);
L
Linus Torvalds 已提交
1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424

		/*
		 * Leave the last 3% for root
		 */
		if (!cap_sys_admin)
			free -= free / 32;

		if (free > pages)
			return 0;

		/*
		 * nr_free_pages() is very expensive on large systems,
		 * only call if we're about to fail.
		 */
		n = nr_free_pages();
1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436

		/*
		 * Leave reserved pages. The pages are not for anonymous pages.
		 */
		if (n <= totalreserve_pages)
			goto error;
		else
			n -= totalreserve_pages;

		/*
		 * Leave the last 3% for root
		 */
L
Linus Torvalds 已提交
1437 1438 1439 1440 1441 1442
		if (!cap_sys_admin)
			n -= n / 32;
		free += n;

		if (free > pages)
			return 0;
1443 1444

		goto error;
L
Linus Torvalds 已提交
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
	}

	allowed = totalram_pages * sysctl_overcommit_ratio / 100;
	/*
	 * Leave the last 3% for root
	 */
	if (!cap_sys_admin)
		allowed -= allowed / 32;
	allowed += total_swap_pages;

	/* Don't let a single process grow too big:
	   leave 3% of the size of this process for other processes */
	allowed -= current->mm->total_vm / 32;

1459 1460 1461 1462
	/*
	 * cast `allowed' as a signed long because vm_committed_space
	 * sometimes has a negative value
	 */
A
Alan Cox 已提交
1463
	if (atomic_long_read(&vm_committed_space) < (long)allowed)
L
Linus Torvalds 已提交
1464
		return 0;
1465
error:
L
Linus Torvalds 已提交
1466 1467 1468 1469 1470 1471 1472 1473 1474
	vm_unacct_memory(pages);

	return -ENOMEM;
}

int in_gate_area_no_task(unsigned long addr)
{
	return 0;
}
1475

N
Nick Piggin 已提交
1476
int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
1477 1478
{
	BUG();
N
Nick Piggin 已提交
1479
	return 0;
1480
}
1481
EXPORT_SYMBOL(filemap_fault);
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501

/*
 * Access another process' address space.
 * - source/target buffer must be kernel space
 */
int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm;

	if (addr + len < addr)
		return 0;

	mm = get_task_mm(tsk);
	if (!mm)
		return 0;

	down_read(&mm->mmap_sem);

	/* the access must start within one of the target process's mappings */
1502 1503
	vma = find_vma(mm, addr);
	if (vma) {
1504 1505 1506 1507 1508
		/* don't overrun this mapping */
		if (addr + len >= vma->vm_end)
			len = vma->vm_end - addr;

		/* only read or write mappings where it is permitted */
1509
		if (write && vma->vm_flags & VM_MAYWRITE)
1510
			len -= copy_to_user((void *) addr, buf, len);
1511
		else if (!write && vma->vm_flags & VM_MAYREAD)
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522
			len -= copy_from_user(buf, (void *) addr, len);
		else
			len = 0;
	} else {
		len = 0;
	}

	up_read(&mm->mmap_sem);
	mmput(mm);
	return len;
}