mmap.c

	/* Clear old maps */
	error = -ENOMEM;
munmap_back:
	vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	if (vma && vma->vm_start < addr + len) {
		if (do_munmap(mm, addr, len))
			return -ENOMEM;
		goto munmap_back;
	}

	/* Check against address space limit. */
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
		return -ENOMEM;

	if (accountable && (!(flags & MAP_NORESERVE) ||
			    sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
		if (vm_flags & VM_SHARED) {
			/* Check memory availability in shmem_file_setup? */
			vm_flags |= VM_ACCOUNT;
		} else if (vm_flags & VM_WRITE) {
			/*
			 * Private writable mapping: check memory availability
			 */
			charged = len >> PAGE_SHIFT;
			if (security_vm_enough_memory(charged))
				return -ENOMEM;
			vm_flags |= VM_ACCOUNT;
		}
	}

	/*
	 * Can we just expand an old private anonymous mapping?
	 * The VM_SHARED test is necessary because shmem_zero_setup
	 * will create the file object for a shared anonymous map below.
	 */
	if (!file && !(vm_flags & VM_SHARED) &&
	    vma_merge(mm, prev, addr, addr + len, vm_flags,
					NULL, NULL, pgoff, NULL))
		goto out;

	/*
	 * Determine the object being mapped and call the appropriate
	 * specific mapper. the address has already been validated, but
	 * not unmapped, but the maps are removed from the list.
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!vma) {
		error = -ENOMEM;
		goto unacct_error;
	}
	memset(vma, 0, sizeof(*vma));

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = vm_flags;
	vma->vm_page_prot = protection_map[vm_flags & 0x0f];
	vma->vm_pgoff = pgoff;

	if (file) {
		error = -EINVAL;
		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
			goto free_vma;
		if (vm_flags & VM_DENYWRITE) {
			error = deny_write_access(file);
			if (error)
				goto free_vma;
			correct_wcount = 1;
		}
		vma->vm_file = file;
		get_file(file);
		error = file->f_op->mmap(file, vma);
		if (error)
			goto unmap_and_free_vma;
	} else if (vm_flags & VM_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
	 * that memory reservation must be checked; but that reservation
	 * belongs to shared memory object, not to vma: so now clear it.
	 */
	if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT))
		vma->vm_flags &= ~VM_ACCOUNT;

	/* Can addr have changed??
	 *
	 * Answer: Yes, several device drivers can do it in their
	 *         f_op->mmap method. -DaveM
	 */
	addr = vma->vm_start;
	pgoff = vma->vm_pgoff;
	vm_flags = vma->vm_flags;

	if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
		file = vma->vm_file;
		vma_link(mm, vma, prev, rb_link, rb_parent);
		if (correct_wcount)
			atomic_inc(&inode->i_writecount);
	} else {
		if (file) {
			if (correct_wcount)
				atomic_inc(&inode->i_writecount);
			fput(file);
		}
		mpol_free(vma_policy(vma));
		kmem_cache_free(vm_area_cachep, vma);
	}
out:	
	mm->total_vm += len >> PAGE_SHIFT;
	__vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
	if (vm_flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	if (flags & MAP_POPULATE) {
		up_write(&mm->mmap_sem);
		sys_remap_file_pages(addr, len, 0,
					pgoff, flags & MAP_NONBLOCK);
		down_write(&mm->mmap_sem);
	}
	return addr;

unmap_and_free_vma:
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
	vma->vm_file = NULL;
	fput(file);

	/* Undo any partial mapping done by a device driver. */
	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
	charged = 0;
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
unacct_error:
	if (charged)
		vm_unacct_memory(charged);
	return error;
}

EXPORT_SYMBOL(do_mmap_pgoff);

/* Get an address range which is currently unmapped.
 * For shmat() with addr=0.
 *
 * Ugly calling convention alert:
 * Return value with the low bits set means error value,
 * ie
 *	if (ret & ~PAGE_MASK)
 *		error = ret;
 *
 * This function "knows" that -ENOMEM has the bits set.
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long start_addr;

	if (len > TASK_SIZE)
		return -ENOMEM;

	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}
	start_addr = addr = mm->free_area_cache;

full_search:
	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr) {
			/*
			 * Start a new search - just in case we missed
			 * some holes.
			 */
			if (start_addr != TASK_UNMAPPED_BASE) {
				start_addr = addr = TASK_UNMAPPED_BASE;
				goto full_search;
			}
			return -ENOMEM;
		}
		if (!vma || addr + len <= vma->vm_start) {
			/*
			 * Remember the place where we stopped the search:
			 */
			mm->free_area_cache = addr + len;
			return addr;
		}
		addr = vma->vm_end;
	}
}
#endif	

void arch_unmap_area(struct vm_area_struct *area)
{
	/*
	 * Is this a new hole at the lowest possible address?
	 */
	if (area->vm_start >= TASK_UNMAPPED_BASE &&
			area->vm_start < area->vm_mm->free_area_cache)
		area->vm_mm->free_area_cache = area->vm_start;
}

/*
 * This mmap-allocator allocates new areas top-down from below the
 * stack's low limit (the base):
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
			  const unsigned long len, const unsigned long pgoff,
			  const unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	unsigned long addr = addr0;

	/* requested length too big for entire address space */
	if (len > TASK_SIZE)
		return -ENOMEM;

	/* requesting a specific address */
	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
				(!vma || addr + len <= vma->vm_start))
			return addr;
	}

	/* either no address requested or can't fit in requested address hole */
	addr = mm->free_area_cache;

	/* make sure it can fit in the remaining address space */
	if (addr >= len) {
		vma = find_vma(mm, addr-len);
		if (!vma || addr <= vma->vm_start)
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr-len);
	}

	addr = mm->mmap_base-len;

	do {
		/*
		 * Lookup failure means no vma is above this address,
		 * else if new region fits below vma->vm_start,
		 * return with success:
		 */
		vma = find_vma(mm, addr);
		if (!vma || addr+len <= vma->vm_start)
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr);

		/* try just below the current vma->vm_start */
		addr = vma->vm_start-len;
	} while (len <= vma->vm_start);

	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
	mm->free_area_cache = TASK_UNMAPPED_BASE;
	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
	/*
	 * Restore the topdown base:
	 */
	mm->free_area_cache = mm->mmap_base;

	return addr;
}
#endif

void arch_unmap_area_topdown(struct vm_area_struct *area)
{
	/*
	 * Is this a new hole at the highest possible address?
	 */
	if (area->vm_end > area->vm_mm->free_area_cache)
		area->vm_mm->free_area_cache = area->vm_end;

	/* dont allow allocations above current base */
	if (area->vm_mm->free_area_cache > area->vm_mm->mmap_base)
		area->vm_mm->free_area_cache = area->vm_mm->mmap_base;
}

unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
	if (flags & MAP_FIXED) {
		unsigned long ret;

		if (addr > TASK_SIZE - len)
			return -ENOMEM;
		if (addr & ~PAGE_MASK)
			return -EINVAL;
		if (file && is_file_hugepages(file))  {
			/*
			 * Check if the given range is hugepage aligned, and
			 * can be made suitable for hugepages.
			 */
			ret = prepare_hugepage_range(addr, len);
		} else {
			/*
			 * Ensure that a normal request is not falling in a
			 * reserved hugepage range.  For some archs like IA-64,
			 * there is a separate region for hugepages.
			 */
			ret = is_hugepage_only_range(current->mm, addr, len);
		}
		if (ret)
			return -EINVAL;
		return addr;
	}

	if (file && file->f_op && file->f_op->get_unmapped_area)
		return file->f_op->get_unmapped_area(file, addr, len,
						pgoff, flags);

	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
}

EXPORT_SYMBOL(get_unmapped_area);

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct *vma = NULL;

	if (mm) {
		/* Check the cache first. */
		/* (Cache hit rate is typically around 35%.) */
		vma = mm->mmap_cache;
		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
			struct rb_node * rb_node;

			rb_node = mm->mm_rb.rb_node;
			vma = NULL;

			while (rb_node) {
				struct vm_area_struct * vma_tmp;

				vma_tmp = rb_entry(rb_node,
						struct vm_area_struct, vm_rb);

				if (vma_tmp->vm_end > addr) {
					vma = vma_tmp;
					if (vma_tmp->vm_start <= addr)
						break;
					rb_node = rb_node->rb_left;
				} else
					rb_node = rb_node->rb_right;
			}
			if (vma)
				mm->mmap_cache = vma;
		}
	}
	return vma;
}

EXPORT_SYMBOL(find_vma);

/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */
struct vm_area_struct *
find_vma_prev(struct mm_struct *mm, unsigned long addr,
			struct vm_area_struct **pprev)
{
	struct vm_area_struct *vma = NULL, *prev = NULL;
	struct rb_node * rb_node;
	if (!mm)
		goto out;

	/* Guard against addr being lower than the first VMA */
	vma = mm->mmap;

	/* Go through the RB tree quickly. */
	rb_node = mm->mm_rb.rb_node;

	while (rb_node) {
		struct vm_area_struct *vma_tmp;
		vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);

		if (addr < vma_tmp->vm_end) {
			rb_node = rb_node->rb_left;
		} else {
			prev = vma_tmp;
			if (!prev->vm_next || (addr < prev->vm_next->vm_end))
				break;
			rb_node = rb_node->rb_right;
		}
	}

out:
	*pprev = prev;
	return prev ? prev->vm_next : vma;
}

/*
 * Verify that the stack growth is acceptable and
 * update accounting. This is shared with both the
 * grow-up and grow-down cases.
 */
static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, unsigned long grow)
{
	struct mm_struct *mm = vma->vm_mm;
	struct rlimit *rlim = current->signal->rlim;

	/* address space limit tests */
	if (!may_expand_vm(mm, grow))
		return -ENOMEM;

	/* Stack limit test */
	if (size > rlim[RLIMIT_STACK].rlim_cur)
		return -ENOMEM;

	/* mlock limit tests */
	if (vma->vm_flags & VM_LOCKED) {
		unsigned long locked;
		unsigned long limit;
		locked = mm->locked_vm + grow;
		limit = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
		if (locked > limit && !capable(CAP_IPC_LOCK))
			return -ENOMEM;
	}

	/*
	 * Overcommit..  This must be the final test, as it will
	 * update security statistics.
	 */
	if (security_vm_enough_memory(grow))
		return -ENOMEM;

	/* Ok, everything looks good - let it rip */
	mm->total_vm += grow;
	if (vma->vm_flags & VM_LOCKED)
		mm->locked_vm += grow;
	__vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
	return 0;
}

#ifdef CONFIG_STACK_GROWSUP
/*
 * vma is the first one with address > vma->vm_end.  Have to extend vma.
 */
int expand_stack(struct vm_area_struct * vma, unsigned long address)
{
	int error;

	if (!(vma->vm_flags & VM_GROWSUP))
		return -EFAULT;

	/*
	 * We must make sure the anon_vma is allocated
	 * so that the anon_vma locking is not a noop.
	 */
	if (unlikely(anon_vma_prepare(vma)))
		return -ENOMEM;
	anon_vma_lock(vma);

	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_sem in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */
	address += 4 + PAGE_SIZE - 1;
	address &= PAGE_MASK;
	error = 0;

	/* Somebody else might have raced and expanded it already */
	if (address > vma->vm_end) {
		unsigned long size, grow;

		size = address - vma->vm_start;
		grow = (address - vma->vm_end) >> PAGE_SHIFT;

		error = acct_stack_growth(vma, size, grow);
		if (!error)
			vma->vm_end = address;
	}
	anon_vma_unlock(vma);
	return error;
}

struct vm_area_struct *
find_extend_vma(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma, *prev;

	addr &= PAGE_MASK;
	vma = find_vma_prev(mm, addr, &prev);
	if (vma && (vma->vm_start <= addr))
		return vma;
	if (!prev || expand_stack(prev, addr))
		return NULL;
	if (prev->vm_flags & VM_LOCKED) {
		make_pages_present(addr, prev->vm_end);
	}
	return prev;
}
#else
/*
 * vma is the first one with address < vma->vm_start.  Have to extend vma.
 */
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
	int error;

	/*
	 * We must make sure the anon_vma is allocated
	 * so that the anon_vma locking is not a noop.
	 */
	if (unlikely(anon_vma_prepare(vma)))
		return -ENOMEM;
	anon_vma_lock(vma);

	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_sem in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */
	address &= PAGE_MASK;
	error = 0;

	/* Somebody else might have raced and expanded it already */
	if (address < vma->vm_start) {
		unsigned long size, grow;

		size = vma->vm_end - address;
		grow = (vma->vm_start - address) >> PAGE_SHIFT;

		error = acct_stack_growth(vma, size, grow);
		if (!error) {
			vma->vm_start = address;
			vma->vm_pgoff -= grow;
		}
	}
	anon_vma_unlock(vma);
	return error;
}

struct vm_area_struct *
find_extend_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct * vma;
	unsigned long start;

	addr &= PAGE_MASK;
	vma = find_vma(mm,addr);
	if (!vma)
		return NULL;
	if (vma->vm_start <= addr)
		return vma;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		return NULL;
	start = vma->vm_start;
	if (expand_stack(vma, addr))
		return NULL;
	if (vma->vm_flags & VM_LOCKED) {
		make_pages_present(addr, start);
	}
	return vma;
}
#endif

/* Normal function to fix up a mapping
 * This function is the default for when an area has no specific
 * function.  This may be used as part of a more specific routine.
 *
 * By the time this function is called, the area struct has been
 * removed from the process mapping list.
 */
static void unmap_vma(struct mm_struct *mm, struct vm_area_struct *area)
{
	size_t len = area->vm_end - area->vm_start;

	area->vm_mm->total_vm -= len >> PAGE_SHIFT;
	if (area->vm_flags & VM_LOCKED)
		area->vm_mm->locked_vm -= len >> PAGE_SHIFT;
	vm_stat_unaccount(area);
	area->vm_mm->unmap_area(area);
	remove_vm_struct(area);
}

/*
 * Update the VMA and inode share lists.
 *
 * Ok - we have the memory areas we should free on the 'free' list,
 * so release them, and do the vma updates.
 */
static void unmap_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
{
	do {
		struct vm_area_struct *next = vma->vm_next;
		unmap_vma(mm, vma);
		vma = next;
	} while (vma);
	validate_mm(mm);
}

/*
 * Get rid of page table information in the indicated region.
 *
 * Called with the page table lock held.
 */
static void unmap_region(struct mm_struct *mm,
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		unsigned long start, unsigned long end)
{
	struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
	struct mmu_gather *tlb;
	unsigned long nr_accounted = 0;

	lru_add_drain();
	spin_lock(&mm->page_table_lock);
	tlb = tlb_gather_mmu(mm, 0);
	unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
	vm_unacct_memory(nr_accounted);
	free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
				 next? next->vm_start: 0);
	tlb_finish_mmu(tlb, start, end);
	spin_unlock(&mm->page_table_lock);
}

/*
 * Create a list of vma's touched by the unmap, removing them from the mm's
 * vma list as we go..
 */
static void
detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
	struct vm_area_struct *prev, unsigned long end)
{
	struct vm_area_struct **insertion_point;
	struct vm_area_struct *tail_vma = NULL;

	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
	do {
		rb_erase(&vma->vm_rb, &mm->mm_rb);
		mm->map_count--;
		tail_vma = vma;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
	*insertion_point = vma;
	tail_vma->vm_next = NULL;
	mm->mmap_cache = NULL;		/* Kill the cache. */
}

/*
 * Split a vma into two pieces at address 'addr', a new vma is allocated
 * either for the first part or the the tail.
 */
int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
	      unsigned long addr, int new_below)
{
	struct mempolicy *pol;
	struct vm_area_struct *new;

	if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK))
		return -EINVAL;

	if (mm->map_count >= sysctl_max_map_count)
		return -ENOMEM;

	new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!new)
		return -ENOMEM;

	/* most fields are the same, copy all, and then fixup */
	*new = *vma;

	if (new_below)
		new->vm_end = addr;
	else {
		new->vm_start = addr;
		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
	}

	pol = mpol_copy(vma_policy(vma));
	if (IS_ERR(pol)) {
		kmem_cache_free(vm_area_cachep, new);
		return PTR_ERR(pol);
	}
	vma_set_policy(new, pol);

	if (new->vm_file)
		get_file(new->vm_file);

	if (new->vm_ops && new->vm_ops->open)
		new->vm_ops->open(new);

	if (new_below)
		vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
			((addr - new->vm_start) >> PAGE_SHIFT), new);
	else
		vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);

	return 0;
}

/* Munmap is split into 2 main parts -- this part which finds
 * what needs doing, and the areas themselves, which do the
 * work.  This now handles partial unmappings.
 * Jeremy Fitzhardinge <jeremy@goop.org>
 */
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
{
	unsigned long end;
	struct vm_area_struct *vma, *prev, *last;

	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
		return -EINVAL;

	if ((len = PAGE_ALIGN(len)) == 0)
		return -EINVAL;

	/* Find the first overlapping VMA */
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
		return 0;
	/* we have  start < vma->vm_end  */

	/* if it doesn't overlap, we have nothing.. */
	end = start + len;
	if (vma->vm_start >= end)
		return 0;

	/*
	 * If we need to split any vma, do it now to save pain later.
	 *
	 * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially
	 * unmapped vm_area_struct will remain in use: so lower split_vma
	 * places tmp vma above, and higher split_vma places tmp vma below.
	 */
	if (start > vma->vm_start) {
		int error = split_vma(mm, vma, start, 0);
		if (error)
			return error;
		prev = vma;
	}

	/* Does it split the last one? */
	last = find_vma(mm, end);
	if (last && end > last->vm_start) {
		int error = split_vma(mm, last, end, 1);
		if (error)
			return error;
	}
	vma = prev? prev->vm_next: mm->mmap;

	/*
	 * Remove the vma's, and unmap the actual pages
	 */
	detach_vmas_to_be_unmapped(mm, vma, prev, end);
	unmap_region(mm, vma, prev, start, end);

	/* Fix up all other VM information */
	unmap_vma_list(mm, vma);

	return 0;
}

EXPORT_SYMBOL(do_munmap);

asmlinkage long sys_munmap(unsigned long addr, size_t len)
{
	int ret;
	struct mm_struct *mm = current->mm;

	profile_munmap(addr);

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

static inline void verify_mm_writelocked(struct mm_struct *mm)
{
#ifdef CONFIG_DEBUG_KERNEL
	if (unlikely(down_read_trylock(&mm->mmap_sem))) {
		WARN_ON(1);
		up_read(&mm->mmap_sem);
	}
#endif
}

/*
 *  this is really a simplified "do_mmap".  it only handles
 *  anonymous maps.  eventually we may be able to do some
 *  brk-specific accounting here.
 */
unsigned long do_brk(unsigned long addr, unsigned long len)
{
	struct mm_struct * mm = current->mm;
	struct vm_area_struct * vma, * prev;
	unsigned long flags;
	struct rb_node ** rb_link, * rb_parent;
	pgoff_t pgoff = addr >> PAGE_SHIFT;

	len = PAGE_ALIGN(len);
	if (!len)
		return addr;

	if ((addr + len) > TASK_SIZE || (addr + len) < addr)
		return -EINVAL;

	/*
	 * mlock MCL_FUTURE?
	 */
	if (mm->def_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
		locked = mm->locked_vm << PAGE_SHIFT;
		lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
		locked += len;
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return -EAGAIN;
	}

	/*
	 * mm->mmap_sem is required to protect against another thread
	 * changing the mappings in case we sleep.
	 */
	verify_mm_writelocked(mm);

	/*
	 * Clear old maps.  this also does some error checking for us
	 */
 munmap_back:
	vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	if (vma && vma->vm_start < addr + len) {
		if (do_munmap(mm, addr, len))
			return -ENOMEM;
		goto munmap_back;
	}

	/* Check against address space limits *after* clearing old maps... */
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
		return -ENOMEM;

	if (mm->map_count > sysctl_max_map_count)
		return -ENOMEM;

	if (security_vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;

	/* Can we just expand an old private anonymous mapping? */
	if (vma_merge(mm, prev, addr, addr + len, flags,
					NULL, NULL, pgoff, NULL))
		goto out;

	/*
	 * create a vma struct for an anonymous mapping
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!vma) {
		vm_unacct_memory(len >> PAGE_SHIFT);
		return -ENOMEM;
	}
	memset(vma, 0, sizeof(*vma));

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_pgoff = pgoff;
	vma->vm_flags = flags;
	vma->vm_page_prot = protection_map[flags & 0x0f];
	vma_link(mm, vma, prev, rb_link, rb_parent);
out:
	mm->total_vm += len >> PAGE_SHIFT;
	if (flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	return addr;
}

EXPORT_SYMBOL(do_brk);

/* Release all mmaps. */
void exit_mmap(struct mm_struct *mm)
{
	struct mmu_gather *tlb;
	struct vm_area_struct *vma = mm->mmap;
	unsigned long nr_accounted = 0;
	unsigned long end;

	lru_add_drain();

	spin_lock(&mm->page_table_lock);

	flush_cache_mm(mm);
	tlb = tlb_gather_mmu(mm, 1);
	/* Use -1 here to ensure all VMAs in the mm are unmapped */
	end = unmap_vmas(&tlb, mm, vma, 0, -1, &nr_accounted, NULL);
	vm_unacct_memory(nr_accounted);
	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
	tlb_finish_mmu(tlb, 0, end);

	mm->mmap = mm->mmap_cache = NULL;
	mm->mm_rb = RB_ROOT;
	set_mm_counter(mm, rss, 0);
	mm->total_vm = 0;
	mm->locked_vm = 0;

	spin_unlock(&mm->page_table_lock);

	/*
	 * Walk the list again, actually closing and freeing it
	 * without holding any MM locks.
	 */
	while (vma) {
		struct vm_area_struct *next = vma->vm_next;
		remove_vm_struct(vma);
		vma = next;
	}

	BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
}

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap tree.  If vm_file is non-NULL
 * then i_mmap_lock is taken here.
 */
int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	struct rb_node ** rb_link, * rb_parent;

	/*
	 * The vm_pgoff of a purely anonymous vma should be irrelevant
	 * until its first write fault, when page's anon_vma and index
	 * are set.  But now set the vm_pgoff it will almost certainly
	 * end up with (unless mremap moves it elsewhere before that
	 * first wfault), so /proc/pid/maps tells a consistent story.
	 *
	 * By setting it to reflect the virtual start address of the
	 * vma, merges and splits can happen in a seamless way, just
	 * using the existing file pgoff checks and manipulations.
	 * Similarly in do_mmap_pgoff and in do_brk.
	 */
	if (!vma->vm_file) {
		BUG_ON(vma->anon_vma);
		vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
	}
	__vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		return -ENOMEM;
	vma_link(mm, vma, prev, rb_link, rb_parent);
	return 0;
}

/*
 * Copy the vma structure to a new location in the same mm,
 * prior to moving page table entries, to effect an mremap move.
 */
struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
	unsigned long addr, unsigned long len, pgoff_t pgoff)
{
	struct vm_area_struct *vma = *vmap;
	unsigned long vma_start = vma->vm_start;
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *new_vma, *prev;
	struct rb_node **rb_link, *rb_parent;
	struct mempolicy *pol;

	/*
	 * If anonymous vma has not yet been faulted, update new pgoff
	 * to match new location, to increase its chance of merging.
	 */
	if (!vma->vm_file && !vma->anon_vma)
		pgoff = addr >> PAGE_SHIFT;

	find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
	if (new_vma) {
		/*
		 * Source vma may have been merged into new_vma
		 */
		if (vma_start >= new_vma->vm_start &&
		    vma_start < new_vma->vm_end)
			*vmap = new_vma;
	} else {
		new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
		if (new_vma) {