mlock.c

最新最稳定的Linux内存管理模块源代码

 *  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.
 */
void munlock_vma_pages_range(struct vm_area_struct *vma,
			   unsigned long start, unsigned long end)
{
	vma->vm_flags &= ~VM_LOCKED;
	__mlock_vma_pages_range(vma, start, end, 0);
}

/*
 * 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.
 */
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
	unsigned long start, unsigned long end, unsigned int newflags)
{
	struct mm_struct *mm = vma->vm_mm;
	pgoff_t pgoff;
	int nr_pages;
	int ret = 0;
	int lock = newflags & VM_LOCKED;

	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 */
	}

	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:
	/*
	 * Keep track of amount of locked VM.
	 */
	nr_pages = (end - start) >> PAGE_SHIFT;
	if (!lock)
		nr_pages = -nr_pages;
	mm->locked_vm += nr_pages;

	/*
	 * 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
	 * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
	 */
	vma->vm_flags = newflags;

	if (lock) {
		ret = __mlock_vma_pages_range(vma, start, end, 1);

		if (ret > 0) {
			mm->locked_vm -= ret;
			ret = 0;
		} else
			ret = __mlock_posix_error_return(ret); /* translate if needed */
	} else {
		__mlock_vma_pages_range(vma, start, end, 0);
	}

out:
	*prev = vma;
	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;
}

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
	unsigned long locked;
	unsigned long lock_limit;
	int error = -ENOMEM;

	if (!can_do_mlock())
		return -EPERM;

	lru_add_drain_all();	/* flush pagevec */

	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;
}

SYSCALL_DEFINE2(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;
}

SYSCALL_DEFINE1(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;

	lru_add_drain_all();	/* flush pagevec */

	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;
}

SYSCALL_DEFINE0(munlockall)
{
	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;
	if (lock_limit == RLIM_INFINITY)
		allowed = 1;
	lock_limit >>= PAGE_SHIFT;
	spin_lock(&shmlock_user_lock);
	if (!allowed &&
	    locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
		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);
}

void *alloc_locked_buffer(size_t size)
{
	unsigned long rlim, vm, pgsz;
	void *buffer = NULL;

	pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;

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

	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
	vm   = current->mm->total_vm + pgsz;
	if (rlim < vm)
		goto out;

	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
	vm   = current->mm->locked_vm + pgsz;
	if (rlim < vm)
		goto out;

	buffer = kzalloc(size, GFP_KERNEL);
	if (!buffer)
		goto out;

	current->mm->total_vm  += pgsz;
	current->mm->locked_vm += pgsz;

 out:
	up_write(&current->mm->mmap_sem);
	return buffer;
}

void release_locked_buffer(void *buffer, size_t size)
{
	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;

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

	current->mm->total_vm  -= pgsz;
	current->mm->locked_vm -= pgsz;

	up_write(&current->mm->mmap_sem);
}

void free_locked_buffer(void *buffer, size_t size)
{
	release_locked_buffer(buffer, size);

	kfree(buffer);
}