nommu.c

最新最稳定的Linux内存管理模块源代码

	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
	if (!new) {
		kmem_cache_free(vm_region_jar, region);
		return -ENOMEM;
	}

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

	npages = (addr - vma->vm_start) >> PAGE_SHIFT;

	if (new_below) {
		region->vm_top = region->vm_end = new->vm_end = addr;
	} else {
		region->vm_start = new->vm_start = addr;
		region->vm_pgoff = new->vm_pgoff += npages;
	}

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

	delete_vma_from_mm(vma);
	down_write(&nommu_region_sem);
	delete_nommu_region(vma->vm_region);
	if (new_below) {
		vma->vm_region->vm_start = vma->vm_start = addr;
		vma->vm_region->vm_pgoff = vma->vm_pgoff += npages;
	} else {
		vma->vm_region->vm_end = vma->vm_end = addr;
		vma->vm_region->vm_top = addr;
	}
	add_nommu_region(vma->vm_region);
	add_nommu_region(new->vm_region);
	up_write(&nommu_region_sem);
	add_vma_to_mm(mm, vma);
	add_vma_to_mm(mm, new);
	return 0;
}

/*
 * shrink a VMA by removing the specified chunk from either the beginning or
 * the end
 */
static int shrink_vma(struct mm_struct *mm,
		      struct vm_area_struct *vma,
		      unsigned long from, unsigned long to)
{
	struct vm_region *region;

	kenter("");

	/* adjust the VMA's pointers, which may reposition it in the MM's tree
	 * and list */
	delete_vma_from_mm(vma);
	if (from > vma->vm_start)
		vma->vm_end = from;
	else
		vma->vm_start = to;
	add_vma_to_mm(mm, vma);

	/* cut the backing region down to size */
	region = vma->vm_region;
	BUG_ON(atomic_read(&region->vm_usage) != 1);

	down_write(&nommu_region_sem);
	delete_nommu_region(region);
	if (from > region->vm_start) {
		to = region->vm_top;
		region->vm_top = region->vm_end = from;
	} else {
		region->vm_start = to;
	}
	add_nommu_region(region);
	up_write(&nommu_region_sem);

	free_page_series(from, to);
	return 0;
}

/*
 * release a mapping
 * - under NOMMU conditions the chunk to be unmapped must be backed by a single
 *   VMA, though it need not cover the whole VMA
 */
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
{
	struct vm_area_struct *vma;
	struct rb_node *rb;
	unsigned long end = start + len;
	int ret;

	kenter(",%lx,%zx", start, len);

	if (len == 0)
		return -EINVAL;

	/* find the first potentially overlapping VMA */
	vma = find_vma(mm, start);
	if (!vma) {
		printk(KERN_WARNING
		       "munmap of memory not mmapped by process %d (%s):"
		       " 0x%lx-0x%lx\n",
		       current->pid, current->comm, start, start + len - 1);
		return -EINVAL;
	}

	/* we're allowed to split an anonymous VMA but not a file-backed one */
	if (vma->vm_file) {
		do {
			if (start > vma->vm_start) {
				kleave(" = -EINVAL [miss]");
				return -EINVAL;
			}
			if (end == vma->vm_end)
				goto erase_whole_vma;
			rb = rb_next(&vma->vm_rb);
			vma = rb_entry(rb, struct vm_area_struct, vm_rb);
		} while (rb);
		kleave(" = -EINVAL [split file]");
		return -EINVAL;
	} else {
		/* the chunk must be a subset of the VMA found */
		if (start == vma->vm_start && end == vma->vm_end)
			goto erase_whole_vma;
		if (start < vma->vm_start || end > vma->vm_end) {
			kleave(" = -EINVAL [superset]");
			return -EINVAL;
		}
		if (start & ~PAGE_MASK) {
			kleave(" = -EINVAL [unaligned start]");
			return -EINVAL;
		}
		if (end != vma->vm_end && end & ~PAGE_MASK) {
			kleave(" = -EINVAL [unaligned split]");
			return -EINVAL;
		}
		if (start != vma->vm_start && end != vma->vm_end) {
			ret = split_vma(mm, vma, start, 1);
			if (ret < 0) {
				kleave(" = %d [split]", ret);
				return ret;
			}
		}
		return shrink_vma(mm, vma, start, end);
	}

erase_whole_vma:
	delete_vma_from_mm(vma);
	delete_vma(mm, vma);
	kleave(" = 0");
	return 0;
}
EXPORT_SYMBOL(do_munmap);

SYSCALL_DEFINE2(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 the mappings made in a process's VM space
 */
void exit_mmap(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	if (!mm)
		return;

	kenter("");

	mm->total_vm = 0;

	while ((vma = mm->mmap)) {
		mm->mmap = vma->vm_next;
		delete_vma_from_mm(vma);
		delete_vma(mm, vma);
	}

	kleave("");
}

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

/*
 * expand (or shrink) an existing mapping, potentially moving it at the same
 * time (controlled by the MREMAP_MAYMOVE flag and available VM space)
 *
 * under NOMMU conditions, we only permit changing a mapping's size, and only
 * as long as it stays within the region allocated by do_mmap_private() and the
 * block is not shareable
 *
 * MREMAP_FIXED is not supported under NOMMU conditions
 */
unsigned long do_mremap(unsigned long addr,
			unsigned long old_len, unsigned long new_len,
			unsigned long flags, unsigned long new_addr)
{
	struct vm_area_struct *vma;

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

	if (addr & ~PAGE_MASK)
		return -EINVAL;

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

	vma = find_vma_exact(current->mm, addr, old_len);
	if (!vma)
		return (unsigned long) -EINVAL;

	if (vma->vm_end != vma->vm_start + old_len)
		return (unsigned long) -EFAULT;

	if (vma->vm_flags & VM_MAYSHARE)
		return (unsigned long) -EPERM;

	if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start)
		return (unsigned long) -ENOMEM;

	/* all checks complete - do it */
	vma->vm_end = vma->vm_start + new_len;
	return vma->vm_start;
}
EXPORT_SYMBOL(do_mremap);

SYSCALL_DEFINE5(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;
}

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

int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
		unsigned long to, unsigned long size, pgprot_t prot)
{
	vma->vm_start = vma->vm_pgoff << PAGE_SHIFT;
	return 0;
}
EXPORT_SYMBOL(remap_pfn_range);

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);

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;
}

void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
{
}

void unmap_mapping_range(struct address_space *mapping,
			 loff_t const holebegin, loff_t const holelen,
			 int even_cows)
{
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * 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);

/*
 * 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.
 */
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
	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;

		free = global_page_state(NR_FILE_PAGES);
		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
		 */
		free += global_page_state(NR_SLAB_RECLAIMABLE);

		/*
		 * 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();

		/*
		 * 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
		 */
		if (!cap_sys_admin)
			n -= n / 32;
		free += n;

		if (free > pages)
			return 0;

		goto error;
	}

	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 */
	if (mm)
		allowed -= mm->total_vm / 32;

	/*
	 * cast `allowed' as a signed long because vm_committed_space
	 * sometimes has a negative value
	 */
	if (atomic_long_read(&vm_committed_space) < (long)allowed)
		return 0;
error:
	vm_unacct_memory(pages);

	return -ENOMEM;
}

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

int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	BUG();
	return 0;
}
EXPORT_SYMBOL(filemap_fault);

/*
 * 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 */
	vma = find_vma(mm, addr);
	if (vma) {
		/* 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 */
		if (write && vma->vm_flags & VM_MAYWRITE)
			len -= copy_to_user((void *) addr, buf, len);
		else if (!write && vma->vm_flags & VM_MAYREAD)
			len -= copy_from_user(buf, (void *) addr, len);
		else
			len = 0;
	} else {
		len = 0;
	}

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