mmap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

	struct vm_area_struct * vma, * prev;
	unsigned int vm_flags;
	int correct_wcount = 0;
	int error;
	rb_node_t ** rb_link, * rb_parent;

	if (file && (!file->f_op || !file->f_op->mmap))
		return -ENODEV;

	if ((len = PAGE_ALIGN(len)) == 0)
		return addr;

	if (len > TASK_SIZE)
		return -EINVAL;

	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
		return -EINVAL;

	/* Too many mappings? */
	if (mm->map_count > MAX_MAP_COUNT)
		return -ENOMEM;

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	if (addr & ~PAGE_MASK)
		return addr;

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	vm_flags = calc_vm_flags(prot,flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

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

	if (file) {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if ((prot & PROT_WRITE) && !(file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* Make sure we don't allow writing to an append-only file.. */
			if (IS_APPEND(file->f_dentry->d_inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* make sure there are no mandatory locks on the file. */
			if (locks_verify_locked(file->f_dentry->d_inode))
				return -EAGAIN;

			vm_flags |= VM_SHARED | VM_MAYSHARE;
			if (!(file->f_mode & FMODE_WRITE))
				vm_flags &= ~(VM_MAYWRITE | VM_SHARED);

			/* fall through */
		case MAP_PRIVATE:
			if (!(file->f_mode & FMODE_READ))
				return -EACCES;
			break;

		default:
			return -EINVAL;
		}
	} else {
		vm_flags |= VM_SHARED | VM_MAYSHARE;
		switch (flags & MAP_TYPE) {
		default:
			return -EINVAL;
		case MAP_PRIVATE:
			vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
			/* fall through */
		case MAP_SHARED:
			break;
		}
	}

	/* 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 ((mm->total_vm << PAGE_SHIFT) + len
	    > current->rlim[RLIMIT_AS].rlim_cur)
		return -ENOMEM;

	/* Private writable mapping? Check memory availability.. */
	if ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
	    !(flags & MAP_NORESERVE)				 &&
	    !vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	/* Can we just expand an old anonymous mapping? */
	if (!file && !(vm_flags & VM_SHARED) && rb_parent)
		if (vma_merge(mm, prev, rb_parent, addr, addr + len, vm_flags))
			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)
		return -ENOMEM;

	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_ops = NULL;
	vma->vm_pgoff = pgoff;
	vma->vm_file = NULL;
	vma->vm_private_data = NULL;
	vma->vm_raend = 0;

	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 (flags & MAP_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

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

	vma_link(mm, vma, prev, rb_link, rb_parent);
	if (correct_wcount)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);

out:	
	mm->total_vm += len >> PAGE_SHIFT;
	if (vm_flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	return addr;

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

	/* Undo any partial mapping done by a device driver. */
	zap_page_range(mm, vma->vm_start, vma->vm_end - vma->vm_start);
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
	return error;
}

/* 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
static inline unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct vm_area_struct *vma;

	if (len > TASK_SIZE)
		return -ENOMEM;

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

	for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr)
			return -ENOMEM;
		if (!vma || addr + len <= vma->vm_start)
			return addr;
		addr = vma->vm_end;
	}
}
#else
extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
#endif	

unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
	if (flags & MAP_FIXED) {
		if (addr > TASK_SIZE - len)
			return -ENOMEM;
		if (addr & ~PAGE_MASK)
			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 arch_get_unmapped_area(file, addr, len, pgoff, flags);
}

/* 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)) {
			rb_node_t * 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;
}

/* 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)
{
	if (mm) {
		/* Go through the RB tree quickly. */
		struct vm_area_struct * vma;
		rb_node_t * rb_node, * rb_last_right, * rb_prev;
		
		rb_node = mm->mm_rb.rb_node;
		rb_last_right = rb_prev = NULL;
		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;
				rb_prev = rb_last_right;
				if (vma_tmp->vm_start <= addr)
					break;
				rb_node = rb_node->rb_left;
			} else {
				rb_last_right = rb_node;
				rb_node = rb_node->rb_right;
			}
		}
		if (vma) {
			if (vma->vm_rb.rb_left) {
				rb_prev = vma->vm_rb.rb_left;
				while (rb_prev->rb_right)
					rb_prev = rb_prev->rb_right;
			}
			*pprev = NULL;
			if (rb_prev)
				*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
			if ((rb_prev ? (*pprev)->vm_next : mm->mmap) != vma)
				BUG();
			return vma;
		}
	}
	*pprev = NULL;
	return NULL;
}

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;
}

/* 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.
 * This function works out what part of an area is affected and
 * adjusts the mapping information.  Since the actual page
 * manipulation is done in do_mmap(), none need be done here,
 * though it would probably be more appropriate.
 *
 * By the time this function is called, the area struct has been
 * removed from the process mapping list, so it needs to be
 * reinserted if necessary.
 *
 * The 4 main cases are:
 *    Unmapping the whole area
 *    Unmapping from the start of the segment to a point in it
 *    Unmapping from an intermediate point to the end
 *    Unmapping between to intermediate points, making a hole.
 *
 * Case 4 involves the creation of 2 new areas, for each side of
 * the hole.  If possible, we reuse the existing area rather than
 * allocate a new one, and the return indicates whether the old
 * area was reused.
 */
static struct vm_area_struct * unmap_fixup(struct mm_struct *mm, 
	struct vm_area_struct *area, unsigned long addr, size_t len, 
	struct vm_area_struct *extra)
{
	struct vm_area_struct *mpnt;
	unsigned long end = addr + len;

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

	/* Unmapping the whole area. */
	if (addr == area->vm_start && end == area->vm_end) {
		if (area->vm_ops && area->vm_ops->close)
			area->vm_ops->close(area);
		if (area->vm_file)
			fput(area->vm_file);
		kmem_cache_free(vm_area_cachep, area);
		return extra;
	}

	/* Work out to one of the ends. */
	if (end == area->vm_end) {
		/*
		 * here area isn't visible to the semaphore-less readers
		 * so we don't need to update it under the spinlock.
		 */
		area->vm_end = addr;
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
	} else if (addr == area->vm_start) {
		area->vm_pgoff += (end - area->vm_start) >> PAGE_SHIFT;