mmap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

		/* same locking considerations of the above case */
		area->vm_start = end;
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
	} else {
	/* Unmapping a hole: area->vm_start < addr <= end < area->vm_end */
		/* Add end mapping -- leave beginning for below */
		mpnt = extra;
		extra = NULL;

		mpnt->vm_mm = area->vm_mm;
		mpnt->vm_start = end;
		mpnt->vm_end = area->vm_end;
		mpnt->vm_page_prot = area->vm_page_prot;
		mpnt->vm_flags = area->vm_flags;
		mpnt->vm_raend = 0;
		mpnt->vm_ops = area->vm_ops;
		mpnt->vm_pgoff = area->vm_pgoff + ((end - area->vm_start) >> PAGE_SHIFT);
		mpnt->vm_file = area->vm_file;
		mpnt->vm_private_data = area->vm_private_data;
		if (mpnt->vm_file)
			get_file(mpnt->vm_file);
		if (mpnt->vm_ops && mpnt->vm_ops->open)
			mpnt->vm_ops->open(mpnt);
		area->vm_end = addr;	/* Truncate area */

		/* Because mpnt->vm_file == area->vm_file this locks
		 * things correctly.
		 */
		lock_vma_mappings(area);
		spin_lock(&mm->page_table_lock);
		__insert_vm_struct(mm, mpnt);
	}

	__insert_vm_struct(mm, area);
	spin_unlock(&mm->page_table_lock);
	unlock_vma_mappings(area);
	return extra;
}

/*
 * Try to free as many page directory entries as we can,
 * without having to work very hard at actually scanning
 * the page tables themselves.
 *
 * Right now we try to free page tables if we have a nice
 * PGDIR-aligned area that got free'd up. We could be more
 * granular if we want to, but this is fast and simple,
 * and covers the bad cases.
 *
 * "prev", if it exists, points to a vma before the one
 * we just free'd - but there's no telling how much before.
 */
static void free_pgtables(struct mm_struct * mm, struct vm_area_struct *prev,
	unsigned long start, unsigned long end)
{
	unsigned long first = start & PGDIR_MASK;
	unsigned long last = end + PGDIR_SIZE - 1;
	unsigned long start_index, end_index;

	if (!prev) {
		prev = mm->mmap;
		if (!prev)
			goto no_mmaps;
		if (prev->vm_end > start) {
			if (last > prev->vm_start)
				last = prev->vm_start;
			goto no_mmaps;
		}
	}
	for (;;) {
		struct vm_area_struct *next = prev->vm_next;

		if (next) {
			if (next->vm_start < start) {
				prev = next;
				continue;
			}
			if (last > next->vm_start)
				last = next->vm_start;
		}
		if (prev->vm_end > first)
			first = prev->vm_end + PGDIR_SIZE - 1;
		break;
	}
no_mmaps:
	/*
	 * If the PGD bits are not consecutive in the virtual address, the
	 * old method of shifting the VA >> by PGDIR_SHIFT doesn't work.
	 */
	start_index = pgd_index(first);
	if (start_index < FIRST_USER_PGD_NR)
		start_index = FIRST_USER_PGD_NR;
	end_index = pgd_index(last);
	if (end_index > start_index) {
		clear_page_tables(mm, start_index, end_index - start_index);
		flush_tlb_pgtables(mm, first & PGDIR_MASK, last & PGDIR_MASK);
	}
}

/* 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 Fitzhardine <[e-mail]>
 */
int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
{
	struct vm_area_struct *mpnt, *prev, **npp, *free, *extra;

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

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

	/* Check if this memory area is ok - put it on the temporary
	 * list if so..  The checks here are pretty simple --
	 * every area affected in some way (by any overlap) is put
	 * on the list.  If nothing is put on, nothing is affected.
	 */
	mpnt = find_vma_prev(mm, addr, &prev);
	if (!mpnt)
		return 0;
	/* we have  addr < mpnt->vm_end  */

	if (mpnt->vm_start >= addr+len)
		return 0;

	/* If we'll make "hole", check the vm areas limit */
	if ((mpnt->vm_start < addr && mpnt->vm_end > addr+len)
	    && mm->map_count >= MAX_MAP_COUNT)
		return -ENOMEM;

	/*
	 * We may need one additional vma to fix up the mappings ... 
	 * and this is the last chance for an easy error exit.
	 */
	extra = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!extra)
		return -ENOMEM;

	npp = (prev ? &prev->vm_next : &mm->mmap);
	free = NULL;
	spin_lock(&mm->page_table_lock);
	for ( ; mpnt && mpnt->vm_start < addr+len; mpnt = *npp) {
		*npp = mpnt->vm_next;
		mpnt->vm_next = free;
		free = mpnt;
		rb_erase(&mpnt->vm_rb, &mm->mm_rb);
	}
	mm->mmap_cache = NULL;	/* Kill the cache. */
	spin_unlock(&mm->page_table_lock);

	/* Ok - we have the memory areas we should free on the 'free' list,
	 * so release them, and unmap the page range..
	 * If the one of the segments is only being partially unmapped,
	 * it will put new vm_area_struct(s) into the address space.
	 * In that case we have to be careful with VM_DENYWRITE.
	 */
	while ((mpnt = free) != NULL) {
		unsigned long st, end, size;
		struct file *file = NULL;

		free = free->vm_next;

		st = addr < mpnt->vm_start ? mpnt->vm_start : addr;
		end = addr+len;
		end = end > mpnt->vm_end ? mpnt->vm_end : end;
		size = end - st;

		if (mpnt->vm_flags & VM_DENYWRITE &&
		    (st != mpnt->vm_start || end != mpnt->vm_end) &&
		    (file = mpnt->vm_file) != NULL) {
			atomic_dec(&file->f_dentry->d_inode->i_writecount);
		}
		remove_shared_vm_struct(mpnt);
		mm->map_count--;

		zap_page_range(mm, st, size);

		/*
		 * Fix the mapping, and free the old area if it wasn't reused.
		 */
		extra = unmap_fixup(mm, mpnt, st, size, extra);
		if (file)
			atomic_inc(&file->f_dentry->d_inode->i_writecount);
	}
	validate_mm(mm);

	/* Release the extra vma struct if it wasn't used */
	if (extra)
		kmem_cache_free(vm_area_cachep, extra);

	free_pgtables(mm, prev, addr, addr+len);

	return 0;
}

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;
}

/*
 *  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;
	rb_node_t ** rb_link, * rb_parent;

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

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

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

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

	if (!vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	flags = calc_vm_flags(PROT_READ|PROT_WRITE|PROT_EXEC,
				MAP_FIXED|MAP_PRIVATE) | mm->def_flags;

	flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

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

	/*
	 * create a vma struct for an anonymous mapping
	 */
	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 = flags;
	vma->vm_page_prot = protection_map[flags & 0x0f];
	vma->vm_ops = NULL;
	vma->vm_pgoff = 0;
	vma->vm_file = NULL;
	vma->vm_private_data = NULL;

	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;
}

/* Build the RB tree corresponding to the VMA list. */
void build_mmap_rb(struct mm_struct * mm)
{
	struct vm_area_struct * vma;
	rb_node_t ** rb_link, * rb_parent;

	mm->mm_rb = RB_ROOT;
	rb_link = &mm->mm_rb.rb_node;
	rb_parent = NULL;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		__vma_link_rb(mm, vma, rb_link, rb_parent);
		rb_parent = &vma->vm_rb;
		rb_link = &rb_parent->rb_right;
	}
}

/* Release all mmaps. */
void exit_mmap(struct mm_struct * mm)
{
	mmu_gather_t *tlb;
	struct vm_area_struct * mpnt;

	release_segments(mm);
	spin_lock(&mm->page_table_lock);

	tlb = tlb_gather_mmu(mm);

	flush_cache_mm(mm);
	mpnt = mm->mmap;
	while (mpnt) {
		unsigned long start = mpnt->vm_start;
		unsigned long end = mpnt->vm_end;

		mm->map_count--;
		remove_shared_vm_struct(mpnt);
		unmap_page_range(tlb, mm, start, end);
		mpnt = mpnt->vm_next;
	}

	/* This is just debugging */
	if (mm->map_count)
		BUG();

	tlb_finish_mmu(tlb, 0, TASK_SIZE);

	mpnt = mm->mmap;
	mm->mmap = mm->mmap_cache = NULL;
	mm->mm_rb = RB_ROOT;
	mm->rss = 0;
	mm->total_vm = 0;
	mm->locked_vm = 0;

	spin_unlock(&mm->page_table_lock);

	clear_page_tables(mm, FIRST_USER_PGD_NR, USER_PTRS_PER_PGD);

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

		if (mpnt->vm_ops) {
			if (mpnt->vm_ops->close)
				mpnt->vm_ops->close(mpnt);
		}
		if (mpnt->vm_file)
			fput(mpnt->vm_file);
		kmem_cache_free(vm_area_cachep, mpnt);
		mpnt = next;
	}
}

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap ring.  If vm_file is non-NULL
 * then the i_shared_lock must be held here.
 */
void __insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	rb_node_t ** rb_link, * rb_parent;

	__vma = find_vma_prepare(mm, vma->vm_start, &prev, &rb_link, &rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		BUG();
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	mm->map_count++;
	validate_mm(mm);
}

void insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	rb_node_t ** rb_link, * rb_parent;

	__vma = find_vma_prepare(mm, vma->vm_start, &prev, &rb_link, &rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		BUG();
	vma_link(mm, vma, prev, rb_link, rb_parent);
	validate_mm(mm);
}