内存管理API之do_mmap

unsigned long do_mmap(struct file *file, unsigned long addr,
			unsigned long len, unsigned long prot,
			unsigned long flags, vm_flags_t vm_flags,
			unsigned long pgoff, unsigned long *populate,
			struct list_head *uf)
这个函数是分配一个新的线性地址空间，如果file不为空，则进行内存映射，如果file为空，则进行
匿名映射，就和前面讲的do_brk的作用类似.


unsigned long do_mmap(struct file *file, unsigned long addr,
			unsigned long len, unsigned long prot,
			unsigned long flags, vm_flags_t vm_flags,
			unsigned long pgoff, unsigned long *populate,
			struct list_head *uf)
{
	#得到当前进程的mm结构，后面会更新mm 中vm相关的成员变量
	struct mm_struct *mm = current->mm;
	int pkey = 0;

	*populate = 0;
	#长度为零，就直接退出
	if (!len)
		return -EINVAL;

	/*
	 * Does the application expect PROT_READ to imply PROT_EXEC?
	 *
	 * (the exception is when the underlying filesystem is noexec
	 *  mounted, in which case we dont add PROT_EXEC.)
	 */
	#检查相应的flag
	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
		if (!(file && path_noexec(&file->f_path)))
			prot |= PROT_EXEC;

	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
	if (!len)
		return -ENOMEM;

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

	/* Too many mappings? */
	#检查当前进程是否超过系统规定的最大映射size
	if (mm->map_count > sysctl_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.
	 */
	#得到未映射的一段虚拟地址
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	#看addr是否在已经被映射过了，如果映射过了，这里就直接返回了
	if (offset_in_page(addr))
		return addr;

	if (prot == PROT_EXEC) {
		pkey = execute_only_pkey(mm);
		if (pkey < 0)
			pkey = 0;
	}

	/* 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_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) |
			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

	if (flags & MAP_LOCKED)
		if (!can_do_mlock())
			return -EPERM;

	if (mlock_future_check(mm, vm_flags, len))
		return -EAGAIN;

	if (file) {
	#针对形参不为null的case。
		struct inode *inode = file_inode(file);
		unsigned long flags_mask;

		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
		#根据映射的flag，分别对vm置位相应的flag
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			/*
			 * Force use of MAP_SHARED_VALIDATE with non-legacy
			 * flags. E.g. MAP_SYNC is dangerous to use with
			 * MAP_SHARED as you don't know which consistency model
			 * you will get. We silently ignore unsupported flags
			 * with MAP_SHARED to preserve backward compatibility.
			 */
			flags &= LEGACY_MAP_MASK;
			/* fall through */
		case MAP_SHARED_VALIDATE:
			if (flags & ~flags_mask)
				return -EOPNOTSUPP;
			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(inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			/*
			 * Make sure there are no mandatory locks on the file.
			 */
			if (locks_verify_locked(file))
				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;
			if (path_noexec(&file->f_path)) {
				if (vm_flags & VM_EXEC)
					return -EPERM;
				vm_flags &= ~VM_MAYEXEC;
			}

			if (!file->f_op->mmap)
				return -ENODEV;
			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
				return -EINVAL;
			break;

		default:
			return -EINVAL;
		}
	} else {
	#第一个形参file 为零的case，即进行所谓的匿名映射
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
				return -EINVAL;
			/*
			 * Ignore pgoff.
			 */
			pgoff = 0;
			vm_flags |= VM_SHARED | VM_MAYSHARE;
			break;
		case MAP_PRIVATE:
			/*
			 * Set pgoff according to addr for anon_vma.
			 */
			pgoff = addr >> PAGE_SHIFT;
			break;
		default:
			return -EINVAL;
		}
	}

	/*
	 * Set 'VM_NORESERVE' if we should not account for the
	 * memory use of this mapping.
	 */
	if (flags & MAP_NORESERVE) {
		/* We honor MAP_NORESERVE if allowed to overcommit */
		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
			vm_flags |= VM_NORESERVE;

		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
		if (file && is_file_hugepages(file))
			vm_flags |= VM_NORESERVE;
	}
	#映射addr~addr+len 这段内存，然后返回addr给用户.
	addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
	if (!IS_ERR_VALUE(addr) &&
	    ((vm_flags & VM_LOCKED) ||
	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
		*populate = len;
	return addr;
}