sys_mmap_pgoff

sys_mmap_pgoff

SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, pgoff)
{
	struct file * file = NULL;
	unsigned long retval = -EBADF;

	if (!(flags & MAP_ANONYMOUS)) { /* 不是匿名映射，则打开文件，否则file为NULL */
		if (unlikely(flags & MAP_HUGETLB))
			return -EINVAL;
		file = fget(fd);
		if (!file)
			goto out;
	} else if (flags & MAP_HUGETLB) {
		struct user_struct *user = NULL;
		/*
		 * VM_NORESERVE is used because the reservations will be
		 * taken when vm_ops->mmap() is called
		 * A dummy user value is used because we are not locking
		 * memory so no accounting is necessary
		 */
		len = ALIGN(len, huge_page_size(&default_hstate));
		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
						&user, HUGETLB_ANONHUGE_INODE);
		if (IS_ERR(file))
			return PTR_ERR(file);
	}

	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);

	down_write(¤t->mm->mmap_sem);
	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);    /* 执行映射 */
	up_write(¤t->mm->mmap_sem);

	if (file)
		fput(file);
out:
	return retval;
}

do_mmap_pgoff

/*
 * The caller must hold down_write(¤t->mm->mmap_sem).
 */

unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
			unsigned long len, unsigned long prot,
			unsigned long flags, unsigned long pgoff)
{
	struct mm_struct * mm = current->mm;
	struct inode *inode;
	unsigned int vm_flags;
	int error;
	unsigned long reqprot = prot;

	/*
	 * 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.)
	 */
	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
			prot |= PROT_EXEC;

	if (!len)
		return -EINVAL;

	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? */   /* 一个程序最多可以映射sysctl_max_map_count个section  */ 
	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.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);    /* 获取一个空洞地址 arch_get_unmapped_area */
	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_prot_bits(prot) | calc_vm_flag_bits(flags) |
			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

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

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

	inode = file ? file->f_path.dentry->d_inode : NULL;

	if (file) {     /* 根据文件是否为NULL，创建vm_flags */
		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(inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

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

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

		default:
			return -EINVAL;
		}
	} else {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			/*
			 * 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;
		}
	}

	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
	if (error)
		return error;
	error = ima_file_mmap(file, prot);
	if (error)
		return error;

	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
}

mmap_region

unsigned long mmap_region(struct file *file, unsigned long addr,
			  unsigned long len, unsigned long flags,
			  unsigned int vm_flags, unsigned long pgoff)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma, *prev;
	int correct_wcount = 0;
	int error;
	struct rb_node **rb_link, *rb_parent;
	unsigned long charged = 0;
	struct inode *inode =  file ? file->f_path.dentry->d_inode : NULL;

	/* Clear old maps */
	error = -ENOMEM;
munmap_back:        /* 查找重叠空间，unmap之 */
	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. */    /* 地址空间最多可以映射多少页 */
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
		return -ENOMEM;

	/*
	 * 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;
	}

	/*
	 * Private writable mapping: check memory availability
	 */
	if (accountable_mapping(file, vm_flags)) {
		charged = len >> PAGE_SHIFT;
		if (security_vm_enough_memory(charged))
			return -ENOMEM;
		vm_flags |= VM_ACCOUNT;
	}

	/*
	 * Can we just expand an old mapping?
	 */ /* 当前映射空间是否可以和上一个prev空间合并，如果可以，则跳转到out，不必分配了，但是奇怪的是，file映射流程不知道在哪里，求指教?? */
	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
	if (vma)
		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.
	 */ /* 可以映射，创建一个全新的vm_area_struct */
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
	if (!vma) {
		error = -ENOMEM;
		goto unacct_error;
	}

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = vm_flags;
	vma->vm_page_prot = vm_get_page_prot(vm_flags);
	vma->vm_pgoff = pgoff;

	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);    /* 进行文件映射，generic_file_mmap ==> filemap_fault，到page_fault才真映射 */
		if (error)
			goto unmap_and_free_vma;
		if (vm_flags & VM_EXECUTABLE)
			added_exe_file_vma(mm);

		/* Can addr have changed??
		 *
		 * Answer: Yes, several device drivers can do it in their
		 *         f_op->mmap method. -DaveM
		 */
		addr = vma->vm_start;
		pgoff = vma->vm_pgoff;
		vm_flags = vma->vm_flags;
	} else if (vm_flags & VM_SHARED) {
		error = shmem_zero_setup(vma);  /* 匿名映射，如果是共享内存，则映射到特殊共享文件? */
		if (error)
			goto free_vma;
	}

	if (vma_wants_writenotify(vma))
		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);

	vma_link(mm, vma, prev, rb_link, rb_parent);    /* vma数据结构调整 */
	file = vma->vm_file;

	/* Once vma denies write, undo our temporary denial count */
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
out:
	perf_event_mmap(vma);

	mm->total_vm += len >> PAGE_SHIFT;
	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
	if (vm_flags & VM_LOCKED) {
		/*
		 * makes pages present; downgrades, drops, reacquires mmap_sem
		 */
		long nr_pages = mlock_vma_pages_range(vma, addr, addr + len);
		if (nr_pages < 0)
			return nr_pages;	/* vma gone! */
		mm->locked_vm += (len >> PAGE_SHIFT) - nr_pages;
	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
		make_pages_present(addr, addr + len);
	return addr;

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

	/* Undo any partial mapping done by a device driver. */
	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
	charged = 0;
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
unacct_error:
	if (charged)
		vm_unacct_memory(charged);
	return error;
}

mmap.c (F:\linux-2.6.32\mm) 66210 2013/6/10
SYSCALL_DEFINE1(brk, unsigned long, brk)