Linux文件系统学习：文件write过程分析（5）

  • A+
所属分类：Linux系统

从vfs_write 开始分析

ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_WRITE))
		return -EBADF;
	if (!(file->f_mode & FMODE_CAN_WRITE))
		return -EINVAL;
	if (unlikely(!access_ok(VERIFY_READ, buf, count)))
		return -EFAULT;

	ret = rw_verify_area(WRITE, file, pos, count);
	if (ret >= 0) {
		count = ret;
		file_start_write(file);
		ret = __vfs_write(file, buf, count, pos);
		if (ret > 0) {
			fsnotify_modify(file);
			add_wchar(current, ret);
		}
		inc_syscw(current);
		file_end_write(file);
	}

	return ret;
}

  • access_ok
  • __vfs_write
  • fsnotify_modify

ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
		    loff_t *pos)
{
	if (file->f_op->write)
		return file->f_op->write(file, p, count, pos);
	else if (file->f_op->write_iter)
		return new_sync_write(file, p, count, pos);
	else
		return -EINVAL;
}

 

这里检查f_op 的write接口，我们以ext4为例。

const struct file_operations ext4_file_operations = {
	.llseek		= ext4_llseek,
	.read_iter	= generic_file_read_iter,
	.write_iter	= ext4_file_write_iter,
	.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= ext4_compat_ioctl,
#endif
	.mmap		= ext4_file_mmap,
	.open		= ext4_file_open,
	.release	= ext4_release_file,
	.fsync		= ext4_sync_file,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= ext4_fallocate,
};

 

那么它会走write_iter接口，

static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
	struct kiocb kiocb;
	struct iov_iter iter;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	iov_iter_init(&iter, WRITE, &iov, 1, len);

	ret = filp->f_op->write_iter(&kiocb, &iter);
	BUG_ON(ret == -EIOCBQUEUED);
	if (ret > 0)
		*ppos = kiocb.ki_pos;
	return ret;
}

 

这里只是转换数据结构。

static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(iocb->ki_filp);
	struct mutex *aio_mutex = NULL;
	struct blk_plug plug;
	int o_direct = iocb->ki_flags & IOCB_DIRECT;
	int overwrite = 0;
	ssize_t ret;


	if (o_direct) {
		size_t length = iov_iter_count(from);
		loff_t pos = iocb->ki_pos;
		blk_start_plug(&plug);
		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
			struct ext4_map_blocks map;
			unsigned int blkbits = inode->i_blkbits;
			int err, len;

			map.m_lblk = pos >> blkbits;
			map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
				- map.m_lblk;
			len = map.m_len;

			err = ext4_map_blocks(NULL, inode, &map, 0);
	
			if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
				overwrite = 1;
		}
	}

	ret = __generic_file_write_iter(iocb, from);
	mutex_unlock(&inode->i_mutex);

	if (ret > 0) {
		ssize_t err;

		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
		if (err < 0)
			ret = err;
	}
	if (o_direct)
		blk_finish_plug(&plug);

	if (aio_mutex)
		mutex_unlock(aio_mutex);
	return ret;

out:
	mutex_unlock(&inode->i_mutex);
	if (aio_mutex)
		mutex_unlock(aio_mutex);
	return ret;
}

 

这边检查o_direct，应该就是直接写入的标签，前面会做一些工作，我先假设没有这个东东。

ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct address_space * mapping = file->f_mapping;
	struct inode 	*inode = mapping->host;
	ssize_t		written = 0;
	ssize_t		err;
	ssize_t		status;

	current->backing_dev_info = inode_to_bdi(inode);
	err = file_remove_privs(file);
	if (err)
		goto out;

	err = file_update_time(file);
	if (err)
		goto out;

	if (iocb->ki_flags & IOCB_DIRECT) {
		loff_t pos, endbyte;

		written = generic_file_direct_write(iocb, from, iocb->ki_pos);
		if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
			goto out;

		status = generic_perform_write(file, from, pos = iocb->ki_pos);

		if (unlikely(status < 0)) {
			err = status;
			goto out;
		}

		endbyte = pos + status - 1;
		err = filemap_write_and_wait_range(mapping, pos, endbyte);
		if (err == 0) {
			iocb->ki_pos = endbyte + 1;
			written += status;
			invalidate_mapping_pages(mapping,
						 pos >> PAGE_CACHE_SHIFT,
						 endbyte >> PAGE_CACHE_SHIFT);
		} else {

		}
	} else {
		written = generic_perform_write(file, from, iocb->ki_pos);
		if (likely(written > 0))
			iocb->ki_pos += written;
	}
out:
	current->backing_dev_info = NULL;
	return written ? written : err;
}

 

这里还是会检查IOCB_DIRECT，直接写流程，我们先不看了。

ssize_t generic_perform_write(struct file *file,
				struct iov_iter *i, loff_t pos)
{
	struct address_space *mapping = file->f_mapping;
	const struct address_space_operations *a_ops = mapping->a_ops;
	long status = 0;
	ssize_t written = 0;
	unsigned int flags = 0;

	if (!iter_is_iovec(i))
		flags |= AOP_FLAG_UNINTERRUPTIBLE;

	do {
		struct page *page;
		unsigned long offset;	/* Offset into pagecache page */
		unsigned long bytes;	/* Bytes to write to page */
		size_t copied;		/* Bytes copied from user */
		void *fsdata;

		offset = (pos & (PAGE_CACHE_SIZE - 1));
		bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
						iov_iter_count(i));

again:

		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
			status = -EFAULT;
			break;
		}

		if (fatal_signal_pending(current)) {
			status = -EINTR;
			break;
		}

		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
						&page, &fsdata);
		if (unlikely(status < 0))
			break;

		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
		flush_dcache_page(page);

		status = a_ops->write_end(file, mapping, pos, bytes, copied,
						page, fsdata);
		if (unlikely(status < 0))
			break;
		copied = status;

		cond_resched();

		iov_iter_advance(i, copied);
		if (unlikely(copied == 0)) {

			bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
						iov_iter_single_seg_count(i));
			goto again;
		}
		pos += copied;
		written += copied;

		balance_dirty_pages_ratelimited(mapping);
	} while (iov_iter_count(i));

	return written ? written : status;
}

 

这里就是循环一页一页的写。当然是写到缓存中，

 

  • 1、a_ops->write_begin 和a_ops交互准备开始写
  • 2、iov_iter_copy_from_user_atomic 拷贝用户数据到 page
  • 3、a_ops->write_end 写入
  • 4、balance_dirty_pages_ratelimited 做限制检查

 

那么准备cache的过程在write_begin中。做限制的后面再看。我们的目标就是这两个。

 

static const struct address_space_operations ext4_aops = {
	.readpage		= ext4_readpage,
	.readpages		= ext4_readpages,
	.writepage		= ext4_writepage,
	.writepages		= ext4_writepages,
	.write_begin		= ext4_write_begin,
	.write_end		= ext4_write_end,
	.bmap			= ext4_bmap,
	.invalidatepage		= ext4_invalidatepage,
	.releasepage		= ext4_releasepage,
	.direct_IO		= ext4_direct_IO,
	.migratepage		= buffer_migrate_page,
	.is_partially_uptodate  = block_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
};

static int ext4_write_begin(struct file *file, struct address_space *mapping,
			    loff_t pos, unsigned len, unsigned flags,
			    struct page **pagep, void **fsdata)
{
	struct inode *inode = mapping->host;
	int ret, needed_blocks;
	handle_t *handle;
	int retries = 0;
	struct page *page;
	pgoff_t index;
	unsigned from, to;

	trace_android_fs_datawrite_start(inode, pos, len,
					 current->pid, current->comm);
	trace_ext4_write_begin(inode, pos, len, flags);

	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
	index = pos >> PAGE_CACHE_SHIFT;
	from = pos & (PAGE_CACHE_SIZE - 1);
	to = from + len;

	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
		ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
						    flags, pagep);
		if (ret < 0)
			return ret;
		if (ret == 1)
			return 0;
	}


retry_grab:
	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;
	unlock_page(page);

retry_journal:
	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
	if (IS_ERR(handle)) {
		page_cache_release(page);
		return PTR_ERR(handle);
	}

	lock_page(page);
	if (page->mapping != mapping) {
		/* The page got truncated from under us */
		unlock_page(page);
		page_cache_release(page);
		ext4_journal_stop(handle);
		goto retry_grab;
	}

	wait_for_stable_page(page);

#ifdef CONFIG_EXT4_FS_ENCRYPTION
	if (ext4_should_dioread_nolock(inode))
		ret = ext4_block_write_begin(page, pos, len,
					     ext4_get_block_write);
	else
		ret = ext4_block_write_begin(page, pos, len,
					     ext4_get_block);
#else
	if (ext4_should_dioread_nolock(inode))
		ret = __block_write_begin(page, pos, len, ext4_get_block_write);
	else
		ret = __block_write_begin(page, pos, len, ext4_get_block);
#endif
	if (!ret && ext4_should_journal_data(inode)) {
		ret = ext4_walk_page_buffers(handle, page_buffers(page),
					     from, to, NULL,
					     do_journal_get_write_access);
	}

	if (ret) {
		unlock_page(page);

		if (pos + len > inode->i_size && ext4_can_truncate(inode))
			ext4_orphan_add(handle, inode);

		ext4_journal_stop(handle);
		if (pos + len > inode->i_size) {
			ext4_truncate_failed_write(inode);

			if (inode->i_nlink)
				ext4_orphan_del(NULL, inode);
		}

		if (ret == -ENOSPC &&
		    ext4_should_retry_alloc(inode->i_sb, &retries))
			goto retry_journal;
		page_cache_release(page);
		return ret;
	}
	*pagep = page;
	mtk_btag_pidlog_write_begin(*pagep);

	return ret;
}

 

  • 前面做一些检查
  • 后面的handle是和block buffers进行交互的
  • 主要的过程是中间的grab_cache_page_write_begin

struct page *grab_cache_page_write_begin(struct address_space *mapping,
					pgoff_t index, unsigned flags)
{
	struct page *page;
	int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;

	if (flags & AOP_FLAG_NOFS)
		fgp_flags |= FGP_NOFS;

	page = pagecache_get_page(mapping, index, fgp_flags,
			mapping_gfp_mask(mapping));
	if (page)
		wait_for_stable_page(page);

	return page;
}

 

pagecache_get_page 从radix中获取一页。

struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
	int fgp_flags, gfp_t gfp_mask)
{
	struct page *page;

repeat:
	page = find_get_entry(mapping, offset);
	if (radix_tree_exceptional_entry(page))
		page = NULL;
	if (!page)
		goto no_page;

	if (fgp_flags & FGP_LOCK) {
		if (fgp_flags & FGP_NOWAIT) {
			if (!trylock_page(page)) {
				page_cache_release(page);
				return NULL;
			}
		} else {
			lock_page(page);
		}

		/* Has the page been truncated? */
		if (unlikely(page->mapping != mapping)) {
			unlock_page(page);
			page_cache_release(page);
			goto repeat;
		}
		VM_BUG_ON_PAGE(page->index != offset, page);
	}

	if (page && (fgp_flags & FGP_ACCESSED))
		mark_page_accessed(page);

no_page:
	if (!page && (fgp_flags & FGP_CREAT)) {
		int err;
		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
			gfp_mask |= __GFP_WRITE;
		if (fgp_flags & FGP_NOFS)
			gfp_mask &= ~__GFP_FS;

		page = __page_cache_alloc(gfp_mask);
		if (!page)
			return NULL;

		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
			fgp_flags |= FGP_LOCK;

		/* Init accessed so avoid atomic mark_page_accessed later */
		if (fgp_flags & FGP_ACCESSED)
			__SetPageReferenced(page);

		err = add_to_page_cache_lru(page, mapping, offset,
				gfp_mask & GFP_RECLAIM_MASK);
		if (unlikely(err)) {
			page_cache_release(page);
			page = NULL;
			if (err == -EEXIST)
				goto repeat;
		}
	}

	return page;
}

 

  • find_get_entry 获取一页
  • mark_page_accessed 标记页据说是给清除的时候用的
  • no_page流程，如果没有获取到page就 __page_cache_alloc 一个 然后add_to_page_cache_lru

struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
	void **pagep;
	struct page *page;

	rcu_read_lock();
repeat:
	page = NULL;
	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
	if (pagep) {
		page = radix_tree_deref_slot(pagep);
		if (unlikely(!page))
			goto out;
		if (radix_tree_exception(page)) {
			if (radix_tree_deref_retry(page))
				goto repeat;
			goto out;
		}
		if (!page_cache_get_speculative(page))
			goto repeat;

		if (unlikely(page != *pagep)) {
			page_cache_release(page);
			goto repeat;
		}
	}
out:
	rcu_read_unlock();

	return page;
}

 

find_get_entry 也很简单，就是在radix_tree_lookup_slot 找一个。

 

# Linux必备书籍推荐

 

《LINUX内核源代码情景分析(上册) 》毛德操,胡希明      >>>京东购买     >>>淘宝购买 

《LINUX内核源代码情景分析(下册) 》毛德操,胡希明      >>>京东购买     >>>淘宝购买

《嵌入式Linux应用开发完全手册 》韦东山 著     >>>京东购买     >>>淘宝购买 （领券）

《深入理解Linux内核第3版》（美）博韦      >>>京东购买     >>>淘宝购买    

《鸟哥的Linux私房菜：基础学习篇(第四版)》鸟哥      >>>京东购买     >>>淘宝购买

 

#免费电子书领取

神农笔记微信公众号

扫一扫关注微信公众号，上述5本电子书免费领取。

https://pan.baidu.com/s/1q5IjXAmybs8NBseR4R8Ksg

扫码关注微信公众号，回复“Linux” ，即可获取提取码

 

--- Linux文件系统学习系列笔记 ---

（原创笔记，转载请联系博主授权）

Linux文件系统学习：整体框架图（1）

Linux文件系统学习：初始化过程（2）

Linux文件系统学习：文件read流程分析（3）

Linux文件系统学习:文件read和BIO调度分析(4)

Linux文件系统学习：文件write过程分析（5）

Linux文件系统学习：io调度框架（6）

Linux文件系统学习：io的提交过程（7）

Linux文件系统学习：io的plug过程-启动篇（8）

Linux文件系统学习：io的plug过程-request请求（9）

Linux文件系统学习：io的plug过程-blk_init_queue（10）

Linux文件系统学习：io的plug过程-blk_flush_plug_list的情况（11）

Linux文件系统学习：io的plug过程-queuelist的问题（12）

Linux文件系统学习：电梯算法简介（13）

Linux文件系统学习：电梯算法noop（14）

Linux文件系统学习：电梯算法deadline（15）

 

<欢迎关注微信公众号，第一时间查看最新内容>

神农笔记微信公众号

发表评论

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen: