[RFC V2 06/37] dmemfs: support truncating inode down

[yulei.kernel@gmail.com]

From: Yulei Zhang <yuleixzhang@tencent.com>

To support cut inode down, it will
introduce the race between page fault handler and
truncating handler as the entry to be deleted is being
mapped into process's VMA

in order to make page fault faster (as it's the hot
path), we use RCU to sync these two handlers. When
inode's size is updated, the handler makes sure the
new size is visible to page fault handler who will
not use truncated entry anymore and will not create
new entry in that region

Signed-off-by: Xiao Guangrong <gloryxiao@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 fs/dmemfs/inode.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/fs/dmemfs/inode.c b/fs/dmemfs/inode.c
index 7b6e51d..9ec62dc 100644
--- a/fs/dmemfs/inode.c
+++ b/fs/dmemfs/inode.c
@@ -98,8 +98,73 @@ static int dmemfs_mkdir(struct inode *dir, struct dentry *dentry,
 	.rename		= simple_rename,
 };
 
+static void inode_drop_dpages(struct inode *inode, loff_t start, loff_t end);
+
+static int dmemfs_truncate(struct inode *inode, loff_t newsize)
+{
+	struct super_block *sb = inode->i_sb;
+	loff_t current_size;
+
+	if (newsize & ((1 << sb->s_blocksize_bits) - 1))
+		return -EINVAL;
+
+	current_size = i_size_read(inode);
+	i_size_write(inode, newsize);
+
+	if (newsize >= current_size)
+		return 0;
+
+	/* it cuts the inode down */
+
+	/*
+	 * we should make sure inode->i_size has been updated before
+	 * unmapping and dropping radix entries, so that other sides
+	 * can not create new i_mapping entry beyond inode->i_size
+	 * and the radix entry in the truncated region is not being
+	 * used
+	 *
+	 * see the comments in dmemfs_fault()
+	 */
+	synchronize_rcu();
+
+	/*
+	 * should unmap all mapping first as dmem pages are freed in
+	 * inode_drop_dpages()
+	 *
+	 * after that, dmem page in the truncated region is not used
+	 * by any process
+	 */
+	unmap_mapping_range(inode->i_mapping, newsize, 0, 1);
+
+	inode_drop_dpages(inode, newsize, LLONG_MAX);
+	return 0;
+}
+
+/*
+ * same logic as simple_setattr but we need to handle ftruncate
+ * carefully as we inserted self-defined entry into radix tree
+ */
+static int dmemfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error;
+
+	error = setattr_prepare(dentry, iattr);
+	if (error)
+		return error;
+
+	if (iattr->ia_valid & ATTR_SIZE) {
+		error = dmemfs_truncate(inode, iattr->ia_size);
+		if (error)
+			return error;
+	}
+	setattr_copy(inode, iattr);
+	mark_inode_dirty(inode);
+	return 0;
+}
+
 static const struct inode_operations dmemfs_file_inode_operations = {
-	.setattr = simple_setattr,
+	.setattr = dmemfs_setattr,
 	.getattr = simple_getattr,
 };
 
-- 
1.8.3.1