f2fs: guarantee journalled quota data by checkpoint

For journalled quota mode, let checkpoint to flush dquot dirty data
and quota file data to guarntee persistence of all quota sysfile in
last checkpoint, by this way, we can avoid corrupting quota sysfile
when encountering SPO.

The implementation is as below:

1. add a global state SBI_QUOTA_NEED_FLUSH to indicate that there is
cached dquot metadata changes in quota subsystem, and later checkpoint
should:
 a) flush dquot metadata into quota file.
 b) flush quota file to storage to keep file usage be consistent.

2. add a global state SBI_QUOTA_NEED_REPAIR to indicate that quota
operation failed due to -EIO or -ENOSPC, so later,
 a) checkpoint will skip syncing dquot metadata.
 b) CP_QUOTA_NEED_FSCK_FLAG will be set in last cp pack to give a
    hint for fsck repairing.

3. add a global state SBI_QUOTA_SKIP_FLUSH, in checkpoint, if quota
data updating is very heavy, it may cause hungtask in block_operation().
To avoid this, if our retry time exceed threshold, let's just skip
flushing and retry in next checkpoint().

Signed-off-by: Weichao Guo <guoweichao@huawei.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: avoid warnings and set fsck flag]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 24 insertions, 7 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 543c742f8bd7..971463e0589e 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -586,7 +586,8 @@ truncate_out:
 	return 0;
 }
 
-int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock,
+							bool buf_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
@@ -594,6 +595,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 	int count = 0, err = 0;
 	struct page *ipage;
 	bool truncate_page = false;
+	int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO;
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
@@ -603,7 +605,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto free_partial;
 
 	if (lock)
-		f2fs_lock_op(sbi);
+		__do_map_lock(sbi, flag, true);
 
 	ipage = f2fs_get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
@@ -641,7 +643,7 @@ free_next:
 	err = f2fs_truncate_inode_blocks(inode, free_from);
 out:
 	if (lock)
-		f2fs_unlock_op(sbi);
+		__do_map_lock(sbi, flag, false);
 free_partial:
 	/* lastly zero out the first data page */
 	if (!err)
@@ -676,7 +678,7 @@ int f2fs_truncate(struct inode *inode)
 			return err;
 	}
 
-	err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
+	err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false);
 	if (err)
 		return err;
 
@@ -785,9 +787,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 		!uid_eq(attr->ia_uid, inode->i_uid)) ||
 		(attr->ia_valid & ATTR_GID &&
 		!gid_eq(attr->ia_gid, inode->i_gid))) {
+		f2fs_lock_op(F2FS_I_SB(inode));
 		err = dquot_transfer(inode, attr);
-		if (err)
+		if (err) {
+			set_sbi_flag(F2FS_I_SB(inode),
+					SBI_QUOTA_NEED_REPAIR);
+			f2fs_unlock_op(F2FS_I_SB(inode));
 			return err;
+		}
+		/*
+		 * update uid/gid under lock_op(), so that dquot and inode can
+		 * be updated atomically.
+		 */
+		if (attr->ia_valid & ATTR_UID)
+			inode->i_uid = attr->ia_uid;
+		if (attr->ia_valid & ATTR_GID)
+			inode->i_gid = attr->ia_gid;
+		f2fs_mark_inode_dirty_sync(inode, true);
+		f2fs_unlock_op(F2FS_I_SB(inode));
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
@@ -1242,7 +1259,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	new_size = i_size_read(inode) - len;
 	truncate_pagecache(inode, new_size);
 
-	ret = f2fs_truncate_blocks(inode, new_size, true);
+	ret = f2fs_truncate_blocks(inode, new_size, true, false);
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
@@ -1427,7 +1444,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	f2fs_balance_fs(sbi, true);
 
 	down_write(&F2FS_I(inode)->i_mmap_sem);
-	ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
+	ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false);
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	if (ret)
 		return ret;