f2fs: support plain user/group quota

This patch adds to support plain user/group quota.

Change Note by Jaegeuk Kim.

- Use f2fs page cache for quota files in order to consider garbage collection.
  so, quota files are not tolerable for sudden power-cuts, so user needs to do
  quotacheck.

- setattr() calls dquot_transfer which will transfer inode->i_blocks.
  We can't reclaim that during f2fs_evict_inode(). So, we need to count
  node blocks as well in order to match i_blocks with dquot's space.

  Note that, Chao wrote a patch to count inode->i_blocks without inode block.
  (f2fs: don't count inode block in in-memory inode.i_blocks)

- in f2fs_remount, we need to make RW in prior to dquot_resume.

- handle fault_injection case during f2fs_quota_off_umount

- TODO: Project quota

Signed-off-by: Chao Yu <[email protected]>
Signed-off-by: Jaegeuk Kim <[email protected]>

Author: chaseyu

Documentation/filesystems/f2fs.txt

@@ -162,6 +162,8 @@ mode=%s                Control block allocation mode which supports "adaptive"
                        writes towards main area.
 io_bits=%u             Set the bit size of write IO requests. It should be set
                        with "mode=lfs".
+usrquota               Enable plain user disk quota accounting.
+grpquota               Enable plain group disk quota accounting.
 
 ================================================================================
 DEBUGFS ENTRIES

fs/f2fs/data.c

@@ -491,14 +491,15 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	int err;
 
 	if (!count)
 		return 0;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 	trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
 						dn->ofs_in_node, count);
@@ -749,6 +750,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct node_info ni;
 	pgoff_t fofs;
 	blkcnt_t count = 1;
+	int err;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
@@ -757,8 +759,8 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (dn->data_blkaddr == NEW_ADDR)
 		goto alloc;
 
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 alloc:
 	get_node_info(sbi, dn->nid, &ni);

fs/f2fs/f2fs.h

@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/quotaops.h>
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 #include <linux/fscrypt_supp.h>
 #else
@@ -88,6 +89,8 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
 #define F2FS_MOUNT_ADAPTIVE		0x00020000
 #define F2FS_MOUNT_LFS			0x00040000
+#define F2FS_MOUNT_USRQUOTA		0x00080000
+#define F2FS_MOUNT_GRPQUOTA		0x00100000
 
 #define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -521,6 +524,12 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	loff_t	last_disk_size;		/* lastly written file size */
 
+#ifdef CONFIG_QUOTA
+	struct dquot *i_dquot[MAXQUOTAS];
+
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
 	struct list_head dirty_list;	/* dirty list for dirs and files */
 	struct list_head gdirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
@@ -1376,17 +1385,23 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 	return ofs == XATTR_NODE_OFFSET;
 }
 
-static inline void f2fs_i_blocks_write(struct inode *, block_t, bool);
-static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
+static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 				 struct inode *inode, blkcnt_t *count)
 {
-	blkcnt_t diff;
+	blkcnt_t diff = 0, release = 0;
 	block_t avail_user_block_count;
+	int ret;
+
+	ret = dquot_reserve_block(inode, *count);
+	if (ret)
+		return ret;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_BLOCK)) {
 		f2fs_show_injection_info(FAULT_BLOCK);
-		return false;
+		release = *count;
+		goto enospc;
 	}
 #endif
 	/*
@@ -1401,17 +1416,24 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
 	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
 		diff = sbi->total_valid_block_count - avail_user_block_count;
 		*count -= diff;
+		release = diff;
 		sbi->total_valid_block_count = avail_user_block_count;
 		if (!*count) {
 			spin_unlock(&sbi->stat_lock);
 			percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
-			return false;
+			goto enospc;
 		}
 	}
 	spin_unlock(&sbi->stat_lock);
 
-	f2fs_i_blocks_write(inode, *count, true);
-	return true;
+	if (release)
+		dquot_release_reservation_block(inode, release);
+	f2fs_i_blocks_write(inode, *count, true, true);
+	return 0;
+
+enospc:
+	dquot_release_reservation_block(inode, release);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
@@ -1425,7 +1447,7 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
-	f2fs_i_blocks_write(inode, count, false);
+	f2fs_i_blocks_write(inode, count, false, true);
 }
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1554,40 +1576,52 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
 }
 
-static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
+static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
 					struct inode *inode, bool is_inode)
 {
 	block_t	valid_block_count;
 	unsigned int valid_node_count;
+	bool quota = inode && !is_inode;
+
+	if (quota) {
+		int ret = dquot_reserve_block(inode, 1);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock(&sbi->stat_lock);
 
 	valid_block_count = sbi->total_valid_block_count + 1;
 	if (unlikely(valid_block_count + sbi->reserved_blocks >
 						sbi->user_block_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
 	valid_node_count = sbi->total_valid_node_count + 1;
 	if (unlikely(valid_node_count > sbi->total_node_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
+	sbi->total_valid_node_count++;
+	sbi->total_valid_block_count++;
+	spin_unlock(&sbi->stat_lock);
+
 	if (inode) {
 		if (is_inode)
 			f2fs_mark_inode_dirty_sync(inode, true);
 		else
-			f2fs_i_blocks_write(inode, 1, true);
+			f2fs_i_blocks_write(inode, 1, true, true);
 	}
 
-	sbi->total_valid_node_count++;
-	sbi->total_valid_block_count++;
-	spin_unlock(&sbi->stat_lock);
-
 	percpu_counter_inc(&sbi->alloc_valid_block_count);
-	return true;
+	return 0;
+
+enospc:
+	if (quota)
+		dquot_release_reservation_block(inode, 1);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
@@ -1599,12 +1633,13 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
 	f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
 
-	if (!is_inode)
-		f2fs_i_blocks_write(inode, 1, false);
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
 
 	spin_unlock(&sbi->stat_lock);
+
+	if (!is_inode)
+		f2fs_i_blocks_write(inode, 1, false, true);
 }
 
 static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1879,14 +1914,21 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 }
 
 static inline void f2fs_i_blocks_write(struct inode *inode,
-					block_t diff, bool add)
+					block_t diff, bool add, bool claim)
 {
 	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
 	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
-	blkcnt_t sectors = diff << F2FS_LOG_SECTORS_PER_BLOCK;
 
-	inode->i_blocks = add ? inode->i_blocks + sectors :
-				inode->i_blocks - sectors;
+	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
+	if (add) {
+		if (claim)
+			dquot_claim_block(inode, diff);
+		else
+			dquot_alloc_block_nofail(inode, diff);
+	} else {
+		dquot_free_block(inode, diff);
+	}
+
 	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);

fs/f2fs/file.c

@@ -442,11 +442,10 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
-	int ret = generic_file_open(inode, filp);
 	struct dentry *dir;
 
-	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = fscrypt_get_encryption_info(inode);
+	if (f2fs_encrypted_inode(inode)) {
+		int ret = fscrypt_get_encryption_info(inode);
 		if (ret)
 			return -EACCES;
 		if (!fscrypt_has_encryption_key(inode))
@@ -459,7 +458,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 		return -EPERM;
 	}
 	dput(dir);
-	return ret;
+	return dquot_file_open(inode, filp);
 }
 
 int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -710,6 +709,20 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		return err;
 
+	if (is_quota_modification(inode, attr)) {
+		err = dquot_initialize(inode);
+		if (err)
+			return err;
+	}
+	if ((attr->ia_valid & ATTR_UID &&
+		!uid_eq(attr->ia_uid, inode->i_uid)) ||
+		(attr->ia_valid & ATTR_GID &&
+		!gid_eq(attr->ia_gid, inode->i_gid))) {
+		err = dquot_transfer(inode, attr);
+		if (err)
+			return err;
+	}
+
 	if (attr->ia_valid & ATTR_SIZE) {
 		if (f2fs_encrypted_inode(inode)) {
 			err = fscrypt_get_encryption_info(inode);
@@ -996,9 +1009,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 
 				if (do_replace[i]) {
 					f2fs_i_blocks_write(src_inode,
-								1, false);
+							1, false, false);
 					f2fs_i_blocks_write(dst_inode,
-								1, true);
+							1, true, false);
 					f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
 					blkaddr[i], ni.version, true, false);
 
@@ -1523,6 +1536,13 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 
 	inode_lock(inode);
 
+	/* Is it quota file? Do not allow user to mess with it */
+	if (IS_NOQUOTA(inode)) {
+		inode_unlock(inode);
+		ret = -EPERM;
+		goto unlock_out;
+	}
+
 	flags = f2fs_mask_flags(inode->i_mode, flags);
 
 	oldflags = fi->i_flags;
@@ -1542,7 +1562,7 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	inode->i_ctime = current_time(inode);
 	f2fs_set_inode_flags(inode);
 	f2fs_mark_inode_dirty_sync(inode, false);
-
+unlock_out:
 	inode_unlock(inode);
 out:
 	mnt_drop_write_file(filp);

fs/f2fs/inode.c

@@ -373,6 +373,8 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
+	dquot_initialize(inode);
+
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 
@@ -405,8 +407,11 @@ void f2fs_evict_inode(struct inode *inode)
 
 	if (err)
 		update_inode_page(inode);
+	dquot_free_inode(inode);
 	sb_end_intwrite(inode->i_sb);
 no_delete:
+	dquot_drop(inode);
+
 	stat_dec_inline_xattr(inode);
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);