shmem: Add user and group quota support for tmpfs

index 2f2e0e618072..51d17655a6e1 100644
@@ -199,13 +199,14 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
 }
 
-static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
+static inline int shmem_inode_acct_block(struct inode *inode, long pages)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	int err = -ENOSPC;
 
 	if (shmem_acct_block(info->flags, pages))
-		return false;
+		return err;
 
 	if (sbinfo->max_blocks) {
 		if (percpu_counter_compare(&sbinfo->used_blocks,

@@ -214,11 +215,11 @@ static inline bool shmem_inode_acct_block(struct inode *inode, long pages)
 		percpu_counter_add(&sbinfo->used_blocks, pages);
 	}
 
-	return true;
+	return 0;
 
 unacct:
 	shmem_unacct_blocks(info->flags, pages);
-	return false;
+	return err;
 }
 
 static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages)

@@ -370,7 +371,7 @@ bool shmem_charge(struct inode *inode, long pages)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long flags;
 
-	if (!shmem_inode_acct_block(inode, pages))
+	if (shmem_inode_acct_block(inode, pages))
 		return false;
 
 	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */

@@ -1588,13 +1589,14 @@ static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode,
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct folio *folio;
 	int nr;
-	int err = -ENOSPC;
+	int err;
 
 	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
 		huge = false;
 	nr = huge ? HPAGE_PMD_NR : 1;
 
-	if (!shmem_inode_acct_block(inode, nr))
+	err = shmem_inode_acct_block(inode, nr);
+	if (err)
 		goto failed;
 
 	if (huge)

@@ -2445,7 +2447,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 	int ret;
 	pgoff_t max_off;
 
-	if (!shmem_inode_acct_block(inode, 1)) {
+	if (shmem_inode_acct_block(inode, 1)) {
 		/*
 		 * We may have got a page, returned -ENOENT triggering a retry,
 		 * and now we find ourselves with -ENOMEM. Release the page, to

index 51d17655a6e1..2a7b8060b6f4 100644
@@ -2365,67 +2365,74 @@ static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block
 	struct shmem_inode_info *info;
 	struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
 	ino_t ino;
+	int err;
+
+	err = shmem_reserve_inode(sb, &ino);
+	if (err)
+		return ERR_PTR(err);
 
-	if (shmem_reserve_inode(sb, &ino))
-		return NULL;
 
 	inode = new_inode(sb);
-	if (inode) {
-		inode->i_ino = ino;
-		inode_init_owner(idmap, inode, dir, mode);
-		inode->i_blocks = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-		inode->i_generation = get_random_u32();
-		info = SHMEM_I(inode);
-		memset(info, 0, (char *)inode - (char *)info);
-		spin_lock_init(&info->lock);
-		atomic_set(&info->stop_eviction, 0);
-		info->seals = F_SEAL_SEAL;
-		info->flags = flags & VM_NORESERVE;
-		info->i_crtime = inode->i_mtime;
-		info->fsflags = (dir == NULL) ? 0 :
-			SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
-		if (info->fsflags)
-			shmem_set_inode_flags(inode, info->fsflags);
-		INIT_LIST_HEAD(&info->shrinklist);
-		INIT_LIST_HEAD(&info->swaplist);
-		if (sbinfo->noswap)
-			mapping_set_unevictable(inode->i_mapping);
-		simple_xattrs_init(&info->xattrs);
-		cache_no_acl(inode);
-		mapping_set_large_folios(inode->i_mapping);
-
-		switch (mode & S_IFMT) {
-		default:
-			inode->i_op = &shmem_special_inode_operations;
-			init_special_inode(inode, mode, dev);
-			break;
-		case S_IFREG:
-			inode->i_mapping->a_ops = &shmem_aops;
-			inode->i_op = &shmem_inode_operations;
-			inode->i_fop = &shmem_file_operations;
-			mpol_shared_policy_init(&info->policy,
-						 shmem_get_sbmpol(sbinfo));
-			break;
-		case S_IFDIR:
-			inc_nlink(inode);
-			/* Some things misbehave if size == 0 on a directory */
-			inode->i_size = 2 * BOGO_DIRENT_SIZE;
-			inode->i_op = &shmem_dir_inode_operations;
-			inode->i_fop = &simple_dir_operations;
-			break;
-		case S_IFLNK:
-			/*
-			 * Must not load anything in the rbtree,
-			 * mpol_free_shared_policy will not be called.
-			 */
-			mpol_shared_policy_init(&info->policy, NULL);
-			break;
-		}
 
-		lockdep_annotate_inode_mutex_key(inode);
-	} else
+	if (!inode) {
 		shmem_free_inode(sb);
+		return ERR_PTR(-ENOSPC);
+	}
+
+	inode->i_ino = ino;
+	inode_init_owner(idmap, inode, dir, mode);
+	inode->i_blocks = 0;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+	inode->i_generation = get_random_u32();
+	info = SHMEM_I(inode);
+	memset(info, 0, (char *)inode - (char *)info);
+	spin_lock_init(&info->lock);
+	atomic_set(&info->stop_eviction, 0);
+	info->seals = F_SEAL_SEAL;
+	info->flags = flags & VM_NORESERVE;
+	info->i_crtime = inode->i_mtime;
+	info->fsflags = (dir == NULL) ? 0 :
+		SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
+	if (info->fsflags)
+		shmem_set_inode_flags(inode, info->fsflags);
+	INIT_LIST_HEAD(&info->shrinklist);
+	INIT_LIST_HEAD(&info->swaplist);
+	INIT_LIST_HEAD(&info->swaplist);
+	if (sbinfo->noswap)
+		mapping_set_unevictable(inode->i_mapping);
+	simple_xattrs_init(&info->xattrs);
+	cache_no_acl(inode);
+	mapping_set_large_folios(inode->i_mapping);
+
+	switch (mode & S_IFMT) {
+	default:
+		inode->i_op = &shmem_special_inode_operations;
+		init_special_inode(inode, mode, dev);
+		break;
+	case S_IFREG:
+		inode->i_mapping->a_ops = &shmem_aops;
+		inode->i_op = &shmem_inode_operations;
+		inode->i_fop = &shmem_file_operations;
+		mpol_shared_policy_init(&info->policy,
+					 shmem_get_sbmpol(sbinfo));
+		break;
+	case S_IFDIR:
+		inc_nlink(inode);
+		/* Some things misbehave if size == 0 on a directory */
+		inode->i_size = 2 * BOGO_DIRENT_SIZE;
+		inode->i_op = &shmem_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		break;
+	case S_IFLNK:
+		/*
+		 * Must not load anything in the rbtree,
+		 * mpol_free_shared_policy will not be called.
+		 */
+		mpol_shared_policy_init(&info->policy, NULL);
+		break;
+	}
+
+	lockdep_annotate_inode_mutex_key(inode);
 	return inode;
 }
 

@@ -3071,27 +3078,30 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	    struct dentry *dentry, umode_t mode, dev_t dev)
 {
 	struct inode *inode;
-	int error = -ENOSPC;
+	int error;
 
 	inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, dev, VM_NORESERVE);
-	if (inode) {
-		error = simple_acl_create(dir, inode);
-		if (error)
-			goto out_iput;
-		error = security_inode_init_security(inode, dir,
-						     &dentry->d_name,
-						     shmem_initxattrs, NULL);
-		if (error && error != -EOPNOTSUPP)
-			goto out_iput;
 
-		error = 0;
-		dir->i_size += BOGO_DIRENT_SIZE;
-		dir->i_ctime = dir->i_mtime = current_time(dir);
-		inode_inc_iversion(dir);
-		d_instantiate(dentry, inode);
-		dget(dentry); /* Extra count - pin the dentry in core */
-	}
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	error = simple_acl_create(dir, inode);
+	if (error)
+		goto out_iput;
+	error = security_inode_init_security(inode, dir,
+					     &dentry->d_name,
+					     shmem_initxattrs, NULL);
+	if (error && error != -EOPNOTSUPP)
+		goto out_iput;
+
+	error = 0;
+	dir->i_size += BOGO_DIRENT_SIZE;
+	dir->i_ctime = dir->i_mtime = current_time(dir);
+	inode_inc_iversion(dir);
+	d_instantiate(dentry, inode);
+	dget(dentry); /* Extra count - pin the dentry in core */
 	return error;
+
 out_iput:
 	iput(inode);
 	return error;

@@ -3102,20 +3112,26 @@ shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 	      struct file *file, umode_t mode)
 {
 	struct inode *inode;
-	int error = -ENOSPC;
+	int error;
 
 	inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE);
-	if (inode) {
-		error = security_inode_init_security(inode, dir,
-						     NULL,
-						     shmem_initxattrs, NULL);
-		if (error && error != -EOPNOTSUPP)
-			goto out_iput;
-		error = simple_acl_create(dir, inode);
-		if (error)
-			goto out_iput;
-		d_tmpfile(file, inode);
+
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
+		goto err_out;
 	}
+
+	error = security_inode_init_security(inode, dir,
+					     NULL,
+					     shmem_initxattrs, NULL);
+	if (error && error != -EOPNOTSUPP)
+		goto out_iput;
+	error = simple_acl_create(dir, inode);
+	if (error)
+		goto out_iput;
+	d_tmpfile(file, inode);
+
+err_out:
 	return finish_open_simple(file, error);
 out_iput:
 	iput(inode);

@@ -3290,8 +3306,9 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
 
 	inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0,
 				VM_NORESERVE);
-	if (!inode)
-		return -ENOSPC;
+
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
 	error = security_inode_init_security(inode, dir, &dentry->d_name,
 					     shmem_initxattrs, NULL);

@@ -3929,12 +3946,13 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 	struct shmem_options *ctx = fc->fs_private;
 	struct inode *inode;
 	struct shmem_sb_info *sbinfo;
+	int error = -ENOMEM;
 
 	/* Round up to L1_CACHE_BYTES to resist false sharing */
 	sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
 				L1_CACHE_BYTES), GFP_KERNEL);
 	if (!sbinfo)
-		return -ENOMEM;
+		return error;
 
 	sb->s_fs_info = sbinfo;
 

@@ -3997,8 +4015,10 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0,
 				VM_NORESERVE);
-	if (!inode)
+	if (IS_ERR(inode)) {
+		error = PTR_ERR(inode);
 		goto failed;
+	}
 	inode->i_uid = sbinfo->uid;
 	inode->i_gid = sbinfo->gid;
 	sb->s_root = d_make_root(inode);

@@ -4008,7 +4028,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 
 failed:
 	shmem_put_super(sb);
-	return -ENOMEM;
+	return error;
 }
 
 static int shmem_get_tree(struct fs_context *fc)

@@ -4377,10 +4397,16 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 #define shmem_vm_ops				generic_file_vm_ops
 #define shmem_anon_vm_ops			generic_file_vm_ops
 #define shmem_file_operations			ramfs_file_operations
-#define shmem_get_inode(idmap, sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
 #define shmem_acct_size(flags, size)		0
 #define shmem_unacct_size(flags, size)		do {} while (0)
 
+static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir,
+					    umode_t mode, dev_t dev, unsigned long flags)
+{
+	struct inode *inode = ramfs_get_inode(sb, dir, mode, dev);
+	return inode ? inode : ERR_PTR(-ENOSPC);
+}
+
 #endif /* CONFIG_SHMEM */
 
 /* common code */

@@ -4405,9 +4431,10 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 
 	inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL,
 				S_IFREG | S_IRWXUGO, 0, flags);
-	if (unlikely(!inode)) {
+
+	if (IS_ERR(inode)) {
 		shmem_unacct_size(flags, size);
-		return ERR_PTR(-ENOSPC);
+		return ERR_CAST(inode);
 	}
 	inode->i_flags |= i_flags;
 	inode->i_size = size;

index e3e4f4047657..4d826c369da2 100644
@@ -2367,7 +2367,7 @@ int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
 
 	if (!fmt)
 		return -ESRCH;
-	if (!sb->s_op->quota_write || !sb->s_op->quota_read ||
+	if (!sb->dq_op || !sb->s_qcop ||
 	    (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) {
 		error = -EINVAL;
 		goto out_fmt;

index 9029abd29b1c..7abfaf70b58a 100644
@@ -13,6 +13,10 @@
 
 /* inode in-kernel data */
 
+#ifdef CONFIG_TMPFS_QUOTA
+#define SHMEM_MAXQUOTAS 2
+#endif
+
 struct shmem_inode_info {
 	spinlock_t		lock;
 	unsigned int		seals;		/* shmem seals */

@@ -172,4 +176,12 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 #endif /* CONFIG_SHMEM */
 #endif /* CONFIG_USERFAULTFD */
 
+/*
+ * Used space is stored as unsigned 64-bit value in bytes but
+ * quota core supports only signed 64-bit values so use that
+ * as a limit
+ */
+#define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */
+#define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL
+
 #endif

index f17c9636a859..52090105b828 100644
@@ -77,6 +77,7 @@
 #define	QFMT_VFS_V0 2
 #define QFMT_OCFS2 3
 #define	QFMT_VFS_V1 4
+#define	QFMT_SHMEM 5
 
 /* Size of block in which space limits are passed through the quota
  * interface */

318 lines not on this page · raw message

index 7abfaf70b58a..1a568a0f542f 100644
@@ -31,6 +31,9 @@ struct shmem_inode_info {
 	atomic_t		stop_eviction;	/* hold when working on inode */
 	struct timespec64	i_crtime;	/* file creation time */
 	unsigned int		fsflags;	/* flags for FS_IOC_[SG]ETFLAGS */
+#ifdef CONFIG_TMPFS_QUOTA
+	struct dquot		*i_dquot[MAXQUOTAS];
+#endif
 	struct inode		vfs_inode;
 };
 

@@ -184,4 +187,9 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */
 #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL
 
+#ifdef CONFIG_TMPFS_QUOTA
+extern const struct dquot_operations shmem_quota_operations;
+extern struct quota_format_type shmem_quota_format;
+#endif /* CONFIG_TMPFS_QUOTA */
+
 #endif

342 lines not on this page · raw message

index 1a568a0f542f..c0058f3bba70 100644
@@ -42,6 +42,13 @@ struct shmem_inode_info {
 	(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL)
 #define SHMEM_FL_INHERITED		(FS_NODUMP_FL | FS_NOATIME_FL)
 
+struct shmem_quota_limits {
+	qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */
+	qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */
+	qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */
+	qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */
+};
+
 struct shmem_sb_info {
 	unsigned long max_blocks;   /* How many blocks are allowed */
 	struct percpu_counter used_blocks;  /* How many are allocated */

@@ -60,6 +67,7 @@ struct shmem_sb_info {
 	spinlock_t shrinklist_lock;   /* Protects shrinklist */
 	struct list_head shrinklist;  /* List of shinkable inodes */
 	unsigned long shrinklist_len; /* Length of shrinklist */
+	struct shmem_quota_limits qlimits; /* Default quota limits */
 };
 
 static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)

97 lines not on this page · raw message

index c0b531e2ef68..e349c0901bce 100644
@@ -166,6 +166,7 @@ static int shmem_acquire_dquot(struct dquot *dquot)
 {
 	struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type);
 	struct rb_node **n = &((struct rb_root *)info->dqi_priv)->rb_node;
+	struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info;
 	struct rb_node *parent = NULL, *new_node = NULL;
 	struct quota_id *new_entry, *entry;
 	qid_t id = from_kqid(&init_user_ns, dquot->dq_id);

@@ -195,6 +196,14 @@ static int shmem_acquire_dquot(struct dquot *dquot)
 	}
 
 	new_entry->id = id;
+	if (dquot->dq_id.type == USRQUOTA) {
+		new_entry->bhardlimit = sbinfo->qlimits.usrquota_bhardlimit;
+		new_entry->ihardlimit = sbinfo->qlimits.usrquota_ihardlimit;
+	} else if (dquot->dq_id.type == GRPQUOTA) {
+		new_entry->bhardlimit = sbinfo->qlimits.grpquota_bhardlimit;
+		new_entry->ihardlimit = sbinfo->qlimits.grpquota_ihardlimit;
+	}
+
 	new_node = &new_entry->node;
 	rb_link_node(new_node, parent, n);
 	rb_insert_color(new_node, (struct rb_root *)info->dqi_priv);

@@ -224,6 +233,29 @@ static int shmem_acquire_dquot(struct dquot *dquot)
 	return ret;
 }
 
+static bool shmem_is_empty_dquot(struct dquot *dquot)
+{
+	struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info;
+	qsize_t bhardlimit;
+	qsize_t ihardlimit;
+
+	if (dquot->dq_id.type == USRQUOTA) {
+		bhardlimit = sbinfo->qlimits.usrquota_bhardlimit;
+		ihardlimit = sbinfo->qlimits.usrquota_ihardlimit;
+	} else if (dquot->dq_id.type == GRPQUOTA) {
+		bhardlimit = sbinfo->qlimits.grpquota_bhardlimit;
+		ihardlimit = sbinfo->qlimits.grpquota_ihardlimit;
+	}
+
+	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
+		(dquot->dq_dqb.dqb_curspace == 0 &&
+		 dquot->dq_dqb.dqb_curinodes == 0 &&
+		 dquot->dq_dqb.dqb_bhardlimit == bhardlimit &&
+		 dquot->dq_dqb.dqb_ihardlimit == ihardlimit))
+		return true;
+
+	return false;
+}
 /*
  * Store limits from dquot in the tree unless it's fake. If it is fake
  * remove the id from the tree since there is no useful information in

@@ -261,7 +293,7 @@ static int shmem_release_dquot(struct dquot *dquot)
 	return -ENOENT;
 
 found:
-	if (test_bit(DQ_FAKE_B, &dquot->dq_flags)) {
+	if (shmem_is_empty_dquot(dquot)) {
 		/* Remove entry from the tree */
 		rb_erase(&entry->node, info->dqi_priv);
 		kfree(entry);