efivarfs: fix error on write to new variable leaving remnants

Make variable cleanup go through the fops release mechanism and use
zero inode size as the indicator to delete the file.  Since all EFI
variables must have an initial u32 attribute, zero size occurs either
because the update deleted the variable or because an unsuccessful
write after create caused the size never to be set in the first place.
In the case of multiple racing opens and closes, the open is counted
to ensure that the zero size check is done on the last close.

Even though this fixes the bug that a create either not followed by a
write or followed by a write that errored would leave a remnant file
for the variable, the file will appear momentarily globally visible
until the last close of the fd deletes it.  This is safe because the
normal filesystem operations will mediate any races; however, it is
still possible for a directory listing at that instant between create
and close contain a zero size variable that doesn't exist in the EFI
table.

Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>

Author: James Bottomley

fs/efivarfs/file.c

@@ -36,28 +36,41 @@ static ssize_t efivarfs_file_write(struct file *file,
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	inode_lock(inode);
+	if (var->removed) {
+		/*
+		 * file got removed; don't allow a set.  Caused by an
+		 * unsuccessful create or successful delete write
+		 * racing with us.
+		 */
+		bytes = -EIO;
+		goto out;
+	}
+
 	bytes = efivar_entry_set_get_size(var, attributes, &datasize,
 					  data, &set);
-	if (!set && bytes) {
+	if (!set) {
 		if (bytes == -ENOENT)
 			bytes = -EIO;
 		goto out;
 	}
 
 	if (bytes == -ENOENT) {
-		drop_nlink(inode);
-		d_delete(file->f_path.dentry);
-		dput(file->f_path.dentry);
+		/*
+		 * zero size signals to release that the write deleted
+		 * the variable
+		 */
+		i_size_write(inode, 0);
 	} else {
-		inode_lock(inode);
 		i_size_write(inode, datasize + sizeof(attributes));
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
-		inode_unlock(inode);
 	}
 
 	bytes = count;
 
 out:
+	inode_unlock(inode);
+
 	kfree(data);
 
 	return bytes;
@@ -106,8 +119,36 @@ static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf,
 	return size;
 }
 
+static int efivarfs_file_release(struct inode *inode, struct file *file)
+{
+	struct efivar_entry *var = inode->i_private;
+
+	inode_lock(inode);
+	var->removed = (--var->open_count == 0 && i_size_read(inode) == 0);
+	inode_unlock(inode);
+
+	if (var->removed)
+		simple_recursive_removal(file->f_path.dentry, NULL);
+
+	return 0;
+}
+
+static int efivarfs_file_open(struct inode *inode, struct file *file)
+{
+	struct efivar_entry *entry = inode->i_private;
+
+	file->private_data = entry;
+
+	inode_lock(inode);
+	entry->open_count++;
+	inode_unlock(inode);
+
+	return 0;
+}
+
 const struct file_operations efivarfs_file_operations = {
-	.open	= simple_open,
-	.read	= efivarfs_file_read,
-	.write	= efivarfs_file_write,
+	.open		= efivarfs_file_open,
+	.read		= efivarfs_file_read,
+	.write		= efivarfs_file_write,
+	.release	= efivarfs_file_release,
 };

fs/efivarfs/internal.h

@@ -27,6 +27,8 @@ struct efi_variable {
 struct efivar_entry {
 	struct efi_variable var;
 	struct inode vfs_inode;
+	unsigned long open_count;
+	bool removed;
 };
 
 static inline struct efivar_entry *efivar_entry(struct inode *inode)

fs/efivarfs/super.c

@@ -47,6 +47,7 @@ static struct inode *efivarfs_alloc_inode(struct super_block *sb)
 		return NULL;
 
 	inode_init_once(&entry->vfs_inode);
+	entry->removed = false;
 
 	return &entry->vfs_inode;
 }