[CIFS] fix small memory leak in an error path in new posix mkdir

There is a small memory leak in fs/cifs/inode.c::cifs_mkdir().
Storage for 'pInfo' is allocated with kzalloc(), but if the call
to CIFSPOSIXCreate(...) happens to return 0 and pInfo->Type == -1,
then we'll jump to the 'mkdir_get_info' label without freeing the
storage allocated for 'pInfo'.
This patch adds a kfree() call to free the storage just before
jumping to the label, thus getting rid of the leak.

Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
This commit is contained in:
Steve French 2007-09-16 23:12:47 +00:00
parent a23d306981
commit 5a07cdf86c

View file

@ -930,8 +930,10 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
d_drop(direntry);
} else {
int obj_type;
if (pInfo->Type == -1) /* no return info - go query */
if (pInfo->Type == -1) /* no return info - go query */ {
kfree(pInfo);
goto mkdir_get_info;
}
/*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need
to set uid/gid */
inc_nlink(inode);
@ -941,8 +943,10 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
direntry->d_op = &cifs_dentry_ops;
newinode = new_inode(inode->i_sb);
if (newinode == NULL)
if (newinode == NULL) {
kfree(pInfo);
goto mkdir_get_info;
}
/* Is an i_ino of zero legal? */
/* Are there sanity checks we can use to ensure that
the server is really filling in that field? */