Hi Tejun,
I think we have to fix kernfs in order to fix refcnt leak in sysfs
and cgroupfs. This fix is for 3.14, but it creates conflicts for
cgroup-next.
====================
As mount() and kill_sb() is not a one-to-one match, we shoudn't get
ns refcnt unconditionally in sysfs_mount(), and instead we should
get the refcnt only when kernfs_mount() allocated a new superblock.
Signed-off-by: Li Zefan <lizefan@xxxxxxxxxx>
---
fs/kernfs/mount.c | 7 ++++++-
fs/sysfs/mount.c | 5 +++--
include/linux/kernfs.h | 9 +++++----
3 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 405279b..53ce420 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -132,6 +132,7 @@ const void *kernfs_super_ns(struct super_block *sb)
* @flags: mount flags specified for the mount
* @root: kernfs_root of the hierarchy being mounted
* @ns: optional namespace tag of the mount
+ * @new: tell the caller if we allocated a new superblock
*
* This is to be called from each kernfs user's file_system_type->mount()
* implementation, which should pass through the specified @fs_type and
@@ -141,12 +142,15 @@ const void *kernfs_super_ns(struct super_block *sb)
* The return value can be passed to the vfs layer verbatim.
*/
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, const void *ns,
+ bool *new_sb)
{
struct super_block *sb;
struct kernfs_super_info *info;
int error;
+ *new_sb = false;
+
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info)
return ERR_PTR(-ENOMEM);
@@ -166,6 +170,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
return ERR_PTR(error);
}
sb->s_flags |= MS_ACTIVE;
+ *new_sb = true;
}
return dget(sb->s_root);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 5c7fdd9..f5bea79 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
{
struct dentry *root;
void *ns;
+ bool new_sb;
if (!(flags & MS_KERNMOUNT)) {
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
}
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
- root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
- if (IS_ERR(root))
+ root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns, &new_sb);
+ if (IS_ERR(root) || !new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
return root;
}
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 649497a..1b1849f 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -279,7 +279,8 @@ void kernfs_notify(struct kernfs_node *kn);
const void *kernfs_super_ns(struct super_block *sb);
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns);
+ struct kernfs_root *root, const void *ns,
+ bool *new_sb);
void kernfs_kill_sb(struct super_block *sb);
void kernfs_init(void);
@@ -372,7 +373,7 @@ static inline const void *kernfs_super_ns(struct super_block *sb)
static inline struct dentry *
kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, const void *ns, bool *new_sb)
{ return ERR_PTR(-ENOSYS); }
static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -430,9 +431,9 @@ static inline int kernfs_rename(struct kernfs_node *kn,
static inline struct dentry *
kernfs_mount(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root)
+ struct kernfs_root *root, bool *new_sb)
{
- return kernfs_mount_ns(fs_type, flags, root, NULL);
+ return kernfs_mount_ns(fs_type, flags, root, NULL, new_sb);
}
#endif /* __LINUX_KERNFS_H */
--
1.8.0.2
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
