c61a2810a2
When freeing a deeply nested user namespace free_user_ns calls put_user_ns on it's parent which may in turn call free_user_ns again. When -fno-optimize-sibling-calls is passed to gcc one stack frame per user namespace is left on the stack, potentially overflowing the kernel stack. CONFIG_FRAME_POINTER forces -fno-optimize-sibling-calls so we can't count on gcc to optimize this code. Remove struct kref and use a plain atomic_t. Making the code more flexible and easier to comprehend. Make the loop in free_user_ns explict to guarantee that the stack does not overflow with CONFIG_FRAME_POINTER enabled. I have tested this fix with a simple program that uses unshare to create a deeply nested user namespace structure and then calls exit. With 1000 nesteuser namespaces before this change running my test program causes the kernel to die a horrible death. With 10,000,000 nested user namespaces after this change my test program runs to completion and causes no harm. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Pointed-out-by: Vasily Kulikov <segoon@openwall.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
86 lines
2 KiB
C
86 lines
2 KiB
C
#ifndef _LINUX_USER_NAMESPACE_H
|
|
#define _LINUX_USER_NAMESPACE_H
|
|
|
|
#include <linux/kref.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/err.h>
|
|
|
|
#define UID_GID_MAP_MAX_EXTENTS 5
|
|
|
|
struct uid_gid_map { /* 64 bytes -- 1 cache line */
|
|
u32 nr_extents;
|
|
struct uid_gid_extent {
|
|
u32 first;
|
|
u32 lower_first;
|
|
u32 count;
|
|
} extent[UID_GID_MAP_MAX_EXTENTS];
|
|
};
|
|
|
|
struct user_namespace {
|
|
struct uid_gid_map uid_map;
|
|
struct uid_gid_map gid_map;
|
|
struct uid_gid_map projid_map;
|
|
atomic_t count;
|
|
struct user_namespace *parent;
|
|
kuid_t owner;
|
|
kgid_t group;
|
|
unsigned int proc_inum;
|
|
};
|
|
|
|
extern struct user_namespace init_user_ns;
|
|
|
|
#ifdef CONFIG_USER_NS
|
|
|
|
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
|
|
{
|
|
if (ns)
|
|
atomic_inc(&ns->count);
|
|
return ns;
|
|
}
|
|
|
|
extern int create_user_ns(struct cred *new);
|
|
extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred);
|
|
extern void free_user_ns(struct user_namespace *ns);
|
|
|
|
static inline void put_user_ns(struct user_namespace *ns)
|
|
{
|
|
if (ns && atomic_dec_and_test(&ns->count))
|
|
free_user_ns(ns);
|
|
}
|
|
|
|
struct seq_operations;
|
|
extern struct seq_operations proc_uid_seq_operations;
|
|
extern struct seq_operations proc_gid_seq_operations;
|
|
extern struct seq_operations proc_projid_seq_operations;
|
|
extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
#else
|
|
|
|
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
|
|
{
|
|
return &init_user_ns;
|
|
}
|
|
|
|
static inline int create_user_ns(struct cred *new)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
static inline int unshare_userns(unsigned long unshare_flags,
|
|
struct cred **new_cred)
|
|
{
|
|
if (unshare_flags & CLONE_NEWUSER)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static inline void put_user_ns(struct user_namespace *ns)
|
|
{
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif /* _LINUX_USER_H */
|