提交 74bd9b82 编写于 作者: Z Zhang Qiao 提交者: Yang Yingliang

sched: Fix sched_fork() access an invalid sched_task_group

hulk inclusion
category: bugfix
bugzilla: 177205, https://gitee.com/openeuler/kernel/issues/I484Y1
CVE: NA

--------------------------------

There is a small race between copy_process() and sched_fork()
where child->sched_task_group point to an already freed pointer.

parent doing fork()      | someone moving the parent
				to another cgroup
-------------------------------+-------------------------------
copy_process()
     + dup_task_struct()<1>
                                parent move to another cgroup,
                                and free the old cgroup. <2>
     + sched_fork()
       + __set_task_cpu()<3>
         + task_fork_fair()
           + sched_slice()<4>

In the worst case, this bug can lead to "use-after-free" and
cause panic as shown above,
(1)parent copy its sched_task_group to child at <1>;
(2)someone move the parent to another cgroup and free the old
   cgroup at <2>;
(3)the sched_task_group and cfs_rq that belong to the old cgroup
   will be accessed at <3> and <4>, which cause a panic:

[89249.732198] BUG: unable to handle kernel NULL pointer
dereference at 0000000000000000
[89249.732701] PGD 8000001fa0a86067 P4D 8000001fa0a86067 PUD
2029955067 PMD 0
[89249.733005] Oops: 0000 [#1] SMP PTI
[89249.733288] CPU: 7 PID: 648398 Comm: ebizzy Kdump: loaded
Tainted: G           OE    --------- -  - 4.18.0.x86_64+ #1
[89249.734318] RIP: 0010:sched_slice+0x84/0xc0
....
[89249.737910] Call Trace:
[89249.738181]  task_fork_fair+0x81/0x120
[89249.738457]  sched_fork+0x132/0x240
[89249.738732]  copy_process.part.5+0x675/0x20e0
[89249.739010]  ? __handle_mm_fault+0x63f/0x690
[89249.739286]  _do_fork+0xcd/0x3b0
[89249.739558]  do_syscall_64+0x5d/0x1d0
[89249.739830]  entry_SYSCALL_64_after_hwframe+0x65/0xca
[89249.740107] RIP: 0033:0x7f04418cd7e1

When a new process is forked, cgroup_post_fork() associates it
with the cgroup of its parent. Therefore this commit move the
__set_task_cpu() and task_fork() that access some cgroup-related
fields(sched_task_group and cfs_rq) to sched_post_fork() and
call sched_post_fork() after cgroup_post_fork().

Fixes: 8323f26c ("sched: Fix race in task_group")
Signed-off-by: NZhang Qiao <zhangqiao22@huawei.com>
Reviewed-by: NChen Hui <judy.chenhui@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>
上级 64cf0fac
......@@ -33,6 +33,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_post_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);
void __noreturn do_task_dead(void);
......
......@@ -2156,6 +2156,7 @@ static __latent_entropy struct task_struct *copy_process(
proc_fork_connector(p);
cgroup_post_fork(p);
sched_post_fork(p);
cgroup_threadgroup_change_end(current);
perf_event_fork(p);
......
......@@ -2295,8 +2295,6 @@ static inline void init_schedstats(void) {}
*/
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
__sched_fork(clone_flags, p);
/*
* We mark the process as NEW here. This guarantees that
......@@ -2340,6 +2338,26 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
init_entity_runnable_average(&p->se);
#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
p->on_cpu = 0;
#endif
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
return 0;
}
void sched_post_fork(struct task_struct *p)
{
unsigned long flags;
/*
* The child is not yet in the pid-hash so no cgroup attach races,
* and the cgroup is pinned to this child due to cgroup_fork()
......@@ -2357,20 +2375,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
p->on_cpu = 0;
#endif
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
return 0;
}
unsigned long to_ratio(u64 period, u64 runtime)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册