Re: [PATCH v2] cpufreq: fix race on cpufreq online

[Rafael J. Wysocki]

On Tue, May 10, 2022 at 5:28 PM Schspa Shi <schspa@xxxxxxxxx> wrote:
>
> When cpufreq online failed, policy->cpus are not empty while
> cpufreq sysfs file available, we may access some data freed.
>
> Take policy->clk as an example:
>
> static int cpufreq_online(unsigned int cpu)
> {
>   ...
>   // policy->cpus != 0 at this time
>   down_write(&policy->rwsem);
>   ret = cpufreq_add_dev_interface(policy);
>   up_write(&policy->rwsem);
>
>   down_write(&policy->rwsem);
>   ...
>   /* cpufreq nitialization fails in some cases */
>   if (cpufreq_driver->get && has_target()) {
>     policy->cur = cpufreq_driver->get(policy->cpu);
>     if (!policy->cur) {
>       ret = -EIO;
>       pr_err("%s: ->get() failed\n", __func__);
>       goto out_destroy_policy;
>     }
>   }
>   ...
>   up_write(&policy->rwsem);
>   ...
>
>   return 0;
>
> out_destroy_policy:
>         for_each_cpu(j, policy->real_cpus)
>                 remove_cpu_dev_symlink(policy, get_cpu_device(j));
>     up_write(&policy->rwsem);
> ...
> out_exit_policy:
>   if (cpufreq_driver->exit)
>     cpufreq_driver->exit(policy);
>       clk_put(policy->clk);
>       // policy->clk is a wild pointer
> ...
>                                     ^
>                                     |
>                             Another process access
>                             __cpufreq_get
>                               cpufreq_verify_current_freq
>                                 cpufreq_generic_get
>                                   // acces wild pointer of policy->clk;
>                                     |
>                                     |
> out_offline_policy:                 |
>   cpufreq_policy_free(policy);      |
>     // deleted here, and will wait for no body reference
>     cpufreq_policy_put_kobj(policy);
> }
>
> We can fix it by clear the policy->cpus mask.
> Both show_scaling_cur_freq and show_cpuinfo_cur_freq will return an
> error by checking this mask, thus avoiding UAF.
>
> Signed-off-by: Schspa Shi <schspa@xxxxxxxxx>
>
> ---
>
> Changelog:
> v1 -> v2:
>         - Fix bad critical region enlarge which causes uninitialized
>           unlock.
> ---
>  drivers/cpufreq/cpufreq.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
> index 80f535cc8a75..8edfa840dd74 100644
> --- a/drivers/cpufreq/cpufreq.c
> +++ b/drivers/cpufreq/cpufreq.c
> @@ -1337,12 +1337,12 @@ static int cpufreq_online(unsigned int cpu)
>                 down_write(&policy->rwsem);
>                 policy->cpu = cpu;
>                 policy->governor = NULL;
> -               up_write(&policy->rwsem);
>         } else {
>                 new_policy = true;
>                 policy = cpufreq_policy_alloc(cpu);
>                 if (!policy)
>                         return -ENOMEM;
> +               down_write(&policy->rwsem);
>         }
>
>         if (!new_policy && cpufreq_driver->online) {

You seem to have missed the down_write() before the

cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);

statement.

It needs to be removed, because the semaphore is already being held
for writing at that point after the changes above.

> @@ -1533,7 +1533,7 @@ static int cpufreq_online(unsigned int cpu)
>         for_each_cpu(j, policy->real_cpus)
>                 remove_cpu_dev_symlink(policy, get_cpu_device(j));
>
> -       up_write(&policy->rwsem);
> +       cpumask_clear(policy->cpus);
>
>  out_offline_policy:
>         if (cpufreq_driver->offline)
> @@ -1542,6 +1542,7 @@ static int cpufreq_online(unsigned int cpu)
>  out_exit_policy:
>         if (cpufreq_driver->exit)
>                 cpufreq_driver->exit(policy);
> +       up_write(&policy->rwsem);
>
>  out_free_policy:
>         cpufreq_policy_free(policy);
> --