| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <00043e79-3647-3979-07bb-27039921efb4@codeaurora.org>
Date: Wed, 25 Oct 2017 14:09:54 +0530
From: Prateek Sood <prsood@...eaurora.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: tj@...nel.org, lizefan@...wei.com, cgroups@...r.kernel.org,
mingo@...nel.org, longman@...hat.com, boqun.feng@...il.com,
tglx@...utronix.de, linux-kernel@...r.kernel.org,
sramana@...eaurora.org
Subject: Re: [PATCH] cgroup/cpuset: remove circular dependency deadlock
On 10/11/2017 03:18 PM, Peter Zijlstra wrote:
> On Mon, Oct 09, 2017 at 06:57:46PM +0530, Prateek Sood wrote:
>> On 09/07/2017 11:21 PM, Peter Zijlstra wrote:
>
>>> But if you invert these locks, the need for cpuset_hotplug_workfn() goes
>>> away, at least for the CPU part, and we can make in synchronous again.
>>> Yay!!
>
>> The callback making a call to cpuset_hotplug_workfn()in hotplug path are
>> [CPUHP_AP_ACTIVE] = {
>> .name = "sched:active",
>> .startup.single = sched_cpu_activate,
>> .teardown.single = sched_cpu_deactivate,
>> },
>>
>> if we make cpuset_hotplug_workfn() synchronous, deadlock might happen:
>> _cpu_down()
>> cpus_write_lock() //held
>> cpuhp_kick_ap_work()
>> cpuhp_kick_ap()
>> __cpuhp_kick_ap()
>> wake_up_process() //cpuhp_thread_fun
>> wait_for_ap_thread() //wait for complete from cpuhp_thread_fun()
>>
>> cpuhp_thread_fun()
>> cpuhp_invoke_callback()
>> sched_cpu_deactivate()
>> cpuset_cpu_inactive()
>> cpuset_update_active_cpus()
>> cpuset_hotplug_work()
>> rebuild_sched_domains()
>> cpus_read_lock() //waiting as acquired in _cpu_down()
>
> Well, duh, don't use rebuild_sched_domains() 'obviously' :-) use
> rebuild_sched_domains_cpuslocked() instead and it works just fine.
>
> After applying your patch, the below boots and survives a hotplug.
>
> ---
> include/linux/cpuset.h | 6 ------
> kernel/cgroup/cpuset.c | 30 +++++++++---------------------
> kernel/power/process.c | 2 --
> kernel/sched/core.c | 1 -
> 4 files changed, 9 insertions(+), 30 deletions(-)
>
> --- a/include/linux/cpuset.h
> +++ b/include/linux/cpuset.h
> @@ -51,9 +51,7 @@ static inline void cpuset_dec(void)
>
> extern int cpuset_init(void);
> extern void cpuset_init_smp(void);
> -extern void cpuset_force_rebuild(void);
> extern void cpuset_update_active_cpus(void);
> -extern void cpuset_wait_for_hotplug(void);
> extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
> extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
> extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
> @@ -166,15 +164,11 @@ static inline bool cpusets_enabled(void)
> static inline int cpuset_init(void) { return 0; }
> static inline void cpuset_init_smp(void) {}
>
> -static inline void cpuset_force_rebuild(void) { }
> -
> static inline void cpuset_update_active_cpus(void)
> {
> partition_sched_domains(1, NULL, NULL);
> }
>
> -static inline void cpuset_wait_for_hotplug(void) { }
> -
> static inline void cpuset_cpus_allowed(struct task_struct *p,
> struct cpumask *mask)
> {
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -833,7 +833,12 @@ static void rebuild_sched_domains_cpuslo
> cpumask_var_t *doms;
> int ndoms;
>
> + /*
> + * When called during hotplug, this lock is held by the calling
> + * thread, not cpuhp_thread_fun :/
> + *
> lockdep_assert_cpus_held();
> + */
> lockdep_assert_held(&cpuset_mutex);
>
> /*
> @@ -2281,13 +2286,6 @@ static void cpuset_hotplug_update_tasks(
> mutex_unlock(&cpuset_mutex);
> }
>
> -static bool force_rebuild;
> -
> -void cpuset_force_rebuild(void)
> -{
> - force_rebuild = true;
> -}
> -
> /**
> * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
> *
> @@ -2362,25 +2360,15 @@ static void cpuset_hotplug_workfn(struct
> }
>
> /* rebuild sched domains if cpus_allowed has changed */
> - if (cpus_updated || force_rebuild) {
> - force_rebuild = false;
> + if (cpus_updated)
> rebuild_sched_domains();
> - }
> }
>
> void cpuset_update_active_cpus(void)
> {
> - /*
> - * We're inside cpu hotplug critical region which usually nests
> - * inside cgroup synchronization. Bounce actual hotplug processing
> - * to a work item to avoid reverse locking order.
> - */
> - schedule_work(&cpuset_hotplug_work);
> -}
> -
> -void cpuset_wait_for_hotplug(void)
> -{
> - flush_work(&cpuset_hotplug_work);
> + mutex_lock(&cpuset_mutex);
> + rebuild_sched_domains_cpuslocked();
> + mutex_unlock(&cpuset_mutex);
> }
>
> /*
> --- a/kernel/power/process.c
> +++ b/kernel/power/process.c
> @@ -203,8 +203,6 @@ void thaw_processes(void)
> __usermodehelper_set_disable_depth(UMH_FREEZING);
> thaw_workqueues();
>
> - cpuset_wait_for_hotplug();
> -
> read_lock(&tasklist_lock);
> for_each_process_thread(g, p) {
> /* No other threads should have PF_SUSPEND_TASK set */
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5598,7 +5598,6 @@ static void cpuset_cpu_active(void)
> * restore the original sched domains by considering the
> * cpuset configurations.
> */
> - cpuset_force_rebuild();
> }
> cpuset_update_active_cpus();
> }
>
Thanks Peter for sharing the patch and test results.
> void cpuset_update_active_cpus(void)
> {
> - /*
> - * We're inside cpu hotplug critical region which usually nests
> - * inside cgroup synchronization. Bounce actual hotplug processing
> - * to a work item to avoid reverse locking order.
> - */
> - schedule_work(&cpuset_hotplug_work);
> -}
> -
> -void cpuset_wait_for_hotplug(void)
> -{
> - flush_work(&cpuset_hotplug_work);
> + mutex_lock(&cpuset_mutex);
> + rebuild_sched_domains_cpuslocked();
> + mutex_unlock(&cpuset_mutex);
> }
In the above patch rebuild_sched_domains_cpuslocked() has been
used directly. Earlier cpuset_hotplug_update_tasks() was also
called from cpuset_hotplug_workfn(). So migration of tasks
related to cgroup which has empty cpuset would not happen
during cpu hotplug.
Could you please help in understanding more on this.
--
Qualcomm India Private Limited, on behalf of Qualcomm Innovation
Center, Inc., is a member of Code Aurora Forum, a Linux Foundation
Collaborative Project
Powered by blists - more mailing lists