rcu: Grace-period initialization excludes only RCU notifier
Kirill noted the following deadlock cycle on shutdown involving padata:
> With commit 755609a908
I've got deadlock on
> poweroff.
>
> It guess it happens because of race for cpu_hotplug.lock:
>
> CPU A CPU B
> disable_nonboot_cpus()
> _cpu_down()
> cpu_hotplug_begin()
> mutex_lock(&cpu_hotplug.lock);
> __cpu_notify()
> padata_cpu_callback()
> __padata_remove_cpu()
> padata_replace()
> synchronize_rcu()
> rcu_gp_kthread()
> get_online_cpus();
> mutex_lock(&cpu_hotplug.lock);
It would of course be good to eliminate grace-period delays from
CPU-hotplug notifiers, but that is a separate issue. Deadlock is
not an appropriate diagnostic for excessive CPU-hotplug latency.
Fortunately, grace-period initialization does not actually need to
exclude all of the CPU-hotplug operation, but rather only RCU's own
CPU_UP_PREPARE and CPU_DEAD CPU-hotplug notifiers. This commit therefore
introduces a new per-rcu_state onoff_mutex that provides the required
concurrency control in place of the get_online_cpus() that was previously
in rcu_gp_init().
Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Kirill A. Shutemov <kirill@shutemov.name>
This commit is contained in:
parent
cb349ca954
commit
a4fbe35a12
2 changed files with 16 additions and 11 deletions
|
@ -394,11 +394,17 @@ struct rcu_state {
|
|||
struct rcu_head **orphan_donetail; /* Tail of above. */
|
||||
long qlen_lazy; /* Number of lazy callbacks. */
|
||||
long qlen; /* Total number of callbacks. */
|
||||
/* End of fields guarded by onofflock. */
|
||||
|
||||
struct mutex onoff_mutex; /* Coordinate hotplug & GPs. */
|
||||
|
||||
struct mutex barrier_mutex; /* Guards barrier fields. */
|
||||
atomic_t barrier_cpu_count; /* # CPUs waiting on. */
|
||||
struct completion barrier_completion; /* Wake at barrier end. */
|
||||
unsigned long n_barrier_done; /* ++ at start and end of */
|
||||
/* _rcu_barrier(). */
|
||||
/* End of fields guarded by barrier_mutex. */
|
||||
|
||||
unsigned long jiffies_force_qs; /* Time at which to invoke */
|
||||
/* force_quiescent_state(). */
|
||||
unsigned long n_force_qs; /* Number of calls to */
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue