Re: freezer problems

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Wed, Feb 21, 2007 at 07:13:40PM +0100, Rafael J. Wysocki wrote:
> On Wednesday, 21 February 2007 19:14, Paul E. McKenney wrote:
> > On Tue, Feb 20, 2007 at 07:29:01PM +0100, Rafael J. Wysocki wrote:
> > > On Tuesday, 20 February 2007 01:32, Rafael J. Wysocki wrote:
> > > > On Tuesday, 20 February 2007 01:12, Oleg Nesterov wrote:
> > > > Hm.  In the case discussed above we have a task that's right before calling
> > > > frozen_process(), so we can't thaw it, because it's not frozen.  It will be
> > > > frozen just in a while, but try_to_freeze_tasks() and thaw_tasks() have no
> > > > way to check this.
> > > > 
> > > > I think to close this race the refrigerator should check TIF_FREEZE and set
> > > > PF_FROZEN _and_ reset TIF_FREEZE under a lock that would also have to be
> > > > taken by try_to_freeze_tasks() in the beginning of the error path.  This will
> > > > ensure that all tasks either freeze themselves before the error path in
> > > > try_to_freeze_tasks() is executed, or remain unfrozen.
> > > > 
> > > > I'll try to prepare a patch to illustrate this, but right now I'm too tired to
> > > > do it. :-)
> > > 
> > > Something like this, perhaps:
> > > 
> > > ---
> > >  include/linux/freezer.h |   10 +++-------
> > >  kernel/power/process.c  |   18 ++++++++++++++++--
> > >  2 files changed, 19 insertions(+), 9 deletions(-)
> > > 
> > > Index: linux-2.6.20-mm2/include/linux/freezer.h
> > > ===================================================================
> > > --- linux-2.6.20-mm2.orig/include/linux/freezer.h
> > > +++ linux-2.6.20-mm2/include/linux/freezer.h
> > > @@ -58,17 +58,13 @@ static inline void frozen_process(struct
> > >  	clear_tsk_thread_flag(p, TIF_FREEZE);
> > >  }
> > > 
> > > -extern void refrigerator(void);
> > > +extern int refrigerator(void);
> > >  extern int freeze_processes(void);
> > >  extern void thaw_processes(void);
> > > 
> > >  static inline int try_to_freeze(void)
> > >  {
> > > -	if (freezing(current)) {
> > > -		refrigerator();
> > > -		return 1;
> > > -	} else
> > > -		return 0;
> > > +	return refrigerator();
> > >  }
> > > 
> > >  /*
> > > @@ -104,7 +100,7 @@ static inline void freeze(struct task_st
> > >  static inline int thaw_process(struct task_struct *p) { return 1; }
> > >  static inline void frozen_process(struct task_struct *p) { BUG(); }
> > > 
> > > -static inline void refrigerator(void) {}
> > > +static inline int refrigerator(void) { return 0; }
> > >  static inline int freeze_processes(void) { BUG(); return 0; }
> > >  static inline void thaw_processes(void) {}
> > > 
> > > Index: linux-2.6.20-mm2/kernel/power/process.c
> > > ===================================================================
> > > --- linux-2.6.20-mm2.orig/kernel/power/process.c
> > > +++ linux-2.6.20-mm2/kernel/power/process.c
> > > @@ -24,6 +24,8 @@
> > >  #define FREEZER_KERNEL_THREADS 0
> > >  #define FREEZER_USER_SPACE 1
> > > 
> > > +spinlock_t refrigerator_lock;
> > > +
> > >  static inline int freezeable(struct task_struct * p)
> > >  {
> > >  	if ((p == current) ||
> > > @@ -34,15 +36,23 @@ static inline int freezeable(struct task
> > >  }
> > > 
> > >  /* Refrigerator is place where frozen processes are stored :-). */
> > > -void refrigerator(void)
> > > +int refrigerator(void)
> > >  {
> > >  	/* Hmm, should we be allowed to suspend when there are realtime
> > >  	   processes around? */
> > >  	long save;
> > > +
> > > +	spin_lock(&refrigerator_lock);
> > 
> > I hope we can do this without a global lock that is acquired on each
> > try_to_freeze() call!
> 
> Yes.  Here's the current version (try_to_freeze() is unchanged, so the lock
> is only taken by the tasks that are going to freeze, or so they think):

Ah, OK, that should work much better from a lock-contention viewpoint!

							Thanx, Paul

> ---
>  kernel/power/process.c |   15 ++++++++++++++-
>  1 file changed, 14 insertions(+), 1 deletion(-)
> 
> Index: linux-2.6.20-mm2/kernel/power/process.c
> ===================================================================
> --- linux-2.6.20-mm2.orig/kernel/power/process.c
> +++ linux-2.6.20-mm2/kernel/power/process.c
> @@ -24,6 +24,8 @@
>  #define FREEZER_KERNEL_THREADS 0
>  #define FREEZER_USER_SPACE 1
> 
> +static spinlock_t refrigerator_lock;
> +
>  static inline int freezeable(struct task_struct * p)
>  {
>  	if ((p == current) ||
> @@ -39,10 +41,18 @@ void refrigerator(void)
>  	/* Hmm, should we be allowed to suspend when there are realtime
>  	   processes around? */
>  	long save;
> +
> +	spin_lock(&refrigerator_lock);
> +	if (freezing(current)) {
> +		frozen_process(current);
> +		spin_unlock(&refrigerator_lock);
> +	} else {
> +		spin_unlock(&refrigerator_lock);
> +		return;
> +	}
>  	save = current->state;
>  	pr_debug("%s entered refrigerator\n", current->comm);
> 
> -	frozen_process(current);
>  	spin_lock_irq(&current->sighand->siglock);
>  	recalc_sigpending(); /* We sent fake signal, clean it up */
>  	spin_unlock_irq(&current->sighand->siglock);
> @@ -143,6 +153,7 @@ static unsigned int try_to_freeze_tasks(
>  					"kernel threads",
>  				TIMEOUT / HZ, todo);
>  		read_lock(&tasklist_lock);
> +		spin_lock(&refrigerator_lock);
>  		do_each_thread(g, p) {
>  			if (is_user_space(p) == !freeze_user_space)
>  				continue;
> @@ -152,6 +163,7 @@ static unsigned int try_to_freeze_tasks(
> 
>  			cancel_freezing(p);
>  		} while_each_thread(g, p);
> +		spin_unlock(&refrigerator_lock);
>  		read_unlock(&tasklist_lock);
>  	}
> 
> @@ -169,6 +181,7 @@ int freeze_processes(void)
>  	unsigned int nr_unfrozen;
> 
>  	printk("Stopping tasks ... ");
> +	spin_lock_init(&refrigerator_lock);
>  	nr_unfrozen = try_to_freeze_tasks(FREEZER_USER_SPACE);
>  	if (nr_unfrozen)
>  		return nr_unfrozen;