On Wed, Apr 13, 2011 at 17:05, Pavel Machek wrote:
> On Wed 2011-04-13 17:02:45, Mike Frysinger wrote:
>> On Wed, Apr 13, 2011 at 16:58, Rafael J. Wysocki wrote:
>> > On Wednesday, April 13, 2011, Mike Frysinger wrote:
>> >> when we suspend/resume Blackfin SMP systems, we notice that the
>> >> freezer code runs on multiple cores. this is of course what you want
>> >> -- freeze processes in parallel. however, the code only uses non-smp
>> >> based barriers which causes us problems ... our cores need software
>> >> support to keep caches in sync, so our smp barriers do just that. but
>> >> the non-smp barriers do not, and so the frozen/thawed processes
>> >> randomly get stuck in the wrong task state.
>> >>
>> >> thinking about it, shouldnt the freezer code be using smp barriers ?
>> >
>> > Yes, it should, but rmb() and wmb() are supposed to be SMP barriers.
>> >
>> > Or do you mean something different?
>>
>> then what's the diff between smp_rmb() and rmb() ?
>>
>> this is what i'm proposing:
>> --- a/kernel/freezer.c
>> +++ b/kernel/freezer.c
>> @@ -17,7 +17,7 @@ static inline void frozen_process(void)
>> {
>> if (!unlikely(current->flags & PF_NOFREEZE)) {
>> current->flags |= PF_FROZEN;
>> - wmb();
>> + smp_wmb();
>> }
>> clear_freeze_flag(current);
>> }
>> @@ -93,7 +93,7 @@ bool freeze_task(struct task_struct *p, bool sig_only)
>> * the task as frozen and next clears its TIF_FREEZE.
>> */
>> if (!freezing(p)) {
>> - rmb();
>> + smp_rmb();
>> if (frozen(p))
>> return false;
>
> smp_rmb() is NOP on uniprocessor.
>
> I believe the code is correct as is.
that isnt what the code / documentation says. unless i'm reading them
wrong, both seem to indicate that the proposed patch is what we
actually want.
include/linux/compiler-gcc.h:
#define barrier() __asm__ __volatile__("": : :"memory")
include/asm-generic/system.h:
#define mb() asm volatile ("": : :"memory")
#define rmb() mb()
#define wmb() asm volatile ("": : :"memory")
#ifdef CONFIG_SMP
#define smp_mb() mb()
#define smp_rmb() rmb()
#define smp_wmb() wmb()
#else
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
#endif
Documentation/memory-barriers.txt:
SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
systems because it is assumed that a CPU will appear to be self-consistent,
and will order overlapping accesses correctly with respect to itself.
[!] Note that SMP memory barriers _must_ be used to control the ordering of
references to shared memory on SMP systems, though the use of locking instead
is sufficient.
-mike
_______________________________________________
Uclinux-dist-devel mailing list
Uclinux-dist-devel@blackfin.uclinux.org
https://blackfin.uclinux.org/mailman/listinfo/uclinux-dist-devel
