svn commit: r235931 - head/sys/powerpc/include
Nathan Whitehorn
nwhitehorn at freebsd.org
Thu May 24 22:15:17 UTC 2012
On 05/24/12 17:07, Marcel Moolenaar wrote:
>
> On May 24, 2012, at 2:13 PM, Nathan Whitehorn wrote:
>
>> On 05/24/12 15:45, Marcel Moolenaar wrote:
>>> Author: marcel
>>> Date: Thu May 24 20:45:44 2012
>>> New Revision: 235931
>>> URL: http://svn.freebsd.org/changeset/base/235931
>>>
>>> Log:
>>> Fix the memory barriers for CPUs that do not like lwsync and wedge or cause
>>> exceptions early enough during boot that the kernel will do ithe same.
>>> Use lwsync only when compiling for LP64 and revert to the more proven isync
>>> when compiling for ILP32. Note that in the end (i.e. between revision 222198
>>> and this change) ILP32 changed from using sync to using isync. As per Nathan
>>> the isync is needed to make sure I/O accesses are properly serialized with
>>> locks and isync tends to be more effecient than sync.
>>>
>>
>> This badly breaks the synchronization primitives. The functions mb()/wmb()/rmb() need to be sync or lwsync on ILP32, not isync.
>
> I guess I misinterpreted your email in which you stated that isync is better.
It's just in this one single case. Otherwise, it's still faster but
doesn't work :)
>> Summary:
>> 1. *mb() must be lwsync or sync on all machines, except for wmb() which could be eieio
>> 2. __ATOMIC_ACQ() must be isync (though could be reduced to lwsync with bus_space changes)
>> 3. __ATOMIC_REL() must be lwsync or sync
>
> This is absolutely not what I concluded from our discussions. I have no idea
> how we could end up so out of sync...
>
Thanks for the quick change. No idea how we got out of sync. I find all
of this synchronization stuff a little mind-bending, so sorry for any
miscommunication. __ATOMIC_ACQ() needed to also be isync on ppc64, so
I've fixed that up. Things should be good now.
-Nathan
More information about the svn-src-head
mailing list