On 8-Jul-11, at 6:13 PM, Carlos O'Donell wrote:
On 7/8/2011 5:42 PM, Mike Frysinger wrote:
On Friday, July 08, 2011 17:27:00 Carlos O'Donell wrote:
Implements futex op support and makes futex cmpxchg atomic.
Tested on 64-bit SMP kernel running on 2 x PA8700s.
seems like all the changes to this func are arch-independent and
could be
placed into asm-generic/futex.h. the current parisc futex.h looks
like a copy
of the asm-generic one ...
-mike
That's true. I didn't want to rock the boat on this one until
I hammered out all the userspace testing.
Do you have a userspace patch? There was the thread stack allocation
bug and possibly
futex related issues.
I can more or less consistently hpmc my rp3440 running the GCC libgomp
testsuite with
3.0.0-rc7+. Unfortunately, it seems hpmcs are somewhat deferred, so
it's really hard to
to tell what's happening. Usually, the machine hpmcs in the idle loop.
One instance seemed to have a corrupt user space stack pointer.
Another instance
seemed to occur with inconsistent space registers in the kernel.
Often two cpus check
almost simultaneously. When this happens, both have the same "Assist
Check" value
(space register).
The "Check Summary" is always 0x8400000000800000. I think Kyle fixed
one of these last March.
The cause was missing IPC system calls. I'm a bit vague regarding
whether the fix was installed
or not.
Dave
--
John David Anglin dave.anglin@xxxxxxxx
--
To unsubscribe from this list: send the line "unsubscribe linux-parisc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
