On Jan 11, 2006, at 2:43 PM, Andrey Petrov wrote:

> On Wed, Jan 11, 2006 at 09:27:01PM +0000, David Laight wrote:
>> On Wed, Jan 11, 2006 at 04:18:27PM -0500, Chapman Flack wrote:
>>> Is there any port where the simple read or simple write
>>> of a single pointer is nonatomic?
>>
>> i386 when the data is misaligned and crosses a page boundary and the
>> second read faults.
>>
>
> Wouldn't failed instruction be repeated after page fault resolved?

Yes.

-- thorpej