Re: [PATCH 0/3] mm/gup: track FOLL_PIN pages (follow on from v12)

[John Hubbard]

On 1/28/20 9:47 PM, Leon Romanovsky wrote:
> On Sat, Jan 25, 2020 at 06:23:39PM +0200, Leon Romanovsky wrote:
>> On Fri, Jan 24, 2020 at 06:11:12PM -0800, John Hubbard wrote:
>>> Leon Romanovsky:
>>>
>>> If you get a chance, I'd love to have this short series (or even just
>>> the first patch; the others are just selftests) run through your test
>>> suite that was previously choking on my earlier v11 patchset. The huge
>>> page pincount limitations are removed, so I'm expecting a perfect test
>>> run this time!
>>>
>>
>> I added those patches to our regression and I will post the in the
>> couple of days.
> 
> Hi John,
> 
> The patches survived our RDMA verification night runs.
> 

Great! Thanks very much for running those. That's a pretty solid 
confirmation that the earlier patch *did* allow a huge page refcount
overflow, and that this approach avoids it. 

thanks,
-- 
John Hubbard
NVIDIA