Re: [PATCH v2 1/2] mm: uninitialized struct page poisoning sanity checking

[Pavel Tatashin]

On 18-04-05 19:22:58, Sasha Levin wrote:
> On Thu, Apr 05, 2018 at 09:49:40AM -0400, Pavel Tatashin wrote:
> >> Hi Sasha,
> >>
> >> I have registered on Azure's portal, and created a VM with 4 CPUs and 16G
> >> of RAM. However, I still was not able to reproduce the boot bug you found.
> >
> >I have also tried to reproduce this issue on Windows 10 + Hyper-V, still
> >unsuccessful.
> 
> I'm not sure why you can't reproduce it. I built a 4.16 kernel + your 6
> patches on top, and booting on a D64s_v3 instance gives me this:

Hi Sasha,

Thank you for running it again, the new trace is cleaner, as we do not get
nested panics within dump_page.

Perhaps a NUMA is required to reproduce this issue. I have tried,
unsuccessfully, on D4S_V3. This is the largest VM allowed with free trial,
as 4 CPU is the limit. D64S_V3 is with 64 CPUs and over $2K a month! :)

Let me study your trace, perhaps I will able to figure out the issue
without reproducing it.

Thank you,
Pasha