Re: [PATCH v1 0/4] Fix issues with huge mapping in ioremap

["Kani, Toshi" <toshi.kani@hpe.com>]

On Thu, 2018-03-15 at 12:47 +0530, Chintan Pandya wrote:
> 
> On 3/14/2018 8:08 PM, Kani, Toshi wrote:
> > On Wed, 2018-03-14 at 14:18 +0530, Chintan Pandya wrote:
> > > Note: I was working on these patches for quite sometime
> > > and realized that Toshi Kani has shared some patches
> > > addressing the same isssue with subject
> > > "[PATCH 0/2] fix memory leak / panic in ioremap huge pages".
> > > I've taken slightly different approach here, so sending
> > > to the list, finally.
> > 
> > Hi Chintan,
> 
> Hi Toshi
> > 
> > Do you have any issue in my patchset?  If so, can you please comment on
> 
> Not functional issues. But I didn't see issues you mentioned in your
> commit text being solved for ARM64 in your patches. It is just being
> masked which they were already by Will's patch. In my approach, end
> goal was to get benefits of huge mapping back for ARM64.

Right, my patchset does not implement the fix for arm64.  The stub
version is only a workaround and is meant to be replaced by the fix.

> > them?  It complicates the thing when you send a different approach
> > without telling why a different approach is needed.  Your approach
> 
> See my reply above. I just had my original patches and I sent it.
> 
> > purges TLB after updating pmd/pud, which I think is broken.  Can you
> 
> Yes, they are broken. I understood the issues after Mark and Marc's
> review comments.
> 
> > work on top of my patchset and properly implement pXd_free_pte_page()
> 
> I have realized that if I address Mark's comments, my new patch will
> look similar to what you have done. So, I will work on top of your
> patches.

Sounds great.

Thanks,
-Toshi