Re: [PATCH 1/3] iommu: match the original algorithm
From: Cong Wang
Date: Thu Nov 28 2019 - 14:31:05 EST
On Wed, Nov 27, 2019 at 10:01 AM John Garry <john.garry@xxxxxxxxxx> wrote:
>
> On 21/11/2019 00:13, Cong Wang wrote:
> > The IOVA cache algorithm implemented in IOMMU code does not
> > exactly match the original algorithm described in the paper.
> >
> > Particularly, it doesn't need to free the loaded empty magazine
> > when trying to put it back to global depot.
> >
> > This patch makes it exactly match the original algorithm.
> >
>
> I haven't gone into the details, but this patch alone is giving this:
>
> root@(none)$ [ 123.857024] kmemleak: 8 new suspected memory leaks (see
> /sys/kernel/debug/kmemleak)
Ah, thanks for catching it! I see what I missed, I should pre-allocate those
empty entries in order to make it work correctly.
I didn't catch this because this was tested on a production machine where
we can't afford CONFIG_DEBUG_KMEMLEAK=y for obvious performance
concerns.
Anyway, I will fix this and send v2.
Thanks!