[PATCH 3/3] iommu/dma: Avoid unlikely high-order allocations

[Yong Wu]

On Fri, 2015-12-18 at 14:35 -0800, Doug Anderson wrote:
> Robin,
> 
> On Fri, Dec 18, 2015 at 9:01 AM, Robin Murphy <robin.murphy at arm.com> wrote:
> > Doug reports that the equivalent page allocator on 32-bit ARM exhibits
> > particularly pathalogical behaviour under memory pressure when
> > fragmentation is high, where allocating a 4MB buffer takes tens of
> > seconds and the number of calls to alloc_pages() is over 9000![1]
> >
> > We can drastically improve that situation without losing the other
> > benefits of high-order allocations when they would succeed, by assuming
> > memory pressure is relatively constant over the course of an allocation,
> > and not retrying allocations at orders we know to have failed before.
> > This way, the best-case behaviour remains unchanged, and in the worst
> > case we should see at most a dozen or so (MAX_ORDER - 1) failed attempts
> > before falling back to single pages for the remainder of the buffer.
> >
> > [1]:http://lists.infradead.org/pipermail/linux-arm-kernel/2015-December/394660.html
> >
> > Reported-by: Douglas Anderson <dianders at chromium.org>
> > Signed-off-by: Robin Murphy <robin.murphy at arm.com>
> > ---
> >  drivers/iommu/dma-iommu.c | 6 ++++--
> >  1 file changed, 4 insertions(+), 2 deletions(-)
> 
> Presumably it makes sense to update this based on v2 of my patch to
> the original code?  AKA: <https://patchwork.kernel.org/patch/7888851/>
> ?

Hi Robin,

    Thanks very much for this patch.

    And Douglas has sent his v2 which improve the flow of alloc_pages.
Do you have any plan to update this patch according to this v2, or any
concern about it?


> _______________________________________________
> iommu mailing list
> iommu at lists.linux-foundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/iommu