Re: [PATCH 0/3] Add support to handle prefetchable memoryg

[Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>]

On Tue, Nov 17, 2020 at 10:08:35AM +0530, Vidya Sagar wrote:
> Hi Lorenzo & Bjorn,
> Sorry to bother you.
> Could you please take a look at the patches-1 & 2 from this series?

IIUC we should:

(1) apply https://patchwork.kernel.org/project/linux-pci/patch/20201026181652.418729-1-robh@kernel.org
(2) apply [1,2] from this series

For (2), are they rebased against v5.10-rc3 with (1) applied ? I need to
check but I will probably have to use v5.10-rc3 as baseline owing to
commit:

9fff3256f93d

(1) depends on it.

Lorenzo

> Thanks,
> Vidya Sagar
> 
> On 11/4/2020 1:16 PM, Vidya Sagar wrote:
> > External email: Use caution opening links or attachments
> > 
> > 
> > Lorenzo / Bjorn,
> > Could you please review patches-1 & 2 in this series?
> > For the third patch, we already went with Rob's patch @
> > http://patchwork.ozlabs.org/project/linux-pci/patch/20201026154852.221483-1-robh@kernel.org/
> > 
> > 
> > Thanks,
> > Vidya Sagar
> > 
> > On 10/26/2020 6:02 PM, Thierry Reding wrote:
> > > On Sat, Oct 24, 2020 at 04:03:41AM +0000, Jingoo Han wrote:
> > > > On 10/23/20, 3:57 PM, Vidya Sagar wrote:
> > > > > 
> > > > > This patch series adds support for configuring the DesignWare IP's ATU
> > > > > region for prefetchable memory translations.
> > > > > It first starts by flagging a warning if the size of non-prefetchable
> > > > > aperture goes beyond 32-bit as PCIe spec doesn't allow it.
> > > > > And then adds required support for programming the ATU to handle higher
> > > > > (i.e. >4GB) sizes and then finally adds support for differentiating
> > > > > between prefetchable and non-prefetchable regions and
> > > > > configuring one of
> > > > > the ATU regions for prefetchable memory translations purpose.
> > > > > 
> > > > > Vidya Sagar (3):
> > > > >    PCI: of: Warn if non-prefetchable memory aperture size is > 32-bit
> > > > >    PCI: dwc: Add support to program ATU for >4GB memory aperture sizes
> > > > >    PCI: dwc: Add support to handle prefetchable memory mapping
> > > > 
> > > > For 2nd & 3rd,
> > > > Acked-by: Jingoo <jingoohan1@gmail.com>
> > > > But, I still want someone to ack 1st patch, not me.
> > > > 
> > > > To Vidya,
> > > > If possible, can you ask your coworker to give 'Tested-by'? It
> > > > will be very helpful.
> > > > Thank you.
> > > 
> > > On next-20201026 (but also going back quite a while) I'm seeing this
> > > during boot on Jetson AGX Xavier (Tegra194):
> > > 
> > > [    3.493382] ahci 0001:01:00.0: version 3.0
> > > [    3.493889] ahci 0001:01:00.0: SSS flag set, parallel bus scan
> > > disabled
> > > [    4.497706] ahci 0001:01:00.0: controller reset failed (0xffffffff)
> > > [    4.498114] ahci: probe of 0001:01:00.0 failed with error -5
> > > 
> > > After applying this series, AHCI over PCI is back to normal:
> > > 
> > > [    3.543230] ahci 0001:01:00.0: AHCI 0001.0000 32 slots 1 ports 6
> > > Gbps 0x1 impl SATA mode
> > > [    3.550841] ahci 0001:01:00.0: flags: 64bit ncq sntf led only pmp
> > > fbs pio slum part sxs
> > > [    3.559747] scsi host0: ahci
> > > [    3.561998] ata1: SATA max UDMA/133 abar m512@0x1230010000 port
> > > 0x1230010100 irq 63
> > > 
> > > So for the series:
> > > 
> > > Tested-by: Thierry Reding <treding@nvidia.com>
> > >