AMD IOMMU + SME + amdgpu regression

AMD IOMMU + SME + amdgpu regression

[Alex Xu (Hello71)]

Hi,

amdgpu + IOMMU + SME is now working for me on 5.7, yay! But, it is 
broken on torvalds master, boo. On boot, depending on which exact commit 
I test, it either hangs immediately (with built-in driver, before 
starting initramfs), displays some errors then hangs, or spams the 
screen with many amdgpu errors.

I bisected the black screen hang to:

commit dce8d6964ebdb333383bacf5e7ab8c27df151218
Author: Joerg Roedel <jroedel@suse.de>
Date:   Wed Apr 29 15:36:53 2020 +0200

    iommu/amd: Convert to probe/release_device() call-backs

    Convert the AMD IOMMU Driver to use the probe_device() and
    release_device() call-backs of iommu_ops, so that the iommu core code
    does the group and sysfs setup.

    Signed-off-by: Joerg Roedel <jroedel@suse.de>
    Link: https://lore.kernel.org/r/20200429133712.31431-16-joro@8bytes.org
    Signed-off-by: Joerg Roedel <jroedel@suse.de>

Testing torvalds master (623f6dc593) with the containing merge 
(98bdc74b36) plus the DMA mapping merge (4e94d08734) reverted allows 
amdgpu + IOMMU + SME to once again work.

I think that nobody is really working on amdgpu + SME, but it would be a 
shame if it was supported and then incidentally broken by a small 
change.

I am using an ASRock B450 Pro4 with Ryzen 1600 and ASUS RX 480. I don't 
understand this code at all, but let me know what I can do to 
troubleshoot.

Thanks,
Alex.

Re: AMD IOMMU + SME + amdgpu regression

[Joerg Roedel]

Hi Alex,

On Thu, Jun 11, 2020 at 07:05:21PM -0400, Alex Xu (Hello71) wrote:
> I am using an ASRock B450 Pro4 with Ryzen 1600 and ASUS RX 480. I don't 
> understand this code at all, but let me know what I can do to 
> troubleshoot.

Does it boot without SME enabled?


Regards,

	Joerg

Re: AMD IOMMU + SME + amdgpu regression

[Alex Xu (Hello71)]

Excerpts from Joerg Roedel's message of June 22, 2020 6:02 am:
> Hi Alex,
> 
> On Thu, Jun 11, 2020 at 07:05:21PM -0400, Alex Xu (Hello71) wrote:
>> I am using an ASRock B450 Pro4 with Ryzen 1600 and ASUS RX 480. I don't 
>> understand this code at all, but let me know what I can do to 
>> troubleshoot.
> 
> Does it boot without SME enabled?
> 
> 
> Regards,
> 
> 	Joerg
> 

Yes, it works with SME off with dbed452a078 ("dma-pool: decouple 
DMA_REMAP from DMA_COHERENT_POOL") applied.

Re: AMD IOMMU + SME + amdgpu regression

[Joerg Roedel]

On Mon, Jun 22, 2020 at 11:30:04AM -0400, Alex Xu (Hello71) wrote:
> Yes, it works with SME off with dbed452a078 ("dma-pool: decouple 
> DMA_REMAP from DMA_COHERENT_POOL") applied.

Okay, I can reproduce the problem on my Ryzen System, and the boot log
shows various warnings/bugs from the amdgpu driver. I think this should
be looked at by the AMDGPU folks first, as I didn't really got far
looking into the GPU drivers code.

Regards,

	Joerg