Am 09.02.2018 um 15:51 schrieb Tom St Denis:
> On 09/02/18 09:12 AM, Christian König wrote:
>> No, there is simply no need to initialize the system domain. What are
>> the values of p->mapping and adev->mman.bdev.dev_mapping when they
>> don't match? Maybe we are allocating memory before initializing
>> adev->mman.bdev.dev_mapping.
>
> In my test setup I'm running test 3 from libdrm (suite 1) with a pause
> before the unmap/free call. So the IB should still be mapped. Indeed
> the VM PTE decoding has the V bit set.
>
>> Or do you have more than one GPU in the system? E.g. APU+dGPU? Could
>> it be that you read through the wrong device?
>
> I found the issue:
>
> Â Â Â Â while (size) {
> Â Â Â Â Â Â Â phys_addr_t addr = *pos & PAGE_MASK;
> Â Â Â Â Â Â Â loff_t off = *pos & ~PAGE_MASK;
> Â Â Â Â Â Â Â size_t bytes = PAGE_SIZE - off;
>
> "bytes" should be limited by the 'size' parameter passed in. What is
> happening instead is it's reading the entire PTB until it hits a V=0
> page and then returns an error and in the process is doing "fun
> things" to the user mode application (by copying more data than I
> asked for).
Ah, obvious problem.
Do you want to fix it or should I take a look? You wanted to add write
support as well anyway IIRC.
I've just pushed the first three patches from that series to
amd-staging-drm-next.
Thanks for testing,
Christian.
>
>
> Tom
