linux-kernel - Re: [PATCH 1/1] amdgpu: use MMIO to init atombios if device is Thunderbolt / USB4 attached

Open Source and information security mailing list archives

Date:   Tue, 16 Mar 2021 11:01:23 +0800
From:   Nicholas Johnson <nicholas.johnson-opensource@...look.com.au>
To:     Alex Deucher <alexdeucher@...il.com>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Alex Deucher <alexander.deucher@....com>,
        Christian König <christian.koenig@....com>,
        amd-gfx list <amd-gfx@...ts.freedesktop.org>
Subject: Re: [PATCH 1/1] amdgpu: use MMIO to init atombios if device is
 Thunderbolt / USB4 attached

On Mon, Mar 15, 2021 at 11:05:21AM -0400, Alex Deucher wrote:
> On Mon, Mar 15, 2021 at 4:04 AM Nicholas Johnson
> <nicholas.johnson-opensource@...look.com.au> wrote:
> >
> > When using some Thunderbolt hosts using BIOS-assisted PCI enumeration
> > with IO BAR assigned, we get an atombios timeout, such as:
> >
> > [drm:atom_op_jump [amdgpu]] *ERROR* atombios stuck in loop for more than 20secs aborting
> > [drm:amdgpu_atom_execute_table_locked [amdgpu]] *ERROR* atombios stuck executing B456 (len 304, WS 4, PS 0) @ 0xB51B
> > [drm:amdgpu_atom_execute_table_locked [amdgpu]] *ERROR* atombios stuck executing B104 (len 183, WS 0, PS 8) @ 0xB17E
> > amdgpu 0000:08:00.0: amdgpu: gpu post error!
> > amdgpu 0000:08:00.0: amdgpu: Fatal error during GPU init
> > amdgpu: probe of 0000:08:00.0 failed with error -22
> >
> > A workaround is to use MMIO to access ATOMBIOS when device is
> > Thunderbolt / USB4 attached.
> 
> Missing your signed-off-by.  Also, we can just remove the legacy IO
> callbacks altogether.  They are leftover from radeon and not required
> at all on amdgpu.
Sorry, it's been a while; I forgot "-s". And I like your patch much 
better. I look forward to the day when all new PCIe devices only have 
64-bit MMIO_PREF BARs.

Thanks for looking at this! If you are still doing work on surprise 
removal / driver unloading for Thunderbolt, then I am happy to do 
testing for you. Removal of DRM devices in Linux is the main sore point 
for me, and I would love to see it through.

Regards,
Nicholas Johnson
> 
> Alex
> 
> 
> > ---
> >  drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 8 ++++++--
> >  1 file changed, 6 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
> > index 86add0f4e..5d16ec10d 100644
> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
> > @@ -1999,11 +1999,15 @@ int amdgpu_atombios_init(struct amdgpu_device *adev)
> >         atom_card_info->reg_read = cail_reg_read;
> >         atom_card_info->reg_write = cail_reg_write;
> >         /* needed for iio ops */
> > -       if (adev->rio_mem) {
> > +       if (adev->rio_mem && !pci_is_thunderbolt_attached(adev->pdev)) {
> >                 atom_card_info->ioreg_read = cail_ioreg_read;
> >                 atom_card_info->ioreg_write = cail_ioreg_write;
> >         } else {
> > -               DRM_DEBUG("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n");
> > +               if (pci_is_thunderbolt_attached(adev->pdev))
> > +                       DRM_DEBUG("Device is attached via Thunderbolt / USB4. Using MMIO to access ATOM BIOS\n");
> > +               else
> > +                       DRM_DEBUG("PCI I/O BAR is not found. Using MMIO to access ATOM BIOS\n");
> > +
> >                 atom_card_info->ioreg_read = cail_reg_read;
> >                 atom_card_info->ioreg_write = cail_reg_write;
> >         }
> > --
> > 2.30.2
> >
> > _______________________________________________
> > amd-gfx mailing list
> > amd-gfx@...ts.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/amd-gfx

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives