Memory used by KFD applications can contain sensitive information that
should not be leaked to other processes. The current approach to prevent
leaks is to clear VRAM at allocation time. This is not effective because
memory can be reused in other ways without being cleared. Synchronously
clearing m
With mm_nodes larger than 4GB, byte_count in amdgpu_fill_buffer would
overflow.
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/am
This memory allocation flag will be used to indicate BOs containing
sensitive data that should not be leaked to other processes.
Signed-off-by: Felix Kuehling
---
include/uapi/drm/amdgpu_drm.h | 4
1 file changed, 4 insertions(+)
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/dr
This notifies the driver that a BO is about to be released.
Releasing a BO also invokes the move_notify callback from
ttm_bo_cleanup_memtype_use, but that happens too late for anything
that would add fences to the BO and require a delayed delete.
Signed-off-by: Felix Kuehling
---
drivers/gpu/dr
Wipe VRAM memory containing sensitive data when moving or releasing
BOs. Clearing the memory is pipelined to minimize any impact on
subsequent memory allocation latency. Use of a poison value should
help debug future use-after-free bugs.
When moving BOs, the existing ttm_bo_pipelined_move ensures
Walk page table for the faulting address and dump PDEs and PTEs at
all levels. Also flag discrepancies where a PDE points to a different
address than the next level PDB or PTB BO.
Signed-off-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 5 +-
drivers/gpu/drm/amd/amdgpu/amdgpu
Hi Dave, Daniel,
Fixes for 5.3. Mostly fixes for Navi10 and a few other odds and ends.
Also contains a patch to ease the merge with hmm. Trivial merge fix
when the trees are merged:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -783,7 +783,7
Issue: On host P520 with S03J3226A SBIOS platform, passthrough both
gfx and audio device to VM, the first time start VM after host bootup,
driver woule load fail.
Root cause: Passthrough both devices allows VFIO to do hot reset
on bridge, this reset clears register BIOS_SCRATCH_7 which is used
for
On Tue, Jul 9, 2019 at 12:30 PM Nicholas Kazlauskas
wrote:
>
> [Why]
> The drm_audio_component can be used to give pin ELD notifications
> directly to the sound driver. This fixes audio endpoints disappearing
> due to missing unsolicited notifications.
>
> [How]
> Send the notification via the aud
Remove duplicated include.
Signed-off-by: YueHaibing
---
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 5ba332376710..822f45161240 100644
--- a/drivers/gpu/drm/amd/amdgp
Issue: On host P520 with S03J3226A SBIOS platform, passthrough both
gfx and audio device to VM, the first time start VM after host bootup,
driver woule load fail.
Root cause: Passthrough both devices allows VFIO to do hot reset
on bridge, this reset clears register BIOS_SCRATCH_7 which is used
for
Hi Alex,
There are actually two MAX_USEC_TIMEOUT related macros.
AMD_MAX_USEC_TIMEOUT is used for SMU and AMDGPU_MAX_USEC_TIMEOUT is used widely
in other parts.
Maybe you mistreated it as AMDGPU_MAX_USEC_TIMEOUT. I was confused by them too.
drivers/gpu/drm/amd/include/amd_shared.h:29:#define AM
On Tue, Jul 09, 2019 at 08:51:33PM +0200, Arnd Bergmann wrote:
> On Thu, Jul 4, 2019 at 7:52 AM Nathan Chancellor
> wrote:
> >
> > clang warns:
> >
> > drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_pp_smu.c:336:8:
> > warning: implicit conversion from enumeration type 'enum smu_clk_typ
On Tue, Jul 9, 2019 at 6:40 PM Deucher, Alexander
wrote:
>
> I'll just apply Arnd's patch. If the display team wants to adjust it later
> to clarify the
> operation, they should go ahead as a follow up patch.
Thanks!
> From: Abramov, Slava
> Sent: Tuesday, July 9, 2019 12:31 PM
> > Thanks for
On 2019-07-09 8:58 a.m., Zhou, David(ChunMing) wrote:
> I've raised it up when Christian make page fault, at that patch,
> amdgpu_job_submit_direct uses exclusive page fault ring for that.
>
> But if you use amdgpu_job_submit_direct for gerneral rings ocuppied by
> scheduler, I guess varias bugs wi
Hi Linus,
As was discussed some time ago here are the mostly -mm patches related
to hmm functions. In agreement with Andrew we split this out from
quilt into a git topic branch so it can be shared between the DRM and
RDMA git trees. However, this cycle did not see dependencies with work
in DRM or
Hi Lyude, sorry - just realized I forgot to CC you on this series! Let
me know if I should resend them.
Adding some additional reviewers as well.
Thanks,
Leo
On 2019-07-04 3:05 p.m., sunpeng...@amd.com wrote:
> From: Leo Li
>
> Hi all,
>
> Here's the second revision of patches to enable mst
On 2019-07-09 8:59 a.m., Alex Deucher wrote:
> On Tue, Jul 9, 2019 at 1:32 AM Kuehling, Felix wrote:
>> This memory allocation flag will be used to indicate BOs containing
>> sensitive data that should not be leaked to other processes.
>>
>> Signed-off-by: Felix Kuehling
>> ---
>> include/uapi/
On 2019-07-09 6:34 a.m., Michel Dänzer wrote:
> On 2019-07-09 7:32 a.m., Kuehling, Felix wrote:
>> This memory allocation flag will be used to indicate BOs containing
>> sensitive data that should not be leaked to other processes.
>>
>> Signed-off-by: Felix Kuehling
>> ---
>> include/uapi/drm/am
On Thu, Jul 4, 2019 at 7:52 AM Nathan Chancellor
wrote:
>
> clang warns:
>
> drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_pp_smu.c:336:8:
> warning: implicit conversion from enumeration type 'enum smu_clk_type'
> to different enumeration type 'enum amd_pp_clock_type'
> [-Wenum-convers
I'll just apply Arnd's patch. If the display team wants to adjust it later to
clarify the operation, they should go ahead as a follow up patch.
Thanks,
Alex
From: Abramov, Slava
Sent: Tuesday, July 9, 2019 12:31 PM
To: Arnd Bergmann; Wentland, Harry; Li, Sun pen
Hi Arnd!
Thanks for bisecting this issue.
I wonder whether you are going to commit your patch or planning to update it
and it's still in your work queue. We have one of our 32-bit builds failing
because of this issue, so that I would like either to fix it or wait to your
fix if it has chanc
[Why]
In order to give pin notifications to the sound driver from DM we need
to know whether audio is enabled on a stream and what pin it's using
from DC.
[How]
Expose the instance via stream status if it's a mapped resource for
the stream. It will be -1 if there's no audio mapped.
Cc: Leo Li
Cc
[Why]
The drm_audio_component can be used to give pin ELD notifications
directly to the sound driver. This fixes audio endpoints disappearing
due to missing unsolicited notifications.
[How]
Send the notification via the audio component whenever we enable or
disable audio state on a stream. This ma
On Tue, Jul 9, 2019 at 8:55 AM YueHaibing wrote:
>
> If CONFIG_HMM_MIRROR is not set, building may fails:
>
> In file included from drivers/gpu/drm/amd/amdgpu/amdgpu.h:72:0,
> from drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:40:
> drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h:69:20: error
On Tue, Jul 9, 2019 at 1:32 AM Kuehling, Felix wrote:
>
> This memory allocation flag will be used to indicate BOs containing
> sensitive data that should not be leaked to other processes.
>
> Signed-off-by: Felix Kuehling
> ---
> include/uapi/drm/amdgpu_drm.h | 4
> 1 file changed, 4 inser
I've raised it up when Christian make page fault, at that patch,
amdgpu_job_submit_direct uses exclusive page fault ring for that.
But if you use amdgpu_job_submit_direct for gerneral rings ocuppied by
scheduler, I guess varias bugs will happen.
-David
在 2019/7/9 12:53, Kuehling, Felix 写道:
> I
If this is just for the SMU, maybe it would be better to add a separate timeout
for the SMU since this will increase the timeout for lots of things, unless we
need an overall timeout increase for mode1 reset.
Alex
From: amd-gfx on behalf of Evan Quan
Sent: Tue
On 2019-07-09 7:32 a.m., Kuehling, Felix wrote:
> This memory allocation flag will be used to indicate BOs containing
> sensitive data that should not be leaked to other processes.
>
> Signed-off-by: Felix Kuehling
> ---
> include/uapi/drm/amdgpu_drm.h | 4
> 1 file changed, 4 insertions(+)
If CONFIG_HMM_MIRROR is not set, building may fails:
In file included from drivers/gpu/drm/amd/amdgpu/amdgpu.h:72:0,
from drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:40:
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h:69:20: error: field mirror has
incomplete type
struct hmm_mirror mirro
On Mon, Jul 08, 2019 at 11:55:50AM -0400, Alex Deucher wrote:
> Applied the series. thanks!
>
> Alex
Thank you :)
I don't see the enum conversion ones in your current tree. If they
indeed caused issues, could you guys please look into fixing the
warnings properly yourselves (maybe something lik
31 matches
Mail list logo
