Hi Menzel,
Thanks for your advice, will have a try.
Best wishes
Emily Deng
-Original Message-
From: Paul Menzel
Sent: Thursday, August 9, 2018 2:47 PM
To: Deng, Emily
Cc: amd-gfx@lists.freedesktop.org; Liu, Monk
Subject: Re: [PATCH] drm/amdgpu/sriov: give 8s for recover vram unde
On Wed, Aug 08, 2018 at 05:30:17PM +0530, Nayan Deshmukh wrote:
> On Wed, Aug 8, 2018 at 4:58 PM Huang Rui wrote:
>
> > On Wed, Aug 08, 2018 at 03:10:07PM +0800, Koenig, Christian wrote:
> > > Yeah that is a known issue, but this solution is not correct either.
> > >
> > > See the scheduler where
Am 09.08.2018 um 08:18 schrieb Huang Rui:
On Wed, Aug 08, 2018 at 06:47:49PM +0800, Christian König wrote:
Am 08.08.2018 um 11:59 schrieb Huang Rui:
I continue to work for bulk moving that based on the proposal by Christian.
Background:
amdgpu driver will move all PD/PT and PerVM BOs into idle
Am 09.08.2018 um 05:19 schrieb Junwei Zhang:
a helper function to create and initialize amdgpu bo
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 184 -
1 file changed, 84 insertions(+), 100 deletions(-)
diff --git a/amdgpu/amdgpu_bo.
there may be gfx off delay work pending when suspend/driver
unload, need to cancel them first.
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdg
Comments inline.
Regards,
Qiang
From: amd-gfx on behalf of Junwei Zhang
Sent: Thursday, August 9, 2018 11:19 AM
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Jerry; Koenig, Christian
Subject: [PATCH libdrm] amdgpu: add a function to create amdgpu bo inter
On 08/09/2018 03:40 PM, Yu, Qiang wrote:
Comments inline.
Regards,
Qiang
From: amd-gfx on behalf of Junwei Zhang
Sent: Thursday, August 9, 2018 11:19 AM
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Jerry; Koenig, Christian
Subject: [PATCH libdrm] amdgp
> + r = amdgpu_bo_create(dev, alloc_buffer->alloc_size, args.out.handle,
> +buf_handle);
> if (r)
> - amdgpu_bo_free(bo);
> - else
> - *buf_handle = bo;
> + goto out;
> [yuq] the handle is not freed.
Do yo
On Fri, Jul 20, 2018 at 2:21 PM, Nayan Deshmukh
wrote:
> entity has a scheduler field and we don't need the sched argument
> in any of the functions where entity is provided.
>
> Signed-off-by: Nayan Deshmukh
This breaks the make htmldocs build a bit:
./drivers/gpu/drm/scheduler/gpu_scheduler.c
Hi Daniel,
On Thu, Aug 9, 2018 at 2:27 PM Daniel Vetter wrote:
>
> On Fri, Jul 20, 2018 at 2:21 PM, Nayan Deshmukh
> wrote:
> > entity has a scheduler field and we don't need the sched argument
> > in any of the functions where entity is provided.
> >
> > Signed-off-by: Nayan Deshmukh
>
> This
>
>
> > + r = amdgpu_bo_create(dev, alloc_buffer->alloc_size, args.out.handle,
> > +buf_handle);
> > if (r)
> > - amdgpu_bo_free(bo);
> > - else
> > - *buf_handle = bo;
> > + goto out;
> > [yuq] the handle
a helper function to create and initialize amdgpu bo
v2: update error handling: add label and free bo
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 186 +
1 file changed, 89 insertions(+), 97 deletions(-)
diff --git a/amdgpu/amdgpu_bo.
Hi everyone,
This set of patches tries to improve read after write hazard handling for
reservation objects.
It allows us to specify for each shared fence if it represents a write
operation.
Based on this the i915 driver is modified to always wait for all writes before
pageflip and the previou
That allows us to only retreive fences of write operations.
Signed-off-by: Christian König
---
drivers/dma-buf/reservation.c| 19 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 3 ++-
drivers/gpu/drm/amd/
No need for that any more. Just replace the list when there isn't enough
room any more for at least one additional fence.
Signed-off-by: Christian König
---
drivers/dma-buf/reservation.c | 180 ++
include/linux/reservation.h | 4 -
2 files changed, 60
Add a helper to access the shared fences in an reservation object.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 7 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 3 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++--
drivers/gpu/
Wait for all write operations before page flipping.
Signed-off-by: Christian König
---
drivers/gpu/drm/i915/intel_display.c | 28 ++--
1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_display.c
b/drivers/gpu/drm/i915/intel_display
Note if the added fence is a write by using the lsb in the fenc pointer.
Signed-off-by: Christian König
---
drivers/dma-buf/dma-buf.c| 8 +++-
drivers/dma-buf/reservation.c| 59 +---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
We now note that all fences are potential writers.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 1 -
Am 09.08.2018 um 11:29 schrieb Junwei Zhang:
a helper function to create and initialize amdgpu bo
v2: update error handling: add label and free bo
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 186 +
1 file changed, 89 insertions(+)
Quoting Christian König (2018-08-09 12:37:08)
> void reservation_object_add_shared_fence(struct reservation_object *obj,
> struct dma_fence *fence)
> {
> - struct reservation_object_list *old, *fobj = obj->staged;
> + struct reservation_object_
Am 09.08.2018 um 14:08 schrieb Chris Wilson:
Quoting Christian König (2018-08-09 12:37:08)
void reservation_object_add_shared_fence(struct reservation_object *obj,
struct dma_fence *fence)
{
- struct reservation_object_list *old, *fobj = obj->s
On Thu, Aug 09, 2018 at 03:18:55PM +0800, Koenig, Christian wrote:
> Am 09.08.2018 um 08:18 schrieb Huang Rui:
> > On Wed, Aug 08, 2018 at 06:47:49PM +0800, Christian König wrote:
> >> Am 08.08.2018 um 11:59 schrieb Huang Rui:
> >>> I continue to work for bulk moving that based on the proposal by
Am 09.08.2018 um 14:25 schrieb Huang Rui:
On Thu, Aug 09, 2018 at 03:18:55PM +0800, Koenig, Christian wrote:
Am 09.08.2018 um 08:18 schrieb Huang Rui:
On Wed, Aug 08, 2018 at 06:47:49PM +0800, Christian König wrote:
Am 08.08.2018 um 11:59 schrieb Huang Rui:
I continue to work for bulk moving
Reviewed-by: Alex Deucher
From: amd-gfx on behalf of Rex Zhu
Sent: Thursday, August 9, 2018 3:31 AM
To: amd-gfx@lists.freedesktop.org
Cc: Zhu, Rex
Subject: [PATCH] drm/amdgpu: Cancel gfx off delay work when driver fini/suspend
there may be gfx off delay work
On Thu, Aug 09, 2018 at 01:37:07PM +0200, Christian König wrote:
> Hi everyone,
>
> This set of patches tries to improve read after write hazard handling
> for reservation objects.
>
> It allows us to specify for each shared fence if it represents a write
> operation.
>
> Based on this the i915
Am 09.08.2018 um 15:38 schrieb Daniel Vetter:
On Thu, Aug 09, 2018 at 01:37:07PM +0200, Christian König wrote:
Hi everyone,
This set of patches tries to improve read after write hazard handling
for reservation objects.
It allows us to specify for each shared fence if it represents a write
oper
On Thu, Aug 9, 2018 at 3:58 PM, Christian König
wrote:
> Am 09.08.2018 um 15:38 schrieb Daniel Vetter:
>>
>> On Thu, Aug 09, 2018 at 01:37:07PM +0200, Christian König wrote:
>>>
>>> Hi everyone,
>>>
>>> This set of patches tries to improve read after write hazard handling
>>> for reservation objec
Am 09.08.2018 um 16:22 schrieb Daniel Vetter:
On Thu, Aug 9, 2018 at 3:58 PM, Christian König
wrote:
Am 09.08.2018 um 15:38 schrieb Daniel Vetter:
On Thu, Aug 09, 2018 at 01:37:07PM +0200, Christian König wrote:
[SNIP]
See to me the explicit fence in the reservation object is not even remotel
Signed-off-by: James Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 9f1a5bd..5b39d13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/driver
Signed-off-by: James Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 08e3857..edb7baf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/
Signed-off-by: James Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h | 1 +
drivers/gpu/drm/amd/amdgpu/psp_v10_0.c| 3 +++
2 files changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index edb7baf..bdc472b 100644
---
Signed-off-by: James Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 17 +--
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 38 ++---
2 files changed, 40 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
b/drivers/gpu/drm/am
On Thu, Aug 9, 2018 at 11:41 AM, James Zhu wrote:
> Signed-off-by: James Zhu
Please include a commit message. E.g.,
Track the TMR address for VCN PSP firmware loading.
With that added:
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h | 3 +++
> 1 file changed, 3 i
On 2018-07-25 11:05 AM, Alex Deucher wrote:
On Wed, Jul 25, 2018 at 10:01 AM, Boyuan Zhang wrote:
On 2018-07-24 08:50 AM, Christian König wrote:
Am 23.07.2018 um 21:53 schrieb Boyuan Zhang:
On 2018-07-19 02:51 PM, Alex Deucher wrote:
On Wed, Jul 18, 2018 at 4:39 PM, wrote:
From: Boyua
On Thu, Aug 9, 2018 at 11:41 AM, James Zhu wrote:
> Signed-off-by: James Zhu
Please include a patch description. E.g.,
Track the TMR address returned by the PSP for later use by the driver
when setting up the IPs.
With that fixed:
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/amdgpu
On Thu, Aug 9, 2018 at 11:41 AM, James Zhu wrote:
> Signed-off-by: James Zhu
The subject doesn't really make sense. Please also include a patch
description. This should also be split into two patches, one to add
the new id to the enum and one to add support for VCN to the psp
driver.
Alex
>
Hi Alex
Sure, I will send out V2 with the fix.
thanks!
James Zhu
On 2018-08-09 11:48 AM, Alex Deucher wrote:
On Thu, Aug 9, 2018 at 11:41 AM, James Zhu wrote:
Signed-off-by: James Zhu
Please include a commit message. E.g.,
Track the TMR address for VCN PSP firmware loading.
With that adde
On Thu, Aug 9, 2018 at 11:41 AM, James Zhu wrote:
> Signed-off-by: James Zhu
Please include a patch description. E.g., update VCN code to handle
firmware loading via the psp. With that fixed:
Reviewed-by: Alex Deucher
Alex
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 17 +--
amdgpu IP blocks booting need Trust Memory Region(tmr) mac address
of its firmware which is loaded by PSP
Signed-off-by: James Zhu
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uco
From: Likun Gao
Add VCN support in PSP driver
Signed-off-by: James Zhu
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/psp_v10_0.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 0ff136d..02
From: Likun Gao
Add the new firmware id for VCN into the enum
Signed-off-by: James Zhu
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_uco
From: Likun Gao
Setup psp firmware loading for VCN, and make VCN block
booting from tmr mac address.
Signed-off-by: James Zhu
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 17 +--
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 38 ++
Update tmr mac address with firmware loading address
which is returned from PSP firmware
Signed-off-by: James Zhu
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
b/drivers/gpu
I don't think this is a good idea. Can you please explain why this
won't cause performance regressions?
Thanks
Marek
On Fri, Aug 3, 2018 at 7:34 AM, Christian König
wrote:
> This way we can always find a BO structure by its handle.
>
> Signed-off-by: Christian König
> ---
> amdgpu/amdgpu_bo.c
I just read the headline and thought, what are we doing with "mac
addresses"? This is not a network driver.
I think MC address stands for "memory controller" address. I think
nowadays that's basically a synonym for VMID 0 virtual address.
Regards,
Felix
On 2018-08-09 11:41 AM, James Zhu wrote
Hi Dave,
More fixes for 4.19:
- Fixes for scheduler
- Fix for SR-IOV
- Fixes for display
The following changes since commit df36b2fb8390d98453fff1aae3927095fe9ff36c:
drm/ttm: clean up non-x86 definitions on ttm_tt (2018-08-01 17:23:56 -0500)
are available in the git repository at:
git://pe
Compare the current vrefresh in addition to the number of displays
when determining whether or not the smu needs updates when changing
modes. The SMU needs to be updated if the vbi timeout changes due
to a different refresh rate. Fixes flickering around mode changes
in some cases on polaris parts.
On Fri, Aug 10, 2018 at 12:31:38AM +0800, James Zhu wrote:
> amdgpu IP blocks booting need Trust Memory Region(tmr) mac address
> of its firmware which is loaded by PSP
>
> Signed-off-by: James Zhu
> Reviewed-by: Alex Deucher
For series:
Acked-by: Huang Rui
> ---
> drivers/gpu/drm/amd/amdgpu
a helper function to create and initialize amdgpu bo
v2: update error handling: add label and free bo
v3: update error handling: separate each error label
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 195 ++---
1 file changed, 94 insertion
the flink bo is used to export
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/amdgpu/amdgpu_bo.c b/amdgpu/amdgpu_bo.c
index 2947715..0d0c73b 100644
--- a/amdgpu/amdgpu_bo.c
+++ b/amdgpu/amdgpu_bo.c
@@ -219,12 +219,6 @@ static int amdgp
a helper function to create and initialize amdgpu bo
v2: update error handling: add label and free bo
v3: update error handling: separate each error label
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 196 ++---
1 file changed, 95 insertion
the flink bo is used to export
Signed-off-by: Junwei Zhang
---
amdgpu/amdgpu_bo.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/amdgpu/amdgpu_bo.c b/amdgpu/amdgpu_bo.c
index 6f0baf1..5b91cfc 100644
--- a/amdgpu/amdgpu_bo.c
+++ b/amdgpu/amdgpu_bo.c
@@ -219,12 +219,6 @@ static int amdgp
code cleanup for amdgpu ttm structures
Signed-off-by: Junwei Zhang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 20
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 17 +
2 files changed, 17 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/am
Please ignore this one, which was send from a temporal branch.
Regards,
Jerry
> -Original Message-
> From: amd-gfx On Behalf Of Junwei
> Zhang
> Sent: Friday, August 10, 2018 12:59
> To: amd-gfx@lists.freedesktop.org
> Cc: Zhang, Jerry ; Koenig, Christian
>
> Subject: [PATCH libdrm 1/2]
Patch is Reviewed-by: Rex Zhu
Thanks.
Best Regards
Rex
From: amd-gfx on behalf of Alex Deucher
Sent: Friday, August 10, 2018 4:16:23 AM
To: amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander
Subject: [PATCH] drm/amdgpu/powerplay: check vrefresh when whe
This patch adds a mechanism by which the VCE 3.0 block
shall check if it was enabled or in use before suspending,
if it was powergated while entering suspend then there
is no need to repeat it in vce_3_0_suspend().
Similarly, if the block was powergated while entering suspend
itself then there is n
I am Ok with the check when call vce_v3_0_hw_fini.
But we may still need to call amdpug_vce_suspend/resume.
and not sure whether need to do ring test when resume back.
Best Regards
Rex
From: S, Shirish
Sent: Friday, August 10, 2018 2:15 PM
To: Deucher, Alexan
There are ASIC reset/ASIC resume during S4 freeze()/throw() process, I am
afraid there may be some problem for ring/ib test.
It should be more test to confirm it.
Thanks
JimQu
发件人: amd-gfx 代表 Zhu, Rex
发送时间: 2018年8月10日 14:32:36
收件人: S, Shirish; Deucher
Fix typo throw() to thaw().
Thanks
JimQu
发件人: Qu, Jim
发送时间: 2018年8月10日 14:55:09
收件人: Zhu, Rex; S, Shirish; Deucher, Alexander; Liu, Leo
抄送: amd-gfx@lists.freedesktop.org
主题: 答复: [PATCH] drm/amdpu/vce_v3: skip suspend and resume if powergated
There are AS
60 matches
Mail list logo
