Am 16.01.2018 um 07:02 schrieb He, Roger:
-Original Message-
From: Andrey Grodzovsky [mailto:andrey.grodzov...@amd.com]
Sent: Saturday, January 13, 2018 6:29 AM
To: dri-de...@lists.freedesktop.org; amd-gfx@lists.freedesktop.org
Cc: Koenig, Christian ; He, Roger ;
Grodzovsky, Andrey
Sub
Am 16.01.2018 um 07:18 schrieb He, Roger:
-Original Message-
From: Andrey Grodzovsky [mailto:andrey.grodzov...@amd.com]
Sent: Saturday, January 13, 2018 6:29 AM
To: dri-de...@lists.freedesktop.org; amd-gfx@lists.freedesktop.org
Cc: Koenig, Christian ; He, Roger ;
Grodzovsky, Andrey
Subj
Moving from the amd-gfx list to dri-devel, since this isn't amdgpu specific.
On 2018-01-16 03:54 AM, Chunming Zhou wrote:
> otherwise -ETIME is missed.
>
> Change-Id: Ic5580a74d8027cc468c6135f8cf2f81817993423
> Signed-off-by: Chunming Zhou
> ---
> xf86drm.c | 2 +-
> 1 file changed, 1 inserti
Otherwise buffer placement is very restrictive and might fail.
Fixes: "drm/amdgpu: fix VCE buffer placement restrictions v2"
Signed-off-by: Christian König
Reported-by: Deng, Emily
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
v2: simplify check smu_memory_size code.
simplify allocate smu memroy code.
Signed-off-by: Rex Zhu
Change-Id: I6d5f4212adc3621d2bf71ca9d2a4d952867d0a01
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 43 +++
Change-Id: I34d323c240e65b47c3558eb7042255b61078e2bb
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h | 1 +
drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h | 6 --
drivers/gpu/drm/amd/include/asic_reg/smuio/sm
Store the voltage regulator configuration,
so we can properly query the voltage.
Change-Id: Icec3a93f26b532e466a36d0ebac5886d43df8e6d
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c| 12 +++-
drivers/gpu/drm/amd/powerplay/hwm
Change-Id: I7be7cb442c620f850044d58bd8097735e3398b07
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 13 +
drivers/gpu/drm/amd/powerplay/inc/pp_soc15.h | 3 ++-
2 files changed, 15 insertions(+), 1 deletion(-)
diff --g
Store the voltage regulator configuration
so we can properly query the voltage
Change-Id: Icf916cfedbc2e5ac3037ef6f4f19b9a76ee36fff
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/inc/smu7.h | 19
drivers/gpu/drm/amd/powerplay/inc/smu7_di
Setup smio table(smio registers's address and voltage ID)
for various voltage domain.
Change-Id: I14be46053ffb2954c1533f4e67d3b0632107af7a
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c | 31 +++-
1 file changed, 20 inse
On 2018-01-16 11:03 AM, Christian König wrote:
> Otherwise buffer placement is very restrictive and might fail.
>
> Fixes: "drm/amdgpu: fix VCE buffer placement restrictions v2"
>
> Signed-off-by: Christian König
> Reported-by: Deng, Emily
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 4 ++
v2: merge tip drm-next code.
simplify check smu_memory_size code.
simplify allocate smu memroy code.
Change-Id: Ie8e865cc7d6c9d60fe234f29ac07e9f9fae60e9f
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 43 +
when cat pp_power_profile_mode on Vega10
NUMMODE_NAME BUSY_SET_POINT FPS USE_RLC_BUSY MIN_ACTIVE_LEVEL
0 3D_FULL_SCREEN : 70 60 1 3
1 POWER_SAVING : 90 60 0 0
2 VIDEO*: 70 60 0
v2: delete uncessary blank line.
Add static const modifiers to an array
Signed-off-by: Rex Zhu
Change-Id: If6b81ade742ef434717010ca0783d2af9145c975
---
drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 38 +++
drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 78 ++
Am 16.01.2018 um 12:46 schrieb Rex Zhu:
v2: merge tip drm-next code.
simplify check smu_memory_size code.
simplify allocate smu memroy code.
Change-Id: Ie8e865cc7d6c9d60fe234f29ac07e9f9fae60e9f
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
driver
User can use to calculate profiling ratios when
set UMD Pstate.
Signed-off-by: Rex Zhu
Change-Id: I3c6b82ebface57eb969d474c57149e8658ab7014
---
drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c | 2 ++
drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c | 3 +++
drivers/gpu/drm/amd/powerplay/
The additional output are at the end of sclk/mclk info as
cat pp_dpm_mclk
0: 300Mhz *
1: 1650Mhz
P: 300Mhz
Signed-off-by: Rex Zhu
Change-Id: Idf8eeedb5d399d9ffb7de7a2fb2976c7fa7c01a8
---
drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c | 2 ++
drivers/gpu/drm/amd/powerplay/hwmgr/rv_hwmgr.c
The additional output are: PSTATE_SCLK and PSTATE_MCLK value
in MHz as:
300 MHz (PSTATE_SCLK)
300 MHz (PSTATE_MCLK)
Change-Id: I96dac70d7e7d9702a5bfc3a40bd9bb57a21abdd7
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 4
drivers/gpu/drm/amd/include/kgd_pp_interf
abbreviate variable name number_of_performance_levels
to num_of_pl in struct phm_odn_clock_levels
Change-Id: I132c59dfd28933c4f6eba74fa53ffd0d014ec354
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 8
drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
when this bit was set on module load,
driver will allow the user over/under gpu
clock and voltage through sysfs.
by default, this bit was not set.
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c| 2 +-
drivers/gpu/drm/amd/powerplay/hwmgr
Add initial infrastructure for manual dpm control.
Change-Id: Id9d8dd3043d4c9b90854a94f9749bc70eaf9162e
Reviewed-by: Alex Deucher
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 75
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h | 14
Add odn_edit_dpm_table function
points for setting user assigned clock/voltage.
Change-Id: I7e49ffdc30b77d07b46bf12ebb275fa0ff901588
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h | 6 ++
drivers/gpu/drm/amd/powerplay/inc/hwmgr.h | 3 +++
2 files cha
Change-Id: I54bb964a3905f675e93411f93810cc1aa1f67d12
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/include/kgd_pp_interface.h | 2 ++
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 21 +
2 files changed, 23 insertions(+)
diff --git a/drivers/gpu/drm/amd/include/kgd_pp
Change-Id: I301be04db3c56e16e2c10091016efa5439fbc744
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 104 ++-
1 file changed, 103 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
b/drivers/gpu/drm/amd/po
Change-Id: I46cdf4f39f4c9c448a2c76b67f1cbbfed26c7488
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h| 5 -
drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h | 6 --
drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h | 11 +++
3 files changed, 1
when Over-driver engine clock and voltage were set,
need to recalculate AVFS voltage on VI asics.
Change-Id: If2a2226d64c0c2aa37c2e84f36b0dad8b7dee25e
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 80 ++
drivers/gpu/drm/amd/powerplay/smumgr/s
when cat pp_od_clk_voltage it show
OD_SCLK:
0:300Mhz800 mV
1:466Mhz818 mV
2:751Mhz824 mV
3: 1019Mhz987 mV
4: 1074Mhz 1037 mV
5: 1126Mhz 1087 mV
6: 1169Mhz 1137 mV
7: 1206Mhz 1150 mV
OD_MCLK
On 01/16/2018 03:54 AM, Christian König wrote:
Am 16.01.2018 um 07:18 schrieb He, Roger:
-Original Message-
From: Andrey Grodzovsky [mailto:andrey.grodzov...@amd.com]
Sent: Saturday, January 13, 2018 6:29 AM
To: dri-de...@lists.freedesktop.org; amd-gfx@lists.freedesktop.org
Cc: Koenig,
Am 16.01.2018 um 13:43 schrieb Andrey Grodzovsky:
On 01/16/2018 03:54 AM, Christian König wrote:
Am 16.01.2018 um 07:18 schrieb He, Roger:
-Original Message-
From: Andrey Grodzovsky [mailto:andrey.grodzov...@amd.com]
Sent: Saturday, January 13, 2018 6:29 AM
To: dri-de...@lists.freedes
Hello Alex Deucher,
The patch a12551072126: "drm/amdgpu: rework IP block registration
(v2)" from Oct 13, 2016, leads to the following static checker
warning:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1504 amdgpu_device_ip_fini()
error: dereferencing freed memory 'adev'
drivers/g
This to allow drivers to choose to avoid OOM invocation and handle
page allocation failures instead.
v2:
Remove extra new lines.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/ttm/ttm_bo.c | 3 +++
drivers/gpu/drm/ttm/ttm_page_alloc.c | 6 ++
drivers/gpu/drm/ttm/ttm_
Avoid OOM on syatem pages allocations.
v2:
Remove modeprobe parameter, making this behaviour the only option.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
b/dri
Am 16.01.2018 um 16:18 schrieb Andrey Grodzovsky:
This to allow drivers to choose to avoid OOM invocation and handle
page allocation failures instead.
v2:
Remove extra new lines.
Signed-off-by: Andrey Grodzovsky
Reviewed-by: Christian König for the series.
---
drivers/gpu/drm/ttm/ttm_bo
On Tue, Dec 5, 2017 at 6:01 PM, Harry Wentland wrote:
>>
>
> Thanks, Arnd. This is what I was missing. I'll take another look.
>
> It would still work without KCOV, although I agree that's not ideal by any
> means.
Any update on this? I see building DCN1.0 with KCOV using gcc-8 is still broken.
On Tue, Jan 16, 2018 at 6:18 AM, Rex Zhu wrote:
> Setup smio table(smio registers's address and voltage ID)
> for various voltage domain.
>
> Change-Id: I14be46053ffb2954c1533f4e67d3b0632107af7a
> Reviewed-by: Alex Deucher
> Signed-off-by: Rex Zhu
Series is:
Reviewed-by: Alex Deucher
> ---
>
On Tue, Jan 16, 2018 at 7:00 AM, Rex Zhu wrote:
> abbreviate variable name number_of_performance_levels
> to num_of_pl in struct phm_odn_clock_levels
>
> Change-Id: I132c59dfd28933c4f6eba74fa53ffd0d014ec354
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/powerpl
That got accidentially removed.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 14 +-
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d75637f02ef4..155e6f
This way we can better handle the differences for CPU based updates.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 79 +-
1 file changed, 29 insertions(+), 50 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/driver
On Tue, Jan 16, 2018 at 6:50 AM, Rex Zhu wrote:
> when cat pp_power_profile_mode on Vega10
> NUMMODE_NAME BUSY_SET_POINT FPS USE_RLC_BUSY MIN_ACTIVE_LEVEL
> 0 3D_FULL_SCREEN : 70 60 1 3
> 1 POWER_SAVING : 90 60 0 0
On Tue, Jan 16, 2018 at 6:50 AM, Rex Zhu wrote:
> v2: delete uncessary blank line.
> Add static const modifiers to an array
>
> Signed-off-by: Rex Zhu
>
> Change-Id: If6b81ade742ef434717010ca0783d2af9145c975
Reviewed-by: Alex Deucher
Do you have a similar patch for smu7 yet?
> ---
> dri
On Tue, Jan 16, 2018 at 6:59 AM, Rex Zhu wrote:
> The additional output are at the end of sclk/mclk info as
> cat pp_dpm_mclk
> 0: 300Mhz *
> 1: 1650Mhz
> P: 300Mhz
>
> Signed-off-by: Rex Zhu
I'm not crazy about this patch. I think it conflates things and
breaks older versions of the rocm smi t
On Tue, Jan 16, 2018 at 6:59 AM, Rex Zhu wrote:
> User can use to calculate profiling ratios when
> set UMD Pstate.
>
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
>
> Change-Id: I3c6b82ebface57eb969d474c57149e8658ab7014
> ---
> drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c | 2 ++
On Tue, Jan 16, 2018 at 6:59 AM, Rex Zhu wrote:
> The additional output are: PSTATE_SCLK and PSTATE_MCLK value
> in MHz as:
>
> 300 MHz (PSTATE_SCLK)
> 300 MHz (PSTATE_MCLK)
>
> Change-Id: I96dac70d7e7d9702a5bfc3a40bd9bb57a21abdd7
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
> ---
> dri
On 2018-01-16 10:18 AM, Andrey Grodzovsky wrote:
> Avoid OOM on syatem pages allocations.
>
> v2:
> Remove modeprobe parameter, making this behaviour the only option.
>
> Signed-off-by: Andrey Grodzovsky
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4
> 1 file changed, 4 insertions(+
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> Change-Id: I301be04db3c56e16e2c10091016efa5439fbc744
> Signed-off-by: Rex Zhu
> ---
> drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 104
> ++-
> 1 file changed, 103 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/g
Thanks for taking care of this. Patch 2 is a nice simplification that
should reduce the chances of breaking CPU updates in the future. The
series is Reviewed-by: Felix Kuehling
Regards,
Felix
On 2018-01-16 10:56 AM, Christian König wrote:
> That got accidentially removed.
>
> Signed-off-by: C
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> when Over-driver engine clock and voltage were set,
> need to recalculate AVFS voltage on VI asics.
>
> Change-Id: If2a2226d64c0c2aa37c2e84f36b0dad8b7dee25e
> Signed-off-by: Rex Zhu
> ---
> drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 80
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> when this bit was set on module load,
> driver will allow the user over/under gpu
> clock and voltage through sysfs.
>
> by default, this bit was not set.
>
> Reviewed-by: Alex Deucher
> Signed-off-by: Rex Zhu
> ---
> drivers/gpu/drm/amd/amdgpu/
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> Change-Id: I54bb964a3905f675e93411f93810cc1aa1f67d12
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/include/kgd_pp_interface.h | 2 ++
> drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 21 +
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> Add odn_edit_dpm_table function
> points for setting user assigned clock/voltage.
>
> Change-Id: I7e49ffdc30b77d07b46bf12ebb275fa0ff901588
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/powerplay/inc/hardwareman
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> Change-Id: I46cdf4f39f4c9c448a2c76b67f1cbbfed26c7488
> Signed-off-by: Rex Zhu
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h| 5 -
> drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h | 6 --
>
On Tue, Jan 16, 2018 at 7:02 AM, Rex Zhu wrote:
> when cat pp_od_clk_voltage it show
> OD_SCLK:
> 0:300Mhz800 mV
> 1:466Mhz818 mV
> 2:751Mhz824 mV
> 3: 1019Mhz987 mV
> 4: 1074Mhz 1037 mV
> 5: 1126Mhz 1087 mV
> 6:
On 01/16/2018 11:42 AM, Felix Kuehling wrote:
On 2018-01-16 10:18 AM, Andrey Grodzovsky wrote:
Avoid OOM on syatem pages allocations.
v2:
Remove modeprobe parameter, making this behaviour the only option.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4
On Tue, Jan 16, 2018 at 2:02 PM, Rex Zhu wrote:
> when this bit was set on module load,
> driver will allow the user over/under gpu
> clock and voltage through sysfs.
>
> by default, this bit was not set.
>
> Reviewed-by: Alex Deucher
> Signed-off-by: Rex Zhu
> ---
> drivers/gpu/drm/amd/amdgpu/
Christian König wrote:
Otherwise buffer placement is very restrictive and might fail.
Fixes: "drm/amdgpu: fix VCE buffer placement restrictions v2"
Signed-off-by: Christian König
Reported-by: Deng, Emily
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 4 ++--
1 file changed, 2 insertions(+),
Signed-off-by: Tom St Denis
---
src/app/main.c | 2 +-
src/lib/discover.c | 2 +-
src/lib/discover_by_did.c | 37 -
src/lib/discover_by_name.c | 8
4 files changed, 42 insertions(+), 7 deletions(-)
diff --git a/src/app/main.c b
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index e29c22a72764..a8899ecd9387 100644
---
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index c4de1c18bf77..0fb4b4409ef1 100644
---
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 66d9b5f85d6e..fbbac8498044 100644
--- a/driv
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 85a0ecaba3e3..8efe7f3ec0a1 100644
--- a/driv
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/vce_v4_0.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index a54e88821de3..9a0d6d9824d0 100755
--- a/driv
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 17 -
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 3fd7eb2a9a7b..ebec3
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 24 +---
1 file changed, 17 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 44f1a3dde4d
Unify tlb flushing for gmc v6.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 25 -
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 20
drivers/gpu/drm/amd/amdgpu/si.h | 2 ++
drivers/gpu/drm/amd/amdgpu/si_dma.c | 15 +++--
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 3e22ae4c3802..935c3a8b6629 100644
---
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 39acafbc84d6..e72f3e5d24b8 100644
---
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/cik.h | 2 +-
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 2 ++
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.h b/drivers/gpu/drm/amd/amdgpu/c
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 12
1 file changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index c6e22eff89e7..b48b843c66ae 100644
--- a
Unify tlb flushing for gmc v8.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 27 +++
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 19 +++
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 17 ++---
drivers/gpu/drm/amd/amdgpu/sd
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/si_dma.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c
b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index 697475a25749..c70e1d35975c 100644
--- a/drivers/gp
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 10 ++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index f0b10cb63940..282b402d93ee 100644
---
Needed for vm_flush unification.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 19 +--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 1f580328f571..b6
Add a new GMC function to unify vm flushing.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 3 +++
2 files changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.
Unify tlb flushing for gmc v7.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/cik.h | 2 ++
drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 15 ++-
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 25 +++--
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 19 ++
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f7bcfa53eff0.
Unify tlb flushing for gmc v9.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 1 -
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 29
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 25 +-
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 23 ++---
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 2 ++
drivers/gpu/drm/amd/amdgpu/vi.h | 2 +-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
b/drivers/gpu/drm/amd/am
Avoid OOM on syatem pages allocations.
v2:
Remove modeprobe parameter, make this behaviour the only option.
v3:
Move setting no_retry flag into amdgpu_ttm_init.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4
1 file changed, 4 insertions(+)
diff --git a/
Reviewed-by: Felix Kuehling
On 2018-01-16 02:50 PM, Andrey Grodzovsky wrote:
> Avoid OOM on syatem pages allocations.
>
> v2:
> Remove modeprobe parameter, make this behaviour the only option.
>
> v3:
> Move setting no_retry flag into amdgpu_ttm_init.
>
> Signed-off-by: Andrey Grodzovsky
> ---
On Tue, Jan 16, 2018 at 2:40 PM, Christian König
wrote:
> Needed for vm_flush unification.
>
> Signed-off-by: Christian König
> ---
> drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 12
> 1 file changed, 12 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
> b/drivers/gp
On Tue, Jan 16, 2018 at 2:40 PM, Christian König
wrote:
> Needed for vm_flush unification.
>
> Signed-off-by: Christian König
> ---
> drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 24 +---
> 1 file changed, 17 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgp
On Tue, Jan 16, 2018 at 2:39 PM, Christian König
wrote:
> Needed for vm_flush unification.
>
> Signed-off-by: Christian König
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 13 +
> 1 file changed, 13 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
> b/drivers/g
>-Original Message-
>From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Rex
>Zhu
>Sent: Tuesday, January 16, 2018 7:47 PM
>To: amd-gfx@lists.freedesktop.org
>Cc: Zhu, Rex
>Subject: [PATCH v2] drm/amdgpu: reserved requested gtt buffer for smu
>
>v2: merge tip drm-n
Reviewed-by: Deng, Emily
> -Original Message-
> From: Andy Furniss [mailto:adf.li...@gmail.com]
> Sent: Wednesday, January 17, 2018 2:06 AM
> To: Christian König ; amd-
> g...@lists.freedesktop.org; Deng, Emily
> Subject: Re: [PATCH] drm/amdgpu: fix typo in amdgpu_vce_validate_bo
>
> Ch
-Original Message-
From: Christian König [mailto:ckoenig.leichtzumer...@gmail.com]
Sent: Tuesday, January 16, 2018 8:46 PM
To: Grodzovsky, Andrey ; Koenig, Christian
; He, Roger ;
dri-de...@lists.freedesktop.org; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/2] drm/amdgpu: Use ne
Reviewed-by: Roger He
Thanks
Roger(Hongbo.He)
-Original Message-
From: dri-devel [mailto:dri-devel-boun...@lists.freedesktop.org] On Behalf Of
Andrey Grodzovsky
Sent: Tuesday, January 16, 2018 11:18 PM
To: dri-de...@lists.freedesktop.org; amd-gfx@lists.freedesktop.org; Koenig,
Christia
The series is Ached-by: Chunming Zhou
On 2018年01月17日 01:05, Felix Kuehling wrote:
Thanks for taking care of this. Patch 2 is a nice simplification that
should reduce the chances of breaking CPU updates in the future. The
series is Reviewed-by: Felix Kuehling
Regards,
Felix
On 2018-01-16
I'm running an eviction stress test with KFD and find that sometimes it
starts swapping. When that happens, swap usage goes up rapidly, but it
never comes down. Even after the processes terminate, and all VRAM and
GTT allocations are freed (checked in
/sys/kernel/debug/dri/0/amdgpu_{gtt|vram}_mm),
Hi Felix,
Could I get your test to have a try?
Thanks,
David Zhou
On 2018年01月17日 11:21, Felix Kuehling wrote:
I'm running an eviction stress test with KFD and find that sometimes it
starts swapping. When that happens, swap usage goes up rapidly, but it
never comes down. Even after the proce
>>Setting the feature mask to 0x2fff unsets PP_SOCCLK_DPM_MASK.
>>Probably not intended. I think you want 0x3fff.
Yes, Thanks for pointing it out.
Best Regards
Rex
-Original Message-
From: Alex Deucher [mailto:alexdeuc...@gmail.com]
Sent: Wednesday, January 17, 2018 1:12 AM
To: Zhu, Rex
-Original Message-
From: Grazvydas Ignotas [mailto:nota...@gmail.com]
Sent: Wednesday, January 17, 2018 1:53 AM
To: Zhu, Rex
Cc: amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 1/8] drm/amd/pp: Add a new pp feature mask bit for OD
feature
On Tue, Jan 16, 2018 at 2:02 PM, Rex Zhu wrot
Ok, I will drop this patch. and please review the new attached patch expose
stable pstate clock by ioctl.
Best Regards
Rex
-Original Message-
From: Alex Deucher [mailto:alexdeuc...@gmail.com]
Sent: Wednesday, January 17, 2018 12:03 AM
To: Zhu, Rex
Cc: amd-gfx list
Subject: Re: [PATCH 2/
patch #19, #20, #21 are Reviewed-by: Chunming Zhou
On 2018年01月17日 03:40, Christian König wrote:
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --g
and please fix patch #21 tile, which should be gfx9 not gfx8.
On 2018年01月17日 14:11, Chunming Zhou wrote:
patch #19, #20, #21 are Reviewed-by: Chunming Zhou
On 2018年01月17日 03:40, Christian König wrote:
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
drivers
and please fix patch #21 title, which should be gfx9 not gfx8.
On 2018年01月17日 14:11, Chunming Zhou wrote:
patch #19, #20, #21 are Reviewed-by: Chunming Zhou
On 2018年01月17日 03:40, Christian König wrote:
This way we can see the PASID in VM faults.
Signed-off-by: Christian König
---
driver
v3: - fix return value check in amdgpu_pp_alloc_mem_for_smu
- save memory size in struct powerplay
- not modify module parameter
v2: - merge tip drm-next code.
- simplify check smu_memory_size code.
- simplify allocate smu memroy code.
Signed-off-by: Rex Zhu
---
drivers/gpu/drm/a
gmc8, gmc9, not gfx...
On 2018年01月17日 14:13, Chunming Zhou wrote:
and please fix patch #21 title, which should be gfx9 not gfx8.
On 2018年01月17日 14:11, Chunming Zhou wrote:
patch #19, #20, #21 are Reviewed-by: Chunming Zhou
On 2018年01月17日 03:40, Christian König wrote:
This way we can see
I'm not sure if this is a good ongoing, as I know, our per IP topology
is intended for every generation asic bringup.
I think there are many similar logics which we can abstract, but we
don't do that.
For emit_wreg above patches, they only can be used by vm flush part, but
they are common fu
It should be enabled until ECC is supported for Raven.
Change-Id: If847663d503c26d2a08274ca721b4ce1bc637111
Signed-off-by: Junwei Zhang
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
b/drivers/gpu/drm/amd/a
Sure.
We should add the PP_SMC_POWER_PROFILE_AUTO in PP_SMC_POWER_PROFILE.
And will be implemented as auto wattman feature.
Best Regards
Rex
-Original Message-
From: Alex Deucher [mailto:alexdeuc...@gmail.com]
Sent: Tuesday, January 16, 2018 11:59 PM
To: Zhu, Rex
Cc: amd-gfx list
Subject:
100 matches
Mail list logo
