Am 04.01.2017 um 21:56 schrieb Andres Rodriguez:
Hey Serguei
On 2017-01-04 07:56 AM, Christian König wrote:
Am 04.01.2017 um 12:03 schrieb Sagalovitch, Serguei:
Andres,
I have on rather generic design question:
Why we want to restrict it to CAP_SYS_ADMIN?
+ if (priority == AMD_SCHED_
In general please don't use HTML mail for public mailing lists, those
mails are usually rejected by most lists (but not amd-gfx).
Apart from that the patch looks sane to me and is Acked-by: Christian
König .
Regards,
Christian.
Am 04.01.2017 um 20:54 schrieb Lin, Amber:
Current amdgpu allo
This series patches implement to get the clock gating status
dynamically into debugfs. User will enter profiling mode to runtime
disable clockgating, so it needs an interface to expose clock gating
states. Part 1 works for VI, I will implement it on CI/SI in following
days.
Here is the example on
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 16
1 file changed, 16 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 2f36417..6f46562 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/d
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 40 +++
1 file changed, 40 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index c4afa8e..25e5670 100644
--- a/drivers/gpu/drm/amd/amdgpu
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 12
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 12
2 files changed, 24 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 03a35d9..9f1d8f6 1006
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 4ca38a1..581f4a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
++
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12
drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 4
drivers/gpu/drm/amd/include/amd_shared.h | 2 ++
4 files changed, 19 insertions(+)
diff --git a/d
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/vi.c | 27 +++
1 file changed, 27 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 2523f31..88e3fd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 18 ++
1 file changed, 18 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 35ff1c3..15742e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 95 ++
1 file changed, 95 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 7aa561d..431bae4 100644
--- a/drivers/gpu/drm/amd/amdg
Reviewed-by: Alex Deucher
From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Lin,
Amber
Sent: Wednesday, January 04, 2017 2:55 PM
To: amd-gfx@lists.freedesktop.org
Cc: Kuehling, Felix; Russell, Kent
Subject: code review of amdgpu change
Current amdgpu allows to disable PC
> -Original Message-
> From: Huang Rui [mailto:ray.hu...@amd.com]
> Sent: Thursday, January 05, 2017 8:50 AM
> To: Deucher, Alexander; amd-gfx@lists.freedesktop.org
> Cc: Zhu, Rex; Mao, David; Fu, Ping; Zhang, Hawking; Huang, Ray
> Subject: [PART1 PATCH 0/8] Introduce a method to get clock
Some of them are part of AON tiles but are unstable during PM switches. That's
why the debugfs mmio entry supports a PM lock.
So they might be readable while powered off but unstable if the firmware is in
the middle of a PM switch.
Tom
From: amd-gfx on beh
This could be done with much less code duplication:
static const struct {
u32 flag;
const char *name;
} clocks[] = {
{AMD_CG_SUPPORT_GFX_MGCG, "Medium Grain Clock Gating"},
{AMD_CG_SUPPORT_GFX_MGLS, "Medium Grain memor
Minor nit.
s/Grain/Grained/
Also, amdgpu_clockgating_state as a function name does not seem explicit
enough as to what it's doing, maybe amdgpu_get_clockgating_state?
On 01/05/17 07:49, Huang Rui wrote:
> Signed-off-by: Huang Rui
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 95
> +++
Cool, thanks for the heads up David.
Regards,
Andres
On 1/4/2017 11:13 PM, Mao, David wrote:
Hi Andres,
We have a local change made yesterday which eliminate the need to get
unused fd in the creation time.
If everything goes well, I expect the change could be sent out for
review next w
From: Flora Cui
Signed-off-by: Flora Cui
Reviewed-by: Junwei Zhang
Signed-off-by: Alex Deucher
Cc: sta...@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/si_dpm.c | 57 ++---
1 file changed, 28 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/amd/amd
Required for certain MC configs.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/radeon/si.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ad4d7b8..bbc239e 100644
--- a/drivers/gpu/drm/radeon/si.c
+
Fixed by the new 58 MC firmware.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/si_dpm.c | 11 ---
1 file changed, 11 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 10bedfa..34cb7ea 100644
--- a/drivers/gpu/drm/amd/
fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=98897
https://bugs.launchpad.net/bugs/1651981
Signed-off-by: Alex Deucher
Cc: sta...@vger.kernel.org
Cc: Adrian Fiergolski
---
drivers/gpu/drm/radeon/si_dpm.c | 13 -
1 file changed, 13 deletions(-)
diff --git a/drivers/gpu/drm/ra
Use the appropriate smc firmware for each chip revision.
Signed-off-by: Alex Deucher
Cc: sta...@vger.kernel.org
---
drivers/gpu/drm/radeon/si.c | 60 +
1 file changed, 28 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu/drm/radeon/si.c b/driver
Fixed by the new 58 MC firmware.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/radeon/si_dpm.c | 11 ---
1 file changed, 11 deletions(-)
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 13ba73f..668060f 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+
Required for certain MC configs.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 45a573e..3864682 100644
--- a/
fixed by the new 58 mc firmware.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/radeon/si_dpm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 668060f..2944916 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/
fixed by the new 58 mc firmware.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/si_dpm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 34cb7ea..e9242d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm
Port of radeon change to amdgpu.
Signed-off-by: Alex Deucher
Cc: sta...@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/si_dpm.c | 13 -
1 file changed, 13 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 0566e9a..10bedfa 1006
Hey Michel,
Sounds fair. I don't think we are in a rush to get this merged until it
actually can provide the guarantees that we need.
I've gotten some good feedback on code change improvements, and that
should be enough to get me to the next stage with HW support.
I'll send and updated patc
On Thu, Jan 05, 2017 at 11:40:33PM +0800, Deucher, Alexander wrote:
> > -Original Message-
> > From: Huang Rui [mailto:ray.hu...@amd.com]
> > Sent: Thursday, January 05, 2017 8:50 AM
> > To: Deucher, Alexander; amd-gfx@lists.freedesktop.org
> > Cc: Zhu, Rex; Mao, David; Fu, Ping; Zhang, Haw
On Thu, Jan 05, 2017 at 11:33:38AM -0500, Felix Kuehling wrote:
> This could be done with much less code duplication:
>
> static const struct {
> u32 flag;
> const char *name;
> } clocks[] = {
> {AMD_CG_SUPPORT_GFX_MGCG, "Medium Grain Clock Gat
On Thu, Jan 05, 2017 at 04:34:45PM +, William Lewis wrote:
> Minor nit.
>
> s/Grain/Grained/
>
> Also, amdgpu_clockgating_state as a function name does not seem explicit
> enough as to what it's doing, maybe amdgpu_get_clockgating_state?
>
Yep, thanks to reminder.
Thanks,
Rui
Signed-off-by: Huang Rui
Reviewed-by: Alex Deucher
Cc: William Lewis
Cc: Felix Kuehling
---
William,
"Medium Grain Clock Gating" is referred from HW spec. So it's better
to align with it. I updated function name from clockgating_state to
get_clockgating_state.
Thanks,
Rui
---
drivers/gpu/d
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 37 +++
2 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
ind
This series patches implement to get the clock gating status
dynamically into debugfs. User will enter profiling mode to runtime
disable clockgating, so it needs an interface to expose clock gating
states. Part 1 works for VI, I will implement it on CI/SI in following
days.
Changes from V1 -> V2:
Signed-off-by: Huang Rui
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c | 26 --
drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 26 --
3 files changed, 49 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/
35 matches
Mail list logo
