After commit 005440066f92 ("drm/amdgpu: enable gfxoff again on raven
series (v2)"), some Raven Ridge systems start to have rendering
corruption in browser [1].
Chip specific flags like cg_flags and pg_flags are applied in
amdgpu_device_ip_early_init(). For Raven Ridge, the flags may depend on
Acked-by: Alex Deucher
On Wed, Aug 14, 2019 at 11:41 PM Yuan, Xiaojie wrote:
>
> gfxoff doesn't work on navi12 yet, so disable it for now
>
> Signed-off-by: Xiaojie Yuan
> ---
> drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git
gfxoff doesn't work on navi12 yet, so disable it for now
Signed-off-by: Xiaojie Yuan
---
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 066ba593af23..d644669e5d93
Hi Dave, Daniel,
A few fixes for 5.3. Nothing major.
The following changes since commit d45331b00ddb179e291766617259261c112db872:
Linux 5.3-rc4 (2019-08-11 13:26:41 -0700)
are available in the Git repository at:
git://people.freedesktop.org/~agd5f/linux tags/drm-fixes-5.3-2019-08-14
for
On Thu, Aug 08, 2019 at 12:25:56PM +0200, Christoph Hellwig wrote:
> Looks good,
>
> Reviewed-by: Christoph Hellwig
Dimitri, are you OK with this patch?
Thanks,
Jason
___
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
On Wed, Aug 14, 2019 at 03:58:34PM +, Jason Gunthorpe wrote:
> On Thu, Aug 08, 2019 at 12:25:56PM +0200, Christoph Hellwig wrote:
> > Looks good,
> >
> > Reviewed-by: Christoph Hellwig
>
> Dimitri, are you OK with this patch?
>
I think this looks OK.
Reviewed-by: Dimitri Sivanich
Series is Reviewed-by: Evan Quan
> -Original Message-
> From: amd-gfx On Behalf Of
> Andrey Grodzovsky
> Sent: Thursday, August 15, 2019 4:40 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Deucher, Alexander ; Grodzovsky,
> Andrey ; Quan, Evan
> ; S, Shirish
> Subject: [PATCH v2 5/5]
Reviewed-by: Evan Quan
> -Original Message-
> From: amd-gfx On Behalf Of Alex
> Deucher
> Sent: Thursday, August 15, 2019 4:42 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Deucher, Alexander ; Ahzo
>
> Subject: [PATCH] drm/amd/powerplay/smu7: enforce minimal VBITimeout
> (v2)
>
>
On Wed, Aug 14, 2019 at 02:20:31PM -0700, Ralph Campbell wrote:
>
> On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
> > From: Jason Gunthorpe
> >
> > Many places in the kernel have a flow where userspace will create some
> > object and that object will need to connect to the subsystem's
> >
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
This series introduces a new registration flow for mmu_notifiers based on
the idea that the user would like to get a single refcounted piece of
memory for a mm, keyed to its use.
For instance many users of mmu_notifiers use an
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
mmu_notifier_unregister_no_release() and mmu_notifier_call_srcu() no
longer have any users, they have all been converted to use
mmu_notifier_put().
So delete this difficult to use interface.
Signed-off-by: Jason Gunthorpe
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
This is a significant simplification, it eliminates all the remaining
'hmm' stuff in mm_struct, eliminates krefing along the critical notifier
paths, and takes away all the ugly locking and abuse of page_table_lock.
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
Many places in the kernel have a flow where userspace will create some
object and that object will need to connect to the subsystem's
mmu_notifier subscription for the duration of its lifetime.
In this case the subsystem is
Please add patch descriptions for patches 3, 4, 5. With that fixed, series is:
Reviewed-by: Alex Deucher
From: amd-gfx on behalf of Andrey
Grodzovsky
Sent: Wednesday, August 14, 2019 4:40 PM
To: amd-gfx@lists.freedesktop.org
Cc: Deucher, Alexander ;
From: Ahzo
This fixes screen corruption/flickering on 75 Hz displays.
v2: make print statement debug only (Alex)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102646
Signed-off-by: Ahzo
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 5 +
1
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/include/kgd_pp_interface.h | 1 +
drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 21 +
2 files changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
This patchset adds mode 2 reset through SMU for RV2 and Picasso.
v2:
Split into more patches per functional unit.
Add some NULL checks and fix typos.
Andrey Grodzovsky (5):
drm/amd/powerplay: Fix meaning of 0x1E PPSMC_MSG
drm/amd/powerplay: add mode2 reset callback for pp_smu_mgr
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 18e780f..1115761 100644
---
v2:
Check ppfuncs pointer for NULL
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
drivers/gpu/drm/amd/amdgpu/soc15.c | 25 +
2 files changed, 18 insertions(+), 8 deletions(-)
diff --git
Also define reset modes (0, 1 and 2)
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/powerplay/inc/hwmgr.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 07fd64a..abeff15 100644
By comparing to windows it means ASIC reset.
Signed-off-by: Andrey Grodzovsky
Reviewed-by: Alex Deucher
---
drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
A prior commit e0f3c3f78da2 ("mm/mmu_notifier: init notifier if necessary")
made an attempt at doing this, but had to be reverted as calling
the GFP_KERNEL allocator under the i_mmap_mutex causes deadlock, see
commit 35cfa2b0b491
On 8/6/19 4:15 PM, Jason Gunthorpe wrote:
From: Jason Gunthorpe
This simplifies the code to not have so many one line functions and extra
logic. __mmu_notifier_register() simply becomes the entry point to
register the notifier, and the other one calls it under lock.
Also add a
On Wed, Aug 14, 2019 at 3:54 PM Andrey Grodzovsky
wrote:
>
> Signed-off-by: Andrey Grodzovsky
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
> drivers/gpu/drm/amd/amdgpu/soc15.c | 21 +
> 2 files changed, 14 insertions(+), 8 deletions(-)
>
> diff --git
On Wed, Aug 14, 2019 at 3:53 PM Andrey Grodzovsky
wrote:
>
> By comparing to windows it means ASIC reset.
>
> Signed-off-by: Andrey Grodzovsky
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git
On Wed, Aug 14, 2019 at 3:54 PM Andrey Grodzovsky
wrote:
>
> Mode 2 GPU reset should be done by sending message to SMU.
>
> Signed-off-by: Andrey Grodzovsky
I think this should be 3 patches:
1. add the pp_smumgr_func callback
2. add the smu10 implementation
3. add the amd_pm_funcs
By comparing to windows it means ASIC reset.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
b/drivers/gpu/drm/amd/powerplay/inc/rv_ppsmc.h
index
Mode 2 GPU reset should be done by sending message to SMU.
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/include/kgd_pp_interface.h| 1 +
drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 21 +
drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 7 +++
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
drivers/gpu/drm/amd/amdgpu/soc15.c | 21 +
2 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
This patchset adds mode 2 reset through SMU for RV2 and Picasso.
Andrey Grodzovsky (3):
drm/amd/powerplay: Fix meaning of 0x1E PPSMC_MSG
drm/amd/powerplay: Add support for mode2 ASIC reset.
drm/amdgpu: Use new mode2 reset interface for RV.
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
Double defintion of 'i'
Signed-off-by: Andrey Grodzovsky
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index a67..f204dbd 100644
---
Pushed! Thanks.
Yong
On 2019-08-14 3:27 a.m., Christian König wrote:
> Am 13.08.19 um 20:08 schrieb Zhao, Yong:
>> RW is also useful in most cases.
>>
>> Change-Id: Icf4bd65ea168e5965a6a8ebe32ce9327a2de2851
>> Signed-off-by: Yong Zhao
>
> Reviewed-by: Christian König for the series.
>
>> ---
Reviewed-by: Harish Kasiviswanathan
On 2019-08-14 4:13 a.m., Christian König wrote:
> Am 13.08.19 um 21:20 schrieb Zhao, Yong:
>> The amdgpu_task_info will be used when printing VM page fault for KFD
>> processes.
>>
>> Change-Id: Ifd983db5dceb1d477e7287e4893f80565a7a6b06
>> Signed-off-by: Yong
When VM state changed and system in large bar mode,
make sure to use CPU update function, otherwise use
SDMA function.
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++
1 file changed, 7 insertions(+)
diff --git
Am 14.08.19 um 19:35 schrieb Gang Ba:
When VM state changed and system in large bar mode,
make sure to use CPU update function, otherwise use
SDMA function.
Looks like you have some extra spaces in front of the commit message.
Apart from that looks good to me now and fix the commit
When VM state changed and system in large bar mode,
make sure to use CPU update function, otherwise use
SDMA function.
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++
1 file changed, 7 insertions(+)
diff
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c1baf3d..7ddca3e 100644
---
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c1baf3d..72dd434 100644
---
Am 14.08.19 um 18:58 schrieb Liu, Leo:
On 2019-08-14 7:11 a.m., Kenneth Feng wrote:
On Vega20, tools depends on UVD_STATUS.VCPU_REPORT bit0
to decide if UVD instances are in busy state or idle state.
This workaround fixes the issue that tools always fetch the
UVD instances state as busy state
On 2019-08-14 7:11 a.m., Kenneth Feng wrote:
> On Vega20, tools depends on UVD_STATUS.VCPU_REPORT bit0
> to decide if UVD instances are in busy state or idle state.
> This workaround fixes the issue that tools always fetch the
> UVD instances state as busy state no matter if there is a UVD work.
On Tue, Aug 06, 2019 at 08:15:45PM -0300, Jason Gunthorpe wrote:
> From: Jason Gunthorpe
>
> radeon is using a device global hash table to track what mmu_notifiers
> have been registered on struct mm. This is better served with the new
> get/put scheme instead.
>
> radeon has a bug where it was
On Wed, Aug 14, 2019 at 6:28 AM Jason Gunthorpe wrote:
>
> On Wed, Aug 14, 2019 at 09:38:54AM +0200, Christoph Hellwig wrote:
> > On Tue, Aug 13, 2019 at 06:36:33PM -0700, Dan Williams wrote:
> > > Section alignment constraints somewhat save us here. The only example
> > > I can think of a PMD
Please also include a patch description so we understand why this change is
needed.
Alex
From: amd-gfx on behalf of Christian
K?nig
Sent: Wednesday, August 14, 2019 11:06 AM
To: Ba, Gang ; amd-gfx@lists.freedesktop.org
Cc: Ba, Gang
Subject: Re: [PATCH]
Am 14.08.19 um 17:01 schrieb Gang Ba:
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
Good catch, but there is a problem below.
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 ++
1 file changed, 6 insertions(+)
diff --git
Change-Id: Ibcfada560a00c9aeebfd922ae48de920e44a5866
Signed-off-by: Gang Ba
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c1baf3d..72dd434 100644
---
On Tue, Aug 13, 2019 at 06:36:33PM -0700, Dan Williams wrote:
> Section alignment constraints somewhat save us here. The only example
> I can think of a PMD not containing a uniform pgmap association for
> each pte is the case when the pgmap overlaps normal dram, i.e. shares
> the same 'struct
On Wed, Aug 7, 2019 at 11:59 PM Christoph Hellwig wrote:
>
> On Wed, Aug 07, 2019 at 11:47:22AM -0700, Dan Williams wrote:
> > > Unrelated to this patch, but what is the point of getting checking
> > > that the pgmap exists for the page and then immediately releasing it?
> > > This code has this
Pass the connector info to the CEC adapter. This makes it possible
to associate the CEC adapter with the corresponding drm connector.
Signed-off-by: Dariusz Marcinkiewicz
Signed-off-by: Hans Verkuil
Tested-by: Hans Verkuil
---
.../display/amdgpu_dm/amdgpu_dm_mst_types.c | 2 +-
On Wed, Aug 14, 2019 at 09:38:54AM +0200, Christoph Hellwig wrote:
> On Tue, Aug 13, 2019 at 06:36:33PM -0700, Dan Williams wrote:
> > Section alignment constraints somewhat save us here. The only example
> > I can think of a PMD not containing a uniform pgmap association for
> > each pte is the
This series updates DRM drivers to use new CEC notifier API.
Changes since v6:
Made CEC notifiers' registration and de-registration symmetric
in tda998x and dw-hdmi drivers. Also, accidentally dropped one
patch in v6 (change to drm_dp_cec), brought it back now.
Changes
Reviewed-by: Hawking Zhang
Regards,
Hawking
-Original Message-
From: Yuan, Xiaojie
Sent: 2019年8月14日 19:30
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Hawking ; Xiao, Jack ;
Yin, Tianci (Rico) ; Wang, Kevin(Yang)
; Yuan, Xiaojie
Subject: [PATCH] drm/amd/powerplay: add smu if version
Hi Christian,
This is used by AGM.
Thanks.
-Original Message-
From: Christian König [mailto:ckoenig.leichtzumer...@gmail.com]
Sent: Wednesday, August 14, 2019 7:16 PM
To: Feng, Kenneth ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amd/amdgpu: workaround for UVD busy status
Signed-off-by: Xiaojie Yuan
---
drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h | 1 +
drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 3 +++
2 files changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index
Am 14.08.19 um 13:11 schrieb Kenneth Feng:
On Vega20, tools depends on UVD_STATUS.VCPU_REPORT bit0
to decide if UVD instances are in busy state or idle state.
This workaround fixes the issue that tools always fetch the
UVD instances state as busy state no matter if there is a UVD work.
Well
On Vega20, tools depends on UVD_STATUS.VCPU_REPORT bit0
to decide if UVD instances are in busy state or idle state.
This workaround fixes the issue that tools always fetch the
UVD instances state as busy state no matter if there is a UVD work.
Signed-off-by: Kenneth Feng
---
Hi,
> > Changing the order doesn't look hard. Patch attached (untested, have no
> > test hardware). But maybe I missed some detail ...
>
> I came up with something very similar by splitting up nouveau_bo_new()
> into allocation and initialization steps, so that when necessary the GEM
>
On Wed, Aug 14, 2019 at 07:58:27AM +0200, Gerd Hoffmann wrote:
> > Hi Gerd,
> >
> > I've been seeing a regression on Nouveau with recent linux-next releases
> > and git bisect points at this commit as the first bad one. If I revert
> > it (there's a tiny conflict with a patch that was merged
Am 13.08.19 um 21:20 schrieb Zhao, Yong:
The amdgpu_task_info will be used when printing VM page fault for KFD
processes.
Change-Id: Ifd983db5dceb1d477e7287e4893f80565a7a6b06
Signed-off-by: Yong Zhao
Acked-by: Christian König
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 2 ++
1 file
Am 09.08.19 um 06:21 schrieb Zeng, Oak:
> Calling amdgpu function to invalidate TLB, instead of using a
> kfd implementation. Delete the kfd local TLB invalidation
> implementation.
>
> Change-Id: Ia16fcf9091a93b8c0acdaf9981f8a5a1f9a5ca1d
> Signed-off-by: Oak Zeng
Reviewed-by: Christian König
Am 09.08.19 um 06:21 schrieb Zeng, Oak:
> This is for kfd to reuse amdgpu TLB invalidation function.
> On gfx10, kfd only needs to flush TLB on gfx hub but not
> on mm hub. So export a function for KFD flush TLB only on
> specific hub.
>
> Change-Id: I58ff00969f88438cfd3dc7e9deb7bff0c1bb4133
>
Am 13.08.19 um 20:43 schrieb Zhao, Yong:
We have done this for pre-GFX10 asics, but GFX10 did not pick up the
new change. The below is the commit message for that change.
This is recommended by HW designers. Previously when it was set to 1,
the PDE walk error in VM fault will be treated as
Am 13.08.19 um 20:08 schrieb Zhao, Yong:
RW is also useful in most cases.
Change-Id: Icf4bd65ea168e5965a6a8ebe32ce9327a2de2851
Signed-off-by: Yong Zhao
Reviewed-by: Christian König for the series.
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 +++
1 file changed, 3 insertions(+)
diff
62 matches
Mail list logo