On Tue, Feb 08, 2022 at 03:37:12PM +0800, Hsin-Yi Wang wrote:
> +int drm_connector_init_panel_orientation_property(
> + struct drm_connector *connector)
> +{
> + struct drm_device *dev = connector->dev;
> + struct drm_property *prop;
> +
> + prop = drm_property_create_enum(dev, DRM_
> -static inline bool page_is_devmap_managed(struct page *page)
> +bool __put_devmap_managed_page(struct page *page);
> +static inline bool put_devmap_managed_page(struct page *page)
> {
> if (!static_branch_unlikely(&devmap_managed_key))
> return false;
> if (!is_zone_d
only vangogh has 2 types of hwmon power node: "fastPPT" and "slowPPT",
the other asic only has 1 type of hwmon power node: "PPT".
Signed-off-by: Yang Wang
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/
On 2/6/22 10:32 PM, Christoph Hellwig wrote:
> free_devmap_managed_page has nothing to do with the code in swap.c,
> move it to live with the rest of the code for devmap handling.
>
> Signed-off-by: Christoph Hellwig
True, the only devmap code is present in the swap.c is couple of
calls in my tre
On 2/6/22 10:32 PM, Christoph Hellwig wrote:
> hmm.h pulls in the world for no good reason at all. Remove the
> includes and push a few ones into the users instead.
>
> Signed-off-by: Christoph Hellwig
Looks good.
Reviewed-by: Chaitanya Kulkarni
Am 08.02.22 um 04:14 schrieb zhanglianjie:
after the buffer object is successfully mapped, call radeon_bo_kunmap before
the function returns.
Signed-off-by: zhanglianjie
Reviewed-by: Christian König
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c
b/drivers/gpu/drm/radeon/radeon_uvd.c
i
On 2/6/22 10:32 PM, Christoph Hellwig wrote:
> __KERNEL__ ifdefs don't make sense outside of include/uapi/.
>
> Signed-off-by: Christoph Hellwig
> ---
> include/linux/mm.h | 4
> 1 file changed, 4 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 213cc569b1922
On 2/6/22 10:32 PM, Christoph Hellwig wrote:
> memremap.c is only built when CONFIG_ZONE_DEVICE is set, so remove
> the superflous extra check.
>
> Signed-off-by: Christoph Hellwig
> ---
> mm/memremap.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/mm/memremap.c b
it will cause hwmon node of power1_label is not created.
v2:
the hwmon node of "power1_lable" is always needed for all ASICs.
and the patch will remove ASIC type check for "power1_label".
Fixes: ae07970a06 ("drm/amd/pm: add support for hwmon control of slow and fast
PPT limit on vangogh")
Signe
Reviewed-by: Kenneth Feng
-Original Message-
From: Wang, Yang(Kevin)
Sent: Tuesday, February 8, 2022 2:35 PM
To: amd-gfx@lists.freedesktop.org
Cc: Feng, Kenneth ; Lazar, Lijo ;
Hou, Xiaomeng (Matthew) ; Wang, Yang(Kevin)
Subject: [PATCH] drm/amd/pm: fix hwmon node of power1_label cr
On Mon, Feb 07, 2022 at 04:19:29PM -0500, Felix Kuehling wrote:
>
> Am 2022-02-07 um 01:32 schrieb Christoph Hellwig:
>> Move the check for the actual pgmap types that need the free at refcount
>> one behavior into the out of line helper, and thus avoid the need to
>> pull memremap.h into mm.h.
>>
fix typo issue about "power1_label",
it will cause hwmon node of power1_label is not created.
Fixes: ae07970a06 ("drm/amd/pm: add support for hwmon control of slow and fast
PPT limit on vangogh")
Signed-off-by: Yang Wang
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 2 +-
1 file changed, 1 insertio
On 1/26/2022 4:07 AM, Andrey Grodzovsky wrote:
Since we serialize all resets no need to protect from concurrent
resets.
Signed-off-by: Andrey Grodzovsky
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 19 +--
drivers/gpu/drm/amd/amdgpu/amdgpu
Reviewed-by: Kenneth Feng
-Original Message-
From: Wang, Yang(Kevin)
Sent: Tuesday, February 8, 2022 12:30 PM
To: amd-gfx@lists.freedesktop.org
Cc: Feng, Kenneth ; Lazar, Lijo ;
Nikolic, Marina ; Wang, Yang(Kevin)
Subject: [PATCH] drm/amd/pm: disable GetPptLimit message in sriov mod
On 2/8/2022 10:00 AM, Yang Wang wrote:
the pmfw is not allowed GetPptLimit message in virtualzation mode.
Maybe rephrase as - "PPT limit cannot be queried from VF".
Reviewed-by: Lijo Lazar
Thanks,
Lijo
Fixes: 3e4a01689daa ("drm/amd/pm: Enable sysfs required by rocm-smi toolfor One VF
the pmfw is not allowed GetPptLimit message in virtualzation mode.
Fixes: 3e4a01689daa ("drm/amd/pm: Enable sysfs required by rocm-smi toolfor One
VF mode")
Signed-off-by: Yang Wang
---
drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-
Fulfill the implementations for DriverSmuConfig setting on Navi1x.
Signed-off-by: Evan Quan
Change-Id: I244766a893b4070dfdf171451f6338d33572ec1d
---
.../gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 50 +++
1 file changed, 50 insertions(+)
diff --git a/drivers/gpu/drm/amd/pm/swsmu
MMHUB PG needs to be disabled for Picasso for stability reasons.
Signed-off-by: Evan Quan
Change-Id: Iea0ec757582a764ab5a000d7cc411fb814ffb19f
---
drivers/gpu/drm/amd/amdgpu/soc15.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c
b/driv
Add a quirk in sienna_cichlid_ppt.c to fix some OEM SKU
specific stability issues.
Signed-off-by: Evan Quan
Change-Id: I172c6429c54253788dbf28f7acf877375f2bfc5b
---
.../amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 32 ++-
1 file changed, 31 insertions(+), 1 deletion(-)
diff --git
Fulfill the implementations for DriverSmuConfig setting on Sienna_Cichlid.
Signed-off-by: Evan Quan
Change-Id: Ic519c8d4fcfeefdda79ba9ed01b235824d76e40f
---
.../amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 54 +++
1 file changed, 54 insertions(+)
diff --git a/drivers/gpu/drm/amd/
Enable the support for DriverSmuConfig table on Navi1x and
Sienna_Cichlid.
Signed-off-by: Evan Quan
Change-Id: Ie510f8b06b7a4910b1574b6e9affa875805ef868
---
drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 1 +
drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 9 +
.../gpu/drm
For Some ASICs, with the PMFW default settings, we may see the
power consumption reported via metrics table is "Very Erratic".
With the socket power alpha filter set as 10/100ms, we can correct
that issue.
Signed-off-by: Evan Quan
Change-Id: Ia352579e1cc7a531cb1de5c835fe5bf132d5dd20
---
drivers/
Correct the UMD pstate profiling clocks for Dimgrey Cavefish and Beige
Goby.
Signed-off-by: Evan Quan
Change-Id: I74fdbcf2cfa11f97ae16e4921449ab7cdb7e43c9
---
.../amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 26 +++
.../amd/pm/swsmu/smu11/sienna_cichlid_ppt.h | 8 ++
2 file
On 2/6/22 22:32, Christoph Hellwig wrote:
ZONE_DEVICE struct pages have an extra reference count that complicates
the code for put_page() and several places in the kernel that need to
check the reference count to see that a page is not being used (gup,
compaction, migration, etc.). Clean up the c
On 2022-02-06 11:32 p.m., Christoph Hellwig wrote:
> Hi all,
>
> this series removes the offset by one refcount for ZONE_DEVICE pages
> that are freed back to the driver owning them, which is just device
> private ones for now, but also the planned device coherent pages
> and the ehanced p2p on
On Sun, Feb 6, 2022 at 10:33 PM Christoph Hellwig wrote:
>
> Move the check for the actual pgmap types that need the free at refcount
> one behavior into the out of line helper, and thus avoid the need to
> pull memremap.h into mm.h.
Looks good to me assuming the compile bots agree.
Reviewed-by:
On Sun, Feb 6, 2022 at 10:33 PM Christoph Hellwig wrote:
>
> Make put_devmap_managed_page return if it took charge of the page
> or not and remove the separate page_is_devmap_managed helper.
Looks good to me:
Reviewed-by: Dan Williams
Am 2022-02-07 um 14:53 schrieb Mukul Joshi:
A few MQD manager functions are duplicated for all versions of
MQD manager. Remove this duplication by moving the common
functions into kfd_mqd_manager.c file.
Signed-off-by: Mukul Joshi
Reviewed-by: Felix Kuehling
---
v1->v2:
- Add "kfd_" pre
Am 2022-02-07 um 14:52 schrieb Mukul Joshi:
With no HWS, TLB flushing will not work in SVM code.
Fix this by calling kfd_flush_tlb() which works for both
HWS and no HWS case.
Signed-off-by: Mukul Joshi
Reviewed-by: Philip Yang
---
v1->v2:
- Don't pass adev to svm_range_map_to_gpu().
drive
Am 2022-02-07 um 14:52 schrieb Mukul Joshi:
Cleanup the kfd code by removing the unused old debugger
implementation.
You can add here, that address watch was only ever implemented in the
upstream driver for GFXv7 (Kaveri). The user mode tools runtime using
this API was never open-sourced. Wor
Am 2022-02-07 um 01:32 schrieb Christoph Hellwig:
Move the check for the actual pgmap types that need the free at refcount
one behavior into the out of line helper, and thus avoid the need to
pull memremap.h into mm.h.
Signed-off-by: Christoph Hellwig
The amdkfd part looks good to me.
It l
Applied. Thanks!
On Sun, Feb 6, 2022 at 10:30 PM Quan, Evan wrote:
>
> [AMD Official Use Only]
>
> Thanks for the fix!
> Reviewed-by: Evan Quan
>
> > -Original Message-
> > From: Maíra Canal
> > Sent: Thursday, February 3, 2022 8:40 AM
> > To: Quan, Evan ; Deucher, Alexander
> > ; Koen
Applied. Thanks!
Alex
On Sun, Feb 6, 2022 at 10:04 PM Quan, Evan wrote:
>
> [AMD Official Use Only]
>
> Reviewed-by: Evan Quan
>
> > -Original Message-
> > From: t...@redhat.com
> > Sent: Saturday, February 5, 2022 11:00 PM
> > To: Quan, Evan ; Deucher, Alexander
> > ; Koenig, Christi
A few MQD manager functions are duplicated for all versions of
MQD manager. Remove this duplication by moving the common
functions into kfd_mqd_manager.c file.
Signed-off-by: Mukul Joshi
---
v1->v2:
- Add "kfd_" prefix to functions moved to kfd_mqd_manager.c.
- Also, suffix "_cp" to function name
Cleanup the kfd code by removing the unused old debugger
implementation.
Only a small piece of resetting wavefronts is kept and
is moved to kfd_device_queue_manager.c
Signed-off-by: Mukul Joshi
---
v1->v2:
- Rename AMDKFD_IOC_DBG_* to AMDKFD_IOC_DBG_*_DEPRECATED.
- Cleanup address_watch_disable()
With no HWS, TLB flushing will not work in SVM code.
Fix this by calling kfd_flush_tlb() which works for both
HWS and no HWS case.
Signed-off-by: Mukul Joshi
Reviewed-by: Philip Yang
---
v1->v2:
- Don't pass adev to svm_range_map_to_gpu().
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 24 ++-
On Mon, Feb 07, 2022 at 07:32:49AM +0100, Christoph Hellwig wrote:
> Add a depends on ZONE_DEVICE support or the s390-specific limited DAX
> support, as one of the two is required at runtime for fsdax code to
> actually work.
>
> Signed-off-by: Christoph Hellwig
> ---
> fs/Kconfig | 1 +
> 1 fil
On Mon, Feb 07, 2022 at 07:32:47AM +0100, Christoph Hellwig wrote:
> Move the check for the actual pgmap types that need the free at refcount
> one behavior into the out of line helper, and thus avoid the need to
> pull memremap.h into mm.h.
>
> Signed-off-by: Christoph Hellwig
> ---
> arch/arm6
On Mon, Feb 07, 2022 at 07:32:46AM +0100, Christoph Hellwig wrote:
> Make put_devmap_managed_page return if it took charge of the page
> or not and remove the separate page_is_devmap_managed helper.
>
> Signed-off-by: Christoph Hellwig
> ---
> include/linux/mm.h | 34 ++--
On Mon, Feb 07, 2022 at 07:32:45AM +0100, Christoph Hellwig wrote:
> free_devmap_managed_page has nothing to do with the code in swap.c,
> move it to live with the rest of the code for devmap handling.
>
> Signed-off-by: Christoph Hellwig
> ---
> include/linux/mm.h | 1 -
> mm/memremap.c |
On Mon, Feb 07, 2022 at 07:32:43AM +0100, Christoph Hellwig wrote:
> __KERNEL__ ifdefs don't make sense outside of include/uapi/.
>
> Signed-off-by: Christoph Hellwig
> ---
> include/linux/mm.h | 4
> 1 file changed, 4 deletions(-)
Reviewed-by: Jason Gunthorpe
Jason
On Mon, Feb 07, 2022 at 07:32:42AM +0100, Christoph Hellwig wrote:
> memremap.c is only built when CONFIG_ZONE_DEVICE is set, so remove
> the superflous extra check.
>
> Signed-off-by: Christoph Hellwig
> ---
> mm/memremap.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
Reviewed-by:
On Mon, Feb 07, 2022 at 07:32:48AM +0100, Christoph Hellwig wrote:
> ZONE_DEVICE struct pages have an extra reference count that complicates
> the code for put_page() and several places in the kernel that need to
> check the reference count to see that a page is not being used (gup,
> compaction, m
On Sun, Feb 6, 2022 at 10:33 PM Christoph Hellwig wrote:
>
> free_devmap_managed_page has nothing to do with the code in swap.c,
> move it to live with the rest of the code for devmap handling.
>
Looks good.
Reviewed-by: Dan Williams
On 2022-02-07 13:57, Harry Wentland wrote:
> On 2022-02-07 11:34, Maxime Ripard wrote:
>> The amdgpu KMS driver calls drm_plane_create_color_properties() with a
>> default encoding set to BT709.
>>
>> However, the core will ignore it and the driver doesn't force it in its
>> plane state reset ho
On 2022-02-07 11:34, Maxime Ripard wrote:
> The amdgpu KMS driver calls drm_plane_create_color_properties() with a
> default encoding set to BT709.
>
> However, the core will ignore it and the driver doesn't force it in its
> plane state reset hook, so the initial value will be 0, which represents
The amdgpu KMS driver calls drm_plane_create_color_properties() with a
default encoding set to BT709.
However, the core will ignore it and the driver doesn't force it in its
plane state reset hook, so the initial value will be 0, which represents
BT601.
Fix the mismatch by using an initial value
On 2022-02-06 11:32 p.m., Christoph Hellwig wrote:
> Move the check for the actual pgmap types that need the free at refcount
> one behavior into the out of line helper, and thus avoid the need to
> pull memremap.h into mm.h.
>
> Signed-off-by: Christoph Hellwig
I've noticed mm/memcontrol.c u
On Sun, Feb 6, 2022 at 10:33 PM Christoph Hellwig wrote:
>
> __KERNEL__ ifdefs don't make sense outside of include/uapi/.
Yes.
Reviewed-by: Dan Williams
On Sun, Feb 6, 2022 at 10:33 PM Christoph Hellwig wrote:
>
> memremap.c is only built when CONFIG_ZONE_DEVICE is set, so remove
> the superflous extra check.
Looks good to me.
Reviewed-by: Dan Williams
Am 2022-02-07 um 12:50 schrieb Joshi, Mukul:
[AMD Official Use Only]
-Original Message-
From: Kuehling, Felix
Sent: Monday, February 7, 2022 10:43 AM
To: Joshi, Mukul ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 3/3] drm/amdkfd: Consolidate MQD manager functions
Am 2022-02
[AMD Official Use Only]
> -Original Message-
> From: Kuehling, Felix
> Sent: Monday, February 7, 2022 10:43 AM
> To: Joshi, Mukul ; amd-gfx@lists.freedesktop.org
> Subject: Re: [PATCH 3/3] drm/amdkfd: Consolidate MQD manager functions
>
>
> Am 2022-02-04 um 18:45 schrieb Mukul Joshi:
Am 2022-02-07 um 12:10 schrieb Joshi, Mukul:
[AMD Official Use Only]
-Original Message-
From: Kuehling, Felix
Sent: Monday, February 7, 2022 10:33 AM
To: Joshi, Mukul ; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH 2/3] drm/amdkfd: Remove unused old debugger
implementation
Am 2
[AMD Official Use Only]
> -Original Message-
> From: Kuehling, Felix
> Sent: Monday, February 7, 2022 10:33 AM
> To: Joshi, Mukul ; amd-gfx@lists.freedesktop.org
> Subject: Re: [PATCH 2/3] drm/amdkfd: Remove unused old debugger
> implementation
>
>
> Am 2022-02-04 um 18:45 schrieb Muk
This reverts commit 733a212f20dfa14fa20814f21526fb180f25fdd8.
---
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 ++-
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 +-
.../gpu/drm/amd/display/dc/core/dc_resource.c | 2 +-
.../gpu/drm/amd/display/include/dal_asic_id.h | 3
Reverting patch
Jasdeep Dhillon (1):
Revert "drm/amd/display: Basic support with device ID"
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 ++-
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 +-
.../gpu/drm/amd/display/dc/core/dc_resource.c | 2 +-
.../gpu/drm/amd/disp
[AMD Official Use Only]
Acked-by: Alex Deucher
From: amd-gfx on behalf of Jasdeep
Dhillon
Sent: Monday, February 7, 2022 11:23 AM
To: amd-gfx@lists.freedesktop.org
Cc: Wang, Chao-kai (Stylon) ; Li, Sun peng (Leo)
; Wentland, Harry ; Zhuo, Qingqing
(Lillian)
[AMD Official Use Only]
Most of the register programming in evergreen_gpu_init is required. That code
handles things like harvesting (e.g., disabling bad hardware resources) and
setting sane asic specific settings in some registers. If you don't do it,
work may get scheduled to bad or incorre
[AMD Official Use Only]
Hi Alex,
I already merged the branch but I have sent you the revert patch.
Regards,
Jasdeep
From: Alex Deucher
Sent: February 7, 2022 10:58 AM
To: Dhillon, Jasdeep
Cc: amd-gfx list ; Wang, Chao-kai (Stylon)
; Liu, Charlene ; Logush, Oli
Reverting patch
Jasdeep Dhillon (1):
Revert "drm/amd/display: Basic support with device ID"
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 ++-
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 +-
.../gpu/drm/amd/display/dc/core/dc_resource.c | 2 +-
.../gpu/drm/amd/disp
On Fri, Feb 4, 2022 at 11:33 PM Jasdeep Dhillon wrote:
>
> From: Oliver Logush
>
> [why]
> To get the the cyan_skillfish check working
NAK. This is still not correct.
>
> Reviewed-by: Charlene Liu
> Reviewed-by: Charlene Liu
> Acked-by: Jasdeep Dhillon
> Signed-off-by: Oliver Logush
> ---
Am 2022-02-04 um 18:45 schrieb Mukul Joshi:
A few MQD manager functions are duplicated for all versions of
MQD manager. Remove this duplication by moving the common
functions into kfd_mqd_manager.c file.
Signed-off-by: Mukul Joshi
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c | 63 +
Am 2022-02-04 um 18:45 schrieb Mukul Joshi:
Cleanup the kfd code by removing the unused old debugger
implementation.
Only a small piece of resetting wavefronts is kept and
is moved to kfd_device_queue_manager.c
Signed-off-by: Mukul Joshi
We should update include/uapi/linux/kfd_ioctl.h as we
On 2022-02-04 6:45 p.m., Mukul Joshi
wrote:
With no HWS, TLB flushing will not work in SVM code.
Fix this by calling kfd_flush_tlb() which works for both
HWS and no HWS case.
Signed-off-by: Mukul Joshi
With below change to remove one extra calling
Hi Guchun,
SDMA FW team confirms MI50/VG20 doesn't have the same bug as MI100,
which cases asic hang issue when running RVS test. If this change makes
KFDMemoryTest failed, please fill a Jira and assign to me.
Thanks,
Eric
On 2022-02-07 08:01, Chen, Guchun wrote:
[Public]
Hi Eric,
Are you
[Public]
Hi all,
This week this patchset was tested on the following systems:
HP Envy 360, with Ryzen 5 4500U, with the following display types: eDP 1080p
60hz, 4k 60hz (via USB-C to DP/HDMI), 1440p 144hz (via USB-C to DP/HDMI),
1680*1050 60hz (via USB-C to DP and then DP to DVI/VGA)
Leno
Am 2022-02-07 um 03:07 schrieb Christian König:
We want to have lockdep annotation here, so make sure that we reserve
the PD while removing PRTs even if it isn't strictly necessary since the
VM object is about to be destroyed anyway.
Signed-off-by: Christian König
Reviewed-by: Felix Kuehling
Am 2022-02-07 um 02:27 schrieb Tao Zhou:
Replace reset queue for specific PASID with unmap all queues, reset
queue could break CP scheduler.
Signed-off-by: Tao Zhou
The series is
Reviewed-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 3 +--
1 file changed,
On Mon, Feb 07, 2022 at 07:32:44AM +0100, Christoph Hellwig wrote:
> hmm.h pulls in the world for no good reason at all. Remove the
> includes and push a few ones into the users instead.
>
> Signed-off-by: Christoph Hellwig
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 1 +
> drivers/gpu/d
[Public]
Hi Eric,
Are you sure that there is no FW requirement for this patch on Vega20?
KFDMemory test failed by this commit.
Regards,
Guchun
-Original Message-
From: amd-gfx On Behalf Of Alex Deucher
Sent: Tuesday, January 25, 2022 4:08 AM
To: Huang, JinHuiEric
Cc: amd-gfx list
Su
migrate_vma_setup() checks that a valid vma is passed so that the page
tables can be walked to find the pfns associated with a given address
range. However in some cases the pfns are already known, such as when
migrating device coherent pages during pin_user_pages() meaning a valid
vma isn't requir
kmalloc_array()/kcalloc() should be used to avoid potential overflow when
a multiplication is needed to compute the size of the requested memory.
So turn a kzalloc()+explicit size computation into an equivalent kcalloc().
Signed-off-by: Christophe JAILLET
---
drivers/gpu/drm/radeon/radeon_atomb
Currently any attempts to pin a device coherent page will fail. This is
because device coherent pages need to be managed by a device driver, and
pinning them would prevent a driver from migrating them off the device.
However this is no reason to fail pinning of these pages. These are
coherent and
On Wednesday, 2 February 2022 2:03:01 AM AEDT Felix Kuehling wrote:
>
> Am 2022-02-01 um 02:05 schrieb Alistair Popple:
> > Currently any attempts to pin a device coherent page will fail. This is
> > because device coherent pages need to be managed by a device driver, and
> > pinning them would pr
Device coherent pages represent memory on a coherently attached device such
as a GPU which is usually under the control of a driver. These pages should
not be pinned as the driver needs to be able to move pages as required.
Currently this is enforced by failing any attempt to pin a device coherent
On Mon, Jul 12, 2021 at 11:56 AM Tomasz Moń wrote:
> I am having trouble getting Linux to run on MacBook Pro 2019 with
> Radeon Pro Vega 20 4 GB. Basically as soon as graphical user interface
> starts, the whole system freezes. This happens with every Linux kernel
> version I have tried over the l
From: Alex Sierra
The intention is to test device coherent type pages that have been
called through get user pages with PIN_LONGTERM flag set. These pages
should get migrated back to normal system memory.
Signed-off-by: Alex Sierra
Signed-off-by: Alistair Popple
Reviewed-by: Felix Kuehling
-
From: Tom Rix
clang static analysis reports this error
amdgpu_smu.c:2289:9: warning: Called function pointer
is null (null dereference)
return smu->ppt_funcs->emit_clk_levels(
^~~~
There is a logic error in the earlier check of
emit_clk_levels
We want to have lockdep annotation here, so make sure that we reserve
the PD while removing PRTs even if it isn't strictly necessary since the
VM object is about to be destroyed anyway.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 6 --
1 file changed, 4 inser
Am 05.02.22 um 18:38 schrieb Christophe JAILLET:
kmalloc_array()/kcalloc() should be used to avoid potential overflow when
a multiplication is needed to compute the size of the requested memory.
So turn a kzalloc()+explicit size computation into an equivalent kcalloc().
Signed-off-by: Christoph
80 matches
Mail list logo
