[AMD Official Use Only - General]
Reviewed-by: Hawking Zhang
Regards,
Hawking
-Original Message-
From: Chai, Thomas
Sent: Thursday, August 10, 2023 10:01
To: amd-gfx@lists.freedesktop.org
Cc: Chai, Thomas ; Zhang, Hawking ;
Zhou1, Tao ; Li, Candice ; Yang, Stanley
; Chai, Thomas
[AMD Official Use Only - General]
Reviewed-by: Tao Zhou
> -Original Message-
> From: Hawking Zhang
> Sent: Wednesday, August 9, 2023 7:22 PM
> To: amd-gfx@lists.freedesktop.org; Zhou1, Tao
> Cc: Zhang, Hawking
> Subject: [PATCH] drm/amdgpu: Remove unnecessary ras cap check
>
> RAS
Mode1 reset needs to recover mp1 in fatal error case
for mp0 v13_0_10.
v2:
Define a macro to wrap psp function calls.
Signed-off-by: YiPeng Chai
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h | 5 +
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 2 ++
drivers/gpu/drm/amd/amdgpu/psp_v13_0.c |
[Public]
Reviewed-by: Guchun Chen
Regards,
Guchun
> -Original Message-
> From: amd-gfx On Behalf Of Alex
> Deucher
> Sent: Wednesday, July 12, 2023 11:53 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Deucher, Alexander
> Subject: [PATCH] drm/amdgpu: expand runpm parameter
>
> Allow
Applied. Thanks!
Alex
On Mon, Jul 3, 2023 at 7:16 PM Uros Bizjak wrote:
>
> Use local64_try_cmpxchg instead of local64_cmpxchg (*ptr, old, new) == old
> in amdgpu_perf_read. x86 CMPXCHG instruction returns success in ZF flag,
> so this change saves a compare after cmpxchg (and related move
On 2023-08-09 17:26, Jay Cornwall wrote:
Previously asymptomatic because high 32 bits were zero.
Fixes: 615222cfed20 ("drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole")
Signed-off-by: Jay Cornwall
Reviewed-by: Felix Kuehling
---
[AMD Official Use Only - General]
Reviewed-by: Alex Deucher
From: amd-gfx on behalf of Jay Cornwall
Sent: Wednesday, August 9, 2023 5:26 PM
To: amd-gfx@lists.freedesktop.org
Cc: Cornwall, Jay ; Kasiviswanathan, Harish
Subject: [PATCH] drm/amdkfd: Add
Previously asymptomatic because high 32 bits were zero.
Fixes: 615222cfed20 ("drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole")
Signed-off-by: Jay Cornwall
---
drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c | 1 +
1 file changed, 1 insertion(+)
diff --git
On Wed, Aug 9, 2023 at 3:35 AM Michel Dänzer wrote:
>
> On 8/8/23 19:03, Marek Olšák wrote:
> > It's the same situation as SIGSEGV. A process can catch the signal,
> > but if it doesn't, it gets killed. GL and Vulkan APIs give you a way
> > to catch the GPU error and prevent the process
On 2023-08-09 01:30, Atul Raut wrote:
To prevent its redundant implementation and streamline
code, use memdup_user.
This fixes warnings reported by Coccinelle:
./drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c:2811:13-20: WARNING
opportunity for memdup_user
Signed-off-by: Atul Raut
This reverts commit e490d60a2f76bff636c68ce4fe34c1b6c34bbd86.
This causes hangs on SI when DC is enabled.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2755
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 29 ++
1 file changed, 29
We need the domains in amdgpu_drm.h for the kernel driver to manage
the pool, but we don't want userspace using it until the code
is ready. So reject for now.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4
1 file changed, 4 insertions(+)
diff --git
tree/branch:
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
branch HEAD: 21ef7b1e17d039053edaeaf41142423810572741 Add linux-next specific
files for 20230809
Error/Warning reports:
https://lore.kernel.org/oe-kbuild-all/202307251531.p8zlftmz-...@intel.com
https
Hi Dave, Daniel,
Fixes for 6.5. Was on PTO last week, so two weeks worth.
The following changes since commit 52a93d39b17dc7eb98b6aa3edb93943248e03b2f:
Linux 6.5-rc5 (2023-08-06 15:07:51 -0700)
are available in the Git repository at:
https://gitlab.freedesktop.org/agd5f/linux.git
[AMD Official Use Only - General]
Hi Stylon,
Sorry, the title is misleading. This doesn't touch display. Could you please
remove display from the title and make it drm/amd:
--
Regards,
Jay
From: Wang, Chao-kai (Stylon)
Sent: Wednesday, August 9, 2023 11:05 AM
From: Aric Cyr
This version brings along following fixes:
- Improve power saving feature
- Clean up for code clarity
- Fix MST issues in system resume
- Fix crashing bug
- Fix pipe allocation for older ASIC
- Fix for gamut remap
- Fix 8K 60Hz display in test cases
- Fix bug in clock gating
-
From: Anthony Koo
- Add defines to specify new PHY power states
Acked-by: Stylon Wang
Signed-off-by: Anthony Koo
---
drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
From: Aurabindo Pillai
[Why]
Freesync Video mode was enabled by default. Hence no need for the module
parameter, so remove it completely
Acked-by: Stylon Wang
Signed-off-by: Aurabindo Pillai
Reviewed-by: Stylon Wang
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 -
From: Aurabindo Pillai
[Why]
When unused, all memory blocks should be put in a low power state
[How]
Check the value of enable_mem_low_power.bits.vga and set
corresponding bit in the hardware register
Acked-by: Stylon Wang
Signed-off-by: Aurabindo Pillai
Reviewed-by: Rodrigo Siqueira
---
From: Aurabindo Pillai
[Why]
Add some missing register definitions and rearrange some others to
maintain consistency with related definitions.
Acked-by: Stylon Wang
Signed-off-by: Aurabindo Pillai
Reviewed-by: Rodrigo Siqueira
---
.../gpu/drm/amd/display/dc/dce/dce_hwseq.h| 69
From: Wenjing Liu
[why]
There is a lack of encapsulation of pipe connection representation in pipe
context.
This has caused many challenging bugs and coding errors with repeated
logic to identify the same pipe type.
[how]
Formally define pipe types and provide getters to identify a pipe type
From: Charlene Liu
[why]
add dml1 used calculate_wm_and_dlg function pointer check to prevent crash.
add z8 watermarks to struct for later asic use
Reviewed-by: Alvin Lee
Acked-by: Stylon Wang
Signed-off-by: Charlene Liu
---
drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 3 ++-
From: Wayne Lin
[Why]
In current dm_resume, dm->cached_state is restored after link get
detected and updated which will cause problems especially for MST
case.
In drm_dp_mst_topology_mgr_resume() today, it will resume the
mst branch to be ready handling mst mode and also consecutively do
the
From: Wenjing Liu
[why]
There is a recent work for developing a new pipe resource allocation
policy used for new ASIC. The new code change needs to modify asic
independent pipe resource allocation flow and hook up the new allocation
policy in asic dependent layer. Unfortunately this change
From: Alvin Lee
[Description]
We want PMFW to wait for DMCUB to ACK the MCLK end message
for FPO cases as well.
Reviewed-by: Samson Tam
Acked-by: Stylon Wang
Signed-off-by: Alvin Lee
---
.../gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c | 5 +
From: Alvin Lee
[Description]
Expand the SubVP policy to include up to 175hz displays
for better power saving on more display configs.
Reviewed-by: Chaitanya Dhere
Acked-by: Stylon Wang
Signed-off-by: Alvin Lee
---
drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 2 +-
From: Krunoslav Kovac
[WHY]
If surface format is dynamically changed within app without changing
timing / whole plane, we don't reprogram gamut remap matrix.
Issue example:
Linear FP16 scRGB going to PQ+BT.2020 monitor.
Remap = scRGB->BT.2020
App switches swapchain format to 10-bit PQ+BT.2020.
From: Nicholas Susanto
[Why]
8k60hz compliace test failing because we restrict it single memory
channels. Workaround by not restricting it on single displays.
[How]
Adding an additional check to DCN314 to restrict 8k60hz mode if it has
more than 1 display connected.
Reviewed-by: Nicholas
From: Michael Strauss
[WHY]
Certain retimer requires workarounds in order to correctly output test patterns.
[HOW]
Add vendor-specific aux sequences to program retimer's TX and pattern generator
when specific compliance test patterns are requested by sink.
Note: SQ128 w/a in DPMF mode only
From: Muhammad Ahmed
[Why]
disable clock gating logic reversed bug fix
Reviewed-by: Charlene Liu
Acked-by: Stylon Wang
Signed-off-by: Muhammad Ahmed
---
drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c | 4 ++--
drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c | 4 ++--
2 files
This DC patchset brings improvements in multiple areas. In summary, we have:
- Improve power saving feature
- Clean up for code clarity
- Fix MST issues in system resume
- Fix crashing bug
- Fix pipe allocation for older ASIC
- Fix for gamut remap
- Fix 8K 60Hz display in test cases
- Fix bug in
On Tue, Aug 8, 2023 at 11:21 PM wrote:
>
> From: Jiadong Zhu
>
> The parameter amdgpu_mcbp shall have priority against the default value
> calculated from the chip version.
> User could disable mcbp by setting the parameter mcbp as zero.
>
> v2: do not trigger preemption in sw ring muxer when
Ping?
On Wed, Jul 12, 2023 at 11:53 AM Alex Deucher wrote:
>
> Allow the user to specify -2 as auto enabled with displays.
>
> By default we don't enter runtime suspend when there are
> displays attached because it does not work well in some
> desktop environments due to the driver sending
Applied. Thanks!
On Wed, Aug 9, 2023 at 2:15 AM Christian König wrote:
>
> Am 09.08.23 um 05:44 schrieb Ruan Jinjie:
> > The NULL initialization of the pointers assigned by kzalloc() first is
> > not necessary, because if the kzalloc() failed, the pointers will be
> > assigned NULL, otherwise
Applied. Thanks!
On Tue, Aug 8, 2023 at 7:26 PM Randy Dunlap wrote:
>
> These functions don't use kernel-doc notation for comments so
> don't begin each comment block with the "/**" kernel-doc marker.
>
> This prevents a bunch of kernel-doc warnings:
>
> dmub_replay.c:37: warning: This comment
On 8/9/2023 6:07 PM, Alex Deucher wrote:
On Wed, Aug 9, 2023 at 8:28 AM Lazar, Lijo wrote:
On 8/9/2023 5:50 PM, Alex Deucher wrote:
On Wed, Aug 9, 2023 at 6:12 AM Kenneth Feng wrote:
drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
V2: depend on pm.no_fan to
On Wed, Aug 9, 2023 at 5:50 AM Srinivasan Shanmugam
wrote:
>
> Fixes the following:
>
> WARNING: Avoid multiple line dereference - prefer 'ctx->io_attr'
> + ((ctx->
> + io_attr >> CU8(base + 2)) & (0x >> (32 -
>
> Cc: Guchun Chen
>
On Wed, Aug 9, 2023 at 8:28 AM Lazar, Lijo wrote:
>
>
>
> On 8/9/2023 5:50 PM, Alex Deucher wrote:
> > On Wed, Aug 9, 2023 at 6:12 AM Kenneth Feng wrote:
> >>
> >> drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
> >> V2: depend on pm.no_fan to check
> >>
> >> Signed-off-by:
On 8/9/2023 5:50 PM, Alex Deucher wrote:
On Wed, Aug 9, 2023 at 6:12 AM Kenneth Feng wrote:
drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
V2: depend on pm.no_fan to check
Signed-off-by: Kenneth Feng
You can still read the fan speed though right? Don't we want
On 09/08/23 00:44, Ruan Jinjie wrote:
> The NULL initialization of the pointers assigned by
> kunit_kzalloc() first is not necessary, because if kunit_kzalloc()
> failed, the pointers will be assigned NULL, otherwise it works
> as usual. so remove it.
>
> Signed-off-by: Ruan Jinjie
> ---
>
On Wed, Aug 9, 2023 at 6:12 AM Kenneth Feng wrote:
>
> drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
> V2: depend on pm.no_fan to check
>
> Signed-off-by: Kenneth Feng
You can still read the fan speed though right? Don't we want to just
not expose the ability to
From: Luben Tuikov
commit 3273f11675ef11959d25a56df3279f712bcd41b7 upstream
Remove the "domain" argument to amdgpu_bo_create_kernel_at() since this
function takes an "offset" argument which is the offset off of VRAM, and as
such allocation always takes place in VRAM. Thus, the "domain" argument
Hello Bhawanpreet Lakha,
The patch c7ddc0a800bc: "drm/amd/display: Add Functions to enable
Freesync Panel Replay" from May 12, 2023 (linux-next), leads to the
following Smatch static checker warning:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_edp_panel_control.c:849
This is a note to let you know that I've just added the patch titled
drm/amdgpu: Remove unnecessary domain argument
to the 6.1-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
On Wed, Aug 9, 2023 at 3:15 AM Umio Yasuno
wrote:
>
> Sorry, I had mistaken MP1 for MP0.
> Also, should I add an `drm/amdgpu:` or `drm/amdgpu/swsmu` or `drm/amdgpu/pm`
> to
> the prefix of the patch title?
I fixed it up when I applied it.
Thanks,
Alex
>
RAS global isr will only be invoked by hardware
interrupt. Don't need to query ras capability in isr
In addition, amdgpu_ras_interrupt_fatal_error_handler
ensures the isr won't be called from guest linux
side by accident. The RAS cap check in isr that
introduced to fix sriov crash is not needed
drm/amd/pm: disallow the fan setting if there is no fan on smu 13.0.0
V2: depend on pm.no_fan to check
Signed-off-by: Kenneth Feng
---
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 4
1 file changed, 4 insertions(+)
diff --git
Fixes the following:
WARNING: Avoid multiple line dereference - prefer 'ctx->io_attr'
+ ((ctx->
+ io_attr >> CU8(base + 2)) & (0x >> (32 -
Cc: Guchun Chen
Cc: Christian König
Cc: Alex Deucher
Cc: "Pan, Xinhui"
Signed-off-by:
[AMD Official Use Only - General]
Reviewed-by: Hawking Zhang
Regards,
Hawking
-Original Message-
From: Kamal, Asad
Sent: Wednesday, August 9, 2023 17:10
To: amd-gfx@lists.freedesktop.org
Cc: Kamal, Asad ; Zhang, Hawking ;
Lazar, Lijo
Subject: [PATCH] drm/amd/pm: Add vclk and dclk
Expose sysfs vclck and dclk entries for GC version 9.4.3
Signed-off-by: Asad Kamal
Reviewed-by: Lijo Lazar
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
[Public]
> -Original Message-
> From: amd-gfx On Behalf Of Asad
> Kamal
> Sent: Wednesday, August 9, 2023 4:30 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Lazar, Lijo ; Zhang, Morris
> ; Kamal, Asad ; Zhang,
> Hawking
> Subject: [PATCH 1/2] drm/amdgpu: Add pcie usage callback to nbio
>
[AMD Official Use Only - General]
Series is
Reviewed-by: Hawking Zhang
Regards,
Hawking
-Original Message-
From: Kamal, Asad
Sent: Wednesday, August 9, 2023 16:30
To: amd-gfx@lists.freedesktop.org
Cc: Kamal, Asad ; Zhang, Hawking ;
Lazar, Lijo ; Zhang, Morris
Subject: [PATCH 2/2]
Add implementation to get pcie usage for nbio v7.9.
Signed-off-by: Asad Kamal
Reviewed-by: Lijo Lazar
Reviewed-by: Shiwu Zhang
---
drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c| 63 +++
drivers/gpu/drm/amd/amdgpu/soc15.c| 2 +-
Add a callback in nbio to get pcie usage
Signed-off-by: Asad Kamal
Reviewed-by: Lijo Lazar
Reviewed-by: Shiwu Zhang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c | 8
drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h | 3 +++
2 files changed, 11 insertions(+)
diff --git
[Public]
Reviewed-by: Guchun Chen
Regards,
Guchun
> -Original Message-
> From: SHANMUGAM, SRINIVASAN
> Sent: Wednesday, August 9, 2023 3:29 PM
> To: Koenig, Christian ; Deucher, Alexander
> ; Chen, Guchun ;
> Pan, Xinhui
> Cc: amd-gfx@lists.freedesktop.org; SHANMUGAM, SRINIVASAN
>
>
On 8/8/23 19:03, Marek Olšák wrote:
> It's the same situation as SIGSEGV. A process can catch the signal,
> but if it doesn't, it gets killed. GL and Vulkan APIs give you a way
> to catch the GPU error and prevent the process termination. If you
> don't use the API, you'll get undefined behavior,
This patch adds the missing code comment for memory barrier
WARNING: memory barrier without comment
+ mb();
WARNING: memory barrier without comment
+ mb();
Cc: Guchun Chen
Cc: Christian König
Cc: Alex Deucher
Cc: "Pan, Xinhui"
Signed-off-by:
Sorry, I had mistaken MP1 for MP0.
Also, should I add an `drm/amdgpu:` or `drm/amdgpu/swsmu` or `drm/amdgpu/pm` to
the prefix of the patch title?
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/amd/display/dc/bios/bios_parser.c | 4 ++--
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/radeon/radeon_agp.c | 2 +-
The NULL initialization of the pointers assigned by kzalloc() or
kunit_kzalloc() first is not necessary, because if the kzalloc() or
kunit_kzalloc() failed, the pointers will be assigned NULL, otherwise
it works as usual. so remove it.
Ruan Jinjie (7):
drm/amdkfd: Remove unnecessary NULL values
To prevent its redundant implementation and streamline
code, use memdup_user.
This fixes warnings reported by Coccinelle:
./drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c:2811:13-20: WARNING
opportunity for memdup_user
Signed-off-by: Atul Raut
---
v1 -> v2
caller checks for errors,
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/drm_agpsupport.c | 2 +-
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 2 +-
The NULL initialization of the pointers assigned by
kunit_kzalloc() first is not necessary, because if kunit_kzalloc()
failed, the pointers will be assigned NULL, otherwise it works
as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
.../gpu/drm/tests/drm_format_helper_test.c| 28
The NULL initialization of the pointer assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointer will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/virtio/virtgpu_submit.c | 2 +-
1 file changed, 1
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c | 4 ++--
1 file
Fixes the following:
WARNING: Possible repeated word: 'Fences'
WARNING: Missing a blank line after declarations
WARNING: braces {} are not necessary for single statement blocks
WARNING: braces {} are not necessary for any arm of this statement
WARNING: Prefer 'unsigned int' to bare use of
On 8/9/2023 11:16 AM, Srinivasan Shanmugam wrote:
This patch adds the missing code comment for memory barrier
WARNING: memory barrier without comment
+ mb();
WARNING: memory barrier without comment
+ mb();
Cc: Guchun Chen
Cc: Christian König
Am 09.08.23 um 05:44 schrieb Ruan Jinjie:
The NULL initialization of the pointers assigned by kzalloc() first is
not necessary, because if the kzalloc() failed, the pointers will be
assigned NULL, otherwise it works as usual. so remove it.
Signed-off-by: Ruan Jinjie
Reviewed-by: Christian
70 matches
Mail list logo