[Public]
Feel free to add:
Acked-by: Wayne Lin
> -Original Message-
> From: Tom Chung
> Sent: Tuesday, February 4, 2025 3:13 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Lin, Wayne ; Li, Sun peng (Leo)
> ; Chung, ChiaHsuan (Tom)
>
> Subject: [PATCH] Revert "drm/amd/display: Use HW lock
On 2/4/2025 3:13 AM, Alex Deucher wrote:
> Manually disallow and then allow gfxoff in begin_use
> and end_use to avoid any potential FW races when
> ringing the doorbell. There are no known issues
> with gfxoff that this solves, but it shouldn't hurt anything
> and shouldn't affect power usage
This reverts commit
2a69ae1e1354 ("drm/amd/display: Use HW lock mgr for PSR1")
Because it may cause system hang while connect with two edp panel.
Signed-off-by: Tom Chung
---
drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --gi
For amdgpu_get_pp_force_state, amdgpu_get_pp_cur_state already takes
care of device state check. In other cases, values are returned from
driver cached variables and are not dependent on device state.
Signed-off-by: Lijo Lazar
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 14 --
1 file ch
If a device supports runtime pm, then pm_runtime_get_if_active returns 0
if a device is not active and 1 if already active. However, if a device
doesn't support runtime pm, the API returns -EINVAL. A device not
supporting runtime pm implies it's not affected by runtime pm and it's
active. Hence no
Wrap the checks before device access in helper functions and use them
for device access. The generic order of APIs now is to do input argument
validation first and check if device access is allowed.
Signed-off-by: Lijo Lazar
---
drivers/gpu/drm/amd/pm/amdgpu_pm.c | 616 +++---
On 1/31/2025 11:21, Alex Deucher wrote:
If the user has configured a large carveout on a small APU,
only use GTT for VRAM allocations if GTT is larger than
VRAM.
v2: fix reversed check (Philip)
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 --
1 file change
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
Use amdgpu_gfx_off_ctrl_immediate() when powergating.
There's no need for the delay in gfx off allow. The
powergating is dynamically disabled/enabled as for
RV/PCO on compute queues and allowing gfx off again as
soon the job is submitted improves power savings.
Suggested-by: Błażej Szczygieł
Lin
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
In begin_use/end_use use amdgpu_gfx_off_ctrl_immediate()
rather than amdgpu_gfx_off_ctrl() as we don't need the
extra delay before we allow gfxoff again.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a
Bump the driver version for RV/PCO compute stability fix
so mesa can use this check to enable compute queues on
RV/PCO.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_
Manually disallow and then allow gfxoff in begin_use
and end_use to avoid any potential FW races when
ringing the doorbell. There are no known issues
with gfxoff that this solves, but it shouldn't hurt anything
and shouldn't affect power usage since we are only
toggling it around the doorbell upda
When mesa started using compute queues more often
we started seeing additional hangs with compute queues.
Disabling gfxoff seems to mitigate that. Manually
control gfxoff and gfx pg with command submissions to avoid
any issues related to gfxoff. KFD already does the same
thing for these chips.
v
Same as amdgpu_gfx_off_ctrl(), but without the delay
for gfxoff disallow.
Suggested-by: Błażej Szczygieł
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 53 +++--
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h | 1 +
2 files changed, 41 insertions(+), 13
On 2025-01-09 11:57, Felix Kuehling wrote:
From: Christian König
Try pinning into VRAM to allow P2P with RDMA NICs without ODP
support if all attachments can do P2P. If any attachment can't do
P2P just pin into GTT instead.
Signed-off-by: Christian König
Signed-off-by: Felix Kuehling
Revie
Applied. Thanks!
Alex
On Sun, Feb 2, 2025 at 5:08 PM wrote:
>
> From: "Dr. David Alan Gilbert"
>
> Another small pile of deadcode patches.
>
> Signed-off-by: Dr. David Alan Gilbert
>
>
> Dr. David Alan Gilbert (7):
> drm/amd/display: Remove unused mpc1_is_mpcc_idle
> drm/amd/display: Remo
Applied. Thanks!
Alex
On Fri, Jan 31, 2025 at 5:38 PM Nathan Chancellor wrote:
>
> Currently, there are several files in drm/amd/display that aim to have a
> higher -Wframe-larger-than value to avoid instances of that warning with
> a lower value from the user's configuration. However, with the
Use DC_LOG_DEBUG instead of pr_info to match other uses in dc.c.
Fixes: eb8eec752038 ("drm/amd/display: Add debug messages for
dc_validate_boot_timing()")
Reviewed-by: Mario Limonciello
Signed-off-by: Alex Hung
---
drivers/gpu/drm/amd/display/dc/core/dc.c | 2 +-
1 file changed, 1 insertion(+
On 2/3/2025 9:36 PM, Alex Deucher wrote:
> On Fri, Jan 31, 2025 at 11:53 PM Lijo Lazar wrote:
>>
>> If a device supports runtime pm, then pm_runtime_get_if_active returns 0
>> if a device is not active and 1 if already active. However, if a device
>> doesn't support runtime pm, the API returns
On Fri, Jan 31, 2025 at 11:53 PM Lijo Lazar wrote:
>
> If a device supports runtime pm, then pm_runtime_get_if_active returns 0
> if a device is not active and 1 if already active. However, if a device
> doesn't support runtime pm, the API returns -EINVAL. A device not
> supporting runtime pm impl
SDMA 4.x is not part of the GFX power domain so this is
not necessary.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index b48d9c0b2e1c3.
[Public]
Hi all,
This week this patchset was tested on 4 systems, two dGPU and two APU based,
and tested across multiple display and connection types.
APU
* Single Display eDP -> 1080p 60hz, 2560x1600 120hz, 1920x1200 165hz
* Single Display DP (SST DSC) -> 4k144hz, 4k240hz
From: Tim Huang
[ Upstream commit 20b5a8f9f4670a8503aa9fa95ca632e77c6bf55d ]
Flexible endpoints use DIGs from available inflexible endpoints,
so only the encoders of inflexible links need to be freed.
Otherwise, a double free issue may occur when unloading the
amdgpu module.
[ 279.190523] RIP:
Limiting the number of available VMIDs to enforce isolation causes some
issues with gang submit and applying certain HW workarounds which
require multiple VMIDs to work correctly.
So instead start to track all submissions to the relevant engines in a
per partition data structure and use the dma_fe
That was quite troublesome for gang submit. Completely drop this
approach and enforce the isolation separately.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 9 ++---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 11
Instead of emitting the cleaner shader for every job which has the
enforce_isolation flag set only emit it for the first submission from
every client.
v2: add missing NULL check
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 25 -
1 file chan
This allows using amdgpu_sync even without peeking into the fences for a
long time.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 13 +
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
b/drivers/gp
In the critical submission path memory allocations can't wait for
reclaim since that can potentially wait for submissions to finish.
Finally clean that up and mark most memory allocations in the critical
path with GFP_NOWAIT. The only exception left is the dma_fence_array()
used when no VMID is av
We keep the gang submission fence around in adev, make sure that it
stays alive.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev
From: "Dr. David Alan Gilbert"
mod_freesync_get_vmin_vmax() and mod_freesync_get_v_position() were
added in 2017 by
commit 72ada5f76939 ("drm/amd/display: FreeSync Auto Sweep Support")
mod_freesync_is_valid_range() was added in 2018 by
commit e80e94460841 ("drm/amd/display: add method to check f
From: "Dr. David Alan Gilbert"
link_enc_cfg_get_link_enc_used_by_stream() is no longer used after
2021's:
commit 6366b00346c0 ("drm/amd/display: Maintain consistent mode of
operation during encoder assignment")
which introduces and uses the _current version instead.
Remove it.
Signed-off-by: Dr
From: "Dr. David Alan Gilbert"
get_clock_requirements_for_state() was added in 2018 by
commit 8ab2180f96f5 ("drm/amd/display: Add function to fetch clock
requirements")
but never used.
Remove it.
Signed-off-by: Dr. David Alan Gilbert
---
drivers/gpu/drm/amd/display/dc/core/dc.c | 12 -
Hello,
I was exploring the Linux kernel code and came across the following
functions marked with //TODO in mmhub_v3_0_2.c:
static void mmhub_v3_0_2_update_medium_grain_clock_gating(struct
amdgpu_device *adev, bool enable) { //TODO }
static void mmhub_v3_0_2_update_medium_grain_light_sleep(struct
Hi Charlene, Alex,
My scripts spotted that all 3 functions added by the commit
dbc2309cac2a ("drm/amd/display: add hubbub_init related")
are uncalled, and instead of deadcoding them, I wondered if it's
actually a simple bug and they should be assigned somewhere.
That patch also added a member
This is a workaround to this issue:
https://gitlab.freedesktop.org/drm/amd/-/issues/3701
Signed-off-by: poscat
---
drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
From: "Dr. David Alan Gilbert"
get_max_support_fbc_buffersize() is unused since 2021's
commit 94f0d0c80cf3 ("drm/amd/display/dc/dce110/dce110_compressor: Remove
unused function 'dce110_get_required_compressed_surfacesize")
removed it's only caller.
Remove it.
Signed-off-by: Dr. David Alan Gilbe
From: "Dr. David Alan Gilbert"
mpc1_is_mpcc_idle() was added in 2017 by
commit feb4a3cd8eb0 ("drm/amd/display: Integrating MPC pseudocode")
but never used.
Remove it.
Signed-off-by: Dr. David Alan Gilbert
---
.../gpu/drm/amd/display/dc/mpc/dcn10/dcn10_mpc.c | 16
.../gpu/drm/
From: "Dr. David Alan Gilbert"
Another small pile of deadcode patches.
Signed-off-by: Dr. David Alan Gilbert
Dr. David Alan Gilbert (7):
drm/amd/display: Remove unused mpc1_is_mpcc_idle
drm/amd/display: Remove unused freesync functions
drm/amd/display: Remove unused dc_stream_get_crtc_p
From: "Dr. David Alan Gilbert"
hubbub1_toggle_watermark_change_req() last use was removed in 2017 by
commit b8fce2c9d773 ("drm/amd/display: Optimize programming front end")
Remove it.
Signed-off-by: Dr. David Alan Gilbert
---
.../amd/display/dc/hubbub/dcn10/dcn10_hubbub.c | 18 ---
From: "Dr. David Alan Gilbert"
The last user of dc_stream_get_crtc_position() was
mod_freesync_get_v_position() which is removed in a previous
patch in this series.
Remove it.
Signed-off-by: Dr. David Alan Gilbert
---
drivers/gpu/drm/amd/display/dc/core/dc.c | 27 --
dri
44 matches
Mail list logo
