Re: [Freedreno] [PATCH] drm/msm/a6xx: fix for kernels without CONFIG_NVMEM

2021-04-02 Thread Akhil P Oommen
On 4/2/2021 3:19 AM, Rob Clark wrote: On Thu, Apr 1, 2021 at 2:03 PM Dmitry Baryshkov wrote: On Thu, 1 Apr 2021 at 23:09, Rob Clark wrote: On Mon, Feb 22, 2021 at 8:06 AM Rob Clark wrote: On Mon, Feb 22, 2021 at 7:45 AM Akhil P Oommen wrote: On 2/19/2021 9:30 PM, Rob Clark wrote: On

Re: [Freedreno] [PATCH v2] drm/msm: Drop mm_lock in scan loop

2021-04-02 Thread Doug Anderson
Hi, On Fri, Apr 2, 2021 at 2:08 PM Rob Clark wrote: > > From: Rob Clark > > lock_stat + mmm_donut[1] say that this reduces contention on mm_lock > significantly (~350x lower waittime-max, and ~100x lower waittime-avg) > > [1] >

[Freedreno] [PATCH v2] drm/msm: Drop mm_lock in scan loop

2021-04-02 Thread Rob Clark
From: Rob Clark lock_stat + mmm_donut[1] say that this reduces contention on mm_lock significantly (~350x lower waittime-max, and ~100x lower waittime-avg) [1] https://chromium.googlesource.com/chromiumos/platform/microbenchmarks/+/refs/heads/main/mmm_donut.py Signed-off-by: Rob Clark ---

[Freedreno] [pull] drm/msm: drm-msm-fixes-2021-04-02 for v5.12-rc6

2021-04-02 Thread Rob Clark
Hi Dave & Daniel, A couple more small fixes for v5.12 The following changes since commit 627dc55c273dab308303a5217bd3e767d7083ddb: drm/msm/disp/dpu1: icc path needs to be set before dpu runtime resume (2021-03-22 18:52:34 -0700) are available in the Git repository at:

Re: [Freedreno] [v1] drm/msm/disp/dpu1: program 3d_merge only if block is attached

2021-04-02 Thread Rob Clark
On Fri, Apr 2, 2021 at 4:55 AM Kalyan Thota wrote: > > Update the 3d merge as active in the data path only if > the hw block is selected in the configuration. > > Reported-by: Stephen Boyd Thanks, I've added: Fixes: 73bfb790ac78 ("msm:disp:dpu1: setup display datapath for SC7180 target") >

Re: [Freedreno] [PATCH 2/2] drm/msm: Add param for userspace to query suspend count

2021-04-02 Thread Jordan Crouse
On Wed, Mar 24, 2021 at 06:23:53PM -0700, Rob Clark wrote: > From: Rob Clark > > Performance counts, and ALWAYS_ON counters used for capturing GPU > timestamps, lose their state across suspend/resume cycles. Userspace > tooling for performance monitoring needs to be aware of this. For >

Re: [Freedreno] [PATCH 1/2] drm/msm: Fix a5xx/a6xx timestamps

2021-04-02 Thread Jordan Crouse
On Wed, Mar 24, 2021 at 06:23:52PM -0700, Rob Clark wrote: > From: Rob Clark > > They were reading a counter that was configured to ALWAYS_COUNT (ie. > cycles that the GPU is doing something) rather than ALWAYS_ON. This > isn't the thing that userspace is looking for. Acked-by: Jordan Crouse

[Freedreno] [v1] drm/msm/disp/dpu1: program 3d_merge only if block is attached

2021-04-02 Thread Kalyan Thota
Update the 3d merge as active in the data path only if the hw block is selected in the configuration. Reported-by: Stephen Boyd Signed-off-by: Kalyan Thota --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git

Re: [Freedreno] [v1] drm/msm/disp/dpu1: fix warn stack reported during dpu resume

2021-04-02 Thread kalyan_t
On 2021-04-01 19:01, Dmitry Baryshkov wrote: On Thu, 1 Apr 2021 at 16:19, wrote: On 2021-04-01 07:37, Dmitry Baryshkov wrote: > On 01/04/2021 01:47, Rob Clark wrote: >> On Wed, Mar 31, 2021 at 9:03 AM Dmitry Baryshkov >> wrote: >>> >>> On 31/03/2021 14:27, Kalyan Thota wrote: WARN_ON