diff options
author | Rob Clark <robdclark@chromium.org> | 2022-11-14 22:30:41 +0300 |
---|---|---|
committer | Rob Clark <robdclark@chromium.org> | 2022-11-17 21:39:12 +0300 |
commit | d73b1d02de0858b96f743e1e8b767fb092ae4c1b (patch) | |
tree | a5fedb0e54c0f5e721fa11619796c818a9963e01 /drivers/gpu/drm/msm/msm_gpu.h | |
parent | cade05b2a88558847984287dd389fae0c7de31d6 (diff) | |
download | linux-d73b1d02de0858b96f743e1e8b767fb092ae4c1b.tar.xz |
drm/msm: Hangcheck progress detection
If the hangcheck timer expires, check if the fw's position in the
cmdstream has advanced (changed) since last timer expiration, and
allow it up to three additional "extensions" to it's alotted time.
The intention is to continue to catch "shader stuck in a loop" type
hangs quickly, but allow more time for things that are actually
making forward progress.
Because we need to sample the CP state twice to detect if there has
not been progress, this also cuts the the timer's duration in half.
v2: Fix typo (REG_A6XX_CP_CSQ_IB2_STAT), add comment
v3: Only halve hangcheck timer duration for generations which
support progress detection (hdanton); removed unused a5xx
progress (without knowing how to adjust for data buffered
in ROQ it is too likely to report a false negative)
v4: Comment updates to better describe the total hangcheck
duration when progress detection is applied
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Tested-by: Chia-I Wu <olvaffe@gmail.com> # dEQP-GLES2.functional.flush_finish.wait
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/511584/
Link: https://lore.kernel.org/r/20221114193049.1533391-3-robdclark@gmail.com
Diffstat (limited to 'drivers/gpu/drm/msm/msm_gpu.h')
-rw-r--r-- | drivers/gpu/drm/msm/msm_gpu.h | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 06a651ee50f6..629712f90dc1 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -78,6 +78,15 @@ struct msm_gpu_funcs { struct msm_gem_address_space *(*create_private_address_space) (struct msm_gpu *gpu); uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + + /** + * progress: Has the GPU made progress? + * + * Return true if GPU position in cmdstream has advanced (or changed) + * since the last call. To avoid false negatives, this should account + * for cmdstream that is buffered in this FIFO upstream of the CP fw. + */ + bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); }; /* Additional state for iommu faults: */ @@ -237,6 +246,7 @@ struct msm_gpu { #define DRM_MSM_INACTIVE_PERIOD 66 /* in ms (roughly four frames) */ #define DRM_MSM_HANGCHECK_DEFAULT_PERIOD 500 /* in ms */ +#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; /* Fault info for most recent iova fault: */ |