There is no recovery mechanism in place yet to recover from mmu
faults for DPU. We can only prevent the faults by making sure there
is no misconfiguration.

Rate-limit the snapshot capture for mmu faults to once per
msm_kms_init_aspace() as that should be sufficient to capture
the snapshot for debugging otherwise there will be a lot of
dpu snapshots getting captured for the same fault which is
redundant and also might affect capturing even one snapshot
accurately.

Signed-off-by: Abhinav Kumar <quic_abhin...@quicinc.com>
---
 drivers/gpu/drm/msm/msm_kms.c | 6 +++++-
 drivers/gpu/drm/msm/msm_kms.h | 3 +++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index d5d3117259cf..90a333920c01 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -168,7 +168,10 @@ static int msm_kms_fault_handler(void *arg, unsigned long 
iova, int flags, void
 {
        struct msm_kms *kms = arg;
 
-       msm_disp_snapshot_state(kms->dev);
+       if (!kms->fault_snapshot_capture) {
+               msm_disp_snapshot_state(kms->dev);
+               kms->fault_snapshot_capture++;
+       }
 
        return -ENOSYS;
 }
@@ -208,6 +211,7 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct 
drm_device *dev)
                mmu->funcs->destroy(mmu);
        }
 
+       kms->fault_snapshot_capture = 0;
        msm_mmu_set_fault_handler(aspace->mmu, kms, msm_kms_fault_handler);
 
        return aspace;
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 1e0c54de3716..240b39e60828 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -134,6 +134,9 @@ struct msm_kms {
        int irq;
        bool irq_requested;
 
+       /* rate limit the snapshot capture to once per attach */
+       int fault_snapshot_capture;
+
        /* mapper-id used to request GEM buffer mapped for scanout: */
        struct msm_gem_address_space *aspace;
 
-- 
2.44.0

Reply via email to