drm/amdgpu: Handle fault with same timestamp

Remove not unique timestamp WARNING as same timestamp interrupt happens
on some chips,

Drain fault need to wait for the processed_timestamp to be truly greater
than the checkpoint or the ring to be empty to be sure no stale faults
are handled.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1818
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 8050f7b..3df1465 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -188,8 +188,8 @@ int amdgpu_ih_wait_on_checkpoint_process_ts(struct amdgpu_device *adev,
        checkpoint_ts = amdgpu_ih_decode_iv_ts(adev, ih, checkpoint_wptr, -1);
 
        return wait_event_interruptible_timeout(ih->wait_process,
-                   !amdgpu_ih_ts_after(ih->processed_timestamp, checkpoint_ts),
-                   timeout);
+                   amdgpu_ih_ts_after(checkpoint_ts, ih->processed_timestamp) ||
+                   ih->rptr == amdgpu_ih_get_wptr(adev, ih), timeout);
 }
 
 /**

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index e4618c7..f5cbc27 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -529,9 +529,6 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev,
        if (!handled)
                amdgpu_amdkfd_interrupt(adev, entry.iv_entry);
 
-       dev_WARN_ONCE(adev->dev, ih->processed_timestamp == entry.timestamp,
-                     "IH timestamps are not unique");
-
        if (amdgpu_ih_ts_after(ih->processed_timestamp, entry.timestamp))
                ih->processed_timestamp = entry.timestamp;
 }