drm/amdgpu: handle IH ring1 overflow

IH ring1 is used to process GPU retry fault, overflow is enabled to
drain retry fault because we want receive other interrupts while
handling retry fault to recover range. There is no overflow flag set
when wptr pass rptr. Use timestamp of rptr and wptr to handle overflow
and drain retry fault.

If fault timestamp goes backward, the fault is filtered and should not
be processed. Drain fault is finished if processed_timestamp is equal to
or larger than checkpoint timestamp.

Add amdgpu_ih_functions interface decode_iv_ts for different chips to
get timestamp from IV entry with different iv size and timestamp offset.
amdgpu_ih_decode_iv_ts_helper is used for vega10, vega20, navi10.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 25 insertions, 30 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 0c7963dfacad..8050f7ba93ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -164,52 +164,32 @@ void amdgpu_ih_ring_write(struct amdgpu_ih_ring *ih, const uint32_t *iv,
 	}
 }
 
-/* Waiter helper that checks current rptr matches or passes checkpoint wptr */
-static bool amdgpu_ih_has_checkpoint_processed(struct amdgpu_device *adev,
-					struct amdgpu_ih_ring *ih,
-					uint32_t checkpoint_wptr,
-					uint32_t *prev_rptr)
-{
-	uint32_t cur_rptr = ih->rptr | (*prev_rptr & ~ih->ptr_mask);
-
-	/* rptr has wrapped. */
-	if (cur_rptr < *prev_rptr)
-		cur_rptr += ih->ptr_mask + 1;
-	*prev_rptr = cur_rptr;
-
-	/* check ring is empty to workaround missing wptr overflow flag */
-	return cur_rptr >= checkpoint_wptr ||
-	       (cur_rptr & ih->ptr_mask) == amdgpu_ih_get_wptr(adev, ih);
-}
-
 /**
- * amdgpu_ih_wait_on_checkpoint_process - wait to process IVs up to checkpoint
+ * amdgpu_ih_wait_on_checkpoint_process_ts - wait to process IVs up to checkpoint
  *
  * @adev: amdgpu_device pointer
  * @ih: ih ring to process
  *
  * Used to ensure ring has processed IVs up to the checkpoint write pointer.
  */
-int amdgpu_ih_wait_on_checkpoint_process(struct amdgpu_device *adev,
+int amdgpu_ih_wait_on_checkpoint_process_ts(struct amdgpu_device *adev,
 					struct amdgpu_ih_ring *ih)
 {
-	uint32_t checkpoint_wptr, rptr;
+	uint32_t checkpoint_wptr;
+	uint64_t checkpoint_ts;
+	long timeout = HZ;
 
 	if (!ih->enabled || adev->shutdown)
 		return -ENODEV;
 
 	checkpoint_wptr = amdgpu_ih_get_wptr(adev, ih);
-	/* Order wptr with rptr. */
+	/* Order wptr with ring data. */
 	rmb();
-	rptr = READ_ONCE(ih->rptr);
-
-	/* wptr has wrapped. */
-	if (rptr > checkpoint_wptr)
-		checkpoint_wptr += ih->ptr_mask + 1;
+	checkpoint_ts = amdgpu_ih_decode_iv_ts(adev, ih, checkpoint_wptr, -1);
 
-	return wait_event_interruptible(ih->wait_process,
-				amdgpu_ih_has_checkpoint_processed(adev, ih,
-						checkpoint_wptr, &rptr));
+	return wait_event_interruptible_timeout(ih->wait_process,
+		    !amdgpu_ih_ts_after(ih->processed_timestamp, checkpoint_ts),
+		    timeout);
 }
 
 /**
@@ -299,3 +279,18 @@ void amdgpu_ih_decode_iv_helper(struct amdgpu_device *adev,
 	/* wptr/rptr are in bytes! */
 	ih->rptr += 32;
 }
+
+uint64_t amdgpu_ih_decode_iv_ts_helper(struct amdgpu_ih_ring *ih, u32 rptr,
+				       signed int offset)
+{
+	uint32_t iv_size = 32;
+	uint32_t ring_index;
+	uint32_t dw1, dw2;
+
+	rptr += iv_size * offset;
+	ring_index = (rptr & ih->ptr_mask) >> 2;
+
+	dw1 = le32_to_cpu(ih->ring[ring_index + 1]);
+	dw2 = le32_to_cpu(ih->ring[ring_index + 2]);
+	return dw1 | ((u64)(dw2 & 0xffff) << 32);
+}