Flush via the ring works differently on CIK and requires a
special sequence.
Signed-off-by: Alex Deucher <alexander.deuc...@amd.com>
---
drivers/gpu/drm/radeon/cik.c | 73 +++++++++++++++++++++++++++-----------------
1 file changed, 45 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 0847367..03dd075 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3485,6 +3485,48 @@ int cik_ring_test(struct radeon_device *rdev, struct
radeon_ring *ring)
return r;
}
+static void cik_gfx_hdp_flush(struct radeon_device *rdev,
+ int ridx)
+{
+ struct radeon_ring *ring = &rdev->ring[ridx];
+ u32 ref_and_mask;
+
+ switch (ring->idx) {
+ case CAYMAN_RING_TYPE_CP1_INDEX:
+ case CAYMAN_RING_TYPE_CP2_INDEX:
+ switch (ring->me) {
+ case 0:
+ ref_and_mask = CP2 << ring->pipe;
+ break;
+ case 1:
+ ref_and_mask = CP6 << ring->pipe;
+ break;
+ default:
+ return;
+ }
+ break;
+ case RADEON_RING_TYPE_GFX_INDEX:
+ ref_and_mask = CP0;
+ break;
+ default:
+ return;
+ }
+
+ radeon_ring_write(ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
+ radeon_ring_write(ring, ((CP_WAIT_REG_MEM_TIMEOUT -
+ PACKET3_SET_UCONFIG_REG_START) >> 2));
+ radeon_ring_write(ring, 0xfff);
+
+ radeon_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+ radeon_ring_write(ring, (WAIT_REG_MEM_OPERATION(1) | /* special op */
+ WAIT_REG_MEM_FUNCTION(3))); /* == */
+ radeon_ring_write(ring, GPU_HDP_FLUSH_REQ >> 2);
+ radeon_ring_write(ring, GPU_HDP_FLUSH_DONE >> 2);
+ radeon_ring_write(ring, ref_and_mask);
+ radeon_ring_write(ring, ref_and_mask);
+ radeon_ring_write(ring, 0xa); /* poll interval */
+}
+
/**
* cik_fence_gfx_ring_emit - emit a fence on the gfx ring
*
@@ -3511,15 +3553,7 @@ void cik_fence_gfx_ring_emit(struct radeon_device *rdev,
radeon_ring_write(ring, fence->seq);
radeon_ring_write(ring, 0);
/* HDP flush */
- /* We should be using the new WAIT_REG_MEM special op packet here
- * but it causes the CP to hang
- */
- radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
- radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
- WRITE_DATA_DST_SEL(0)));
- radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
- radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 0);
+ cik_gfx_hdp_flush(rdev, fence->ring);
}
/**
@@ -3549,15 +3583,7 @@ void cik_fence_compute_ring_emit(struct radeon_device
*rdev,
radeon_ring_write(ring, fence->seq);
radeon_ring_write(ring, 0);
/* HDP flush */
- /* We should be using the new WAIT_REG_MEM special op packet here
- * but it causes the CP to hang
- */
- radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
- radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
- WRITE_DATA_DST_SEL(0)));
- radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
- radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 0);
+ cik_gfx_hdp_flush(rdev, fence->ring);
}
bool cik_semaphore_ring_emit(struct radeon_device *rdev,
@@ -5369,16 +5395,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx,
struct radeon_vm *vm)
radeon_ring_write(ring, VMID(0));
/* HDP flush */
- /* We should be using the WAIT_REG_MEM packet here like in
- * cik_fence_ring_emit(), but it causes the CP to hang in this
- * context...
- */
- radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
- radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
- WRITE_DATA_DST_SEL(0)));
- radeon_ring_write(ring, HDP_MEM_COHERENCY_FLUSH_CNTL >> 2);
- radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 0);
+ cik_gfx_hdp_flush(rdev, ridx);
/* bits 0-15 are the VM contexts0-15 */
radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
