drm/radeon: remove generic rptr/wptr functions (v2)

Fill in asic family specific versions rather than
using the generic version.  This lets us handle asic
specific differences more easily.  In this case, we
disable sw swapping of the rtpr writeback value on
r6xx+ since the hw does it for us.  Fixes bogus
rptr readback on BE systems.

v2: remove missed cpu_to_le32(), add comments

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 39 insertions, 17 deletions

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 25a6ef6c7e4c..e66eb4745347 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4015,15 +4015,43 @@ static int cik_cp_gfx_resume(struct radeon_device *rdev)
 	return 0;
 }
 
-u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
-			      struct radeon_ring *ring)
+u32 cik_gfx_get_rptr(struct radeon_device *rdev,
+		     struct radeon_ring *ring)
 {
 	u32 rptr;
 
+	if (rdev->wb.enabled)
+		rptr = rdev->wb.wb[ring->rptr_offs/4];
+	else
+		rptr = RREG32(CP_RB0_RPTR);
+
+	return rptr;
+}
+
+u32 cik_gfx_get_wptr(struct radeon_device *rdev,
+		     struct radeon_ring *ring)
+{
+	u32 wptr;
+
+	wptr = RREG32(CP_RB0_WPTR);
 
+	return wptr;
+}
+
+void cik_gfx_set_wptr(struct radeon_device *rdev,
+		      struct radeon_ring *ring)
+{
+	WREG32(CP_RB0_WPTR, ring->wptr);
+	(void)RREG32(CP_RB0_WPTR);
+}
+
+u32 cik_compute_get_rptr(struct radeon_device *rdev,
+			 struct radeon_ring *ring)
+{
+	u32 rptr;
 
 	if (rdev->wb.enabled) {
-		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
+		rptr = rdev->wb.wb[ring->rptr_offs/4];
 	} else {
 		mutex_lock(&rdev->srbm_mutex);
 		cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
@@ -4035,13 +4063,14 @@ u32 cik_compute_ring_get_rptr(struct radeon_device *rdev,
 	return rptr;
 }
 
-u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
-			      struct radeon_ring *ring)
+u32 cik_compute_get_wptr(struct radeon_device *rdev,
+			 struct radeon_ring *ring)
 {
 	u32 wptr;
 
 	if (rdev->wb.enabled) {
-		wptr = le32_to_cpu(rdev->wb.wb[ring->wptr_offs/4]);
+		/* XXX check if swapping is necessary on BE */
+		wptr = rdev->wb.wb[ring->wptr_offs/4];
 	} else {
 		mutex_lock(&rdev->srbm_mutex);
 		cik_srbm_select(rdev, ring->me, ring->pipe, ring->queue, 0);
@@ -4053,10 +4082,11 @@ u32 cik_compute_ring_get_wptr(struct radeon_device *rdev,
 	return wptr;
 }
 
-void cik_compute_ring_set_wptr(struct radeon_device *rdev,
-			       struct radeon_ring *ring)
+void cik_compute_set_wptr(struct radeon_device *rdev,
+			  struct radeon_ring *ring)
 {
-	rdev->wb.wb[ring->wptr_offs/4] = cpu_to_le32(ring->wptr);
+	/* XXX check if swapping is necessary on BE */
+	rdev->wb.wb[ring->wptr_offs/4] = ring->wptr;
 	WDOORBELL32(ring->doorbell_index, ring->wptr);
 }
 
@@ -7606,7 +7636,6 @@ static int cik_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
-			     CP_RB0_RPTR, CP_RB0_WPTR,
 			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
@@ -7615,7 +7644,6 @@ static int cik_startup(struct radeon_device *rdev)
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET,
-			     CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
 			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
@@ -7627,7 +7655,6 @@ static int cik_startup(struct radeon_device *rdev)
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET,
-			     CP_HQD_PQ_RPTR, CP_HQD_PQ_WPTR,
 			     PACKET3(PACKET3_NOP, 0x3FFF));
 	if (r)
 		return r;
@@ -7639,16 +7666,12 @@ static int cik_startup(struct radeon_device *rdev)
 
 	ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, R600_WB_DMA_RPTR_OFFSET,
-			     SDMA0_GFX_RB_RPTR + SDMA0_REGISTER_OFFSET,
-			     SDMA0_GFX_RB_WPTR + SDMA0_REGISTER_OFFSET,
 			     SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
 	if (r)
 		return r;
 
 	ring = &rdev->ring[CAYMAN_RING_TYPE_DMA1_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, CAYMAN_WB_DMA1_RPTR_OFFSET,
-			     SDMA0_GFX_RB_RPTR + SDMA1_REGISTER_OFFSET,
-			     SDMA0_GFX_RB_WPTR + SDMA1_REGISTER_OFFSET,
 			     SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
 	if (r)
 		return r;
@@ -7664,7 +7687,6 @@ static int cik_startup(struct radeon_device *rdev)
 	ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
 	if (ring->ring_size) {
 		r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
-				     UVD_RBC_RB_RPTR, UVD_RBC_RB_WPTR,
 				     RADEON_CP_PACKET2);
 		if (!r)
 			r = uvd_v1_0_init(rdev);