[PATCH] drm/amdgpu: Program ring for vce instance 1 at its own register space

[Leo Liu]

when harvest part has only instance 1 available

Signed-off-by: Leo Liu <leo.liu at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 61 +++++++++++++++++++++++++++++++----
 1 file changed, 55 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index fb08193..77af395 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -77,13 +77,26 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
+	u32 v;
+
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		mutex_lock(&adev->grbm_idx_mutex);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+	}
 
 	if (ring == &adev->vce.ring[0])
-		return RREG32(mmVCE_RB_RPTR);
+		v = RREG32(mmVCE_RB_RPTR);
 	else if (ring == &adev->vce.ring[1])
-		return RREG32(mmVCE_RB_RPTR2);
+		v = RREG32(mmVCE_RB_RPTR2);
 	else
-		return RREG32(mmVCE_RB_RPTR3);
+		v = RREG32(mmVCE_RB_RPTR3);
+
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	return v;
 }
 
 /**
@@ -96,13 +109,26 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
+	u32 v;
+
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		mutex_lock(&adev->grbm_idx_mutex);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+	}
 
 	if (ring == &adev->vce.ring[0])
-		return RREG32(mmVCE_RB_WPTR);
+		v = RREG32(mmVCE_RB_WPTR);
 	else if (ring == &adev->vce.ring[1])
-		return RREG32(mmVCE_RB_WPTR2);
+		v = RREG32(mmVCE_RB_WPTR2);
 	else
-		return RREG32(mmVCE_RB_WPTR3);
+		v = RREG32(mmVCE_RB_WPTR3);
+
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	return v;
 }
 
 /**
@@ -116,12 +142,22 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		mutex_lock(&adev->grbm_idx_mutex);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+	}
+
 	if (ring == &adev->vce.ring[0])
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	else if (ring == &adev->vce.ring[1])
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
+
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
 }
 
 static void vce_v3_0_override_vce_clock_gating(struct amdgpu_device *adev, bool override)
@@ -231,6 +267,14 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring;
 	int idx, r;
 
+	/* we need program ring buffer on instance 1 register space domain
+	when only if instance 1 available, with two instances or instance 0
+	we need only program instance 0 regsiter space domain for ring */
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		mutex_lock(&adev->grbm_idx_mutex);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+	}
+
 	ring = &adev->vce.ring[0];
 	WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
 	WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
@@ -252,6 +296,11 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 	WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
 	WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
 
+	if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+		WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (idx = 0; idx < 2; ++idx) {
 		if (adev->vce.harvest_config & (1 << idx))
-- 
2.9.3