drm/amdgpu:unmap KCQ in gfx hw_fini(v2)

v2:
move kcq_disable out of SRIOV, make it genearal

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

2 files changed, 115 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 0c4a3b8e8596..dfc10b1baea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5034,12 +5034,69 @@ static int gfx_v8_0_hw_init(void *handle)
 	return r;
 }
 
+static int gfx_v8_0_kcq_disable(struct amdgpu_ring *kiq_ring,struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = kiq_ring->adev;
+	uint32_t scratch, tmp = 0;
+	int r, i;
+
+	r = amdgpu_gfx_scratch_get(adev, &scratch);
+	if (r) {
+		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
+		return r;
+	}
+	WREG32(scratch, 0xCAFEDEAD);
+
+	r = amdgpu_ring_alloc(kiq_ring, 10);
+	if (r) {
+		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
+		amdgpu_gfx_scratch_free(adev, scratch);
+		return r;
+	}
+
+	/* unmap queues */
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+						PACKET3_UNMAP_QUEUES_ACTION(1) | /* RESET_QUEUES */
+						PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
+						PACKET3_UNMAP_QUEUES_ENGINE_SEL(0) |
+						PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring, PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
+	amdgpu_ring_write(kiq_ring, 0);
+	amdgpu_ring_write(kiq_ring, 0);
+	amdgpu_ring_write(kiq_ring, 0);
+	/* write to scratch for completion */
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
+	amdgpu_ring_write(kiq_ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
+	amdgpu_ring_write(kiq_ring, 0xDEADBEEF);
+	amdgpu_ring_commit(kiq_ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(scratch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+	if (i >= adev->usec_timeout) {
+		DRM_ERROR("KCQ disabled failed (scratch(0x%04X)=0x%08X)\n", scratch, tmp);
+		r = -EINVAL;
+	}
+	amdgpu_gfx_scratch_free(adev, scratch);
+	return r;
+}
+
 static int gfx_v8_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i;
 
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
+
+	/* disable KCQ to avoid CPC touch memory not valid anymore */
+	for (i = 0; i < adev->gfx.num_compute_rings; i++)
+		gfx_v8_0_kcq_disable(&adev->gfx.kiq.ring, &adev->gfx.compute_ring[i]);
+
 	if (amdgpu_sriov_vf(adev)) {
 		pr_debug("For SRIOV client, shouldn't do anything.\n");
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e2ae00df1d52..9945218a5489 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2895,12 +2895,70 @@ static int gfx_v9_0_hw_init(void *handle)
 	return r;
 }
 
+static int gfx_v9_0_kcq_disable(struct amdgpu_ring *kiq_ring,struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = kiq_ring->adev;
+	uint32_t scratch, tmp = 0;
+	int r, i;
+
+	r = amdgpu_gfx_scratch_get(adev, &scratch);
+	if (r) {
+		DRM_ERROR("Failed to get scratch reg (%d).\n", r);
+		return r;
+	}
+	WREG32(scratch, 0xCAFEDEAD);
+
+	r = amdgpu_ring_alloc(kiq_ring, 10);
+	if (r) {
+		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
+		amdgpu_gfx_scratch_free(adev, scratch);
+		return r;
+	}
+
+	/* unmap queues */
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+						PACKET3_UNMAP_QUEUES_ACTION(1) | /* RESET_QUEUES */
+						PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
+						PACKET3_UNMAP_QUEUES_ENGINE_SEL(0) |
+						PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring, PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
+	amdgpu_ring_write(kiq_ring, 0);
+	amdgpu_ring_write(kiq_ring, 0);
+	amdgpu_ring_write(kiq_ring, 0);
+	/* write to scratch for completion */
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
+	amdgpu_ring_write(kiq_ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
+	amdgpu_ring_write(kiq_ring, 0xDEADBEEF);
+	amdgpu_ring_commit(kiq_ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(scratch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+	if (i >= adev->usec_timeout) {
+		DRM_ERROR("KCQ disabled failed (scratch(0x%04X)=0x%08X)\n", scratch, tmp);
+		r = -EINVAL;
+	}
+	amdgpu_gfx_scratch_free(adev, scratch);
+	return r;
+}
+
+
 static int gfx_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i;
 
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
+
+	/* disable KCQ to avoid CPC touch memory not valid anymore */
+	for (i = 0; i < adev->gfx.num_compute_rings; i++)
+		gfx_v9_0_kcq_disable(&adev->gfx.kiq.ring, &adev->gfx.compute_ring[i]);
+
 	if (amdgpu_sriov_vf(adev)) {
 		pr_debug("For SRIOV client, shouldn't do anything.\n");
 		return 0;