From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 29 Mar 2017 15:31:22 -0400
Subject: drm/amdgpu/gfx8: move SET_RESOURCES into the same command stream
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 346586d5672d9d63057d4fa03dc0816a59439001
Patch-mainline: v4.13-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

As the KCQ setup.  This way we only have to wait once for the
entire MEC.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c |   87 ++++++++--------------------------
 1 file changed, 23 insertions(+), 64 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4572,57 +4572,7 @@ static void gfx_v8_0_kiq_setting(struct
 	WREG32(mmRLC_CP_SCHEDULERS, tmp);
 }
 
-static int gfx_v8_0_kiq_enable(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = 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(ring, 11);
-	if (r) {
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-		amdgpu_gfx_scratch_free(adev, scratch);
-		return r;
-	}
-	/* set resources */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_RESOURCES, 6));
-	amdgpu_ring_write(ring, 0);	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(ring, 0x000000FF);	/* queue mask lo */
-	amdgpu_ring_write(ring, 0);	/* queue mask hi */
-	amdgpu_ring_write(ring, 0);	/* gws mask lo */
-	amdgpu_ring_write(ring, 0);	/* gws mask hi */
-	amdgpu_ring_write(ring, 0);	/* oac mask */
-	amdgpu_ring_write(ring, 0);	/* gds heap base:0, gds heap size:0 */
-	/* write to scratch for completion */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
-	amdgpu_ring_write(ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
-	amdgpu_ring_write(ring, 0xDEADBEEF);
-	amdgpu_ring_commit(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("KIQ enable failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
-		r = -EINVAL;
-	}
-	amdgpu_gfx_scratch_free(adev, scratch);
-
-	return r;
-}
-
-static int gfx_v8_0_map_queues_enable(struct amdgpu_device *adev)
+static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
 	uint32_t scratch, tmp = 0;
@@ -4635,12 +4585,21 @@ static int gfx_v8_0_map_queues_enable(st
 	}
 	WREG32(scratch, 0xCAFEDEAD);
 
-	r = amdgpu_ring_alloc(kiq_ring, (8 * adev->gfx.num_compute_rings) + 3);
+	r = amdgpu_ring_alloc(kiq_ring, (8 * adev->gfx.num_compute_rings) + 11);
 	if (r) {
 		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
 		amdgpu_gfx_scratch_free(adev, scratch);
 		return r;
 	}
+	/* set resources */
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
+	amdgpu_ring_write(kiq_ring, 0);	/* vmid_mask:0 queue_type:0 (KIQ) */
+	amdgpu_ring_write(kiq_ring, 0x000000FF);	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring, 0);	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
+	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
 		uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
@@ -4902,7 +4861,6 @@ static int gfx_v8_0_kiq_init_queue(struc
 	struct amdgpu_device *adev = ring->adev;
 	struct vi_mqd *mqd = ring->mqd_ptr;
 	int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
-	int r;
 
 	gfx_v8_0_kiq_setting(ring);
 
@@ -4933,9 +4891,7 @@ static int gfx_v8_0_kiq_init_queue(struc
 		mutex_unlock(&adev->srbm_mutex);
 	}
 
-	r = gfx_v8_0_kiq_enable(ring);
-
-	return r;
+	return 0;
 }
 
 static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring)
@@ -4990,13 +4946,6 @@ static int gfx_v8_0_kiq_resume(struct am
 	if (r)
 		goto done;
 
-	ring->ready = true;
-	r = amdgpu_ring_test_ring(ring);
-	if (r) {
-		ring->ready = false;
-		goto done;
-	}
-
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
 
@@ -5014,10 +4963,20 @@ static int gfx_v8_0_kiq_resume(struct am
 			goto done;
 	}
 
-	r = gfx_v8_0_map_queues_enable(adev);
+	r = gfx_v8_0_kiq_kcq_enable(adev);
 	if (r)
 		goto done;
 
+	/* Test KIQ */
+	ring = &adev->gfx.kiq.ring;
+	ring->ready = true;
+	r = amdgpu_ring_test_ring(ring);
+	if (r) {
+		ring->ready = false;
+		goto done;
+	}
+
+	/* Test KCQs */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
 		ring->ready = true;