[PATCH 15/17] drm/amdgpu: remove hardcoded queue_mask in PACKET3_SET_RESOURCES

[Andres Rodriguez]

The assumption that we are only using the first pipe no longer holds.
Instead, calculate the queue_mask from the queue_bitmap.

Acked-by: Felix Kuehling <Felix.Kuehling at amd.com>
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 20 ++++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 23 +++++++++++++++++++++--
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 99a1a0f..d9c6867 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4698,60 +4698,76 @@ static int gfx_v8_0_cp_compute_load_microcode(struct amdgpu_device *adev)
 
 /* KIQ functions */
 static void gfx_v8_0_kiq_setting(struct amdgpu_ring *ring)
 {
 	uint32_t tmp;
 	struct amdgpu_device *adev = ring->adev;
 
 	/* tell RLC which is KIQ queue */
 	tmp = RREG32(mmRLC_CP_SCHEDULERS);
 	tmp &= 0xffffff00;
 	tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue);
 	WREG32(mmRLC_CP_SCHEDULERS, tmp);
 	tmp |= 0x80;
 	WREG32(mmRLC_CP_SCHEDULERS, tmp);
 }
 
 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;
+	uint64_t queue_mask = 0;
 	int r, i;
 
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << 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, (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, lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* 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);
 		uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
 
 		/* map queues */
 		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
 		/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
 		amdgpu_ring_write(kiq_ring,
 				  PACKET3_MAP_QUEUES_NUM_QUEUES(1));
 		amdgpu_ring_write(kiq_ring,
 				  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index) |
 				  PACKET3_MAP_QUEUES_QUEUE(ring->queue) |
 				  PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
 				  PACKET3_MAP_QUEUES_ME(ring->me == 1 ? 0 : 1)); /* doorbell */
 		amdgpu_ring_write(kiq_ring, lower_32_bits(mqd_addr));
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 4681f49..6ff002d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1893,46 +1893,65 @@ static int gfx_v9_0_cp_compute_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
 /* KIQ functions */
 static void gfx_v9_0_kiq_setting(struct amdgpu_ring *ring)
 {
 	uint32_t tmp;
 	struct amdgpu_device *adev = ring->adev;
 
 	/* tell RLC which is KIQ queue */
 	tmp = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS);
 	tmp &= 0xffffff00;
 	tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue);
 	WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, tmp);
 	tmp |= 0x80;
 	WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, tmp);
 }
 
 static void gfx_v9_0_kiq_enable(struct amdgpu_ring *ring)
 {
+	int i;
+	struct amdgpu_device *adev = ring->adev;
+	uint64_t queue_mask = 0;
+
+	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
+		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
+			continue;
+
+		/* This situation may be hit in the future if a new HW
+		 * generation exposes more than 64 queues. If so, the
+		 * definition of queue_mask needs updating */
+		if (WARN_ON(i > (sizeof(queue_mask)*8))) {
+			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
+			break;
+		}
+
+		queue_mask |= (1ull << i);
+	}
+
 	amdgpu_ring_alloc(ring, 8);
 	/* 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, lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(ring, upper_32_bits(queue_mask));	/* 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 */
 	amdgpu_ring_commit(ring);
 	udelay(50);
 }
 
 static void gfx_v9_0_map_queue_enable(struct amdgpu_ring *kiq_ring,
 				   struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = kiq_ring->adev;
 	uint64_t mqd_addr, wptr_addr;
 
 	mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
 	wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
 	amdgpu_ring_alloc(kiq_ring, 8);
 
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
 	/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
-- 
2.9.3