drm/amdgpu: limiting AV1 to first instance on VCN4 decode

AV1 is only supported on first instance.
Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c

@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
 #include "amdgpu_pm.h"
+#include "amdgpu_cs.h"
 #include "soc15.h"
 #include "soc15d.h"
 #include "soc15_hw_ip.h"
@@ -44,6 +45,9 @@
 #define VCN_VID_SOC_ADDRESS_2_0							0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0						0x48300
 
+#define RDECODE_MSG_CREATE							0x00000000
+#define RDECODE_MESSAGE_CREATE							0x00000001
+
 static int amdgpu_ih_clientid_vcns[] = {
 	SOC15_IH_CLIENTID_VCN,
 	SOC15_IH_CLIENTID_VCN1
@@ -1323,6 +1327,132 @@ static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
+static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p)
+{
+	struct drm_gpu_scheduler **scheds;
+
+	/* The create msg must be in the first IB submitted */
+	if (atomic_read(&p->entity->fence_seq))
+		return -EINVAL;
+
+	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC]
+		[AMDGPU_RING_PRIO_0].sched;
+	drm_sched_entity_modify_sched(p->entity, scheds, 1);
+	return 0;
+}
+
+static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
+{
+	struct ttm_operation_ctx ctx = { false, false };
+	struct amdgpu_bo_va_mapping *map;
+	uint32_t *msg, num_buffers;
+	struct amdgpu_bo *bo;
+	uint64_t start, end;
+	unsigned int i;
+	void *ptr;
+	int r;
+
+	addr &= AMDGPU_GMC_HOLE_MASK;
+	r = amdgpu_cs_find_mapping(p, addr, &bo, &map);
+	if (r) {
+		DRM_ERROR("Can't find BO for addr 0x%08llx\n", addr);
+		return r;
+	}
+
+	start = map->start * AMDGPU_GPU_PAGE_SIZE;
+	end = (map->last + 1) * AMDGPU_GPU_PAGE_SIZE;
+	if (addr & 0x7) {
+		DRM_ERROR("VCN messages must be 8 byte aligned!\n");
+		return -EINVAL;
+	}
+
+	bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+	amdgpu_bo_placement_from_domain(bo, bo->allowed_domains);
+	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+	if (r) {
+		DRM_ERROR("Failed validating the VCN message BO (%d)!\n", r);
+		return r;
+	}
+
+	r = amdgpu_bo_kmap(bo, &ptr);
+	if (r) {
+		DRM_ERROR("Failed mapping the VCN message (%d)!\n", r);
+		return r;
+	}
+
+	msg = ptr + addr - start;
+
+	/* Check length */
+	if (msg[1] > end - addr) {
+		r = -EINVAL;
+		goto out;
+	}
+
+	if (msg[3] != RDECODE_MSG_CREATE)
+		goto out;
+
+	num_buffers = msg[2];
+	for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) {
+		uint32_t offset, size, *create;
+
+		if (msg[0] != RDECODE_MESSAGE_CREATE)
+			continue;
+
+		offset = msg[1];
+		size = msg[2];
+
+		if (offset + size > end) {
+			r = -EINVAL;
+			goto out;
+		}
+
+		create = ptr + addr + offset - start;
+
+		/* H246, HEVC and VP9 can run on any instance */
+		if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11)
+			continue;
+
+		r = vcn_v4_0_limit_sched(p);
+		if (r)
+			goto out;
+	}
+
+out:
+	amdgpu_bo_kunmap(bo);
+	return r;
+}
+
+#define RADEON_VCN_ENGINE_TYPE_DECODE                                 (0x00000003)
+
+static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
+				struct amdgpu_job *job,
+				struct amdgpu_ib *ib)
+{
+	struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched);
+	struct amdgpu_vcn_decode_buffer *decode_buffer = NULL;
+	uint32_t val;
+	int r = 0;
+
+	/* The first instance can decode anything */
+	if (!ring->me)
+		return r;
+
+	/* unified queue ib header has 8 double words. */
+	if (ib->length_dw < 8)
+		return r;
+
+	val = amdgpu_ib_get_value(ib, 6); //RADEON_VCN_ENGINE_TYPE
+
+	if (val == RADEON_VCN_ENGINE_TYPE_DECODE) {
+		decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[10];
+
+		if (decode_buffer->valid_buf_flag  & 0x1)
+			r = vcn_v4_0_dec_msg(p, ((u64)decode_buffer->msg_buffer_address_hi) << 32 |
+						decode_buffer->msg_buffer_address_lo);
+	}
+	return r;
+}
+
 static const struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_ENC,
 	.align_mask = 0x3f,
@@ -1331,6 +1461,7 @@ static const struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = {
 	.get_rptr = vcn_v4_0_unified_ring_get_rptr,
 	.get_wptr = vcn_v4_0_unified_ring_get_wptr,
 	.set_wptr = vcn_v4_0_unified_ring_set_wptr,
+	.patch_cs_in_place = vcn_v4_0_ring_patch_cs_in_place,
 	.emit_frame_size =
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
 		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 +