drm/amdgpu: cleanup instance limit on VCN4 v4

Similar to what we did for VCN3 use the job instead of the parser
entity. Cleanup the coding style quite a bit as well.

v2: merge improved application check into this patch
v3: finally fix the check
v4: limit to the correct engine
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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

@@ -1591,21 +1591,23 @@ 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)
+static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p,
+				struct amdgpu_job *job)
 {
 	struct drm_gpu_scheduler **scheds;
 
 	/* The create msg must be in the first IB submitted */
-	if (atomic_read(&p->entity->fence_seq))
+	if (atomic_read(&job->base.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);
+	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
 	return 0;
 }
 
-static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
+static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,
+			    uint64_t addr)
 {
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_bo_va_mapping *map;
@@ -1676,7 +1678,7 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
 		if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11)
 			continue;
 
-		r = vcn_v4_0_limit_sched(p);
+		r = vcn_v4_0_limit_sched(p, job);
 		if (r)
 			goto out;
 	}
@@ -1689,32 +1691,34 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
 #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_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;
+	struct amdgpu_ring *ring = amdgpu_job_ring(job);
+	struct amdgpu_vcn_decode_buffer *decode_buffer;
+	uint64_t addr;
 	uint32_t val;
-	int r = 0;
 
 	/* The first instance can decode anything */
 	if (!ring->me)
-		return r;
+		return 0;
 
 	/* unified queue ib header has 8 double words. */
 	if (ib->length_dw < 8)
-		return r;
+		return 0;
 
 	val = amdgpu_ib_get_value(ib, 6); //RADEON_VCN_ENGINE_TYPE
+	if (val != RADEON_VCN_ENGINE_TYPE_DECODE)
+		return 0;
 
-	if (val == RADEON_VCN_ENGINE_TYPE_DECODE) {
-		decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[10];
+	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;
+	if (!(decode_buffer->valid_buf_flag  & 0x1))
+		return 0;
+
+	addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 |
+		decode_buffer->msg_buffer_address_lo;
+	return vcn_v4_0_dec_msg(p, job, addr);
 }
 
 static const struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = {