drm/amdgpu: fix double ucode load by PSP(v3)

previously the ucode loading of PSP was repreated, one executed in
phase_1 init/re-init/resume and the other in fw_loading routine

Avoid this double loading by clearing ip_blocks.status.hw in suspend or reset
prior to the FW loading and any block's hw_init/resume

v2:
still do the smu fw loading since it is needed by bare-metal

v3:
drop the change in reinit_early_sriov, just clear all block's status.hw
in the head place and set the status.hw after hw_init done is enough
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1745,28 +1745,34 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 
 	if (adev->asic_type >= CHIP_VEGA10) {
 		for (i = 0; i < adev->num_ip_blocks; i++) {
-			if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
-				if (adev->in_gpu_reset || adev->in_suspend) {
-					if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
-						break; /* sriov gpu reset, psp need to do hw_init before IH because of hw limit */
-					r = adev->ip_blocks[i].version->funcs->resume(adev);
-					if (r) {
-						DRM_ERROR("resume of IP block <%s> failed %d\n",
+			if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_PSP)
+				continue;
+
+			/* no need to do the fw loading again if already done*/
+			if (adev->ip_blocks[i].status.hw == true)
+				break;
+
+			if (adev->in_gpu_reset || adev->in_suspend) {
+				r = adev->ip_blocks[i].version->funcs->resume(adev);
+				if (r) {
+					DRM_ERROR("resume of IP block <%s> failed %d\n",
 							  adev->ip_blocks[i].version->funcs->name, r);
-						return r;
-					}
-				} else {
-					r = adev->ip_blocks[i].version->funcs->hw_init(adev);
-					if (r) {
-						DRM_ERROR("hw_init of IP block <%s> failed %d\n",
-						  adev->ip_blocks[i].version->funcs->name, r);
-						return r;
-					}
+					return r;
+				}
+			} else {
+				r = adev->ip_blocks[i].version->funcs->hw_init(adev);
+				if (r) {
+					DRM_ERROR("hw_init of IP block <%s> failed %d\n",
+							  adev->ip_blocks[i].version->funcs->name, r);
+					return r;
 				}
-				adev->ip_blocks[i].status.hw = true;
 			}
+
+			adev->ip_blocks[i].status.hw = true;
+			break;
 		}
 	}
+
 	r = amdgpu_pm_load_smu_firmware(adev, &smu_version);
 
 	return r;
@@ -2208,7 +2214,9 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 			if (r) {
 				DRM_ERROR("suspend of IP block <%s> failed %d\n",
 					  adev->ip_blocks[i].version->funcs->name, r);
+				return r;
 			}
+			adev->ip_blocks[i].status.hw = false;
 		}
 	}
 
@@ -2248,14 +2256,16 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 			if (is_support_sw_smu(adev)) {
 				/* todo */
 			} else if (adev->powerplay.pp_funcs &&
-				   adev->powerplay.pp_funcs->set_mp1_state) {
+					   adev->powerplay.pp_funcs->set_mp1_state) {
 				r = adev->powerplay.pp_funcs->set_mp1_state(
 					adev->powerplay.pp_handle,
 					adev->mp1_state);
 				if (r) {
 					DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
 						  adev->mp1_state, r);
+					return r;
 				}
+				adev->ip_blocks[i].status.hw = false;
 			}
 		}
 	}
@@ -2310,6 +2320,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 		for (j = 0; j < adev->num_ip_blocks; j++) {
 			block = &adev->ip_blocks[j];
 
+			block->status.hw = false;
 			if (block->version->type != ip_order[i] ||
 				!block->status.valid)
 				continue;
@@ -2318,6 +2329,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 			DRM_INFO("RE-INIT-early: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
+			block->status.hw = true;
 		}
 	}
 
@@ -2345,13 +2357,15 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 			block = &adev->ip_blocks[j];
 
 			if (block->version->type != ip_order[i] ||
-				!block->status.valid)
+				!block->status.valid ||
+				block->status.hw)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
 			DRM_INFO("RE-INIT-late: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
+			block->status.hw = true;
 		}
 	}
 
@@ -2375,17 +2389,19 @@ static int amdgpu_device_ip_resume_phase1(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.valid)
+		if (!adev->ip_blocks[i].status.valid || adev->ip_blocks[i].status.hw)
 			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_IH) {
+
 			r = adev->ip_blocks[i].version->funcs->resume(adev);
 			if (r) {
 				DRM_ERROR("resume of IP block <%s> failed %d\n",
 					  adev->ip_blocks[i].version->funcs->name, r);
 				return r;
 			}
+			adev->ip_blocks[i].status.hw = true;
 		}
 	}
 
@@ -2410,7 +2426,7 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_blocks[i].status.valid)
+		if (!adev->ip_blocks[i].status.valid || adev->ip_blocks[i].status.hw)
 			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_COMMON ||
 		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC ||
@@ -2423,6 +2439,7 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
 				  adev->ip_blocks[i].version->funcs->name, r);
 			return r;
 		}
+		adev->ip_blocks[i].status.hw = true;
 	}
 
 	return 0;