drm/amdgpu: Add GPU reset functionality for Vega10

V2

Signed-off-by: Ken Wang <Ken.Wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -2581,7 +2581,8 @@ static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
 		if ((adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) ||
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) ||
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_ACP) ||
-		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)) {
+		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) ||
+		     adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
 			if (adev->ip_blocks[i].status.hang) {
 				DRM_INFO("Some block need full reset!\n");
 				return true;

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

@@ -62,6 +62,7 @@ static int psp_sw_init(void *handle)
 		psp->cmd_submit = psp_v3_1_cmd_submit;
 		psp->compare_sram_data = psp_v3_1_compare_sram_data;
 		psp->smu_reload_quirk = psp_v3_1_smu_reload_quirk;
+		psp->mode1_reset = psp_v3_1_mode1_reset;
 		break;
 	case CHIP_RAVEN:
 		psp->init_microcode = psp_v10_0_init_microcode;
@@ -72,6 +73,7 @@ static int psp_sw_init(void *handle)
 		psp->ring_destroy = psp_v10_0_ring_destroy;
 		psp->cmd_submit = psp_v10_0_cmd_submit;
 		psp->compare_sram_data = psp_v10_0_compare_sram_data;
+		psp->mode1_reset = psp_v10_0_mode1_reset;
 		break;
 	default:
 		return -EINVAL;
@@ -497,6 +499,22 @@ failed:
 	return ret;
 }
 
+static bool psp_check_reset(void* handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (adev->flags & AMD_IS_APU)
+		return true;
+
+	return false;
+}
+
+static int psp_reset(void* handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	return psp_mode1_reset(&adev->psp);
+}
+
 static bool psp_check_fw_loading_status(struct amdgpu_device *adev,
 					enum AMDGPU_UCODE_ID ucode_type)
 {
@@ -540,8 +558,9 @@ const struct amd_ip_funcs psp_ip_funcs = {
 	.suspend = psp_suspend,
 	.resume = psp_resume,
 	.is_idle = NULL,
+	.check_soft_reset = psp_check_reset,
 	.wait_for_idle = NULL,
-	.soft_reset = NULL,
+	.soft_reset = psp_reset,
 	.set_clockgating_state = psp_set_clockgating_state,
 	.set_powergating_state = psp_set_powergating_state,
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h

@@ -76,6 +76,7 @@ struct psp_context
 				  struct amdgpu_firmware_info *ucode,
 				  enum AMDGPU_UCODE_ID ucode_type);
 	bool (*smu_reload_quirk)(struct psp_context *psp);
+	int (*mode1_reset)(struct psp_context *psp);
 
 	/* fence buffer */
 	struct amdgpu_bo 		*fw_pri_bo;
@@ -139,6 +140,8 @@ struct amdgpu_psp_funcs {
 		((psp)->bootloader_load_sos ? (psp)->bootloader_load_sos((psp)) : 0)
 #define psp_smu_reload_quirk(psp) \
 		((psp)->smu_reload_quirk ? (psp)->smu_reload_quirk((psp)) : false)
+#define psp_mode1_reset(psp) \
+		((psp)->mode1_reset ? (psp)->mode1_reset((psp)) : false)
 
 extern const struct amd_ip_funcs psp_ip_funcs;
 

drivers/gpu/drm/amd/amdgpu/psp_v10_0.c

@@ -407,3 +407,10 @@ bool psp_v10_0_compare_sram_data(struct psp_context *psp,
 
 	return true;
 }
+
+
+int psp_v10_0_mode1_reset(struct psp_context *psp)
+{
+	DRM_INFO("psp mode 1 reset not supported now! \n");
+	return -EINVAL;
+}

drivers/gpu/drm/amd/amdgpu/psp_v10_0.h

@@ -45,4 +45,6 @@ extern int psp_v10_0_cmd_submit(struct psp_context *psp,
 extern bool psp_v10_0_compare_sram_data(struct psp_context *psp,
 				       struct amdgpu_firmware_info *ucode,
 				       enum AMDGPU_UCODE_ID ucode_type);
+
+extern int psp_v10_0_mode1_reset(struct psp_context *psp);
 #endif

drivers/gpu/drm/amd/amdgpu/psp_v3_1.c

@@ -530,3 +530,37 @@ bool psp_v3_1_smu_reload_quirk(struct psp_context *psp)
 	reg = RREG32_SOC15(NBIO, 0, mmPCIE_DATA2);
 	return (reg & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) ? true : false;
 }
+
+int psp_v3_1_mode1_reset(struct psp_context *psp)
+{
+	int ret;
+	uint32_t offset;
+	struct amdgpu_device *adev = psp->adev;
+
+	offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64);
+
+	ret = psp_wait_for(psp, offset, 0x80000000, 0x8000FFFF, false);
+
+	if (ret) {
+		DRM_INFO("psp is not working correctly before mode1 reset!\n");
+		return -EINVAL;
+	}
+
+	/*send the mode 1 reset command*/
+	WREG32(offset, 0x70000);
+
+	mdelay(1000);
+
+	offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33);
+
+	ret = psp_wait_for(psp, offset, 0x80000000, 0x80000000, false);
+
+	if (ret) {
+		DRM_INFO("psp mode 1 reset failed!\n");
+		return -EINVAL;
+	}
+
+	DRM_INFO("psp mode1 reset succeed \n");
+
+	return 0;
+}

drivers/gpu/drm/amd/amdgpu/psp_v3_1.h

@@ -53,4 +53,5 @@ extern bool psp_v3_1_compare_sram_data(struct psp_context *psp,
 				       struct amdgpu_firmware_info *ucode,
 				       enum AMDGPU_UCODE_ID ucode_type);
 extern bool psp_v3_1_smu_reload_quirk(struct psp_context *psp);
+extern int psp_v3_1_mode1_reset(struct psp_context *psp);
 #endif

drivers/gpu/drm/amd/amdgpu/soc15.c

@@ -407,18 +407,27 @@ static int soc15_read_register(struct amdgpu_device *adev, u32 se_num,
 	return -EINVAL;
 }
 
-static void soc15_gpu_pci_config_reset(struct amdgpu_device *adev)
+static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	u32 i;
 
-	dev_info(adev->dev, "GPU pci config reset\n");
+	amdgpu_atombios_scratch_regs_engine_hung(adev, true);
+
+	dev_info(adev->dev, "GPU reset\n");
 
 	/* disable BM */
 	pci_clear_master(adev->pdev);
-	/* reset */
-	amdgpu_pci_config_reset(adev);
 
-	udelay(100);
+	pci_save_state(adev->pdev);
+
+	for (i = 0; i < AMDGPU_MAX_IP_NUM; i++) {
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP){
+			adev->ip_blocks[i].version->funcs->soft_reset((void *)adev);
+			break;
+		}
+	}
+
+	pci_restore_state(adev->pdev);
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
@@ -430,14 +439,6 @@ static void soc15_gpu_pci_config_reset(struct amdgpu_device *adev)
 		udelay(1);
 	}
 
-}
-
-static int soc15_asic_reset(struct amdgpu_device *adev)
-{
-	amdgpu_atombios_scratch_regs_engine_hung(adev, true);
-
-	soc15_gpu_pci_config_reset(adev);
-
 	amdgpu_atombios_scratch_regs_engine_hung(adev, false);
 
 	return 0;