drm/amd/pm: fix Navi1x runtime resume failure V2

The RLC was put into a wrong state on runtime suspend. Thus the RLC
autoload will fail on the succeeding runtime resume. By adding an
intermediate PPSMC_MSG_PrepareMp1ForUnload(some GC hard reset involved,
designed for PnP), we can bring RLC back into the desired state.

V2: integrate INTERRUPTS_ENABLED flag clearing into current
    mp1 state set routines

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

9 files changed, 102 insertions, 27 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index bae304b0d67a..c2b7ee693719 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2146,9 +2146,12 @@ static int psp_load_smu_fw(struct psp_context *psp)
 	if (!ucode->fw || amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-
-	if (amdgpu_in_reset(adev) && ras && ras->supported &&
-		adev->asic_type == CHIP_ARCTURUS) {
+	if ((amdgpu_in_reset(adev) &&
+	     ras && ras->supported &&
+	     adev->asic_type == CHIP_ARCTURUS) ||
+	     (adev->in_runpm &&
+	      adev->asic_type >= CHIP_NAVI10 &&
+	      adev->asic_type <= CHIP_NAVI12)) {
 		ret = amdgpu_dpm_set_mp1_state(adev, PP_MP1_STATE_UNLOAD);
 		if (ret) {
 			DRM_WARN("Failed to set MP1 state prepare for reload\n");
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 25d5f03aaa67..2edb634bc1c6 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -807,6 +807,13 @@ struct pptable_funcs {
 	int (*check_fw_status)(struct smu_context *smu);
 
 	/**
+	 * @set_mp1_state: put SMU into a correct state for comming
+	 *                 resume from runpm or gpu reset.
+	 */
+	int (*set_mp1_state)(struct smu_context *smu,
+			     enum pp_mp1_state mp1_state);
+
+	/**
 	 * @setup_pptable: Initialize the power play table and populate it with
 	 *                 default values.
 	 */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 143e3783251e..05f00900d10c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1908,36 +1908,16 @@ int smu_set_mp1_state(void *handle,
 		      enum pp_mp1_state mp1_state)
 {
 	struct smu_context *smu = handle;
-	uint16_t msg;
-	int ret;
+	int ret = 0;
 
 	if (!smu->pm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	switch (mp1_state) {
-	case PP_MP1_STATE_SHUTDOWN:
-		msg = SMU_MSG_PrepareMp1ForShutdown;
-		break;
-	case PP_MP1_STATE_UNLOAD:
-		msg = SMU_MSG_PrepareMp1ForUnload;
-		break;
-	case PP_MP1_STATE_RESET:
-		msg = SMU_MSG_PrepareMp1ForReset;
-		break;
-	case PP_MP1_STATE_NONE:
-	default:
-		mutex_unlock(&smu->mutex);
-		return 0;
-	}
-
-	ret = smu_send_smc_msg(smu, msg, NULL);
-	/* some asics may not support those messages */
-	if (ret == -EINVAL)
-		ret = 0;
-	if (ret)
-		dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n");
+	if (smu->ppt_funcs &&
+	    smu->ppt_funcs->set_mp1_state)
+		ret = smu->ppt_funcs->set_mp1_state(smu, mp1_state);
 
 	mutex_unlock(&smu->mutex);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index bbc03092b0a9..77693bf0840c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -2365,6 +2365,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.get_fan_parameters = arcturus_get_fan_parameters,
 	.interrupt_work = smu_v11_0_interrupt_work,
 	.set_light_sbr = smu_v11_0_set_light_sbr,
+	.set_mp1_state = smu_cmn_set_mp1_state,
 };
 
 void arcturus_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 3d0de2c958fa..f827096dc849 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -431,6 +431,30 @@ static int navi10_store_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
+static int navi10_set_mp1_state(struct smu_context *smu,
+				enum pp_mp1_state mp1_state)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t mp1_fw_flags;
+	int ret = 0;
+
+	ret = smu_cmn_set_mp1_state(smu, mp1_state);
+	if (ret)
+		return ret;
+
+	if (mp1_state == PP_MP1_STATE_UNLOAD) {
+		mp1_fw_flags = RREG32_PCIE(MP1_Public |
+					   (smnMP1_FIRMWARE_FLAGS & 0xffffffff));
+
+		mp1_fw_flags &= ~MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK;
+
+		WREG32_PCIE(MP1_Public |
+			    (smnMP1_FIRMWARE_FLAGS & 0xffffffff), mp1_fw_flags);
+	}
+
+	return 0;
+}
+
 static int navi10_setup_pptable(struct smu_context *smu)
 {
 	int ret = 0;
@@ -3031,6 +3055,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_fan_parameters = navi10_get_fan_parameters,
 	.post_init = navi10_post_smu_init,
 	.interrupt_work = smu_v11_0_interrupt_work,
+	.set_mp1_state = navi10_set_mp1_state,
 };
 
 void navi10_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 3621884c3293..722fe067ac2c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -3110,6 +3110,19 @@ static int sienna_cichlid_system_features_control(struct smu_context *smu,
 	return smu_v11_0_system_features_control(smu, en);
 }
 
+static int sienna_cichlid_set_mp1_state(struct smu_context *smu,
+					enum pp_mp1_state mp1_state)
+{
+	switch (mp1_state) {
+	case PP_MP1_STATE_UNLOAD:
+		return smu_cmn_set_mp1_state(smu, mp1_state);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.get_allowed_feature_mask = sienna_cichlid_get_allowed_feature_mask,
 	.set_default_dpm_table = sienna_cichlid_set_default_dpm_table,
@@ -3195,6 +3208,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.get_fan_parameters = sienna_cichlid_get_fan_parameters,
 	.interrupt_work = smu_v11_0_interrupt_work,
 	.gpo_control = sienna_cichlid_gpo_control,
+	.set_mp1_state = sienna_cichlid_set_mp1_state,
 };
 
 void sienna_cichlid_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 9813a86ca31a..7d38b92a78dc 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1460,6 +1460,19 @@ static bool aldebaran_is_mode2_reset_supported(struct smu_context *smu)
 	return true;
 }
 
+static int aldebaran_set_mp1_state(struct smu_context *smu,
+				   enum pp_mp1_state mp1_state)
+{
+	switch (mp1_state) {
+	case PP_MP1_STATE_UNLOAD:
+		return smu_cmn_set_mp1_state(smu, mp1_state);
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pptable_funcs aldebaran_ppt_funcs = {
 	/* init dpm */
 	.get_allowed_feature_mask = aldebaran_get_allowed_feature_mask,
@@ -1518,6 +1531,7 @@ static const struct pptable_funcs aldebaran_ppt_funcs = {
 	.mode2_reset_is_support = aldebaran_is_mode2_reset_supported,
 	.mode1_reset = smu_v13_0_mode1_reset,
 	.mode2_reset = smu_v13_0_mode2_reset,
+	.set_mp1_state = aldebaran_set_mp1_state,
 };
 
 void aldebaran_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 4b45953b36d8..2d216f5b167d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -780,3 +780,31 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 	header->structure_size = structure_size;
 
 }
+
+int smu_cmn_set_mp1_state(struct smu_context *smu,
+			  enum pp_mp1_state mp1_state)
+{
+	enum smu_message_type msg;
+	int ret;
+
+	switch (mp1_state) {
+	case PP_MP1_STATE_SHUTDOWN:
+		msg = SMU_MSG_PrepareMp1ForShutdown;
+		break;
+	case PP_MP1_STATE_UNLOAD:
+		msg = SMU_MSG_PrepareMp1ForUnload;
+		break;
+	case PP_MP1_STATE_RESET:
+		msg = SMU_MSG_PrepareMp1ForReset;
+		break;
+	case PP_MP1_STATE_NONE:
+	default:
+		return 0;
+	}
+
+	ret = smu_cmn_send_smc_msg(smu, msg, NULL);
+	if (ret)
+		dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n");
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index c69250185575..155e2a68fa1c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -99,5 +99,8 @@ int smu_cmn_get_metrics_table(struct smu_context *smu,
 
 void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev);
 
+int smu_cmn_set_mp1_state(struct smu_context *smu,
+			  enum pp_mp1_state mp1_state);
+
 #endif
 #endif