Merge tag 'drm-next-2023-07-07' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Lots of fixes, mostly i915 and amdgpu. It's two weeks of i915, and I
  think three weeks of amdgpu.

  fbdev:
   - Fix module infos on sparc

  panel:
   - Fix mode on Starry-ili9882t

  i915:
   - Allow DC states along with PW2 only for PWB functionality [adlp+]
   - Fix SSC selection for MPLLA [mtl]
   - Use hw.adjusted mode when calculating io/fast wake times [psr]
   - Apply min softlimit correctly [guc/slpc]
   - Assign correct hdcp content type [hdcp]
   - Add missing forward declarations/includes to display power headers
   - Fix BDW PSR AUX CH data register offsets [psr]
   - Use mock device info for creating mock device

  amdgpu:
   - Misc cleanups
   - GFX 9.4.3 fixes
   - DEBUGFS build fix
   - Fix LPDDR5 reporting
   - ASPM fixes
   - DCN 3.1.4 fixes
   - DP MST fixes
   - DCN 3.2.x fixes
   - Display PSR TCON fixes
   - SMU 13.x fixes
   - RAS fixes
   - Vega12/20 SMU fixes
   - PSP flashing cleanup
   - GFX9 MCBP fixes
   - SR-IOV fixes
   - GPUVM clear mappings fix for always valid BOs
   - Add FAMS quirk for problematic monitor
   - Fix possible UAF
   - Better handle monentary temperature fluctuations
   - SDMA 4.4.2 fixes
   - Fencing fix"

* tag 'drm-next-2023-07-07' of git://anongit.freedesktop.org/drm/drm: (83 commits)
  drm/i915: use mock device info for creating mock device
  drm/i915/psr: Fix BDW PSR AUX CH data register offsets
  drm/amdgpu: Fix potential fence use-after-free v2
  drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation
  drm/amd/pm: expose swctf threshold setting for legacy powerplay
  drm/amd/display: 3.2.241
  drm/amd/display: Take full update path if number of planes changed
  drm/amd/display: Create debugging mechanism for Gaming FAMS
  drm/amd/display: Add monitor specific edid quirk
  drm/amd/display: For new fast update path, loop through each surface
  drm/amd/display: Remove Phantom Pipe Check When Calculating K1 and K2
  drm/amd/display: Limit new fast update path to addr and gamma / color
  drm/amd/display: Fix the delta clamping for shaper LUT
  drm/amdgpu: Keep non-psp path for partition switch
  drm/amd/display: program DPP shaper and 3D LUT if updated
  Revert "drm/amd/display: edp do not add non-edid timings"
  drm/amdgpu: share drm device for pci amdgpu device with 1st partition device
  drm/amd/pm: Add GFX v9.4.3 unique id to sysfs
  drm/amd/pm: Enable pp_feature attribute
  drm/amdgpu/vcn: Need to unpause dpg before stop dpg
  ...

20 files changed, 181 insertions, 81 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index a57952b93e73..9ef88a0b1b57 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -35,44 +35,6 @@
 #include <linux/pm_runtime.h>
 #include <asm/processor.h>
 
-static const struct cg_flag_name clocks[] = {
-	{AMD_CG_SUPPORT_GFX_FGCG, "Graphics Fine Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_MGCG, "Graphics Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_MGLS, "Graphics Medium Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CGCG, "Graphics Coarse Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_CGLS, "Graphics Coarse Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CGTS, "Graphics Coarse Grain Tree Shader Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_CGTS_LS, "Graphics Coarse Grain Tree Shader Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CP_LS, "Graphics Command Processor Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_RLC_LS, "Graphics Run List Controller Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_3D_CGCG, "Graphics 3D Coarse Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_3D_CGLS, "Graphics 3D Coarse Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_MC_LS, "Memory Controller Light Sleep"},
-	{AMD_CG_SUPPORT_MC_MGCG, "Memory Controller Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_SDMA_LS, "System Direct Memory Access Light Sleep"},
-	{AMD_CG_SUPPORT_SDMA_MGCG, "System Direct Memory Access Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_BIF_MGCG, "Bus Interface Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_BIF_LS, "Bus Interface Light Sleep"},
-	{AMD_CG_SUPPORT_UVD_MGCG, "Unified Video Decoder Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_VCE_MGCG, "Video Compression Engine Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_HDP_LS, "Host Data Path Light Sleep"},
-	{AMD_CG_SUPPORT_HDP_MGCG, "Host Data Path Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DRM_MGCG, "Digital Right Management Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DRM_LS, "Digital Right Management Light Sleep"},
-	{AMD_CG_SUPPORT_ROM_MGCG, "Rom Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DF_MGCG, "Data Fabric Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_VCN_MGCG, "VCN Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_HDP_DS, "Host Data Path Deep Sleep"},
-	{AMD_CG_SUPPORT_HDP_SD, "Host Data Path Shutdown"},
-	{AMD_CG_SUPPORT_IH_CG, "Interrupt Handler Clock Gating"},
-	{AMD_CG_SUPPORT_JPEG_MGCG, "JPEG Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_REPEATER_FGCG, "Repeater Fine Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_PERF_CLK, "Perfmon Clock Gating"},
-	{AMD_CG_SUPPORT_ATHUB_MGCG, "Address Translation Hub Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_ATHUB_LS, "Address Translation Hub Light Sleep"},
-	{0, NULL},
-};
-
 static const struct hwmon_temp_label {
 	enum PP_HWMON_TEMP channel;
 	const char *label;
@@ -2110,6 +2072,7 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		case IP_VERSION(9, 4, 0):
 		case IP_VERSION(9, 4, 1):
 		case IP_VERSION(9, 4, 2):
+		case IP_VERSION(9, 4, 3):
 		case IP_VERSION(10, 3, 0):
 		case IP_VERSION(11, 0, 0):
 		case IP_VERSION(11, 0, 1):
@@ -2120,7 +2083,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 			*states = ATTR_STATE_UNSUPPORTED;
 		}
 	} else if (DEVICE_ATTR_IS(pp_features)) {
-		if (adev->flags & AMD_IS_APU || gc_ver < IP_VERSION(9, 0, 0))
+		if ((adev->flags & AMD_IS_APU &&
+		     gc_ver != IP_VERSION(9, 4, 3)) ||
+		    gc_ver < IP_VERSION(9, 0, 0))
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(gpu_metrics)) {
 		if (gc_ver < IP_VERSION(9, 1, 0))
@@ -3684,6 +3649,44 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 	return 0;
 }
 
+static const struct cg_flag_name clocks[] = {
+	{AMD_CG_SUPPORT_GFX_FGCG, "Graphics Fine Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_MGCG, "Graphics Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_MGLS, "Graphics Medium Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CGCG, "Graphics Coarse Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_CGLS, "Graphics Coarse Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CGTS, "Graphics Coarse Grain Tree Shader Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_CGTS_LS, "Graphics Coarse Grain Tree Shader Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CP_LS, "Graphics Command Processor Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_RLC_LS, "Graphics Run List Controller Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_3D_CGCG, "Graphics 3D Coarse Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_3D_CGLS, "Graphics 3D Coarse Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_MC_LS, "Memory Controller Light Sleep"},
+	{AMD_CG_SUPPORT_MC_MGCG, "Memory Controller Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_SDMA_LS, "System Direct Memory Access Light Sleep"},
+	{AMD_CG_SUPPORT_SDMA_MGCG, "System Direct Memory Access Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_BIF_MGCG, "Bus Interface Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_BIF_LS, "Bus Interface Light Sleep"},
+	{AMD_CG_SUPPORT_UVD_MGCG, "Unified Video Decoder Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_VCE_MGCG, "Video Compression Engine Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_HDP_LS, "Host Data Path Light Sleep"},
+	{AMD_CG_SUPPORT_HDP_MGCG, "Host Data Path Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DRM_MGCG, "Digital Right Management Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DRM_LS, "Digital Right Management Light Sleep"},
+	{AMD_CG_SUPPORT_ROM_MGCG, "Rom Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DF_MGCG, "Data Fabric Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_VCN_MGCG, "VCN Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_HDP_DS, "Host Data Path Deep Sleep"},
+	{AMD_CG_SUPPORT_HDP_SD, "Host Data Path Shutdown"},
+	{AMD_CG_SUPPORT_IH_CG, "Interrupt Handler Clock Gating"},
+	{AMD_CG_SUPPORT_JPEG_MGCG, "JPEG Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_REPEATER_FGCG, "Repeater Fine Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_PERF_CLK, "Perfmon Clock Gating"},
+	{AMD_CG_SUPPORT_ATHUB_MGCG, "Address Translation Hub Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_ATHUB_LS, "Address Translation Hub Light Sleep"},
+	{0, NULL},
+};
+
 static void amdgpu_parse_cg_state(struct seq_file *m, u64 flags)
 {
 	int i;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index d178f3f44081..42172b00be66 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal {
 	int                max_mem_crit_temp;
 	/* memory max emergency(shutdown) temp */
 	int                max_mem_emergency_temp;
+	/* SWCTF threshold */
+	int                sw_ctf_threshold;
 	/* was last interrupt low to high or high to low */
 	bool               high_to_low;
 	/* interrupt source */
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 11b7b4cffaae..ff360c699171 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -26,6 +26,7 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/firmware.h>
+#include <linux/reboot.h>
 #include "amd_shared.h"
 #include "amd_powerplay.h"
 #include "power_state.h"
@@ -91,6 +92,45 @@ static int pp_early_init(void *handle)
 	return 0;
 }
 
+static void pp_swctf_delayed_work_handler(struct work_struct *work)
+{
+	struct pp_hwmgr *hwmgr =
+		container_of(work, struct pp_hwmgr, swctf_delayed_work.work);
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct amdgpu_dpm_thermal *range =
+				&adev->pm.dpm.thermal;
+	uint32_t gpu_temperature, size;
+	int ret;
+
+	/*
+	 * If the hotspot/edge temperature is confirmed as below SW CTF setting point
+	 * after the delay enforced, nothing will be done.
+	 * Otherwise, a graceful shutdown will be performed to prevent further damage.
+	 */
+	if (range->sw_ctf_threshold &&
+	    hwmgr->hwmgr_func->read_sensor) {
+		ret = hwmgr->hwmgr_func->read_sensor(hwmgr,
+						     AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+						     &gpu_temperature,
+						     &size);
+		/*
+		 * For some legacy ASICs, hotspot temperature retrieving might be not
+		 * supported. Check the edge temperature instead then.
+		 */
+		if (ret == -EOPNOTSUPP)
+			ret = hwmgr->hwmgr_func->read_sensor(hwmgr,
+							     AMDGPU_PP_SENSOR_EDGE_TEMP,
+							     &gpu_temperature,
+							     &size);
+		if (!ret && gpu_temperature / 1000 < range->sw_ctf_threshold)
+			return;
+	}
+
+	dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+	dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+	orderly_poweroff(true);
+}
+
 static int pp_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = handle;
@@ -101,6 +141,10 @@ static int pp_sw_init(void *handle)
 
 	pr_debug("powerplay sw init %s\n", ret ? "failed" : "successfully");
 
+	if (!ret)
+		INIT_DELAYED_WORK(&hwmgr->swctf_delayed_work,
+				  pp_swctf_delayed_work_handler);
+
 	return ret;
 }
 
@@ -135,6 +179,8 @@ static int pp_hw_fini(void *handle)
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
+	cancel_delayed_work_sync(&hwmgr->swctf_delayed_work);
+
 	hwmgr_hw_fini(hwmgr);
 
 	return 0;
@@ -221,6 +267,8 @@ static int pp_suspend(void *handle)
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
+	cancel_delayed_work_sync(&hwmgr->swctf_delayed_work);
+
 	return hwmgr_suspend(hwmgr);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
index 981dc8c7112d..90452b66e107 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
@@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 		TEMP_RANGE_MAX,
 		TEMP_RANGE_MIN,
 		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX};
+		TEMP_RANGE_MAX,
+		0};
 	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (!hwmgr->not_vf)
@@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 	adev->pm.dpm.thermal.min_mem_temp = range.mem_min;
 	adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max;
 	adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max;
+	adev->pm.dpm.thermal.sw_ctf_threshold = range.sw_ctf_threshold;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index e10cc5e7928e..6841a4bce186 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -5432,6 +5432,8 @@ static int smu7_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	thermal_data->sw_ctf_threshold = thermal_data->max;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index bfe80ac0ad8c..d0b1ab6c4523 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
@@ -603,21 +603,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 			   struct amdgpu_irq_src *source,
 			   struct amdgpu_iv_entry *entry)
 {
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 	uint32_t client_id = entry->client_id;
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) {
 		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) {
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
-		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
+		} else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
 			dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 			/*
 			 * HW CTF just occurred. Shutdown to prevent further damage.
@@ -626,15 +622,10 @@ int phm_irq_process(struct amdgpu_device *adev,
 			orderly_poweroff(true);
 		}
 	} else if (client_id == SOC15_IH_CLIENTID_THM) {
-		if (src_id == 0) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else
+		if (src_id == 0)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		else
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
 	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
 		dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 99cd2e63afdd..c51dd4c74fe9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -5241,6 +5241,9 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	struct phm_ppt_v2_information *pp_table_info =
+		(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
 
 	memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange));
 
@@ -5257,6 +5260,13 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit &&
+	    tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP)
+		thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp;
+	else
+		thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
+	thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index e9db137cd1c6..1937be1cf5b4 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2763,6 +2763,8 @@ static int vega12_notify_cac_buffer_info(struct pp_hwmgr *hwmgr,
 static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -2781,6 +2783,8 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
index ed3dff0b52d2..ae342c58cd3e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
@@ -192,7 +192,9 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
-	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
+	val &= ~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 0d4d4811527c..4e19ccbdb807 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -4206,6 +4206,8 @@ static int vega20_notify_cac_buffer_info(struct pp_hwmgr *hwmgr,
 static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -4224,6 +4226,8 @@ static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
index f4f4efdbda79..e9737ca8418a 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
@@ -263,7 +263,9 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
-	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
+	val &= ~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
index f1580a26a850..612d66aeaab9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
@@ -811,6 +811,8 @@ struct pp_hwmgr {
 	bool gfxoff_state_changed_by_workload;
 	uint32_t pstate_sclk_peak;
 	uint32_t pstate_mclk_peak;
+
+	struct delayed_work swctf_delayed_work;
 };
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
index a5f2227a3971..0ffc2347829d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
@@ -131,6 +131,7 @@ struct PP_TemperatureRange {
 	int mem_min;
 	int mem_crit_max;
 	int mem_emergency_max;
+	int sw_ctf_threshold;
 };
 
 struct PP_StateValidationBlock {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 4dea79a0c5b5..ce41a8309582 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/reboot.h>
 
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
@@ -1078,6 +1079,34 @@ static void smu_interrupt_work_fn(struct work_struct *work)
 		smu->ppt_funcs->interrupt_work(smu);
 }
 
+static void smu_swctf_delayed_work_handler(struct work_struct *work)
+{
+	struct smu_context *smu =
+		container_of(work, struct smu_context, swctf_delayed_work.work);
+	struct smu_temperature_range *range =
+				&smu->thermal_range;
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t hotspot_tmp, size;
+
+	/*
+	 * If the hotspot temperature is confirmed as below SW CTF setting point
+	 * after the delay enforced, nothing will be done.
+	 * Otherwise, a graceful shutdown will be performed to prevent further damage.
+	 */
+	if (range->software_shutdown_temp &&
+	    smu->ppt_funcs->read_sensor &&
+	    !smu->ppt_funcs->read_sensor(smu,
+					 AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+					 &hotspot_tmp,
+					 &size) &&
+	    hotspot_tmp / 1000 < range->software_shutdown_temp)
+		return;
+
+	dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+	dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+	orderly_poweroff(true);
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1120,6 +1149,9 @@ static int smu_sw_init(void *handle)
 	smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 
+	INIT_DELAYED_WORK(&smu->swctf_delayed_work,
+			  smu_swctf_delayed_work_handler);
+
 	ret = smu_smc_table_sw_init(smu);
 	if (ret) {
 		dev_err(adev->dev, "Failed to sw init smc table!\n");
@@ -1600,6 +1632,8 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&smu->swctf_delayed_work);
+
 	ret = smu_disable_dpms(smu);
 	if (ret) {
 		dev_err(adev->dev, "Fail to disable dpm features!\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 09469c750a96..6e2069dcb6b9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -573,6 +573,8 @@ struct smu_context
 	u32 debug_param_reg;
 	u32 debug_msg_reg;
 	u32 debug_resp_reg;
+
+	struct delayed_work		swctf_delayed_work;
 };
 
 struct i2c_adapter;
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 275f708db636..c94d825a871b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1654,7 +1654,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 				   enum smu_clk_type clk_type, uint32_t mask)
 {
 
-	int ret = 0, size = 0;
+	int ret = 0;
 	uint32_t soft_min_level = 0, soft_max_level = 0, min_freq = 0, max_freq = 0;
 
 	soft_min_level = mask ? (ffs(mask) - 1) : 0;
@@ -1675,15 +1675,15 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 
 		ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
-			return size;
+			return 0;
 
 		ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
 		if (ret)
-			return size;
+			return 0;
 
 		ret = smu_v11_0_set_soft_freq_limited_range(smu, clk_type, min_freq, max_freq);
 		if (ret)
-			return size;
+			return 0;
 		break;
 	case SMU_DCEFCLK:
 		dev_info(smu->adev->dev,"Setting DCEFCLK min/max dpm level is not supported!\n");
@@ -1693,7 +1693,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 		break;
 	}
 
-	return size;
+	return 0;
 }
 
 static int navi10_populate_umd_state_clk(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index e1ef88ee1ed3..aa4a5498a12f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1412,13 +1412,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 		break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e52c563f0dac..3856da6c3f3d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1353,13 +1353,8 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 			break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a6083957ae51..124287cbbff8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1710,6 +1710,7 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu,
 	range->mem_emergency_max = (pptable->SkuTable.TemperatureLimit[TEMP_MEM] + CTF_OFFSET_MEM)*
 		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	range->software_shutdown_temp = powerplay_table->software_shutdown_temp;
+	range->software_shutdown_temp_offset = pptable->SkuTable.FanAbnormalTempLimitOffset;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index a92ea4601ea4..6ef12252beb5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -200,7 +200,6 @@ struct PPTable_t {
 };
 
 #define SMUQ10_TO_UINT(x) ((x) >> 10)
-#define SMUQ16_TO_UINT(x) ((x) >> 16)
 
 struct smu_v13_0_6_dpm_map {
 	enum smu_clk_type clk_type;
@@ -1994,8 +1993,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 
 	gpu_metrics->average_socket_power =
 		SMUQ10_TO_UINT(metrics->SocketPower);
+	/* Energy is reported in 15.625mJ units */
 	gpu_metrics->energy_accumulator =
-		SMUQ16_TO_UINT(metrics->SocketEnergyAcc);
+		SMUQ10_TO_UINT(metrics->SocketEnergyAcc);
 
 	gpu_metrics->current_gfxclk =
 		SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]);