--- /dev/null
+From b75efe88b20c2be28b67e2821a794cc183e32374 Mon Sep 17 00:00:00 2001
+From: Evan Quan <evan.quan@amd.com>
+Date: Thu, 4 May 2023 17:09:39 +0800
+Subject: drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation
+
+From: Evan Quan <evan.quan@amd.com>
+
+commit b75efe88b20c2be28b67e2821a794cc183e32374 upstream.
+
+An intentional delay is added on soft ctf triggered. Then there will
+be a double check for the GPU temperature before taking further
+action. This can avoid unintended shutdown due to temperature
+momentary fluctuation.
+
+Signed-off-by: Evan Quan <evan.quan@amd.com>
+Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+[ Hand-modified because XCP support added to amdgpu.h in kernel 6.5
+ and is not necessary for this fix. ]
+Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1267
+Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2779
+Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +
+ drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c | 48 ++++++++++++++++++++
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c | 27 +++--------
+ drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h | 2
+ drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 34 ++++++++++++++
+ drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 2
+ drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 9 ---
+ drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 9 ---
+ 8 files changed, 102 insertions(+), 32 deletions(-)
+
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+@@ -282,6 +282,9 @@ extern int amdgpu_sg_display;
+ #define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
+ #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
+
++/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */
++#define AMDGPU_SWCTF_EXTRA_DELAY 50
++
+ struct amdgpu_device;
+ struct amdgpu_irq_src;
+ struct amdgpu_fpriv;
+--- 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);
+ }
+
+--- 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
+ 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
+ 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");
+--- 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);
+--- 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"
+@@ -1070,6 +1071,34 @@ static void smu_interrupt_work_fn(struct
+ 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;
+@@ -1112,6 +1141,9 @@ 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");
+@@ -1592,6 +1624,8 @@ static int smu_smc_hw_cleanup(struct 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");
+--- 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;
+--- 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
+ 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");
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+@@ -1377,13 +1377,8 @@ static int smu_v13_0_irq_process(struct
+ 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");
--- /dev/null
+From 064329c595da56eff6d7a7e7760660c726433139 Mon Sep 17 00:00:00 2001
+From: Evan Quan <evan.quan@amd.com>
+Date: Thu, 25 May 2023 10:30:39 +0800
+Subject: drm/amd/pm: expose swctf threshold setting for legacy powerplay
+
+From: Evan Quan <evan.quan@amd.com>
+
+commit 064329c595da56eff6d7a7e7760660c726433139 upstream.
+
+Preparation for coming optimization which eliminates the influence of
+GPU temperature momentary fluctuation.
+
+Signed-off-by: Evan Quan <evan.quan@amd.com>
+Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h | 2 ++
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c | 4 +++-
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 2 ++
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 10 ++++++++++
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 4 ++++
+ drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 4 ++++
+ drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h | 1 +
+ 7 files changed, 26 insertions(+), 1 deletion(-)
+
+--- 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 */
+--- 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
+ 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
+ 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;
+ }
+--- 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_
+ thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
++ thermal_data->sw_ctf_threshold = thermal_data->max;
++
+ return 0;
+ }
+
+--- 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_temperatur
+ {
+ 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_temperatur
+ 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;
+ }
+
+--- 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
+ 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_temperatur
+ 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;
+ }
+--- 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
+ 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_temperatur
+ 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;
+ }
+--- 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 {
projects / thirdparty / kernel / stable-queue.git / commitdiff
