drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation

From Evan Quan
0f19195d639764d68f6f316dda363ba29821e5bc in linux-6.1.y/6.1.46
b75efe88b20c2be28b67e2821a794cc183e32374 in mainline linux

8 files changed, 102 insertions, 32 deletions

diff --git a/sys/dev/pci/drm/amd/amdgpu/amdgpu.h b/sys/dev/pci/drm/amd/amdgpu/amdgpu.h
index b15b9dc227a..6bd8895f3d4 100644
--- a/sys/dev/pci/drm/amd/amdgpu/amdgpu.h
+++ b/sys/dev/pci/drm/amd/amdgpu/amdgpu.h
@@ -288,6 +288,9 @@ 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;
diff --git a/sys/dev/pci/drm/amd/pm/powerplay/amd_powerplay.c b/sys/dev/pci/drm/amd/pm/powerplay/amd_powerplay.c
index 012dbdb193a..aa1b7a4cb26 100644
--- a/sys/dev/pci/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/sys/dev/pci/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;
 }
 
@@ -136,6 +180,8 @@ 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;
@@ -222,6 +268,8 @@ 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/sys/dev/pci/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/sys/dev/pci/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index bfe80ac0ad8..d0b1ab6c452 100644
--- a/sys/dev/pci/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/sys/dev/pci/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/sys/dev/pci/drm/amd/pm/powerplay/inc/hwmgr.h b/sys/dev/pci/drm/amd/pm/powerplay/inc/hwmgr.h
index 06ad0aebfff..713c95725af 100644
--- a/sys/dev/pci/drm/amd/pm/powerplay/inc/hwmgr.h
+++ b/sys/dev/pci/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/sys/dev/pci/drm/amd/pm/swsmu/amdgpu_smu.c b/sys/dev/pci/drm/amd/pm/swsmu/amdgpu_smu.c
index 7a7d3a5e0d3..f68365e8a89 100644
--- a/sys/dev/pci/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/sys/dev/pci/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"
@@ -1061,6 +1062,34 @@ 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;
@@ -1109,6 +1138,9 @@ static int smu_sw_init(void *handle)
 		return ret;
 	}
 
+	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");
@@ -1581,6 +1613,8 @@ 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/sys/dev/pci/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/sys/dev/pci/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 1bb953c9796..d070ce60fd4 100644
--- a/sys/dev/pci/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/sys/dev/pci/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/sys/dev/pci/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/sys/dev/pci/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index efd7d1feb0c..6de309a4a60 100644
--- a/sys/dev/pci/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/sys/dev/pci/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1438,13 +1438,8 @@ 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/sys/dev/pci/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/sys/dev/pci/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index a2ad1a06806..7a4c6aef0ef 100644
--- a/sys/dev/pci/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/sys/dev/pci/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1386,13 +1386,8 @@ 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");