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

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>

1 files changed, 34 insertions, 0 deletions

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");