[PATCH 1/2] drm/amd/powerplay: try to do a graceful shutdown on SW CTF

[Evan Quan]

Normally this(SW CTF) should not happen. And by doing graceful
shutdown we can prevent further damage.

Change-Id: I84f0c0643f78dcb5251089fe83305c460b815b62
Signed-off-by: Evan Quan <evan.quan at amd.com>
---
 .../gpu/drm/amd/powerplay/hwmgr/smu_helper.c  | 21 +++++++++++++++----
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     |  7 +++++++
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 91b5d96db674..782f6d295202 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/reboot.h>
 
 #include "hwmgr.h"
 #include "pp_debug.h"
@@ -595,12 +596,18 @@ int phm_irq_process(struct amdgpu_device *adev,
 	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)
+		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) {
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
 						PCI_BUS_NUM(adev->pdev->devfn),
 						PCI_SLOT(adev->pdev->devfn),
 						PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
+			/*
+			 * SW CTF just occurred.
+			 * Try to do a graceful shutdown to prevent further damage.
+			 */
+			dev_emerg(adev->dev, "System is going to shutdown due to SW CTF!\n");
+			orderly_poweroff(true);
+		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
@@ -611,12 +618,18 @@ int phm_irq_process(struct amdgpu_device *adev,
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
 	} else if (client_id == SOC15_IH_CLIENTID_THM) {
-		if (src_id == 0)
+		if (src_id == 0) {
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
 						PCI_BUS_NUM(adev->pdev->devfn),
 						PCI_SLOT(adev->pdev->devfn),
 						PCI_FUNC(adev->pdev->devfn));
-		else
+			/*
+			 * SW CTF just occurred.
+			 * Try to do a graceful shutdown to prevent further damage.
+			 */
+			dev_emerg(adev->dev, "System is going to shutdown due to SW CTF!\n");
+			orderly_poweroff(true);
+		} else
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index 5792b224b0c3..5b493f140dda 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -23,6 +23,7 @@
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/reboot.h>
 
 #define SMU_11_0_PARTIAL_PPTABLE
 
@@ -1535,6 +1536,12 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 				PCI_BUS_NUM(adev->pdev->devfn),
 				PCI_SLOT(adev->pdev->devfn),
 				PCI_FUNC(adev->pdev->devfn));
+			/*
+			 * SW CTF just occurred.
+			 * Try to do a graceful shutdown to prevent further damage.
+			 */
+			dev_emerg(adev->dev, "System is going to shutdown due to SW CTF!\n");
+			orderly_poweroff(true);
 		break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
-- 
2.26.2