[PATCH AUTOSEL 5.4 265/330] drm/amd/powerplay: try to do a graceful shutdown on SW CTF

[Quan, Evan]

[AMD Official Use Only - Internal Distribution Only]

Hi @Sasha Levin @Deucher, Alexander,

The following changes need to be applied also.
Otherwise, you may see unexpected shutdown on stress gpu loading on Vega10.

drm/amd/pm: avoid false alarm due to confusing softwareshutdowntemp setting
drm/amd/pm: correct the thermal alert temperature limit settings
drm/amd/pm: correct Vega20 swctf limit setting
drm/amd/pm: correct Vega12 swctf limit setting
drm/amd/pm: correct Vega10 swctf limit setting

BR
Evan
-----Original Message-----
From: Sasha Levin <sashal at kernel.org>
Sent: Friday, September 18, 2020 10:00 AM
To: linux-kernel at vger.kernel.org; stable at vger.kernel.org
Cc: Quan, Evan <Evan.Quan at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>; Sasha Levin <sashal at kernel.org>; dri-devel at lists.freedesktop.org
Subject: [PATCH AUTOSEL 5.4 265/330] drm/amd/powerplay: try to do a graceful shutdown on SW CTF

From: Evan Quan <evan.quan at amd.com>

[ Upstream commit 9495220577416632675959caf122e968469ffd16 ]

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

Signed-off-by: Evan Quan <evan.quan at amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
 .../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 d09690fca4520..414added3d02c 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"
@@ -593,12 +594,18 @@ 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),
@@ -609,12 +616,18 @@ 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 c4d8c52c6b9ca..6c4405622c9bb 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>

 #include "pp_debug.h"
 #include "amdgpu.h"
@@ -1538,6 +1539,12 @@ 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",
--
2.25.1