Skip to contentSkip to conversation

drm/amd/powerplay: try to do a graceful shutdown on SW CTF

PATCH In review Evan Quan 2 participants 3 messages May 9, 2020 – May 11, 2020

Subsystems (2)
lore
Share & tools
lore

Evan Quan

author
#0 lore raw

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

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

Change-Id I84f0c0643f78dcb5251089fe83305c460b815b62
---
 .../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(-)
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +17 -4
index 91b5d96db674..782f6d295202 100644
@@ -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),
drivers/gpu/drm/amd/powerplay/smu_v11_0.c +7 -0
index 5792b224b0c3..5b493f140dda 100644
@@ -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",
Signature · 6 lines
2.26.2

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
author
#1 lore raw

PATCH 2/2 drm/amd/powerplay: shutdown on HW CTF

To prevent further damage.

Change-Id Iae0399001694bb7446bcc6071cd03d8fa47c9d02
---
 .../gpu/drm/amd/powerplay/hwmgr/smu_helper.c  | 16 +++++++++++++--
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 20 ++++++++++++++++++-
 2 files changed, 33 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +14 -2
index 782f6d295202..4279f95ba779 100644
@@ -612,11 +612,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19)
+		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
 			pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
+			/*
+			 * HW CTF just occurred. Shutdown to prevent further damage.
+			 */
+			dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+			orderly_poweroff(true);
+		}
 	} else if (client_id == SOC15_IH_CLIENTID_THM) {
 		if (src_id == 0) {
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
@@ -634,11 +640,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
-	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO)
+	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
 		pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
 				PCI_BUS_NUM(adev->pdev->devfn),
 				PCI_SLOT(adev->pdev->devfn),
 				PCI_FUNC(adev->pdev->devfn));
+		/*
+		 * HW CTF just occurred. Shutdown to prevent further damage.
+		 */
+		dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+		orderly_poweroff(true);
+	}
 
 	return 0;
 }
drivers/gpu/drm/amd/powerplay/smu_v11_0.c +19 -1
index 5b493f140dda..041aac272a9e 100644
@@ -1517,6 +1517,8 @@ static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu)
 #define THM_11_0__SRCID__THM_DIG_THERM_L2H		0		/* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
 #define THM_11_0__SRCID__THM_DIG_THERM_H2L		1		/* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
 
+#define SMUIO_11_0__SRCID__SMUIO_GPIO19			83
+
 static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 				 struct amdgpu_irq_src *source,
 				 struct amdgpu_iv_entry *entry)
@@ -1556,8 +1558,17 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 				PCI_SLOT(adev->pdev->devfn),
 				PCI_FUNC(adev->pdev->devfn));
 		break;
-
 		}
+	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
+		pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
+				PCI_BUS_NUM(adev->pdev->devfn),
+				PCI_SLOT(adev->pdev->devfn),
+				PCI_FUNC(adev->pdev->devfn));
+		/*
+		 * HW CTF just occurred. Shutdown to prevent further damage.
+		 */
+		dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+		orderly_poweroff(true);
 	} else if (client_id == SOC15_IH_CLIENTID_MP1) {
 		if (src_id == 0xfe) {
 			switch (ctxid) {
@@ -1610,6 +1621,13 @@ int smu_v11_0_register_irq_handler(struct smu_context *smu)
 	if (ret)
 		return ret;
 
+	/* Register CTF(GPIO_19) interrupt */
+	ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_ROM_SMUIO,
+				SMUIO_11_0__SRCID__SMUIO_GPIO19,
+				irq_src);
+	if (ret)
+		return ret;
+
 	ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1,
 				0xfe,
 				irq_src);
Signature · 6 lines
2.26.2

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Reviewed-by on v1 2/2
#2 lore raw

Re: [PATCH 2/2] drm/amd/powerplay: shutdown on HW CTF

Quoted 5 lines · Evan Quan

To prevent further damage.

Change-Id Iae0399001694bb7446bcc6071cd03d8fa47c9d02

Series is:

Quoted 96 lines
---
 .../gpu/drm/amd/powerplay/hwmgr/smu_helper.c  | 16 +++++++++++++--
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 20 ++++++++++++++++++-
 2 files changed, 33 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +14 -2
index 782f6d295202..4279f95ba779 100644
@@ -612,11 +612,17 @@ int phm_irq_process(struct amdgpu_device *adev,
                                        PCI_BUS_NUM(adev->pdev->devfn),
                                        PCI_SLOT(adev->pdev->devfn),
                                        PCI_FUNC(adev->pdev->devfn));
-               else if (src_id == VISLANDS30_IV_SRCID_GPIO_19)
+               else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
                        pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
                                        PCI_BUS_NUM(adev->pdev->devfn),
                                        PCI_SLOT(adev->pdev->devfn),
                                        PCI_FUNC(adev->pdev->devfn));
+                       /*
+                        * HW CTF just occurred. Shutdown to prevent further damage.
+                        */
+                       dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+                       orderly_poweroff(true);
+               }
        } else if (client_id == SOC15_IH_CLIENTID_THM) {
                if (src_id == 0) {
                        pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
@@ -634,11 +640,17 @@ int phm_irq_process(struct amdgpu_device *adev,
                                        PCI_BUS_NUM(adev->pdev->devfn),
                                        PCI_SLOT(adev->pdev->devfn),
                                        PCI_FUNC(adev->pdev->devfn));
-       } else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO)
+       } else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
                pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
                                PCI_BUS_NUM(adev->pdev->devfn),
                                PCI_SLOT(adev->pdev->devfn),
                                PCI_FUNC(adev->pdev->devfn));
+               /*
+                * HW CTF just occurred. Shutdown to prevent further damage.
+                */
+               dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+               orderly_poweroff(true);
+       }
 
        return 0;
 }
drivers/gpu/drm/amd/powerplay/smu_v11_0.c +19 -2
index 5b493f140dda..041aac272a9e 100644
@@ -1517,6 +1517,8 @@ static int smu_v11_0_ack_ac_dc_interrupt(struct smu_context *smu)
 #define THM_11_0__SRCID__THM_DIG_THERM_L2H             0               /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
 #define THM_11_0__SRCID__THM_DIG_THERM_H2L             1               /* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
 
+#define SMUIO_11_0__SRCID__SMUIO_GPIO19                        83
+
 static int smu_v11_0_irq_process(struct amdgpu_device *adev,
                                 struct amdgpu_irq_src *source,
                                 struct amdgpu_iv_entry *entry)
@@ -1556,8 +1558,17 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
                                PCI_SLOT(adev->pdev->devfn),
                                PCI_FUNC(adev->pdev->devfn));
                break;
-
                }
+       } else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
+               pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
+                               PCI_BUS_NUM(adev->pdev->devfn),
+                               PCI_SLOT(adev->pdev->devfn),
+                               PCI_FUNC(adev->pdev->devfn));
+               /*
+                * HW CTF just occurred. Shutdown to prevent further damage.
+                */
+               dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+               orderly_poweroff(true);
        } else if (client_id == SOC15_IH_CLIENTID_MP1) {
                if (src_id == 0xfe) {
                        switch (ctxid) {
@@ -1610,6 +1621,13 @@ int smu_v11_0_register_irq_handler(struct smu_context *smu)
        if (ret)
                return ret;
 
+       /* Register CTF(GPIO_19) interrupt */
+       ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_ROM_SMUIO,
+                               SMUIO_11_0__SRCID__SMUIO_GPIO19,
+                               irq_src);
+       if (ret)
+               return ret;
+
        ret = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_MP1,
                                0xfe,
                                irq_src);
--

2.26.2

Quoted 4 lines

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx