Skip to contentSkip to conversation

drm/amd/powerplay: unify the prompts on thermal interrupts

PATCH In review Evan Quan 2 participants 2 messages May 20, 2020

Subsystems (2)
lore
Share & tools
lore

Evan Quan

author
#0 lore raw

PATCH 1/1 drm/amd/powerplay: unify the prompts on thermal interrupts

The prompts will contain pci address(segment/bus/port/function), severity(warn or error) and some keywords(GPU, amdgpu). Also this address the issue that pci bus retrieved by PCI_BUS_NUM(adev->pdev->devfn) is wrong.

Change-Id I714d1dffb30a6cf76dcede087cf5d9302f683ed8
---
 .../gpu/drm/amd/powerplay/hwmgr/smu_helper.c  | 38 +++++--------------
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 26 ++++---------
 2 files changed, 17 insertions(+), 47 deletions(-)
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +10 -28
index 4279f95ba779..60b5ca974356 100644
@@ -597,58 +597,40 @@ int phm_irq_process(struct amdgpu_device *adev,
 
 	if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) {
 		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));
+			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, "System is going to shutdown due to SW CTF!\n");
+			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)
-			pr_warn("GPU under 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));
+			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
 		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));
+			dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 			/*
 			 * HW CTF just occurred. Shutdown to prevent further damage.
 			 */
-			dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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",
-						PCI_BUS_NUM(adev->pdev->devfn),
-						PCI_SLOT(adev->pdev->devfn),
-						PCI_FUNC(adev->pdev->devfn));
+			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, "System is going to shutdown due to SW CTF!\n");
+			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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),
-					PCI_FUNC(adev->pdev->devfn));
+			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
 	} 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));
+		dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 		/*
 		 * HW CTF just occurred. Shutdown to prevent further damage.
 		 */
-		dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+		dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
 		orderly_poweroff(true);
 	}
 
drivers/gpu/drm/amd/powerplay/smu_v11_0.c +7 -19
index c1ba77344107..f56789f8ec11 100644
@@ -1540,40 +1540,28 @@ 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:
-			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));
+			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, "System is going to shutdown due to SW CTF!\n");
+			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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",
-				PCI_BUS_NUM(adev->pdev->devfn),
-				PCI_SLOT(adev->pdev->devfn),
-				PCI_FUNC(adev->pdev->devfn));
+			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
 		break;
 		default:
-			pr_warn("GPU under temperature range unknown src id (%d), detected on PCIe %d:%d.%d!\n",
-				src_id,
-				PCI_BUS_NUM(adev->pdev->devfn),
-				PCI_SLOT(adev->pdev->devfn),
-				PCI_FUNC(adev->pdev->devfn));
+			dev_emerg(adev->dev, "ERROR: GPU under temperature range unknown src id (%d)\n",
+				src_id);
 		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));
+		dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 		/*
 		 * HW CTF just occurred. Shutdown to prevent further damage.
 		 */
-		dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+		dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
 		orderly_poweroff(true);
 	} else if (client_id == SOC15_IH_CLIENTID_MP1) {
 		if (src_id == 0xfe) {
Signature · 6 lines
2.26.2

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Reviewed-by on v1 1/1
#1 lore raw
Quoted 8 lines · Evan Quan

The prompts will contain pci address(segment/bus/port/function), severity(warn or error) and some keywords(GPU, amdgpu). Also this address the issue that pci bus retrieved by PCI_BUS_NUM(adev->pdev->devfn) is wrong.

Change-Id I714d1dffb30a6cf76dcede087cf5d9302f683ed8
Quoted 133 lines
---
 .../gpu/drm/amd/powerplay/hwmgr/smu_helper.c  | 38 +++++--------------
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 26 ++++---------
 2 files changed, 17 insertions(+), 47 deletions(-)
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +10 -28
index 4279f95ba779..60b5ca974356 100644
@@ -597,58 +597,40 @@ int phm_irq_process(struct amdgpu_device *adev,
 
        if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) {
                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));
+                       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, "System is going to shutdown due to SW CTF!\n");
+                       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)
-                       pr_warn("GPU under 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));
+                       dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
                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));
+                       dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
                        /*
                         * HW CTF just occurred. Shutdown to prevent further damage.
                         */
-                       dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+                       dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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",
-                                               PCI_BUS_NUM(adev->pdev->devfn),
-                                               PCI_SLOT(adev->pdev->devfn),
-                                               PCI_FUNC(adev->pdev->devfn));
+                       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, "System is going to shutdown due to SW CTF!\n");
+                       dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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),
-                                       PCI_FUNC(adev->pdev->devfn));
+                       dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
        } 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));
+               dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
                /*
                 * HW CTF just occurred. Shutdown to prevent further damage.
                 */
-               dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+               dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
                orderly_poweroff(true);
        }
 
drivers/gpu/drm/amd/powerplay/smu_v11_0.c +7 -20
index c1ba77344107..f56789f8ec11 100644
@@ -1540,40 +1540,28 @@ 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:
-                       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));
+                       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, "System is going to shutdown due to SW CTF!\n");
+                       dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU 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",
-                               PCI_BUS_NUM(adev->pdev->devfn),
-                               PCI_SLOT(adev->pdev->devfn),
-                               PCI_FUNC(adev->pdev->devfn));
+                       dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
                break;
                default:
-                       pr_warn("GPU under temperature range unknown src id (%d), detected on PCIe %d:%d.%d!\n",
-                               src_id,
-                               PCI_BUS_NUM(adev->pdev->devfn),
-                               PCI_SLOT(adev->pdev->devfn),
-                               PCI_FUNC(adev->pdev->devfn));
+                       dev_emerg(adev->dev, "ERROR: GPU under temperature range unknown src id (%d)\n",
+                               src_id);
                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));
+               dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
                /*
                 * HW CTF just occurred. Shutdown to prevent further damage.
                 */
-               dev_emerg(adev->dev, "System is going to shutdown due to HW CTF!\n");
+               dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU HW CTF!\n");
                orderly_poweroff(true);
        } else if (client_id == SOC15_IH_CLIENTID_MP1) {
                if (src_id == 0xfe) {
--

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