diff options
Diffstat (limited to 'drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c')
| -rw-r--r-- | drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c | 37 |
1 files changed, 31 insertions, 6 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..4279f95ba779 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" @@ -595,37 +596,61 @@ 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), 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) + 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), 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; } |