leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source 
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.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Evan Quan 2020-05-20 18:13:50 +08:00 committed by Alex Deucher
parent fa63ed8170
commit 27a468eac5
2 changed files with 17 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
View File

@ -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);
}

26
drivers/gpu/drm/amd/powerplay/smu_v11_0.c
View File

@ -1565,40 +1565,28 @@ 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) {