Re: [PATCH v2 09/12] drm/amdgpu: Catch register access while GMUX keeps the GPU off

From: Christian König

Date: Mon Nov 16 2026 - 07:25:00 EST


On 11/14/26 17:06, Atharva Tiwari wrote:
> From: Andre Eikmeyer <dev@deq.rocks>
>
> As mentioned previous any access to the GPU when the GMUX has
> shut off the rails results in a CPU CATTER, skip and report
> any register access after the GPU was runtime suspended for GMUX power-off.

Well absolutely clear NAK to the whole approach. That looks like a not throught through approach to me.

In general the driver requests runtime PM support based on if it is in use or not and *NOT* based on the GMUX status.

What the heck is going on here?

Regards,
Christian.

>
> Tested-by: Sebastian Zygadlo <szgit@xxxxxxxxxx>
> Tested-by: Yossef Osman <yossef.osman@xxxxxxxxx>
> Signed-off-by: Andre Eikmeyer <dev@deq.rocks>
> Signed-off-by: Atharva Tiwari <atharvatiwarilinuxdev@xxxxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 ++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 5 ++++
> .../gpu/drm/amd/amdgpu/amdgpu_reg_access.c | 24 +++++++++++++++++++
> 4 files changed, 35 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 6fd607587..9938ae48f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -881,6 +881,7 @@ struct amdgpu_device {
> /* enable runtime pm on the device */
> bool in_runpm;
> bool has_pr3;
> + bool runpm_active;
>
> bool ucode_sysfs_en;
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index ac336594b..ed205352f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -947,6 +947,10 @@ bool amdgpu_device_skip_hw_access(struct amdgpu_device *adev)
> if (adev->no_hw_access)
> return true;
>
> + if (unlikely(!READ_ONCE(adev->runpm_active))) {
> + WARN_RATELIMIT(1, "%s: register access while powered off\n", dev_name(adev->dev));
> + return true;
> + }
> #ifdef CONFIG_LOCKDEP
> /*
> * This is a bit complicated to understand, so worth a comment. What we assert
> @@ -2029,6 +2033,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
> int i, r;
>
> amdgpu_device_enable_virtual_display(adev);
> + adev->runpm_active = true;
>
> if (amdgpu_sriov_vf(adev)) {
> /*
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 3978ed284..d1b0c6c73 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2935,6 +2935,9 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
> amdgpu_device_baco_enter(adev);
> }
>
> + if (adev->pm.rpm_mode == AMDGPU_RUNPM_GMUX)
> + WRITE_ONCE(adev->runpm_active, false);
> +
> dev_dbg(&pdev->dev, "asic/device is runtime suspended\n");
>
> return 0;
> @@ -2963,6 +2966,8 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
> if (adev->pm.rpm_mode == AMDGPU_RUNPM_NONE)
> return -EINVAL;
>
> + WRITE_ONCE(adev->runpm_active, true);
> +
> /* Avoids registers access if device is physically gone */
> if (!pci_device_is_present(adev->pdev))
> adev->no_hw_access = true;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reg_access.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reg_access.c
> index 7468855c1..64eba8a97 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reg_access.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reg_access.c
> @@ -594,6 +594,9 @@ u32 amdgpu_device_indirect_rreg(struct amdgpu_device *adev, u32 reg_addr)
> void __iomem *pcie_data_offset;
> u32 r;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return 0;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
>
> @@ -617,6 +620,9 @@ u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev, u64 reg_addr)
> void __iomem *pcie_index_hi_offset;
> void __iomem *pcie_data_offset;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return 0;
> +
> if (unlikely(!adev->nbio.funcs)) {
> pcie_index = AMDGPU_PCIE_INDEX_FALLBACK;
> pcie_data = AMDGPU_PCIE_DATA_FALLBACK;
> @@ -677,6 +683,9 @@ u64 amdgpu_device_indirect_rreg64(struct amdgpu_device *adev, u32 reg_addr)
> void __iomem *pcie_data_offset;
> u64 r;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return 0;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
>
> @@ -706,6 +715,9 @@ u64 amdgpu_device_indirect_rreg64_ext(struct amdgpu_device *adev, u64 reg_addr)
> void __iomem *pcie_data_offset;
> u64 r;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return 0;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
> if ((reg_addr >> 32) && (adev->nbio.funcs->get_pcie_index_hi_offset))
> @@ -762,6 +774,9 @@ void amdgpu_device_indirect_wreg(struct amdgpu_device *adev, u32 reg_addr,
> void __iomem *pcie_index_offset;
> void __iomem *pcie_data_offset;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
>
> @@ -784,6 +799,9 @@ void amdgpu_device_indirect_wreg_ext(struct amdgpu_device *adev, u64 reg_addr,
> void __iomem *pcie_index_hi_offset;
> void __iomem *pcie_data_offset;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
> if ((reg_addr >> 32) && (adev->nbio.funcs->get_pcie_index_hi_offset))
> @@ -832,6 +850,9 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, u32 reg_addr,
> void __iomem *pcie_index_offset;
> void __iomem *pcie_data_offset;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
>
> @@ -861,6 +882,9 @@ void amdgpu_device_indirect_wreg64_ext(struct amdgpu_device *adev, u64 reg_addr,
> void __iomem *pcie_index_hi_offset;
> void __iomem *pcie_data_offset;
>
> + if (amdgpu_device_skip_hw_access(adev))
> + return;
> +
> pcie_index = adev->nbio.funcs->get_pcie_index_offset(adev);
> pcie_data = adev->nbio.funcs->get_pcie_data_offset(adev);
> if ((reg_addr >> 32) && (adev->nbio.funcs->get_pcie_index_hi_offset))