From 34f3a4a98bd388ad6298c42dc9b00c72d3398330 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Thu, 9 Dec 2021 15:10:32 +0800 Subject: drm/amdgpu: introduce a kind of halt state for amdgpu device It is useful to maintain error context when debugging SW/FW issues. Introduce amdgpu_device_halt() for this purpose. It will bring hardware to a kind of halt state, so that no one can touch it any more. Compare to a simple hang, the system will keep stable at least for SSH access. Then it should be trivial to inspect the hardware state and see what's going on. v2: - Set adev->no_hw_access earlier to avoid potential crashes.(Christian) Suggested-by: Christian Koenig Suggested-by: Andrey Grodzovsky Signed-off-by: Lang Yu Reviewed-by: Christian Koenig Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 39 ++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'drivers/gpu/drm/amd') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 54c882a6b433..89278f17a70b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1317,6 +1317,8 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring); +void amdgpu_device_halt(struct amdgpu_device *adev); + /* atpx handler */ #if defined(CONFIG_VGA_SWITCHEROO) void amdgpu_register_atpx_handler(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 15e3f4473e23..c9b8e5d8b824 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5663,3 +5663,42 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, amdgpu_asic_invalidate_hdp(adev, ring); } + +/** + * amdgpu_device_halt() - bring hardware to some kind of halt state + * + * @adev: amdgpu_device pointer + * + * Bring hardware to some kind of halt state so that no one can touch it + * any more. It will help to maintain error context when error occurred. + * Compare to a simple hang, the system will keep stable at least for SSH + * access. Then it should be trivial to inspect the hardware state and + * see what's going on. Implemented as following: + * + * 1. drm_dev_unplug() makes device inaccessible to user space(IOCTLs, etc), + * clears all CPU mappings to device, disallows remappings through page faults + * 2. amdgpu_irq_disable_all() disables all interrupts + * 3. amdgpu_fence_driver_hw_fini() signals all HW fences + * 4. set adev->no_hw_access to avoid potential crashes after setp 5 + * 5. amdgpu_device_unmap_mmio() clears all MMIO mappings + * 6. pci_disable_device() and pci_wait_for_pending_transaction() + * flush any in flight DMA operations + */ +void amdgpu_device_halt(struct amdgpu_device *adev) +{ + struct pci_dev *pdev = adev->pdev; + struct drm_device *ddev = &adev->ddev; + + drm_dev_unplug(ddev); + + amdgpu_irq_disable_all(adev); + + amdgpu_fence_driver_hw_fini(adev); + + adev->no_hw_access = true; + + amdgpu_device_unmap_mmio(adev); + + pci_disable_device(pdev); + pci_wait_for_pending_transaction(pdev); +} -- cgit v1.2.3