We need to call amdgpu_vm_handle_fault() on page fault on all gfx9 and newer parts to properly update the page tables, not just for recoverable page faults.
Signed-off-by: Alex Deucher <[email protected]> --- drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 27 ++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c index cad2d19105c4c..43f8e96d3fe53 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c @@ -91,6 +91,8 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { struct amdgpu_vmhub *hub; + bool retry_fault = !!(entry->src_data[1] & 0x80); + bool write_fault = !!(entry->src_data[1] & 0x20); uint32_t status = 0; u64 addr; @@ -102,6 +104,31 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev, else hub = &adev->vmhub[AMDGPU_GFXHUB(0)]; + if (retry_fault) { + /* Returning 1 here also prevents sending the IV to the KFD */ + + /* Process it onyl if it's the first fault for this address */ + if (entry->ih != &adev->irq.ih_soft && + amdgpu_gmc_filter_faults(adev, entry->ih, addr, entry->pasid, + entry->timestamp)) + return 1; + + /* Delegate it to a different ring if the hardware hasn't + * already done it. + */ + if (entry->ih == &adev->irq.ih) { + amdgpu_irq_delegate(adev, entry, 8); + return 1; + } + + /* Try to handle the recoverable page faults by filling page + * tables + */ + if (amdgpu_vm_handle_fault(adev, entry->pasid, 0, 0, addr, + entry->timestamp, write_fault)) + return 1; + } + if (!amdgpu_sriov_vf(adev)) { /* * Issue a dummy read to wait for the status register to -- 2.51.1
