Normally scratch page is not allowed when a vm is operate under page fault mode, i.e., in the existing codes, DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE and DRM_XE_VM_CREATE_FLAG_FAULT_MODE are mutual exclusive. The reason is fault mode relies on recoverable page to work, while scratch page can mute recoverable page fault. On xe2 and xe3, out of bound prefetch can cause page fault and further system hang because xekmd can't resolve such page fault. SYCL and OCL language runtime requires out of bound prefetch to be silently dropped without causing any functional problem, thus the existing behavior doesn't meet language runtime requirement. At the same time, HW prefetching can cause page fault interrupt. Due to page fault interrupt overhead (i.e., need Guc and KMD involved to fix the page fault), HW prefetching can be slowed by many orders of magnitude. Fix those problems by allowing scratch page under fault mode for xe2 and xe3. With scratch page in place, HW prefetching could always hit scratch page instead of causing interrupt. A side effect is, scratch page could hide application program error. Application out of bound accesses are hided by scratch page mapping, instead of get reported to user. v2: Refine commit message (Thomas) v3: Move the scratch page flag check to after scratch page wa (Thomas) v4: drop NEEDS_SCRATCH macro (matt) Add a comment to DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE
Showing the changes to include/uapi (1 of 2 files). Show all
Unified · Split
| @@ -917,7 +917,11 @@ struct drm_xe_gem_mmap_offset { · 916 unmodified lines | |||
| 917 | * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE | 917 | * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE |
| 918 | * | 918 | * |
| 919 | * The @flags can be: | 919 | * The @flags can be: |
| 920 | * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE | 920 | * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE - Map the whole virtual address |
| 921 | * space of the VM to scratch page. A vm_bind would overwrite the scratch | ||
| 922 | * page mapping. This flag is mutually exclusive with the | ||
| 923 | * %DRM_XE_VM_CREATE_FLAG_FAULT_MODE flag, with an exception of on x2 and | ||
| 924 | * xe3 platform. | ||
| 921 | * - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts | 925 | * - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts |
| 922 | * exec submissions to its exec_queues that don't have an upper time | 926 | * exec submissions to its exec_queues that don't have an upper time |
| 923 | * limit on the job execution time. But exec submissions to these | 927 | * limit on the job execution time. But exec submissions to these |