xe_vma_need_vram_for_atomic(9)
β¨ xe_vma_need_vram_for_atomic(9) β¨
okay so bestie, we're in the Kernel API Manual and this page is literally about xe_vma_need_vram_for_atomic(9) β the title is right there, we're being efficient π
πΈ NAME πΈ
xe_vma_need_vram_for_atomic β check if VMA needs VRAM migration for atomic operations. That's the whole vibe check, no cap.
β SYNOPSIS β
int xe_vma_need_vram_for_atomic (struct xe_device *xe , struct xe_vma
*vma , bool is_atomic );
π ARGUMENTS π
Here's the cast, and yes they're all main characters:
xeβ Pointer to the Xe device structure.vmaβ Pointer to the virtual memory area (VMA) structure.is_atomicβ In pagefault path and atomic operation.
π DESCRIPTION π
This function determines whether the given VMA needs to be migrated to VRAM in order to do atomic GPU operation. So it's the "do we need to move this VMA to VRAM for this atomic GPU operation?" gatekeeper, and it hands you back a return value instead of just β¨vibesβ¨.
π RETURN π
1β Migration to VRAM is required.0β Migration is not required.-EACCESβ Invalid access for atomic memory attr.
π¦ SEE ALSO π¦
Kernel file: ./drivers/gpu/drm/xe/xe_vm.c β and here's the whole friend group, zero skips:
xe_vm_drm_exec_lock(9)xe_vm_remove_compute_exec_queue(9)xe_vm_kill(9)xe_vm_validate_rebind(9)xe_vm_bump_lru(9)xe_vm_resume_rebind_worker(9)xe_vm_add_fault_entry_pf(9)xe_vm_range_rebind(9)xe_vm_range_unbind(9)xe_vma_mem_attr_copy(9)xe_vm_lock_vma(9)xe_vm_create_scratch(9)xe_vm_find_vma_by_addr(9)xe_vma_has_default_mem_attrs(9)struct xe_vma_lock_and_validate_flags(9)xe_vm_bind_kernel_bo(9)xe_vm_lock(9)xe_vm_unlock(9)xe_vm_invalidate_vma_submit(9)xe_vm_invalidate_vma(9)xe_vm_alloc_madvise_vma(9)xe_vm_find_cpu_addr_mirror_vma_range(9)xe_vm_alloc_cpu_addr_mirror_vma(9)xe_vm_add_exec_queue(9)xe_vm_remove_exec_queue(9)
xoxo, signing off from the source/version ./drivers/gpu/drm/xe, dated October 2026, on page xe_vma_need_vram_for_atomic(9) π«Άπ
β¨
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms