1 ===========================
2 drm/i915 Intel GFX Driver
3 ===========================
5 The drm/i915 driver supports all (with the exception of some very early
6 models) integrated GFX chipsets with both Intel display and rendering
7 blocks. This excludes a set of SoC platforms with an SGX rendering unit,
8 those have basic support through the gma500 drm driver.
10 Core Driver Infrastructure
11 ==========================
13 This section covers core driver infrastructure used by both the display
14 and the GEM parts of the driver.
16 Runtime Power Management
17 ------------------------
19 .. kernel-doc:: drivers/gpu/drm/i915/intel_runtime_pm.c
22 .. kernel-doc:: drivers/gpu/drm/i915/intel_runtime_pm.c
25 .. kernel-doc:: drivers/gpu/drm/i915/intel_uncore.c
31 .. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
32 :doc: interrupt handling
34 .. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
35 :functions: intel_irq_init intel_irq_init_hw intel_hpd_init
37 .. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
38 :functions: intel_runtime_pm_disable_interrupts
40 .. kernel-doc:: drivers/gpu/drm/i915/i915_irq.c
41 :functions: intel_runtime_pm_enable_interrupts
43 Intel GVT-g Guest Support(vGPU)
44 -------------------------------
46 .. kernel-doc:: drivers/gpu/drm/i915/i915_vgpu.c
47 :doc: Intel GVT-g guest support
49 .. kernel-doc:: drivers/gpu/drm/i915/i915_vgpu.c
52 Intel GVT-g Host Support(vGPU device model)
53 -------------------------------------------
55 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
56 :doc: Intel GVT-g host support
58 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
64 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_workarounds.c
65 :doc: Hardware workarounds
67 Display Hardware Handling
68 =========================
70 This section covers everything related to the display hardware including
71 the mode setting infrastructure, plane, sprite and cursor handling and
72 display, output probing and related topics.
74 Mode Setting Infrastructure
75 ---------------------------
77 The i915 driver is thus far the only DRM driver which doesn't use the
78 common DRM helper code to implement mode setting sequences. Thus it has
79 its own tailor-made infrastructure for executing a display configuration
85 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_frontbuffer.c
86 :doc: frontbuffer tracking
88 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_frontbuffer.h
91 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_frontbuffer.c
94 Display FIFO Underrun Reporting
95 -------------------------------
97 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_fifo_underrun.c
98 :doc: fifo underrun handling
100 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_fifo_underrun.c
106 This section covers plane configuration and composition with the primary
107 plane, sprites, cursors and overlays. This includes the infrastructure
108 to do atomic vsync'ed updates of all this state and also tightly coupled
109 topics like watermark setup and computation, framebuffer compression and
115 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_atomic_plane.c
116 :doc: atomic plane helpers
118 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_atomic_plane.c
121 Asynchronous Page Flip
122 ----------------------
124 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_display.c
125 :doc: asynchronous flip implementation
130 This section covers output probing and related infrastructure like the
131 hotplug interrupt storm detection and mitigation code. Note that the
132 i915 driver still uses most of the common DRM helper code for output
133 probing, so those sections fully apply.
138 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_hotplug.c
141 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_hotplug.c
144 High Definition Audio
145 ---------------------
147 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_audio.c
148 :doc: High Definition Audio over HDMI and Display Port
150 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_audio.c
153 .. kernel-doc:: include/drm/i915_component.h
156 Intel HDMI LPE Audio Support
157 ----------------------------
159 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_lpe_audio.c
160 :doc: LPE Audio integration for HDMI or DP playback
162 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_lpe_audio.c
165 Panel Self Refresh PSR (PSR/SRD)
166 --------------------------------
168 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_psr.c
169 :doc: Panel Self Refresh (PSR/SRD)
171 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_psr.c
174 Frame Buffer Compression (FBC)
175 ------------------------------
177 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_fbc.c
178 :doc: Frame Buffer Compression (FBC)
180 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_fbc.c
183 Display Refresh Rate Switching (DRRS)
184 -------------------------------------
186 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
187 :doc: Display Refresh Rate Switching (DRRS)
189 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
195 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dpio_phy.c
201 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dmc.c
202 :doc: DMC Firmware Support
204 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dmc.c
207 Video BIOS Table (VBT)
208 ----------------------
210 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_bios.c
211 :doc: Video BIOS Table (VBT)
213 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_bios.c
216 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_vbt_defs.h
222 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_cdclk.c
225 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_cdclk.c
231 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dpll_mgr.c
234 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dpll_mgr.c
237 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dpll_mgr.h
243 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dsb.c
246 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dsb.c
252 Multicast/Replicated (MCR) Registers
253 ------------------------------------
255 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_gt_mcr.c
256 :doc: GT Multicast/Replicated (MCR) Register Support
258 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_gt_mcr.c
261 Memory Management and Command Submission
262 ========================================
264 This sections covers all things related to the GEM implementation in the
270 An Intel GPU has multiple engines. There are several engine types.
272 - RCS engine is for rendering 3D and performing compute, this is named
273 `I915_EXEC_RENDER` in user space.
274 - BCS is a blitting (copy) engine, this is named `I915_EXEC_BLT` in user
276 - VCS is a video encode and decode engine, this is named `I915_EXEC_BSD`
278 - VECS is video enhancement engine, this is named `I915_EXEC_VEBOX` in user
280 - The enumeration `I915_EXEC_DEFAULT` does not refer to specific engine;
281 instead it is to be used by user space to specify a default rendering
282 engine (for 3D) that may or may not be the same as RCS.
284 The Intel GPU family is a family of integrated GPU's using Unified
285 Memory Access. For having the GPU "do work", user space will feed the
286 GPU batch buffers via one of the ioctls `DRM_IOCTL_I915_GEM_EXECBUFFER2`
287 or `DRM_IOCTL_I915_GEM_EXECBUFFER2_WR`. Most such batchbuffers will
288 instruct the GPU to perform work (for example rendering) and that work
289 needs memory from which to read and memory to which to write. All memory
290 is encapsulated within GEM buffer objects (usually created with the ioctl
291 `DRM_IOCTL_I915_GEM_CREATE`). An ioctl providing a batchbuffer for the GPU
292 to create will also list all GEM buffer objects that the batchbuffer reads
293 and/or writes. For implementation details of memory management see
294 `GEM BO Management Implementation Details`_.
296 The i915 driver allows user space to create a context via the ioctl
297 `DRM_IOCTL_I915_GEM_CONTEXT_CREATE` which is identified by a 32-bit
298 integer. Such a context should be viewed by user-space as -loosely-
299 analogous to the idea of a CPU process of an operating system. The i915
300 driver guarantees that commands issued to a fixed context are to be
301 executed so that writes of a previously issued command are seen by
302 reads of following commands. Actions issued between different contexts
303 (even if from the same file descriptor) are NOT given that guarantee
304 and the only way to synchronize across contexts (even from the same
305 file descriptor) is through the use of fences. At least as far back as
306 Gen4, also have that a context carries with it a GPU HW context;
307 the HW context is essentially (most of atleast) the state of a GPU.
308 In addition to the ordering guarantees, the kernel will restore GPU
309 state via HW context when commands are issued to a context, this saves
310 user space the need to restore (most of atleast) the GPU state at the
311 start of each batchbuffer. The non-deprecated ioctls to submit batchbuffer
312 work can pass that ID (in the lower bits of drm_i915_gem_execbuffer2::rsvd1)
313 to identify what context to use with the command.
315 The GPU has its own memory management and address space. The kernel
316 driver maintains the memory translation table for the GPU. For older
317 GPUs (i.e. those before Gen8), there is a single global such translation
318 table, a global Graphics Translation Table (GTT). For newer generation
319 GPUs each context has its own translation table, called Per-Process
320 Graphics Translation Table (PPGTT). Of important note, is that although
321 PPGTT is named per-process it is actually per context. When user space
322 submits a batchbuffer, the kernel walks the list of GEM buffer objects
323 used by the batchbuffer and guarantees that not only is the memory of
324 each such GEM buffer object resident but it is also present in the
325 (PP)GTT. If the GEM buffer object is not yet placed in the (PP)GTT,
326 then it is given an address. Two consequences of this are: the kernel
327 needs to edit the batchbuffer submitted to write the correct value of
328 the GPU address when a GEM BO is assigned a GPU address and the kernel
329 might evict a different GEM BO from the (PP)GTT to make address room
330 for another GEM BO. Consequently, the ioctls submitting a batchbuffer
331 for execution also include a list of all locations within buffers that
332 refer to GPU-addresses so that the kernel can edit the buffer correctly.
333 This process is dubbed relocation.
339 This is a description of how the locking should be after
340 refactoring is done. Does not necessarily reflect what the locking
341 looks like while WIP.
343 #. All locking rules and interface contracts with cross-driver interfaces
344 (dma-buf, dma_fence) need to be followed.
346 #. No struct_mutex anywhere in the code
348 #. dma_resv will be the outermost lock (when needed) and ww_acquire_ctx
349 is to be hoisted at highest level and passed down within i915_gem_ctx
352 #. While holding lru/memory manager (buddy, drm_mm, whatever) locks
353 system memory allocations are not allowed
355 * Enforce this by priming lockdep (with fs_reclaim). If we
356 allocate memory while holding these looks we get a rehash
357 of the shrinker vs. struct_mutex saga, and that would be
360 #. Do not nest different lru/memory manager locks within each other.
361 Take them in turn to update memory allocations, relying on the object’s
362 dma_resv ww_mutex to serialize against other operations.
364 #. The suggestion for lru/memory managers locks is that they are small
365 enough to be spinlocks.
367 #. All features need to come with exhaustive kernel selftests and/or
368 IGT tests when appropriate
370 #. All LMEM uAPI paths need to be fully restartable (_interruptible()
371 for all locks/waits/sleeps)
373 * Error handling validation through signal injection.
374 Still the best strategy we have for validating GEM uAPI
376 Must be excessively used in the IGT, and we need to check
377 that we really have full path coverage of all error cases.
379 * -EDEADLK handling with ww_mutex
381 GEM BO Management Implementation Details
382 ----------------------------------------
384 .. kernel-doc:: drivers/gpu/drm/i915/i915_vma_types.h
385 :doc: Virtual Memory Address
387 Buffer Object Eviction
388 ----------------------
390 This section documents the interface functions for evicting buffer
391 objects to make space available in the virtual gpu address spaces. Note
392 that this is mostly orthogonal to shrinking buffer objects caches, which
393 has the goal to make main memory (shared with the gpu through the
394 unified memory architecture) available.
396 .. kernel-doc:: drivers/gpu/drm/i915/i915_gem_evict.c
399 Buffer Object Memory Shrinking
400 ------------------------------
402 This section documents the interface function for shrinking memory usage
403 of buffer object caches. Shrinking is used to make main memory
404 available. Note that this is mostly orthogonal to evicting buffer
405 objects, which has the goal to make space in gpu virtual address spaces.
407 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
413 .. kernel-doc:: drivers/gpu/drm/i915/i915_cmd_parser.c
414 :doc: batch buffer command parser
416 .. kernel-doc:: drivers/gpu/drm/i915/i915_cmd_parser.c
419 User Batchbuffer Execution
420 --------------------------
422 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_context_types.h
424 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
425 :doc: User command execution
429 .. kernel-doc:: drivers/gpu/drm/i915/i915_scheduler_types.h
430 :functions: i915_sched_engine
432 Logical Rings, Logical Ring Contexts and Execlists
433 --------------------------------------------------
435 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_execlists_submission.c
436 :doc: Logical Rings, Logical Ring Contexts and Execlists
441 .. kernel-doc:: drivers/gpu/drm/i915/i915_vma_types.h
442 :doc: Global GTT views
444 .. kernel-doc:: drivers/gpu/drm/i915/i915_gem_gtt.c
447 GTT Fences and Swizzling
448 ------------------------
450 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
453 Global GTT Fence Handling
454 ~~~~~~~~~~~~~~~~~~~~~~~~~
456 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
457 :doc: fence register handling
459 Hardware Tiling and Swizzling Details
460 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
462 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
463 :doc: tiling swizzling details
468 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_tiling.c
471 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_tiling.c
472 :doc: buffer object tiling
477 .. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp.c
480 .. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp_types.h
485 Starting from gen9, three microcontrollers are available on the HW: the
486 graphics microcontroller (GuC), the HEVC/H.265 microcontroller (HuC) and the
487 display microcontroller (DMC). The driver is responsible for loading the
488 firmwares on the microcontrollers; the GuC and HuC firmwares are transferred
489 to WOPCM using the DMA engine, while the DMC firmware is written through MMIO.
497 .. kernel-doc:: drivers/gpu/drm/i915/gt/intel_wopcm.c
503 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
506 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.h
511 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
512 :doc: Firmware Layout
514 GuC Memory Management
515 ~~~~~~~~~~~~~~~~~~~~~
517 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
518 :doc: GuC Memory Management
519 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
520 :functions: intel_guc_allocate_vma
523 GuC-specific firmware loader
524 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
526 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
529 GuC-based command submission
530 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
532 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
533 :doc: GuC-based command submission
536 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
538 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_messages_abi.h
539 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h
540 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h
541 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h
542 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h
546 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
548 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
549 :functions: intel_huc_auth
551 HuC Memory Management
552 ~~~~~~~~~~~~~~~~~~~~~
554 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
555 :doc: HuC Memory Management
559 The HuC FW layout is the same as the GuC one, see `GuC Firmware Layout`_
563 See `DMC Firmware Support`_
568 This sections covers all things related to the tracepoints implemented
571 i915_ppgtt_create and i915_ppgtt_release
572 ----------------------------------------
574 .. kernel-doc:: drivers/gpu/drm/i915/i915_trace.h
575 :doc: i915_ppgtt_create and i915_ppgtt_release tracepoints
577 i915_context_create and i915_context_free
578 -----------------------------------------
580 .. kernel-doc:: drivers/gpu/drm/i915/i915_trace.h
581 :doc: i915_context_create and i915_context_free tracepoints
588 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
589 :doc: i915 Perf Overview
591 Comparison with Core Perf
592 -------------------------
593 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
594 :doc: i915 Perf History and Comparison with Core Perf
596 i915 Driver Entry Points
597 ------------------------
599 This section covers the entrypoints exported outside of i915_perf.c to
600 integrate with drm/i915 and to handle the `DRM_I915_PERF_OPEN` ioctl.
602 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
603 :functions: i915_perf_init
604 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
605 :functions: i915_perf_fini
606 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
607 :functions: i915_perf_register
608 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
609 :functions: i915_perf_unregister
610 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
611 :functions: i915_perf_open_ioctl
612 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
613 :functions: i915_perf_release
614 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
615 :functions: i915_perf_add_config_ioctl
616 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
617 :functions: i915_perf_remove_config_ioctl
622 This section covers the stream-semantics-agnostic structures and functions
623 for representing an i915 perf stream FD and associated file operations.
625 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
626 :functions: i915_perf_stream
627 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
628 :functions: i915_perf_stream_ops
630 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
631 :functions: read_properties_unlocked
632 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
633 :functions: i915_perf_open_ioctl_locked
634 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
635 :functions: i915_perf_destroy_locked
636 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
637 :functions: i915_perf_read
638 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
639 :functions: i915_perf_ioctl
640 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
641 :functions: i915_perf_enable_locked
642 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
643 :functions: i915_perf_disable_locked
644 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
645 :functions: i915_perf_poll
646 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
647 :functions: i915_perf_poll_locked
649 i915 Perf Observation Architecture Stream
650 -----------------------------------------
652 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
653 :functions: i915_oa_ops
655 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
656 :functions: i915_oa_stream_init
657 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
658 :functions: i915_oa_read
659 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
660 :functions: i915_oa_stream_enable
661 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
662 :functions: i915_oa_stream_disable
663 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
664 :functions: i915_oa_wait_unlocked
665 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
666 :functions: i915_oa_poll_wait
668 Other i915 Perf Internals
669 -------------------------
671 This section simply includes all other currently documented i915 perf internals,
672 in no particular order, but may include some more minor utilities or platform
673 specific details than found in the more high-level sections.
675 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
684 i915_perf_add_config_ioctl
685 i915_perf_remove_config_ioctl
686 read_properties_unlocked
687 i915_perf_open_ioctl_locked
688 i915_perf_destroy_locked
689 i915_perf_read i915_perf_ioctl
690 i915_perf_enable_locked
691 i915_perf_disable_locked
692 i915_perf_poll i915_perf_poll_locked
693 i915_oa_stream_init i915_oa_read
694 i915_oa_stream_enable
695 i915_oa_stream_disable
696 i915_oa_wait_unlocked
702 The drm/i915 driver codebase has some style rules in addition to (and, in some
703 cases, deviating from) the kernel coding style.
705 Register macro definition style
706 -------------------------------
708 The style guide for ``i915_reg.h``.
710 .. kernel-doc:: drivers/gpu/drm/i915/i915_reg.h
711 :doc: The i915 register macro definition style guide
713 .. _i915-usage-stats:
715 i915 DRM client usage stats implementation
716 ==========================================
718 The drm/i915 driver implements the DRM client usage stats specification as
719 documented in :ref:`drm-client-usage-stats`.
721 Example of the output showing the implemented key value pairs and entirety of
722 the currently possible format options:
730 drm-pdev: 0000:00:02.0
732 drm-engine-render: 9288864723 ns
733 drm-engine-copy: 2035071108 ns
734 drm-engine-video: 0 ns
735 drm-engine-capacity-video: 2
736 drm-engine-video-enhance: 0 ns
738 Possible `drm-engine-` key names are: `render`, `copy`, `video` and