Documentation/driver-api/dma-buf.rst

21  - dma-resv, which manages a set of dma-fences for a particular dma-buf
169    :doc: DMA fences overview
243 * Future fences, used in HWC1 to signal when a buffer isn't used by the display
247 * Proxy fences, proposed to handle &drm_syncobj for which the fence has not yet
250 * Userspace fences or gpu futexes, fine-grained locking within a command buffer
256   batch DMA fences for memory management instead of context preemption DMA
257   fences which get reattached when the compute job is rescheduled.
260 fences and controls when they fire. Mixing indefinite fences with normal
261 in-kernel DMA fences does not work, even when a fallback timeout is included to
267 * Only userspace knows about all dependencies in indefinite fences and when
271 for memory management needs, which means we must support indefinite fences being
272 dependent upon DMA fences. If the kernel also support indefinite fences in the
283       userspace [label="userspace controlled fences"]
298 fences in the kernel. This means:
300 * No future fences, proxy fences or userspace fences imported as DMA fences,
303 * No DMA fences that signal end of batchbuffer for command submission where
312 implications for DMA fences.
316 But memory allocations are not allowed to gate completion of DMA fences, which
317 means any workload using recoverable page faults cannot use DMA fences for
318 synchronization. Synchronization fences controlled by userspace must be used
322 Linux rely on DMA fences, which means without an entirely new userspace stack
323 built on top of userspace fences, they cannot benefit from recoverable page
358   requiring DMA fences or jobs requiring page fault handling: This means all DMA
359   fences must complete before a compute job with page fault handling can be
367   fences. This results very wide impact on the kernel, since resolving the page
373 GPUs do not have any impact. This allows us to keep using DMA fences internally
378 Fences` discussions: Infinite fences from compute workloads are allowed to
379 depend on DMA fences, but not the other way around. And not even the page fault