|author||Linus Torvalds <email@example.com>||2016-03-25 08:48:31 -0700|
|committer||Linus Torvalds <firstname.lastname@example.org>||2016-03-25 08:48:31 -0700|
|parent||Merge tag 'asm-generic-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic (diff)|
|parent||Merge branch 'drm-next-4.6' of git://people.freedesktop.org/~agd5f/linux into drm-next (diff)|
Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes from Dave Airlie: "Just a couple of dma-buf related fixes and some amdgpu fixes, along with a regression fix for radeon off but default feature, but makes my 30" monitor happy again" * 'drm-next' of git://people.freedesktop.org/~airlied/linux: drm/radeon/mst: cleanup code indentation drm/radeon/mst: fix regression in lane/link handling. drm/amdgpu: add invalidate_page callback for userptrs drm/amdgpu: Revert "remove the userptr rmn->lock" drm/amdgpu: clean up path handling for powerplay drm/amd/powerplay: fix memory leak of tdp_table dma-buf/fence: fix fence_is_later v2 dma-buf: Update docs for SYNC ioctl drm: remove excess description dma-buf, drm, ion: Propagate error code from dma_buf_start_cpu_access() drm/atmel-hlcdc: use helper to get crtc state drm/atomic: use helper to get crtc state
Diffstat (limited to 'Documentation')
1 files changed, 6 insertions, 5 deletions
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index 32ac32e773e1..ca44c5820585 100644
@@ -352,7 +352,8 @@ Being able to mmap an export dma-buf buffer object has 2 main use-cases:
No special interfaces, userspace simply calls mmap on the dma-buf fd, making
sure that the cache synchronization ioctl (DMA_BUF_IOCTL_SYNC) is *always*
- used when the access happens. This is discussed next paragraphs.
+ used when the access happens. Note that DMA_BUF_IOCTL_SYNC can fail with
+ -EAGAIN or -EINTR, in which case it must be restarted.
Some systems might need some sort of cache coherency management e.g. when
CPU and GPU domains are being accessed through dma-buf at the same time. To
@@ -366,10 +367,10 @@ Being able to mmap an export dma-buf buffer object has 2 main use-cases:
want (with the new data being consumed by the GPU or say scanout device)
- munmap once you don't need the buffer any more
- Therefore, for correctness and optimal performance, systems with the memory
- cache shared by the GPU and CPU i.e. the "coherent" and also the
- "incoherent" are always required to use SYNC_START and SYNC_END before and
- after, respectively, when accessing the mapped address.
+ For correctness and optimal performance, it is always required to use
+ SYNC_START and SYNC_END before and after, respectively, when accessing the
+ mapped address. Userspace cannot rely on coherent access, even when there
+ are systems where it just works without calling these ioctls.
2. Supporting existing mmap interfaces in importers