linux-toradex.git/drivers/dma-buf/dma-fence.c, branch v6.8 Linux kernel for Apalis and Colibri modules dma-buf/sync_file: Add SET_DEADLINE ioctl 2023-12-01T23:17:48+00:00 Rob Clark robdclark@chromium.org 2023-08-23T21:54:55+00:00 63ee44540205d993854f143a5ab1d7d9e63ffcf1 The initial purpose is for igt tests, but this would also be useful for compositors that wait until close to vblank deadline to make decisions about which frame to show. The igt tests can be found at: https://gitlab.freedesktop.org/robclark/igt-gpu-tools/-/commits/fence-deadline v2: Clarify the timebase, add link to igt tests v3: Use u64 value in ns to express deadline. v4: More doc Signed-off-by: Rob Clark <robdclark@chromium.org> Acked-by: Pekka Paalanen <pekka.paalanen@collabora.com> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Link: https://patchwork.freedesktop.org/patch/msgid/20230823215458.203366-3-robdclark@gmail.com 
The initial purpose is for igt tests, but this would also be useful for
compositors that wait until close to vblank deadline to make decisions
about which frame to show.

The igt tests can be found at:

https://gitlab.freedesktop.org/robclark/igt-gpu-tools/-/commits/fence-deadline

v2: Clarify the timebase, add link to igt tests
v3: Use u64 value in ns to express deadline.
v4: More doc

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Pekka Paalanen <pekka.paalanen@collabora.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230823215458.203366-3-robdclark@gmail.com
dma-buf: fix an error pointer vs NULL bug 2023-07-06T14:20:23+00:00 Dan Carpenter dan.carpenter@linaro.org 2023-07-06T12:37:51+00:00 00ae1491f970acc454be0df63f50942d94825860 Smatch detected potential error pointer dereference. drivers/gpu/drm/drm_syncobj.c:888 drm_syncobj_transfer_to_timeline() error: 'fence' dereferencing possible ERR_PTR() The error pointer comes from dma_fence_allocate_private_stub(). One caller expected error pointers and one expected NULL pointers. Change it to return NULL and update the caller which expected error pointers, drm_syncobj_assign_null_handle(), to check for NULL instead. Fixes: f781f661e8c9 ("dma-buf: keep the signaling time of merged fences v3") Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Sumit Semwal <sumit.semwal@linaro.org> Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org> Link: https://patchwork.freedesktop.org/patch/msgid/b09f1996-3838-4fa2-9193-832b68262e43@moroto.mountain 
Smatch detected potential error pointer dereference.

    drivers/gpu/drm/drm_syncobj.c:888 drm_syncobj_transfer_to_timeline()
    error: 'fence' dereferencing possible ERR_PTR()

The error pointer comes from dma_fence_allocate_private_stub().  One
caller expected error pointers and one expected NULL pointers.  Change
it to return NULL and update the caller which expected error pointers,
drm_syncobj_assign_null_handle(), to check for NULL instead.

Fixes: f781f661e8c9 ("dma-buf: keep the signaling time of merged fences v3")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/b09f1996-3838-4fa2-9193-832b68262e43@moroto.mountain
dma-buf: keep the signaling time of merged fences v3 2023-07-03T11:47:06+00:00 Christian König christian.koenig@amd.com 2023-06-13T08:09:20+00:00 f781f661e8c99b0cb34129f2e374234d61864e77 Some Android CTS is testing if the signaling time keeps consistent during merges. v2: use the current time if the fence is still in the signaling path and the timestamp not yet available. v3: improve comment, fix one more case to use the correct timestamp Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Luben Tuikov <luben.tuikov@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230630120041.109216-1-christian.koenig@amd.com 
Some Android CTS is testing if the signaling time keeps consistent
during merges.

v2: use the current time if the fence is still in the signaling path and
the timestamp not yet available.
v3: improve comment, fix one more case to use the correct timestamp

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230630120041.109216-1-christian.koenig@amd.com
dma-buf/dma-fence: Add deadline awareness 2023-03-25T17:55:07+00:00 Rob Clark robdclark@chromium.org 2021-09-03T18:47:52+00:00 aec11c8d7cb31c67deeba4c9fe015d09735c6813 Add a way to hint to the fence signaler of an upcoming deadline, such as vblank, which the fence waiter would prefer not to miss. This is to aid the fence signaler in making power management decisions, like boosting frequency as the deadline approaches and awareness of missing deadlines so that can be factored in to the frequency scaling. v2: Drop dma_fence::deadline and related logic to filter duplicate deadlines, to avoid increasing dma_fence size. The fence-context implementation will need similar logic to track deadlines of all the fences on the same timeline. [ckoenig] v3: Clarify locking wrt. set_deadline callback v4: Clarify in docs comment that this is a hint v5: Drop DMA_FENCE_FLAG_HAS_DEADLINE_BIT. v6: More docs v7: Fix typo, clarify past deadlines Signed-off-by: Rob Clark <robdclark@chromium.org> Reviewed-by: Christian König <christian.koenig@amd.com> Acked-by: Pekka Paalanen <pekka.paalanen@collabora.com> Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com> 
Add a way to hint to the fence signaler of an upcoming deadline, such as
vblank, which the fence waiter would prefer not to miss.  This is to aid
the fence signaler in making power management decisions, like boosting
frequency as the deadline approaches and awareness of missing deadlines
so that can be factored in to the frequency scaling.

v2: Drop dma_fence::deadline and related logic to filter duplicate
    deadlines, to avoid increasing dma_fence size.  The fence-context
    implementation will need similar logic to track deadlines of all
    the fences on the same timeline.  [ckoenig]
v3: Clarify locking wrt. set_deadline callback
v4: Clarify in docs comment that this is a hint
v5: Drop DMA_FENCE_FLAG_HAS_DEADLINE_BIT.
v6: More docs
v7: Fix typo, clarify past deadlines

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Pekka Paalanen <pekka.paalanen@collabora.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
dma-buf: actually set signaling bit for private stub fences 2023-01-27T13:16:18+00:00 Danilo Krummrich dakr@redhat.com 2023-01-26T00:28:44+00:00 d2ceea0eb6e17bb37d8b85cb4c16797c0d683d1c In dma_fence_allocate_private_stub() set the signaling bit of the newly allocated private stub fence rather than the signaling bit of the shared dma_fence_stub. Cc: <stable@vger.kernel.org> # v6.1 Fixes: c85d00d4fd8b ("dma-buf: set signaling bit for the stub fence") Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Danilo Krummrich <dakr@redhat.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230126002844.339593-1-dakr@redhat.com 
In dma_fence_allocate_private_stub() set the signaling bit of the newly
allocated private stub fence rather than the signaling bit of the
shared dma_fence_stub.

Cc: <stable@vger.kernel.org> # v6.1
Fixes: c85d00d4fd8b ("dma-buf: set signaling bit for the stub fence")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230126002844.339593-1-dakr@redhat.com
dma-buf: fix dma_fence_default_wait() signaling check 2022-09-19T18:45:17+00:00 Christian König christian.koenig@amd.com 2022-09-19T12:00:33+00:00 3cc3dd73c420dc70cd366f91a680035ef47edf4f That check must now come after grabing the spinlock, not before. Signed-off-by: Christian König <christian.koenig@amd.com> Fixes: b96fb1e724ae ("dma-buf: dma_fence_wait must enable signaling") Acked-by: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220919120618.113332-1-christian.koenig@amd.com 
That check must now come after grabing the spinlock, not before.

Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: b96fb1e724ae ("dma-buf: dma_fence_wait must enable signaling")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220919120618.113332-1-christian.koenig@amd.com
dma-buf: dma_fence_wait must enable signaling 2022-09-16T13:53:25+00:00 Arvind Yadav Arvind.Yadav@amd.com 2022-09-14T16:43:19+00:00 b96fb1e724ae6839d5bffcf42dd3503db7cc7df5 dma_fence_wait() should always enable signaling even when the fence is already signaled. Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-5-Arvind.Yadav@amd.com Signed-off-by: Christian König <christian.koenig@amd.com> 
dma_fence_wait() should always enable signaling even
when the fence is already signaled.

Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-5-Arvind.Yadav@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
dma-buf: set signaling bit for the stub fence 2022-09-16T13:53:25+00:00 Arvind Yadav Arvind.Yadav@amd.com 2022-09-14T16:43:17+00:00 c85d00d4fd8b98ea4d16817f397a4de5e177afd6 Here's setting software signaling bit for the stub fence which is always signaled. If this fence signaling bit is not set then the AMD GPU scheduler will cause a GPU reset due to a GPU scheduler cleanup activity timeout. Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-3-Arvind.Yadav@amd.com Signed-off-by: Christian König <christian.koenig@amd.com> 
Here's setting software signaling bit for the stub fence
which is always signaled. If this fence signaling bit is
not set then the AMD GPU scheduler will cause a GPU reset
due to a GPU scheduler cleanup activity timeout.

Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-3-Arvind.Yadav@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
dma-buf: Remove the signaled bit status check 2022-09-16T13:53:20+00:00 Arvind Yadav Arvind.Yadav@amd.com 2022-09-14T16:43:16+00:00 6ad9aa476ce23be45de9dcb03edcdbfdf6117c25 Remove the signaled bit status check because it is returning early when the fence is already signaled and __dma_fence_enable_signaling is checking the status of signaled bit again. Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-2-Arvind.Yadav@amd.com Signed-off-by: Christian König <christian.koenig@amd.com> 
Remove the signaled bit status check because it is returning
early when the fence is already signaled and
__dma_fence_enable_signaling is checking the status of signaled
bit again.

Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220914164321.2156-2-Arvind.Yadav@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
dma-buf: add dma_fence_describe and dma_resv_describe v2 2021-11-11T08:35:13+00:00 Christian König christian.koenig@amd.com 2021-09-23T11:57:42+00:00 a25efb3863d068929f0bbeb87a995df11507e691 Add functions to dump dma_fence and dma_resv objects into a seq_file and use them for printing the debugfs information. v2: fix missing include reported by test robot. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Rob Clark <robdclark@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20211103081231.18578-2-christian.koenig@amd.com 
Add functions to dump dma_fence and dma_resv objects into a seq_file and
use them for printing the debugfs information.

v2: fix missing include reported by test robot.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211103081231.18578-2-christian.koenig@amd.com