bianbu-linux-6.6/drivers/gpu/drm/i915/gem
Chris Wilson d19d71fc2b drm/i915: Mark i915_request.timeline as a volatile, rcu pointer
The request->timeline is only valid until the request is retired (i.e.
before it is completed). Upon retiring the request, the context may be
unpinned and freed, and along with it the timeline may be freed. We
therefore need to be very careful when chasing rq->timeline that the
pointer does not disappear beneath us. The vast majority of users are in
a protected context, either during request construction or retirement,
where the timeline->mutex is held and the timeline cannot disappear. It
is those few off the beaten path (where we access a second timeline) that
need extra scrutiny -- to be added in the next patch after first adding
the warnings about dangerous access.

One complication, where we cannot use the timeline->mutex itself, is
during request submission onto hardware (under spinlocks). Here, we want
to check on the timeline to finalize the breadcrumb, and so we need to
impose a second rule to ensure that the request->timeline is indeed
valid. As we are submitting the request, it's context and timeline must
be pinned, as it will be used by the hardware. Since it is pinned, we
know the request->timeline must still be valid, and we cannot submit the
idle barrier until after we release the engine->active.lock, ergo while
submitting and holding that spinlock, a second thread cannot release the
timeline.

v2: Don't be lazy inside selftests; hold the timeline->mutex for as long
as we need it, and tidy up acquiring the timeline with a bit of
refactoring (i915_active_add_request)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919111912.21631-1-chris@chris-wilson.co.uk
2019-09-20 10:24:09 +01:00
..
selftests drm/i915/selftests: Tighten the timeout testing for partial mmaps 2019-09-10 14:04:46 +01:00
i915_gem_busy.c dma-buf: Restore seqlock around dma_resv updates 2019-08-16 12:40:58 +01:00
i915_gem_clflush.c drm/i915: Generalise the clflush dma-worker 2019-08-22 08:27:44 +01:00
i915_gem_clflush.h drm/i915: Move more GEM objects under gem/ 2019-05-28 12:45:29 +01:00
i915_gem_client_blt.c drm/i915: Mark i915_request.timeline as a volatile, rcu pointer 2019-09-20 10:24:09 +01:00
i915_gem_client_blt.h drm/i915: add in-kernel blitter client 2019-05-30 12:01:44 +01:00
i915_gem_context.c drm/i915: Mark i915_request.timeline as a volatile, rcu pointer 2019-09-20 10:24:09 +01:00
i915_gem_context.h drm/i915: Remove i915_gem_context_create_gvt() 2019-08-09 20:18:30 +01:00
i915_gem_context_types.h drm/i915: Push the ring creation flags to the backend 2019-08-09 20:18:30 +01:00
i915_gem_dmabuf.c dma-buf: rename reservation_object to dma_resv 2019-08-13 09:09:30 +02:00
i915_gem_domain.c drm/i915: Make shrink/unshrink be atomic 2019-09-11 08:14:23 +01:00
i915_gem_execbuffer.c drm/i915: use a separate context for gpu relocs 2019-08-27 21:14:43 +01:00
i915_gem_fence.c Merge drm/drm-next into drm-intel-next-queued 2019-08-22 00:10:36 -07:00
i915_gem_internal.c drm/i915: Pull scatterlist utils out of i915_gem.h 2019-05-28 12:45:29 +01:00
i915_gem_ioctls.h
i915_gem_mman.c drm/i915: Don't mix srcu tag and negative error codes 2019-09-13 15:07:34 +01:00
i915_gem_object.c drm/i915: Make i915_vma.flags atomic_t for mutex reduction 2019-09-11 13:39:42 +01:00
i915_gem_object.h drm/i915: Replace obj->pin_global with obj->frontbuffer 2019-09-03 05:39:37 +01:00
i915_gem_object_blt.c drm/i915: Make engine's batch pool safe for use with virtual engines 2019-08-27 16:42:12 +01:00
i915_gem_object_blt.h drm/i915/blt: support copying objects 2019-08-10 19:35:36 +01:00
i915_gem_object_types.h drm/i915: Make shrink/unshrink be atomic 2019-09-11 08:14:23 +01:00
i915_gem_pages.c drm/i915: Make shrink/unshrink be atomic 2019-09-11 08:14:23 +01:00
i915_gem_phys.c drm/i915: Free the imported shmemfs file for phys objects 2019-08-09 13:32:29 +01:00
i915_gem_pm.c drm/i915/pmu: Use GT parked for estimating RC6 while asleep 2019-09-12 17:02:50 +01:00
i915_gem_pm.h drm/i915: Move more GEM objects under gem/ 2019-05-28 12:45:29 +01:00
i915_gem_shmem.c drm/i915: avoid including intel_drv.h via i915_drv.h->i915_trace.h 2019-08-07 12:43:14 +03:00
i915_gem_shrinker.c drm/i915: Make shrink/unshrink be atomic 2019-09-11 08:14:23 +01:00
i915_gem_shrinker.h drm/i915: extract i915_gem_shrinker.h from i915_drv.h 2019-08-09 12:03:32 +03:00
i915_gem_stolen.c drm/i915: Make i915_vma.flags atomic_t for mutex reduction 2019-09-11 13:39:42 +01:00
i915_gem_stolen.h drm/i915: extract gem/i915_gem_stolen.h from i915_drv.h 2019-08-09 12:03:29 +03:00
i915_gem_throttle.c drm/i915: Keep drm_i915_file_private around under RCU 2019-08-23 22:13:17 +01:00
i915_gem_tiling.c drm/i915: disable set/get_tiling ioctl on gen12+ 2019-09-04 12:31:12 -07:00
i915_gem_userptr.c drm/i915: remove unnecessary includes of intel_display_types.h header 2019-08-07 12:43:55 +03:00
i915_gem_wait.c dma-buf: rename reservation_object to dma_resv 2019-08-13 09:09:30 +02:00
i915_gemfs.c drm/i915: Stop reconfiguring our shmemfs mountpoint 2019-08-09 20:18:30 +01:00
i915_gemfs.h drm/i915: Move more GEM objects under gem/ 2019-05-28 12:45:29 +01:00
Makefile drm/i915: use upstream version of header tests 2019-07-30 12:11:57 +03:00