mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00
736e785f9b
As we now protect the timeline list using RCU, we can drop the timeline->mutex for guarding the list iteration during context close, as we are searching for an inflight request. Any new request will see the context is banned and not be submitted. In doing so, pull the checks for a concurrent submission of the request (notably the i915_request_completed()) under the engine spinlock, to fully serialise with __i915_request_submit()). That is in the case of preempt-to-busy where the request may be completed during the __i915_request_submit(), we need to be careful that we sample the request status after serialising so that we don't miss the request the engine is actually submitting. Fixes: |
||
|---|---|---|
| .. | ||
| selftests | ||
| i915_gem_busy.c | ||
| i915_gem_clflush.c | ||
| i915_gem_clflush.h | ||
| i915_gem_client_blt.c | ||
| i915_gem_client_blt.h | ||
| i915_gem_context.c | ||
| i915_gem_context.h | ||
| i915_gem_context_types.h | ||
| i915_gem_dmabuf.c | ||
| i915_gem_domain.c | ||
| i915_gem_execbuffer.c | ||
| i915_gem_fence.c | ||
| i915_gem_internal.c | ||
| i915_gem_ioctls.h | ||
| i915_gem_lmem.c | ||
| i915_gem_lmem.h | ||
| i915_gem_mman.c | ||
| i915_gem_mman.h | ||
| i915_gem_object.c | ||
| i915_gem_object.h | ||
| i915_gem_object_blt.c | ||
| i915_gem_object_blt.h | ||
| i915_gem_object_types.h | ||
| i915_gem_pages.c | ||
| i915_gem_phys.c | ||
| i915_gem_pm.c | ||
| i915_gem_pm.h | ||
| i915_gem_region.c | ||
| i915_gem_region.h | ||
| i915_gem_shmem.c | ||
| i915_gem_shrinker.c | ||
| i915_gem_shrinker.h | ||
| i915_gem_stolen.c | ||
| i915_gem_stolen.h | ||
| i915_gem_throttle.c | ||
| i915_gem_tiling.c | ||
| i915_gem_userptr.c | ||
| i915_gem_wait.c | ||
| i915_gemfs.c | ||
| i915_gemfs.h | ||