| Message ID | 20211013204231.19287-23-matthew.brost@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Parallel submission aka multi-bb execbuf | expand |
On 10/13/2021 13:42, Matthew Brost wrote: > If an object in the excl or shared slot is a composite fence from a > parallel submit and the current request in the conflict tracking is from > the same parallel context there is no need to enforce ordering as the > ordering is already implicit. Make the request conflict tracking > understand this by comparing a parallel submit's parent context and > skipping conflict insertion if the values match. > > v2: > (John Harrison) > - Reword commit message > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> > --- > drivers/gpu/drm/i915/i915_request.c | 43 +++++++++++++++++++---------- > 1 file changed, 29 insertions(+), 14 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c > index 8bdf9f2f9b90..820a1f38b271 100644 > --- a/drivers/gpu/drm/i915/i915_request.c > +++ b/drivers/gpu/drm/i915/i915_request.c > @@ -1335,6 +1335,25 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence) > return err; > } > > +static inline bool is_parallel_rq(struct i915_request *rq) > +{ > + return intel_context_is_parallel(rq->context); > +} > + > +static inline struct intel_context *request_to_parent(struct i915_request *rq) > +{ > + return intel_context_to_parent(rq->context); > +} > + > +static bool is_same_parallel_context(struct i915_request *to, > + struct i915_request *from) > +{ > + if (is_parallel_rq(to)) > + return request_to_parent(to) == request_to_parent(from); > + > + return false; > +} > + > int > i915_request_await_execution(struct i915_request *rq, > struct dma_fence *fence) > @@ -1366,11 +1385,14 @@ i915_request_await_execution(struct i915_request *rq, > * want to run our callback in all cases. > */ > > - if (dma_fence_is_i915(fence)) > + if (dma_fence_is_i915(fence)) { > + if (is_same_parallel_context(rq, to_request(fence))) > + continue; > ret = __i915_request_await_execution(rq, > to_request(fence)); > - else > + } else { > ret = i915_request_await_external(rq, fence); > + } > if (ret < 0) > return ret; > } while (--nchild); > @@ -1471,10 +1493,13 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) > fence)) > continue; > > - if (dma_fence_is_i915(fence)) > + if (dma_fence_is_i915(fence)) { > + if (is_same_parallel_context(rq, to_request(fence))) > + continue; > ret = i915_request_await_request(rq, to_request(fence)); > - else > + } else { > ret = i915_request_await_external(rq, fence); > + } > if (ret < 0) > return ret; > > @@ -1525,16 +1550,6 @@ i915_request_await_object(struct i915_request *to, > return ret; > } > > -static inline bool is_parallel_rq(struct i915_request *rq) > -{ > - return intel_context_is_parallel(rq->context); > -} > - > -static inline struct intel_context *request_to_parent(struct i915_request *rq) > -{ > - return intel_context_to_parent(rq->context); > -} > - > static struct i915_request * > __i915_request_ensure_parallel_ordering(struct i915_request *rq, > struct intel_timeline *timeline)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 8bdf9f2f9b90..820a1f38b271 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1335,6 +1335,25 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence) return err; } +static inline bool is_parallel_rq(struct i915_request *rq) +{ + return intel_context_is_parallel(rq->context); +} + +static inline struct intel_context *request_to_parent(struct i915_request *rq) +{ + return intel_context_to_parent(rq->context); +} + +static bool is_same_parallel_context(struct i915_request *to, + struct i915_request *from) +{ + if (is_parallel_rq(to)) + return request_to_parent(to) == request_to_parent(from); + + return false; +} + int i915_request_await_execution(struct i915_request *rq, struct dma_fence *fence) @@ -1366,11 +1385,14 @@ i915_request_await_execution(struct i915_request *rq, * want to run our callback in all cases. */ - if (dma_fence_is_i915(fence)) + if (dma_fence_is_i915(fence)) { + if (is_same_parallel_context(rq, to_request(fence))) + continue; ret = __i915_request_await_execution(rq, to_request(fence)); - else + } else { ret = i915_request_await_external(rq, fence); + } if (ret < 0) return ret; } while (--nchild); @@ -1471,10 +1493,13 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence) fence)) continue; - if (dma_fence_is_i915(fence)) + if (dma_fence_is_i915(fence)) { + if (is_same_parallel_context(rq, to_request(fence))) + continue; ret = i915_request_await_request(rq, to_request(fence)); - else + } else { ret = i915_request_await_external(rq, fence); + } if (ret < 0) return ret; @@ -1525,16 +1550,6 @@ i915_request_await_object(struct i915_request *to, return ret; } -static inline bool is_parallel_rq(struct i915_request *rq) -{ - return intel_context_is_parallel(rq->context); -} - -static inline struct intel_context *request_to_parent(struct i915_request *rq) -{ - return intel_context_to_parent(rq->context); -} - static struct i915_request * __i915_request_ensure_parallel_ordering(struct i915_request *rq, struct intel_timeline *timeline)
If an object in the excl or shared slot is a composite fence from a parallel submit and the current request in the conflict tracking is from the same parallel context there is no need to enforce ordering as the ordering is already implicit. Make the request conflict tracking understand this by comparing a parallel submit's parent context and skipping conflict insertion if the values match. v2: (John Harrison) - Reword commit message Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/i915/i915_request.c | 43 +++++++++++++++++++---------- 1 file changed, 29 insertions(+), 14 deletions(-)