[Intel-gfx] [PATCH 13/25] drm/i915/guc: Insert submit fences between requests in parent-child relationship
The GuC must receive requests in the order submitted for contexts in a parent-child relationship to function correctly. To ensure this, insert a submit fence between the current request and last request submitted for requests / contexts in a parent child relationship. This is conceptually similar to a single timeline. Signed-off-by: Matthew Brost Cc: John Harrison Reviewed-by: John Harrison --- drivers/gpu/drm/i915/gt/intel_context.h | 5 + drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 5 +- drivers/gpu/drm/i915/i915_request.c | 120 ++ 4 files changed, 108 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 9f0995150a7a..edf12caaade3 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -77,6 +77,11 @@ intel_context_to_parent(struct intel_context *ce) } } +static inline bool intel_context_is_parallel(struct intel_context *ce) +{ + return intel_context_is_child(ce) || intel_context_is_parent(ce); +} + void intel_context_bind_parent_child(struct intel_context *parent, struct intel_context *child); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 48decb5ee954..8309d1141d0a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -237,6 +237,12 @@ struct intel_context { }; /** @parent: pointer to parent if child */ struct intel_context *parent; + /** +* @last_rq: last request submitted on a parallel context, used +* to insert submit fences between requests in the parallel +* context +*/ + struct i915_request *last_rq; /** @number_children: number of children if parent */ u8 number_children; /** @guc: GuC specific members for parallel submission */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 71ae5eb69849..ebb64fb50396 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -684,8 +684,7 @@ static inline int rq_prio(const struct i915_request *rq) static bool is_multi_lrc_rq(struct i915_request *rq) { - return intel_context_is_child(rq->context) || - intel_context_is_parent(rq->context); + return intel_context_is_parallel(rq->context); } static bool can_merge_rq(struct i915_request *rq, @@ -2873,6 +2872,8 @@ static void guc_parent_context_unpin(struct intel_context *ce) GEM_BUG_ON(!intel_context_is_parent(ce)); GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + if (ce->parallel.last_rq) + i915_request_put(ce->parallel.last_rq); unpin_guc_id(guc, ce); lrc_unpin(ce); } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0d27072c28d..8bdf9f2f9b90 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1525,36 +1525,62 @@ 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_add_to_timeline(struct i915_request *rq) +__i915_request_ensure_parallel_ordering(struct i915_request *rq, + struct intel_timeline *timeline) { - struct intel_timeline *timeline = i915_request_timeline(rq); struct i915_request *prev; - /* -* Dependency tracking and request ordering along the timeline -* is special cased so that we can eliminate redundant ordering -* operations while building the request (we know that the timeline -* itself is ordered, and here we guarantee it). -* -* As we know we will need to emit tracking along the timeline, -* we embed the hooks into our request struct -- at the cost of -* having to have specialised no-allocation interfaces (which will -* be beneficial elsewhere). -* -* A second benefit to open-coding i915_request_await_request is -* that we can apply a slight variant of the rules specialised -* for timelines that jump between engines (such as virtual engines). -* If we consider the case of virtual engine, we must emit a dma-fence -* to prevent scheduling of the second request until the first is -* compl
[Intel-gfx] [PATCH 13/25] drm/i915/guc: Insert submit fences between requests in parent-child relationship
The GuC must receive requests in the order submitted for contexts in a parent-child relationship to function correctly. To ensure this, insert a submit fence between the current request and last request submitted for requests / contexts in a parent child relationship. This is conceptually similar to a single timeline. Signed-off-by: Matthew Brost Cc: John Harrison Reviewed-by: John Harrison --- drivers/gpu/drm/i915/gt/intel_context.h | 5 + drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 5 +- drivers/gpu/drm/i915/i915_request.c | 120 ++ 4 files changed, 108 insertions(+), 28 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index b63c10a144af..1bc705f98e2a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -75,6 +75,11 @@ intel_context_to_parent(struct intel_context *ce) } } +static inline bool intel_context_is_parallel(struct intel_context *ce) +{ + return intel_context_is_child(ce) || intel_context_is_parent(ce); +} + void intel_context_bind_parent_child(struct intel_context *parent, struct intel_context *child); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 48decb5ee954..8309d1141d0a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -237,6 +237,12 @@ struct intel_context { }; /** @parent: pointer to parent if child */ struct intel_context *parent; + /** +* @last_rq: last request submitted on a parallel context, used +* to insert submit fences between requests in the parallel +* context +*/ + struct i915_request *last_rq; /** @number_children: number of children if parent */ u8 number_children; /** @guc: GuC specific members for parallel submission */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 77591e764195..f690b7c2b295 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -685,8 +685,7 @@ static inline int rq_prio(const struct i915_request *rq) static bool is_multi_lrc_rq(struct i915_request *rq) { - return intel_context_is_child(rq->context) || - intel_context_is_parent(rq->context); + return intel_context_is_parallel(rq->context); } static bool can_merge_rq(struct i915_request *rq, @@ -2874,6 +2873,8 @@ static void guc_parent_context_unpin(struct intel_context *ce) GEM_BUG_ON(!intel_context_is_parent(ce)); GEM_BUG_ON(!intel_engine_is_virtual(ce->engine)); + if (ce->parallel.last_rq) + i915_request_put(ce->parallel.last_rq); unpin_guc_id(guc, ce); lrc_unpin(ce); } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0d27072c28d..8bdf9f2f9b90 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1525,36 +1525,62 @@ 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_add_to_timeline(struct i915_request *rq) +__i915_request_ensure_parallel_ordering(struct i915_request *rq, + struct intel_timeline *timeline) { - struct intel_timeline *timeline = i915_request_timeline(rq); struct i915_request *prev; - /* -* Dependency tracking and request ordering along the timeline -* is special cased so that we can eliminate redundant ordering -* operations while building the request (we know that the timeline -* itself is ordered, and here we guarantee it). -* -* As we know we will need to emit tracking along the timeline, -* we embed the hooks into our request struct -- at the cost of -* having to have specialised no-allocation interfaces (which will -* be beneficial elsewhere). -* -* A second benefit to open-coding i915_request_await_request is -* that we can apply a slight variant of the rules specialised -* for timelines that jump between engines (such as virtual engines). -* If we consider the case of virtual engine, we must emit a dma-fence -* to prevent scheduling of the second request until the first is -* compl