From 2efa2c522ab0df5176b59274d2e7d16608e3c6ca Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 24 Dec 2020 13:55:38 +0000 Subject: [PATCH] drm/i915/gt: Decouple inflight virtual engines Once a virtual engine has been bound to a sibling, it will remain bound until we finally schedule out the last active request. We can not rebind the context to a new sibling while it is inflight as the context save will conflict, hence we wait. As we cannot then use any other sibliing while the context is inflight, only kick the bound sibling while it inflight and upon scheduling out the kick the rest (so that we can swap engines on timeslicing if the previously bound engine becomes oversubscribed). Signed-off-by: Chris Wilson Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20201224135544.1713-3-chris@chris-wilson.co.uk --- .../gpu/drm/i915/gt/intel_execlists_submission.c | 28 ++++++++++------------ 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index ddfd6b2..fbd0572 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -581,9 +581,8 @@ static inline void execlists_schedule_in(struct i915_request *rq, int idx) static void kick_siblings(struct i915_request *rq, struct intel_context *ce) { struct virtual_engine *ve = container_of(ce, typeof(*ve), context); - struct i915_request *next = READ_ONCE(ve->request); - if (next == rq || (next && next->execution_mask & ~rq->execution_mask)) + if (READ_ONCE(ve->request)) tasklet_hi_schedule(&ve->base.execlists.tasklet); } @@ -997,17 +996,13 @@ first_virtual_engine(struct intel_engine_cs *engine) struct i915_request *rq = READ_ONCE(ve->request); /* lazily cleanup after another engine handled rq */ - if (!rq) { + if (!rq || !virtual_matches(ve, rq, engine)) { rb_erase_cached(rb, &el->virtual); RB_CLEAR_NODE(rb); rb = rb_first_cached(&el->virtual); continue; } - if (!virtual_matches(ve, rq, engine)) { - rb = rb_next(rb); - continue; - } return ve; } @@ -3435,7 +3430,6 @@ static void virtual_submission_tasklet(unsigned long data) if (unlikely(!mask)) return; - local_irq_disable(); for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = READ_ONCE(ve->siblings[n]); struct ve_node * const node = &ve->nodes[sibling->id]; @@ -3445,20 +3439,19 @@ static void virtual_submission_tasklet(unsigned long data) if (!READ_ONCE(ve->request)) break; /* already handled by a sibling's tasklet */ + spin_lock_irq(&sibling->active.lock); + if (unlikely(!(mask & sibling->mask))) { if (!RB_EMPTY_NODE(&node->rb)) { - spin_lock(&sibling->active.lock); rb_erase_cached(&node->rb, &sibling->execlists.virtual); RB_CLEAR_NODE(&node->rb); - spin_unlock(&sibling->active.lock); } - continue; - } - spin_lock(&sibling->active.lock); + goto unlock_engine; + } - if (!RB_EMPTY_NODE(&node->rb)) { + if (unlikely(!RB_EMPTY_NODE(&node->rb))) { /* * Cheat and avoid rebalancing the tree if we can * reuse this node in situ. @@ -3498,9 +3491,12 @@ submit_engine: if (first && prio > sibling->execlists.queue_priority_hint) tasklet_hi_schedule(&sibling->execlists.tasklet); - spin_unlock(&sibling->active.lock); +unlock_engine: + spin_unlock_irq(&sibling->active.lock); + + if (intel_context_inflight(&ve->context)) + break; } - local_irq_enable(); } static void virtual_submit_request(struct i915_request *rq) -- 2.7.4