diff options
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_lrc.c | 65 |
1 files changed, 40 insertions, 25 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 17e70778bf9d..e5a37d14bce8 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1805,6 +1805,33 @@ static bool virtual_matches(const struct virtual_engine *ve, return true; } +static void virtual_xfer_context(struct virtual_engine *ve, + struct intel_engine_cs *engine) +{ + unsigned int n; + + if (likely(engine == ve->siblings[0])) + return; + + GEM_BUG_ON(READ_ONCE(ve->context.inflight)); + if (!intel_engine_has_relative_mmio(engine)) + virtual_update_register_offsets(ve->context.lrc_reg_state, + engine); + + /* + * Move the bound engine to the top of the list for + * future execution. We then kick this tasklet first + * before checking others, so that we preferentially + * reuse this set of bound registers. + */ + for (n = 1; n < ve->num_siblings; n++) { + if (ve->siblings[n] == engine) { + swap(ve->siblings[n], ve->siblings[0]); + break; + } + } +} + #define for_each_waiter(p__, rq__) \ list_for_each_entry_lockless(p__, \ &(rq__)->sched.waiters_list, \ @@ -2245,35 +2272,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine) GEM_BUG_ON(!(rq->execution_mask & engine->mask)); WRITE_ONCE(rq->engine, engine); - if (engine != ve->siblings[0]) { - u32 *regs = ve->context.lrc_reg_state; - unsigned int n; - - GEM_BUG_ON(READ_ONCE(ve->context.inflight)); - - if (!intel_engine_has_relative_mmio(engine)) - virtual_update_register_offsets(regs, - engine); - + if (__i915_request_submit(rq)) { /* - * Move the bound engine to the top of the list - * for future execution. We then kick this - * tasklet first before checking others, so that - * we preferentially reuse this set of bound - * registers. + * Only after we confirm that we will submit + * this request (i.e. it has not already + * completed), do we want to update the context. + * + * This serves two purposes. It avoids + * unnecessary work if we are resubmitting an + * already completed request after timeslicing. + * But more importantly, it prevents us altering + * ve->siblings[] on an idle context, where + * we may be using ve->siblings[] in + * virtual_context_enter / virtual_context_exit. */ - for (n = 1; n < ve->num_siblings; n++) { - if (ve->siblings[n] == engine) { - swap(ve->siblings[n], - ve->siblings[0]); - break; - } - } - + virtual_xfer_context(ve, engine); GEM_BUG_ON(ve->siblings[0] != engine); - } - if (__i915_request_submit(rq)) { submit = true; last = rq; } |