diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_lrc.c')
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_lrc.c | 76 |
1 files changed, 44 insertions, 32 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 06a506c29463..66f6d1a897f2 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -471,12 +471,6 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) return desc; } -static void unwind_wa_tail(struct i915_request *rq) -{ - rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES); - assert_ring_tail_valid(rq->ring, rq->tail); -} - static struct i915_request * __unwind_incomplete_requests(struct intel_engine_cs *engine) { @@ -495,7 +489,6 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) continue; /* XXX */ __i915_request_unsubmit(rq); - unwind_wa_tail(rq); /* * Push the request back into the queue for later resubmission. @@ -525,7 +518,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) */ if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags)) { - spin_lock(&rq->lock); + spin_lock_nested(&rq->lock, + SINGLE_DEPTH_NESTING); i915_request_cancel_breadcrumb(rq); spin_unlock(&rq->lock); } @@ -649,13 +643,35 @@ execlists_schedule_out(struct i915_request *rq) i915_request_put(rq); } -static u64 execlists_update_context(const struct i915_request *rq) +static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->hw_context; - u64 desc; + u64 desc = ce->lrc_desc; + u32 tail, prev; - ce->lrc_reg_state[CTX_RING_TAIL + 1] = - intel_ring_set_tail(rq->ring, rq->tail); + /* + * WaIdleLiteRestore:bdw,skl + * + * We should never submit the context with the same RING_TAIL twice + * just in case we submit an empty ring, which confuses the HW. + * + * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of + * the normal request to be able to always advance the RING_TAIL on + * subsequent resubmissions (for lite restore). Should that fail us, + * and we try and submit the same tail again, force the context + * reload. + * + * If we need to return to a preempted context, we need to skip the + * lite-restore and force it to reload the RING_TAIL. Otherwise, the + * HW has a tendency to ignore us rewinding the TAIL to the end of + * an earlier request. + */ + tail = intel_ring_set_tail(rq->ring, rq->tail); + prev = ce->lrc_reg_state[CTX_RING_TAIL + 1]; + if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0)) + desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_reg_state[CTX_RING_TAIL + 1] = tail; + rq->tail = rq->wa_tail; /* * Make sure the context image is complete before we submit it to HW. @@ -674,7 +690,6 @@ static u64 execlists_update_context(const struct i915_request *rq) */ mb(); - desc = ce->lrc_desc; ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; return desc; @@ -918,6 +933,11 @@ last_active(const struct intel_engine_execlists *execlists) return *last; } +#define for_each_waiter(p__, rq__) \ + list_for_each_entry_lockless(p__, \ + &(rq__)->sched.waiters_list, \ + wait_link) + static void defer_request(struct i915_request *rq, struct list_head * const pl) { LIST_HEAD(list); @@ -935,7 +955,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) GEM_BUG_ON(i915_request_is_active(rq)); list_move_tail(&rq->sched.link, pl); - list_for_each_entry(p, &rq->sched.waiters_list, wait_link) { + for_each_waiter(p, rq) { struct i915_request *w = container_of(p->waiter, typeof(*w), sched); @@ -1101,14 +1121,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ __unwind_incomplete_requests(engine); - /* - * If we need to return to the preempted context, we - * need to skip the lite-restore and force it to - * reload the RING_TAIL. Otherwise, the HW has a - * tendency to ignore us rewinding the TAIL to the - * end of an earlier request. - */ - last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE; last = NULL; } else if (need_timeslice(engine, last) && !timer_pending(&engine->execlists.timer)) { @@ -1149,16 +1161,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (!list_is_last(&last->sched.link, &engine->active.requests)) return; - - /* - * WaIdleLiteRestore:bdw,skl - * Apply the wa NOOPs to prevent - * ring:HEAD == rq:TAIL as we resubmit the - * request. See gen8_emit_fini_breadcrumb() for - * where we prepare the padding after the - * end of the request. - */ - last->tail = last->wa_tail; } } @@ -2131,6 +2133,14 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch = gen8_emit_flush_coherentl3_wa(engine, batch); + /* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */ + batch = gen8_emit_pipe_control(batch, + PIPE_CONTROL_FLUSH_L3 | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE, + slm_offset(engine)); + batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); /* WaMediaPoolStateCmdInWABB:bxt,glk */ @@ -3715,9 +3725,11 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx, ve->base.i915 = ctx->i915; ve->base.gt = siblings[0]->gt; ve->base.id = -1; + ve->base.class = OTHER_CLASS; ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; /* * The decision on whether to submit a request using semaphores |