From a3174b4c9601c7ef99f1e3a3f6cd32b1072f1a9c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 9 Dec 2019 02:32:15 +0000 Subject: [PATCH] drm/i915/gt: Detect if we miss WaIdleLiteRestore In order to avoid confusing the HW, we must never submit an empty ring during lite-restore, that is we should always advance the RING_TAIL before submitting to stay ahead of the RING_HEAD. Normally this is prevented by keeping a couple of spare NOPs in the request->wa_tail so that on resubmission we can advance the tail. This relies on the request only being resubmitted once, which is the normal condition as it is seen once for ELSP[1] and then later in ELSP[0]. On preemption, the requests are unwound and the tail reset back to the normal end point (as we know the request is incomplete and therefore its RING_HEAD is even earlier). However, if this w/a should fail we would try and resubmit the request with the RING_TAIL already set to the location of this request's wa_tail potentially causing a GPU hang. We can spot when we do try and incorrectly resubmit without advancing the RING_TAIL and spare any embarrassment by forcing the context restore. In the case of preempt-to-busy, we leave the requests running on the HW while we unwind. As the ring is still live, we cannot rewind our rq->tail without forcing a reload so leave it set to rq->wa_tail and only force a reload if we resubmit after a lite-restore. (Normally, the forced reload will be a part of the preemption event.) Fixes: c7e4d40378c6 ("drm/i915/execlists: Preempt-to-busy") Closes: https://gitlab.freedesktop.org/drm/intel/issues/673 Signed-off-by: Chris Wilson Cc: Mika Kuoppala Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Cc: stable@kernel.vger.org Link: https://patchwork.freedesktop.org/patch/msgid/20191209023215.3519970-1-chris@chris-wilson.co.uk (cherry picked from commit 82c69bf58650e644c61aa2bf5100b63a1070fd2f) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gt/intel_lrc.c | 46 +++++++++++++---------------- 1 file changed, 21 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 17bb52aeff190..75dd0e0367b7a 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -845,12 +845,6 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) } } -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) { @@ -863,12 +857,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) list_for_each_entry_safe_reverse(rq, rn, &engine->active.requests, sched.link) { - if (i915_request_completed(rq)) continue; /* XXX */ __i915_request_unsubmit(rq); - unwind_wa_tail(rq); /* * Push the request back into the queue for later resubmission. @@ -1161,13 +1153,29 @@ 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; - ce->lrc_reg_state[CTX_RING_TAIL] = - 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. + */ + tail = intel_ring_set_tail(rq->ring, rq->tail); + if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) + desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_reg_state[CTX_RING_TAIL] = tail; + rq->tail = rq->wa_tail; /* * Make sure the context image is complete before we submit it to HW. @@ -1186,13 +1194,11 @@ static u64 execlists_update_context(const struct i915_request *rq) */ mb(); - desc = ce->lrc_desc; - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; - /* Wa_1607138340:tgl */ if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0)) desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1703,16 +1709,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) 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; } } -- 2.39.5