Message ID | 1406217891-8912-33-git-send-email-thomas.daniel@intel.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On Thu, Jul 24, 2014 at 05:04:40PM +0100, Thomas Daniel wrote: > From: Oscar Mateo <oscar.mateo@intel.com> > > In the current Execlists feeding mechanism, full preemption is not > supported yet: only lite-restores are allowed (this is: the GPU > simply samples a new tail pointer for the context currently in > execution). > > But we have identified an scenario in which a full preemption occurs: > 1) We submit two contexts for execution (A & B). > 2) The GPU finishes with the first one (A), switches to the second one > (B) and informs us. > 3) We submit B again (hoping to cause a lite restore) together with C, > but in the time we spend writing to the ELSP, the GPU finishes B. > 4) The GPU start executing B again (since we told it so). > 5) We receive a B finished interrupt and, mistakenly, we submit C (again) > and D, causing a full preemption of B. > > The race is avoided by keeping track of how many times a context has been > submitted to the hardware and by better discriminating the received context > switch interrupts: in the example, when we have submitted B twice, we won´t > submit C and D as soon as we receive the notification that B is completed > because we were expecting to get a LITE_RESTORE and we didn´t, so we know a > second completion will be received shortly. > > Without this explicit checking, somehow, the batch buffer execution order > gets messed with. This can be verified with the IGT test I sent together with > the series. I don´t know the exact mechanism by which the pre-emption messes > with the execution order but, since other people is working on the Scheduler > + Preemption on Execlists, I didn´t try to fix it. In these series, only Lite > Restores are supported (other kind of preemptions WARN). Where's this igt patch? The kernel patch here is at least missing the Testcase: igt/foo tag. Please supply. -Daniel > > v2: elsp_submitted belongs in the new intel_ctx_submit_request. Several > rebase changes. > > v3: Clarify how the race is avoided, as requested by Daniel. > > Signed-off-by: Oscar Mateo <oscar.mateo@intel.com> > --- > drivers/gpu/drm/i915/intel_lrc.c | 28 ++++++++++++++++++++++++---- > drivers/gpu/drm/i915/intel_lrc.h | 2 ++ > 2 files changed, 26 insertions(+), 4 deletions(-) > > diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c > index 65f4f26..895dbfc 100644 > --- a/drivers/gpu/drm/i915/intel_lrc.c > +++ b/drivers/gpu/drm/i915/intel_lrc.c > @@ -264,6 +264,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) > else if (req0->ctx == cursor->ctx) { > /* Same ctx: ignore first request, as second request > * will update tail past first request's workload */ > + cursor->elsp_submitted = req0->elsp_submitted; > list_del(&req0->execlist_link); > queue_work(dev_priv->wq, &req0->work); > req0 = cursor; > @@ -273,8 +274,14 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) > } > } > > + WARN_ON(req1 && req1->elsp_submitted); > + > BUG_ON(execlists_submit_context(ring, req0->ctx, req0->tail, > req1? req1->ctx : NULL, req1? req1->tail : 0)); > + > + req0->elsp_submitted++; > + if (req1) > + req1->elsp_submitted++; > } > > static bool execlists_check_remove_request(struct intel_engine_cs *ring, > @@ -291,9 +298,13 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring, > struct drm_i915_gem_object *ctx_obj = > head_req->ctx->engine[ring->id].state; > if (intel_execlists_ctx_id(ctx_obj) == request_id) { > - list_del(&head_req->execlist_link); > - queue_work(dev_priv->wq, &head_req->work); > - return true; > + WARN(head_req->elsp_submitted == 0, > + "Never submitted head request\n"); > + if (--head_req->elsp_submitted <= 0) { > + list_del(&head_req->execlist_link); > + queue_work(dev_priv->wq, &head_req->work); > + return true; > + } > } > } > > @@ -326,7 +337,16 @@ void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring) > status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + > (read_pointer % 6) * 8 + 4); > > - if (status & GEN8_CTX_STATUS_COMPLETE) { > + if (status & GEN8_CTX_STATUS_PREEMPTED) { > + if (status & GEN8_CTX_STATUS_LITE_RESTORE) { > + if (execlists_check_remove_request(ring, status_id)) > + WARN(1, "Lite Restored request removed from queue\n"); > + } else > + WARN(1, "Preemption without Lite Restore\n"); > + } > + > + if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) || > + (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) { > if (execlists_check_remove_request(ring, status_id)) > submit_contexts++; > } > diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h > index 2e8929f..074b44f 100644 > --- a/drivers/gpu/drm/i915/intel_lrc.h > +++ b/drivers/gpu/drm/i915/intel_lrc.h > @@ -67,6 +67,8 @@ struct intel_ctx_submit_request { > > struct list_head execlist_link; > struct work_struct work; > + > + int elsp_submitted; > }; > > void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring); > -- > 1.7.9.5 > > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 65f4f26..895dbfc 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -264,6 +264,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) else if (req0->ctx == cursor->ctx) { /* Same ctx: ignore first request, as second request * will update tail past first request's workload */ + cursor->elsp_submitted = req0->elsp_submitted; list_del(&req0->execlist_link); queue_work(dev_priv->wq, &req0->work); req0 = cursor; @@ -273,8 +274,14 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) } } + WARN_ON(req1 && req1->elsp_submitted); + BUG_ON(execlists_submit_context(ring, req0->ctx, req0->tail, req1? req1->ctx : NULL, req1? req1->tail : 0)); + + req0->elsp_submitted++; + if (req1) + req1->elsp_submitted++; } static bool execlists_check_remove_request(struct intel_engine_cs *ring, @@ -291,9 +298,13 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring, struct drm_i915_gem_object *ctx_obj = head_req->ctx->engine[ring->id].state; if (intel_execlists_ctx_id(ctx_obj) == request_id) { - list_del(&head_req->execlist_link); - queue_work(dev_priv->wq, &head_req->work); - return true; + WARN(head_req->elsp_submitted == 0, + "Never submitted head request\n"); + if (--head_req->elsp_submitted <= 0) { + list_del(&head_req->execlist_link); + queue_work(dev_priv->wq, &head_req->work); + return true; + } } } @@ -326,7 +337,16 @@ void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring) status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + (read_pointer % 6) * 8 + 4); - if (status & GEN8_CTX_STATUS_COMPLETE) { + if (status & GEN8_CTX_STATUS_PREEMPTED) { + if (status & GEN8_CTX_STATUS_LITE_RESTORE) { + if (execlists_check_remove_request(ring, status_id)) + WARN(1, "Lite Restored request removed from queue\n"); + } else + WARN(1, "Preemption without Lite Restore\n"); + } + + if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) || + (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) { if (execlists_check_remove_request(ring, status_id)) submit_contexts++; } diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 2e8929f..074b44f 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -67,6 +67,8 @@ struct intel_ctx_submit_request { struct list_head execlist_link; struct work_struct work; + + int elsp_submitted; }; void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring);