Merge tag 'drm-intel-next-fixes-2020-10-02' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Propagated from drm-intel-next-queued:
- Fix CRTC state checker (Ville)

Propated from drm-intel-gt-next:
- Avoid implicit vmpa for highmem on 32b (Chris)
- Prevent PAT attriutes for writecombine if CPU doesn't support PAT (Chris)
- Clear the buffer pool age before use. (Chris)
- Fix error code (Dan)
- Break up error capture compression loops (Chris)
- Fix uninitialized variable in context_create_request (Maarten)
- Check for errors on i915_vm_alloc_pt_stash to avoid NULL dereference (Matt)
- Serialize debugfs i915_gem_objects with ctx->mutex (Chris)
- Fix a rebase mistake caused during drm-intel-gt-next creation (Chris)
- Hold request reference for canceling an active context (Chris)
- Heartbeats fixes (Chris)
- Use usigned during batch copies (Chris)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201002182610.GA2204465@intel.com

Author: airlied

drivers/gpu/drm/i915/display/intel_display.c

@@ -14304,7 +14304,6 @@ verify_crtc_state(struct intel_crtc *crtc,
 	struct intel_encoder *encoder;
 	struct intel_crtc_state *pipe_config = old_crtc_state;
 	struct drm_atomic_state *state = old_crtc_state->uapi.state;
-	bool active;
 
 	__drm_atomic_helper_crtc_destroy_state(&old_crtc_state->uapi);
 	intel_crtc_free_hw_state(old_crtc_state);
@@ -14314,16 +14313,19 @@ verify_crtc_state(struct intel_crtc *crtc,
 	drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s]\n", crtc->base.base.id,
 		    crtc->base.name);
 
-	active = dev_priv->display.get_pipe_config(crtc, pipe_config);
+	pipe_config->hw.enable = new_crtc_state->hw.enable;
+
+	pipe_config->hw.active =
+		dev_priv->display.get_pipe_config(crtc, pipe_config);
 
 	/* we keep both pipes enabled on 830 */
-	if (IS_I830(dev_priv))
-		active = new_crtc_state->hw.active;
+	if (IS_I830(dev_priv) && pipe_config->hw.active)
+		pipe_config->hw.active = new_crtc_state->hw.active;
 
-	I915_STATE_WARN(new_crtc_state->hw.active != active,
+	I915_STATE_WARN(new_crtc_state->hw.active != pipe_config->hw.active,
 			"crtc active state doesn't match with hw state "
 			"(expected %i, found %i)\n",
-			new_crtc_state->hw.active, active);
+			new_crtc_state->hw.active, pipe_config->hw.active);
 
 	I915_STATE_WARN(crtc->active != new_crtc_state->hw.active,
 			"transitional active state does not match atomic hw state "
@@ -14332,6 +14334,7 @@ verify_crtc_state(struct intel_crtc *crtc,
 
 	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
 		enum pipe pipe;
+		bool active;
 
 		active = encoder->get_hw_state(encoder, &pipe);
 		I915_STATE_WARN(active != new_crtc_state->hw.active,

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -390,24 +390,6 @@ __context_engines_static(const struct i915_gem_context *ctx)
 	return rcu_dereference_protected(ctx->engines, true);
 }
 
-static bool __reset_engine(struct intel_engine_cs *engine)
-{
-	struct intel_gt *gt = engine->gt;
-	bool success = false;
-
-	if (!intel_has_reset_engine(gt))
-		return false;
-
-	if (!test_and_set_bit(I915_RESET_ENGINE + engine->id,
-			      &gt->reset.flags)) {
-		success = intel_engine_reset(engine, NULL) == 0;
-		clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
-				      &gt->reset.flags);
-	}
-
-	return success;
-}
-
 static void __reset_context(struct i915_gem_context *ctx,
 			    struct intel_engine_cs *engine)
 {
@@ -431,12 +413,7 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
 	 * kill the banned context, we fallback to doing a local reset
 	 * instead.
 	 */
-	if (IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT) &&
-	    !intel_engine_pulse(engine))
-		return true;
-
-	/* If we are unable to send a pulse, try resetting this engine. */
-	return __reset_engine(engine);
+	return intel_engine_pulse(engine) == 0;
 }
 
 static bool
@@ -460,8 +437,8 @@ __active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 		spin_lock(&locked->active.lock);
 	}
 
-	if (!i915_request_completed(rq)) {
-		if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+	if (i915_request_is_active(rq)) {
+		if (!i915_request_completed(rq))
 			*active = locked;
 		ret = true;
 	}
@@ -479,21 +456,34 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
+	/*
+	 * rq->link is only SLAB_TYPESAFE_BY_RCU, we need to hold a reference
+	 * to the request to prevent it being transferred to a new timeline
+	 * (and onto a new timeline->requests list).
+	 */
 	rcu_read_lock();
-	list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
-		if (i915_request_is_active(rq) && i915_request_completed(rq))
-			continue;
+	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
+		bool found;
+
+		/* timeline is already completed upto this point? */
+		if (!i915_request_get_rcu(rq))
+			break;
 
 		/* Check with the backend if the request is inflight */
-		if (__active_engine(rq, &engine))
+		found = true;
+		if (likely(rcu_access_pointer(rq->timeline) == ce->timeline))
+			found = __active_engine(rq, &engine);
+
+		i915_request_put(rq);
+		if (found)
 			break;
 	}
 	rcu_read_unlock();
 
 	return engine;
 }
 
-static void kill_engines(struct i915_gem_engines *engines)
+static void kill_engines(struct i915_gem_engines *engines, bool ban)
 {
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
@@ -508,7 +498,7 @@ static void kill_engines(struct i915_gem_engines *engines)
 	for_each_gem_engine(ce, engines, it) {
 		struct intel_engine_cs *engine;
 
-		if (intel_context_set_banned(ce))
+		if (ban && intel_context_set_banned(ce))
 			continue;
 
 		/*
@@ -521,7 +511,7 @@ static void kill_engines(struct i915_gem_engines *engines)
 		engine = active_engine(ce);
 
 		/* First attempt to gracefully cancel the context */
-		if (engine && !__cancel_engine(engine))
+		if (engine && !__cancel_engine(engine) && ban)
 			/*
 			 * If we are unable to send a preemptive pulse to bump
 			 * the context from the GPU, we have to resort to a full
@@ -531,8 +521,10 @@ static void kill_engines(struct i915_gem_engines *engines)
 	}
 }
 
-static void kill_stale_engines(struct i915_gem_context *ctx)
+static void kill_context(struct i915_gem_context *ctx)
 {
+	bool ban = (!i915_gem_context_is_persistent(ctx) ||
+		    !ctx->i915->params.enable_hangcheck);
 	struct i915_gem_engines *pos, *next;
 
 	spin_lock_irq(&ctx->stale.lock);
@@ -545,7 +537,7 @@ static void kill_stale_engines(struct i915_gem_context *ctx)
 
 		spin_unlock_irq(&ctx->stale.lock);
 
-		kill_engines(pos);
+		kill_engines(pos, ban);
 
 		spin_lock_irq(&ctx->stale.lock);
 		GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence));
@@ -557,11 +549,6 @@ static void kill_stale_engines(struct i915_gem_context *ctx)
 	spin_unlock_irq(&ctx->stale.lock);
 }
 
-static void kill_context(struct i915_gem_context *ctx)
-{
-	kill_stale_engines(ctx);
-}
-
 static void engines_idle_release(struct i915_gem_context *ctx,
 				 struct i915_gem_engines *engines)
 {
@@ -596,7 +583,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 
 kill:
 	if (list_empty(&engines->link)) /* raced, already closed */
-		kill_engines(engines);
+		kill_engines(engines, true);
 
 	i915_sw_fence_commit(&engines->fence);
 }
@@ -654,9 +641,7 @@ static void context_close(struct i915_gem_context *ctx)
 	 * case we opt to forcibly kill off all remaining requests on
 	 * context close.
 	 */
-	if (!i915_gem_context_is_persistent(ctx) ||
-	    !ctx->i915->params.enable_hangcheck)
-		kill_context(ctx);
+	kill_context(ctx);
 
 	i915_gem_context_put(ctx);
 }

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -2267,8 +2267,8 @@ struct eb_parse_work {
 	struct i915_vma *batch;
 	struct i915_vma *shadow;
 	struct i915_vma *trampoline;
-	unsigned int batch_offset;
-	unsigned int batch_length;
+	unsigned long batch_offset;
+	unsigned long batch_length;
 };
 
 static int __eb_parse(struct dma_fence_work *work)
@@ -2338,6 +2338,9 @@ static int eb_parse_pipeline(struct i915_execbuffer *eb,
 	struct eb_parse_work *pw;
 	int err;
 
+	GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
+	GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
+
 	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
 	if (!pw)
 		return -ENOMEM;

drivers/gpu/drm/i915/gem/i915_gem_object_blt.c

@@ -364,7 +364,7 @@ int i915_gem_object_copy_blt(struct drm_i915_gem_object *src,
 
 	vma[1] = i915_vma_instance(dst, vm, NULL);
 	if (IS_ERR(vma[1]))
-		return PTR_ERR(vma);
+		return PTR_ERR(vma[1]);
 
 	i915_gem_ww_ctx_init(&ww, true);
 	intel_engine_pm_get(ce->engine);

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -254,9 +254,35 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
 		return NULL;
 
+	if (GEM_WARN_ON(type == I915_MAP_WC &&
+			!static_cpu_has(X86_FEATURE_PAT)))
+		return NULL;
+
 	/* A single page can always be kmapped */
-	if (n_pte == 1 && type == I915_MAP_WB)
-		return kmap(sg_page(sgt->sgl));
+	if (n_pte == 1 && type == I915_MAP_WB) {
+		struct page *page = sg_page(sgt->sgl);
+
+		/*
+		 * On 32b, highmem using a finite set of indirect PTE (i.e.
+		 * vmap) to provide virtual mappings of the high pages.
+		 * As these are finite, map_new_virtual() must wait for some
+		 * other kmap() to finish when it runs out. If we map a large
+		 * number of objects, there is no method for it to tell us
+		 * to release the mappings, and we deadlock.
+		 *
+		 * However, if we make an explicit vmap of the page, that
+		 * uses a larger vmalloc arena, and also has the ability
+		 * to tell us to release unwanted mappings. Most importantly,
+		 * it will fail and propagate an error instead of waiting
+		 * forever.
+		 *
+		 * So if the page is beyond the 32b boundary, make an explicit
+		 * vmap. On 64b, this check will be optimised away as we can
+		 * directly kmap any page on the system.
+		 */
+		if (!PageHighMem(page))
+			return kmap(page);
+	}
 
 	mem = stack;
 	if (n_pte > ARRAY_SIZE(stack)) {

drivers/gpu/drm/i915/gt/intel_context.c

@@ -472,6 +472,7 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 		err = i915_gem_ww_ctx_backoff(&ww);
 		if (!err)
 			goto retry;
+		rq = ERR_PTR(err);
 	} else {
 		rq = ERR_PTR(err);
 	}

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -337,4 +337,13 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
+static inline bool
+intel_engine_has_heartbeat(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL))
+		return false;
+
+	return READ_ONCE(engine->props.heartbeat_interval_ms);
+}
+
 #endif /* _INTEL_RINGBUFFER_H_ */