drm/i915/gt: Track all timelines created using the HWSP

We assume that the contents of the HWSP are lost across suspend, and so
upon resume we must restore critical values such as the timeline seqno.
Keep track of every timeline allocated that uses the HWSP as its storage
and so we can then reset all seqno values by walking that list.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201222104242.10993-1-chris@chris-wilson.co.uk

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

@@ -648,6 +648,8 @@ static int init_status_page(struct intel_engine_cs *engine)
 	void *vaddr;
 	int ret;
 
+	INIT_LIST_HEAD(&engine->status_page.timelines);
+
 	/*
 	 * Though the HWS register does support 36bit addresses, historically
 	 * we have had hangs and corruption reported due to wild writes if
@@ -830,6 +832,21 @@ create_pinned_context(struct intel_engine_cs *engine,
 	return ce;
 }
 
+static void destroy_pinned_context(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = ce->engine;
+	struct i915_vma *hwsp = engine->status_page.vma;
+
+	GEM_BUG_ON(ce->timeline->hwsp_ggtt != hwsp);
+
+	mutex_lock(&hwsp->vm->mutex);
+	list_del(&ce->timeline->engine_link);
+	mutex_unlock(&hwsp->vm->mutex);
+
+	intel_context_unpin(ce);
+	intel_context_put(ce);
+}
+
 static struct intel_context *
 create_kernel_context(struct intel_engine_cs *engine)
 {
@@ -926,7 +943,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	GEM_BUG_ON(!list_empty(&engine->active.requests));
 	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
-	cleanup_status_page(engine);
 	intel_breadcrumbs_free(engine->breadcrumbs);
 
 	intel_engine_fini_retire(engine);
@@ -935,11 +951,11 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		fput(engine->default_state);
 
-	if (engine->kernel_context) {
-		intel_context_unpin(engine->kernel_context);
-		intel_context_put(engine->kernel_context);
-	}
+	if (engine->kernel_context)
+		destroy_pinned_context(engine->kernel_context);
+
 	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
+	cleanup_status_page(engine);
 
 	intel_wa_list_free(&engine->ctx_wa_list);
 	intel_wa_list_free(&engine->wa_list);
@@ -1274,8 +1290,12 @@ void intel_engines_reset_default_submission(struct intel_gt *gt)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt, id)
+	for_each_engine(engine, gt, id) {
+		if (engine->sanitize)
+			engine->sanitize(engine);
+
 		engine->set_default_submission(engine);
+	}
 }
 
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)

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

@@ -60,6 +60,13 @@ static int __engine_unpark(struct intel_wakeref *wf)
 
 		/* Scrub the context image after our loss of control */
 		ce->ops->reset(ce);
+
+		CE_TRACE(ce, "reset { seqno:%x, *hwsp:%x, ring:%x }\n",
+			 ce->timeline->seqno,
+			 READ_ONCE(*ce->timeline->hwsp_seqno),
+			 ce->ring->emit);
+		GEM_BUG_ON(ce->timeline->seqno !=
+			   READ_ONCE(*ce->timeline->hwsp_seqno));
 	}
 
 	if (engine->unpark)

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

@@ -68,6 +68,7 @@ typedef u8 intel_engine_mask_t;
 #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
 
 struct intel_hw_status_page {
+	struct list_head timelines;
 	struct i915_vma *vma;
 	u32 *addr;
 };

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

@@ -2698,6 +2698,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 	GEM_BUG_ON(READ_ONCE(*execlists->csb_write) != reset_value);
 }
 
+static void sanitize_hwsp(struct intel_engine_cs *engine)
+{
+	struct intel_timeline *tl;
+
+	list_for_each_entry(tl, &engine->status_page.timelines, engine_link)
+		intel_timeline_reset_seqno(tl);
+}
+
 static void execlists_sanitize(struct intel_engine_cs *engine)
 {
 	GEM_BUG_ON(execlists_active(&engine->execlists));
@@ -2721,7 +2729,7 @@ static void execlists_sanitize(struct intel_engine_cs *engine)
 	 * that may be lost on resume/initialisation, and so we need to
 	 * reset the value in the HWSP.
 	 */
-	intel_timeline_reset_seqno(engine->kernel_context->timeline);
+	sanitize_hwsp(engine);
 
 	/* And scrub the dirty cachelines for the HWSP */
 	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);

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

@@ -885,7 +885,6 @@ err_vma:
 
 void lrc_reset(struct intel_context *ce)
 {
-	CE_TRACE(ce, "reset\n");
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
 
 	intel_ring_reset(ce->ring, ce->ring->emit);

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

@@ -321,6 +321,39 @@ out:
 	return ret;
 }
 
+static void sanitize_hwsp(struct intel_engine_cs *engine)
+{
+	struct intel_timeline *tl;
+
+	list_for_each_entry(tl, &engine->status_page.timelines, engine_link)
+		intel_timeline_reset_seqno(tl);
+}
+
+static void xcs_sanitize(struct intel_engine_cs *engine)
+{
+	/*
+	 * Poison residual state on resume, in case the suspend didn't!
+	 *
+	 * We have to assume that across suspend/resume (or other loss
+	 * of control) that the contents of our pinned buffers has been
+	 * lost, replaced by garbage. Since this doesn't always happen,
+	 * let's poison such state so that we more quickly spot when
+	 * we falsely assume it has been preserved.
+	 */
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		memset(engine->status_page.addr, POISON_INUSE, PAGE_SIZE);
+
+	/*
+	 * The kernel_context HWSP is stored in the status_page. As above,
+	 * that may be lost on resume/initialisation, and so we need to
+	 * reset the value in the HWSP.
+	 */
+	sanitize_hwsp(engine);
+
+	/* And scrub the dirty cachelines for the HWSP */
+	clflush_cache_range(engine->status_page.addr, PAGE_SIZE);
+}
+
 static void reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_uncore *uncore = engine->uncore;
@@ -1070,6 +1103,8 @@ static void setup_common(struct intel_engine_cs *engine)
 	setup_irq(engine);
 
 	engine->resume = xcs_resume;
+	engine->sanitize = xcs_sanitize;
+
 	engine->reset.prepare = reset_prepare;
 	engine->reset.rewind = reset_rewind;
 	engine->reset.cancel = reset_cancel;

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

@@ -319,6 +319,25 @@ __intel_timeline_create(struct intel_gt *gt,
 	return timeline;
 }
 
+struct intel_timeline *
+intel_timeline_create_from_engine(struct intel_engine_cs *engine,
+				  unsigned int offset)
+{
+	struct i915_vma *hwsp = engine->status_page.vma;
+	struct intel_timeline *tl;
+
+	tl = __intel_timeline_create(engine->gt, hwsp, offset);
+	if (IS_ERR(tl))
+		return tl;
+
+	/* Borrow a nearby lock; we only create these timelines during init */
+	mutex_lock(&hwsp->vm->mutex);
+	list_add_tail(&tl->engine_link, &engine->status_page.timelines);
+	mutex_unlock(&hwsp->vm->mutex);
+
+	return tl;
+}
+
 void __intel_timeline_pin(struct intel_timeline *tl)
 {
 	GEM_BUG_ON(!atomic_read(&tl->pin_count));

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

@@ -44,14 +44,9 @@ intel_timeline_create(struct intel_gt *gt)
 	return __intel_timeline_create(gt, NULL, 0);
 }
 
-static inline struct intel_timeline *
+struct intel_timeline *
 intel_timeline_create_from_engine(struct intel_engine_cs *engine,
-				  unsigned int offset)
-{
-	return __intel_timeline_create(engine->gt,
-				       engine->status_page.vma,
-				       offset);
-}
+				  unsigned int offset);
 
 static inline struct intel_timeline *
 intel_timeline_get(struct intel_timeline *timeline)

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

@@ -84,6 +84,8 @@ struct intel_timeline {
 	struct list_head link;
 	struct intel_gt *gt;
 
+	struct list_head engine_link;
+
 	struct kref kref;
 	struct rcu_head rcu;
 };