drm/i915/selftests: Add a simple exerciser for suspend/hibernate

Although we cannot do a full system-level test of suspend/hibernate from
deep with the kernel selftests, we can exercise the GEM subsystem in
isolation and simulate the external effects (such as losing stolen
contents and trashing the register state).

v2: Don't forget to hold rpm
v3: Suspend the GTT mappings, and more rpm!

References: https://bugs.freedesktop.org/show_bug.cgi?id=96526
References: 5ab57c70 ("drm/i915: Flush logical context image out to memory upon suspend")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jakub Bartmiński <jakub.bartminski@intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Jakub Bartmiński <jakub.bartminski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180830134806.21939-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_gem.c

@@ -6207,4 +6207,5 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 #include "selftests/huge_pages.c"
 #include "selftests/i915_gem_object.c"
 #include "selftests/i915_gem_coherency.c"
+#include "selftests/i915_gem.c"
 #endif

drivers/gpu/drm/i915/selftests/i915_gem.c

+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include <linux/random.h>
+
+#include "../i915_selftest.h"
+
+#include "mock_context.h"
+#include "igt_flush_test.h"
+
+static int switch_to_context(struct drm_i915_private *i915,
+			     struct i915_gem_context *ctx)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	intel_runtime_pm_get(i915);
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		rq = i915_request_alloc(engine, ctx);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
+
+		i915_request_add(rq);
+	}
+
+	intel_runtime_pm_put(i915);
+
+	return err;
+}
+
+static void trash_stolen(struct drm_i915_private *i915)
+{
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	const u64 slot = ggtt->error_capture.start;
+	const resource_size_t size = resource_size(&i915->dsm);
+	unsigned long page;
+	u32 prng = 0x12345678;
+
+	for (page = 0; page < size; page += PAGE_SIZE) {
+		const dma_addr_t dma = i915->dsm.start + page;
+		u32 __iomem *s;
+		int x;
+
+		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
+
+		s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
+		for (x = 0; x < PAGE_SIZE / sizeof(u32); x++) {
+			prng = next_pseudo_random32(prng);
+			iowrite32(prng, &s[x]);
+		}
+		io_mapping_unmap_atomic(s);
+	}
+
+	ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
+}
+
+static void simulate_hibernate(struct drm_i915_private *i915)
+{
+	intel_runtime_pm_get(i915);
+
+	/*
+	 * As a final sting in the tail, invalidate stolen. Under a real S4,
+	 * stolen is lost and needs to be refilled on resume. However, under
+	 * CI we merely do S4-device testing (as full S4 is too unreliable
+	 * for automated testing across a cluster), so to simulate the effect
+	 * of stolen being trashed across S4, we trash it ourselves.
+	 */
+	trash_stolen(i915);
+
+	intel_runtime_pm_put(i915);
+}
+
+static int pm_prepare(struct drm_i915_private *i915)
+{
+	int err = 0;
+
+	if (i915_gem_suspend(i915)) {
+		pr_err("i915_gem_suspend failed\n");
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static void pm_suspend(struct drm_i915_private *i915)
+{
+	intel_runtime_pm_get(i915);
+
+	i915_gem_suspend_gtt_mappings(i915);
+	i915_gem_suspend_late(i915);
+
+	intel_runtime_pm_put(i915);
+}
+
+static void pm_hibernate(struct drm_i915_private *i915)
+{
+	intel_runtime_pm_get(i915);
+
+	i915_gem_suspend_gtt_mappings(i915);
+
+	i915_gem_freeze(i915);
+	i915_gem_freeze_late(i915);
+
+	intel_runtime_pm_put(i915);
+}
+
+static void pm_resume(struct drm_i915_private *i915)
+{
+	/*
+	 * Both suspend and hibernate follow the same wakeup path and assume
+	 * that runtime-pm just works.
+	 */
+	intel_runtime_pm_get(i915);
+
+	intel_engines_sanitize(i915);
+	i915_gem_sanitize(i915);
+	i915_gem_resume(i915);
+
+	intel_runtime_pm_put(i915);
+}
+
+static int igt_gem_suspend(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx;
+	struct drm_file *file;
+	int err;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = -ENOMEM;
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = live_context(i915, file);
+	if (!IS_ERR(ctx))
+		err = switch_to_context(i915, ctx);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (err)
+		goto out;
+
+	err = pm_prepare(i915);
+	if (err)
+		goto out;
+
+	pm_suspend(i915);
+
+	/* Here be dragons! Note that with S3RST any S3 may become S4! */
+	simulate_hibernate(i915);
+
+	pm_resume(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = switch_to_context(i915, ctx);
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+out:
+	mock_file_free(i915, file);
+	return err;
+}
+
+static int igt_gem_hibernate(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx;
+	struct drm_file *file;
+	int err;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = -ENOMEM;
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = live_context(i915, file);
+	if (!IS_ERR(ctx))
+		err = switch_to_context(i915, ctx);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (err)
+		goto out;
+
+	err = pm_prepare(i915);
+	if (err)
+		goto out;
+
+	pm_hibernate(i915);
+
+	/* Here be dragons! */
+	simulate_hibernate(i915);
+
+	pm_resume(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = switch_to_context(i915, ctx);
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+out:
+	mock_file_free(i915, file);
+	return err;
+}
+
+int i915_gem_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_gem_suspend),
+		SUBTEST(igt_gem_hibernate),
+	};
+
+	return i915_subtests(tests, i915);
+}

drivers/gpu/drm/i915/selftests/i915_live_selftests.h

@@ -17,6 +17,7 @@ selftest(objects, i915_gem_object_live_selftests)
 selftest(dmabuf, i915_gem_dmabuf_live_selftests)
 selftest(coherency, i915_gem_coherency_live_selftests)
 selftest(gtt, i915_gem_gtt_live_selftests)
+selftest(gem, i915_gem_live_selftests)
 selftest(evict, i915_gem_evict_live_selftests)
 selftest(hugepages, i915_gem_huge_page_live_selftests)
 selftest(contexts, i915_gem_context_live_selftests)