A collection of pending bug [fixes]

A collection of pending bug [fixes]

[Chris Wilson]

Hopefully more fixes than bugs, but these have been annoying CI and
users for yonks (the ilk-m has been known for a few _years_, but only
recently did CI start to pick up on the error and now refuses to run on
ilk-m because of it).
-Chris


_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 01/19] drm/i915: Return immediately if trylock fails for direct-reclaim

[Chris Wilson]

Ignore trying to shrink from i915 if we fail to acquire the struct_mutex
in the shrinker while performing direct-reclaim. The trade-off being
(much) lower latency for non-i915 clients at an increased risk of being
unable to obtain a page from direct-reclaim without hitting the
oom-notifier. The proviso being that we still keep trying to hard
obtain the lock for oom so that we can reap under heavy memory pressure.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h          |  4 ++--
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 24 +++++++++++-------------
 2 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e70707e79386..53f16b037f62 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2915,9 +2915,9 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_unpin_pages(obj);
 }
 
-enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock */
+enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
 	I915_MM_NORMAL = 0,
-	I915_MM_SHRINKER
+	I915_MM_SHRINKER /* called "recursively" from direct-reclaim-esque */
 };
 
 void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index ea90d3a0d511..d461f458f4af 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -36,7 +36,9 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool shrinker_lock(struct drm_i915_private *i915, bool *unlock)
+static bool shrinker_lock(struct drm_i915_private *i915,
+			  unsigned int flags,
+			  bool *unlock)
 {
 	switch (mutex_trylock_recursive(&i915->drm.struct_mutex)) {
 	case MUTEX_TRYLOCK_RECURSIVE:
@@ -45,15 +47,11 @@ static bool shrinker_lock(struct drm_i915_private *i915, bool *unlock)
 
 	case MUTEX_TRYLOCK_FAILED:
 		*unlock = false;
-		preempt_disable();
-		do {
-			cpu_relax();
-			if (mutex_trylock(&i915->drm.struct_mutex)) {
-				*unlock = true;
-				break;
-			}
-		} while (!need_resched());
-		preempt_enable();
+		if (flags & I915_SHRINK_ACTIVE) {
+			mutex_lock_nested(&i915->drm.struct_mutex,
+					  I915_MM_SHRINKER);
+			*unlock = true;
+		}
 		return *unlock;
 
 	case MUTEX_TRYLOCK_SUCCESS:
@@ -160,7 +158,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	unsigned long scanned = 0;
 	bool unlock;
 
-	if (!shrinker_lock(i915, &unlock))
+	if (!shrinker_lock(i915, flags, &unlock))
 		return 0;
 
 	/*
@@ -357,7 +355,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	sc->nr_scanned = 0;
 
-	if (!shrinker_lock(i915, &unlock))
+	if (!shrinker_lock(i915, 0, &unlock))
 		return SHRINK_STOP;
 
 	freed = i915_gem_shrink(i915,
@@ -397,7 +395,7 @@ shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 	do {
 		if (i915_gem_wait_for_idle(i915,
 					   0, MAX_SCHEDULE_TIMEOUT) == 0 &&
-		    shrinker_lock(i915, unlock))
+		    shrinker_lock(i915, 0, unlock))
 			break;
 
 		schedule_timeout_killable(1);
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 02/19] drm/i915/userptr: Avoid struct_mutex recursion for mmu_invalidate_range_start

[Chris Wilson]

Since commit 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu
notifiers") we have been able to report failure from
mmu_invalidate_range_start which allows us to use a trylock on the
struct_mutex to avoid potential recursion and report -EBUSY instead.
Furthermore, this allows us to pull the work into the main callback and
avoid the sleight-of-hand in using a workqueue to avoid lockdep.

However, not all paths to mmu_invalidate_range_start are prepared to
handle failure, so instead of reporting the recursion, deal with it by
propagating the failure upwards, who can decide themselves to handle it
or report it.

v2: Mark up the recursive lock behaviour and comment on the various weak
points.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108375
References: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |   4 +-
 drivers/gpu/drm/i915/i915_gem.c         |  30 +++-
 drivers/gpu/drm/i915/i915_gem_object.h  |   7 +
 drivers/gpu/drm/i915/i915_gem_userptr.c | 221 +++++++++++-------------
 4 files changed, 136 insertions(+), 126 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 53f16b037f62..f625a5c40ca3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2920,8 +2920,8 @@ enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
 	I915_MM_SHRINKER /* called "recursively" from direct-reclaim-esque */
 };
 
-void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				 enum i915_mm_subclass subclass);
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
+				enum i915_mm_subclass subclass);
 void __i915_gem_object_invalidate(struct drm_i915_gem_object *obj);
 
 enum i915_map_type {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 649847b87e41..ba741b3904e9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2447,8 +2447,8 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	struct sg_table *pages;
 
 	pages = fetch_and_zero(&obj->mm.pages);
-	if (!pages)
-		return NULL;
+	if (IS_ERR_OR_NULL(pages))
+		return pages;
 
 	spin_lock(&i915->mm.obj_lock);
 	list_del(&obj->mm.link);
@@ -2472,22 +2472,23 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	return pages;
 }
 
-void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				 enum i915_mm_subclass subclass)
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
+				enum i915_mm_subclass subclass)
 {
 	struct sg_table *pages;
+	int ret;
 
 	if (i915_gem_object_has_pinned_pages(obj))
-		return;
+		return -EBUSY;
 
 	GEM_BUG_ON(obj->bind_count);
-	if (!i915_gem_object_has_pages(obj))
-		return;
 
 	/* May be called by shrinker from within get_pages() (on another bo) */
 	mutex_lock_nested(&obj->mm.lock, subclass);
-	if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
+	if (unlikely(atomic_read(&obj->mm.pages_pin_count))) {
+		ret = -EBUSY;
 		goto unlock;
+	}
 
 	/*
 	 * ->put_pages might need to allocate memory for the bit17 swizzle
@@ -2495,11 +2496,24 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 	 * lists early.
 	 */
 	pages = __i915_gem_object_unset_pages(obj);
+
+	/*
+	 * XXX Temporary hijinx to avoid updating all backends to handle
+	 * NULL pages. In the future, when we have more asynchronous
+	 * get_pages backends we should be better able to handle the
+	 * cancellation of the async task in a more uniform manner.
+	 */
+	if (!pages && !i915_gem_object_needs_async_cancel(obj))
+		pages = ERR_PTR(-EINVAL);
+
 	if (!IS_ERR(pages))
 		obj->ops->put_pages(obj, pages);
 
+	ret = 0;
 unlock:
 	mutex_unlock(&obj->mm.lock);
+
+	return ret;
 }
 
 bool i915_sg_trim(struct sg_table *orig_st)
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index a6dd7c46de0d..49ce797173b5 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -56,6 +56,7 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
@@ -386,6 +387,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY;
 }
 
+static inline bool
+i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
+}
+
 static inline bool
 i915_gem_object_is_active(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 2c9b284036d1..8b07fd44731f 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -50,79 +50,84 @@ struct i915_mmu_notifier {
 	struct hlist_node node;
 	struct mmu_notifier mn;
 	struct rb_root_cached objects;
-	struct workqueue_struct *wq;
+	struct i915_mm_struct *mm;
 };
 
 struct i915_mmu_object {
 	struct i915_mmu_notifier *mn;
 	struct drm_i915_gem_object *obj;
 	struct interval_tree_node it;
-	struct list_head link;
-	struct work_struct work;
-	bool attached;
 };
 
-static void cancel_userptr(struct work_struct *work)
-{
-	struct i915_mmu_object *mo = container_of(work, typeof(*mo), work);
-	struct drm_i915_gem_object *obj = mo->obj;
-	struct work_struct *active;
-
-	/* Cancel any active worker and force us to re-evaluate gup */
-	mutex_lock(&obj->mm.lock);
-	active = fetch_and_zero(&obj->userptr.work);
-	mutex_unlock(&obj->mm.lock);
-	if (active)
-		goto out;
-
-	i915_gem_object_wait(obj, I915_WAIT_ALL, MAX_SCHEDULE_TIMEOUT, NULL);
-
-	mutex_lock(&obj->base.dev->struct_mutex);
-
-	/* We are inside a kthread context and can't be interrupted */
-	if (i915_gem_object_unbind(obj) == 0)
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
-	WARN_ONCE(i915_gem_object_has_pages(obj),
-		  "Failed to release pages: bind_count=%d, pages_pin_count=%d, pin_global=%d\n",
-		  obj->bind_count,
-		  atomic_read(&obj->mm.pages_pin_count),
-		  obj->pin_global);
-
-	mutex_unlock(&obj->base.dev->struct_mutex);
-
-out:
-	i915_gem_object_put(obj);
-}
-
 static void add_object(struct i915_mmu_object *mo)
 {
-	if (mo->attached)
+	if (!RB_EMPTY_NODE(&mo->it.rb))
 		return;
 
 	interval_tree_insert(&mo->it, &mo->mn->objects);
-	mo->attached = true;
 }
 
 static void del_object(struct i915_mmu_object *mo)
 {
-	if (!mo->attached)
+	if (RB_EMPTY_NODE(&mo->it.rb))
 		return;
 
 	interval_tree_remove(&mo->it, &mo->mn->objects);
-	mo->attached = false;
+	RB_CLEAR_NODE(&mo->it.rb);
+}
+
+static void
+__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj, bool value)
+{
+	struct i915_mmu_object *mo = obj->userptr.mmu_object;
+
+	/*
+	 * During mm_invalidate_range we need to cancel any userptr that
+	 * overlaps the range being invalidated. Doing so requires the
+	 * struct_mutex, and that risks recursion. In order to cause
+	 * recursion, the user must alias the userptr address space with
+	 * a GTT mmapping (possible with a MAP_FIXED) - then when we have
+	 * to invalidate that mmaping, mm_invalidate_range is called with
+	 * the userptr address *and* the struct_mutex held.  To prevent that
+	 * we set a flag under the i915_mmu_notifier spinlock to indicate
+	 * whether this object is valid.
+	 */
+	if (!mo)
+		return;
+
+	spin_lock(&mo->mn->lock);
+	if (value)
+		add_object(mo);
+	else
+		del_object(mo);
+	spin_unlock(&mo->mn->lock);
+}
+
+static struct mutex *__i915_mutex_lock_recursive(struct mutex *m)
+{
+	switch (mutex_trylock_recursive(m)) {
+	default:
+	case MUTEX_TRYLOCK_FAILED:
+		mutex_lock_nested(m, I915_MM_SHRINKER);
+	case MUTEX_TRYLOCK_SUCCESS:
+		return m;
+
+	case MUTEX_TRYLOCK_RECURSIVE:
+		return ERR_PTR(-EEXIST);
+	}
 }
 
 static int i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
-						       struct mm_struct *mm,
-						       unsigned long start,
-						       unsigned long end,
-						       bool blockable)
+						      struct mm_struct *mm,
+						      unsigned long start,
+						      unsigned long end,
+						      bool blockable)
 {
 	struct i915_mmu_notifier *mn =
 		container_of(_mn, struct i915_mmu_notifier, mn);
-	struct i915_mmu_object *mo;
 	struct interval_tree_node *it;
-	LIST_HEAD(cancelled);
+	struct mutex *unlock = NULL;
+	int ret = 0;
 
 	if (RB_EMPTY_ROOT(&mn->objects.rb_root))
 		return 0;
@@ -133,11 +138,15 @@ static int i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	spin_lock(&mn->lock);
 	it = interval_tree_iter_first(&mn->objects, start, end);
 	while (it) {
+		struct drm_i915_gem_object *obj;
+
 		if (!blockable) {
-			spin_unlock(&mn->lock);
-			return -EAGAIN;
+			ret = -EAGAIN;
+			break;
 		}
-		/* The mmu_object is released late when destroying the
+
+		/*
+		 * The mmu_object is released late when destroying the
 		 * GEM object so it is entirely possible to gain a
 		 * reference on an object in the process of being freed
 		 * since our serialisation is via the spinlock and not
@@ -146,21 +155,39 @@ static int i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 		 * use-after-free we only acquire a reference on the
 		 * object if it is not in the process of being destroyed.
 		 */
-		mo = container_of(it, struct i915_mmu_object, it);
-		if (kref_get_unless_zero(&mo->obj->base.refcount))
-			queue_work(mn->wq, &mo->work);
+		obj = container_of(it, struct i915_mmu_object, it)->obj;
+		if (!kref_get_unless_zero(&obj->base.refcount)) {
+			it = interval_tree_iter_next(it, start, end);
+			continue;
+		}
+		spin_unlock(&mn->lock);
 
-		list_add(&mo->link, &cancelled);
-		it = interval_tree_iter_next(it, start, end);
+		if (!unlock)
+			unlock = __i915_mutex_lock_recursive(&mn->mm->i915->drm.struct_mutex);
+		ret = i915_gem_object_unbind(obj);
+		if (ret == 0)
+			ret = __i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
+		i915_gem_object_put(obj);
+		if (ret)
+			goto unlock;
+
+		spin_lock(&mn->lock);
+
+		/*
+		 * As we do not (yet) protect the mmu from concurrent insertion
+		 * over this range, there is no guarantee that this search will
+		 * terminate given a pathologic workload.
+		 */
+		it = interval_tree_iter_first(&mn->objects, start, end);
 	}
-	list_for_each_entry(mo, &cancelled, link)
-		del_object(mo);
 	spin_unlock(&mn->lock);
 
-	if (!list_empty(&cancelled))
-		flush_workqueue(mn->wq);
+unlock:
+	if (!IS_ERR_OR_NULL(unlock))
+		mutex_unlock(unlock);
+
+	return ret;
 
-	return 0;
 }
 
 static const struct mmu_notifier_ops i915_gem_userptr_notifier = {
@@ -168,7 +195,7 @@ static const struct mmu_notifier_ops i915_gem_userptr_notifier = {
 };
 
 static struct i915_mmu_notifier *
-i915_mmu_notifier_create(struct mm_struct *mm)
+i915_mmu_notifier_create(struct i915_mm_struct *mm)
 {
 	struct i915_mmu_notifier *mn;
 
@@ -179,13 +206,7 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 	spin_lock_init(&mn->lock);
 	mn->mn.ops = &i915_gem_userptr_notifier;
 	mn->objects = RB_ROOT_CACHED;
-	mn->wq = alloc_workqueue("i915-userptr-release",
-				 WQ_UNBOUND | WQ_MEM_RECLAIM,
-				 0);
-	if (mn->wq == NULL) {
-		kfree(mn);
-		return ERR_PTR(-ENOMEM);
-	}
+	mn->mm = mm;
 
 	return mn;
 }
@@ -195,16 +216,14 @@ i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 {
 	struct i915_mmu_object *mo;
 
-	mo = obj->userptr.mmu_object;
-	if (mo == NULL)
+	mo = fetch_and_zero(&obj->userptr.mmu_object);
+	if (!mo)
 		return;
 
 	spin_lock(&mo->mn->lock);
 	del_object(mo);
 	spin_unlock(&mo->mn->lock);
 	kfree(mo);
-
-	obj->userptr.mmu_object = NULL;
 }
 
 static struct i915_mmu_notifier *
@@ -217,7 +236,7 @@ i915_mmu_notifier_find(struct i915_mm_struct *mm)
 	if (mn)
 		return mn;
 
-	mn = i915_mmu_notifier_create(mm->mm);
+	mn = i915_mmu_notifier_create(mm);
 	if (IS_ERR(mn))
 		err = PTR_ERR(mn);
 
@@ -240,10 +259,8 @@ i915_mmu_notifier_find(struct i915_mm_struct *mm)
 	mutex_unlock(&mm->i915->mm_lock);
 	up_write(&mm->mm->mmap_sem);
 
-	if (mn && !IS_ERR(mn)) {
-		destroy_workqueue(mn->wq);
+	if (mn && !IS_ERR(mn))
 		kfree(mn);
-	}
 
 	return err ? ERR_PTR(err) : mm->mn;
 }
@@ -266,14 +283,14 @@ i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
 		return PTR_ERR(mn);
 
 	mo = kzalloc(sizeof(*mo), GFP_KERNEL);
-	if (mo == NULL)
+	if (!mo)
 		return -ENOMEM;
 
 	mo->mn = mn;
 	mo->obj = obj;
 	mo->it.start = obj->userptr.ptr;
 	mo->it.last = obj->userptr.ptr + obj->base.size - 1;
-	INIT_WORK(&mo->work, cancel_userptr);
+	RB_CLEAR_NODE(&mo->it.rb);
 
 	obj->userptr.mmu_object = mo;
 	return 0;
@@ -287,12 +304,16 @@ i915_mmu_notifier_free(struct i915_mmu_notifier *mn,
 		return;
 
 	mmu_notifier_unregister(&mn->mn, mm);
-	destroy_workqueue(mn->wq);
 	kfree(mn);
 }
 
 #else
 
+static void
+__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj, bool value)
+{
+}
+
 static void
 i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 {
@@ -461,42 +482,6 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	return st;
 }
 
-static int
-__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj,
-			      bool value)
-{
-	int ret = 0;
-
-	/* During mm_invalidate_range we need to cancel any userptr that
-	 * overlaps the range being invalidated. Doing so requires the
-	 * struct_mutex, and that risks recursion. In order to cause
-	 * recursion, the user must alias the userptr address space with
-	 * a GTT mmapping (possible with a MAP_FIXED) - then when we have
-	 * to invalidate that mmaping, mm_invalidate_range is called with
-	 * the userptr address *and* the struct_mutex held.  To prevent that
-	 * we set a flag under the i915_mmu_notifier spinlock to indicate
-	 * whether this object is valid.
-	 */
-#if defined(CONFIG_MMU_NOTIFIER)
-	if (obj->userptr.mmu_object == NULL)
-		return 0;
-
-	spin_lock(&obj->userptr.mmu_object->mn->lock);
-	/* In order to serialise get_pages with an outstanding
-	 * cancel_userptr, we must drop the struct_mutex and try again.
-	 */
-	if (!value)
-		del_object(obj->userptr.mmu_object);
-	else if (!work_pending(&obj->userptr.mmu_object->work))
-		add_object(obj->userptr.mmu_object);
-	else
-		ret = -EAGAIN;
-	spin_unlock(&obj->userptr.mmu_object->mn->lock);
-#endif
-
-	return ret;
-}
-
 static void
 __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 {
@@ -682,8 +667,11 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 	struct sgt_iter sgt_iter;
 	struct page *page;
 
-	BUG_ON(obj->userptr.work != NULL);
+	/* Cancel any inflight work and force them to restart their gup */
+	obj->userptr.work = NULL;
 	__i915_gem_userptr_set_active(obj, false);
+	if (!pages)
+		return;
 
 	if (obj->mm.madv != I915_MADV_WILLNEED)
 		obj->mm.dirty = false;
@@ -721,7 +709,8 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
-		 I915_GEM_OBJECT_IS_SHRINKABLE,
+		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
 	.dmabuf_export = i915_gem_userptr_dmabuf_export,
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 03/19] drm/i915/userptr: Probe vma range before gup

[Chris Wilson]

We want to exclude any GGTT objects from being present on our internal
lists to avoid the deadlock we may run into with our requirement for
struct_mutex during invalidate. However, if the gup_fast fails, we put
the userptr onto the workqueue and mark it as active, so that we
remember to serialise the worker upon mmu_invalidate.

Note that despite the previous fix, it is still better to avoid the
struct_mutex recursion where possible, leaving the recursion only to
handle the shrinker-esque paths.

v2: Hold mmap_sem to prevent modifications to the mm while we probe and
add ourselves to the interval-tree for notificiation.
v3: Rely on mmap_sem for a simpler patch.
v4: Mark up the mmap_sem nesting
v5: Don't deactivate on -EAGAIN as that means the worker is queued
v6: Fight the indentation and chained if-else error handling
v7: Fight again.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104209
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_userptr.c | 158 ++++++++++++++++--------
 1 file changed, 106 insertions(+), 52 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 8b07fd44731f..744aa538d5db 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -439,7 +439,7 @@ struct get_pages_work {
 	struct task_struct *task;
 };
 
-static struct sg_table *
+static int
 __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 			       struct page **pvec, int num_pages)
 {
@@ -450,7 +450,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
 	if (!st)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 alloc_table:
 	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
@@ -459,7 +459,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 					  GFP_KERNEL);
 	if (ret) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ret;
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
@@ -472,14 +472,14 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 		}
 
 		kfree(st);
-		return ERR_PTR(ret);
+		return ret;
 	}
 
 	sg_page_sizes = i915_sg_page_sizes(st->sgl);
 
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
-	return st;
+	return 0;
 }
 
 static void
@@ -524,19 +524,14 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 
 	mutex_lock(&obj->mm.lock);
 	if (obj->userptr.work == &work->work) {
-		struct sg_table *pages = ERR_PTR(ret);
-
 		if (pinned == npages) {
-			pages = __i915_gem_userptr_alloc_pages(obj, pvec,
-							       npages);
-			if (!IS_ERR(pages)) {
+			ret = __i915_gem_userptr_alloc_pages(obj, pvec, npages);
+			if (!ret)
 				pinned = 0;
-				pages = NULL;
-			}
 		}
 
-		obj->userptr.work = ERR_CAST(pages);
-		if (IS_ERR(pages))
+		obj->userptr.work = ERR_PTR(ret);
+		if (ret)
 			__i915_gem_userptr_set_active(obj, false);
 	}
 	mutex_unlock(&obj->mm.lock);
@@ -549,7 +544,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	kfree(work);
 }
 
-static struct sg_table *
+static int
 __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
 {
 	struct get_pages_work *work;
@@ -575,7 +570,7 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
 	 */
 	work = kmalloc(sizeof(*work), GFP_KERNEL);
 	if (work == NULL)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	obj->userptr.work = &work->work;
 
@@ -587,19 +582,89 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj)
 	INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker);
 	queue_work(to_i915(obj->base.dev)->mm.userptr_wq, &work->work);
 
-	return ERR_PTR(-EAGAIN);
+	return -EAGAIN;
 }
 
-static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
+static int
+probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len)
+{
+	const unsigned long end = addr + len;
+	struct vm_area_struct *vma;
+	int ret = -EFAULT;
+
+	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+		if (vma->vm_start > addr)
+			break;
+
+		/*
+		 * Exclude any VMA that is not backed only by struct_page, i.e.
+		 * IO regions that include our own GGTT mmaps. We cannot handle
+		 * such ranges, as we may encounter deadlocks around our
+		 * struct_mutex on mmu_invalidate_range.
+		 */
+		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
+			break;
+
+		if (vma->vm_end >= end) {
+			ret = 0;
+			break;
+		}
+
+		addr = vma->vm_end;
+	}
+
+	return ret;
+}
+
+static int try_fast_gup(struct drm_i915_gem_object *obj)
 {
 	const int num_pages = obj->base.size >> PAGE_SHIFT;
-	struct mm_struct *mm = obj->userptr.mm->mm;
 	struct page **pvec;
-	struct sg_table *pages;
-	bool active;
-	int pinned;
+	int pinned, err;
 
-	/* If userspace should engineer that these pages are replaced in
+	pvec = kvmalloc_array(num_pages, sizeof(struct page *),
+			      GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	if (!pvec) /* defer to worker if malloc fails */
+		return -ENOMEM;
+
+	pinned = __get_user_pages_fast(obj->userptr.ptr,
+				       num_pages,
+				       !i915_gem_object_is_readonly(obj),
+				       pvec);
+	if (pinned < 0) {
+		err = pinned;
+		pinned = 0;
+		goto out_pvec;
+	}
+
+	if (pinned < num_pages) {
+		err = -EFAULT;
+		goto out_pinned;
+	}
+
+	__i915_gem_userptr_set_active(obj, true);
+
+	err = __i915_gem_userptr_alloc_pages(obj, pvec, num_pages);
+	if (err) {
+		__i915_gem_userptr_set_active(obj, false);
+		goto out_pinned;
+	}
+
+	pinned = 0;
+out_pinned:
+	release_pages(pvec, pinned);
+out_pvec:
+	kvfree(pvec);
+	return err;
+}
+
+static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
+{
+	struct mm_struct *mm = obj->userptr.mm->mm;
+	int err;
+
+	/*
+	 * If userspace should engineer that these pages are replaced in
 	 * the vma between us binding this page into the GTT and completion
 	 * of rendering... Their loss. If they change the mapping of their
 	 * pages they need to create a new bo to point to the new vma.
@@ -624,40 +689,29 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 			return -EAGAIN;
 	}
 
-	pvec = NULL;
-	pinned = 0;
-
 	if (mm == current->mm) {
-		pvec = kvmalloc_array(num_pages, sizeof(struct page *),
-				      GFP_KERNEL |
-				      __GFP_NORETRY |
-				      __GFP_NOWARN);
-		if (pvec) /* defer to worker if malloc fails */
-			pinned = __get_user_pages_fast(obj->userptr.ptr,
-						       num_pages,
-						       !i915_gem_object_is_readonly(obj),
-						       pvec);
+		err = try_fast_gup(obj);
+		if (!err)
+			return 0;
 	}
 
-	active = false;
-	if (pinned < 0) {
-		pages = ERR_PTR(pinned);
-		pinned = 0;
-	} else if (pinned < num_pages) {
-		pages = __i915_gem_userptr_get_pages_schedule(obj);
-		active = pages == ERR_PTR(-EAGAIN);
-	} else {
-		pages = __i915_gem_userptr_alloc_pages(obj, pvec, num_pages);
-		active = !IS_ERR(pages);
-	}
-	if (active)
-		__i915_gem_userptr_set_active(obj, true);
+	/* lockdep doesn't yet automatically allow nesting of readers */
+	down_read_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
 
-	if (IS_ERR(pages))
-		release_pages(pvec, pinned);
-	kvfree(pvec);
+	err = probe_range(mm, obj->userptr.ptr, obj->base.size);
+	if (err)
+		goto err_unlock;
+
+	__i915_gem_userptr_set_active(obj, true);
+
+	err = __i915_gem_userptr_get_pages_schedule(obj);
+	if (err != -EAGAIN)
+		__i915_gem_userptr_set_active(obj, false);
+
+err_unlock:
+	up_read(&mm->mmap_sem);
 
-	return PTR_ERR_OR_ZERO(pages);
+	return err;
 }
 
 static void
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 04/19] drm/i915/selftests: Check we can recover a wedged device

[Chris Wilson]

After declaring a terminally wedged device, we allow ourselves to
recover on the next GPU reset (manually triggered), or resume. Check
that resetting a wedged device does work.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../gpu/drm/i915/selftests/intel_hangcheck.c  | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 805e40aff407..65c318d14077 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -385,6 +385,28 @@ static int igt_global_reset(void *arg)
 	return err;
 }
 
+static int igt_wedged_reset(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+
+	/* Check that we can recover a wedged device with a GPU reset */
+
+	igt_global_reset_lock(i915);
+	mutex_lock(&i915->drm.struct_mutex);
+
+	i915_gem_set_wedged(i915);
+	GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error));
+
+	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
+	i915_reset(i915, ALL_ENGINES, NULL);
+	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
+
+	mutex_unlock(&i915->drm.struct_mutex);
+	igt_global_reset_unlock(i915);
+
+	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
+}
+
 static bool wait_for_idle(struct intel_engine_cs *engine)
 {
 	return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
@@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
+		SUBTEST(igt_wedged_reset),
 		SUBTEST(igt_hang_sanitycheck),
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 05/19] drm/i915/selftests: Verify we can perform resets from atomic context

[Chris Wilson]

We currently require that our per-engine reset can be called from any
context, even hardirq, and in the future wish to perform the device
reset without holding struct_mutex (which requires some lockless
shenanigans that demand the lowlevel intel_reset_gpu() be able to be
used in atomic context). Test that we meet the current requirements by
calling i915_reset_engine() from under various atomic contexts.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../gpu/drm/i915/selftests/intel_hangcheck.c  | 172 ++++++++++++++++++
 1 file changed, 172 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 65c318d14077..5f2f67b149af 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -1470,6 +1470,177 @@ static int igt_handle_error(void *arg)
 	return err;
 }
 
+static void __preempt_begin(void)
+{
+	preempt_disable();
+}
+
+static void __preempt_end(void)
+{
+	preempt_enable();
+}
+
+static void __softirq_begin(void)
+{
+	local_bh_disable();
+}
+
+static void __softirq_end(void)
+{
+	local_bh_enable();
+}
+
+static void __hardirq_begin(void)
+{
+	local_irq_disable();
+}
+
+static void __hardirq_end(void)
+{
+	local_irq_enable();
+}
+
+struct atomic_section {
+	const char *name;
+	void (*critical_section_begin)(void);
+	void (*critical_section_end)(void);
+};
+
+static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
+				     const struct atomic_section *p,
+				     const char *mode)
+{
+	struct tasklet_struct * const t = &engine->execlists.tasklet;
+	int err;
+
+	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
+		  engine->name, mode, p->name);
+
+	tasklet_disable_nosync(t);
+	p->critical_section_begin();
+
+	err = i915_reset_engine(engine, NULL);
+
+	p->critical_section_end();
+	tasklet_enable(t);
+
+	if (err)
+		pr_err("i915_reset_engine(%s:%s) failed under %s\n",
+		       engine->name, mode, p->name);
+
+	return err;
+}
+
+static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
+				   const struct atomic_section *p)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	struct i915_request *rq;
+	struct hang h;
+	int err;
+
+	err = __igt_atomic_reset_engine(engine, p, "idle");
+	if (err)
+		return err;
+
+	err = hang_init(&h, i915);
+	if (err)
+		return err;
+
+	rq = hang_create_request(&h, engine);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out;
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	if (wait_until_running(&h, rq)) {
+		err = __igt_atomic_reset_engine(engine, p, "active");
+	} else {
+		pr_err("%s(%s): Failed to start request %llx, at %x\n",
+		       __func__, engine->name,
+		       rq->fence.seqno, hws_seqno(&h, rq));
+		err = -EIO;
+	}
+
+	if (err == 0) {
+		struct igt_wedge_me w;
+
+		igt_wedge_on_timeout(&w, i915, HZ / 20 /* 50ms timeout*/)
+			i915_request_wait(rq,
+					  I915_WAIT_LOCKED,
+					  MAX_SCHEDULE_TIMEOUT);
+		if (i915_terminally_wedged(&i915->gpu_error))
+			err = -EIO;
+	}
+
+	i915_request_put(rq);
+out:
+	hang_fini(&h);
+	return err;
+}
+
+static void force_reset(struct drm_i915_private *i915)
+{
+	i915_gem_set_wedged(i915);
+	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
+	i915_reset(i915, 0, NULL);
+}
+
+static int igt_atomic_reset(void *arg)
+{
+	static const struct atomic_section phases[] = {
+		{ "preempt", __preempt_begin, __preempt_end },
+		{ "softirq", __softirq_begin, __softirq_end },
+		{ "hardirq", __hardirq_begin, __hardirq_end },
+		{ }
+	};
+	struct drm_i915_private *i915 = arg;
+	int err = 0;
+
+	/* Check that the resets are usable from atomic context */
+
+	if (USES_GUC_SUBMISSION(i915))
+		return 0; /* guc is dead; long live the guc */
+
+	igt_global_reset_lock(i915);
+	mutex_lock(&i915->drm.struct_mutex);
+	intel_runtime_pm_get(i915);
+
+	/* Flush any requests before we get started and check basics */
+	force_reset(i915);
+	if (i915_terminally_wedged(&i915->gpu_error))
+		goto unlock;
+
+	if (intel_has_reset_engine(i915)) {
+		struct intel_engine_cs *engine;
+		enum intel_engine_id id;
+
+		for_each_engine(engine, i915, id) {
+			const typeof(*phases) *p;
+
+			for (p = phases; p->name; p++) {
+				err = igt_atomic_reset_engine(engine, p);
+				if (err)
+					goto out;
+			}
+		}
+	}
+
+out:
+	/* As we poke around the guts, do a full reset before continuing. */
+	force_reset(i915);
+
+unlock:
+	intel_runtime_pm_put(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	igt_global_reset_unlock(i915);
+
+	return err;
+}
+
 int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
@@ -1485,6 +1656,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_evict_ppgtt),
 		SUBTEST(igt_reset_evict_fence),
 		SUBTEST(igt_handle_error),
+		SUBTEST(igt_atomic_reset),
 	};
 	bool saved_hangcheck;
 	int err;
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 06/19] drm/i915/icl: Record the valid VDBoxes with SFC capability

[Chris Wilson]

From: Oscar Mateo <oscar.mateo@intel.com>

In Gen11, only even numbered "logical" VDBoxes are hooked up to an SFC
(Scaler & Format Converter) unit. We will use this information to decide
when the SFC units need to be reset.

BSpec: 20189

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_device_info.c | 11 ++++++++++-
 drivers/gpu/drm/i915/intel_device_info.h |  3 +++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index bd5c4d62c635..acd7ee74d308 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -884,8 +884,9 @@ void intel_driver_caps_print(const struct intel_driver_caps *caps,
 void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 {
 	struct intel_device_info *info = mkwrite_device_info(dev_priv);
-	u32 media_fuse;
+	unsigned int logical_vdbox = 0;
 	unsigned int i;
+	u32 media_fuse;
 
 	if (INTEL_GEN(dev_priv) < 11)
 		return;
@@ -904,7 +905,15 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 		if (!(BIT(i) & info->vdbox_enable)) {
 			info->ring_mask &= ~ENGINE_MASK(_VCS(i));
 			DRM_DEBUG_DRIVER("vcs%u fused off\n", i);
+			continue;
 		}
+
+		/*
+		 * In Gen11, only even numbered logical VDBOXes are
+		 * hooked up to an SFC (Scaler & Format Converter) unit.
+		 */
+		if (logical_vdbox++ % 2 == 0)
+			info->vdbox_sfc_access |= BIT(i);
 	}
 
 	DRM_DEBUG_DRIVER("vebox enable: %04x\n", info->vebox_enable);
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 1caf24e2cf0b..dd34f974a857 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -198,6 +198,9 @@ struct intel_device_info {
 	u8 vdbox_enable;
 	u8 vebox_enable;
 
+	/* Media engine access to SFC per instance */
+	u8 vdbox_sfc_access;
+
 	struct color_luts {
 		u16 degamma_lut_size;
 		u16 gamma_lut_size;
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Chris Wilson]

From: Oscar Mateo <oscar.mateo@intel.com>

SFC (Scaler & Format Converter) units are shared between VD and VEBoxes.
They also happen to have separate reset bits. So, whenever we want to reset
one or more of the media engines, we have to make sure the SFCs do not
change owner in the process and, if this owner happens to be one of the
engines being reset, we need to reset the SFC as well.

This happens in 4 steps:

1) Tell the engine that a software reset is going to happen. The engine
will then try to force lock the SFC (if currently locked, it will
remain so; if currently unlocked, it will ignore this and all new lock
requests).

2) Poll the ack bit to make sure the hardware has received the forced
lock from the driver. Once this bit is set, it indicates SFC status
(lock or unlock) will not change anymore (until we tell the engine it
is safe to unlock again).

3) Check the usage bit to see if the SFC has ended up being locked to
the engine we want to reset. If this is the case, we have to reset
the SFC as well.

4) Unlock all the SFCs once the reset sequence is completed.

Obviously, if we are resetting the whole GPU, we don't have to worry
about all of this.

BSpec: 10989
BSpec: 10990
BSpec: 10954
BSpec: 10955
BSpec: 10956
BSpec: 19212

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_reg.h     |  18 +++++
 drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++--
 2 files changed, 128 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0a7d60509ca7..0796526dc10f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -347,6 +347,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN11_GRDOM_MEDIA4		(1 << 8)
 #define  GEN11_GRDOM_VECS		(1 << 13)
 #define  GEN11_GRDOM_VECS2		(1 << 14)
+#define  GEN11_GRDOM_SFC0		(1 << 17)
+#define  GEN11_GRDOM_SFC1		(1 << 18)
+
+#define  GEN11_VCS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << ((instance) >> 1))
+#define  GEN11_VECS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << (instance))
+
+#define GEN11_VCS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x88C)
+#define   GEN11_VCS_SFC_FORCED_LOCK_BIT		(1 << 0)
+#define GEN11_VCS_SFC_LOCK_STATUS(engine)	_MMIO((engine)->mmio_base + 0x890)
+#define   GEN11_VCS_SFC_USAGE_BIT		(1 << 0)
+#define   GEN11_VCS_SFC_LOCK_ACK_BIT		(1 << 1)
+
+#define GEN11_VECS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x201C)
+#define   GEN11_VECS_SFC_FORCED_LOCK_BIT	(1 << 0)
+#define GEN11_VECS_SFC_LOCK_ACK(engine)		_MMIO((engine)->mmio_base + 0x2018)
+#define   GEN11_VECS_SFC_LOCK_ACK_BIT		(1 << 0)
+#define GEN11_VECS_SFC_USAGE(engine)		_MMIO((engine)->mmio_base + 0x2014)
+#define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
 
 #define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base + 0x228)
 #define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base + 0x518)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 9289515108c3..408692b88c98 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
 	return gen6_hw_domain_reset(dev_priv, hw_mask);
 }
 
+static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
+			  struct intel_engine_cs *engine)
+{
+	u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
+	i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
+	u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
+	i915_reg_t sfc_usage;
+	u32 sfc_usage_bit;
+	u32 sfc_reset_bit;
+
+	switch (engine->class) {
+	case VIDEO_DECODE_CLASS:
+		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
+			return 0;
+
+		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
+		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
+
+		sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
+
+		sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
+		sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
+		sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
+		break;
+
+	case VIDEO_ENHANCEMENT_CLASS:
+		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
+		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
+
+		sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
+		sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
+
+		sfc_usage = GEN11_VECS_SFC_USAGE(engine);
+		sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
+		sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
+		break;
+
+	default:
+		return 0;
+	}
+
+	/*
+	 * Tell the engine that a software reset is going to happen. The engine
+	 * will then try to force lock the SFC (if currently locked, it will
+	 * remain so until we tell the engine it is safe to unlock; if currently
+	 * unlocked, it will ignore this and all new lock requests). If SFC
+	 * ends up being locked to the engine we want to reset, we have to reset
+	 * it as well (we will unlock it once the reset sequence is completed).
+	 */
+	I915_WRITE_FW(sfc_forced_lock,
+		      I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
+
+	if (__intel_wait_for_register_fw(dev_priv,
+					 sfc_forced_lock_ack,
+					 sfc_forced_lock_ack_bit,
+					 sfc_forced_lock_ack_bit,
+					 1000, 0, NULL)) {
+		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
+		return 0;
+	}
+
+	if ((I915_READ_FW(sfc_usage) & sfc_usage_bit) == sfc_usage_bit)
+		return sfc_reset_bit;
+
+	return 0;
+}
+
+static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
+			     struct intel_engine_cs *engine)
+{
+	u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
+	i915_reg_t sfc_forced_lock;
+	u32 sfc_forced_lock_bit;
+
+	switch (engine->class) {
+	case VIDEO_DECODE_CLASS:
+		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
+			return;
+
+		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
+		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
+		break;
+
+	case VIDEO_ENHANCEMENT_CLASS:
+		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
+		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
+		break;
+
+	default:
+		return;
+	}
+
+	I915_WRITE_FW(sfc_forced_lock,
+		      I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
+}
+
 /**
  * gen11_reset_engines - reset individual engines
  * @dev_priv: i915 device
@@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
 static int gen11_reset_engines(struct drm_i915_private *dev_priv,
 			       unsigned int engine_mask)
 {
-	struct intel_engine_cs *engine;
 	const u32 hw_engine_mask[I915_NUM_ENGINES] = {
 		[RCS] = GEN11_GRDOM_RENDER,
 		[BCS] = GEN11_GRDOM_BLT,
@@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct drm_i915_private *dev_priv,
 		[VECS] = GEN11_GRDOM_VECS,
 		[VECS2] = GEN11_GRDOM_VECS2,
 	};
+	struct intel_engine_cs *engine;
+	unsigned int tmp;
 	u32 hw_mask;
+	int ret;
 
 	BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
 
 	if (engine_mask == ALL_ENGINES) {
 		hw_mask = GEN11_GRDOM_FULL;
 	} else {
-		unsigned int tmp;
-
 		hw_mask = 0;
-		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
+		for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
 			hw_mask |= hw_engine_mask[engine->id];
+			hw_mask |= gen11_lock_sfc(dev_priv, engine);
+		}
 	}
 
-	return gen6_hw_domain_reset(dev_priv, hw_mask);
+	ret = gen6_hw_domain_reset(dev_priv, hw_mask);
+
+	if (engine_mask != ALL_ENGINES)
+		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
+			gen11_unlock_sfc(dev_priv, engine);
+
+	return ret;
 }
 
 /**
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 08/19] drm/i915: Always try to reset the GPU on takeover

[Chris Wilson]

When we first introduced the reset to sanitize the GPU on taking over
from the BIOS and before returning control to third parties (the BIOS!),
we restricted it to only systems utilizing HW contexts as we were
uncertain of how stable our reset mechanism truly was. We now have
reasonable coverage across all machines that expose a GPU reset method,
and so we should be safe to sanitize the GPU state everywhere.

v2: We _have_ to skip the reset if it would clobber the display.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.c           |  2 +-
 drivers/gpu/drm/i915/i915_gem.c           | 11 ++---------
 drivers/gpu/drm/i915/i915_pci.c           |  5 +++++
 drivers/gpu/drm/i915/intel_device_info.h  |  1 +
 drivers/gpu/drm/i915/intel_display.c      |  4 ++--
 drivers/gpu/drm/i915/intel_engine_cs.c    | 14 +++++++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.h   |  2 +-
 drivers/gpu/drm/i915/selftests/i915_gem.c |  2 +-
 8 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b310a897a4ad..f6c2a096ee3c 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -2174,7 +2174,7 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	intel_power_domains_resume(dev_priv);
 
-	intel_engines_sanitize(dev_priv);
+	intel_engines_sanitize(dev_priv, true);
 
 	enable_rpm_wakeref_asserts(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ba741b3904e9..8d351caf8f2e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3439,8 +3439,7 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	i915_retire_requests(i915);
 	GEM_BUG_ON(i915->gt.active_requests);
 
-	if (!intel_gpu_reset(i915, ALL_ENGINES))
-		intel_engines_sanitize(i915);
+	intel_engines_sanitize(i915, false);
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
@@ -5044,8 +5043,6 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	int err;
-
 	GEM_TRACE("\n");
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -5070,11 +5067,7 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 * it may impact the display and we are uncertain about the stability
 	 * of the reset, so this could be applied to even earlier gen.
 	 */
-	err = -ENODEV;
-	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
-		err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
-	if (!err)
-		intel_engines_sanitize(i915);
+	intel_engines_sanitize(i915, false);
 
 	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
 	intel_runtime_pm_put(i915);
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 6350db5503cd..6a4441817638 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -82,6 +82,7 @@
 	.display.has_overlay = 1, \
 	.display.overlay_needs_physical = 1, \
 	.display.has_gmch_display = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.hws_needs_physical = 1, \
 	.unfenced_needs_alignment = 1, \
 	.ring_mask = RENDER_RING, \
@@ -122,6 +123,7 @@ static const struct intel_device_info intel_i865g_info = {
 	GEN(3), \
 	.num_pipes = 2, \
 	.display.has_gmch_display = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
@@ -198,6 +200,7 @@ static const struct intel_device_info intel_pineview_info = {
 	.num_pipes = 2, \
 	.display.has_hotplug = 1, \
 	.display.has_gmch_display = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
@@ -228,6 +231,7 @@ static const struct intel_device_info intel_g45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_G45),
 	.ring_mask = RENDER_RING | BSD_RING,
+	.gpu_reset_clobbers_display = false,
 };
 
 static const struct intel_device_info intel_gm45_info = {
@@ -237,6 +241,7 @@ static const struct intel_device_info intel_gm45_info = {
 	.display.has_fbc = 1,
 	.display.supports_tv = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
+	.gpu_reset_clobbers_display = false,
 };
 
 #define GEN5_FEATURES \
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index dd34f974a857..8fd683497956 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -89,6 +89,7 @@ enum intel_ppgtt {
 	func(is_alpha_support); \
 	/* Keep has_* in alphabetical order */ \
 	func(has_64bit_reloc); \
+	func(gpu_reset_clobbers_display); \
 	func(has_reset_engine); \
 	func(has_fpga_dbg); \
 	func(has_guc); \
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 13e5650b6f31..a9b2a4a530a4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3746,8 +3746,8 @@ __intel_display_resume(struct drm_device *dev,
 
 static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv)
 {
-	return intel_has_gpu_reset(dev_priv) &&
-		INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv);
+	return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display &&
+		intel_has_gpu_reset(dev_priv));
 }
 
 void intel_prepare_reset(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index ff5b7bc692ce..71636e009f13 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1030,22 +1030,34 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 		engine->set_default_submission(engine);
 }
 
+static bool reset_engines(struct drm_i915_private *i915)
+{
+	if (INTEL_INFO(i915)->gpu_reset_clobbers_display)
+		return false;
+
+	return intel_gpu_reset(i915, ALL_ENGINES) == 0;
+}
+
 /**
  * intel_engines_sanitize: called after the GPU has lost power
  * @i915: the i915 device
+ * @force: ignore a failed reset and sanitize engine state anyway
  *
  * Anytime we reset the GPU, either with an explicit GPU reset or through a
  * PCI power cycle, the GPU loses state and we must reset our state tracking
  * to match. Note that calling intel_engines_sanitize() if the GPU has not
  * been reset results in much confusion!
  */
-void intel_engines_sanitize(struct drm_i915_private *i915)
+void intel_engines_sanitize(struct drm_i915_private *i915, bool force)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
 	GEM_TRACE("\n");
 
+	if (!reset_engines(i915) && !force)
+		return;
+
 	for_each_engine(engine, i915, id) {
 		if (engine->reset.reset)
 			engine->reset.reset(engine, NULL);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 72edaa7ff411..1519f36e8c19 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1092,7 +1092,7 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset)
 	return cs;
 }
 
-void intel_engines_sanitize(struct drm_i915_private *i915);
+void intel_engines_sanitize(struct drm_i915_private *i915, bool force);
 
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index d0aa19d17653..bdcc53e15e75 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -121,7 +121,7 @@ static void pm_resume(struct drm_i915_private *i915)
 	 */
 	intel_runtime_pm_get(i915);
 
-	intel_engines_sanitize(i915);
+	intel_engines_sanitize(i915, false);
 	i915_gem_sanitize(i915);
 	i915_gem_resume(i915);
 
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 09/19] drm/i915: Report the number of closed vma held by each context in debugfs

[Chris Wilson]

Include the total size of closed vma when reporting the per_ctx_stats of
debugfs/i915_gem_objects.

Whilst adjusting the context tracking, note that we can simply use our
list of contexts in i915->contexts rather than circumlocute via
dev->filelist and the per-file context idr, with the result that we can
show objects allocated to different vm (i.e. contexts within a file).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 124 +++++++++++-----------------
 1 file changed, 47 insertions(+), 77 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 40a61ef9aac1..21d122024707 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -297,11 +297,12 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 }
 
 struct file_stats {
-	struct drm_i915_file_private *file_priv;
+	struct i915_address_space *vm;
 	unsigned long count;
 	u64 total, unbound;
 	u64 global, shared;
 	u64 active, inactive;
+	u64 closed;
 };
 
 static int per_file_stats(int id, void *ptr, void *data)
@@ -326,9 +327,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 		if (i915_vma_is_ggtt(vma)) {
 			stats->global += vma->node.size;
 		} else {
-			struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm);
-
-			if (ppgtt->vm.file != stats->file_priv)
+			if (vma->vm != stats->vm)
 				continue;
 		}
 
@@ -336,6 +335,9 @@ static int per_file_stats(int id, void *ptr, void *data)
 			stats->active += vma->node.size;
 		else
 			stats->inactive += vma->node.size;
+
+		if (i915_vma_is_closed(vma))
+			stats->closed += vma->node.size;
 	}
 
 	return 0;
@@ -343,7 +345,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 
 #define print_file_stats(m, name, stats) do { \
 	if (stats.count) \
-		seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound)\n", \
+		seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound, %llu closed)\n", \
 			   name, \
 			   stats.count, \
 			   stats.total, \
@@ -351,20 +353,19 @@ static int per_file_stats(int id, void *ptr, void *data)
 			   stats.inactive, \
 			   stats.global, \
 			   stats.shared, \
-			   stats.unbound); \
+			   stats.unbound, \
+			   stats.closed); \
 } while (0)
 
 static void print_batch_pool_stats(struct seq_file *m,
 				   struct drm_i915_private *dev_priv)
 {
 	struct drm_i915_gem_object *obj;
-	struct file_stats stats;
 	struct intel_engine_cs *engine;
+	struct file_stats stats = {};
 	enum intel_engine_id id;
 	int j;
 
-	memset(&stats, 0, sizeof(stats));
-
 	for_each_engine(engine, dev_priv, id) {
 		for (j = 0; j < ARRAY_SIZE(engine->batch_pool.cache_list); j++) {
 			list_for_each_entry(obj,
@@ -377,44 +378,47 @@ static void print_batch_pool_stats(struct seq_file *m,
 	print_file_stats(m, "[k]batch pool", stats);
 }
 
-static int per_file_ctx_stats(int idx, void *ptr, void *data)
+static void print_context_stats(struct seq_file *m,
+				struct drm_i915_private *i915)
 {
-	struct i915_gem_context *ctx = ptr;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	struct file_stats kstats = {};
+	struct i915_gem_context *ctx;
 
-	for_each_engine(engine, ctx->i915, id) {
-		struct intel_context *ce = to_intel_context(ctx, engine);
+	list_for_each_entry(ctx, &i915->contexts.list, link) {
+		struct intel_engine_cs *engine;
+		enum intel_engine_id id;
 
-		if (ce->state)
-			per_file_stats(0, ce->state->obj, data);
-		if (ce->ring)
-			per_file_stats(0, ce->ring->vma->obj, data);
-	}
+		for_each_engine(engine, i915, id) {
+			struct intel_context *ce = to_intel_context(ctx, engine);
 
-	return 0;
-}
+			if (ce->state)
+				per_file_stats(0, ce->state->obj, &kstats);
+			if (ce->ring)
+				per_file_stats(0, ce->ring->vma->obj, &kstats);
+		}
 
-static void print_context_stats(struct seq_file *m,
-				struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = &dev_priv->drm;
-	struct file_stats stats;
-	struct drm_file *file;
+		if (!IS_ERR_OR_NULL(ctx->file_priv)) {
+			struct file_stats stats = { .vm = &ctx->ppgtt->vm, };
+			struct drm_file *file = ctx->file_priv->file;
+			struct task_struct *task;
+			char name[80];
 
-	memset(&stats, 0, sizeof(stats));
+			spin_lock(&file->table_lock);
+			idr_for_each(&file->object_idr, per_file_stats, &stats);
+			spin_unlock(&file->table_lock);
 
-	mutex_lock(&dev->struct_mutex);
-	if (dev_priv->kernel_context)
-		per_file_ctx_stats(0, dev_priv->kernel_context, &stats);
+			rcu_read_lock();
+			task = pid_task(ctx->pid ?: file->pid, PIDTYPE_PID);
+			snprintf(name, sizeof(name), "%s/%d",
+				 task ? task->comm : "<unknown>",
+				 ctx->user_handle);
+			rcu_read_unlock();
 
-	list_for_each_entry(file, &dev->filelist, lhead) {
-		struct drm_i915_file_private *fpriv = file->driver_priv;
-		idr_for_each(&fpriv->context_idr, per_file_ctx_stats, &stats);
+			print_file_stats(m, name, stats);
+		}
 	}
-	mutex_unlock(&dev->struct_mutex);
 
-	print_file_stats(m, "[k]contexts", stats);
+	print_file_stats(m, "[k]contexts", kstats);
 }
 
 static int i915_gem_object_info(struct seq_file *m, void *data)
@@ -426,14 +430,9 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 	u64 size, mapped_size, purgeable_size, dpy_size, huge_size;
 	struct drm_i915_gem_object *obj;
 	unsigned int page_sizes = 0;
-	struct drm_file *file;
 	char buf[80];
 	int ret;
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
 	seq_printf(m, "%u objects, %llu bytes\n",
 		   dev_priv->mm.object_count,
 		   dev_priv->mm.object_memory);
@@ -514,43 +513,14 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 					buf, sizeof(buf)));
 
 	seq_putc(m, '\n');
-	print_batch_pool_stats(m, dev_priv);
-	mutex_unlock(&dev->struct_mutex);
-
-	mutex_lock(&dev->filelist_mutex);
-	print_context_stats(m, dev_priv);
-	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
-		struct file_stats stats;
-		struct drm_i915_file_private *file_priv = file->driver_priv;
-		struct i915_request *request;
-		struct task_struct *task;
-
-		mutex_lock(&dev->struct_mutex);
 
-		memset(&stats, 0, sizeof(stats));
-		stats.file_priv = file->driver_priv;
-		spin_lock(&file->table_lock);
-		idr_for_each(&file->object_idr, per_file_stats, &stats);
-		spin_unlock(&file->table_lock);
-		/*
-		 * Although we have a valid reference on file->pid, that does
-		 * not guarantee that the task_struct who called get_pid() is
-		 * still alive (e.g. get_pid(current) => fork() => exit()).
-		 * Therefore, we need to protect this ->comm access using RCU.
-		 */
-		request = list_first_entry_or_null(&file_priv->mm.request_list,
-						   struct i915_request,
-						   client_link);
-		rcu_read_lock();
-		task = pid_task(request && request->gem_context->pid ?
-				request->gem_context->pid : file->pid,
-				PIDTYPE_PID);
-		print_file_stats(m, task ? task->comm : "<unknown>", stats);
-		rcu_read_unlock();
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
-		mutex_unlock(&dev->struct_mutex);
-	}
-	mutex_unlock(&dev->filelist_mutex);
+	print_batch_pool_stats(m, dev_priv);
+	print_context_stats(m, dev_priv);
+	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 10/19] drm/i915: Remove debugfs/i915_ppgtt_info

[Chris Wilson]

The information presented here is not relevant to current development.
We can either use the context information, but more often we want to
inspect the active gpu state.

The ulterior motive is to eradicate dev->filelist.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 119 ------------------------
 drivers/gpu/drm/i915/i915_gem_gtt.c | 134 ----------------------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |   2 -
 3 files changed, 255 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 21d122024707..06d407d4102d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2046,124 +2046,6 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int per_file_ctx(int id, void *ptr, void *data)
-{
-	struct i915_gem_context *ctx = ptr;
-	struct seq_file *m = data;
-	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
-
-	if (!ppgtt) {
-		seq_printf(m, "  no ppgtt for context %d\n",
-			   ctx->user_handle);
-		return 0;
-	}
-
-	if (i915_gem_context_is_default(ctx))
-		seq_puts(m, "  default context:\n");
-	else
-		seq_printf(m, "  context %d:\n", ctx->user_handle);
-	ppgtt->debug_dump(ppgtt, m);
-
-	return 0;
-}
-
-static void gen8_ppgtt_info(struct seq_file *m,
-			    struct drm_i915_private *dev_priv)
-{
-	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int i;
-
-	if (!ppgtt)
-		return;
-
-	for_each_engine(engine, dev_priv, id) {
-		seq_printf(m, "%s\n", engine->name);
-		for (i = 0; i < 4; i++) {
-			u64 pdp = I915_READ(GEN8_RING_PDP_UDW(engine, i));
-			pdp <<= 32;
-			pdp |= I915_READ(GEN8_RING_PDP_LDW(engine, i));
-			seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp);
-		}
-	}
-}
-
-static void gen6_ppgtt_info(struct seq_file *m,
-			    struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	if (IS_GEN6(dev_priv))
-		seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE));
-
-	for_each_engine(engine, dev_priv, id) {
-		seq_printf(m, "%s\n", engine->name);
-		if (IS_GEN7(dev_priv))
-			seq_printf(m, "GFX_MODE: 0x%08x\n",
-				   I915_READ(RING_MODE_GEN7(engine)));
-		seq_printf(m, "PP_DIR_BASE: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_BASE(engine)));
-		seq_printf(m, "PP_DIR_BASE_READ: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_BASE_READ(engine)));
-		seq_printf(m, "PP_DIR_DCLV: 0x%08x\n",
-			   I915_READ(RING_PP_DIR_DCLV(engine)));
-	}
-	if (dev_priv->mm.aliasing_ppgtt) {
-		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-
-		seq_puts(m, "aliasing PPGTT:\n");
-		seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.base.ggtt_offset);
-
-		ppgtt->debug_dump(ppgtt, m);
-	}
-
-	seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK));
-}
-
-static int i915_ppgtt_info(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct drm_file *file;
-	int ret;
-
-	mutex_lock(&dev->filelist_mutex);
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		goto out_unlock;
-
-	intel_runtime_pm_get(dev_priv);
-
-	if (INTEL_GEN(dev_priv) >= 8)
-		gen8_ppgtt_info(m, dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_ppgtt_info(m, dev_priv);
-
-	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
-		struct drm_i915_file_private *file_priv = file->driver_priv;
-		struct task_struct *task;
-
-		task = get_pid_task(file->pid, PIDTYPE_PID);
-		if (!task) {
-			ret = -ESRCH;
-			goto out_rpm;
-		}
-		seq_printf(m, "\nproc: %s\n", task->comm);
-		put_task_struct(task);
-		idr_for_each(&file_priv->context_idr, per_file_ctx,
-			     (void *)(unsigned long)m);
-	}
-
-out_rpm:
-	intel_runtime_pm_put(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
-out_unlock:
-	mutex_unlock(&dev->filelist_mutex);
-	return ret;
-}
-
 static int count_irq_waiters(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
@@ -4882,7 +4764,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_context_status", i915_context_status, 0},
 	{"i915_forcewake_domains", i915_forcewake_domains, 0},
 	{"i915_swizzle_info", i915_swizzle_info, 0},
-	{"i915_ppgtt_info", i915_ppgtt_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
 	{"i915_energy_uJ", i915_energy_uJ, 0},
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 62bde517d383..9f5eeae5af2b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1488,84 +1488,6 @@ static int gen8_ppgtt_alloc_4lvl(struct i915_address_space *vm,
 	return -ENOMEM;
 }
 
-static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
-			  struct i915_page_directory_pointer *pdp,
-			  u64 start, u64 length,
-			  gen8_pte_t scratch_pte,
-			  struct seq_file *m)
-{
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct i915_page_directory *pd;
-	u32 pdpe;
-
-	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
-		struct i915_page_table *pt;
-		u64 pd_len = length;
-		u64 pd_start = start;
-		u32 pde;
-
-		if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd)
-			continue;
-
-		seq_printf(m, "\tPDPE #%d\n", pdpe);
-		gen8_for_each_pde(pt, pd, pd_start, pd_len, pde) {
-			u32 pte;
-			gen8_pte_t *pt_vaddr;
-
-			if (pd->page_table[pde] == ppgtt->vm.scratch_pt)
-				continue;
-
-			pt_vaddr = kmap_atomic_px(pt);
-			for (pte = 0; pte < GEN8_PTES; pte += 4) {
-				u64 va = (pdpe << GEN8_PDPE_SHIFT |
-					  pde << GEN8_PDE_SHIFT |
-					  pte << GEN8_PTE_SHIFT);
-				int i;
-				bool found = false;
-
-				for (i = 0; i < 4; i++)
-					if (pt_vaddr[pte + i] != scratch_pte)
-						found = true;
-				if (!found)
-					continue;
-
-				seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte);
-				for (i = 0; i < 4; i++) {
-					if (pt_vaddr[pte + i] != scratch_pte)
-						seq_printf(m, " %llx", pt_vaddr[pte + i]);
-					else
-						seq_puts(m, "  SCRATCH ");
-				}
-				seq_puts(m, "\n");
-			}
-			kunmap_atomic(pt_vaddr);
-		}
-	}
-}
-
-static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
-{
-	struct i915_address_space *vm = &ppgtt->vm;
-	const gen8_pte_t scratch_pte = vm->scratch_pte;
-	u64 start = 0, length = ppgtt->vm.total;
-
-	if (use_4lvl(vm)) {
-		u64 pml4e;
-		struct i915_pml4 *pml4 = &ppgtt->pml4;
-		struct i915_page_directory_pointer *pdp;
-
-		gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
-			if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp)
-				continue;
-
-			seq_printf(m, "    PML4E #%llu\n", pml4e);
-			gen8_dump_pdp(ppgtt, pdp, start, length, scratch_pte, m);
-		}
-	} else {
-		gen8_dump_pdp(ppgtt, &ppgtt->pdp, start, length, scratch_pte, m);
-	}
-}
-
 static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt)
 {
 	struct i915_address_space *vm = &ppgtt->vm;
@@ -1670,7 +1592,6 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
 	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
-	ppgtt->debug_dump = gen8_dump_ppgtt;
 
 	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
 	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
@@ -1686,60 +1607,6 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	return ERR_PTR(err);
 }
 
-static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
-{
-	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	const gen6_pte_t scratch_pte = base->vm.scratch_pte;
-	struct i915_page_table *pt;
-	u32 pte, pde;
-
-	gen6_for_all_pdes(pt, &base->pd, pde) {
-		gen6_pte_t *vaddr;
-
-		if (pt == base->vm.scratch_pt)
-			continue;
-
-		if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND)) {
-			u32 expected =
-				GEN6_PDE_ADDR_ENCODE(px_dma(pt)) |
-				GEN6_PDE_VALID;
-			u32 pd_entry = readl(ppgtt->pd_addr + pde);
-
-			if (pd_entry != expected)
-				seq_printf(m,
-					   "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
-					   pde,
-					   pd_entry,
-					   expected);
-
-			seq_printf(m, "\tPDE: %x\n", pd_entry);
-		}
-
-		vaddr = kmap_atomic_px(base->pd.page_table[pde]);
-		for (pte = 0; pte < GEN6_PTES; pte += 4) {
-			int i;
-
-			for (i = 0; i < 4; i++)
-				if (vaddr[pte + i] != scratch_pte)
-					break;
-			if (i == 4)
-				continue;
-
-			seq_printf(m, "\t\t(%03d, %04d) %08llx: ",
-				   pde, pte,
-				   (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE);
-			for (i = 0; i < 4; i++) {
-				if (vaddr[pte + i] != scratch_pte)
-					seq_printf(m, " %08x", vaddr[pte + i]);
-				else
-					seq_puts(m, "  SCRATCH");
-			}
-			seq_puts(m, "\n");
-		}
-		kunmap_atomic(vaddr);
-	}
-}
-
 /* Write pde (index) from the page directory @pd to the page table @pt */
 static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt,
 				  const unsigned int pde,
@@ -2127,7 +1994,6 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
-	ppgtt->base.debug_dump = gen6_dump_ppgtt;
 
 	ppgtt->base.vm.vma_ops.bind_vma    = ppgtt_bind_vma;
 	ppgtt->base.vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 4874da09a3c4..e2360f16427a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -413,8 +413,6 @@ struct i915_hw_ppgtt {
 		struct i915_page_directory_pointer pdp;	/* GEN8+ */
 		struct i915_page_directory pd;		/* GEN6-7 */
 	};
-
-	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
 struct gen6_hw_ppgtt {
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 11/19] drm/i915: Track all held rpm wakerefs

[Chris Wilson]

Everytime we take a wakeref, record the stack trace of where it was
taken; clearing the set if we ever drop back to no owners. For debugging
a rpm leak, we can look at all the current wakerefs and check if they
have a matching rpm_put.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig.debug            |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |   6 +
 drivers/gpu/drm/i915/i915_drv.c               |   8 +-
 drivers/gpu/drm/i915/i915_drv.h               |   7 +
 drivers/gpu/drm/i915/intel_drv.h              |  44 ++-
 drivers/gpu/drm/i915/intel_runtime_pm.c       | 267 ++++++++++++++++--
 .../gpu/drm/i915/selftests/mock_gem_device.c  |   8 +-
 7 files changed, 292 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 9e36ffb5eb7c..a97929c47466 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -21,11 +21,11 @@ config DRM_I915_DEBUG
         select DEBUG_FS
         select PREEMPT_COUNT
         select I2C_CHARDEV
+        select STACKDEPOT
         select DRM_DP_AUX_CHARDEV
         select X86_MSR # used by igt/pm_rpm
         select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
         select DRM_DEBUG_MM if DRM=y
-        select STACKDEPOT if DRM=y # for DRM_DEBUG_MM
 	select DRM_DEBUG_SELFTEST
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 06d407d4102d..424c919f66da 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2726,6 +2726,12 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 		   pci_power_name(pdev->current_state),
 		   pdev->current_state);
 
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)) {
+		struct drm_printer p = drm_seq_file_printer(m);
+
+		print_intel_runtime_pm_wakeref(dev_priv, &p);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f6c2a096ee3c..7653c741bb78 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -906,6 +906,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->pps_mutex);
 
 	i915_memcpy_init_early(dev_priv);
+	intel_runtime_pm_init_early(dev_priv);
 
 	ret = i915_workqueues_init(dev_priv);
 	if (ret < 0)
@@ -1802,8 +1803,7 @@ void i915_driver_unload(struct drm_device *dev)
 	i915_driver_cleanup_mmio(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);
-
-	WARN_ON(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 }
 
 static void i915_driver_release(struct drm_device *dev)
@@ -2005,6 +2005,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 out:
 	enable_rpm_wakeref_asserts(dev_priv);
+	if (!dev_priv->uncore.user_forcewake.count)
+		intel_runtime_pm_cleanup(dev_priv);
 
 	return ret;
 }
@@ -2959,7 +2961,7 @@ static int intel_runtime_suspend(struct device *kdev)
 	}
 
 	enable_rpm_wakeref_asserts(dev_priv);
-	WARN_ON_ONCE(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 
 	if (intel_uncore_arm_unclaimed_mmio_detection(dev_priv))
 		DRM_ERROR("Unclaimed access detected prior to suspending\n");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f625a5c40ca3..1c8dba661cda 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -45,6 +45,7 @@
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
 #include <linux/shmem_fs.h>
+#include <linux/stackdepot.h>
 
 #include <drm/drmP.h>
 #include <drm/intel-gtt.h>
@@ -1154,6 +1155,12 @@ struct i915_runtime_pm {
 	atomic_t wakeref_count;
 	bool suspended;
 	bool irqs_enabled;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+	spinlock_t debug_lock;
+	depot_stack_handle_t *debug_owners;
+	unsigned long debug_count;
+#endif
 };
 
 enum intel_pipe_crc_source {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d08f08f607dd..5cd851390672 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -41,6 +41,8 @@
 #include <drm/drm_atomic.h>
 #include <media/cec-notifier.h>
 
+struct drm_printer;
+
 /**
  * __wait_for - magic wait macro
  *
@@ -2075,6 +2077,7 @@ bool intel_psr_enabled(struct intel_dp *intel_dp);
 void intel_init_quirks(struct drm_i915_private *dev_priv);
 
 /* intel_runtime_pm.c */
+void intel_runtime_pm_init_early(struct drm_i915_private *dev_priv);
 int intel_power_domains_init(struct drm_i915_private *);
 void intel_power_domains_cleanup(struct drm_i915_private *dev_priv);
 void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume);
@@ -2097,6 +2100,7 @@ void bxt_display_core_init(struct drm_i915_private *dev_priv, bool resume);
 void bxt_display_core_uninit(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_enable(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_disable(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_cleanup(struct drm_i915_private *dev_priv);
 const char *
 intel_display_power_domain_str(enum intel_display_power_domain domain);
 
@@ -2114,23 +2118,23 @@ void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 			    u8 req_slices);
 
 static inline void
-assert_rpm_device_not_suspended(struct drm_i915_private *dev_priv)
+assert_rpm_device_not_suspended(struct drm_i915_private *i915)
 {
-	WARN_ONCE(dev_priv->runtime_pm.suspended,
+	WARN_ONCE(i915->runtime_pm.suspended,
 		  "Device suspended during HW access\n");
 }
 
 static inline void
-assert_rpm_wakelock_held(struct drm_i915_private *dev_priv)
+assert_rpm_wakelock_held(struct drm_i915_private *i915)
 {
-	assert_rpm_device_not_suspended(dev_priv);
-	WARN_ONCE(!atomic_read(&dev_priv->runtime_pm.wakeref_count),
+	assert_rpm_device_not_suspended(i915);
+	WARN_ONCE(!atomic_read(&i915->runtime_pm.wakeref_count),
 		  "RPM wakelock ref not held during HW access");
 }
 
 /**
  * disable_rpm_wakeref_asserts - disable the RPM assert checks
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function disable asserts that check if we hold an RPM wakelock
  * reference, while keeping the device-not-suspended checks still enabled.
@@ -2147,14 +2151,14 @@ assert_rpm_wakelock_held(struct drm_i915_private *dev_priv)
  * enable_rpm_wakeref_asserts().
  */
 static inline void
-disable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
+disable_rpm_wakeref_asserts(struct drm_i915_private *i915)
 {
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
 }
 
 /**
  * enable_rpm_wakeref_asserts - re-enable the RPM assert checks
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function re-enables the RPM assert checks after disabling them with
  * disable_rpm_wakeref_asserts. It's meant to be used only in special
@@ -2164,15 +2168,25 @@ disable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
  * disable_rpm_wakeref_asserts().
  */
 static inline void
-enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
+enable_rpm_wakeref_asserts(struct drm_i915_private *i915)
 {
-	atomic_dec(&dev_priv->runtime_pm.wakeref_count);
+	atomic_dec(&i915->runtime_pm.wakeref_count);
 }
 
-void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv);
-void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
-void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_get(struct drm_i915_private *i915);
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915);
+void intel_runtime_pm_get_noresume(struct drm_i915_private *i915);
+void intel_runtime_pm_put(struct drm_i915_private *i915);
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+				    struct drm_printer *p);
+#else
+static inline void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+						  struct drm_printer *p)
+{
+}
+#endif
 
 void chv_phy_powergate_lanes(struct intel_encoder *encoder,
 			     bool override, unsigned int mask);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 4350a5270423..d98f73bd7358 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -29,6 +29,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/vgaarb.h>
 
+#include <drm/drm_print.h>
+
 #include "i915_drv.h"
 #include "intel_drv.h"
 
@@ -49,6 +51,189 @@
  * present for a given platform.
  */
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+
+#include <linux/sort.h>
+
+#define STACKDEPTH 8
+
+static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	spin_lock_init(&i915->runtime_pm.debug_lock);
+}
+
+static noinline void
+track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	unsigned long entries[STACKDEPTH];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+		.skip = 1
+	};
+	unsigned long flags;
+	depot_stack_handle_t stack, *stacks;
+
+	if (!HAS_RUNTIME_PM(i915))
+		return;
+
+	save_stack_trace(&trace);
+	if (trace.nr_entries &&
+	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
+		trace.nr_entries--;
+
+	stack = depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	if (!stack)
+		return;
+
+	spin_lock_irqsave(&rpm->debug_lock, flags);
+	stacks = krealloc(rpm->debug_owners,
+			  (rpm->debug_count + 1) * sizeof(*stacks),
+			  GFP_NOWAIT | __GFP_NOWARN);
+	if (stacks) {
+		stacks[rpm->debug_count++] = stack;
+		rpm->debug_owners = stacks;
+	}
+	spin_unlock_irqrestore(&rpm->debug_lock, flags);
+}
+
+static void untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	depot_stack_handle_t *stacks;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rpm->debug_lock, flags);
+	stacks = fetch_and_zero(&rpm->debug_owners);
+	rpm->debug_count = 0;
+	spin_unlock_irqrestore(&rpm->debug_lock, flags);
+
+	kfree(stacks);
+}
+
+static int cmphandle(const void *_a, const void *_b)
+{
+	const depot_stack_handle_t * const a = _a, * const b = _b;
+
+	if (*a < *b)
+		return -1;
+	else if (*a > *b)
+		return 1;
+	else
+		return 0;
+}
+
+static void __print_intel_runtime_pm_wakeref(struct drm_printer *p,
+					     depot_stack_handle_t *stacks,
+					     unsigned long count)
+{
+	unsigned long entries[STACKDEPTH];
+	unsigned long i;
+	char *buf;
+
+	drm_printf(p, "Wakeref count: %lu\n", count);
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	sort(stacks, count, sizeof(*stacks), cmphandle, NULL);
+
+	for (i = 0; i < count; i++) {
+		struct stack_trace trace = {
+			.entries = entries,
+			.max_entries = ARRAY_SIZE(entries),
+		};
+		depot_stack_handle_t stack = stacks[i];
+		unsigned long rep;
+
+		rep = 1;
+		while (i + 1 < count && stacks[i + 1] == stack)
+			rep++, i++;
+		depot_fetch_stack(stack, &trace);
+		snprint_stack_trace(buf, PAGE_SIZE, &trace, 2);
+		drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf);
+	}
+
+	kfree(buf);
+}
+
+static void show_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	depot_stack_handle_t *stacks;
+	unsigned long flags, count;
+	struct drm_printer p;
+
+	spin_lock_irqsave(&rpm->debug_lock, flags);
+	stacks = fetch_and_zero(&rpm->debug_owners);
+	count = fetch_and_zero(&rpm->debug_count);
+	spin_unlock_irqrestore(&rpm->debug_lock, flags);
+	if (!count)
+		return;
+
+	p = drm_debug_printer("i915");
+	__print_intel_runtime_pm_wakeref(&p, stacks, count);
+
+	kfree(stacks);
+}
+
+void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+				    struct drm_printer *p)
+{
+	depot_stack_handle_t *stacks = NULL;
+	unsigned long count = 0;
+
+	do {
+		struct i915_runtime_pm *rpm = &i915->runtime_pm;
+		unsigned long alloc = count;
+		depot_stack_handle_t *s;
+
+		spin_lock_irq(&rpm->debug_lock);
+		count = rpm->debug_count;
+		if (count == alloc) {
+			memcpy(stacks,
+			       rpm->debug_owners,
+			       count * sizeof(*stacks));
+		}
+		spin_unlock_irq(&rpm->debug_lock);
+		if (count == alloc)
+			break;
+
+		s = krealloc(stacks, count * sizeof(*stacks), GFP_KERNEL);
+		if (!s)
+			goto out;
+
+		stacks = s;
+	} while (1);
+
+	__print_intel_runtime_pm_wakeref(p, stacks, count);
+
+out:
+	kfree(stacks);
+}
+
+#else
+
+static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void show_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+#endif
+
 bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
 					 enum i915_power_well_id power_well_id);
 
@@ -3986,7 +4171,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
 
 /**
  * intel_runtime_pm_get - grab a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference (mostly used for GEM
  * code to ensure the GTT or GT is on) and ensures that it is powered up.
@@ -3994,22 +4179,24 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_get(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 	int ret;
 
 	ret = pm_runtime_get_sync(kdev);
 	WARN_ONCE(ret < 0, "pm_runtime_get_sync() failed: %d\n", ret);
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
-	assert_rpm_wakelock_held(dev_priv);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+
+	track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
  * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference if the device is
  * already in use and ensures that it is powered up. It is illegal to try
@@ -4020,10 +4207,10 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
  *
  * Returns: True if the wakeref was acquired, or False otherwise.
  */
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
 {
 	if (IS_ENABLED(CONFIG_PM)) {
-		struct pci_dev *pdev = dev_priv->drm.pdev;
+		struct pci_dev *pdev = i915->drm.pdev;
 		struct device *kdev = &pdev->dev;
 
 		/*
@@ -4036,15 +4223,17 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
 			return false;
 	}
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
-	assert_rpm_wakelock_held(dev_priv);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+
+	track_intel_runtime_pm_wakeref(i915);
 
 	return true;
 }
 
 /**
  * intel_runtime_pm_get_noresume - grab a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference (mostly used for GEM
  * code to ensure the GTT or GT is on).
@@ -4059,32 +4248,35 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
-	assert_rpm_wakelock_held(dev_priv);
+	assert_rpm_wakelock_held(i915);
 	pm_runtime_get_noresume(kdev);
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+
+	track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
  * intel_runtime_pm_put - release a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function drops the device-level runtime pm reference obtained by
  * intel_runtime_pm_get() and might power down the corresponding
  * hardware block right away if this is the last reference.
  */
-void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_put(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
-	assert_rpm_wakelock_held(dev_priv);
-	atomic_dec(&dev_priv->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+	if (atomic_dec_and_test(&i915->runtime_pm.wakeref_count))
+		untrack_intel_runtime_pm_wakeref(i915);
 
 	pm_runtime_mark_last_busy(kdev);
 	pm_runtime_put_autosuspend(kdev);
@@ -4092,7 +4284,7 @@ void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
 
 /**
  * intel_runtime_pm_enable - enable runtime pm
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function enables runtime pm at the end of the driver load sequence.
  *
@@ -4100,9 +4292,9 @@ void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
  * subordinate display power domains. That is done by
  * intel_power_domains_enable().
  */
-void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_enable(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
 	/*
@@ -4124,7 +4316,7 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	 * so the driver's own RPM reference tracking asserts also work on
 	 * platforms without RPM support.
 	 */
-	if (!HAS_RUNTIME_PM(dev_priv)) {
+	if (!HAS_RUNTIME_PM(i915)) {
 		int ret;
 
 		pm_runtime_dont_use_autosuspend(kdev);
@@ -4142,17 +4334,36 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	pm_runtime_put_autosuspend(kdev);
 }
 
-void intel_runtime_pm_disable(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_disable(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
 	/* Transfer rpm ownership back to core */
-	WARN(pm_runtime_get_sync(&dev_priv->drm.pdev->dev) < 0,
+	WARN(pm_runtime_get_sync(kdev) < 0,
 	     "Failed to pass rpm ownership back to core\n");
 
 	pm_runtime_dont_use_autosuspend(kdev);
 
-	if (!HAS_RUNTIME_PM(dev_priv))
+	if (!HAS_RUNTIME_PM(i915))
 		pm_runtime_put(kdev);
 }
+
+void intel_runtime_pm_cleanup(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+
+	if (WARN(atomic_read(&rpm->wakeref_count),
+		 "i915->runtime_pm.wakeref_count=%d on cleanup\n",
+		 atomic_read(&rpm->wakeref_count))) {
+		show_intel_runtime_pm_wakeref(i915);
+		atomic_set(&rpm->wakeref_count, 0);
+	}
+
+	untrack_intel_runtime_pm_wakeref(i915);
+}
+
+void intel_runtime_pm_init_early(struct drm_i915_private *i915)
+{
+	init_intel_runtime_pm_wakeref(i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 43ed8b28aeaa..0eb283e7fc96 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -154,15 +154,17 @@ struct drm_i915_private *mock_gem_device(void)
 	pdev->dev.archdata.iommu = (void *)-1;
 #endif
 
+	i915 = (struct drm_i915_private *)(pdev + 1);
+	pci_set_drvdata(pdev, i915);
+
+	intel_runtime_pm_init_early(i915);
+
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	if (pm_runtime_enabled(&pdev->dev))
 		WARN_ON(pm_runtime_get_sync(&pdev->dev));
 
-	i915 = (struct drm_i915_private *)(pdev + 1);
-	pci_set_drvdata(pdev, i915);
-
 	err = drm_dev_init(&i915->drm, &mock_driver, &pdev->dev);
 	if (err) {
 		pr_err("Failed to initialise mock GEM device: err=%d\n", err);
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 12/19] drm/i915: Markup paired operations on wakerefs

[Chris Wilson]

The majority of runtime-pm operations are bounded and scoped within a
function; these are easy to verify that the wakeref are handled
correctly. We can employ the compiler to help us, and reduce the number
of wakerefs tracked when debugging, by passing around cookies provided
by the various rpm_get functions to their rpm_put counterpart. This
makes the pairing explicit, and given the required wakeref cookie the
compiler can verify that we pass an initialised value to the rpm_put
(quite handy for double checking error paths).

For regular builds, the compiler should be able to eliminate the unused
local variables and the program growth should be minimal. Fwiw, it came
out as a net improvement as gcc was able to refactor rpm_get and
rpm_get_if_in_use together,

add/remove: 1/1 grow/shrink: 20/9 up/down: 191/-268 (-77)
Function                                     old     new   delta
intel_runtime_pm_put_unchecked                 -     136    +136
i915_gem_unpark                              396     406     +10
intel_runtime_pm_get                         135     141      +6
intel_runtime_pm_get_noresume                136     141      +5
i915_perf_open_ioctl                        4375    4379      +4
i915_gpu_busy                                 72      76      +4
i915_gem_idle_work_handler                   954     958      +4
capture                                     6814    6818      +4
mock_gem_device                             1433    1436      +3
__execlists_submission_tasklet              2573    2576      +3
i915_sample                                  756     758      +2
intel_guc_submission_disable                 364     365      +1
igt_mmap_offset_exhaustion                  1035    1036      +1
i915_runtime_pm_status                       257     258      +1
i915_rps_boost_info                         1358    1359      +1
i915_hangcheck_info                         1229    1230      +1
i915_gem_switch_to_kernel_context            682     683      +1
i915_gem_suspend                             410     411      +1
i915_gem_resume                              254     255      +1
i915_gem_park                                190     191      +1
i915_engine_info                             279     280      +1
intel_rps_mark_interactive                   194     193      -1
i915_hangcheck_elapsed                      1526    1525      -1
i915_gem_wait_for_idle                       298     297      -1
i915_drop_caches_set                         555     554      -1
execlists_submission_tasklet                 126     125      -1
aliasing_gtt_bind_vma                        235     234      -1
i915_gem_retire_work_handler                 144     142      -2
igt_evict_contexts.part                      916     910      -6
intel_runtime_pm_get_if_in_use               141      23    -118
intel_runtime_pm_put                         136       -    -136

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig.debug            |   1 +
 drivers/gpu/drm/i915/gvt/aperture_gm.c        |   8 +-
 drivers/gpu/drm/i915/gvt/gvt.h                |   2 +-
 drivers/gpu/drm/i915/gvt/sched_policy.c       |   2 +-
 drivers/gpu/drm/i915/gvt/scheduler.c          |   4 +-
 drivers/gpu/drm/i915/i915_debugfs.c           | 142 +++++++++++-------
 drivers/gpu/drm/i915/i915_drv.h               |   6 +-
 drivers/gpu/drm/i915/i915_gem.c               |  58 ++++---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c    |   5 +-
 drivers/gpu/drm/i915/i915_gem_fence_reg.c     |   6 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c           |  22 ++-
 drivers/gpu/drm/i915/i915_gem_shrinker.c      |  27 ++--
 drivers/gpu/drm/i915/i915_irq.c               |   5 +-
 drivers/gpu/drm/i915/i915_perf.c              |  10 +-
 drivers/gpu/drm/i915/i915_pmu.c               |  26 ++--
 drivers/gpu/drm/i915/i915_sysfs.c             |  24 +--
 drivers/gpu/drm/i915/intel_display.c          |   5 +-
 drivers/gpu/drm/i915/intel_drv.h              |  15 +-
 drivers/gpu/drm/i915/intel_engine_cs.c        |  12 +-
 drivers/gpu/drm/i915/intel_fbdev.c            |   9 +-
 drivers/gpu/drm/i915/intel_guc_log.c          |  15 +-
 drivers/gpu/drm/i915/intel_hotplug.c          |   5 +-
 drivers/gpu/drm/i915/intel_huc.c              |   5 +-
 drivers/gpu/drm/i915/intel_panel.c            |   5 +-
 drivers/gpu/drm/i915/intel_runtime_pm.c       |  89 ++++++++---
 drivers/gpu/drm/i915/intel_uncore.c           |   5 +-
 drivers/gpu/drm/i915/selftests/huge_pages.c   |   5 +-
 drivers/gpu/drm/i915/selftests/i915_gem.c     |  29 ++--
 .../drm/i915/selftests/i915_gem_coherency.c   |   5 +-
 .../gpu/drm/i915/selftests/i915_gem_context.c |  27 ++--
 .../gpu/drm/i915/selftests/i915_gem_evict.c   |  11 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c |  10 +-
 .../gpu/drm/i915/selftests/i915_gem_object.c  |  18 ++-
 drivers/gpu/drm/i915/selftests/i915_request.c |  22 +--
 drivers/gpu/drm/i915/selftests/intel_guc.c    |  10 +-
 .../gpu/drm/i915/selftests/intel_hangcheck.c  |  10 +-
 drivers/gpu/drm/i915/selftests/intel_lrc.c    |  25 +--
 .../drm/i915/selftests/intel_workarounds.c    |  29 ++--
 38 files changed, 458 insertions(+), 256 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index a97929c47466..ad4d71161dda 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -173,6 +173,7 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	bool "Enable extra state checking for runtime PM"
 	depends on DRM_I915
 	default n
+	select STACKDEPOT
 	help
 	  Choose this option to turn on extra state checking for the
 	  runtime PM functionality. This may introduce overhead during
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 359d37d5c958..1fa2f65c3cd1 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -180,7 +180,7 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu)
 	}
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
@@ -206,7 +206,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 	_clear_vgpu_fence(vgpu);
 
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	return 0;
 out_free_fence:
 	gvt_vgpu_err("Failed to alloc fences\n");
@@ -219,7 +219,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 		vgpu->fence.regs[i] = NULL;
 	}
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	return -ENOSPC;
 }
 
@@ -317,7 +317,7 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
 
 	intel_runtime_pm_get(dev_priv);
 	_clear_vgpu_fence(vgpu);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index b4ab1dad0143..435c746c3f73 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -597,7 +597,7 @@ static inline void mmio_hw_access_pre(struct drm_i915_private *dev_priv)
 
 static inline void mmio_hw_access_post(struct drm_i915_private *dev_priv)
 {
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index c32e7d5e8629..f04b3b965bfc 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -474,6 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		}
 	}
 	spin_unlock_bh(&scheduler->mmio_context_lock);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	mutex_unlock(&vgpu->gvt->sched_lock);
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1ad8c5e1455d..3816dcae2185 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -997,7 +997,7 @@ static int workload_thread(void *priv)
 			intel_uncore_forcewake_put(gvt->dev_priv,
 					FORCEWAKE_ALL);
 
-		intel_runtime_pm_put(gvt->dev_priv);
+		intel_runtime_pm_put_unchecked(gvt->dev_priv);
 		if (ret && (vgpu_is_vm_unhealthy(ret)))
 			enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
 	}
@@ -1451,7 +1451,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 		mutex_lock(&dev_priv->drm.struct_mutex);
 		ret = intel_gvt_scan_and_shadow_workload(workload);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put_unchecked(dev_priv);
 	}
 
 	if (ret && (vgpu_is_vm_unhealthy(ret))) {
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 424c919f66da..18a7f81dadcd 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -674,9 +674,10 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int i, pipe;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
 		seq_printf(m, "Master Interrupt Control:\t%08x\n",
@@ -877,7 +878,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		}
 	}
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -950,10 +951,11 @@ static int i915_gpu_info_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *i915 = inode->i_private;
 	struct i915_gpu_state *gpu;
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	gpu = i915_capture_gpu_state(i915);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	if (IS_ERR(gpu))
 		return PTR_ERR(gpu);
 
@@ -1013,15 +1015,16 @@ i915_next_seqno_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
 	struct drm_device *dev = &dev_priv->drm;
+	intel_wakeref_t wakeref;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	ret = i915_gem_set_global_seqno(dev, val);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1036,9 +1039,10 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	intel_wakeref_t wakeref;
 	int ret = 0;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (IS_GEN5(dev_priv)) {
 		u16 rgvswctl = I915_READ16(MEMSWCTL);
@@ -1250,7 +1254,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 	seq_printf(m, "Max CD clock frequency: %d kHz\n", dev_priv->max_cdclk_freq);
 	seq_printf(m, "Max pixel clock frequency: %d kHz\n", dev_priv->max_dotclk_freq);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	return ret;
 }
 
@@ -1289,6 +1293,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	u64 acthd[I915_NUM_ENGINES];
 	u32 seqno[I915_NUM_ENGINES];
 	struct intel_instdone instdone;
+	intel_wakeref_t wakeref;
 	enum intel_engine_id id;
 
 	if (test_bit(I915_WEDGED, &dev_priv->gpu_error.flags))
@@ -1307,7 +1312,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		return 0;
 	}
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
 		acthd[id] = intel_engine_get_active_head(engine);
@@ -1316,7 +1321,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 
 	intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	if (timer_pending(&dev_priv->gpu_error.hangcheck_work.timer))
 		seq_printf(m, "Hangcheck active, timer fires in %dms\n",
@@ -1592,9 +1597,10 @@ static int gen6_drpc_info(struct seq_file *m)
 static int i915_drpc_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	int err;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		err = vlv_drpc_info(m);
@@ -1603,7 +1609,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 	else
 		err = ironlake_drpc_info(m);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return err;
 }
@@ -1625,11 +1631,12 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_fbc *fbc = &dev_priv->fbc;
+	intel_wakeref_t wakeref;
 
 	if (!HAS_FBC(dev_priv))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	mutex_lock(&fbc->lock);
 
 	if (intel_fbc_is_active(dev_priv))
@@ -1656,7 +1663,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	}
 
 	mutex_unlock(&fbc->lock);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -1701,11 +1708,12 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_fbc_false_color_fops,
 static int i915_ips_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 
 	if (!HAS_IPS(dev_priv))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "Enabled by kernel parameter: %s\n",
 		   yesno(i915_modparams.enable_ips));
@@ -1719,7 +1727,7 @@ static int i915_ips_status(struct seq_file *m, void *unused)
 			seq_puts(m, "Currently: disabled\n");
 	}
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -1727,9 +1735,10 @@ static int i915_ips_status(struct seq_file *m, void *unused)
 static int i915_sr_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	bool sr_enabled = false;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
 
 	if (INTEL_GEN(dev_priv) >= 9)
@@ -1747,7 +1756,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 		sr_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	seq_printf(m, "self-refresh: %s\n", enableddisabled(sr_enabled));
 
@@ -1759,29 +1768,30 @@ static int i915_emon_status(struct seq_file *m, void *unused)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_device *dev = &dev_priv->drm;
 	unsigned long temp, chipset, gfx;
+	intel_wakeref_t wakeref;
 	int ret;
 
 	if (!IS_GEN5(dev_priv))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
-
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
+	wakeref = intel_runtime_pm_get(dev_priv);
+
 	temp = i915_mch_val(dev_priv);
 	chipset = i915_chipset_val(dev_priv);
 	gfx = i915_gfx_val(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_runtime_pm_put(dev_priv, wakeref);
+
 	seq_printf(m, "GMCH temp: %ld\n", temp);
 	seq_printf(m, "Chipset power: %ld\n", chipset);
 	seq_printf(m, "GFX power: %ld\n", gfx);
 	seq_printf(m, "Total power: %ld\n", chipset + gfx);
 
-	intel_runtime_pm_put(dev_priv);
-
 	return 0;
 }
 
@@ -1790,13 +1800,14 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	unsigned int max_gpu_freq, min_gpu_freq;
+	intel_wakeref_t wakeref;
 	int gpu_freq, ia_freq;
 	int ret;
 
 	if (!HAS_LLC(dev_priv))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	ret = mutex_lock_interruptible(&dev_priv->pcu_lock);
 	if (ret)
@@ -1829,7 +1840,7 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 	mutex_unlock(&dev_priv->pcu_lock);
 
 out:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	return ret;
 }
 
@@ -2002,8 +2013,9 @@ static const char *swizzle_string(unsigned swizzle)
 static int i915_swizzle_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "bit6 swizzle for X-tiling = %s\n",
 		   swizzle_string(dev_priv->mm.bit_6_swizzle_x));
@@ -2041,7 +2053,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 	if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES)
 		seq_puts(m, "L-shaped memory detected\n");
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -2078,9 +2090,11 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 act_freq = rps->cur_freq;
+	intel_wakeref_t wakeref;
 	struct drm_file *file;
 
-	if (intel_runtime_pm_get_if_in_use(dev_priv)) {
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (wakeref) {
 		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 			mutex_lock(&dev_priv->pcu_lock);
 			act_freq = vlv_punit_read(dev_priv,
@@ -2091,7 +2105,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 			act_freq = intel_get_cagf(dev_priv,
 						  I915_READ(GEN6_RPSTAT1));
 		}
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(dev_priv, wakeref);
 	}
 
 	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
@@ -2174,6 +2188,7 @@ static int i915_llc(struct seq_file *m, void *data)
 static int i915_huc_load_status_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	struct drm_printer p;
 
 	if (!HAS_HUC(dev_priv))
@@ -2182,9 +2197,9 @@ static int i915_huc_load_status_info(struct seq_file *m, void *data)
 	p = drm_seq_file_printer(m);
 	intel_uc_fw_dump(&dev_priv->huc.fw, &p);
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	seq_printf(m, "\nHuC status 0x%08x:\n", I915_READ(HUC_STATUS2));
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -2192,6 +2207,7 @@ static int i915_huc_load_status_info(struct seq_file *m, void *data)
 static int i915_guc_load_status_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	struct drm_printer p;
 	u32 tmp, i;
 
@@ -2201,7 +2217,7 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)
 	p = drm_seq_file_printer(m);
 	intel_uc_fw_dump(&dev_priv->guc.fw, &p);
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	tmp = I915_READ(GUC_STATUS);
 
@@ -2216,7 +2232,7 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)
 	for (i = 0; i < 16; i++)
 		seq_printf(m, "\t%2d: \t0x%x\n", i, I915_READ(SOFT_SCRATCH(i)));
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -2574,6 +2590,7 @@ psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
 static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	u32 psrperf = 0;
 	bool enabled = false;
 	bool sink_support;
@@ -2586,7 +2603,7 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	if (!sink_support)
 		return 0;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->psr.lock);
 	seq_printf(m, "PSR mode: %s\n",
@@ -2625,7 +2642,7 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 			   dev_priv->psr.last_exit);
 	}
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	return 0;
 }
 
@@ -2634,6 +2651,7 @@ i915_edp_psr_debug_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
 	struct drm_modeset_acquire_ctx ctx;
+	intel_wakeref_t wakeref;
 	int ret;
 
 	if (!CAN_PSR(dev_priv))
@@ -2641,7 +2659,7 @@ i915_edp_psr_debug_set(void *data, u64 val)
 
 	DRM_DEBUG_KMS("Setting PSR debug to %llx\n", val);
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
 
@@ -2656,7 +2674,7 @@ i915_edp_psr_debug_set(void *data, u64 val)
 	drm_modeset_drop_locks(&ctx);
 	drm_modeset_acquire_fini(&ctx);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret;
 }
@@ -2681,15 +2699,16 @@ static int i915_energy_uJ(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	unsigned long long power;
+	intel_wakeref_t wakeref;
 	u32 units;
 
 	if (INTEL_GEN(dev_priv) < 6)
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &power)) {
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(dev_priv, wakeref);
 		return -ENODEV;
 	}
 
@@ -2697,7 +2716,7 @@ static int i915_energy_uJ(struct seq_file *m, void *data)
 	power = I915_READ(MCH_SECP_NRG_STTS);
 	power = (1000000 * power) >> units; /* convert to uJ */
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	seq_printf(m, "%llu", power);
 
@@ -2766,6 +2785,7 @@ static int i915_power_domain_info(struct seq_file *m, void *unused)
 static int i915_dmc_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 	struct intel_csr *csr;
 
 	if (!HAS_CSR(dev_priv))
@@ -2773,7 +2793,7 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 
 	csr = &dev_priv->csr;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "fw loaded: %s\n", yesno(csr->dmc_payload != NULL));
 	seq_printf(m, "path: %s\n", csr->fw_path);
@@ -2799,7 +2819,7 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 	seq_printf(m, "ssp base: 0x%08x\n", I915_READ(CSR_SSP_BASE));
 	seq_printf(m, "htp: 0x%08x\n", I915_READ(CSR_HTP_SKL));
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -3089,8 +3109,10 @@ static int i915_display_info(struct seq_file *m, void *unused)
 	struct intel_crtc *crtc;
 	struct drm_connector *connector;
 	struct drm_connector_list_iter conn_iter;
+	intel_wakeref_t wakeref;
+
+	wakeref = intel_runtime_pm_get(dev_priv);
 
-	intel_runtime_pm_get(dev_priv);
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
 	for_each_intel_crtc(dev, crtc) {
@@ -3138,7 +3160,7 @@ static int i915_display_info(struct seq_file *m, void *unused)
 	drm_connector_list_iter_end(&conn_iter);
 	mutex_unlock(&dev->mode_config.mutex);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -3147,10 +3169,11 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
 	enum intel_engine_id id;
 	struct drm_printer p;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	seq_printf(m, "GT awake? %s (epoch %u)\n",
 		   yesno(dev_priv->gt.awake), dev_priv->gt.epoch);
@@ -3163,7 +3186,7 @@ static int i915_engine_info(struct seq_file *m, void *unused)
 	for_each_engine(engine, dev_priv, id)
 		intel_engine_dump(engine, &p, "%s\n", engine->name);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return 0;
 }
@@ -3276,6 +3299,7 @@ static ssize_t i915_ipc_status_write(struct file *file, const char __user *ubuf,
 {
 	struct seq_file *m = file->private_data;
 	struct drm_i915_private *dev_priv = m->private;
+	intel_wakeref_t wakeref;
 	int ret;
 	bool enable;
 
@@ -3283,13 +3307,15 @@ static ssize_t i915_ipc_status_write(struct file *file, const char __user *ubuf,
 	if (ret < 0)
 		return ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
+
 	if (!dev_priv->ipc_enabled && enable)
 		DRM_INFO("Enabling IPC: WM will be proper only after next commit\n");
 	dev_priv->wm.distrust_bios_wm = true;
 	dev_priv->ipc_enabled = enable;
 	intel_enable_ipc(dev_priv);
-	intel_runtime_pm_put(dev_priv);
+
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return len;
 }
@@ -4055,11 +4081,12 @@ static int
 i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_i915_private *i915 = data;
+	intel_wakeref_t wakeref;
 	int ret = 0;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n",
 		  val, val & DROP_ALL);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (val & DROP_RESET_ACTIVE && !intel_engines_are_idle(i915))
 		i915_gem_set_wedged(i915);
@@ -4117,7 +4144,7 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_drain_freed_objects(i915);
 
 out:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	return ret;
 }
@@ -4130,16 +4157,17 @@ static int
 i915_cache_sharing_get(void *data, u64 *val)
 {
 	struct drm_i915_private *dev_priv = data;
+	intel_wakeref_t wakeref;
 	u32 snpcr;
 
 	if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv)))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	*val = (snpcr & GEN6_MBC_SNPCR_MASK) >> GEN6_MBC_SNPCR_SHIFT;
 
@@ -4150,6 +4178,7 @@ static int
 i915_cache_sharing_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
+	intel_wakeref_t wakeref;
 	u32 snpcr;
 
 	if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv)))
@@ -4158,7 +4187,7 @@ i915_cache_sharing_set(void *data, u64 val)
 	if (val > 3)
 		return -EINVAL;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	DRM_DEBUG_DRIVER("Manually setting uncore sharing to %llu\n", val);
 
 	/* Update the cache sharing policy here as well */
@@ -4167,7 +4196,7 @@ i915_cache_sharing_set(void *data, u64 val)
 	snpcr |= (val << GEN6_MBC_SNPCR_SHIFT);
 	I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	return 0;
 }
 
@@ -4389,6 +4418,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct sseu_dev_info sseu;
+	intel_wakeref_t wakeref;
 
 	if (INTEL_GEN(dev_priv) < 8)
 		return -ENODEV;
@@ -4403,7 +4433,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 	sseu.max_eus_per_subslice =
 		INTEL_INFO(dev_priv)->sseu.max_eus_per_subslice;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
 		cherryview_sseu_device_status(dev_priv, &sseu);
@@ -4415,7 +4445,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		gen10_sseu_device_status(dev_priv, &sseu);
 	}
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	i915_print_sseu_info(m, false, &sseu);
 
@@ -4443,7 +4473,7 @@ static int i915_forcewake_release(struct inode *inode, struct file *file)
 		return 0;
 
 	intel_uncore_forcewake_user_put(i915);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put_unchecked(i915);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1c8dba661cda..e2b6dc3027c1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -131,6 +131,8 @@ bool i915_error_injected(void);
 	__i915_printk(i915, i915_error_injected() ? KERN_DEBUG : KERN_ERR, \
 		      fmt, ##__VA_ARGS__)
 
+typedef depot_stack_handle_t intel_wakeref_t;
+
 enum hpd_pin {
 	HPD_NONE = 0,
 	HPD_TV = HPD_NONE,     /* TV is known to be unreliable */
@@ -1316,6 +1318,8 @@ struct i915_perf_stream {
 	 */
 	struct list_head link;
 
+	intel_wakeref_t wakeref;
+
 	/**
 	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
 	 * properties given when opening a stream, representing the contents
@@ -1962,7 +1966,7 @@ struct drm_i915_private {
 		 * In order to reduce the effect on performance, there
 		 * is a slight delay before we do so.
 		 */
-		bool awake;
+		intel_wakeref_t awake;
 
 		/**
 		 * The number of times we have woken up.
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8d351caf8f2e..b856f4f97746 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -139,6 +139,8 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 
 static u32 __i915_gem_park(struct drm_i915_private *i915)
 {
+	intel_wakeref_t wakeref;
+
 	GEM_TRACE("\n");
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -169,14 +171,15 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 	i915_pmu_gt_parked(i915);
 	i915_vma_parked(i915);
 
-	i915->gt.awake = false;
+	wakeref = fetch_and_zero(&i915->gt.awake);
+	GEM_BUG_ON(!wakeref);
 
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
 	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ);
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	return i915->gt.epoch;
 }
@@ -205,7 +208,8 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 	if (i915->gt.awake)
 		return;
 
-	intel_runtime_pm_get_noresume(i915);
+	i915->gt.awake = intel_runtime_pm_get_noresume(i915);
+	GEM_BUG_ON(!i915->gt.awake);
 
 	/*
 	 * It seems that the DMC likes to transition between the DC states a lot
@@ -220,7 +224,6 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 	 */
 	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 
-	i915->gt.awake = true;
 	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
 		i915->gt.epoch = 1;
 
@@ -783,6 +786,8 @@ fb_write_origin(struct drm_i915_gem_object *obj, unsigned int domain)
 
 void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 {
+	intel_wakeref_t wakeref;
+
 	/*
 	 * No actual flushing is required for the GTT write domain for reads
 	 * from the GTT domain. Writes to it "immediately" go to main memory
@@ -809,13 +814,13 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 
 	i915_gem_chipset_flush(dev_priv);
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	spin_lock_irq(&dev_priv->uncore.lock);
 
 	POSTING_READ_FW(RING_HEAD(RENDER_RING_BASE));
 
 	spin_unlock_irq(&dev_priv->uncore.lock);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 }
 
 static void
@@ -1174,6 +1179,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_ggtt *ggtt = &i915->ggtt;
+	intel_wakeref_t wakeref;
 	struct drm_mm_node node;
 	struct i915_vma *vma;
 	void __user *user_data;
@@ -1184,7 +1190,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 	if (ret)
 		return ret;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
 				       PIN_MAPPABLE |
 				       PIN_NONFAULT |
@@ -1257,7 +1263,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		i915_vma_unpin(vma);
 	}
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	return ret;
@@ -1359,6 +1365,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_ggtt *ggtt = &i915->ggtt;
+	intel_wakeref_t wakeref;
 	struct drm_mm_node node;
 	struct i915_vma *vma;
 	u64 remain, offset;
@@ -1377,13 +1384,14 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		 * This easily dwarfs any performance advantage from
 		 * using the cache bypass of indirect GGTT access.
 		 */
-		if (!intel_runtime_pm_get_if_in_use(i915)) {
+		wakeref = intel_runtime_pm_get_if_in_use(i915);
+		if (!wakeref) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
 	} else {
 		/* No backing pages, no fallback, we must force GGTT access */
-		intel_runtime_pm_get(i915);
+		wakeref = intel_runtime_pm_get(i915);
 	}
 
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
@@ -1465,7 +1473,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		i915_vma_unpin(vma);
 	}
 out_rpm:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 out_unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	return ret;
@@ -2012,6 +2020,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	bool write = area->vm_flags & VM_WRITE;
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	pgoff_t page_offset;
 	int ret;
@@ -2041,7 +2050,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	if (ret)
 		goto err;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
@@ -2119,7 +2128,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 err_unlock:
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	i915_gem_object_unpin_pages(obj);
 err:
 	switch (ret) {
@@ -2192,6 +2201,7 @@ void
 i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	intel_wakeref_t wakeref;
 
 	/* Serialisation between user GTT access and our code depends upon
 	 * revoking the CPU's PTE whilst the mutex is held. The next user
@@ -2202,7 +2212,7 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	 * wakeref.
 	 */
 	lockdep_assert_held(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (!obj->userfault_count)
 		goto out;
@@ -2219,7 +2229,7 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	wmb();
 
 out:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
@@ -4872,8 +4882,9 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 				    struct llist_node *freed)
 {
 	struct drm_i915_gem_object *obj, *on;
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	llist_for_each_entry_safe(obj, on, freed, freed) {
 		struct i915_vma *vma, *vn;
 
@@ -4934,7 +4945,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		if (on)
 			cond_resched();
 	}
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static void i915_gem_flush_free_objects(struct drm_i915_private *i915)
@@ -5043,11 +5054,13 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
+	intel_wakeref_t wakeref;
+
 	GEM_TRACE("\n");
 
 	mutex_lock(&i915->drm.struct_mutex);
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
 
 	/*
@@ -5070,7 +5083,7 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	intel_engines_sanitize(i915, false);
 
 	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	i915_gem_contexts_lost(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
@@ -5078,11 +5091,12 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 
 int i915_gem_suspend(struct drm_i915_private *i915)
 {
+	intel_wakeref_t wakeref;
 	int ret;
 
 	GEM_TRACE("\n");
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	intel_suspend_gt_powersave(i915);
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -5134,12 +5148,12 @@ int i915_gem_suspend(struct drm_i915_private *i915)
 	if (WARN_ON(!intel_engines_are_idle(i915)))
 		i915_gem_set_wedged(i915); /* no hope, discard everything */
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	return 0;
 
 err_unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 786d719e652d..f959679ba86f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -2200,6 +2200,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct sync_file *out_fence = NULL;
+	intel_wakeref_t wakeref;
 	int out_fence_fd = -1;
 	int err;
 
@@ -2270,7 +2271,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	 * wakeref that we hold until the GPU has been idle for at least
 	 * 100ms.
 	 */
-	intel_runtime_pm_get(eb.i915);
+	wakeref = intel_runtime_pm_get(eb.i915);
 
 	err = i915_mutex_lock_interruptible(dev);
 	if (err)
@@ -2422,7 +2423,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		eb_release_vmas(&eb);
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
-	intel_runtime_pm_put(eb.i915);
+	intel_runtime_pm_put(eb.i915, wakeref);
 	i915_gem_context_put(eb.ctx);
 err_destroy:
 	eb_destroy(&eb);
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index d548ac05ccd7..33148d12dfd5 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -210,6 +210,7 @@ static void fence_write(struct drm_i915_fence_reg *fence,
 static int fence_update(struct drm_i915_fence_reg *fence,
 			struct i915_vma *vma)
 {
+	intel_wakeref_t wakeref;
 	int ret;
 
 	if (vma) {
@@ -257,9 +258,10 @@ static int fence_update(struct drm_i915_fence_reg *fence,
 	 * If the device is currently powered down, we will defer the write
 	 * to the runtime resume, see i915_gem_restore_fences().
 	 */
-	if (intel_runtime_pm_get_if_in_use(fence->i915)) {
+	wakeref = intel_runtime_pm_get_if_in_use(fence->i915);
+	if (wakeref) {
 		fence_write(fence, vma);
-		intel_runtime_pm_put(fence->i915);
+		intel_runtime_pm_put(fence->i915, wakeref);
 	}
 
 	if (vma) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9f5eeae5af2b..1bc964ea8f03 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2519,6 +2519,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
 	struct drm_i915_gem_object *obj = vma->obj;
+	intel_wakeref_t wakeref;
 	u32 pte_flags;
 
 	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
@@ -2526,9 +2527,9 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 
@@ -2545,10 +2546,11 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 static void ggtt_unbind_vma(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static int aliasing_gtt_bind_vma(struct i915_vma *vma,
@@ -2580,9 +2582,11 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	}
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
-		intel_runtime_pm_get(i915);
+		intel_wakeref_t wakeref;
+
+		wakeref = intel_runtime_pm_get(i915);
 		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 	}
 
 	return 0;
@@ -2593,9 +2597,11 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 	struct drm_i915_private *i915 = vma->vm->i915;
 
 	if (vma->flags & I915_VMA_GLOBAL_BIND) {
-		intel_runtime_pm_get(i915);
+		intel_wakeref_t wakeref;
+
+		wakeref = intel_runtime_pm_get(i915);
 		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 	}
 
 	if (vma->flags & I915_VMA_LOCAL_BIND) {
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index d461f458f4af..eac3a47f2a62 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -154,6 +154,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 		{ &i915->mm.bound_list, I915_SHRINK_BOUND },
 		{ NULL, 0 },
 	}, *phase;
+	intel_wakeref_t wakeref = 0;
 	unsigned long count = 0;
 	unsigned long scanned = 0;
 	bool unlock;
@@ -183,9 +184,11 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	 * device just to recover a little memory. If absolutely necessary,
 	 * we will force the wake during oom-notifier.
 	 */
-	if ((flags & I915_SHRINK_BOUND) &&
-	    !intel_runtime_pm_get_if_in_use(i915))
-		flags &= ~I915_SHRINK_BOUND;
+	if (flags & I915_SHRINK_BOUND) {
+		wakeref = intel_runtime_pm_get_if_in_use(i915);
+		if (!wakeref)
+			flags &= ~I915_SHRINK_BOUND;
+	}
 
 	/*
 	 * As we may completely rewrite the (un)bound list whilst unbinding
@@ -266,7 +269,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	}
 
 	if (flags & I915_SHRINK_BOUND)
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 
 	i915_retire_requests(i915);
 
@@ -293,14 +296,15 @@ i915_gem_shrink(struct drm_i915_private *i915,
  */
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 {
+	intel_wakeref_t wakeref;
 	unsigned long freed;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	freed = i915_gem_shrink(i915, -1UL, NULL,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	return freed;
 }
@@ -371,14 +375,16 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
 	if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
-		intel_runtime_pm_get(i915);
+		intel_wakeref_t wakeref;
+
+		wakeref = intel_runtime_pm_get(i915);
 		freed += i915_gem_shrink(i915,
 					 sc->nr_to_scan - sc->nr_scanned,
 					 &sc->nr_scanned,
 					 I915_SHRINK_ACTIVE |
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 	}
 
 	shrinker_unlock(i915, unlock);
@@ -461,6 +467,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		container_of(nb, struct drm_i915_private, mm.vmap_notifier);
 	struct i915_vma *vma, *next;
 	unsigned long freed_pages = 0;
+	intel_wakeref_t wakeref;
 	bool unlock;
 	int ret;
 
@@ -474,13 +481,13 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 	if (ret)
 		goto out;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	freed_pages += i915_gem_shrink(i915, -1UL, NULL,
 				       I915_SHRINK_BOUND |
 				       I915_SHRINK_UNBOUND |
 				       I915_SHRINK_ACTIVE |
 				       I915_SHRINK_VMAPS);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index d447d7d508f4..bd5ef8ea8752 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3299,6 +3299,7 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 		       const char *fmt, ...)
 {
 	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
 	unsigned int tmp;
 	char error_msg[80];
 	char *msg = NULL;
@@ -3320,7 +3321,7 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 	 * isn't the case at least when we get here by doing a
 	 * simulated reset via debugfs, so get an RPM reference.
 	 */
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	engine_mask &= INTEL_INFO(dev_priv)->ring_mask;
 
@@ -3382,7 +3383,7 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 	wake_up_all(&dev_priv->gpu_error.reset_queue);
 
 out:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 }
 
 /* Called from drm generic code, passed 'crtc' which
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 4529edfdcfc8..e54c04fed076 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1364,14 +1364,14 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 
 	free_oa_buffer(dev_priv);
 
+	put_oa_config(dev_priv, stream->oa_config);
+
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, stream->wakeref);
 
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
-	put_oa_config(dev_priv, stream->oa_config);
-
 	if (dev_priv->perf.oa.spurious_report_rs.missed) {
 		DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
 			 dev_priv->perf.oa.spurious_report_rs.missed);
@@ -2087,7 +2087,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 *   In our case we are expecting that taking pm + FORCEWAKE
 	 *   references will effectively disable RC6.
 	 */
-	intel_runtime_pm_get(dev_priv);
+	stream->wakeref = intel_runtime_pm_get(dev_priv);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	ret = alloc_oa_buffer(dev_priv);
@@ -2123,7 +2123,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	put_oa_config(dev_priv, stream->oa_config);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, stream->wakeref);
 
 err_config:
 	if (stream->ctx)
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d6c8f8fdfda5..3d43fc9dd25d 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -167,6 +167,7 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	bool fw = false;
 
 	if ((dev_priv->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
@@ -175,7 +176,8 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 	if (!dev_priv->gt.awake)
 		return;
 
-	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (!wakeref)
 		return;
 
 	for_each_engine(engine, dev_priv, id) {
@@ -210,7 +212,7 @@ engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 	if (fw)
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 }
 
 static void
@@ -227,11 +229,15 @@ frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 		u32 val;
 
 		val = dev_priv->gt_pm.rps.cur_freq;
-		if (dev_priv->gt.awake &&
-		    intel_runtime_pm_get_if_in_use(dev_priv)) {
-			val = intel_get_cagf(dev_priv,
-					     I915_READ_NOTRACE(GEN6_RPSTAT1));
-			intel_runtime_pm_put(dev_priv);
+		if (dev_priv->gt.awake) {
+			intel_wakeref_t wakeref =
+				intel_runtime_pm_get_if_in_use(dev_priv);
+
+			if (wakeref) {
+				val = intel_get_cagf(dev_priv,
+						     I915_READ_NOTRACE(GEN6_RPSTAT1));
+				intel_runtime_pm_put(dev_priv, wakeref);
+			}
 		}
 
 		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
@@ -443,12 +449,14 @@ static u64 __get_rc6(struct drm_i915_private *i915)
 static u64 get_rc6(struct drm_i915_private *i915)
 {
 #if IS_ENABLED(CONFIG_PM)
+	intel_wakeref_t wakeref;
 	unsigned long flags;
 	u64 val;
 
-	if (intel_runtime_pm_get_if_in_use(i915)) {
+	wakeref = intel_runtime_pm_get_if_in_use(i915);
+	if (wakeref) {
 		val = __get_rc6(i915);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 
 		/*
 		 * If we are coming back from being runtime suspended we must
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index c0cfe7ae2ba5..2cbbf165d179 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -42,11 +42,12 @@ static inline struct drm_i915_private *kdev_minor_to_i915(struct device *kdev)
 static u32 calc_residency(struct drm_i915_private *dev_priv,
 			  i915_reg_t reg)
 {
+	intel_wakeref_t wakeref;
 	u64 res;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	res = intel_rc6_residency_us(dev_priv, reg);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
@@ -258,9 +259,10 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	intel_wakeref_t wakeref;
 	int ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->pcu_lock);
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
@@ -274,7 +276,7 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 	}
 	mutex_unlock(&dev_priv->pcu_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
@@ -354,6 +356,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	intel_wakeref_t wakeref;
 	u32 val;
 	ssize_t ret;
 
@@ -361,7 +364,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	if (ret)
 		return ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->pcu_lock);
 
@@ -371,7 +374,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 	    val > rps->max_freq ||
 	    val < rps->min_freq_softlimit) {
 		mutex_unlock(&dev_priv->pcu_lock);
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(dev_priv, wakeref);
 		return -EINVAL;
 	}
 
@@ -392,7 +395,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 
 	mutex_unlock(&dev_priv->pcu_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret ?: count;
 }
@@ -412,6 +415,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	intel_wakeref_t wakeref;
 	u32 val;
 	ssize_t ret;
 
@@ -419,7 +423,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	if (ret)
 		return ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->pcu_lock);
 
@@ -429,7 +433,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 	    val > rps->max_freq ||
 	    val > rps->max_freq_softlimit) {
 		mutex_unlock(&dev_priv->pcu_lock);
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put(dev_priv, wakeref);
 		return -EINVAL;
 	}
 
@@ -446,7 +450,7 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 
 	mutex_unlock(&dev_priv->pcu_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret ?: count;
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a9b2a4a530a4..09f21f39bbdb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2024,6 +2024,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	struct drm_device *dev = fb->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	unsigned int pinctl;
 	u32 alignment;
@@ -2047,7 +2048,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 * intel_runtime_pm_put(), so it is correct to wrap only the
 	 * pin/unpin/fence and not more.
 	 */
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
@@ -2102,7 +2103,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 err:
 	atomic_dec(&dev_priv->gpu_error.pending_fb_pin);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	return vma;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 5cd851390672..50231696ccfb 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -29,6 +29,7 @@
 #include <linux/i2c.h>
 #include <linux/hdmi.h>
 #include <linux/sched/clock.h>
+#include <linux/stackdepot.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include <drm/drm_crtc.h>
@@ -2173,10 +2174,16 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *i915)
 	atomic_dec(&i915->runtime_pm.wakeref_count);
 }
 
-void intel_runtime_pm_get(struct drm_i915_private *i915);
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915);
-void intel_runtime_pm_get_noresume(struct drm_i915_private *i915);
-void intel_runtime_pm_put(struct drm_i915_private *i915);
+intel_wakeref_t intel_runtime_pm_get(struct drm_i915_private *i915);
+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915);
+intel_wakeref_t intel_runtime_pm_get_noresume(struct drm_i915_private *i915);
+
+void intel_runtime_pm_put_unchecked(struct drm_i915_private *i915);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+void intel_runtime_pm_put(struct drm_i915_private *i915, intel_wakeref_t wref);
+#else
+#define intel_runtime_pm_put(i915, wref) intel_runtime_pm_put_unchecked(i915)
+#endif
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 71636e009f13..ec540c32a690 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -900,10 +900,12 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 static bool ring_is_idle(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	intel_wakeref_t wakeref;
 	bool idle = true;
 
 	/* If the whole device is asleep, the engine must be idle */
-	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (!wakeref)
 		return true;
 
 	/* First check that no commands are left in the ring */
@@ -915,7 +917,7 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
 		idle = false;
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return idle;
 }
@@ -1422,6 +1424,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
 	struct i915_request *rq, *last;
+	intel_wakeref_t wakeref;
 	unsigned long flags;
 	struct rb_node *rb;
 	int count;
@@ -1480,9 +1483,10 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 	rcu_read_unlock();
 
-	if (intel_runtime_pm_get_if_in_use(engine->i915)) {
+	wakeref = intel_runtime_pm_get_if_in_use(engine->i915);
+	if (wakeref) {
 		intel_engine_print_registers(engine, m);
-		intel_runtime_pm_put(engine->i915);
+		intel_runtime_pm_put(engine->i915, wakeref);
 	} else {
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index fb5bb5b32a60..de14cd78aa0f 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -178,8 +178,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	const struct i915_ggtt_view view = {
 		.type = I915_GGTT_VIEW_NORMAL,
 	};
-	struct fb_info *info;
 	struct drm_framebuffer *fb;
+	intel_wakeref_t wakeref;
+	struct fb_info *info;
 	struct i915_vma *vma;
 	unsigned long flags = 0;
 	bool prealloc = false;
@@ -210,7 +211,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	}
 
 	mutex_lock(&dev->struct_mutex);
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	/* Pin the GGTT vma for our access via info->screen_base.
 	 * This also validates that any existing fb inherited from the
@@ -277,7 +278,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	ifbdev->vma = vma;
 	ifbdev->vma_flags = flags;
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	mutex_unlock(&dev->struct_mutex);
 	vga_switcheroo_client_fb_set(pdev, info);
 	return 0;
@@ -285,7 +286,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 out_unpin:
 	intel_unpin_fb_vma(vma, flags);
 out_unlock:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index d3ebdbc0182e..20c0b36d748e 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -436,6 +436,7 @@ static void guc_log_capture_logs(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	intel_wakeref_t wakeref;
 
 	guc_read_update_log_buffer(log);
 
@@ -443,9 +444,9 @@ static void guc_log_capture_logs(struct intel_guc_log *log)
 	 * Generally device is expected to be active only at this
 	 * time, so get/put should be really quick.
 	 */
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	guc_action_flush_log_complete(guc);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 }
 
 int intel_guc_log_create(struct intel_guc_log *log)
@@ -505,6 +506,7 @@ int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	intel_wakeref_t wakeref;
 	int ret;
 
 	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN != 0);
@@ -524,11 +526,11 @@ int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 		goto out_unlock;
 	}
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(level),
 				     GUC_LOG_LEVEL_IS_ENABLED(level),
 				     GUC_LOG_LEVEL_TO_VERBOSITY(level));
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	if (ret) {
 		DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret);
 		goto out_unlock;
@@ -601,6 +603,7 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *i915 = guc_to_i915(guc);
+	intel_wakeref_t wakeref;
 
 	/*
 	 * Before initiating the forceful flush, wait for any pending/ongoing
@@ -608,9 +611,9 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 	 */
 	flush_work(&log->relay.flush_work);
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	guc_action_flush_log(guc);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	/* GuC would have updated log buffer by now, so capture it */
 	guc_log_capture_logs(log);
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index e24174d08fed..6df8820b8b80 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -227,9 +227,10 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		container_of(work, typeof(*dev_priv),
 			     hotplug.reenable_work.work);
 	struct drm_device *dev = &dev_priv->drm;
+	intel_wakeref_t wakeref;
 	enum hpd_pin pin;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	for_each_hpd_pin(pin) {
@@ -262,7 +263,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 }
 
 bool intel_encoder_hotplug(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index bc27b691d824..3e8c18b6a42d 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -115,14 +115,15 @@ int intel_huc_auth(struct intel_huc *huc)
 int intel_huc_check_status(struct intel_huc *huc)
 {
 	struct drm_i915_private *dev_priv = huc_to_i915(huc);
+	intel_wakeref_t wakeref;
 	bool status;
 
 	if (!HAS_HUC(dev_priv))
 		return -ENODEV;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	status = I915_READ(HUC_STATUS2) & HUC_FW_VERIFIED;
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return status;
 }
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index e6cd7b55c018..2c6cfb2086a9 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1203,17 +1203,18 @@ static int intel_backlight_device_get_brightness(struct backlight_device *bd)
 	struct intel_connector *connector = bl_get_data(bd);
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	intel_wakeref_t wakeref;
 	u32 hw_level;
 	int ret;
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 
 	hw_level = intel_panel_get_backlight(connector);
 	ret = scale_hw_to_user(connector, hw_level, bd->props.max_brightness);
 
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d98f73bd7358..1dab3f54df1e 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -62,7 +62,7 @@ static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 	spin_lock_init(&i915->runtime_pm.debug_lock);
 }
 
-static noinline void
+static noinline depot_stack_handle_t
 track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 {
 	struct i915_runtime_pm *rpm = &i915->runtime_pm;
@@ -76,7 +76,7 @@ track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 	depot_stack_handle_t stack, *stacks;
 
 	if (!HAS_RUNTIME_PM(i915))
-		return;
+		return -1;
 
 	save_stack_trace(&trace);
 	if (trace.nr_entries &&
@@ -85,7 +85,7 @@ track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 
 	stack = depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
 	if (!stack)
-		return;
+		return -1;
 
 	spin_lock_irqsave(&rpm->debug_lock, flags);
 	stacks = krealloc(rpm->debug_owners,
@@ -94,8 +94,55 @@ track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 	if (stacks) {
 		stacks[rpm->debug_count++] = stack;
 		rpm->debug_owners = stacks;
+	} else {
+		stack = -1;
 	}
 	spin_unlock_irqrestore(&rpm->debug_lock, flags);
+
+	return stack;
+}
+
+static void cancel_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+					    depot_stack_handle_t stack)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	unsigned long flags, n;
+	bool found = false;
+
+	if (unlikely(stack == -1))
+		return;
+
+	spin_lock_irqsave(&rpm->debug_lock, flags);
+	for (n = rpm->debug_count; n--; ) {
+		if (rpm->debug_owners[n] == stack) {
+			memmove(rpm->debug_owners + n,
+				rpm->debug_owners + n + 1,
+				(--rpm->debug_count - n) * sizeof(stack));
+			found = true;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&rpm->debug_lock, flags);
+
+	if (WARN(!found,
+		 "Unmatched wakeref (tracking %lu)\n",
+		 rpm->debug_count)) {
+		unsigned long entries[STACKDEPTH];
+		struct stack_trace trace = {
+			.entries = entries,
+			.max_entries = ARRAY_SIZE(entries),
+		};
+		char *buf;
+
+		buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!buf)
+			return;
+
+		depot_fetch_stack(stack, &trace);
+		snprint_stack_trace(buf, PAGE_SIZE, &trace, 0);
+		DRM_DEBUG_DRIVER("wakeref %x from\n%s", stack, buf);
+		kfree(buf);
+	}
 }
 
 static void untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
@@ -220,8 +267,10 @@ static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 {
 }
 
-static void track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+static depot_stack_handle_t
+track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
 {
+	return -1;
 }
 
 static void untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
@@ -1823,7 +1872,7 @@ bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
 	mutex_unlock(&power_domains->lock);
 
 	if (!is_enabled)
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put_unchecked(dev_priv);
 
 	return is_enabled;
 }
@@ -1857,7 +1906,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 
 	mutex_unlock(&power_domains->lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 #define I830_PIPES_POWER_DOMAINS (		\
@@ -3965,7 +4014,7 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
 void intel_power_domains_fini_hw(struct drm_i915_private *dev_priv)
 {
 	/* Keep the power well enabled, but cancel its rpm wakeref. */
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 
 	/* Remove the refcount we took to keep power well support disabled. */
 	if (!i915_modparams.disable_power_well)
@@ -4179,7 +4228,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get(struct drm_i915_private *i915)
+intel_wakeref_t intel_runtime_pm_get(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
@@ -4191,7 +4240,7 @@ void intel_runtime_pm_get(struct drm_i915_private *i915)
 	atomic_inc(&i915->runtime_pm.wakeref_count);
 	assert_rpm_wakelock_held(i915);
 
-	track_intel_runtime_pm_wakeref(i915);
+	return track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
@@ -4207,7 +4256,7 @@ void intel_runtime_pm_get(struct drm_i915_private *i915)
  *
  * Returns: True if the wakeref was acquired, or False otherwise.
  */
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
 {
 	if (IS_ENABLED(CONFIG_PM)) {
 		struct pci_dev *pdev = i915->drm.pdev;
@@ -4220,15 +4269,13 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
 		 * atm to the late/early system suspend/resume handlers.
 		 */
 		if (pm_runtime_get_if_in_use(kdev) <= 0)
-			return false;
+			return 0;
 	}
 
 	atomic_inc(&i915->runtime_pm.wakeref_count);
 	assert_rpm_wakelock_held(i915);
 
-	track_intel_runtime_pm_wakeref(i915);
-
-	return true;
+	return track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
@@ -4248,7 +4295,7 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
+intel_wakeref_t intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
@@ -4258,7 +4305,7 @@ void intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
 
 	atomic_inc(&i915->runtime_pm.wakeref_count);
 
-	track_intel_runtime_pm_wakeref(i915);
+	return track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
@@ -4269,7 +4316,7 @@ void intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
  * intel_runtime_pm_get() and might power down the corresponding
  * hardware block right away if this is the last reference.
  */
-void intel_runtime_pm_put(struct drm_i915_private *i915)
+void intel_runtime_pm_put_unchecked(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
@@ -4282,6 +4329,14 @@ void intel_runtime_pm_put(struct drm_i915_private *i915)
 	pm_runtime_put_autosuspend(kdev);
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+void intel_runtime_pm_put(struct drm_i915_private *i915, intel_wakeref_t wref)
+{
+	cancel_intel_runtime_pm_wakeref(i915, wref);
+	intel_runtime_pm_put_unchecked(i915);
+}
+#endif
+
 /**
  * intel_runtime_pm_enable - enable runtime pm
  * @i915: i915 device instance
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 408692b88c98..e042238e39f6 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1670,6 +1670,7 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_reg_read *reg = data;
 	struct reg_whitelist const *entry;
+	intel_wakeref_t wakeref;
 	unsigned int flags;
 	int remain;
 	int ret = 0;
@@ -1695,7 +1696,7 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 
 	flags = reg->offset & (entry->size - 1);
 
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 	if (entry->size == 8 && flags == I915_REG_READ_8B_WA)
 		reg->val = I915_READ64_2x32(entry->offset_ldw,
 					    entry->offset_udw);
@@ -1709,7 +1710,7 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 		reg->val = I915_READ8(entry->offset_ldw);
 	else
 		ret = -EINVAL;
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index a0c7cbc212ba..c7a4599173bb 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1760,6 +1760,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	};
 	struct drm_file *file;
 	struct i915_gem_context *ctx;
+	intel_wakeref_t wakeref;
 	int err;
 
 	if (!HAS_PPGTT(dev_priv)) {
@@ -1775,7 +1776,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 		return PTR_ERR(file);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	ctx = live_context(dev_priv, file);
 	if (IS_ERR(ctx)) {
@@ -1789,7 +1790,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	err = i915_subtests(tests, ctx);
 
 out_unlock:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	mock_file_free(dev_priv, file);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bdcc53e15e75..01a46c46fe25 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -16,9 +16,10 @@ static int switch_to_context(struct drm_i915_private *i915,
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	for_each_engine(engine, i915, id) {
 		struct i915_request *rq;
@@ -32,7 +33,7 @@ static int switch_to_context(struct drm_i915_private *i915,
 		i915_request_add(rq);
 	}
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	return err;
 }
@@ -65,7 +66,9 @@ static void trash_stolen(struct drm_i915_private *i915)
 
 static void simulate_hibernate(struct drm_i915_private *i915)
 {
-	intel_runtime_pm_get(i915);
+	intel_wakeref_t wakeref;
+
+	wakeref = intel_runtime_pm_get(i915);
 
 	/*
 	 * As a final sting in the tail, invalidate stolen. Under a real S4,
@@ -76,7 +79,7 @@ static void simulate_hibernate(struct drm_i915_private *i915)
 	 */
 	trash_stolen(i915);
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static int pm_prepare(struct drm_i915_private *i915)
@@ -93,39 +96,45 @@ static int pm_prepare(struct drm_i915_private *i915)
 
 static void pm_suspend(struct drm_i915_private *i915)
 {
-	intel_runtime_pm_get(i915);
+	intel_wakeref_t wakeref;
+
+	wakeref = intel_runtime_pm_get(i915);
 
 	i915_gem_suspend_gtt_mappings(i915);
 	i915_gem_suspend_late(i915);
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static void pm_hibernate(struct drm_i915_private *i915)
 {
-	intel_runtime_pm_get(i915);
+	intel_wakeref_t wakeref;
+
+	wakeref = 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);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static void pm_resume(struct drm_i915_private *i915)
 {
+	intel_wakeref_t wakeref;
+
 	/*
 	 * Both suspend and hibernate follow the same wakeup path and assume
 	 * that runtime-pm just works.
 	 */
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	intel_engines_sanitize(i915, false);
 	i915_gem_sanitize(i915);
 	i915_gem_resume(i915);
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 static int igt_gem_suspend(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index f7392c1ffe75..fd89a5a33c1a 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -279,6 +279,7 @@ static int igt_gem_coherency(void *arg)
 	struct drm_i915_private *i915 = arg;
 	const struct igt_coherency_mode *read, *write, *over;
 	struct drm_i915_gem_object *obj;
+	intel_wakeref_t wakeref;
 	unsigned long count, n;
 	u32 *offsets, *values;
 	int err = 0;
@@ -298,7 +299,7 @@ static int igt_gem_coherency(void *arg)
 	values = offsets + ncachelines;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	for (over = igt_coherency_mode; over->name; over++) {
 		if (!over->set)
 			continue;
@@ -376,7 +377,7 @@ static int igt_gem_coherency(void *arg)
 		}
 	}
 unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	kfree(offsets);
 	return err;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 7d82043aff10..6edf943892d0 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -119,6 +119,7 @@ static int live_nop_switch(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context **ctx;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	struct drm_file *file;
 	struct live_test t;
 	unsigned long n;
@@ -140,7 +141,7 @@ static int live_nop_switch(void *arg)
 		return PTR_ERR(file);
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	ctx = kcalloc(nctx, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx) {
@@ -243,7 +244,7 @@ static int live_nop_switch(void *arg)
 	}
 
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	mock_file_free(i915, file);
 	return err;
@@ -593,6 +594,8 @@ static int igt_ctx_exec(void *arg)
 		}
 
 		for_each_engine(engine, i915, id) {
+			intel_wakeref_t wakeref;
+
 			if (!engine->context_size)
 				continue; /* No logical context support in HW */
 
@@ -607,9 +610,9 @@ static int igt_ctx_exec(void *arg)
 				}
 			}
 
-			intel_runtime_pm_get(i915);
+			wakeref = intel_runtime_pm_get(i915);
 			err = gpu_fill(obj, ctx, engine, dw);
-			intel_runtime_pm_put(i915);
+			intel_runtime_pm_put(i915, wakeref);
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
@@ -699,6 +702,8 @@ static int igt_ctx_readonly(void *arg)
 		unsigned int id;
 
 		for_each_engine(engine, i915, id) {
+			intel_wakeref_t wakeref;
+
 			if (!intel_engine_can_store_dword(engine))
 				continue;
 
@@ -713,9 +718,9 @@ static int igt_ctx_readonly(void *arg)
 					i915_gem_object_set_readonly(obj);
 			}
 
-			intel_runtime_pm_get(i915);
+			wakeref = intel_runtime_pm_get(i915);
 			err = gpu_fill(obj, ctx, engine, dw);
-			intel_runtime_pm_put(i915);
+			intel_runtime_pm_put(i915, wakeref);
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
@@ -976,6 +981,7 @@ static int igt_vm_isolation(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx_a, *ctx_b;
 	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
 	struct drm_file *file;
 	I915_RND_STATE(prng);
 	unsigned long count;
@@ -1022,7 +1028,7 @@ static int igt_vm_isolation(void *arg)
 	GEM_BUG_ON(ctx_b->ppgtt->vm.total != vm_total);
 	vm_total -= I915_GTT_PAGE_SIZE;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	count = 0;
 	for_each_engine(engine, i915, id) {
@@ -1067,7 +1073,7 @@ static int igt_vm_isolation(void *arg)
 		count, INTEL_INFO(i915)->num_rings);
 
 out_rpm:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 out_unlock:
 	if (end_live_test(&t))
 		err = -EIO;
@@ -1165,6 +1171,7 @@ static int igt_switch_to_kernel_context(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err;
 
 	/*
@@ -1175,7 +1182,7 @@ static int igt_switch_to_kernel_context(void *arg)
 	 */
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	ctx = kernel_context(i915);
 	if (IS_ERR(ctx)) {
@@ -1200,7 +1207,7 @@ static int igt_switch_to_kernel_context(void *arg)
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		err = -EIO;
 
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	kernel_context_close(ctx);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 4365979d8222..e1ff6a1c2cb0 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -336,6 +336,7 @@ static int igt_evict_contexts(void *arg)
 		struct drm_mm_node node;
 		struct reserved *next;
 	} *reserved = NULL;
+	intel_wakeref_t wakeref;
 	struct drm_mm_node hole;
 	unsigned long count;
 	int err;
@@ -355,7 +356,7 @@ static int igt_evict_contexts(void *arg)
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	/* Reserve a block so that we know we have enough to fit a few rq */
 	memset(&hole, 0, sizeof(hole));
@@ -400,8 +401,10 @@ static int igt_evict_contexts(void *arg)
 		struct drm_file *file;
 
 		file = mock_file(i915);
-		if (IS_ERR(file))
-			return PTR_ERR(file);
+		if (IS_ERR(file)) {
+			err = PTR_ERR(file);
+			break;
+		}
 
 		count = 0;
 		mutex_lock(&i915->drm.struct_mutex);
@@ -464,7 +467,7 @@ static int igt_evict_contexts(void *arg)
 	}
 	if (drm_mm_node_allocated(&hole))
 		drm_mm_remove_node(&hole);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	return err;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 69fe86b30fbb..b946c90508d3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -275,6 +275,7 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 
 		for (n = 0; n < count; n++) {
 			u64 addr = hole_start + order[n] * BIT_ULL(size);
+			intel_wakeref_t wakeref;
 
 			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
 
@@ -293,9 +294,9 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			mock_vma.node.size = BIT_ULL(size);
 			mock_vma.node.start = addr;
 
-			intel_runtime_pm_get(i915);
+			wakeref = intel_runtime_pm_get(i915);
 			vm->insert_entries(vm, &mock_vma, I915_CACHE_NONE, 0);
-			intel_runtime_pm_put(i915);
+			intel_runtime_pm_put(i915, wakeref);
 		}
 		count = n;
 
@@ -1144,6 +1145,7 @@ static int igt_ggtt_page(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct drm_i915_gem_object *obj;
+	intel_wakeref_t wakeref;
 	struct drm_mm_node tmp;
 	unsigned int *order, n;
 	int err;
@@ -1169,7 +1171,7 @@ static int igt_ggtt_page(void *arg)
 	if (err)
 		goto out_unpin;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	for (n = 0; n < count; n++) {
 		u64 offset = tmp.start + n * PAGE_SIZE;
@@ -1216,7 +1218,7 @@ static int igt_ggtt_page(void *arg)
 	kfree(order);
 out_remove:
 	ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	drm_mm_remove_node(&tmp);
 out_unpin:
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index c3999dd2021e..26706aec7d73 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -307,6 +307,7 @@ static int igt_partial_tiling(void *arg)
 	const unsigned int nreal = 1 << 12; /* largest tile row x2 */
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
+	intel_wakeref_t wakeref;
 	int tiling;
 	int err;
 
@@ -332,7 +333,7 @@ static int igt_partial_tiling(void *arg)
 	}
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (1) {
 		IGT_TIMEOUT(end);
@@ -443,7 +444,7 @@ next_tiling: ;
 	}
 
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	i915_gem_object_unpin_pages(obj);
 out:
@@ -505,11 +506,14 @@ static void disable_retire_worker(struct drm_i915_private *i915)
 
 	mutex_lock(&i915->drm.struct_mutex);
 	if (!i915->gt.active_requests++) {
-		intel_runtime_pm_get(i915);
+		intel_wakeref_t wakeref;
+
+		wakeref = intel_runtime_pm_get(i915);
 		i915_gem_unpark(i915);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 	}
 	mutex_unlock(&i915->drm.struct_mutex);
+
 	cancel_delayed_work_sync(&i915->gt.retire_work);
 	cancel_delayed_work_sync(&i915->gt.idle_work);
 }
@@ -577,6 +581,8 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 	/* Now fill with busy dead objects that we expect to reap */
 	for (loop = 0; loop < 3; loop++) {
+		intel_wakeref_t wakeref;
+
 		if (i915_terminally_wedged(&i915->gpu_error))
 			break;
 
@@ -587,9 +593,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		}
 
 		mutex_lock(&i915->drm.struct_mutex);
-		intel_runtime_pm_get(i915);
+		wakeref = intel_runtime_pm_get(i915);
 		err = make_obj_busy(obj);
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 		mutex_unlock(&i915->drm.struct_mutex);
 		if (err) {
 			pr_err("[loop %d] Failed to busy the object\n", loop);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 07e557815308..8b73a8c21377 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -332,6 +332,7 @@ static int live_nop_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
 	struct live_test t;
 	unsigned int id;
 	int err = -ENODEV;
@@ -342,7 +343,7 @@ static int live_nop_request(void *arg)
 	 */
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	for_each_engine(engine, i915, id) {
 		struct i915_request *request = NULL;
@@ -403,7 +404,7 @@ static int live_nop_request(void *arg)
 	}
 
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -478,8 +479,9 @@ static int live_empty_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
-	struct live_test t;
+	intel_wakeref_t wakeref;
 	struct i915_vma *batch;
+	struct live_test t;
 	unsigned int id;
 	int err = 0;
 
@@ -489,7 +491,7 @@ static int live_empty_request(void *arg)
 	 */
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	batch = empty_batch(i915);
 	if (IS_ERR(batch)) {
@@ -553,7 +555,7 @@ static int live_empty_request(void *arg)
 	i915_vma_unpin(batch);
 	i915_vma_put(batch);
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -637,6 +639,7 @@ static int live_all_engines(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	struct i915_request *request[I915_NUM_ENGINES];
+	intel_wakeref_t wakeref;
 	struct i915_vma *batch;
 	struct live_test t;
 	unsigned int id;
@@ -648,7 +651,7 @@ static int live_all_engines(void *arg)
 	 */
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	err = begin_live_test(&t, i915, __func__, "");
 	if (err)
@@ -731,7 +734,7 @@ static int live_all_engines(void *arg)
 	i915_vma_unpin(batch);
 	i915_vma_put(batch);
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -742,6 +745,7 @@ static int live_sequential_engines(void *arg)
 	struct i915_request *request[I915_NUM_ENGINES] = {};
 	struct i915_request *prev = NULL;
 	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
 	struct live_test t;
 	unsigned int id;
 	int err;
@@ -753,7 +757,7 @@ static int live_sequential_engines(void *arg)
 	 */
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	err = begin_live_test(&t, i915, __func__, "");
 	if (err)
@@ -860,7 +864,7 @@ static int live_sequential_engines(void *arg)
 		i915_request_put(request[id]);
 	}
 out_unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c
index 32cba4cae31a..c5e0a0e98fcb 100644
--- a/drivers/gpu/drm/i915/selftests/intel_guc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_guc.c
@@ -137,12 +137,13 @@ static bool client_doorbell_in_sync(struct intel_guc_client *client)
 static int igt_guc_clients(void *args)
 {
 	struct drm_i915_private *dev_priv = args;
+	intel_wakeref_t wakeref;
 	struct intel_guc *guc;
 	int err = 0;
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	guc = &dev_priv->guc;
 	if (!guc) {
@@ -225,7 +226,7 @@ static int igt_guc_clients(void *args)
 	guc_clients_create(guc);
 	guc_clients_enable(guc);
 unlock:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
@@ -238,13 +239,14 @@ static int igt_guc_clients(void *args)
 static int igt_guc_doorbells(void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
+	intel_wakeref_t wakeref;
 	struct intel_guc *guc;
 	int i, err = 0;
 	u16 db_id;
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_get(dev_priv);
+	wakeref = intel_runtime_pm_get(dev_priv);
 
 	guc = &dev_priv->guc;
 	if (!guc) {
@@ -337,7 +339,7 @@ static int igt_guc_doorbells(void *arg)
 			guc_client_free(clients[i]);
 		}
 unlock:
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, wakeref);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 5f2f67b149af..751b5991f747 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -1598,6 +1598,7 @@ static int igt_atomic_reset(void *arg)
 		{ }
 	};
 	struct drm_i915_private *i915 = arg;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that the resets are usable from atomic context */
@@ -1607,7 +1608,7 @@ static int igt_atomic_reset(void *arg)
 
 	igt_global_reset_lock(i915);
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	/* Flush any requests before we get started and check basics */
 	force_reset(i915);
@@ -1634,7 +1635,7 @@ static int igt_atomic_reset(void *arg)
 	force_reset(i915);
 
 unlock:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	igt_global_reset_unlock(i915);
 
@@ -1658,6 +1659,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_handle_error),
 		SUBTEST(igt_atomic_reset),
 	};
+	intel_wakeref_t wakeref;
 	bool saved_hangcheck;
 	int err;
 
@@ -1667,7 +1669,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return -EIO; /* we're long past hope of a successful reset */
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 
 	err = i915_subtests(tests, i915);
@@ -1677,7 +1679,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	i915_modparams.enable_hangcheck = saved_hangcheck;
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index ca461e3a5f27..3196012adf8c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -18,13 +18,14 @@ static int live_sanitycheck(void *arg)
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
+	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (igt_spinner_init(&spin, i915))
 		goto err_unlock;
@@ -65,7 +66,7 @@ static int live_sanitycheck(void *arg)
 	igt_spinner_fini(&spin);
 err_unlock:
 	igt_flush_test(i915, I915_WAIT_LOCKED);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -77,13 +78,14 @@ static int live_preempt(void *arg)
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (igt_spinner_init(&spin_hi, i915))
 		goto err_unlock;
@@ -158,7 +160,7 @@ static int live_preempt(void *arg)
 	igt_spinner_fini(&spin_hi);
 err_unlock:
 	igt_flush_test(i915, I915_WAIT_LOCKED);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -171,13 +173,14 @@ static int live_late_preempt(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_sched_attr attr = {};
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (igt_spinner_init(&spin_hi, i915))
 		goto err_unlock;
@@ -251,7 +254,7 @@ static int live_late_preempt(void *arg)
 	igt_spinner_fini(&spin_hi);
 err_unlock:
 	igt_flush_test(i915, I915_WAIT_LOCKED);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
@@ -270,6 +273,7 @@ static int live_preempt_hang(void *arg)
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
@@ -279,7 +283,7 @@ static int live_preempt_hang(void *arg)
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	if (igt_spinner_init(&spin_hi, i915))
 		goto err_unlock;
@@ -374,7 +378,7 @@ static int live_preempt_hang(void *arg)
 	igt_spinner_fini(&spin_hi);
 err_unlock:
 	igt_flush_test(i915, I915_WAIT_LOCKED);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
@@ -562,6 +566,7 @@ static int live_preempt_smoke(void *arg)
 		.ncontext = 1024,
 	};
 	const unsigned int phase[] = { 0, BATCH };
+	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 	u32 *cs;
 	int n;
@@ -576,7 +581,7 @@ static int live_preempt_smoke(void *arg)
 		return -ENOMEM;
 
 	mutex_lock(&smoke.i915->drm.struct_mutex);
-	intel_runtime_pm_get(smoke.i915);
+	wakeref = intel_runtime_pm_get(smoke.i915);
 
 	smoke.batch = i915_gem_object_create_internal(smoke.i915, PAGE_SIZE);
 	if (IS_ERR(smoke.batch)) {
@@ -627,7 +632,7 @@ static int live_preempt_smoke(void *arg)
 err_batch:
 	i915_gem_object_put(smoke.batch);
 err_unlock:
-	intel_runtime_pm_put(smoke.i915);
+	intel_runtime_pm_put(smoke.i915, wakeref);
 	mutex_unlock(&smoke.i915->drm.struct_mutex);
 	kfree(smoke.contexts);
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index c2b3cd8fcc34..c6a26d7ad326 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -15,10 +15,11 @@
 static struct drm_i915_gem_object *
 read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 {
+	const u32 base = engine->mmio_base;
 	struct drm_i915_gem_object *result;
+	intel_wakeref_t wakeref;
 	struct i915_request *rq;
 	struct i915_vma *vma;
-	const u32 base = engine->mmio_base;
 	u32 srm, *cs;
 	int err;
 	int i;
@@ -47,9 +48,9 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	if (err)
 		goto err_obj;
 
-	intel_runtime_pm_get(engine->i915);
+	wakeref = intel_runtime_pm_get(engine->i915);
 	rq = i915_request_alloc(engine, ctx);
-	intel_runtime_pm_put(engine->i915);
+	intel_runtime_pm_put(engine->i915, wakeref);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_pin;
@@ -183,20 +184,21 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 {
 	struct i915_gem_context *ctx;
 	struct i915_request *rq;
+	intel_wakeref_t wakeref;
 	int err = 0;
 
 	ctx = kernel_context(engine->i915);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	intel_runtime_pm_get(engine->i915);
+	wakeref = intel_runtime_pm_get(engine->i915);
 
 	if (spin)
 		rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
 	else
 		rq = i915_request_alloc(engine, ctx);
 
-	intel_runtime_pm_put(engine->i915);
+	intel_runtime_pm_put(engine->i915, wakeref);
 
 	kernel_context_close(ctx);
 
@@ -228,6 +230,7 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	bool want_spin = reset == do_engine_reset;
 	struct i915_gem_context *ctx;
 	struct igt_spinner spin;
+	intel_wakeref_t wakeref;
 	int err;
 
 	pr_info("Checking %d whitelisted registers (RING_NONPRIV) [%s]\n",
@@ -253,9 +256,9 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	if (err)
 		goto out;
 
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 	err = reset(engine);
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 
 	if (want_spin) {
 		igt_spinner_end(&spin);
@@ -344,6 +347,7 @@ live_gpu_reset_gt_engine_workarounds(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gpu_error *error = &i915->gpu_error;
+	intel_wakeref_t wakeref;
 	bool ok;
 
 	if (!intel_has_gpu_reset(i915))
@@ -352,7 +356,7 @@ live_gpu_reset_gt_engine_workarounds(void *arg)
 	pr_info("Verifying after GPU reset...\n");
 
 	igt_global_reset_lock(i915);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	ok = verify_gt_engine_wa(i915, "before reset");
 	if (!ok)
@@ -364,7 +368,7 @@ live_gpu_reset_gt_engine_workarounds(void *arg)
 	ok = verify_gt_engine_wa(i915, "after reset");
 
 out:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	igt_global_reset_unlock(i915);
 
 	return ok ? 0 : -ESRCH;
@@ -379,6 +383,7 @@ live_engine_reset_gt_engine_workarounds(void *arg)
 	struct igt_spinner spin;
 	enum intel_engine_id id;
 	struct i915_request *rq;
+	intel_wakeref_t wakeref;
 	int ret = 0;
 
 	if (!intel_has_reset_engine(i915))
@@ -389,7 +394,7 @@ live_engine_reset_gt_engine_workarounds(void *arg)
 		return PTR_ERR(ctx);
 
 	igt_global_reset_lock(i915);
-	intel_runtime_pm_get(i915);
+	wakeref = intel_runtime_pm_get(i915);
 
 	for_each_engine(engine, i915, id) {
 		bool ok;
@@ -417,6 +422,7 @@ live_engine_reset_gt_engine_workarounds(void *arg)
 		rq = igt_spinner_create_request(&spin, ctx, engine, MI_NOOP);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
+			intel_runtime_pm_put(i915, wakeref);
 			igt_spinner_fini(&spin);
 			goto err;
 		}
@@ -425,6 +431,7 @@ live_engine_reset_gt_engine_workarounds(void *arg)
 
 		if (!igt_wait_for_spinner(&spin, rq)) {
 			pr_err("Spinner failed to start\n");
+			intel_runtime_pm_put(i915, wakeref);
 			igt_spinner_fini(&spin);
 			ret = -ETIMEDOUT;
 			goto err;
@@ -443,7 +450,7 @@ live_engine_reset_gt_engine_workarounds(void *arg)
 	}
 
 err:
-	intel_runtime_pm_put(i915);
+	intel_runtime_pm_put(i915, wakeref);
 	igt_global_reset_unlock(i915);
 	kernel_context_close(ctx);
 
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 13/19] drm/i915: Syntatic sugar for using intel_runtime_pm

[Chris Wilson]

Frequently, we use intel_runtime_pm_get/_put around a small block.
Formalise that usage by providing a macro to define such a block with an
automatic closure to scope the intel_runtime_pm wakeref to that block,
i.e. macro abuse smelling of python.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c           | 167 ++++++++----------
 drivers/gpu/drm/i915/i915_gem.c               |  10 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c           |  23 ++-
 drivers/gpu/drm/i915/i915_gem_shrinker.c      |  44 ++---
 drivers/gpu/drm/i915/i915_pmu.c               |   7 +-
 drivers/gpu/drm/i915/i915_sysfs.c             |   7 +-
 drivers/gpu/drm/i915/intel_drv.h              |   8 +
 drivers/gpu/drm/i915/intel_guc_log.c          |  26 ++-
 drivers/gpu/drm/i915/intel_huc.c              |   7 +-
 drivers/gpu/drm/i915/intel_panel.c            |  18 +-
 drivers/gpu/drm/i915/intel_uncore.c           |  30 ++--
 drivers/gpu/drm/i915/selftests/i915_gem.c     |  34 ++--
 .../gpu/drm/i915/selftests/i915_gem_context.c |  12 +-
 .../gpu/drm/i915/selftests/i915_gem_object.c  |  11 +-
 .../drm/i915/selftests/intel_workarounds.c    |  28 +--
 15 files changed, 202 insertions(+), 230 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 18a7f81dadcd..756f14763585 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -953,9 +953,9 @@ static int i915_gpu_info_open(struct inode *inode, struct file *file)
 	struct i915_gpu_state *gpu;
 	intel_wakeref_t wakeref;
 
-	wakeref = intel_runtime_pm_get(i915);
-	gpu = i915_capture_gpu_state(i915);
-	intel_runtime_pm_put(i915, wakeref);
+	gpu = NULL;
+	with_intel_runtime_pm(i915, wakeref)
+		gpu = i915_capture_gpu_state(i915);
 	if (IS_ERR(gpu))
 		return PTR_ERR(gpu);
 
@@ -1022,9 +1022,8 @@ i915_next_seqno_set(void *data, u64 val)
 	if (ret)
 		return ret;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	ret = i915_gem_set_global_seqno(dev, val);
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		ret = i915_gem_set_global_seqno(dev, val);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1312,17 +1311,15 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		return 0;
 	}
 
-	wakeref = intel_runtime_pm_get(dev_priv);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		for_each_engine(engine, dev_priv, id) {
+			acthd[id] = intel_engine_get_active_head(engine);
+			seqno[id] = intel_engine_get_seqno(engine);
+		}
 
-	for_each_engine(engine, dev_priv, id) {
-		acthd[id] = intel_engine_get_active_head(engine);
-		seqno[id] = intel_engine_get_seqno(engine);
+		intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
 	}
 
-	intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
-
-	intel_runtime_pm_put(dev_priv, wakeref);
-
 	if (timer_pending(&dev_priv->gpu_error.hangcheck_work.timer))
 		seq_printf(m, "Hangcheck active, timer fires in %dms\n",
 			   jiffies_to_msecs(dev_priv->gpu_error.hangcheck_work.timer.expires -
@@ -1598,18 +1595,16 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	intel_wakeref_t wakeref;
-	int err;
-
-	wakeref = intel_runtime_pm_get(dev_priv);
+	int err = -ENODEV;
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		err = vlv_drpc_info(m);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		err = gen6_drpc_info(m);
-	else
-		err = ironlake_drpc_info(m);
-
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+			err = vlv_drpc_info(m);
+		else if (INTEL_GEN(dev_priv) >= 6)
+			err = gen6_drpc_info(m);
+		else
+			err = ironlake_drpc_info(m);
+	}
 
 	return err;
 }
@@ -2093,8 +2088,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	intel_wakeref_t wakeref;
 	struct drm_file *file;
 
-	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
-	if (wakeref) {
+	with_intel_runtime_pm_if_in_use(dev_priv, wakeref) {
 		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 			mutex_lock(&dev_priv->pcu_lock);
 			act_freq = vlv_punit_read(dev_priv,
@@ -2105,7 +2099,6 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 			act_freq = intel_get_cagf(dev_priv,
 						  I915_READ(GEN6_RPSTAT1));
 		}
-		intel_runtime_pm_put(dev_priv, wakeref);
 	}
 
 	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
@@ -2197,9 +2190,8 @@ static int i915_huc_load_status_info(struct seq_file *m, void *data)
 	p = drm_seq_file_printer(m);
 	intel_uc_fw_dump(&dev_priv->huc.fw, &p);
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	seq_printf(m, "\nHuC status 0x%08x:\n", I915_READ(HUC_STATUS2));
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		seq_printf(m, "\nHuC status 0x%08x:\n", I915_READ(HUC_STATUS2));
 
 	return 0;
 }
@@ -2209,7 +2201,6 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	intel_wakeref_t wakeref;
 	struct drm_printer p;
-	u32 tmp, i;
 
 	if (!HAS_GUC(dev_priv))
 		return -ENODEV;
@@ -2217,22 +2208,23 @@ static int i915_guc_load_status_info(struct seq_file *m, void *data)
 	p = drm_seq_file_printer(m);
 	intel_uc_fw_dump(&dev_priv->guc.fw, &p);
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	tmp = I915_READ(GUC_STATUS);
-
-	seq_printf(m, "\nGuC status 0x%08x:\n", tmp);
-	seq_printf(m, "\tBootrom status = 0x%x\n",
-		(tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT);
-	seq_printf(m, "\tuKernel status = 0x%x\n",
-		(tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT);
-	seq_printf(m, "\tMIA Core status = 0x%x\n",
-		(tmp & GS_MIA_MASK) >> GS_MIA_SHIFT);
-	seq_puts(m, "\nScratch registers:\n");
-	for (i = 0; i < 16; i++)
-		seq_printf(m, "\t%2d: \t0x%x\n", i, I915_READ(SOFT_SCRATCH(i)));
-
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		u32 tmp = I915_READ(GUC_STATUS);
+		u32 i;
+
+		seq_printf(m, "\nGuC status 0x%08x:\n", tmp);
+		seq_printf(m, "\tBootrom status = 0x%x\n",
+			   (tmp & GS_BOOTROM_MASK) >> GS_BOOTROM_SHIFT);
+		seq_printf(m, "\tuKernel status = 0x%x\n",
+			   (tmp & GS_UKERNEL_MASK) >> GS_UKERNEL_SHIFT);
+		seq_printf(m, "\tMIA Core status = 0x%x\n",
+			   (tmp & GS_MIA_MASK) >> GS_MIA_SHIFT);
+		seq_puts(m, "\nScratch registers:\n");
+		for (i = 0; i < 16; i++) {
+			seq_printf(m, "\t%2d: \t0x%x\n",
+				   i, I915_READ(SOFT_SCRATCH(i)));
+		}
+	}
 
 	return 0;
 }
@@ -2705,19 +2697,14 @@ static int i915_energy_uJ(struct seq_file *m, void *data)
 	if (INTEL_GEN(dev_priv) < 6)
 		return -ENODEV;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &power)) {
-		intel_runtime_pm_put(dev_priv, wakeref);
+	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &power))
 		return -ENODEV;
-	}
 
 	units = (power & 0x1f00) >> 8;
-	power = I915_READ(MCH_SECP_NRG_STTS);
-	power = (1000000 * power) >> units; /* convert to uJ */
-
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		power = I915_READ(MCH_SECP_NRG_STTS);
 
+	power = (1000000 * power) >> units; /* convert to uJ */
 	seq_printf(m, "%llu", power);
 
 	return 0;
@@ -3300,22 +3287,20 @@ static ssize_t i915_ipc_status_write(struct file *file, const char __user *ubuf,
 	struct seq_file *m = file->private_data;
 	struct drm_i915_private *dev_priv = m->private;
 	intel_wakeref_t wakeref;
-	int ret;
 	bool enable;
+	int ret;
 
 	ret = kstrtobool_from_user(ubuf, len, &enable);
 	if (ret < 0)
 		return ret;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	if (!dev_priv->ipc_enabled && enable)
-		DRM_INFO("Enabling IPC: WM will be proper only after next commit\n");
-	dev_priv->wm.distrust_bios_wm = true;
-	dev_priv->ipc_enabled = enable;
-	intel_enable_ipc(dev_priv);
-
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		if (!dev_priv->ipc_enabled && enable)
+			DRM_INFO("Enabling IPC: WM will be proper only after next commit\n");
+		dev_priv->wm.distrust_bios_wm = true;
+		dev_priv->ipc_enabled = enable;
+		intel_enable_ipc(dev_priv);
+	}
 
 	return len;
 }
@@ -4158,16 +4143,13 @@ i915_cache_sharing_get(void *data, u64 *val)
 {
 	struct drm_i915_private *dev_priv = data;
 	intel_wakeref_t wakeref;
-	u32 snpcr;
+	u32 snpcr = 0;
 
 	if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv)))
 		return -ENODEV;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
-
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
 
 	*val = (snpcr & GEN6_MBC_SNPCR_MASK) >> GEN6_MBC_SNPCR_SHIFT;
 
@@ -4179,7 +4161,6 @@ i915_cache_sharing_set(void *data, u64 val)
 {
 	struct drm_i915_private *dev_priv = data;
 	intel_wakeref_t wakeref;
-	u32 snpcr;
 
 	if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv)))
 		return -ENODEV;
@@ -4187,16 +4168,17 @@ i915_cache_sharing_set(void *data, u64 val)
 	if (val > 3)
 		return -EINVAL;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
 	DRM_DEBUG_DRIVER("Manually setting uncore sharing to %llu\n", val);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		u32 snpcr;
+
+		/* Update the cache sharing policy here as well */
+		snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
+		snpcr &= ~GEN6_MBC_SNPCR_MASK;
+		snpcr |= val << GEN6_MBC_SNPCR_SHIFT;
+		I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
+	}
 
-	/* Update the cache sharing policy here as well */
-	snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
-	snpcr &= ~GEN6_MBC_SNPCR_MASK;
-	snpcr |= (val << GEN6_MBC_SNPCR_SHIFT);
-	I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
-
-	intel_runtime_pm_put(dev_priv, wakeref);
 	return 0;
 }
 
@@ -4433,20 +4415,17 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 	sseu.max_eus_per_subslice =
 		INTEL_INFO(dev_priv)->sseu.max_eus_per_subslice;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	if (IS_CHERRYVIEW(dev_priv)) {
-		cherryview_sseu_device_status(dev_priv, &sseu);
-	} else if (IS_BROADWELL(dev_priv)) {
-		broadwell_sseu_device_status(dev_priv, &sseu);
-	} else if (IS_GEN9(dev_priv)) {
-		gen9_sseu_device_status(dev_priv, &sseu);
-	} else if (INTEL_GEN(dev_priv) >= 10) {
-		gen10_sseu_device_status(dev_priv, &sseu);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		if (IS_CHERRYVIEW(dev_priv))
+			cherryview_sseu_device_status(dev_priv, &sseu);
+		else if (IS_BROADWELL(dev_priv))
+			broadwell_sseu_device_status(dev_priv, &sseu);
+		else if (IS_GEN9(dev_priv))
+			gen9_sseu_device_status(dev_priv, &sseu);
+		else if (INTEL_GEN(dev_priv) >= 10)
+			gen10_sseu_device_status(dev_priv, &sseu);
 	}
 
-	intel_runtime_pm_put(dev_priv, wakeref);
-
 	i915_print_sseu_info(m, false, &sseu);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b856f4f97746..79017fb9900f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -814,13 +814,13 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 
 	i915_gem_chipset_flush(dev_priv);
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	spin_lock_irq(&dev_priv->uncore.lock);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		spin_lock_irq(&dev_priv->uncore.lock);
 
-	POSTING_READ_FW(RING_HEAD(RENDER_RING_BASE));
+		POSTING_READ_FW(RING_HEAD(RENDER_RING_BASE));
 
-	spin_unlock_irq(&dev_priv->uncore.lock);
-	intel_runtime_pm_put(dev_priv, wakeref);
+		spin_unlock_irq(&dev_priv->uncore.lock);
+	}
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 1bc964ea8f03..c1dd1786fe7b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2527,9 +2527,8 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
-	wakeref = intel_runtime_pm_get(i915);
-	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref)
+		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 
@@ -2548,9 +2547,8 @@ static void ggtt_unbind_vma(struct i915_vma *vma)
 	struct drm_i915_private *i915 = vma->vm->i915;
 	intel_wakeref_t wakeref;
 
-	wakeref = intel_runtime_pm_get(i915);
-	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref)
+		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
 }
 
 static int aliasing_gtt_bind_vma(struct i915_vma *vma,
@@ -2584,9 +2582,10 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	if (flags & I915_VMA_GLOBAL_BIND) {
 		intel_wakeref_t wakeref;
 
-		wakeref = intel_runtime_pm_get(i915);
-		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-		intel_runtime_pm_put(i915, wakeref);
+		with_intel_runtime_pm(i915, wakeref) {
+			vma->vm->insert_entries(vma->vm, vma,
+						cache_level, pte_flags);
+		}
 	}
 
 	return 0;
@@ -2597,11 +2596,11 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 	struct drm_i915_private *i915 = vma->vm->i915;
 
 	if (vma->flags & I915_VMA_GLOBAL_BIND) {
+		struct i915_address_space *vm = vma->vm;
 		intel_wakeref_t wakeref;
 
-		wakeref = intel_runtime_pm_get(i915);
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-		intel_runtime_pm_put(i915, wakeref);
+		with_intel_runtime_pm(i915, wakeref)
+			vm->clear_range(vm, vma->node.start, vma->size);
 	}
 
 	if (vma->flags & I915_VMA_LOCAL_BIND) {
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index eac3a47f2a62..cb55dc4f0d1d 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -297,14 +297,14 @@ i915_gem_shrink(struct drm_i915_private *i915,
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
-	unsigned long freed;
+	unsigned long freed = 0;
 
-	wakeref = intel_runtime_pm_get(i915);
-	freed = i915_gem_shrink(i915, -1UL, NULL,
-				I915_SHRINK_BOUND |
-				I915_SHRINK_UNBOUND |
-				I915_SHRINK_ACTIVE);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref) {
+		freed = i915_gem_shrink(i915, -1UL, NULL,
+					I915_SHRINK_BOUND |
+					I915_SHRINK_UNBOUND |
+					I915_SHRINK_ACTIVE);
+	}
 
 	return freed;
 }
@@ -377,14 +377,14 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
 		intel_wakeref_t wakeref;
 
-		wakeref = intel_runtime_pm_get(i915);
-		freed += i915_gem_shrink(i915,
-					 sc->nr_to_scan - sc->nr_scanned,
-					 &sc->nr_scanned,
-					 I915_SHRINK_ACTIVE |
-					 I915_SHRINK_BOUND |
-					 I915_SHRINK_UNBOUND);
-		intel_runtime_pm_put(i915, wakeref);
+		with_intel_runtime_pm(i915, wakeref) {
+			freed += i915_gem_shrink(i915,
+						 sc->nr_to_scan - sc->nr_scanned,
+						 &sc->nr_scanned,
+						 I915_SHRINK_ACTIVE |
+						 I915_SHRINK_BOUND |
+						 I915_SHRINK_UNBOUND);
+		}
 	}
 
 	shrinker_unlock(i915, unlock);
@@ -481,13 +481,13 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 	if (ret)
 		goto out;
 
-	wakeref = intel_runtime_pm_get(i915);
-	freed_pages += i915_gem_shrink(i915, -1UL, NULL,
-				       I915_SHRINK_BOUND |
-				       I915_SHRINK_UNBOUND |
-				       I915_SHRINK_ACTIVE |
-				       I915_SHRINK_VMAPS);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref) {
+		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
+					       I915_SHRINK_BOUND |
+					       I915_SHRINK_UNBOUND |
+					       I915_SHRINK_ACTIVE |
+					       I915_SHRINK_VMAPS);
+	}
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 3d43fc9dd25d..b1cb2d3cae16 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -230,14 +230,11 @@ frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 
 		val = dev_priv->gt_pm.rps.cur_freq;
 		if (dev_priv->gt.awake) {
-			intel_wakeref_t wakeref =
-				intel_runtime_pm_get_if_in_use(dev_priv);
+			intel_wakeref_t wakeref;
 
-			if (wakeref) {
+			with_intel_runtime_pm_if_in_use(dev_priv, wakeref)
 				val = intel_get_cagf(dev_priv,
 						     I915_READ_NOTRACE(GEN6_RPSTAT1));
-				intel_runtime_pm_put(dev_priv, wakeref);
-			}
 		}
 
 		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 2cbbf165d179..41313005af42 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -43,11 +43,10 @@ static u32 calc_residency(struct drm_i915_private *dev_priv,
 			  i915_reg_t reg)
 {
 	intel_wakeref_t wakeref;
-	u64 res;
+	u64 res = 0;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	res = intel_rc6_residency_us(dev_priv, reg);
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		res = intel_rc6_residency_us(dev_priv, reg);
 
 	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 50231696ccfb..ce1b851273b4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -2178,6 +2178,14 @@ intel_wakeref_t intel_runtime_pm_get(struct drm_i915_private *i915);
 intel_wakeref_t intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915);
 intel_wakeref_t intel_runtime_pm_get_noresume(struct drm_i915_private *i915);
 
+#define with_intel_runtime_pm(i915, wf) \
+	for (wf = intel_runtime_pm_get(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)
+
+#define with_intel_runtime_pm_if_in_use(i915, wf) \
+	for (wf = intel_runtime_pm_get_if_in_use(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)
+
 void intel_runtime_pm_put_unchecked(struct drm_i915_private *i915);
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 void intel_runtime_pm_put(struct drm_i915_private *i915, intel_wakeref_t wref);
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index 20c0b36d748e..b53582c0c6c1 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -444,9 +444,8 @@ static void guc_log_capture_logs(struct intel_guc_log *log)
 	 * Generally device is expected to be active only at this
 	 * time, so get/put should be really quick.
 	 */
-	wakeref = intel_runtime_pm_get(dev_priv);
-	guc_action_flush_log_complete(guc);
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		guc_action_flush_log_complete(guc);
 }
 
 int intel_guc_log_create(struct intel_guc_log *log)
@@ -507,7 +506,7 @@ int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	intel_wakeref_t wakeref;
-	int ret;
+	int ret = 0;
 
 	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN != 0);
 	GEM_BUG_ON(!log->vma);
@@ -521,16 +520,14 @@ int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
-	if (log->level == level) {
-		ret = 0;
+	if (log->level == level)
 		goto out_unlock;
-	}
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(level),
-				     GUC_LOG_LEVEL_IS_ENABLED(level),
-				     GUC_LOG_LEVEL_TO_VERBOSITY(level));
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		ret = guc_action_control_log(guc,
+					     GUC_LOG_LEVEL_IS_VERBOSE(level),
+					     GUC_LOG_LEVEL_IS_ENABLED(level),
+					     GUC_LOG_LEVEL_TO_VERBOSITY(level));
 	if (ret) {
 		DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret);
 		goto out_unlock;
@@ -611,9 +608,8 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 	 */
 	flush_work(&log->relay.flush_work);
 
-	wakeref = intel_runtime_pm_get(i915);
-	guc_action_flush_log(guc);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref)
+		guc_action_flush_log(guc);
 
 	/* GuC would have updated log buffer by now, so capture it */
 	guc_log_capture_logs(log);
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 3e8c18b6a42d..9bd1c9002c2a 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -116,14 +116,13 @@ int intel_huc_check_status(struct intel_huc *huc)
 {
 	struct drm_i915_private *dev_priv = huc_to_i915(huc);
 	intel_wakeref_t wakeref;
-	bool status;
+	bool status = false;
 
 	if (!HAS_HUC(dev_priv))
 		return -ENODEV;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	status = I915_READ(HUC_STATUS2) & HUC_FW_VERIFIED;
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref)
+		status = I915_READ(HUC_STATUS2) & HUC_FW_VERIFIED;
 
 	return status;
 }
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 2c6cfb2086a9..04d416e540cc 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1204,17 +1204,19 @@ static int intel_backlight_device_get_brightness(struct backlight_device *bd)
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	intel_wakeref_t wakeref;
-	u32 hw_level;
-	int ret;
+	int ret = 0;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		u32 hw_level;
 
-	hw_level = intel_panel_get_backlight(connector);
-	ret = scale_hw_to_user(connector, hw_level, bd->props.max_brightness);
+		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
-	intel_runtime_pm_put(dev_priv, wakeref);
+		hw_level = intel_panel_get_backlight(connector);
+		ret = scale_hw_to_user(connector,
+				       hw_level, bd->props.max_brightness);
+
+		drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index e042238e39f6..44ea203b27e7 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1696,21 +1696,21 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 
 	flags = reg->offset & (entry->size - 1);
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	if (entry->size == 8 && flags == I915_REG_READ_8B_WA)
-		reg->val = I915_READ64_2x32(entry->offset_ldw,
-					    entry->offset_udw);
-	else if (entry->size == 8 && flags == 0)
-		reg->val = I915_READ64(entry->offset_ldw);
-	else if (entry->size == 4 && flags == 0)
-		reg->val = I915_READ(entry->offset_ldw);
-	else if (entry->size == 2 && flags == 0)
-		reg->val = I915_READ16(entry->offset_ldw);
-	else if (entry->size == 1 && flags == 0)
-		reg->val = I915_READ8(entry->offset_ldw);
-	else
-		ret = -EINVAL;
-	intel_runtime_pm_put(dev_priv, wakeref);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		if (entry->size == 8 && flags == I915_REG_READ_8B_WA)
+			reg->val = I915_READ64_2x32(entry->offset_ldw,
+						    entry->offset_udw);
+		else if (entry->size == 8 && flags == 0)
+			reg->val = I915_READ64(entry->offset_ldw);
+		else if (entry->size == 4 && flags == 0)
+			reg->val = I915_READ(entry->offset_ldw);
+		else if (entry->size == 2 && flags == 0)
+			reg->val = I915_READ16(entry->offset_ldw);
+		else if (entry->size == 1 && flags == 0)
+			reg->val = I915_READ8(entry->offset_ldw);
+		else
+			ret = -EINVAL;
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 01a46c46fe25..e77b7ed449ae 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -98,26 +98,22 @@ static void pm_suspend(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
 
-	wakeref = intel_runtime_pm_get(i915);
-
-	i915_gem_suspend_gtt_mappings(i915);
-	i915_gem_suspend_late(i915);
-
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref) {
+		i915_gem_suspend_gtt_mappings(i915);
+		i915_gem_suspend_late(i915);
+	}
 }
 
 static void pm_hibernate(struct drm_i915_private *i915)
 {
 	intel_wakeref_t wakeref;
 
-	wakeref = intel_runtime_pm_get(i915);
-
-	i915_gem_suspend_gtt_mappings(i915);
-
-	i915_gem_freeze(i915);
-	i915_gem_freeze_late(i915);
+	with_intel_runtime_pm(i915, wakeref) {
+		i915_gem_suspend_gtt_mappings(i915);
 
-	intel_runtime_pm_put(i915, wakeref);
+		i915_gem_freeze(i915);
+		i915_gem_freeze_late(i915);
+	}
 }
 
 static void pm_resume(struct drm_i915_private *i915)
@@ -128,13 +124,11 @@ 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.
 	 */
-	wakeref = intel_runtime_pm_get(i915);
-
-	intel_engines_sanitize(i915, false);
-	i915_gem_sanitize(i915);
-	i915_gem_resume(i915);
-
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref) {
+		intel_engines_sanitize(i915, false);
+		i915_gem_sanitize(i915);
+		i915_gem_resume(i915);
+	}
 }
 
 static int igt_gem_suspend(void *arg)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 6edf943892d0..f5926aa23e9d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -610,9 +610,9 @@ static int igt_ctx_exec(void *arg)
 				}
 			}
 
-			wakeref = intel_runtime_pm_get(i915);
-			err = gpu_fill(obj, ctx, engine, dw);
-			intel_runtime_pm_put(i915, wakeref);
+			err = 0;
+			with_intel_runtime_pm(i915, wakeref)
+				err = gpu_fill(obj, ctx, engine, dw);
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
@@ -718,9 +718,9 @@ static int igt_ctx_readonly(void *arg)
 					i915_gem_object_set_readonly(obj);
 			}
 
-			wakeref = intel_runtime_pm_get(i915);
-			err = gpu_fill(obj, ctx, engine, dw);
-			intel_runtime_pm_put(i915, wakeref);
+			err = 0;
+			with_intel_runtime_pm(i915, wakeref)
+				err = gpu_fill(obj, ctx, engine, dw);
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 26706aec7d73..5b7fea064481 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -508,9 +508,8 @@ static void disable_retire_worker(struct drm_i915_private *i915)
 	if (!i915->gt.active_requests++) {
 		intel_wakeref_t wakeref;
 
-		wakeref = intel_runtime_pm_get(i915);
-		i915_gem_unpark(i915);
-		intel_runtime_pm_put(i915, wakeref);
+		with_intel_runtime_pm(i915, wakeref)
+			i915_gem_unpark(i915);
 	}
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -592,10 +591,10 @@ static int igt_mmap_offset_exhaustion(void *arg)
 			goto out;
 		}
 
+		err = 0;
 		mutex_lock(&i915->drm.struct_mutex);
-		wakeref = intel_runtime_pm_get(i915);
-		err = make_obj_busy(obj);
-		intel_runtime_pm_put(i915, wakeref);
+		with_intel_runtime_pm(i915, wakeref)
+			err = make_obj_busy(obj);
 		mutex_unlock(&i915->drm.struct_mutex);
 		if (err) {
 			pr_err("[loop %d] Failed to busy the object\n", loop);
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index c6a26d7ad326..b7b5bbeff51c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -48,9 +48,9 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	if (err)
 		goto err_obj;
 
-	wakeref = intel_runtime_pm_get(engine->i915);
-	rq = i915_request_alloc(engine, ctx);
-	intel_runtime_pm_put(engine->i915, wakeref);
+	rq = ERR_PTR(-ENODEV);
+	with_intel_runtime_pm(engine->i915, wakeref)
+		rq = i915_request_alloc(engine, ctx);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_pin;
@@ -191,14 +191,15 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	wakeref = intel_runtime_pm_get(engine->i915);
-
-	if (spin)
-		rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
-	else
-		rq = i915_request_alloc(engine, ctx);
-
-	intel_runtime_pm_put(engine->i915, wakeref);
+	rq = ERR_PTR(-ENODEV);
+	with_intel_runtime_pm(engine->i915, wakeref) {
+		if (spin)
+			rq = igt_spinner_create_request(spin,
+							ctx, engine,
+							MI_NOOP);
+		else
+			rq = i915_request_alloc(engine, ctx);
+	}
 
 	kernel_context_close(ctx);
 
@@ -256,9 +257,8 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	if (err)
 		goto out;
 
-	wakeref = intel_runtime_pm_get(i915);
-	err = reset(engine);
-	intel_runtime_pm_put(i915, wakeref);
+	with_intel_runtime_pm(i915, wakeref)
+		err = reset(engine);
 
 	if (want_spin) {
 		igt_spinner_end(&spin);
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 14/19] drm/i915: Markup paired operations on display power domains

[Chris Wilson]

The majority of runtime-pm operations are bounded and scoped within a
function; these are easy to verify that the wakeref are handled
correctly. We can employ the compiler to help us, and reduce the number
of wakerefs tracked when debugging, by passing around cookies provided
by the various rpm_get functions to their rpm_put counterpart. This
makes the pairing explicit, and given the required wakeref cookie the
compiler can verify that we pass an initialised value to the rpm_put
(quite handy for double checking error paths).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c     | 35 ++++++------
 drivers/gpu/drm/i915/i915_drv.h         |  2 +
 drivers/gpu/drm/i915/i915_gem.c         |  4 +-
 drivers/gpu/drm/i915/icl_dsi.c          | 36 ++++++++-----
 drivers/gpu/drm/i915/intel_audio.c      |  3 +-
 drivers/gpu/drm/i915/intel_cdclk.c      | 10 ++--
 drivers/gpu/drm/i915/intel_crt.c        | 25 +++++----
 drivers/gpu/drm/i915/intel_csr.c        | 25 +++++++--
 drivers/gpu/drm/i915/intel_ddi.c        | 36 ++++++++-----
 drivers/gpu/drm/i915/intel_display.c    | 68 ++++++++++++++---------
 drivers/gpu/drm/i915/intel_dp.c         | 38 +++++++------
 drivers/gpu/drm/i915/intel_dpll_mgr.c   | 66 +++++++++++++++--------
 drivers/gpu/drm/i915/intel_drv.h        | 17 ++++--
 drivers/gpu/drm/i915/intel_dsi.h        |  1 +
 drivers/gpu/drm/i915/intel_hdmi.c       | 18 ++++---
 drivers/gpu/drm/i915/intel_i2c.c        | 20 +++----
 drivers/gpu/drm/i915/intel_lvds.c       |  8 +--
 drivers/gpu/drm/i915/intel_pipe_crc.c   |  6 ++-
 drivers/gpu/drm/i915/intel_pm.c         |  6 ++-
 drivers/gpu/drm/i915/intel_runtime_pm.c | 71 ++++++++++++++++---------
 drivers/gpu/drm/i915/intel_sprite.c     | 24 ++++++---
 drivers/gpu/drm/i915/intel_vdsc.c       |  4 +-
 drivers/gpu/drm/i915/vlv_dsi.c          | 14 +++--
 23 files changed, 347 insertions(+), 190 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 756f14763585..248a03953ba7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -626,10 +626,12 @@ static void gen8_display_interrupt_info(struct seq_file *m)
 
 	for_each_pipe(dev_priv, pipe) {
 		enum intel_display_power_domain power_domain;
+		intel_wakeref_t wakeref;
 
 		power_domain = POWER_DOMAIN_PIPE(pipe);
-		if (!intel_display_power_get_if_enabled(dev_priv,
-							power_domain)) {
+		wakeref = intel_display_power_get_if_enabled(dev_priv,
+							     power_domain);
+		if (!wakeref) {
 			seq_printf(m, "Pipe %c power disabled\n",
 				   pipe_name(pipe));
 			continue;
@@ -644,7 +646,7 @@ static void gen8_display_interrupt_info(struct seq_file *m)
 			   pipe_name(pipe),
 			   I915_READ(GEN8_DE_PIPE_IER(pipe)));
 
-		intel_display_power_put(dev_priv, power_domain);
+		intel_display_power_put(dev_priv, power_domain, wakeref);
 	}
 
 	seq_printf(m, "Display Engine port interrupt mask:\t%08x\n",
@@ -680,6 +682,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 	wakeref = intel_runtime_pm_get(dev_priv);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
+		intel_wakeref_t pref;
+
 		seq_printf(m, "Master Interrupt Control:\t%08x\n",
 			   I915_READ(GEN8_MASTER_IRQ));
 
@@ -695,8 +699,9 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			enum intel_display_power_domain power_domain;
 
 			power_domain = POWER_DOMAIN_PIPE(pipe);
-			if (!intel_display_power_get_if_enabled(dev_priv,
-								power_domain)) {
+			pref = intel_display_power_get_if_enabled(dev_priv,
+								  power_domain);
+			if (!pref) {
 				seq_printf(m, "Pipe %c power disabled\n",
 					   pipe_name(pipe));
 				continue;
@@ -706,17 +711,17 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 				   pipe_name(pipe),
 				   I915_READ(PIPESTAT(pipe)));
 
-			intel_display_power_put(dev_priv, power_domain);
+			intel_display_power_put(dev_priv, power_domain, pref);
 		}
 
-		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+		pref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
 		seq_printf(m, "Port hotplug:\t%08x\n",
 			   I915_READ(PORT_HOTPLUG_EN));
 		seq_printf(m, "DPFLIPSTAT:\t%08x\n",
 			   I915_READ(VLV_DPFLIPSTAT));
 		seq_printf(m, "DPINVGTT:\t%08x\n",
 			   I915_READ(DPINVGTT));
-		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, pref);
 
 		for (i = 0; i < 4; i++) {
 			seq_printf(m, "GT Interrupt IMR %d:\t%08x\n",
@@ -779,10 +784,12 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			   I915_READ(VLV_IMR));
 		for_each_pipe(dev_priv, pipe) {
 			enum intel_display_power_domain power_domain;
+			intel_wakeref_t pref;
 
 			power_domain = POWER_DOMAIN_PIPE(pipe);
-			if (!intel_display_power_get_if_enabled(dev_priv,
-								power_domain)) {
+			pref = intel_display_power_get_if_enabled(dev_priv,
+								  power_domain);
+			if (!pref) {
 				seq_printf(m, "Pipe %c power disabled\n",
 					   pipe_name(pipe));
 				continue;
@@ -791,7 +798,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			seq_printf(m, "Pipe %c stat:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(PIPESTAT(pipe)));
-			intel_display_power_put(dev_priv, power_domain);
+			intel_display_power_put(dev_priv, power_domain, pref);
 		}
 
 		seq_printf(m, "Master IER:\t%08x\n",
@@ -1733,8 +1740,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 	intel_wakeref_t wakeref;
 	bool sr_enabled = false;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		/* no global SR status; inspect per-plane WM */;
@@ -1750,8 +1756,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		sr_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
-	intel_runtime_pm_put(dev_priv, wakeref);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref);
 
 	seq_printf(m, "self-refresh: %s\n", enableddisabled(sr_enabled));
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e2b6dc3027c1..233190eaae62 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -344,6 +344,7 @@ struct intel_csr {
 	uint32_t mmiodata[8];
 	uint32_t dc_state;
 	uint32_t allowed_dc_mask;
+	intel_wakeref_t wakeref;
 };
 
 enum i915_cache_level {
@@ -1967,6 +1968,7 @@ struct drm_i915_private {
 		 * is a slight delay before we do so.
 		 */
 		intel_wakeref_t awake;
+		intel_wakeref_t power;
 
 		/**
 		 * The number of times we have woken up.
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 79017fb9900f..d481580f09c1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -177,7 +177,7 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
-	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ);
+	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, i915->gt.power);
 
 	intel_runtime_pm_put(i915, wakeref);
 
@@ -222,7 +222,7 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 	 * Work around it by grabbing a GT IRQ power domain whilst there is any
 	 * GT activity, preventing any DC state transitions.
 	 */
-	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+	i915->gt.power = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 
 	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
 		i915->gt.epoch = 1;
diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
index 4dd793b78996..f3a5f03646ce 100644
--- a/drivers/gpu/drm/i915/icl_dsi.c
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -337,9 +337,11 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 	}
 
 	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_display_power_get(dev_priv, port == PORT_A ?
-					POWER_DOMAIN_PORT_DDI_A_IO :
-					POWER_DOMAIN_PORT_DDI_B_IO);
+		intel_dsi->io_wakeref[port] =
+			intel_display_power_get(dev_priv,
+						port == PORT_A ?
+						POWER_DOMAIN_PORT_DDI_A_IO :
+						POWER_DOMAIN_PORT_DDI_B_IO);
 	}
 }
 
@@ -1125,10 +1127,18 @@ static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 	enum port port;
 	u32 tmp;
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PORT_DDI_A_IO);
-
-	if (intel_dsi->dual_link)
-		intel_display_power_put(dev_priv, POWER_DOMAIN_PORT_DDI_B_IO);
+	for_each_dsi_port(port, intel_dsi->ports) {
+		intel_wakeref_t wakeref;
+
+		wakeref = fetch_and_zero(&intel_dsi->io_wakeref[port]);
+		if (wakeref) {
+			intel_display_power_put(dev_priv,
+						port == PORT_A ?
+						POWER_DOMAIN_PORT_DDI_A_IO :
+						POWER_DOMAIN_PORT_DDI_B_IO,
+						wakeref);
+		}
+	}
 
 	/* set mode to DDI */
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -1229,13 +1239,15 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	u32 tmp;
-	enum port port;
 	enum transcoder dsi_trans;
+	intel_wakeref_t wakeref;
+	enum port port;
 	bool ret = false;
+	u32 tmp;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -1260,7 +1272,7 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 		ret = tmp & PIPECONF_ENABLE;
 	}
 out:
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index ae55a6865d5c..b2da5415f407 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -749,7 +749,8 @@ static void i915_audio_component_get_power(struct device *kdev)
 
 static void i915_audio_component_put_power(struct device *kdev)
 {
-	intel_display_power_put(kdev_to_i915(kdev), POWER_DOMAIN_AUDIO);
+	intel_display_power_put_unchecked(kdev_to_i915(kdev),
+					  POWER_DOMAIN_AUDIO);
 }
 
 static void i915_audio_component_codec_wake_override(struct device *kdev,
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 25e3aba9cded..2f3e771ce663 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -520,6 +520,7 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 {
 	int cdclk = cdclk_state->cdclk;
 	u32 val, cmd = cdclk_state->voltage_level;
+	intel_wakeref_t wakeref;
 
 	switch (cdclk) {
 	case 400000:
@@ -539,7 +540,7 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 	 * a system suspend.  So grab the PIPE-A domain, which covers
 	 * the HW blocks needed for the following programming.
 	 */
-	intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
 
 	mutex_lock(&dev_priv->pcu_lock);
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
@@ -593,7 +594,7 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv,
 
 	vlv_program_pfi_credits(dev_priv);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A, wakeref);
 }
 
 static void chv_set_cdclk(struct drm_i915_private *dev_priv,
@@ -601,6 +602,7 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 {
 	int cdclk = cdclk_state->cdclk;
 	u32 val, cmd = cdclk_state->voltage_level;
+	intel_wakeref_t wakeref;
 
 	switch (cdclk) {
 	case 333333:
@@ -619,7 +621,7 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 	 * a system suspend.  So grab the PIPE-A domain, which covers
 	 * the HW blocks needed for the following programming.
 	 */
-	intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A);
 
 	mutex_lock(&dev_priv->pcu_lock);
 	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
@@ -637,7 +639,7 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv,
 
 	vlv_program_pfi_credits(dev_priv);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A, wakeref);
 }
 
 static int bdw_calc_cdclk(int min_cdclk)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 68f2fb89ece3..d4ea034cbe44 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -84,15 +84,17 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
+	intel_wakeref_t wakeref;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = intel_crt_port_enabled(dev_priv, crt->adpa_reg, pipe);
 
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return ret;
 }
@@ -777,6 +779,7 @@ intel_crt_detect(struct drm_connector *connector,
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_crt *crt = intel_attached_crt(connector);
 	struct intel_encoder *intel_encoder = &crt->base;
+	intel_wakeref_t wakeref;
 	int status, ret;
 	struct intel_load_detect_pipe tmp;
 
@@ -785,7 +788,8 @@ intel_crt_detect(struct drm_connector *connector,
 		      force);
 
 	if (i915_modparams.load_detect_test) {
-		intel_display_power_get(dev_priv, intel_encoder->power_domain);
+		wakeref = intel_display_power_get(dev_priv,
+						  intel_encoder->power_domain);
 		goto load_detect;
 	}
 
@@ -793,7 +797,8 @@ intel_crt_detect(struct drm_connector *connector,
 	if (dmi_check_system(intel_spurious_crt_detect))
 		return connector_status_disconnected;
 
-	intel_display_power_get(dev_priv, intel_encoder->power_domain);
+	wakeref = intel_display_power_get(dev_priv,
+					  intel_encoder->power_domain);
 
 	if (I915_HAS_HOTPLUG(dev_priv)) {
 		/* We can not rely on the HPD pin always being correctly wired
@@ -848,7 +853,7 @@ intel_crt_detect(struct drm_connector *connector,
 	}
 
 out:
-	intel_display_power_put(dev_priv, intel_encoder->power_domain);
+	intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
 	return status;
 }
 
@@ -858,10 +863,12 @@ static int intel_crt_get_modes(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crt *crt = intel_attached_crt(connector);
 	struct intel_encoder *intel_encoder = &crt->base;
-	int ret;
+	intel_wakeref_t wakeref;
 	struct i2c_adapter *i2c;
+	int ret;
 
-	intel_display_power_get(dev_priv, intel_encoder->power_domain);
+	wakeref = intel_display_power_get(dev_priv,
+					  intel_encoder->power_domain);
 
 	i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->vbt.crt_ddc_pin);
 	ret = intel_crt_ddc_get_modes(connector, i2c);
@@ -873,7 +880,7 @@ static int intel_crt_get_modes(struct drm_connector *connector)
 	ret = intel_crt_ddc_get_modes(connector, i2c);
 
 out:
-	intel_display_power_put(dev_priv, intel_encoder->power_domain);
+	intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index a516697bf57d..ea5fb64d33dd 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -409,6 +409,21 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
 	return memcpy(dmc_payload, &fw->data[readcount], nbytes);
 }
 
+static void intel_csr_runtime_pm_get(struct drm_i915_private *dev_priv)
+{
+	WARN_ON(dev_priv->csr.wakeref);
+	dev_priv->csr.wakeref =
+		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+}
+
+static void intel_csr_runtime_pm_put(struct drm_i915_private *dev_priv)
+{
+	intel_wakeref_t wakeref __maybe_unused =
+		fetch_and_zero(&dev_priv->csr.wakeref);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref);
+}
+
 static void csr_load_work_fn(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv;
@@ -424,8 +439,7 @@ static void csr_load_work_fn(struct work_struct *work)
 
 	if (dev_priv->csr.dmc_payload) {
 		intel_csr_load_program(dev_priv);
-
-		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+		intel_csr_runtime_pm_put(dev_priv);
 
 		DRM_INFO("Finished loading DMC firmware %s (v%u.%u)\n",
 			 dev_priv->csr.fw_path,
@@ -467,7 +481,7 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv)
 	 * suspend as runtime suspend *requires* a working CSR for whatever
 	 * reason.
 	 */
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	intel_csr_runtime_pm_get(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
 		/* Allow to load fw via parameter using the last known size */
@@ -538,7 +552,7 @@ void intel_csr_ucode_suspend(struct drm_i915_private *dev_priv)
 
 	/* Drop the reference held in case DMC isn't loaded. */
 	if (!dev_priv->csr.dmc_payload)
-		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+		intel_csr_runtime_pm_put(dev_priv);
 }
 
 /**
@@ -558,7 +572,7 @@ void intel_csr_ucode_resume(struct drm_i915_private *dev_priv)
 	 * loaded.
 	 */
 	if (!dev_priv->csr.dmc_payload)
-		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+		intel_csr_runtime_pm_get(dev_priv);
 }
 
 /**
@@ -574,6 +588,7 @@ void intel_csr_ucode_fini(struct drm_i915_private *dev_priv)
 		return;
 
 	intel_csr_ucode_suspend(dev_priv);
+	WARN_ON(dev_priv->csr.wakeref);
 
 	kfree(dev_priv->csr.dmc_payload);
 }
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 92c0bf70fe09..f9d644055276 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1922,12 +1922,14 @@ int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	intel_wakeref_t wakeref;
 	enum pipe pipe = 0;
 	int ret = 0;
 	uint32_t tmp;
 
-	if (WARN_ON(!intel_display_power_get_if_enabled(dev_priv,
-						intel_encoder->power_domain)))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     intel_encoder->power_domain);
+	if (WARN_ON(!wakeref))
 		return -ENXIO;
 
 	if (WARN_ON(!intel_encoder->get_hw_state(intel_encoder, &pipe))) {
@@ -1942,7 +1944,7 @@ int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
 		tmp &= ~TRANS_DDI_HDCP_SIGNALLING;
 	I915_WRITE(TRANS_DDI_FUNC_CTL(pipe), tmp);
 out:
-	intel_display_power_put(dev_priv, intel_encoder->power_domain);
+	intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
 	return ret;
 }
 
@@ -1953,13 +1955,15 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	struct intel_encoder *encoder = intel_connector->encoder;
 	int type = intel_connector->base.connector_type;
 	enum port port = encoder->port;
-	enum pipe pipe = 0;
 	enum transcoder cpu_transcoder;
+	intel_wakeref_t wakeref;
+	enum pipe pipe = 0;
 	uint32_t tmp;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	if (!encoder->get_hw_state(encoder, &pipe)) {
@@ -2001,7 +2005,7 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	}
 
 out:
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return ret;
 }
@@ -2012,6 +2016,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = encoder->port;
+	intel_wakeref_t wakeref;
 	enum pipe p;
 	u32 tmp;
 	u8 mst_pipe_mask;
@@ -2019,8 +2024,9 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 	*pipe_mask = 0;
 	*is_dp_mst = false;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return;
 
 	tmp = I915_READ(DDI_BUF_CTL(port));
@@ -2091,7 +2097,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 				  "(PHY_CTL %08x)\n", port_name(port), tmp);
 	}
 
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 }
 
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
@@ -3349,7 +3355,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	intel_edp_panel_vdd_on(intel_dp);
 	intel_edp_panel_off(intel_dp);
 
-	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
+	intel_display_power_put_unchecked(dev_priv,
+					  dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
 }
@@ -3369,7 +3376,8 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 
 	intel_disable_ddi_buf(encoder, old_crtc_state);
 
-	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
+	intel_display_power_put_unchecked(dev_priv,
+					  dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
 
@@ -3671,8 +3679,8 @@ intel_ddi_post_pll_disable(struct intel_encoder *encoder,
 
 	if (intel_crtc_has_dp_encoder(crtc_state) ||
 	    intel_port_is_tc(dev_priv, encoder->port))
-		intel_display_power_put(dev_priv,
-					intel_ddi_main_link_aux_domain(dig_port));
+		intel_display_power_put_unchecked(dev_priv,
+						  intel_ddi_main_link_aux_domain(dig_port));
 }
 
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 09f21f39bbdb..4e822ae56c90 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1198,17 +1198,19 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 
 	/* we keep both pipes enabled on 830 */
 	if (IS_I830(dev_priv))
 		state = true;
 
 	power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
-	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (wakeref) {
 		u32 val = I915_READ(PIPECONF(cpu_transcoder));
 		cur_state = !!(val & PIPECONF_ENABLE);
 
-		intel_display_power_put(dev_priv, power_domain);
+		intel_display_power_put(dev_priv, power_domain, wakeref);
 	} else {
 		cur_state = false;
 	}
@@ -3413,6 +3415,7 @@ static bool i9xx_plane_get_hw_state(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
+	intel_wakeref_t wakeref;
 	bool ret;
 	u32 val;
 
@@ -3422,7 +3425,8 @@ static bool i9xx_plane_get_hw_state(struct intel_plane *plane,
 	 * display power wells.
 	 */
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(DSPCNTR(i9xx_plane));
@@ -3435,7 +3439,7 @@ static bool i9xx_plane_get_hw_state(struct intel_plane *plane,
 		*pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
 			DISPPLANE_SEL_PIPE_SHIFT;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -6088,7 +6092,7 @@ static void modeset_put_power_domains(struct drm_i915_private *dev_priv,
 	enum intel_display_power_domain domain;
 
 	for_each_power_domain(domain, domains)
-		intel_display_power_put(dev_priv, domain);
+		intel_display_power_put_unchecked(dev_priv, domain);
 }
 
 static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
@@ -6335,7 +6339,7 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc,
 
 	domains = intel_crtc->enabled_power_domains;
 	for_each_power_domain(domain, domains)
-		intel_display_power_put(dev_priv, domain);
+		intel_display_power_put_unchecked(dev_priv, domain);
 	intel_crtc->enabled_power_domains = 0;
 
 	dev_priv->active_crtcs &= ~(1 << intel_crtc->pipe);
@@ -7947,11 +7951,13 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	uint32_t tmp;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
@@ -8052,7 +8058,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -9019,11 +9025,13 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	uint32_t tmp;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
@@ -9106,7 +9114,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -9715,7 +9723,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 out:
 	for_each_power_domain(power_domain, power_domain_mask)
-		intel_display_power_put(dev_priv, power_domain);
+		intel_display_power_put_unchecked(dev_priv, power_domain);
 
 	return active;
 }
@@ -9965,17 +9973,19 @@ static bool i845_cursor_get_hw_state(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(PIPE_A);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE;
 
 	*pipe = PIPE_A;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -10198,6 +10208,7 @@ static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	bool ret;
 	u32 val;
 
@@ -10207,7 +10218,8 @@ static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
 	 * display power wells.
 	 */
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(CURCNTR(plane->pipe));
@@ -10220,7 +10232,7 @@ static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
 		*pipe = (val & MCURSOR_PIPE_SELECT_MASK) >>
 			MCURSOR_PIPE_SELECT_SHIFT;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -12926,6 +12938,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_crtc *crtc;
 	struct intel_crtc *intel_crtc;
 	u64 put_domains[I915_MAX_PIPES] = {};
+	intel_wakeref_t wakeref = 0;
 	int i;
 
 	intel_atomic_commit_fence_wait(intel_state);
@@ -12933,7 +12946,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	drm_atomic_helper_wait_for_dependencies(state);
 
 	if (intel_state->modeset)
-		intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
+		wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
 
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		old_intel_crtc_state = to_intel_crtc_state(old_crtc_state);
@@ -13070,7 +13083,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 		 * the culprit.
 		 */
 		intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
-		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
+		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET, wakeref);
 	}
 
 	/*
@@ -15472,19 +15485,25 @@ void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv)
 
 void i915_redisable_vga(struct drm_i915_private *dev_priv)
 {
-	/* This function can be called both from intel_modeset_setup_hw_state or
+	intel_wakeref_t wakeref;
+
+	/*
+	 * This function can be called both from intel_modeset_setup_hw_state or
 	 * at a very early point in our resume sequence, where the power well
 	 * structures are not yet restored. Since this function is at a very
 	 * paranoid "someone might have enabled VGA while we were not looking"
 	 * level, just check if the power well is enabled instead of trying to
 	 * follow the "don't touch the power well if we don't need it" policy
-	 * the rest of the driver uses. */
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA))
+	 * the rest of the driver uses.
+	 */
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_VGA);
+	if (!wakeref)
 		return;
 
 	i915_redisable_vga_power_on(dev_priv);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA, wakeref);
 }
 
 /* FIXME read out full plane state for all planes */
@@ -15784,12 +15803,13 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 			     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc;
 	struct intel_crtc_state *crtc_state;
 	struct intel_encoder *encoder;
+	struct intel_crtc *crtc;
+	intel_wakeref_t wakeref;
 	int i;
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
 
 	intel_early_display_was(dev_priv);
 	intel_modeset_readout_hw_state(dev);
@@ -15859,7 +15879,7 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 			modeset_put_power_domains(dev_priv, put_domains);
 	}
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref);
 
 	intel_fbc_init_pipe_state(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index e94faa0a42eb..2fb7f297d0a1 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -620,8 +620,8 @@ static void pps_unlock(struct intel_dp *intel_dp)
 
 	mutex_unlock(&dev_priv->pps_mutex);
 
-	intel_display_power_put(dev_priv,
-				intel_aux_power_domain(dp_to_dig_port(intel_dp)));
+	intel_display_power_put_unchecked(dev_priv,
+					  intel_aux_power_domain(dp_to_dig_port(intel_dp)));
 }
 
 static void
@@ -2509,8 +2509,8 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	if ((pp & PANEL_POWER_ON) == 0)
 		intel_dp->panel_power_off_time = ktime_get_boottime();
 
-	intel_display_power_put(dev_priv,
-				intel_aux_power_domain(intel_dig_port));
+	intel_display_power_put_unchecked(dev_priv,
+					  intel_aux_power_domain(intel_dig_port));
 }
 
 static void edp_panel_vdd_work(struct work_struct *__work)
@@ -2655,7 +2655,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	intel_dp->panel_power_off_time = ktime_get_boottime();
 
 	/* We got a reference when we enabled the VDD. */
-	intel_display_power_put(dev_priv, intel_aux_power_domain(dig_port));
+	intel_display_power_put_unchecked(dev_priv, intel_aux_power_domain(dig_port));
 }
 
 void intel_edp_panel_off(struct intel_dp *intel_dp)
@@ -2981,16 +2981,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_wakeref_t wakeref;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = intel_dp_port_enabled(dev_priv, intel_dp->output_reg,
 				    encoder->port, pipe);
 
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return ret;
 }
@@ -5343,12 +5345,13 @@ intel_dp_detect(struct drm_connector *connector,
 	enum drm_connector_status status;
 	enum intel_display_power_domain aux_domain =
 		intel_aux_power_domain(dig_port);
+	intel_wakeref_t wakeref;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
 
-	intel_display_power_get(dev_priv, aux_domain);
+	wakeref = intel_display_power_get(dev_priv, aux_domain);
 
 	/* Can't disconnect eDP */
 	if (intel_dp_is_edp(intel_dp))
@@ -5414,7 +5417,7 @@ intel_dp_detect(struct drm_connector *connector,
 
 		ret = intel_dp_retrain_link(encoder, ctx);
 		if (ret) {
-			intel_display_power_put(dev_priv, aux_domain);
+			intel_display_power_put(dev_priv, aux_domain, wakeref);
 			return ret;
 		}
 	}
@@ -5438,7 +5441,7 @@ intel_dp_detect(struct drm_connector *connector,
 	if (status != connector_status_connected && !intel_dp->is_mst)
 		intel_dp_unset_edid(intel_dp);
 
-	intel_display_power_put(dev_priv, aux_domain);
+	intel_display_power_put(dev_priv, aux_domain, wakeref);
 	return status;
 }
 
@@ -5451,6 +5454,7 @@ intel_dp_force(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
 	enum intel_display_power_domain aux_domain =
 		intel_aux_power_domain(dig_port);
+	intel_wakeref_t wakeref;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
@@ -5459,11 +5463,11 @@ intel_dp_force(struct drm_connector *connector)
 	if (connector->status != connector_status_connected)
 		return;
 
-	intel_display_power_get(dev_priv, aux_domain);
+	wakeref = intel_display_power_get(dev_priv, aux_domain);
 
 	intel_dp_set_edid(intel_dp);
 
-	intel_display_power_put(dev_priv, aux_domain);
+	intel_display_power_put(dev_priv, aux_domain, wakeref);
 }
 
 static int intel_dp_get_modes(struct drm_connector *connector)
@@ -5904,6 +5908,7 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	enum irqreturn ret = IRQ_NONE;
+	intel_wakeref_t wakeref;
 
 	if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
 		/*
@@ -5926,8 +5931,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 		return IRQ_NONE;
 	}
 
-	intel_display_power_get(dev_priv,
-				intel_aux_power_domain(intel_dig_port));
+	wakeref = intel_display_power_get(dev_priv,
+					  intel_aux_power_domain(intel_dig_port));
 
 	if (intel_dp->is_mst) {
 		if (intel_dp_check_mst_status(intel_dp) == -EINVAL) {
@@ -5957,7 +5962,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 
 put_power:
 	intel_display_power_put(dev_priv,
-				intel_aux_power_domain(intel_dig_port));
+				intel_aux_power_domain(intel_dig_port),
+				wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index d513ca875c67..04870e960537 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -345,9 +345,12 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 				      struct intel_dpll_hw_state *hw_state)
 {
 	const enum intel_dpll_id id = pll->info->id;
+	intel_wakeref_t wakeref;
 	uint32_t val;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(PCH_DPLL(id));
@@ -355,7 +358,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 	hw_state->fp0 = I915_READ(PCH_FP0(id));
 	hw_state->fp1 = I915_READ(PCH_FP1(id));
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return val & DPLL_VCO_ENABLE;
 }
@@ -509,15 +512,18 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
 				       struct intel_dpll_hw_state *hw_state)
 {
 	const enum intel_dpll_id id = pll->info->id;
+	intel_wakeref_t wakeref;
 	uint32_t val;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(WRPLL_CTL(id));
 	hw_state->wrpll = val;
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return val & WRPLL_PLL_ENABLE;
 }
@@ -526,15 +532,18 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv,
 				      struct intel_shared_dpll *pll,
 				      struct intel_dpll_hw_state *hw_state)
 {
+	intel_wakeref_t wakeref;
 	uint32_t val;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(SPLL_CTL);
 	hw_state->spll = val;
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return val & SPLL_PLL_ENABLE;
 }
@@ -989,9 +998,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	uint32_t val;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
 	const enum intel_dpll_id id = pll->info->id;
+	intel_wakeref_t wakeref;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	ret = false;
@@ -1011,7 +1023,7 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return ret;
 }
@@ -1020,12 +1032,15 @@ static bool skl_ddi_dpll0_get_hw_state(struct drm_i915_private *dev_priv,
 				       struct intel_shared_dpll *pll,
 				       struct intel_dpll_hw_state *hw_state)
 {
-	uint32_t val;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
 	const enum intel_dpll_id id = pll->info->id;
+	intel_wakeref_t wakeref;
+	uint32_t val;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	ret = false;
@@ -1041,7 +1056,7 @@ static bool skl_ddi_dpll0_get_hw_state(struct drm_i915_private *dev_priv,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return ret;
 }
@@ -1579,14 +1594,17 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 					struct intel_dpll_hw_state *hw_state)
 {
 	enum port port = (enum port)pll->info->id; /* 1:1 port->PLL mapping */
-	uint32_t val;
-	bool ret;
+	intel_wakeref_t wakeref;
 	enum dpio_phy phy;
 	enum dpio_channel ch;
+	uint32_t val;
+	bool ret;
 
 	bxt_port_to_phy_channel(dev_priv, port, &phy, &ch);
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	ret = false;
@@ -1643,7 +1661,7 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return ret;
 }
@@ -2091,10 +2109,13 @@ static bool cnl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				     struct intel_dpll_hw_state *hw_state)
 {
 	const enum intel_dpll_id id = pll->info->id;
+	intel_wakeref_t wakeref;
 	uint32_t val;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	ret = false;
@@ -2113,7 +2134,7 @@ static bool cnl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	ret = true;
 
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 
 	return ret;
 }
@@ -2950,11 +2971,14 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				 struct intel_dpll_hw_state *hw_state)
 {
 	const enum intel_dpll_id id = pll->info->id;
-	uint32_t val;
-	enum port port;
+	intel_wakeref_t wakeref;
 	bool ret = false;
+	enum port port;
+	uint32_t val;
 
-	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_PLLS);
+	if (!wakeref)
 		return false;
 
 	val = I915_READ(icl_pll_id_to_enable_reg(id));
@@ -3007,7 +3031,7 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 
 	ret = true;
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS, wakeref);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ce1b851273b4..235d370833df 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -2109,12 +2109,21 @@ bool intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				    enum intel_display_power_domain domain);
 bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				      enum intel_display_power_domain domain);
-void intel_display_power_get(struct drm_i915_private *dev_priv,
-			     enum intel_display_power_domain domain);
-bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+intel_wakeref_t intel_display_power_get(struct drm_i915_private *dev_priv,
 					enum intel_display_power_domain domain);
+intel_wakeref_t
+intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+				   enum intel_display_power_domain domain);
+void intel_display_power_put_unchecked(struct drm_i915_private *dev_priv,
+				       enum intel_display_power_domain domain);
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 void intel_display_power_put(struct drm_i915_private *dev_priv,
-			     enum intel_display_power_domain domain);
+			     enum intel_display_power_domain domain,
+			     intel_wakeref_t wakeref);
+#else
+#define intel_display_power_put(i915, domain, wakeref) \
+	intel_display_power_put_unchecked(i915, domain)
+#endif
 void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 			    u8 req_slices);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index d968f1f13e09..1c3f44e23e5d 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -40,6 +40,7 @@ struct intel_dsi {
 	struct intel_encoder base;
 
 	struct intel_dsi_host *dsi_hosts[I915_MAX_PORTS];
+	intel_wakeref_t io_wakeref[I915_MAX_PORTS];
 
 	/* GPIO Desc for CRC based Panel control */
 	struct gpio_desc *gpio_panel;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 07e803a604bd..284a08a8bd2a 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1191,15 +1191,17 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	intel_wakeref_t wakeref;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = intel_sdvo_port_enabled(dev_priv, intel_hdmi->hdmi_reg, pipe);
 
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return ret;
 }
@@ -1896,11 +1898,12 @@ intel_hdmi_set_edid(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	intel_wakeref_t wakeref;
 	struct edid *edid;
 	bool connected = false;
 	struct i2c_adapter *i2c;
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
 	i2c = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
 
@@ -1915,7 +1918,7 @@ intel_hdmi_set_edid(struct drm_connector *connector)
 
 	intel_hdmi_dp_dual_mode_detect(connector, edid != NULL);
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref);
 
 	to_intel_connector(connector)->detect_edid = edid;
 	if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) {
@@ -1940,11 +1943,12 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 	struct intel_encoder *encoder = &hdmi_to_dig_port(intel_hdmi)->base;
+	intel_wakeref_t wakeref;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
 	if (IS_ICELAKE(dev_priv) &&
 	    !intel_digital_port_connected(encoder))
@@ -1956,7 +1960,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 		status = connector_status_connected;
 
 out:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref);
 
 	if (status != connector_status_connected)
 		cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier);
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 802d0394ccc4..012341a66431 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -698,12 +698,13 @@ do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num,
 static int
 gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
 {
-	struct intel_gmbus *bus = container_of(adapter, struct intel_gmbus,
-					       adapter);
+	struct intel_gmbus *bus =
+		container_of(adapter, struct intel_gmbus, adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
+	intel_wakeref_t wakeref;
 	int ret;
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
 	if (bus->force_bit) {
 		ret = i2c_bit_algo.master_xfer(adapter, msgs, num);
@@ -715,17 +716,16 @@ gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num)
 			bus->force_bit |= GMBUS_FORCE_BIT_RETRY;
 	}
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref);
 
 	return ret;
 }
 
 int intel_gmbus_output_aksv(struct i2c_adapter *adapter)
 {
-	struct intel_gmbus *bus = container_of(adapter, struct intel_gmbus,
-					       adapter);
+	struct intel_gmbus *bus =
+		container_of(adapter, struct intel_gmbus, adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
-	int ret;
 	u8 cmd = DRM_HDCP_DDC_AKSV;
 	u8 buf[DRM_HDCP_KSV_LEN] = { 0 };
 	struct i2c_msg msgs[] = {
@@ -742,8 +742,10 @@ int intel_gmbus_output_aksv(struct i2c_adapter *adapter)
 			.buf = buf,
 		}
 	};
+	intel_wakeref_t wakeref;
+	int ret;
 
-	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+	wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 	mutex_lock(&dev_priv->gmbus_mutex);
 
 	/*
@@ -754,7 +756,7 @@ int intel_gmbus_output_aksv(struct i2c_adapter *adapter)
 	ret = do_gmbus_xfer(adapter, msgs, ARRAY_SIZE(msgs), GMBUS_AKSV_SELECT);
 
 	mutex_unlock(&dev_priv->gmbus_mutex);
-	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index e6c5d985ea0a..6e03d3641b53 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -95,15 +95,17 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
+	intel_wakeref_t wakeref;
 	bool ret;
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = intel_lvds_port_enabled(dev_priv, lvds_encoder->reg, pipe);
 
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index f3c9010e332a..f14e27ef8690 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -589,6 +589,7 @@ int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name)
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[crtc->index];
 	enum intel_display_power_domain power_domain;
 	enum intel_pipe_crc_source source;
+	intel_wakeref_t wakeref;
 	u32 val = 0; /* shut up gcc */
 	int ret = 0;
 
@@ -598,7 +599,8 @@ int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name)
 	}
 
 	power_domain = POWER_DOMAIN_PIPE(crtc->index);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref) {
 		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
 		return -EIO;
 	}
@@ -624,7 +626,7 @@ int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name)
 	pipe_crc->skipped = 0;
 
 out:
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6d074f2e69d3..c118dd3ee82d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3989,10 +3989,12 @@ void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum pipe pipe = crtc->pipe;
+	intel_wakeref_t wakeref;
 	enum plane_id plane_id;
 
 	power_domain = POWER_DOMAIN_PIPE(pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return;
 
 	for_each_plane_id_on_crtc(crtc, plane_id)
@@ -4001,7 +4003,7 @@ void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc,
 					   &ddb_y[plane_id],
 					   &ddb_uv[plane_id]);
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 }
 
 void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 1dab3f54df1e..5037b3a07de3 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1825,18 +1825,19 @@ __intel_display_power_get_domain(struct drm_i915_private *dev_priv,
  * Any power domain reference obtained by this function must have a symmetric
  * call to intel_display_power_put() to release the reference again.
  */
-void intel_display_power_get(struct drm_i915_private *dev_priv,
-			     enum intel_display_power_domain domain)
+intel_wakeref_t intel_display_power_get(struct drm_i915_private *dev_priv,
+					enum intel_display_power_domain domain)
 {
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-
-	intel_runtime_pm_get(dev_priv);
+	intel_wakeref_t wakeref = intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&power_domains->lock);
 
 	__intel_display_power_get_domain(dev_priv, domain);
 
 	mutex_unlock(&power_domains->lock);
+
+	return wakeref;
 }
 
 /**
@@ -1851,13 +1852,16 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
  * Any power domain reference obtained by this function must have a symmetric
  * call to intel_display_power_put() to release the reference again.
  */
-bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
-					enum intel_display_power_domain domain)
+intel_wakeref_t
+intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+				   enum intel_display_power_domain domain)
 {
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	intel_wakeref_t wakeref;
 	bool is_enabled;
 
-	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+	wakeref = intel_runtime_pm_get_if_in_use(dev_priv);
+	if (!wakeref)
 		return false;
 
 	mutex_lock(&power_domains->lock);
@@ -1871,23 +1875,16 @@ bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
 
 	mutex_unlock(&power_domains->lock);
 
-	if (!is_enabled)
-		intel_runtime_pm_put_unchecked(dev_priv);
+	if (!is_enabled) {
+		intel_runtime_pm_put(dev_priv, wakeref);
+		wakeref = 0;
+	}
 
-	return is_enabled;
+	return wakeref;
 }
 
-/**
- * intel_display_power_put - release a power domain reference
- * @dev_priv: i915 device instance
- * @domain: power domain to reference
- *
- * This function drops the power domain reference obtained by
- * intel_display_power_get() and might power down the corresponding hardware
- * block right away if this is the last reference.
- */
-void intel_display_power_put(struct drm_i915_private *dev_priv,
-			     enum intel_display_power_domain domain)
+static void __intel_display_power_put(struct drm_i915_private *dev_priv,
+				      enum intel_display_power_domain domain)
 {
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
@@ -1905,10 +1902,34 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 		intel_power_well_put(dev_priv, power_well);
 
 	mutex_unlock(&power_domains->lock);
+}
 
+/**
+ * intel_display_power_put - release a power domain reference
+ * @dev_priv: i915 device instance
+ * @domain: power domain to reference
+ *
+ * This function drops the power domain reference obtained by
+ * intel_display_power_get() and might power down the corresponding hardware
+ * block right away if this is the last reference.
+ */
+void intel_display_power_put_unchecked(struct drm_i915_private *dev_priv,
+				       enum intel_display_power_domain domain)
+{
+	__intel_display_power_put(dev_priv, domain);
 	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+void intel_display_power_put(struct drm_i915_private *dev_priv,
+			     enum intel_display_power_domain domain,
+			     intel_wakeref_t wakeref)
+{
+	__intel_display_power_put(dev_priv, domain);
+	intel_runtime_pm_put(dev_priv, wakeref);
+}
+#endif
+
 #define I830_PIPES_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_PIPE_A) |		\
 	BIT_ULL(POWER_DOMAIN_PIPE_B) |		\
@@ -4018,7 +4039,7 @@ void intel_power_domains_fini_hw(struct drm_i915_private *dev_priv)
 
 	/* Remove the refcount we took to keep power well support disabled. */
 	if (!i915_modparams.disable_power_well)
-		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+		intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
 
 	intel_power_domains_verify_state(dev_priv);
 }
@@ -4037,7 +4058,7 @@ void intel_power_domains_fini_hw(struct drm_i915_private *dev_priv)
  */
 void intel_power_domains_enable(struct drm_i915_private *dev_priv)
 {
-	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+	intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
 
 	intel_power_domains_verify_state(dev_priv);
 }
@@ -4072,7 +4093,7 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
 {
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 
-	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+	intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
 
 	/*
 	 * In case of suspend-to-idle (aka S0ix) on a DMC platform without DC9
@@ -4093,7 +4114,7 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
 	 * power wells if power domains must be deinitialized for suspend.
 	 */
 	if (!i915_modparams.disable_power_well) {
-		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+		intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
 		intel_power_domains_verify_state(dev_priv);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index d2e003d8f3db..57b7e96a90a8 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -619,17 +619,19 @@ skl_plane_get_hw_state(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
+	intel_wakeref_t wakeref;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = I915_READ(PLANE_CTL(plane->pipe, plane_id)) & PLANE_CTL_ENABLE;
 
 	*pipe = plane->pipe;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -883,17 +885,19 @@ vlv_plane_get_hw_state(struct intel_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
+	intel_wakeref_t wakeref;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = I915_READ(SPCNTR(plane->pipe, plane_id)) & SP_ENABLE;
 
 	*pipe = plane->pipe;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -1052,17 +1056,19 @@ ivb_plane_get_hw_state(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	ret =  I915_READ(SPRCTL(plane->pipe)) & SPRITE_ENABLE;
 
 	*pipe = plane->pipe;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
@@ -1218,17 +1224,19 @@ g4x_plane_get_hw_state(struct intel_plane *plane,
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
 	bool ret;
 
 	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return false;
 
 	ret = I915_READ(DVSCNTR(plane->pipe)) & DVS_ENABLE;
 
 	*pipe = plane->pipe;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_vdsc.c b/drivers/gpu/drm/i915/intel_vdsc.c
index c56ba0e04044..0754eb5f4ae7 100644
--- a/drivers/gpu/drm/i915/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/intel_vdsc.c
@@ -1083,6 +1083,6 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 	I915_WRITE(dss_ctl2_reg, dss_ctl2_val);
 
 	/* Disable Power wells for VDSC/joining */
-	intel_display_power_put(dev_priv,
-				intel_dsc_power_domain(old_crtc_state));
+	intel_display_power_put_unchecked(dev_priv,
+					  intel_dsc_power_domain(old_crtc_state));
 }
diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 361e962a7969..397da55de28c 100644
--- a/drivers/gpu/drm/i915/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -960,13 +960,15 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	intel_wakeref_t wakeref;
 	enum port port;
 	bool active = false;
 
 	DRM_DEBUG_KMS("\n");
 
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     encoder->power_domain);
+	if (!wakeref)
 		return false;
 
 	/*
@@ -1022,7 +1024,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	}
 
 out_put_power:
-	intel_display_power_put(dev_priv, encoder->power_domain);
+	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
 
 	return active;
 }
@@ -1575,6 +1577,7 @@ vlv_dsi_get_hw_panel_orientation(struct intel_connector *connector)
 	enum drm_panel_orientation orientation;
 	struct intel_plane *plane;
 	struct intel_crtc *crtc;
+	intel_wakeref_t wakeref;
 	enum pipe pipe;
 	u32 val;
 
@@ -1585,7 +1588,8 @@ vlv_dsi_get_hw_panel_orientation(struct intel_connector *connector)
 	plane = to_intel_plane(crtc->base.primary);
 
 	power_domain = POWER_DOMAIN_PIPE(pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
 		return DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
 
 	val = I915_READ(DSPCNTR(plane->i9xx_plane));
@@ -1597,7 +1601,7 @@ vlv_dsi_get_hw_panel_orientation(struct intel_connector *connector)
 	else
 		orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, power_domain, wakeref);
 
 	return orientation;
 }
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 15/19] drm/i915: Track the wakeref used to initialise display power domains

[Chris Wilson]

On module load and unload, we grab the POWER_DOMAIN_INIT powerwells and
transfer them to the runtime-pm code. We can use our wakeref tracking to
verify that the wakeref is indeed passed from init to enable, and
disable to fini; and across suspend.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |   3 +
 drivers/gpu/drm/i915/i915_drv.h         |   2 +
 drivers/gpu/drm/i915/intel_runtime_pm.c | 151 +++++++++++++-----------
 3 files changed, 88 insertions(+), 68 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 248a03953ba7..8aa9d7090385 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2723,6 +2723,9 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 	if (!HAS_RUNTIME_PM(dev_priv))
 		seq_puts(m, "Runtime power management not supported\n");
 
+	seq_printf(m, "Runtime power management: %s\n",
+		   enableddisabled(!dev_priv->power_domains.wakeref));
+
 	seq_printf(m, "GPU idle: %s (epoch %u)\n",
 		   yesno(!dev_priv->gt.awake), dev_priv->gt.epoch);
 	seq_printf(m, "IRQs disabled: %s\n",
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 233190eaae62..2ed3c56a6381 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -822,6 +822,8 @@ struct i915_power_domains {
 	bool display_core_suspended;
 	int power_well_count;
 
+	intel_wakeref_t wakeref;
+
 	struct mutex lock;
 	int domain_use_count[POWER_DOMAIN_NUM];
 	struct i915_power_well *power_wells;
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 5037b3a07de3..9d7adb8d1be2 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -3967,7 +3967,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv);
 
 /**
  * intel_power_domains_init_hw - initialize hardware power domain state
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  * @resume: Called from resume code paths or not
  *
  * This function initializes the hardware power domain state and enables all
@@ -3981,30 +3981,31 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv);
  * intel_power_domains_enable()) and must be paired with
  * intel_power_domains_fini_hw().
  */
-void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
+void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume)
 {
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_domains *power_domains = &i915->power_domains;
 
 	power_domains->initializing = true;
 
-	if (IS_ICELAKE(dev_priv)) {
-		icl_display_core_init(dev_priv, resume);
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		cnl_display_core_init(dev_priv, resume);
-	} else if (IS_GEN9_BC(dev_priv)) {
-		skl_display_core_init(dev_priv, resume);
-	} else if (IS_GEN9_LP(dev_priv)) {
-		bxt_display_core_init(dev_priv, resume);
-	} else if (IS_CHERRYVIEW(dev_priv)) {
+	if (IS_ICELAKE(i915)) {
+		icl_display_core_init(i915, resume);
+	} else if (IS_CANNONLAKE(i915)) {
+		cnl_display_core_init(i915, resume);
+	} else if (IS_GEN9_BC(i915)) {
+		skl_display_core_init(i915, resume);
+	} else if (IS_GEN9_LP(i915)) {
+		bxt_display_core_init(i915, resume);
+	} else if (IS_CHERRYVIEW(i915)) {
 		mutex_lock(&power_domains->lock);
-		chv_phy_control_init(dev_priv);
+		chv_phy_control_init(i915);
 		mutex_unlock(&power_domains->lock);
-	} else if (IS_VALLEYVIEW(dev_priv)) {
+	} else if (IS_VALLEYVIEW(i915)) {
 		mutex_lock(&power_domains->lock);
-		vlv_cmnlane_wa(dev_priv);
+		vlv_cmnlane_wa(i915);
 		mutex_unlock(&power_domains->lock);
-	} else if (IS_IVYBRIDGE(dev_priv) || INTEL_GEN(dev_priv) >= 7)
-		intel_pch_reset_handshake(dev_priv, !HAS_PCH_NOP(dev_priv));
+	} else if (IS_IVYBRIDGE(i915) || INTEL_GEN(i915) >= 7) {
+		intel_pch_reset_handshake(i915, !HAS_PCH_NOP(i915));
+	}
 
 	/*
 	 * Keep all power wells enabled for any dependent HW access during
@@ -4012,18 +4013,20 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
 	 * resources powered until display HW readout is complete. We drop
 	 * this reference in intel_power_domains_enable().
 	 */
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	power_domains->wakeref =
+		intel_display_power_get(i915, POWER_DOMAIN_INIT);
+
 	/* Disable power support if the user asked so. */
 	if (!i915_modparams.disable_power_well)
-		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
-	intel_power_domains_sync_hw(dev_priv);
+		intel_display_power_get(i915, POWER_DOMAIN_INIT);
+	intel_power_domains_sync_hw(i915);
 
 	power_domains->initializing = false;
 }
 
 /**
  * intel_power_domains_fini_hw - deinitialize hw power domain state
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * De-initializes the display power domain HW state. It also ensures that the
  * device stays powered up so that the driver can be reloaded.
@@ -4032,21 +4035,24 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
  * intel_power_domains_disable()) and must be paired with
  * intel_power_domains_init_hw().
  */
-void intel_power_domains_fini_hw(struct drm_i915_private *dev_priv)
+void intel_power_domains_fini_hw(struct drm_i915_private *i915)
 {
-	/* Keep the power well enabled, but cancel its rpm wakeref. */
-	intel_runtime_pm_put_unchecked(dev_priv);
+	intel_wakeref_t wakeref __maybe_unused =
+		fetch_and_zero(&i915->power_domains.wakeref);
 
 	/* Remove the refcount we took to keep power well support disabled. */
 	if (!i915_modparams.disable_power_well)
-		intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
+		intel_display_power_put_unchecked(i915, POWER_DOMAIN_INIT);
+
+	intel_power_domains_verify_state(i915);
 
-	intel_power_domains_verify_state(dev_priv);
+	/* Keep the power well enabled, but cancel its rpm wakeref. */
+	intel_runtime_pm_put(i915, wakeref);
 }
 
 /**
  * intel_power_domains_enable - enable toggling of display power wells
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * Enable the ondemand enabling/disabling of the display power wells. Note that
  * power wells not belonging to POWER_DOMAIN_INIT are allowed to be toggled
@@ -4056,30 +4062,36 @@ void intel_power_domains_fini_hw(struct drm_i915_private *dev_priv)
  * of display HW readout (which will acquire the power references reflecting
  * the current HW state).
  */
-void intel_power_domains_enable(struct drm_i915_private *dev_priv)
+void intel_power_domains_enable(struct drm_i915_private *i915)
 {
-	intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
+	intel_wakeref_t wakeref __maybe_unused =
+		fetch_and_zero(&i915->power_domains.wakeref);
 
-	intel_power_domains_verify_state(dev_priv);
+	intel_display_power_put(i915, POWER_DOMAIN_INIT, wakeref);
+	intel_power_domains_verify_state(i915);
 }
 
 /**
  * intel_power_domains_disable - disable toggling of display power wells
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * Disable the ondemand enabling/disabling of the display power wells. See
  * intel_power_domains_enable() for which power wells this call controls.
  */
-void intel_power_domains_disable(struct drm_i915_private *dev_priv)
+void intel_power_domains_disable(struct drm_i915_private *i915)
 {
-	intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+	struct i915_power_domains *power_domains = &i915->power_domains;
 
-	intel_power_domains_verify_state(dev_priv);
+	WARN_ON(power_domains->wakeref);
+	power_domains->wakeref =
+		intel_display_power_get(i915, POWER_DOMAIN_INIT);
+
+	intel_power_domains_verify_state(i915);
 }
 
 /**
  * intel_power_domains_suspend - suspend power domain state
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  * @suspend_mode: specifies the target suspend state (idle, mem, hibernation)
  *
  * This function prepares the hardware power domain state before entering
@@ -4088,12 +4100,14 @@ void intel_power_domains_disable(struct drm_i915_private *dev_priv)
  * It must be called with power domains already disabled (after a call to
  * intel_power_domains_disable()) and paired with intel_power_domains_resume().
  */
-void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
+void intel_power_domains_suspend(struct drm_i915_private *i915,
 				 enum i915_drm_suspend_mode suspend_mode)
 {
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_domains *power_domains = &i915->power_domains;
+	intel_wakeref_t wakeref __maybe_unused =
+		fetch_and_zero(&power_domains->wakeref);
 
-	intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
+	intel_display_power_put(i915, POWER_DOMAIN_INIT, wakeref);
 
 	/*
 	 * In case of suspend-to-idle (aka S0ix) on a DMC platform without DC9
@@ -4102,10 +4116,10 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
 	 * resources as required and also enable deeper system power states
 	 * that would be blocked if the firmware was inactive.
 	 */
-	if (!(dev_priv->csr.allowed_dc_mask & DC_STATE_EN_DC9) &&
+	if (!(i915->csr.allowed_dc_mask & DC_STATE_EN_DC9) &&
 	    suspend_mode == I915_DRM_SUSPEND_IDLE &&
-	    dev_priv->csr.dmc_payload != NULL) {
-		intel_power_domains_verify_state(dev_priv);
+	    i915->csr.dmc_payload) {
+		intel_power_domains_verify_state(i915);
 		return;
 	}
 
@@ -4114,25 +4128,25 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
 	 * power wells if power domains must be deinitialized for suspend.
 	 */
 	if (!i915_modparams.disable_power_well) {
-		intel_display_power_put_unchecked(dev_priv, POWER_DOMAIN_INIT);
-		intel_power_domains_verify_state(dev_priv);
+		intel_display_power_put_unchecked(i915, POWER_DOMAIN_INIT);
+		intel_power_domains_verify_state(i915);
 	}
 
-	if (IS_ICELAKE(dev_priv))
-		icl_display_core_uninit(dev_priv);
-	else if (IS_CANNONLAKE(dev_priv))
-		cnl_display_core_uninit(dev_priv);
-	else if (IS_GEN9_BC(dev_priv))
-		skl_display_core_uninit(dev_priv);
-	else if (IS_GEN9_LP(dev_priv))
-		bxt_display_core_uninit(dev_priv);
+	if (IS_ICELAKE(i915))
+		icl_display_core_uninit(i915);
+	else if (IS_CANNONLAKE(i915))
+		cnl_display_core_uninit(i915);
+	else if (IS_GEN9_BC(i915))
+		skl_display_core_uninit(i915);
+	else if (IS_GEN9_LP(i915))
+		bxt_display_core_uninit(i915);
 
 	power_domains->display_core_suspended = true;
 }
 
 /**
  * intel_power_domains_resume - resume power domain state
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function resume the hardware power domain state during system resume.
  *
@@ -4140,28 +4154,30 @@ void intel_power_domains_suspend(struct drm_i915_private *dev_priv,
  * intel_power_domains_enable()) and must be paired with
  * intel_power_domains_suspend().
  */
-void intel_power_domains_resume(struct drm_i915_private *dev_priv)
+void intel_power_domains_resume(struct drm_i915_private *i915)
 {
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_domains *power_domains = &i915->power_domains;
 
 	if (power_domains->display_core_suspended) {
-		intel_power_domains_init_hw(dev_priv, true);
+		intel_power_domains_init_hw(i915, true);
 		power_domains->display_core_suspended = false;
 	} else {
-		intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
+		WARN_ON(power_domains->wakeref);
+		power_domains->wakeref =
+			intel_display_power_get(i915, POWER_DOMAIN_INIT);
 	}
 
-	intel_power_domains_verify_state(dev_priv);
+	intel_power_domains_verify_state(i915);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
 
-static void intel_power_domains_dump_info(struct drm_i915_private *dev_priv)
+static void intel_power_domains_dump_info(struct drm_i915_private *i915)
 {
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_domains *power_domains = &i915->power_domains;
 	struct i915_power_well *power_well;
 
-	for_each_power_well(dev_priv, power_well) {
+	for_each_power_well(i915, power_well) {
 		enum intel_display_power_domain domain;
 
 		DRM_DEBUG_DRIVER("%-25s %d\n",
@@ -4176,7 +4192,7 @@ static void intel_power_domains_dump_info(struct drm_i915_private *dev_priv)
 
 /**
  * intel_power_domains_verify_state - verify the HW/SW state for all power wells
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * Verify if the reference count of each power well matches its HW enabled
  * state and the total refcount of the domains it belongs to. This must be
@@ -4184,22 +4200,21 @@ static void intel_power_domains_dump_info(struct drm_i915_private *dev_priv)
  * acquiring reference counts for any power wells in use and disabling the
  * ones left on by BIOS but not required by any active output.
  */
-static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
+static void intel_power_domains_verify_state(struct drm_i915_private *i915)
 {
-	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_domains *power_domains = &i915->power_domains;
 	struct i915_power_well *power_well;
 	bool dump_domain_info;
 
 	mutex_lock(&power_domains->lock);
 
 	dump_domain_info = false;
-	for_each_power_well(dev_priv, power_well) {
+	for_each_power_well(i915, power_well) {
 		enum intel_display_power_domain domain;
 		int domains_count;
 		bool enabled;
 
-		enabled = power_well->desc->ops->is_enabled(dev_priv,
-							    power_well);
+		enabled = power_well->desc->ops->is_enabled(i915, power_well);
 		if ((power_well->count || power_well->desc->always_on) !=
 		    enabled)
 			DRM_ERROR("power well %s state mismatch (refcount %d/enabled %d)",
@@ -4223,7 +4238,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
 		static bool dumped;
 
 		if (!dumped) {
-			intel_power_domains_dump_info(dev_priv);
+			intel_power_domains_dump_info(i915);
 			dumped = true;
 		}
 	}
@@ -4233,7 +4248,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
 
 #else
 
-static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
+static void intel_power_domains_verify_state(struct drm_i915_private *i915)
 {
 }
 
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 16/19] drm/i915: Combined gt.awake/gt.power wakerefs

[Chris Wilson]

As the GT_IRQ power domain implies a wakeref, we can use it inplace of
our existing redundant rpm grab.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h                  |  1 -
 drivers/gpu/drm/i915/i915_gem.c                  | 11 ++++-------
 drivers/gpu/drm/i915/selftests/mock_gem_device.c |  1 +
 3 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2ed3c56a6381..7429b4f78d45 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1970,7 +1970,6 @@ struct drm_i915_private {
 		 * is a slight delay before we do so.
 		 */
 		intel_wakeref_t awake;
-		intel_wakeref_t power;
 
 		/**
 		 * The number of times we have woken up.
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d481580f09c1..490b149ce9ab 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -177,9 +177,7 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
-	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, i915->gt.power);
-
-	intel_runtime_pm_put(i915, wakeref);
+	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, wakeref);
 
 	return i915->gt.epoch;
 }
@@ -204,13 +202,11 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915->gt.active_requests);
+	assert_rpm_wakelock_held(i915);
 
 	if (i915->gt.awake)
 		return;
 
-	i915->gt.awake = intel_runtime_pm_get_noresume(i915);
-	GEM_BUG_ON(!i915->gt.awake);
-
 	/*
 	 * It seems that the DMC likes to transition between the DC states a lot
 	 * when there are no connected displays (no active power domains) during
@@ -222,7 +218,8 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 	 * Work around it by grabbing a GT IRQ power domain whilst there is any
 	 * GT activity, preventing any DC state transitions.
 	 */
-	i915->gt.power = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+	i915->gt.awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
+	GEM_BUG_ON(!i915->gt.awake);
 
 	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
 		i915->gt.epoch = 1;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 0eb283e7fc96..aa4ddae94aca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -164,6 +164,7 @@ struct drm_i915_private *mock_gem_device(void)
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	if (pm_runtime_enabled(&pdev->dev))
 		WARN_ON(pm_runtime_get_sync(&pdev->dev));
+	disable_rpm_wakeref_asserts(i915);
 
 	err = drm_dev_init(&i915->drm, &mock_driver, &pdev->dev);
 	if (err) {
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 17/19] drm/i915/dp: Markup pps lock power well

[Chris Wilson]

Track where and when we acquire and release the power well for pps
access along the dp aux link, with a view to detecting if we leak any
wakerefs.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_dp.c | 231 +++++++++++++++++---------------
 1 file changed, 121 insertions(+), 110 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2fb7f297d0a1..b36e68b041a7 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -600,30 +600,39 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 static void
 intel_dp_pps_init(struct intel_dp *intel_dp);
 
-static void pps_lock(struct intel_dp *intel_dp)
+static intel_wakeref_t
+pps_lock(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	intel_wakeref_t wakeref;
 
 	/*
 	 * See intel_power_sequencer_reset() why we need
 	 * a power domain reference here.
 	 */
-	intel_display_power_get(dev_priv,
-				intel_aux_power_domain(dp_to_dig_port(intel_dp)));
+	wakeref = intel_display_power_get(dev_priv,
+					  intel_aux_power_domain(dp_to_dig_port(intel_dp)));
 
 	mutex_lock(&dev_priv->pps_mutex);
+
+	return wakeref;
 }
 
-static void pps_unlock(struct intel_dp *intel_dp)
+static intel_wakeref_t
+pps_unlock(struct intel_dp *intel_dp, intel_wakeref_t wakeref)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
 	mutex_unlock(&dev_priv->pps_mutex);
-
-	intel_display_power_put_unchecked(dev_priv,
-					  intel_aux_power_domain(dp_to_dig_port(intel_dp)));
+	intel_display_power_put(dev_priv,
+				intel_aux_power_domain(dp_to_dig_port(intel_dp)),
+				wakeref);
+	return 0;
 }
 
+#define with_pps_lock(dp, wf) \
+	for (wf = pps_lock(dp); wf; wf = pps_unlock(dp, wf))
+
 static void
 vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 {
@@ -972,30 +981,30 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 	struct intel_dp *intel_dp = container_of(this, typeof(* intel_dp),
 						 edp_notifier);
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	intel_wakeref_t wakeref;
 
 	if (!intel_dp_is_edp(intel_dp) || code != SYS_RESTART)
 		return 0;
 
-	pps_lock(intel_dp);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
-		i915_reg_t pp_ctrl_reg, pp_div_reg;
-		u32 pp_div;
-
-		pp_ctrl_reg = PP_CONTROL(pipe);
-		pp_div_reg  = PP_DIVISOR(pipe);
-		pp_div = I915_READ(pp_div_reg);
-		pp_div &= PP_REFERENCE_DIVIDER_MASK;
-
-		/* 0x1F write to PP_DIV_REG sets max cycle delay */
-		I915_WRITE(pp_div_reg, pp_div | 0x1F);
-		I915_WRITE(pp_ctrl_reg, PANEL_UNLOCK_REGS | PANEL_POWER_OFF);
-		msleep(intel_dp->panel_power_cycle_delay);
+	with_pps_lock(intel_dp, wakeref) {
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+			enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+			i915_reg_t pp_ctrl_reg, pp_div_reg;
+			u32 pp_div;
+
+			pp_ctrl_reg = PP_CONTROL(pipe);
+			pp_div_reg  = PP_DIVISOR(pipe);
+			pp_div = I915_READ(pp_div_reg);
+			pp_div &= PP_REFERENCE_DIVIDER_MASK;
+
+			/* 0x1F write to PP_DIV_REG sets max cycle delay */
+			I915_WRITE(pp_div_reg, pp_div | 0x1F);
+			I915_WRITE(pp_ctrl_reg,
+				   PANEL_UNLOCK_REGS | PANEL_POWER_OFF);
+			msleep(intel_dp->panel_power_cycle_delay);
+		}
 	}
 
-	pps_unlock(intel_dp);
-
 	return 0;
 }
 
@@ -1183,16 +1192,17 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 			to_i915(intel_dig_port->base.base.dev);
 	i915_reg_t ch_ctl, ch_data[5];
 	uint32_t aux_clock_divider;
+	intel_wakeref_t wakeref;
 	int i, ret, recv_bytes;
-	uint32_t status;
 	int try, clock = 0;
+	uint32_t status;
 	bool vdd;
 
 	ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
 	for (i = 0; i < ARRAY_SIZE(ch_data); i++)
 		ch_data[i] = intel_dp->aux_ch_data_reg(intel_dp, i);
 
-	pps_lock(intel_dp);
+	wakeref = pps_lock(intel_dp);
 
 	/*
 	 * We will be called with VDD already enabled for dpcd/edid/oui reads.
@@ -1336,7 +1346,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);
 
-	pps_unlock(intel_dp);
+	pps_unlock(intel_dp, wakeref);
 
 	return ret;
 }
@@ -2462,15 +2472,15 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
  */
 void intel_edp_panel_vdd_on(struct intel_dp *intel_dp)
 {
+	intel_wakeref_t wakeref;
 	bool vdd;
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	pps_lock(intel_dp);
-	vdd = edp_panel_vdd_on(intel_dp);
-	pps_unlock(intel_dp);
-
+	vdd = false;
+	with_pps_lock(intel_dp, wakeref)
+		vdd = edp_panel_vdd_on(intel_dp);
 	I915_STATE_WARN(!vdd, "eDP port %c VDD already requested on\n",
 	     port_name(dp_to_dig_port(intel_dp)->base.port));
 }
@@ -2515,13 +2525,15 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 
 static void edp_panel_vdd_work(struct work_struct *__work)
 {
-	struct intel_dp *intel_dp = container_of(to_delayed_work(__work),
-						 struct intel_dp, panel_vdd_work);
+	struct intel_dp *intel_dp =
+		container_of(to_delayed_work(__work),
+			     struct intel_dp, panel_vdd_work);
+	intel_wakeref_t wakeref;
 
-	pps_lock(intel_dp);
-	if (!intel_dp->want_panel_vdd)
-		edp_panel_vdd_off_sync(intel_dp);
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref) {
+		if (!intel_dp->want_panel_vdd)
+			edp_panel_vdd_off_sync(intel_dp);
+	}
 }
 
 static void edp_panel_vdd_schedule_off(struct intel_dp *intel_dp)
@@ -2611,12 +2623,13 @@ static void edp_panel_on(struct intel_dp *intel_dp)
 
 void intel_edp_panel_on(struct intel_dp *intel_dp)
 {
+	intel_wakeref_t wakeref;
+
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	pps_lock(intel_dp);
-	edp_panel_on(intel_dp);
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref)
+		edp_panel_on(intel_dp);
 }
 
 
@@ -2660,20 +2673,20 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 
 void intel_edp_panel_off(struct intel_dp *intel_dp)
 {
+	intel_wakeref_t wakeref;
+
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	pps_lock(intel_dp);
-	edp_panel_off(intel_dp);
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref)
+		edp_panel_off(intel_dp);
 }
 
 /* Enable backlight in the panel power control. */
 static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	u32 pp;
-	i915_reg_t pp_ctrl_reg;
+	intel_wakeref_t wakeref;
 
 	/*
 	 * If we enable the backlight right away following a panel power
@@ -2683,17 +2696,16 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 	 */
 	wait_backlight_on(intel_dp);
 
-	pps_lock(intel_dp);
+	with_pps_lock(intel_dp, wakeref) {
+		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
+		u32 pp;
 
-	pp = ironlake_get_pp_control(intel_dp);
-	pp |= EDP_BLC_ENABLE;
-
-	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
-
-	I915_WRITE(pp_ctrl_reg, pp);
-	POSTING_READ(pp_ctrl_reg);
+		pp = ironlake_get_pp_control(intel_dp);
+		pp |= EDP_BLC_ENABLE;
 
-	pps_unlock(intel_dp);
+		I915_WRITE(pp_ctrl_reg, pp);
+		POSTING_READ(pp_ctrl_reg);
+	}
 }
 
 /* Enable backlight PWM and backlight PP control. */
@@ -2715,23 +2727,21 @@ void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state,
 static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	u32 pp;
-	i915_reg_t pp_ctrl_reg;
+	intel_wakeref_t wakeref;
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	pps_lock(intel_dp);
-
-	pp = ironlake_get_pp_control(intel_dp);
-	pp &= ~EDP_BLC_ENABLE;
-
-	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
+	with_pps_lock(intel_dp, wakeref) {
+		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
+		u32 pp;
 
-	I915_WRITE(pp_ctrl_reg, pp);
-	POSTING_READ(pp_ctrl_reg);
+		pp = ironlake_get_pp_control(intel_dp);
+		pp &= ~EDP_BLC_ENABLE;
 
-	pps_unlock(intel_dp);
+		I915_WRITE(pp_ctrl_reg, pp);
+		POSTING_READ(pp_ctrl_reg);
+	}
 
 	intel_dp->last_backlight_off = jiffies;
 	edp_wait_backlight_off(intel_dp);
@@ -2759,12 +2769,12 @@ static void intel_edp_backlight_power(struct intel_connector *connector,
 				      bool enable)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(&connector->base);
+	intel_wakeref_t wakeref;
 	bool is_enabled;
 
-	pps_lock(intel_dp);
-	is_enabled = ironlake_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
-	pps_unlock(intel_dp);
-
+	is_enabled = false;
+	with_pps_lock(intel_dp, wakeref)
+		is_enabled = ironlake_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
 	if (is_enabled == enable)
 		return;
 
@@ -3274,22 +3284,21 @@ static void intel_enable_dp(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
 	uint32_t dp_reg = I915_READ(intel_dp->output_reg);
 	enum pipe pipe = crtc->pipe;
+	intel_wakeref_t wakeref;
 
 	if (WARN_ON(dp_reg & DP_PORT_EN))
 		return;
 
-	pps_lock(intel_dp);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_init_panel_power_sequencer(encoder, pipe_config);
-
-	intel_dp_enable_port(intel_dp, pipe_config);
+	with_pps_lock(intel_dp, wakeref) {
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+			vlv_init_panel_power_sequencer(encoder, pipe_config);
 
-	edp_panel_vdd_on(intel_dp);
-	edp_panel_on(intel_dp);
-	edp_panel_vdd_off(intel_dp, true);
+		intel_dp_enable_port(intel_dp, pipe_config);
 
-	pps_unlock(intel_dp);
+		edp_panel_vdd_on(intel_dp);
+		edp_panel_on(intel_dp);
+		edp_panel_vdd_off(intel_dp, true);
+	}
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		unsigned int lane_mask = 0x0;
@@ -3987,9 +3996,10 @@ intel_dp_link_down(struct intel_encoder *encoder,
 	intel_dp->DP = DP;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		pps_lock(intel_dp);
-		intel_dp->active_pipe = INVALID_PIPE;
-		pps_unlock(intel_dp);
+		intel_wakeref_t wakeref;
+
+		with_pps_lock(intel_dp, wakeref)
+			intel_dp->active_pipe = INVALID_PIPE;
 	}
 }
 
@@ -5539,14 +5549,15 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 
 	intel_dp_mst_encoder_cleanup(intel_dig_port);
 	if (intel_dp_is_edp(intel_dp)) {
+		intel_wakeref_t wakeref;
+
 		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
 		/*
 		 * vdd might still be enabled do to the delayed vdd off.
 		 * Make sure vdd is actually turned off here.
 		 */
-		pps_lock(intel_dp);
-		edp_panel_vdd_off_sync(intel_dp);
-		pps_unlock(intel_dp);
+		with_pps_lock(intel_dp, wakeref)
+			edp_panel_vdd_off_sync(intel_dp);
 
 		if (intel_dp->edp_notifier.notifier_call) {
 			unregister_reboot_notifier(&intel_dp->edp_notifier);
@@ -5563,6 +5574,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+	intel_wakeref_t wakeref;
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
@@ -5572,9 +5584,8 @@ void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 	 * Make sure vdd is actually turned off here.
 	 */
 	cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-	pps_lock(intel_dp);
-	edp_panel_vdd_off_sync(intel_dp);
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref)
+		edp_panel_vdd_off_sync(intel_dp);
 }
 
 static
@@ -5855,6 +5866,7 @@ void intel_dp_encoder_reset(struct drm_encoder *encoder)
 	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_lspcon *lspcon = dp_to_lspcon(intel_dp);
+	intel_wakeref_t wakeref;
 
 	if (!HAS_DDI(dev_priv))
 		intel_dp->DP = I915_READ(intel_dp->output_reg);
@@ -5864,18 +5876,19 @@ void intel_dp_encoder_reset(struct drm_encoder *encoder)
 
 	intel_dp->reset_link_params = true;
 
-	pps_lock(intel_dp);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		intel_dp->active_pipe = vlv_active_pipe(intel_dp);
+	with_pps_lock(intel_dp, wakeref) {
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+			intel_dp->active_pipe = vlv_active_pipe(intel_dp);
 
-	if (intel_dp_is_edp(intel_dp)) {
-		/* Reinit the power sequencer, in case BIOS did something with it. */
-		intel_dp_pps_init(intel_dp);
-		intel_edp_panel_vdd_sanitize(intel_dp);
+		if (intel_dp_is_edp(intel_dp)) {
+			/*
+			 * Reinit the power sequencer, in case BIOS did
+			 * something nasty with it.
+			 */
+			intel_dp_pps_init(intel_dp);
+			intel_edp_panel_vdd_sanitize(intel_dp);
+		}
 	}
-
-	pps_unlock(intel_dp);
 }
 
 static const struct drm_connector_funcs intel_dp_connector_funcs = {
@@ -6671,8 +6684,9 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	struct drm_display_mode *downclock_mode = NULL;
 	bool has_dpcd;
 	struct drm_display_mode *scan;
-	struct edid *edid;
 	enum pipe pipe = INVALID_PIPE;
+	intel_wakeref_t wakeref;
+	struct edid *edid;
 
 	if (!intel_dp_is_edp(intel_dp))
 		return true;
@@ -6692,13 +6706,11 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	pps_lock(intel_dp);
-
-	intel_dp_init_panel_power_timestamps(intel_dp);
-	intel_dp_pps_init(intel_dp);
-	intel_edp_panel_vdd_sanitize(intel_dp);
-
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref) {
+		intel_dp_init_panel_power_timestamps(intel_dp);
+		intel_dp_pps_init(intel_dp);
+		intel_edp_panel_vdd_sanitize(intel_dp);
+	}
 
 	/* Cache DPCD and EDID for edp. */
 	has_dpcd = intel_edp_init_dpcd(intel_dp);
@@ -6783,9 +6795,8 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	 * vdd might still be enabled do to the delayed vdd off.
 	 * Make sure vdd is actually turned off here.
 	 */
-	pps_lock(intel_dp);
-	edp_panel_vdd_off_sync(intel_dp);
-	pps_unlock(intel_dp);
+	with_pps_lock(intel_dp, wakeref)
+		edp_panel_vdd_off_sync(intel_dp);
 
 	return false;
 }
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 18/19] drm/i915: Complain if hsw_get_pipe_config acquires the same power well twice

[Chris Wilson]

As we only release each power well once, we assume that each transcoder
maps to a different domain. Complain if this is not so.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_display.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4e822ae56c90..55329592b513 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9550,6 +9550,8 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 	power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
+
+	WARN_ON(*power_domain_mask & BIT_ULL(power_domain));
 	*power_domain_mask |= BIT_ULL(power_domain);
 
 	tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder));
@@ -9577,6 +9579,8 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 		power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
 		if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 			continue;
+
+		WARN_ON(*power_domain_mask & BIT_ULL(power_domain));
 		*power_domain_mask |= BIT_ULL(power_domain);
 
 		/*
@@ -9693,7 +9697,9 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
 	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
+		WARN_ON(power_domain_mask & BIT_ULL(power_domain));
 		power_domain_mask |= BIT_ULL(power_domain);
+
 		if (INTEL_GEN(dev_priv) >= 9)
 			skylake_get_pfit_config(crtc, pipe_config);
 		else
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH 19/19] drm/i915: Mark up Ironlake ips with rpm wakerefs

[Chris Wilson]

Currently Ironlake operates under the assumption that rpm awake (and its
error checking is disabled). As such, we have missed a few places where we
access registers without taking the rpm wakeref and thus trigger
warnings. intel_ips being one culprit.

As this involved adding a potentially sleeping rpm_get, we have to
rearrange the spinlocks slightly and so switch to acquiring a device-ref
under the spinlock rather than hold the spinlock for the whole
operation. To be consistent, we make the change in pattern common to the
intel_ips interface even though this adds a few more atomic operations
than necessary in a few cases.

v2: Sagar noted the mb around setting mch_dev were overkill as we only
need ordering there, and that i915_emon_status was still using
struct_mutex for no reason, but lacked rpm.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c |  32 ++----
 drivers/gpu/drm/i915/i915_drv.c     |   3 +
 drivers/gpu/drm/i915/intel_pm.c     | 172 ++++++++++++++--------------
 3 files changed, 102 insertions(+), 105 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 8aa9d7090385..e40fc00882f3 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1765,32 +1765,24 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 
 static int i915_emon_status(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	unsigned long temp, chipset, gfx;
+	struct drm_i915_private *i915 = node_to_i915(m->private);
 	intel_wakeref_t wakeref;
-	int ret;
 
-	if (!IS_GEN5(dev_priv))
+	if (!IS_GEN5(i915))
 		return -ENODEV;
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
+	with_intel_runtime_pm(i915, wakeref) {
+		unsigned long temp, chipset, gfx;
 
-	wakeref = intel_runtime_pm_get(dev_priv);
-
-	temp = i915_mch_val(dev_priv);
-	chipset = i915_chipset_val(dev_priv);
-	gfx = i915_gfx_val(dev_priv);
-	mutex_unlock(&dev->struct_mutex);
+		temp = i915_mch_val(i915);
+		chipset = i915_chipset_val(i915);
+		gfx = i915_gfx_val(i915);
 
-	intel_runtime_pm_put(dev_priv, wakeref);
-
-	seq_printf(m, "GMCH temp: %ld\n", temp);
-	seq_printf(m, "Chipset power: %ld\n", chipset);
-	seq_printf(m, "GFX power: %ld\n", gfx);
-	seq_printf(m, "Total power: %ld\n", chipset + gfx);
+		seq_printf(m, "GMCH temp: %ld\n", temp);
+		seq_printf(m, "Chipset power: %ld\n", chipset);
+		seq_printf(m, "GFX power: %ld\n", gfx);
+		seq_printf(m, "Total power: %ld\n", chipset + gfx);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 7653c741bb78..d29a477e6945 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1775,6 +1775,9 @@ void i915_driver_unload(struct drm_device *dev)
 
 	i915_driver_unregister(dev_priv);
 
+	/* Flush any external code that still may be under the RCU lock */
+	synchronize_rcu();
+
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index c118dd3ee82d..bdb35e99d281 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6199,10 +6199,6 @@ void intel_init_ipc(struct drm_i915_private *dev_priv)
  */
 DEFINE_SPINLOCK(mchdev_lock);
 
-/* Global for IPS driver to get at the current i915 device. Protected by
- * mchdev_lock. */
-static struct drm_i915_private *i915_mch_dev;
-
 bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val)
 {
 	u16 rgvswctl;
@@ -7845,16 +7841,17 @@ static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv)
 
 unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
 {
-	unsigned long val;
+	intel_wakeref_t wakeref;
+	unsigned long val = 0;
 
 	if (!IS_GEN5(dev_priv))
 		return 0;
 
-	spin_lock_irq(&mchdev_lock);
-
-	val = __i915_chipset_val(dev_priv);
-
-	spin_unlock_irq(&mchdev_lock);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		spin_lock_irq(&mchdev_lock);
+		val = __i915_chipset_val(dev_priv);
+		spin_unlock_irq(&mchdev_lock);
+	}
 
 	return val;
 }
@@ -7931,14 +7928,16 @@ static void __i915_update_gfx_val(struct drm_i915_private *dev_priv)
 
 void i915_update_gfx_val(struct drm_i915_private *dev_priv)
 {
+	intel_wakeref_t wakeref;
+
 	if (!IS_GEN5(dev_priv))
 		return;
 
-	spin_lock_irq(&mchdev_lock);
-
-	__i915_update_gfx_val(dev_priv);
-
-	spin_unlock_irq(&mchdev_lock);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		spin_lock_irq(&mchdev_lock);
+		__i915_update_gfx_val(dev_priv);
+		spin_unlock_irq(&mchdev_lock);
+	}
 }
 
 static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
@@ -7980,18 +7979,34 @@ static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
 
 unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
 {
-	unsigned long val;
+	intel_wakeref_t wakeref;
+	unsigned long val = 0;
 
 	if (!IS_GEN5(dev_priv))
 		return 0;
 
-	spin_lock_irq(&mchdev_lock);
+	with_intel_runtime_pm(dev_priv, wakeref) {
+		spin_lock_irq(&mchdev_lock);
+		val = __i915_gfx_val(dev_priv);
+		spin_unlock_irq(&mchdev_lock);
+	}
 
-	val = __i915_gfx_val(dev_priv);
+	return val;
+}
 
-	spin_unlock_irq(&mchdev_lock);
+static struct drm_i915_private *i915_mch_dev;
 
-	return val;
+static struct drm_i915_private *mchdev_get(void)
+{
+	struct drm_i915_private *i915;
+
+	rcu_read_lock();
+	i915 = i915_mch_dev;
+	if (!kref_get_unless_zero(&i915->drm.ref))
+		i915 = NULL;
+	rcu_read_unlock();
+
+	return i915;
 }
 
 /**
@@ -8002,23 +8017,24 @@ unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
  */
 unsigned long i915_read_mch_val(void)
 {
-	struct drm_i915_private *dev_priv;
-	unsigned long chipset_val, graphics_val, ret = 0;
-
-	spin_lock_irq(&mchdev_lock);
-	if (!i915_mch_dev)
-		goto out_unlock;
-	dev_priv = i915_mch_dev;
-
-	chipset_val = __i915_chipset_val(dev_priv);
-	graphics_val = __i915_gfx_val(dev_priv);
+	struct drm_i915_private *i915;
+	unsigned long chipset_val = 0;
+	unsigned long graphics_val = 0;
+	intel_wakeref_t wakeref;
 
-	ret = chipset_val + graphics_val;
+	i915 = mchdev_get();
+	if (!i915)
+		return 0;
 
-out_unlock:
-	spin_unlock_irq(&mchdev_lock);
+	with_intel_runtime_pm(i915, wakeref) {
+		spin_lock_irq(&mchdev_lock);
+		chipset_val = __i915_chipset_val(i915);
+		graphics_val = __i915_gfx_val(i915);
+		spin_unlock_irq(&mchdev_lock);
+	}
 
-	return ret;
+	drm_dev_put(&i915->drm);
+	return chipset_val + graphics_val;
 }
 EXPORT_SYMBOL_GPL(i915_read_mch_val);
 
@@ -8029,23 +8045,19 @@ EXPORT_SYMBOL_GPL(i915_read_mch_val);
  */
 bool i915_gpu_raise(void)
 {
-	struct drm_i915_private *dev_priv;
-	bool ret = true;
-
-	spin_lock_irq(&mchdev_lock);
-	if (!i915_mch_dev) {
-		ret = false;
-		goto out_unlock;
-	}
-	dev_priv = i915_mch_dev;
+	struct drm_i915_private *i915;
 
-	if (dev_priv->ips.max_delay > dev_priv->ips.fmax)
-		dev_priv->ips.max_delay--;
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
 
-out_unlock:
+	spin_lock_irq(&mchdev_lock);
+	if (i915->ips.max_delay > i915->ips.fmax)
+		i915->ips.max_delay--;
 	spin_unlock_irq(&mchdev_lock);
 
-	return ret;
+	drm_dev_put(&i915->drm);
+	return true;
 }
 EXPORT_SYMBOL_GPL(i915_gpu_raise);
 
@@ -8057,23 +8069,19 @@ EXPORT_SYMBOL_GPL(i915_gpu_raise);
  */
 bool i915_gpu_lower(void)
 {
-	struct drm_i915_private *dev_priv;
-	bool ret = true;
-
-	spin_lock_irq(&mchdev_lock);
-	if (!i915_mch_dev) {
-		ret = false;
-		goto out_unlock;
-	}
-	dev_priv = i915_mch_dev;
+	struct drm_i915_private *i915;
 
-	if (dev_priv->ips.max_delay < dev_priv->ips.min_delay)
-		dev_priv->ips.max_delay++;
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
 
-out_unlock:
+	spin_lock_irq(&mchdev_lock);
+	if (i915->ips.max_delay < i915->ips.min_delay)
+		i915->ips.max_delay++;
 	spin_unlock_irq(&mchdev_lock);
 
-	return ret;
+	drm_dev_put(&i915->drm);
+	return true;
 }
 EXPORT_SYMBOL_GPL(i915_gpu_lower);
 
@@ -8084,13 +8092,16 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower);
  */
 bool i915_gpu_busy(void)
 {
-	bool ret = false;
+	struct drm_i915_private *i915;
+	bool ret;
 
-	spin_lock_irq(&mchdev_lock);
-	if (i915_mch_dev)
-		ret = i915_mch_dev->gt.awake;
-	spin_unlock_irq(&mchdev_lock);
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
 
+	ret = i915->gt.awake;
+
+	drm_dev_put(&i915->drm);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(i915_gpu_busy);
@@ -8103,24 +8114,19 @@ EXPORT_SYMBOL_GPL(i915_gpu_busy);
  */
 bool i915_gpu_turbo_disable(void)
 {
-	struct drm_i915_private *dev_priv;
-	bool ret = true;
-
-	spin_lock_irq(&mchdev_lock);
-	if (!i915_mch_dev) {
-		ret = false;
-		goto out_unlock;
-	}
-	dev_priv = i915_mch_dev;
-
-	dev_priv->ips.max_delay = dev_priv->ips.fstart;
+	struct drm_i915_private *i915;
+	bool ret;
 
-	if (!ironlake_set_drps(dev_priv, dev_priv->ips.fstart))
-		ret = false;
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
 
-out_unlock:
+	spin_lock_irq(&mchdev_lock);
+	i915->ips.max_delay = i915->ips.fstart;
+	ret = ironlake_set_drps(i915, i915->ips.fstart);
 	spin_unlock_irq(&mchdev_lock);
 
+	drm_dev_put(&i915->drm);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
@@ -8149,18 +8155,14 @@ void intel_gpu_ips_init(struct drm_i915_private *dev_priv)
 {
 	/* We only register the i915 ips part with intel-ips once everything is
 	 * set up, to avoid intel-ips sneaking in and reading bogus values. */
-	spin_lock_irq(&mchdev_lock);
-	i915_mch_dev = dev_priv;
-	spin_unlock_irq(&mchdev_lock);
+	rcu_assign_pointer(i915_mch_dev, dev_priv);
 
 	ips_ping_for_i915_load();
 }
 
 void intel_gpu_ips_teardown(void)
 {
-	spin_lock_irq(&mchdev_lock);
-	i915_mch_dev = NULL;
-	spin_unlock_irq(&mchdev_lock);
+	rcu_assign_pointer(i915_mch_dev, NULL);
 }
 
 static void intel_init_emon(struct drm_i915_private *dev_priv)
-- 
2.20.0.rc2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.CHECKPATCH: warning for series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim

[Patchwork]

== Series Details ==

Series: series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim
URL   : https://patchwork.freedesktop.org/series/53953/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
916a3be212e3 drm/i915: Return immediately if trylock fails for direct-reclaim
26917cf8d163 drm/i915/userptr: Avoid struct_mutex recursion for mmu_invalidate_range_start
-:23: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line)
#23: 
References: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers")

-:23: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers")'
#23: 
References: 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers")

-:240: ERROR:LOCKING: recursive locking is bad, do not use this ever.
#240: FILE: drivers/gpu/drm/i915/i915_gem_userptr.c:108:
+	switch (mutex_trylock_recursive(m)) {

total: 2 errors, 1 warnings, 0 checks, 444 lines checked
c19a3aa46c49 drm/i915/userptr: Probe vma range before gup
bde35602ca66 drm/i915/selftests: Check we can recover a wedged device
10e12b27ed33 drm/i915/selftests: Verify we can perform resets from atomic context
ce3fa3096959 drm/i915/icl: Record the valid VDBoxes with SFC capability
b5cc02d7c587 drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines
6db7a50be19a drm/i915: Always try to reset the GPU on takeover
654c916de1ce drm/i915: Report the number of closed vma held by each context in debugfs
-:61: WARNING:LONG_LINE: line over 100 characters
#61: FILE: drivers/gpu/drm/i915/i915_debugfs.c:348:
+		seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound, %llu closed)\n", \

total: 0 errors, 1 warnings, 0 checks, 201 lines checked
0e7e9b9d070d drm/i915: Remove debugfs/i915_ppgtt_info
12f7cb4ec2ad drm/i915: Track all held rpm wakerefs
-:105: CHECK:UNCOMMENTED_DEFINITION: spinlock_t definition without comment
#105: FILE: drivers/gpu/drm/i915/i915_drv.h:1160:
+	spinlock_t debug_lock;

total: 0 errors, 0 warnings, 1 checks, 571 lines checked
c4143336103e drm/i915: Markup paired operations on wakerefs
-:783: WARNING:NEW_TYPEDEFS: do not add new typedefs
#783: FILE: drivers/gpu/drm/i915/i915_drv.h:134:
+typedef depot_stack_handle_t intel_wakeref_t;

total: 0 errors, 1 warnings, 0 checks, 2533 lines checked
b72c3febcaf2 drm/i915: Syntatic sugar for using intel_runtime_pm
-:509: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'i915' - possible side-effects?
#509: FILE: drivers/gpu/drm/i915/intel_drv.h:2181:
+#define with_intel_runtime_pm(i915, wf) \
+	for (wf = intel_runtime_pm_get(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)

-:509: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'wf' - possible side-effects?
#509: FILE: drivers/gpu/drm/i915/intel_drv.h:2181:
+#define with_intel_runtime_pm(i915, wf) \
+	for (wf = intel_runtime_pm_get(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)

-:513: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'i915' - possible side-effects?
#513: FILE: drivers/gpu/drm/i915/intel_drv.h:2185:
+#define with_intel_runtime_pm_if_in_use(i915, wf) \
+	for (wf = intel_runtime_pm_get_if_in_use(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)

-:513: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'wf' - possible side-effects?
#513: FILE: drivers/gpu/drm/i915/intel_drv.h:2185:
+#define with_intel_runtime_pm_if_in_use(i915, wf) \
+	for (wf = intel_runtime_pm_get_if_in_use(i915); wf; \
+	     intel_runtime_pm_put(i915, wf), wf = 0)

total: 0 errors, 0 warnings, 4 checks, 732 lines checked
507dba016bbc drm/i915: Markup paired operations on display power domains
e1be67c9baf0 drm/i915: Track the wakeref used to initialise display power domains
-:213: WARNING:LINE_SPACING: Missing a blank line after declarations
#213: FILE: drivers/gpu/drm/i915/intel_runtime_pm.c:4107:
+	struct i915_power_domains *power_domains = &i915->power_domains;
+	intel_wakeref_t wakeref __maybe_unused =

total: 0 errors, 1 warnings, 0 checks, 324 lines checked
5b0a7f1a093b drm/i915: Combined gt.awake/gt.power wakerefs
7d9692b87640 drm/i915/dp: Markup pps lock power well
-:57: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'dp' - possible side-effects?
#57: FILE: drivers/gpu/drm/i915/intel_dp.c:633:
+#define with_pps_lock(dp, wf) \
+	for (wf = pps_lock(dp); wf; wf = pps_unlock(dp, wf))

-:57: CHECK:MACRO_ARG_REUSE: Macro argument reuse 'wf' - possible side-effects?
#57: FILE: drivers/gpu/drm/i915/intel_dp.c:633:
+#define with_pps_lock(dp, wf) \
+	for (wf = pps_lock(dp); wf; wf = pps_unlock(dp, wf))

total: 0 errors, 0 warnings, 2 checks, 430 lines checked
6649c0427ac7 drm/i915: Complain if hsw_get_pipe_config acquires the same power well twice
7d9e140908f7 drm/i915: Mark up Ironlake ips with rpm wakerefs

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.SPARSE: warning for series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim

[Patchwork]

== Series Details ==

Series: series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim
URL   : https://patchwork.freedesktop.org/series/53953/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Sparse version: v0.5.2
Commit: drm/i915: Return immediately if trylock fails for direct-reclaim
Okay!

Commit: drm/i915/userptr: Avoid struct_mutex recursion for mmu_invalidate_range_start
Okay!

Commit: drm/i915/userptr: Probe vma range before gup
Okay!

Commit: drm/i915/selftests: Check we can recover a wedged device
Okay!

Commit: drm/i915/selftests: Verify we can perform resets from atomic context
Okay!

Commit: drm/i915/icl: Record the valid VDBoxes with SFC capability
Okay!

Commit: drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines
Okay!

Commit: drm/i915: Always try to reset the GPU on takeover
Okay!

Commit: drm/i915: Report the number of closed vma held by each context in debugfs
Okay!

Commit: drm/i915: Remove debugfs/i915_ppgtt_info
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1501:9: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1501:9: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1511:17: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1511:17: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1557:17: warning: expression using sizeof(void)
-O:drivers/gpu/drm/i915/i915_gem_gtt.c:1557:17: warning: expression using sizeof(void)
-drivers/gpu/drm/i915/i915_gem_gtt.c:348:14: warning: expression using sizeof(void)
-drivers/gpu/drm/i915/i915_gem_gtt.c:348:14: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/i915_gem_gtt.c:348:14: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/i915_gem_gtt.c:348:14: warning: expression using sizeof(void)

Commit: drm/i915: Track all held rpm wakerefs
-drivers/gpu/drm/i915/selftests/../i915_drv.h:3561:16: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/selftests/../i915_drv.h:3568:16: warning: expression using sizeof(void)
+./include/linux/slab.h:332:43: warning: dubious: x & !y

Commit: drm/i915: Markup paired operations on wakerefs
-drivers/gpu/drm/i915/selftests/../i915_drv.h:3568:16: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/selftests/../i915_drv.h:3572:16: warning: expression using sizeof(void)
+./include/linux/slab.h:332:43: warning: dubious: x & !y

Commit: drm/i915: Syntatic sugar for using intel_runtime_pm
Okay!

Commit: drm/i915: Markup paired operations on display power domains
-drivers/gpu/drm/i915/selftests/../i915_drv.h:3572:16: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/selftests/../i915_drv.h:3574:16: warning: expression using sizeof(void)

Commit: drm/i915: Track the wakeref used to initialise display power domains
-drivers/gpu/drm/i915/selftests/../i915_drv.h:3574:16: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/selftests/../i915_drv.h:3576:16: warning: expression using sizeof(void)

Commit: drm/i915: Combined gt.awake/gt.power wakerefs
-drivers/gpu/drm/i915/selftests/../i915_drv.h:3576:16: warning: expression using sizeof(void)
+drivers/gpu/drm/i915/selftests/../i915_drv.h:3575:16: warning: expression using sizeof(void)

Commit: drm/i915/dp: Markup pps lock power well
Okay!

Commit: drm/i915: Complain if hsw_get_pipe_config acquires the same power well twice
Okay!

Commit: drm/i915: Mark up Ironlake ips with rpm wakerefs
Okay!

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.BAT: success for series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim

[Patchwork]

== Series Details ==

Series: series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim
URL   : https://patchwork.freedesktop.org/series/53953/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_5296 -> Patchwork_11077
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://patchwork.freedesktop.org/api/1.0/series/53953/revisions/1/mbox/

Known issues
------------

  Here are the changes found in Patchwork_11077 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_exec_suspend@basic-s3:
    - fi-blb-e6850:       PASS -> INCOMPLETE [fdo#107718]

  * igt@i915_module_load@reload-no-display:
    - fi-byt-clapper:     PASS -> WARN [fdo#108688]

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-kbl-7500u:       PASS -> FAIL [fdo#108767]

  * igt@kms_flip@basic-flip-vs-dpms:
    - fi-icl-u3:          NOTRUN -> DMESG-WARN [fdo#108924]
    - fi-skl-6700hq:      PASS -> DMESG-WARN [fdo#105998]

  * igt@kms_psr@sprite_plane_onoff:
    - fi-skl-6700hq:      PASS -> FAIL [fdo#107383] +3

  * {igt@runner@aborted}:
    - fi-icl-u3:          NOTRUN -> FAIL [fdo#108924]

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#105998]: https://bugs.freedesktop.org/show_bug.cgi?id=105998
  [fdo#107383]: https://bugs.freedesktop.org/show_bug.cgi?id=107383
  [fdo#107718]: https://bugs.freedesktop.org/show_bug.cgi?id=107718
  [fdo#108688]: https://bugs.freedesktop.org/show_bug.cgi?id=108688
  [fdo#108767]: https://bugs.freedesktop.org/show_bug.cgi?id=108767
  [fdo#108924]: https://bugs.freedesktop.org/show_bug.cgi?id=108924


Participating hosts (48 -> 45)
------------------------------

  Additional (2): fi-byt-j1900 fi-icl-u3 
  Missing    (5): fi-kbl-soraka fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-ctg-p8600 


Build changes
-------------

    * Linux: CI_DRM_5296 -> Patchwork_11077

  CI_DRM_5296: 70751bd8a3f27b035d203ecafcad452f4d7c2c15 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4745: 3b52e8a5809a4e860350c59476a456745cd9fee0 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_11077: 7d9e140908f7c1926714fd99b17f2f08be5eb022 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

7d9e140908f7 drm/i915: Mark up Ironlake ips with rpm wakerefs
6649c0427ac7 drm/i915: Complain if hsw_get_pipe_config acquires the same power well twice
7d9692b87640 drm/i915/dp: Markup pps lock power well
5b0a7f1a093b drm/i915: Combined gt.awake/gt.power wakerefs
e1be67c9baf0 drm/i915: Track the wakeref used to initialise display power domains
507dba016bbc drm/i915: Markup paired operations on display power domains
b72c3febcaf2 drm/i915: Syntatic sugar for using intel_runtime_pm
c4143336103e drm/i915: Markup paired operations on wakerefs
12f7cb4ec2ad drm/i915: Track all held rpm wakerefs
0e7e9b9d070d drm/i915: Remove debugfs/i915_ppgtt_info
654c916de1ce drm/i915: Report the number of closed vma held by each context in debugfs
6db7a50be19a drm/i915: Always try to reset the GPU on takeover
b5cc02d7c587 drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines
ce3fa3096959 drm/i915/icl: Record the valid VDBoxes with SFC capability
10e12b27ed33 drm/i915/selftests: Verify we can perform resets from atomic context
bde35602ca66 drm/i915/selftests: Check we can recover a wedged device
c19a3aa46c49 drm/i915/userptr: Probe vma range before gup
26917cf8d163 drm/i915/userptr: Avoid struct_mutex recursion for mmu_invalidate_range_start
916a3be212e3 drm/i915: Return immediately if trylock fails for direct-reclaim

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_11077/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 06/19] drm/i915/icl: Record the valid VDBoxes with SFC capability

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> From: Oscar Mateo <oscar.mateo@intel.com>
> 
> In Gen11, only even numbered "logical" VDBoxes are hooked up to an SFC
> (Scaler & Format Converter) unit. We will use this information to decide
> when the SFC units need to be reset.
> 
> BSpec: 20189
> 
> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
> Signed-off-by: Michel Thierry <michel.thierry@intel.com>
> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Cc: Michel Thierry <michel.thierry@intel.com>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/intel_device_info.c | 11 ++++++++++-
>   drivers/gpu/drm/i915/intel_device_info.h |  3 +++
>   2 files changed, 13 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
> index bd5c4d62c635..acd7ee74d308 100644
> --- a/drivers/gpu/drm/i915/intel_device_info.c
> +++ b/drivers/gpu/drm/i915/intel_device_info.c
> @@ -884,8 +884,9 @@ void intel_driver_caps_print(const struct intel_driver_caps *caps,
>   void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
>   {
>   	struct intel_device_info *info = mkwrite_device_info(dev_priv);
> -	u32 media_fuse;
> +	unsigned int logical_vdbox = 0;
>   	unsigned int i;
> +	u32 media_fuse;
>   
>   	if (INTEL_GEN(dev_priv) < 11)
>   		return;
> @@ -904,7 +905,15 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
>   		if (!(BIT(i) & info->vdbox_enable)) {
>   			info->ring_mask &= ~ENGINE_MASK(_VCS(i));
>   			DRM_DEBUG_DRIVER("vcs%u fused off\n", i);
> +			continue;
>   		}
> +
> +		/*
> +		 * In Gen11, only even numbered logical VDBOXes are
> +		 * hooked up to an SFC (Scaler & Format Converter) unit.
> +		 */
> +		if (logical_vdbox++ % 2 == 0)
> +			info->vdbox_sfc_access |= BIT(i);
>   	}
>   
>   	DRM_DEBUG_DRIVER("vebox enable: %04x\n", info->vebox_enable);
> diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
> index 1caf24e2cf0b..dd34f974a857 100644
> --- a/drivers/gpu/drm/i915/intel_device_info.h
> +++ b/drivers/gpu/drm/i915/intel_device_info.h
> @@ -198,6 +198,9 @@ struct intel_device_info {
>   	u8 vdbox_enable;
>   	u8 vebox_enable;
>   
> +	/* Media engine access to SFC per instance */
> +	u8 vdbox_sfc_access;
> +
>   	struct color_luts {
>   		u16 degamma_lut_size;
>   		u16 gamma_lut_size;
> 

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> From: Oscar Mateo <oscar.mateo@intel.com>
> 
> SFC (Scaler & Format Converter) units are shared between VD and VEBoxes.
> They also happen to have separate reset bits. So, whenever we want to reset
> one or more of the media engines, we have to make sure the SFCs do not
> change owner in the process and, if this owner happens to be one of the
> engines being reset, we need to reset the SFC as well.
> 
> This happens in 4 steps:
> 
> 1) Tell the engine that a software reset is going to happen. The engine
> will then try to force lock the SFC (if currently locked, it will
> remain so; if currently unlocked, it will ignore this and all new lock
> requests).
> 
> 2) Poll the ack bit to make sure the hardware has received the forced
> lock from the driver. Once this bit is set, it indicates SFC status
> (lock or unlock) will not change anymore (until we tell the engine it
> is safe to unlock again).
> 
> 3) Check the usage bit to see if the SFC has ended up being locked to
> the engine we want to reset. If this is the case, we have to reset
> the SFC as well.
> 
> 4) Unlock all the SFCs once the reset sequence is completed.
> 
> Obviously, if we are resetting the whole GPU, we don't have to worry
> about all of this.
> 
> BSpec: 10989
> BSpec: 10990
> BSpec: 10954
> BSpec: 10955
> BSpec: 10956
> BSpec: 19212
> 
> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
> Signed-off-by: Michel Thierry <michel.thierry@intel.com>
> Cc: Michel Thierry <michel.thierry@intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/i915_reg.h     |  18 +++++
>   drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++--
>   2 files changed, 128 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 0a7d60509ca7..0796526dc10f 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -347,6 +347,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
>   #define  GEN11_GRDOM_MEDIA4		(1 << 8)
>   #define  GEN11_GRDOM_VECS		(1 << 13)
>   #define  GEN11_GRDOM_VECS2		(1 << 14)
> +#define  GEN11_GRDOM_SFC0		(1 << 17)
> +#define  GEN11_GRDOM_SFC1		(1 << 18)
> +
> +#define  GEN11_VCS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << ((instance) >> 1))
> +#define  GEN11_VECS_SFC_RESET_BIT(instance)	(GEN11_GRDOM_SFC0 << (instance))
> +
> +#define GEN11_VCS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x88C)
> +#define   GEN11_VCS_SFC_FORCED_LOCK_BIT		(1 << 0)
> +#define GEN11_VCS_SFC_LOCK_STATUS(engine)	_MMIO((engine)->mmio_base + 0x890)
> +#define   GEN11_VCS_SFC_USAGE_BIT		(1 << 0)
> +#define   GEN11_VCS_SFC_LOCK_ACK_BIT		(1 << 1)
> +
> +#define GEN11_VECS_SFC_FORCED_LOCK(engine)	_MMIO((engine)->mmio_base + 0x201C)
> +#define   GEN11_VECS_SFC_FORCED_LOCK_BIT	(1 << 0)
> +#define GEN11_VECS_SFC_LOCK_ACK(engine)		_MMIO((engine)->mmio_base + 0x2018)
> +#define   GEN11_VECS_SFC_LOCK_ACK_BIT		(1 << 0)
> +#define GEN11_VECS_SFC_USAGE(engine)		_MMIO((engine)->mmio_base + 0x2014)
> +#define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
>   
>   #define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base + 0x228)
>   #define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base + 0x518)
> diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> index 9289515108c3..408692b88c98 100644
> --- a/drivers/gpu/drm/i915/intel_uncore.c
> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
>   	return gen6_hw_domain_reset(dev_priv, hw_mask);
>   }
>   
> +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
> +			  struct intel_engine_cs *engine)
> +{
> +	u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;

Only a single use site so could get away with a local copy.

> +	i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
> +	u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
> +	i915_reg_t sfc_usage;
> +	u32 sfc_usage_bit;
> +	u32 sfc_reset_bit;
> +
> +	switch (engine->class) {
> +	case VIDEO_DECODE_CLASS:
> +		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
> +			return 0;
> +
> +		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
> +		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
> +
> +		sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
> +		sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
> +
> +		sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
> +		sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
> +		sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
> +		break;
> +
> +	case VIDEO_ENHANCEMENT_CLASS:
> +		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
> +		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
> +
> +		sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
> +		sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
> +
> +		sfc_usage = GEN11_VECS_SFC_USAGE(engine);
> +		sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
> +		sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
> +		break;
> +
> +	default:
> +		return 0;
> +	}
> +
> +	/*
> +	 * Tell the engine that a software reset is going to happen. The engine
> +	 * will then try to force lock the SFC (if currently locked, it will
> +	 * remain so until we tell the engine it is safe to unlock; if currently
> +	 * unlocked, it will ignore this and all new lock requests). If SFC
> +	 * ends up being locked to the engine we want to reset, we have to reset
> +	 * it as well (we will unlock it once the reset sequence is completed).
> +	 */
> +	I915_WRITE_FW(sfc_forced_lock,
> +		      I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
> +
> +	if (__intel_wait_for_register_fw(dev_priv,
> +					 sfc_forced_lock_ack,
> +					 sfc_forced_lock_ack_bit,
> +					 sfc_forced_lock_ack_bit,
> +					 1000, 0, NULL)) {
> +		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
> +		return 0;
> +	}
> +
> +	if ((I915_READ_FW(sfc_usage) & sfc_usage_bit) == sfc_usage_bit)

"== sfc_usage_bit" parts is redundant.

> +		return sfc_reset_bit;
> +
> +	return 0;
> +}
> +
> +static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
> +			     struct intel_engine_cs *engine)
> +{
> +	u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
> +	i915_reg_t sfc_forced_lock;
> +	u32 sfc_forced_lock_bit;
> +
> +	switch (engine->class) {
> +	case VIDEO_DECODE_CLASS:
> +		if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
> +			return;
> +
> +		sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
> +		sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
> +		break;
> +
> +	case VIDEO_ENHANCEMENT_CLASS:
> +		sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
> +		sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
> +		break;
> +
> +	default:
> +		return;
> +	}
> +
> +	I915_WRITE_FW(sfc_forced_lock,
> +		      I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
> +}
> +
>   /**
>    * gen11_reset_engines - reset individual engines
>    * @dev_priv: i915 device
> @@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
>   static int gen11_reset_engines(struct drm_i915_private *dev_priv,
>   			       unsigned int engine_mask)
>   {
> -	struct intel_engine_cs *engine;
>   	const u32 hw_engine_mask[I915_NUM_ENGINES] = {
>   		[RCS] = GEN11_GRDOM_RENDER,
>   		[BCS] = GEN11_GRDOM_BLT,
> @@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct drm_i915_private *dev_priv,
>   		[VECS] = GEN11_GRDOM_VECS,
>   		[VECS2] = GEN11_GRDOM_VECS2,
>   	};
> +	struct intel_engine_cs *engine;
> +	unsigned int tmp;
>   	u32 hw_mask;
> +	int ret;
>   
>   	BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
>   
>   	if (engine_mask == ALL_ENGINES) {
>   		hw_mask = GEN11_GRDOM_FULL;
>   	} else {
> -		unsigned int tmp;
> -
>   		hw_mask = 0;
> -		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
> +		for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
>   			hw_mask |= hw_engine_mask[engine->id];
> +			hw_mask |= gen11_lock_sfc(dev_priv, engine);

Presumably point No. 3 from the commit message does not mean there is a 
separate way to reset the SFC, just that the act of resetting the engine 
to which the SFC is locked to, will reset SFC as well?

> +		}
>   	}
>   
> -	return gen6_hw_domain_reset(dev_priv, hw_mask);
> +	ret = gen6_hw_domain_reset(dev_priv, hw_mask);
> +
> +	if (engine_mask != ALL_ENGINES)
> +		for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
> +			gen11_unlock_sfc(dev_priv, engine);

And this presumably means it is okay to unlock engines which we haven't 
lock in the previous loop?

> +
> +	return ret;
>   }
>   
>   /**
> 
I'll go to look for answers to the commit message question before 
applying the r-b.

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✓ Fi.CI.IGT: success for series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim

[Patchwork]

== Series Details ==

Series: series starting with [01/19] drm/i915: Return immediately if trylock fails for direct-reclaim
URL   : https://patchwork.freedesktop.org/series/53953/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_5296_full -> Patchwork_11077_full
====================================================

Summary
-------

  **WARNING**

  Minor unknown changes coming with Patchwork_11077_full need to be verified
  manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_11077_full, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_11077_full:

### IGT changes ###

#### Warnings ####

  * igt@kms_draw_crc@draw-method-xrgb8888-pwrite-xtiled:
    - shard-snb:          PASS -> SKIP +2

  * igt@tools_test@tools_test:
    - shard-skl:          SKIP -> PASS

  
Known issues
------------

  Here are the changes found in Patchwork_11077_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_exec_whisper@normal:
    - shard-skl:          PASS -> TIMEOUT [fdo#108592]

  * igt@i915_selftest@live_contexts:
    - shard-iclb:         NOTRUN -> DMESG-FAIL [fdo#108569]

  * igt@kms_atomic_transition@plane-toggle-modeset-transition:
    - shard-iclb:         PASS -> DMESG-WARN [fdo#107724] +12

  * igt@kms_busy@extended-modeset-hang-newfb-render-b:
    - shard-skl:          NOTRUN -> DMESG-WARN [fdo#107956]
    - shard-iclb:         NOTRUN -> DMESG-WARN [fdo#107956]

  * igt@kms_busy@extended-modeset-hang-newfb-with-reset-render-b:
    - shard-iclb:         PASS -> DMESG-WARN [fdo#107956]

  * igt@kms_busy@extended-modeset-hang-newfb-with-reset-render-c:
    - shard-glk:          NOTRUN -> DMESG-WARN [fdo#107956]

  * igt@kms_chv_cursor_fail@pipe-b-256x256-right-edge:
    - shard-iclb:         PASS -> DMESG-WARN [fdo#107724] / [fdo#108336] +5

  * igt@kms_color@pipe-a-legacy-gamma:
    - shard-apl:          PASS -> FAIL [fdo#104782] / [fdo#108145]

  * igt@kms_cursor_crc@cursor-128x42-sliding:
    - shard-glk:          PASS -> FAIL [fdo#103232]

  * igt@kms_cursor_crc@cursor-256x85-random:
    - shard-apl:          PASS -> FAIL [fdo#103232] +5

  * igt@kms_fbcon_fbt@fbc-suspend:
    - shard-glk:          PASS -> FAIL [fdo#103833] / [fdo#105681]

  * igt@kms_fbcon_fbt@psr-suspend:
    - shard-skl:          NOTRUN -> FAIL [fdo#107882]

  * igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-fullscreen:
    - shard-apl:          PASS -> FAIL [fdo#103167]

  * igt@kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-pwrite:
    - shard-glk:          PASS -> FAIL [fdo#103167] +2

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-pri-shrfb-draw-mmap-cpu:
    - shard-iclb:         PASS -> DMESG-FAIL [fdo#107724] +4

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-render:
    - shard-iclb:         PASS -> FAIL [fdo#103167] +3

  * igt@kms_plane@pixel-format-pipe-b-planes-source-clamping:
    - shard-apl:          PASS -> FAIL [fdo#108948]

  * igt@kms_plane@plane-position-covered-pipe-b-planes:
    - shard-iclb:         PASS -> FAIL [fdo#103166] +1

  * igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max:
    - shard-skl:          NOTRUN -> FAIL [fdo#108145] +1

  * igt@kms_plane_alpha_blend@pipe-c-alpha-opaque-fb:
    - shard-apl:          PASS -> FAIL [fdo#108145]

  * igt@kms_plane_multiple@atomic-pipe-c-tiling-y:
    - shard-apl:          PASS -> FAIL [fdo#103166]

  * igt@kms_psr@no_drrs:
    - shard-iclb:         PASS -> FAIL [fdo#108341]

  * igt@kms_rotation_crc@multiplane-rotation-cropping-top:
    - shard-glk:          PASS -> DMESG-FAIL [fdo#105763] / [fdo#106538]

  * igt@kms_sysfs_edid_timing:
    - shard-skl:          NOTRUN -> FAIL [fdo#100047]

  * igt@pm_rpm@gem-execbuf:
    - shard-skl:          PASS -> INCOMPLETE [fdo#107803] / [fdo#107807]

  * igt@pm_rpm@gem-execbuf-stress-extra-wait:
    - shard-iclb:         PASS -> INCOMPLETE [fdo#108840]

  
#### Possible fixes ####

  * igt@kms_busy@extended-pageflip-modeset-hang-oldfb-render-b:
    - shard-glk:          DMESG-WARN [fdo#107956] -> PASS

  * igt@kms_color@pipe-b-ctm-negative:
    - shard-skl:          FAIL [fdo#107361] -> PASS

  * igt@kms_cursor_crc@cursor-256x256-dpms:
    - shard-apl:          FAIL [fdo#103232] -> PASS

  * igt@kms_cursor_crc@cursor-256x85-onscreen:
    - shard-glk:          FAIL [fdo#103232] -> PASS

  * igt@kms_draw_crc@draw-method-rgb565-render-ytiled:
    - shard-iclb:         WARN [fdo#108336] -> PASS +1

  * igt@kms_flip@dpms-off-confusion:
    - shard-iclb:         DMESG-WARN [fdo#107724] -> PASS +23

  * igt@kms_flip_tiling@flip-changes-tiling:
    - shard-iclb:         DMESG-WARN [fdo#107724] / [fdo#108336] -> PASS +10

  * igt@kms_frontbuffer_tracking@fbc-1p-offscren-pri-indfb-draw-pwrite:
    - shard-iclb:         DMESG-FAIL [fdo#107724] -> PASS +6

  * igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-gtt:
    - shard-glk:          FAIL [fdo#103167] -> PASS +1

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-pwrite:
    - shard-iclb:         FAIL [fdo#103167] -> PASS +1

  * igt@kms_pipe_crc_basic@suspend-read-crc-pipe-b:
    - shard-skl:          INCOMPLETE [fdo#104108] / [fdo#107773] -> PASS

  * igt@kms_plane@pixel-format-pipe-c-planes:
    - shard-apl:          FAIL [fdo#103166] -> PASS +2

  * igt@kms_plane_alpha_blend@pipe-b-coverage-7efc:
    - shard-skl:          FAIL [fdo#107815] -> PASS

  * igt@kms_plane_alpha_blend@pipe-c-constant-alpha-max:
    - shard-apl:          FAIL [fdo#108145] -> PASS

  * igt@kms_plane_multiple@atomic-pipe-a-tiling-x:
    - shard-glk:          FAIL [fdo#103166] -> PASS

  * igt@kms_rotation_crc@sprite-rotation-90:
    - shard-glk:          INCOMPLETE [fdo#103359] / [k.org#198133] -> PASS

  * igt@kms_setmode@basic:
    - shard-apl:          FAIL [fdo#99912] -> PASS

  * igt@kms_vblank@pipe-c-ts-continuation-suspend:
    - shard-iclb:         INCOMPLETE [fdo#107713] -> PASS

  * igt@perf@blocking:
    - shard-hsw:          FAIL [fdo#102252] -> PASS

  * igt@sw_sync@sync_busy_fork_unixsocket:
    - shard-iclb:         INCOMPLETE [fdo#108889] -> PASS

  
#### Warnings ####

  * igt@kms_cursor_crc@cursor-256x256-random:
    - shard-iclb:         DMESG-WARN [fdo#107724] / [fdo#108336] -> FAIL [fdo#103232] +3

  * igt@kms_frontbuffer_tracking@fbcpsr-1p-primscrn-spr-indfb-draw-mmap-wc:
    - shard-iclb:         DMESG-FAIL [fdo#107724] -> FAIL [fdo#103167] +1

  * igt@kms_frontbuffer_tracking@psr-1p-primscrn-spr-indfb-draw-render:
    - shard-iclb:         DMESG-WARN [fdo#107724] / [fdo#108336] -> FAIL [fdo#103167]

  * igt@kms_plane@pixel-format-pipe-a-planes:
    - shard-iclb:         DMESG-WARN [fdo#107724] / [fdo#108336] -> FAIL [fdo#103166]

  * igt@kms_plane@pixel-format-pipe-a-planes-source-clamping:
    - shard-iclb:         DMESG-WARN [fdo#107724] / [fdo#108336] -> FAIL [fdo#108948]

  * igt@prime_vgem@fence-wait-blt:
    - shard-snb:          DMESG-WARN [fdo#107469] -> INCOMPLETE [fdo#105411]

  
  [fdo#100047]: https://bugs.freedesktop.org/show_bug.cgi?id=100047
  [fdo#102252]: https://bugs.freedesktop.org/show_bug.cgi?id=102252
  [fdo#103166]: https://bugs.freedesktop.org/show_bug.cgi?id=103166
  [fdo#103167]: https://bugs.freedesktop.org/show_bug.cgi?id=103167
  [fdo#103232]: https://bugs.freedesktop.org/show_bug.cgi?id=103232
  [fdo#103359]: https://bugs.freedesktop.org/show_bug.cgi?id=103359
  [fdo#103833]: https://bugs.freedesktop.org/show_bug.cgi?id=103833
  [fdo#104108]: https://bugs.freedesktop.org/show_bug.cgi?id=104108
  [fdo#104782]: https://bugs.freedesktop.org/show_bug.cgi?id=104782
  [fdo#105411]: https://bugs.freedesktop.org/show_bug.cgi?id=105411
  [fdo#105681]: https://bugs.freedesktop.org/show_bug.cgi?id=105681
  [fdo#105763]: https://bugs.freedesktop.org/show_bug.cgi?id=105763
  [fdo#106538]: https://bugs.freedesktop.org/show_bug.cgi?id=106538
  [fdo#107361]: https://bugs.freedesktop.org/show_bug.cgi?id=107361
  [fdo#107469]: https://bugs.freedesktop.org/show_bug.cgi?id=107469
  [fdo#107713]: https://bugs.freedesktop.org/show_bug.cgi?id=107713
  [fdo#107724]: https://bugs.freedesktop.org/show_bug.cgi?id=107724
  [fdo#107773]: https://bugs.freedesktop.org/show_bug.cgi?id=107773
  [fdo#107803]: https://bugs.freedesktop.org/show_bug.cgi?id=107803
  [fdo#107807]: https://bugs.freedesktop.org/show_bug.cgi?id=107807
  [fdo#107815]: https://bugs.freedesktop.org/show_bug.cgi?id=107815
  [fdo#107882]: https://bugs.freedesktop.org/show_bug.cgi?id=107882
  [fdo#107956]: https://bugs.freedesktop.org/show_bug.cgi?id=107956
  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#108336]: https://bugs.freedesktop.org/show_bug.cgi?id=108336
  [fdo#108341]: https://bugs.freedesktop.org/show_bug.cgi?id=108341
  [fdo#108569]: https://bugs.freedesktop.org/show_bug.cgi?id=108569
  [fdo#108592]: https://bugs.freedesktop.org/show_bug.cgi?id=108592
  [fdo#108840]: https://bugs.freedesktop.org/show_bug.cgi?id=108840
  [fdo#108889]: https://bugs.freedesktop.org/show_bug.cgi?id=108889
  [fdo#108948]: https://bugs.freedesktop.org/show_bug.cgi?id=108948
  [fdo#99912]: https://bugs.freedesktop.org/show_bug.cgi?id=99912
  [k.org#198133]: https://bugzilla.kernel.org/show_bug.cgi?id=198133


Participating hosts (7 -> 7)
------------------------------

  No changes in participating hosts


Build changes
-------------

    * Linux: CI_DRM_5296 -> Patchwork_11077

  CI_DRM_5296: 70751bd8a3f27b035d203ecafcad452f4d7c2c15 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_4745: 3b52e8a5809a4e860350c59476a456745cd9fee0 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_11077: 7d9e140908f7c1926714fd99b17f2f08be5eb022 @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_11077/
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Tvrtko Ursulin]

On 12/12/2018 14:36, Tvrtko Ursulin wrote:
> 
> On 12/12/2018 13:41, Chris Wilson wrote:
>> From: Oscar Mateo <oscar.mateo@intel.com>
>>
>> SFC (Scaler & Format Converter) units are shared between VD and VEBoxes.
>> They also happen to have separate reset bits. So, whenever we want to 
>> reset
>> one or more of the media engines, we have to make sure the SFCs do not
>> change owner in the process and, if this owner happens to be one of the
>> engines being reset, we need to reset the SFC as well.
>>
>> This happens in 4 steps:
>>
>> 1) Tell the engine that a software reset is going to happen. The engine
>> will then try to force lock the SFC (if currently locked, it will
>> remain so; if currently unlocked, it will ignore this and all new lock
>> requests).
>>
>> 2) Poll the ack bit to make sure the hardware has received the forced
>> lock from the driver. Once this bit is set, it indicates SFC status
>> (lock or unlock) will not change anymore (until we tell the engine it
>> is safe to unlock again).
>>
>> 3) Check the usage bit to see if the SFC has ended up being locked to
>> the engine we want to reset. If this is the case, we have to reset
>> the SFC as well.
>>
>> 4) Unlock all the SFCs once the reset sequence is completed.
>>
>> Obviously, if we are resetting the whole GPU, we don't have to worry
>> about all of this.
>>
>> BSpec: 10989
>> BSpec: 10990
>> BSpec: 10954
>> BSpec: 10955
>> BSpec: 10956
>> BSpec: 19212
>>
>> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
>> Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
>> Signed-off-by: Michel Thierry <michel.thierry@intel.com>
>> Cc: Michel Thierry <michel.thierry@intel.com>
>> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
>> Cc: Chris Wilson <chris@chris-wilson.co.uk>
>> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
>> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>> ---
>>   drivers/gpu/drm/i915/i915_reg.h     |  18 +++++
>>   drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++--
>>   2 files changed, 128 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_reg.h 
>> b/drivers/gpu/drm/i915/i915_reg.h
>> index 0a7d60509ca7..0796526dc10f 100644
>> --- a/drivers/gpu/drm/i915/i915_reg.h
>> +++ b/drivers/gpu/drm/i915/i915_reg.h
>> @@ -347,6 +347,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t 
>> reg)
>>   #define  GEN11_GRDOM_MEDIA4        (1 << 8)
>>   #define  GEN11_GRDOM_VECS        (1 << 13)
>>   #define  GEN11_GRDOM_VECS2        (1 << 14)
>> +#define  GEN11_GRDOM_SFC0        (1 << 17)
>> +#define  GEN11_GRDOM_SFC1        (1 << 18)
>> +
>> +#define  GEN11_VCS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 << 
>> ((instance) >> 1))
>> +#define  GEN11_VECS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 << 
>> (instance))

These two lines could be a bit of a hidden mine for the future. They 
silently describe which video engines are connected to which SFC 
instance. I guess we'll just have to remember to update this if/when it 
changes.

>> +
>> +#define GEN11_VCS_SFC_FORCED_LOCK(engine)    
>> _MMIO((engine)->mmio_base + 0x88C)
>> +#define   GEN11_VCS_SFC_FORCED_LOCK_BIT        (1 << 0)
>> +#define GEN11_VCS_SFC_LOCK_STATUS(engine)    
>> _MMIO((engine)->mmio_base + 0x890)
>> +#define   GEN11_VCS_SFC_USAGE_BIT        (1 << 0)
>> +#define   GEN11_VCS_SFC_LOCK_ACK_BIT        (1 << 1)
>> +
>> +#define GEN11_VECS_SFC_FORCED_LOCK(engine)    
>> _MMIO((engine)->mmio_base + 0x201C)
>> +#define   GEN11_VECS_SFC_FORCED_LOCK_BIT    (1 << 0)
>> +#define GEN11_VECS_SFC_LOCK_ACK(engine)        
>> _MMIO((engine)->mmio_base + 0x2018)
>> +#define   GEN11_VECS_SFC_LOCK_ACK_BIT        (1 << 0)
>> +#define GEN11_VECS_SFC_USAGE(engine)        _MMIO((engine)->mmio_base 
>> + 0x2014)
>> +#define   GEN11_VECS_SFC_USAGE_BIT        (1 << 0)
>>   #define RING_PP_DIR_BASE(engine)    _MMIO((engine)->mmio_base + 0x228)
>>   #define RING_PP_DIR_BASE_READ(engine)    _MMIO((engine)->mmio_base + 
>> 0x518)
>> diff --git a/drivers/gpu/drm/i915/intel_uncore.c 
>> b/drivers/gpu/drm/i915/intel_uncore.c
>> index 9289515108c3..408692b88c98 100644
>> --- a/drivers/gpu/drm/i915/intel_uncore.c
>> +++ b/drivers/gpu/drm/i915/intel_uncore.c
>> @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct 
>> drm_i915_private *dev_priv,
>>       return gen6_hw_domain_reset(dev_priv, hw_mask);
>>   }
>> +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
>> +              struct intel_engine_cs *engine)
>> +{
>> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
> 
> Only a single use site so could get away with a local copy.
> 
>> +    i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
>> +    u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
>> +    i915_reg_t sfc_usage;
>> +    u32 sfc_usage_bit;
>> +    u32 sfc_reset_bit;
>> +
>> +    switch (engine->class) {
>> +    case VIDEO_DECODE_CLASS:
>> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
>> +            return 0;
>> +
>> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
>> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
>> +
>> +        sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
>> +        sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
>> +
>> +        sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
>> +        sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
>> +        sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
>> +        break;
>> +
>> +    case VIDEO_ENHANCEMENT_CLASS:
>> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
>> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
>> +
>> +        sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
>> +        sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
>> +
>> +        sfc_usage = GEN11_VECS_SFC_USAGE(engine);
>> +        sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
>> +        sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
>> +        break;
>> +
>> +    default:
>> +        return 0;
>> +    }
>> +
>> +    /*
>> +     * Tell the engine that a software reset is going to happen. The 
>> engine
>> +     * will then try to force lock the SFC (if currently locked, it will
>> +     * remain so until we tell the engine it is safe to unlock; if 
>> currently
>> +     * unlocked, it will ignore this and all new lock requests). If SFC
>> +     * ends up being locked to the engine we want to reset, we have 
>> to reset
>> +     * it as well (we will unlock it once the reset sequence is 
>> completed).
>> +     */
>> +    I915_WRITE_FW(sfc_forced_lock,
>> +              I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
>> +
>> +    if (__intel_wait_for_register_fw(dev_priv,
>> +                     sfc_forced_lock_ack,
>> +                     sfc_forced_lock_ack_bit,
>> +                     sfc_forced_lock_ack_bit,
>> +                     1000, 0, NULL)) {
>> +        DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
>> +        return 0;
>> +    }
>> +
>> +    if ((I915_READ_FW(sfc_usage) & sfc_usage_bit) == sfc_usage_bit)
> 
> "== sfc_usage_bit" parts is redundant.
> 
>> +        return sfc_reset_bit;
>> +
>> +    return 0;
>> +}
>> +
>> +static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
>> +                 struct intel_engine_cs *engine)
>> +{
>> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
>> +    i915_reg_t sfc_forced_lock;
>> +    u32 sfc_forced_lock_bit;
>> +
>> +    switch (engine->class) {
>> +    case VIDEO_DECODE_CLASS:
>> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
>> +            return;
>> +
>> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
>> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
>> +        break;
>> +
>> +    case VIDEO_ENHANCEMENT_CLASS:
>> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
>> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
>> +        break;
>> +
>> +    default:
>> +        return;
>> +    }
>> +
>> +    I915_WRITE_FW(sfc_forced_lock,
>> +              I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
>> +}
>> +
>>   /**
>>    * gen11_reset_engines - reset individual engines
>>    * @dev_priv: i915 device
>> @@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct 
>> drm_i915_private *dev_priv,
>>   static int gen11_reset_engines(struct drm_i915_private *dev_priv,
>>                      unsigned int engine_mask)
>>   {
>> -    struct intel_engine_cs *engine;
>>       const u32 hw_engine_mask[I915_NUM_ENGINES] = {
>>           [RCS] = GEN11_GRDOM_RENDER,
>>           [BCS] = GEN11_GRDOM_BLT,
>> @@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct 
>> drm_i915_private *dev_priv,
>>           [VECS] = GEN11_GRDOM_VECS,
>>           [VECS2] = GEN11_GRDOM_VECS2,
>>       };
>> +    struct intel_engine_cs *engine;
>> +    unsigned int tmp;
>>       u32 hw_mask;
>> +    int ret;
>>       BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
>>       if (engine_mask == ALL_ENGINES) {
>>           hw_mask = GEN11_GRDOM_FULL;
>>       } else {
>> -        unsigned int tmp;
>> -
>>           hw_mask = 0;
>> -        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
>> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
>>               hw_mask |= hw_engine_mask[engine->id];
>> +            hw_mask |= gen11_lock_sfc(dev_priv, engine);
> 
> Presumably point No. 3 from the commit message does not mean there is a 
> separate way to reset the SFC, just that the act of resetting the engine 
> to which the SFC is locked to, will reset SFC as well?

My bad, gen11_lock_sfc is returning the bit which resets the SFC.

> 
>> +        }
>>       }
>> -    return gen6_hw_domain_reset(dev_priv, hw_mask);
>> +    ret = gen6_hw_domain_reset(dev_priv, hw_mask);
>> +
>> +    if (engine_mask != ALL_ENGINES)
>> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
>> +            gen11_unlock_sfc(dev_priv, engine);
> 
> And this presumably means it is okay to unlock engines which we haven't 
> lock in the previous loop?

For this I found no clear information. Presumably it is okay to clear 
what hasn't been set in the first place...

>> +
>> +    return ret;
>>   }
>>   /**
>>
> I'll go to look for answers to the commit message question before 
> applying the r-b.

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko


> 
> Regards,
> 
> Tvrtko
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 04/19] drm/i915/selftests: Check we can recover a wedged device

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> After declaring a terminally wedged device, we allow ourselves to
> recover on the next GPU reset (manually triggered), or resume. Check
> that resetting a wedged device does work.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>   .../gpu/drm/i915/selftests/intel_hangcheck.c  | 23 +++++++++++++++++++
>   1 file changed, 23 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> index 805e40aff407..65c318d14077 100644
> --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg)
>   	return err;
>   }
>   
> +static int igt_wedged_reset(void *arg)
> +{
> +	struct drm_i915_private *i915 = arg;
> +
> +	/* Check that we can recover a wedged device with a GPU reset */
> +
> +	igt_global_reset_lock(i915);
> +	mutex_lock(&i915->drm.struct_mutex);
> +
> +	i915_gem_set_wedged(i915);
> +	GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error));
> +
> +	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
> +	i915_reset(i915, ALL_ENGINES, NULL);
> +	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
> +
> +	mutex_unlock(&i915->drm.struct_mutex);
> +	igt_global_reset_unlock(i915);
> +
> +	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
> +}
> +
>   static bool wait_for_idle(struct intel_engine_cs *engine)
>   {
>   	return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
> @@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
>   {
>   	static const struct i915_subtest tests[] = {
>   		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
> +		SUBTEST(igt_wedged_reset),
>   		SUBTEST(igt_hang_sanitycheck),
>   		SUBTEST(igt_reset_idle_engine),
>   		SUBTEST(igt_reset_active_engine),
> 

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 05/19] drm/i915/selftests: Verify we can perform resets from atomic context

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> We currently require that our per-engine reset can be called from any
> context, even hardirq, and in the future wish to perform the device
> reset without holding struct_mutex (which requires some lockless
> shenanigans that demand the lowlevel intel_reset_gpu() be able to be
> used in atomic context). Test that we meet the current requirements by
> calling i915_reset_engine() from under various atomic contexts.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>   .../gpu/drm/i915/selftests/intel_hangcheck.c  | 172 ++++++++++++++++++
>   1 file changed, 172 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> index 65c318d14077..5f2f67b149af 100644
> --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> @@ -1470,6 +1470,177 @@ static int igt_handle_error(void *arg)
>   	return err;
>   }
>   
> +static void __preempt_begin(void)
> +{
> +	preempt_disable();
> +}
> +
> +static void __preempt_end(void)
> +{
> +	preempt_enable();
> +}
> +
> +static void __softirq_begin(void)
> +{
> +	local_bh_disable();
> +}
> +
> +static void __softirq_end(void)
> +{
> +	local_bh_enable();
> +}
> +
> +static void __hardirq_begin(void)
> +{
> +	local_irq_disable();
> +}
> +
> +static void __hardirq_end(void)
> +{
> +	local_irq_enable();
> +}
> +
> +struct atomic_section {
> +	const char *name;
> +	void (*critical_section_begin)(void);
> +	void (*critical_section_end)(void);
> +};
> +
> +static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
> +				     const struct atomic_section *p,
> +				     const char *mode)
> +{
> +	struct tasklet_struct * const t = &engine->execlists.tasklet;
> +	int err;
> +
> +	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
> +		  engine->name, mode, p->name);
> +
> +	tasklet_disable_nosync(t);
> +	p->critical_section_begin();
> +
> +	err = i915_reset_engine(engine, NULL);
> +
> +	p->critical_section_end();
> +	tasklet_enable(t);
> +
> +	if (err)
> +		pr_err("i915_reset_engine(%s:%s) failed under %s\n",
> +		       engine->name, mode, p->name);
> +
> +	return err;
> +}
> +
> +static int igt_atomic_reset_engine(struct intel_engine_cs *engine,
> +				   const struct atomic_section *p)
> +{
> +	struct drm_i915_private *i915 = engine->i915;
> +	struct i915_request *rq;
> +	struct hang h;
> +	int err;
> +
> +	err = __igt_atomic_reset_engine(engine, p, "idle");
> +	if (err)
> +		return err;
> +
> +	err = hang_init(&h, i915);
> +	if (err)
> +		return err;
> +
> +	rq = hang_create_request(&h, engine);
> +	if (IS_ERR(rq)) {
> +		err = PTR_ERR(rq);
> +		goto out;
> +	}
> +
> +	i915_request_get(rq);
> +	i915_request_add(rq);
> +
> +	if (wait_until_running(&h, rq)) {
> +		err = __igt_atomic_reset_engine(engine, p, "active");
> +	} else {
> +		pr_err("%s(%s): Failed to start request %llx, at %x\n",
> +		       __func__, engine->name,
> +		       rq->fence.seqno, hws_seqno(&h, rq));
> +		err = -EIO;
> +	}
> +
> +	if (err == 0) {
> +		struct igt_wedge_me w;
> +
> +		igt_wedge_on_timeout(&w, i915, HZ / 20 /* 50ms timeout*/)
> +			i915_request_wait(rq,
> +					  I915_WAIT_LOCKED,
> +					  MAX_SCHEDULE_TIMEOUT);
> +		if (i915_terminally_wedged(&i915->gpu_error))
> +			err = -EIO;
> +	}
> +
> +	i915_request_put(rq);
> +out:
> +	hang_fini(&h);
> +	return err;
> +}
> +
> +static void force_reset(struct drm_i915_private *i915)
> +{
> +	i915_gem_set_wedged(i915);
> +	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
> +	i915_reset(i915, 0, NULL);
> +}
> +
> +static int igt_atomic_reset(void *arg)
> +{
> +	static const struct atomic_section phases[] = {
> +		{ "preempt", __preempt_begin, __preempt_end },
> +		{ "softirq", __softirq_begin, __softirq_end },
> +		{ "hardirq", __hardirq_begin, __hardirq_end },
> +		{ }
> +	};
> +	struct drm_i915_private *i915 = arg;
> +	int err = 0;
> +
> +	/* Check that the resets are usable from atomic context */
> +
> +	if (USES_GUC_SUBMISSION(i915))
> +		return 0; /* guc is dead; long live the guc */
> +
> +	igt_global_reset_lock(i915);
> +	mutex_lock(&i915->drm.struct_mutex);
> +	intel_runtime_pm_get(i915);
> +
> +	/* Flush any requests before we get started and check basics */
> +	force_reset(i915);
> +	if (i915_terminally_wedged(&i915->gpu_error))
> +		goto unlock;
> +
> +	if (intel_has_reset_engine(i915)) {

This check could/should go earlier.

> +		struct intel_engine_cs *engine;
> +		enum intel_engine_id id;
> +
> +		for_each_engine(engine, i915, id) {
> +			const typeof(*phases) *p;
> +
> +			for (p = phases; p->name; p++) {
> +				err = igt_atomic_reset_engine(engine, p);
> +				if (err)
> +					goto out;
> +			}
> +		}
> +	}
> +
> +out:
> +	/* As we poke around the guts, do a full reset before continuing. */
> +	force_reset(i915);
> +
> +unlock:
> +	intel_runtime_pm_put(i915);
> +	mutex_unlock(&i915->drm.struct_mutex);
> +	igt_global_reset_unlock(i915);
> +
> +	return err;
> +}
> +
>   int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
>   {
>   	static const struct i915_subtest tests[] = {
> @@ -1485,6 +1656,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
>   		SUBTEST(igt_reset_evict_ppgtt),
>   		SUBTEST(igt_reset_evict_fence),
>   		SUBTEST(igt_handle_error),
> +		SUBTEST(igt_atomic_reset),
>   	};
>   	bool saved_hangcheck;
>   	int err;
> 

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 04/19] drm/i915/selftests: Check we can recover a wedged device

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> After declaring a terminally wedged device, we allow ourselves to
> recover on the next GPU reset (manually triggered), or resume. Check
> that resetting a wedged device does work.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> ---
>   .../gpu/drm/i915/selftests/intel_hangcheck.c  | 23 +++++++++++++++++++
>   1 file changed, 23 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> index 805e40aff407..65c318d14077 100644
> --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg)
>   	return err;
>   }
>   
> +static int igt_wedged_reset(void *arg)
> +{
> +	struct drm_i915_private *i915 = arg;
> +
> +	/* Check that we can recover a wedged device with a GPU reset */
> +
> +	igt_global_reset_lock(i915);
> +	mutex_lock(&i915->drm.struct_mutex);

rpm get?

> +
> +	i915_gem_set_wedged(i915);
> +	GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error));
> +
> +	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);
> +	i915_reset(i915, ALL_ENGINES, NULL);
> +	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
> +
> +	mutex_unlock(&i915->drm.struct_mutex);
> +	igt_global_reset_unlock(i915);
> +
> +	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
> +}
> +
>   static bool wait_for_idle(struct intel_engine_cs *engine)
>   {
>   	return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0;
> @@ -1452,6 +1474,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
>   {
>   	static const struct i915_subtest tests[] = {
>   		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
> +		SUBTEST(igt_wedged_reset),
>   		SUBTEST(igt_hang_sanitycheck),
>   		SUBTEST(igt_reset_idle_engine),
>   		SUBTEST(igt_reset_active_engine),
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 04/19] drm/i915/selftests: Check we can recover a wedged device

[Chris Wilson]

Quoting Tvrtko Ursulin (2018-12-13 08:28:54)
> 
> On 12/12/2018 13:41, Chris Wilson wrote:
> > After declaring a terminally wedged device, we allow ourselves to
> > recover on the next GPU reset (manually triggered), or resume. Check
> > that resetting a wedged device does work.
> > 
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> > ---
> >   .../gpu/drm/i915/selftests/intel_hangcheck.c  | 23 +++++++++++++++++++
> >   1 file changed, 23 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> > index 805e40aff407..65c318d14077 100644
> > --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> > +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
> > @@ -385,6 +385,28 @@ static int igt_global_reset(void *arg)
> >       return err;
> >   }
> >   
> > +static int igt_wedged_reset(void *arg)
> > +{
> > +     struct drm_i915_private *i915 = arg;
> > +
> > +     /* Check that we can recover a wedged device with a GPU reset */
> > +
> > +     igt_global_reset_lock(i915);
> > +     mutex_lock(&i915->drm.struct_mutex);
> 
> rpm get?

True.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 05/19] drm/i915/selftests: Verify we can perform resets from atomic context

[Chris Wilson]

Quoting Tvrtko Ursulin (2018-12-13 08:28:00)
> 
> On 12/12/2018 13:41, Chris Wilson wrote:
> > +static int igt_atomic_reset(void *arg)
> > +{
> > +     static const struct atomic_section phases[] = {
> > +             { "preempt", __preempt_begin, __preempt_end },
> > +             { "softirq", __softirq_begin, __softirq_end },
> > +             { "hardirq", __hardirq_begin, __hardirq_end },
> > +             { }
> > +     };
> > +     struct drm_i915_private *i915 = arg;
> > +     int err = 0;
> > +
> > +     /* Check that the resets are usable from atomic context */
> > +
> > +     if (USES_GUC_SUBMISSION(i915))
> > +             return 0; /* guc is dead; long live the guc */
> > +
> > +     igt_global_reset_lock(i915);
> > +     mutex_lock(&i915->drm.struct_mutex);
> > +     intel_runtime_pm_get(i915);
> > +
> > +     /* Flush any requests before we get started and check basics */
> > +     force_reset(i915);
> > +     if (i915_terminally_wedged(&i915->gpu_error))
> > +             goto unlock;
> > +
> > +     if (intel_has_reset_engine(i915)) {
> 
> This check could/should go earlier.

My plan is to add a device reset test here later.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Chris Wilson]

Quoting Tvrtko Ursulin (2018-12-13 08:20:58)
> 
> On 12/12/2018 14:36, Tvrtko Ursulin wrote:
> > 
> > On 12/12/2018 13:41, Chris Wilson wrote:
> >> From: Oscar Mateo <oscar.mateo@intel.com>
> >>
> >> SFC (Scaler & Format Converter) units are shared between VD and VEBoxes.
> >> They also happen to have separate reset bits. So, whenever we want to 
> >> reset
> >> one or more of the media engines, we have to make sure the SFCs do not
> >> change owner in the process and, if this owner happens to be one of the
> >> engines being reset, we need to reset the SFC as well.
> >>
> >> This happens in 4 steps:
> >>
> >> 1) Tell the engine that a software reset is going to happen. The engine
> >> will then try to force lock the SFC (if currently locked, it will
> >> remain so; if currently unlocked, it will ignore this and all new lock
> >> requests).
> >>
> >> 2) Poll the ack bit to make sure the hardware has received the forced
> >> lock from the driver. Once this bit is set, it indicates SFC status
> >> (lock or unlock) will not change anymore (until we tell the engine it
> >> is safe to unlock again).
> >>
> >> 3) Check the usage bit to see if the SFC has ended up being locked to
> >> the engine we want to reset. If this is the case, we have to reset
> >> the SFC as well.
> >>
> >> 4) Unlock all the SFCs once the reset sequence is completed.
> >>
> >> Obviously, if we are resetting the whole GPU, we don't have to worry
> >> about all of this.
> >>
> >> BSpec: 10989
> >> BSpec: 10990
> >> BSpec: 10954
> >> BSpec: 10955
> >> BSpec: 10956
> >> BSpec: 19212
> >>
> >> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
> >> Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
> >> Signed-off-by: Michel Thierry <michel.thierry@intel.com>
> >> Cc: Michel Thierry <michel.thierry@intel.com>
> >> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> >> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> >> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
> >> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> >> ---
> >>   drivers/gpu/drm/i915/i915_reg.h     |  18 +++++
> >>   drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++--
> >>   2 files changed, 128 insertions(+), 5 deletions(-)
> >>
> >> diff --git a/drivers/gpu/drm/i915/i915_reg.h 
> >> b/drivers/gpu/drm/i915/i915_reg.h
> >> index 0a7d60509ca7..0796526dc10f 100644
> >> --- a/drivers/gpu/drm/i915/i915_reg.h
> >> +++ b/drivers/gpu/drm/i915/i915_reg.h
> >> @@ -347,6 +347,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t 
> >> reg)
> >>   #define  GEN11_GRDOM_MEDIA4        (1 << 8)
> >>   #define  GEN11_GRDOM_VECS        (1 << 13)
> >>   #define  GEN11_GRDOM_VECS2        (1 << 14)
> >> +#define  GEN11_GRDOM_SFC0        (1 << 17)
> >> +#define  GEN11_GRDOM_SFC1        (1 << 18)
> >> +
> >> +#define  GEN11_VCS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 << 
> >> ((instance) >> 1))
> >> +#define  GEN11_VECS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 << 
> >> (instance))
> 
> These two lines could be a bit of a hidden mine for the future. They 
> silently describe which video engines are connected to which SFC 
> instance. I guess we'll just have to remember to update this if/when it 
> changes.

Hmm, that sounds like the type of info we put into the tables for
intel_engine_cs.

Will we ever notice a bug here? What test do we actually need to perform
to hit an error. Presumably more than just a spinner on a media engine.

That strays back into the topic of a lack of real world test samples for
GPU reset handling.
> 
> >> +
> >> +#define GEN11_VCS_SFC_FORCED_LOCK(engine)    
> >> _MMIO((engine)->mmio_base + 0x88C)
> >> +#define   GEN11_VCS_SFC_FORCED_LOCK_BIT        (1 << 0)
> >> +#define GEN11_VCS_SFC_LOCK_STATUS(engine)    
> >> _MMIO((engine)->mmio_base + 0x890)
> >> +#define   GEN11_VCS_SFC_USAGE_BIT        (1 << 0)
> >> +#define   GEN11_VCS_SFC_LOCK_ACK_BIT        (1 << 1)
> >> +
> >> +#define GEN11_VECS_SFC_FORCED_LOCK(engine)    
> >> _MMIO((engine)->mmio_base + 0x201C)
> >> +#define   GEN11_VECS_SFC_FORCED_LOCK_BIT    (1 << 0)
> >> +#define GEN11_VECS_SFC_LOCK_ACK(engine)        
> >> _MMIO((engine)->mmio_base + 0x2018)
> >> +#define   GEN11_VECS_SFC_LOCK_ACK_BIT        (1 << 0)
> >> +#define GEN11_VECS_SFC_USAGE(engine)        _MMIO((engine)->mmio_base 
> >> + 0x2014)
> >> +#define   GEN11_VECS_SFC_USAGE_BIT        (1 << 0)
> >>   #define RING_PP_DIR_BASE(engine)    _MMIO((engine)->mmio_base + 0x228)
> >>   #define RING_PP_DIR_BASE_READ(engine)    _MMIO((engine)->mmio_base + 
> >> 0x518)
> >> diff --git a/drivers/gpu/drm/i915/intel_uncore.c 
> >> b/drivers/gpu/drm/i915/intel_uncore.c
> >> index 9289515108c3..408692b88c98 100644
> >> --- a/drivers/gpu/drm/i915/intel_uncore.c
> >> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> >> @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct 
> >> drm_i915_private *dev_priv,
> >>       return gen6_hw_domain_reset(dev_priv, hw_mask);
> >>   }
> >> +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
> >> +              struct intel_engine_cs *engine)
> >> +{
> >> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
> > 
> > Only a single use site so could get away with a local copy.
> > 
> >> +    i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
> >> +    u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
> >> +    i915_reg_t sfc_usage;
> >> +    u32 sfc_usage_bit;
> >> +    u32 sfc_reset_bit;
> >> +
> >> +    switch (engine->class) {
> >> +    case VIDEO_DECODE_CLASS:
> >> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
> >> +            return 0;
> >> +
> >> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
> >> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
> >> +
> >> +        sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
> >> +        sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
> >> +
> >> +        sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
> >> +        sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
> >> +        sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
> >> +        break;
> >> +
> >> +    case VIDEO_ENHANCEMENT_CLASS:
> >> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
> >> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
> >> +
> >> +        sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
> >> +        sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
> >> +
> >> +        sfc_usage = GEN11_VECS_SFC_USAGE(engine);
> >> +        sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
> >> +        sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
> >> +        break;
> >> +
> >> +    default:
> >> +        return 0;
> >> +    }
> >> +
> >> +    /*
> >> +     * Tell the engine that a software reset is going to happen. The 
> >> engine
> >> +     * will then try to force lock the SFC (if currently locked, it will
> >> +     * remain so until we tell the engine it is safe to unlock; if 
> >> currently
> >> +     * unlocked, it will ignore this and all new lock requests). If SFC
> >> +     * ends up being locked to the engine we want to reset, we have 
> >> to reset
> >> +     * it as well (we will unlock it once the reset sequence is 
> >> completed).
> >> +     */
> >> +    I915_WRITE_FW(sfc_forced_lock,
> >> +              I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
> >> +
> >> +    if (__intel_wait_for_register_fw(dev_priv,
> >> +                     sfc_forced_lock_ack,
> >> +                     sfc_forced_lock_ack_bit,
> >> +                     sfc_forced_lock_ack_bit,
> >> +                     1000, 0, NULL)) {
> >> +        DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
> >> +        return 0;
> >> +    }
> >> +
> >> +    if ((I915_READ_FW(sfc_usage) & sfc_usage_bit) == sfc_usage_bit)
> > 
> > "== sfc_usage_bit" parts is redundant.
> > 
> >> +        return sfc_reset_bit;
> >> +
> >> +    return 0;
> >> +}
> >> +
> >> +static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
> >> +                 struct intel_engine_cs *engine)
> >> +{
> >> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
> >> +    i915_reg_t sfc_forced_lock;
> >> +    u32 sfc_forced_lock_bit;
> >> +
> >> +    switch (engine->class) {
> >> +    case VIDEO_DECODE_CLASS:
> >> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
> >> +            return;
> >> +
> >> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
> >> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
> >> +        break;
> >> +
> >> +    case VIDEO_ENHANCEMENT_CLASS:
> >> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
> >> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
> >> +        break;
> >> +
> >> +    default:
> >> +        return;
> >> +    }
> >> +
> >> +    I915_WRITE_FW(sfc_forced_lock,
> >> +              I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
> >> +}
> >> +
> >>   /**
> >>    * gen11_reset_engines - reset individual engines
> >>    * @dev_priv: i915 device
> >> @@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct 
> >> drm_i915_private *dev_priv,
> >>   static int gen11_reset_engines(struct drm_i915_private *dev_priv,
> >>                      unsigned int engine_mask)
> >>   {
> >> -    struct intel_engine_cs *engine;
> >>       const u32 hw_engine_mask[I915_NUM_ENGINES] = {
> >>           [RCS] = GEN11_GRDOM_RENDER,
> >>           [BCS] = GEN11_GRDOM_BLT,
> >> @@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct 
> >> drm_i915_private *dev_priv,
> >>           [VECS] = GEN11_GRDOM_VECS,
> >>           [VECS2] = GEN11_GRDOM_VECS2,
> >>       };
> >> +    struct intel_engine_cs *engine;
> >> +    unsigned int tmp;
> >>       u32 hw_mask;
> >> +    int ret;
> >>       BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
> >>       if (engine_mask == ALL_ENGINES) {
> >>           hw_mask = GEN11_GRDOM_FULL;
> >>       } else {
> >> -        unsigned int tmp;
> >> -
> >>           hw_mask = 0;
> >> -        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
> >> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
> >>               hw_mask |= hw_engine_mask[engine->id];
> >> +            hw_mask |= gen11_lock_sfc(dev_priv, engine);
> > 
> > Presumably point No. 3 from the commit message does not mean there is a 
> > separate way to reset the SFC, just that the act of resetting the engine 
> > to which the SFC is locked to, will reset SFC as well?
> 
> My bad, gen11_lock_sfc is returning the bit which resets the SFC.
> 
> > 
> >> +        }
> >>       }
> >> -    return gen6_hw_domain_reset(dev_priv, hw_mask);
> >> +    ret = gen6_hw_domain_reset(dev_priv, hw_mask);
> >> +
> >> +    if (engine_mask != ALL_ENGINES)
> >> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
> >> +            gen11_unlock_sfc(dev_priv, engine);
> > 
> > And this presumably means it is okay to unlock engines which we haven't 
> > lock in the previous loop?
> 
> For this I found no clear information. Presumably it is okay to clear 
> what hasn't been set in the first place...

Yeah, that was the reasoning I came to as well. So long as we do not
broaden engine_mask so that we can concurrently operate on disjoint sets
the RMW should be safe.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Chris Wilson]

Quoting Tvrtko Ursulin (2018-12-12 14:36:27)
> 
> On 12/12/2018 13:41, Chris Wilson wrote:
> > diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> > index 9289515108c3..408692b88c98 100644
> > --- a/drivers/gpu/drm/i915/intel_uncore.c
> > +++ b/drivers/gpu/drm/i915/intel_uncore.c
> > @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv,
> >       return gen6_hw_domain_reset(dev_priv, hw_mask);
> >   }
> >   
> > +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
> > +                       struct intel_engine_cs *engine)
> > +{
> > +     u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
> 
> Only a single use site so could get away with a local copy.
> 
> > +     i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
> > +     u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
> > +     i915_reg_t sfc_usage;
> > +     u32 sfc_usage_bit;
> > +     u32 sfc_reset_bit;
> > +
> > +     switch (engine->class) {
> > +     case VIDEO_DECODE_CLASS:
> > +             if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
> > +                     return 0;

I presume you meant instead of vdbox_sfc_access here. Doesn't fit nicely
without using a local for engine->instance instead (which isn't bad as
it is repeated here) but then we lose the symmetry with unlock.

I tried a few different ways (though without much imagination) to try
and share the definitions between lock_sfc/unlock_sfc but didn't like
any of them more than the repetition. So I left this chunk as it is.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 07/19] drm/i915/icl: Mind the SFC units when resetting VD or VEBox engines

[Tvrtko Ursulin]

On 13/12/2018 08:47, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2018-12-13 08:20:58)
>>
>> On 12/12/2018 14:36, Tvrtko Ursulin wrote:
>>>
>>> On 12/12/2018 13:41, Chris Wilson wrote:
>>>> From: Oscar Mateo <oscar.mateo@intel.com>
>>>>
>>>> SFC (Scaler & Format Converter) units are shared between VD and VEBoxes.
>>>> They also happen to have separate reset bits. So, whenever we want to
>>>> reset
>>>> one or more of the media engines, we have to make sure the SFCs do not
>>>> change owner in the process and, if this owner happens to be one of the
>>>> engines being reset, we need to reset the SFC as well.
>>>>
>>>> This happens in 4 steps:
>>>>
>>>> 1) Tell the engine that a software reset is going to happen. The engine
>>>> will then try to force lock the SFC (if currently locked, it will
>>>> remain so; if currently unlocked, it will ignore this and all new lock
>>>> requests).
>>>>
>>>> 2) Poll the ack bit to make sure the hardware has received the forced
>>>> lock from the driver. Once this bit is set, it indicates SFC status
>>>> (lock or unlock) will not change anymore (until we tell the engine it
>>>> is safe to unlock again).
>>>>
>>>> 3) Check the usage bit to see if the SFC has ended up being locked to
>>>> the engine we want to reset. If this is the case, we have to reset
>>>> the SFC as well.
>>>>
>>>> 4) Unlock all the SFCs once the reset sequence is completed.
>>>>
>>>> Obviously, if we are resetting the whole GPU, we don't have to worry
>>>> about all of this.
>>>>
>>>> BSpec: 10989
>>>> BSpec: 10990
>>>> BSpec: 10954
>>>> BSpec: 10955
>>>> BSpec: 10956
>>>> BSpec: 19212
>>>>
>>>> Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
>>>> Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
>>>> Signed-off-by: Michel Thierry <michel.thierry@intel.com>
>>>> Cc: Michel Thierry <michel.thierry@intel.com>
>>>> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
>>>> Cc: Chris Wilson <chris@chris-wilson.co.uk>
>>>> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
>>>> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>>>> ---
>>>>    drivers/gpu/drm/i915/i915_reg.h     |  18 +++++
>>>>    drivers/gpu/drm/i915/intel_uncore.c | 115 ++++++++++++++++++++++++++--
>>>>    2 files changed, 128 insertions(+), 5 deletions(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/i915/i915_reg.h
>>>> b/drivers/gpu/drm/i915/i915_reg.h
>>>> index 0a7d60509ca7..0796526dc10f 100644
>>>> --- a/drivers/gpu/drm/i915/i915_reg.h
>>>> +++ b/drivers/gpu/drm/i915/i915_reg.h
>>>> @@ -347,6 +347,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t
>>>> reg)
>>>>    #define  GEN11_GRDOM_MEDIA4        (1 << 8)
>>>>    #define  GEN11_GRDOM_VECS        (1 << 13)
>>>>    #define  GEN11_GRDOM_VECS2        (1 << 14)
>>>> +#define  GEN11_GRDOM_SFC0        (1 << 17)
>>>> +#define  GEN11_GRDOM_SFC1        (1 << 18)
>>>> +
>>>> +#define  GEN11_VCS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 <<
>>>> ((instance) >> 1))
>>>> +#define  GEN11_VECS_SFC_RESET_BIT(instance)    (GEN11_GRDOM_SFC0 <<
>>>> (instance))
>>
>> These two lines could be a bit of a hidden mine for the future. They
>> silently describe which video engines are connected to which SFC
>> instance. I guess we'll just have to remember to update this if/when it
>> changes.
> 
> Hmm, that sounds like the type of info we put into the tables for
> intel_engine_cs.

That is a good idea. I can take on myself to convert it to such scheme 
in scope of engine discovery, where I plan to fiddle with engine to SFC 
mapping anyway.

> Will we ever notice a bug here? What test do we actually need to perform
> to hit an error. Presumably more than just a spinner on a media engine.
> 
> That strays back into the topic of a lack of real world test samples for
> GPU reset handling.

I agree in thinking that we have no coverage for it. We'd probably need 
something actually using the SFC unit so we can detect the wrong one has 
been reset, or that the right one hasn't been, etc. Or at least from 
userspace that engine resets on other engines do not affect the SFC 
workload.

Regards,

Tvrtko

>>
>>>> +
>>>> +#define GEN11_VCS_SFC_FORCED_LOCK(engine)
>>>> _MMIO((engine)->mmio_base + 0x88C)
>>>> +#define   GEN11_VCS_SFC_FORCED_LOCK_BIT        (1 << 0)
>>>> +#define GEN11_VCS_SFC_LOCK_STATUS(engine)
>>>> _MMIO((engine)->mmio_base + 0x890)
>>>> +#define   GEN11_VCS_SFC_USAGE_BIT        (1 << 0)
>>>> +#define   GEN11_VCS_SFC_LOCK_ACK_BIT        (1 << 1)
>>>> +
>>>> +#define GEN11_VECS_SFC_FORCED_LOCK(engine)
>>>> _MMIO((engine)->mmio_base + 0x201C)
>>>> +#define   GEN11_VECS_SFC_FORCED_LOCK_BIT    (1 << 0)
>>>> +#define GEN11_VECS_SFC_LOCK_ACK(engine)
>>>> _MMIO((engine)->mmio_base + 0x2018)
>>>> +#define   GEN11_VECS_SFC_LOCK_ACK_BIT        (1 << 0)
>>>> +#define GEN11_VECS_SFC_USAGE(engine)        _MMIO((engine)->mmio_base
>>>> + 0x2014)
>>>> +#define   GEN11_VECS_SFC_USAGE_BIT        (1 << 0)
>>>>    #define RING_PP_DIR_BASE(engine)    _MMIO((engine)->mmio_base + 0x228)
>>>>    #define RING_PP_DIR_BASE_READ(engine)    _MMIO((engine)->mmio_base +
>>>> 0x518)
>>>> diff --git a/drivers/gpu/drm/i915/intel_uncore.c
>>>> b/drivers/gpu/drm/i915/intel_uncore.c
>>>> index 9289515108c3..408692b88c98 100644
>>>> --- a/drivers/gpu/drm/i915/intel_uncore.c
>>>> +++ b/drivers/gpu/drm/i915/intel_uncore.c
>>>> @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct
>>>> drm_i915_private *dev_priv,
>>>>        return gen6_hw_domain_reset(dev_priv, hw_mask);
>>>>    }
>>>> +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv,
>>>> +              struct intel_engine_cs *engine)
>>>> +{
>>>> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
>>>
>>> Only a single use site so could get away with a local copy.
>>>
>>>> +    i915_reg_t sfc_forced_lock, sfc_forced_lock_ack;
>>>> +    u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit;
>>>> +    i915_reg_t sfc_usage;
>>>> +    u32 sfc_usage_bit;
>>>> +    u32 sfc_reset_bit;
>>>> +
>>>> +    switch (engine->class) {
>>>> +    case VIDEO_DECODE_CLASS:
>>>> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
>>>> +            return 0;
>>>> +
>>>> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
>>>> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
>>>> +
>>>> +        sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine);
>>>> +        sfc_forced_lock_ack_bit  = GEN11_VCS_SFC_LOCK_ACK_BIT;
>>>> +
>>>> +        sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine);
>>>> +        sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT;
>>>> +        sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance);
>>>> +        break;
>>>> +
>>>> +    case VIDEO_ENHANCEMENT_CLASS:
>>>> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
>>>> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
>>>> +
>>>> +        sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine);
>>>> +        sfc_forced_lock_ack_bit  = GEN11_VECS_SFC_LOCK_ACK_BIT;
>>>> +
>>>> +        sfc_usage = GEN11_VECS_SFC_USAGE(engine);
>>>> +        sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT;
>>>> +        sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance);
>>>> +        break;
>>>> +
>>>> +    default:
>>>> +        return 0;
>>>> +    }
>>>> +
>>>> +    /*
>>>> +     * Tell the engine that a software reset is going to happen. The
>>>> engine
>>>> +     * will then try to force lock the SFC (if currently locked, it will
>>>> +     * remain so until we tell the engine it is safe to unlock; if
>>>> currently
>>>> +     * unlocked, it will ignore this and all new lock requests). If SFC
>>>> +     * ends up being locked to the engine we want to reset, we have
>>>> to reset
>>>> +     * it as well (we will unlock it once the reset sequence is
>>>> completed).
>>>> +     */
>>>> +    I915_WRITE_FW(sfc_forced_lock,
>>>> +              I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit);
>>>> +
>>>> +    if (__intel_wait_for_register_fw(dev_priv,
>>>> +                     sfc_forced_lock_ack,
>>>> +                     sfc_forced_lock_ack_bit,
>>>> +                     sfc_forced_lock_ack_bit,
>>>> +                     1000, 0, NULL)) {
>>>> +        DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
>>>> +        return 0;
>>>> +    }
>>>> +
>>>> +    if ((I915_READ_FW(sfc_usage) & sfc_usage_bit) == sfc_usage_bit)
>>>
>>> "== sfc_usage_bit" parts is redundant.
>>>
>>>> +        return sfc_reset_bit;
>>>> +
>>>> +    return 0;
>>>> +}
>>>> +
>>>> +static void gen11_unlock_sfc(struct drm_i915_private *dev_priv,
>>>> +                 struct intel_engine_cs *engine)
>>>> +{
>>>> +    u8 vdbox_sfc_access = INTEL_INFO(dev_priv)->vdbox_sfc_access;
>>>> +    i915_reg_t sfc_forced_lock;
>>>> +    u32 sfc_forced_lock_bit;
>>>> +
>>>> +    switch (engine->class) {
>>>> +    case VIDEO_DECODE_CLASS:
>>>> +        if ((BIT(engine->instance) & vdbox_sfc_access) == 0)
>>>> +            return;
>>>> +
>>>> +        sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine);
>>>> +        sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT;
>>>> +        break;
>>>> +
>>>> +    case VIDEO_ENHANCEMENT_CLASS:
>>>> +        sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine);
>>>> +        sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT;
>>>> +        break;
>>>> +
>>>> +    default:
>>>> +        return;
>>>> +    }
>>>> +
>>>> +    I915_WRITE_FW(sfc_forced_lock,
>>>> +              I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit);
>>>> +}
>>>> +
>>>>    /**
>>>>     * gen11_reset_engines - reset individual engines
>>>>     * @dev_priv: i915 device
>>>> @@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct
>>>> drm_i915_private *dev_priv,
>>>>    static int gen11_reset_engines(struct drm_i915_private *dev_priv,
>>>>                       unsigned int engine_mask)
>>>>    {
>>>> -    struct intel_engine_cs *engine;
>>>>        const u32 hw_engine_mask[I915_NUM_ENGINES] = {
>>>>            [RCS] = GEN11_GRDOM_RENDER,
>>>>            [BCS] = GEN11_GRDOM_BLT,
>>>> @@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct
>>>> drm_i915_private *dev_priv,
>>>>            [VECS] = GEN11_GRDOM_VECS,
>>>>            [VECS2] = GEN11_GRDOM_VECS2,
>>>>        };
>>>> +    struct intel_engine_cs *engine;
>>>> +    unsigned int tmp;
>>>>        u32 hw_mask;
>>>> +    int ret;
>>>>        BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES);
>>>>        if (engine_mask == ALL_ENGINES) {
>>>>            hw_mask = GEN11_GRDOM_FULL;
>>>>        } else {
>>>> -        unsigned int tmp;
>>>> -
>>>>            hw_mask = 0;
>>>> -        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
>>>> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
>>>>                hw_mask |= hw_engine_mask[engine->id];
>>>> +            hw_mask |= gen11_lock_sfc(dev_priv, engine);
>>>
>>> Presumably point No. 3 from the commit message does not mean there is a
>>> separate way to reset the SFC, just that the act of resetting the engine
>>> to which the SFC is locked to, will reset SFC as well?
>>
>> My bad, gen11_lock_sfc is returning the bit which resets the SFC.
>>
>>>
>>>> +        }
>>>>        }
>>>> -    return gen6_hw_domain_reset(dev_priv, hw_mask);
>>>> +    ret = gen6_hw_domain_reset(dev_priv, hw_mask);
>>>> +
>>>> +    if (engine_mask != ALL_ENGINES)
>>>> +        for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
>>>> +            gen11_unlock_sfc(dev_priv, engine);
>>>
>>> And this presumably means it is okay to unlock engines which we haven't
>>> lock in the previous loop?
>>
>> For this I found no clear information. Presumably it is okay to clear
>> what hasn't been set in the first place...
> 
> Yeah, that was the reasoning I came to as well. So long as we do not
> broaden engine_mask so that we can concurrently operate on disjoint sets
> the RMW should be safe.
> -Chris
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 11/19] drm/i915: Track all held rpm wakerefs

[Chris Wilson]

Quoting Chris Wilson (2018-12-12 13:41:41)
> Everytime we take a wakeref, record the stack trace of where it was
> taken; clearing the set if we ever drop back to no owners. For debugging
> a rpm leak, we can look at all the current wakerefs and check if they
> have a matching rpm_put.

This information would be invaluable to help debug the sporadic failure
in BAT's pm_rpm.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 10/19] drm/i915: Remove debugfs/i915_ppgtt_info

[Tvrtko Ursulin]

On 12/12/2018 13:41, Chris Wilson wrote:
> The information presented here is not relevant to current development.
> We can either use the context information, but more often we want to
> inspect the active gpu state.
> 
> The ulterior motive is to eradicate dev->filelist.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/i915_debugfs.c | 119 ------------------------
>   drivers/gpu/drm/i915/i915_gem_gtt.c | 134 ----------------------------
>   drivers/gpu/drm/i915/i915_gem_gtt.h |   2 -
>   3 files changed, 255 deletions(-)

I said in November, that I gave r-b for this one already back in 
September. :)

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko

> 
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 21d122024707..06d407d4102d 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -2046,124 +2046,6 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
>   	return 0;
>   }
>   
> -static int per_file_ctx(int id, void *ptr, void *data)
> -{
> -	struct i915_gem_context *ctx = ptr;
> -	struct seq_file *m = data;
> -	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
> -
> -	if (!ppgtt) {
> -		seq_printf(m, "  no ppgtt for context %d\n",
> -			   ctx->user_handle);
> -		return 0;
> -	}
> -
> -	if (i915_gem_context_is_default(ctx))
> -		seq_puts(m, "  default context:\n");
> -	else
> -		seq_printf(m, "  context %d:\n", ctx->user_handle);
> -	ppgtt->debug_dump(ppgtt, m);
> -
> -	return 0;
> -}
> -
> -static void gen8_ppgtt_info(struct seq_file *m,
> -			    struct drm_i915_private *dev_priv)
> -{
> -	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> -	struct intel_engine_cs *engine;
> -	enum intel_engine_id id;
> -	int i;
> -
> -	if (!ppgtt)
> -		return;
> -
> -	for_each_engine(engine, dev_priv, id) {
> -		seq_printf(m, "%s\n", engine->name);
> -		for (i = 0; i < 4; i++) {
> -			u64 pdp = I915_READ(GEN8_RING_PDP_UDW(engine, i));
> -			pdp <<= 32;
> -			pdp |= I915_READ(GEN8_RING_PDP_LDW(engine, i));
> -			seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp);
> -		}
> -	}
> -}
> -
> -static void gen6_ppgtt_info(struct seq_file *m,
> -			    struct drm_i915_private *dev_priv)
> -{
> -	struct intel_engine_cs *engine;
> -	enum intel_engine_id id;
> -
> -	if (IS_GEN6(dev_priv))
> -		seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE));
> -
> -	for_each_engine(engine, dev_priv, id) {
> -		seq_printf(m, "%s\n", engine->name);
> -		if (IS_GEN7(dev_priv))
> -			seq_printf(m, "GFX_MODE: 0x%08x\n",
> -				   I915_READ(RING_MODE_GEN7(engine)));
> -		seq_printf(m, "PP_DIR_BASE: 0x%08x\n",
> -			   I915_READ(RING_PP_DIR_BASE(engine)));
> -		seq_printf(m, "PP_DIR_BASE_READ: 0x%08x\n",
> -			   I915_READ(RING_PP_DIR_BASE_READ(engine)));
> -		seq_printf(m, "PP_DIR_DCLV: 0x%08x\n",
> -			   I915_READ(RING_PP_DIR_DCLV(engine)));
> -	}
> -	if (dev_priv->mm.aliasing_ppgtt) {
> -		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
> -
> -		seq_puts(m, "aliasing PPGTT:\n");
> -		seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.base.ggtt_offset);
> -
> -		ppgtt->debug_dump(ppgtt, m);
> -	}
> -
> -	seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK));
> -}
> -
> -static int i915_ppgtt_info(struct seq_file *m, void *data)
> -{
> -	struct drm_i915_private *dev_priv = node_to_i915(m->private);
> -	struct drm_device *dev = &dev_priv->drm;
> -	struct drm_file *file;
> -	int ret;
> -
> -	mutex_lock(&dev->filelist_mutex);
> -	ret = mutex_lock_interruptible(&dev->struct_mutex);
> -	if (ret)
> -		goto out_unlock;
> -
> -	intel_runtime_pm_get(dev_priv);
> -
> -	if (INTEL_GEN(dev_priv) >= 8)
> -		gen8_ppgtt_info(m, dev_priv);
> -	else if (INTEL_GEN(dev_priv) >= 6)
> -		gen6_ppgtt_info(m, dev_priv);
> -
> -	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
> -		struct drm_i915_file_private *file_priv = file->driver_priv;
> -		struct task_struct *task;
> -
> -		task = get_pid_task(file->pid, PIDTYPE_PID);
> -		if (!task) {
> -			ret = -ESRCH;
> -			goto out_rpm;
> -		}
> -		seq_printf(m, "\nproc: %s\n", task->comm);
> -		put_task_struct(task);
> -		idr_for_each(&file_priv->context_idr, per_file_ctx,
> -			     (void *)(unsigned long)m);
> -	}
> -
> -out_rpm:
> -	intel_runtime_pm_put(dev_priv);
> -	mutex_unlock(&dev->struct_mutex);
> -out_unlock:
> -	mutex_unlock(&dev->filelist_mutex);
> -	return ret;
> -}
> -
>   static int count_irq_waiters(struct drm_i915_private *i915)
>   {
>   	struct intel_engine_cs *engine;
> @@ -4882,7 +4764,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
>   	{"i915_context_status", i915_context_status, 0},
>   	{"i915_forcewake_domains", i915_forcewake_domains, 0},
>   	{"i915_swizzle_info", i915_swizzle_info, 0},
> -	{"i915_ppgtt_info", i915_ppgtt_info, 0},
>   	{"i915_llc", i915_llc, 0},
>   	{"i915_edp_psr_status", i915_edp_psr_status, 0},
>   	{"i915_energy_uJ", i915_energy_uJ, 0},
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index 62bde517d383..9f5eeae5af2b 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -1488,84 +1488,6 @@ static int gen8_ppgtt_alloc_4lvl(struct i915_address_space *vm,
>   	return -ENOMEM;
>   }
>   
> -static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
> -			  struct i915_page_directory_pointer *pdp,
> -			  u64 start, u64 length,
> -			  gen8_pte_t scratch_pte,
> -			  struct seq_file *m)
> -{
> -	struct i915_address_space *vm = &ppgtt->vm;
> -	struct i915_page_directory *pd;
> -	u32 pdpe;
> -
> -	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
> -		struct i915_page_table *pt;
> -		u64 pd_len = length;
> -		u64 pd_start = start;
> -		u32 pde;
> -
> -		if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd)
> -			continue;
> -
> -		seq_printf(m, "\tPDPE #%d\n", pdpe);
> -		gen8_for_each_pde(pt, pd, pd_start, pd_len, pde) {
> -			u32 pte;
> -			gen8_pte_t *pt_vaddr;
> -
> -			if (pd->page_table[pde] == ppgtt->vm.scratch_pt)
> -				continue;
> -
> -			pt_vaddr = kmap_atomic_px(pt);
> -			for (pte = 0; pte < GEN8_PTES; pte += 4) {
> -				u64 va = (pdpe << GEN8_PDPE_SHIFT |
> -					  pde << GEN8_PDE_SHIFT |
> -					  pte << GEN8_PTE_SHIFT);
> -				int i;
> -				bool found = false;
> -
> -				for (i = 0; i < 4; i++)
> -					if (pt_vaddr[pte + i] != scratch_pte)
> -						found = true;
> -				if (!found)
> -					continue;
> -
> -				seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte);
> -				for (i = 0; i < 4; i++) {
> -					if (pt_vaddr[pte + i] != scratch_pte)
> -						seq_printf(m, " %llx", pt_vaddr[pte + i]);
> -					else
> -						seq_puts(m, "  SCRATCH ");
> -				}
> -				seq_puts(m, "\n");
> -			}
> -			kunmap_atomic(pt_vaddr);
> -		}
> -	}
> -}
> -
> -static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
> -{
> -	struct i915_address_space *vm = &ppgtt->vm;
> -	const gen8_pte_t scratch_pte = vm->scratch_pte;
> -	u64 start = 0, length = ppgtt->vm.total;
> -
> -	if (use_4lvl(vm)) {
> -		u64 pml4e;
> -		struct i915_pml4 *pml4 = &ppgtt->pml4;
> -		struct i915_page_directory_pointer *pdp;
> -
> -		gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
> -			if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp)
> -				continue;
> -
> -			seq_printf(m, "    PML4E #%llu\n", pml4e);
> -			gen8_dump_pdp(ppgtt, pdp, start, length, scratch_pte, m);
> -		}
> -	} else {
> -		gen8_dump_pdp(ppgtt, &ppgtt->pdp, start, length, scratch_pte, m);
> -	}
> -}
> -
>   static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt)
>   {
>   	struct i915_address_space *vm = &ppgtt->vm;
> @@ -1670,7 +1592,6 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
>   		gen8_ppgtt_notify_vgt(ppgtt, true);
>   
>   	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
> -	ppgtt->debug_dump = gen8_dump_ppgtt;
>   
>   	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
>   	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
> @@ -1686,60 +1607,6 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
>   	return ERR_PTR(err);
>   }
>   
> -static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
> -{
> -	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
> -	const gen6_pte_t scratch_pte = base->vm.scratch_pte;
> -	struct i915_page_table *pt;
> -	u32 pte, pde;
> -
> -	gen6_for_all_pdes(pt, &base->pd, pde) {
> -		gen6_pte_t *vaddr;
> -
> -		if (pt == base->vm.scratch_pt)
> -			continue;
> -
> -		if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND)) {
> -			u32 expected =
> -				GEN6_PDE_ADDR_ENCODE(px_dma(pt)) |
> -				GEN6_PDE_VALID;
> -			u32 pd_entry = readl(ppgtt->pd_addr + pde);
> -
> -			if (pd_entry != expected)
> -				seq_printf(m,
> -					   "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
> -					   pde,
> -					   pd_entry,
> -					   expected);
> -
> -			seq_printf(m, "\tPDE: %x\n", pd_entry);
> -		}
> -
> -		vaddr = kmap_atomic_px(base->pd.page_table[pde]);
> -		for (pte = 0; pte < GEN6_PTES; pte += 4) {
> -			int i;
> -
> -			for (i = 0; i < 4; i++)
> -				if (vaddr[pte + i] != scratch_pte)
> -					break;
> -			if (i == 4)
> -				continue;
> -
> -			seq_printf(m, "\t\t(%03d, %04d) %08llx: ",
> -				   pde, pte,
> -				   (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE);
> -			for (i = 0; i < 4; i++) {
> -				if (vaddr[pte + i] != scratch_pte)
> -					seq_printf(m, " %08x", vaddr[pte + i]);
> -				else
> -					seq_puts(m, "  SCRATCH");
> -			}
> -			seq_puts(m, "\n");
> -		}
> -		kunmap_atomic(vaddr);
> -	}
> -}
> -
>   /* Write pde (index) from the page directory @pd to the page table @pt */
>   static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt,
>   				  const unsigned int pde,
> @@ -2127,7 +1994,6 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
>   	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
>   	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
>   	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
> -	ppgtt->base.debug_dump = gen6_dump_ppgtt;
>   
>   	ppgtt->base.vm.vma_ops.bind_vma    = ppgtt_bind_vma;
>   	ppgtt->base.vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index 4874da09a3c4..e2360f16427a 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -413,8 +413,6 @@ struct i915_hw_ppgtt {
>   		struct i915_page_directory_pointer pdp;	/* GEN8+ */
>   		struct i915_page_directory pd;		/* GEN6-7 */
>   	};
> -
> -	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
>   };
>   
>   struct gen6_hw_ppgtt {
> 
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx