Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull DRM updates from Dave Airlie:
 "Like all good pull reqs this ends with a revert, so it must mean we
  tested it,

[ Ed. That's _one_ way of looking at it ]

  This pull is missing nouveau, Ben has been stuck trying to track down
  a very longstanding bug that revealed itself due to some other
  changes.  I've asked him to send you a direct pull request for nouveau
  once he cleans things up.  I'm away until Monday so don't want to
  delay things, you can make a decision on that when he sends it, I have
  my phone so I can ack things just not really merge much.

  It has one trivial conflict with your tree in armada_drv.c, and also
  the pull request contains some component changes that are already in
  your tree, the base tree from Russell went via Greg's tree already,
  but some stuff still shows up in here that doesn't when I merge my
  tree into yours.

  Otherwise all pretty standard graphics fare, one new driver and
  changes all over the place.

  New drivers:
   - sti kms driver for STMicroelectronics chipsets stih416 and stih407.

  core:
   - lots of cleanups to the drm core
   - DP MST helper code merged
   - universal cursor planes.
   - render nodes enabled by default

  panel:
   - better panel interfaces
   - new panel support
   - non-continuous cock advertising ability

  ttm:
   - shrinker fixes

  i915:
   - hopefully ditched UMS support
   - runtime pm fixes
   - psr tracking and locking - now enabled by default
   - userptr fixes
   - backlight brightness fixes
   - MST support merged
   - runtime PM for dpms
   - primary planes locking fixes
   - gen8 hw semaphore support
   - fbc fixes
   - runtime PM on SOix sleep state hw.
   - mmio base page flipping
   - lots of vlv/chv fixes.
   - universal cursor planes

  radeon:
   - Hawaii fixes
   - display scalar support for non-fixed mode displays
   - new firmware format support
   - dpm on more asics by default
   - GPUVM improvements
   - uncached and wc GTT buffers
   - BOs > visible VRAM

  exynos:
   - i80 interface support
   - module auto-loading
   - ipp driver consolidated.

  armada:
   - irq handling in crtc layer only
   - crtc renumbering
   - add component support
   - DT interaction changes.

  tegra:
   - load as module fixes
   - eDP bpp and sync polarity fixed
   - DSI non-continuous clock mode support
   - better support for importing buffers from nouveau

  msm:
   - mdp5/adq8084 v1.3 hw enablement
   - devicetree clk changse
   - ifc6410 board working

  tda998x:
   - component support
   - DT documentation update

  vmwgfx:
   - fix compat shader namespace"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (551 commits)
  Revert "drm: drop redundant drm_file->is_master"
  drm/panel: simple: Use devm_gpiod_get_optional()
  drm/dsi: Replace upcasting macro by function
  drm/panel: ld9040: Replace upcasting macro by function
  drm/exynos: dp: Modify driver to support drm_panel
  drm/exynos: Move DP setup into commit()
  drm/panel: simple: Add AUO B133HTN01 panel support
  drm/panel: simple: Support delays in panel functions
  drm/panel: simple: Add proper definition for prepare and unprepare
  drm/panel: s6e8aa0: Add proper definition for prepare and unprepare
  drm/panel: ld9040: Add proper definition for prepare and unprepare
  drm/tegra: Add support for panel prepare and unprepare routines
  drm/exynos: dsi: Add support for panel prepare and unprepare routines
  drm/exynos: dpi: Add support for panel prepare and unprepare routines
  drm/panel: simple: Add dummy prepare and unprepare routines
  drm/panel: s6e8aa0: Add dummy prepare and unprepare routines
  drm/panel: ld9040: Add dummy prepare and unprepare routines
  drm/panel: Provide convenience wrapper for .get_modes()
  drm/panel: add .prepare() and .unprepare() functions
  drm/panel: simple: Remove simple-panel compatible
  ...

1 files changed, 109 insertions, 40 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 21ea92886a56..fe69fc837d9e 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -40,19 +40,87 @@ struct i915_mmu_notifier {
 	struct hlist_node node;
 	struct mmu_notifier mn;
 	struct rb_root objects;
+	struct list_head linear;
 	struct drm_device *dev;
 	struct mm_struct *mm;
 	struct work_struct work;
 	unsigned long count;
 	unsigned long serial;
+	bool has_linear;
 };
 
 struct i915_mmu_object {
 	struct i915_mmu_notifier *mmu;
 	struct interval_tree_node it;
+	struct list_head link;
 	struct drm_i915_gem_object *obj;
+	bool is_linear;
 };
 
+static unsigned long cancel_userptr(struct drm_i915_gem_object *obj)
+{
+	struct drm_device *dev = obj->base.dev;
+	unsigned long end;
+
+	mutex_lock(&dev->struct_mutex);
+	/* Cancel any active worker and force us to re-evaluate gup */
+	obj->userptr.work = NULL;
+
+	if (obj->pages != NULL) {
+		struct drm_i915_private *dev_priv = to_i915(dev);
+		struct i915_vma *vma, *tmp;
+		bool was_interruptible;
+
+		was_interruptible = dev_priv->mm.interruptible;
+		dev_priv->mm.interruptible = false;
+
+		list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) {
+			int ret = i915_vma_unbind(vma);
+			WARN_ON(ret && ret != -EIO);
+		}
+		WARN_ON(i915_gem_object_put_pages(obj));
+
+		dev_priv->mm.interruptible = was_interruptible;
+	}
+
+	end = obj->userptr.ptr + obj->base.size;
+
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+
+	return end;
+}
+
+static void *invalidate_range__linear(struct i915_mmu_notifier *mn,
+				      struct mm_struct *mm,
+				      unsigned long start,
+				      unsigned long end)
+{
+	struct i915_mmu_object *mmu;
+	unsigned long serial;
+
+restart:
+	serial = mn->serial;
+	list_for_each_entry(mmu, &mn->linear, link) {
+		struct drm_i915_gem_object *obj;
+
+		if (mmu->it.last < start || mmu->it.start > end)
+			continue;
+
+		obj = mmu->obj;
+		drm_gem_object_reference(&obj->base);
+		spin_unlock(&mn->lock);
+
+		cancel_userptr(obj);
+
+		spin_lock(&mn->lock);
+		if (serial != mn->serial)
+			goto restart;
+	}
+
+	return NULL;
+}
+
 static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 						       struct mm_struct *mm,
 						       unsigned long start,
@@ -60,16 +128,18 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 {
 	struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn);
 	struct interval_tree_node *it = NULL;
+	unsigned long next = start;
 	unsigned long serial = 0;
 
 	end--; /* interval ranges are inclusive, but invalidate range is exclusive */
-	while (start < end) {
-		struct drm_i915_gem_object *obj;
+	while (next < end) {
+		struct drm_i915_gem_object *obj = NULL;
 
-		obj = NULL;
 		spin_lock(&mn->lock);
-		if (serial == mn->serial)
-			it = interval_tree_iter_next(it, start, end);
+		if (mn->has_linear)
+			it = invalidate_range__linear(mn, mm, start, end);
+		else if (serial == mn->serial)
+			it = interval_tree_iter_next(it, next, end);
 		else
 			it = interval_tree_iter_first(&mn->objects, start, end);
 		if (it != NULL) {
@@ -81,31 +151,7 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 		if (obj == NULL)
 			return;
 
-		mutex_lock(&mn->dev->struct_mutex);
-		/* Cancel any active worker and force us to re-evaluate gup */
-		obj->userptr.work = NULL;
-
-		if (obj->pages != NULL) {
-			struct drm_i915_private *dev_priv = to_i915(mn->dev);
-			struct i915_vma *vma, *tmp;
-			bool was_interruptible;
-
-			was_interruptible = dev_priv->mm.interruptible;
-			dev_priv->mm.interruptible = false;
-
-			list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) {
-				int ret = i915_vma_unbind(vma);
-				WARN_ON(ret && ret != -EIO);
-			}
-			WARN_ON(i915_gem_object_put_pages(obj));
-
-			dev_priv->mm.interruptible = was_interruptible;
-		}
-
-		start = obj->userptr.ptr + obj->base.size;
-
-		drm_gem_object_unreference(&obj->base);
-		mutex_unlock(&mn->dev->struct_mutex);
+		next = cancel_userptr(obj);
 	}
 }
 
@@ -150,7 +196,9 @@ i915_mmu_notifier_get(struct drm_device *dev, struct mm_struct *mm)
 	mmu->mm = mm;
 	mmu->objects = RB_ROOT;
 	mmu->count = 0;
-	mmu->serial = 0;
+	mmu->serial = 1;
+	INIT_LIST_HEAD(&mmu->linear);
+	mmu->has_linear = false;
 
 	/* Protected by mmap_sem (write-lock) */
 	ret = __mmu_notifier_register(&mmu->mn, mm);
@@ -197,6 +245,17 @@ static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mmu)
 		mmu->serial = 1;
 }
 
+static bool i915_mmu_notifier_has_linear(struct i915_mmu_notifier *mmu)
+{
+	struct i915_mmu_object *mn;
+
+	list_for_each_entry(mn, &mmu->linear, link)
+		if (mn->is_linear)
+			return true;
+
+	return false;
+}
+
 static void
 i915_mmu_notifier_del(struct i915_mmu_notifier *mmu,
 		      struct i915_mmu_object *mn)
@@ -204,7 +263,11 @@ i915_mmu_notifier_del(struct i915_mmu_notifier *mmu,
 	lockdep_assert_held(&mmu->dev->struct_mutex);
 
 	spin_lock(&mmu->lock);
-	interval_tree_remove(&mn->it, &mmu->objects);
+	list_del(&mn->link);
+	if (mn->is_linear)
+		mmu->has_linear = i915_mmu_notifier_has_linear(mmu);
+	else
+		interval_tree_remove(&mn->it, &mmu->objects);
 	__i915_mmu_notifier_update_serial(mmu);
 	spin_unlock(&mmu->lock);
 
@@ -230,7 +293,6 @@ i915_mmu_notifier_add(struct i915_mmu_notifier *mmu,
 	 */
 	i915_gem_retire_requests(mmu->dev);
 
-	/* Disallow overlapping userptr objects */
 	spin_lock(&mmu->lock);
 	it = interval_tree_iter_first(&mmu->objects,
 				      mn->it.start, mn->it.last);
@@ -243,14 +305,22 @@ i915_mmu_notifier_add(struct i915_mmu_notifier *mmu,
 		 * to flush their object references upon which the object will
 		 * be removed from the interval-tree, or the the range is
 		 * still in use by another client and the overlap is invalid.
+		 *
+		 * If we do have an overlap, we cannot use the interval tree
+		 * for fast range invalidation.
 		 */
 
 		obj = container_of(it, struct i915_mmu_object, it)->obj;
-		ret = obj->userptr.workers ? -EAGAIN : -EINVAL;
-	} else {
+		if (!obj->userptr.workers)
+			mmu->has_linear = mn->is_linear = true;
+		else
+			ret = -EAGAIN;
+	} else
 		interval_tree_insert(&mn->it, &mmu->objects);
+
+	if (ret == 0) {
+		list_add(&mn->link, &mmu->linear);
 		__i915_mmu_notifier_update_serial(mmu);
-		ret = 0;
 	}
 	spin_unlock(&mmu->lock);
 	mutex_unlock(&mmu->dev->struct_mutex);
@@ -611,12 +681,11 @@ static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
  * We impose several restrictions upon the memory being mapped
  * into the GPU.
  * 1. It must be page aligned (both start/end addresses, i.e ptr and size).
- * 2. It cannot overlap any other userptr object in the same address space.
- * 3. It must be normal system memory, not a pointer into another map of IO
+ * 2. It must be normal system memory, not a pointer into another map of IO
  *    space (e.g. it must not be a GTT mmapping of another object).
- * 4. We only allow a bo as large as we could in theory map into the GTT,
+ * 3. We only allow a bo as large as we could in theory map into the GTT,
  *    that is we limit the size to the total size of the GTT.
- * 5. The bo is marked as being snoopable. The backing pages are left
+ * 4. The bo is marked as being snoopable. The backing pages are left
  *    accessible directly by the CPU, but reads and writes by the GPU may
  *    incur the cost of a snoop (unless you have an LLC architecture).
  *