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, 70 insertions, 23 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f247d92..2151850 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1095,7 +1095,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
  * Compare seqno against outstanding lazy request. Emit a request if they are
  * equal.
  */
-static int
+int
 i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno)
 {
 	int ret;
@@ -1161,14 +1161,14 @@ static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno,
 	s64 before, now;
 	int ret;
 
-	WARN(dev_priv->pm.irqs_disabled, "IRQs disabled\n");
+	WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled");
 
 	if (i915_seqno_passed(ring->get_seqno(ring, true), seqno))
 		return 0;
 
 	timeout_expire = timeout ? jiffies + nsecs_to_jiffies((u64)*timeout) : 0;
 
-	if (INTEL_INFO(dev)->gen >= 6 && can_wait_boost(file_priv)) {
+	if (INTEL_INFO(dev)->gen >= 6 && ring->id == RCS && can_wait_boost(file_priv)) {
 		gen6_rps_boost(dev_priv);
 		if (file_priv)
 			mod_delayed_work(dev_priv->wq,
@@ -1560,14 +1560,29 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret)
 		goto unpin;
 
-	obj->fault_mappable = true;
-
+	/* Finally, remap it using the new GTT offset */
 	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
 	pfn >>= PAGE_SHIFT;
-	pfn += page_offset;
 
-	/* Finally, remap it using the new GTT offset */
-	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	if (!obj->fault_mappable) {
+		unsigned long size = min_t(unsigned long,
+					   vma->vm_end - vma->vm_start,
+					   obj->base.size);
+		int i;
+
+		for (i = 0; i < size >> PAGE_SHIFT; i++) {
+			ret = vm_insert_pfn(vma,
+					    (unsigned long)vma->vm_start + i * PAGE_SIZE,
+					    pfn + i);
+			if (ret)
+				break;
+		}
+
+		obj->fault_mappable = true;
+	} else
+		ret = vm_insert_pfn(vma,
+				    (unsigned long)vmf->virtual_address,
+				    pfn + page_offset);
 unpin:
 	i915_gem_object_ggtt_unpin(obj);
 unlock:
@@ -2051,16 +2066,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 			 * our own buffer, now let the real VM do its job and
 			 * go down in flames if truly OOM.
 			 */
-			gfp &= ~(__GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD);
-			gfp |= __GFP_IO | __GFP_WAIT;
-
 			i915_gem_shrink_all(dev_priv);
-			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+			page = shmem_read_mapping_page(mapping, i);
 			if (IS_ERR(page))
 				goto err_pages;
-
-			gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
-			gfp &= ~(__GFP_IO | __GFP_WAIT);
 		}
 #ifdef CONFIG_SWIOTLB
 		if (swiotlb_nr_tbl()) {
@@ -2209,6 +2218,8 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 			list_move_tail(&vma->mm_list, &vm->inactive_list);
 	}
 
+	intel_fb_obj_flush(obj, true);
+
 	list_del_init(&obj->ring_list);
 	obj->ring = NULL;
 
@@ -2318,7 +2329,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	u32 request_ring_position, request_start;
 	int ret;
 
-	request_start = intel_ring_get_tail(ring);
+	request_start = intel_ring_get_tail(ring->buffer);
 	/*
 	 * Emit any outstanding flushes - execbuf can fail to emit the flush
 	 * after having emitted the batchbuffer command. Hence we need to fix
@@ -2339,7 +2350,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 * GPU processing the request, we never over-estimate the
 	 * position of the head.
 	 */
-	request_ring_position = intel_ring_get_tail(ring);
+	request_ring_position = intel_ring_get_tail(ring->buffer);
 
 	ret = ring->add_request(ring);
 	if (ret)
@@ -2822,6 +2833,8 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 	idx = intel_ring_sync_index(from, to);
 
 	seqno = obj->last_read_seqno;
+	/* Optimization: Avoid semaphore sync when we are sure we already
+	 * waited for an object with higher seqno */
 	if (seqno <= from->semaphore.sync_seqno[idx])
 		return 0;
 
@@ -2905,8 +2918,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	vma->unbind_vma(vma);
 
-	i915_gem_gtt_finish_object(obj);
-
 	list_del_init(&vma->mm_list);
 	/* Avoid an unnecessary call to unbind on rebind. */
 	if (i915_is_ggtt(vma->vm))
@@ -2917,8 +2928,10 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	/* Since the unbound list is global, only move to that list if
 	 * no more VMAs exist. */
-	if (list_empty(&obj->vma_list))
+	if (list_empty(&obj->vma_list)) {
+		i915_gem_gtt_finish_object(obj);
 		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
+	}
 
 	/* And finally now the object is completely decoupled from this vma,
 	 * we can drop its hold on the backing storage and allow it to be
@@ -3530,6 +3543,8 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3551,6 +3566,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3604,6 +3621,9 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->dirty = 1;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -3940,6 +3960,9 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -4428,13 +4451,14 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->stolen)
 		i915_gem_object_unpin_pages(obj);
 
+	WARN_ON(obj->frontbuffer_bits);
+
 	if (WARN_ON(obj->pages_pin_count))
 		obj->pages_pin_count = 0;
 	if (discard_backing_storage(obj))
 		obj->madv = I915_MADV_DONTNEED;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
-	i915_gem_object_release_stolen(obj);
 
 	BUG_ON(obj->pages);
 
@@ -4912,6 +4936,8 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
 	register_oom_notifier(&dev_priv->mm.oom_notifier);
+
+	mutex_init(&dev_priv->fb_tracking.lock);
 }
 
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
@@ -4973,6 +4999,23 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file)
 	return ret;
 }
 
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits)
+{
+	if (old) {
+		WARN_ON(!mutex_is_locked(&old->base.dev->struct_mutex));
+		WARN_ON(!(old->frontbuffer_bits & frontbuffer_bits));
+		old->frontbuffer_bits &= ~frontbuffer_bits;
+	}
+
+	if (new) {
+		WARN_ON(!mutex_is_locked(&new->base.dev->struct_mutex));
+		WARN_ON(new->frontbuffer_bits & frontbuffer_bits);
+		new->frontbuffer_bits |= frontbuffer_bits;
+	}
+}
+
 static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 {
 	if (!mutex_is_locked(mutex))
@@ -5055,12 +5098,13 @@ unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
 	    vm == &dev_priv->mm.aliasing_ppgtt->base)
 		vm = &dev_priv->gtt.base;
 
-	BUG_ON(list_empty(&o->vma_list));
 	list_for_each_entry(vma, &o->vma_list, vma_link) {
 		if (vma->vm == vm)
 			return vma->node.start;
 
 	}
+	WARN(1, "%s vma for this object not found.\n",
+	     i915_is_ggtt(vm) ? "global" : "ppgtt");
 	return -1;
 }
 
@@ -5141,8 +5185,11 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 	bool was_interruptible;
 	bool unlock;
 
-	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout)
+	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) {
 		schedule_timeout_killable(1);
+		if (fatal_signal_pending(current))
+			return NOTIFY_DONE;
+	}
 	if (timeout == 0) {
 		pr_err("Unable to purge GPU memory due lock contention.\n");
 		return NOTIFY_DONE;