Merge drm-upstream/drm-next into drm-intel-next-queued

Need MST sideband message transaction to power up/down nodes.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

14 files changed, 73 insertions, 124 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 23a9bbbb6565..2c0ccbb817dc 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -2725,7 +2725,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 unmap_src:
 	i915_gem_object_unpin_map(obj);
 put_obj:
-	i915_gem_object_put(wa_ctx->indirect_ctx.obj);
+	i915_gem_object_put(obj);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 3502a59166ff..2294466dd415 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2659,7 +2659,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_PWR_WELL_CTL_BIOS(SKL_DISP_PW_MISC_IO), D_SKL_PLUS);
 	MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL,
 		skl_power_well_ctl_write);
-	MMIO_DH(GEN6_PCODE_MAILBOX, D_SKL_PLUS, NULL, mailbox_write);
 
 	MMIO_D(0xa210, D_SKL_PLUS);
 	MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 86c799ac4b85..b4a6ac60e7c6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -28,6 +28,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/sort.h>
+#include <linux/sched/mm.h>
 #include "intel_drv.h"
 
 static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
@@ -4360,16 +4361,16 @@ i915_drop_caches_set(void *data, u64 val)
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	lockdep_set_current_reclaim_state(GFP_KERNEL);
+	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
-		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
+		i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND);
 
 	if (val & DROP_UNBOUND)
-		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND);
+		i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND);
 
 	if (val & DROP_SHRINK_ALL)
 		i915_gem_shrink_all(dev_priv);
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(GFP_KERNEL);
 
 	if (val & DROP_FREED) {
 		synchronize_rcu();
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 59fd4bceec7b..8e4280838f14 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -725,8 +725,7 @@ struct drm_i915_display_funcs {
 			    struct drm_atomic_state *old_state);
 	void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
 			     struct drm_atomic_state *old_state);
-	void (*update_crtcs)(struct drm_atomic_state *state,
-			     unsigned int *crtc_vblank_mask);
+	void (*update_crtcs)(struct drm_atomic_state *state);
 	void (*audio_codec_enable)(struct drm_connector *connector,
 				   struct intel_encoder *encoder,
 				   const struct drm_display_mode *adjusted_mode);
@@ -3829,6 +3828,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
 /* i915_gem_shrinker.c */
 unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
 			      unsigned long target,
+			      unsigned long *nr_scanned,
 			      unsigned flags);
 #define I915_SHRINK_PURGEABLE 0x1
 #define I915_SHRINK_UNBOUND 0x2
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 49bf5ddfa7fd..73eeb6b1f1cd 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2352,7 +2352,7 @@ rebuild_st:
 				goto err_sg;
 			}
 
-			i915_gem_shrink(dev_priv, 2 * page_count, *s++);
+			i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++);
 			cond_resched();
 
 			/* We've tried hard to allocate the memory by reaping
@@ -2539,7 +2539,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj,
 
 	if (n_pages > ARRAY_SIZE(stack_pages)) {
 		/* Too big for stack -- allocate temporary array instead */
-		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_TEMPORARY);
+		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
 		if (!pages)
 			return NULL;
 	}
@@ -4987,7 +4987,7 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
 	 * the objects as well, see i915_gem_freeze()
 	 */
 
-	i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND);
+	i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND);
 	i915_gem_drain_freed_objects(dev_priv);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index fa18677cdb54..d733c4d5a500 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -299,7 +299,7 @@ static int eb_create(struct i915_execbuffer *eb)
 			 * as possible to perform the allocation and warn
 			 * if it fails.
 			 */
-			flags = GFP_TEMPORARY;
+			flags = GFP_KERNEL;
 			if (size > 1)
 				flags |= __GFP_NORETRY | __GFP_NOWARN;
 
@@ -1523,7 +1523,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 		urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
 		size = nreloc * sizeof(*relocs);
 
-		relocs = kvmalloc_array(size, 1, GFP_TEMPORARY);
+		relocs = kvmalloc_array(size, 1, GFP_KERNEL);
 		if (!relocs) {
 			kvfree(relocs);
 			err = -ENOMEM;
@@ -2085,7 +2085,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 		return ERR_PTR(-EFAULT);
 
 	fences = kvmalloc_array(args->num_cliprects, sizeof(*fences),
-				__GFP_NOWARN | GFP_TEMPORARY);
+				__GFP_NOWARN | GFP_KERNEL);
 	if (!fences)
 		return ERR_PTR(-ENOMEM);
 
@@ -2472,9 +2472,9 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 
 	/* Copy in the exec list from userland */
 	exec_list = kvmalloc_array(args->buffer_count, sizeof(*exec_list),
-				   __GFP_NOWARN | GFP_TEMPORARY);
+				   __GFP_NOWARN | GFP_KERNEL);
 	exec2_list = kvmalloc_array(args->buffer_count + 1, sz,
-				    __GFP_NOWARN | GFP_TEMPORARY);
+				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec_list == NULL || exec2_list == NULL) {
 		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
 			  args->buffer_count);
@@ -2552,7 +2552,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 
 	/* Allocate an extra slot for use by the command parser */
 	exec2_list = kvmalloc_array(args->buffer_count + 1, sz,
-				    __GFP_NOWARN | GFP_TEMPORARY);
+				    __GFP_NOWARN | GFP_KERNEL);
 	if (exec2_list == NULL) {
 		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
 			  args->buffer_count);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ecb5e8cd37ba..64d785262d14 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2131,7 +2131,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 		 */
 		GEM_BUG_ON(obj->mm.pages == pages);
 	} while (i915_gem_shrink(to_i915(obj->base.dev),
-				 obj->base.size >> PAGE_SHIFT,
+				 obj->base.size >> PAGE_SHIFT, NULL,
 				 I915_SHRINK_BOUND |
 				 I915_SHRINK_UNBOUND |
 				 I915_SHRINK_ACTIVE));
@@ -3499,7 +3499,7 @@ intel_rotate_pages(struct intel_rotation_info *rot_info,
 	/* Allocate a temporary list of source pages for random access. */
 	page_addr_list = kvmalloc_array(n_pages,
 					sizeof(dma_addr_t),
-					GFP_TEMPORARY);
+					GFP_KERNEL);
 	if (!page_addr_list)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 77fb39808131..74002b2d1b6f 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -136,6 +136,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
  * i915_gem_shrink - Shrink buffer object caches
  * @dev_priv: i915 device
  * @target: amount of memory to make available, in pages
+ * @nr_scanned: optional output for number of pages scanned (incremental)
  * @flags: control flags for selecting cache types
  *
  * This function is the main interface to the shrinker. It will try to release
@@ -158,7 +159,9 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
  */
 unsigned long
 i915_gem_shrink(struct drm_i915_private *dev_priv,
-		unsigned long target, unsigned flags)
+		unsigned long target,
+		unsigned long *nr_scanned,
+		unsigned flags)
 {
 	const struct {
 		struct list_head *list;
@@ -169,6 +172,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 		{ NULL, 0 },
 	}, *phase;
 	unsigned long count = 0;
+	unsigned long scanned = 0;
 	bool unlock;
 
 	if (!shrinker_lock(dev_priv, &unlock))
@@ -249,6 +253,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 					count += obj->base.size >> PAGE_SHIFT;
 				}
 				mutex_unlock(&obj->mm.lock);
+				scanned += obj->base.size >> PAGE_SHIFT;
 			}
 		}
 		list_splice_tail(&still_in_list, phase->list);
@@ -261,6 +266,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 
 	shrinker_unlock(dev_priv, unlock);
 
+	if (nr_scanned)
+		*nr_scanned += scanned;
 	return count;
 }
 
@@ -283,7 +290,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 	unsigned long freed;
 
 	intel_runtime_pm_get(dev_priv);
-	freed = i915_gem_shrink(dev_priv, -1UL,
+	freed = i915_gem_shrink(dev_priv, -1UL, NULL,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
@@ -329,23 +336,28 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	unsigned long freed;
 	bool unlock;
 
+	sc->nr_scanned = 0;
+
 	if (!shrinker_lock(dev_priv, &unlock))
 		return SHRINK_STOP;
 
 	freed = i915_gem_shrink(dev_priv,
 				sc->nr_to_scan,
+				&sc->nr_scanned,
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_PURGEABLE);
 	if (freed < sc->nr_to_scan)
 		freed += i915_gem_shrink(dev_priv,
-					 sc->nr_to_scan - freed,
+					 sc->nr_to_scan - sc->nr_scanned,
+					 &sc->nr_scanned,
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
 	if (freed < sc->nr_to_scan && current_is_kswapd()) {
 		intel_runtime_pm_get(dev_priv);
 		freed += i915_gem_shrink(dev_priv,
-					 sc->nr_to_scan - freed,
+					 sc->nr_to_scan - sc->nr_scanned,
+					 &sc->nr_scanned,
 					 I915_SHRINK_ACTIVE |
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
@@ -354,7 +366,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	shrinker_unlock(dev_priv, unlock);
 
-	return freed;
+	return sc->nr_scanned ? freed : SHRINK_STOP;
 }
 
 static bool
@@ -453,7 +465,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		goto out;
 
 	intel_runtime_pm_get(dev_priv);
-	freed_pages += i915_gem_shrink(dev_priv, -1UL,
+	freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL,
 				       I915_SHRINK_BOUND |
 				       I915_SHRINK_UNBOUND |
 				       I915_SHRINK_ACTIVE |
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 15547c8f7d3f..2d4996de7331 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -49,7 +49,7 @@ struct i915_mmu_notifier {
 	spinlock_t lock;
 	struct hlist_node node;
 	struct mmu_notifier mn;
-	struct rb_root objects;
+	struct rb_root_cached objects;
 	struct workqueue_struct *wq;
 };
 
@@ -123,7 +123,7 @@ static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	struct interval_tree_node *it;
 	LIST_HEAD(cancelled);
 
-	if (RB_EMPTY_ROOT(&mn->objects))
+	if (RB_EMPTY_ROOT(&mn->objects.rb_root))
 		return;
 
 	/* interval ranges are inclusive, but invalidate range is exclusive */
@@ -172,7 +172,7 @@ i915_mmu_notifier_create(struct mm_struct *mm)
 
 	spin_lock_init(&mn->lock);
 	mn->mn.ops = &i915_gem_userptr_notifier;
-	mn->objects = RB_ROOT;
+	mn->objects = RB_ROOT_CACHED;
 	mn->wq = alloc_workqueue("i915-userptr-release", WQ_UNBOUND, 0);
 	if (mn->wq == NULL) {
 		kfree(mn);
@@ -485,7 +485,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	ret = -ENOMEM;
 	pinned = 0;
 
-	pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_TEMPORARY);
+	pvec = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
@@ -622,7 +622,7 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 
 	if (mm == current->mm) {
 		pvec = kvmalloc_array(num_pages, sizeof(struct page *),
-				      GFP_TEMPORARY |
+				      GFP_KERNEL |
 				      __GFP_NORETRY |
 				      __GFP_NOWARN);
 		if (pvec) /* defer to worker if malloc fails */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9f7b351621f3..c14552ab270b 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -792,16 +792,16 @@ int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf,
 	 */
 	ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE;
 	ebuf->buf = kmalloc(ebuf->size,
-				GFP_TEMPORARY | __GFP_NORETRY | __GFP_NOWARN);
+				GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 
 	if (ebuf->buf == NULL) {
 		ebuf->size = PAGE_SIZE;
-		ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+		ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
 	}
 
 	if (ebuf->buf == NULL) {
 		ebuf->size = 128;
-		ebuf->buf = kmalloc(ebuf->size, GFP_TEMPORARY);
+		ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL);
 	}
 
 	if (ebuf->buf == NULL)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index aa9ccc3ecff9..c4b224a3a0ee 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12137,73 +12137,10 @@ u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc)
 	return dev->driver->get_vblank_counter(dev, crtc->pipe);
 }
 
-static void intel_atomic_wait_for_vblanks(struct drm_device *dev,
-					  struct drm_i915_private *dev_priv,
-					  unsigned crtc_mask)
-{
-	unsigned last_vblank_count[I915_MAX_PIPES];
-	enum pipe pipe;
-	int ret;
-
-	if (!crtc_mask)
-		return;
-
-	for_each_pipe(dev_priv, pipe) {
-		struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
-								  pipe);
-
-		if (!((1 << pipe) & crtc_mask))
-			continue;
-
-		ret = drm_crtc_vblank_get(&crtc->base);
-		if (WARN_ON(ret != 0)) {
-			crtc_mask &= ~(1 << pipe);
-			continue;
-		}
-
-		last_vblank_count[pipe] = drm_crtc_vblank_count(&crtc->base);
-	}
-
-	for_each_pipe(dev_priv, pipe) {
-		struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
-								  pipe);
-		long lret;
-
-		if (!((1 << pipe) & crtc_mask))
-			continue;
-
-		lret = wait_event_timeout(dev->vblank[pipe].queue,
-				last_vblank_count[pipe] !=
-					drm_crtc_vblank_count(&crtc->base),
-				msecs_to_jiffies(50));
-
-		WARN(!lret, "pipe %c vblank wait timed out\n", pipe_name(pipe));
-
-		drm_crtc_vblank_put(&crtc->base);
-	}
-}
-
-static bool needs_vblank_wait(struct intel_crtc_state *crtc_state)
-{
-	/* fb updated, need to unpin old fb */
-	if (crtc_state->fb_changed)
-		return true;
-
-	/* wm changes, need vblank before final wm's */
-	if (crtc_state->update_wm_post)
-		return true;
-
-	if (crtc_state->wm.need_postvbl_update)
-		return true;
-
-	return false;
-}
-
 static void intel_update_crtc(struct drm_crtc *crtc,
 			      struct drm_atomic_state *state,
 			      struct drm_crtc_state *old_crtc_state,
-			      struct drm_crtc_state *new_crtc_state,
-			      unsigned int *crtc_vblank_mask)
+			      struct drm_crtc_state *new_crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -12226,13 +12163,9 @@ static void intel_update_crtc(struct drm_crtc *crtc,
 	}
 
 	drm_atomic_helper_commit_planes_on_crtc(old_crtc_state);
-
-	if (needs_vblank_wait(pipe_config))
-		*crtc_vblank_mask |= drm_crtc_mask(crtc);
 }
 
-static void intel_update_crtcs(struct drm_atomic_state *state,
-			       unsigned int *crtc_vblank_mask)
+static void intel_update_crtcs(struct drm_atomic_state *state)
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
@@ -12243,12 +12176,11 @@ static void intel_update_crtcs(struct drm_atomic_state *state,
 			continue;
 
 		intel_update_crtc(crtc, state, old_crtc_state,
-				  new_crtc_state, crtc_vblank_mask);
+				  new_crtc_state);
 	}
 }
 
-static void skl_update_crtcs(struct drm_atomic_state *state,
-			     unsigned int *crtc_vblank_mask)
+static void skl_update_crtcs(struct drm_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
@@ -12307,7 +12239,7 @@ static void skl_update_crtcs(struct drm_atomic_state *state,
 				vbl_wait = true;
 
 			intel_update_crtc(crtc, state, old_crtc_state,
-					  new_crtc_state, crtc_vblank_mask);
+					  new_crtc_state);
 
 			if (vbl_wait)
 				intel_wait_for_vblank(dev_priv, pipe);
@@ -12368,7 +12300,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_crtc *crtc;
 	struct intel_crtc_state *intel_cstate;
 	u64 put_domains[I915_MAX_PIPES] = {};
-	unsigned crtc_vblank_mask = 0;
 	int i;
 
 	intel_atomic_commit_fence_wait(intel_state);
@@ -12457,7 +12388,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
-	dev_priv->display.update_crtcs(state, &crtc_vblank_mask);
+	dev_priv->display.update_crtcs(state);
 
 	/* FIXME: We should call drm_atomic_helper_commit_hw_done() here
 	 * already, but still need the state for the delayed optimization. To
@@ -12468,8 +12399,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	 * - switch over to the vblank wait helper in the core after that since
 	 *   we don't need out special handling any more.
 	 */
-	if (!state->legacy_cursor_update)
-		intel_atomic_wait_for_vblanks(dev, dev_priv, crtc_vblank_mask);
+	drm_atomic_helper_wait_for_flip_done(dev, state);
 
 	/*
 	 * Now that the vblank has passed, we can go ahead and program the
@@ -13133,6 +13063,14 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 		goto slow;
 
 	old_plane_state = plane->state;
+	/*
+	 * Don't do an async update if there is an outstanding commit modifying
+	 * the plane.  This prevents our async update's changes from getting
+	 * overridden by a previous synchronous update's state.
+	 */
+	if (old_plane_state->commit &&
+	    !try_wait_for_completion(&old_plane_state->commit->hw_done))
+		goto slow;
 
 	/*
 	 * If any parameters change that may affect watermarks,
@@ -13194,17 +13132,12 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	}
 
 	old_fb = old_plane_state->fb;
-	old_vma = to_intel_plane_state(old_plane_state)->vma;
 
 	i915_gem_track_fb(intel_fb_obj(old_fb), intel_fb_obj(fb),
 			  intel_plane->frontbuffer_bit);
 
 	/* Swap plane state */
-	new_plane_state->fence = old_plane_state->fence;
-	*to_intel_plane_state(old_plane_state) = *to_intel_plane_state(new_plane_state);
-	new_plane_state->fence = NULL;
-	new_plane_state->fb = old_fb;
-	to_intel_plane_state(new_plane_state)->vma = NULL;
+	plane->state = new_plane_state;
 
 	if (plane->state->visible) {
 		trace_intel_update_plane(plane, to_intel_crtc(crtc));
@@ -13216,13 +13149,17 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 		intel_plane->disable_plane(intel_plane, to_intel_crtc(crtc));
 	}
 
+	old_vma = fetch_and_zero(&to_intel_plane_state(old_plane_state)->vma);
 	if (old_vma)
 		intel_unpin_fb_vma(old_vma);
 
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 out_free:
-	intel_plane_destroy_state(plane, new_plane_state);
+	if (ret)
+		intel_plane_destroy_state(plane, new_plane_state);
+	else
+		intel_plane_destroy_state(plane, old_plane_state);
 	return ret;
 
 slow:
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
index ea0f5dbc0eb7..b85872cc7fbe 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.c
+++ b/drivers/gpu/drm/i915/selftests/i915_random.c
@@ -57,7 +57,7 @@ unsigned int *i915_random_order(unsigned int count, struct rnd_state *state)
 {
 	unsigned int *order, i;
 
-	order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY);
+	order = kmalloc_array(count, sizeof(*order), GFP_KERNEL);
 	if (!order)
 		return order;
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
index 7276194c04f7..828904b7d468 100644
--- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
@@ -117,12 +117,12 @@ static int igt_random_insert_remove(void *arg)
 
 	mock_engine_reset(engine);
 
-	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY);
+	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL);
 	if (!waiters)
 		goto out_engines;
 
 	bitmap = kcalloc(DIV_ROUND_UP(count, BITS_PER_LONG), sizeof(*bitmap),
-			 GFP_TEMPORARY);
+			 GFP_KERNEL);
 	if (!bitmap)
 		goto out_waiters;
 
@@ -187,12 +187,12 @@ static int igt_insert_complete(void *arg)
 
 	mock_engine_reset(engine);
 
-	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY);
+	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL);
 	if (!waiters)
 		goto out_engines;
 
 	bitmap = kcalloc(DIV_ROUND_UP(count, BITS_PER_LONG), sizeof(*bitmap),
-			 GFP_TEMPORARY);
+			 GFP_KERNEL);
 	if (!bitmap)
 		goto out_waiters;
 
@@ -368,7 +368,7 @@ static int igt_wakeup(void *arg)
 
 	mock_engine_reset(engine);
 
-	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_TEMPORARY);
+	waiters = kvmalloc_array(count, sizeof(*waiters), GFP_KERNEL);
 	if (!waiters)
 		goto out_engines;
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 2d0fef2cfca6..3cac22eb47ce 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -127,7 +127,7 @@ static int intel_uncore_check_forcewake_domains(struct drm_i915_private *dev_pri
 		return 0;
 
 	valid = kzalloc(BITS_TO_LONGS(FW_RANGE) * sizeof(*valid),
-			GFP_TEMPORARY);
+			GFP_KERNEL);
 	if (!valid)
 		return -ENOMEM;