Merge tag 'drm-fixes-for-v4.11-rc3' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes from Dave Airlie:
 "Bunch of fixes across the drivers, in a St Patrick's day pull request
  (please turn terminal colors to green on black or black on green for
  full effect).

  On the arm side, tilcdc, omap and malidp got fixes, while amd has some
  powermanagement fixes, and intel has a set of fixes across the driver.

  Nothing seems to bad or scary at this point"

* tag 'drm-fixes-for-v4.11-rc3' of git://people.freedesktop.org/~airlied/linux: (27 commits)
  drm/amd/amdgpu:  Fix debugfs reg read/write address width
  drm/amdgpu/si: add dpm quirk for Oland
  drm/radeon/si: add dpm quirk for Oland
  drm: amd: remove broken include path
  drm/amd/powerplay: fix copy error in smu7_clockpoweragting.c
  drm/tilcdc: Set framebuffer DMA address to HW only if CRTC is enabled
  drm/tilcdc: Fix hardcoded fail-return value in tilcdc_crtc_create()
  drm/i915: Fix forcewake active domain tracking
  drm/i915: Nuke skl_update_plane debug message from the pipe update critical section
  drm/i915: use correct node for handling cache domain eviction
  uapi: fix drm/omap_drm.h userspace compilation errors
  drm/omap: fix dmabuf mmap for dma_alloc'ed buffers
  drm/amdgpu: fix parser init error path to avoid crash in parser fini
  drm/amd/amdgpu: Disable GFX_PG on Carrizo until compute issues solved
  drm: mali-dp: Fix smart layer not going to composition
  drm: mali-dp: Remove mclk rate management
  drm/i915: Drain the freed state from the tail of the next commit
  drm/i915: Nuke debug messages from the pipe update critical section
  drm/i915: Use pagecache write to prepopulate shmemfs from pwrite-ioctl
  drm/i915: Store a permanent error in obj->mm.pages
  ...

24 files changed, 271 insertions, 123 deletions

diff --git a/drivers/gpu/drm/amd/acp/Makefile b/drivers/gpu/drm/amd/acp/Makefile
index 8363cb57915b..8a08e81ee90d 100644
--- a/drivers/gpu/drm/amd/acp/Makefile
+++ b/drivers/gpu/drm/amd/acp/Makefile
@@ -3,6 +3,4 @@
 # of AMDSOC/AMDGPU drm driver.
 # It provides the HW control for ACP related functionalities.
 
-subdir-ccflags-y += -I$(AMDACPPATH)/ -I$(AMDACPPATH)/include
-
 AMD_ACP_FILES := $(AMDACPPATH)/acp_hw.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d2d0f60ff36d..99424cb8020b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -240,6 +240,8 @@ free_partial_kdata:
 	for (; i >= 0; i--)
 		drm_free_large(p->chunks[i].kdata);
 	kfree(p->chunks);
+	p->chunks = NULL;
+	p->nchunks = 0;
 put_ctx:
 	amdgpu_ctx_put(p->ctx);
 free_chunk:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 4120b351a8e5..a3a105ec99e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2590,7 +2590,7 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf,
 		use_bank = 0;
 	}
 
-	*pos &= 0x3FFFF;
+	*pos &= (1UL << 22) - 1;
 
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
@@ -2666,7 +2666,7 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 		use_bank = 0;
 	}
 
-	*pos &= 0x3FFFF;
+	*pos &= (1UL << 22) - 1;
 
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index f55e45b52fbc..33b504bafb88 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3464,6 +3464,12 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
 		}
+	} else if (adev->asic_type == CHIP_OLAND) {
+		if ((adev->pdev->device == 0x6604) &&
+		    (adev->pdev->subsystem_vendor == 0x1028) &&
+		    (adev->pdev->subsystem_device == 0x066F)) {
+			max_sclk = 75000;
+		}
 	}
 
 	if (rps->vce_active) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 50bdb24ef8d6..4a785d6acfb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1051,7 +1051,7 @@ static int vi_common_early_init(void *handle)
 		/* rev0 hardware requires workarounds to support PG */
 		adev->pg_flags = 0;
 		if (adev->rev_id != 0x00) {
-			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+			adev->pg_flags |=
 				AMD_PG_SUPPORT_GFX_SMG |
 				AMD_PG_SUPPORT_GFX_PIPELINE |
 				AMD_PG_SUPPORT_CP |
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 8cf71f3c6d0e..261b828ad590 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -178,7 +178,7 @@ int smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	if (bgate) {
 		cgs_set_powergating_state(hwmgr->device,
 						AMD_IP_BLOCK_TYPE_VCE,
-						AMD_PG_STATE_UNGATE);
+						AMD_PG_STATE_GATE);
 		cgs_set_clockgating_state(hwmgr->device,
 				AMD_IP_BLOCK_TYPE_VCE,
 				AMD_CG_STATE_GATE);
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index 08e6a71f5d05..294b53697334 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -63,8 +63,7 @@ static void malidp_crtc_enable(struct drm_crtc *crtc)
 
 	clk_prepare_enable(hwdev->pxlclk);
 
-	/* mclk needs to be set to the same or higher rate than pxlclk */
-	clk_set_rate(hwdev->mclk, crtc->state->adjusted_mode.crtc_clock * 1000);
+	/* We rely on firmware to set mclk to a sensible level. */
 	clk_set_rate(hwdev->pxlclk, crtc->state->adjusted_mode.crtc_clock * 1000);
 
 	hwdev->modeset(hwdev, &vm);
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 488aedf5b58d..9f5513006eee 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -83,7 +83,7 @@ static const struct malidp_layer malidp550_layers[] = {
 	{ DE_VIDEO1, MALIDP550_DE_LV1_BASE, MALIDP550_DE_LV1_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
 	{ DE_GRAPHICS1, MALIDP550_DE_LG_BASE, MALIDP550_DE_LG_PTR_BASE, MALIDP_DE_LG_STRIDE },
 	{ DE_VIDEO2, MALIDP550_DE_LV2_BASE, MALIDP550_DE_LV2_PTR_BASE, MALIDP_DE_LV_STRIDE0 },
-	{ DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, 0 },
+	{ DE_SMART, MALIDP550_DE_LS_BASE, MALIDP550_DE_LS_PTR_BASE, MALIDP550_DE_LS_R1_STRIDE },
 };
 
 #define MALIDP_DE_DEFAULT_PREFETCH_START	5
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 414aada10fe5..d5aec082294c 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -37,6 +37,8 @@
 #define   LAYER_V_VAL(x)		(((x) & 0x1fff) << 16)
 #define MALIDP_LAYER_COMP_SIZE		0x010
 #define MALIDP_LAYER_OFFSET		0x014
+#define MALIDP550_LS_ENABLE		0x01c
+#define MALIDP550_LS_R1_IN_SIZE		0x020
 
 /*
  * This 4-entry look-up-table is used to determine the full 8-bit alpha value
@@ -242,6 +244,11 @@ static void malidp_de_plane_update(struct drm_plane *plane,
 			LAYER_V_VAL(plane->state->crtc_y),
 			mp->layer->base + MALIDP_LAYER_OFFSET);
 
+	if (mp->layer->id == DE_SMART)
+		malidp_hw_write(mp->hwdev,
+				LAYER_H_VAL(src_w) | LAYER_V_VAL(src_h),
+				mp->layer->base + MALIDP550_LS_R1_IN_SIZE);
+
 	/* first clear the rotation bits */
 	val = malidp_hw_read(mp->hwdev, mp->layer->base + MALIDP_LAYER_CONTROL);
 	val &= ~LAYER_ROT_MASK;
@@ -330,9 +337,16 @@ int malidp_de_planes_init(struct drm_device *drm)
 		plane->hwdev = malidp->dev;
 		plane->layer = &map->layers[i];
 
-		/* Skip the features which the SMART layer doesn't have */
-		if (id == DE_SMART)
+		if (id == DE_SMART) {
+			/*
+			 * Enable the first rectangle in the SMART layer to be
+			 * able to use it as a drm plane.
+			 */
+			malidp_hw_write(malidp->dev, 1,
+					plane->layer->base + MALIDP550_LS_ENABLE);
+			/* Skip the features which the SMART layer doesn't have. */
 			continue;
+		}
 
 		drm_plane_create_rotation_property(&plane->base, DRM_ROTATE_0, flags);
 		malidp_hw_write(malidp->dev, MALIDP_ALPHA_LUT,
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index aff6d4a84e99..b816067a65c5 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -84,6 +84,7 @@
 /* Stride register offsets relative to Lx_BASE */
 #define MALIDP_DE_LG_STRIDE		0x18
 #define MALIDP_DE_LV_STRIDE0		0x18
+#define MALIDP550_DE_LS_R1_STRIDE	0x28
 
 /* macros to set values into registers */
 #define MALIDP_DE_H_FRONTPORCH(x)	(((x) & 0xfff) << 0)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a4b42d31391..7febe6eecf72 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -293,6 +293,7 @@ enum plane_id {
 	PLANE_PRIMARY,
 	PLANE_SPRITE0,
 	PLANE_SPRITE1,
+	PLANE_SPRITE2,
 	PLANE_CURSOR,
 	I915_MAX_PLANES,
 };
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6908123162d1..10777da73039 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1434,6 +1434,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
+	ret = -ENODEV;
+	if (obj->ops->pwrite)
+		ret = obj->ops->pwrite(obj, args);
+	if (ret != -ENODEV)
+		goto err;
+
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE |
 				   I915_WAIT_ALL,
@@ -2119,6 +2125,7 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
 	 */
 	shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
 	obj->mm.madv = __I915_MADV_PURGED;
+	obj->mm.pages = ERR_PTR(-EFAULT);
 }
 
 /* Try to discard unwanted pages */
@@ -2218,7 +2225,9 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 
 	__i915_gem_object_reset_page_iter(obj);
 
-	obj->ops->put_pages(obj, pages);
+	if (!IS_ERR(pages))
+		obj->ops->put_pages(obj, pages);
+
 unlock:
 	mutex_unlock(&obj->mm.lock);
 }
@@ -2437,7 +2446,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	if (err)
 		return err;
 
-	if (unlikely(!obj->mm.pages)) {
+	if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
 		err = ____i915_gem_object_get_pages(obj);
 		if (err)
 			goto unlock;
@@ -2515,7 +2524,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 
 	pinned = true;
 	if (!atomic_inc_not_zero(&obj->mm.pages_pin_count)) {
-		if (unlikely(!obj->mm.pages)) {
+		if (unlikely(IS_ERR_OR_NULL(obj->mm.pages))) {
 			ret = ____i915_gem_object_get_pages(obj);
 			if (ret)
 				goto err_unlock;
@@ -2563,6 +2572,75 @@ err_unlock:
 	goto out_unlock;
 }
 
+static int
+i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
+			   const struct drm_i915_gem_pwrite *arg)
+{
+	struct address_space *mapping = obj->base.filp->f_mapping;
+	char __user *user_data = u64_to_user_ptr(arg->data_ptr);
+	u64 remain, offset;
+	unsigned int pg;
+
+	/* Before we instantiate/pin the backing store for our use, we
+	 * can prepopulate the shmemfs filp efficiently using a write into
+	 * the pagecache. We avoid the penalty of instantiating all the
+	 * pages, important if the user is just writing to a few and never
+	 * uses the object on the GPU, and using a direct write into shmemfs
+	 * allows it to avoid the cost of retrieving a page (either swapin
+	 * or clearing-before-use) before it is overwritten.
+	 */
+	if (READ_ONCE(obj->mm.pages))
+		return -ENODEV;
+
+	/* Before the pages are instantiated the object is treated as being
+	 * in the CPU domain. The pages will be clflushed as required before
+	 * use, and we can freely write into the pages directly. If userspace
+	 * races pwrite with any other operation; corruption will ensue -
+	 * that is userspace's prerogative!
+	 */
+
+	remain = arg->size;
+	offset = arg->offset;
+	pg = offset_in_page(offset);
+
+	do {
+		unsigned int len, unwritten;
+		struct page *page;
+		void *data, *vaddr;
+		int err;
+
+		len = PAGE_SIZE - pg;
+		if (len > remain)
+			len = remain;
+
+		err = pagecache_write_begin(obj->base.filp, mapping,
+					    offset, len, 0,
+					    &page, &data);
+		if (err < 0)
+			return err;
+
+		vaddr = kmap(page);
+		unwritten = copy_from_user(vaddr + pg, user_data, len);
+		kunmap(page);
+
+		err = pagecache_write_end(obj->base.filp, mapping,
+					  offset, len, len - unwritten,
+					  page, data);
+		if (err < 0)
+			return err;
+
+		if (unwritten)
+			return -EFAULT;
+
+		remain -= len;
+		user_data += len;
+		offset += len;
+		pg = 0;
+	} while (remain);
+
+	return 0;
+}
+
 static bool ban_context(const struct i915_gem_context *ctx)
 {
 	return (i915_gem_context_is_bannable(ctx) &&
@@ -3029,6 +3107,16 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		args->timeout_ns -= ktime_to_ns(ktime_sub(ktime_get(), start));
 		if (args->timeout_ns < 0)
 			args->timeout_ns = 0;
+
+		/*
+		 * Apparently ktime isn't accurate enough and occasionally has a
+		 * bit of mismatch in the jiffies<->nsecs<->ktime loop. So patch
+		 * things up to make the test happy. We allow up to 1 jiffy.
+		 *
+		 * This is a regression from the timespec->ktime conversion.
+		 */
+		if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns))
+			args->timeout_ns = 0;
 	}
 
 	i915_gem_object_put(obj);
@@ -3974,8 +4062,11 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE,
+
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
+
+	.pwrite = i915_gem_object_pwrite_gtt,
 };
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index c181b1bb3d2c..3be2503aa042 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -293,12 +293,12 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 		 * those as well to make room for our guard pages.
 		 */
 		if (check_color) {
-			if (vma->node.start + vma->node.size == node->start) {
-				if (vma->node.color == node->color)
+			if (node->start + node->size == target->start) {
+				if (node->color == target->color)
 					continue;
 			}
-			if (vma->node.start == node->start + node->size) {
-				if (vma->node.color == node->color)
+			if (node->start == target->start + target->size) {
+				if (node->color == target->color)
 					continue;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index bf90b07163d1..76b80a0be797 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -54,6 +54,9 @@ struct drm_i915_gem_object_ops {
 	struct sg_table *(*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *, struct sg_table *);
 
+	int (*pwrite)(struct drm_i915_gem_object *,
+		      const struct drm_i915_gem_pwrite *);
+
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 155906e84812..df20e9bc1c0f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -512,10 +512,36 @@ err_unpin:
 	return ret;
 }
 
+static void
+i915_vma_remove(struct i915_vma *vma)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
+
+	drm_mm_remove_node(&vma->node);
+	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
+
+	/* Since the unbound list is global, only move to that list if
+	 * no more VMAs exist.
+	 */
+	if (--obj->bind_count == 0)
+		list_move_tail(&obj->global_link,
+			       &to_i915(obj->base.dev)->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
+	 * reaped by the shrinker.
+	 */
+	i915_gem_object_unpin_pages(obj);
+	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+}
+
 int __i915_vma_do_pin(struct i915_vma *vma,
 		      u64 size, u64 alignment, u64 flags)
 {
-	unsigned int bound = vma->flags;
+	const unsigned int bound = vma->flags;
 	int ret;
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -524,18 +550,18 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 
 	if (WARN_ON(bound & I915_VMA_PIN_OVERFLOW)) {
 		ret = -EBUSY;
-		goto err;
+		goto err_unpin;
 	}
 
 	if ((bound & I915_VMA_BIND_MASK) == 0) {
 		ret = i915_vma_insert(vma, size, alignment, flags);
 		if (ret)
-			goto err;
+			goto err_unpin;
 	}
 
 	ret = i915_vma_bind(vma, vma->obj->cache_level, flags);
 	if (ret)
-		goto err;
+		goto err_remove;
 
 	if ((bound ^ vma->flags) & I915_VMA_GLOBAL_BIND)
 		__i915_vma_set_map_and_fenceable(vma);
@@ -544,7 +570,12 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 	GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
 	return 0;
 
-err:
+err_remove:
+	if ((bound & I915_VMA_BIND_MASK) == 0) {
+		GEM_BUG_ON(vma->pages);
+		i915_vma_remove(vma);
+	}
+err_unpin:
 	__i915_vma_unpin(vma);
 	return ret;
 }
@@ -657,9 +688,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
 
-	drm_mm_remove_node(&vma->node);
-	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
-
 	if (vma->pages != obj->mm.pages) {
 		GEM_BUG_ON(!vma->pages);
 		sg_free_table(vma->pages);
@@ -667,18 +695,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	vma->pages = NULL;
 
-	/* Since the unbound list is global, only move to that list if
-	 * no more VMAs exist. */
-	if (--obj->bind_count == 0)
-		list_move_tail(&obj->global_link,
-			       &to_i915(obj->base.dev)->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
-	 * reaped by the shrinker.
-	 */
-	i915_gem_object_unpin_pages(obj);
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+	i915_vma_remove(vma);
 
 destroy:
 	if (unlikely(i915_vma_is_closed(vma)))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 01341670738f..3282b0f4b134 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3669,10 +3669,6 @@ static void intel_update_pipe_config(struct intel_crtc *crtc,
 	/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
 	crtc->base.mode = crtc->base.state->mode;
 
-	DRM_DEBUG_KMS("Updating pipe size %ix%i -> %ix%i\n",
-		      old_crtc_state->pipe_src_w, old_crtc_state->pipe_src_h,
-		      pipe_config->pipe_src_w, pipe_config->pipe_src_h);
-
 	/*
 	 * Update pipe size and adjust fitter if needed: the reason for this is
 	 * that in compute_mode_changes we check the native mode (not the pfit
@@ -4796,23 +4792,17 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc->config->scaler_state;
 
-	DRM_DEBUG_KMS("for crtc_state = %p\n", crtc->config);
-
 	if (crtc->config->pch_pfit.enabled) {
 		int id;
 
-		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) {
-			DRM_ERROR("Requesting pfit without getting a scaler first\n");
+		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
-		}
 
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
 			PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
 		I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
-
-		DRM_DEBUG_KMS("for crtc_state = %p scaler_id = %d\n", crtc->config, id);
 	}
 }
 
@@ -14379,6 +14369,24 @@ static void skl_update_crtcs(struct drm_atomic_state *state,
 	} while (progress);
 }
 
+static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv)
+{
+	struct intel_atomic_state *state, *next;
+	struct llist_node *freed;
+
+	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+	llist_for_each_entry_safe(state, next, freed, freed)
+		drm_atomic_state_put(&state->base);
+}
+
+static void intel_atomic_helper_free_state_worker(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+
+	intel_atomic_helper_free_state(dev_priv);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -14545,6 +14553,8 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	 * can happen also when the device is completely off.
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
+
+	intel_atomic_helper_free_state(dev_priv);
 }
 
 static void intel_atomic_commit_work(struct work_struct *work)
@@ -14946,17 +14956,19 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc,
 		to_intel_atomic_state(old_crtc_state->state);
 	bool modeset = needs_modeset(crtc->state);
 
+	if (!modeset &&
+	    (intel_cstate->base.color_mgmt_changed ||
+	     intel_cstate->update_pipe)) {
+		intel_color_set_csc(crtc->state);
+		intel_color_load_luts(crtc->state);
+	}
+
 	/* Perform vblank evasion around commit operation */
 	intel_pipe_update_start(intel_crtc);
 
 	if (modeset)
 		goto out;
 
-	if (crtc->state->color_mgmt_changed || to_intel_crtc_state(crtc->state)->update_pipe) {
-		intel_color_set_csc(crtc->state);
-		intel_color_load_luts(crtc->state);
-	}
-
 	if (intel_cstate->update_pipe)
 		intel_update_pipe_config(intel_crtc, old_intel_cstate);
 	else if (INTEL_GEN(dev_priv) >= 9)
@@ -16599,18 +16611,6 @@ fail:
 	drm_modeset_acquire_fini(&ctx);
 }
 
-static void intel_atomic_helper_free_state(struct work_struct *work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
-	struct intel_atomic_state *state, *next;
-	struct llist_node *freed;
-
-	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
-	llist_for_each_entry_safe(state, next, freed, freed)
-		drm_atomic_state_put(&state->base);
-}
-
 int intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16631,7 +16631,7 @@ int intel_modeset_init(struct drm_device *dev)
 	dev->mode_config.funcs = &intel_mode_funcs;
 
 	INIT_WORK(&dev_priv->atomic_helper.free_work,
-		  intel_atomic_helper_free_state);
+		  intel_atomic_helper_free_state_worker);
 
 	intel_init_quirks(dev);
 
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 1b8ba2e77539..2d449fb5d1d2 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -357,14 +357,13 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    bool *enabled, int width, int height)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
-	unsigned long conn_configured, mask;
+	unsigned long conn_configured, conn_seq, mask;
 	unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
 	int i, j;
 	bool *save_enabled;
 	bool fallback = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
-	int pass = 0;
 
 	save_enabled = kcalloc(count, sizeof(bool), GFP_KERNEL);
 	if (!save_enabled)
@@ -374,6 +373,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	mask = BIT(count) - 1;
 	conn_configured = 0;
 retry:
+	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
@@ -387,7 +387,7 @@ retry:
 		if (conn_configured & BIT(i))
 			continue;
 
-		if (pass == 0 && !connector->has_tile)
+		if (conn_seq == 0 && !connector->has_tile)
 			continue;
 
 		if (connector->status == connector_status_connected)
@@ -498,10 +498,8 @@ retry:
 		conn_configured |= BIT(i);
 	}
 
-	if ((conn_configured & mask) != mask) {
-		pass++;
+	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
 		goto retry;
-	}
 
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 249623d45be0..940bab22d464 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4891,6 +4891,12 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		break;
 	}
 
+	/* When byt can survive without system hang with dynamic
+	 * sw freq adjustments, this restriction can be lifted.
+	 */
+	if (IS_VALLEYVIEW(dev_priv))
+		goto skip_hw_write;
+
 	I915_WRITE(GEN6_RP_UP_EI,
 		   GT_INTERVAL_FROM_US(dev_priv, ei_up));
 	I915_WRITE(GEN6_RP_UP_THRESHOLD,
@@ -4911,6 +4917,7 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		   GEN6_RP_UP_BUSY_AVG |
 		   GEN6_RP_DOWN_IDLE_AVG);
 
+skip_hw_write:
 	dev_priv->rps.power = new_power;
 	dev_priv->rps.up_threshold = threshold_up;
 	dev_priv->rps.down_threshold = threshold_down;
@@ -7916,10 +7923,10 @@ static bool skl_pcode_try_request(struct drm_i915_private *dev_priv, u32 mbox,
  * @timeout_base_ms: timeout for polling with preemption enabled
  *
  * Keep resending the @request to @mbox until PCODE acknowledges it, PCODE
- * reports an error or an overall timeout of @timeout_base_ms+10 ms expires.
+ * reports an error or an overall timeout of @timeout_base_ms+50 ms expires.
  * The request is acknowledged once the PCODE reply dword equals @reply after
  * applying @reply_mask. Polling is first attempted with preemption enabled
- * for @timeout_base_ms and if this times out for another 10 ms with
+ * for @timeout_base_ms and if this times out for another 50 ms with
  * preemption disabled.
  *
  * Returns 0 on success, %-ETIMEDOUT in case of a timeout, <0 in case of some
@@ -7955,14 +7962,15 @@ int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
 	 * worst case) _and_ PCODE was busy for some reason even after a
 	 * (queued) request and @timeout_base_ms delay. As a workaround retry
 	 * the poll with preemption disabled to maximize the number of
-	 * requests. Increase the timeout from @timeout_base_ms to 10ms to
+	 * requests. Increase the timeout from @timeout_base_ms to 50ms to
 	 * account for interrupts that could reduce the number of these
-	 * requests.
+	 * requests, and for any quirks of the PCODE firmware that delays
+	 * the request completion.
 	 */
 	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
 	WARN_ON_ONCE(timeout_base_ms > 3);
 	preempt_disable();
-	ret = wait_for_atomic(COND, 10);
+	ret = wait_for_atomic(COND, 50);
 	preempt_enable();
 
 out:
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 9ef54688872a..9481ca9a3ae7 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -254,9 +254,6 @@ skl_update_plane(struct drm_plane *drm_plane,
 		int scaler_id = plane_state->scaler_id;
 		const struct intel_scaler *scaler;
 
-		DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n",
-			      plane_id, PS_PLANE_SEL(plane_id));
-
 		scaler = &crtc_state->scaler_state.scalers[scaler_id];
 
 		I915_WRITE(SKL_PS_CTRL(pipe, scaler_id),
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index abe08885a5ba..b7ff592b14f5 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -119,6 +119,8 @@ fw_domains_get(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
 
 	for_each_fw_domain_masked(d, fw_domains, dev_priv)
 		fw_domain_wait_ack(d);
+
+	dev_priv->uncore.fw_domains_active |= fw_domains;
 }
 
 static void
@@ -130,6 +132,8 @@ fw_domains_put(struct drm_i915_private *dev_priv, enum forcewake_domains fw_doma
 		fw_domain_put(d);
 		fw_domain_posting_read(d);
 	}
+
+	dev_priv->uncore.fw_domains_active &= ~fw_domains;
 }
 
 static void
@@ -240,10 +244,8 @@ intel_uncore_fw_release_timer(struct hrtimer *timer)
 	if (WARN_ON(domain->wake_count == 0))
 		domain->wake_count++;
 
-	if (--domain->wake_count == 0) {
+	if (--domain->wake_count == 0)
 		dev_priv->uncore.funcs.force_wake_put(dev_priv, domain->mask);
-		dev_priv->uncore.fw_domains_active &= ~domain->mask;
-	}
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
@@ -454,10 +456,8 @@ static void __intel_uncore_forcewake_get(struct drm_i915_private *dev_priv,
 			fw_domains &= ~domain->mask;
 	}
 
-	if (fw_domains) {
+	if (fw_domains)
 		dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
-		dev_priv->uncore.fw_domains_active |= fw_domains;
-	}
 }
 
 /**
@@ -968,7 +968,6 @@ static noinline void ___force_wake_auto(struct drm_i915_private *dev_priv,
 		fw_domain_arm_timer(domain);
 
 	dev_priv->uncore.funcs.force_wake_get(dev_priv, fw_domains);
-	dev_priv->uncore.fw_domains_active |= fw_domains;
 }
 
 static inline void __force_wake_auto(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index af267c35d813..ee5883f59be5 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -147,9 +147,6 @@ static int omap_gem_dmabuf_mmap(struct dma_buf *buffer,
 	struct drm_gem_object *obj = buffer->priv;
 	int ret = 0;
 
-	if (WARN_ON(!obj->filp))
-		return -EINVAL;
-
 	ret = drm_gem_mmap_obj(obj, omap_gem_mmap_size(obj), vma);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index d12b8978142f..72e1588580a1 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2984,6 +2984,12 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		    (rdev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
 		}
+	} else if (rdev->family == CHIP_OLAND) {
+		if ((rdev->pdev->device == 0x6604) &&
+		    (rdev->pdev->subsystem_vendor == 0x1028) &&
+		    (rdev->pdev->subsystem_device == 0x066F)) {
+			max_sclk = 75000;
+		}
 	}
 
 	if (rps->vce_active) {
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
index f80bf9385e41..d745e8b50fb8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c
@@ -464,6 +464,7 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
+	unsigned long flags;
 
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 	mutex_lock(&tilcdc_crtc->enable_lock);
@@ -484,7 +485,17 @@ static void tilcdc_crtc_enable(struct drm_crtc *crtc)
 	tilcdc_write_mask(dev, LCDC_RASTER_CTRL_REG,
 			  LCDC_PALETTE_LOAD_MODE(DATA_ONLY),
 			  LCDC_PALETTE_LOAD_MODE_MASK);
+
+	/* There is no real chance for a race here as the time stamp
+	 * is taken before the raster DMA is started. The spin-lock is
+	 * taken to have a memory barrier after taking the time-stamp
+	 * and to avoid a context switch between taking the stamp and
+	 * enabling the raster.
+	 */
+	spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+	tilcdc_crtc->last_vblank = ktime_get();
 	tilcdc_set(dev, LCDC_RASTER_CTRL_REG, LCDC_RASTER_ENABLE);
+	spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
 
 	drm_crtc_vblank_on(crtc);
 
@@ -539,7 +550,6 @@ static void tilcdc_crtc_off(struct drm_crtc *crtc, bool shutdown)
 	}
 
 	drm_flip_work_commit(&tilcdc_crtc->unref_work, priv->wq);
-	tilcdc_crtc->last_vblank = 0;
 
 	tilcdc_crtc->enabled = false;
 	mutex_unlock(&tilcdc_crtc->enable_lock);
@@ -602,7 +612,6 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
 {
 	struct tilcdc_crtc *tilcdc_crtc = to_tilcdc_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
-	unsigned long flags;
 
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
@@ -614,28 +623,30 @@ int tilcdc_crtc_update_fb(struct drm_crtc *crtc,
 	drm_framebuffer_reference(fb);
 
 	crtc->primary->fb = fb;
+	tilcdc_crtc->event = event;
 
-	spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
+	mutex_lock(&tilcdc_crtc->enable_lock);
 
-	if (crtc->hwmode.vrefresh && ktime_to_ns(tilcdc_crtc->last_vblank)) {
+	if (tilcdc_crtc->enabled) {
+		unsigned long flags;
 		ktime_t next_vblank;
 		s64 tdiff;
 
-		next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
-			1000000 / crtc->hwmode.vrefresh);
+		spin_lock_irqsave(&tilcdc_crtc->irq_lock, flags);
 
+		next_vblank = ktime_add_us(tilcdc_crtc->last_vblank,
+					   1000000 / crtc->hwmode.vrefresh);
 		tdiff = ktime_to_us(ktime_sub(next_vblank, ktime_get()));
 
 		if (tdiff < TILCDC_VBLANK_SAFETY_THRESHOLD_US)
 			tilcdc_crtc->next_fb = fb;
-	}
-
-	if (tilcdc_crtc->next_fb != fb)
-		set_scanout(crtc, fb);
+		else
+			set_scanout(crtc, fb);
 
-	tilcdc_crtc->event = event;
+		spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
+	}
 
-	spin_unlock_irqrestore(&tilcdc_crtc->irq_lock, flags);
+	mutex_unlock(&tilcdc_crtc->enable_lock);
 
 	return 0;
 }
@@ -1036,5 +1047,5 @@ int tilcdc_crtc_create(struct drm_device *dev)
 
 fail:
 	tilcdc_crtc_destroy(crtc);
-	return -ENOMEM;
+	return ret;
 }
diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h
index 407cb55df6ac..7fb97863c945 100644
--- a/include/uapi/drm/omap_drm.h
+++ b/include/uapi/drm/omap_drm.h
@@ -33,8 +33,8 @@ extern "C" {
 #define OMAP_PARAM_CHIPSET_ID	1	/* ie. 0x3430, 0x4430, etc */
 
 struct drm_omap_param {
-	uint64_t param;			/* in */
-	uint64_t value;			/* in (set_param), out (get_param) */
+	__u64 param;			/* in */
+	__u64 value;			/* in (set_param), out (get_param) */
 };
 
 #define OMAP_BO_SCANOUT		0x00000001	/* scanout capable (phys contiguous) */
@@ -53,18 +53,18 @@ struct drm_omap_param {
 #define OMAP_BO_TILED		(OMAP_BO_TILED_8 | OMAP_BO_TILED_16 | OMAP_BO_TILED_32)
 
 union omap_gem_size {
-	uint32_t bytes;		/* (for non-tiled formats) */
+	__u32 bytes;		/* (for non-tiled formats) */
 	struct {
-		uint16_t width;
-		uint16_t height;
+		__u16 width;
+		__u16 height;
 	} tiled;		/* (for tiled formats) */
 };
 
 struct drm_omap_gem_new {
 	union omap_gem_size size;	/* in */
-	uint32_t flags;			/* in */
-	uint32_t handle;		/* out */
-	uint32_t __pad;
+	__u32 flags;			/* in */
+	__u32 handle;			/* out */
+	__u32 __pad;
 };
 
 /* mask of operations: */
@@ -74,33 +74,33 @@ enum omap_gem_op {
 };
 
 struct drm_omap_gem_cpu_prep {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t op;			/* mask of omap_gem_op (in) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
 };
 
 struct drm_omap_gem_cpu_fini {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t op;			/* mask of omap_gem_op (in) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
 	/* TODO maybe here we pass down info about what regions are touched
 	 * by sw so we can be clever about cache ops?  For now a placeholder,
 	 * set to zero and we just do full buffer flush..
 	 */
-	uint32_t nregions;
-	uint32_t __pad;
+	__u32 nregions;
+	__u32 __pad;
 };
 
 struct drm_omap_gem_info {
-	uint32_t handle;		/* buffer handle (in) */
-	uint32_t pad;
-	uint64_t offset;		/* mmap offset (out) */
+	__u32 handle;			/* buffer handle (in) */
+	__u32 pad;
+	__u64 offset;			/* mmap offset (out) */
 	/* note: in case of tiled buffers, the user virtual size can be
 	 * different from the physical size (ie. how many pages are needed
 	 * to back the object) which is returned in DRM_IOCTL_GEM_OPEN..
 	 * This size here is the one that should be used if you want to
 	 * mmap() the buffer:
 	 */
-	uint32_t size;			/* virtual size for mmap'ing (out) */
-	uint32_t __pad;
+	__u32 size;			/* virtual size for mmap'ing (out) */
+	__u32 __pad;
 };
 
 #define DRM_OMAP_GET_PARAM		0x00