Merge tag 'v3.6-rc2' into drm-intel-next

Backmerge Linux 3.6-rc2 to resolve a few funny conflicts before we put
even more madness on top:

- drivers/gpu/drm/i915/i915_irq.c: Just a spurious WARN removed in
  -fixes, that has been changed in a variable-rename in -next, too.

- drivers/gpu/drm/i915/intel_ringbuffer.c: -next remove scratch_addr
  (since all their users have been extracted in another fucntion),
  -fixes added another user for a hw workaroudn.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

100 files changed, 1752 insertions, 1222 deletions

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 5873e481e5d..a8743c399e8 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1039,6 +1039,24 @@ mode_in_range(const struct drm_display_mode *mode, struct edid *edid,
 	return true;
 }
 
+static bool valid_inferred_mode(const struct drm_connector *connector,
+				const struct drm_display_mode *mode)
+{
+	struct drm_display_mode *m;
+	bool ok = false;
+
+	list_for_each_entry(m, &connector->probed_modes, head) {
+		if (mode->hdisplay == m->hdisplay &&
+		    mode->vdisplay == m->vdisplay &&
+		    drm_mode_vrefresh(mode) == drm_mode_vrefresh(m))
+			return false; /* duplicated */
+		if (mode->hdisplay <= m->hdisplay &&
+		    mode->vdisplay <= m->vdisplay)
+			ok = true;
+	}
+	return ok;
+}
+
 static int
 drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			struct detailed_timing *timing)
@@ -1048,7 +1066,8 @@ drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 	struct drm_device *dev = connector->dev;
 
 	for (i = 0; i < drm_num_dmt_modes; i++) {
-		if (mode_in_range(drm_dmt_modes + i, edid, timing)) {
+		if (mode_in_range(drm_dmt_modes + i, edid, timing) &&
+		    valid_inferred_mode(connector, drm_dmt_modes + i)) {
 			newmode = drm_mode_duplicate(dev, &drm_dmt_modes[i]);
 			if (newmode) {
 				drm_mode_probed_add(connector, newmode);
@@ -1088,7 +1107,8 @@ drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			return modes;
 
 		fixup_mode_1366x768(newmode);
-		if (!mode_in_range(newmode, edid, timing)) {
+		if (!mode_in_range(newmode, edid, timing) ||
+		    !valid_inferred_mode(connector, newmode)) {
 			drm_mode_destroy(dev, newmode);
 			continue;
 		}
@@ -1116,7 +1136,8 @@ drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			return modes;
 
 		fixup_mode_1366x768(newmode);
-		if (!mode_in_range(newmode, edid, timing)) {
+		if (!mode_in_range(newmode, edid, timing) ||
+		    !valid_inferred_mode(connector, newmode)) {
 			drm_mode_destroy(dev, newmode);
 			continue;
 		}
diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c
index 66d4a28ad5a..0303935d10e 100644
--- a/drivers/gpu/drm/drm_edid_load.c
+++ b/drivers/gpu/drm/drm_edid_load.c
@@ -119,7 +119,7 @@ static int edid_load(struct drm_connector *connector, char *name,
 {
 	const struct firmware *fw;
 	struct platform_device *pdev;
-	u8 *fwdata = NULL, *edid;
+	u8 *fwdata = NULL, *edid, *new_edid;
 	int fwsize, expected;
 	int builtin = 0, err = 0;
 	int i, valid_extensions = 0;
@@ -195,12 +195,14 @@ static int edid_load(struct drm_connector *connector, char *name,
 		    "\"%s\" for connector \"%s\"\n", valid_extensions,
 		    edid[0x7e], name, connector_name);
 		edid[0x7e] = valid_extensions;
-		edid = krealloc(edid, (valid_extensions + 1) * EDID_LENGTH,
+		new_edid = krealloc(edid, (valid_extensions + 1) * EDID_LENGTH,
 		    GFP_KERNEL);
-		if (edid == NULL) {
+		if (new_edid == NULL) {
 			err = -ENOMEM;
+			kfree(edid);
 			goto relfw_out;
 		}
+		edid = new_edid;
 	}
 
 	connector->display_info.raw_edid = edid;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index d25a61739a7..5062eec673f 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -140,12 +140,12 @@ int drm_open(struct inode *inode, struct file *filp)
 	}
 	if (!retcode) {
 		mutex_lock(&dev->struct_mutex);
-		if (minor->type == DRM_MINOR_LEGACY) {
-			if (dev->dev_mapping == NULL)
-				dev->dev_mapping = inode->i_mapping;
-			else if (dev->dev_mapping != inode->i_mapping)
-				retcode = -ENODEV;
-		}
+		if (dev->dev_mapping == NULL)
+			dev->dev_mapping = &inode->i_data;
+		/* ihold ensures nobody can remove inode with our i_data */
+		ihold(container_of(dev->dev_mapping, struct inode, i_data));
+		inode->i_mapping = dev->dev_mapping;
+		filp->f_mapping = dev->dev_mapping;
 		mutex_unlock(&dev->struct_mutex);
 	}
 
@@ -509,6 +509,9 @@ int drm_release(struct inode *inode, struct file *filp)
 		}
 	}
 
+	BUG_ON(dev->dev_mapping == NULL);
+	iput(container_of(dev->dev_mapping, struct inode, i_data));
+
 	/* drop the reference held my the file priv */
 	drm_master_put(&file_priv->master);
 	file_priv->is_master = 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
index bf791fa0e50..d9568198c30 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c
@@ -196,7 +196,8 @@ static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
 	return ret;
 }
 
-struct drm_encoder *exynos_drm_best_encoder(struct drm_connector *connector)
+static struct drm_encoder *exynos_drm_best_encoder(
+						struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct exynos_drm_connector *exynos_connector =
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index eaf630dc5db..84dd099eae3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -33,7 +33,6 @@
 #include "exynos_drm_fbdev.h"
 
 static LIST_HEAD(exynos_drm_subdrv_list);
-static struct drm_device *drm_dev;
 
 static int exynos_drm_subdrv_probe(struct drm_device *dev,
 					struct exynos_drm_subdrv *subdrv)
@@ -120,8 +119,6 @@ int exynos_drm_device_register(struct drm_device *dev)
 	if (!dev)
 		return -EINVAL;
 
-	drm_dev = dev;
-
 	list_for_each_entry_safe(subdrv, n, &exynos_drm_subdrv_list, list) {
 		subdrv->drm_dev = dev;
 		err = exynos_drm_subdrv_probe(dev, subdrv);
@@ -149,8 +146,6 @@ int exynos_drm_device_unregister(struct drm_device *dev)
 	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list)
 		exynos_drm_subdrv_remove(dev, subdrv);
 
-	drm_dev = NULL;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(exynos_drm_device_unregister);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 32a34c85899..abb1e2f8227 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -29,21 +29,23 @@
 #include "drmP.h"
 #include "drm_crtc_helper.h"
 
-#include "exynos_drm_crtc.h"
 #include "exynos_drm_drv.h"
-#include "exynos_drm_fb.h"
 #include "exynos_drm_encoder.h"
-#include "exynos_drm_gem.h"
+#include "exynos_drm_plane.h"
 
 #define to_exynos_crtc(x)	container_of(x, struct exynos_drm_crtc,\
 				drm_crtc)
 
+enum exynos_crtc_mode {
+	CRTC_MODE_NORMAL,	/* normal mode */
+	CRTC_MODE_BLANK,	/* The private plane of crtc is blank */
+};
+
 /*
  * Exynos specific crtc structure.
  *
  * @drm_crtc: crtc object.
- * @overlay: contain information common to display controller and hdmi and
- *	contents of this overlay object would be copied to sub driver size.
+ * @drm_plane: pointer of private plane object for this crtc
  * @pipe: a crtc index created at load() with a new crtc object creation
  *	and the crtc object would be set to private->crtc array
  *	to get a crtc object corresponding to this pipe from private->crtc
@@ -52,115 +54,16 @@
  *	we can refer to the crtc to current hardware interrupt occured through
  *	this pipe value.
  * @dpms: store the crtc dpms value
+ * @mode: store the crtc mode value
  */
 struct exynos_drm_crtc {
 	struct drm_crtc			drm_crtc;
-	struct exynos_drm_overlay	overlay;
+	struct drm_plane		*plane;
 	unsigned int			pipe;
 	unsigned int			dpms;
+	enum exynos_crtc_mode		mode;
 };
 
-static void exynos_drm_crtc_apply(struct drm_crtc *crtc)
-{
-	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
-	struct exynos_drm_overlay *overlay = &exynos_crtc->overlay;
-
-	exynos_drm_fn_encoder(crtc, overlay,
-			exynos_drm_encoder_crtc_mode_set);
-	exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
-			exynos_drm_encoder_crtc_commit);
-}
-
-int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
-			      struct drm_framebuffer *fb,
-			      struct drm_display_mode *mode,
-			      struct exynos_drm_crtc_pos *pos)
-{
-	struct exynos_drm_gem_buf *buffer;
-	unsigned int actual_w;
-	unsigned int actual_h;
-	int nr = exynos_drm_format_num_buffers(fb->pixel_format);
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		buffer = exynos_drm_fb_buffer(fb, i);
-		if (!buffer) {
-			DRM_LOG_KMS("buffer is null\n");
-			return -EFAULT;
-		}
-
-		overlay->dma_addr[i] = buffer->dma_addr;
-		overlay->vaddr[i] = buffer->kvaddr;
-
-		DRM_DEBUG_KMS("buffer: %d, vaddr = 0x%lx, dma_addr = 0x%lx\n",
-				i, (unsigned long)overlay->vaddr[i],
-				(unsigned long)overlay->dma_addr[i]);
-	}
-
-	actual_w = min((mode->hdisplay - pos->crtc_x), pos->crtc_w);
-	actual_h = min((mode->vdisplay - pos->crtc_y), pos->crtc_h);
-
-	/* set drm framebuffer data. */
-	overlay->fb_x = pos->fb_x;
-	overlay->fb_y = pos->fb_y;
-	overlay->fb_width = fb->width;
-	overlay->fb_height = fb->height;
-	overlay->src_width = pos->src_w;
-	overlay->src_height = pos->src_h;
-	overlay->bpp = fb->bits_per_pixel;
-	overlay->pitch = fb->pitches[0];
-	overlay->pixel_format = fb->pixel_format;
-
-	/* set overlay range to be displayed. */
-	overlay->crtc_x = pos->crtc_x;
-	overlay->crtc_y = pos->crtc_y;
-	overlay->crtc_width = actual_w;
-	overlay->crtc_height = actual_h;
-
-	/* set drm mode data. */
-	overlay->mode_width = mode->hdisplay;
-	overlay->mode_height = mode->vdisplay;
-	overlay->refresh = mode->vrefresh;
-	overlay->scan_flag = mode->flags;
-
-	DRM_DEBUG_KMS("overlay : offset_x/y(%d,%d), width/height(%d,%d)",
-			overlay->crtc_x, overlay->crtc_y,
-			overlay->crtc_width, overlay->crtc_height);
-
-	return 0;
-}
-
-static int exynos_drm_crtc_update(struct drm_crtc *crtc)
-{
-	struct exynos_drm_crtc *exynos_crtc;
-	struct exynos_drm_overlay *overlay;
-	struct exynos_drm_crtc_pos pos;
-	struct drm_display_mode *mode = &crtc->mode;
-	struct drm_framebuffer *fb = crtc->fb;
-
-	if (!mode || !fb)
-		return -EINVAL;
-
-	exynos_crtc = to_exynos_crtc(crtc);
-	overlay = &exynos_crtc->overlay;
-
-	memset(&pos, 0, sizeof(struct exynos_drm_crtc_pos));
-
-	/* it means the offset of framebuffer to be displayed. */
-	pos.fb_x = crtc->x;
-	pos.fb_y = crtc->y;
-
-	/* OSD position to be displayed. */
-	pos.crtc_x = 0;
-	pos.crtc_y = 0;
-	pos.crtc_w = fb->width - crtc->x;
-	pos.crtc_h = fb->height - crtc->y;
-	pos.src_w = pos.crtc_w;
-	pos.src_h = pos.crtc_h;
-
-	return exynos_drm_overlay_update(overlay, crtc->fb, mode, &pos);
-}
-
 static void exynos_drm_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
@@ -175,23 +78,8 @@ static void exynos_drm_crtc_dpms(struct drm_crtc *crtc, int mode)
 
 	mutex_lock(&dev->struct_mutex);
 
-	switch (mode) {
-	case DRM_MODE_DPMS_ON:
-		exynos_drm_fn_encoder(crtc, &mode,
-				exynos_drm_encoder_crtc_dpms);
-		exynos_crtc->dpms = mode;
-		break;
-	case DRM_MODE_DPMS_STANDBY:
-	case DRM_MODE_DPMS_SUSPEND:
-	case DRM_MODE_DPMS_OFF:
-		exynos_drm_fn_encoder(crtc, &mode,
-				exynos_drm_encoder_crtc_dpms);
-		exynos_crtc->dpms = mode;
-		break;
-	default:
-		DRM_ERROR("unspecified mode %d\n", mode);
-		break;
-	}
+	exynos_drm_fn_encoder(crtc, &mode, exynos_drm_encoder_crtc_dpms);
+	exynos_crtc->dpms = mode;
 
 	mutex_unlock(&dev->struct_mutex);
 }
@@ -209,30 +97,8 @@ static void exynos_drm_crtc_commit(struct drm_crtc *crtc)
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	/*
-	 * when set_crtc is requested from user or at booting time,
-	 * crtc->commit would be called without dpms call so if dpms is
-	 * no power on then crtc->dpms should be called
-	 * with DRM_MODE_DPMS_ON for the hardware power to be on.
-	 */
-	if (exynos_crtc->dpms != DRM_MODE_DPMS_ON) {
-		int mode = DRM_MODE_DPMS_ON;
-
-		/*
-		 * enable hardware(power on) to all encoders hdmi connected
-		 * to current crtc.
-		 */
-		exynos_drm_crtc_dpms(crtc, mode);
-		/*
-		 * enable dma to all encoders connected to current crtc and
-		 * lcd panel.
-		 */
-		exynos_drm_fn_encoder(crtc, &mode,
-					exynos_drm_encoder_dpms_from_crtc);
-	}
-
-	exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
-			exynos_drm_encoder_crtc_commit);
+	exynos_plane_commit(exynos_crtc->plane);
+	exynos_plane_dpms(exynos_crtc->plane, DRM_MODE_DPMS_ON);
 }
 
 static bool
@@ -251,31 +117,61 @@ exynos_drm_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
 			  struct drm_display_mode *adjusted_mode, int x, int y,
 			  struct drm_framebuffer *old_fb)
 {
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+	struct drm_plane *plane = exynos_crtc->plane;
+	unsigned int crtc_w;
+	unsigned int crtc_h;
+	int pipe = exynos_crtc->pipe;
+	int ret;
+
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
+	exynos_drm_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
+
 	/*
 	 * copy the mode data adjusted by mode_fixup() into crtc->mode
 	 * so that hardware can be seet to proper mode.
 	 */
 	memcpy(&crtc->mode, adjusted_mode, sizeof(*adjusted_mode));
 
-	return exynos_drm_crtc_update(crtc);
+	crtc_w = crtc->fb->width - x;
+	crtc_h = crtc->fb->height - y;
+
+	ret = exynos_plane_mode_set(plane, crtc, crtc->fb, 0, 0, crtc_w, crtc_h,
+				    x, y, crtc_w, crtc_h);
+	if (ret)
+		return ret;
+
+	plane->crtc = crtc;
+	plane->fb = crtc->fb;
+
+	exynos_drm_fn_encoder(crtc, &pipe, exynos_drm_encoder_crtc_pipe);
+
+	return 0;
 }
 
 static int exynos_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 					  struct drm_framebuffer *old_fb)
 {
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+	struct drm_plane *plane = exynos_crtc->plane;
+	unsigned int crtc_w;
+	unsigned int crtc_h;
 	int ret;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	ret = exynos_drm_crtc_update(crtc);
+	crtc_w = crtc->fb->width - x;
+	crtc_h = crtc->fb->height - y;
+
+	ret = exynos_plane_mode_set(plane, crtc, crtc->fb, 0, 0, crtc_w, crtc_h,
+				    x, y, crtc_w, crtc_h);
 	if (ret)
 		return ret;
 
-	exynos_drm_crtc_apply(crtc);
+	exynos_drm_crtc_commit(crtc);
 
-	return ret;
+	return 0;
 }
 
 static void exynos_drm_crtc_load_lut(struct drm_crtc *crtc)
@@ -284,6 +180,16 @@ static void exynos_drm_crtc_load_lut(struct drm_crtc *crtc)
 	/* drm framework doesn't check NULL */
 }
 
+static void exynos_drm_crtc_disable(struct drm_crtc *crtc)
+{
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+
+	DRM_DEBUG_KMS("%s\n", __FILE__);
+
+	exynos_plane_dpms(exynos_crtc->plane, DRM_MODE_DPMS_OFF);
+	exynos_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+}
+
 static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
 	.dpms		= exynos_drm_crtc_dpms,
 	.prepare	= exynos_drm_crtc_prepare,
@@ -292,6 +198,7 @@ static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
 	.mode_set	= exynos_drm_crtc_mode_set,
 	.mode_set_base	= exynos_drm_crtc_mode_set_base,
 	.load_lut	= exynos_drm_crtc_load_lut,
+	.disable	= exynos_drm_crtc_disable,
 };
 
 static int exynos_drm_crtc_page_flip(struct drm_crtc *crtc,
@@ -327,7 +234,8 @@ static int exynos_drm_crtc_page_flip(struct drm_crtc *crtc,
 				&dev_priv->pageflip_event_list);
 
 		crtc->fb = fb;
-		ret = exynos_drm_crtc_update(crtc);
+		ret = exynos_drm_crtc_mode_set_base(crtc, crtc->x, crtc->y,
+						    NULL);
 		if (ret) {
 			crtc->fb = old_fb;
 			drm_vblank_put(dev, exynos_crtc->pipe);
@@ -335,14 +243,6 @@ static int exynos_drm_crtc_page_flip(struct drm_crtc *crtc,
 
 			goto out;
 		}
-
-		/*
-		 * the values related to a buffer of the drm framebuffer
-		 * to be applied should be set at here. because these values
-		 * first, are set to shadow registers and then to
-		 * real registers at vsync front porch period.
-		 */
-		exynos_drm_crtc_apply(crtc);
 	}
 out:
 	mutex_unlock(&dev->struct_mutex);
@@ -362,18 +262,73 @@ static void exynos_drm_crtc_destroy(struct drm_crtc *crtc)
 	kfree(exynos_crtc);
 }
 
+static int exynos_drm_crtc_set_property(struct drm_crtc *crtc,
+					struct drm_property *property,
+					uint64_t val)
+{
+	struct drm_device *dev = crtc->dev;
+	struct exynos_drm_private *dev_priv = dev->dev_private;
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	if (property == dev_priv->crtc_mode_property) {
+		enum exynos_crtc_mode mode = val;
+
+		if (mode == exynos_crtc->mode)
+			return 0;
+
+		exynos_crtc->mode = mode;
+
+		switch (mode) {
+		case CRTC_MODE_NORMAL:
+			exynos_drm_crtc_commit(crtc);
+			break;
+		case CRTC_MODE_BLANK:
+			exynos_plane_dpms(exynos_crtc->plane,
+					  DRM_MODE_DPMS_OFF);
+			break;
+		default:
+			break;
+		}
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static struct drm_crtc_funcs exynos_crtc_funcs = {
 	.set_config	= drm_crtc_helper_set_config,
 	.page_flip	= exynos_drm_crtc_page_flip,
 	.destroy	= exynos_drm_crtc_destroy,
+	.set_property	= exynos_drm_crtc_set_property,
+};
+
+static const struct drm_prop_enum_list mode_names[] = {
+	{ CRTC_MODE_NORMAL, "normal" },
+	{ CRTC_MODE_BLANK, "blank" },
 };
 
-struct exynos_drm_overlay *get_exynos_drm_overlay(struct drm_device *dev,
-		struct drm_crtc *crtc)
+static void exynos_drm_crtc_attach_mode_property(struct drm_crtc *crtc)
 {
-	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct exynos_drm_private *dev_priv = dev->dev_private;
+	struct drm_property *prop;
 
-	return &exynos_crtc->overlay;
+	DRM_DEBUG_KMS("%s\n", __func__);
+
+	prop = dev_priv->crtc_mode_property;
+	if (!prop) {
+		prop = drm_property_create_enum(dev, 0, "mode", mode_names,
+						ARRAY_SIZE(mode_names));
+		if (!prop)
+			return;
+
+		dev_priv->crtc_mode_property = prop;
+	}
+
+	drm_object_attach_property(&crtc->base, prop, 0);
 }
 
 int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr)
@@ -392,7 +347,12 @@ int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr)
 
 	exynos_crtc->pipe = nr;
 	exynos_crtc->dpms = DRM_MODE_DPMS_OFF;
-	exynos_crtc->overlay.zpos = DEFAULT_ZPOS;
+	exynos_crtc->plane = exynos_plane_init(dev, 1 << nr, true);
+	if (!exynos_crtc->plane) {
+		kfree(exynos_crtc);
+		return -ENOMEM;
+	}
+
 	crtc = &exynos_crtc->drm_crtc;
 
 	private->crtc[nr] = crtc;
@@ -400,6 +360,8 @@ int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr)
 	drm_crtc_init(dev, crtc, &exynos_crtc_funcs);
 	drm_crtc_helper_add(crtc, &exynos_crtc_helper_funcs);
 
+	exynos_drm_crtc_attach_mode_property(crtc);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index 16b8e2195a0..6bae8d8c250 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -29,39 +29,8 @@
 #ifndef _EXYNOS_DRM_CRTC_H_
 #define _EXYNOS_DRM_CRTC_H_
 
-struct exynos_drm_overlay *get_exynos_drm_overlay(struct drm_device *dev,
-		struct drm_crtc *crtc);
 int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr);
 int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int crtc);
 void exynos_drm_crtc_disable_vblank(struct drm_device *dev, int crtc);
 
-/*
- * Exynos specific crtc postion structure.
- *
- * @fb_x: offset x on a framebuffer to be displyed
- *	- the unit is screen coordinates.
- * @fb_y: offset y on a framebuffer to be displayed
- *	- the unit is screen coordinates.
- * @src_w: width of source area to be displayed from a framebuffer.
- * @src_h: height of source area to be displayed from a framebuffer.
- * @crtc_x: offset x on hardware screen.
- * @crtc_y: offset y on hardware screen.
- * @crtc_w: width of hardware screen.
- * @crtc_h: height of hardware screen.
- */
-struct exynos_drm_crtc_pos {
-	unsigned int fb_x;
-	unsigned int fb_y;
-	unsigned int src_w;
-	unsigned int src_h;
-	unsigned int crtc_x;
-	unsigned int crtc_y;
-	unsigned int crtc_w;
-	unsigned int crtc_h;
-};
-
-int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
-			      struct drm_framebuffer *fb,
-			      struct drm_display_mode *mode,
-			      struct exynos_drm_crtc_pos *pos);
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index 274909271c3..613bf8a5d9b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -25,6 +25,7 @@
 
 #include "drmP.h"
 #include "drm.h"
+#include "exynos_drm.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_gem.h"
 
@@ -86,6 +87,10 @@ static struct sg_table *
 	npages = buf->size / buf->page_size;
 
 	sgt = exynos_pages_to_sg(buf->pages, npages, buf->page_size);
+	if (!sgt) {
+		DRM_DEBUG_PRIME("exynos_pages_to_sg returned NULL!\n");
+		goto err_unlock;
+	}
 	nents = dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir);
 
 	DRM_DEBUG_PRIME("npages = %d buffer size = 0x%lx page_size = 0x%lx\n",
@@ -186,7 +191,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 	struct exynos_drm_gem_obj *exynos_gem_obj;
 	struct exynos_drm_gem_buf *buffer;
 	struct page *page;
-	int ret, i = 0;
+	int ret;
 
 	DRM_DEBUG_PRIME("%s\n", __FILE__);
 
@@ -210,7 +215,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 
 
 	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR(sgt)) {
+	if (IS_ERR_OR_NULL(sgt)) {
 		ret = PTR_ERR(sgt);
 		goto err_buf_detach;
 	}
@@ -236,13 +241,25 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 	}
 
 	sgl = sgt->sgl;
-	buffer->dma_addr = sg_dma_address(sgl);
 
-	while (i < sgt->nents) {
-		buffer->pages[i] = sg_page(sgl);
-		buffer->size += sg_dma_len(sgl);
-		sgl = sg_next(sgl);
-		i++;
+	if (sgt->nents == 1) {
+		buffer->dma_addr = sg_dma_address(sgt->sgl);
+		buffer->size = sg_dma_len(sgt->sgl);
+
+		/* always physically continuous memory if sgt->nents is 1. */
+		exynos_gem_obj->flags |= EXYNOS_BO_CONTIG;
+	} else {
+		unsigned int i = 0;
+
+		buffer->dma_addr = sg_dma_address(sgl);
+		while (i < sgt->nents) {
+			buffer->pages[i] = sg_page(sgl);
+			buffer->size += sg_dma_len(sgl);
+			sgl = sg_next(sgl);
+			i++;
+		}
+
+		exynos_gem_obj->flags |= EXYNOS_BO_NONCONTIG;
 	}
 
 	exynos_gem_obj->buffer = buffer;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index d6de2e07fa0..ebacec6f1e4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -85,8 +85,11 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 	}
 
 	for (nr = 0; nr < MAX_PLANE; nr++) {
-		ret = exynos_plane_init(dev, nr);
-		if (ret)
+		struct drm_plane *plane;
+		unsigned int possible_crtcs = (1 << MAX_CRTC) - 1;
+
+		plane = exynos_plane_init(dev, possible_crtcs, false);
+		if (!plane)
 			goto err_crtc;
 	}
 
@@ -221,8 +224,6 @@ static struct drm_ioctl_desc exynos_ioctls[] = {
 			exynos_drm_gem_mmap_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_GET,
 			exynos_drm_gem_get_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(EXYNOS_PLANE_SET_ZPOS, exynos_plane_set_zpos_ioctl,
-			DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_VIDI_CONNECTION,
 			vidi_connection_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_G2D_GET_VER,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 277653d5fda..e22704b249d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -59,12 +59,14 @@ enum exynos_drm_output_type {
  *
  * @mode_set: copy drm overlay info to hw specific overlay info.
  * @commit: apply hardware specific overlay data to registers.
+ * @enable: enable hardware specific overlay.
  * @disable: disable hardware specific overlay.
  */
 struct exynos_drm_overlay_ops {
 	void (*mode_set)(struct device *subdrv_dev,
 			 struct exynos_drm_overlay *overlay);
 	void (*commit)(struct device *subdrv_dev, int zpos);
+	void (*enable)(struct device *subdrv_dev, int zpos);
 	void (*disable)(struct device *subdrv_dev, int zpos);
 };
 
@@ -235,6 +237,8 @@ struct exynos_drm_private {
 	 * this array is used to be aware of which crtc did it request vblank.
 	 */
 	struct drm_crtc *crtc[MAX_CRTC];
+	struct drm_property *plane_zpos_property;
+	struct drm_property *crtc_mode_property;
 };
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.c b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
index 4a13a747f5d..2c037cd7d2d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
@@ -30,7 +30,6 @@
 #include "drm_crtc_helper.h"
 
 #include "exynos_drm_drv.h"
-#include "exynos_drm_crtc.h"
 #include "exynos_drm_encoder.h"
 
 #define to_exynos_encoder(x)	container_of(x, struct exynos_drm_encoder,\
@@ -136,21 +135,16 @@ static void exynos_drm_encoder_mode_set(struct drm_encoder *encoder,
 	struct drm_connector *connector;
 	struct exynos_drm_manager *manager = exynos_drm_get_manager(encoder);
 	struct exynos_drm_manager_ops *manager_ops = manager->ops;
-	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
-	struct exynos_drm_overlay *overlay = get_exynos_drm_overlay(dev,
-						encoder->crtc);
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
+	exynos_drm_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
+		if (connector->encoder == encoder)
 			if (manager_ops && manager_ops->mode_set)
 				manager_ops->mode_set(manager->dev,
 							adjusted_mode);
-
-			if (overlay_ops && overlay_ops->mode_set)
-				overlay_ops->mode_set(manager->dev, overlay);
-		}
 	}
 }
 
@@ -310,8 +304,8 @@ void exynos_drm_enable_vblank(struct drm_encoder *encoder, void *data)
 	struct exynos_drm_manager_ops *manager_ops = manager->ops;
 	int crtc = *(int *)data;
 
-	if (manager->pipe == -1)
-		manager->pipe = crtc;
+	if (manager->pipe != crtc)
+		return;
 
 	if (manager_ops->enable_vblank)
 		manager_ops->enable_vblank(manager->dev);
@@ -324,34 +318,41 @@ void exynos_drm_disable_vblank(struct drm_encoder *encoder, void *data)
 	struct exynos_drm_manager_ops *manager_ops = manager->ops;
 	int crtc = *(int *)data;
 
-	if (manager->pipe == -1)
-		manager->pipe = crtc;
+	if (manager->pipe != crtc)
+		return;
 
 	if (manager_ops->disable_vblank)
 		manager_ops->disable_vblank(manager->dev);
 }
 
-void exynos_drm_encoder_crtc_plane_commit(struct drm_encoder *encoder,
-					  void *data)
+void exynos_drm_encoder_crtc_dpms(struct drm_encoder *encoder, void *data)
 {
-	struct exynos_drm_manager *manager =
-		to_exynos_encoder(encoder)->manager;
-	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
-	int zpos = DEFAULT_ZPOS;
+	struct exynos_drm_encoder *exynos_encoder = to_exynos_encoder(encoder);
+	struct exynos_drm_manager *manager = exynos_encoder->manager;
+	struct exynos_drm_manager_ops *manager_ops = manager->ops;
+	int mode = *(int *)data;
 
-	if (data)
-		zpos = *(int *)data;
+	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	if (overlay_ops && overlay_ops->commit)
-		overlay_ops->commit(manager->dev, zpos);
+	if (manager_ops && manager_ops->dpms)
+		manager_ops->dpms(manager->dev, mode);
+
+	/*
+	 * if this condition is ok then it means that the crtc is already
+	 * detached from encoder and last function for detaching is properly
+	 * done, so clear pipe from manager to prevent repeated call.
+	 */
+	if (mode > DRM_MODE_DPMS_ON) {
+		if (!encoder->crtc)
+			manager->pipe = -1;
+	}
 }
 
-void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data)
+void exynos_drm_encoder_crtc_pipe(struct drm_encoder *encoder, void *data)
 {
 	struct exynos_drm_manager *manager =
 		to_exynos_encoder(encoder)->manager;
-	int crtc = *(int *)data;
-	int zpos = DEFAULT_ZPOS;
+	int pipe = *(int *)data;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -359,76 +360,62 @@ void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data)
 	 * when crtc is detached from encoder, this pipe is used
 	 * to select manager operation
 	 */
-	manager->pipe = crtc;
-
-	exynos_drm_encoder_crtc_plane_commit(encoder, &zpos);
+	manager->pipe = pipe;
 }
 
-void exynos_drm_encoder_dpms_from_crtc(struct drm_encoder *encoder, void *data)
+void exynos_drm_encoder_plane_mode_set(struct drm_encoder *encoder, void *data)
 {
-	struct exynos_drm_encoder *exynos_encoder = to_exynos_encoder(encoder);
-	int mode = *(int *)data;
+	struct exynos_drm_manager *manager =
+		to_exynos_encoder(encoder)->manager;
+	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+	struct exynos_drm_overlay *overlay = data;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	exynos_drm_encoder_dpms(encoder, mode);
-
-	exynos_encoder->dpms = mode;
+	if (overlay_ops && overlay_ops->mode_set)
+		overlay_ops->mode_set(manager->dev, overlay);
 }
 
-void exynos_drm_encoder_crtc_dpms(struct drm_encoder *encoder, void *data)
+void exynos_drm_encoder_plane_commit(struct drm_encoder *encoder, void *data)
 {
-	struct drm_device *dev = encoder->dev;
-	struct exynos_drm_encoder *exynos_encoder = to_exynos_encoder(encoder);
-	struct exynos_drm_manager *manager = exynos_encoder->manager;
-	struct exynos_drm_manager_ops *manager_ops = manager->ops;
-	struct drm_connector *connector;
-	int mode = *(int *)data;
+	struct exynos_drm_manager *manager =
+		to_exynos_encoder(encoder)->manager;
+	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+	int zpos = DEFAULT_ZPOS;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	if (manager_ops && manager_ops->dpms)
-		manager_ops->dpms(manager->dev, mode);
-
-	/*
-	 * set current dpms mode to the connector connected to
-	 * current encoder. connector->dpms would be checked
-	 * at drm_helper_connector_dpms()
-	 */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
-		if (connector->encoder == encoder)
-			connector->dpms = mode;
+	if (data)
+		zpos = *(int *)data;
 
-	/*
-	 * if this condition is ok then it means that the crtc is already
-	 * detached from encoder and last function for detaching is properly
-	 * done, so clear pipe from manager to prevent repeated call.
-	 */
-	if (mode > DRM_MODE_DPMS_ON) {
-		if (!encoder->crtc)
-			manager->pipe = -1;
-	}
+	if (overlay_ops && overlay_ops->commit)
+		overlay_ops->commit(manager->dev, zpos);
 }
 
-void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data)
+void exynos_drm_encoder_plane_enable(struct drm_encoder *encoder, void *data)
 {
 	struct exynos_drm_manager *manager =
 		to_exynos_encoder(encoder)->manager;
 	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
-	struct exynos_drm_overlay *overlay = data;
+	int zpos = DEFAULT_ZPOS;
 
-	if (overlay_ops && overlay_ops->mode_set)
-		overlay_ops->mode_set(manager->dev, overlay);
+	DRM_DEBUG_KMS("%s\n", __FILE__);
+
+	if (data)
+		zpos = *(int *)data;
+
+	if (overlay_ops && overlay_ops->enable)
+		overlay_ops->enable(manager->dev, zpos);
 }
 
-void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data)
+void exynos_drm_encoder_plane_disable(struct drm_encoder *encoder, void *data)
 {
 	struct exynos_drm_manager *manager =
 		to_exynos_encoder(encoder)->manager;
 	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
 	int zpos = DEFAULT_ZPOS;
 
-	DRM_DEBUG_KMS("\n");
+	DRM_DEBUG_KMS("%s\n", __FILE__);
 
 	if (data)
 		zpos = *(int *)data;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.h b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
index eb7d2316847..6470d9ddf5a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
@@ -40,13 +40,11 @@ void exynos_drm_fn_encoder(struct drm_crtc *crtc, void *data,
 			    void (*fn)(struct drm_encoder *, void *));
 void exynos_drm_enable_vblank(struct drm_encoder *encoder, void *data);
 void exynos_drm_disable_vblank(struct drm_encoder *encoder, void *data);
-void exynos_drm_encoder_crtc_plane_commit(struct drm_encoder *encoder,
-					  void *data);
-void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data);
-void exynos_drm_encoder_dpms_from_crtc(struct drm_encoder *encoder,
-					void *data);
 void exynos_drm_encoder_crtc_dpms(struct drm_encoder *encoder, void *data);
-void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data);
-void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_crtc_pipe(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_plane_mode_set(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_plane_commit(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_plane_enable(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_plane_disable(struct drm_encoder *encoder, void *data);
 
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 29fdbfeb43c..a68d2b313f0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -78,7 +78,6 @@ struct fimd_context {
 	struct drm_crtc			*crtc;
 	struct clk			*bus_clk;
 	struct clk			*lcd_clk;
-	struct resource			*regs_res;
 	void __iomem			*regs;
 	struct fimd_win_data		win_data[WINDOWS_NR];
 	unsigned int			clkdiv;
@@ -813,7 +812,7 @@ static int __devinit fimd_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -838,33 +837,26 @@ static int __devinit fimd_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
-	ctx->regs_res = request_mem_region(res->start, resource_size(res),
-					   dev_name(dev));
-	if (!ctx->regs_res) {
-		dev_err(dev, "failed to claim register region\n");
-		ret = -ENOENT;
-		goto err_clk;
-	}
-
-	ctx->regs = ioremap(res->start, resource_size(res));
+	ctx->regs = devm_request_and_ioremap(&pdev->dev, res);
 	if (!ctx->regs) {
 		dev_err(dev, "failed to map registers\n");
 		ret = -ENXIO;
-		goto err_req_region_io;
+		goto err_clk;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res) {
 		dev_err(dev, "irq request failed.\n");
-		goto err_req_region_irq;
+		goto err_clk;
 	}
 
 	ctx->irq = res->start;
 
-	ret = request_irq(ctx->irq, fimd_irq_handler, 0, "drm_fimd", ctx);
-	if (ret < 0) {
+	ret = devm_request_irq(&pdev->dev, ctx->irq, fimd_irq_handler,
+							0, "drm_fimd", ctx);
+	if (ret) {
 		dev_err(dev, "irq request failed.\n");
-		goto err_req_irq;
+		goto err_clk;
 	}
 
 	ctx->vidcon0 = pdata->vidcon0;
@@ -899,14 +891,6 @@ static int __devinit fimd_probe(struct platform_device *pdev)
 
 	return 0;
 
-err_req_irq:
-err_req_region_irq:
-	iounmap(ctx->regs);
-
-err_req_region_io:
-	release_resource(ctx->regs_res);
-	kfree(ctx->regs_res);
-
 err_clk:
 	clk_disable(ctx->lcd_clk);
 	clk_put(ctx->lcd_clk);
@@ -916,7 +900,6 @@ err_bus_clk:
 	clk_put(ctx->bus_clk);
 
 err_clk_get:
-	kfree(ctx);
 	return ret;
 }
 
@@ -944,13 +927,6 @@ out:
 	clk_put(ctx->lcd_clk);
 	clk_put(ctx->bus_clk);
 
-	iounmap(ctx->regs);
-	release_resource(ctx->regs_res);
-	kfree(ctx->regs_res);
-	free_irq(ctx->irq, ctx);
-
-	kfree(ctx);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 5c8b683029e..f9efde40c09 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -99,25 +99,17 @@ out:
 struct page **exynos_gem_get_pages(struct drm_gem_object *obj,
 						gfp_t gfpmask)
 {
-	struct inode *inode;
-	struct address_space *mapping;
 	struct page *p, **pages;
 	int i, npages;
 
-	/* This is the shared memory object that backs the GEM resource */
-	inode = obj->filp->f_path.dentry->d_inode;
-	mapping = inode->i_mapping;
-
 	npages = obj->size >> PAGE_SHIFT;
 
 	pages = drm_malloc_ab(npages, sizeof(struct page *));
 	if (pages == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	gfpmask |= mapping_gfp_mask(mapping);
-
 	for (i = 0; i < npages; i++) {
-		p = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
+		p = alloc_page(gfpmask);
 		if (IS_ERR(p))
 			goto fail;
 		pages[i] = p;
@@ -126,31 +118,22 @@ struct page **exynos_gem_get_pages(struct drm_gem_object *obj,
 	return pages;
 
 fail:
-	while (i--)
-		page_cache_release(pages[i]);
+	while (--i)
+		__free_page(pages[i]);
 
 	drm_free_large(pages);
 	return ERR_PTR(PTR_ERR(p));
 }
 
 static void exynos_gem_put_pages(struct drm_gem_object *obj,
-					struct page **pages,
-					bool dirty, bool accessed)
+					struct page **pages)
 {
-	int i, npages;
+	int npages;
 
 	npages = obj->size >> PAGE_SHIFT;
 
-	for (i = 0; i < npages; i++) {
-		if (dirty)
-			set_page_dirty(pages[i]);
-
-		if (accessed)
-			mark_page_accessed(pages[i]);
-
-		/* Undo the reference we took when populating the table */
-		page_cache_release(pages[i]);
-	}
+	while (--npages >= 0)
+		__free_page(pages[npages]);
 
 	drm_free_large(pages);
 }
@@ -189,7 +172,7 @@ static int exynos_drm_gem_get_pages(struct drm_gem_object *obj)
 		return -EINVAL;
 	}
 
-	pages = exynos_gem_get_pages(obj, GFP_KERNEL);
+	pages = exynos_gem_get_pages(obj, GFP_HIGHUSER_MOVABLE);
 	if (IS_ERR(pages)) {
 		DRM_ERROR("failed to get pages.\n");
 		return PTR_ERR(pages);
@@ -230,7 +213,7 @@ err1:
 	kfree(buf->sgt);
 	buf->sgt = NULL;
 err:
-	exynos_gem_put_pages(obj, pages, true, false);
+	exynos_gem_put_pages(obj, pages);
 	return ret;
 
 }
@@ -248,7 +231,7 @@ static void exynos_drm_gem_put_pages(struct drm_gem_object *obj)
 	kfree(buf->sgt);
 	buf->sgt = NULL;
 
-	exynos_gem_put_pages(obj, buf->pages, true, false);
+	exynos_gem_put_pages(obj, buf->pages);
 	buf->pages = NULL;
 
 	/* add some codes for UNCACHED type here. TODO */
@@ -291,11 +274,21 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj)
 	if (!buf->pages)
 		return;
 
+	/*
+	 * do not release memory region from exporter.
+	 *
+	 * the region will be released by exporter
+	 * once dmabuf's refcount becomes 0.
+	 */
+	if (obj->import_attach)
+		goto out;
+
 	if (exynos_gem_obj->flags & EXYNOS_BO_NONCONTIG)
 		exynos_drm_gem_put_pages(obj);
 	else
 		exynos_drm_free_buf(obj->dev, exynos_gem_obj->flags, buf);
 
+out:
 	exynos_drm_fini_buf(obj->dev, buf);
 	exynos_gem_obj->buffer = NULL;
 
@@ -668,7 +661,7 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 	 *	with DRM_IOCTL_MODE_CREATE_DUMB command.
 	 */
 
-	args->pitch = args->width * args->bpp >> 3;
+	args->pitch = args->width * ((args->bpp + 7) / 8);
 	args->size = PAGE_ALIGN(args->pitch * args->height);
 
 	exynos_gem_obj = exynos_drm_gem_create(dev, args->flags, args->size);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 14d038b6cb0..085b2a5d5f7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -63,7 +63,8 @@ struct exynos_drm_gem_buf {
  *	by user request or at framebuffer creation.
  *	continuous memory region allocated by user request
  *	or at framebuffer creation.
- * @size: total memory size to physically non-continuous memory region.
+ * @size: size requested from user, in bytes and this size is aligned
+ *	in page unit.
  * @flags: indicate memory type to allocated buffer and cache attruibute.
  *
  * P.S. this object would be transfered to user as kms_bo.handle so
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index c4c6525d465..b89829e5043 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -12,9 +12,12 @@
 #include "drmP.h"
 
 #include "exynos_drm.h"
-#include "exynos_drm_crtc.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_encoder.h"
+#include "exynos_drm_fb.h"
+#include "exynos_drm_gem.h"
+
+#define to_exynos_plane(x)	container_of(x, struct exynos_plane, base)
 
 struct exynos_plane {
 	struct drm_plane		base;
@@ -30,6 +33,108 @@ static const uint32_t formats[] = {
 	DRM_FORMAT_NV12MT,
 };
 
+int exynos_plane_mode_set(struct drm_plane *plane, struct drm_crtc *crtc,
+			  struct drm_framebuffer *fb, int crtc_x, int crtc_y,
+			  unsigned int crtc_w, unsigned int crtc_h,
+			  uint32_t src_x, uint32_t src_y,
+			  uint32_t src_w, uint32_t src_h)
+{
+	struct exynos_plane *exynos_plane = to_exynos_plane(plane);
+	struct exynos_drm_overlay *overlay = &exynos_plane->overlay;
+	unsigned int actual_w;
+	unsigned int actual_h;
+	int nr;
+	int i;
+
+	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
+
+	nr = exynos_drm_format_num_buffers(fb->pixel_format);
+	for (i = 0; i < nr; i++) {
+		struct exynos_drm_gem_buf *buffer = exynos_drm_fb_buffer(fb, i);
+
+		if (!buffer) {
+			DRM_LOG_KMS("buffer is null\n");
+			return -EFAULT;
+		}
+
+		overlay->dma_addr[i] = buffer->dma_addr;
+		overlay->vaddr[i] = buffer->kvaddr;
+
+		DRM_DEBUG_KMS("buffer: %d, vaddr = 0x%lx, dma_addr = 0x%lx\n",
+				i, (unsigned long)overlay->vaddr[i],
+				(unsigned long)overlay->dma_addr[i]);
+	}
+
+	actual_w = min((unsigned)(crtc->mode.hdisplay - crtc_x), crtc_w);
+	actual_h = min((unsigned)(crtc->mode.vdisplay - crtc_y), crtc_h);
+
+	/* set drm framebuffer data. */
+	overlay->fb_x = src_x;
+	overlay->fb_y = src_y;
+	overlay->fb_width = fb->width;
+	overlay->fb_height = fb->height;
+	overlay->src_width = src_w;
+	overlay->src_height = src_h;
+	overlay->bpp = fb->bits_per_pixel;
+	overlay->pitch = fb->pitches[0];
+	overlay->pixel_format = fb->pixel_format;
+
+	/* set overlay range to be displayed. */
+	overlay->crtc_x = crtc_x;
+	overlay->crtc_y = crtc_y;
+	overlay->crtc_width = actual_w;
+	overlay->crtc_height = actual_h;
+
+	/* set drm mode data. */
+	overlay->mode_width = crtc->mode.hdisplay;
+	overlay->mode_height = crtc->mode.vdisplay;
+	overlay->refresh = crtc->mode.vrefresh;
+	overlay->scan_flag = crtc->mode.flags;
+
+	DRM_DEBUG_KMS("overlay : offset_x/y(%d,%d), width/height(%d,%d)",
+			overlay->crtc_x, overlay->crtc_y,
+			overlay->crtc_width, overlay->crtc_height);
+
+	exynos_drm_fn_encoder(crtc, overlay, exynos_drm_encoder_plane_mode_set);
+
+	return 0;
+}
+
+void exynos_plane_commit(struct drm_plane *plane)
+{
+	struct exynos_plane *exynos_plane = to_exynos_plane(plane);
+	struct exynos_drm_overlay *overlay = &exynos_plane->overlay;
+
+	exynos_drm_fn_encoder(plane->crtc, &overlay->zpos,
+			exynos_drm_encoder_plane_commit);
+}
+
+void exynos_plane_dpms(struct drm_plane *plane, int mode)
+{
+	struct exynos_plane *exynos_plane = to_exynos_plane(plane);
+	struct exynos_drm_overlay *overlay = &exynos_plane->overlay;
+
+	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
+
+	if (mode == DRM_MODE_DPMS_ON) {
+		if (exynos_plane->enabled)
+			return;
+
+		exynos_drm_fn_encoder(plane->crtc, &overlay->zpos,
+				exynos_drm_encoder_plane_enable);
+
+		exynos_plane->enabled = true;
+	} else {
+		if (!exynos_plane->enabled)
+			return;
+
+		exynos_drm_fn_encoder(plane->crtc, &overlay->zpos,
+				exynos_drm_encoder_plane_disable);
+
+		exynos_plane->enabled = false;
+	}
+}
+
 static int
 exynos_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		     struct drm_framebuffer *fb, int crtc_x, int crtc_y,
@@ -37,64 +142,37 @@ exynos_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		     uint32_t src_x, uint32_t src_y,
 		     uint32_t src_w, uint32_t src_h)
 {
-	struct exynos_plane *exynos_plane =
-		container_of(plane, struct exynos_plane, base);
-	struct exynos_drm_overlay *overlay = &exynos_plane->overlay;
-	struct exynos_drm_crtc_pos pos;
 	int ret;
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	memset(&pos, 0, sizeof(struct exynos_drm_crtc_pos));
-	pos.crtc_x = crtc_x;
-	pos.crtc_y = crtc_y;
-	pos.crtc_w = crtc_w;
-	pos.crtc_h = crtc_h;
-
-	/* considering 16.16 fixed point of source values */
-	pos.fb_x = src_x >> 16;
-	pos.fb_y = src_y >> 16;
-	pos.src_w = src_w >> 16;
-	pos.src_h = src_h >> 16;
-
-	ret = exynos_drm_overlay_update(overlay, fb, &crtc->mode, &pos);
+	ret = exynos_plane_mode_set(plane, crtc, fb, crtc_x, crtc_y,
+			crtc_w, crtc_h, src_x >> 16, src_y >> 16,
+			src_w >> 16, src_h >> 16);
 	if (ret < 0)
 		return ret;
 
-	exynos_drm_fn_encoder(crtc, overlay,
-			exynos_drm_encoder_crtc_mode_set);
-	exynos_drm_fn_encoder(crtc, &overlay->zpos,
-			exynos_drm_encoder_crtc_plane_commit);
+	plane->crtc = crtc;
+	plane->fb = crtc->fb;
 
-	exynos_plane->enabled = true;
+	exynos_plane_commit(plane);
+	exynos_plane_dpms(plane, DRM_MODE_DPMS_ON);
 
 	return 0;
 }
 
 static int exynos_disable_plane(struct drm_plane *plane)
 {
-	struct exynos_plane *exynos_plane =
-		container_of(plane, struct exynos_plane, base);
-	struct exynos_drm_overlay *overlay = &exynos_plane->overlay;
-
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	if (!exynos_plane->enabled)
-		return 0;
-
-	exynos_drm_fn_encoder(plane->crtc, &overlay->zpos,
-			exynos_drm_encoder_crtc_disable);
-
-	exynos_plane->enabled = false;
-	exynos_plane->overlay.zpos = DEFAULT_ZPOS;
+	exynos_plane_dpms(plane, DRM_MODE_DPMS_OFF);
 
 	return 0;
 }
 
 static void exynos_plane_destroy(struct drm_plane *plane)
 {
-	struct exynos_plane *exynos_plane =
-		container_of(plane, struct exynos_plane, base);
+	struct exynos_plane *exynos_plane = to_exynos_plane(plane);
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
@@ -103,69 +181,79 @@ static void exynos_plane_destroy(struct drm_plane *plane)
 	kfree(exynos_plane);
 }
 
+static int exynos_plane_set_property(struct drm_plane *plane,
+				     struct drm_property *property,
+				     uint64_t val)
+{
+	struct drm_device *dev = plane->dev;
+	struct exynos_plane *exynos_plane = to_exynos_plane(plane);
+	struct exynos_drm_private *dev_priv = dev->dev_private;
+
+	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
+
+	if (property == dev_priv->plane_zpos_property) {
+		exynos_plane->overlay.zpos = val;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 static struct drm_plane_funcs exynos_plane_funcs = {
 	.update_plane	= exynos_update_plane,
 	.disable_plane	= exynos_disable_plane,
 	.destroy	= exynos_plane_destroy,
+	.set_property	= exynos_plane_set_property,
 };
 
-int exynos_plane_init(struct drm_device *dev, unsigned int nr)
+static void exynos_plane_attach_zpos_property(struct drm_plane *plane)
 {
-	struct exynos_plane *exynos_plane;
-	uint32_t possible_crtcs;
+	struct drm_device *dev = plane->dev;
+	struct exynos_drm_private *dev_priv = dev->dev_private;
+	struct drm_property *prop;
 
-	exynos_plane = kzalloc(sizeof(struct exynos_plane), GFP_KERNEL);
-	if (!exynos_plane)
-		return -ENOMEM;
+	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	/* all CRTCs are available */
-	possible_crtcs = (1 << MAX_CRTC) - 1;
+	prop = dev_priv->plane_zpos_property;
+	if (!prop) {
+		prop = drm_property_create_range(dev, 0, "zpos", 0,
+						 MAX_PLANE - 1);
+		if (!prop)
+			return;
 
-	exynos_plane->overlay.zpos = DEFAULT_ZPOS;
+		dev_priv->plane_zpos_property = prop;
+	}
 
-	return drm_plane_init(dev, &exynos_plane->base, possible_crtcs,
-			      &exynos_plane_funcs, formats, ARRAY_SIZE(formats),
-			      false);
+	drm_object_attach_property(&plane->base, prop, 0);
 }
 
-int exynos_plane_set_zpos_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *file_priv)
+struct drm_plane *exynos_plane_init(struct drm_device *dev,
+				    unsigned int possible_crtcs, bool priv)
 {
-	struct drm_exynos_plane_set_zpos *zpos_req = data;
-	struct drm_mode_object *obj;
-	struct drm_plane *plane;
 	struct exynos_plane *exynos_plane;
-	int ret = 0;
+	int err;
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	if (!drm_core_check_feature(dev, DRIVER_MODESET))
-		return -EINVAL;
-
-	if (zpos_req->zpos < 0 || zpos_req->zpos >= MAX_PLANE) {
-		if (zpos_req->zpos != DEFAULT_ZPOS) {
-			DRM_ERROR("zpos not within limits\n");
-			return -EINVAL;
-		}
+	exynos_plane = kzalloc(sizeof(struct exynos_plane), GFP_KERNEL);
+	if (!exynos_plane) {
+		DRM_ERROR("failed to allocate plane\n");
+		return NULL;
 	}
 
-	mutex_lock(&dev->mode_config.mutex);
-
-	obj = drm_mode_object_find(dev, zpos_req->plane_id,
-			DRM_MODE_OBJECT_PLANE);
-	if (!obj) {
-		DRM_DEBUG_KMS("Unknown plane ID %d\n",
-			      zpos_req->plane_id);
-		ret = -EINVAL;
-		goto out;
+	err = drm_plane_init(dev, &exynos_plane->base, possible_crtcs,
+			      &exynos_plane_funcs, formats, ARRAY_SIZE(formats),
+			      priv);
+	if (err) {
+		DRM_ERROR("failed to initialize plane\n");
+		kfree(exynos_plane);
+		return NULL;
 	}
 
-	plane = obj_to_plane(obj);
-	exynos_plane = container_of(plane, struct exynos_plane, base);
-
-	exynos_plane->overlay.zpos = zpos_req->zpos;
+	if (priv)
+		exynos_plane->overlay.zpos = DEFAULT_ZPOS;
+	else
+		exynos_plane_attach_zpos_property(&exynos_plane->base);
 
-out:
-	mutex_unlock(&dev->mode_config.mutex);
-	return ret;
+	return &exynos_plane->base;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.h b/drivers/gpu/drm/exynos/exynos_drm_plane.h
index 16b71f8217e..88312458580 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.h
@@ -9,6 +9,12 @@
  *
  */
 
-int exynos_plane_init(struct drm_device *dev, unsigned int nr);
-int exynos_plane_set_zpos_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *file_priv);
+int exynos_plane_mode_set(struct drm_plane *plane, struct drm_crtc *crtc,
+			  struct drm_framebuffer *fb, int crtc_x, int crtc_y,
+			  unsigned int crtc_w, unsigned int crtc_h,
+			  uint32_t src_x, uint32_t src_y,
+			  uint32_t src_w, uint32_t src_h);
+void exynos_plane_commit(struct drm_plane *plane);
+void exynos_plane_dpms(struct drm_plane *plane, int mode);
+struct drm_plane *exynos_plane_init(struct drm_device *dev,
+				    unsigned int possible_crtcs, bool priv);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 7b9c153dceb..bb1550c4dd5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -85,8 +85,6 @@ static const char fake_edid_info[] = {
 	0x00, 0x00, 0x00, 0x06
 };
 
-static void vidi_fake_vblank_handler(struct work_struct *work);
-
 static bool vidi_display_is_connected(struct device *dev)
 {
 	struct vidi_context *ctx = get_vidi_context(dev);
@@ -531,6 +529,16 @@ static int vidi_store_connection(struct device *dev,
 	if (ctx->connected > 1)
 		return -EINVAL;
 
+	/* use fake edid data for test. */
+	if (!ctx->raw_edid)
+		ctx->raw_edid = (struct edid *)fake_edid_info;
+
+	/* if raw_edid isn't same as fake data then it can't be tested. */
+	if (ctx->raw_edid != (struct edid *)fake_edid_info) {
+		DRM_DEBUG_KMS("edid data is not fake data.\n");
+		return -EINVAL;
+	}
+
 	DRM_DEBUG_KMS("requested connection.\n");
 
 	drm_helper_hpd_irq_event(ctx->subdrv.drm_dev);
@@ -549,6 +557,8 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data,
 	struct exynos_drm_manager *manager;
 	struct exynos_drm_display_ops *display_ops;
 	struct drm_exynos_vidi_connection *vidi = data;
+	struct edid *raw_edid;
+	int edid_len;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -557,11 +567,6 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data,
 		return -EINVAL;
 	}
 
-	if (!vidi->edid) {
-		DRM_DEBUG_KMS("edid data is null.\n");
-		return -EINVAL;
-	}
-
 	if (vidi->connection > 1) {
 		DRM_DEBUG_KMS("connection should be 0 or 1.\n");
 		return -EINVAL;
@@ -588,8 +593,30 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data,
 		return -EINVAL;
 	}
 
-	if (vidi->connection)
-		ctx->raw_edid = (struct edid *)vidi->edid;
+	if (vidi->connection) {
+		if (!vidi->edid) {
+			DRM_DEBUG_KMS("edid data is null.\n");
+			return -EINVAL;
+		}
+		raw_edid = (struct edid *)(uint32_t)vidi->edid;
+		edid_len = (1 + raw_edid->extensions) * EDID_LENGTH;
+		ctx->raw_edid = kzalloc(edid_len, GFP_KERNEL);
+		if (!ctx->raw_edid) {
+			DRM_DEBUG_KMS("failed to allocate raw_edid.\n");
+			return -ENOMEM;
+		}
+		memcpy(ctx->raw_edid, raw_edid, edid_len);
+	} else {
+		/*
+		 * with connection = 0, free raw_edid
+		 * only if raw edid data isn't same as fake data.
+		 */
+		if (ctx->raw_edid && ctx->raw_edid !=
+				(struct edid *)fake_edid_info) {
+			kfree(ctx->raw_edid);
+			ctx->raw_edid = NULL;
+		}
+	}
 
 	ctx->connected = vidi->connection;
 	drm_helper_hpd_irq_event(ctx->subdrv.drm_dev);
@@ -614,9 +641,6 @@ static int __devinit vidi_probe(struct platform_device *pdev)
 
 	INIT_WORK(&ctx->work, vidi_fake_vblank_handler);
 
-	/* for test */
-	ctx->raw_edid = (struct edid *)fake_edid_info;
-
 	subdrv = &ctx->subdrv;
 	subdrv->dev = dev;
 	subdrv->manager = &vidi_manager;
@@ -644,6 +668,11 @@ static int __devexit vidi_remove(struct platform_device *pdev)
 
 	exynos_drm_subdrv_unregister(&ctx->subdrv);
 
+	if (ctx->raw_edid != (struct edid *)fake_edid_info) {
+		kfree(ctx->raw_edid);
+		ctx->raw_edid = NULL;
+	}
+
 	kfree(ctx);
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 066bde3f19c..409e2ec1207 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -63,7 +63,6 @@ struct hdmi_context {
 	bool				dvi_mode;
 	struct mutex			hdmi_mutex;
 
-	struct resource			*regs_res;
 	void __iomem			*regs;
 	unsigned int			external_irq;
 	unsigned int			internal_irq;
@@ -2280,16 +2279,17 @@ static int __devinit hdmi_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	drm_hdmi_ctx = kzalloc(sizeof(*drm_hdmi_ctx), GFP_KERNEL);
+	drm_hdmi_ctx = devm_kzalloc(&pdev->dev, sizeof(*drm_hdmi_ctx),
+								GFP_KERNEL);
 	if (!drm_hdmi_ctx) {
 		DRM_ERROR("failed to allocate common hdmi context.\n");
 		return -ENOMEM;
 	}
 
-	hdata = kzalloc(sizeof(struct hdmi_context), GFP_KERNEL);
+	hdata = devm_kzalloc(&pdev->dev, sizeof(struct hdmi_context),
+								GFP_KERNEL);
 	if (!hdata) {
 		DRM_ERROR("out of memory\n");
-		kfree(drm_hdmi_ctx);
 		return -ENOMEM;
 	}
 
@@ -2318,26 +2318,18 @@ static int __devinit hdmi_probe(struct platform_device *pdev)
 		goto err_resource;
 	}
 
-	hdata->regs_res = request_mem_region(res->start, resource_size(res),
-					   dev_name(dev));
-	if (!hdata->regs_res) {
-		DRM_ERROR("failed to claim register region\n");
-		ret = -ENOENT;
-		goto err_resource;
-	}
-
-	hdata->regs = ioremap(res->start, resource_size(res));
+	hdata->regs = devm_request_and_ioremap(&pdev->dev, res);
 	if (!hdata->regs) {
 		DRM_ERROR("failed to map registers\n");
 		ret = -ENXIO;
-		goto err_req_region;
+		goto err_resource;
 	}
 
 	/* DDC i2c driver */
 	if (i2c_add_driver(&ddc_driver)) {
 		DRM_ERROR("failed to register ddc i2c driver\n");
 		ret = -ENOENT;
-		goto err_iomap;
+		goto err_resource;
 	}
 
 	hdata->ddc_port = hdmi_ddc;
@@ -2398,16 +2390,9 @@ err_hdmiphy:
 	i2c_del_driver(&hdmiphy_driver);
 err_ddc:
 	i2c_del_driver(&ddc_driver);
-err_iomap:
-	iounmap(hdata->regs);
-err_req_region:
-	release_mem_region(hdata->regs_res->start,
-			resource_size(hdata->regs_res));
 err_resource:
 	hdmi_resources_cleanup(hdata);
 err_data:
-	kfree(hdata);
-	kfree(drm_hdmi_ctx);
 	return ret;
 }
 
@@ -2425,18 +2410,11 @@ static int __devexit hdmi_remove(struct platform_device *pdev)
 
 	hdmi_resources_cleanup(hdata);
 
-	iounmap(hdata->regs);
-
-	release_mem_region(hdata->regs_res->start,
-			resource_size(hdata->regs_res));
-
 	/* hdmiphy i2c driver */
 	i2c_del_driver(&hdmiphy_driver);
 	/* DDC i2c driver */
 	i2c_del_driver(&ddc_driver);
 
-	kfree(hdata);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index e2147a2ddce..30fcc12f81d 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -956,7 +956,8 @@ static int __devinit mixer_resources_init(struct exynos_drm_hdmi_context *ctx,
 
 	clk_set_parent(mixer_res->sclk_mixer, mixer_res->sclk_hdmi);
 
-	mixer_res->mixer_regs = ioremap(res->start, resource_size(res));
+	mixer_res->mixer_regs = devm_ioremap(&pdev->dev, res->start,
+							resource_size(res));
 	if (mixer_res->mixer_regs == NULL) {
 		dev_err(dev, "register mapping failed.\n");
 		ret = -ENXIO;
@@ -967,38 +968,34 @@ static int __devinit mixer_resources_init(struct exynos_drm_hdmi_context *ctx,
 	if (res == NULL) {
 		dev_err(dev, "get memory resource failed.\n");
 		ret = -ENXIO;
-		goto fail_mixer_regs;
+		goto fail;
 	}
 
-	mixer_res->vp_regs = ioremap(res->start, resource_size(res));
+	mixer_res->vp_regs = devm_ioremap(&pdev->dev, res->start,
+							resource_size(res));
 	if (mixer_res->vp_regs == NULL) {
 		dev_err(dev, "register mapping failed.\n");
 		ret = -ENXIO;
-		goto fail_mixer_regs;
+		goto fail;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "irq");
 	if (res == NULL) {
 		dev_err(dev, "get interrupt resource failed.\n");
 		ret = -ENXIO;
-		goto fail_vp_regs;
+		goto fail;
 	}
 
-	ret = request_irq(res->start, mixer_irq_handler, 0, "drm_mixer", ctx);
+	ret = devm_request_irq(&pdev->dev, res->start, mixer_irq_handler,
+							0, "drm_mixer", ctx);
 	if (ret) {
 		dev_err(dev, "request interrupt failed.\n");
-		goto fail_vp_regs;
+		goto fail;
 	}
 	mixer_res->irq = res->start;
 
 	return 0;
 
-fail_vp_regs:
-	iounmap(mixer_res->vp_regs);
-
-fail_mixer_regs:
-	iounmap(mixer_res->mixer_regs);
-
 fail:
 	if (!IS_ERR_OR_NULL(mixer_res->sclk_dac))
 		clk_put(mixer_res->sclk_dac);
@@ -1013,16 +1010,6 @@ fail:
 	return ret;
 }
 
-static void mixer_resources_cleanup(struct mixer_context *ctx)
-{
-	struct mixer_resources *res = &ctx->mixer_res;
-
-	free_irq(res->irq, ctx);
-
-	iounmap(res->vp_regs);
-	iounmap(res->mixer_regs);
-}
-
 static int __devinit mixer_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1032,16 +1019,16 @@ static int __devinit mixer_probe(struct platform_device *pdev)
 
 	dev_info(dev, "probe start\n");
 
-	drm_hdmi_ctx = kzalloc(sizeof(*drm_hdmi_ctx), GFP_KERNEL);
+	drm_hdmi_ctx = devm_kzalloc(&pdev->dev, sizeof(*drm_hdmi_ctx),
+								GFP_KERNEL);
 	if (!drm_hdmi_ctx) {
 		DRM_ERROR("failed to allocate common hdmi context.\n");
 		return -ENOMEM;
 	}
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx) {
 		DRM_ERROR("failed to alloc mixer context.\n");
-		kfree(drm_hdmi_ctx);
 		return -ENOMEM;
 	}
 
@@ -1072,17 +1059,10 @@ fail:
 
 static int mixer_remove(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	struct exynos_drm_hdmi_context *drm_hdmi_ctx =
-					platform_get_drvdata(pdev);
-	struct mixer_context *ctx = drm_hdmi_ctx->ctx;
-
-	dev_info(dev, "remove successful\n");
+	dev_info(&pdev->dev, "remove successful\n");
 
 	pm_runtime_disable(&pdev->dev);
 
-	mixer_resources_cleanup(ctx);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index 9764045428c..b7e7b49d8f6 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -78,21 +78,6 @@ static int cdv_backlight_combination_mode(struct drm_device *dev)
 	return REG_READ(BLC_PWM_CTL2) & PWM_LEGACY_MODE;
 }
 
-static int cdv_get_brightness(struct backlight_device *bd)
-{
-	struct drm_device *dev = bl_get_data(bd);
-	u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
-
-	if (cdv_backlight_combination_mode(dev)) {
-		u8 lbpc;
-
-		val &= ~1;
-		pci_read_config_byte(dev->pdev, 0xF4, &lbpc);
-		val *= lbpc;
-	}
-	return val;
-}
-
 static u32 cdv_get_max_backlight(struct drm_device *dev)
 {
 	u32 max = REG_READ(BLC_PWM_CTL);
@@ -110,6 +95,22 @@ static u32 cdv_get_max_backlight(struct drm_device *dev)
 	return max;
 }
 
+static int cdv_get_brightness(struct backlight_device *bd)
+{
+	struct drm_device *dev = bl_get_data(bd);
+	u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
+
+	if (cdv_backlight_combination_mode(dev)) {
+		u8 lbpc;
+
+		val &= ~1;
+		pci_read_config_byte(dev->pdev, 0xF4, &lbpc);
+		val *= lbpc;
+	}
+	return (val * 100)/cdv_get_max_backlight(dev);
+
+}
+
 static int cdv_set_brightness(struct backlight_device *bd)
 {
 	struct drm_device *dev = bl_get_data(bd);
@@ -120,6 +121,9 @@ static int cdv_set_brightness(struct backlight_device *bd)
 	if (level < 1)
 		level = 1;
 
+	level *= cdv_get_max_backlight(dev);
+	level /= 100;
+
 	if (cdv_backlight_combination_mode(dev)) {
 		u32 max = cdv_get_max_backlight(dev);
 		u8 lbpc;
@@ -157,7 +161,6 @@ static int cdv_backlight_init(struct drm_device *dev)
 
 	cdv_backlight_device->props.brightness =
 			cdv_get_brightness(cdv_backlight_device);
-	cdv_backlight_device->props.max_brightness = cdv_get_max_backlight(dev);
 	backlight_update_status(cdv_backlight_device);
 	dev_priv->backlight_device = cdv_backlight_device;
 	return 0;
diff --git a/drivers/gpu/drm/gma500/opregion.c b/drivers/gpu/drm/gma500/opregion.c
index 4f186eca3a3..c430bd42468 100644
--- a/drivers/gpu/drm/gma500/opregion.c
+++ b/drivers/gpu/drm/gma500/opregion.c
@@ -144,6 +144,8 @@ struct opregion_asle {
 
 #define ASLE_CBLV_VALID         (1<<31)
 
+static struct psb_intel_opregion *system_opregion;
+
 static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
@@ -205,7 +207,7 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev)
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct opregion_asle *asle = dev_priv->opregion.asle;
 
-	if (asle) {
+	if (asle && system_opregion ) {
 		/* Don't do this on Medfield or other non PC like devices, they
 		   use the bit for something different altogether */
 		psb_enable_pipestat(dev_priv, 0, PIPE_LEGACY_BLC_EVENT_ENABLE);
@@ -221,7 +223,6 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev)
 #define ACPI_EV_LID            (1<<1)
 #define ACPI_EV_DOCK           (1<<2)
 
-static struct psb_intel_opregion *system_opregion;
 
 static int psb_intel_opregion_video_event(struct notifier_block *nb,
 					  unsigned long val, void *data)
@@ -266,9 +267,6 @@ void psb_intel_opregion_init(struct drm_device *dev)
 		system_opregion = opregion;
 		register_acpi_notifier(&psb_intel_opregion_notifier);
 	}
-
-	if (opregion->asle)
-		psb_intel_opregion_enable_asle(dev);
 }
 
 void psb_intel_opregion_fini(struct drm_device *dev)
diff --git a/drivers/gpu/drm/gma500/opregion.h b/drivers/gpu/drm/gma500/opregion.h
index 72dc6b92126..4a90f8b0e16 100644
--- a/drivers/gpu/drm/gma500/opregion.h
+++ b/drivers/gpu/drm/gma500/opregion.h
@@ -27,6 +27,7 @@ extern void psb_intel_opregion_asle_intr(struct drm_device *dev);
 extern void psb_intel_opregion_init(struct drm_device *dev);
 extern void psb_intel_opregion_fini(struct drm_device *dev);
 extern int psb_intel_opregion_setup(struct drm_device *dev);
+extern void psb_intel_opregion_enable_asle(struct drm_device *dev);
 
 #else
 
@@ -46,4 +47,8 @@ extern inline int psb_intel_opregion_setup(struct drm_device *dev)
 {
 	return 0;
 }
+
+extern inline void psb_intel_opregion_enable_asle(struct drm_device *dev)
+{
+}
 #endif
diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c
index eff039bf92d..5971bc82b76 100644
--- a/drivers/gpu/drm/gma500/psb_device.c
+++ b/drivers/gpu/drm/gma500/psb_device.c
@@ -144,6 +144,10 @@ static int psb_backlight_init(struct drm_device *dev)
 	psb_backlight_device->props.max_brightness = 100;
 	backlight_update_status(psb_backlight_device);
 	dev_priv->backlight_device = psb_backlight_device;
+
+	/* This must occur after the backlight is properly initialised */
+	psb_lid_timer_init(dev_priv);
+
 	return 0;
 }
 
@@ -354,13 +358,6 @@ static int psb_chip_setup(struct drm_device *dev)
 	return 0;
 }
 
-/* Not exactly an erratum more an irritation */
-static void psb_chip_errata(struct drm_device *dev)
-{
-	struct drm_psb_private *dev_priv = dev->dev_private;
-	psb_lid_timer_init(dev_priv);
-}
-
 static void psb_chip_teardown(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
@@ -379,7 +376,6 @@ const struct psb_ops psb_chip_ops = {
 	.sgx_offset = PSB_SGX_OFFSET,
 	.chip_setup = psb_chip_setup,
 	.chip_teardown = psb_chip_teardown,
-	.errata = psb_chip_errata,
 
 	.crtc_helper = &psb_intel_helper_funcs,
 	.crtc_funcs = &psb_intel_crtc_funcs,
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index cd1dd1b14c7..0c473743853 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -374,6 +374,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	if (ret)
 		return ret;
+	psb_intel_opregion_enable_asle(dev);
 #if 0
 	/*enable runtime pm at last*/
 	pm_runtime_enable(&dev->pdev->dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ff569cc3537..7ebb13b6513 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -346,11 +346,40 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
 	INTEL_VGA_DEVICE(0x0402, &intel_haswell_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0412, &intel_haswell_d_info), /* GT2 desktop */
+	INTEL_VGA_DEVICE(0x0422, &intel_haswell_d_info), /* GT2 desktop */
 	INTEL_VGA_DEVICE(0x040a, &intel_haswell_d_info), /* GT1 server */
 	INTEL_VGA_DEVICE(0x041a, &intel_haswell_d_info), /* GT2 server */
+	INTEL_VGA_DEVICE(0x042a, &intel_haswell_d_info), /* GT2 server */
 	INTEL_VGA_DEVICE(0x0406, &intel_haswell_m_info), /* GT1 mobile */
 	INTEL_VGA_DEVICE(0x0416, &intel_haswell_m_info), /* GT2 mobile */
-	INTEL_VGA_DEVICE(0x0c16, &intel_haswell_d_info), /* SDV */
+	INTEL_VGA_DEVICE(0x0426, &intel_haswell_m_info), /* GT2 mobile */
+	INTEL_VGA_DEVICE(0x0C02, &intel_haswell_d_info), /* SDV GT1 desktop */
+	INTEL_VGA_DEVICE(0x0C12, &intel_haswell_d_info), /* SDV GT2 desktop */
+	INTEL_VGA_DEVICE(0x0C22, &intel_haswell_d_info), /* SDV GT2 desktop */
+	INTEL_VGA_DEVICE(0x0C0A, &intel_haswell_d_info), /* SDV GT1 server */
+	INTEL_VGA_DEVICE(0x0C1A, &intel_haswell_d_info), /* SDV GT2 server */
+	INTEL_VGA_DEVICE(0x0C2A, &intel_haswell_d_info), /* SDV GT2 server */
+	INTEL_VGA_DEVICE(0x0C06, &intel_haswell_m_info), /* SDV GT1 mobile */
+	INTEL_VGA_DEVICE(0x0C16, &intel_haswell_m_info), /* SDV GT2 mobile */
+	INTEL_VGA_DEVICE(0x0C26, &intel_haswell_m_info), /* SDV GT2 mobile */
+	INTEL_VGA_DEVICE(0x0A02, &intel_haswell_d_info), /* ULT GT1 desktop */
+	INTEL_VGA_DEVICE(0x0A12, &intel_haswell_d_info), /* ULT GT2 desktop */
+	INTEL_VGA_DEVICE(0x0A22, &intel_haswell_d_info), /* ULT GT2 desktop */
+	INTEL_VGA_DEVICE(0x0A0A, &intel_haswell_d_info), /* ULT GT1 server */
+	INTEL_VGA_DEVICE(0x0A1A, &intel_haswell_d_info), /* ULT GT2 server */
+	INTEL_VGA_DEVICE(0x0A2A, &intel_haswell_d_info), /* ULT GT2 server */
+	INTEL_VGA_DEVICE(0x0A06, &intel_haswell_m_info), /* ULT GT1 mobile */
+	INTEL_VGA_DEVICE(0x0A16, &intel_haswell_m_info), /* ULT GT2 mobile */
+	INTEL_VGA_DEVICE(0x0A26, &intel_haswell_m_info), /* ULT GT2 mobile */
+	INTEL_VGA_DEVICE(0x0D12, &intel_haswell_d_info), /* CRW GT1 desktop */
+	INTEL_VGA_DEVICE(0x0D22, &intel_haswell_d_info), /* CRW GT2 desktop */
+	INTEL_VGA_DEVICE(0x0D32, &intel_haswell_d_info), /* CRW GT2 desktop */
+	INTEL_VGA_DEVICE(0x0D1A, &intel_haswell_d_info), /* CRW GT1 server */
+	INTEL_VGA_DEVICE(0x0D2A, &intel_haswell_d_info), /* CRW GT2 server */
+	INTEL_VGA_DEVICE(0x0D3A, &intel_haswell_d_info), /* CRW GT2 server */
+	INTEL_VGA_DEVICE(0x0D16, &intel_haswell_m_info), /* CRW GT1 mobile */
+	INTEL_VGA_DEVICE(0x0D26, &intel_haswell_m_info), /* CRW GT2 mobile */
+	INTEL_VGA_DEVICE(0x0D36, &intel_haswell_m_info), /* CRW GT2 mobile */
 	INTEL_VGA_DEVICE(0x0f30, &intel_valleyview_m_info),
 	INTEL_VGA_DEVICE(0x0157, &intel_valleyview_m_info),
 	INTEL_VGA_DEVICE(0x0155, &intel_valleyview_d_info),
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 25b2c54e126..afb312ee050 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -117,6 +117,16 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	target_i915_obj = to_intel_bo(target_obj);
 	target_offset = target_i915_obj->gtt_offset;
 
+	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
+	 * pipe_control writes because the gpu doesn't properly redirect them
+	 * through the ppgtt for non_secure batchbuffers. */
+	if (unlikely(IS_GEN6(dev) &&
+	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
+	    !target_i915_obj->has_global_gtt_mapping)) {
+		i915_gem_gtt_bind_object(target_i915_obj,
+					 target_i915_obj->cache_level);
+	}
+
 	/* The target buffer should have appeared before us in the
 	 * exec_object list, so it should have a GTT space bound by now.
 	 */
@@ -225,16 +235,6 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		io_mapping_unmap_atomic(reloc_page);
 	}
 
-	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
-	 * pipe_control writes because the gpu doesn't properly redirect them
-	 * through the ppgtt for non_secure batchbuffers. */
-	if (unlikely(IS_GEN6(dev) &&
-	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
-	    !target_i915_obj->has_global_gtt_mapping)) {
-		i915_gem_gtt_bind_object(target_i915_obj,
-					 target_i915_obj->cache_level);
-	}
-
 	/* and update the user's relocation entry */
 	reloc->presumed_offset = target_offset;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 4584f7f0063..3b3b731a17c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -361,7 +361,8 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (dev_priv->mm.gtt->needs_dmar)
+	/* don't map imported dma buf objects */
+	if (dev_priv->mm.gtt->needs_dmar && !obj->sg_table)
 		return intel_gtt_map_memory(obj->pages,
 					    obj->base.size >> PAGE_SHIFT,
 					    &obj->sg_list,
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0c37101934f..a61b41a8c60 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -507,7 +507,6 @@ static void gen6_queue_rps_work(struct drm_i915_private *dev_priv,
 	 */
 
 	spin_lock_irqsave(&dev_priv->rps.lock, flags);
-	WARN(dev_priv->rps.pm_iir & pm_iir, "Missed a PM interrupt\n");
 	dev_priv->rps.pm_iir |= pm_iir;
 	I915_WRITE(GEN6_PMIMR, dev_priv->rps.pm_iir);
 	POSTING_READ(GEN6_PMIMR);
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 740c076ea33..4776ccf1b3c 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -740,8 +740,11 @@ static void i915_restore_display(struct drm_device *dev)
 	if (HAS_PCH_SPLIT(dev)) {
 		I915_WRITE(BLC_PWM_PCH_CTL1, dev_priv->saveBLC_PWM_CTL);
 		I915_WRITE(BLC_PWM_PCH_CTL2, dev_priv->saveBLC_PWM_CTL2);
-		I915_WRITE(BLC_PWM_CPU_CTL, dev_priv->saveBLC_CPU_PWM_CTL);
+		/* NOTE: BLC_PWM_CPU_CTL must be written after BLC_PWM_CPU_CTL2;
+		 * otherwise we get blank eDP screen after S3 on some machines
+		 */
 		I915_WRITE(BLC_PWM_CPU_CTL2, dev_priv->saveBLC_CPU_PWM_CTL2);
+		I915_WRITE(BLC_PWM_CPU_CTL, dev_priv->saveBLC_CPU_PWM_CTL);
 		I915_WRITE(PCH_PP_ON_DELAYS, dev_priv->savePP_ON_DELAYS);
 		I915_WRITE(PCH_PP_OFF_DELAYS, dev_priv->savePP_OFF_DELAYS);
 		I915_WRITE(PCH_PP_DIVISOR, dev_priv->savePP_DIVISOR);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 77a97bfabb6..c5ee7ee3b17 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -32,6 +32,7 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+#ifdef CONFIG_PM
 static u32 calc_residency(struct drm_device *dev, const u32 reg)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -224,3 +225,14 @@ void i915_teardown_sysfs(struct drm_device *dev)
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
 }
+#else
+void i915_setup_sysfs(struct drm_device *dev)
+{
+	return;
+}
+
+void i915_teardown_sysfs(struct drm_device *dev)
+{
+	return;
+}
+#endif /* CONFIG_PM */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e3afe968890..a9ab1aff2c7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -869,6 +869,7 @@ intel_vlv_find_best_pll(const intel_limit_t *limit, struct drm_crtc *crtc,
 	unsigned long bestppm, ppm, absppm;
 	int dotclk, flag;
 
+	flag = 0;
 	dotclk = target * 1000;
 	bestppm = 1000000;
 	ppm = absppm = 0;
@@ -3755,17 +3756,6 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			continue;
 		}
 
-		if (intel_encoder->type == INTEL_OUTPUT_EDP) {
-			/* Use VBT settings if we have an eDP panel */
-			unsigned int edp_bpc = dev_priv->edp.bpp / 3;
-
-			if (edp_bpc < display_bpc) {
-				DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
-				display_bpc = edp_bpc;
-			}
-			continue;
-		}
-
 		/* Not one of the known troublemakers, check the EDID */
 		list_for_each_entry(connector, &dev->mode_config.connector_list,
 				    head) {
@@ -7093,19 +7083,6 @@ static void i915_disable_vga(struct drm_device *dev)
 	POSTING_READ(vga_reg);
 }
 
-static void ivb_pch_pwm_override(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	/*
-	 * IVB has CPU eDP backlight regs too, set things up to let the
-	 * PCH regs control the backlight
-	 */
-	I915_WRITE(BLC_PWM_CPU_CTL2, BLM_PWM_ENABLE);
-	I915_WRITE(BLC_PWM_CPU_CTL, 0);
-	I915_WRITE(BLC_PWM_PCH_CTL1, BLM_PCH_PWM_ENABLE | BLM_PCH_OVERRIDE_ENABLE);
-}
-
 void intel_modeset_init_hw(struct drm_device *dev)
 {
 	/* We attempt to init the necessary power wells early in the initialization
@@ -7120,9 +7097,6 @@ void intel_modeset_init_hw(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	intel_enable_gt_powersave(dev);
 	mutex_unlock(&dev->struct_mutex);
-
-	if (IS_IVYBRIDGE(dev))
-		ivb_pch_pwm_override(dev);
 }
 
 void intel_modeset_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index ad90a499dab..977d9d216c7 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1142,10 +1142,14 @@ static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
 
 	pp = ironlake_get_pp_control(dev_priv);
-	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	/* We need to switch off panel power _and_ force vdd, for otherwise some
+	 * panels get very unhappy and cease to work. */
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
 
+	intel_dp->want_panel_vdd = false;
+
 	ironlake_wait_panel_off(intel_dp);
 }
 
@@ -1255,11 +1259,9 @@ static void intel_dp_prepare(struct drm_encoder *encoder)
 	 * ensure that we have vdd while we switch off the panel. */
 	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
-	ironlake_edp_panel_off(intel_dp);
-
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	ironlake_edp_panel_off(intel_dp);
 	intel_dp_link_down(intel_dp);
-	ironlake_edp_panel_vdd_off(intel_dp, false);
 }
 
 static void intel_dp_commit(struct drm_encoder *encoder)
@@ -1294,11 +1296,9 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 		/* Switching the panel off requires vdd. */
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_backlight_off(intel_dp);
-		ironlake_edp_panel_off(intel_dp);
-
 		intel_dp_sink_dpms(intel_dp, mode);
+		ironlake_edp_panel_off(intel_dp);
 		intel_dp_link_down(intel_dp);
-		ironlake_edp_panel_vdd_off(intel_dp, false);
 
 		if (is_cpu_edp(intel_dp))
 			ironlake_edp_pll_off(encoder);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 13f0467c1f4..6920bc26a2e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -47,15 +47,16 @@
 })
 
 #define wait_for_atomic_us(COND, US) ({ \
-	int i, ret__ = -ETIMEDOUT;	\
-	for (i = 0; i < (US); i++) {	\
-		if ((COND)) {		\
-			ret__ = 0;	\
-			break;		\
-		}			\
-		udelay(1);		\
-	}				\
-	ret__;				\
+	unsigned long timeout__ = jiffies + usecs_to_jiffies(US);	\
+	int ret__ = 0;							\
+	while (!(COND)) {						\
+		if (time_after(jiffies, timeout__)) {			\
+			ret__ = -ETIMEDOUT;				\
+			break;						\
+		}							\
+		cpu_relax();						\
+	}								\
+	ret__;								\
 })
 
 #define wait_for(COND, MS) _wait_for(COND, MS, 1)
@@ -398,7 +399,6 @@ extern void intel_pch_panel_fitting(struct drm_device *dev,
 				    const struct drm_display_mode *mode,
 				    struct drm_display_mode *adjusted_mode);
 extern u32 intel_panel_get_max_backlight(struct drm_device *dev);
-extern u32 intel_panel_get_backlight(struct drm_device *dev);
 extern void intel_panel_set_backlight(struct drm_device *dev, u32 level);
 extern int intel_panel_setup_backlight(struct drm_device *dev);
 extern void intel_panel_enable_backlight(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 1991a4408cf..b9755f6378d 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -486,9 +486,6 @@ int intel_setup_gmbus(struct drm_device *dev)
 		bus->dev_priv = dev_priv;
 
 		bus->adapter.algo = &gmbus_algorithm;
-		ret = i2c_add_adapter(&bus->adapter);
-		if (ret)
-			goto err;
 
 		/* By default use a conservative clock rate */
 		bus->reg0 = port | GMBUS_RATE_100KHZ;
@@ -498,6 +495,10 @@ int intel_setup_gmbus(struct drm_device *dev)
 			bus->force_bit = true;
 
 		intel_gpio_setup(bus, port);
+
+		ret = i2c_add_adapter(&bus->adapter);
+		if (ret)
+			goto err;
 	}
 
 	intel_i2c_reset(dev_priv->dev);
@@ -540,9 +541,6 @@ void intel_teardown_gmbus(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	if (dev_priv->gmbus == NULL)
-		return;
-
 	for (i = 0; i < GMBUS_NUM_PORTS; i++) {
 		struct intel_gmbus *bus = &dev_priv->gmbus[i];
 		i2c_del_adapter(&bus->adapter);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 10c7d39034e..3df4f5fa892 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -213,7 +213,7 @@ static u32 intel_panel_compute_brightness(struct drm_device *dev, u32 val)
 	return val;
 }
 
-u32 intel_panel_get_backlight(struct drm_device *dev)
+static u32 intel_panel_get_backlight(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val;
@@ -311,9 +311,6 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 	if (dev_priv->backlight_level == 0)
 		dev_priv->backlight_level = intel_panel_get_max_backlight(dev);
 
-	dev_priv->backlight_enabled = true;
-	intel_panel_actually_set_backlight(dev, dev_priv->backlight_level);
-
 	if (INTEL_INFO(dev)->gen >= 4) {
 		uint32_t reg, tmp;
 
@@ -326,7 +323,7 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 		 * we don't track the backlight dpms state, hence check whether
 		 * we have to do anything first. */
 		if (tmp & BLM_PWM_ENABLE)
-			return;
+			goto set_level;
 
 		if (dev_priv->num_pipe == 3)
 			tmp &= ~BLM_PIPE_SELECT_IVB;
@@ -347,6 +344,14 @@ void intel_panel_enable_backlight(struct drm_device *dev,
 			I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
 		}
 	}
+
+set_level:
+	/* Call below after setting BLC_PWM_CPU_CTL2 and BLC_PWM_PCH_CTL1.
+	 * BLC_PWM_CPU_CTL may be cleared to zero automatically when these
+	 * registers are set.
+	 */
+	dev_priv->backlight_enabled = true;
+	intel_panel_actually_set_backlight(dev, dev_priv->backlight_level);
 }
 
 static void intel_panel_init_backlight(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d64dffbe0e0..c0407aa5baa 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3972,6 +3972,7 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Force wake wait timed out\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE, 1);
+	POSTING_READ(FORCEWAKE);
 
 	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
 		DRM_ERROR("Force wake wait timed out\n");
@@ -3992,6 +3993,7 @@ static void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Force wake wait timed out\n");
 
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_ENABLE(1));
+	POSTING_READ(FORCEWAKE_MT);
 
 	if (wait_for_atomic_us((I915_READ_NOTRACE(forcewake_ack) & 1), 500))
 		DRM_ERROR("Force wake wait timed out\n");
@@ -4027,14 +4029,14 @@ void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv)
 static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE, 0);
-	/* The below doubles as a POSTING_READ */
+	POSTING_READ(FORCEWAKE);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
 static void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE_NOTRACE(FORCEWAKE_MT, _MASKED_BIT_DISABLE(1));
-	/* The below doubles as a POSTING_READ */
+	POSTING_READ(FORCEWAKE_MT);
 	gen6_gt_check_fifodbg(dev_priv);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e278675cdff..c828169c73a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -214,26 +214,35 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
                          u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
+	struct pipe_control *pc = ring->private;
+	u32 scratch_addr = pc->gtt_offset + 128;
 	int ret;
 
 	/* Just flush everything.  Experiments have shown that reducing the
 	 * number of bits based on the write domains has little performance
 	 * impact.
 	 */
-	flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_TLB_INVALIDATE;
-	flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
-	flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
-	flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
-	/*
-	 * Ensure that any following seqno writes only happen when the render
-	 * cache is indeed flushed (but only if the caller actually wants that).
-	 */
-	if (flush_domains)
+	if (flush_domains) {
+		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+		/*
+		 * Ensure that any following seqno writes only happen
+		 * when the render cache is indeed flushed.
+		 */
 		flags |= PIPE_CONTROL_CS_STALL;
+	}
+	if (invalidate_domains) {
+		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		/*
+		 * TLB invalidate requires a post-sync write.
+		 */
+		flags |= PIPE_CONTROL_QW_WRITE;
+	}
 
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
@@ -241,7 +250,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 
 	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4));
 	intel_ring_emit(ring, flags);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
@@ -294,8 +303,6 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	I915_WRITE_HEAD(ring, 0);
 	ring->write_tail(ring, 0);
 
-	/* Initialize the ring. */
-	I915_WRITE_START(ring, obj->gtt_offset);
 	head = I915_READ_HEAD(ring) & HEAD_ADDR;
 
 	/* G45 ring initialization fails to reset head to zero */
@@ -321,6 +328,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		}
 	}
 
+	/* Initialize the ring. This must happen _after_ we've cleared the ring
+	 * registers with the above sequence (the readback of the HEAD registers
+	 * also enforces ordering), otherwise the hw might lose the new ring
+	 * register values. */
+	I915_WRITE_START(ring, obj->gtt_offset);
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index d881602a915..f3762f8b719 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -444,13 +444,16 @@ static bool intel_sdvo_write_cmd(struct intel_sdvo *intel_sdvo, u8 cmd,
 	struct i2c_msg *msgs;
 	int i, ret = true;
 
+        /* Would be simpler to allocate both in one go ? */        
 	buf = (u8 *)kzalloc(args_len * 2 + 2, GFP_KERNEL);
 	if (!buf)
 		return false;
 
 	msgs = kcalloc(args_len + 3, sizeof(*msgs), GFP_KERNEL);
-	if (!msgs)
+	if (!msgs) {
+	        kfree(buf);
 		return false;
+        }
 
 	intel_sdvo_debug_write(intel_sdvo, cmd, args, args_len);
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index a4d7c500c97..b69642d5d85 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -468,10 +468,11 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 {
 	unsigned int vcomax, vcomin, pllreffreq;
 	unsigned int delta, tmpdelta;
-	unsigned int testr, testn, testm, testo;
+	int testr, testn, testm, testo;
 	unsigned int p, m, n;
-	unsigned int computed;
+	unsigned int computed, vco;
 	int tmp;
+	const unsigned int m_div_val[] = { 1, 2, 4, 8 };
 
 	m = n = p = 0;
 	vcomax = 1488000;
@@ -490,12 +491,13 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 				if (delta == 0)
 					break;
 				for (testo = 5; testo < 33; testo++) {
-					computed = pllreffreq * (testn + 1) /
+					vco = pllreffreq * (testn + 1) /
 						(testr + 1);
-					if (computed < vcomin)
+					if (vco < vcomin)
 						continue;
-					if (computed > vcomax)
+					if (vco > vcomax)
 						continue;
+					computed = vco / (m_div_val[testm] * (testo + 1));
 					if (computed > clock)
 						tmpdelta = computed - clock;
 					else
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index fe5267d06ab..1cece6a78f3 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -4,7 +4,7 @@
 
 ccflags-y := -Iinclude/drm
 nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \
-             nouveau_object.o nouveau_irq.o nouveau_notifier.o \
+             nouveau_gpuobj.o nouveau_irq.o nouveau_notifier.o \
              nouveau_sgdma.o nouveau_dma.o nouveau_util.o \
              nouveau_bo.o nouveau_fence.o nouveau_gem.o nouveau_ttm.o \
              nouveau_hw.o nouveau_calc.o nouveau_bios.o nouveau_i2c.o \
@@ -12,6 +12,7 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \
              nouveau_hdmi.o nouveau_dp.o nouveau_ramht.o \
 	     nouveau_pm.o nouveau_volt.o nouveau_perf.o nouveau_temp.o \
 	     nouveau_mm.o nouveau_vm.o nouveau_mxm.o nouveau_gpio.o \
+	     nouveau_abi16.o \
              nv04_timer.o \
              nv04_mc.o nv40_mc.o nv50_mc.o \
              nv04_fb.o nv10_fb.o nv20_fb.o nv30_fb.o nv40_fb.o \
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
new file mode 100644
index 00000000000..ff23d88880e
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -0,0 +1,245 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "drmP.h"
+
+#include "nouveau_drv.h"
+#include "nouveau_dma.h"
+#include "nouveau_abi16.h"
+#include "nouveau_ramht.h"
+#include "nouveau_software.h"
+
+int
+nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct drm_nouveau_getparam *getparam = data;
+
+	switch (getparam->param) {
+	case NOUVEAU_GETPARAM_CHIPSET_ID:
+		getparam->value = dev_priv->chipset;
+		break;
+	case NOUVEAU_GETPARAM_PCI_VENDOR:
+		getparam->value = dev->pci_vendor;
+		break;
+	case NOUVEAU_GETPARAM_PCI_DEVICE:
+		getparam->value = dev->pci_device;
+		break;
+	case NOUVEAU_GETPARAM_BUS_TYPE:
+		if (drm_pci_device_is_agp(dev))
+			getparam->value = 0;
+		else
+		if (!pci_is_pcie(dev->pdev))
+			getparam->value = 1;
+		else
+			getparam->value = 2;
+		break;
+	case NOUVEAU_GETPARAM_FB_SIZE:
+		getparam->value = dev_priv->fb_available_size;
+		break;
+	case NOUVEAU_GETPARAM_AGP_SIZE:
+		getparam->value = dev_priv->gart_info.aper_size;
+		break;
+	case NOUVEAU_GETPARAM_VM_VRAM_BASE:
+		getparam->value = 0; /* deprecated */
+		break;
+	case NOUVEAU_GETPARAM_PTIMER_TIME:
+		getparam->value = dev_priv->engine.timer.read(dev);
+		break;
+	case NOUVEAU_GETPARAM_HAS_BO_USAGE:
+		getparam->value = 1;
+		break;
+	case NOUVEAU_GETPARAM_HAS_PAGEFLIP:
+		getparam->value = 1;
+		break;
+	case NOUVEAU_GETPARAM_GRAPH_UNITS:
+		/* NV40 and NV50 versions are quite different, but register
+		 * address is the same. User is supposed to know the card
+		 * family anyway... */
+		if (dev_priv->chipset >= 0x40) {
+			getparam->value = nv_rd32(dev, NV40_PMC_GRAPH_UNITS);
+			break;
+		}
+		/* FALLTHRU */
+	default:
+		NV_DEBUG(dev, "unknown parameter %lld\n", getparam->param);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int
+nouveau_abi16_ioctl_setparam(ABI16_IOCTL_ARGS)
+{
+	return -EINVAL;
+}
+
+int
+nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct drm_nouveau_channel_alloc *init = data;
+	struct nouveau_channel *chan;
+	int ret;
+
+	if (!dev_priv->eng[NVOBJ_ENGINE_GR])
+		return -ENODEV;
+
+	if (init->fb_ctxdma_handle == ~0 || init->tt_ctxdma_handle == ~0)
+		return -EINVAL;
+
+	ret = nouveau_channel_alloc(dev, &chan, file_priv,
+				    init->fb_ctxdma_handle,
+				    init->tt_ctxdma_handle);
+	if (ret)
+		return ret;
+	init->channel  = chan->id;
+
+	if (nouveau_vram_pushbuf == 0) {
+		if (chan->dma.ib_max)
+			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM |
+						NOUVEAU_GEM_DOMAIN_GART;
+		else if (chan->pushbuf_bo->bo.mem.mem_type == TTM_PL_VRAM)
+			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM;
+		else
+			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_GART;
+	} else {
+		init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM;
+	}
+
+	if (dev_priv->card_type < NV_C0) {
+		init->subchan[0].handle = 0x00000000;
+		init->subchan[0].grclass = 0x0000;
+		init->subchan[1].handle = NvSw;
+		init->subchan[1].grclass = NV_SW;
+		init->nr_subchan = 2;
+	}
+
+	/* Named memory object area */
+	ret = drm_gem_handle_create(file_priv, chan->notifier_bo->gem,
+				    &init->notifier_handle);
+
+	if (ret == 0)
+		atomic_inc(&chan->users); /* userspace reference */
+	nouveau_channel_put(&chan);
+	return ret;
+}
+
+int
+nouveau_abi16_ioctl_channel_free(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_channel_free *req = data;
+	struct nouveau_channel *chan;
+
+	chan = nouveau_channel_get(file_priv, req->channel);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	list_del(&chan->list);
+	atomic_dec(&chan->users);
+	nouveau_channel_put(&chan);
+	return 0;
+}
+
+int
+nouveau_abi16_ioctl_grobj_alloc(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_grobj_alloc *init = data;
+	struct nouveau_channel *chan;
+	int ret;
+
+	if (init->handle == ~0)
+		return -EINVAL;
+
+	/* compatibility with userspace that assumes 506e for all chipsets */
+	if (init->class == 0x506e) {
+		init->class = nouveau_software_class(dev);
+		if (init->class == 0x906e)
+			return 0;
+	} else
+	if (init->class == 0x906e) {
+		NV_ERROR(dev, "906e not supported yet\n");
+		return -EINVAL;
+	}
+
+	chan = nouveau_channel_get(file_priv, init->channel);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	if (nouveau_ramht_find(chan, init->handle)) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	ret = nouveau_gpuobj_gr_new(chan, init->handle, init->class);
+	if (ret) {
+		NV_ERROR(dev, "Error creating object: %d (%d/0x%08x)\n",
+			 ret, init->channel, init->handle);
+	}
+
+out:
+	nouveau_channel_put(&chan);
+	return ret;
+}
+
+int
+nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct drm_nouveau_notifierobj_alloc *na = data;
+	struct nouveau_channel *chan;
+	int ret;
+
+	/* completely unnecessary for these chipsets... */
+	if (unlikely(dev_priv->card_type >= NV_C0))
+		return -EINVAL;
+
+	chan = nouveau_channel_get(file_priv, na->channel);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	ret = nouveau_notifier_alloc(chan, na->handle, na->size, 0, 0x1000,
+				     &na->offset);
+	nouveau_channel_put(&chan);
+	return ret;
+}
+
+int
+nouveau_abi16_ioctl_gpuobj_free(ABI16_IOCTL_ARGS)
+{
+	struct drm_nouveau_gpuobj_free *objfree = data;
+	struct nouveau_channel *chan;
+	int ret;
+
+	chan = nouveau_channel_get(file_priv, objfree->channel);
+	if (IS_ERR(chan))
+		return PTR_ERR(chan);
+
+	/* Synchronize with the user channel */
+	nouveau_channel_idle(chan);
+
+	ret = nouveau_ramht_remove(chan, objfree->handle);
+	nouveau_channel_put(&chan);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
new file mode 100644
index 00000000000..e6328b008a8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -0,0 +1,83 @@
+#ifndef __NOUVEAU_ABI16_H__
+#define __NOUVEAU_ABI16_H__
+
+#define ABI16_IOCTL_ARGS                                                       \
+	struct drm_device *dev, void *data, struct drm_file *file_priv
+int nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_setparam(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_channel_free(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_grobj_alloc(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS);
+int nouveau_abi16_ioctl_gpuobj_free(ABI16_IOCTL_ARGS);
+
+struct drm_nouveau_channel_alloc {
+	uint32_t     fb_ctxdma_handle;
+	uint32_t     tt_ctxdma_handle;
+
+	int          channel;
+	uint32_t     pushbuf_domains;
+
+	/* Notifier memory */
+	uint32_t     notifier_handle;
+
+	/* DRM-enforced subchannel assignments */
+	struct {
+		uint32_t handle;
+		uint32_t grclass;
+	} subchan[8];
+	uint32_t nr_subchan;
+};
+
+struct drm_nouveau_channel_free {
+	int channel;
+};
+
+struct drm_nouveau_grobj_alloc {
+	int      channel;
+	uint32_t handle;
+	int      class;
+};
+
+struct drm_nouveau_notifierobj_alloc {
+	uint32_t channel;
+	uint32_t handle;
+	uint32_t size;
+	uint32_t offset;
+};
+
+struct drm_nouveau_gpuobj_free {
+	int      channel;
+	uint32_t handle;
+};
+
+#define NOUVEAU_GETPARAM_PCI_VENDOR      3
+#define NOUVEAU_GETPARAM_PCI_DEVICE      4
+#define NOUVEAU_GETPARAM_BUS_TYPE        5
+#define NOUVEAU_GETPARAM_FB_SIZE         8
+#define NOUVEAU_GETPARAM_AGP_SIZE        9
+#define NOUVEAU_GETPARAM_CHIPSET_ID      11
+#define NOUVEAU_GETPARAM_VM_VRAM_BASE    12
+#define NOUVEAU_GETPARAM_GRAPH_UNITS     13
+#define NOUVEAU_GETPARAM_PTIMER_TIME     14
+#define NOUVEAU_GETPARAM_HAS_BO_USAGE    15
+#define NOUVEAU_GETPARAM_HAS_PAGEFLIP    16
+struct drm_nouveau_getparam {
+	uint64_t param;
+	uint64_t value;
+};
+
+struct drm_nouveau_setparam {
+	uint64_t param;
+	uint64_t value;
+};
+
+#define DRM_IOCTL_NOUVEAU_GETPARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GETPARAM, struct drm_nouveau_getparam)
+#define DRM_IOCTL_NOUVEAU_SETPARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SETPARAM, struct drm_nouveau_setparam)
+#define DRM_IOCTL_NOUVEAU_CHANNEL_ALLOC      DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_ALLOC, struct drm_nouveau_channel_alloc)
+#define DRM_IOCTL_NOUVEAU_CHANNEL_FREE       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_FREE, struct drm_nouveau_channel_free)
+#define DRM_IOCTL_NOUVEAU_GROBJ_ALLOC        DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GROBJ_ALLOC, struct drm_nouveau_grobj_alloc)
+#define DRM_IOCTL_NOUVEAU_NOTIFIEROBJ_ALLOC  DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_NOTIFIEROBJ_ALLOC, struct drm_nouveau_notifierobj_alloc)
+#define DRM_IOCTL_NOUVEAU_GPUOBJ_FREE        DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GPUOBJ_FREE, struct drm_nouveau_gpuobj_free)
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 2f11e16a81a..a0a3fe3c016 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -6091,6 +6091,18 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf)
 		}
 	}
 
+	/* fdo#50830: connector indices for VGA and DVI-I are backwards */
+	if (nv_match_device(dev, 0x0421, 0x3842, 0xc793)) {
+		if (idx == 0 && *conn == 0x02000300)
+			*conn = 0x02011300;
+		else
+		if (idx == 1 && *conn == 0x04011310)
+			*conn = 0x04000310;
+		else
+		if (idx == 2 && *conn == 0x02011312)
+			*conn = 0x02000312;
+	}
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c
index 629d8a2df5b..debd90225a8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_channel.c
+++ b/drivers/gpu/drm/nouveau/nouveau_channel.c
@@ -395,98 +395,3 @@ nouveau_channel_cleanup(struct drm_device *dev, struct drm_file *file_priv)
 		nouveau_channel_put(&chan);
 	}
 }
-
-
-/***********************************
- * ioctls wrapping the functions
- ***********************************/
-
-static int
-nouveau_ioctl_fifo_alloc(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv)
-{
-	struct drm_nouveau_private *dev_priv = dev->dev_private;
-	struct drm_nouveau_channel_alloc *init = data;
-	struct nouveau_channel *chan;
-	int ret;
-
-	if (!dev_priv->eng[NVOBJ_ENGINE_GR])
-		return -ENODEV;
-
-	if (init->fb_ctxdma_handle == ~0 || init->tt_ctxdma_handle == ~0)
-		return -EINVAL;
-
-	ret = nouveau_channel_alloc(dev, &chan, file_priv,
-				    init->fb_ctxdma_handle,
-				    init->tt_ctxdma_handle);
-	if (ret)
-		return ret;
-	init->channel  = chan->id;
-
-	if (nouveau_vram_pushbuf == 0) {
-		if (chan->dma.ib_max)
-			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM |
-						NOUVEAU_GEM_DOMAIN_GART;
-		else if (chan->pushbuf_bo->bo.mem.mem_type == TTM_PL_VRAM)
-			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM;
-		else
-			init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_GART;
-	} else {
-		init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM;
-	}
-
-	if (dev_priv->card_type < NV_C0) {
-		init->subchan[0].handle = 0x00000000;
-		init->subchan[0].grclass = 0x0000;
-		init->subchan[1].handle = NvSw;
-		init->subchan[1].grclass = NV_SW;
-		init->nr_subchan = 2;
-	}
-
-	/* Named memory object area */
-	ret = drm_gem_handle_create(file_priv, chan->notifier_bo->gem,
-				    &init->notifier_handle);
-
-	if (ret == 0)
-		atomic_inc(&chan->users); /* userspace reference */
-	nouveau_channel_put(&chan);
-	return ret;
-}
-
-static int
-nouveau_ioctl_fifo_free(struct drm_device *dev, void *data,
-			struct drm_file *file_priv)
-{
-	struct drm_nouveau_channel_free *req = data;
-	struct nouveau_channel *chan;
-
-	chan = nouveau_channel_get(file_priv, req->channel);
-	if (IS_ERR(chan))
-		return PTR_ERR(chan);
-
-	list_del(&chan->list);
-	atomic_dec(&chan->users);
-	nouveau_channel_put(&chan);
-	return 0;
-}
-
-/***********************************
- * finally, the ioctl table
- ***********************************/
-
-struct drm_ioctl_desc nouveau_ioctls[] = {
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GETPARAM, nouveau_ioctl_getparam, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_SETPARAM, nouveau_ioctl_setparam, DRM_UNLOCKED|DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_ALLOC, nouveau_ioctl_fifo_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_FREE, nouveau_ioctl_fifo_free, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GROBJ_ALLOC, nouveau_ioctl_grobj_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_ioctl_notifier_alloc, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_ioctl_gpuobj_free, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_PUSHBUF, nouveau_gem_ioctl_pushbuf, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_UNLOCKED|DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_UNLOCKED|DRM_AUTH),
-};
-
-int nouveau_max_ioctl = DRM_ARRAY_SIZE(nouveau_ioctls);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.c b/drivers/gpu/drm/nouveau/nouveau_drv.c
index b4d1b4afcac..9a36f5f39b0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.c
@@ -29,6 +29,7 @@
 #include "drm.h"
 #include "drm_crtc_helper.h"
 #include "nouveau_drv.h"
+#include "nouveau_abi16.h"
 #include "nouveau_hw.h"
 #include "nouveau_fb.h"
 #include "nouveau_fbcon.h"
@@ -384,6 +385,21 @@ nouveau_pci_resume(struct pci_dev *pdev)
 	return 0;
 }
 
+static struct drm_ioctl_desc nouveau_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GETPARAM, nouveau_abi16_ioctl_getparam, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_SETPARAM, nouveau_abi16_ioctl_setparam, DRM_UNLOCKED|DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_ALLOC, nouveau_abi16_ioctl_channel_alloc, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_CHANNEL_FREE, nouveau_abi16_ioctl_channel_free, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GROBJ_ALLOC, nouveau_abi16_ioctl_grobj_alloc, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_NOTIFIEROBJ_ALLOC, nouveau_abi16_ioctl_notifierobj_alloc, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GPUOBJ_FREE, nouveau_abi16_ioctl_gpuobj_free, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_NEW, nouveau_gem_ioctl_new, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_PUSHBUF, nouveau_gem_ioctl_pushbuf, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_UNLOCKED|DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_UNLOCKED|DRM_AUTH),
+};
+
 static const struct file_operations nouveau_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -462,7 +478,7 @@ static struct pci_driver nouveau_pci_driver = {
 
 static int __init nouveau_init(void)
 {
-	driver.num_ioctls = nouveau_max_ioctl;
+	driver.num_ioctls = ARRAY_SIZE(nouveau_ioctls);
 
 	if (nouveau_modeset == -1) {
 #ifdef CONFIG_VGA_CONSOLE
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8613cb23808..4f2cc95ce26 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -689,8 +689,6 @@ struct drm_nouveau_private {
 	void (*irq_handler[32])(struct drm_device *);
 	bool msi_enabled;
 
-	struct list_head vbl_waiting;
-
 	struct {
 		struct drm_global_reference mem_global_ref;
 		struct ttm_bo_global_ref bo_global_ref;
@@ -872,10 +870,6 @@ extern int  nouveau_load(struct drm_device *, unsigned long flags);
 extern int  nouveau_firstopen(struct drm_device *);
 extern void nouveau_lastclose(struct drm_device *);
 extern int  nouveau_unload(struct drm_device *);
-extern int  nouveau_ioctl_getparam(struct drm_device *, void *data,
-				   struct drm_file *);
-extern int  nouveau_ioctl_setparam(struct drm_device *, void *data,
-				   struct drm_file *);
 extern bool nouveau_wait_eq(struct drm_device *, uint64_t timeout,
 			    uint32_t reg, uint32_t mask, uint32_t val);
 extern bool nouveau_wait_ne(struct drm_device *, uint64_t timeout,
@@ -914,15 +908,8 @@ extern void nouveau_notifier_takedown_channel(struct nouveau_channel *);
 extern int  nouveau_notifier_alloc(struct nouveau_channel *, uint32_t handle,
 				   int cout, uint32_t start, uint32_t end,
 				   uint32_t *offset);
-extern int  nouveau_notifier_offset(struct nouveau_gpuobj *, uint32_t *);
-extern int  nouveau_ioctl_notifier_alloc(struct drm_device *, void *data,
-					 struct drm_file *);
-extern int  nouveau_ioctl_notifier_free(struct drm_device *, void *data,
-					struct drm_file *);
 
 /* nouveau_channel.c */
-extern struct drm_ioctl_desc nouveau_ioctls[];
-extern int nouveau_max_ioctl;
 extern void nouveau_channel_cleanup(struct drm_device *, struct drm_file *);
 extern int  nouveau_channel_alloc(struct drm_device *dev,
 				  struct nouveau_channel **chan,
@@ -938,7 +925,7 @@ extern void nouveau_channel_ref(struct nouveau_channel *chan,
 				struct nouveau_channel **pchan);
 extern int  nouveau_channel_idle(struct nouveau_channel *chan);
 
-/* nouveau_object.c */
+/* nouveau_gpuobj.c */
 #define NVOBJ_ENGINE_ADD(d, e, p) do {                                         \
 	struct drm_nouveau_private *dev_priv = (d)->dev_private;               \
 	dev_priv->eng[NVOBJ_ENGINE_##e] = (p);                                 \
@@ -993,10 +980,6 @@ extern int nv50_gpuobj_dma_new(struct nouveau_channel *, int class, u64 base,
 extern void nv50_gpuobj_dma_init(struct nouveau_gpuobj *, u32 offset,
 				 int class, u64 base, u64 size, int target,
 				 int access, u32 type, u32 comp);
-extern int nouveau_ioctl_grobj_alloc(struct drm_device *, void *data,
-				     struct drm_file *);
-extern int nouveau_ioctl_gpuobj_free(struct drm_device *, void *data,
-				     struct drm_file *);
 
 /* nouveau_irq.c */
 extern int         nouveau_irq_init(struct drm_device *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 153b9a15469..1074bc5dd41 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -467,7 +467,7 @@ int nouveau_fbcon_init(struct drm_device *dev)
 	nfbdev->helper.funcs = &nouveau_fbcon_helper_funcs;
 
 	ret = drm_fb_helper_init(dev, &nfbdev->helper,
-				 nv_two_heads(dev) ? 2 : 1, 4);
+				 dev->mode_config.num_crtc, 4);
 	if (ret) {
 		kfree(nfbdev);
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 30f54231694..af7cfb82571 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -207,8 +207,7 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data,
 	struct nouveau_bo *nvbo = NULL;
 	int ret = 0;
 
-	if (unlikely(dev_priv->ttm.bdev.dev_mapping == NULL))
-		dev_priv->ttm.bdev.dev_mapping = dev_priv->dev->dev_mapping;
+	dev_priv->ttm.bdev.dev_mapping = dev->dev_mapping;
 
 	if (!dev_priv->engine.vram.flags_valid(dev, req->info.tile_flags)) {
 		NV_ERROR(dev, "bad page flags: 0x%08x\n", req->info.tile_flags);
@@ -342,6 +341,7 @@ retry:
 		if (nvbo->reserved_by && nvbo->reserved_by == file_priv) {
 			NV_ERROR(dev, "multiple instances of buffer %d on "
 				      "validation list\n", b->handle);
+			drm_gem_object_unreference_unlocked(gem);
 			validate_fini(op, NULL);
 			return -EINVAL;
 		}
diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_gpuobj.c
index b190cc01c82..bd79fedb705 100644
--- a/drivers/gpu/drm/nouveau/nouveau_object.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gpuobj.c
@@ -758,66 +758,6 @@ nouveau_gpuobj_resume(struct drm_device *dev)
 	dev_priv->engine.instmem.flush(dev);
 }
 
-int nouveau_ioctl_grobj_alloc(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv)
-{
-	struct drm_nouveau_grobj_alloc *init = data;
-	struct nouveau_channel *chan;
-	int ret;
-
-	if (init->handle == ~0)
-		return -EINVAL;
-
-	/* compatibility with userspace that assumes 506e for all chipsets */
-	if (init->class == 0x506e) {
-		init->class = nouveau_software_class(dev);
-		if (init->class == 0x906e)
-			return 0;
-	} else
-	if (init->class == 0x906e) {
-		NV_ERROR(dev, "906e not supported yet\n");
-		return -EINVAL;
-	}
-
-	chan = nouveau_channel_get(file_priv, init->channel);
-	if (IS_ERR(chan))
-		return PTR_ERR(chan);
-
-	if (nouveau_ramht_find(chan, init->handle)) {
-		ret = -EEXIST;
-		goto out;
-	}
-
-	ret = nouveau_gpuobj_gr_new(chan, init->handle, init->class);
-	if (ret) {
-		NV_ERROR(dev, "Error creating object: %d (%d/0x%08x)\n",
-			 ret, init->channel, init->handle);
-	}
-
-out:
-	nouveau_channel_put(&chan);
-	return ret;
-}
-
-int nouveau_ioctl_gpuobj_free(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv)
-{
-	struct drm_nouveau_gpuobj_free *objfree = data;
-	struct nouveau_channel *chan;
-	int ret;
-
-	chan = nouveau_channel_get(file_priv, objfree->channel);
-	if (IS_ERR(chan))
-		return PTR_ERR(chan);
-
-	/* Synchronize with the user channel */
-	nouveau_channel_idle(chan);
-
-	ret = nouveau_ramht_remove(chan, objfree->handle);
-	nouveau_channel_put(&chan);
-	return ret;
-}
-
 u32
 nv_ro32(struct nouveau_gpuobj *gpuobj, u32 offset)
 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
index 77e564667b5..240cf962c99 100644
--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
+++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
@@ -229,7 +229,7 @@ nouveau_i2c_init(struct drm_device *dev)
 			}
 			break;
 		case 6: /* NV50- DP AUX */
-			port->drive = entry[0];
+			port->drive = entry[0] & 0x0f;
 			port->sense = port->drive;
 			port->adapter.algo = &nouveau_dp_i2c_algo;
 			break;
diff --git a/drivers/gpu/drm/nouveau/nouveau_irq.c b/drivers/gpu/drm/nouveau/nouveau_irq.c
index 868c7fd7485..b2c2937531a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_irq.c
+++ b/drivers/gpu/drm/nouveau/nouveau_irq.c
@@ -41,12 +41,8 @@
 void
 nouveau_irq_preinstall(struct drm_device *dev)
 {
-	struct drm_nouveau_private *dev_priv = dev->dev_private;
-
 	/* Master disable */
 	nv_wr32(dev, NV03_PMC_INTR_EN_0, 0);
-
-	INIT_LIST_HEAD(&dev_priv->vbl_waiting);
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nouveau_notifier.c b/drivers/gpu/drm/nouveau/nouveau_notifier.c
index 2ef883c4bbc..69c93b86451 100644
--- a/drivers/gpu/drm/nouveau/nouveau_notifier.c
+++ b/drivers/gpu/drm/nouveau/nouveau_notifier.c
@@ -161,44 +161,3 @@ nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle,
 	*b_offset = mem->start;
 	return 0;
 }
-
-int
-nouveau_notifier_offset(struct nouveau_gpuobj *nobj, uint32_t *poffset)
-{
-	if (!nobj || nobj->dtor != nouveau_notifier_gpuobj_dtor)
-		return -EINVAL;
-
-	if (poffset) {
-		struct drm_mm_node *mem = nobj->priv;
-
-		if (*poffset >= mem->size)
-			return false;
-
-		*poffset += mem->start;
-	}
-
-	return 0;
-}
-
-int
-nouveau_ioctl_notifier_alloc(struct drm_device *dev, void *data,
-			     struct drm_file *file_priv)
-{
-	struct drm_nouveau_private *dev_priv = dev->dev_private;
-	struct drm_nouveau_notifierobj_alloc *na = data;
-	struct nouveau_channel *chan;
-	int ret;
-
-	/* completely unnecessary for these chipsets... */
-	if (unlikely(dev_priv->card_type >= NV_C0))
-		return -EINVAL;
-
-	chan = nouveau_channel_get(file_priv, na->channel);
-	if (IS_ERR(chan))
-		return PTR_ERR(chan);
-
-	ret = nouveau_notifier_alloc(chan, na->handle, na->size, 0, 0x1000,
-				     &na->offset);
-	nouveau_channel_put(&chan);
-	return ret;
-}
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index a89240e5fb2..a25cf2cb931 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -1,3 +1,26 @@
+/*
+ * Copyright 2011 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Dave Airlie
+ */
 
 #include "drmP.h"
 #include "drm.h"
diff --git a/drivers/gpu/drm/nouveau/nouveau_software.h b/drivers/gpu/drm/nouveau/nouveau_software.h
index e60bc6ce900..709e5ac680e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_software.h
+++ b/drivers/gpu/drm/nouveau/nouveau_software.h
@@ -4,13 +4,15 @@
 struct nouveau_software_priv {
 	struct nouveau_exec_engine base;
 	struct list_head vblank;
+	spinlock_t peephole_lock;
 };
 
 struct nouveau_software_chan {
 	struct list_head flip;
 	struct {
 		struct list_head list;
-		struct nouveau_bo *bo;
+		u32 channel;
+		u32 ctxdma;
 		u32 offset;
 		u32 value;
 		u32 head;
@@ -18,32 +20,17 @@ struct nouveau_software_chan {
 };
 
 static inline void
-nouveau_software_vblank(struct drm_device *dev, int crtc)
-{
-	struct nouveau_software_priv *psw = nv_engine(dev, NVOBJ_ENGINE_SW);
-	struct nouveau_software_chan *pch, *tmp;
-
-	list_for_each_entry_safe(pch, tmp, &psw->vblank, vblank.list) {
-		if (pch->vblank.head != crtc)
-			continue;
-
-		nouveau_bo_wr32(pch->vblank.bo, pch->vblank.offset,
-						pch->vblank.value);
-		list_del(&pch->vblank.list);
-		drm_vblank_put(dev, crtc);
-	}
-}
-
-static inline void
 nouveau_software_context_new(struct nouveau_software_chan *pch)
 {
 	INIT_LIST_HEAD(&pch->flip);
+	INIT_LIST_HEAD(&pch->vblank.list);
 }
 
 static inline void
 nouveau_software_create(struct nouveau_software_priv *psw)
 {
 	INIT_LIST_HEAD(&psw->vblank);
+	spin_lock_init(&psw->peephole_lock);
 }
 
 static inline u16
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 19706f0532e..1866dbb4997 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -731,7 +731,6 @@ nouveau_card_init(struct drm_device *dev)
 			case 0xa3:
 			case 0xa5:
 			case 0xa8:
-			case 0xaf:
 				nva3_copy_create(dev);
 				break;
 			}
@@ -1234,80 +1233,6 @@ int nouveau_unload(struct drm_device *dev)
 	return 0;
 }
 
-int nouveau_ioctl_getparam(struct drm_device *dev, void *data,
-						struct drm_file *file_priv)
-{
-	struct drm_nouveau_private *dev_priv = dev->dev_private;
-	struct drm_nouveau_getparam *getparam = data;
-
-	switch (getparam->param) {
-	case NOUVEAU_GETPARAM_CHIPSET_ID:
-		getparam->value = dev_priv->chipset;
-		break;
-	case NOUVEAU_GETPARAM_PCI_VENDOR:
-		getparam->value = dev->pci_vendor;
-		break;
-	case NOUVEAU_GETPARAM_PCI_DEVICE:
-		getparam->value = dev->pci_device;
-		break;
-	case NOUVEAU_GETPARAM_BUS_TYPE:
-		if (drm_pci_device_is_agp(dev))
-			getparam->value = NV_AGP;
-		else if (pci_is_pcie(dev->pdev))
-			getparam->value = NV_PCIE;
-		else
-			getparam->value = NV_PCI;
-		break;
-	case NOUVEAU_GETPARAM_FB_SIZE:
-		getparam->value = dev_priv->fb_available_size;
-		break;
-	case NOUVEAU_GETPARAM_AGP_SIZE:
-		getparam->value = dev_priv->gart_info.aper_size;
-		break;
-	case NOUVEAU_GETPARAM_VM_VRAM_BASE:
-		getparam->value = 0; /* deprecated */
-		break;
-	case NOUVEAU_GETPARAM_PTIMER_TIME:
-		getparam->value = dev_priv->engine.timer.read(dev);
-		break;
-	case NOUVEAU_GETPARAM_HAS_BO_USAGE:
-		getparam->value = 1;
-		break;
-	case NOUVEAU_GETPARAM_HAS_PAGEFLIP:
-		getparam->value = 1;
-		break;
-	case NOUVEAU_GETPARAM_GRAPH_UNITS:
-		/* NV40 and NV50 versions are quite different, but register
-		 * address is the same. User is supposed to know the card
-		 * family anyway... */
-		if (dev_priv->chipset >= 0x40) {
-			getparam->value = nv_rd32(dev, NV40_PMC_GRAPH_UNITS);
-			break;
-		}
-		/* FALLTHRU */
-	default:
-		NV_DEBUG(dev, "unknown parameter %lld\n", getparam->param);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-int
-nouveau_ioctl_setparam(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv)
-{
-	struct drm_nouveau_setparam *setparam = data;
-
-	switch (setparam->param) {
-	default:
-		NV_DEBUG(dev, "unknown parameter %lld\n", setparam->param);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /* Wait until (value(reg) & mask) == val, up until timeout has hit */
 bool
 nouveau_wait_eq(struct drm_device *dev, uint64_t timeout,
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 5c41612723b..b244d9968c5 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -646,7 +646,30 @@ nv50_display_script_select(struct drm_device *dev, struct dcb_entry *dcb,
 static void
 nv50_display_vblank_crtc_handler(struct drm_device *dev, int crtc)
 {
-	nouveau_software_vblank(dev, crtc);
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct nouveau_software_priv *psw = nv_engine(dev, NVOBJ_ENGINE_SW);
+	struct nouveau_software_chan *pch, *tmp;
+
+	list_for_each_entry_safe(pch, tmp, &psw->vblank, vblank.list) {
+		if (pch->vblank.head != crtc)
+			continue;
+
+		spin_lock(&psw->peephole_lock);
+		nv_wr32(dev, 0x001704, pch->vblank.channel);
+		nv_wr32(dev, 0x001710, 0x80000000 | pch->vblank.ctxdma);
+		if (dev_priv->chipset == 0x50) {
+			nv_wr32(dev, 0x001570, pch->vblank.offset);
+			nv_wr32(dev, 0x001574, pch->vblank.value);
+		} else {
+			nv_wr32(dev, 0x060010, pch->vblank.offset);
+			nv_wr32(dev, 0x060014, pch->vblank.value);
+		}
+		spin_unlock(&psw->peephole_lock);
+
+		list_del(&pch->vblank.list);
+		drm_vblank_put(dev, crtc);
+	}
+
 	drm_handle_vblank(dev, crtc);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nv50_graph.c b/drivers/gpu/drm/nouveau/nv50_graph.c
index d9cc2f2638d..437608d1dfe 100644
--- a/drivers/gpu/drm/nouveau/nv50_graph.c
+++ b/drivers/gpu/drm/nouveau/nv50_graph.c
@@ -299,7 +299,7 @@ static struct nouveau_bitfield nv50_graph_trap_ccache[] = {
 
 /* There must be a *lot* of these. Will take some time to gather them up. */
 struct nouveau_enum nv50_data_error_names[] = {
-	{ 0x00000003, "INVALID_QUERY_OR_TEXTURE", NULL },
+	{ 0x00000003, "INVALID_OPERATION", NULL },
 	{ 0x00000004, "INVALID_VALUE", NULL },
 	{ 0x00000005, "INVALID_ENUM", NULL },
 	{ 0x00000008, "INVALID_OBJECT", NULL },
diff --git a/drivers/gpu/drm/nouveau/nv50_software.c b/drivers/gpu/drm/nouveau/nv50_software.c
index 114d2517d4a..df554d9dacb 100644
--- a/drivers/gpu/drm/nouveau/nv50_software.c
+++ b/drivers/gpu/drm/nouveau/nv50_software.c
@@ -36,9 +36,6 @@ struct nv50_software_priv {
 
 struct nv50_software_chan {
 	struct nouveau_software_chan base;
-	struct {
-		struct nouveau_gpuobj *object;
-	} vblank;
 };
 
 static int
@@ -51,11 +48,7 @@ mthd_dma_vblsem(struct nouveau_channel *chan, u32 class, u32 mthd, u32 data)
 	if (!gpuobj)
 		return -ENOENT;
 
-	if (nouveau_notifier_offset(gpuobj, NULL))
-		return -EINVAL;
-
-	pch->vblank.object = gpuobj;
-	pch->base.vblank.offset = ~0;
+	pch->base.vblank.ctxdma = gpuobj->cinst >> 4;
 	return 0;
 }
 
@@ -63,11 +56,7 @@ static int
 mthd_vblsem_offset(struct nouveau_channel *chan, u32 class, u32 mthd, u32 data)
 {
 	struct nv50_software_chan *pch = chan->engctx[NVOBJ_ENGINE_SW];
-
-	if (nouveau_notifier_offset(pch->vblank.object, &data))
-		return -ERANGE;
-
-	pch->base.vblank.offset = data >> 2;
+	pch->base.vblank.offset = data;
 	return 0;
 }
 
@@ -86,7 +75,7 @@ mthd_vblsem_release(struct nouveau_channel *chan, u32 class, u32 mthd, u32 data)
 	struct nv50_software_chan *pch = chan->engctx[NVOBJ_ENGINE_SW];
 	struct drm_device *dev = chan->dev;
 
-	if (!pch->vblank.object || pch->base.vblank.offset == ~0 || data > 1)
+	if (data > 1)
 		return -EINVAL;
 
 	drm_vblank_get(dev, data);
@@ -116,7 +105,7 @@ nv50_software_context_new(struct nouveau_channel *chan, int engine)
 		return -ENOMEM;
 
 	nouveau_software_context_new(&pch->base);
-	pch->base.vblank.bo = chan->notifier_bo;
+	pch->base.vblank.channel = chan->ramin->vinst >> 12;
 	chan->engctx[engine] = pch;
 
 	/* dma objects for display sync channel semaphore blocks */
diff --git a/drivers/gpu/drm/nouveau/nv84_crypt.c b/drivers/gpu/drm/nouveau/nv84_crypt.c
index edece9c616e..bbfcc73b670 100644
--- a/drivers/gpu/drm/nouveau/nv84_crypt.c
+++ b/drivers/gpu/drm/nouveau/nv84_crypt.c
@@ -117,18 +117,30 @@ nv84_crypt_tlb_flush(struct drm_device *dev, int engine)
 	nv50_vm_flush_engine(dev, 0x0a);
 }
 
+static struct nouveau_bitfield nv84_crypt_intr[] = {
+	{ 0x00000001, "INVALID_STATE" },
+	{ 0x00000002, "ILLEGAL_MTHD" },
+	{ 0x00000004, "ILLEGAL_CLASS" },
+	{ 0x00000080, "QUERY" },
+	{ 0x00000100, "FAULT" },
+	{}
+};
+
 static void
 nv84_crypt_isr(struct drm_device *dev)
 {
 	u32 stat = nv_rd32(dev, 0x102130);
 	u32 mthd = nv_rd32(dev, 0x102190);
 	u32 data = nv_rd32(dev, 0x102194);
-	u32 inst = nv_rd32(dev, 0x102188) & 0x7fffffff;
+	u64 inst = (u64)(nv_rd32(dev, 0x102188) & 0x7fffffff) << 12;
 	int show = nouveau_ratelimit();
+	int chid = nv50_graph_isr_chid(dev, inst);
 
 	if (show) {
-		NV_INFO(dev, "PCRYPT_INTR: 0x%08x 0x%08x 0x%08x 0x%08x\n",
-			     stat, mthd, data, inst);
+		NV_INFO(dev, "PCRYPT:");
+		nouveau_bitfield_print(nv84_crypt_intr, stat);
+		printk(KERN_CONT " ch %d (0x%010llx) mthd 0x%04x data 0x%08x\n",
+			chid, inst, mthd, data);
 	}
 
 	nv_wr32(dev, 0x102130, stat);
diff --git a/drivers/gpu/drm/nouveau/nv84_fifo.c b/drivers/gpu/drm/nouveau/nv84_fifo.c
index cc82d799fc3..c564c5e4c30 100644
--- a/drivers/gpu/drm/nouveau/nv84_fifo.c
+++ b/drivers/gpu/drm/nouveau/nv84_fifo.c
@@ -117,17 +117,22 @@ nv84_fifo_context_del(struct nouveau_channel *chan, int engine)
 	struct drm_device *dev = chan->dev;
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	unsigned long flags;
+	u32 save;
 
 	/* remove channel from playlist, will context switch if active */
 	spin_lock_irqsave(&dev_priv->context_switch_lock, flags);
 	nv_mask(dev, 0x002600 + (chan->id * 4), 0x80000000, 0x00000000);
 	nv50_fifo_playlist_update(dev);
 
+	save = nv_mask(dev, 0x002520, 0x0000003f, 0x15);
+
 	/* tell any engines on this channel to unload their contexts */
 	nv_wr32(dev, 0x0032fc, chan->ramin->vinst >> 12);
 	if (!nv_wait_ne(dev, 0x0032fc, 0xffffffff, 0xffffffff))
 		NV_INFO(dev, "PFIFO: channel %d unload timeout\n", chan->id);
 
+	nv_wr32(dev, 0x002520, save);
+
 	nv_wr32(dev, 0x002600 + (chan->id * 4), 0x00000000);
 	spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags);
 
@@ -184,10 +189,13 @@ nv84_fifo_fini(struct drm_device *dev, int engine, bool suspend)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nv84_fifo_priv *priv = nv_engine(dev, engine);
 	int i;
+	u32 save;
 
 	/* set playlist length to zero, fifo will unload context */
 	nv_wr32(dev, 0x0032ec, 0);
 
+	save = nv_mask(dev, 0x002520, 0x0000003f, 0x15);
+
 	/* tell all connected engines to unload their contexts */
 	for (i = 0; i < priv->base.channels; i++) {
 		struct nouveau_channel *chan = dev_priv->channels.ptr[i];
@@ -199,6 +207,7 @@ nv84_fifo_fini(struct drm_device *dev, int engine, bool suspend)
 		}
 	}
 
+	nv_wr32(dev, 0x002520, save);
 	nv_wr32(dev, 0x002140, 0);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nva3_copy.fuc b/drivers/gpu/drm/nouveau/nva3_copy.fuc
index abc36626fef..219850d5328 100644
--- a/drivers/gpu/drm/nouveau/nva3_copy.fuc
+++ b/drivers/gpu/drm/nouveau/nva3_copy.fuc
@@ -119,9 +119,9 @@ dispatch_dma:
 // mthd 0x030c-0x0340, various stuff
 .b16 0xc3 14
 .b32 #ctx_src_address_high           ~0x000000ff
-.b32 #ctx_src_address_low            ~0xfffffff0
+.b32 #ctx_src_address_low            ~0xffffffff
 .b32 #ctx_dst_address_high           ~0x000000ff
-.b32 #ctx_dst_address_low            ~0xfffffff0
+.b32 #ctx_dst_address_low            ~0xffffffff
 .b32 #ctx_src_pitch                  ~0x0007ffff
 .b32 #ctx_dst_pitch                  ~0x0007ffff
 .b32 #ctx_xcnt                       ~0x0000ffff
diff --git a/drivers/gpu/drm/nouveau/nva3_copy.fuc.h b/drivers/gpu/drm/nouveau/nva3_copy.fuc.h
index 1f33fbdc00b..37d6de3c9d6 100644
--- a/drivers/gpu/drm/nouveau/nva3_copy.fuc.h
+++ b/drivers/gpu/drm/nouveau/nva3_copy.fuc.h
@@ -1,37 +1,72 @@
-uint32_t nva3_pcopy_data[] = {
+u32 nva3_pcopy_data[] = {
+/* 0x0000: ctx_object */
 	0x00000000,
+/* 0x0004: ctx_dma */
+/* 0x0004: ctx_dma_query */
 	0x00000000,
+/* 0x0008: ctx_dma_src */
 	0x00000000,
+/* 0x000c: ctx_dma_dst */
 	0x00000000,
+/* 0x0010: ctx_query_address_high */
 	0x00000000,
+/* 0x0014: ctx_query_address_low */
 	0x00000000,
+/* 0x0018: ctx_query_counter */
 	0x00000000,
+/* 0x001c: ctx_src_address_high */
 	0x00000000,
+/* 0x0020: ctx_src_address_low */
 	0x00000000,
+/* 0x0024: ctx_src_pitch */
 	0x00000000,
+/* 0x0028: ctx_src_tile_mode */
 	0x00000000,
+/* 0x002c: ctx_src_xsize */
 	0x00000000,
+/* 0x0030: ctx_src_ysize */
 	0x00000000,
+/* 0x0034: ctx_src_zsize */
 	0x00000000,
+/* 0x0038: ctx_src_zoff */
 	0x00000000,
+/* 0x003c: ctx_src_xoff */
 	0x00000000,
+/* 0x0040: ctx_src_yoff */
 	0x00000000,
+/* 0x0044: ctx_src_cpp */
 	0x00000000,
+/* 0x0048: ctx_dst_address_high */
 	0x00000000,
+/* 0x004c: ctx_dst_address_low */
 	0x00000000,
+/* 0x0050: ctx_dst_pitch */
 	0x00000000,
+/* 0x0054: ctx_dst_tile_mode */
 	0x00000000,
+/* 0x0058: ctx_dst_xsize */
 	0x00000000,
+/* 0x005c: ctx_dst_ysize */
 	0x00000000,
+/* 0x0060: ctx_dst_zsize */
 	0x00000000,
+/* 0x0064: ctx_dst_zoff */
 	0x00000000,
+/* 0x0068: ctx_dst_xoff */
 	0x00000000,
+/* 0x006c: ctx_dst_yoff */
 	0x00000000,
+/* 0x0070: ctx_dst_cpp */
 	0x00000000,
+/* 0x0074: ctx_format */
 	0x00000000,
+/* 0x0078: ctx_swz_const0 */
 	0x00000000,
+/* 0x007c: ctx_swz_const1 */
 	0x00000000,
+/* 0x0080: ctx_xcnt */
 	0x00000000,
+/* 0x0084: ctx_ycnt */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -63,6 +98,7 @@ uint32_t nva3_pcopy_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+/* 0x0100: dispatch_table */
 	0x00010000,
 	0x00000000,
 	0x00000000,
@@ -73,6 +109,7 @@ uint32_t nva3_pcopy_data[] = {
 	0x00010162,
 	0x00000000,
 	0x00030060,
+/* 0x0128: dispatch_dma */
 	0x00010170,
 	0x00000000,
 	0x00010170,
@@ -118,11 +155,11 @@ uint32_t nva3_pcopy_data[] = {
 	0x0000001c,
 	0xffffff00,
 	0x00000020,
-	0x0000000f,
+	0x00000000,
 	0x00000048,
 	0xffffff00,
 	0x0000004c,
-	0x0000000f,
+	0x00000000,
 	0x00000024,
 	0xfff80000,
 	0x00000050,
@@ -146,7 +183,8 @@ uint32_t nva3_pcopy_data[] = {
 	0x00000800,
 };
 
-uint32_t nva3_pcopy_code[] = {
+u32 nva3_pcopy_code[] = {
+/* 0x0000: main */
 	0x04fe04bd,
 	0x3517f000,
 	0xf10010fe,
@@ -158,23 +196,31 @@ uint32_t nva3_pcopy_code[] = {
 	0x17f11031,
 	0x27f01200,
 	0x0012d003,
+/* 0x002f: spin */
 	0xf40031f4,
 	0x0ef40028,
+/* 0x0035: ih */
 	0x8001cffd,
 	0xf40812c4,
 	0x21f4060b,
+/* 0x0041: ih_no_chsw */
 	0x0412c472,
 	0xf4060bf4,
+/* 0x004a: ih_no_cmd */
 	0x11c4c321,
 	0x4001d00c,
+/* 0x0052: swctx */
 	0x47f101f8,
 	0x4bfe7700,
 	0x0007fe00,
 	0xf00204b9,
 	0x01f40643,
 	0x0604fa09,
+/* 0x006b: swctx_load */
 	0xfa060ef4,
+/* 0x006e: swctx_done */
 	0x03f80504,
+/* 0x0072: chsw */
 	0x27f100f8,
 	0x23cf1400,
 	0x1e3fc800,
@@ -183,18 +229,22 @@ uint32_t nva3_pcopy_code[] = {
 	0x1e3af052,
 	0xf00023d0,
 	0x24d00147,
+/* 0x0093: chsw_no_unload */
 	0xcf00f880,
 	0x3dc84023,
 	0x220bf41e,
 	0xf40131f4,
 	0x57f05221,
 	0x0367f004,
+/* 0x00a8: chsw_load_ctx_dma */
 	0xa07856bc,
 	0xb6018068,
 	0x87d00884,
 	0x0162b600,
+/* 0x00bb: chsw_finish_load */
 	0xf0f018f4,
 	0x23d00237,
+/* 0x00c3: dispatch */
 	0xf100f880,
 	0xcf190037,
 	0x33cf4032,
@@ -202,6 +252,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x1024b607,
 	0x010057f1,
 	0x74bd64bd,
+/* 0x00dc: dispatch_loop */
 	0x58005658,
 	0x50b60157,
 	0x0446b804,
@@ -211,6 +262,7 @@ uint32_t nva3_pcopy_code[] = {
 	0xb60276bb,
 	0x57bb0374,
 	0xdf0ef400,
+/* 0x0100: dispatch_valid_mthd */
 	0xb60246bb,
 	0x45bb0344,
 	0x01459800,
@@ -220,31 +272,41 @@ uint32_t nva3_pcopy_code[] = {
 	0xb0014658,
 	0x1bf40064,
 	0x00538009,
+/* 0x0127: dispatch_cmd */
 	0xf4300ef4,
 	0x55f90132,
 	0xf40c01f4,
+/* 0x0132: dispatch_invalid_bitfield */
 	0x25f0250e,
+/* 0x0135: dispatch_illegal_mthd */
 	0x0125f002,
+/* 0x0138: dispatch_error */
 	0x100047f1,
 	0xd00042d0,
 	0x27f04043,
 	0x0002d040,
+/* 0x0148: hostirq_wait */
 	0xf08002cf,
 	0x24b04024,
 	0xf71bf400,
+/* 0x0154: dispatch_done */
 	0x1d0027f1,
 	0xd00137f0,
 	0x00f80023,
+/* 0x0160: cmd_nop */
+/* 0x0162: cmd_pm_trigger */
 	0x27f100f8,
 	0x34bd2200,
 	0xd00233f0,
 	0x00f80023,
+/* 0x0170: cmd_dma */
 	0x012842b7,
 	0xf00145b6,
 	0x43801e39,
 	0x0040b701,
 	0x0644b606,
 	0xf80043d0,
+/* 0x0189: cmd_exec_set_format */
 	0xf030f400,
 	0xb00001b0,
 	0x01b00101,
@@ -256,20 +318,26 @@ uint32_t nva3_pcopy_code[] = {
 	0x70b63847,
 	0x0232f401,
 	0x94bd84bd,
+/* 0x01b4: ncomp_loop */
 	0xb60f4ac4,
 	0xb4bd0445,
+/* 0x01bc: bpc_loop */
 	0xf404a430,
 	0xa5ff0f18,
 	0x00cbbbc0,
 	0xf40231f4,
+/* 0x01ce: cmp_c0 */
 	0x1bf4220e,
 	0x10c7f00c,
 	0xf400cbbb,
+/* 0x01da: cmp_c1 */
 	0xa430160e,
 	0x0c18f406,
 	0xbb14c7f0,
 	0x0ef400cb,
+/* 0x01e9: cmp_zero */
 	0x80c7f107,
+/* 0x01ed: bpc_next */
 	0x01c83800,
 	0xb60180b6,
 	0xb5b801b0,
@@ -280,6 +348,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x98110680,
 	0x68fd2008,
 	0x0502f400,
+/* 0x0216: dst_xcnt */
 	0x75fd64bd,
 	0x1c078000,
 	0xf10078fd,
@@ -304,6 +373,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x980056d0,
 	0x56d01f06,
 	0x1030f440,
+/* 0x0276: cmd_exec_set_surface_tiled */
 	0x579800f8,
 	0x6879c70a,
 	0xb66478c7,
@@ -311,9 +381,11 @@ uint32_t nva3_pcopy_code[] = {
 	0x0e76b060,
 	0xf0091bf4,
 	0x0ef40477,
+/* 0x0291: xtile64 */
 	0x027cf00f,
 	0xfd1170b6,
 	0x77f00947,
+/* 0x029d: xtileok */
 	0x0f5a9806,
 	0xfd115b98,
 	0xb7f000ab,
@@ -371,6 +443,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x67d00600,
 	0x0060b700,
 	0x0068d004,
+/* 0x0382: cmd_exec_set_surface_linear */
 	0x6cf000f8,
 	0x0260b702,
 	0x0864b602,
@@ -381,13 +454,16 @@ uint32_t nva3_pcopy_code[] = {
 	0xb70067d0,
 	0x98040060,
 	0x67d00957,
+/* 0x03ab: cmd_exec_wait */
 	0xf900f800,
 	0xf110f900,
 	0xb6080007,
+/* 0x03b6: loop */
 	0x01cf0604,
 	0x0114f000,
 	0xfcfa1bf4,
 	0xf800fc10,
+/* 0x03c5: cmd_exec_query */
 	0x0d34c800,
 	0xf5701bf4,
 	0xf103ab21,
@@ -417,6 +493,7 @@ uint32_t nva3_pcopy_code[] = {
 	0x47f10153,
 	0x44b60800,
 	0x0045d006,
+/* 0x0438: query_counter */
 	0x03ab21f5,
 	0x080c47f1,
 	0x980644b6,
@@ -439,11 +516,13 @@ uint32_t nva3_pcopy_code[] = {
 	0x47f10153,
 	0x44b60800,
 	0x0045d006,
+/* 0x0492: cmd_exec */
 	0x21f500f8,
 	0x3fc803ab,
 	0x0e0bf400,
 	0x018921f5,
 	0x020047f1,
+/* 0x04a7: cmd_exec_no_format */
 	0xf11e0ef4,
 	0xb6081067,
 	0x77f00664,
@@ -451,19 +530,24 @@ uint32_t nva3_pcopy_code[] = {
 	0x981c0780,
 	0x67d02007,
 	0x4067d000,
+/* 0x04c2: cmd_exec_init_src_surface */
 	0x32f444bd,
 	0xc854bd02,
 	0x0bf4043f,
 	0x8221f50a,
 	0x0a0ef403,
+/* 0x04d4: src_tiled */
 	0x027621f5,
+/* 0x04db: cmd_exec_init_dst_surface */
 	0xf40749f0,
 	0x57f00231,
 	0x083fc82c,
 	0xf50a0bf4,
 	0xf4038221,
+/* 0x04ee: dst_tiled */
 	0x21f50a0e,
 	0x49f00276,
+/* 0x04f5: cmd_exec_kick */
 	0x0057f108,
 	0x0654b608,
 	0xd0210698,
@@ -473,6 +557,8 @@ uint32_t nva3_pcopy_code[] = {
 	0xc80054d0,
 	0x0bf40c3f,
 	0xc521f507,
+/* 0x0519: cmd_exec_done */
+/* 0x051b: cmd_wrcache_flush */
 	0xf100f803,
 	0xbd220027,
 	0x0133f034,
diff --git a/drivers/gpu/drm/nouveau/nvc0_copy.fuc.h b/drivers/gpu/drm/nouveau/nvc0_copy.fuc.h
index a8d17458ced..cd879f31bb3 100644
--- a/drivers/gpu/drm/nouveau/nvc0_copy.fuc.h
+++ b/drivers/gpu/drm/nouveau/nvc0_copy.fuc.h
@@ -1,34 +1,65 @@
-uint32_t nvc0_pcopy_data[] = {
+u32 nvc0_pcopy_data[] = {
+/* 0x0000: ctx_object */
 	0x00000000,
+/* 0x0004: ctx_query_address_high */
 	0x00000000,
+/* 0x0008: ctx_query_address_low */
 	0x00000000,
+/* 0x000c: ctx_query_counter */
 	0x00000000,
+/* 0x0010: ctx_src_address_high */
 	0x00000000,
+/* 0x0014: ctx_src_address_low */
 	0x00000000,
+/* 0x0018: ctx_src_pitch */
 	0x00000000,
+/* 0x001c: ctx_src_tile_mode */
 	0x00000000,
+/* 0x0020: ctx_src_xsize */
 	0x00000000,
+/* 0x0024: ctx_src_ysize */
 	0x00000000,
+/* 0x0028: ctx_src_zsize */
 	0x00000000,
+/* 0x002c: ctx_src_zoff */
 	0x00000000,
+/* 0x0030: ctx_src_xoff */
 	0x00000000,
+/* 0x0034: ctx_src_yoff */
 	0x00000000,
+/* 0x0038: ctx_src_cpp */
 	0x00000000,
+/* 0x003c: ctx_dst_address_high */
 	0x00000000,
+/* 0x0040: ctx_dst_address_low */
 	0x00000000,
+/* 0x0044: ctx_dst_pitch */
 	0x00000000,
+/* 0x0048: ctx_dst_tile_mode */
 	0x00000000,
+/* 0x004c: ctx_dst_xsize */
 	0x00000000,
+/* 0x0050: ctx_dst_ysize */
 	0x00000000,
+/* 0x0054: ctx_dst_zsize */
 	0x00000000,
+/* 0x0058: ctx_dst_zoff */
 	0x00000000,
+/* 0x005c: ctx_dst_xoff */
 	0x00000000,
+/* 0x0060: ctx_dst_yoff */
 	0x00000000,
+/* 0x0064: ctx_dst_cpp */
 	0x00000000,
+/* 0x0068: ctx_format */
 	0x00000000,
+/* 0x006c: ctx_swz_const0 */
 	0x00000000,
+/* 0x0070: ctx_swz_const1 */
 	0x00000000,
+/* 0x0074: ctx_xcnt */
 	0x00000000,
+/* 0x0078: ctx_ycnt */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -63,6 +94,7 @@ uint32_t nvc0_pcopy_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+/* 0x0100: dispatch_table */
 	0x00010000,
 	0x00000000,
 	0x00000000,
@@ -111,11 +143,11 @@ uint32_t nvc0_pcopy_data[] = {
 	0x00000010,
 	0xffffff00,
 	0x00000014,
-	0x0000000f,
+	0x00000000,
 	0x0000003c,
 	0xffffff00,
 	0x00000040,
-	0x0000000f,
+	0x00000000,
 	0x00000018,
 	0xfff80000,
 	0x00000044,
@@ -139,7 +171,8 @@ uint32_t nvc0_pcopy_data[] = {
 	0x00000800,
 };
 
-uint32_t nvc0_pcopy_code[] = {
+u32 nvc0_pcopy_code[] = {
+/* 0x0000: main */
 	0x04fe04bd,
 	0x3517f000,
 	0xf10010fe,
@@ -151,15 +184,20 @@ uint32_t nvc0_pcopy_code[] = {
 	0x17f11031,
 	0x27f01200,
 	0x0012d003,
+/* 0x002f: spin */
 	0xf40031f4,
 	0x0ef40028,
+/* 0x0035: ih */
 	0x8001cffd,
 	0xf40812c4,
 	0x21f4060b,
+/* 0x0041: ih_no_chsw */
 	0x0412c4ca,
 	0xf5070bf4,
+/* 0x004b: ih_no_cmd */
 	0xc4010221,
 	0x01d00c11,
+/* 0x0053: swctx */
 	0xf101f840,
 	0xfe770047,
 	0x47f1004b,
@@ -188,8 +226,11 @@ uint32_t nvc0_pcopy_code[] = {
 	0xf00204b9,
 	0x01f40643,
 	0x0604fa09,
+/* 0x00c3: swctx_load */
 	0xfa060ef4,
+/* 0x00c6: swctx_done */
 	0x03f80504,
+/* 0x00ca: chsw */
 	0x27f100f8,
 	0x23cf1400,
 	0x1e3fc800,
@@ -198,18 +239,22 @@ uint32_t nvc0_pcopy_code[] = {
 	0x1e3af053,
 	0xf00023d0,
 	0x24d00147,
+/* 0x00eb: chsw_no_unload */
 	0xcf00f880,
 	0x3dc84023,
 	0x090bf41e,
 	0xf40131f4,
+/* 0x00fa: chsw_finish_load */
 	0x37f05321,
 	0x8023d002,
+/* 0x0102: dispatch */
 	0x37f100f8,
 	0x32cf1900,
 	0x0033cf40,
 	0x07ff24e4,
 	0xf11024b6,
 	0xbd010057,
+/* 0x011b: dispatch_loop */
 	0x5874bd64,
 	0x57580056,
 	0x0450b601,
@@ -219,6 +264,7 @@ uint32_t nvc0_pcopy_code[] = {
 	0xbb0f08f4,
 	0x74b60276,
 	0x0057bb03,
+/* 0x013f: dispatch_valid_mthd */
 	0xbbdf0ef4,
 	0x44b60246,
 	0x0045bb03,
@@ -229,24 +275,33 @@ uint32_t nvc0_pcopy_code[] = {
 	0x64b00146,
 	0x091bf400,
 	0xf4005380,
+/* 0x0166: dispatch_cmd */
 	0x32f4300e,
 	0xf455f901,
 	0x0ef40c01,
+/* 0x0171: dispatch_invalid_bitfield */
 	0x0225f025,
+/* 0x0174: dispatch_illegal_mthd */
+/* 0x0177: dispatch_error */
 	0xf10125f0,
 	0xd0100047,
 	0x43d00042,
 	0x4027f040,
+/* 0x0187: hostirq_wait */
 	0xcf0002d0,
 	0x24f08002,
 	0x0024b040,
+/* 0x0193: dispatch_done */
 	0xf1f71bf4,
 	0xf01d0027,
 	0x23d00137,
+/* 0x019f: cmd_nop */
 	0xf800f800,
+/* 0x01a1: cmd_pm_trigger */
 	0x0027f100,
 	0xf034bd22,
 	0x23d00233,
+/* 0x01af: cmd_exec_set_format */
 	0xf400f800,
 	0x01b0f030,
 	0x0101b000,
@@ -258,20 +313,26 @@ uint32_t nvc0_pcopy_code[] = {
 	0x3847c701,
 	0xf40170b6,
 	0x84bd0232,
+/* 0x01da: ncomp_loop */
 	0x4ac494bd,
 	0x0445b60f,
+/* 0x01e2: bpc_loop */
 	0xa430b4bd,
 	0x0f18f404,
 	0xbbc0a5ff,
 	0x31f400cb,
 	0x220ef402,
+/* 0x01f4: cmp_c0 */
 	0xf00c1bf4,
 	0xcbbb10c7,
 	0x160ef400,
+/* 0x0200: cmp_c1 */
 	0xf406a430,
 	0xc7f00c18,
 	0x00cbbb14,
+/* 0x020f: cmp_zero */
 	0xf1070ef4,
+/* 0x0213: bpc_next */
 	0x380080c7,
 	0x80b601c8,
 	0x01b0b601,
@@ -283,6 +344,7 @@ uint32_t nvc0_pcopy_code[] = {
 	0x1d08980e,
 	0xf40068fd,
 	0x64bd0502,
+/* 0x023c: dst_xcnt */
 	0x800075fd,
 	0x78fd1907,
 	0x1057f100,
@@ -307,15 +369,18 @@ uint32_t nvc0_pcopy_code[] = {
 	0x1c069800,
 	0xf44056d0,
 	0x00f81030,
+/* 0x029c: cmd_exec_set_surface_tiled */
 	0xc7075798,
 	0x78c76879,
 	0x0380b664,
 	0xb06077c7,
 	0x1bf40e76,
 	0x0477f009,
+/* 0x02b7: xtile64 */
 	0xf00f0ef4,
 	0x70b6027c,
 	0x0947fd11,
+/* 0x02c3: xtileok */
 	0x980677f0,
 	0x5b980c5a,
 	0x00abfd0e,
@@ -374,6 +439,7 @@ uint32_t nvc0_pcopy_code[] = {
 	0xb70067d0,
 	0xd0040060,
 	0x00f80068,
+/* 0x03a8: cmd_exec_set_surface_linear */
 	0xb7026cf0,
 	0xb6020260,
 	0x57980864,
@@ -384,12 +450,15 @@ uint32_t nvc0_pcopy_code[] = {
 	0x0060b700,
 	0x06579804,
 	0xf80067d0,
+/* 0x03d1: cmd_exec_wait */
 	0xf900f900,
 	0x0007f110,
 	0x0604b608,
+/* 0x03dc: loop */
 	0xf00001cf,
 	0x1bf40114,
 	0xfc10fcfa,
+/* 0x03eb: cmd_exec_query */
 	0xc800f800,
 	0x1bf40d34,
 	0xd121f570,
@@ -419,6 +488,7 @@ uint32_t nvc0_pcopy_code[] = {
 	0x0153f026,
 	0x080047f1,
 	0xd00644b6,
+/* 0x045e: query_counter */
 	0x21f50045,
 	0x47f103d1,
 	0x44b6080c,
@@ -442,11 +512,13 @@ uint32_t nvc0_pcopy_code[] = {
 	0x080047f1,
 	0xd00644b6,
 	0x00f80045,
+/* 0x04b8: cmd_exec */
 	0x03d121f5,
 	0xf4003fc8,
 	0x21f50e0b,
 	0x47f101af,
 	0x0ef40200,
+/* 0x04cd: cmd_exec_no_format */
 	0x1067f11e,
 	0x0664b608,
 	0x800177f0,
@@ -454,18 +526,23 @@ uint32_t nvc0_pcopy_code[] = {
 	0x1d079819,
 	0xd00067d0,
 	0x44bd4067,
+/* 0x04e8: cmd_exec_init_src_surface */
 	0xbd0232f4,
 	0x043fc854,
 	0xf50a0bf4,
 	0xf403a821,
+/* 0x04fa: src_tiled */
 	0x21f50a0e,
 	0x49f0029c,
+/* 0x0501: cmd_exec_init_dst_surface */
 	0x0231f407,
 	0xc82c57f0,
 	0x0bf4083f,
 	0xa821f50a,
 	0x0a0ef403,
+/* 0x0514: dst_tiled */
 	0x029c21f5,
+/* 0x051b: cmd_exec_kick */
 	0xf10849f0,
 	0xb6080057,
 	0x06980654,
@@ -475,7 +552,9 @@ uint32_t nvc0_pcopy_code[] = {
 	0x54d00546,
 	0x0c3fc800,
 	0xf5070bf4,
+/* 0x053f: cmd_exec_done */
 	0xf803eb21,
+/* 0x0541: cmd_wrcache_flush */
 	0x0027f100,
 	0xf034bd22,
 	0x23d00133,
diff --git a/drivers/gpu/drm/nouveau/nvc0_pm.c b/drivers/gpu/drm/nouveau/nvc0_pm.c
index 7c95c44e288..4e712b10ebd 100644
--- a/drivers/gpu/drm/nouveau/nvc0_pm.c
+++ b/drivers/gpu/drm/nouveau/nvc0_pm.c
@@ -557,7 +557,7 @@ prog_mem(struct drm_device *dev, struct nvc0_pm_state *info)
 	nouveau_mem_exec(&exec, info->perflvl);
 
 	if (dev_priv->chipset < 0xd0)
-		nv_wr32(dev, 0x611200, 0x00003300);
+		nv_wr32(dev, 0x611200, 0x00003330);
 	else
 		nv_wr32(dev, 0x62c000, 0x03030300);
 }
diff --git a/drivers/gpu/drm/nouveau/nvd0_display.c b/drivers/gpu/drm/nouveau/nvd0_display.c
index d0d60e1e7f9..dac525b2994 100644
--- a/drivers/gpu/drm/nouveau/nvd0_display.c
+++ b/drivers/gpu/drm/nouveau/nvd0_display.c
@@ -790,7 +790,7 @@ nvd0_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	int ch = EVO_CURS(nv_crtc->index);
 
-	evo_piow(crtc->dev, ch, 0x0084, (y << 16) | x);
+	evo_piow(crtc->dev, ch, 0x0084, (y << 16) | (x & 0xffff));
 	evo_piow(crtc->dev, ch, 0x0080, 0x00000000);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nve0_fifo.c b/drivers/gpu/drm/nouveau/nve0_fifo.c
index 1855ecbd843..e98d144e6eb 100644
--- a/drivers/gpu/drm/nouveau/nve0_fifo.c
+++ b/drivers/gpu/drm/nouveau/nve0_fifo.c
@@ -294,6 +294,25 @@ nve0_fifo_isr_vm_fault(struct drm_device *dev, int unit)
 	printk(" on channel 0x%010llx\n", (u64)inst << 12);
 }
 
+static int
+nve0_fifo_page_flip(struct drm_device *dev, u32 chid)
+{
+	struct nve0_fifo_priv *priv = nv_engine(dev, NVOBJ_ENGINE_FIFO);
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct nouveau_channel *chan = NULL;
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&dev_priv->channels.lock, flags);
+	if (likely(chid >= 0 && chid < priv->base.channels)) {
+		chan = dev_priv->channels.ptr[chid];
+		if (likely(chan))
+			ret = nouveau_finish_page_flip(chan, NULL);
+	}
+	spin_unlock_irqrestore(&dev_priv->channels.lock, flags);
+	return ret;
+}
+
 static void
 nve0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit)
 {
@@ -303,11 +322,21 @@ nve0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit)
 	u32 chid = nv_rd32(dev, 0x040120 + (unit * 0x2000)) & 0x7f;
 	u32 subc = (addr & 0x00070000);
 	u32 mthd = (addr & 0x00003ffc);
+	u32 show = stat;
+
+	if (stat & 0x00200000) {
+		if (mthd == 0x0054) {
+			if (!nve0_fifo_page_flip(dev, chid))
+				show &= ~0x00200000;
+		}
+	}
 
-	NV_INFO(dev, "PSUBFIFO %d:", unit);
-	nouveau_bitfield_print(nve0_fifo_subfifo_intr, stat);
-	NV_INFO(dev, "PSUBFIFO %d: ch %d subc %d mthd 0x%04x data 0x%08x\n",
-		unit, chid, subc, mthd, data);
+	if (show) {
+		NV_INFO(dev, "PFIFO%d:", unit);
+		nouveau_bitfield_print(nve0_fifo_subfifo_intr, show);
+		NV_INFO(dev, "PFIFO%d: ch %d subc %d mthd 0x%04x data 0x%08x\n",
+			unit, chid, subc, mthd, data);
+	}
 
 	nv_wr32(dev, 0x0400c0 + (unit * 0x2000), 0x80600008);
 	nv_wr32(dev, 0x040108 + (unit * 0x2000), stat);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9e6f76fec52..c6fcb5b86a4 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -259,7 +259,7 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 		/* adjust pm to dpms changes BEFORE enabling crtcs */
 		radeon_pm_compute_clocks(rdev);
 		/* disable crtc pair power gating before programming */
-		if (ASIC_IS_DCE6(rdev))
+		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set)
 			atombios_powergate_crtc(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_ENABLE);
 		if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev))
@@ -279,7 +279,7 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 		atombios_enable_crtc(crtc, ATOM_DISABLE);
 		radeon_crtc->enabled = false;
 		/* power gating is per-pair */
-		if (ASIC_IS_DCE6(rdev)) {
+		if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) {
 			struct drm_crtc *other_crtc;
 			struct radeon_crtc *other_radeon_crtc;
 			list_for_each_entry(other_crtc, &rdev->ddev->mode_config.crtc_list, head) {
@@ -1531,12 +1531,12 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				 * crtc virtual pixel clock.
 				 */
 				if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) {
-					if (ASIC_IS_DCE5(rdev))
-						return ATOM_DCPLL;
+					if (rdev->clock.dp_extclk)
+						return ATOM_PPLL_INVALID;
 					else if (ASIC_IS_DCE6(rdev))
 						return ATOM_PPLL0;
-					else if (rdev->clock.dp_extclk)
-						return ATOM_PPLL_INVALID;
+					else if (ASIC_IS_DCE5(rdev))
+						return ATOM_DCPLL;
 				}
 			}
 		}
@@ -1635,18 +1635,28 @@ static bool atombios_crtc_mode_fixup(struct drm_crtc *crtc,
 static void atombios_crtc_prepare(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	struct radeon_device *rdev = dev->dev_private;
 
+	radeon_crtc->in_mode_set = true;
 	/* pick pll */
 	radeon_crtc->pll_id = radeon_atom_pick_pll(crtc);
 
+	/* disable crtc pair power gating before programming */
+	if (ASIC_IS_DCE6(rdev))
+		atombios_powergate_crtc(crtc, ATOM_DISABLE);
+
 	atombios_lock_crtc(crtc, ATOM_ENABLE);
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
 static void atombios_crtc_commit(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+
 	atombios_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 	atombios_lock_crtc(crtc, ATOM_DISABLE);
+	radeon_crtc->in_mode_set = false;
 }
 
 static void atombios_crtc_disable(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 0355536f61e..7712cf5ab33 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -22,6 +22,7 @@
  *
  * Authors: Dave Airlie
  *          Alex Deucher
+ *          Jerome Glisse
  */
 #include "drmP.h"
 #include "radeon_drm.h"
@@ -654,7 +655,6 @@ static bool radeon_dp_get_link_status(struct radeon_connector *radeon_connector,
 	ret = radeon_dp_aux_native_read(radeon_connector, DP_LANE0_1_STATUS,
 					link_status, DP_LINK_STATUS_SIZE, 100);
 	if (ret <= 0) {
-		DRM_ERROR("displayport link status failed\n");
 		return false;
 	}
 
@@ -833,8 +833,10 @@ static int radeon_dp_link_train_cr(struct radeon_dp_link_train_info *dp_info)
 		else
 			mdelay(dp_info->rd_interval * 4);
 
-		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status))
+		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) {
+			DRM_ERROR("displayport link status failed\n");
 			break;
+		}
 
 		if (dp_clock_recovery_ok(dp_info->link_status, dp_info->dp_lane_count)) {
 			clock_recovery = true;
@@ -896,8 +898,10 @@ static int radeon_dp_link_train_ce(struct radeon_dp_link_train_info *dp_info)
 		else
 			mdelay(dp_info->rd_interval * 4);
 
-		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status))
+		if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) {
+			DRM_ERROR("displayport link status failed\n");
 			break;
+		}
 
 		if (dp_channel_eq_ok(dp_info->link_status, dp_info->dp_lane_count)) {
 			channel_eq = true;
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 7dfc62fae6a..f9bc27fe269 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1392,10 +1392,18 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 	case DRM_MODE_DPMS_ON:
 		/* some early dce3.2 boards have a bug in their transmitter control table */
 		if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730) ||
-		    ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev))
+		    ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+			if (ASIC_IS_DCE6(rdev)) {
+				/* It seems we need to call ATOM_ENCODER_CMD_SETUP again
+				 * before reenabling encoder on DPMS ON, otherwise we never
+				 * get picture
+				 */
+				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0);
+			}
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
-		else
+		} else {
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
+		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
 			if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 				atombios_set_edp_panel_power(connector,
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e585a3b947e..e93b80a6d4e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1229,24 +1229,8 @@ void evergreen_agp_enable(struct radeon_device *rdev)
 
 void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save)
 {
-	save->vga_control[0] = RREG32(D1VGA_CONTROL);
-	save->vga_control[1] = RREG32(D2VGA_CONTROL);
 	save->vga_render_control = RREG32(VGA_RENDER_CONTROL);
 	save->vga_hdp_control = RREG32(VGA_HDP_CONTROL);
-	save->crtc_control[0] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET);
-	save->crtc_control[1] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET);
-	if (rdev->num_crtc >= 4) {
-		save->vga_control[2] = RREG32(EVERGREEN_D3VGA_CONTROL);
-		save->vga_control[3] = RREG32(EVERGREEN_D4VGA_CONTROL);
-		save->crtc_control[2] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET);
-		save->crtc_control[3] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET);
-	}
-	if (rdev->num_crtc >= 6) {
-		save->vga_control[4] = RREG32(EVERGREEN_D5VGA_CONTROL);
-		save->vga_control[5] = RREG32(EVERGREEN_D6VGA_CONTROL);
-		save->crtc_control[4] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET);
-		save->crtc_control[5] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET);
-	}
 
 	/* Stop all video */
 	WREG32(VGA_RENDER_CONTROL, 0);
@@ -1357,47 +1341,6 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s
 	/* Unlock host access */
 	WREG32(VGA_HDP_CONTROL, save->vga_hdp_control);
 	mdelay(1);
-	/* Restore video state */
-	WREG32(D1VGA_CONTROL, save->vga_control[0]);
-	WREG32(D2VGA_CONTROL, save->vga_control[1]);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_D3VGA_CONTROL, save->vga_control[2]);
-		WREG32(EVERGREEN_D4VGA_CONTROL, save->vga_control[3]);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_D5VGA_CONTROL, save->vga_control[4]);
-		WREG32(EVERGREEN_D6VGA_CONTROL, save->vga_control[5]);
-	}
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1);
-	}
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, save->crtc_control[0]);
-	WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, save->crtc_control[1]);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, save->crtc_control[2]);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, save->crtc_control[3]);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, save->crtc_control[4]);
-		WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, save->crtc_control[5]);
-	}
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
-	WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
-	if (rdev->num_crtc >= 4) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
-	}
-	if (rdev->num_crtc >= 6) {
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
-		WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
-	}
 	WREG32(VGA_RENDER_CONTROL, save->vga_render_control);
 }
 
@@ -1986,10 +1929,18 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	if (rdev->flags & RADEON_IS_IGP)
 		rdev->config.evergreen.tile_config |= 1 << 4;
 	else {
-		if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-			rdev->config.evergreen.tile_config |= 1 << 4;
-		else
+		switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+		case 0: /* four banks */
 			rdev->config.evergreen.tile_config |= 0 << 4;
+			break;
+		case 1: /* eight banks */
+			rdev->config.evergreen.tile_config |= 1 << 4;
+			break;
+		case 2: /* sixteen banks */
+		default:
+			rdev->config.evergreen.tile_config |= 2 << 4;
+			break;
+		}
 	}
 	rdev->config.evergreen.tile_config |= 0 << 8;
 	rdev->config.evergreen.tile_config |=
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index c16554122cc..e44a62a07fe 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -788,6 +788,13 @@ static int evergreen_cs_track_validate_texture(struct radeon_cs_parser *p,
 	case V_030000_SQ_TEX_DIM_1D_ARRAY:
 	case V_030000_SQ_TEX_DIM_2D_ARRAY:
 		depth = 1;
+		break;
+	case V_030000_SQ_TEX_DIM_2D_MSAA:
+	case V_030000_SQ_TEX_DIM_2D_ARRAY_MSAA:
+		surf.nsamples = 1 << llevel;
+		llevel = 0;
+		depth = 1;
+		break;
 	case V_030000_SQ_TEX_DIM_3D:
 		break;
 	default:
@@ -961,13 +968,15 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 
 	if (track->db_dirty) {
 		/* Check stencil buffer */
-		if (G_028800_STENCIL_ENABLE(track->db_depth_control)) {
+		if (G_028044_FORMAT(track->db_s_info) != V_028044_STENCIL_INVALID &&
+		    G_028800_STENCIL_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_stencil(p);
 			if (r)
 				return r;
 		}
 		/* Check depth buffer */
-		if (G_028800_Z_ENABLE(track->db_depth_control)) {
+		if (G_028040_FORMAT(track->db_z_info) != V_028040_Z_INVALID &&
+		    G_028800_Z_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_depth(p);
 			if (r)
 				return r;
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index d3bd098e4e1..79347855d9b 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -1277,6 +1277,8 @@
 #define   S_028044_FORMAT(x)                           (((x) & 0x1) << 0)
 #define   G_028044_FORMAT(x)                           (((x) >> 0) & 0x1)
 #define   C_028044_FORMAT                              0xFFFFFFFE
+#define	    V_028044_STENCIL_INVALID			0
+#define	    V_028044_STENCIL_8				1
 #define   G_028044_TILE_SPLIT(x)                       (((x) >> 8) & 0x7)
 #define DB_Z_READ_BASE					0x28048
 #define DB_STENCIL_READ_BASE				0x2804c
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 9945d86d900..853800e8582 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -574,10 +574,18 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 	if (rdev->flags & RADEON_IS_IGP)
 		rdev->config.cayman.tile_config |= 1 << 4;
 	else {
-		if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-			rdev->config.cayman.tile_config |= 1 << 4;
-		else
+		switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+		case 0: /* four banks */
 			rdev->config.cayman.tile_config |= 0 << 4;
+			break;
+		case 1: /* eight banks */
+			rdev->config.cayman.tile_config |= 1 << 4;
+			break;
+		case 2: /* sixteen banks */
+		default:
+			rdev->config.cayman.tile_config |= 2 << 4;
+			break;
+		}
 	}
 	rdev->config.cayman.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 637280f541a..d79c639ae73 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3789,3 +3789,23 @@ static void r600_pcie_gen2_enable(struct radeon_device *rdev)
 		WREG32_PCIE_P(PCIE_LC_LINK_WIDTH_CNTL, link_width_cntl);
 	}
 }
+
+/**
+ * r600_get_gpu_clock - return GPU clock counter snapshot
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Fetches a GPU clock counter snapshot (R6xx-cayman).
+ * Returns the 64 bit clock counter snapshot.
+ */
+uint64_t r600_get_gpu_clock(struct radeon_device *rdev)
+{
+	uint64_t clock;
+
+	mutex_lock(&rdev->gpu_clock_mutex);
+	WREG32(RLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+	clock = (uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_LSB) |
+	        ((uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	mutex_unlock(&rdev->gpu_clock_mutex);
+	return clock;
+}
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index ca87f7afaf2..3dab49cb1d4 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -764,8 +764,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 	}
 
 	/* Check depth buffer */
-	if (track->db_dirty && (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
-		G_028800_Z_ENABLE(track->db_depth_control))) {
+	if (track->db_dirty &&
+	    G_028010_FORMAT(track->db_depth_info) != V_028010_DEPTH_INVALID &&
+	    (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
+	     G_028800_Z_ENABLE(track->db_depth_control))) {
 		r = r600_cs_track_validate_db(p);
 		if (r)
 			return r;
@@ -1557,13 +1559,14 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 					      u32 tiling_flags)
 {
 	struct r600_cs_track *track = p->track;
-	u32 nfaces, llevel, blevel, w0, h0, d0;
-	u32 word0, word1, l0_size, mipmap_size, word2, word3;
+	u32 dim, nfaces, llevel, blevel, w0, h0, d0;
+	u32 word0, word1, l0_size, mipmap_size, word2, word3, word4, word5;
 	u32 height_align, pitch, pitch_align, depth_align;
-	u32 array, barray, larray;
+	u32 barray, larray;
 	u64 base_align;
 	struct array_mode_checker array_check;
 	u32 format;
+	bool is_array;
 
 	/* on legacy kernel we don't perform advanced check */
 	if (p->rdev == NULL)
@@ -1581,12 +1584,28 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
 	}
 	word1 = radeon_get_ib_value(p, idx + 1);
+	word2 = radeon_get_ib_value(p, idx + 2) << 8;
+	word3 = radeon_get_ib_value(p, idx + 3) << 8;
+	word4 = radeon_get_ib_value(p, idx + 4);
+	word5 = radeon_get_ib_value(p, idx + 5);
+	dim = G_038000_DIM(word0);
 	w0 = G_038000_TEX_WIDTH(word0) + 1;
+	pitch = (G_038000_PITCH(word0) + 1) * 8;
 	h0 = G_038004_TEX_HEIGHT(word1) + 1;
 	d0 = G_038004_TEX_DEPTH(word1);
+	format = G_038004_DATA_FORMAT(word1);
+	blevel = G_038010_BASE_LEVEL(word4);
+	llevel = G_038014_LAST_LEVEL(word5);
+	/* pitch in texels */
+	array_check.array_mode = G_038000_TILE_MODE(word0);
+	array_check.group_size = track->group_size;
+	array_check.nbanks = track->nbanks;
+	array_check.npipes = track->npipes;
+	array_check.nsamples = 1;
+	array_check.blocksize = r600_fmt_get_blocksize(format);
 	nfaces = 1;
-	array = 0;
-	switch (G_038000_DIM(word0)) {
+	is_array = false;
+	switch (dim) {
 	case V_038000_SQ_TEX_DIM_1D:
 	case V_038000_SQ_TEX_DIM_2D:
 	case V_038000_SQ_TEX_DIM_3D:
@@ -1599,29 +1618,25 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		break;
 	case V_038000_SQ_TEX_DIM_1D_ARRAY:
 	case V_038000_SQ_TEX_DIM_2D_ARRAY:
-		array = 1;
+		is_array = true;
 		break;
-	case V_038000_SQ_TEX_DIM_2D_MSAA:
 	case V_038000_SQ_TEX_DIM_2D_ARRAY_MSAA:
+		is_array = true;
+		/* fall through */
+	case V_038000_SQ_TEX_DIM_2D_MSAA:
+		array_check.nsamples = 1 << llevel;
+		llevel = 0;
+		break;
 	default:
 		dev_warn(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0));
 		return -EINVAL;
 	}
-	format = G_038004_DATA_FORMAT(word1);
 	if (!r600_fmt_is_valid_texture(format, p->family)) {
 		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
 			 __func__, __LINE__, format);
 		return -EINVAL;
 	}
 
-	/* pitch in texels */
-	pitch = (G_038000_PITCH(word0) + 1) * 8;
-	array_check.array_mode = G_038000_TILE_MODE(word0);
-	array_check.group_size = track->group_size;
-	array_check.nbanks = track->nbanks;
-	array_check.npipes = track->npipes;
-	array_check.nsamples = 1;
-	array_check.blocksize = r600_fmt_get_blocksize(format);
 	if (r600_get_array_mode_alignment(&array_check,
 					  &pitch_align, &height_align, &depth_align, &base_align)) {
 		dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n",
@@ -1647,20 +1662,13 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		return -EINVAL;
 	}
 
-	word2 = radeon_get_ib_value(p, idx + 2) << 8;
-	word3 = radeon_get_ib_value(p, idx + 3) << 8;
-
-	word0 = radeon_get_ib_value(p, idx + 4);
-	word1 = radeon_get_ib_value(p, idx + 5);
-	blevel = G_038010_BASE_LEVEL(word0);
-	llevel = G_038014_LAST_LEVEL(word1);
 	if (blevel > llevel) {
 		dev_warn(p->dev, "texture blevel %d > llevel %d\n",
 			 blevel, llevel);
 	}
-	if (array == 1) {
-		barray = G_038014_BASE_ARRAY(word1);
-		larray = G_038014_LAST_ARRAY(word1);
+	if (is_array) {
+		barray = G_038014_BASE_ARRAY(word5);
+		larray = G_038014_LAST_ARRAY(word5);
 
 		nfaces = larray - barray + 1;
 	}
@@ -1677,7 +1685,6 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		return -EINVAL;
 	}
 	/* using get ib will give us the offset into the mipmap bo */
-	word3 = radeon_get_ib_value(p, idx + 3) << 8;
 	if ((mipmap_size + word3) > radeon_bo_size(mipmap)) {
 		/*dev_warn(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n",
 		  w0, h0, format, blevel, nlevels, word3, mipmap_size, radeon_bo_size(texture));*/
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 4b116ae75fc..fd328f4c3ea 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -602,6 +602,9 @@
 #define RLC_HB_WPTR                                       0x3f1c
 #define RLC_HB_WPTR_LSB_ADDR                              0x3f14
 #define RLC_HB_WPTR_MSB_ADDR                              0x3f18
+#define RLC_GPU_CLOCK_COUNT_LSB				  0x3f38
+#define RLC_GPU_CLOCK_COUNT_MSB				  0x3f3c
+#define RLC_CAPTURE_GPU_CLOCK_COUNT			  0x3f40
 #define RLC_MC_CNTL                                       0x3f44
 #define RLC_UCODE_CNTL                                    0x3f48
 #define RLC_UCODE_ADDR                                    0x3f2c
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 5431af29240..99304194a65 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -300,6 +300,7 @@ struct radeon_bo_va {
 	uint64_t			soffset;
 	uint64_t			eoffset;
 	uint32_t			flags;
+	struct radeon_fence		*fence;
 	bool				valid;
 };
 
@@ -1533,6 +1534,7 @@ struct radeon_device {
 	unsigned 		debugfs_count;
 	/* virtual memory */
 	struct radeon_vm_manager	vm_manager;
+	struct mutex			gpu_clock_mutex;
 };
 
 int radeon_device_init(struct radeon_device *rdev,
@@ -1733,11 +1735,11 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_pm_finish(rdev) (rdev)->asic->pm.finish((rdev))
 #define radeon_pm_init_profile(rdev) (rdev)->asic->pm.init_profile((rdev))
 #define radeon_pm_get_dynpm_state(rdev) (rdev)->asic->pm.get_dynpm_state((rdev))
-#define radeon_pre_page_flip(rdev, crtc) rdev->asic->pflip.pre_page_flip((rdev), (crtc))
-#define radeon_page_flip(rdev, crtc, base) rdev->asic->pflip.page_flip((rdev), (crtc), (base))
-#define radeon_post_page_flip(rdev, crtc) rdev->asic->pflip.post_page_flip((rdev), (crtc))
-#define radeon_wait_for_vblank(rdev, crtc) rdev->asic->display.wait_for_vblank((rdev), (crtc))
-#define radeon_mc_wait_for_idle(rdev) rdev->asic->mc_wait_for_idle((rdev))
+#define radeon_pre_page_flip(rdev, crtc) (rdev)->asic->pflip.pre_page_flip((rdev), (crtc))
+#define radeon_page_flip(rdev, crtc, base) (rdev)->asic->pflip.page_flip((rdev), (crtc), (base))
+#define radeon_post_page_flip(rdev, crtc) (rdev)->asic->pflip.post_page_flip((rdev), (crtc))
+#define radeon_wait_for_vblank(rdev, crtc) (rdev)->asic->display.wait_for_vblank((rdev), (crtc))
+#define radeon_mc_wait_for_idle(rdev) (rdev)->asic->mc_wait_for_idle((rdev))
 
 /* Common functions */
 /* AGP */
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index f4af2431043..18c38d14c8c 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -255,13 +255,10 @@ extern int rs690_mc_wait_for_idle(struct radeon_device *rdev);
  * rv515
  */
 struct rv515_mc_save {
-	u32 d1vga_control;
-	u32 d2vga_control;
 	u32 vga_render_control;
 	u32 vga_hdp_control;
-	u32 d1crtc_control;
-	u32 d2crtc_control;
 };
+
 int rv515_init(struct radeon_device *rdev);
 void rv515_fini(struct radeon_device *rdev);
 uint32_t rv515_mc_rreg(struct radeon_device *rdev, uint32_t reg);
@@ -371,6 +368,7 @@ void r600_kms_blit_copy(struct radeon_device *rdev,
 			unsigned num_gpu_pages,
 			struct radeon_sa_bo *vb);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
+uint64_t r600_get_gpu_clock(struct radeon_device *rdev);
 
 /*
  * rv770,rv730,rv710,rv740
@@ -389,11 +387,10 @@ void r700_cp_fini(struct radeon_device *rdev);
  * evergreen
  */
 struct evergreen_mc_save {
-	u32 vga_control[6];
 	u32 vga_render_control;
 	u32 vga_hdp_control;
-	u32 crtc_control[6];
 };
+
 void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev);
 int evergreen_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
@@ -472,5 +469,6 @@ int si_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm, int id);
 void si_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm);
 void si_vm_tlb_flush(struct radeon_device *rdev, struct radeon_vm *vm);
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
+uint64_t si_get_gpu_clock(struct radeon_device *rdev);
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index b1e3820df36..f9c21f9d16b 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1263,6 +1263,8 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 union igp_info {
 	struct _ATOM_INTEGRATED_SYSTEM_INFO info;
 	struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6;
+	struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7;
 };
 
 bool radeon_atombios_sideport_present(struct radeon_device *rdev)
@@ -1390,27 +1392,50 @@ static void radeon_atombios_get_igp_ss_overrides(struct radeon_device *rdev,
 	struct radeon_mode_info *mode_info = &rdev->mode_info;
 	int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo);
 	u16 data_offset, size;
-	struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 *igp_info;
+	union igp_info *igp_info;
 	u8 frev, crev;
 	u16 percentage = 0, rate = 0;
 
 	/* get any igp specific overrides */
 	if (atom_parse_data_header(mode_info->atom_context, index, &size,
 				   &frev, &crev, &data_offset)) {
-		igp_info = (struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 *)
+		igp_info = (union igp_info *)
 			(mode_info->atom_context->bios + data_offset);
-		switch (id) {
-		case ASIC_INTERNAL_SS_ON_TMDS:
-			percentage = le16_to_cpu(igp_info->usDVISSPercentage);
-			rate = le16_to_cpu(igp_info->usDVISSpreadRateIn10Hz);
+		switch (crev) {
+		case 6:
+			switch (id) {
+			case ASIC_INTERNAL_SS_ON_TMDS:
+				percentage = le16_to_cpu(igp_info->info_6.usDVISSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usDVISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_HDMI:
+				percentage = le16_to_cpu(igp_info->info_6.usHDMISSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usHDMISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_LVDS:
+				percentage = le16_to_cpu(igp_info->info_6.usLvdsSSPercentage);
+				rate = le16_to_cpu(igp_info->info_6.usLvdsSSpreadRateIn10Hz);
+				break;
+			}
 			break;
-		case ASIC_INTERNAL_SS_ON_HDMI:
-			percentage = le16_to_cpu(igp_info->usHDMISSPercentage);
-			rate = le16_to_cpu(igp_info->usHDMISSpreadRateIn10Hz);
+		case 7:
+			switch (id) {
+			case ASIC_INTERNAL_SS_ON_TMDS:
+				percentage = le16_to_cpu(igp_info->info_7.usDVISSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usDVISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_HDMI:
+				percentage = le16_to_cpu(igp_info->info_7.usHDMISSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usHDMISSpreadRateIn10Hz);
+				break;
+			case ASIC_INTERNAL_SS_ON_LVDS:
+				percentage = le16_to_cpu(igp_info->info_7.usLvdsSSPercentage);
+				rate = le16_to_cpu(igp_info->info_7.usLvdsSSpreadRateIn10Hz);
+				break;
+			}
 			break;
-		case ASIC_INTERNAL_SS_ON_LVDS:
-			percentage = le16_to_cpu(igp_info->usLvdsSSPercentage);
-			rate = le16_to_cpu(igp_info->usLvdsSSpreadRateIn10Hz);
+		default:
+			DRM_ERROR("Unsupported IGP table: %d %d\n", frev, crev);
 			break;
 		}
 		if (percentage)
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 576f4f6919f..f75247d42ff 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -719,6 +719,34 @@ static struct radeon_i2c_bus_rec combios_setup_i2c_bus(struct radeon_device *rde
 	return i2c;
 }
 
+static struct radeon_i2c_bus_rec radeon_combios_get_i2c_info_from_table(struct radeon_device *rdev)
+{
+	struct drm_device *dev = rdev->ddev;
+	struct radeon_i2c_bus_rec i2c;
+	u16 offset;
+	u8 id, blocks, clk, data;
+	int i;
+
+	i2c.valid = false;
+
+	offset = combios_get_table_offset(dev, COMBIOS_I2C_INFO_TABLE);
+	if (offset) {
+		blocks = RBIOS8(offset + 2);
+		for (i = 0; i < blocks; i++) {
+			id = RBIOS8(offset + 3 + (i * 5) + 0);
+			if (id == 136) {
+				clk = RBIOS8(offset + 3 + (i * 5) + 3);
+				data = RBIOS8(offset + 3 + (i * 5) + 4);
+				/* gpiopad */
+				i2c = combios_setup_i2c_bus(rdev, DDC_MONID,
+							    (1 << clk), (1 << data));
+				break;
+			}
+		}
+	}
+	return i2c;
+}
+
 void radeon_combios_i2c_init(struct radeon_device *rdev)
 {
 	struct drm_device *dev = rdev->ddev;
@@ -755,30 +783,14 @@ void radeon_combios_i2c_init(struct radeon_device *rdev)
 	} else if (rdev->family == CHIP_RS300 ||
 		   rdev->family == CHIP_RS400 ||
 		   rdev->family == CHIP_RS480) {
-		u16 offset;
-		u8 id, blocks, clk, data;
-		int i;
-
 		/* 0x68 */
 		i2c = combios_setup_i2c_bus(rdev, DDC_CRT2, 0, 0);
 		rdev->i2c_bus[3] = radeon_i2c_create(dev, &i2c, "MONID");
 
-		offset = combios_get_table_offset(dev, COMBIOS_I2C_INFO_TABLE);
-		if (offset) {
-			blocks = RBIOS8(offset + 2);
-			for (i = 0; i < blocks; i++) {
-				id = RBIOS8(offset + 3 + (i * 5) + 0);
-				if (id == 136) {
-					clk = RBIOS8(offset + 3 + (i * 5) + 3);
-					data = RBIOS8(offset + 3 + (i * 5) + 4);
-					/* gpiopad */
-					i2c = combios_setup_i2c_bus(rdev, DDC_MONID,
-								    (1 << clk), (1 << data));
-					rdev->i2c_bus[4] = radeon_i2c_create(dev, &i2c, "GPIOPAD_MASK");
-					break;
-				}
-			}
-		}
+		/* gpiopad */
+		i2c = radeon_combios_get_i2c_info_from_table(rdev);
+		if (i2c.valid)
+			rdev->i2c_bus[4] = radeon_i2c_create(dev, &i2c, "GPIOPAD_MASK");
 	} else if ((rdev->family == CHIP_R200) ||
 		   (rdev->family >= CHIP_R300)) {
 		/* 0x68 */
@@ -2321,7 +2333,10 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev)
 			connector = (tmp >> 12) & 0xf;
 
 			ddc_type = (tmp >> 8) & 0xf;
-			ddc_i2c = combios_setup_i2c_bus(rdev, ddc_type, 0, 0);
+			if (ddc_type == 5)
+				ddc_i2c = radeon_combios_get_i2c_info_from_table(rdev);
+			else
+				ddc_i2c = combios_setup_i2c_bus(rdev, ddc_type, 0, 0);
 
 			switch (connector) {
 			case CONNECTOR_PROPRIETARY_LEGACY:
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2914c5761cf..895e628b60f 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -64,14 +64,33 @@ void radeon_connector_hotplug(struct drm_connector *connector)
 
 	/* just deal with DP (not eDP) here. */
 	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
-		int saved_dpms = connector->dpms;
-
-		/* Only turn off the display it it's physically disconnected */
-		if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
-			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
-		else if (radeon_dp_needs_link_train(radeon_connector))
-			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-		connector->dpms = saved_dpms;
+		struct radeon_connector_atom_dig *dig_connector =
+			radeon_connector->con_priv;
+
+		/* if existing sink type was not DP no need to retrain */
+		if (dig_connector->dp_sink_type != CONNECTOR_OBJECT_ID_DISPLAYPORT)
+			return;
+
+		/* first get sink type as it may be reset after (un)plug */
+		dig_connector->dp_sink_type = radeon_dp_getsinktype(radeon_connector);
+		/* don't do anything if sink is not display port, i.e.,
+		 * passive dp->(dvi|hdmi) adaptor
+		 */
+		if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) {
+			int saved_dpms = connector->dpms;
+			/* Only turn off the display if it's physically disconnected */
+			if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) {
+				drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+			} else if (radeon_dp_needs_link_train(radeon_connector)) {
+				/* set it to OFF so that drm_helper_connector_dpms()
+				 * won't return immediately since the current state
+				 * is ON at this point.
+				 */
+				connector->dpms = DRM_MODE_DPMS_OFF;
+				drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
+			}
+			connector->dpms = saved_dpms;
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 8a4c49ef0cc..b4a0db24f4d 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -278,6 +278,30 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 	return 0;
 }
 
+static void radeon_bo_vm_fence_va(struct radeon_cs_parser *parser,
+				  struct radeon_fence *fence)
+{
+	struct radeon_fpriv *fpriv = parser->filp->driver_priv;
+	struct radeon_vm *vm = &fpriv->vm;
+	struct radeon_bo_list *lobj;
+
+	if (parser->chunk_ib_idx == -1) {
+		return;
+	}
+	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) {
+		return;
+	}
+
+	list_for_each_entry(lobj, &parser->validated, tv.head) {
+		struct radeon_bo_va *bo_va;
+		struct radeon_bo *rbo = lobj->bo;
+
+		bo_va = radeon_bo_va(rbo, vm);
+		radeon_fence_unref(&bo_va->fence);
+		bo_va->fence = radeon_fence_ref(fence);
+	}
+}
+
 /**
  * cs_parser_fini() - clean parser states
  * @parser:	parser structure holding parsing context.
@@ -290,11 +314,14 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 {
 	unsigned i;
 
-	if (!error)
+	if (!error) {
+		/* fence all bo va before ttm_eu_fence_buffer_objects so bo are still reserved */
+		radeon_bo_vm_fence_va(parser, parser->ib.fence);
 		ttm_eu_fence_buffer_objects(&parser->validated,
 					    parser->ib.fence);
-	else
+	} else {
 		ttm_eu_backoff_reservation(&parser->validated);
+	}
 
 	if (parser->relocs != NULL) {
 		for (i = 0; i < parser->nrelocs; i++) {
@@ -388,7 +415,6 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 
 	if (parser->chunk_ib_idx == -1)
 		return 0;
-
 	if ((parser->cs_flags & RADEON_CS_USE_VM) == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 711e95ad39b..8794744cdf1 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -67,7 +67,8 @@ static void radeon_hide_cursor(struct drm_crtc *crtc)
 
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
-		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT));
+		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
+		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, (AVIVO_D1CURSOR_MODE_24BPP << AVIVO_D1CURSOR_MODE_SHIFT));
@@ -94,7 +95,8 @@ static void radeon_show_cursor(struct drm_crtc *crtc)
 	if (ASIC_IS_DCE4(rdev)) {
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_EN |
-		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT));
+		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
+		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, AVIVO_D1CURSOR_EN |
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 742af8244e8..d2e243867ac 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1009,6 +1009,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	atomic_set(&rdev->ih.lock, 0);
 	mutex_init(&rdev->gem.mutex);
 	mutex_init(&rdev->pm.mutex);
+	mutex_init(&rdev->gpu_clock_mutex);
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index dcea6f01ae4..d7269f48d37 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -59,9 +59,12 @@
  *   2.15.0 - add max_pipes query
  *   2.16.0 - fix evergreen 2D tiled surface calculation
  *   2.17.0 - add STRMOUT_BASE_UPDATE for r7xx
+ *   2.18.0 - r600-eg: allow "invalid" DB formats
+ *   2.19.0 - r600-eg: MSAA textures
+ *   2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	17
+#define KMS_DRIVER_MINOR	20
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 9727ea11722..bb3b7fe05cc 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -438,8 +438,9 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 
 	if (!rdev->vm_manager.enabled) {
 		/* mark first vm as always in use, it's the system one */
+		/* allocate enough for 2 full VM pts */
 		r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-					      rdev->vm_manager.max_pfn * 8,
+					      rdev->vm_manager.max_pfn * 8 * 2,
 					      RADEON_GEM_DOMAIN_VRAM);
 		if (r) {
 			dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
@@ -813,7 +814,7 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 		return -EINVAL;
 	}
 
-	if (bo_va->valid)
+	if (bo_va->valid && mem)
 		return 0;
 
 	ngpu_pages = radeon_bo_ngpu_pages(bo);
@@ -858,11 +859,27 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev,
 		     struct radeon_bo *bo)
 {
 	struct radeon_bo_va *bo_va;
+	int r;
 
 	bo_va = radeon_bo_va(bo, vm);
 	if (bo_va == NULL)
 		return 0;
 
+	/* wait for va use to end */
+	while (bo_va->fence) {
+		r = radeon_fence_wait(bo_va->fence, false);
+		if (r) {
+			DRM_ERROR("error while waiting for fence: %d\n", r);
+		}
+		if (r == -EDEADLK) {
+			r = radeon_gpu_reset(rdev);
+			if (!r)
+				continue;
+		}
+		break;
+	}
+	radeon_fence_unref(&bo_va->fence);
+
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&vm->mutex);
 	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
@@ -915,7 +932,15 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 	mutex_init(&vm->mutex);
 	INIT_LIST_HEAD(&vm->list);
 	INIT_LIST_HEAD(&vm->va);
-	vm->last_pfn = 0;
+	/* SI requires equal sized PTs for all VMs, so always set
+	 * last_pfn to max_pfn.  cayman allows variable sized
+	 * pts so we can grow then as needed.  Once we switch
+	 * to two level pts we can unify this again.
+	 */
+	if (rdev->family >= CHIP_TAHITI)
+		vm->last_pfn = rdev->vm_manager.max_pfn;
+	else
+		vm->last_pfn = 0;
 	/* map the ib pool buffer at 0 in virtual address space, set
 	 * read only
 	 */
@@ -925,7 +950,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 }
 
 /**
- * radeon_vm_init - tear down a vm instance
+ * radeon_vm_fini - tear down a vm instance
  *
  * @rdev: radeon_device pointer
  * @vm: requested vm
@@ -943,12 +968,15 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	radeon_vm_unbind_locked(rdev, vm);
 	mutex_unlock(&rdev->vm_manager.lock);
 
-	/* remove all bo */
+	/* remove all bo at this point non are busy any more because unbind
+	 * waited for the last vm fence to signal
+	 */
 	r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 	if (!r) {
 		bo_va = radeon_bo_va(rdev->ring_tmp_bo.bo, vm);
 		list_del_init(&bo_va->bo_list);
 		list_del_init(&bo_va->vm_list);
+		radeon_fence_unref(&bo_va->fence);
 		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		kfree(bo_va);
 	}
@@ -960,6 +988,7 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 		r = radeon_bo_reserve(bo_va->bo, false);
 		if (!r) {
 			list_del_init(&bo_va->bo_list);
+			radeon_fence_unref(&bo_va->fence);
 			radeon_bo_unreserve(bo_va->bo);
 			kfree(bo_va);
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index b0be9c4f4c9..1b57b0058ad 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -134,25 +134,16 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	struct radeon_device *rdev = rbo->rdev;
 	struct radeon_fpriv *fpriv = file_priv->driver_priv;
 	struct radeon_vm *vm = &fpriv->vm;
-	struct radeon_bo_va *bo_va, *tmp;
 
 	if (rdev->family < CHIP_CAYMAN) {
 		return;
 	}
 
 	if (radeon_bo_reserve(rbo, false)) {
+		dev_err(rdev->dev, "leaking bo va because we fail to reserve bo\n");
 		return;
 	}
-	list_for_each_entry_safe(bo_va, tmp, &rbo->va, bo_list) {
-		if (bo_va->vm == vm) {
-			/* remove from this vm address space */
-			mutex_lock(&vm->mutex);
-			list_del(&bo_va->vm_list);
-			mutex_unlock(&vm->mutex);
-			list_del(&bo_va->bo_list);
-			kfree(bo_va);
-		}
-	}
+	radeon_vm_bo_rmv(rdev, vm, rbo);
 	radeon_bo_unreserve(rbo);
 }
 
@@ -298,6 +289,7 @@ int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data,
 int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_busy *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -323,13 +315,14 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(robj->rdev, r);
+	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 
 int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp)
 {
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_wait_idle *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -342,10 +335,10 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_wait(robj, NULL, false);
 	/* callback hw specific functions if any */
-	if (robj->rdev->asic->ioctl_wait_idle)
-		robj->rdev->asic->ioctl_wait_idle(robj->rdev, robj);
+	if (rdev->asic->ioctl_wait_idle)
+		robj->rdev->asic->ioctl_wait_idle(rdev, robj);
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(robj->rdev, r);
+	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 1d73f16b5d9..414b4acf694 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -29,6 +29,7 @@
 #include "drm_sarea.h"
 #include "radeon.h"
 #include "radeon_drm.h"
+#include "radeon_asic.h"
 
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
@@ -167,17 +168,39 @@ static void radeon_set_filp_rights(struct drm_device *dev,
 int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_radeon_info *info;
+	struct drm_radeon_info *info = data;
 	struct radeon_mode_info *minfo = &rdev->mode_info;
-	uint32_t *value_ptr;
-	uint32_t value;
+	uint32_t value, *value_ptr;
+	uint64_t value64, *value_ptr64;
 	struct drm_crtc *crtc;
 	int i, found;
 
-	info = data;
+	/* TIMESTAMP is a 64-bit value, needs special handling. */
+	if (info->request == RADEON_INFO_TIMESTAMP) {
+		if (rdev->family >= CHIP_R600) {
+			value_ptr64 = (uint64_t*)((unsigned long)info->value);
+			if (rdev->family >= CHIP_TAHITI) {
+				value64 = si_get_gpu_clock(rdev);
+			} else {
+				value64 = r600_get_gpu_clock(rdev);
+			}
+
+			if (DRM_COPY_TO_USER(value_ptr64, &value64, sizeof(value64))) {
+				DRM_ERROR("copy_to_user %s:%u\n", __func__, __LINE__);
+				return -EFAULT;
+			}
+			return 0;
+		} else {
+			DRM_DEBUG_KMS("timestamp is r6xx+ only!\n");
+			return -EINVAL;
+		}
+	}
+
 	value_ptr = (uint32_t *)((unsigned long)info->value);
-	if (DRM_COPY_FROM_USER(&value, value_ptr, sizeof(value)))
+	if (DRM_COPY_FROM_USER(&value, value_ptr, sizeof(value))) {
+		DRM_ERROR("copy_from_user %s:%u\n", __func__, __LINE__);
 		return -EFAULT;
+	}
 
 	switch (info->request) {
 	case RADEON_INFO_DEVICE_ID:
@@ -337,7 +360,7 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		return -EINVAL;
 	}
 	if (DRM_COPY_TO_USER(value_ptr, &value, sizeof(uint32_t))) {
-		DRM_ERROR("copy_to_user\n");
+		DRM_ERROR("copy_to_user %s:%u\n", __func__, __LINE__);
 		return -EFAULT;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index d5fd615897e..94b4a1c1289 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -1025,9 +1025,11 @@ static int radeon_crtc_mode_set(struct drm_crtc *crtc,
 
 static void radeon_crtc_prepare(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
+	radeon_crtc->in_mode_set = true;
 	/*
 	* The hardware wedges sometimes if you reconfigure one CRTC
 	* whilst another is running (see fdo bug #24611).
@@ -1038,6 +1040,7 @@ static void radeon_crtc_prepare(struct drm_crtc *crtc)
 
 static void radeon_crtc_commit(struct drm_crtc *crtc)
 {
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
 	struct drm_crtc *crtci;
 
@@ -1048,6 +1051,7 @@ static void radeon_crtc_commit(struct drm_crtc *crtc)
 		if (crtci->enabled)
 			radeon_crtc_dpms(crtci, DRM_MODE_DPMS_ON);
 	}
+	radeon_crtc->in_mode_set = false;
 }
 
 static const struct drm_crtc_helper_funcs legacy_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index f380d59c576..d56978949f3 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -275,6 +275,7 @@ struct radeon_crtc {
 	u16 lut_r[256], lut_g[256], lut_b[256];
 	bool enabled;
 	bool can_tile;
+	bool in_mode_set;
 	uint32_t crtc_offset;
 	struct drm_gem_object *cursor_bo;
 	uint64_t cursor_addr;
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 6ecb2006e27..1cb014b571a 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -52,11 +52,7 @@ void radeon_bo_clear_va(struct radeon_bo *bo)
 
 	list_for_each_entry_safe(bo_va, tmp, &bo->va, bo_list) {
 		/* remove from all vm address space */
-		mutex_lock(&bo_va->vm->mutex);
-		list_del(&bo_va->vm_list);
-		mutex_unlock(&bo_va->vm->mutex);
-		list_del(&bo_va->bo_list);
-		kfree(bo_va);
+		radeon_vm_bo_rmv(bo->rdev, bo_va->vm, bo);
 	}
 }
 
@@ -115,9 +111,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 
 	size = ALIGN(size, PAGE_SIZE);
 
-	if (unlikely(rdev->mman.bdev.dev_mapping == NULL)) {
-		rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
-	}
+	rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
 	if (kernel) {
 		type = ttm_bo_type_kernel;
 	} else if (sg) {
@@ -138,7 +132,6 @@ int radeon_bo_create(struct radeon_device *rdev,
 	acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size,
 				       sizeof(struct radeon_bo));
 
-retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
@@ -152,6 +145,8 @@ retry:
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	INIT_LIST_HEAD(&bo->va);
+
+retry:
 	radeon_ttm_placement_from_domain(bo, domain);
 	/* Kernel allocation are uninterruptible */
 	down_read(&rdev->pm.mclk_lock);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index f2fc25de0b2..ec79b375043 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -594,7 +594,11 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 	}
 
 	/* and then save the content of the ring */
-	*data = kmalloc(size * 4, GFP_KERNEL);
+	*data = kmalloc_array(size, sizeof(uint32_t), GFP_KERNEL);
+	if (!*data) {
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
 	for (i = 0; i < size; ++i) {
 		(*data)[i] = ring->ring[ptr++];
 		ptr &= ring->ptr_mask;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 0881131a038..5b71c716d83 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -734,9 +734,7 @@ int radeon_ttm_init(struct radeon_device *rdev)
 	}
 	DRM_INFO("radeon: %uM of GTT memory ready.\n",
 		 (unsigned)(rdev->mc.gtt_size / (1024 * 1024)));
-	if (unlikely(rdev->mman.bdev.dev_mapping == NULL)) {
-		rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
-	}
+	rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
 
 	r = radeon_ttm_debugfs_init(rdev);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index a12fbcc8ccb..aa8ef491ef3 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -281,12 +281,8 @@ int rv515_debugfs_ga_info_init(struct radeon_device *rdev)
 
 void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save)
 {
-	save->d1vga_control = RREG32(R_000330_D1VGA_CONTROL);
-	save->d2vga_control = RREG32(R_000338_D2VGA_CONTROL);
 	save->vga_render_control = RREG32(R_000300_VGA_RENDER_CONTROL);
 	save->vga_hdp_control = RREG32(R_000328_VGA_HDP_CONTROL);
-	save->d1crtc_control = RREG32(R_006080_D1CRTC_CONTROL);
-	save->d2crtc_control = RREG32(R_006880_D2CRTC_CONTROL);
 
 	/* Stop all video */
 	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0);
@@ -311,15 +307,6 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
 	/* Unlock host access */
 	WREG32(R_000328_VGA_HDP_CONTROL, save->vga_hdp_control);
 	mdelay(1);
-	/* Restore video state */
-	WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control);
-	WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control);
-	WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1);
-	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 1);
-	WREG32(R_006080_D1CRTC_CONTROL, save->d1crtc_control);
-	WREG32(R_006880_D2CRTC_CONTROL, save->d2crtc_control);
-	WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0);
-	WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0);
 	WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control);
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 7c3e330c7b5..0139e227e3c 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1639,11 +1639,19 @@ static void si_gpu_init(struct radeon_device *rdev)
 		/* XXX what about 12? */
 		rdev->config.si.tile_config |= (3 << 0);
 		break;
-	}
-	if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-		rdev->config.si.tile_config |= 1 << 4;
-	else
+	}	
+	switch ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) {
+	case 0: /* four banks */
 		rdev->config.si.tile_config |= 0 << 4;
+		break;
+	case 1: /* eight banks */
+		rdev->config.si.tile_config |= 1 << 4;
+		break;
+	case 2: /* sixteen banks */
+	default:
+		rdev->config.si.tile_config |= 2 << 4;
+		break;
+	}
 	rdev->config.si.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
 	rdev->config.si.tile_config |=
@@ -2398,12 +2406,12 @@ int si_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(0x15DC, 0);
 
 	/* empty context1-15 */
-	/* FIXME start with 1G, once using 2 level pt switch to full
+	/* FIXME start with 4G, once using 2 level pt switch to full
 	 * vm size space
 	 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, (1 << 30) / RADEON_GPU_PAGE_SIZE);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
@@ -3960,3 +3968,22 @@ void si_fini(struct radeon_device *rdev)
 	rdev->bios = NULL;
 }
 
+/**
+ * si_get_gpu_clock - return GPU clock counter snapshot
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Fetches a GPU clock counter snapshot (SI).
+ * Returns the 64 bit clock counter snapshot.
+ */
+uint64_t si_get_gpu_clock(struct radeon_device *rdev)
+{
+	uint64_t clock;
+
+	mutex_lock(&rdev->gpu_clock_mutex);
+	WREG32(RLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+	clock = (uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_LSB) |
+	        ((uint64_t)RREG32(RLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	mutex_unlock(&rdev->gpu_clock_mutex);
+	return clock;
+}
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 7869089e876..ef4815c27b1 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -698,6 +698,9 @@
 #define RLC_UCODE_ADDR                                    0xC32C
 #define RLC_UCODE_DATA                                    0xC330
 
+#define RLC_GPU_CLOCK_COUNT_LSB                           0xC338
+#define RLC_GPU_CLOCK_COUNT_MSB                           0xC33C
+#define RLC_CAPTURE_GPU_CLOCK_COUNT                       0xC340
 #define RLC_MC_CNTL                                       0xC344
 #define RLC_UCODE_CNTL                                    0xC348
 
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 7bd65bdd15a..291ecc14558 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -308,7 +308,7 @@ struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev,
 	/* need to attach */
 	attach = dma_buf_attach(dma_buf, dev->dev);
 	if (IS_ERR(attach))
-		return ERR_PTR(PTR_ERR(attach));
+		return ERR_CAST(attach);
 
 	sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
 	if (IS_ERR(sg)) {
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index a8d5f09428c..4c2d836a089 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -61,7 +61,7 @@ static int udl_parse_vendor_descriptor(struct drm_device *dev,
 			u8 length;
 			u16 key;
 
-			key = *((u16 *) desc);
+			key = le16_to_cpu(*((u16 *) desc));
 			desc += sizeof(u16);
 			length = *desc;
 			desc++;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 5d5632f5265..4d9edead01a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -769,10 +769,7 @@ static int vmw_driver_open(struct drm_device *dev, struct drm_file *file_priv)
 		goto out_no_tfile;
 
 	file_priv->driver_priv = vmw_fp;
-
-	if (unlikely(dev_priv->bdev.dev_mapping == NULL))
-		dev_priv->bdev.dev_mapping =
-			file_priv->filp->f_path.dentry->d_inode->i_mapping;
+	dev_priv->bdev.dev_mapping = dev->dev_mapping;
 
 	return 0;