Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

46 files changed, 962 insertions, 198 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index cc1148837e2..e354bc0b052 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -9,6 +9,7 @@ menuconfig DRM
 	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU
 	select I2C
 	select I2C_ALGOBIT
+	select DMA_SHARED_BUFFER
 	help
 	  Kernel-level support for the Direct Rendering Infrastructure (DRI)
 	  introduced in XFree86 4.0. If you say Y here, you need to select
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index a858532806a..c20da5bda35 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -12,7 +12,7 @@ drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
 		drm_platform.o drm_sysfs.o drm_hashtab.o drm_mm.o \
 		drm_crtc.o drm_modes.o drm_edid.o \
 		drm_info.o drm_debugfs.o drm_encoder_slave.o \
-		drm_trace_points.o drm_global.o
+		drm_trace_points.o drm_global.o drm_prime.o
 
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 0b65fbc8a63..6116e3b7539 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -136,6 +136,10 @@ static struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED),
+
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 7740dd26f00..a0d6e894d97 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -559,9 +559,13 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 		return -EINVAL;
 
 	/* Need to resize the fb object !!! */
-	if (var->bits_per_pixel > fb->bits_per_pixel || var->xres > fb->width || var->yres > fb->height) {
+	if (var->bits_per_pixel > fb->bits_per_pixel ||
+	    var->xres > fb->width || var->yres > fb->height ||
+	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
 		DRM_DEBUG("fb userspace requested width/height/bpp is greater than current fb "
-			  "object %dx%d-%d > %dx%d-%d\n", var->xres, var->yres, var->bits_per_pixel,
+			  "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
+			  var->xres, var->yres, var->bits_per_pixel,
+			  var->xres_virtual, var->yres_virtual,
 			  fb->width, fb->height, fb->bits_per_pixel);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 7348a3dab25..cdfbf27b2b3 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -271,6 +271,9 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 	if (dev->driver->driver_features & DRIVER_GEM)
 		drm_gem_open(dev, priv);
 
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_init_file_private(&priv->prime);
+
 	if (dev->driver->open) {
 		ret = dev->driver->open(dev, priv);
 		if (ret < 0)
@@ -571,6 +574,10 @@ int drm_release(struct inode *inode, struct file *filp)
 
 	if (dev->driver->postclose)
 		dev->driver->postclose(dev, file_priv);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file_priv->prime);
+
 	kfree(file_priv);
 
 	/* ========================================================
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 0ef358e5324..83114b5e3ce 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -35,6 +35,7 @@
 #include <linux/mman.h>
 #include <linux/pagemap.h>
 #include <linux/shmem_fs.h>
+#include <linux/dma-buf.h>
 #include "drmP.h"
 
 /** @file drm_gem.c
@@ -232,6 +233,10 @@ drm_gem_handle_delete(struct drm_file *filp, u32 handle)
 	idr_remove(&filp->object_idr, handle);
 	spin_unlock(&filp->table_lock);
 
+	if (obj->import_attach)
+		drm_prime_remove_imported_buf_handle(&filp->prime,
+				obj->import_attach->dmabuf);
+
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, filp);
 	drm_gem_object_handle_unreference_unlocked(obj);
@@ -527,6 +532,10 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_gem_object *obj = ptr;
 	struct drm_device *dev = obj->dev;
 
+	if (obj->import_attach)
+		drm_prime_remove_imported_buf_handle(&file_priv->prime,
+				obj->import_attach->dmabuf);
+
 	if (dev->driver->gem_close_object)
 		dev->driver->gem_close_object(obj, file_priv);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
new file mode 100644
index 00000000000..1bdf2b54eaf
--- /dev/null
+++ b/drivers/gpu/drm/drm_prime.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright © 2012 Red Hat
+ *
+ * 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 (including the next
+ * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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 <airlied@redhat.com>
+ *      Rob Clark <rob.clark@linaro.org>
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/dma-buf.h>
+#include "drmP.h"
+
+/*
+ * DMA-BUF/GEM Object references and lifetime overview:
+ *
+ * On the export the dma_buf holds a reference to the exporting GEM
+ * object. It takes this reference in handle_to_fd_ioctl, when it
+ * first calls .prime_export and stores the exporting GEM object in
+ * the dma_buf priv. This reference is released when the dma_buf
+ * object goes away in the driver .release function.
+ *
+ * On the import the importing GEM object holds a reference to the
+ * dma_buf (which in turn holds a ref to the exporting GEM object).
+ * It takes that reference in the fd_to_handle ioctl.
+ * It calls dma_buf_get, creates an attachment to it and stores the
+ * attachment in the GEM object. When this attachment is destroyed
+ * when the imported object is destroyed, we remove the attachment
+ * and drop the reference to the dma_buf.
+ *
+ * Thus the chain of references always flows in one direction
+ * (avoiding loops): importing_gem -> dmabuf -> exporting_gem
+ *
+ * Self-importing: if userspace is using PRIME as a replacement for flink
+ * then it will get a fd->handle request for a GEM object that it created.
+ * Drivers should detect this situation and return back the gem object
+ * from the dma-buf private.
+ */
+
+struct drm_prime_member {
+	struct list_head entry;
+	struct dma_buf *dma_buf;
+	uint32_t handle;
+};
+
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+		struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+		int *prime_fd)
+{
+	struct drm_gem_object *obj;
+	void *buf;
+
+	obj = drm_gem_object_lookup(dev, file_priv, handle);
+	if (!obj)
+		return -ENOENT;
+
+	mutex_lock(&file_priv->prime.lock);
+	/* re-export the original imported object */
+	if (obj->import_attach) {
+		get_dma_buf(obj->import_attach->dmabuf);
+		*prime_fd = dma_buf_fd(obj->import_attach->dmabuf, flags);
+		drm_gem_object_unreference_unlocked(obj);
+		mutex_unlock(&file_priv->prime.lock);
+		return 0;
+	}
+
+	if (obj->export_dma_buf) {
+		get_dma_buf(obj->export_dma_buf);
+		*prime_fd = dma_buf_fd(obj->export_dma_buf, flags);
+		drm_gem_object_unreference_unlocked(obj);
+	} else {
+		buf = dev->driver->gem_prime_export(dev, obj, flags);
+		if (IS_ERR(buf)) {
+			/* normally the created dma-buf takes ownership of the ref,
+			 * but if that fails then drop the ref
+			 */
+			drm_gem_object_unreference_unlocked(obj);
+			mutex_unlock(&file_priv->prime.lock);
+			return PTR_ERR(buf);
+		}
+		obj->export_dma_buf = buf;
+		*prime_fd = dma_buf_fd(buf, flags);
+	}
+	mutex_unlock(&file_priv->prime.lock);
+	return 0;
+}
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
+
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+		struct drm_file *file_priv, int prime_fd, uint32_t *handle)
+{
+	struct dma_buf *dma_buf;
+	struct drm_gem_object *obj;
+	int ret;
+
+	dma_buf = dma_buf_get(prime_fd);
+	if (IS_ERR(dma_buf))
+		return PTR_ERR(dma_buf);
+
+	mutex_lock(&file_priv->prime.lock);
+
+	ret = drm_prime_lookup_imported_buf_handle(&file_priv->prime,
+			dma_buf, handle);
+	if (!ret) {
+		ret = 0;
+		goto out_put;
+	}
+
+	/* never seen this one, need to import */
+	obj = dev->driver->gem_prime_import(dev, dma_buf);
+	if (IS_ERR(obj)) {
+		ret = PTR_ERR(obj);
+		goto out_put;
+	}
+
+	ret = drm_gem_handle_create(file_priv, obj, handle);
+	drm_gem_object_unreference_unlocked(obj);
+	if (ret)
+		goto out_put;
+
+	ret = drm_prime_add_imported_buf_handle(&file_priv->prime,
+			dma_buf, *handle);
+	if (ret)
+		goto fail;
+
+	mutex_unlock(&file_priv->prime.lock);
+	return 0;
+
+fail:
+	/* hmm, if driver attached, we are relying on the free-object path
+	 * to detach.. which seems ok..
+	 */
+	drm_gem_object_handle_unreference_unlocked(obj);
+out_put:
+	dma_buf_put(dma_buf);
+	mutex_unlock(&file_priv->prime.lock);
+	return ret;
+}
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
+
+int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct drm_prime_handle *args = data;
+	uint32_t flags;
+
+	if (!drm_core_check_feature(dev, DRIVER_PRIME))
+		return -EINVAL;
+
+	if (!dev->driver->prime_handle_to_fd)
+		return -ENOSYS;
+
+	/* check flags are valid */
+	if (args->flags & ~DRM_CLOEXEC)
+		return -EINVAL;
+
+	/* we only want to pass DRM_CLOEXEC which is == O_CLOEXEC */
+	flags = args->flags & DRM_CLOEXEC;
+
+	return dev->driver->prime_handle_to_fd(dev, file_priv,
+			args->handle, flags, &args->fd);
+}
+
+int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct drm_prime_handle *args = data;
+
+	if (!drm_core_check_feature(dev, DRIVER_PRIME))
+		return -EINVAL;
+
+	if (!dev->driver->prime_fd_to_handle)
+		return -ENOSYS;
+
+	return dev->driver->prime_fd_to_handle(dev, file_priv,
+			args->fd, &args->handle);
+}
+
+/*
+ * drm_prime_pages_to_sg
+ *
+ * this helper creates an sg table object from a set of pages
+ * the driver is responsible for mapping the pages into the
+ * importers address space
+ */
+struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages)
+{
+	struct sg_table *sg = NULL;
+	struct scatterlist *iter;
+	int i;
+	int ret;
+
+	sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
+	if (!sg)
+		goto out;
+
+	ret = sg_alloc_table(sg, nr_pages, GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	for_each_sg(sg->sgl, iter, nr_pages, i)
+		sg_set_page(iter, pages[i], PAGE_SIZE, 0);
+
+	return sg;
+out:
+	kfree(sg);
+	return NULL;
+}
+EXPORT_SYMBOL(drm_prime_pages_to_sg);
+
+/* helper function to cleanup a GEM/prime object */
+void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg)
+{
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+	attach = obj->import_attach;
+	if (sg)
+		dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	/* remove the reference */
+	dma_buf_put(dma_buf);
+}
+EXPORT_SYMBOL(drm_prime_gem_destroy);
+
+void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
+{
+	INIT_LIST_HEAD(&prime_fpriv->head);
+	mutex_init(&prime_fpriv->lock);
+}
+EXPORT_SYMBOL(drm_prime_init_file_private);
+
+void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv)
+{
+	struct drm_prime_member *member, *safe;
+	list_for_each_entry_safe(member, safe, &prime_fpriv->head, entry) {
+		list_del(&member->entry);
+		kfree(member);
+	}
+}
+EXPORT_SYMBOL(drm_prime_destroy_file_private);
+
+int drm_prime_add_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t handle)
+{
+	struct drm_prime_member *member;
+
+	member = kmalloc(sizeof(*member), GFP_KERNEL);
+	if (!member)
+		return -ENOMEM;
+
+	member->dma_buf = dma_buf;
+	member->handle = handle;
+	list_add(&member->entry, &prime_fpriv->head);
+	return 0;
+}
+EXPORT_SYMBOL(drm_prime_add_imported_buf_handle);
+
+int drm_prime_lookup_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf, uint32_t *handle)
+{
+	struct drm_prime_member *member;
+
+	list_for_each_entry(member, &prime_fpriv->head, entry) {
+		if (member->dma_buf == dma_buf) {
+			*handle = member->handle;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL(drm_prime_lookup_imported_buf_handle);
+
+void drm_prime_remove_imported_buf_handle(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf)
+{
+	struct drm_prime_member *member, *safe;
+
+	mutex_lock(&prime_fpriv->lock);
+	list_for_each_entry_safe(member, safe, &prime_fpriv->head, entry) {
+		if (member->dma_buf == dma_buf) {
+			list_del(&member->entry);
+			kfree(member);
+		}
+	}
+	mutex_unlock(&prime_fpriv->lock);
+}
+EXPORT_SYMBOL(drm_prime_remove_imported_buf_handle);
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
index 4c2cb4a8ad9..5675d93b420 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
@@ -244,7 +244,6 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 				uint64_t value)
 {
 	struct drm_encoder *encoder = connector->encoder;
-	struct backlight_device *psb_bd;
 
 	if (!strcmp(property->name, "scaling mode") && encoder) {
 		struct psb_intel_crtc *psb_crtc =
@@ -301,11 +300,15 @@ static int mdfld_dsi_connector_set_property(struct drm_connector *connector,
 									value))
 			goto set_prop_error;
 		else {
+#ifdef CONFIG_BACKLIGHT_CLASS_DEVICE
+			struct backlight_device *psb_bd;
+
 			psb_bd = mdfld_get_backlight_device();
 			if (psb_bd) {
 				psb_bd->props.brightness = value;
 				mdfld_set_brightness(psb_bd);
 			}
+#endif
 		}
 	}
 set_prop_done:
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fdb7ccefffb..b505b70dba0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1502,14 +1502,6 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int
-i915_debugfs_common_open(struct inode *inode,
-			 struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
 static ssize_t
 i915_wedged_read(struct file *filp,
 		 char __user *ubuf,
@@ -1560,7 +1552,7 @@ i915_wedged_write(struct file *filp,
 
 static const struct file_operations i915_wedged_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_wedged_read,
 	.write = i915_wedged_write,
 	.llseek = default_llseek,
@@ -1622,7 +1614,7 @@ i915_max_freq_write(struct file *filp,
 
 static const struct file_operations i915_max_freq_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_max_freq_read,
 	.write = i915_max_freq_write,
 	.llseek = default_llseek,
@@ -1693,7 +1685,7 @@ i915_cache_sharing_write(struct file *filp,
 
 static const struct file_operations i915_cache_sharing_fops = {
 	.owner = THIS_MODULE,
-	.open = i915_debugfs_common_open,
+	.open = simple_open,
 	.read = i915_cache_sharing_read,
 	.write = i915_cache_sharing_write,
 	.llseek = default_llseek,
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9341eb8ce93..785f67f963e 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1183,6 +1183,21 @@ static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
 	return can_switch;
 }
 
+static bool
+intel_enable_ppgtt(struct drm_device *dev)
+{
+	if (i915_enable_ppgtt >= 0)
+		return i915_enable_ppgtt;
+
+#ifdef CONFIG_INTEL_IOMMU
+	/* Disable ppgtt on SNB if VT-d is on. */
+	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped)
+		return false;
+#endif
+
+	return true;
+}
+
 static int i915_load_gem_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1197,7 +1212,7 @@ static int i915_load_gem_init(struct drm_device *dev)
 	drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size);
 
 	mutex_lock(&dev->struct_mutex);
-	if (i915_enable_ppgtt && HAS_ALIASING_PPGTT(dev)) {
+	if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) {
 		/* PPGTT pdes are stolen from global gtt ptes, so shrink the
 		 * aperture accordingly when using aliasing ppgtt. */
 		gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
@@ -1207,8 +1222,10 @@ static int i915_load_gem_init(struct drm_device *dev)
 		i915_gem_do_init(dev, 0, mappable_size, gtt_size);
 
 		ret = i915_gem_init_aliasing_ppgtt(dev);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&dev->struct_mutex);
 			return ret;
+		}
 	} else {
 		/* Let GEM Manage all of the aperture.
 		 *
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0694e170a33..dfa55e7478f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -66,7 +66,11 @@ MODULE_PARM_DESC(semaphores,
 int i915_enable_rc6 __read_mostly = -1;
 module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
-		"Enable power-saving render C-state 6 (default: -1 (use per-chip default)");
+		"Enable power-saving render C-state 6. "
+		"Different stages can be selected via bitmask values "
+		"(0 = disable; 1 = enable rc6; 2 = enable deep rc6; 4 = enable deepest rc6). "
+		"For example, 3 would enable rc6 and deep rc6, and 7 would enable everything. "
+		"default: -1 (use per-chip default)");
 
 int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
@@ -103,8 +107,8 @@ MODULE_PARM_DESC(enable_hangcheck,
 		"WARNING: Disabling this can cause system wide hangs. "
 		"(default: true)");
 
-bool i915_enable_ppgtt __read_mostly = 1;
-module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, bool, 0600);
+int i915_enable_ppgtt __read_mostly = -1;
+module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, int, 0600);
 MODULE_PARM_DESC(i915_enable_ppgtt,
 		"Enable PPGTT (default: true)");
 
@@ -292,6 +296,7 @@ static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_VGA_DEVICE(0x0152, &intel_ivybridge_d_info), /* GT1 desktop */
 	INTEL_VGA_DEVICE(0x0162, &intel_ivybridge_d_info), /* GT2 desktop */
 	INTEL_VGA_DEVICE(0x015a, &intel_ivybridge_d_info), /* GT1 server */
+	INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */
 	{0, 0, 0}
 };
 
@@ -467,6 +472,10 @@ static int i915_drm_freeze(struct drm_device *dev)
 	/* Modeset on resume, not lid events */
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 1);
+	console_unlock();
+
 	return 0;
 }
 
@@ -529,7 +538,9 @@ static int i915_drm_thaw(struct drm_device *dev)
 		drm_irq_install(dev);
 
 		/* Resume the modeset for every activated CRTC */
+		mutex_lock(&dev->mode_config.mutex);
 		drm_helper_resume_force_mode(dev);
+		mutex_unlock(&dev->mode_config.mutex);
 
 		if (IS_IRONLAKE_M(dev))
 			ironlake_enable_rc6(dev);
@@ -539,6 +550,9 @@ static int i915_drm_thaw(struct drm_device *dev)
 
 	dev_priv->modeset_on_lid = 0;
 
+	console_lock();
+	intel_fbdev_set_suspend(dev, 0);
+	console_unlock();
 	return error;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c0f19f57200..5fabc6c31fe 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1053,6 +1053,27 @@ struct drm_i915_file_private {
 
 #include "i915_trace.h"
 
+/**
+ * RC6 is a special power stage which allows the GPU to enter an very
+ * low-voltage mode when idle, using down to 0V while at this stage.  This
+ * stage is entered automatically when the GPU is idle when RC6 support is
+ * enabled, and as soon as new workload arises GPU wakes up automatically as well.
+ *
+ * There are different RC6 modes available in Intel GPU, which differentiate
+ * among each other with the latency required to enter and leave RC6 and
+ * voltage consumed by the GPU in different states.
+ *
+ * The combination of the following flags define which states GPU is allowed
+ * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
+ * RC6pp is deepest RC6. Their support by hardware varies according to the
+ * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
+ * which brings the most power savings; deeper states save more power, but
+ * require higher latency to switch to and wake up.
+ */
+#define INTEL_RC6_ENABLE			(1<<0)
+#define INTEL_RC6p_ENABLE			(1<<1)
+#define INTEL_RC6pp_ENABLE			(1<<2)
+
 extern struct drm_ioctl_desc i915_ioctls[];
 extern int i915_max_ioctl;
 extern unsigned int i915_fbpercrtc __always_unused;
@@ -1065,7 +1086,7 @@ extern int i915_vbt_sdvo_panel_type __read_mostly;
 extern int i915_enable_rc6 __read_mostly;
 extern int i915_enable_fbc __read_mostly;
 extern bool i915_enable_hangcheck __read_mostly;
-extern bool i915_enable_ppgtt __read_mostly;
+extern int i915_enable_ppgtt __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
 extern int i915_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1f441f5c240..4c65c639f77 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1472,16 +1472,19 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	list_move_tail(&obj->ring_list, &ring->active_list);
 
 	obj->last_rendering_seqno = seqno;
-	if (obj->fenced_gpu_access) {
-		struct drm_i915_fence_reg *reg;
-
-		BUG_ON(obj->fence_reg == I915_FENCE_REG_NONE);
 
+	if (obj->fenced_gpu_access) {
 		obj->last_fenced_seqno = seqno;
 		obj->last_fenced_ring = ring;
 
-		reg = &dev_priv->fence_regs[obj->fence_reg];
-		list_move_tail(&reg->lru_list, &dev_priv->mm.fence_list);
+		/* Bump MRU to take account of the delayed flush */
+		if (obj->fence_reg != I915_FENCE_REG_NONE) {
+			struct drm_i915_fence_reg *reg;
+
+			reg = &dev_priv->fence_regs[obj->fence_reg];
+			list_move_tail(&reg->lru_list,
+				       &dev_priv->mm.fence_list);
+		}
 	}
 }
 
@@ -3754,12 +3757,32 @@ void i915_gem_init_ppgtt(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	uint32_t pd_offset;
 	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	uint32_t __iomem *pd_addr;
+	uint32_t pd_entry;
 	int i;
 
 	if (!dev_priv->mm.aliasing_ppgtt)
 		return;
 
-	pd_offset = dev_priv->mm.aliasing_ppgtt->pd_offset;
+
+	pd_addr = dev_priv->mm.gtt->gtt + ppgtt->pd_offset/sizeof(uint32_t);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		if (dev_priv->mm.gtt->needs_dmar)
+			pt_addr = ppgtt->pt_dma_addr[i];
+		else
+			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
+
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	pd_offset = ppgtt->pd_offset;
 	pd_offset /= 64; /* in cachelines, */
 	pd_offset <<= 16;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 81687af0089..f51a696486c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -498,8 +498,8 @@ pin_and_fence_object(struct drm_i915_gem_object *obj,
 				if (ret)
 					goto err_unpin;
 			}
+			obj->pending_fenced_gpu_access = true;
 		}
-		obj->pending_fenced_gpu_access = need_fence;
 	}
 
 	entry->offset = obj->gtt_offset;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2eacd78bb93..a135c61f411 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -65,9 +65,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_ppgtt *ppgtt;
-	uint32_t pd_entry;
 	unsigned first_pd_entry_in_global_pt;
-	uint32_t __iomem *pd_addr;
 	int i;
 	int ret = -ENOMEM;
 
@@ -100,7 +98,6 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 			goto err_pt_alloc;
 	}
 
-	pd_addr = dev_priv->mm.gtt->gtt + first_pd_entry_in_global_pt;
 	for (i = 0; i < ppgtt->num_pd_entries; i++) {
 		dma_addr_t pt_addr;
 		if (dev_priv->mm.gtt->needs_dmar) {
@@ -117,13 +114,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
 			ppgtt->pt_dma_addr[i] = pt_addr;
 		} else
 			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
-
-		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
-		pd_entry |= GEN6_PDE_VALID;
-
-		writel(pd_entry, pd_addr + i);
 	}
-	readl(pd_addr);
 
 	ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3886cf051ba..2abf4eb9403 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2385,6 +2385,7 @@
 #define   PIPECONF_DISABLE	0
 #define   PIPECONF_DOUBLE_WIDE	(1<<30)
 #define   I965_PIPECONF_ACTIVE	(1<<30)
+#define   PIPECONF_FRAME_START_DELAY_MASK (3<<27)
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
 #define   PIPECONF_PIPE_LOCKED	(1<<25)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 8168d8f8a63..b48fc2a8410 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -24,6 +24,7 @@
  *    Eric Anholt <eric@anholt.net>
  *
  */
+#include <linux/dmi.h>
 #include <drm/drm_dp_helper.h>
 #include "drmP.h"
 #include "drm.h"
@@ -621,6 +622,26 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->edp.bpp = 18;
 }
 
+static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
+{
+	DRM_DEBUG_KMS("Falling back to manually reading VBT from "
+		      "VBIOS ROM for %s\n",
+		      id->ident);
+	return 1;
+}
+
+static const struct dmi_system_id intel_no_opregion_vbt[] = {
+	{
+		.callback = intel_no_opregion_vbt_callback,
+		.ident = "ThinkCentre A57",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "97027RG"),
+		},
+	},
+	{ }
+};
+
 /**
  * intel_parse_bios - find VBT and initialize settings from the BIOS
  * @dev: DRM device
@@ -641,7 +662,7 @@ intel_parse_bios(struct drm_device *dev)
 	init_vbt_defaults(dev_priv);
 
 	/* XXX Should this validation be moved to intel_opregion.c? */
-	if (dev_priv->opregion.vbt) {
+	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) {
 		struct vbt_header *vbt = dev_priv->opregion.vbt;
 		if (memcmp(vbt->signature, "$VBT", 4) == 0) {
 			DRM_DEBUG_KMS("Using VBT from OpRegion: %20s\n",
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d514719f65e..91b35fd1db8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5539,7 +5539,8 @@ void ironlake_init_pch_refclk(struct drm_device *dev)
 		if (intel_panel_use_ssc(dev_priv) && can_ssc) {
 			DRM_DEBUG_KMS("Using SSC on panel\n");
 			temp |= DREF_SSC1_ENABLE;
-		}
+		} else
+			temp &= ~DREF_SSC1_ENABLE;
 
 		/* Get SSC going before enabling the outputs */
 		I915_WRITE(PCH_DREF_CONTROL, temp);
@@ -7580,6 +7581,12 @@ static void intel_sanitize_modesetting(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg, val;
 
+	/* Clear any frame start delays used for debugging left by the BIOS */
+	for_each_pipe(pipe) {
+		reg = PIPECONF(pipe);
+		I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
+	}
+
 	if (HAS_PCH_SPLIT(dev))
 		return;
 
@@ -8215,7 +8222,7 @@ void intel_init_emon(struct drm_device *dev)
 	dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
-static bool intel_enable_rc6(struct drm_device *dev)
+static int intel_enable_rc6(struct drm_device *dev)
 {
 	/*
 	 * Respect the kernel parameter if it is set
@@ -8233,11 +8240,11 @@ static bool intel_enable_rc6(struct drm_device *dev)
 	 * Disable rc6 on Sandybridge
 	 */
 	if (INTEL_INFO(dev)->gen == 6) {
-		DRM_DEBUG_DRIVER("Sandybridge: RC6 disabled\n");
-		return 0;
+		DRM_DEBUG_DRIVER("Sandybridge: deep RC6 disabled\n");
+		return INTEL_RC6_ENABLE;
 	}
-	DRM_DEBUG_DRIVER("RC6 enabled\n");
-	return 1;
+	DRM_DEBUG_DRIVER("RC6 and deep RC6 enabled\n");
+	return (INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE);
 }
 
 void gen6_enable_rps(struct drm_i915_private *dev_priv)
@@ -8247,6 +8254,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	u32 pcu_mbox, rc6_mask = 0;
 	u32 gtfifodbg;
 	int cur_freq, min_freq, max_freq;
+	int rc6_mode;
 	int i;
 
 	/* Here begins a magic sequence of register writes to enable
@@ -8284,9 +8292,20 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN6_RC6p_THRESHOLD, 100000);
 	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
-	if (intel_enable_rc6(dev_priv->dev))
-		rc6_mask = GEN6_RC_CTL_RC6_ENABLE |
-			((IS_GEN7(dev_priv->dev)) ? GEN6_RC_CTL_RC6p_ENABLE : 0);
+	rc6_mode = intel_enable_rc6(dev_priv->dev);
+	if (rc6_mode & INTEL_RC6_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6_ENABLE;
+
+	if (rc6_mode & INTEL_RC6p_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
+
+	if (rc6_mode & INTEL_RC6pp_ENABLE)
+		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
+
+	DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
+			(rc6_mode & INTEL_RC6_ENABLE) ? "on" : "off",
+			(rc6_mode & INTEL_RC6p_ENABLE) ? "on" : "off",
+			(rc6_mode & INTEL_RC6pp_ENABLE) ? "on" : "off");
 
 	I915_WRITE(GEN6_RC_CONTROL,
 		   rc6_mask |
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9cec6c3937f..5a14149b379 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -382,7 +382,7 @@ extern int intel_framebuffer_init(struct drm_device *dev,
 				  struct drm_i915_gem_object *obj);
 extern int intel_fbdev_init(struct drm_device *dev);
 extern void intel_fbdev_fini(struct drm_device *dev);
-
+extern void intel_fbdev_set_suspend(struct drm_device *dev, int state);
 extern void intel_prepare_page_flip(struct drm_device *dev, int plane);
 extern void intel_finish_page_flip(struct drm_device *dev, int pipe);
 extern void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 2d876697838..19ecd78b8a2 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -254,6 +254,16 @@ void intel_fbdev_fini(struct drm_device *dev)
 	kfree(dev_priv->fbdev);
 	dev_priv->fbdev = NULL;
 }
+
+void intel_fbdev_set_suspend(struct drm_device *dev, int state)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	if (!dev_priv->fbdev)
+		return;
+
+	fb_set_suspend(dev_priv->fbdev->helper.fbdev, state);
+}
+
 MODULE_LICENSE("GPL and additional rights");
 
 void intel_fb_output_poll_changed(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index c5c0973af8a..95db2e98822 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -755,6 +755,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "hp st5747"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "MSI Wind Box DC500",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"),
+			DMI_MATCH(DMI_BOARD_NAME, "MS-7469"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index fc66af6a944..e25581a9f60 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -626,7 +626,7 @@ gen6_ring_get_seqno(struct intel_ring_buffer *ring)
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
 	 * ACTHD) before reading the status page. */
-	if (IS_GEN7(dev))
+	if (IS_GEN6(dev) || IS_GEN7(dev))
 		intel_ring_get_active_head(ring);
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 7aa0450399a..a464771a724 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -411,6 +411,9 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 
 	old_obj = intel_plane->obj;
 
+	src_w = src_w >> 16;
+	src_h = src_h >> 16;
+
 	/* Pipe must be running... */
 	if (!(I915_READ(PIPECONF(pipe)) & PIPECONF_ENABLE))
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ca1639918f5..97a81260485 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -13,6 +13,7 @@ config DRM_NOUVEAU
 	select ACPI_VIDEO if ACPI && X86 && BACKLIGHT_CLASS_DEVICE && VIDEO_OUTPUT_CONTROL && INPUT
 	select ACPI_WMI if ACPI
 	select MXM_WMI if ACPI
+	select POWER_SUPPLY
 	help
 	  Choose this option for open-source nVidia support.
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 637afe71de5..80963d05b54 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -177,14 +177,15 @@ bios_shadow_pci(struct nvbios *bios)
 
 	if (!pci_enable_rom(pdev)) {
 		void __iomem *rom = pci_map_rom(pdev, &length);
-		if (rom) {
+		if (rom && length) {
 			bios->data = kmalloc(length, GFP_KERNEL);
 			if (bios->data) {
 				memcpy_fromio(bios->data, rom, length);
 				bios->length = length;
 			}
-			pci_unmap_rom(pdev, rom);
 		}
+		if (rom)
+			pci_unmap_rom(pdev, rom);
 
 		pci_disable_rom(pdev);
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c
index 44e6416d4a3..846afb0bfef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_channel.c
+++ b/drivers/gpu/drm/nouveau/nouveau_channel.c
@@ -436,11 +436,11 @@ nouveau_ioctl_fifo_alloc(struct drm_device *dev, void *data,
 	}
 
 	if (dev_priv->card_type < NV_C0) {
-		init->subchan[0].handle = NvSw;
-		init->subchan[0].grclass = NV_SW;
-		init->nr_subchan = 1;
-	} else {
-		init->nr_subchan = 0;
+		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 */
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 8f510fd956b..fa860358add 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -654,10 +654,13 @@ nouveau_connector_detect_depth(struct drm_connector *connector)
 	if (nv_connector->edid && connector->display_info.bpc)
 		return;
 
-	/* if not, we're out of options unless we're LVDS, default to 6bpc */
-	connector->display_info.bpc = 6;
-	if (nv_encoder->dcb->type != OUTPUT_LVDS)
+	/* if not, we're out of options unless we're LVDS, default to 8bpc */
+	if (nv_encoder->dcb->type != OUTPUT_LVDS) {
+		connector->display_info.bpc = 8;
 		return;
+	}
+
+	connector->display_info.bpc = 6;
 
 	/* LVDS: panel straps */
 	if (bios->fp_no_ddc) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.h b/drivers/gpu/drm/nouveau/nouveau_dma.h
index bcf0fd9e313..23d4edf992b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dma.h
+++ b/drivers/gpu/drm/nouveau/nouveau_dma.h
@@ -48,8 +48,8 @@ void nv50_dma_push(struct nouveau_channel *, struct nouveau_bo *,
 
 /* Hardcoded object assignments to subchannels (subchannel id). */
 enum {
-	NvSubSw		= 0,
-	NvSubM2MF	= 1,
+	NvSubM2MF	= 0,
+	NvSubSw		= 1,
 	NvSub2D		= 2,
 	NvSubCtxSurf2D  = 2,
 	NvSubGdiRect    = 3,
diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
index 8f4f914d9ea..e2be95af2e5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
+++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
@@ -315,8 +315,8 @@ nouveau_i2c_init(struct drm_device *dev)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nvbios *bios = &dev_priv->vbios;
 	struct nouveau_i2c_chan *port;
+	u8 version = 0x00, entries, recordlen;
 	u8 *i2c, *entry, legacy[2][4] = {};
-	u8 version, entries, recordlen;
 	int ret, i;
 
 	INIT_LIST_HEAD(&dev_priv->i2c_ports);
@@ -346,12 +346,12 @@ nouveau_i2c_init(struct drm_device *dev)
 		if (i2c[7]) legacy[1][1] = i2c[7];
 	}
 
-	if (i2c && version >= 0x30) {
+	if (version >= 0x30) {
 		entry     = i2c[1] + i2c;
 		entries   = i2c[2];
 		recordlen = i2c[3];
 	} else
-	if (i2c) {
+	if (version) {
 		entry     = i2c;
 		entries   = 16;
 		recordlen = 4;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index a3ae91fa814..c2a8511e855 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -642,7 +642,7 @@ nouveau_card_channel_init(struct drm_device *dev)
 		OUT_RING  (chan, chan->vram_handle);
 		OUT_RING  (chan, chan->gart_handle);
 	} else
-	if (dev_priv->card_type <= NV_C0) {
+	if (dev_priv->card_type <= NV_D0) {
 		ret = nouveau_gpuobj_gr_new(chan, 0x9039, 0x9039);
 		if (ret)
 			goto error;
@@ -852,7 +852,7 @@ nouveau_card_init(struct drm_device *dev)
 	if (ret)
 		goto out_pm;
 
-	if (!dev_priv->noaccel) {
+	if (dev_priv->eng[NVOBJ_ENGINE_GR]) {
 		ret = nouveau_card_channel_init(dev);
 		if (ret)
 			goto out_fence;
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index d1bd239cd9e..5ce9bf51a8d 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -1306,8 +1306,11 @@ struct atom_context *atom_parse(struct card_info *card, void *bios)
 
 int atom_asic_init(struct atom_context *ctx)
 {
+	struct radeon_device *rdev = ctx->card->dev->dev_private;
 	int hwi = CU16(ctx->data_table + ATOM_DATA_FWI_PTR);
 	uint32_t ps[16];
+	int ret;
+
 	memset(ps, 0, 64);
 
 	ps[0] = cpu_to_le32(CU32(hwi + ATOM_FWI_DEFSCLK_PTR));
@@ -1317,7 +1320,17 @@ int atom_asic_init(struct atom_context *ctx)
 
 	if (!CU16(ctx->cmd_table + 4 + 2 * ATOM_CMD_INIT))
 		return 1;
-	return atom_execute_table(ctx, ATOM_CMD_INIT, ps);
+	ret = atom_execute_table(ctx, ATOM_CMD_INIT, ps);
+	if (ret)
+		return ret;
+
+	memset(ps, 0, 64);
+
+	if (rdev->family < CHIP_R600) {
+		if (CU16(ctx->cmd_table + 4 + 2 * ATOM_CMD_SPDFANCNTL))
+			atom_execute_table(ctx, ATOM_CMD_SPDFANCNTL, ps);
+	}
+	return ret;
 }
 
 void atom_destroy(struct atom_context *ctx)
diff --git a/drivers/gpu/drm/radeon/atom.h b/drivers/gpu/drm/radeon/atom.h
index 93cfe2086ba..25fea631dad 100644
--- a/drivers/gpu/drm/radeon/atom.h
+++ b/drivers/gpu/drm/radeon/atom.h
@@ -44,6 +44,7 @@
 #define ATOM_CMD_SETSCLK	0x0A
 #define ATOM_CMD_SETMCLK	0x0B
 #define ATOM_CMD_SETPCLK	0x0C
+#define ATOM_CMD_SPDFANCNTL	0x39
 
 #define ATOM_DATA_FWI_PTR	0xC
 #define ATOM_DATA_IIO_PTR	0x32
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 083b3eada00..b5ff1f7b6f7 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -588,8 +588,8 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 		if (encoder->crtc == crtc) {
 			radeon_encoder = to_radeon_encoder(encoder);
 			connector = radeon_get_connector_for_encoder(encoder);
-			if (connector && connector->display_info.bpc)
-				bpc = connector->display_info.bpc;
+			/* if (connector && connector->display_info.bpc)
+				bpc = connector->display_info.bpc; */
 			encoder_mode = atombios_get_encoder_mode(encoder);
 			is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
 			if ((radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT | ATOM_DEVICE_DFP_SUPPORT)) ||
@@ -965,7 +965,9 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 		struct radeon_connector_atom_dig *dig_connector =
 			radeon_connector->con_priv;
 		int dp_clock;
-		bpc = connector->display_info.bpc;
+
+		/* if (connector->display_info.bpc)
+			bpc = connector->display_info.bpc; */
 
 		switch (encoder_mode) {
 		case ATOM_ENCODER_MODE_DP_MST:
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 6c62be22680..c57d85664e7 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -405,10 +405,13 @@ static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE],
 /* get bpc from the EDID */
 static int convert_bpc_to_bpp(int bpc)
 {
+#if 0
 	if (bpc == 0)
 		return 24;
 	else
 		return bpc * 3;
+#endif
+	return 24;
 }
 
 /* get the max pix clock supported by the link rate and lane num */
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 468b874336f..e607c4d7dd9 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -541,7 +541,7 @@ atombios_dig_encoder_setup(struct drm_encoder *encoder, int action, int panel_mo
 		dp_clock = dig_connector->dp_clock;
 		dp_lane_count = dig_connector->dp_lane_count;
 		hpd_id = radeon_connector->hpd.hpd;
-		bpc = connector->display_info.bpc;
+		/* bpc = connector->display_info.bpc; */
 	}
 
 	/* no dig encoder assigned */
@@ -1159,7 +1159,7 @@ atombios_external_encoder_setup(struct drm_encoder *encoder,
 		dp_lane_count = dig_connector->dp_lane_count;
 		connector_object_id =
 			(radeon_connector->connector_object_id & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-		bpc = connector->display_info.bpc;
+		/* bpc = connector->display_info.bpc; */
 	}
 
 	memset(&args, 0, sizeof(args));
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index a58b37a2e65..70089d32b80 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -80,6 +80,9 @@ struct evergreen_cs_track {
 	bool			cb_dirty;
 	bool			db_dirty;
 	bool			streamout_dirty;
+	u32			htile_offset;
+	u32			htile_surface;
+	struct radeon_bo	*htile_bo;
 };
 
 static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
@@ -144,6 +147,9 @@ static void evergreen_cs_track_init(struct evergreen_cs_track *track)
 	track->db_s_read_bo = NULL;
 	track->db_s_write_bo = NULL;
 	track->db_dirty = true;
+	track->htile_bo = NULL;
+	track->htile_offset = 0xFFFFFFFF;
+	track->htile_surface = 0;
 
 	for (i = 0; i < 4; i++) {
 		track->vgt_strmout_size[i] = 0;
@@ -444,6 +450,62 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
 	return 0;
 }
 
+static int evergreen_cs_track_validate_htile(struct radeon_cs_parser *p,
+						unsigned nbx, unsigned nby)
+{
+	struct evergreen_cs_track *track = p->track;
+	unsigned long size;
+
+	if (track->htile_bo == NULL) {
+		dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
+				__func__, __LINE__, track->db_z_info);
+		return -EINVAL;
+	}
+
+	if (G_028ABC_LINEAR(track->htile_surface)) {
+		/* pitch must be 16 htiles aligned == 16 * 8 pixel aligned */
+		nbx = round_up(nbx, 16 * 8);
+		/* height is npipes htiles aligned == npipes * 8 pixel aligned */
+		nby = round_up(nby, track->npipes * 8);
+	} else {
+		switch (track->npipes) {
+		case 8:
+			nbx = round_up(nbx, 64 * 8);
+			nby = round_up(nby, 64 * 8);
+			break;
+		case 4:
+			nbx = round_up(nbx, 64 * 8);
+			nby = round_up(nby, 32 * 8);
+			break;
+		case 2:
+			nbx = round_up(nbx, 32 * 8);
+			nby = round_up(nby, 32 * 8);
+			break;
+		case 1:
+			nbx = round_up(nbx, 32 * 8);
+			nby = round_up(nby, 16 * 8);
+			break;
+		default:
+			dev_warn(p->dev, "%s:%d invalid num pipes %d\n",
+					__func__, __LINE__, track->npipes);
+			return -EINVAL;
+		}
+	}
+	/* compute number of htile */
+	nbx = nbx / 8;
+	nby = nby / 8;
+	size = nbx * nby * 4;
+	size += track->htile_offset;
+
+	if (size > radeon_bo_size(track->htile_bo)) {
+		dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
+				__func__, __LINE__, radeon_bo_size(track->htile_bo),
+				size, nbx, nby);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
 {
 	struct evergreen_cs_track *track = p->track;
@@ -530,6 +592,14 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
 		return -EINVAL;
 	}
 
+	/* hyperz */
+	if (G_028040_TILE_SURFACE_ENABLE(track->db_z_info)) {
+		r = evergreen_cs_track_validate_htile(p, surf.nbx, surf.nby);
+		if (r) {
+			return r;
+		}
+	}
+
 	return 0;
 }
 
@@ -617,6 +687,14 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p)
 		return -EINVAL;
 	}
 
+	/* hyperz */
+	if (G_028040_TILE_SURFACE_ENABLE(track->db_z_info)) {
+		r = evergreen_cs_track_validate_htile(p, surf.nbx, surf.nby);
+		if (r) {
+			return r;
+		}
+	}
+
 	return 0;
 }
 
@@ -850,7 +928,7 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 				return r;
 		}
 		/* Check depth buffer */
-		if (G_028800_Z_WRITE_ENABLE(track->db_depth_control)) {
+		if (G_028800_Z_ENABLE(track->db_depth_control)) {
 			r = evergreen_cs_track_validate_depth(p);
 			if (r)
 				return r;
@@ -1616,6 +1694,23 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->cb_color_bo[tmp] = reloc->robj;
 		track->cb_dirty = true;
 		break;
+	case DB_HTILE_DATA_BASE:
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		track->htile_offset = radeon_get_ib_value(p, idx);
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		track->htile_bo = reloc->robj;
+		track->db_dirty = true;
+		break;
+	case DB_HTILE_SURFACE:
+		/* 8x8 only */
+		track->htile_surface = radeon_get_ib_value(p, idx);
+		track->db_dirty = true;
+		break;
 	case CB_IMMED0_BASE:
 	case CB_IMMED1_BASE:
 	case CB_IMMED2_BASE:
@@ -1628,7 +1723,6 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_IMMED9_BASE:
 	case CB_IMMED10_BASE:
 	case CB_IMMED11_BASE:
-	case DB_HTILE_DATA_BASE:
 	case SQ_PGM_START_FS:
 	case SQ_PGM_START_ES:
 	case SQ_PGM_START_VS:
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index eb5708c7159..b4eefc355f1 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -991,6 +991,14 @@
 #define   G_028008_SLICE_MAX(x)                        (((x) >> 13) & 0x7FF)
 #define   C_028008_SLICE_MAX                           0xFF001FFF
 #define DB_HTILE_DATA_BASE				0x28014
+#define DB_HTILE_SURFACE				0x28abc
+#define   S_028ABC_HTILE_WIDTH(x)                      (((x) & 0x1) << 0)
+#define   G_028ABC_HTILE_WIDTH(x)                      (((x) >> 0) & 0x1)
+#define   C_028ABC_HTILE_WIDTH                         0xFFFFFFFE
+#define   S_028ABC_HTILE_HEIGHT(x)                      (((x) & 0x1) << 1)
+#define   G_028ABC_HTILE_HEIGHT(x)                      (((x) >> 1) & 0x1)
+#define   C_028ABC_HTILE_HEIGHT                         0xFFFFFFFD
+#define   G_028ABC_LINEAR(x)                           (((x) >> 2) & 0x1)
 #define DB_Z_INFO					0x28040
 #       define Z_ARRAY_MODE(x)                          ((x) << 4)
 #       define DB_TILE_SPLIT(x)                         (((x) & 0x7) << 8)
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 0ec3f205f9c..b8e12af304a 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -78,6 +78,9 @@ struct r600_cs_track {
 	bool			cb_dirty;
 	bool			db_dirty;
 	bool			streamout_dirty;
+	struct radeon_bo	*htile_bo;
+	u64			htile_offset;
+	u32			htile_surface;
 };
 
 #define FMT_8_BIT(fmt, vc)   [fmt] = { 1, 1, 1, vc, CHIP_R600 }
@@ -321,6 +324,9 @@ static void r600_cs_track_init(struct r600_cs_track *track)
 	track->db_depth_size_idx = 0;
 	track->db_depth_control = 0xFFFFFFFF;
 	track->db_dirty = true;
+	track->htile_bo = NULL;
+	track->htile_offset = 0xFFFFFFFF;
+	track->htile_surface = 0;
 
 	for (i = 0; i < 4; i++) {
 		track->vgt_strmout_size[i] = 0;
@@ -455,12 +461,256 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	return 0;
 }
 
+static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
+{
+	struct r600_cs_track *track = p->track;
+	u32 nviews, bpe, ntiles, size, slice_tile_max, tmp;
+	u32 height_align, pitch_align, depth_align;
+	u32 pitch = 8192;
+	u32 height = 8192;
+	u64 base_offset, base_align;
+	struct array_mode_checker array_check;
+	int array_mode;
+	volatile u32 *ib = p->ib->ptr;
+
+
+	if (track->db_bo == NULL) {
+		dev_warn(p->dev, "z/stencil with no depth buffer\n");
+		return -EINVAL;
+	}
+	switch (G_028010_FORMAT(track->db_depth_info)) {
+	case V_028010_DEPTH_16:
+		bpe = 2;
+		break;
+	case V_028010_DEPTH_X8_24:
+	case V_028010_DEPTH_8_24:
+	case V_028010_DEPTH_X8_24_FLOAT:
+	case V_028010_DEPTH_8_24_FLOAT:
+	case V_028010_DEPTH_32_FLOAT:
+		bpe = 4;
+		break;
+	case V_028010_DEPTH_X24_8_32_FLOAT:
+		bpe = 8;
+		break;
+	default:
+		dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
+		return -EINVAL;
+	}
+	if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
+		if (!track->db_depth_size_idx) {
+			dev_warn(p->dev, "z/stencil buffer size not set\n");
+			return -EINVAL;
+		}
+		tmp = radeon_bo_size(track->db_bo) - track->db_offset;
+		tmp = (tmp / bpe) >> 6;
+		if (!tmp) {
+			dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
+					track->db_depth_size, bpe, track->db_offset,
+					radeon_bo_size(track->db_bo));
+			return -EINVAL;
+		}
+		ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
+	} else {
+		size = radeon_bo_size(track->db_bo);
+		/* pitch in pixels */
+		pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
+		slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
+		slice_tile_max *= 64;
+		height = slice_tile_max / pitch;
+		if (height > 8192)
+			height = 8192;
+		base_offset = track->db_bo_mc + track->db_offset;
+		array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
+		array_check.array_mode = array_mode;
+		array_check.group_size = track->group_size;
+		array_check.nbanks = track->nbanks;
+		array_check.npipes = track->npipes;
+		array_check.nsamples = track->nsamples;
+		array_check.blocksize = bpe;
+		if (r600_get_array_mode_alignment(&array_check,
+					&pitch_align, &height_align, &depth_align, &base_align)) {
+			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+					G_028010_ARRAY_MODE(track->db_depth_info),
+					track->db_depth_info);
+			return -EINVAL;
+		}
+		switch (array_mode) {
+		case V_028010_ARRAY_1D_TILED_THIN1:
+			/* don't break userspace */
+			height &= ~0x7;
+			break;
+		case V_028010_ARRAY_2D_TILED_THIN1:
+			break;
+		default:
+			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+					G_028010_ARRAY_MODE(track->db_depth_info),
+					track->db_depth_info);
+			return -EINVAL;
+		}
+
+		if (!IS_ALIGNED(pitch, pitch_align)) {
+			dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
+					__func__, __LINE__, pitch, pitch_align, array_mode);
+			return -EINVAL;
+		}
+		if (!IS_ALIGNED(height, height_align)) {
+			dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
+					__func__, __LINE__, height, height_align, array_mode);
+			return -EINVAL;
+		}
+		if (!IS_ALIGNED(base_offset, base_align)) {
+			dev_warn(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__,
+					base_offset, base_align, array_mode);
+			return -EINVAL;
+		}
+
+		ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
+		nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
+		tmp = ntiles * bpe * 64 * nviews;
+		if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
+			dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
+					array_mode,
+					track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
+					radeon_bo_size(track->db_bo));
+			return -EINVAL;
+		}
+	}
+
+	/* hyperz */
+	if (G_028010_TILE_SURFACE_ENABLE(track->db_depth_info)) {
+		unsigned long size;
+		unsigned nbx, nby;
+
+		if (track->htile_bo == NULL) {
+			dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
+				 __func__, __LINE__, track->db_depth_info);
+			return -EINVAL;
+		}
+		if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
+			dev_warn(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n",
+				 __func__, __LINE__, track->db_depth_size);
+			return -EINVAL;
+		}
+
+		nbx = pitch;
+		nby = height;
+		if (G_028D24_LINEAR(track->htile_surface)) {
+			/* nbx must be 16 htiles aligned == 16 * 8 pixel aligned */
+			nbx = round_up(nbx, 16 * 8);
+			/* nby is npipes htiles aligned == npipes * 8 pixel aligned */
+			nby = round_up(nby, track->npipes * 8);
+		} else {
+			/* htile widht & nby (8 or 4) make 2 bits number */
+			tmp = track->htile_surface & 3;
+			/* align is htile align * 8, htile align vary according to
+			 * number of pipe and tile width and nby
+			 */
+			switch (track->npipes) {
+			case 8:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 64 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 4:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 64 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 2:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 32 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case 1:
+				switch (tmp) {
+				case 3:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 8*/
+					nbx = round_up(nbx, 32 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 2:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 8*/
+				case 1:	/* HTILE_WIDTH = 8 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 16 * 8);
+					break;
+				case 0:	/* HTILE_WIDTH = 4 & HTILE_HEIGHT = 4*/
+					nbx = round_up(nbx, 16 * 8);
+					nby = round_up(nby, 8 * 8);
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			default:
+				dev_warn(p->dev, "%s:%d invalid num pipes %d\n",
+					 __func__, __LINE__, track->npipes);
+				return -EINVAL;
+			}
+		}
+		/* compute number of htile */
+		nbx = G_028D24_HTILE_WIDTH(track->htile_surface) ? nbx / 8 : nbx / 4;
+		nby = G_028D24_HTILE_HEIGHT(track->htile_surface) ? nby / 8 : nby / 4;
+		size = nbx * nby * 4;
+		size += track->htile_offset;
+
+		if (size > radeon_bo_size(track->htile_bo)) {
+			dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
+				 __func__, __LINE__, radeon_bo_size(track->htile_bo),
+				 size, nbx, nby);
+			return -EINVAL;
+		}
+	}
+
+	track->db_dirty = false;
+	return 0;
+}
+
 static int r600_cs_track_check(struct radeon_cs_parser *p)
 {
 	struct r600_cs_track *track = p->track;
 	u32 tmp;
 	int r, i;
-	volatile u32 *ib = p->ib->ptr;
 
 	/* on legacy kernel we don't perform advanced check */
 	if (p->rdev == NULL)
@@ -513,124 +763,14 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 		track->cb_dirty = false;
 	}
 
-	if (track->db_dirty) {
-		/* Check depth buffer */
-		if (G_028800_STENCIL_ENABLE(track->db_depth_control) ||
-			G_028800_Z_ENABLE(track->db_depth_control)) {
-			u32 nviews, bpe, ntiles, size, slice_tile_max;
-			u32 height, height_align, pitch, pitch_align, depth_align;
-			u64 base_offset, base_align;
-			struct array_mode_checker array_check;
-			int array_mode;
-
-			if (track->db_bo == NULL) {
-				dev_warn(p->dev, "z/stencil with no depth buffer\n");
-				return -EINVAL;
-			}
-			if (G_028010_TILE_SURFACE_ENABLE(track->db_depth_info)) {
-				dev_warn(p->dev, "this kernel doesn't support z/stencil htile\n");
-				return -EINVAL;
-			}
-			switch (G_028010_FORMAT(track->db_depth_info)) {
-			case V_028010_DEPTH_16:
-				bpe = 2;
-				break;
-			case V_028010_DEPTH_X8_24:
-			case V_028010_DEPTH_8_24:
-			case V_028010_DEPTH_X8_24_FLOAT:
-			case V_028010_DEPTH_8_24_FLOAT:
-			case V_028010_DEPTH_32_FLOAT:
-				bpe = 4;
-				break;
-			case V_028010_DEPTH_X24_8_32_FLOAT:
-				bpe = 8;
-				break;
-			default:
-				dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
-				return -EINVAL;
-			}
-			if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
-				if (!track->db_depth_size_idx) {
-					dev_warn(p->dev, "z/stencil buffer size not set\n");
-					return -EINVAL;
-				}
-				tmp = radeon_bo_size(track->db_bo) - track->db_offset;
-				tmp = (tmp / bpe) >> 6;
-				if (!tmp) {
-					dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
-							track->db_depth_size, bpe, track->db_offset,
-							radeon_bo_size(track->db_bo));
-					return -EINVAL;
-				}
-				ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
-			} else {
-				size = radeon_bo_size(track->db_bo);
-				/* pitch in pixels */
-				pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
-				slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
-				slice_tile_max *= 64;
-				height = slice_tile_max / pitch;
-				if (height > 8192)
-					height = 8192;
-				base_offset = track->db_bo_mc + track->db_offset;
-				array_mode = G_028010_ARRAY_MODE(track->db_depth_info);
-				array_check.array_mode = array_mode;
-				array_check.group_size = track->group_size;
-				array_check.nbanks = track->nbanks;
-				array_check.npipes = track->npipes;
-				array_check.nsamples = track->nsamples;
-				array_check.blocksize = bpe;
-				if (r600_get_array_mode_alignment(&array_check,
-								  &pitch_align, &height_align, &depth_align, &base_align)) {
-					dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-						 G_028010_ARRAY_MODE(track->db_depth_info),
-						 track->db_depth_info);
-					return -EINVAL;
-				}
-				switch (array_mode) {
-				case V_028010_ARRAY_1D_TILED_THIN1:
-					/* don't break userspace */
-					height &= ~0x7;
-					break;
-				case V_028010_ARRAY_2D_TILED_THIN1:
-					break;
-				default:
-					dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-						 G_028010_ARRAY_MODE(track->db_depth_info),
-						 track->db_depth_info);
-					return -EINVAL;
-				}
-
-				if (!IS_ALIGNED(pitch, pitch_align)) {
-					dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
-						 __func__, __LINE__, pitch, pitch_align, array_mode);
-					return -EINVAL;
-				}
-				if (!IS_ALIGNED(height, height_align)) {
-					dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
-						 __func__, __LINE__, height, height_align, array_mode);
-					return -EINVAL;
-				}
-				if (!IS_ALIGNED(base_offset, base_align)) {
-					dev_warn(p->dev, "%s offset[%d] 0x%llx, 0x%llx, %d not aligned\n", __func__, i,
-						 base_offset, base_align, array_mode);
-					return -EINVAL;
-				}
-
-				ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
-				nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
-				tmp = ntiles * bpe * 64 * nviews;
-				if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
-					dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
-						 array_mode,
-						 track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
-						 radeon_bo_size(track->db_bo));
-					return -EINVAL;
-				}
-			}
-		}
-		track->db_dirty = false;
+	/* Check depth buffer */
+	if (track->db_dirty && (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;
 	}
+
 	return 0;
 }
 
@@ -1244,6 +1384,21 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_dirty = true;
 		break;
 	case DB_HTILE_DATA_BASE:
+		r = r600_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		track->htile_offset = radeon_get_ib_value(p, idx) << 8;
+		ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+		track->htile_bo = reloc->robj;
+		track->db_dirty = true;
+		break;
+	case DB_HTILE_SURFACE:
+		track->htile_surface = radeon_get_ib_value(p, idx);
+		track->db_dirty = true;
+		break;
 	case SQ_PGM_START_FS:
 	case SQ_PGM_START_ES:
 	case SQ_PGM_START_VS:
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 3568a2e345f..59f9c993cc3 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -195,6 +195,14 @@
 #define		PREZ_MUST_WAIT_FOR_POSTZ_DONE			(1 << 31)
 #define	DB_DEPTH_BASE					0x2800C
 #define	DB_HTILE_DATA_BASE				0x28014
+#define	DB_HTILE_SURFACE				0x28D24
+#define   S_028D24_HTILE_WIDTH(x)                      (((x) & 0x1) << 0)
+#define   G_028D24_HTILE_WIDTH(x)                      (((x) >> 0) & 0x1)
+#define   C_028D24_HTILE_WIDTH                         0xFFFFFFFE
+#define   S_028D24_HTILE_HEIGHT(x)                      (((x) & 0x1) << 1)
+#define   G_028D24_HTILE_HEIGHT(x)                      (((x) >> 1) & 0x1)
+#define   C_028D24_HTILE_HEIGHT                         0xFFFFFFFD
+#define   G_028D24_LINEAR(x)                           (((x) >> 2) & 0x1)
 #define	DB_WATERMARKS					0x9838
 #define		DEPTH_FREE(x)					((x) << 0)
 #define		DEPTH_FLUSH(x)					((x) << 5)
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 91541e63d58..df6a4dbd93f 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -233,7 +233,18 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 		bo->pin_count++;
 		if (gpu_addr)
 			*gpu_addr = radeon_bo_gpu_offset(bo);
-		WARN_ON_ONCE(max_offset != 0);
+
+		if (max_offset != 0) {
+			u64 domain_start;
+
+			if (domain == RADEON_GEM_DOMAIN_VRAM)
+				domain_start = bo->rdev->mc.vram_start;
+			else
+				domain_start = bo->rdev->mc.gtt_start;
+			WARN_ON_ONCE(max_offset <
+				     (radeon_bo_gpu_offset(bo) - domain_start));
+		}
+
 		return 0;
 	}
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index aea63c41585..0f656b111c1 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -509,7 +509,6 @@ cayman 0x9400
 0x00028AA8 IA_MULTI_VGT_PARAM
 0x00028AB4 VGT_REUSE_OFF
 0x00028AB8 VGT_VTX_CNT_EN
-0x00028ABC DB_HTILE_SURFACE
 0x00028AC0 DB_SRESULTS_COMPARE_STATE0
 0x00028AC4 DB_SRESULTS_COMPARE_STATE1
 0x00028AC8 DB_PRELOAD_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/evergreen b/drivers/gpu/drm/radeon/reg_srcs/evergreen
index 77c37202376..b912a37689b 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/evergreen
+++ b/drivers/gpu/drm/radeon/reg_srcs/evergreen
@@ -519,7 +519,6 @@ evergreen 0x9400
 0x00028AA4 VGT_INSTANCE_STEP_RATE_1
 0x00028AB4 VGT_REUSE_OFF
 0x00028AB8 VGT_VTX_CNT_EN
-0x00028ABC DB_HTILE_SURFACE
 0x00028AC0 DB_SRESULTS_COMPARE_STATE0
 0x00028AC4 DB_SRESULTS_COMPARE_STATE1
 0x00028AC8 DB_PRELOAD_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 626c24ea0b5..5e659b034d9 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -713,7 +713,6 @@ r600 0x9400
 0x0000A710 TD_VS_SAMPLER17_BORDER_RED
 0x00009508 TA_CNTL_AUX
 0x0002802C DB_DEPTH_CLEAR
-0x00028D24 DB_HTILE_SURFACE
 0x00028D34 DB_PREFETCH_LIMIT
 0x00028D30 DB_PRELOAD_CONTROL
 0x00028D0C DB_RENDER_CONTROL
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 5340c5f3987..53673907a6a 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -47,7 +47,7 @@ static struct vm_operations_struct udl_gem_vm_ops = {
 static const struct file_operations udl_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
-	.mmap = drm_gem_mmap,
+	.mmap = udl_drm_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 	.unlocked_ioctl	= drm_ioctl,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 1612954a5bc..96820d03a30 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -121,6 +121,7 @@ struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev,
 
 int udl_gem_vmap(struct udl_gem_object *obj);
 void udl_gem_vunmap(struct udl_gem_object *obj);
+int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
 int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 852642dc118..92f19ef329b 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -71,6 +71,20 @@ int udl_dumb_destroy(struct drm_file *file, struct drm_device *dev,
 	return drm_gem_handle_delete(file, handle);
 }
 
+int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	int ret;
+
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
+
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
+
+	return ret;
+}
+
 int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct udl_gem_object *obj = to_udl_bo(vma->vm_private_data);